From be68d63a139bd4a0eae44d06234eaff8c07d207c Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Wed, 12 Jun 2024 19:19:36 -0400 Subject: ring-buffer: Add ring_buffer_alloc_range() In preparation to allowing the trace ring buffer to be allocated in a range of memory that is persistent across reboots, add ring_buffer_alloc_range(). It takes a contiguous range of memory and will split it up evenly for the per CPU ring buffers. If there's not enough memory to handle all CPUs with the minimum size, it will fail to allocate the ring buffer. Link: https://lkml.kernel.org/r/20240612232025.363998725@goodmis.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Vincent Donnefort Cc: Joel Fernandes Cc: Daniel Bristot de Oliveira Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Vineeth Pillai Cc: Youssef Esmat Cc: Beau Belgrave Cc: Alexander Graf Cc: Baoquan He Cc: Borislav Petkov Cc: "Paul E. McKenney" Cc: David Howells Cc: Mike Rapoport Cc: Dave Hansen Cc: Tony Luck Cc: Guenter Roeck Cc: Ross Zwisler Cc: Kees Cook Signed-off-by: Steven Rostedt (Google) --- include/linux/ring_buffer.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 96d2140b471e..a50b0223b1d3 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -89,6 +89,11 @@ void ring_buffer_discard_commit(struct trace_buffer *buffer, struct trace_buffer * __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *key); +struct trace_buffer *__ring_buffer_alloc_range(unsigned long size, unsigned flags, + int order, unsigned long start, + unsigned long range_size, + struct lock_class_key *key); + /* * Because the ring buffer is generic, if other users of the ring buffer get * traced by ftrace, it can produce lockdep warnings. We need to keep each @@ -100,6 +105,18 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k __ring_buffer_alloc((size), (flags), &__key); \ }) +/* + * Because the ring buffer is generic, if other users of the ring buffer get + * traced by ftrace, it can produce lockdep warnings. We need to keep each + * ring buffer's lock class separate. + */ +#define ring_buffer_alloc_range(size, flags, order, start, range_size) \ +({ \ + static struct lock_class_key __key; \ + __ring_buffer_alloc_range((size), (flags), (order), (start), \ + (range_size), &__key); \ +}) + typedef bool (*ring_buffer_cond_fn)(void *data); int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full, ring_buffer_cond_fn cond, void *data); -- cgit v1.2.3 From 7a1d1e4b9639ff08b2f42605c2950ae1ba4a43bf Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Wed, 12 Jun 2024 19:19:44 -0400 Subject: tracing/ring-buffer: Add last_boot_info file to boot instance If an instance is mapped to memory on boot up, create a new file called "last_boot_info" that will hold information that can be used to properly parse the raw data in the ring buffer. It will export the delta of the addresses for text and data from what it was from the last boot. It does not expose actually addresses (unless you knew what the actual address was from the last boot). The output will look like: # cat last_boot_info text delta: -268435456 data delta: -268435456 The text and data are kept separate in case they are ever made different. Link: https://lkml.kernel.org/r/20240612232026.658680738@goodmis.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Vincent Donnefort Cc: Joel Fernandes Cc: Daniel Bristot de Oliveira Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Vineeth Pillai Cc: Youssef Esmat Cc: Beau Belgrave Cc: Alexander Graf Cc: Baoquan He Cc: Borislav Petkov Cc: "Paul E. McKenney" Cc: David Howells Cc: Mike Rapoport Cc: Dave Hansen Cc: Tony Luck Cc: Guenter Roeck Cc: Ross Zwisler Cc: Kees Cook Signed-off-by: Steven Rostedt (Google) --- include/linux/ring_buffer.h | 3 +++ kernel/trace/ring_buffer.c | 23 ++++++++++++++++++++++ kernel/trace/trace.c | 47 ++++++++++++++++++++++++++++++++++++++++++++- kernel/trace/trace.h | 2 ++ 4 files changed, 74 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index a50b0223b1d3..55de3798a9b9 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -94,6 +94,9 @@ struct trace_buffer *__ring_buffer_alloc_range(unsigned long size, unsigned flag unsigned long range_size, struct lock_class_key *key); +bool ring_buffer_last_boot_delta(struct trace_buffer *buffer, long *text, + long *data); + /* * Because the ring buffer is generic, if other users of the ring buffer get * traced by ftrace, it can produce lockdep warnings. We need to keep each diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 8c287430411d..f3d772461a60 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2396,6 +2396,29 @@ struct trace_buffer *__ring_buffer_alloc_range(unsigned long size, unsigned flag return alloc_buffer(size, flags, order, start, start + range_size, key); } +/** + * ring_buffer_last_boot_delta - return the delta offset from last boot + * @buffer: The buffer to return the delta from + * @text: Return text delta + * @data: Return data delta + * + * Returns: The true if the delta is non zero + */ +bool ring_buffer_last_boot_delta(struct trace_buffer *buffer, long *text, + long *data) +{ + if (!buffer) + return false; + + if (!buffer->last_text_delta) + return false; + + *text = buffer->last_text_delta; + *data = buffer->last_data_delta; + + return true; +} + /** * ring_buffer_free - free a ring buffer. * @buffer: the buffer to free. diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index dfde26aa3211..dc4eee33d920 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6041,6 +6041,18 @@ out: return ret; } +static void update_last_data(struct trace_array *tr) +{ + if (!tr->text_delta && !tr->data_delta) + return; + + /* Clear old data */ + tracing_reset_online_cpus(&tr->array_buffer); + + /* Using current data now */ + tr->text_delta = 0; + tr->data_delta = 0; +} /** * tracing_update_buffers - used by tracing facility to expand ring buffers @@ -6058,6 +6070,9 @@ int tracing_update_buffers(struct trace_array *tr) int ret = 0; mutex_lock(&trace_types_lock); + + update_last_data(tr); + if (!tr->ring_buffer_expanded) ret = __tracing_resize_ring_buffer(tr, trace_buf_size, RING_BUFFER_ALL_CPUS); @@ -6113,6 +6128,8 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) mutex_lock(&trace_types_lock); + update_last_data(tr); + if (!tr->ring_buffer_expanded) { ret = __tracing_resize_ring_buffer(tr, trace_buf_size, RING_BUFFER_ALL_CPUS); @@ -6860,6 +6877,21 @@ tracing_total_entries_read(struct file *filp, char __user *ubuf, return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } +static ssize_t +tracing_last_boot_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) +{ + struct trace_array *tr = filp->private_data; + struct seq_buf seq; + char buf[64]; + + seq_buf_init(&seq, buf, 64); + + seq_buf_printf(&seq, "text delta:\t%ld\n", tr->text_delta); + seq_buf_printf(&seq, "data delta:\t%ld\n", tr->data_delta); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, seq_buf_used(&seq)); +} + static int tracing_buffer_meta_open(struct inode *inode, struct file *filp) { struct trace_array *tr = inode->i_private; @@ -7499,6 +7531,13 @@ static const struct file_operations trace_time_stamp_mode_fops = { .release = tracing_single_release_tr, }; +static const struct file_operations last_boot_fops = { + .open = tracing_open_generic_tr, + .read = tracing_last_boot_read, + .llseek = generic_file_llseek, + .release = tracing_release_generic_tr, +}; + #ifdef CONFIG_TRACER_SNAPSHOT static const struct file_operations snapshot_fops = { .open = tracing_snapshot_open, @@ -9242,6 +9281,9 @@ allocate_trace_buffer(struct trace_array *tr, struct array_buffer *buf, int size buf->buffer = ring_buffer_alloc_range(size, rb_flags, 0, tr->range_addr_start, tr->range_addr_size); + + ring_buffer_last_boot_delta(buf->buffer, + &tr->text_delta, &tr->data_delta); /* * This is basically the same as a mapped buffer, * with the same restrictions. @@ -9751,7 +9793,10 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer) MEM_FAIL(1, "Could not allocate function filter files"); #ifdef CONFIG_TRACER_SNAPSHOT - if (!tr->range_addr_start) { + if (tr->range_addr_start) { + trace_create_file("last_boot_info", TRACE_MODE_READ, d_tracer, + tr, &last_boot_fops); + } else { trace_create_file("snapshot", TRACE_MODE_WRITE, d_tracer, tr, &snapshot_fops); } diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 3e56d3b22212..3dc5c8f14ce9 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -347,6 +347,8 @@ struct trace_array { unsigned int mapped; unsigned long range_addr_start; unsigned long range_addr_size; + long text_delta; + long data_delta; struct trace_pid_list __rcu *filtered_pids; struct trace_pid_list __rcu *filtered_no_pids; -- cgit v1.2.3 From 304b3f2bc07ba7c74a1ebc7917a8f0549e6b8d54 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 18 Jun 2024 10:09:16 -1000 Subject: sched: Allow sched_cgroup_fork() to fail and introduce sched_cancel_fork() A new BPF extensible sched_class will need more control over the forking process. It wants to be able to fail from sched_cgroup_fork() after the new task's sched_task_group is initialized so that the loaded BPF program can prepare the task with its cgroup association is established and reject fork if e.g. allocation fails. Allow sched_cgroup_fork() to fail by making it return int instead of void and adding sched_cancel_fork() to undo sched_fork() in the error path. sched_cgroup_fork() doesn't fail yet and this patch shouldn't cause any behavior changes. v2: Patch description updated to detail the expected use. Signed-off-by: Tejun Heo Reviewed-by: David Vernet Acked-by: Josh Don Acked-by: Hao Luo Acked-by: Barret Rhoden --- include/linux/sched/task.h | 3 ++- kernel/fork.c | 15 ++++++++++----- kernel/sched/core.c | 8 +++++++- 3 files changed, 19 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index d362aacf9f89..4df2f9055587 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -63,7 +63,8 @@ extern asmlinkage void schedule_tail(struct task_struct *prev); extern void init_idle(struct task_struct *idle, int cpu); extern int sched_fork(unsigned long clone_flags, struct task_struct *p); -extern void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs); +extern int sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs); +extern void sched_cancel_fork(struct task_struct *p); extern void sched_post_fork(struct task_struct *p); extern void sched_dead(struct task_struct *p); diff --git a/kernel/fork.c b/kernel/fork.c index 99076dbe27d8..e601fdf787c3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2363,7 +2363,7 @@ __latent_entropy struct task_struct *copy_process( retval = perf_event_init_task(p, clone_flags); if (retval) - goto bad_fork_cleanup_policy; + goto bad_fork_sched_cancel_fork; retval = audit_alloc(p); if (retval) goto bad_fork_cleanup_perf; @@ -2496,7 +2496,9 @@ __latent_entropy struct task_struct *copy_process( * cgroup specific, it unconditionally needs to place the task on a * runqueue. */ - sched_cgroup_fork(p, args); + retval = sched_cgroup_fork(p, args); + if (retval) + goto bad_fork_cancel_cgroup; /* * From this point on we must avoid any synchronous user-space @@ -2542,13 +2544,13 @@ __latent_entropy struct task_struct *copy_process( /* Don't start children in a dying pid namespace */ if (unlikely(!(ns_of_pid(pid)->pid_allocated & PIDNS_ADDING))) { retval = -ENOMEM; - goto bad_fork_cancel_cgroup; + goto bad_fork_core_free; } /* Let kill terminate clone/fork in the middle */ if (fatal_signal_pending(current)) { retval = -EINTR; - goto bad_fork_cancel_cgroup; + goto bad_fork_core_free; } /* No more failure paths after this point. */ @@ -2622,10 +2624,11 @@ __latent_entropy struct task_struct *copy_process( return p; -bad_fork_cancel_cgroup: +bad_fork_core_free: sched_core_free(p); spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); +bad_fork_cancel_cgroup: cgroup_cancel_fork(p, args); bad_fork_put_pidfd: if (clone_flags & CLONE_PIDFD) { @@ -2664,6 +2667,8 @@ bad_fork_cleanup_audit: audit_free(p); bad_fork_cleanup_perf: perf_event_free_task(p); +bad_fork_sched_cancel_fork: + sched_cancel_fork(p); bad_fork_cleanup_policy: lockdep_free_task(p); #ifdef CONFIG_NUMA diff --git a/kernel/sched/core.c b/kernel/sched/core.c index b4d4551bc7f2..095604490c26 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4609,7 +4609,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) return 0; } -void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs) +int sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs) { unsigned long flags; @@ -4636,6 +4636,12 @@ void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs) if (p->sched_class->task_fork) p->sched_class->task_fork(p); raw_spin_unlock_irqrestore(&p->pi_lock, flags); + + return 0; +} + +void sched_cancel_fork(struct task_struct *p) +{ } void sched_post_fork(struct task_struct *p) -- cgit v1.2.3 From 4f9c7ca851044273df5d67e00ca0b4d0476a48f6 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 18 Jun 2024 10:09:16 -1000 Subject: sched: Factor out cgroup weight conversion functions Factor out sched_weight_from/to_cgroup() which convert between scheduler shares and cgroup weight. No functional change. The factored out functions will be used by a new BPF extensible sched_class so that the weights can be exposed to the BPF programs in a way which is consistent cgroup weights and easier to interpret. The weight conversions will be used regardless of cgroup usage. It's just borrowing the cgroup weight range as it's more intuitive. CGROUP_WEIGHT_MIN/DFL/MAX constants are moved outside CONFIG_CGROUPS so that the conversion helpers can always be defined. v2: The helpers are now defined regardless of COFNIG_CGROUPS. Signed-off-by: Tejun Heo Reviewed-by: David Vernet Acked-by: Josh Don Acked-by: Hao Luo Acked-by: Barret Rhoden --- include/linux/cgroup.h | 4 ++-- kernel/sched/core.c | 28 +++++++++++++--------------- kernel/sched/sched.h | 18 ++++++++++++++++++ 3 files changed, 33 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 2150ca60394b..3cdaec701600 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -29,8 +29,6 @@ struct kernel_clone_args; -#ifdef CONFIG_CGROUPS - /* * All weight knobs on the default hierarchy should use the following min, * default and max values. The default value is the logarithmic center of @@ -40,6 +38,8 @@ struct kernel_clone_args; #define CGROUP_WEIGHT_DFL 100 #define CGROUP_WEIGHT_MAX 10000 +#ifdef CONFIG_CGROUPS + enum { CSS_TASK_ITER_PROCS = (1U << 0), /* walk only threadgroup leaders */ CSS_TASK_ITER_THREADED = (1U << 1), /* walk all threaded css_sets in the domain */ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index b088fbeaf26d..0bfbceebc4e9 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -9552,29 +9552,27 @@ static int cpu_local_stat_show(struct seq_file *sf, } #ifdef CONFIG_FAIR_GROUP_SCHED + +static unsigned long tg_weight(struct task_group *tg) +{ + return scale_load_down(tg->shares); +} + static u64 cpu_weight_read_u64(struct cgroup_subsys_state *css, struct cftype *cft) { - struct task_group *tg = css_tg(css); - u64 weight = scale_load_down(tg->shares); - - return DIV_ROUND_CLOSEST_ULL(weight * CGROUP_WEIGHT_DFL, 1024); + return sched_weight_to_cgroup(tg_weight(css_tg(css))); } static int cpu_weight_write_u64(struct cgroup_subsys_state *css, - struct cftype *cft, u64 weight) + struct cftype *cft, u64 cgrp_weight) { - /* - * cgroup weight knobs should use the common MIN, DFL and MAX - * values which are 1, 100 and 10000 respectively. While it loses - * a bit of range on both ends, it maps pretty well onto the shares - * value used by scheduler and the round-trip conversions preserve - * the original value over the entire range. - */ - if (weight < CGROUP_WEIGHT_MIN || weight > CGROUP_WEIGHT_MAX) + unsigned long weight; + + if (cgrp_weight < CGROUP_WEIGHT_MIN || cgrp_weight > CGROUP_WEIGHT_MAX) return -ERANGE; - weight = DIV_ROUND_CLOSEST_ULL(weight * 1024, CGROUP_WEIGHT_DFL); + weight = sched_weight_from_cgroup(cgrp_weight); return sched_group_set_shares(css_tg(css), scale_load(weight)); } @@ -9582,7 +9580,7 @@ static int cpu_weight_write_u64(struct cgroup_subsys_state *css, static s64 cpu_weight_nice_read_s64(struct cgroup_subsys_state *css, struct cftype *cft) { - unsigned long weight = scale_load_down(css_tg(css)->shares); + unsigned long weight = tg_weight(css_tg(css)); int last_delta = INT_MAX; int prio, delta; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 0ed4271cedf5..656a63c0d393 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -244,6 +244,24 @@ static inline void update_avg(u64 *avg, u64 sample) #define shr_bound(val, shift) \ (val >> min_t(typeof(shift), shift, BITS_PER_TYPE(typeof(val)) - 1)) +/* + * cgroup weight knobs should use the common MIN, DFL and MAX values which are + * 1, 100 and 10000 respectively. While it loses a bit of range on both ends, it + * maps pretty well onto the shares value used by scheduler and the round-trip + * conversions preserve the original value over the entire range. + */ +static inline unsigned long sched_weight_from_cgroup(unsigned long cgrp_weight) +{ + return DIV_ROUND_CLOSEST_ULL(cgrp_weight * 1024, CGROUP_WEIGHT_DFL); +} + +static inline unsigned long sched_weight_to_cgroup(unsigned long weight) +{ + return clamp_t(unsigned long, + DIV_ROUND_CLOSEST_ULL(weight * CGROUP_WEIGHT_DFL, 1024), + CGROUP_WEIGHT_MIN, CGROUP_WEIGHT_MAX); +} + /* * !! For sched_setattr_nocheck() (kernel) only !! * -- cgit v1.2.3 From a7a9fc549293168c1edbc8433d5d4fbbe1171630 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 18 Jun 2024 10:09:17 -1000 Subject: sched_ext: Add boilerplate for extensible scheduler class This adds dummy implementations of sched_ext interfaces which interact with the scheduler core and hook them in the correct places. As they're all dummies, this doesn't cause any behavior changes. This is split out to help reviewing. v2: balance_scx_on_up() dropped. This will be handled in sched_ext proper. Signed-off-by: Tejun Heo Reviewed-by: David Vernet Acked-by: Josh Don Acked-by: Hao Luo Acked-by: Barret Rhoden --- include/linux/sched/ext.h | 12 ++++++++++++ kernel/fork.c | 2 ++ kernel/sched/core.c | 32 ++++++++++++++++++++++++-------- kernel/sched/ext.h | 24 ++++++++++++++++++++++++ kernel/sched/idle.c | 2 ++ kernel/sched/sched.h | 2 ++ 6 files changed, 66 insertions(+), 8 deletions(-) create mode 100644 include/linux/sched/ext.h create mode 100644 kernel/sched/ext.h (limited to 'include/linux') diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h new file mode 100644 index 000000000000..a05dfcf533b0 --- /dev/null +++ b/include/linux/sched/ext.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_SCHED_EXT_H +#define _LINUX_SCHED_EXT_H + +#ifdef CONFIG_SCHED_CLASS_EXT +#error "NOT IMPLEMENTED YET" +#else /* !CONFIG_SCHED_CLASS_EXT */ + +static inline void sched_ext_free(struct task_struct *p) {} + +#endif /* CONFIG_SCHED_CLASS_EXT */ +#endif /* _LINUX_SCHED_EXT_H */ diff --git a/kernel/fork.c b/kernel/fork.c index e601fdf787c3..741d962db0d9 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include #include @@ -971,6 +972,7 @@ void __put_task_struct(struct task_struct *tsk) WARN_ON(refcount_read(&tsk->usage)); WARN_ON(tsk == current); + sched_ext_free(tsk); io_uring_free(tsk); cgroup_free(tsk); task_numa_free(tsk, true); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 0bfbceebc4e9..d8c963fea9eb 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4559,6 +4559,8 @@ late_initcall(sched_core_sysctl_init); */ int sched_fork(unsigned long clone_flags, struct task_struct *p) { + int ret; + __sched_fork(clone_flags, p); /* * We mark the process as NEW here. This guarantees that @@ -4595,12 +4597,16 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) p->sched_reset_on_fork = 0; } - if (dl_prio(p->prio)) - return -EAGAIN; - else if (rt_prio(p->prio)) + scx_pre_fork(p); + + if (dl_prio(p->prio)) { + ret = -EAGAIN; + goto out_cancel; + } else if (rt_prio(p->prio)) { p->sched_class = &rt_sched_class; - else + } else { p->sched_class = &fair_sched_class; + } init_entity_runnable_average(&p->se); @@ -4618,6 +4624,10 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) RB_CLEAR_NODE(&p->pushable_dl_tasks); #endif return 0; + +out_cancel: + scx_cancel_fork(p); + return ret; } int sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs) @@ -4648,16 +4658,18 @@ int sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs) p->sched_class->task_fork(p); raw_spin_unlock_irqrestore(&p->pi_lock, flags); - return 0; + return scx_fork(p); } void sched_cancel_fork(struct task_struct *p) { + scx_cancel_fork(p); } void sched_post_fork(struct task_struct *p) { uclamp_post_fork(p); + scx_post_fork(p); } unsigned long to_ratio(u64 period, u64 runtime) @@ -5800,7 +5812,7 @@ static void put_prev_task_balance(struct rq *rq, struct task_struct *prev, * We can terminate the balance pass as soon as we know there is * a runnable task of @class priority or higher. */ - for_class_range(class, prev->sched_class, &idle_sched_class) { + for_balance_class_range(class, prev->sched_class, &idle_sched_class) { if (class->balance(rq, prev, rf)) break; } @@ -5818,6 +5830,9 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) const struct sched_class *class; struct task_struct *p; + if (scx_enabled()) + goto restart; + /* * Optimization: we know that if all tasks are in the fair class we can * call that function directly, but only if the @prev task wasn't of a @@ -5858,7 +5873,7 @@ restart: if (prev->dl_server) prev->dl_server = NULL; - for_each_class(class) { + for_each_active_class(class) { p = class->pick_next_task(rq); if (p) return p; @@ -5891,7 +5906,7 @@ static inline struct task_struct *pick_task(struct rq *rq) const struct sched_class *class; struct task_struct *p; - for_each_class(class) { + for_each_active_class(class) { p = class->pick_task(rq); if (p) return p; @@ -8355,6 +8370,7 @@ void __init sched_init(void) balance_push_set(smp_processor_id(), false); #endif init_sched_fair_class(); + init_sched_ext_class(); psi_init(); diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h new file mode 100644 index 000000000000..6a93c4825339 --- /dev/null +++ b/kernel/sched/ext.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifdef CONFIG_SCHED_CLASS_EXT +#error "NOT IMPLEMENTED YET" +#else /* CONFIG_SCHED_CLASS_EXT */ + +#define scx_enabled() false + +static inline void scx_pre_fork(struct task_struct *p) {} +static inline int scx_fork(struct task_struct *p) { return 0; } +static inline void scx_post_fork(struct task_struct *p) {} +static inline void scx_cancel_fork(struct task_struct *p) {} +static inline void init_sched_ext_class(void) {} + +#define for_each_active_class for_each_class +#define for_balance_class_range for_class_range + +#endif /* CONFIG_SCHED_CLASS_EXT */ + +#if defined(CONFIG_SCHED_CLASS_EXT) && defined(CONFIG_SMP) +#error "NOT IMPLEMENTED YET" +#else +static inline void scx_update_idle(struct rq *rq, bool idle) {} +#endif diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 6e78d071beb5..c7a218123b7a 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -452,11 +452,13 @@ static void wakeup_preempt_idle(struct rq *rq, struct task_struct *p, int flags) static void put_prev_task_idle(struct rq *rq, struct task_struct *prev) { + scx_update_idle(rq, false); } static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first) { update_idle_core(rq); + scx_update_idle(rq, true); schedstat_inc(rq->sched_goidle); } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 25660dc9f639..c52ad5fdd096 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -3658,4 +3658,6 @@ static inline void balance_callbacks(struct rq *rq, struct balance_callback *hea #endif +#include "ext.h" + #endif /* _KERNEL_SCHED_SCHED_H */ -- cgit v1.2.3 From f0e1a0643a59bf1f922fa209cec86a170b784f3f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 18 Jun 2024 10:09:17 -1000 Subject: sched_ext: Implement BPF extensible scheduler class MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Implement a new scheduler class sched_ext (SCX), which allows scheduling policies to be implemented as BPF programs to achieve the following: 1. Ease of experimentation and exploration: Enabling rapid iteration of new scheduling policies. 2. Customization: Building application-specific schedulers which implement policies that are not applicable to general-purpose schedulers. 3. Rapid scheduler deployments: Non-disruptive swap outs of scheduling policies in production environments. sched_ext leverages BPF’s struct_ops feature to define a structure which exports function callbacks and flags to BPF programs that wish to implement scheduling policies. The struct_ops structure exported by sched_ext is struct sched_ext_ops, and is conceptually similar to struct sched_class. The role of sched_ext is to map the complex sched_class callbacks to the more simple and ergonomic struct sched_ext_ops callbacks. For more detailed discussion on the motivations and overview, please refer to the cover letter. Later patches will also add several example schedulers and documentation. This patch implements the minimum core framework to enable implementation of BPF schedulers. Subsequent patches will gradually add functionalities including safety guarantee mechanisms, nohz and cgroup support. include/linux/sched/ext.h defines struct sched_ext_ops. With the comment on top, each operation should be self-explanatory. The followings are worth noting: - Both "sched_ext" and its shorthand "scx" are used. If the identifier already has "sched" in it, "ext" is used; otherwise, "scx". - In sched_ext_ops, only .name is mandatory. Every operation is optional and if omitted a simple but functional default behavior is provided. - A new policy constant SCHED_EXT is added and a task can select sched_ext by invoking sched_setscheduler(2) with the new policy constant. However, if the BPF scheduler is not loaded, SCHED_EXT is the same as SCHED_NORMAL and the task is scheduled by CFS. When the BPF scheduler is loaded, all tasks which have the SCHED_EXT policy are switched to sched_ext. - To bridge the workflow imbalance between the scheduler core and sched_ext_ops callbacks, sched_ext uses simple FIFOs called dispatch queues (dsq's). By default, there is one global dsq (SCX_DSQ_GLOBAL), and one local per-CPU dsq (SCX_DSQ_LOCAL). SCX_DSQ_GLOBAL is provided for convenience and need not be used by a scheduler that doesn't require it. SCX_DSQ_LOCAL is the per-CPU FIFO that sched_ext pulls from when putting the next task on the CPU. The BPF scheduler can manage an arbitrary number of dsq's using scx_bpf_create_dsq() and scx_bpf_destroy_dsq(). - sched_ext guarantees system integrity no matter what the BPF scheduler does. To enable this, each task's ownership is tracked through p->scx.ops_state and all tasks are put on scx_tasks list. The disable path can always recover and revert all tasks back to CFS. See p->scx.ops_state and scx_tasks. - A task is not tied to its rq while enqueued. This decouples CPU selection from queueing and allows sharing a scheduling queue across an arbitrary subset of CPUs. This adds some complexities as a task may need to be bounced between rq's right before it starts executing. See dispatch_to_local_dsq() and move_task_to_local_dsq(). - One complication that arises from the above weak association between task and rq is that synchronizing with dequeue() gets complicated as dequeue() may happen anytime while the task is enqueued and the dispatch path might need to release the rq lock to transfer the task. Solving this requires a bit of complexity. See the logic around p->scx.sticky_cpu and p->scx.ops_qseq. - Both enable and disable paths are a bit complicated. The enable path switches all tasks without blocking to avoid issues which can arise from partially switched states (e.g. the switching task itself being starved). The disable path can't trust the BPF scheduler at all, so it also has to guarantee forward progress without blocking. See scx_ops_enable() and scx_ops_disable_workfn(). - When sched_ext is disabled, static_branches are used to shut down the entry points from hot paths. v7: - scx_ops_bypass() was incorrectly and unnecessarily trying to grab scx_ops_enable_mutex which can lead to deadlocks in the disable path. Fixed. - Fixed TASK_DEAD handling bug in scx_ops_enable() path which could lead to use-after-free. - Consolidated per-cpu variable usages and other cleanups. v6: - SCX_NR_ONLINE_OPS replaced with SCX_OPI_*_BEGIN/END so that multiple groups can be expressed. Later CPU hotplug operations are put into their own group. - SCX_OPS_DISABLING state is replaced with the new bypass mechanism which allows temporarily putting the system into simple FIFO scheduling mode bypassing the BPF scheduler. In addition to the shut down path, this will also be used to isolate the BPF scheduler across PM events. Enabling and disabling the bypass mode requires iterating all runnable tasks. rq->scx.runnable_list addition is moved from the later watchdog patch. - ops.prep_enable() is replaced with ops.init_task() and ops.enable/disable() are now called whenever the task enters and leaves sched_ext instead of when the task becomes schedulable on sched_ext and stops being so. A new operation - ops.exit_task() - is called when the task stops being schedulable on sched_ext. - scx_bpf_dispatch() can now be called from ops.select_cpu() too. This removes the need for communicating local dispatch decision made by ops.select_cpu() to ops.enqueue() via per-task storage. SCX_KF_SELECT_CPU is added to support the change. - SCX_TASK_ENQ_LOCAL which told the BPF scheudler that scx_select_cpu_dfl() wants the task to be dispatched to the local DSQ was removed. Instead, scx_bpf_select_cpu_dfl() now dispatches directly if it finds a suitable idle CPU. If such behavior is not desired, users can use scx_bpf_select_cpu_dfl() which returns the verdict in a bool out param. - scx_select_cpu_dfl() was mishandling WAKE_SYNC and could end up queueing many tasks on a local DSQ which makes tasks to execute in order while other CPUs stay idle which made some hackbench numbers really bad. Fixed. - The current state of sched_ext can now be monitored through files under /sys/sched_ext instead of /sys/kernel/debug/sched/ext. This is to enable monitoring on kernels which don't enable debugfs. - sched_ext wasn't telling BPF that ops.dispatch()'s @prev argument may be NULL and a BPF scheduler which derefs the pointer without checking could crash the kernel. Tell BPF. This is currently a bit ugly. A better way to annotate this is expected in the future. - scx_exit_info updated to carry pointers to message buffers instead of embedding them directly. This decouples buffer sizes from API so that they can be changed without breaking compatibility. - exit_code added to scx_exit_info. This is used to indicate different exit conditions on non-error exits and will be used to handle e.g. CPU hotplugs. - The patch "sched_ext: Allow BPF schedulers to switch all eligible tasks into sched_ext" is folded in and the interface is changed so that partial switching is indicated with a new ops flag %SCX_OPS_SWITCH_PARTIAL. This makes scx_bpf_switch_all() unnecessasry and in turn SCX_KF_INIT. ops.init() is now called with SCX_KF_SLEEPABLE. - Code reorganized so that only the parts necessary to integrate with the rest of the kernel are in the header files. - Changes to reflect the BPF and other kernel changes including the addition of bpf_sched_ext_ops.cfi_stubs. v5: - To accommodate 32bit configs, p->scx.ops_state is now atomic_long_t instead of atomic64_t and scx_dsp_buf_ent.qseq which uses load_acquire/store_release is now unsigned long instead of u64. - Fix the bug where bpf_scx_btf_struct_access() was allowing write access to arbitrary fields. - Distinguish kfuncs which can be called from any sched_ext ops and from anywhere. e.g. scx_bpf_pick_idle_cpu() can now be called only from sched_ext ops. - Rename "type" to "kind" in scx_exit_info to make it easier to use on languages in which "type" is a reserved keyword. - Since cff9b2332ab7 ("kernel/sched: Modify initial boot task idle setup"), PF_IDLE is not set on idle tasks which haven't been online yet which made scx_task_iter_next_filtered() include those idle tasks in iterations leading to oopses. Update scx_task_iter_next_filtered() to directly test p->sched_class against idle_sched_class instead of using is_idle_task() which tests PF_IDLE. - Other updates to match upstream changes such as adding const to set_cpumask() param and renaming check_preempt_curr() to wakeup_preempt(). v4: - SCHED_CHANGE_BLOCK replaced with the previous sched_deq_and_put_task()/sched_enq_and_set_tsak() pair. This is because upstream is adaopting a different generic cleanup mechanism. Once that lands, the code will be adapted accordingly. - task_on_scx() used to test whether a task should be switched into SCX, which is confusing. Renamed to task_should_scx(). task_on_scx() now tests whether a task is currently on SCX. - scx_has_idle_cpus is barely used anymore and replaced with direct check on the idle cpumask. - SCX_PICK_IDLE_CORE added and scx_pick_idle_cpu() improved to prefer fully idle cores. - ops.enable() now sees up-to-date p->scx.weight value. - ttwu_queue path is disabled for tasks on SCX to avoid confusing BPF schedulers expecting ->select_cpu() call. - Use cpu_smt_mask() instead of topology_sibling_cpumask() like the rest of the scheduler. v3: - ops.set_weight() added to allow BPF schedulers to track weight changes without polling p->scx.weight. - move_task_to_local_dsq() was losing SCX-specific enq_flags when enqueueing the task on the target dsq because it goes through activate_task() which loses the upper 32bit of the flags. Carry the flags through rq->scx.extra_enq_flags. - scx_bpf_dispatch(), scx_bpf_pick_idle_cpu(), scx_bpf_task_running() and scx_bpf_task_cpu() now use the new KF_RCU instead of KF_TRUSTED_ARGS to make it easier for BPF schedulers to call them. - The kfunc helper access control mechanism implemented through sched_ext_entity.kf_mask is improved. Now SCX_CALL_OP*() is always used when invoking scx_ops operations. v2: - balance_scx_on_up() is dropped. Instead, on UP, balance_scx() is called from put_prev_taks_scx() and pick_next_task_scx() as necessary. To determine whether balance_scx() should be called from put_prev_task_scx(), SCX_TASK_DEQD_FOR_SLEEP flag is added. See the comment in put_prev_task_scx() for details. - sched_deq_and_put_task() / sched_enq_and_set_task() sequences replaced with SCHED_CHANGE_BLOCK(). - Unused all_dsqs list removed. This was a left-over from previous iterations. - p->scx.kf_mask is added to track and enforce which kfunc helpers are allowed. Also, init/exit sequences are updated to make some kfuncs always safe to call regardless of the current BPF scheduler state. Combined, this should make all the kfuncs safe. - BPF now supports sleepable struct_ops operations. Hacky workaround removed and operations and kfunc helpers are tagged appropriately. - BPF now supports bitmask / cpumask helpers. scx_bpf_get_idle_cpumask() and friends are added so that BPF schedulers can use the idle masks with the generic helpers. This replaces the hacky kfunc helpers added by a separate patch in V1. - CONFIG_SCHED_CLASS_EXT can no longer be enabled if SCHED_CORE is enabled. This restriction will be removed by a later patch which adds core-sched support. - Add MAINTAINERS entries and other misc changes. Signed-off-by: Tejun Heo Co-authored-by: David Vernet Acked-by: Josh Don Acked-by: Hao Luo Acked-by: Barret Rhoden Cc: Andrea Righi --- MAINTAINERS | 13 + include/asm-generic/vmlinux.lds.h | 1 + include/linux/sched.h | 5 + include/linux/sched/ext.h | 141 +- include/uapi/linux/sched.h | 1 + init/init_task.c | 11 + kernel/Kconfig.preempt | 25 +- kernel/sched/build_policy.c | 9 + kernel/sched/core.c | 66 +- kernel/sched/debug.c | 3 + kernel/sched/ext.c | 4256 +++++++++++++++++++++++++++++++++++++ kernel/sched/ext.h | 73 +- kernel/sched/sched.h | 17 + kernel/sched/syscalls.c | 2 + 14 files changed, 4616 insertions(+), 7 deletions(-) create mode 100644 kernel/sched/ext.c (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index cd3277a98cfe..9e3ee22f015e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -19936,6 +19936,19 @@ F: include/linux/wait.h F: include/uapi/linux/sched.h F: kernel/sched/ +SCHEDULER - SCHED_EXT +R: Tejun Heo +R: David Vernet +L: linux-kernel@vger.kernel.org +S: Maintained +W: https://github.com/sched-ext/scx +T: git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext.git +F: include/linux/sched/ext.h +F: kernel/sched/ext.h +F: kernel/sched/ext.c +F: tools/sched_ext/ +F: tools/testing/selftests/sched_ext + SCSI LIBSAS SUBSYSTEM R: John Garry R: Jason Yan diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 5703526d6ebf..2e712183ba09 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -133,6 +133,7 @@ *(__dl_sched_class) \ *(__rt_sched_class) \ *(__fair_sched_class) \ + *(__ext_sched_class) \ *(__idle_sched_class) \ __sched_class_lowest = .; diff --git a/include/linux/sched.h b/include/linux/sched.h index 90691d99027e..06beb8a6e0ca 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -80,6 +80,8 @@ struct task_group; struct task_struct; struct user_event_mm; +#include + /* * Task state bitmask. NOTE! These bits are also * encoded in fs/proc/array.c: get_task_state(). @@ -802,6 +804,9 @@ struct task_struct { struct sched_rt_entity rt; struct sched_dl_entity dl; struct sched_dl_entity *dl_server; +#ifdef CONFIG_SCHED_CLASS_EXT + struct sched_ext_entity scx; +#endif const struct sched_class *sched_class; #ifdef CONFIG_SCHED_CORE diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index a05dfcf533b0..c1530a7992cc 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -1,9 +1,148 @@ /* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2022 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2022 Tejun Heo + * Copyright (c) 2022 David Vernet + */ #ifndef _LINUX_SCHED_EXT_H #define _LINUX_SCHED_EXT_H #ifdef CONFIG_SCHED_CLASS_EXT -#error "NOT IMPLEMENTED YET" + +#include +#include + +enum scx_public_consts { + SCX_OPS_NAME_LEN = 128, + + SCX_SLICE_DFL = 20 * 1000000, /* 20ms */ +}; + +/* + * DSQ (dispatch queue) IDs are 64bit of the format: + * + * Bits: [63] [62 .. 0] + * [ B] [ ID ] + * + * B: 1 for IDs for built-in DSQs, 0 for ops-created user DSQs + * ID: 63 bit ID + * + * Built-in IDs: + * + * Bits: [63] [62] [61..32] [31 .. 0] + * [ 1] [ L] [ R ] [ V ] + * + * 1: 1 for built-in DSQs. + * L: 1 for LOCAL_ON DSQ IDs, 0 for others + * V: For LOCAL_ON DSQ IDs, a CPU number. For others, a pre-defined value. + */ +enum scx_dsq_id_flags { + SCX_DSQ_FLAG_BUILTIN = 1LLU << 63, + SCX_DSQ_FLAG_LOCAL_ON = 1LLU << 62, + + SCX_DSQ_INVALID = SCX_DSQ_FLAG_BUILTIN | 0, + SCX_DSQ_GLOBAL = SCX_DSQ_FLAG_BUILTIN | 1, + SCX_DSQ_LOCAL = SCX_DSQ_FLAG_BUILTIN | 2, + SCX_DSQ_LOCAL_ON = SCX_DSQ_FLAG_BUILTIN | SCX_DSQ_FLAG_LOCAL_ON, + SCX_DSQ_LOCAL_CPU_MASK = 0xffffffffLLU, +}; + +/* + * Dispatch queue (dsq) is a simple FIFO which is used to buffer between the + * scheduler core and the BPF scheduler. See the documentation for more details. + */ +struct scx_dispatch_q { + raw_spinlock_t lock; + struct list_head list; /* tasks in dispatch order */ + u32 nr; + u64 id; + struct rhash_head hash_node; + struct llist_node free_node; + struct rcu_head rcu; +}; + +/* scx_entity.flags */ +enum scx_ent_flags { + SCX_TASK_QUEUED = 1 << 0, /* on ext runqueue */ + SCX_TASK_BAL_KEEP = 1 << 1, /* balance decided to keep current */ + SCX_TASK_RESET_RUNNABLE_AT = 1 << 2, /* runnable_at should be reset */ + SCX_TASK_DEQD_FOR_SLEEP = 1 << 3, /* last dequeue was for SLEEP */ + + SCX_TASK_STATE_SHIFT = 8, /* bit 8 and 9 are used to carry scx_task_state */ + SCX_TASK_STATE_BITS = 2, + SCX_TASK_STATE_MASK = ((1 << SCX_TASK_STATE_BITS) - 1) << SCX_TASK_STATE_SHIFT, + + SCX_TASK_CURSOR = 1 << 31, /* iteration cursor, not a task */ +}; + +/* scx_entity.flags & SCX_TASK_STATE_MASK */ +enum scx_task_state { + SCX_TASK_NONE, /* ops.init_task() not called yet */ + SCX_TASK_INIT, /* ops.init_task() succeeded, but task can be cancelled */ + SCX_TASK_READY, /* fully initialized, but not in sched_ext */ + SCX_TASK_ENABLED, /* fully initialized and in sched_ext */ + + SCX_TASK_NR_STATES, +}; + +/* + * Mask bits for scx_entity.kf_mask. Not all kfuncs can be called from + * everywhere and the following bits track which kfunc sets are currently + * allowed for %current. This simple per-task tracking works because SCX ops + * nest in a limited way. BPF will likely implement a way to allow and disallow + * kfuncs depending on the calling context which will replace this manual + * mechanism. See scx_kf_allow(). + */ +enum scx_kf_mask { + SCX_KF_UNLOCKED = 0, /* not sleepable, not rq locked */ + /* all non-sleepables may be nested inside SLEEPABLE */ + SCX_KF_SLEEPABLE = 1 << 0, /* sleepable init operations */ + /* ops.dequeue (in REST) may be nested inside DISPATCH */ + SCX_KF_DISPATCH = 1 << 2, /* ops.dispatch() */ + SCX_KF_ENQUEUE = 1 << 3, /* ops.enqueue() and ops.select_cpu() */ + SCX_KF_SELECT_CPU = 1 << 4, /* ops.select_cpu() */ + SCX_KF_REST = 1 << 5, /* other rq-locked operations */ + + __SCX_KF_RQ_LOCKED = SCX_KF_DISPATCH | + SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU | SCX_KF_REST, +}; + +/* + * The following is embedded in task_struct and contains all fields necessary + * for a task to be scheduled by SCX. + */ +struct sched_ext_entity { + struct scx_dispatch_q *dsq; + struct list_head dsq_node; + u32 flags; /* protected by rq lock */ + u32 weight; + s32 sticky_cpu; + s32 holding_cpu; + u32 kf_mask; /* see scx_kf_mask above */ + atomic_long_t ops_state; + + struct list_head runnable_node; /* rq->scx.runnable_list */ + + u64 ddsp_dsq_id; + u64 ddsp_enq_flags; + + /* BPF scheduler modifiable fields */ + + /* + * Runtime budget in nsecs. This is usually set through + * scx_bpf_dispatch() but can also be modified directly by the BPF + * scheduler. Automatically decreased by SCX as the task executes. On + * depletion, a scheduling event is triggered. + */ + u64 slice; + + /* cold fields */ + /* must be the last field, see init_scx_entity() */ + struct list_head tasks_node; +}; + +void sched_ext_free(struct task_struct *p); + #else /* !CONFIG_SCHED_CLASS_EXT */ static inline void sched_ext_free(struct task_struct *p) {} diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h index 3bac0a8ceab2..359a14cc76a4 100644 --- a/include/uapi/linux/sched.h +++ b/include/uapi/linux/sched.h @@ -118,6 +118,7 @@ struct clone_args { /* SCHED_ISO: reserved but not implemented yet */ #define SCHED_IDLE 5 #define SCHED_DEADLINE 6 +#define SCHED_EXT 7 /* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */ #define SCHED_RESET_ON_FORK 0x40000000 diff --git a/init/init_task.c b/init/init_task.c index eeb110c65fe2..c6804396fe12 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -98,6 +99,16 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = { #endif #ifdef CONFIG_CGROUP_SCHED .sched_task_group = &root_task_group, +#endif +#ifdef CONFIG_SCHED_CLASS_EXT + .scx = { + .dsq_node = LIST_HEAD_INIT(init_task.scx.dsq_node), + .sticky_cpu = -1, + .holding_cpu = -1, + .runnable_node = LIST_HEAD_INIT(init_task.scx.runnable_node), + .ddsp_dsq_id = SCX_DSQ_INVALID, + .slice = SCX_SLICE_DFL, + }, #endif .ptraced = LIST_HEAD_INIT(init_task.ptraced), .ptrace_entry = LIST_HEAD_INIT(init_task.ptrace_entry), diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt index c2f1fd95a821..39ecfc2b5a1c 100644 --- a/kernel/Kconfig.preempt +++ b/kernel/Kconfig.preempt @@ -133,4 +133,27 @@ config SCHED_CORE which is the likely usage by Linux distributions, there should be no measurable impact on performance. - +config SCHED_CLASS_EXT + bool "Extensible Scheduling Class" + depends on BPF_SYSCALL && BPF_JIT && !SCHED_CORE + help + This option enables a new scheduler class sched_ext (SCX), which + allows scheduling policies to be implemented as BPF programs to + achieve the following: + + - Ease of experimentation and exploration: Enabling rapid + iteration of new scheduling policies. + - Customization: Building application-specific schedulers which + implement policies that are not applicable to general-purpose + schedulers. + - Rapid scheduler deployments: Non-disruptive swap outs of + scheduling policies in production environments. + + sched_ext leverages BPF struct_ops feature to define a structure + which exports function callbacks and flags to BPF programs that + wish to implement scheduling policies. The struct_ops structure + exported by sched_ext is struct sched_ext_ops, and is conceptually + similar to struct sched_class. + + For more information: + https://github.com/sched-ext/scx diff --git a/kernel/sched/build_policy.c b/kernel/sched/build_policy.c index 39c315182b35..f0c148fcd2df 100644 --- a/kernel/sched/build_policy.c +++ b/kernel/sched/build_policy.c @@ -21,13 +21,18 @@ #include #include +#include #include +#include #include +#include +#include #include #include #include #include #include +#include #include @@ -52,4 +57,8 @@ #include "cputime.c" #include "deadline.c" +#ifdef CONFIG_SCHED_CLASS_EXT +# include "ext.c" +#endif + #include "syscalls.c" diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d8c963fea9eb..6042ce3bfee0 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3790,6 +3790,15 @@ bool cpus_share_resources(int this_cpu, int that_cpu) static inline bool ttwu_queue_cond(struct task_struct *p, int cpu) { + /* + * The BPF scheduler may depend on select_task_rq() being invoked during + * wakeups. In addition, @p may end up executing on a different CPU + * regardless of what happens in the wakeup path making the ttwu_queue + * optimization less meaningful. Skip if on SCX. + */ + if (task_on_scx(p)) + return false; + /* * Do not complicate things with the async wake_list while the CPU is * in hotplug state. @@ -4357,6 +4366,10 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) p->rt.on_rq = 0; p->rt.on_list = 0; +#ifdef CONFIG_SCHED_CLASS_EXT + init_scx_entity(&p->scx); +#endif + #ifdef CONFIG_PREEMPT_NOTIFIERS INIT_HLIST_HEAD(&p->preempt_notifiers); #endif @@ -4604,6 +4617,10 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) goto out_cancel; } else if (rt_prio(p->prio)) { p->sched_class = &rt_sched_class; +#ifdef CONFIG_SCHED_CLASS_EXT + } else if (task_should_scx(p)) { + p->sched_class = &ext_sched_class; +#endif } else { p->sched_class = &fair_sched_class; } @@ -5511,8 +5528,10 @@ void sched_tick(void) wq_worker_tick(curr); #ifdef CONFIG_SMP - rq->idle_balance = idle_cpu(cpu); - sched_balance_trigger(rq); + if (!scx_switched_all()) { + rq->idle_balance = idle_cpu(cpu); + sched_balance_trigger(rq); + } #endif } @@ -6902,6 +6921,10 @@ void __setscheduler_prio(struct task_struct *p, int prio) p->sched_class = &dl_sched_class; else if (rt_prio(prio)) p->sched_class = &rt_sched_class; +#ifdef CONFIG_SCHED_CLASS_EXT + else if (task_should_scx(p)) + p->sched_class = &ext_sched_class; +#endif else p->sched_class = &fair_sched_class; @@ -8203,6 +8226,10 @@ void __init sched_init(void) BUG_ON(!sched_class_above(&dl_sched_class, &rt_sched_class)); BUG_ON(!sched_class_above(&rt_sched_class, &fair_sched_class)); BUG_ON(!sched_class_above(&fair_sched_class, &idle_sched_class)); +#ifdef CONFIG_SCHED_CLASS_EXT + BUG_ON(!sched_class_above(&fair_sched_class, &ext_sched_class)); + BUG_ON(!sched_class_above(&ext_sched_class, &idle_sched_class)); +#endif wait_bit_init(); @@ -10337,3 +10364,38 @@ void sched_mm_cid_fork(struct task_struct *t) t->mm_cid_active = 1; } #endif + +#ifdef CONFIG_SCHED_CLASS_EXT +void sched_deq_and_put_task(struct task_struct *p, int queue_flags, + struct sched_enq_and_set_ctx *ctx) +{ + struct rq *rq = task_rq(p); + + lockdep_assert_rq_held(rq); + + *ctx = (struct sched_enq_and_set_ctx){ + .p = p, + .queue_flags = queue_flags, + .queued = task_on_rq_queued(p), + .running = task_current(rq, p), + }; + + update_rq_clock(rq); + if (ctx->queued) + dequeue_task(rq, p, queue_flags | DEQUEUE_NOCLOCK); + if (ctx->running) + put_prev_task(rq, p); +} + +void sched_enq_and_set_task(struct sched_enq_and_set_ctx *ctx) +{ + struct rq *rq = task_rq(ctx->p); + + lockdep_assert_rq_held(rq); + + if (ctx->queued) + enqueue_task(rq, ctx->p, ctx->queue_flags | ENQUEUE_NOCLOCK); + if (ctx->running) + set_next_task(rq, ctx->p); +} +#endif /* CONFIG_SCHED_CLASS_EXT */ diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index c1eb9a1afd13..c057ef46c5f8 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -1090,6 +1090,9 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, P(dl.runtime); P(dl.deadline); } +#ifdef CONFIG_SCHED_CLASS_EXT + __PS("ext.enabled", task_on_scx(p)); +#endif #undef PN_SCHEDSTAT #undef P_SCHEDSTAT diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c new file mode 100644 index 000000000000..49b115f5b052 --- /dev/null +++ b/kernel/sched/ext.c @@ -0,0 +1,4256 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2022 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2022 Tejun Heo + * Copyright (c) 2022 David Vernet + */ +#define SCX_OP_IDX(op) (offsetof(struct sched_ext_ops, op) / sizeof(void (*)(void))) + +enum scx_consts { + SCX_DSP_DFL_MAX_BATCH = 32, + + SCX_EXIT_BT_LEN = 64, + SCX_EXIT_MSG_LEN = 1024, +}; + +enum scx_exit_kind { + SCX_EXIT_NONE, + SCX_EXIT_DONE, + + SCX_EXIT_UNREG = 64, /* user-space initiated unregistration */ + SCX_EXIT_UNREG_BPF, /* BPF-initiated unregistration */ + SCX_EXIT_UNREG_KERN, /* kernel-initiated unregistration */ + + SCX_EXIT_ERROR = 1024, /* runtime error, error msg contains details */ + SCX_EXIT_ERROR_BPF, /* ERROR but triggered through scx_bpf_error() */ +}; + +/* + * scx_exit_info is passed to ops.exit() to describe why the BPF scheduler is + * being disabled. + */ +struct scx_exit_info { + /* %SCX_EXIT_* - broad category of the exit reason */ + enum scx_exit_kind kind; + + /* exit code if gracefully exiting */ + s64 exit_code; + + /* textual representation of the above */ + const char *reason; + + /* backtrace if exiting due to an error */ + unsigned long *bt; + u32 bt_len; + + /* informational message */ + char *msg; +}; + +/* sched_ext_ops.flags */ +enum scx_ops_flags { + /* + * Keep built-in idle tracking even if ops.update_idle() is implemented. + */ + SCX_OPS_KEEP_BUILTIN_IDLE = 1LLU << 0, + + /* + * By default, if there are no other task to run on the CPU, ext core + * keeps running the current task even after its slice expires. If this + * flag is specified, such tasks are passed to ops.enqueue() with + * %SCX_ENQ_LAST. See the comment above %SCX_ENQ_LAST for more info. + */ + SCX_OPS_ENQ_LAST = 1LLU << 1, + + /* + * An exiting task may schedule after PF_EXITING is set. In such cases, + * bpf_task_from_pid() may not be able to find the task and if the BPF + * scheduler depends on pid lookup for dispatching, the task will be + * lost leading to various issues including RCU grace period stalls. + * + * To mask this problem, by default, unhashed tasks are automatically + * dispatched to the local DSQ on enqueue. If the BPF scheduler doesn't + * depend on pid lookups and wants to handle these tasks directly, the + * following flag can be used. + */ + SCX_OPS_ENQ_EXITING = 1LLU << 2, + + /* + * If set, only tasks with policy set to SCHED_EXT are attached to + * sched_ext. If clear, SCHED_NORMAL tasks are also included. + */ + SCX_OPS_SWITCH_PARTIAL = 1LLU << 3, + + SCX_OPS_ALL_FLAGS = SCX_OPS_KEEP_BUILTIN_IDLE | + SCX_OPS_ENQ_LAST | + SCX_OPS_ENQ_EXITING | + SCX_OPS_SWITCH_PARTIAL, +}; + +/* argument container for ops.init_task() */ +struct scx_init_task_args { + /* + * Set if ops.init_task() is being invoked on the fork path, as opposed + * to the scheduler transition path. + */ + bool fork; +}; + +/* argument container for ops.exit_task() */ +struct scx_exit_task_args { + /* Whether the task exited before running on sched_ext. */ + bool cancelled; +}; + +/** + * struct sched_ext_ops - Operation table for BPF scheduler implementation + * + * Userland can implement an arbitrary scheduling policy by implementing and + * loading operations in this table. + */ +struct sched_ext_ops { + /** + * select_cpu - Pick the target CPU for a task which is being woken up + * @p: task being woken up + * @prev_cpu: the cpu @p was on before sleeping + * @wake_flags: SCX_WAKE_* + * + * Decision made here isn't final. @p may be moved to any CPU while it + * is getting dispatched for execution later. However, as @p is not on + * the rq at this point, getting the eventual execution CPU right here + * saves a small bit of overhead down the line. + * + * If an idle CPU is returned, the CPU is kicked and will try to + * dispatch. While an explicit custom mechanism can be added, + * select_cpu() serves as the default way to wake up idle CPUs. + * + * @p may be dispatched directly by calling scx_bpf_dispatch(). If @p + * is dispatched, the ops.enqueue() callback will be skipped. Finally, + * if @p is dispatched to SCX_DSQ_LOCAL, it will be dispatched to the + * local DSQ of whatever CPU is returned by this callback. + */ + s32 (*select_cpu)(struct task_struct *p, s32 prev_cpu, u64 wake_flags); + + /** + * enqueue - Enqueue a task on the BPF scheduler + * @p: task being enqueued + * @enq_flags: %SCX_ENQ_* + * + * @p is ready to run. Dispatch directly by calling scx_bpf_dispatch() + * or enqueue on the BPF scheduler. If not directly dispatched, the bpf + * scheduler owns @p and if it fails to dispatch @p, the task will + * stall. + * + * If @p was dispatched from ops.select_cpu(), this callback is + * skipped. + */ + void (*enqueue)(struct task_struct *p, u64 enq_flags); + + /** + * dequeue - Remove a task from the BPF scheduler + * @p: task being dequeued + * @deq_flags: %SCX_DEQ_* + * + * Remove @p from the BPF scheduler. This is usually called to isolate + * the task while updating its scheduling properties (e.g. priority). + * + * The ext core keeps track of whether the BPF side owns a given task or + * not and can gracefully ignore spurious dispatches from BPF side, + * which makes it safe to not implement this method. However, depending + * on the scheduling logic, this can lead to confusing behaviors - e.g. + * scheduling position not being updated across a priority change. + */ + void (*dequeue)(struct task_struct *p, u64 deq_flags); + + /** + * dispatch - Dispatch tasks from the BPF scheduler and/or consume DSQs + * @cpu: CPU to dispatch tasks for + * @prev: previous task being switched out + * + * Called when a CPU's local dsq is empty. The operation should dispatch + * one or more tasks from the BPF scheduler into the DSQs using + * scx_bpf_dispatch() and/or consume user DSQs into the local DSQ using + * scx_bpf_consume(). + * + * The maximum number of times scx_bpf_dispatch() can be called without + * an intervening scx_bpf_consume() is specified by + * ops.dispatch_max_batch. See the comments on top of the two functions + * for more details. + * + * When not %NULL, @prev is an SCX task with its slice depleted. If + * @prev is still runnable as indicated by set %SCX_TASK_QUEUED in + * @prev->scx.flags, it is not enqueued yet and will be enqueued after + * ops.dispatch() returns. To keep executing @prev, return without + * dispatching or consuming any tasks. Also see %SCX_OPS_ENQ_LAST. + */ + void (*dispatch)(s32 cpu, struct task_struct *prev); + + /** + * tick - Periodic tick + * @p: task running currently + * + * This operation is called every 1/HZ seconds on CPUs which are + * executing an SCX task. Setting @p->scx.slice to 0 will trigger an + * immediate dispatch cycle on the CPU. + */ + void (*tick)(struct task_struct *p); + + /** + * yield - Yield CPU + * @from: yielding task + * @to: optional yield target task + * + * If @to is NULL, @from is yielding the CPU to other runnable tasks. + * The BPF scheduler should ensure that other available tasks are + * dispatched before the yielding task. Return value is ignored in this + * case. + * + * If @to is not-NULL, @from wants to yield the CPU to @to. If the bpf + * scheduler can implement the request, return %true; otherwise, %false. + */ + bool (*yield)(struct task_struct *from, struct task_struct *to); + + /** + * set_weight - Set task weight + * @p: task to set weight for + * @weight: new eight [1..10000] + * + * Update @p's weight to @weight. + */ + void (*set_weight)(struct task_struct *p, u32 weight); + + /** + * set_cpumask - Set CPU affinity + * @p: task to set CPU affinity for + * @cpumask: cpumask of cpus that @p can run on + * + * Update @p's CPU affinity to @cpumask. + */ + void (*set_cpumask)(struct task_struct *p, + const struct cpumask *cpumask); + + /** + * update_idle - Update the idle state of a CPU + * @cpu: CPU to udpate the idle state for + * @idle: whether entering or exiting the idle state + * + * This operation is called when @rq's CPU goes or leaves the idle + * state. By default, implementing this operation disables the built-in + * idle CPU tracking and the following helpers become unavailable: + * + * - scx_bpf_select_cpu_dfl() + * - scx_bpf_test_and_clear_cpu_idle() + * - scx_bpf_pick_idle_cpu() + * + * The user also must implement ops.select_cpu() as the default + * implementation relies on scx_bpf_select_cpu_dfl(). + * + * Specify the %SCX_OPS_KEEP_BUILTIN_IDLE flag to keep the built-in idle + * tracking. + */ + void (*update_idle)(s32 cpu, bool idle); + + /** + * init_task - Initialize a task to run in a BPF scheduler + * @p: task to initialize for BPF scheduling + * @args: init arguments, see the struct definition + * + * Either we're loading a BPF scheduler or a new task is being forked. + * Initialize @p for BPF scheduling. This operation may block and can + * be used for allocations, and is called exactly once for a task. + * + * Return 0 for success, -errno for failure. An error return while + * loading will abort loading of the BPF scheduler. During a fork, it + * will abort that specific fork. + */ + s32 (*init_task)(struct task_struct *p, struct scx_init_task_args *args); + + /** + * exit_task - Exit a previously-running task from the system + * @p: task to exit + * + * @p is exiting or the BPF scheduler is being unloaded. Perform any + * necessary cleanup for @p. + */ + void (*exit_task)(struct task_struct *p, struct scx_exit_task_args *args); + + /** + * enable - Enable BPF scheduling for a task + * @p: task to enable BPF scheduling for + * + * Enable @p for BPF scheduling. enable() is called on @p any time it + * enters SCX, and is always paired with a matching disable(). + */ + void (*enable)(struct task_struct *p); + + /** + * disable - Disable BPF scheduling for a task + * @p: task to disable BPF scheduling for + * + * @p is exiting, leaving SCX or the BPF scheduler is being unloaded. + * Disable BPF scheduling for @p. A disable() call is always matched + * with a prior enable() call. + */ + void (*disable)(struct task_struct *p); + + /* + * All online ops must come before ops.init(). + */ + + /** + * init - Initialize the BPF scheduler + */ + s32 (*init)(void); + + /** + * exit - Clean up after the BPF scheduler + * @info: Exit info + */ + void (*exit)(struct scx_exit_info *info); + + /** + * dispatch_max_batch - Max nr of tasks that dispatch() can dispatch + */ + u32 dispatch_max_batch; + + /** + * flags - %SCX_OPS_* flags + */ + u64 flags; + + /** + * name - BPF scheduler's name + * + * Must be a non-zero valid BPF object name including only isalnum(), + * '_' and '.' chars. Shows up in kernel.sched_ext_ops sysctl while the + * BPF scheduler is enabled. + */ + char name[SCX_OPS_NAME_LEN]; +}; + +enum scx_opi { + SCX_OPI_BEGIN = 0, + SCX_OPI_NORMAL_BEGIN = 0, + SCX_OPI_NORMAL_END = SCX_OP_IDX(init), + SCX_OPI_END = SCX_OP_IDX(init), +}; + +enum scx_wake_flags { + /* expose select WF_* flags as enums */ + SCX_WAKE_FORK = WF_FORK, + SCX_WAKE_TTWU = WF_TTWU, + SCX_WAKE_SYNC = WF_SYNC, +}; + +enum scx_enq_flags { + /* expose select ENQUEUE_* flags as enums */ + SCX_ENQ_WAKEUP = ENQUEUE_WAKEUP, + SCX_ENQ_HEAD = ENQUEUE_HEAD, + + /* high 32bits are SCX specific */ + + /* + * The task being enqueued is the only task available for the cpu. By + * default, ext core keeps executing such tasks but when + * %SCX_OPS_ENQ_LAST is specified, they're ops.enqueue()'d with the + * %SCX_ENQ_LAST flag set. + * + * If the BPF scheduler wants to continue executing the task, + * ops.enqueue() should dispatch the task to %SCX_DSQ_LOCAL immediately. + * If the task gets queued on a different dsq or the BPF side, the BPF + * scheduler is responsible for triggering a follow-up scheduling event. + * Otherwise, Execution may stall. + */ + SCX_ENQ_LAST = 1LLU << 41, + + /* high 8 bits are internal */ + __SCX_ENQ_INTERNAL_MASK = 0xffLLU << 56, + + SCX_ENQ_CLEAR_OPSS = 1LLU << 56, +}; + +enum scx_deq_flags { + /* expose select DEQUEUE_* flags as enums */ + SCX_DEQ_SLEEP = DEQUEUE_SLEEP, +}; + +enum scx_pick_idle_cpu_flags { + SCX_PICK_IDLE_CORE = 1LLU << 0, /* pick a CPU whose SMT siblings are also idle */ +}; + +enum scx_ops_enable_state { + SCX_OPS_PREPPING, + SCX_OPS_ENABLING, + SCX_OPS_ENABLED, + SCX_OPS_DISABLING, + SCX_OPS_DISABLED, +}; + +static const char *scx_ops_enable_state_str[] = { + [SCX_OPS_PREPPING] = "prepping", + [SCX_OPS_ENABLING] = "enabling", + [SCX_OPS_ENABLED] = "enabled", + [SCX_OPS_DISABLING] = "disabling", + [SCX_OPS_DISABLED] = "disabled", +}; + +/* + * sched_ext_entity->ops_state + * + * Used to track the task ownership between the SCX core and the BPF scheduler. + * State transitions look as follows: + * + * NONE -> QUEUEING -> QUEUED -> DISPATCHING + * ^ | | + * | v v + * \-------------------------------/ + * + * QUEUEING and DISPATCHING states can be waited upon. See wait_ops_state() call + * sites for explanations on the conditions being waited upon and why they are + * safe. Transitions out of them into NONE or QUEUED must store_release and the + * waiters should load_acquire. + * + * Tracking scx_ops_state enables sched_ext core to reliably determine whether + * any given task can be dispatched by the BPF scheduler at all times and thus + * relaxes the requirements on the BPF scheduler. This allows the BPF scheduler + * to try to dispatch any task anytime regardless of its state as the SCX core + * can safely reject invalid dispatches. + */ +enum scx_ops_state { + SCX_OPSS_NONE, /* owned by the SCX core */ + SCX_OPSS_QUEUEING, /* in transit to the BPF scheduler */ + SCX_OPSS_QUEUED, /* owned by the BPF scheduler */ + SCX_OPSS_DISPATCHING, /* in transit back to the SCX core */ + + /* + * QSEQ brands each QUEUED instance so that, when dispatch races + * dequeue/requeue, the dispatcher can tell whether it still has a claim + * on the task being dispatched. + * + * As some 32bit archs can't do 64bit store_release/load_acquire, + * p->scx.ops_state is atomic_long_t which leaves 30 bits for QSEQ on + * 32bit machines. The dispatch race window QSEQ protects is very narrow + * and runs with IRQ disabled. 30 bits should be sufficient. + */ + SCX_OPSS_QSEQ_SHIFT = 2, +}; + +/* Use macros to ensure that the type is unsigned long for the masks */ +#define SCX_OPSS_STATE_MASK ((1LU << SCX_OPSS_QSEQ_SHIFT) - 1) +#define SCX_OPSS_QSEQ_MASK (~SCX_OPSS_STATE_MASK) + +/* + * During exit, a task may schedule after losing its PIDs. When disabling the + * BPF scheduler, we need to be able to iterate tasks in every state to + * guarantee system safety. Maintain a dedicated task list which contains every + * task between its fork and eventual free. + */ +static DEFINE_SPINLOCK(scx_tasks_lock); +static LIST_HEAD(scx_tasks); + +/* ops enable/disable */ +static struct kthread_worker *scx_ops_helper; +static DEFINE_MUTEX(scx_ops_enable_mutex); +DEFINE_STATIC_KEY_FALSE(__scx_ops_enabled); +DEFINE_STATIC_PERCPU_RWSEM(scx_fork_rwsem); +static atomic_t scx_ops_enable_state_var = ATOMIC_INIT(SCX_OPS_DISABLED); +static atomic_t scx_ops_bypass_depth = ATOMIC_INIT(0); +static bool scx_switching_all; +DEFINE_STATIC_KEY_FALSE(__scx_switched_all); + +static struct sched_ext_ops scx_ops; +static bool scx_warned_zero_slice; + +static DEFINE_STATIC_KEY_FALSE(scx_ops_enq_last); +static DEFINE_STATIC_KEY_FALSE(scx_ops_enq_exiting); +static DEFINE_STATIC_KEY_FALSE(scx_builtin_idle_enabled); + +struct static_key_false scx_has_op[SCX_OPI_END] = + { [0 ... SCX_OPI_END-1] = STATIC_KEY_FALSE_INIT }; + +static atomic_t scx_exit_kind = ATOMIC_INIT(SCX_EXIT_DONE); +static struct scx_exit_info *scx_exit_info; + +/* idle tracking */ +#ifdef CONFIG_SMP +#ifdef CONFIG_CPUMASK_OFFSTACK +#define CL_ALIGNED_IF_ONSTACK +#else +#define CL_ALIGNED_IF_ONSTACK __cacheline_aligned_in_smp +#endif + +static struct { + cpumask_var_t cpu; + cpumask_var_t smt; +} idle_masks CL_ALIGNED_IF_ONSTACK; + +#endif /* CONFIG_SMP */ + +/* + * Direct dispatch marker. + * + * Non-NULL values are used for direct dispatch from enqueue path. A valid + * pointer points to the task currently being enqueued. An ERR_PTR value is used + * to indicate that direct dispatch has already happened. + */ +static DEFINE_PER_CPU(struct task_struct *, direct_dispatch_task); + +/* dispatch queues */ +static struct scx_dispatch_q __cacheline_aligned_in_smp scx_dsq_global; + +static const struct rhashtable_params dsq_hash_params = { + .key_len = 8, + .key_offset = offsetof(struct scx_dispatch_q, id), + .head_offset = offsetof(struct scx_dispatch_q, hash_node), +}; + +static struct rhashtable dsq_hash; +static LLIST_HEAD(dsqs_to_free); + +/* dispatch buf */ +struct scx_dsp_buf_ent { + struct task_struct *task; + unsigned long qseq; + u64 dsq_id; + u64 enq_flags; +}; + +static u32 scx_dsp_max_batch; + +struct scx_dsp_ctx { + struct rq *rq; + struct rq_flags *rf; + u32 cursor; + u32 nr_tasks; + struct scx_dsp_buf_ent buf[]; +}; + +static struct scx_dsp_ctx __percpu *scx_dsp_ctx; + +/* string formatting from BPF */ +struct scx_bstr_buf { + u64 data[MAX_BPRINTF_VARARGS]; + char line[SCX_EXIT_MSG_LEN]; +}; + +static DEFINE_RAW_SPINLOCK(scx_exit_bstr_buf_lock); +static struct scx_bstr_buf scx_exit_bstr_buf; + +/* /sys/kernel/sched_ext interface */ +static struct kset *scx_kset; +static struct kobject *scx_root_kobj; + +static __printf(3, 4) void scx_ops_exit_kind(enum scx_exit_kind kind, + s64 exit_code, + const char *fmt, ...); + +#define scx_ops_error_kind(err, fmt, args...) \ + scx_ops_exit_kind((err), 0, fmt, ##args) + +#define scx_ops_exit(code, fmt, args...) \ + scx_ops_exit_kind(SCX_EXIT_UNREG_KERN, (code), fmt, ##args) + +#define scx_ops_error(fmt, args...) \ + scx_ops_error_kind(SCX_EXIT_ERROR, fmt, ##args) + +#define SCX_HAS_OP(op) static_branch_likely(&scx_has_op[SCX_OP_IDX(op)]) + +/* if the highest set bit is N, return a mask with bits [N+1, 31] set */ +static u32 higher_bits(u32 flags) +{ + return ~((1 << fls(flags)) - 1); +} + +/* return the mask with only the highest bit set */ +static u32 highest_bit(u32 flags) +{ + int bit = fls(flags); + return ((u64)1 << bit) >> 1; +} + +/* + * scx_kf_mask enforcement. Some kfuncs can only be called from specific SCX + * ops. When invoking SCX ops, SCX_CALL_OP[_RET]() should be used to indicate + * the allowed kfuncs and those kfuncs should use scx_kf_allowed() to check + * whether it's running from an allowed context. + * + * @mask is constant, always inline to cull the mask calculations. + */ +static __always_inline void scx_kf_allow(u32 mask) +{ + /* nesting is allowed only in increasing scx_kf_mask order */ + WARN_ONCE((mask | higher_bits(mask)) & current->scx.kf_mask, + "invalid nesting current->scx.kf_mask=0x%x mask=0x%x\n", + current->scx.kf_mask, mask); + current->scx.kf_mask |= mask; + barrier(); +} + +static void scx_kf_disallow(u32 mask) +{ + barrier(); + current->scx.kf_mask &= ~mask; +} + +#define SCX_CALL_OP(mask, op, args...) \ +do { \ + if (mask) { \ + scx_kf_allow(mask); \ + scx_ops.op(args); \ + scx_kf_disallow(mask); \ + } else { \ + scx_ops.op(args); \ + } \ +} while (0) + +#define SCX_CALL_OP_RET(mask, op, args...) \ +({ \ + __typeof__(scx_ops.op(args)) __ret; \ + if (mask) { \ + scx_kf_allow(mask); \ + __ret = scx_ops.op(args); \ + scx_kf_disallow(mask); \ + } else { \ + __ret = scx_ops.op(args); \ + } \ + __ret; \ +}) + +/* @mask is constant, always inline to cull unnecessary branches */ +static __always_inline bool scx_kf_allowed(u32 mask) +{ + if (unlikely(!(current->scx.kf_mask & mask))) { + scx_ops_error("kfunc with mask 0x%x called from an operation only allowing 0x%x", + mask, current->scx.kf_mask); + return false; + } + + if (unlikely((mask & SCX_KF_SLEEPABLE) && in_interrupt())) { + scx_ops_error("sleepable kfunc called from non-sleepable context"); + return false; + } + + /* + * Enforce nesting boundaries. e.g. A kfunc which can be called from + * DISPATCH must not be called if we're running DEQUEUE which is nested + * inside ops.dispatch(). We don't need to check the SCX_KF_SLEEPABLE + * boundary thanks to the above in_interrupt() check. + */ + if (unlikely(highest_bit(mask) == SCX_KF_DISPATCH && + (current->scx.kf_mask & higher_bits(SCX_KF_DISPATCH)))) { + scx_ops_error("dispatch kfunc called from a nested operation"); + return false; + } + + return true; +} + + +/* + * SCX task iterator. + */ +struct scx_task_iter { + struct sched_ext_entity cursor; + struct task_struct *locked; + struct rq *rq; + struct rq_flags rf; +}; + +/** + * scx_task_iter_init - Initialize a task iterator + * @iter: iterator to init + * + * Initialize @iter. Must be called with scx_tasks_lock held. Once initialized, + * @iter must eventually be exited with scx_task_iter_exit(). + * + * scx_tasks_lock may be released between this and the first next() call or + * between any two next() calls. If scx_tasks_lock is released between two + * next() calls, the caller is responsible for ensuring that the task being + * iterated remains accessible either through RCU read lock or obtaining a + * reference count. + * + * All tasks which existed when the iteration started are guaranteed to be + * visited as long as they still exist. + */ +static void scx_task_iter_init(struct scx_task_iter *iter) +{ + lockdep_assert_held(&scx_tasks_lock); + + iter->cursor = (struct sched_ext_entity){ .flags = SCX_TASK_CURSOR }; + list_add(&iter->cursor.tasks_node, &scx_tasks); + iter->locked = NULL; +} + +/** + * scx_task_iter_rq_unlock - Unlock rq locked by a task iterator + * @iter: iterator to unlock rq for + * + * If @iter is in the middle of a locked iteration, it may be locking the rq of + * the task currently being visited. Unlock the rq if so. This function can be + * safely called anytime during an iteration. + * + * Returns %true if the rq @iter was locking is unlocked. %false if @iter was + * not locking an rq. + */ +static bool scx_task_iter_rq_unlock(struct scx_task_iter *iter) +{ + if (iter->locked) { + task_rq_unlock(iter->rq, iter->locked, &iter->rf); + iter->locked = NULL; + return true; + } else { + return false; + } +} + +/** + * scx_task_iter_exit - Exit a task iterator + * @iter: iterator to exit + * + * Exit a previously initialized @iter. Must be called with scx_tasks_lock held. + * If the iterator holds a task's rq lock, that rq lock is released. See + * scx_task_iter_init() for details. + */ +static void scx_task_iter_exit(struct scx_task_iter *iter) +{ + lockdep_assert_held(&scx_tasks_lock); + + scx_task_iter_rq_unlock(iter); + list_del_init(&iter->cursor.tasks_node); +} + +/** + * scx_task_iter_next - Next task + * @iter: iterator to walk + * + * Visit the next task. See scx_task_iter_init() for details. + */ +static struct task_struct *scx_task_iter_next(struct scx_task_iter *iter) +{ + struct list_head *cursor = &iter->cursor.tasks_node; + struct sched_ext_entity *pos; + + lockdep_assert_held(&scx_tasks_lock); + + list_for_each_entry(pos, cursor, tasks_node) { + if (&pos->tasks_node == &scx_tasks) + return NULL; + if (!(pos->flags & SCX_TASK_CURSOR)) { + list_move(cursor, &pos->tasks_node); + return container_of(pos, struct task_struct, scx); + } + } + + /* can't happen, should always terminate at scx_tasks above */ + BUG(); +} + +/** + * scx_task_iter_next_locked - Next non-idle task with its rq locked + * @iter: iterator to walk + * @include_dead: Whether we should include dead tasks in the iteration + * + * Visit the non-idle task with its rq lock held. Allows callers to specify + * whether they would like to filter out dead tasks. See scx_task_iter_init() + * for details. + */ +static struct task_struct * +scx_task_iter_next_locked(struct scx_task_iter *iter, bool include_dead) +{ + struct task_struct *p; +retry: + scx_task_iter_rq_unlock(iter); + + while ((p = scx_task_iter_next(iter))) { + /* + * is_idle_task() tests %PF_IDLE which may not be set for CPUs + * which haven't yet been onlined. Test sched_class directly. + */ + if (p->sched_class != &idle_sched_class) + break; + } + if (!p) + return NULL; + + iter->rq = task_rq_lock(p, &iter->rf); + iter->locked = p; + + /* + * If we see %TASK_DEAD, @p already disabled preemption, is about to do + * the final __schedule(), won't ever need to be scheduled again and can + * thus be safely ignored. If we don't see %TASK_DEAD, @p can't enter + * the final __schedle() while we're locking its rq and thus will stay + * alive until the rq is unlocked. + */ + if (!include_dead && READ_ONCE(p->__state) == TASK_DEAD) + goto retry; + + return p; +} + +static enum scx_ops_enable_state scx_ops_enable_state(void) +{ + return atomic_read(&scx_ops_enable_state_var); +} + +static enum scx_ops_enable_state +scx_ops_set_enable_state(enum scx_ops_enable_state to) +{ + return atomic_xchg(&scx_ops_enable_state_var, to); +} + +static bool scx_ops_tryset_enable_state(enum scx_ops_enable_state to, + enum scx_ops_enable_state from) +{ + int from_v = from; + + return atomic_try_cmpxchg(&scx_ops_enable_state_var, &from_v, to); +} + +static bool scx_ops_bypassing(void) +{ + return unlikely(atomic_read(&scx_ops_bypass_depth)); +} + +/** + * wait_ops_state - Busy-wait the specified ops state to end + * @p: target task + * @opss: state to wait the end of + * + * Busy-wait for @p to transition out of @opss. This can only be used when the + * state part of @opss is %SCX_QUEUEING or %SCX_DISPATCHING. This function also + * has load_acquire semantics to ensure that the caller can see the updates made + * in the enqueueing and dispatching paths. + */ +static void wait_ops_state(struct task_struct *p, unsigned long opss) +{ + do { + cpu_relax(); + } while (atomic_long_read_acquire(&p->scx.ops_state) == opss); +} + +/** + * ops_cpu_valid - Verify a cpu number + * @cpu: cpu number which came from a BPF ops + * @where: extra information reported on error + * + * @cpu is a cpu number which came from the BPF scheduler and can be any value. + * Verify that it is in range and one of the possible cpus. If invalid, trigger + * an ops error. + */ +static bool ops_cpu_valid(s32 cpu, const char *where) +{ + if (likely(cpu >= 0 && cpu < nr_cpu_ids && cpu_possible(cpu))) { + return true; + } else { + scx_ops_error("invalid CPU %d%s%s", cpu, + where ? " " : "", where ?: ""); + return false; + } +} + +/** + * ops_sanitize_err - Sanitize a -errno value + * @ops_name: operation to blame on failure + * @err: -errno value to sanitize + * + * Verify @err is a valid -errno. If not, trigger scx_ops_error() and return + * -%EPROTO. This is necessary because returning a rogue -errno up the chain can + * cause misbehaviors. For an example, a large negative return from + * ops.init_task() triggers an oops when passed up the call chain because the + * value fails IS_ERR() test after being encoded with ERR_PTR() and then is + * handled as a pointer. + */ +static int ops_sanitize_err(const char *ops_name, s32 err) +{ + if (err < 0 && err >= -MAX_ERRNO) + return err; + + scx_ops_error("ops.%s() returned an invalid errno %d", ops_name, err); + return -EPROTO; +} + +static void update_curr_scx(struct rq *rq) +{ + struct task_struct *curr = rq->curr; + u64 now = rq_clock_task(rq); + u64 delta_exec; + + if (time_before_eq64(now, curr->se.exec_start)) + return; + + delta_exec = now - curr->se.exec_start; + curr->se.exec_start = now; + curr->se.sum_exec_runtime += delta_exec; + account_group_exec_runtime(curr, delta_exec); + cgroup_account_cputime(curr, delta_exec); + + curr->scx.slice -= min(curr->scx.slice, delta_exec); +} + +static void dsq_mod_nr(struct scx_dispatch_q *dsq, s32 delta) +{ + /* scx_bpf_dsq_nr_queued() reads ->nr without locking, use WRITE_ONCE() */ + WRITE_ONCE(dsq->nr, dsq->nr + delta); +} + +static void dispatch_enqueue(struct scx_dispatch_q *dsq, struct task_struct *p, + u64 enq_flags) +{ + bool is_local = dsq->id == SCX_DSQ_LOCAL; + + WARN_ON_ONCE(p->scx.dsq || !list_empty(&p->scx.dsq_node)); + + if (!is_local) { + raw_spin_lock(&dsq->lock); + if (unlikely(dsq->id == SCX_DSQ_INVALID)) { + scx_ops_error("attempting to dispatch to a destroyed dsq"); + /* fall back to the global dsq */ + raw_spin_unlock(&dsq->lock); + dsq = &scx_dsq_global; + raw_spin_lock(&dsq->lock); + } + } + + if (enq_flags & SCX_ENQ_HEAD) + list_add(&p->scx.dsq_node, &dsq->list); + else + list_add_tail(&p->scx.dsq_node, &dsq->list); + + dsq_mod_nr(dsq, 1); + p->scx.dsq = dsq; + + /* + * scx.ddsp_dsq_id and scx.ddsp_enq_flags are only relevant on the + * direct dispatch path, but we clear them here because the direct + * dispatch verdict may be overridden on the enqueue path during e.g. + * bypass. + */ + p->scx.ddsp_dsq_id = SCX_DSQ_INVALID; + p->scx.ddsp_enq_flags = 0; + + /* + * We're transitioning out of QUEUEING or DISPATCHING. store_release to + * match waiters' load_acquire. + */ + if (enq_flags & SCX_ENQ_CLEAR_OPSS) + atomic_long_set_release(&p->scx.ops_state, SCX_OPSS_NONE); + + if (is_local) { + struct rq *rq = container_of(dsq, struct rq, scx.local_dsq); + + if (sched_class_above(&ext_sched_class, rq->curr->sched_class)) + resched_curr(rq); + } else { + raw_spin_unlock(&dsq->lock); + } +} + +static void dispatch_dequeue(struct rq *rq, struct task_struct *p) +{ + struct scx_dispatch_q *dsq = p->scx.dsq; + bool is_local = dsq == &rq->scx.local_dsq; + + if (!dsq) { + WARN_ON_ONCE(!list_empty(&p->scx.dsq_node)); + /* + * When dispatching directly from the BPF scheduler to a local + * DSQ, the task isn't associated with any DSQ but + * @p->scx.holding_cpu may be set under the protection of + * %SCX_OPSS_DISPATCHING. + */ + if (p->scx.holding_cpu >= 0) + p->scx.holding_cpu = -1; + return; + } + + if (!is_local) + raw_spin_lock(&dsq->lock); + + /* + * Now that we hold @dsq->lock, @p->holding_cpu and @p->scx.dsq_node + * can't change underneath us. + */ + if (p->scx.holding_cpu < 0) { + /* @p must still be on @dsq, dequeue */ + WARN_ON_ONCE(list_empty(&p->scx.dsq_node)); + list_del_init(&p->scx.dsq_node); + dsq_mod_nr(dsq, -1); + } else { + /* + * We're racing against dispatch_to_local_dsq() which already + * removed @p from @dsq and set @p->scx.holding_cpu. Clear the + * holding_cpu which tells dispatch_to_local_dsq() that it lost + * the race. + */ + WARN_ON_ONCE(!list_empty(&p->scx.dsq_node)); + p->scx.holding_cpu = -1; + } + p->scx.dsq = NULL; + + if (!is_local) + raw_spin_unlock(&dsq->lock); +} + +static struct scx_dispatch_q *find_user_dsq(u64 dsq_id) +{ + return rhashtable_lookup_fast(&dsq_hash, &dsq_id, dsq_hash_params); +} + +static struct scx_dispatch_q *find_non_local_dsq(u64 dsq_id) +{ + lockdep_assert(rcu_read_lock_any_held()); + + if (dsq_id == SCX_DSQ_GLOBAL) + return &scx_dsq_global; + else + return find_user_dsq(dsq_id); +} + +static struct scx_dispatch_q *find_dsq_for_dispatch(struct rq *rq, u64 dsq_id, + struct task_struct *p) +{ + struct scx_dispatch_q *dsq; + + if (dsq_id == SCX_DSQ_LOCAL) + return &rq->scx.local_dsq; + + dsq = find_non_local_dsq(dsq_id); + if (unlikely(!dsq)) { + scx_ops_error("non-existent DSQ 0x%llx for %s[%d]", + dsq_id, p->comm, p->pid); + return &scx_dsq_global; + } + + return dsq; +} + +static void mark_direct_dispatch(struct task_struct *ddsp_task, + struct task_struct *p, u64 dsq_id, + u64 enq_flags) +{ + /* + * Mark that dispatch already happened from ops.select_cpu() or + * ops.enqueue() by spoiling direct_dispatch_task with a non-NULL value + * which can never match a valid task pointer. + */ + __this_cpu_write(direct_dispatch_task, ERR_PTR(-ESRCH)); + + /* @p must match the task on the enqueue path */ + if (unlikely(p != ddsp_task)) { + if (IS_ERR(ddsp_task)) + scx_ops_error("%s[%d] already direct-dispatched", + p->comm, p->pid); + else + scx_ops_error("scheduling for %s[%d] but trying to direct-dispatch %s[%d]", + ddsp_task->comm, ddsp_task->pid, + p->comm, p->pid); + return; + } + + /* + * %SCX_DSQ_LOCAL_ON is not supported during direct dispatch because + * dispatching to the local DSQ of a different CPU requires unlocking + * the current rq which isn't allowed in the enqueue path. Use + * ops.select_cpu() to be on the target CPU and then %SCX_DSQ_LOCAL. + */ + if (unlikely((dsq_id & SCX_DSQ_LOCAL_ON) == SCX_DSQ_LOCAL_ON)) { + scx_ops_error("SCX_DSQ_LOCAL_ON can't be used for direct-dispatch"); + return; + } + + WARN_ON_ONCE(p->scx.ddsp_dsq_id != SCX_DSQ_INVALID); + WARN_ON_ONCE(p->scx.ddsp_enq_flags); + + p->scx.ddsp_dsq_id = dsq_id; + p->scx.ddsp_enq_flags = enq_flags; +} + +static void direct_dispatch(struct task_struct *p, u64 enq_flags) +{ + struct scx_dispatch_q *dsq; + + enq_flags |= (p->scx.ddsp_enq_flags | SCX_ENQ_CLEAR_OPSS); + dsq = find_dsq_for_dispatch(task_rq(p), p->scx.ddsp_dsq_id, p); + dispatch_enqueue(dsq, p, enq_flags); +} + +static bool scx_rq_online(struct rq *rq) +{ +#ifdef CONFIG_SMP + return likely(rq->online); +#else + return true; +#endif +} + +static void do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags, + int sticky_cpu) +{ + struct task_struct **ddsp_taskp; + unsigned long qseq; + + WARN_ON_ONCE(!(p->scx.flags & SCX_TASK_QUEUED)); + + /* rq migration */ + if (sticky_cpu == cpu_of(rq)) + goto local_norefill; + + if (!scx_rq_online(rq)) + goto local; + + if (scx_ops_bypassing()) { + if (enq_flags & SCX_ENQ_LAST) + goto local; + else + goto global; + } + + if (p->scx.ddsp_dsq_id != SCX_DSQ_INVALID) + goto direct; + + /* see %SCX_OPS_ENQ_EXITING */ + if (!static_branch_unlikely(&scx_ops_enq_exiting) && + unlikely(p->flags & PF_EXITING)) + goto local; + + /* see %SCX_OPS_ENQ_LAST */ + if (!static_branch_unlikely(&scx_ops_enq_last) && + (enq_flags & SCX_ENQ_LAST)) + goto local; + + if (!SCX_HAS_OP(enqueue)) + goto global; + + /* DSQ bypass didn't trigger, enqueue on the BPF scheduler */ + qseq = rq->scx.ops_qseq++ << SCX_OPSS_QSEQ_SHIFT; + + WARN_ON_ONCE(atomic_long_read(&p->scx.ops_state) != SCX_OPSS_NONE); + atomic_long_set(&p->scx.ops_state, SCX_OPSS_QUEUEING | qseq); + + ddsp_taskp = this_cpu_ptr(&direct_dispatch_task); + WARN_ON_ONCE(*ddsp_taskp); + *ddsp_taskp = p; + + SCX_CALL_OP(SCX_KF_ENQUEUE, enqueue, p, enq_flags); + + *ddsp_taskp = NULL; + if (p->scx.ddsp_dsq_id != SCX_DSQ_INVALID) + goto direct; + + /* + * If not directly dispatched, QUEUEING isn't clear yet and dispatch or + * dequeue may be waiting. The store_release matches their load_acquire. + */ + atomic_long_set_release(&p->scx.ops_state, SCX_OPSS_QUEUED | qseq); + return; + +direct: + direct_dispatch(p, enq_flags); + return; + +local: + p->scx.slice = SCX_SLICE_DFL; +local_norefill: + dispatch_enqueue(&rq->scx.local_dsq, p, enq_flags); + return; + +global: + p->scx.slice = SCX_SLICE_DFL; + dispatch_enqueue(&scx_dsq_global, p, enq_flags); +} + +static bool task_runnable(const struct task_struct *p) +{ + return !list_empty(&p->scx.runnable_node); +} + +static void set_task_runnable(struct rq *rq, struct task_struct *p) +{ + lockdep_assert_rq_held(rq); + + /* + * list_add_tail() must be used. scx_ops_bypass() depends on tasks being + * appened to the runnable_list. + */ + list_add_tail(&p->scx.runnable_node, &rq->scx.runnable_list); +} + +static void clr_task_runnable(struct task_struct *p) +{ + list_del_init(&p->scx.runnable_node); +} + +static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int enq_flags) +{ + int sticky_cpu = p->scx.sticky_cpu; + + enq_flags |= rq->scx.extra_enq_flags; + + if (sticky_cpu >= 0) + p->scx.sticky_cpu = -1; + + /* + * Restoring a running task will be immediately followed by + * set_next_task_scx() which expects the task to not be on the BPF + * scheduler as tasks can only start running through local DSQs. Force + * direct-dispatch into the local DSQ by setting the sticky_cpu. + */ + if (unlikely(enq_flags & ENQUEUE_RESTORE) && task_current(rq, p)) + sticky_cpu = cpu_of(rq); + + if (p->scx.flags & SCX_TASK_QUEUED) { + WARN_ON_ONCE(!task_runnable(p)); + return; + } + + set_task_runnable(rq, p); + p->scx.flags |= SCX_TASK_QUEUED; + rq->scx.nr_running++; + add_nr_running(rq, 1); + + do_enqueue_task(rq, p, enq_flags, sticky_cpu); +} + +static void ops_dequeue(struct task_struct *p, u64 deq_flags) +{ + unsigned long opss; + + clr_task_runnable(p); + + /* acquire ensures that we see the preceding updates on QUEUED */ + opss = atomic_long_read_acquire(&p->scx.ops_state); + + switch (opss & SCX_OPSS_STATE_MASK) { + case SCX_OPSS_NONE: + break; + case SCX_OPSS_QUEUEING: + /* + * QUEUEING is started and finished while holding @p's rq lock. + * As we're holding the rq lock now, we shouldn't see QUEUEING. + */ + BUG(); + case SCX_OPSS_QUEUED: + if (SCX_HAS_OP(dequeue)) + SCX_CALL_OP(SCX_KF_REST, dequeue, p, deq_flags); + + if (atomic_long_try_cmpxchg(&p->scx.ops_state, &opss, + SCX_OPSS_NONE)) + break; + fallthrough; + case SCX_OPSS_DISPATCHING: + /* + * If @p is being dispatched from the BPF scheduler to a DSQ, + * wait for the transfer to complete so that @p doesn't get + * added to its DSQ after dequeueing is complete. + * + * As we're waiting on DISPATCHING with the rq locked, the + * dispatching side shouldn't try to lock the rq while + * DISPATCHING is set. See dispatch_to_local_dsq(). + * + * DISPATCHING shouldn't have qseq set and control can reach + * here with NONE @opss from the above QUEUED case block. + * Explicitly wait on %SCX_OPSS_DISPATCHING instead of @opss. + */ + wait_ops_state(p, SCX_OPSS_DISPATCHING); + BUG_ON(atomic_long_read(&p->scx.ops_state) != SCX_OPSS_NONE); + break; + } +} + +static void dequeue_task_scx(struct rq *rq, struct task_struct *p, int deq_flags) +{ + if (!(p->scx.flags & SCX_TASK_QUEUED)) { + WARN_ON_ONCE(task_runnable(p)); + return; + } + + ops_dequeue(p, deq_flags); + + if (deq_flags & SCX_DEQ_SLEEP) + p->scx.flags |= SCX_TASK_DEQD_FOR_SLEEP; + else + p->scx.flags &= ~SCX_TASK_DEQD_FOR_SLEEP; + + p->scx.flags &= ~SCX_TASK_QUEUED; + rq->scx.nr_running--; + sub_nr_running(rq, 1); + + dispatch_dequeue(rq, p); +} + +static void yield_task_scx(struct rq *rq) +{ + struct task_struct *p = rq->curr; + + if (SCX_HAS_OP(yield)) + SCX_CALL_OP_RET(SCX_KF_REST, yield, p, NULL); + else + p->scx.slice = 0; +} + +static bool yield_to_task_scx(struct rq *rq, struct task_struct *to) +{ + struct task_struct *from = rq->curr; + + if (SCX_HAS_OP(yield)) + return SCX_CALL_OP_RET(SCX_KF_REST, yield, from, to); + else + return false; +} + +#ifdef CONFIG_SMP +/** + * move_task_to_local_dsq - Move a task from a different rq to a local DSQ + * @rq: rq to move the task into, currently locked + * @p: task to move + * @enq_flags: %SCX_ENQ_* + * + * Move @p which is currently on a different rq to @rq's local DSQ. The caller + * must: + * + * 1. Start with exclusive access to @p either through its DSQ lock or + * %SCX_OPSS_DISPATCHING flag. + * + * 2. Set @p->scx.holding_cpu to raw_smp_processor_id(). + * + * 3. Remember task_rq(@p). Release the exclusive access so that we don't + * deadlock with dequeue. + * + * 4. Lock @rq and the task_rq from #3. + * + * 5. Call this function. + * + * Returns %true if @p was successfully moved. %false after racing dequeue and + * losing. + */ +static bool move_task_to_local_dsq(struct rq *rq, struct task_struct *p, + u64 enq_flags) +{ + struct rq *task_rq; + + lockdep_assert_rq_held(rq); + + /* + * If dequeue got to @p while we were trying to lock both rq's, it'd + * have cleared @p->scx.holding_cpu to -1. While other cpus may have + * updated it to different values afterwards, as this operation can't be + * preempted or recurse, @p->scx.holding_cpu can never become + * raw_smp_processor_id() again before we're done. Thus, we can tell + * whether we lost to dequeue by testing whether @p->scx.holding_cpu is + * still raw_smp_processor_id(). + * + * See dispatch_dequeue() for the counterpart. + */ + if (unlikely(p->scx.holding_cpu != raw_smp_processor_id())) + return false; + + /* @p->rq couldn't have changed if we're still the holding cpu */ + task_rq = task_rq(p); + lockdep_assert_rq_held(task_rq); + + WARN_ON_ONCE(!cpumask_test_cpu(cpu_of(rq), p->cpus_ptr)); + deactivate_task(task_rq, p, 0); + set_task_cpu(p, cpu_of(rq)); + p->scx.sticky_cpu = cpu_of(rq); + + /* + * We want to pass scx-specific enq_flags but activate_task() will + * truncate the upper 32 bit. As we own @rq, we can pass them through + * @rq->scx.extra_enq_flags instead. + */ + WARN_ON_ONCE(rq->scx.extra_enq_flags); + rq->scx.extra_enq_flags = enq_flags; + activate_task(rq, p, 0); + rq->scx.extra_enq_flags = 0; + + return true; +} + +/** + * dispatch_to_local_dsq_lock - Ensure source and destination rq's are locked + * @rq: current rq which is locked + * @rf: rq_flags to use when unlocking @rq + * @src_rq: rq to move task from + * @dst_rq: rq to move task to + * + * We're holding @rq lock and trying to dispatch a task from @src_rq to + * @dst_rq's local DSQ and thus need to lock both @src_rq and @dst_rq. Whether + * @rq stays locked isn't important as long as the state is restored after + * dispatch_to_local_dsq_unlock(). + */ +static void dispatch_to_local_dsq_lock(struct rq *rq, struct rq_flags *rf, + struct rq *src_rq, struct rq *dst_rq) +{ + rq_unpin_lock(rq, rf); + + if (src_rq == dst_rq) { + raw_spin_rq_unlock(rq); + raw_spin_rq_lock(dst_rq); + } else if (rq == src_rq) { + double_lock_balance(rq, dst_rq); + rq_repin_lock(rq, rf); + } else if (rq == dst_rq) { + double_lock_balance(rq, src_rq); + rq_repin_lock(rq, rf); + } else { + raw_spin_rq_unlock(rq); + double_rq_lock(src_rq, dst_rq); + } +} + +/** + * dispatch_to_local_dsq_unlock - Undo dispatch_to_local_dsq_lock() + * @rq: current rq which is locked + * @rf: rq_flags to use when unlocking @rq + * @src_rq: rq to move task from + * @dst_rq: rq to move task to + * + * Unlock @src_rq and @dst_rq and ensure that @rq is locked on return. + */ +static void dispatch_to_local_dsq_unlock(struct rq *rq, struct rq_flags *rf, + struct rq *src_rq, struct rq *dst_rq) +{ + if (src_rq == dst_rq) { + raw_spin_rq_unlock(dst_rq); + raw_spin_rq_lock(rq); + rq_repin_lock(rq, rf); + } else if (rq == src_rq) { + double_unlock_balance(rq, dst_rq); + } else if (rq == dst_rq) { + double_unlock_balance(rq, src_rq); + } else { + double_rq_unlock(src_rq, dst_rq); + raw_spin_rq_lock(rq); + rq_repin_lock(rq, rf); + } +} +#endif /* CONFIG_SMP */ + +static void consume_local_task(struct rq *rq, struct scx_dispatch_q *dsq, + struct task_struct *p) +{ + lockdep_assert_held(&dsq->lock); /* released on return */ + + /* @dsq is locked and @p is on this rq */ + WARN_ON_ONCE(p->scx.holding_cpu >= 0); + list_move_tail(&p->scx.dsq_node, &rq->scx.local_dsq.list); + dsq_mod_nr(dsq, -1); + dsq_mod_nr(&rq->scx.local_dsq, 1); + p->scx.dsq = &rq->scx.local_dsq; + raw_spin_unlock(&dsq->lock); +} + +#ifdef CONFIG_SMP +/* + * Similar to kernel/sched/core.c::is_cpu_allowed() but we're testing whether @p + * can be pulled to @rq. + */ +static bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *rq) +{ + int cpu = cpu_of(rq); + + if (!cpumask_test_cpu(cpu, p->cpus_ptr)) + return false; + if (unlikely(is_migration_disabled(p))) + return false; + if (!(p->flags & PF_KTHREAD) && unlikely(!task_cpu_possible(cpu, p))) + return false; + if (!scx_rq_online(rq)) + return false; + return true; +} + +static bool consume_remote_task(struct rq *rq, struct rq_flags *rf, + struct scx_dispatch_q *dsq, + struct task_struct *p, struct rq *task_rq) +{ + bool moved = false; + + lockdep_assert_held(&dsq->lock); /* released on return */ + + /* + * @dsq is locked and @p is on a remote rq. @p is currently protected by + * @dsq->lock. We want to pull @p to @rq but may deadlock if we grab + * @task_rq while holding @dsq and @rq locks. As dequeue can't drop the + * rq lock or fail, do a little dancing from our side. See + * move_task_to_local_dsq(). + */ + WARN_ON_ONCE(p->scx.holding_cpu >= 0); + list_del_init(&p->scx.dsq_node); + dsq_mod_nr(dsq, -1); + p->scx.holding_cpu = raw_smp_processor_id(); + raw_spin_unlock(&dsq->lock); + + rq_unpin_lock(rq, rf); + double_lock_balance(rq, task_rq); + rq_repin_lock(rq, rf); + + moved = move_task_to_local_dsq(rq, p, 0); + + double_unlock_balance(rq, task_rq); + + return moved; +} +#else /* CONFIG_SMP */ +static bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *rq) { return false; } +static bool consume_remote_task(struct rq *rq, struct rq_flags *rf, + struct scx_dispatch_q *dsq, + struct task_struct *p, struct rq *task_rq) { return false; } +#endif /* CONFIG_SMP */ + +static bool consume_dispatch_q(struct rq *rq, struct rq_flags *rf, + struct scx_dispatch_q *dsq) +{ + struct task_struct *p; +retry: + if (list_empty(&dsq->list)) + return false; + + raw_spin_lock(&dsq->lock); + + list_for_each_entry(p, &dsq->list, scx.dsq_node) { + struct rq *task_rq = task_rq(p); + + if (rq == task_rq) { + consume_local_task(rq, dsq, p); + return true; + } + + if (task_can_run_on_remote_rq(p, rq)) { + if (likely(consume_remote_task(rq, rf, dsq, p, task_rq))) + return true; + goto retry; + } + } + + raw_spin_unlock(&dsq->lock); + return false; +} + +enum dispatch_to_local_dsq_ret { + DTL_DISPATCHED, /* successfully dispatched */ + DTL_LOST, /* lost race to dequeue */ + DTL_NOT_LOCAL, /* destination is not a local DSQ */ + DTL_INVALID, /* invalid local dsq_id */ +}; + +/** + * dispatch_to_local_dsq - Dispatch a task to a local dsq + * @rq: current rq which is locked + * @rf: rq_flags to use when unlocking @rq + * @dsq_id: destination dsq ID + * @p: task to dispatch + * @enq_flags: %SCX_ENQ_* + * + * We're holding @rq lock and want to dispatch @p to the local DSQ identified by + * @dsq_id. This function performs all the synchronization dancing needed + * because local DSQs are protected with rq locks. + * + * The caller must have exclusive ownership of @p (e.g. through + * %SCX_OPSS_DISPATCHING). + */ +static enum dispatch_to_local_dsq_ret +dispatch_to_local_dsq(struct rq *rq, struct rq_flags *rf, u64 dsq_id, + struct task_struct *p, u64 enq_flags) +{ + struct rq *src_rq = task_rq(p); + struct rq *dst_rq; + + /* + * We're synchronized against dequeue through DISPATCHING. As @p can't + * be dequeued, its task_rq and cpus_allowed are stable too. + */ + if (dsq_id == SCX_DSQ_LOCAL) { + dst_rq = rq; + } else if ((dsq_id & SCX_DSQ_LOCAL_ON) == SCX_DSQ_LOCAL_ON) { + s32 cpu = dsq_id & SCX_DSQ_LOCAL_CPU_MASK; + + if (!ops_cpu_valid(cpu, "in SCX_DSQ_LOCAL_ON dispatch verdict")) + return DTL_INVALID; + dst_rq = cpu_rq(cpu); + } else { + return DTL_NOT_LOCAL; + } + + /* if dispatching to @rq that @p is already on, no lock dancing needed */ + if (rq == src_rq && rq == dst_rq) { + dispatch_enqueue(&dst_rq->scx.local_dsq, p, + enq_flags | SCX_ENQ_CLEAR_OPSS); + return DTL_DISPATCHED; + } + +#ifdef CONFIG_SMP + if (cpumask_test_cpu(cpu_of(dst_rq), p->cpus_ptr)) { + struct rq *locked_dst_rq = dst_rq; + bool dsp; + + /* + * @p is on a possibly remote @src_rq which we need to lock to + * move the task. If dequeue is in progress, it'd be locking + * @src_rq and waiting on DISPATCHING, so we can't grab @src_rq + * lock while holding DISPATCHING. + * + * As DISPATCHING guarantees that @p is wholly ours, we can + * pretend that we're moving from a DSQ and use the same + * mechanism - mark the task under transfer with holding_cpu, + * release DISPATCHING and then follow the same protocol. + */ + p->scx.holding_cpu = raw_smp_processor_id(); + + /* store_release ensures that dequeue sees the above */ + atomic_long_set_release(&p->scx.ops_state, SCX_OPSS_NONE); + + dispatch_to_local_dsq_lock(rq, rf, src_rq, locked_dst_rq); + + /* + * We don't require the BPF scheduler to avoid dispatching to + * offline CPUs mostly for convenience but also because CPUs can + * go offline between scx_bpf_dispatch() calls and here. If @p + * is destined to an offline CPU, queue it on its current CPU + * instead, which should always be safe. As this is an allowed + * behavior, don't trigger an ops error. + */ + if (!scx_rq_online(dst_rq)) + dst_rq = src_rq; + + if (src_rq == dst_rq) { + /* + * As @p is staying on the same rq, there's no need to + * go through the full deactivate/activate cycle. + * Optimize by abbreviating the operations in + * move_task_to_local_dsq(). + */ + dsp = p->scx.holding_cpu == raw_smp_processor_id(); + if (likely(dsp)) { + p->scx.holding_cpu = -1; + dispatch_enqueue(&dst_rq->scx.local_dsq, p, + enq_flags); + } + } else { + dsp = move_task_to_local_dsq(dst_rq, p, enq_flags); + } + + /* if the destination CPU is idle, wake it up */ + if (dsp && sched_class_above(p->sched_class, + dst_rq->curr->sched_class)) + resched_curr(dst_rq); + + dispatch_to_local_dsq_unlock(rq, rf, src_rq, locked_dst_rq); + + return dsp ? DTL_DISPATCHED : DTL_LOST; + } +#endif /* CONFIG_SMP */ + + scx_ops_error("SCX_DSQ_LOCAL[_ON] verdict target cpu %d not allowed for %s[%d]", + cpu_of(dst_rq), p->comm, p->pid); + return DTL_INVALID; +} + +/** + * finish_dispatch - Asynchronously finish dispatching a task + * @rq: current rq which is locked + * @rf: rq_flags to use when unlocking @rq + * @p: task to finish dispatching + * @qseq_at_dispatch: qseq when @p started getting dispatched + * @dsq_id: destination DSQ ID + * @enq_flags: %SCX_ENQ_* + * + * Dispatching to local DSQs may need to wait for queueing to complete or + * require rq lock dancing. As we don't wanna do either while inside + * ops.dispatch() to avoid locking order inversion, we split dispatching into + * two parts. scx_bpf_dispatch() which is called by ops.dispatch() records the + * task and its qseq. Once ops.dispatch() returns, this function is called to + * finish up. + * + * There is no guarantee that @p is still valid for dispatching or even that it + * was valid in the first place. Make sure that the task is still owned by the + * BPF scheduler and claim the ownership before dispatching. + */ +static void finish_dispatch(struct rq *rq, struct rq_flags *rf, + struct task_struct *p, + unsigned long qseq_at_dispatch, + u64 dsq_id, u64 enq_flags) +{ + struct scx_dispatch_q *dsq; + unsigned long opss; + +retry: + /* + * No need for _acquire here. @p is accessed only after a successful + * try_cmpxchg to DISPATCHING. + */ + opss = atomic_long_read(&p->scx.ops_state); + + switch (opss & SCX_OPSS_STATE_MASK) { + case SCX_OPSS_DISPATCHING: + case SCX_OPSS_NONE: + /* someone else already got to it */ + return; + case SCX_OPSS_QUEUED: + /* + * If qseq doesn't match, @p has gone through at least one + * dispatch/dequeue and re-enqueue cycle between + * scx_bpf_dispatch() and here and we have no claim on it. + */ + if ((opss & SCX_OPSS_QSEQ_MASK) != qseq_at_dispatch) + return; + + /* + * While we know @p is accessible, we don't yet have a claim on + * it - the BPF scheduler is allowed to dispatch tasks + * spuriously and there can be a racing dequeue attempt. Let's + * claim @p by atomically transitioning it from QUEUED to + * DISPATCHING. + */ + if (likely(atomic_long_try_cmpxchg(&p->scx.ops_state, &opss, + SCX_OPSS_DISPATCHING))) + break; + goto retry; + case SCX_OPSS_QUEUEING: + /* + * do_enqueue_task() is in the process of transferring the task + * to the BPF scheduler while holding @p's rq lock. As we aren't + * holding any kernel or BPF resource that the enqueue path may + * depend upon, it's safe to wait. + */ + wait_ops_state(p, opss); + goto retry; + } + + BUG_ON(!(p->scx.flags & SCX_TASK_QUEUED)); + + switch (dispatch_to_local_dsq(rq, rf, dsq_id, p, enq_flags)) { + case DTL_DISPATCHED: + break; + case DTL_LOST: + break; + case DTL_INVALID: + dsq_id = SCX_DSQ_GLOBAL; + fallthrough; + case DTL_NOT_LOCAL: + dsq = find_dsq_for_dispatch(cpu_rq(raw_smp_processor_id()), + dsq_id, p); + dispatch_enqueue(dsq, p, enq_flags | SCX_ENQ_CLEAR_OPSS); + break; + } +} + +static void flush_dispatch_buf(struct rq *rq, struct rq_flags *rf) +{ + struct scx_dsp_ctx *dspc = this_cpu_ptr(scx_dsp_ctx); + u32 u; + + for (u = 0; u < dspc->cursor; u++) { + struct scx_dsp_buf_ent *ent = &dspc->buf[u]; + + finish_dispatch(rq, rf, ent->task, ent->qseq, ent->dsq_id, + ent->enq_flags); + } + + dspc->nr_tasks += dspc->cursor; + dspc->cursor = 0; +} + +static int balance_scx(struct rq *rq, struct task_struct *prev, + struct rq_flags *rf) +{ + struct scx_dsp_ctx *dspc = this_cpu_ptr(scx_dsp_ctx); + bool prev_on_scx = prev->sched_class == &ext_sched_class; + + lockdep_assert_rq_held(rq); + + if (prev_on_scx) { + WARN_ON_ONCE(prev->scx.flags & SCX_TASK_BAL_KEEP); + update_curr_scx(rq); + + /* + * If @prev is runnable & has slice left, it has priority and + * fetching more just increases latency for the fetched tasks. + * Tell put_prev_task_scx() to put @prev on local_dsq. + * + * See scx_ops_disable_workfn() for the explanation on the + * bypassing test. + */ + if ((prev->scx.flags & SCX_TASK_QUEUED) && + prev->scx.slice && !scx_ops_bypassing()) { + prev->scx.flags |= SCX_TASK_BAL_KEEP; + return 1; + } + } + + /* if there already are tasks to run, nothing to do */ + if (rq->scx.local_dsq.nr) + return 1; + + if (consume_dispatch_q(rq, rf, &scx_dsq_global)) + return 1; + + if (!SCX_HAS_OP(dispatch) || scx_ops_bypassing() || !scx_rq_online(rq)) + return 0; + + dspc->rq = rq; + dspc->rf = rf; + + /* + * The dispatch loop. Because flush_dispatch_buf() may drop the rq lock, + * the local DSQ might still end up empty after a successful + * ops.dispatch(). If the local DSQ is empty even after ops.dispatch() + * produced some tasks, retry. The BPF scheduler may depend on this + * looping behavior to simplify its implementation. + */ + do { + dspc->nr_tasks = 0; + + SCX_CALL_OP(SCX_KF_DISPATCH, dispatch, cpu_of(rq), + prev_on_scx ? prev : NULL); + + flush_dispatch_buf(rq, rf); + + if (rq->scx.local_dsq.nr) + return 1; + if (consume_dispatch_q(rq, rf, &scx_dsq_global)) + return 1; + } while (dspc->nr_tasks); + + return 0; +} + +static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first) +{ + if (p->scx.flags & SCX_TASK_QUEUED) { + WARN_ON_ONCE(atomic_long_read(&p->scx.ops_state) != SCX_OPSS_NONE); + dispatch_dequeue(rq, p); + } + + p->se.exec_start = rq_clock_task(rq); + + clr_task_runnable(p); +} + +static void put_prev_task_scx(struct rq *rq, struct task_struct *p) +{ +#ifndef CONFIG_SMP + /* + * UP workaround. + * + * Because SCX may transfer tasks across CPUs during dispatch, dispatch + * is performed from its balance operation which isn't called in UP. + * Let's work around by calling it from the operations which come right + * after. + * + * 1. If the prev task is on SCX, pick_next_task() calls + * .put_prev_task() right after. As .put_prev_task() is also called + * from other places, we need to distinguish the calls which can be + * done by looking at the previous task's state - if still queued or + * dequeued with %SCX_DEQ_SLEEP, the caller must be pick_next_task(). + * This case is handled here. + * + * 2. If the prev task is not on SCX, the first following call into SCX + * will be .pick_next_task(), which is covered by calling + * balance_scx() from pick_next_task_scx(). + * + * Note that we can't merge the first case into the second as + * balance_scx() must be called before the previous SCX task goes + * through put_prev_task_scx(). + * + * As UP doesn't transfer tasks around, balance_scx() doesn't need @rf. + * Pass in %NULL. + */ + if (p->scx.flags & (SCX_TASK_QUEUED | SCX_TASK_DEQD_FOR_SLEEP)) + balance_scx(rq, p, NULL); +#endif + + update_curr_scx(rq); + + /* + * If we're being called from put_prev_task_balance(), balance_scx() may + * have decided that @p should keep running. + */ + if (p->scx.flags & SCX_TASK_BAL_KEEP) { + p->scx.flags &= ~SCX_TASK_BAL_KEEP; + set_task_runnable(rq, p); + dispatch_enqueue(&rq->scx.local_dsq, p, SCX_ENQ_HEAD); + return; + } + + if (p->scx.flags & SCX_TASK_QUEUED) { + set_task_runnable(rq, p); + + /* + * If @p has slice left and balance_scx() didn't tag it for + * keeping, @p is getting preempted by a higher priority + * scheduler class. Leave it at the head of the local DSQ. + */ + if (p->scx.slice && !scx_ops_bypassing()) { + dispatch_enqueue(&rq->scx.local_dsq, p, SCX_ENQ_HEAD); + return; + } + + /* + * If we're in the pick_next_task path, balance_scx() should + * have already populated the local DSQ if there are any other + * available tasks. If empty, tell ops.enqueue() that @p is the + * only one available for this cpu. ops.enqueue() should put it + * on the local DSQ so that the subsequent pick_next_task_scx() + * can find the task unless it wants to trigger a separate + * follow-up scheduling event. + */ + if (list_empty(&rq->scx.local_dsq.list)) + do_enqueue_task(rq, p, SCX_ENQ_LAST, -1); + else + do_enqueue_task(rq, p, 0, -1); + } +} + +static struct task_struct *first_local_task(struct rq *rq) +{ + return list_first_entry_or_null(&rq->scx.local_dsq.list, + struct task_struct, scx.dsq_node); +} + +static struct task_struct *pick_next_task_scx(struct rq *rq) +{ + struct task_struct *p; + +#ifndef CONFIG_SMP + /* UP workaround - see the comment at the head of put_prev_task_scx() */ + if (unlikely(rq->curr->sched_class != &ext_sched_class)) + balance_scx(rq, rq->curr, NULL); +#endif + + p = first_local_task(rq); + if (!p) + return NULL; + + set_next_task_scx(rq, p, true); + + if (unlikely(!p->scx.slice)) { + if (!scx_ops_bypassing() && !scx_warned_zero_slice) { + printk_deferred(KERN_WARNING "sched_ext: %s[%d] has zero slice in pick_next_task_scx()\n", + p->comm, p->pid); + scx_warned_zero_slice = true; + } + p->scx.slice = SCX_SLICE_DFL; + } + + return p; +} + +#ifdef CONFIG_SMP + +static bool test_and_clear_cpu_idle(int cpu) +{ +#ifdef CONFIG_SCHED_SMT + /* + * SMT mask should be cleared whether we can claim @cpu or not. The SMT + * cluster is not wholly idle either way. This also prevents + * scx_pick_idle_cpu() from getting caught in an infinite loop. + */ + if (sched_smt_active()) { + const struct cpumask *smt = cpu_smt_mask(cpu); + + /* + * If offline, @cpu is not its own sibling and + * scx_pick_idle_cpu() can get caught in an infinite loop as + * @cpu is never cleared from idle_masks.smt. Ensure that @cpu + * is eventually cleared. + */ + if (cpumask_intersects(smt, idle_masks.smt)) + cpumask_andnot(idle_masks.smt, idle_masks.smt, smt); + else if (cpumask_test_cpu(cpu, idle_masks.smt)) + __cpumask_clear_cpu(cpu, idle_masks.smt); + } +#endif + return cpumask_test_and_clear_cpu(cpu, idle_masks.cpu); +} + +static s32 scx_pick_idle_cpu(const struct cpumask *cpus_allowed, u64 flags) +{ + int cpu; + +retry: + if (sched_smt_active()) { + cpu = cpumask_any_and_distribute(idle_masks.smt, cpus_allowed); + if (cpu < nr_cpu_ids) + goto found; + + if (flags & SCX_PICK_IDLE_CORE) + return -EBUSY; + } + + cpu = cpumask_any_and_distribute(idle_masks.cpu, cpus_allowed); + if (cpu >= nr_cpu_ids) + return -EBUSY; + +found: + if (test_and_clear_cpu_idle(cpu)) + return cpu; + else + goto retry; +} + +static s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, + u64 wake_flags, bool *found) +{ + s32 cpu; + + *found = false; + + if (!static_branch_likely(&scx_builtin_idle_enabled)) { + scx_ops_error("built-in idle tracking is disabled"); + return prev_cpu; + } + + /* + * If WAKE_SYNC, the waker's local DSQ is empty, and the system is + * under utilized, wake up @p to the local DSQ of the waker. Checking + * only for an empty local DSQ is insufficient as it could give the + * wakee an unfair advantage when the system is oversaturated. + * Checking only for the presence of idle CPUs is also insufficient as + * the local DSQ of the waker could have tasks piled up on it even if + * there is an idle core elsewhere on the system. + */ + cpu = smp_processor_id(); + if ((wake_flags & SCX_WAKE_SYNC) && p->nr_cpus_allowed > 1 && + !cpumask_empty(idle_masks.cpu) && !(current->flags & PF_EXITING) && + cpu_rq(cpu)->scx.local_dsq.nr == 0) { + if (cpumask_test_cpu(cpu, p->cpus_ptr)) + goto cpu_found; + } + + if (p->nr_cpus_allowed == 1) { + if (test_and_clear_cpu_idle(prev_cpu)) { + cpu = prev_cpu; + goto cpu_found; + } else { + return prev_cpu; + } + } + + /* + * If CPU has SMT, any wholly idle CPU is likely a better pick than + * partially idle @prev_cpu. + */ + if (sched_smt_active()) { + if (cpumask_test_cpu(prev_cpu, idle_masks.smt) && + test_and_clear_cpu_idle(prev_cpu)) { + cpu = prev_cpu; + goto cpu_found; + } + + cpu = scx_pick_idle_cpu(p->cpus_ptr, SCX_PICK_IDLE_CORE); + if (cpu >= 0) + goto cpu_found; + } + + if (test_and_clear_cpu_idle(prev_cpu)) { + cpu = prev_cpu; + goto cpu_found; + } + + cpu = scx_pick_idle_cpu(p->cpus_ptr, 0); + if (cpu >= 0) + goto cpu_found; + + return prev_cpu; + +cpu_found: + *found = true; + return cpu; +} + +static int select_task_rq_scx(struct task_struct *p, int prev_cpu, int wake_flags) +{ + /* + * sched_exec() calls with %WF_EXEC when @p is about to exec(2) as it + * can be a good migration opportunity with low cache and memory + * footprint. Returning a CPU different than @prev_cpu triggers + * immediate rq migration. However, for SCX, as the current rq + * association doesn't dictate where the task is going to run, this + * doesn't fit well. If necessary, we can later add a dedicated method + * which can decide to preempt self to force it through the regular + * scheduling path. + */ + if (unlikely(wake_flags & WF_EXEC)) + return prev_cpu; + + if (SCX_HAS_OP(select_cpu)) { + s32 cpu; + struct task_struct **ddsp_taskp; + + ddsp_taskp = this_cpu_ptr(&direct_dispatch_task); + WARN_ON_ONCE(*ddsp_taskp); + *ddsp_taskp = p; + + cpu = SCX_CALL_OP_RET(SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU, + select_cpu, p, prev_cpu, wake_flags); + *ddsp_taskp = NULL; + if (ops_cpu_valid(cpu, "from ops.select_cpu()")) + return cpu; + else + return prev_cpu; + } else { + bool found; + s32 cpu; + + cpu = scx_select_cpu_dfl(p, prev_cpu, wake_flags, &found); + if (found) { + p->scx.slice = SCX_SLICE_DFL; + p->scx.ddsp_dsq_id = SCX_DSQ_LOCAL; + } + return cpu; + } +} + +static void set_cpus_allowed_scx(struct task_struct *p, + struct affinity_context *ac) +{ + set_cpus_allowed_common(p, ac); + + /* + * The effective cpumask is stored in @p->cpus_ptr which may temporarily + * differ from the configured one in @p->cpus_mask. Always tell the bpf + * scheduler the effective one. + * + * Fine-grained memory write control is enforced by BPF making the const + * designation pointless. Cast it away when calling the operation. + */ + if (SCX_HAS_OP(set_cpumask)) + SCX_CALL_OP(SCX_KF_REST, set_cpumask, p, + (struct cpumask *)p->cpus_ptr); +} + +static void reset_idle_masks(void) +{ + /* + * Consider all online cpus idle. Should converge to the actual state + * quickly. + */ + cpumask_copy(idle_masks.cpu, cpu_online_mask); + cpumask_copy(idle_masks.smt, cpu_online_mask); +} + +void __scx_update_idle(struct rq *rq, bool idle) +{ + int cpu = cpu_of(rq); + + if (SCX_HAS_OP(update_idle)) { + SCX_CALL_OP(SCX_KF_REST, update_idle, cpu_of(rq), idle); + if (!static_branch_unlikely(&scx_builtin_idle_enabled)) + return; + } + + if (idle) + cpumask_set_cpu(cpu, idle_masks.cpu); + else + cpumask_clear_cpu(cpu, idle_masks.cpu); + +#ifdef CONFIG_SCHED_SMT + if (sched_smt_active()) { + const struct cpumask *smt = cpu_smt_mask(cpu); + + if (idle) { + /* + * idle_masks.smt handling is racy but that's fine as + * it's only for optimization and self-correcting. + */ + for_each_cpu(cpu, smt) { + if (!cpumask_test_cpu(cpu, idle_masks.cpu)) + return; + } + cpumask_or(idle_masks.smt, idle_masks.smt, smt); + } else { + cpumask_andnot(idle_masks.smt, idle_masks.smt, smt); + } + } +#endif +} + +#else /* CONFIG_SMP */ + +static bool test_and_clear_cpu_idle(int cpu) { return false; } +static s32 scx_pick_idle_cpu(const struct cpumask *cpus_allowed, u64 flags) { return -EBUSY; } +static void reset_idle_masks(void) {} + +#endif /* CONFIG_SMP */ + +static void task_tick_scx(struct rq *rq, struct task_struct *curr, int queued) +{ + update_other_load_avgs(rq); + update_curr_scx(rq); + + /* + * While bypassing, always resched as we can't trust the slice + * management. + */ + if (scx_ops_bypassing()) + curr->scx.slice = 0; + else if (SCX_HAS_OP(tick)) + SCX_CALL_OP(SCX_KF_REST, tick, curr); + + if (!curr->scx.slice) + resched_curr(rq); +} + +static enum scx_task_state scx_get_task_state(const struct task_struct *p) +{ + return (p->scx.flags & SCX_TASK_STATE_MASK) >> SCX_TASK_STATE_SHIFT; +} + +static void scx_set_task_state(struct task_struct *p, enum scx_task_state state) +{ + enum scx_task_state prev_state = scx_get_task_state(p); + bool warn = false; + + BUILD_BUG_ON(SCX_TASK_NR_STATES > (1 << SCX_TASK_STATE_BITS)); + + switch (state) { + case SCX_TASK_NONE: + break; + case SCX_TASK_INIT: + warn = prev_state != SCX_TASK_NONE; + break; + case SCX_TASK_READY: + warn = prev_state == SCX_TASK_NONE; + break; + case SCX_TASK_ENABLED: + warn = prev_state != SCX_TASK_READY; + break; + default: + warn = true; + return; + } + + WARN_ONCE(warn, "sched_ext: Invalid task state transition %d -> %d for %s[%d]", + prev_state, state, p->comm, p->pid); + + p->scx.flags &= ~SCX_TASK_STATE_MASK; + p->scx.flags |= state << SCX_TASK_STATE_SHIFT; +} + +static int scx_ops_init_task(struct task_struct *p, struct task_group *tg, bool fork) +{ + int ret; + + if (SCX_HAS_OP(init_task)) { + struct scx_init_task_args args = { + .fork = fork, + }; + + ret = SCX_CALL_OP_RET(SCX_KF_SLEEPABLE, init_task, p, &args); + if (unlikely(ret)) { + ret = ops_sanitize_err("init_task", ret); + return ret; + } + } + + scx_set_task_state(p, SCX_TASK_INIT); + + return 0; +} + +static void set_task_scx_weight(struct task_struct *p) +{ + u32 weight = sched_prio_to_weight[p->static_prio - MAX_RT_PRIO]; + + p->scx.weight = sched_weight_to_cgroup(weight); +} + +static void scx_ops_enable_task(struct task_struct *p) +{ + lockdep_assert_rq_held(task_rq(p)); + + /* + * Set the weight before calling ops.enable() so that the scheduler + * doesn't see a stale value if they inspect the task struct. + */ + set_task_scx_weight(p); + if (SCX_HAS_OP(enable)) + SCX_CALL_OP(SCX_KF_REST, enable, p); + scx_set_task_state(p, SCX_TASK_ENABLED); + + if (SCX_HAS_OP(set_weight)) + SCX_CALL_OP(SCX_KF_REST, set_weight, p, p->scx.weight); +} + +static void scx_ops_disable_task(struct task_struct *p) +{ + lockdep_assert_rq_held(task_rq(p)); + WARN_ON_ONCE(scx_get_task_state(p) != SCX_TASK_ENABLED); + + if (SCX_HAS_OP(disable)) + SCX_CALL_OP(SCX_KF_REST, disable, p); + scx_set_task_state(p, SCX_TASK_READY); +} + +static void scx_ops_exit_task(struct task_struct *p) +{ + struct scx_exit_task_args args = { + .cancelled = false, + }; + + lockdep_assert_rq_held(task_rq(p)); + + switch (scx_get_task_state(p)) { + case SCX_TASK_NONE: + return; + case SCX_TASK_INIT: + args.cancelled = true; + break; + case SCX_TASK_READY: + break; + case SCX_TASK_ENABLED: + scx_ops_disable_task(p); + break; + default: + WARN_ON_ONCE(true); + return; + } + + if (SCX_HAS_OP(exit_task)) + SCX_CALL_OP(SCX_KF_REST, exit_task, p, &args); + scx_set_task_state(p, SCX_TASK_NONE); +} + +void init_scx_entity(struct sched_ext_entity *scx) +{ + /* + * init_idle() calls this function again after fork sequence is + * complete. Don't touch ->tasks_node as it's already linked. + */ + memset(scx, 0, offsetof(struct sched_ext_entity, tasks_node)); + + INIT_LIST_HEAD(&scx->dsq_node); + scx->sticky_cpu = -1; + scx->holding_cpu = -1; + INIT_LIST_HEAD(&scx->runnable_node); + scx->ddsp_dsq_id = SCX_DSQ_INVALID; + scx->slice = SCX_SLICE_DFL; +} + +void scx_pre_fork(struct task_struct *p) +{ + /* + * BPF scheduler enable/disable paths want to be able to iterate and + * update all tasks which can become complex when racing forks. As + * enable/disable are very cold paths, let's use a percpu_rwsem to + * exclude forks. + */ + percpu_down_read(&scx_fork_rwsem); +} + +int scx_fork(struct task_struct *p) +{ + percpu_rwsem_assert_held(&scx_fork_rwsem); + + if (scx_enabled()) + return scx_ops_init_task(p, task_group(p), true); + else + return 0; +} + +void scx_post_fork(struct task_struct *p) +{ + if (scx_enabled()) { + scx_set_task_state(p, SCX_TASK_READY); + + /* + * Enable the task immediately if it's running on sched_ext. + * Otherwise, it'll be enabled in switching_to_scx() if and + * when it's ever configured to run with a SCHED_EXT policy. + */ + if (p->sched_class == &ext_sched_class) { + struct rq_flags rf; + struct rq *rq; + + rq = task_rq_lock(p, &rf); + scx_ops_enable_task(p); + task_rq_unlock(rq, p, &rf); + } + } + + spin_lock_irq(&scx_tasks_lock); + list_add_tail(&p->scx.tasks_node, &scx_tasks); + spin_unlock_irq(&scx_tasks_lock); + + percpu_up_read(&scx_fork_rwsem); +} + +void scx_cancel_fork(struct task_struct *p) +{ + if (scx_enabled()) { + struct rq *rq; + struct rq_flags rf; + + rq = task_rq_lock(p, &rf); + WARN_ON_ONCE(scx_get_task_state(p) >= SCX_TASK_READY); + scx_ops_exit_task(p); + task_rq_unlock(rq, p, &rf); + } + + percpu_up_read(&scx_fork_rwsem); +} + +void sched_ext_free(struct task_struct *p) +{ + unsigned long flags; + + spin_lock_irqsave(&scx_tasks_lock, flags); + list_del_init(&p->scx.tasks_node); + spin_unlock_irqrestore(&scx_tasks_lock, flags); + + /* + * @p is off scx_tasks and wholly ours. scx_ops_enable()'s READY -> + * ENABLED transitions can't race us. Disable ops for @p. + */ + if (scx_get_task_state(p) != SCX_TASK_NONE) { + struct rq_flags rf; + struct rq *rq; + + rq = task_rq_lock(p, &rf); + scx_ops_exit_task(p); + task_rq_unlock(rq, p, &rf); + } +} + +static void reweight_task_scx(struct rq *rq, struct task_struct *p, int newprio) +{ + lockdep_assert_rq_held(task_rq(p)); + + set_task_scx_weight(p); + if (SCX_HAS_OP(set_weight)) + SCX_CALL_OP(SCX_KF_REST, set_weight, p, p->scx.weight); +} + +static void prio_changed_scx(struct rq *rq, struct task_struct *p, int oldprio) +{ +} + +static void switching_to_scx(struct rq *rq, struct task_struct *p) +{ + scx_ops_enable_task(p); + + /* + * set_cpus_allowed_scx() is not called while @p is associated with a + * different scheduler class. Keep the BPF scheduler up-to-date. + */ + if (SCX_HAS_OP(set_cpumask)) + SCX_CALL_OP(SCX_KF_REST, set_cpumask, p, + (struct cpumask *)p->cpus_ptr); +} + +static void switched_from_scx(struct rq *rq, struct task_struct *p) +{ + scx_ops_disable_task(p); +} + +static void wakeup_preempt_scx(struct rq *rq, struct task_struct *p,int wake_flags) {} +static void switched_to_scx(struct rq *rq, struct task_struct *p) {} + +/* + * Omitted operations: + * + * - wakeup_preempt: NOOP as it isn't useful in the wakeup path because the task + * isn't tied to the CPU at that point. + * + * - migrate_task_rq: Unnecessary as task to cpu mapping is transient. + * + * - task_fork/dead: We need fork/dead notifications for all tasks regardless of + * their current sched_class. Call them directly from sched core instead. + * + * - task_woken: Unnecessary. + */ +DEFINE_SCHED_CLASS(ext) = { + .enqueue_task = enqueue_task_scx, + .dequeue_task = dequeue_task_scx, + .yield_task = yield_task_scx, + .yield_to_task = yield_to_task_scx, + + .wakeup_preempt = wakeup_preempt_scx, + + .pick_next_task = pick_next_task_scx, + + .put_prev_task = put_prev_task_scx, + .set_next_task = set_next_task_scx, + +#ifdef CONFIG_SMP + .balance = balance_scx, + .select_task_rq = select_task_rq_scx, + .set_cpus_allowed = set_cpus_allowed_scx, +#endif + + .task_tick = task_tick_scx, + + .switching_to = switching_to_scx, + .switched_from = switched_from_scx, + .switched_to = switched_to_scx, + .reweight_task = reweight_task_scx, + .prio_changed = prio_changed_scx, + + .update_curr = update_curr_scx, + +#ifdef CONFIG_UCLAMP_TASK + .uclamp_enabled = 0, +#endif +}; + +static void init_dsq(struct scx_dispatch_q *dsq, u64 dsq_id) +{ + memset(dsq, 0, sizeof(*dsq)); + + raw_spin_lock_init(&dsq->lock); + INIT_LIST_HEAD(&dsq->list); + dsq->id = dsq_id; +} + +static struct scx_dispatch_q *create_dsq(u64 dsq_id, int node) +{ + struct scx_dispatch_q *dsq; + int ret; + + if (dsq_id & SCX_DSQ_FLAG_BUILTIN) + return ERR_PTR(-EINVAL); + + dsq = kmalloc_node(sizeof(*dsq), GFP_KERNEL, node); + if (!dsq) + return ERR_PTR(-ENOMEM); + + init_dsq(dsq, dsq_id); + + ret = rhashtable_insert_fast(&dsq_hash, &dsq->hash_node, + dsq_hash_params); + if (ret) { + kfree(dsq); + return ERR_PTR(ret); + } + return dsq; +} + +static void free_dsq_irq_workfn(struct irq_work *irq_work) +{ + struct llist_node *to_free = llist_del_all(&dsqs_to_free); + struct scx_dispatch_q *dsq, *tmp_dsq; + + llist_for_each_entry_safe(dsq, tmp_dsq, to_free, free_node) + kfree_rcu(dsq, rcu); +} + +static DEFINE_IRQ_WORK(free_dsq_irq_work, free_dsq_irq_workfn); + +static void destroy_dsq(u64 dsq_id) +{ + struct scx_dispatch_q *dsq; + unsigned long flags; + + rcu_read_lock(); + + dsq = find_user_dsq(dsq_id); + if (!dsq) + goto out_unlock_rcu; + + raw_spin_lock_irqsave(&dsq->lock, flags); + + if (dsq->nr) { + scx_ops_error("attempting to destroy in-use dsq 0x%016llx (nr=%u)", + dsq->id, dsq->nr); + goto out_unlock_dsq; + } + + if (rhashtable_remove_fast(&dsq_hash, &dsq->hash_node, dsq_hash_params)) + goto out_unlock_dsq; + + /* + * Mark dead by invalidating ->id to prevent dispatch_enqueue() from + * queueing more tasks. As this function can be called from anywhere, + * freeing is bounced through an irq work to avoid nesting RCU + * operations inside scheduler locks. + */ + dsq->id = SCX_DSQ_INVALID; + llist_add(&dsq->free_node, &dsqs_to_free); + irq_work_queue(&free_dsq_irq_work); + +out_unlock_dsq: + raw_spin_unlock_irqrestore(&dsq->lock, flags); +out_unlock_rcu: + rcu_read_unlock(); +} + + +/******************************************************************************** + * Sysfs interface and ops enable/disable. + */ + +#define SCX_ATTR(_name) \ + static struct kobj_attribute scx_attr_##_name = { \ + .attr = { .name = __stringify(_name), .mode = 0444 }, \ + .show = scx_attr_##_name##_show, \ + } + +static ssize_t scx_attr_state_show(struct kobject *kobj, + struct kobj_attribute *ka, char *buf) +{ + return sysfs_emit(buf, "%s\n", + scx_ops_enable_state_str[scx_ops_enable_state()]); +} +SCX_ATTR(state); + +static ssize_t scx_attr_switch_all_show(struct kobject *kobj, + struct kobj_attribute *ka, char *buf) +{ + return sysfs_emit(buf, "%d\n", READ_ONCE(scx_switching_all)); +} +SCX_ATTR(switch_all); + +static struct attribute *scx_global_attrs[] = { + &scx_attr_state.attr, + &scx_attr_switch_all.attr, + NULL, +}; + +static const struct attribute_group scx_global_attr_group = { + .attrs = scx_global_attrs, +}; + +static void scx_kobj_release(struct kobject *kobj) +{ + kfree(kobj); +} + +static ssize_t scx_attr_ops_show(struct kobject *kobj, + struct kobj_attribute *ka, char *buf) +{ + return sysfs_emit(buf, "%s\n", scx_ops.name); +} +SCX_ATTR(ops); + +static struct attribute *scx_sched_attrs[] = { + &scx_attr_ops.attr, + NULL, +}; +ATTRIBUTE_GROUPS(scx_sched); + +static const struct kobj_type scx_ktype = { + .release = scx_kobj_release, + .sysfs_ops = &kobj_sysfs_ops, + .default_groups = scx_sched_groups, +}; + +static int scx_uevent(const struct kobject *kobj, struct kobj_uevent_env *env) +{ + return add_uevent_var(env, "SCXOPS=%s", scx_ops.name); +} + +static const struct kset_uevent_ops scx_uevent_ops = { + .uevent = scx_uevent, +}; + +/* + * Used by sched_fork() and __setscheduler_prio() to pick the matching + * sched_class. dl/rt are already handled. + */ +bool task_should_scx(struct task_struct *p) +{ + if (!scx_enabled() || + unlikely(scx_ops_enable_state() == SCX_OPS_DISABLING)) + return false; + if (READ_ONCE(scx_switching_all)) + return true; + return p->policy == SCHED_EXT; +} + +/** + * scx_ops_bypass - [Un]bypass scx_ops and guarantee forward progress + * + * Bypassing guarantees that all runnable tasks make forward progress without + * trusting the BPF scheduler. We can't grab any mutexes or rwsems as they might + * be held by tasks that the BPF scheduler is forgetting to run, which + * unfortunately also excludes toggling the static branches. + * + * Let's work around by overriding a couple ops and modifying behaviors based on + * the DISABLING state and then cycling the queued tasks through dequeue/enqueue + * to force global FIFO scheduling. + * + * a. ops.enqueue() is ignored and tasks are queued in simple global FIFO order. + * + * b. ops.dispatch() is ignored. + * + * c. balance_scx() never sets %SCX_TASK_BAL_KEEP as the slice value can't be + * trusted. Whenever a tick triggers, the running task is rotated to the tail + * of the queue. + * + * d. pick_next_task() suppresses zero slice warning. + */ +static void scx_ops_bypass(bool bypass) +{ + int depth, cpu; + + if (bypass) { + depth = atomic_inc_return(&scx_ops_bypass_depth); + WARN_ON_ONCE(depth <= 0); + if (depth != 1) + return; + } else { + depth = atomic_dec_return(&scx_ops_bypass_depth); + WARN_ON_ONCE(depth < 0); + if (depth != 0) + return; + } + + /* + * We need to guarantee that no tasks are on the BPF scheduler while + * bypassing. Either we see enabled or the enable path sees the + * increased bypass_depth before moving tasks to SCX. + */ + if (!scx_enabled()) + return; + + /* + * No task property is changing. We just need to make sure all currently + * queued tasks are re-queued according to the new scx_ops_bypassing() + * state. As an optimization, walk each rq's runnable_list instead of + * the scx_tasks list. + * + * This function can't trust the scheduler and thus can't use + * cpus_read_lock(). Walk all possible CPUs instead of online. + */ + for_each_possible_cpu(cpu) { + struct rq *rq = cpu_rq(cpu); + struct rq_flags rf; + struct task_struct *p, *n; + + rq_lock_irqsave(rq, &rf); + + /* + * The use of list_for_each_entry_safe_reverse() is required + * because each task is going to be removed from and added back + * to the runnable_list during iteration. Because they're added + * to the tail of the list, safe reverse iteration can still + * visit all nodes. + */ + list_for_each_entry_safe_reverse(p, n, &rq->scx.runnable_list, + scx.runnable_node) { + struct sched_enq_and_set_ctx ctx; + + /* cycling deq/enq is enough, see the function comment */ + sched_deq_and_put_task(p, DEQUEUE_SAVE | DEQUEUE_MOVE, &ctx); + sched_enq_and_set_task(&ctx); + } + + rq_unlock_irqrestore(rq, &rf); + } +} + +static void free_exit_info(struct scx_exit_info *ei) +{ + kfree(ei->msg); + kfree(ei->bt); + kfree(ei); +} + +static struct scx_exit_info *alloc_exit_info(void) +{ + struct scx_exit_info *ei; + + ei = kzalloc(sizeof(*ei), GFP_KERNEL); + if (!ei) + return NULL; + + ei->bt = kcalloc(sizeof(ei->bt[0]), SCX_EXIT_BT_LEN, GFP_KERNEL); + ei->msg = kzalloc(SCX_EXIT_MSG_LEN, GFP_KERNEL); + + if (!ei->bt || !ei->msg) { + free_exit_info(ei); + return NULL; + } + + return ei; +} + +static const char *scx_exit_reason(enum scx_exit_kind kind) +{ + switch (kind) { + case SCX_EXIT_UNREG: + return "Scheduler unregistered from user space"; + case SCX_EXIT_UNREG_BPF: + return "Scheduler unregistered from BPF"; + case SCX_EXIT_UNREG_KERN: + return "Scheduler unregistered from the main kernel"; + case SCX_EXIT_ERROR: + return "runtime error"; + case SCX_EXIT_ERROR_BPF: + return "scx_bpf_error"; + default: + return ""; + } +} + +static void scx_ops_disable_workfn(struct kthread_work *work) +{ + struct scx_exit_info *ei = scx_exit_info; + struct scx_task_iter sti; + struct task_struct *p; + struct rhashtable_iter rht_iter; + struct scx_dispatch_q *dsq; + int i, kind; + + kind = atomic_read(&scx_exit_kind); + while (true) { + /* + * NONE indicates that a new scx_ops has been registered since + * disable was scheduled - don't kill the new ops. DONE + * indicates that the ops has already been disabled. + */ + if (kind == SCX_EXIT_NONE || kind == SCX_EXIT_DONE) + return; + if (atomic_try_cmpxchg(&scx_exit_kind, &kind, SCX_EXIT_DONE)) + break; + } + ei->kind = kind; + ei->reason = scx_exit_reason(ei->kind); + + /* guarantee forward progress by bypassing scx_ops */ + scx_ops_bypass(true); + + switch (scx_ops_set_enable_state(SCX_OPS_DISABLING)) { + case SCX_OPS_DISABLING: + WARN_ONCE(true, "sched_ext: duplicate disabling instance?"); + break; + case SCX_OPS_DISABLED: + pr_warn("sched_ext: ops error detected without ops (%s)\n", + scx_exit_info->msg); + WARN_ON_ONCE(scx_ops_set_enable_state(SCX_OPS_DISABLED) != + SCX_OPS_DISABLING); + goto done; + default: + break; + } + + /* + * Here, every runnable task is guaranteed to make forward progress and + * we can safely use blocking synchronization constructs. Actually + * disable ops. + */ + mutex_lock(&scx_ops_enable_mutex); + + static_branch_disable(&__scx_switched_all); + WRITE_ONCE(scx_switching_all, false); + + /* + * Avoid racing against fork. See scx_ops_enable() for explanation on + * the locking order. + */ + percpu_down_write(&scx_fork_rwsem); + cpus_read_lock(); + + spin_lock_irq(&scx_tasks_lock); + scx_task_iter_init(&sti); + /* + * Invoke scx_ops_exit_task() on all non-idle tasks, including + * TASK_DEAD tasks. Because dead tasks may have a nonzero refcount, + * we may not have invoked sched_ext_free() on them by the time a + * scheduler is disabled. We must therefore exit the task here, or we'd + * fail to invoke ops.exit_task(), as the scheduler will have been + * unloaded by the time the task is subsequently exited on the + * sched_ext_free() path. + */ + while ((p = scx_task_iter_next_locked(&sti, true))) { + const struct sched_class *old_class = p->sched_class; + struct sched_enq_and_set_ctx ctx; + + if (READ_ONCE(p->__state) != TASK_DEAD) { + sched_deq_and_put_task(p, DEQUEUE_SAVE | DEQUEUE_MOVE, + &ctx); + + p->scx.slice = min_t(u64, p->scx.slice, SCX_SLICE_DFL); + __setscheduler_prio(p, p->prio); + check_class_changing(task_rq(p), p, old_class); + + sched_enq_and_set_task(&ctx); + + check_class_changed(task_rq(p), p, old_class, p->prio); + } + scx_ops_exit_task(p); + } + scx_task_iter_exit(&sti); + spin_unlock_irq(&scx_tasks_lock); + + /* no task is on scx, turn off all the switches and flush in-progress calls */ + static_branch_disable_cpuslocked(&__scx_ops_enabled); + for (i = SCX_OPI_BEGIN; i < SCX_OPI_END; i++) + static_branch_disable_cpuslocked(&scx_has_op[i]); + static_branch_disable_cpuslocked(&scx_ops_enq_last); + static_branch_disable_cpuslocked(&scx_ops_enq_exiting); + static_branch_disable_cpuslocked(&scx_builtin_idle_enabled); + synchronize_rcu(); + + cpus_read_unlock(); + percpu_up_write(&scx_fork_rwsem); + + if (ei->kind >= SCX_EXIT_ERROR) { + printk(KERN_ERR "sched_ext: BPF scheduler \"%s\" errored, disabling\n", scx_ops.name); + + if (ei->msg[0] == '\0') + printk(KERN_ERR "sched_ext: %s\n", ei->reason); + else + printk(KERN_ERR "sched_ext: %s (%s)\n", ei->reason, ei->msg); + + stack_trace_print(ei->bt, ei->bt_len, 2); + } + + if (scx_ops.exit) + SCX_CALL_OP(SCX_KF_UNLOCKED, exit, ei); + + /* + * Delete the kobject from the hierarchy eagerly in addition to just + * dropping a reference. Otherwise, if the object is deleted + * asynchronously, sysfs could observe an object of the same name still + * in the hierarchy when another scheduler is loaded. + */ + kobject_del(scx_root_kobj); + kobject_put(scx_root_kobj); + scx_root_kobj = NULL; + + memset(&scx_ops, 0, sizeof(scx_ops)); + + rhashtable_walk_enter(&dsq_hash, &rht_iter); + do { + rhashtable_walk_start(&rht_iter); + + while ((dsq = rhashtable_walk_next(&rht_iter)) && !IS_ERR(dsq)) + destroy_dsq(dsq->id); + + rhashtable_walk_stop(&rht_iter); + } while (dsq == ERR_PTR(-EAGAIN)); + rhashtable_walk_exit(&rht_iter); + + free_percpu(scx_dsp_ctx); + scx_dsp_ctx = NULL; + scx_dsp_max_batch = 0; + + free_exit_info(scx_exit_info); + scx_exit_info = NULL; + + mutex_unlock(&scx_ops_enable_mutex); + + WARN_ON_ONCE(scx_ops_set_enable_state(SCX_OPS_DISABLED) != + SCX_OPS_DISABLING); +done: + scx_ops_bypass(false); +} + +static DEFINE_KTHREAD_WORK(scx_ops_disable_work, scx_ops_disable_workfn); + +static void schedule_scx_ops_disable_work(void) +{ + struct kthread_worker *helper = READ_ONCE(scx_ops_helper); + + /* + * We may be called spuriously before the first bpf_sched_ext_reg(). If + * scx_ops_helper isn't set up yet, there's nothing to do. + */ + if (helper) + kthread_queue_work(helper, &scx_ops_disable_work); +} + +static void scx_ops_disable(enum scx_exit_kind kind) +{ + int none = SCX_EXIT_NONE; + + if (WARN_ON_ONCE(kind == SCX_EXIT_NONE || kind == SCX_EXIT_DONE)) + kind = SCX_EXIT_ERROR; + + atomic_try_cmpxchg(&scx_exit_kind, &none, kind); + + schedule_scx_ops_disable_work(); +} + +static void scx_ops_error_irq_workfn(struct irq_work *irq_work) +{ + schedule_scx_ops_disable_work(); +} + +static DEFINE_IRQ_WORK(scx_ops_error_irq_work, scx_ops_error_irq_workfn); + +static __printf(3, 4) void scx_ops_exit_kind(enum scx_exit_kind kind, + s64 exit_code, + const char *fmt, ...) +{ + struct scx_exit_info *ei = scx_exit_info; + int none = SCX_EXIT_NONE; + va_list args; + + if (!atomic_try_cmpxchg(&scx_exit_kind, &none, kind)) + return; + + ei->exit_code = exit_code; + + if (kind >= SCX_EXIT_ERROR) + ei->bt_len = stack_trace_save(ei->bt, SCX_EXIT_BT_LEN, 1); + + va_start(args, fmt); + vscnprintf(ei->msg, SCX_EXIT_MSG_LEN, fmt, args); + va_end(args); + + irq_work_queue(&scx_ops_error_irq_work); +} + +static struct kthread_worker *scx_create_rt_helper(const char *name) +{ + struct kthread_worker *helper; + + helper = kthread_create_worker(0, name); + if (helper) + sched_set_fifo(helper->task); + return helper; +} + +static int validate_ops(const struct sched_ext_ops *ops) +{ + /* + * It doesn't make sense to specify the SCX_OPS_ENQ_LAST flag if the + * ops.enqueue() callback isn't implemented. + */ + if ((ops->flags & SCX_OPS_ENQ_LAST) && !ops->enqueue) { + scx_ops_error("SCX_OPS_ENQ_LAST requires ops.enqueue() to be implemented"); + return -EINVAL; + } + + return 0; +} + +static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) +{ + struct scx_task_iter sti; + struct task_struct *p; + int i, ret; + + mutex_lock(&scx_ops_enable_mutex); + + if (!scx_ops_helper) { + WRITE_ONCE(scx_ops_helper, + scx_create_rt_helper("sched_ext_ops_helper")); + if (!scx_ops_helper) { + ret = -ENOMEM; + goto err_unlock; + } + } + + if (scx_ops_enable_state() != SCX_OPS_DISABLED) { + ret = -EBUSY; + goto err_unlock; + } + + scx_root_kobj = kzalloc(sizeof(*scx_root_kobj), GFP_KERNEL); + if (!scx_root_kobj) { + ret = -ENOMEM; + goto err_unlock; + } + + scx_root_kobj->kset = scx_kset; + ret = kobject_init_and_add(scx_root_kobj, &scx_ktype, NULL, "root"); + if (ret < 0) + goto err; + + scx_exit_info = alloc_exit_info(); + if (!scx_exit_info) { + ret = -ENOMEM; + goto err_del; + } + + /* + * Set scx_ops, transition to PREPPING and clear exit info to arm the + * disable path. Failure triggers full disabling from here on. + */ + scx_ops = *ops; + + WARN_ON_ONCE(scx_ops_set_enable_state(SCX_OPS_PREPPING) != + SCX_OPS_DISABLED); + + atomic_set(&scx_exit_kind, SCX_EXIT_NONE); + scx_warned_zero_slice = false; + + /* + * Keep CPUs stable during enable so that the BPF scheduler can track + * online CPUs by watching ->on/offline_cpu() after ->init(). + */ + cpus_read_lock(); + + if (scx_ops.init) { + ret = SCX_CALL_OP_RET(SCX_KF_SLEEPABLE, init); + if (ret) { + ret = ops_sanitize_err("init", ret); + goto err_disable_unlock_cpus; + } + } + + cpus_read_unlock(); + + ret = validate_ops(ops); + if (ret) + goto err_disable; + + WARN_ON_ONCE(scx_dsp_ctx); + scx_dsp_max_batch = ops->dispatch_max_batch ?: SCX_DSP_DFL_MAX_BATCH; + scx_dsp_ctx = __alloc_percpu(struct_size_t(struct scx_dsp_ctx, buf, + scx_dsp_max_batch), + __alignof__(struct scx_dsp_ctx)); + if (!scx_dsp_ctx) { + ret = -ENOMEM; + goto err_disable; + } + + /* + * Lock out forks before opening the floodgate so that they don't wander + * into the operations prematurely. + * + * We don't need to keep the CPUs stable but grab cpus_read_lock() to + * ease future locking changes for cgroup suport. + * + * Note that cpu_hotplug_lock must nest inside scx_fork_rwsem due to the + * following dependency chain: + * + * scx_fork_rwsem --> pernet_ops_rwsem --> cpu_hotplug_lock + */ + percpu_down_write(&scx_fork_rwsem); + cpus_read_lock(); + + for (i = SCX_OPI_NORMAL_BEGIN; i < SCX_OPI_NORMAL_END; i++) + if (((void (**)(void))ops)[i]) + static_branch_enable_cpuslocked(&scx_has_op[i]); + + if (ops->flags & SCX_OPS_ENQ_LAST) + static_branch_enable_cpuslocked(&scx_ops_enq_last); + + if (ops->flags & SCX_OPS_ENQ_EXITING) + static_branch_enable_cpuslocked(&scx_ops_enq_exiting); + + if (!ops->update_idle || (ops->flags & SCX_OPS_KEEP_BUILTIN_IDLE)) { + reset_idle_masks(); + static_branch_enable_cpuslocked(&scx_builtin_idle_enabled); + } else { + static_branch_disable_cpuslocked(&scx_builtin_idle_enabled); + } + + static_branch_enable_cpuslocked(&__scx_ops_enabled); + + /* + * Enable ops for every task. Fork is excluded by scx_fork_rwsem + * preventing new tasks from being added. No need to exclude tasks + * leaving as sched_ext_free() can handle both prepped and enabled + * tasks. Prep all tasks first and then enable them with preemption + * disabled. + */ + spin_lock_irq(&scx_tasks_lock); + + scx_task_iter_init(&sti); + while ((p = scx_task_iter_next_locked(&sti, false))) { + get_task_struct(p); + scx_task_iter_rq_unlock(&sti); + spin_unlock_irq(&scx_tasks_lock); + + ret = scx_ops_init_task(p, task_group(p), false); + if (ret) { + put_task_struct(p); + spin_lock_irq(&scx_tasks_lock); + scx_task_iter_exit(&sti); + spin_unlock_irq(&scx_tasks_lock); + pr_err("sched_ext: ops.init_task() failed (%d) for %s[%d] while loading\n", + ret, p->comm, p->pid); + goto err_disable_unlock_all; + } + + put_task_struct(p); + spin_lock_irq(&scx_tasks_lock); + } + scx_task_iter_exit(&sti); + + /* + * All tasks are prepped but are still ops-disabled. Ensure that + * %current can't be scheduled out and switch everyone. + * preempt_disable() is necessary because we can't guarantee that + * %current won't be starved if scheduled out while switching. + */ + preempt_disable(); + + /* + * From here on, the disable path must assume that tasks have ops + * enabled and need to be recovered. + * + * Transition to ENABLING fails iff the BPF scheduler has already + * triggered scx_bpf_error(). Returning an error code here would lose + * the recorded error information. Exit indicating success so that the + * error is notified through ops.exit() with all the details. + */ + if (!scx_ops_tryset_enable_state(SCX_OPS_ENABLING, SCX_OPS_PREPPING)) { + preempt_enable(); + spin_unlock_irq(&scx_tasks_lock); + WARN_ON_ONCE(atomic_read(&scx_exit_kind) == SCX_EXIT_NONE); + ret = 0; + goto err_disable_unlock_all; + } + + /* + * We're fully committed and can't fail. The PREPPED -> ENABLED + * transitions here are synchronized against sched_ext_free() through + * scx_tasks_lock. + */ + WRITE_ONCE(scx_switching_all, !(ops->flags & SCX_OPS_SWITCH_PARTIAL)); + + scx_task_iter_init(&sti); + while ((p = scx_task_iter_next_locked(&sti, false))) { + const struct sched_class *old_class = p->sched_class; + struct sched_enq_and_set_ctx ctx; + + sched_deq_and_put_task(p, DEQUEUE_SAVE | DEQUEUE_MOVE, &ctx); + + scx_set_task_state(p, SCX_TASK_READY); + __setscheduler_prio(p, p->prio); + check_class_changing(task_rq(p), p, old_class); + + sched_enq_and_set_task(&ctx); + + check_class_changed(task_rq(p), p, old_class, p->prio); + } + scx_task_iter_exit(&sti); + + spin_unlock_irq(&scx_tasks_lock); + preempt_enable(); + cpus_read_unlock(); + percpu_up_write(&scx_fork_rwsem); + + /* see above ENABLING transition for the explanation on exiting with 0 */ + if (!scx_ops_tryset_enable_state(SCX_OPS_ENABLED, SCX_OPS_ENABLING)) { + WARN_ON_ONCE(atomic_read(&scx_exit_kind) == SCX_EXIT_NONE); + ret = 0; + goto err_disable; + } + + if (!(ops->flags & SCX_OPS_SWITCH_PARTIAL)) + static_branch_enable(&__scx_switched_all); + + kobject_uevent(scx_root_kobj, KOBJ_ADD); + mutex_unlock(&scx_ops_enable_mutex); + + return 0; + +err_del: + kobject_del(scx_root_kobj); +err: + kobject_put(scx_root_kobj); + scx_root_kobj = NULL; + if (scx_exit_info) { + free_exit_info(scx_exit_info); + scx_exit_info = NULL; + } +err_unlock: + mutex_unlock(&scx_ops_enable_mutex); + return ret; + +err_disable_unlock_all: + percpu_up_write(&scx_fork_rwsem); +err_disable_unlock_cpus: + cpus_read_unlock(); +err_disable: + mutex_unlock(&scx_ops_enable_mutex); + /* must be fully disabled before returning */ + scx_ops_disable(SCX_EXIT_ERROR); + kthread_flush_work(&scx_ops_disable_work); + return ret; +} + + +/******************************************************************************** + * bpf_struct_ops plumbing. + */ +#include +#include +#include + +extern struct btf *btf_vmlinux; +static const struct btf_type *task_struct_type; +static u32 task_struct_type_id; + +static bool set_arg_maybe_null(const char *op, int arg_n, int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + struct btf *btf = bpf_get_btf_vmlinux(); + const struct bpf_struct_ops_desc *st_ops_desc; + const struct btf_member *member; + const struct btf_type *t; + u32 btf_id, member_idx; + const char *mname; + + /* struct_ops op args are all sequential, 64-bit numbers */ + if (off != arg_n * sizeof(__u64)) + return false; + + /* btf_id should be the type id of struct sched_ext_ops */ + btf_id = prog->aux->attach_btf_id; + st_ops_desc = bpf_struct_ops_find(btf, btf_id); + if (!st_ops_desc) + return false; + + /* BTF type of struct sched_ext_ops */ + t = st_ops_desc->type; + + member_idx = prog->expected_attach_type; + if (member_idx >= btf_type_vlen(t)) + return false; + + /* + * Get the member name of this struct_ops program, which corresponds to + * a field in struct sched_ext_ops. For example, the member name of the + * dispatch struct_ops program (callback) is "dispatch". + */ + member = &btf_type_member(t)[member_idx]; + mname = btf_name_by_offset(btf_vmlinux, member->name_off); + + if (!strcmp(mname, op)) { + /* + * The value is a pointer to a type (struct task_struct) given + * by a BTF ID (PTR_TO_BTF_ID). It is trusted (PTR_TRUSTED), + * however, can be a NULL (PTR_MAYBE_NULL). The BPF program + * should check the pointer to make sure it is not NULL before + * using it, or the verifier will reject the program. + * + * Longer term, this is something that should be addressed by + * BTF, and be fully contained within the verifier. + */ + info->reg_type = PTR_MAYBE_NULL | PTR_TO_BTF_ID | PTR_TRUSTED; + info->btf = btf_vmlinux; + info->btf_id = task_struct_type_id; + + return true; + } + + return false; +} + +static bool bpf_scx_is_valid_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + if (type != BPF_READ) + return false; + if (set_arg_maybe_null("dispatch", 1, off, size, type, prog, info) || + set_arg_maybe_null("yield", 1, off, size, type, prog, info)) + return true; + if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS) + return false; + if (off % size != 0) + return false; + + return btf_ctx_access(off, size, type, prog, info); +} + +static int bpf_scx_btf_struct_access(struct bpf_verifier_log *log, + const struct bpf_reg_state *reg, int off, + int size) +{ + const struct btf_type *t; + + t = btf_type_by_id(reg->btf, reg->btf_id); + if (t == task_struct_type) { + if (off >= offsetof(struct task_struct, scx.slice) && + off + size <= offsetofend(struct task_struct, scx.slice)) + return SCALAR_VALUE; + } + + return -EACCES; +} + +static const struct bpf_func_proto * +bpf_scx_get_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + switch (func_id) { + case BPF_FUNC_task_storage_get: + return &bpf_task_storage_get_proto; + case BPF_FUNC_task_storage_delete: + return &bpf_task_storage_delete_proto; + default: + return bpf_base_func_proto(func_id, prog); + } +} + +static const struct bpf_verifier_ops bpf_scx_verifier_ops = { + .get_func_proto = bpf_scx_get_func_proto, + .is_valid_access = bpf_scx_is_valid_access, + .btf_struct_access = bpf_scx_btf_struct_access, +}; + +static int bpf_scx_init_member(const struct btf_type *t, + const struct btf_member *member, + void *kdata, const void *udata) +{ + const struct sched_ext_ops *uops = udata; + struct sched_ext_ops *ops = kdata; + u32 moff = __btf_member_bit_offset(t, member) / 8; + int ret; + + switch (moff) { + case offsetof(struct sched_ext_ops, dispatch_max_batch): + if (*(u32 *)(udata + moff) > INT_MAX) + return -E2BIG; + ops->dispatch_max_batch = *(u32 *)(udata + moff); + return 1; + case offsetof(struct sched_ext_ops, flags): + if (*(u64 *)(udata + moff) & ~SCX_OPS_ALL_FLAGS) + return -EINVAL; + ops->flags = *(u64 *)(udata + moff); + return 1; + case offsetof(struct sched_ext_ops, name): + ret = bpf_obj_name_cpy(ops->name, uops->name, + sizeof(ops->name)); + if (ret < 0) + return ret; + if (ret == 0) + return -EINVAL; + return 1; + } + + return 0; +} + +static int bpf_scx_check_member(const struct btf_type *t, + const struct btf_member *member, + const struct bpf_prog *prog) +{ + u32 moff = __btf_member_bit_offset(t, member) / 8; + + switch (moff) { + case offsetof(struct sched_ext_ops, init_task): + case offsetof(struct sched_ext_ops, init): + case offsetof(struct sched_ext_ops, exit): + break; + default: + if (prog->sleepable) + return -EINVAL; + } + + return 0; +} + +static int bpf_scx_reg(void *kdata, struct bpf_link *link) +{ + return scx_ops_enable(kdata, link); +} + +static void bpf_scx_unreg(void *kdata, struct bpf_link *link) +{ + scx_ops_disable(SCX_EXIT_UNREG); + kthread_flush_work(&scx_ops_disable_work); +} + +static int bpf_scx_init(struct btf *btf) +{ + u32 type_id; + + type_id = btf_find_by_name_kind(btf, "task_struct", BTF_KIND_STRUCT); + if (type_id < 0) + return -EINVAL; + task_struct_type = btf_type_by_id(btf, type_id); + task_struct_type_id = type_id; + + return 0; +} + +static int bpf_scx_update(void *kdata, void *old_kdata, struct bpf_link *link) +{ + /* + * sched_ext does not support updating the actively-loaded BPF + * scheduler, as registering a BPF scheduler can always fail if the + * scheduler returns an error code for e.g. ops.init(), ops.init_task(), + * etc. Similarly, we can always race with unregistration happening + * elsewhere, such as with sysrq. + */ + return -EOPNOTSUPP; +} + +static int bpf_scx_validate(void *kdata) +{ + return 0; +} + +static s32 select_cpu_stub(struct task_struct *p, s32 prev_cpu, u64 wake_flags) { return -EINVAL; } +static void enqueue_stub(struct task_struct *p, u64 enq_flags) {} +static void dequeue_stub(struct task_struct *p, u64 enq_flags) {} +static void dispatch_stub(s32 prev_cpu, struct task_struct *p) {} +static bool yield_stub(struct task_struct *from, struct task_struct *to) { return false; } +static void set_weight_stub(struct task_struct *p, u32 weight) {} +static void set_cpumask_stub(struct task_struct *p, const struct cpumask *mask) {} +static void update_idle_stub(s32 cpu, bool idle) {} +static s32 init_task_stub(struct task_struct *p, struct scx_init_task_args *args) { return -EINVAL; } +static void exit_task_stub(struct task_struct *p, struct scx_exit_task_args *args) {} +static void enable_stub(struct task_struct *p) {} +static void disable_stub(struct task_struct *p) {} +static s32 init_stub(void) { return -EINVAL; } +static void exit_stub(struct scx_exit_info *info) {} + +static struct sched_ext_ops __bpf_ops_sched_ext_ops = { + .select_cpu = select_cpu_stub, + .enqueue = enqueue_stub, + .dequeue = dequeue_stub, + .dispatch = dispatch_stub, + .yield = yield_stub, + .set_weight = set_weight_stub, + .set_cpumask = set_cpumask_stub, + .update_idle = update_idle_stub, + .init_task = init_task_stub, + .exit_task = exit_task_stub, + .enable = enable_stub, + .disable = disable_stub, + .init = init_stub, + .exit = exit_stub, +}; + +static struct bpf_struct_ops bpf_sched_ext_ops = { + .verifier_ops = &bpf_scx_verifier_ops, + .reg = bpf_scx_reg, + .unreg = bpf_scx_unreg, + .check_member = bpf_scx_check_member, + .init_member = bpf_scx_init_member, + .init = bpf_scx_init, + .update = bpf_scx_update, + .validate = bpf_scx_validate, + .name = "sched_ext_ops", + .owner = THIS_MODULE, + .cfi_stubs = &__bpf_ops_sched_ext_ops +}; + + +/******************************************************************************** + * System integration and init. + */ + +void __init init_sched_ext_class(void) +{ + s32 cpu, v; + + /* + * The following is to prevent the compiler from optimizing out the enum + * definitions so that BPF scheduler implementations can use them + * through the generated vmlinux.h. + */ + WRITE_ONCE(v, SCX_ENQ_WAKEUP | SCX_DEQ_SLEEP); + + BUG_ON(rhashtable_init(&dsq_hash, &dsq_hash_params)); + init_dsq(&scx_dsq_global, SCX_DSQ_GLOBAL); +#ifdef CONFIG_SMP + BUG_ON(!alloc_cpumask_var(&idle_masks.cpu, GFP_KERNEL)); + BUG_ON(!alloc_cpumask_var(&idle_masks.smt, GFP_KERNEL)); +#endif + for_each_possible_cpu(cpu) { + struct rq *rq = cpu_rq(cpu); + + init_dsq(&rq->scx.local_dsq, SCX_DSQ_LOCAL); + INIT_LIST_HEAD(&rq->scx.runnable_list); + } +} + + +/******************************************************************************** + * Helpers that can be called from the BPF scheduler. + */ +#include + +__bpf_kfunc_start_defs(); + +/** + * scx_bpf_create_dsq - Create a custom DSQ + * @dsq_id: DSQ to create + * @node: NUMA node to allocate from + * + * Create a custom DSQ identified by @dsq_id. Can be called from ops.init() and + * ops.init_task(). + */ +__bpf_kfunc s32 scx_bpf_create_dsq(u64 dsq_id, s32 node) +{ + if (!scx_kf_allowed(SCX_KF_SLEEPABLE)) + return -EINVAL; + + if (unlikely(node >= (int)nr_node_ids || + (node < 0 && node != NUMA_NO_NODE))) + return -EINVAL; + return PTR_ERR_OR_ZERO(create_dsq(dsq_id, node)); +} + +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(scx_kfunc_ids_sleepable) +BTF_ID_FLAGS(func, scx_bpf_create_dsq, KF_SLEEPABLE) +BTF_KFUNCS_END(scx_kfunc_ids_sleepable) + +static const struct btf_kfunc_id_set scx_kfunc_set_sleepable = { + .owner = THIS_MODULE, + .set = &scx_kfunc_ids_sleepable, +}; + +__bpf_kfunc_start_defs(); + +/** + * scx_bpf_select_cpu_dfl - The default implementation of ops.select_cpu() + * @p: task_struct to select a CPU for + * @prev_cpu: CPU @p was on previously + * @wake_flags: %SCX_WAKE_* flags + * @is_idle: out parameter indicating whether the returned CPU is idle + * + * Can only be called from ops.select_cpu() if the built-in CPU selection is + * enabled - ops.update_idle() is missing or %SCX_OPS_KEEP_BUILTIN_IDLE is set. + * @p, @prev_cpu and @wake_flags match ops.select_cpu(). + * + * Returns the picked CPU with *@is_idle indicating whether the picked CPU is + * currently idle and thus a good candidate for direct dispatching. + */ +__bpf_kfunc s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, + u64 wake_flags, bool *is_idle) +{ + if (!scx_kf_allowed(SCX_KF_SELECT_CPU)) { + *is_idle = false; + return prev_cpu; + } +#ifdef CONFIG_SMP + return scx_select_cpu_dfl(p, prev_cpu, wake_flags, is_idle); +#else + *is_idle = false; + return prev_cpu; +#endif +} + +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(scx_kfunc_ids_select_cpu) +BTF_ID_FLAGS(func, scx_bpf_select_cpu_dfl, KF_RCU) +BTF_KFUNCS_END(scx_kfunc_ids_select_cpu) + +static const struct btf_kfunc_id_set scx_kfunc_set_select_cpu = { + .owner = THIS_MODULE, + .set = &scx_kfunc_ids_select_cpu, +}; + +static bool scx_dispatch_preamble(struct task_struct *p, u64 enq_flags) +{ + if (!scx_kf_allowed(SCX_KF_ENQUEUE | SCX_KF_DISPATCH)) + return false; + + lockdep_assert_irqs_disabled(); + + if (unlikely(!p)) { + scx_ops_error("called with NULL task"); + return false; + } + + if (unlikely(enq_flags & __SCX_ENQ_INTERNAL_MASK)) { + scx_ops_error("invalid enq_flags 0x%llx", enq_flags); + return false; + } + + return true; +} + +static void scx_dispatch_commit(struct task_struct *p, u64 dsq_id, u64 enq_flags) +{ + struct scx_dsp_ctx *dspc = this_cpu_ptr(scx_dsp_ctx); + struct task_struct *ddsp_task; + + ddsp_task = __this_cpu_read(direct_dispatch_task); + if (ddsp_task) { + mark_direct_dispatch(ddsp_task, p, dsq_id, enq_flags); + return; + } + + if (unlikely(dspc->cursor >= scx_dsp_max_batch)) { + scx_ops_error("dispatch buffer overflow"); + return; + } + + dspc->buf[dspc->cursor++] = (struct scx_dsp_buf_ent){ + .task = p, + .qseq = atomic_long_read(&p->scx.ops_state) & SCX_OPSS_QSEQ_MASK, + .dsq_id = dsq_id, + .enq_flags = enq_flags, + }; +} + +__bpf_kfunc_start_defs(); + +/** + * scx_bpf_dispatch - Dispatch a task into the FIFO queue of a DSQ + * @p: task_struct to dispatch + * @dsq_id: DSQ to dispatch to + * @slice: duration @p can run for in nsecs + * @enq_flags: SCX_ENQ_* + * + * Dispatch @p into the FIFO queue of the DSQ identified by @dsq_id. It is safe + * to call this function spuriously. Can be called from ops.enqueue(), + * ops.select_cpu(), and ops.dispatch(). + * + * When called from ops.select_cpu() or ops.enqueue(), it's for direct dispatch + * and @p must match the task being enqueued. Also, %SCX_DSQ_LOCAL_ON can't be + * used to target the local DSQ of a CPU other than the enqueueing one. Use + * ops.select_cpu() to be on the target CPU in the first place. + * + * When called from ops.select_cpu(), @enq_flags and @dsp_id are stored, and @p + * will be directly dispatched to the corresponding dispatch queue after + * ops.select_cpu() returns. If @p is dispatched to SCX_DSQ_LOCAL, it will be + * dispatched to the local DSQ of the CPU returned by ops.select_cpu(). + * @enq_flags are OR'd with the enqueue flags on the enqueue path before the + * task is dispatched. + * + * When called from ops.dispatch(), there are no restrictions on @p or @dsq_id + * and this function can be called upto ops.dispatch_max_batch times to dispatch + * multiple tasks. scx_bpf_dispatch_nr_slots() returns the number of the + * remaining slots. scx_bpf_consume() flushes the batch and resets the counter. + * + * This function doesn't have any locking restrictions and may be called under + * BPF locks (in the future when BPF introduces more flexible locking). + * + * @p is allowed to run for @slice. The scheduling path is triggered on slice + * exhaustion. If zero, the current residual slice is maintained. + */ +__bpf_kfunc void scx_bpf_dispatch(struct task_struct *p, u64 dsq_id, u64 slice, + u64 enq_flags) +{ + if (!scx_dispatch_preamble(p, enq_flags)) + return; + + if (slice) + p->scx.slice = slice; + else + p->scx.slice = p->scx.slice ?: 1; + + scx_dispatch_commit(p, dsq_id, enq_flags); +} + +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(scx_kfunc_ids_enqueue_dispatch) +BTF_ID_FLAGS(func, scx_bpf_dispatch, KF_RCU) +BTF_KFUNCS_END(scx_kfunc_ids_enqueue_dispatch) + +static const struct btf_kfunc_id_set scx_kfunc_set_enqueue_dispatch = { + .owner = THIS_MODULE, + .set = &scx_kfunc_ids_enqueue_dispatch, +}; + +__bpf_kfunc_start_defs(); + +/** + * scx_bpf_dispatch_nr_slots - Return the number of remaining dispatch slots + * + * Can only be called from ops.dispatch(). + */ +__bpf_kfunc u32 scx_bpf_dispatch_nr_slots(void) +{ + if (!scx_kf_allowed(SCX_KF_DISPATCH)) + return 0; + + return scx_dsp_max_batch - __this_cpu_read(scx_dsp_ctx->cursor); +} + +/** + * scx_bpf_dispatch_cancel - Cancel the latest dispatch + * + * Cancel the latest dispatch. Can be called multiple times to cancel further + * dispatches. Can only be called from ops.dispatch(). + */ +__bpf_kfunc void scx_bpf_dispatch_cancel(void) +{ + struct scx_dsp_ctx *dspc = this_cpu_ptr(scx_dsp_ctx); + + if (!scx_kf_allowed(SCX_KF_DISPATCH)) + return; + + if (dspc->cursor > 0) + dspc->cursor--; + else + scx_ops_error("dispatch buffer underflow"); +} + +/** + * scx_bpf_consume - Transfer a task from a DSQ to the current CPU's local DSQ + * @dsq_id: DSQ to consume + * + * Consume a task from the non-local DSQ identified by @dsq_id and transfer it + * to the current CPU's local DSQ for execution. Can only be called from + * ops.dispatch(). + * + * This function flushes the in-flight dispatches from scx_bpf_dispatch() before + * trying to consume the specified DSQ. It may also grab rq locks and thus can't + * be called under any BPF locks. + * + * Returns %true if a task has been consumed, %false if there isn't any task to + * consume. + */ +__bpf_kfunc bool scx_bpf_consume(u64 dsq_id) +{ + struct scx_dsp_ctx *dspc = this_cpu_ptr(scx_dsp_ctx); + struct scx_dispatch_q *dsq; + + if (!scx_kf_allowed(SCX_KF_DISPATCH)) + return false; + + flush_dispatch_buf(dspc->rq, dspc->rf); + + dsq = find_non_local_dsq(dsq_id); + if (unlikely(!dsq)) { + scx_ops_error("invalid DSQ ID 0x%016llx", dsq_id); + return false; + } + + if (consume_dispatch_q(dspc->rq, dspc->rf, dsq)) { + /* + * A successfully consumed task can be dequeued before it starts + * running while the CPU is trying to migrate other dispatched + * tasks. Bump nr_tasks to tell balance_scx() to retry on empty + * local DSQ. + */ + dspc->nr_tasks++; + return true; + } else { + return false; + } +} + +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(scx_kfunc_ids_dispatch) +BTF_ID_FLAGS(func, scx_bpf_dispatch_nr_slots) +BTF_ID_FLAGS(func, scx_bpf_dispatch_cancel) +BTF_ID_FLAGS(func, scx_bpf_consume) +BTF_KFUNCS_END(scx_kfunc_ids_dispatch) + +static const struct btf_kfunc_id_set scx_kfunc_set_dispatch = { + .owner = THIS_MODULE, + .set = &scx_kfunc_ids_dispatch, +}; + +__bpf_kfunc_start_defs(); + +/** + * scx_bpf_dsq_nr_queued - Return the number of queued tasks + * @dsq_id: id of the DSQ + * + * Return the number of tasks in the DSQ matching @dsq_id. If not found, + * -%ENOENT is returned. + */ +__bpf_kfunc s32 scx_bpf_dsq_nr_queued(u64 dsq_id) +{ + struct scx_dispatch_q *dsq; + s32 ret; + + preempt_disable(); + + if (dsq_id == SCX_DSQ_LOCAL) { + ret = READ_ONCE(this_rq()->scx.local_dsq.nr); + goto out; + } else if ((dsq_id & SCX_DSQ_LOCAL_ON) == SCX_DSQ_LOCAL_ON) { + s32 cpu = dsq_id & SCX_DSQ_LOCAL_CPU_MASK; + + if (ops_cpu_valid(cpu, NULL)) { + ret = READ_ONCE(cpu_rq(cpu)->scx.local_dsq.nr); + goto out; + } + } else { + dsq = find_non_local_dsq(dsq_id); + if (dsq) { + ret = READ_ONCE(dsq->nr); + goto out; + } + } + ret = -ENOENT; +out: + preempt_enable(); + return ret; +} + +/** + * scx_bpf_destroy_dsq - Destroy a custom DSQ + * @dsq_id: DSQ to destroy + * + * Destroy the custom DSQ identified by @dsq_id. Only DSQs created with + * scx_bpf_create_dsq() can be destroyed. The caller must ensure that the DSQ is + * empty and no further tasks are dispatched to it. Ignored if called on a DSQ + * which doesn't exist. Can be called from any online scx_ops operations. + */ +__bpf_kfunc void scx_bpf_destroy_dsq(u64 dsq_id) +{ + destroy_dsq(dsq_id); +} + +__bpf_kfunc_end_defs(); + +static s32 __bstr_format(u64 *data_buf, char *line_buf, size_t line_size, + char *fmt, unsigned long long *data, u32 data__sz) +{ + struct bpf_bprintf_data bprintf_data = { .get_bin_args = true }; + s32 ret; + + if (data__sz % 8 || data__sz > MAX_BPRINTF_VARARGS * 8 || + (data__sz && !data)) { + scx_ops_error("invalid data=%p and data__sz=%u", + (void *)data, data__sz); + return -EINVAL; + } + + ret = copy_from_kernel_nofault(data_buf, data, data__sz); + if (ret < 0) { + scx_ops_error("failed to read data fields (%d)", ret); + return ret; + } + + ret = bpf_bprintf_prepare(fmt, UINT_MAX, data_buf, data__sz / 8, + &bprintf_data); + if (ret < 0) { + scx_ops_error("format preparation failed (%d)", ret); + return ret; + } + + ret = bstr_printf(line_buf, line_size, fmt, + bprintf_data.bin_args); + bpf_bprintf_cleanup(&bprintf_data); + if (ret < 0) { + scx_ops_error("(\"%s\", %p, %u) failed to format", + fmt, data, data__sz); + return ret; + } + + return ret; +} + +static s32 bstr_format(struct scx_bstr_buf *buf, + char *fmt, unsigned long long *data, u32 data__sz) +{ + return __bstr_format(buf->data, buf->line, sizeof(buf->line), + fmt, data, data__sz); +} + +__bpf_kfunc_start_defs(); + +/** + * scx_bpf_exit_bstr - Gracefully exit the BPF scheduler. + * @exit_code: Exit value to pass to user space via struct scx_exit_info. + * @fmt: error message format string + * @data: format string parameters packaged using ___bpf_fill() macro + * @data__sz: @data len, must end in '__sz' for the verifier + * + * Indicate that the BPF scheduler wants to exit gracefully, and initiate ops + * disabling. + */ +__bpf_kfunc void scx_bpf_exit_bstr(s64 exit_code, char *fmt, + unsigned long long *data, u32 data__sz) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&scx_exit_bstr_buf_lock, flags); + if (bstr_format(&scx_exit_bstr_buf, fmt, data, data__sz) >= 0) + scx_ops_exit_kind(SCX_EXIT_UNREG_BPF, exit_code, "%s", + scx_exit_bstr_buf.line); + raw_spin_unlock_irqrestore(&scx_exit_bstr_buf_lock, flags); +} + +/** + * scx_bpf_error_bstr - Indicate fatal error + * @fmt: error message format string + * @data: format string parameters packaged using ___bpf_fill() macro + * @data__sz: @data len, must end in '__sz' for the verifier + * + * Indicate that the BPF scheduler encountered a fatal error and initiate ops + * disabling. + */ +__bpf_kfunc void scx_bpf_error_bstr(char *fmt, unsigned long long *data, + u32 data__sz) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&scx_exit_bstr_buf_lock, flags); + if (bstr_format(&scx_exit_bstr_buf, fmt, data, data__sz) >= 0) + scx_ops_exit_kind(SCX_EXIT_ERROR_BPF, 0, "%s", + scx_exit_bstr_buf.line); + raw_spin_unlock_irqrestore(&scx_exit_bstr_buf_lock, flags); +} + +/** + * scx_bpf_nr_cpu_ids - Return the number of possible CPU IDs + * + * All valid CPU IDs in the system are smaller than the returned value. + */ +__bpf_kfunc u32 scx_bpf_nr_cpu_ids(void) +{ + return nr_cpu_ids; +} + +/** + * scx_bpf_get_possible_cpumask - Get a referenced kptr to cpu_possible_mask + */ +__bpf_kfunc const struct cpumask *scx_bpf_get_possible_cpumask(void) +{ + return cpu_possible_mask; +} + +/** + * scx_bpf_get_online_cpumask - Get a referenced kptr to cpu_online_mask + */ +__bpf_kfunc const struct cpumask *scx_bpf_get_online_cpumask(void) +{ + return cpu_online_mask; +} + +/** + * scx_bpf_put_cpumask - Release a possible/online cpumask + * @cpumask: cpumask to release + */ +__bpf_kfunc void scx_bpf_put_cpumask(const struct cpumask *cpumask) +{ + /* + * Empty function body because we aren't actually acquiring or releasing + * a reference to a global cpumask, which is read-only in the caller and + * is never released. The acquire / release semantics here are just used + * to make the cpumask is a trusted pointer in the caller. + */ +} + +/** + * scx_bpf_get_idle_cpumask - Get a referenced kptr to the idle-tracking + * per-CPU cpumask. + * + * Returns NULL if idle tracking is not enabled, or running on a UP kernel. + */ +__bpf_kfunc const struct cpumask *scx_bpf_get_idle_cpumask(void) +{ + if (!static_branch_likely(&scx_builtin_idle_enabled)) { + scx_ops_error("built-in idle tracking is disabled"); + return cpu_none_mask; + } + +#ifdef CONFIG_SMP + return idle_masks.cpu; +#else + return cpu_none_mask; +#endif +} + +/** + * scx_bpf_get_idle_smtmask - Get a referenced kptr to the idle-tracking, + * per-physical-core cpumask. Can be used to determine if an entire physical + * core is free. + * + * Returns NULL if idle tracking is not enabled, or running on a UP kernel. + */ +__bpf_kfunc const struct cpumask *scx_bpf_get_idle_smtmask(void) +{ + if (!static_branch_likely(&scx_builtin_idle_enabled)) { + scx_ops_error("built-in idle tracking is disabled"); + return cpu_none_mask; + } + +#ifdef CONFIG_SMP + if (sched_smt_active()) + return idle_masks.smt; + else + return idle_masks.cpu; +#else + return cpu_none_mask; +#endif +} + +/** + * scx_bpf_put_idle_cpumask - Release a previously acquired referenced kptr to + * either the percpu, or SMT idle-tracking cpumask. + */ +__bpf_kfunc void scx_bpf_put_idle_cpumask(const struct cpumask *idle_mask) +{ + /* + * Empty function body because we aren't actually acquiring or releasing + * a reference to a global idle cpumask, which is read-only in the + * caller and is never released. The acquire / release semantics here + * are just used to make the cpumask a trusted pointer in the caller. + */ +} + +/** + * scx_bpf_test_and_clear_cpu_idle - Test and clear @cpu's idle state + * @cpu: cpu to test and clear idle for + * + * Returns %true if @cpu was idle and its idle state was successfully cleared. + * %false otherwise. + * + * Unavailable if ops.update_idle() is implemented and + * %SCX_OPS_KEEP_BUILTIN_IDLE is not set. + */ +__bpf_kfunc bool scx_bpf_test_and_clear_cpu_idle(s32 cpu) +{ + if (!static_branch_likely(&scx_builtin_idle_enabled)) { + scx_ops_error("built-in idle tracking is disabled"); + return false; + } + + if (ops_cpu_valid(cpu, NULL)) + return test_and_clear_cpu_idle(cpu); + else + return false; +} + +/** + * scx_bpf_pick_idle_cpu - Pick and claim an idle cpu + * @cpus_allowed: Allowed cpumask + * @flags: %SCX_PICK_IDLE_CPU_* flags + * + * Pick and claim an idle cpu in @cpus_allowed. Returns the picked idle cpu + * number on success. -%EBUSY if no matching cpu was found. + * + * Idle CPU tracking may race against CPU scheduling state transitions. For + * example, this function may return -%EBUSY as CPUs are transitioning into the + * idle state. If the caller then assumes that there will be dispatch events on + * the CPUs as they were all busy, the scheduler may end up stalling with CPUs + * idling while there are pending tasks. Use scx_bpf_pick_any_cpu() and + * scx_bpf_kick_cpu() to guarantee that there will be at least one dispatch + * event in the near future. + * + * Unavailable if ops.update_idle() is implemented and + * %SCX_OPS_KEEP_BUILTIN_IDLE is not set. + */ +__bpf_kfunc s32 scx_bpf_pick_idle_cpu(const struct cpumask *cpus_allowed, + u64 flags) +{ + if (!static_branch_likely(&scx_builtin_idle_enabled)) { + scx_ops_error("built-in idle tracking is disabled"); + return -EBUSY; + } + + return scx_pick_idle_cpu(cpus_allowed, flags); +} + +/** + * scx_bpf_pick_any_cpu - Pick and claim an idle cpu if available or pick any CPU + * @cpus_allowed: Allowed cpumask + * @flags: %SCX_PICK_IDLE_CPU_* flags + * + * Pick and claim an idle cpu in @cpus_allowed. If none is available, pick any + * CPU in @cpus_allowed. Guaranteed to succeed and returns the picked idle cpu + * number if @cpus_allowed is not empty. -%EBUSY is returned if @cpus_allowed is + * empty. + * + * If ops.update_idle() is implemented and %SCX_OPS_KEEP_BUILTIN_IDLE is not + * set, this function can't tell which CPUs are idle and will always pick any + * CPU. + */ +__bpf_kfunc s32 scx_bpf_pick_any_cpu(const struct cpumask *cpus_allowed, + u64 flags) +{ + s32 cpu; + + if (static_branch_likely(&scx_builtin_idle_enabled)) { + cpu = scx_pick_idle_cpu(cpus_allowed, flags); + if (cpu >= 0) + return cpu; + } + + cpu = cpumask_any_distribute(cpus_allowed); + if (cpu < nr_cpu_ids) + return cpu; + else + return -EBUSY; +} + +/** + * scx_bpf_task_running - Is task currently running? + * @p: task of interest + */ +__bpf_kfunc bool scx_bpf_task_running(const struct task_struct *p) +{ + return task_rq(p)->curr == p; +} + +/** + * scx_bpf_task_cpu - CPU a task is currently associated with + * @p: task of interest + */ +__bpf_kfunc s32 scx_bpf_task_cpu(const struct task_struct *p) +{ + return task_cpu(p); +} + +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(scx_kfunc_ids_any) +BTF_ID_FLAGS(func, scx_bpf_dsq_nr_queued) +BTF_ID_FLAGS(func, scx_bpf_destroy_dsq) +BTF_ID_FLAGS(func, scx_bpf_exit_bstr, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, scx_bpf_error_bstr, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, scx_bpf_nr_cpu_ids) +BTF_ID_FLAGS(func, scx_bpf_get_possible_cpumask, KF_ACQUIRE) +BTF_ID_FLAGS(func, scx_bpf_get_online_cpumask, KF_ACQUIRE) +BTF_ID_FLAGS(func, scx_bpf_put_cpumask, KF_RELEASE) +BTF_ID_FLAGS(func, scx_bpf_get_idle_cpumask, KF_ACQUIRE) +BTF_ID_FLAGS(func, scx_bpf_get_idle_smtmask, KF_ACQUIRE) +BTF_ID_FLAGS(func, scx_bpf_put_idle_cpumask, KF_RELEASE) +BTF_ID_FLAGS(func, scx_bpf_test_and_clear_cpu_idle) +BTF_ID_FLAGS(func, scx_bpf_pick_idle_cpu, KF_RCU) +BTF_ID_FLAGS(func, scx_bpf_pick_any_cpu, KF_RCU) +BTF_ID_FLAGS(func, scx_bpf_task_running, KF_RCU) +BTF_ID_FLAGS(func, scx_bpf_task_cpu, KF_RCU) +BTF_KFUNCS_END(scx_kfunc_ids_any) + +static const struct btf_kfunc_id_set scx_kfunc_set_any = { + .owner = THIS_MODULE, + .set = &scx_kfunc_ids_any, +}; + +static int __init scx_init(void) +{ + int ret; + + /* + * kfunc registration can't be done from init_sched_ext_class() as + * register_btf_kfunc_id_set() needs most of the system to be up. + * + * Some kfuncs are context-sensitive and can only be called from + * specific SCX ops. They are grouped into BTF sets accordingly. + * Unfortunately, BPF currently doesn't have a way of enforcing such + * restrictions. Eventually, the verifier should be able to enforce + * them. For now, register them the same and make each kfunc explicitly + * check using scx_kf_allowed(). + */ + if ((ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, + &scx_kfunc_set_sleepable)) || + (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, + &scx_kfunc_set_select_cpu)) || + (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, + &scx_kfunc_set_enqueue_dispatch)) || + (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, + &scx_kfunc_set_dispatch)) || + (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, + &scx_kfunc_set_any)) || + (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, + &scx_kfunc_set_any)) || + (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, + &scx_kfunc_set_any))) { + pr_err("sched_ext: Failed to register kfunc sets (%d)\n", ret); + return ret; + } + + ret = register_bpf_struct_ops(&bpf_sched_ext_ops, sched_ext_ops); + if (ret) { + pr_err("sched_ext: Failed to register struct_ops (%d)\n", ret); + return ret; + } + + scx_kset = kset_create_and_add("sched_ext", &scx_uevent_ops, kernel_kobj); + if (!scx_kset) { + pr_err("sched_ext: Failed to create /sys/kernel/sched_ext\n"); + return -ENOMEM; + } + + ret = sysfs_create_group(&scx_kset->kobj, &scx_global_attr_group); + if (ret < 0) { + pr_err("sched_ext: Failed to add global attributes\n"); + return ret; + } + + return 0; +} +__initcall(scx_init); diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h index 6a93c4825339..9c5a2d928281 100644 --- a/kernel/sched/ext.h +++ b/kernel/sched/ext.h @@ -1,15 +1,76 @@ /* SPDX-License-Identifier: GPL-2.0 */ - +/* + * Copyright (c) 2022 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2022 Tejun Heo + * Copyright (c) 2022 David Vernet + */ #ifdef CONFIG_SCHED_CLASS_EXT -#error "NOT IMPLEMENTED YET" + +struct sched_enq_and_set_ctx { + struct task_struct *p; + int queue_flags; + bool queued; + bool running; +}; + +void sched_deq_and_put_task(struct task_struct *p, int queue_flags, + struct sched_enq_and_set_ctx *ctx); +void sched_enq_and_set_task(struct sched_enq_and_set_ctx *ctx); + +extern const struct sched_class ext_sched_class; + +DECLARE_STATIC_KEY_FALSE(__scx_ops_enabled); +DECLARE_STATIC_KEY_FALSE(__scx_switched_all); +#define scx_enabled() static_branch_unlikely(&__scx_ops_enabled) +#define scx_switched_all() static_branch_unlikely(&__scx_switched_all) + +static inline bool task_on_scx(const struct task_struct *p) +{ + return scx_enabled() && p->sched_class == &ext_sched_class; +} + +void init_scx_entity(struct sched_ext_entity *scx); +void scx_pre_fork(struct task_struct *p); +int scx_fork(struct task_struct *p); +void scx_post_fork(struct task_struct *p); +void scx_cancel_fork(struct task_struct *p); +bool task_should_scx(struct task_struct *p); +void init_sched_ext_class(void); + +static inline const struct sched_class *next_active_class(const struct sched_class *class) +{ + class++; + if (scx_switched_all() && class == &fair_sched_class) + class++; + if (!scx_enabled() && class == &ext_sched_class) + class++; + return class; +} + +#define for_active_class_range(class, _from, _to) \ + for (class = (_from); class != (_to); class = next_active_class(class)) + +#define for_each_active_class(class) \ + for_active_class_range(class, __sched_class_highest, __sched_class_lowest) + +/* + * SCX requires a balance() call before every pick_next_task() call including + * when waking up from idle. + */ +#define for_balance_class_range(class, prev_class, end_class) \ + for_active_class_range(class, (prev_class) > &ext_sched_class ? \ + &ext_sched_class : (prev_class), (end_class)) + #else /* CONFIG_SCHED_CLASS_EXT */ #define scx_enabled() false +#define scx_switched_all() false static inline void scx_pre_fork(struct task_struct *p) {} static inline int scx_fork(struct task_struct *p) { return 0; } static inline void scx_post_fork(struct task_struct *p) {} static inline void scx_cancel_fork(struct task_struct *p) {} +static inline bool task_on_scx(const struct task_struct *p) { return false; } static inline void init_sched_ext_class(void) {} #define for_each_active_class for_each_class @@ -18,7 +79,13 @@ static inline void init_sched_ext_class(void) {} #endif /* CONFIG_SCHED_CLASS_EXT */ #if defined(CONFIG_SCHED_CLASS_EXT) && defined(CONFIG_SMP) -#error "NOT IMPLEMENTED YET" +void __scx_update_idle(struct rq *rq, bool idle); + +static inline void scx_update_idle(struct rq *rq, bool idle) +{ + if (scx_enabled()) + __scx_update_idle(rq, idle); +} #else static inline void scx_update_idle(struct rq *rq, bool idle) {} #endif diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index c52ad5fdd096..2960e153c3a7 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -194,6 +194,10 @@ static inline int idle_policy(int policy) static inline int normal_policy(int policy) { +#ifdef CONFIG_SCHED_CLASS_EXT + if (policy == SCHED_EXT) + return true; +#endif return policy == SCHED_NORMAL; } @@ -719,6 +723,16 @@ struct cfs_rq { #endif /* CONFIG_FAIR_GROUP_SCHED */ }; +#ifdef CONFIG_SCHED_CLASS_EXT +struct scx_rq { + struct scx_dispatch_q local_dsq; + struct list_head runnable_list; /* runnable tasks on this rq */ + unsigned long ops_qseq; + u64 extra_enq_flags; /* see move_task_to_local_dsq() */ + u32 nr_running; +}; +#endif /* CONFIG_SCHED_CLASS_EXT */ + static inline int rt_bandwidth_enabled(void) { return sysctl_sched_rt_runtime >= 0; @@ -1066,6 +1080,9 @@ struct rq { struct cfs_rq cfs; struct rt_rq rt; struct dl_rq dl; +#ifdef CONFIG_SCHED_CLASS_EXT + struct scx_rq scx; +#endif #ifdef CONFIG_FAIR_GROUP_SCHED /* list of leaf cfs_rq on this CPU: */ diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c index 050215ef8fa4..18d44d180db1 100644 --- a/kernel/sched/syscalls.c +++ b/kernel/sched/syscalls.c @@ -1622,6 +1622,7 @@ SYSCALL_DEFINE1(sched_get_priority_max, int, policy) case SCHED_NORMAL: case SCHED_BATCH: case SCHED_IDLE: + case SCHED_EXT: ret = 0; break; } @@ -1649,6 +1650,7 @@ SYSCALL_DEFINE1(sched_get_priority_min, int, policy) case SCHED_NORMAL: case SCHED_BATCH: case SCHED_IDLE: + case SCHED_EXT: ret = 0; } return ret; -- cgit v1.2.3 From 8a010b81b3a50b033fc3cddc613517abda586cbe Mon Sep 17 00:00:00 2001 From: David Vernet Date: Tue, 18 Jun 2024 10:09:18 -1000 Subject: sched_ext: Implement runnable task stall watchdog The most common and critical way that a BPF scheduler can misbehave is by failing to run runnable tasks for too long. This patch implements a watchdog. * All tasks record when they become runnable. * A watchdog work periodically scans all runnable tasks. If any task has stayed runnable for too long, the BPF scheduler is aborted. * scheduler_tick() monitors whether the watchdog itself is stuck. If so, the BPF scheduler is aborted. Because the watchdog only scans the tasks which are currently runnable and usually very infrequently, the overhead should be negligible. scx_qmap is updated so that it can be told to stall user and/or kernel tasks. A detected task stall looks like the following: sched_ext: BPF scheduler "qmap" errored, disabling sched_ext: runnable task stall (dbus-daemon[953] failed to run for 6.478s) scx_check_timeout_workfn+0x10e/0x1b0 process_one_work+0x287/0x560 worker_thread+0x234/0x420 kthread+0xe9/0x100 ret_from_fork+0x1f/0x30 A detected watchdog stall: sched_ext: BPF scheduler "qmap" errored, disabling sched_ext: runnable task stall (watchdog failed to check in for 5.001s) scheduler_tick+0x2eb/0x340 update_process_times+0x7a/0x90 tick_sched_timer+0xd8/0x130 __hrtimer_run_queues+0x178/0x3b0 hrtimer_interrupt+0xfc/0x390 __sysvec_apic_timer_interrupt+0xb7/0x2b0 sysvec_apic_timer_interrupt+0x90/0xb0 asm_sysvec_apic_timer_interrupt+0x1b/0x20 default_idle+0x14/0x20 arch_cpu_idle+0xf/0x20 default_idle_call+0x50/0x90 do_idle+0xe8/0x240 cpu_startup_entry+0x1d/0x20 kernel_init+0x0/0x190 start_kernel+0x0/0x392 start_kernel+0x324/0x392 x86_64_start_reservations+0x2a/0x2c x86_64_start_kernel+0x104/0x109 secondary_startup_64_no_verify+0xce/0xdb Note that this patch exposes scx_ops_error[_type]() in kernel/sched/ext.h to inline scx_notify_sched_tick(). v4: - While disabling, cancel_delayed_work_sync(&scx_watchdog_work) was being called before forward progress was guaranteed and thus could lead to system lockup. Relocated. - While enabling, it was comparing msecs against jiffies without conversion leading to spurious load failures on lower HZ kernels. Fixed. - runnable list management is now used by core bypass logic and moved to the patch implementing sched_ext core. v3: - bpf_scx_init_member() was incorrectly comparing ops->timeout_ms against SCX_WATCHDOG_MAX_TIMEOUT which is in jiffies without conversion leading to spurious load failures in lower HZ kernels. Fixed. v2: - Julia Lawall noticed that the watchdog code was mixing msecs and jiffies. Fix by using jiffies for everything. Signed-off-by: David Vernet Reviewed-by: Tejun Heo Signed-off-by: Tejun Heo Acked-by: Josh Don Acked-by: Hao Luo Acked-by: Barret Rhoden Cc: Julia Lawall --- include/linux/sched/ext.h | 1 + init/init_task.c | 1 + kernel/sched/core.c | 1 + kernel/sched/ext.c | 130 +++++++++++++++++++++++++++++++++++++++-- kernel/sched/ext.h | 2 + tools/sched_ext/scx_qmap.bpf.c | 12 ++++ tools/sched_ext/scx_qmap.c | 12 +++- 7 files changed, 153 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index c1530a7992cc..96031252436f 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -122,6 +122,7 @@ struct sched_ext_entity { atomic_long_t ops_state; struct list_head runnable_node; /* rq->scx.runnable_list */ + unsigned long runnable_at; u64 ddsp_dsq_id; u64 ddsp_enq_flags; diff --git a/init/init_task.c b/init/init_task.c index c6804396fe12..8a44c932d10f 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -106,6 +106,7 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = { .sticky_cpu = -1, .holding_cpu = -1, .runnable_node = LIST_HEAD_INIT(init_task.scx.runnable_node), + .runnable_at = INITIAL_JIFFIES, .ddsp_dsq_id = SCX_DSQ_INVALID, .slice = SCX_SLICE_DFL, }, diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 6042ce3bfee0..f4365becdc13 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5516,6 +5516,7 @@ void sched_tick(void) calc_global_load_tick(rq); sched_core_tick(rq); task_tick_mm_cid(rq, curr); + scx_tick(rq); rq_unlock(rq, &rf); diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 1f5d80df263a..3dc515b3351f 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -8,6 +8,7 @@ enum scx_consts { SCX_DSP_DFL_MAX_BATCH = 32, + SCX_WATCHDOG_MAX_TIMEOUT = 30 * HZ, SCX_EXIT_BT_LEN = 64, SCX_EXIT_MSG_LEN = 1024, @@ -24,6 +25,7 @@ enum scx_exit_kind { SCX_EXIT_ERROR = 1024, /* runtime error, error msg contains details */ SCX_EXIT_ERROR_BPF, /* ERROR but triggered through scx_bpf_error() */ + SCX_EXIT_ERROR_STALL, /* watchdog detected stalled runnable tasks */ }; /* @@ -319,6 +321,15 @@ struct sched_ext_ops { */ u64 flags; + /** + * timeout_ms - The maximum amount of time, in milliseconds, that a + * runnable task should be able to wait before being scheduled. The + * maximum timeout may not exceed the default timeout of 30 seconds. + * + * Defaults to the maximum allowed timeout value of 30 seconds. + */ + u32 timeout_ms; + /** * name - BPF scheduler's name * @@ -472,6 +483,23 @@ struct static_key_false scx_has_op[SCX_OPI_END] = static atomic_t scx_exit_kind = ATOMIC_INIT(SCX_EXIT_DONE); static struct scx_exit_info *scx_exit_info; +/* + * The maximum amount of time in jiffies that a task may be runnable without + * being scheduled on a CPU. If this timeout is exceeded, it will trigger + * scx_ops_error(). + */ +static unsigned long scx_watchdog_timeout; + +/* + * The last time the delayed work was run. This delayed work relies on + * ksoftirqd being able to run to service timer interrupts, so it's possible + * that this work itself could get wedged. To account for this, we check that + * it's not stalled in the timer tick, and trigger an error if it is. + */ +static unsigned long scx_watchdog_timestamp = INITIAL_JIFFIES; + +static struct delayed_work scx_watchdog_work; + /* idle tracking */ #ifdef CONFIG_SMP #ifdef CONFIG_CPUMASK_OFFSTACK @@ -1170,6 +1198,11 @@ static void set_task_runnable(struct rq *rq, struct task_struct *p) { lockdep_assert_rq_held(rq); + if (p->scx.flags & SCX_TASK_RESET_RUNNABLE_AT) { + p->scx.runnable_at = jiffies; + p->scx.flags &= ~SCX_TASK_RESET_RUNNABLE_AT; + } + /* * list_add_tail() must be used. scx_ops_bypass() depends on tasks being * appened to the runnable_list. @@ -1177,9 +1210,11 @@ static void set_task_runnable(struct rq *rq, struct task_struct *p) list_add_tail(&p->scx.runnable_node, &rq->scx.runnable_list); } -static void clr_task_runnable(struct task_struct *p) +static void clr_task_runnable(struct task_struct *p, bool reset_runnable_at) { list_del_init(&p->scx.runnable_node); + if (reset_runnable_at) + p->scx.flags |= SCX_TASK_RESET_RUNNABLE_AT; } static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int enq_flags) @@ -1217,7 +1252,8 @@ static void ops_dequeue(struct task_struct *p, u64 deq_flags) { unsigned long opss; - clr_task_runnable(p); + /* dequeue is always temporary, don't reset runnable_at */ + clr_task_runnable(p, false); /* acquire ensures that we see the preceding updates on QUEUED */ opss = atomic_long_read_acquire(&p->scx.ops_state); @@ -1826,7 +1862,7 @@ static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first) p->se.exec_start = rq_clock_task(rq); - clr_task_runnable(p); + clr_task_runnable(p, true); } static void put_prev_task_scx(struct rq *rq, struct task_struct *p) @@ -2176,9 +2212,71 @@ static void reset_idle_masks(void) {} #endif /* CONFIG_SMP */ -static void task_tick_scx(struct rq *rq, struct task_struct *curr, int queued) +static bool check_rq_for_timeouts(struct rq *rq) +{ + struct task_struct *p; + struct rq_flags rf; + bool timed_out = false; + + rq_lock_irqsave(rq, &rf); + list_for_each_entry(p, &rq->scx.runnable_list, scx.runnable_node) { + unsigned long last_runnable = p->scx.runnable_at; + + if (unlikely(time_after(jiffies, + last_runnable + scx_watchdog_timeout))) { + u32 dur_ms = jiffies_to_msecs(jiffies - last_runnable); + + scx_ops_error_kind(SCX_EXIT_ERROR_STALL, + "%s[%d] failed to run for %u.%03us", + p->comm, p->pid, + dur_ms / 1000, dur_ms % 1000); + timed_out = true; + break; + } + } + rq_unlock_irqrestore(rq, &rf); + + return timed_out; +} + +static void scx_watchdog_workfn(struct work_struct *work) +{ + int cpu; + + WRITE_ONCE(scx_watchdog_timestamp, jiffies); + + for_each_online_cpu(cpu) { + if (unlikely(check_rq_for_timeouts(cpu_rq(cpu)))) + break; + + cond_resched(); + } + queue_delayed_work(system_unbound_wq, to_delayed_work(work), + scx_watchdog_timeout / 2); +} + +void scx_tick(struct rq *rq) { + unsigned long last_check; + + if (!scx_enabled()) + return; + + last_check = READ_ONCE(scx_watchdog_timestamp); + if (unlikely(time_after(jiffies, + last_check + READ_ONCE(scx_watchdog_timeout)))) { + u32 dur_ms = jiffies_to_msecs(jiffies - last_check); + + scx_ops_error_kind(SCX_EXIT_ERROR_STALL, + "watchdog failed to check in for %u.%03us", + dur_ms / 1000, dur_ms % 1000); + } + update_other_load_avgs(rq); +} + +static void task_tick_scx(struct rq *rq, struct task_struct *curr, int queued) +{ update_curr_scx(rq); /* @@ -2248,6 +2346,7 @@ static int scx_ops_init_task(struct task_struct *p, struct task_group *tg, bool scx_set_task_state(p, SCX_TASK_INIT); + p->scx.flags |= SCX_TASK_RESET_RUNNABLE_AT; return 0; } @@ -2326,6 +2425,7 @@ void init_scx_entity(struct sched_ext_entity *scx) scx->sticky_cpu = -1; scx->holding_cpu = -1; INIT_LIST_HEAD(&scx->runnable_node); + scx->runnable_at = jiffies; scx->ddsp_dsq_id = SCX_DSQ_INVALID; scx->slice = SCX_SLICE_DFL; } @@ -2783,6 +2883,8 @@ static const char *scx_exit_reason(enum scx_exit_kind kind) return "runtime error"; case SCX_EXIT_ERROR_BPF: return "scx_bpf_error"; + case SCX_EXIT_ERROR_STALL: + return "runnable task stall"; default: return ""; } @@ -2904,6 +3006,8 @@ static void scx_ops_disable_workfn(struct kthread_work *work) if (scx_ops.exit) SCX_CALL_OP(SCX_KF_UNLOCKED, exit, ei); + cancel_delayed_work_sync(&scx_watchdog_work); + /* * Delete the kobject from the hierarchy eagerly in addition to just * dropping a reference. Otherwise, if the object is deleted @@ -3026,6 +3130,7 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) { struct scx_task_iter sti; struct task_struct *p; + unsigned long timeout; int i, ret; mutex_lock(&scx_ops_enable_mutex); @@ -3103,6 +3208,16 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) goto err_disable; } + if (ops->timeout_ms) + timeout = msecs_to_jiffies(ops->timeout_ms); + else + timeout = SCX_WATCHDOG_MAX_TIMEOUT; + + WRITE_ONCE(scx_watchdog_timeout, timeout); + WRITE_ONCE(scx_watchdog_timestamp, jiffies); + queue_delayed_work(system_unbound_wq, &scx_watchdog_work, + scx_watchdog_timeout / 2); + /* * Lock out forks before opening the floodgate so that they don't wander * into the operations prematurely. @@ -3413,6 +3528,12 @@ static int bpf_scx_init_member(const struct btf_type *t, if (ret == 0) return -EINVAL; return 1; + case offsetof(struct sched_ext_ops, timeout_ms): + if (msecs_to_jiffies(*(u32 *)(udata + moff)) > + SCX_WATCHDOG_MAX_TIMEOUT) + return -E2BIG; + ops->timeout_ms = *(u32 *)(udata + moff); + return 1; } return 0; @@ -3569,6 +3690,7 @@ void __init init_sched_ext_class(void) } register_sysrq_key('S', &sysrq_sched_ext_reset_op); + INIT_DELAYED_WORK(&scx_watchdog_work, scx_watchdog_workfn); } diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h index 9c5a2d928281..56fcdb0b2c05 100644 --- a/kernel/sched/ext.h +++ b/kernel/sched/ext.h @@ -29,6 +29,7 @@ static inline bool task_on_scx(const struct task_struct *p) return scx_enabled() && p->sched_class == &ext_sched_class; } +void scx_tick(struct rq *rq); void init_scx_entity(struct sched_ext_entity *scx); void scx_pre_fork(struct task_struct *p); int scx_fork(struct task_struct *p); @@ -66,6 +67,7 @@ static inline const struct sched_class *next_active_class(const struct sched_cla #define scx_enabled() false #define scx_switched_all() false +static inline void scx_tick(struct rq *rq) {} static inline void scx_pre_fork(struct task_struct *p) {} static inline int scx_fork(struct task_struct *p) { return 0; } static inline void scx_post_fork(struct task_struct *p) {} diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c index 976a2693da71..8beae08dfdc7 100644 --- a/tools/sched_ext/scx_qmap.bpf.c +++ b/tools/sched_ext/scx_qmap.bpf.c @@ -29,6 +29,8 @@ enum consts { char _license[] SEC("license") = "GPL"; const volatile u64 slice_ns = SCX_SLICE_DFL; +const volatile u32 stall_user_nth; +const volatile u32 stall_kernel_nth; const volatile u32 dsp_batch; u32 test_error_cnt; @@ -129,11 +131,20 @@ static int weight_to_idx(u32 weight) void BPF_STRUCT_OPS(qmap_enqueue, struct task_struct *p, u64 enq_flags) { + static u32 user_cnt, kernel_cnt; struct task_ctx *tctx; u32 pid = p->pid; int idx = weight_to_idx(p->scx.weight); void *ring; + if (p->flags & PF_KTHREAD) { + if (stall_kernel_nth && !(++kernel_cnt % stall_kernel_nth)) + return; + } else { + if (stall_user_nth && !(++user_cnt % stall_user_nth)) + return; + } + if (test_error_cnt && !--test_error_cnt) scx_bpf_error("test triggering error"); @@ -261,4 +272,5 @@ SCX_OPS_DEFINE(qmap_ops, .init_task = (void *)qmap_init_task, .init = (void *)qmap_init, .exit = (void *)qmap_exit, + .timeout_ms = 5000U, .name = "qmap"); diff --git a/tools/sched_ext/scx_qmap.c b/tools/sched_ext/scx_qmap.c index 7c84ade7ecfb..6e9e9726cd62 100644 --- a/tools/sched_ext/scx_qmap.c +++ b/tools/sched_ext/scx_qmap.c @@ -19,10 +19,12 @@ const char help_fmt[] = "\n" "See the top-level comment in .bpf.c for more details.\n" "\n" -"Usage: %s [-s SLICE_US] [-e COUNT] [-b COUNT] [-p] [-v]\n" +"Usage: %s [-s SLICE_US] [-e COUNT] [-t COUNT] [-T COUNT] [-b COUNT] [-p] [-v]\n" "\n" " -s SLICE_US Override slice duration\n" " -e COUNT Trigger scx_bpf_error() after COUNT enqueues\n" +" -t COUNT Stall every COUNT'th user thread\n" +" -T COUNT Stall every COUNT'th kernel thread\n" " -b COUNT Dispatch upto COUNT tasks together\n" " -p Switch only tasks on SCHED_EXT policy intead of all\n" " -v Print libbpf debug messages\n" @@ -55,7 +57,7 @@ int main(int argc, char **argv) skel = SCX_OPS_OPEN(qmap_ops, scx_qmap); - while ((opt = getopt(argc, argv, "s:e:b:pvh")) != -1) { + while ((opt = getopt(argc, argv, "s:e:t:T:b:pvh")) != -1) { switch (opt) { case 's': skel->rodata->slice_ns = strtoull(optarg, NULL, 0) * 1000; @@ -63,6 +65,12 @@ int main(int argc, char **argv) case 'e': skel->bss->test_error_cnt = strtoul(optarg, NULL, 0); break; + case 't': + skel->rodata->stall_user_nth = strtoul(optarg, NULL, 0); + break; + case 'T': + skel->rodata->stall_kernel_nth = strtoul(optarg, NULL, 0); + break; case 'b': skel->rodata->dsp_batch = strtoul(optarg, NULL, 0); break; -- cgit v1.2.3 From 7bb6f0810ecfb73a9d7a2ca56fb001e0201a6758 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 18 Jun 2024 10:09:18 -1000 Subject: sched_ext: Allow BPF schedulers to disallow specific tasks from joining SCHED_EXT BPF schedulers might not want to schedule certain tasks - e.g. kernel threads. This patch adds p->scx.disallow which can be set by BPF schedulers in such cases. The field can be changed anytime and setting it in ops.prep_enable() guarantees that the task can never be scheduled by sched_ext. scx_qmap is updated with the -d option to disallow a specific PID: # echo $$ 1092 # grep -E '(policy)|(ext\.enabled)' /proc/self/sched policy : 0 ext.enabled : 0 # ./set-scx 1092 # grep -E '(policy)|(ext\.enabled)' /proc/self/sched policy : 7 ext.enabled : 0 Run "scx_qmap -p -d 1092" in another terminal. # cat /sys/kernel/sched_ext/nr_rejected 1 # grep -E '(policy)|(ext\.enabled)' /proc/self/sched policy : 0 ext.enabled : 0 # ./set-scx 1092 setparam failed for 1092 (Permission denied) - v4: Refreshed on top of tip:sched/core. - v3: Update description to reflect /sys/kernel/sched_ext interface change. - v2: Use atomic_long_t instead of atomic64_t for scx_kick_cpus_pnt_seqs to accommodate 32bit archs. Signed-off-by: Tejun Heo Suggested-by: Barret Rhoden Reviewed-by: David Vernet Acked-by: Josh Don Acked-by: Hao Luo Acked-by: Barret Rhoden --- include/linux/sched/ext.h | 12 ++++++++++ kernel/sched/ext.c | 50 ++++++++++++++++++++++++++++++++++++++++++ kernel/sched/ext.h | 2 ++ kernel/sched/syscalls.c | 4 ++++ tools/sched_ext/scx_qmap.bpf.c | 4 ++++ tools/sched_ext/scx_qmap.c | 11 ++++++++-- 6 files changed, 81 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index 96031252436f..ea7c501ac819 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -137,6 +137,18 @@ struct sched_ext_entity { */ u64 slice; + /* + * If set, reject future sched_setscheduler(2) calls updating the policy + * to %SCHED_EXT with -%EACCES. + * + * If set from ops.init_task() and the task's policy is already + * %SCHED_EXT, which can happen while the BPF scheduler is being loaded + * or by inhering the parent's policy during fork, the task's policy is + * rejected and forcefully reverted to %SCHED_NORMAL. The number of + * such events are reported through /sys/kernel/debug/sched_ext::nr_rejected. + */ + bool disallow; /* reject switching into SCX */ + /* cold fields */ /* must be the last field, see init_scx_entity() */ struct list_head tasks_node; diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 3dc515b3351f..8ff30b80e862 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -483,6 +483,8 @@ struct static_key_false scx_has_op[SCX_OPI_END] = static atomic_t scx_exit_kind = ATOMIC_INIT(SCX_EXIT_DONE); static struct scx_exit_info *scx_exit_info; +static atomic_long_t scx_nr_rejected = ATOMIC_LONG_INIT(0); + /* * The maximum amount of time in jiffies that a task may be runnable without * being scheduled on a CPU. If this timeout is exceeded, it will trigger @@ -2332,6 +2334,8 @@ static int scx_ops_init_task(struct task_struct *p, struct task_group *tg, bool { int ret; + p->scx.disallow = false; + if (SCX_HAS_OP(init_task)) { struct scx_init_task_args args = { .fork = fork, @@ -2346,6 +2350,27 @@ static int scx_ops_init_task(struct task_struct *p, struct task_group *tg, bool scx_set_task_state(p, SCX_TASK_INIT); + if (p->scx.disallow) { + struct rq *rq; + struct rq_flags rf; + + rq = task_rq_lock(p, &rf); + + /* + * We're either in fork or load path and @p->policy will be + * applied right after. Reverting @p->policy here and rejecting + * %SCHED_EXT transitions from scx_check_setscheduler() + * guarantees that if ops.init_task() sets @p->disallow, @p can + * never be in SCX. + */ + if (p->policy == SCHED_EXT) { + p->policy = SCHED_NORMAL; + atomic_long_inc(&scx_nr_rejected); + } + + task_rq_unlock(rq, p, &rf); + } + p->scx.flags |= SCX_TASK_RESET_RUNNABLE_AT; return 0; } @@ -2549,6 +2574,18 @@ static void switched_from_scx(struct rq *rq, struct task_struct *p) static void wakeup_preempt_scx(struct rq *rq, struct task_struct *p,int wake_flags) {} static void switched_to_scx(struct rq *rq, struct task_struct *p) {} +int scx_check_setscheduler(struct task_struct *p, int policy) +{ + lockdep_assert_rq_held(task_rq(p)); + + /* if disallow, reject transitioning into SCX */ + if (scx_enabled() && READ_ONCE(p->scx.disallow) && + p->policy != policy && policy == SCHED_EXT) + return -EACCES; + + return 0; +} + /* * Omitted operations: * @@ -2703,9 +2740,17 @@ static ssize_t scx_attr_switch_all_show(struct kobject *kobj, } SCX_ATTR(switch_all); +static ssize_t scx_attr_nr_rejected_show(struct kobject *kobj, + struct kobj_attribute *ka, char *buf) +{ + return sysfs_emit(buf, "%ld\n", atomic_long_read(&scx_nr_rejected)); +} +SCX_ATTR(nr_rejected); + static struct attribute *scx_global_attrs[] = { &scx_attr_state.attr, &scx_attr_switch_all.attr, + &scx_attr_nr_rejected.attr, NULL, }; @@ -3178,6 +3223,8 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) atomic_set(&scx_exit_kind, SCX_EXIT_NONE); scx_warned_zero_slice = false; + atomic_long_set(&scx_nr_rejected, 0); + /* * Keep CPUs stable during enable so that the BPF scheduler can track * online CPUs by watching ->on/offline_cpu() after ->init(). @@ -3476,6 +3523,9 @@ static int bpf_scx_btf_struct_access(struct bpf_verifier_log *log, if (off >= offsetof(struct task_struct, scx.slice) && off + size <= offsetofend(struct task_struct, scx.slice)) return SCALAR_VALUE; + if (off >= offsetof(struct task_struct, scx.disallow) && + off + size <= offsetofend(struct task_struct, scx.disallow)) + return SCALAR_VALUE; } return -EACCES; diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h index 56fcdb0b2c05..33a9f7fe5832 100644 --- a/kernel/sched/ext.h +++ b/kernel/sched/ext.h @@ -35,6 +35,7 @@ void scx_pre_fork(struct task_struct *p); int scx_fork(struct task_struct *p); void scx_post_fork(struct task_struct *p); void scx_cancel_fork(struct task_struct *p); +int scx_check_setscheduler(struct task_struct *p, int policy); bool task_should_scx(struct task_struct *p); void init_sched_ext_class(void); @@ -72,6 +73,7 @@ static inline void scx_pre_fork(struct task_struct *p) {} static inline int scx_fork(struct task_struct *p) { return 0; } static inline void scx_post_fork(struct task_struct *p) {} static inline void scx_cancel_fork(struct task_struct *p) {} +static inline int scx_check_setscheduler(struct task_struct *p, int policy) { return 0; } static inline bool task_on_scx(const struct task_struct *p) { return false; } static inline void init_sched_ext_class(void) {} diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c index 18d44d180db1..4fa59c9f69ac 100644 --- a/kernel/sched/syscalls.c +++ b/kernel/sched/syscalls.c @@ -714,6 +714,10 @@ recheck: goto unlock; } + retval = scx_check_setscheduler(p, policy); + if (retval) + goto unlock; + /* * If not changing anything there's no need to proceed further, * but store a possible modification of reset_on_fork. diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c index 8beae08dfdc7..5ff217c4bfa0 100644 --- a/tools/sched_ext/scx_qmap.bpf.c +++ b/tools/sched_ext/scx_qmap.bpf.c @@ -32,6 +32,7 @@ const volatile u64 slice_ns = SCX_SLICE_DFL; const volatile u32 stall_user_nth; const volatile u32 stall_kernel_nth; const volatile u32 dsp_batch; +const volatile s32 disallow_tgid; u32 test_error_cnt; @@ -243,6 +244,9 @@ void BPF_STRUCT_OPS(qmap_dispatch, s32 cpu, struct task_struct *prev) s32 BPF_STRUCT_OPS(qmap_init_task, struct task_struct *p, struct scx_init_task_args *args) { + if (p->tgid == disallow_tgid) + p->scx.disallow = true; + /* * @p is new. Let's ensure that its task_ctx is available. We can sleep * in this function and the following will automatically use GFP_KERNEL. diff --git a/tools/sched_ext/scx_qmap.c b/tools/sched_ext/scx_qmap.c index 6e9e9726cd62..a2614994cfaa 100644 --- a/tools/sched_ext/scx_qmap.c +++ b/tools/sched_ext/scx_qmap.c @@ -19,13 +19,15 @@ const char help_fmt[] = "\n" "See the top-level comment in .bpf.c for more details.\n" "\n" -"Usage: %s [-s SLICE_US] [-e COUNT] [-t COUNT] [-T COUNT] [-b COUNT] [-p] [-v]\n" +"Usage: %s [-s SLICE_US] [-e COUNT] [-t COUNT] [-T COUNT] [-b COUNT]\n" +" [-d PID] [-p] [-v]\n" "\n" " -s SLICE_US Override slice duration\n" " -e COUNT Trigger scx_bpf_error() after COUNT enqueues\n" " -t COUNT Stall every COUNT'th user thread\n" " -T COUNT Stall every COUNT'th kernel thread\n" " -b COUNT Dispatch upto COUNT tasks together\n" +" -d PID Disallow a process from switching into SCHED_EXT (-1 for self)\n" " -p Switch only tasks on SCHED_EXT policy intead of all\n" " -v Print libbpf debug messages\n" " -h Display this help and exit\n"; @@ -57,7 +59,7 @@ int main(int argc, char **argv) skel = SCX_OPS_OPEN(qmap_ops, scx_qmap); - while ((opt = getopt(argc, argv, "s:e:t:T:b:pvh")) != -1) { + while ((opt = getopt(argc, argv, "s:e:t:T:b:d:pvh")) != -1) { switch (opt) { case 's': skel->rodata->slice_ns = strtoull(optarg, NULL, 0) * 1000; @@ -74,6 +76,11 @@ int main(int argc, char **argv) case 'b': skel->rodata->dsp_batch = strtoul(optarg, NULL, 0); break; + case 'd': + skel->rodata->disallow_tgid = strtol(optarg, NULL, 0); + if (skel->rodata->disallow_tgid < 0) + skel->rodata->disallow_tgid = getpid(); + break; case 'p': skel->struct_ops.qmap_ops->flags |= SCX_OPS_SWITCH_PARTIAL; break; -- cgit v1.2.3 From 1538e33995eaf3f315cbb5506019b9f913ed8555 Mon Sep 17 00:00:00 2001 From: David Vernet Date: Tue, 18 Jun 2024 10:09:18 -1000 Subject: sched_ext: Print sched_ext info when dumping stack It would be useful to see what the sched_ext scheduler state is, and what scheduler is running, when we're dumping a task's stack. This patch therefore adds a new print_scx_info() function that's called in the same context as print_worker_info() and print_stop_info(). An example dump follows. BUG: kernel NULL pointer dereference, address: 0000000000000999 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 0 P4D 0 Oops: 0002 [#1] PREEMPT SMP CPU: 13 PID: 2047 Comm: insmod Tainted: G O 6.6.0-work-10323-gb58d4cae8e99-dirty #34 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS unknown 2/2/2022 Sched_ext: qmap (enabled+all), task: runnable_at=-17ms RIP: 0010:init_module+0x9/0x1000 [test_module] ... v3: - scx_ops_enable_state_str[] definition moved to an earlier patch as it's now used by core implementation. - Convert jiffy delta to msecs using jiffies_to_msecs() instead of multiplying by (HZ / MSEC_PER_SEC). The conversion is implemented in jiffies_delta_msecs(). v2: - We are now using scx_ops_enable_state_str[] outside CONFIG_SCHED_DEBUG. Move it outside of CONFIG_SCHED_DEBUG and to the top. This was reported by Changwoo and Andrea. Signed-off-by: David Vernet Reported-by: Changwoo Min Reported-by: Andrea Righi Signed-off-by: Tejun Heo --- include/linux/sched/ext.h | 2 ++ kernel/sched/core.c | 1 + kernel/sched/ext.c | 53 +++++++++++++++++++++++++++++++++++++++++++++++ lib/dump_stack.c | 1 + 4 files changed, 57 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index ea7c501ac819..85fb5dc725ef 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -155,10 +155,12 @@ struct sched_ext_entity { }; void sched_ext_free(struct task_struct *p); +void print_scx_info(const char *log_lvl, struct task_struct *p); #else /* !CONFIG_SCHED_CLASS_EXT */ static inline void sched_ext_free(struct task_struct *p) {} +static inline void print_scx_info(const char *log_lvl, struct task_struct *p) {} #endif /* CONFIG_SCHED_CLASS_EXT */ #endif /* _LINUX_SCHED_EXT_H */ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f4365becdc13..1a3144c80af8 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7486,6 +7486,7 @@ void sched_show_task(struct task_struct *p) print_worker_info(KERN_INFO, p); print_stop_info(KERN_INFO, p); + print_scx_info(KERN_INFO, p); show_stack(p, NULL, KERN_INFO); put_task_stack(p); } diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 8ff30b80e862..6f4de29d7372 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -586,6 +586,14 @@ static __printf(3, 4) void scx_ops_exit_kind(enum scx_exit_kind kind, #define SCX_HAS_OP(op) static_branch_likely(&scx_has_op[SCX_OP_IDX(op)]) +static long jiffies_delta_msecs(unsigned long at, unsigned long now) +{ + if (time_after(at, now)) + return jiffies_to_msecs(at - now); + else + return -(long)jiffies_to_msecs(now - at); +} + /* if the highest set bit is N, return a mask with bits [N+1, 31] set */ static u32 higher_bits(u32 flags) { @@ -3715,6 +3723,51 @@ static const struct sysrq_key_op sysrq_sched_ext_reset_op = { .enable_mask = SYSRQ_ENABLE_RTNICE, }; +/** + * print_scx_info - print out sched_ext scheduler state + * @log_lvl: the log level to use when printing + * @p: target task + * + * If a sched_ext scheduler is enabled, print the name and state of the + * scheduler. If @p is on sched_ext, print further information about the task. + * + * This function can be safely called on any task as long as the task_struct + * itself is accessible. While safe, this function isn't synchronized and may + * print out mixups or garbages of limited length. + */ +void print_scx_info(const char *log_lvl, struct task_struct *p) +{ + enum scx_ops_enable_state state = scx_ops_enable_state(); + const char *all = READ_ONCE(scx_switching_all) ? "+all" : ""; + char runnable_at_buf[22] = "?"; + struct sched_class *class; + unsigned long runnable_at; + + if (state == SCX_OPS_DISABLED) + return; + + /* + * Carefully check if the task was running on sched_ext, and then + * carefully copy the time it's been runnable, and its state. + */ + if (copy_from_kernel_nofault(&class, &p->sched_class, sizeof(class)) || + class != &ext_sched_class) { + printk("%sSched_ext: %s (%s%s)", log_lvl, scx_ops.name, + scx_ops_enable_state_str[state], all); + return; + } + + if (!copy_from_kernel_nofault(&runnable_at, &p->scx.runnable_at, + sizeof(runnable_at))) + scnprintf(runnable_at_buf, sizeof(runnable_at_buf), "%+ldms", + jiffies_delta_msecs(runnable_at, jiffies)); + + /* print everything onto one line to conserve console space */ + printk("%sSched_ext: %s (%s%s), task: runnable_at=%s", + log_lvl, scx_ops.name, scx_ops_enable_state_str[state], all, + runnable_at_buf); +} + void __init init_sched_ext_class(void) { s32 cpu, v; diff --git a/lib/dump_stack.c b/lib/dump_stack.c index 222c6d6c8281..9581ef4efec5 100644 --- a/lib/dump_stack.c +++ b/lib/dump_stack.c @@ -68,6 +68,7 @@ void dump_stack_print_info(const char *log_lvl) print_worker_info(log_lvl, current); print_stop_info(log_lvl, current); + print_scx_info(log_lvl, current); } /** -- cgit v1.2.3 From 81aae789181b5850d77dfdf74d4b85c63f0705e9 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 18 Jun 2024 10:09:19 -1000 Subject: sched_ext: Implement scx_bpf_kick_cpu() and task preemption support It's often useful to wake up and/or trigger reschedule on other CPUs. This patch adds scx_bpf_kick_cpu() kfunc helper that BPF scheduler can call to kick the target CPU into the scheduling path. As a sched_ext task relinquishes its CPU only after its slice is depleted, this patch also adds SCX_KICK_PREEMPT and SCX_ENQ_PREEMPT which clears the slice of the target CPU's current task to guarantee that sched_ext's scheduling path runs on the CPU. If SCX_KICK_IDLE is specified, the target CPU is kicked iff the CPU is idle to guarantee that the target CPU will go through at least one full sched_ext scheduling cycle after the kicking. This can be used to wake up idle CPUs without incurring unnecessary overhead if it isn't currently idle. As a demonstration of how backward compatibility can be supported using BPF CO-RE, tools/sched_ext/include/scx/compat.bpf.h is added. It provides __COMPAT_scx_bpf_kick_cpu_IDLE() which uses SCX_KICK_IDLE if available or becomes a regular kicking otherwise. This allows schedulers to use the new SCX_KICK_IDLE while maintaining support for older kernels. The plan is to temporarily use compat helpers to ease API updates and drop them after a few kernel releases. v5: - SCX_KICK_IDLE added. Note that this also adds a compat mechanism for schedulers so that they can support kernels without SCX_KICK_IDLE. This is useful as a demonstration of how new feature flags can be added in a backward compatible way. - kick_cpus_irq_workfn() reimplemented so that it touches the pending cpumasks only as necessary to reduce kicking overhead on machines with a lot of CPUs. - tools/sched_ext/include/scx/compat.bpf.h added. v4: - Move example scheduler to its own patch. v3: - Make scx_example_central switch all tasks by default. - Convert to BPF inline iterators. v2: - Julia Lawall reported that scx_example_central can overflow the dispatch buffer and malfunction. As scheduling for other CPUs can't be handled by the automatic retry mechanism, fix by implementing an explicit overflow and retry handling. - Updated to use generic BPF cpumask helpers. Signed-off-by: Tejun Heo Reviewed-by: David Vernet Acked-by: Josh Don Acked-by: Hao Luo Acked-by: Barret Rhoden --- include/linux/sched/ext.h | 4 + kernel/sched/ext.c | 225 +++++++++++++++++++++++++++++-- kernel/sched/sched.h | 10 ++ tools/sched_ext/include/scx/common.bpf.h | 1 + 4 files changed, 227 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index 85fb5dc725ef..3b2809b980ac 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -134,6 +134,10 @@ struct sched_ext_entity { * scx_bpf_dispatch() but can also be modified directly by the BPF * scheduler. Automatically decreased by SCX as the task executes. On * depletion, a scheduling event is triggered. + * + * This value is cleared to zero if the task is preempted by + * %SCX_KICK_PREEMPT and shouldn't be used to determine how long the + * task ran. Use p->se.sum_exec_runtime instead. */ u64 slice; diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 66bb9cf075f0..213793d086d7 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -412,6 +412,14 @@ enum scx_enq_flags { /* high 32bits are SCX specific */ + /* + * Set the following to trigger preemption when calling + * scx_bpf_dispatch() with a local dsq as the target. The slice of the + * current task is cleared to zero and the CPU is kicked into the + * scheduling path. Implies %SCX_ENQ_HEAD. + */ + SCX_ENQ_PREEMPT = 1LLU << 32, + /* * The task being enqueued is the only task available for the cpu. By * default, ext core keeps executing such tasks but when @@ -441,6 +449,24 @@ enum scx_pick_idle_cpu_flags { SCX_PICK_IDLE_CORE = 1LLU << 0, /* pick a CPU whose SMT siblings are also idle */ }; +enum scx_kick_flags { + /* + * Kick the target CPU if idle. Guarantees that the target CPU goes + * through at least one full scheduling cycle before going idle. If the + * target CPU can be determined to be currently not idle and going to go + * through a scheduling cycle before going idle, noop. + */ + SCX_KICK_IDLE = 1LLU << 0, + + /* + * Preempt the current task and execute the dispatch path. If the + * current task of the target CPU is an SCX task, its ->scx.slice is + * cleared to zero before the scheduling path is invoked so that the + * task expires and the dispatch path is invoked. + */ + SCX_KICK_PREEMPT = 1LLU << 1, +}; + enum scx_ops_enable_state { SCX_OPS_PREPPING, SCX_OPS_ENABLING, @@ -1019,7 +1045,7 @@ static void dispatch_enqueue(struct scx_dispatch_q *dsq, struct task_struct *p, } } - if (enq_flags & SCX_ENQ_HEAD) + if (enq_flags & (SCX_ENQ_HEAD | SCX_ENQ_PREEMPT)) list_add(&p->scx.dsq_node, &dsq->list); else list_add_tail(&p->scx.dsq_node, &dsq->list); @@ -1045,8 +1071,16 @@ static void dispatch_enqueue(struct scx_dispatch_q *dsq, struct task_struct *p, if (is_local) { struct rq *rq = container_of(dsq, struct rq, scx.local_dsq); + bool preempt = false; + + if ((enq_flags & SCX_ENQ_PREEMPT) && p != rq->curr && + rq->curr->sched_class == &ext_sched_class) { + rq->curr->scx.slice = 0; + preempt = true; + } - if (sched_class_above(&ext_sched_class, rq->curr->sched_class)) + if (preempt || sched_class_above(&ext_sched_class, + rq->curr->sched_class)) resched_curr(rq); } else { raw_spin_unlock(&dsq->lock); @@ -1872,8 +1906,10 @@ static int balance_scx(struct rq *rq, struct task_struct *prev, { struct scx_dsp_ctx *dspc = this_cpu_ptr(scx_dsp_ctx); bool prev_on_scx = prev->sched_class == &ext_sched_class; + bool has_tasks = false; lockdep_assert_rq_held(rq); + rq->scx.flags |= SCX_RQ_BALANCING; if (prev_on_scx) { WARN_ON_ONCE(prev->scx.flags & SCX_TASK_BAL_KEEP); @@ -1890,19 +1926,19 @@ static int balance_scx(struct rq *rq, struct task_struct *prev, if ((prev->scx.flags & SCX_TASK_QUEUED) && prev->scx.slice && !scx_ops_bypassing()) { prev->scx.flags |= SCX_TASK_BAL_KEEP; - return 1; + goto has_tasks; } } /* if there already are tasks to run, nothing to do */ if (rq->scx.local_dsq.nr) - return 1; + goto has_tasks; if (consume_dispatch_q(rq, rf, &scx_dsq_global)) - return 1; + goto has_tasks; if (!SCX_HAS_OP(dispatch) || scx_ops_bypassing() || !scx_rq_online(rq)) - return 0; + goto out; dspc->rq = rq; dspc->rf = rf; @@ -1923,12 +1959,18 @@ static int balance_scx(struct rq *rq, struct task_struct *prev, flush_dispatch_buf(rq, rf); if (rq->scx.local_dsq.nr) - return 1; + goto has_tasks; if (consume_dispatch_q(rq, rf, &scx_dsq_global)) - return 1; + goto has_tasks; } while (dspc->nr_tasks); - return 0; + goto out; + +has_tasks: + has_tasks = true; +out: + rq->scx.flags &= ~SCX_RQ_BALANCING; + return has_tasks; } static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first) @@ -2666,7 +2708,8 @@ int scx_check_setscheduler(struct task_struct *p, int policy) * Omitted operations: * * - wakeup_preempt: NOOP as it isn't useful in the wakeup path because the task - * isn't tied to the CPU at that point. + * isn't tied to the CPU at that point. Preemption is implemented by resetting + * the victim task's slice to 0 and triggering reschedule on the target CPU. * * - migrate_task_rq: Unnecessary as task to cpu mapping is transient. * @@ -2902,6 +2945,9 @@ bool task_should_scx(struct task_struct *p) * of the queue. * * d. pick_next_task() suppresses zero slice warning. + * + * e. scx_bpf_kick_cpu() is disabled to avoid irq_work malfunction during PM + * operations. */ static void scx_ops_bypass(bool bypass) { @@ -3410,11 +3456,21 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len) seq_buf_init(&ns, buf, avail); dump_newline(&ns); - dump_line(&ns, "CPU %-4d: nr_run=%u ops_qseq=%lu", - cpu, rq->scx.nr_running, rq->scx.ops_qseq); + dump_line(&ns, "CPU %-4d: nr_run=%u flags=0x%x ops_qseq=%lu", + cpu, rq->scx.nr_running, rq->scx.flags, + rq->scx.ops_qseq); dump_line(&ns, " curr=%s[%d] class=%ps", rq->curr->comm, rq->curr->pid, rq->curr->sched_class); + if (!cpumask_empty(rq->scx.cpus_to_kick)) + dump_line(&ns, " cpus_to_kick : %*pb", + cpumask_pr_args(rq->scx.cpus_to_kick)); + if (!cpumask_empty(rq->scx.cpus_to_kick_if_idle)) + dump_line(&ns, " idle_to_kick : %*pb", + cpumask_pr_args(rq->scx.cpus_to_kick_if_idle)); + if (!cpumask_empty(rq->scx.cpus_to_preempt)) + dump_line(&ns, " cpus_to_preempt: %*pb", + cpumask_pr_args(rq->scx.cpus_to_preempt)); used = seq_buf_used(&ns); if (SCX_HAS_OP(dump_cpu)) { @@ -4085,6 +4141,82 @@ static const struct sysrq_key_op sysrq_sched_ext_dump_op = { .enable_mask = SYSRQ_ENABLE_RTNICE, }; +static bool can_skip_idle_kick(struct rq *rq) +{ + lockdep_assert_rq_held(rq); + + /* + * We can skip idle kicking if @rq is going to go through at least one + * full SCX scheduling cycle before going idle. Just checking whether + * curr is not idle is insufficient because we could be racing + * balance_one() trying to pull the next task from a remote rq, which + * may fail, and @rq may become idle afterwards. + * + * The race window is small and we don't and can't guarantee that @rq is + * only kicked while idle anyway. Skip only when sure. + */ + return !is_idle_task(rq->curr) && !(rq->scx.flags & SCX_RQ_BALANCING); +} + +static void kick_one_cpu(s32 cpu, struct rq *this_rq) +{ + struct rq *rq = cpu_rq(cpu); + struct scx_rq *this_scx = &this_rq->scx; + unsigned long flags; + + raw_spin_rq_lock_irqsave(rq, flags); + + /* + * During CPU hotplug, a CPU may depend on kicking itself to make + * forward progress. Allow kicking self regardless of online state. + */ + if (cpu_online(cpu) || cpu == cpu_of(this_rq)) { + if (cpumask_test_cpu(cpu, this_scx->cpus_to_preempt)) { + if (rq->curr->sched_class == &ext_sched_class) + rq->curr->scx.slice = 0; + cpumask_clear_cpu(cpu, this_scx->cpus_to_preempt); + } + + resched_curr(rq); + } else { + cpumask_clear_cpu(cpu, this_scx->cpus_to_preempt); + } + + raw_spin_rq_unlock_irqrestore(rq, flags); +} + +static void kick_one_cpu_if_idle(s32 cpu, struct rq *this_rq) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + + raw_spin_rq_lock_irqsave(rq, flags); + + if (!can_skip_idle_kick(rq) && + (cpu_online(cpu) || cpu == cpu_of(this_rq))) + resched_curr(rq); + + raw_spin_rq_unlock_irqrestore(rq, flags); +} + +static void kick_cpus_irq_workfn(struct irq_work *irq_work) +{ + struct rq *this_rq = this_rq(); + struct scx_rq *this_scx = &this_rq->scx; + s32 cpu; + + for_each_cpu(cpu, this_scx->cpus_to_kick) { + kick_one_cpu(cpu, this_rq); + cpumask_clear_cpu(cpu, this_scx->cpus_to_kick); + cpumask_clear_cpu(cpu, this_scx->cpus_to_kick_if_idle); + } + + for_each_cpu(cpu, this_scx->cpus_to_kick_if_idle) { + kick_one_cpu_if_idle(cpu, this_rq); + cpumask_clear_cpu(cpu, this_scx->cpus_to_kick_if_idle); + } +} + /** * print_scx_info - print out sched_ext scheduler state * @log_lvl: the log level to use when printing @@ -4139,7 +4271,7 @@ void __init init_sched_ext_class(void) * definitions so that BPF scheduler implementations can use them * through the generated vmlinux.h. */ - WRITE_ONCE(v, SCX_ENQ_WAKEUP | SCX_DEQ_SLEEP); + WRITE_ONCE(v, SCX_ENQ_WAKEUP | SCX_DEQ_SLEEP | SCX_KICK_PREEMPT); BUG_ON(rhashtable_init(&dsq_hash, &dsq_hash_params)); init_dsq(&scx_dsq_global, SCX_DSQ_GLOBAL); @@ -4152,6 +4284,11 @@ void __init init_sched_ext_class(void) init_dsq(&rq->scx.local_dsq, SCX_DSQ_LOCAL); INIT_LIST_HEAD(&rq->scx.runnable_list); + + BUG_ON(!zalloc_cpumask_var(&rq->scx.cpus_to_kick, GFP_KERNEL)); + BUG_ON(!zalloc_cpumask_var(&rq->scx.cpus_to_kick_if_idle, GFP_KERNEL)); + BUG_ON(!zalloc_cpumask_var(&rq->scx.cpus_to_preempt, GFP_KERNEL)); + init_irq_work(&rq->scx.kick_cpus_irq_work, kick_cpus_irq_workfn); } register_sysrq_key('S', &sysrq_sched_ext_reset_op); @@ -4438,6 +4575,67 @@ static const struct btf_kfunc_id_set scx_kfunc_set_dispatch = { __bpf_kfunc_start_defs(); +/** + * scx_bpf_kick_cpu - Trigger reschedule on a CPU + * @cpu: cpu to kick + * @flags: %SCX_KICK_* flags + * + * Kick @cpu into rescheduling. This can be used to wake up an idle CPU or + * trigger rescheduling on a busy CPU. This can be called from any online + * scx_ops operation and the actual kicking is performed asynchronously through + * an irq work. + */ +__bpf_kfunc void scx_bpf_kick_cpu(s32 cpu, u64 flags) +{ + struct rq *this_rq; + unsigned long irq_flags; + + if (!ops_cpu_valid(cpu, NULL)) + return; + + /* + * While bypassing for PM ops, IRQ handling may not be online which can + * lead to irq_work_queue() malfunction such as infinite busy wait for + * IRQ status update. Suppress kicking. + */ + if (scx_ops_bypassing()) + return; + + local_irq_save(irq_flags); + + this_rq = this_rq(); + + /* + * Actual kicking is bounced to kick_cpus_irq_workfn() to avoid nesting + * rq locks. We can probably be smarter and avoid bouncing if called + * from ops which don't hold a rq lock. + */ + if (flags & SCX_KICK_IDLE) { + struct rq *target_rq = cpu_rq(cpu); + + if (unlikely(flags & SCX_KICK_PREEMPT)) + scx_ops_error("PREEMPT cannot be used with SCX_KICK_IDLE"); + + if (raw_spin_rq_trylock(target_rq)) { + if (can_skip_idle_kick(target_rq)) { + raw_spin_rq_unlock(target_rq); + goto out; + } + raw_spin_rq_unlock(target_rq); + } + cpumask_set_cpu(cpu, this_rq->scx.cpus_to_kick_if_idle); + } else { + cpumask_set_cpu(cpu, this_rq->scx.cpus_to_kick); + + if (flags & SCX_KICK_PREEMPT) + cpumask_set_cpu(cpu, this_rq->scx.cpus_to_preempt); + } + + irq_work_queue(&this_rq->scx.kick_cpus_irq_work); +out: + local_irq_restore(irq_flags); +} + /** * scx_bpf_dsq_nr_queued - Return the number of queued tasks * @dsq_id: id of the DSQ @@ -4836,6 +5034,7 @@ __bpf_kfunc s32 scx_bpf_task_cpu(const struct task_struct *p) __bpf_kfunc_end_defs(); BTF_KFUNCS_START(scx_kfunc_ids_any) +BTF_ID_FLAGS(func, scx_bpf_kick_cpu) BTF_ID_FLAGS(func, scx_bpf_dsq_nr_queued) BTF_ID_FLAGS(func, scx_bpf_destroy_dsq) BTF_ID_FLAGS(func, scx_bpf_exit_bstr, KF_TRUSTED_ARGS) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 2960e153c3a7..d9054eb4ba82 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -724,12 +724,22 @@ struct cfs_rq { }; #ifdef CONFIG_SCHED_CLASS_EXT +/* scx_rq->flags, protected by the rq lock */ +enum scx_rq_flags { + SCX_RQ_BALANCING = 1 << 1, +}; + struct scx_rq { struct scx_dispatch_q local_dsq; struct list_head runnable_list; /* runnable tasks on this rq */ unsigned long ops_qseq; u64 extra_enq_flags; /* see move_task_to_local_dsq() */ u32 nr_running; + u32 flags; + cpumask_var_t cpus_to_kick; + cpumask_var_t cpus_to_kick_if_idle; + cpumask_var_t cpus_to_preempt; + struct irq_work kick_cpus_irq_work; }; #endif /* CONFIG_SCHED_CLASS_EXT */ diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h index 3ea5cdf58bc7..421118bc56ff 100644 --- a/tools/sched_ext/include/scx/common.bpf.h +++ b/tools/sched_ext/include/scx/common.bpf.h @@ -34,6 +34,7 @@ void scx_bpf_dispatch(struct task_struct *p, u64 dsq_id, u64 slice, u64 enq_flag u32 scx_bpf_dispatch_nr_slots(void) __ksym; void scx_bpf_dispatch_cancel(void) __ksym; bool scx_bpf_consume(u64 dsq_id) __ksym; +void scx_bpf_kick_cpu(s32 cpu, u64 flags) __ksym; s32 scx_bpf_dsq_nr_queued(u64 dsq_id) __ksym; void scx_bpf_destroy_dsq(u64 dsq_id) __ksym; void scx_bpf_exit_bstr(s64 exit_code, char *fmt, unsigned long long *data, u32 data__sz) __ksym __weak; -- cgit v1.2.3 From 22a920209ab6aa4f8ec960ed81041643fddeaec6 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 18 Jun 2024 10:09:19 -1000 Subject: sched_ext: Implement tickless support Allow BPF schedulers to indicate tickless operation by setting p->scx.slice to SCX_SLICE_INF. A CPU whose current task has infinte slice goes into tickless operation. scx_central is updated to use tickless operations for all tasks and instead use a BPF timer to expire slices. This also uses the SCX_ENQ_PREEMPT and task state tracking added by the previous patches. Currently, there is no way to pin the timer on the central CPU, so it may end up on one of the worker CPUs; however, outside of that, the worker CPUs can go tickless both while running sched_ext tasks and idling. With schbench running, scx_central shows: root@test ~# grep ^LOC /proc/interrupts; sleep 10; grep ^LOC /proc/interrupts LOC: 142024 656 664 449 Local timer interrupts LOC: 161663 663 665 449 Local timer interrupts Without it: root@test ~ [SIGINT]# grep ^LOC /proc/interrupts; sleep 10; grep ^LOC /proc/interrupts LOC: 188778 3142 3793 3993 Local timer interrupts LOC: 198993 5314 6323 6438 Local timer interrupts While scx_central itself is too barebone to be useful as a production scheduler, a more featureful central scheduler can be built using the same approach. Google's experience shows that such an approach can have significant benefits for certain applications such as VM hosting. v4: Allow operation even if BPF_F_TIMER_CPU_PIN is not available. v3: Pin the central scheduler's timer on the central_cpu using BPF_F_TIMER_CPU_PIN. v2: Convert to BPF inline iterators. Signed-off-by: Tejun Heo Reviewed-by: David Vernet Acked-by: Josh Don Acked-by: Hao Luo Acked-by: Barret Rhoden --- include/linux/sched/ext.h | 1 + kernel/sched/core.c | 11 ++- kernel/sched/ext.c | 52 ++++++++++++- kernel/sched/ext.h | 2 + kernel/sched/sched.h | 1 + tools/sched_ext/scx_central.bpf.c | 159 ++++++++++++++++++++++++++++++++++++-- tools/sched_ext/scx_central.c | 29 ++++++- 7 files changed, 242 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index 3b2809b980ac..6f1a4977e9f8 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -16,6 +16,7 @@ enum scx_public_consts { SCX_OPS_NAME_LEN = 128, SCX_SLICE_DFL = 20 * 1000000, /* 20ms */ + SCX_SLICE_INF = U64_MAX, /* infinite, implies nohz */ }; /* diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 1a3144c80af8..d5eff4036be7 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1256,11 +1256,14 @@ bool sched_can_stop_tick(struct rq *rq) return true; /* - * If there are no DL,RR/FIFO tasks, there must only be CFS tasks left; - * if there's more than one we need the tick for involuntary - * preemption. + * If there are no DL,RR/FIFO tasks, there must only be CFS or SCX tasks + * left. For CFS, if there's more than one we need the tick for + * involuntary preemption. For SCX, ask. */ - if (rq->nr_running > 1) + if (!scx_switched_all() && rq->nr_running > 1) + return false; + + if (scx_enabled() && !scx_can_stop_tick(rq)) return false; /* diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 2e652f7b8f54..ce32fc6b05cd 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -1086,7 +1086,8 @@ static void update_curr_scx(struct rq *rq) account_group_exec_runtime(curr, delta_exec); cgroup_account_cputime(curr, delta_exec); - curr->scx.slice -= min(curr->scx.slice, delta_exec); + if (curr->scx.slice != SCX_SLICE_INF) + curr->scx.slice -= min(curr->scx.slice, delta_exec); } static void dsq_mod_nr(struct scx_dispatch_q *dsq, s32 delta) @@ -2093,6 +2094,28 @@ static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first) SCX_CALL_OP(SCX_KF_REST, running, p); clr_task_runnable(p, true); + + /* + * @p is getting newly scheduled or got kicked after someone updated its + * slice. Refresh whether tick can be stopped. See scx_can_stop_tick(). + */ + if ((p->scx.slice == SCX_SLICE_INF) != + (bool)(rq->scx.flags & SCX_RQ_CAN_STOP_TICK)) { + if (p->scx.slice == SCX_SLICE_INF) + rq->scx.flags |= SCX_RQ_CAN_STOP_TICK; + else + rq->scx.flags &= ~SCX_RQ_CAN_STOP_TICK; + + sched_update_tick_dependency(rq); + + /* + * For now, let's refresh the load_avgs just when transitioning + * in and out of nohz. In the future, we might want to add a + * mechanism which calls the following periodically on + * tick-stopped CPUs. + */ + update_other_load_avgs(rq); + } } static void put_prev_task_scx(struct rq *rq, struct task_struct *p) @@ -2818,6 +2841,26 @@ int scx_check_setscheduler(struct task_struct *p, int policy) return 0; } +#ifdef CONFIG_NO_HZ_FULL +bool scx_can_stop_tick(struct rq *rq) +{ + struct task_struct *p = rq->curr; + + if (scx_ops_bypassing()) + return false; + + if (p->sched_class != &ext_sched_class) + return true; + + /* + * @rq can dispatch from different DSQs, so we can't tell whether it + * needs the tick or not by looking at nr_running. Allow stopping ticks + * iff the BPF scheduler indicated so. See set_next_task_scx(). + */ + return rq->scx.flags & SCX_RQ_CAN_STOP_TICK; +} +#endif + /* * Omitted operations: * @@ -3120,6 +3163,9 @@ static void scx_ops_bypass(bool bypass) } rq_unlock_irqrestore(rq, &rf); + + /* kick to restore ticks */ + resched_cpu(cpu); } } @@ -4576,7 +4622,9 @@ __bpf_kfunc_start_defs(); * BPF locks (in the future when BPF introduces more flexible locking). * * @p is allowed to run for @slice. The scheduling path is triggered on slice - * exhaustion. If zero, the current residual slice is maintained. + * exhaustion. If zero, the current residual slice is maintained. If + * %SCX_SLICE_INF, @p never expires and the BPF scheduler must kick the CPU with + * scx_bpf_kick_cpu() to trigger scheduling. */ __bpf_kfunc void scx_bpf_dispatch(struct task_struct *p, u64 dsq_id, u64 slice, u64 enq_flags) diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h index 33a9f7fe5832..6ed946f72489 100644 --- a/kernel/sched/ext.h +++ b/kernel/sched/ext.h @@ -35,6 +35,7 @@ void scx_pre_fork(struct task_struct *p); int scx_fork(struct task_struct *p); void scx_post_fork(struct task_struct *p); void scx_cancel_fork(struct task_struct *p); +bool scx_can_stop_tick(struct rq *rq); int scx_check_setscheduler(struct task_struct *p, int policy); bool task_should_scx(struct task_struct *p); void init_sched_ext_class(void); @@ -73,6 +74,7 @@ static inline void scx_pre_fork(struct task_struct *p) {} static inline int scx_fork(struct task_struct *p) { return 0; } static inline void scx_post_fork(struct task_struct *p) {} static inline void scx_cancel_fork(struct task_struct *p) {} +static inline bool scx_can_stop_tick(struct rq *rq) { return true; } static inline int scx_check_setscheduler(struct task_struct *p, int policy) { return 0; } static inline bool task_on_scx(const struct task_struct *p) { return false; } static inline void init_sched_ext_class(void) {} diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index d9054eb4ba82..b3c578cb43cd 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -727,6 +727,7 @@ struct cfs_rq { /* scx_rq->flags, protected by the rq lock */ enum scx_rq_flags { SCX_RQ_BALANCING = 1 << 1, + SCX_RQ_CAN_STOP_TICK = 1 << 2, }; struct scx_rq { diff --git a/tools/sched_ext/scx_central.bpf.c b/tools/sched_ext/scx_central.bpf.c index 428b2262faa3..1d8fd570eaa7 100644 --- a/tools/sched_ext/scx_central.bpf.c +++ b/tools/sched_ext/scx_central.bpf.c @@ -13,7 +13,26 @@ * through per-CPU BPF queues. The current design is chosen to maximally * utilize and verify various SCX mechanisms such as LOCAL_ON dispatching. * - * b. Preemption + * b. Tickless operation + * + * All tasks are dispatched with the infinite slice which allows stopping the + * ticks on CONFIG_NO_HZ_FULL kernels running with the proper nohz_full + * parameter. The tickless operation can be observed through + * /proc/interrupts. + * + * Periodic switching is enforced by a periodic timer checking all CPUs and + * preempting them as necessary. Unfortunately, BPF timer currently doesn't + * have a way to pin to a specific CPU, so the periodic timer isn't pinned to + * the central CPU. + * + * c. Preemption + * + * Kthreads are unconditionally queued to the head of a matching local dsq + * and dispatched with SCX_DSQ_PREEMPT. This ensures that a kthread is always + * prioritized over user threads, which is required for ensuring forward + * progress as e.g. the periodic timer may run on a ksoftirqd and if the + * ksoftirqd gets starved by a user thread, there may not be anything else to + * vacate that user thread. * * SCX_KICK_PREEMPT is used to trigger scheduling and CPUs to move to the * next tasks. @@ -32,14 +51,17 @@ char _license[] SEC("license") = "GPL"; enum { FALLBACK_DSQ_ID = 0, + MS_TO_NS = 1000LLU * 1000, + TIMER_INTERVAL_NS = 1 * MS_TO_NS, }; const volatile s32 central_cpu; const volatile u32 nr_cpu_ids = 1; /* !0 for veristat, set during init */ const volatile u64 slice_ns = SCX_SLICE_DFL; +bool timer_pinned = true; u64 nr_total, nr_locals, nr_queued, nr_lost_pids; -u64 nr_dispatches, nr_mismatches, nr_retries; +u64 nr_timers, nr_dispatches, nr_mismatches, nr_retries; u64 nr_overflows; UEI_DEFINE(uei); @@ -52,6 +74,23 @@ struct { /* can't use percpu map due to bad lookups */ bool RESIZABLE_ARRAY(data, cpu_gimme_task); +u64 RESIZABLE_ARRAY(data, cpu_started_at); + +struct central_timer { + struct bpf_timer timer; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, u32); + __type(value, struct central_timer); +} central_timer SEC(".maps"); + +static bool vtime_before(u64 a, u64 b) +{ + return (s64)(a - b) < 0; +} s32 BPF_STRUCT_OPS(central_select_cpu, struct task_struct *p, s32 prev_cpu, u64 wake_flags) @@ -71,9 +110,22 @@ void BPF_STRUCT_OPS(central_enqueue, struct task_struct *p, u64 enq_flags) __sync_fetch_and_add(&nr_total, 1); + /* + * Push per-cpu kthreads at the head of local dsq's and preempt the + * corresponding CPU. This ensures that e.g. ksoftirqd isn't blocked + * behind other threads which is necessary for forward progress + * guarantee as we depend on the BPF timer which may run from ksoftirqd. + */ + if ((p->flags & PF_KTHREAD) && p->nr_cpus_allowed == 1) { + __sync_fetch_and_add(&nr_locals, 1); + scx_bpf_dispatch(p, SCX_DSQ_LOCAL, SCX_SLICE_INF, + enq_flags | SCX_ENQ_PREEMPT); + return; + } + if (bpf_map_push_elem(¢ral_q, &pid, 0)) { __sync_fetch_and_add(&nr_overflows, 1); - scx_bpf_dispatch(p, FALLBACK_DSQ_ID, SCX_SLICE_DFL, enq_flags); + scx_bpf_dispatch(p, FALLBACK_DSQ_ID, SCX_SLICE_INF, enq_flags); return; } @@ -106,7 +158,7 @@ static bool dispatch_to_cpu(s32 cpu) */ if (!bpf_cpumask_test_cpu(cpu, p->cpus_ptr)) { __sync_fetch_and_add(&nr_mismatches, 1); - scx_bpf_dispatch(p, FALLBACK_DSQ_ID, SCX_SLICE_DFL, 0); + scx_bpf_dispatch(p, FALLBACK_DSQ_ID, SCX_SLICE_INF, 0); bpf_task_release(p); /* * We might run out of dispatch buffer slots if we continue dispatching @@ -120,7 +172,7 @@ static bool dispatch_to_cpu(s32 cpu) } /* dispatch to local and mark that @cpu doesn't need more */ - scx_bpf_dispatch(p, SCX_DSQ_LOCAL_ON | cpu, SCX_SLICE_DFL, 0); + scx_bpf_dispatch(p, SCX_DSQ_LOCAL_ON | cpu, SCX_SLICE_INF, 0); if (cpu != central_cpu) scx_bpf_kick_cpu(cpu, SCX_KICK_IDLE); @@ -188,9 +240,102 @@ void BPF_STRUCT_OPS(central_dispatch, s32 cpu, struct task_struct *prev) } } +void BPF_STRUCT_OPS(central_running, struct task_struct *p) +{ + s32 cpu = scx_bpf_task_cpu(p); + u64 *started_at = ARRAY_ELEM_PTR(cpu_started_at, cpu, nr_cpu_ids); + if (started_at) + *started_at = bpf_ktime_get_ns() ?: 1; /* 0 indicates idle */ +} + +void BPF_STRUCT_OPS(central_stopping, struct task_struct *p, bool runnable) +{ + s32 cpu = scx_bpf_task_cpu(p); + u64 *started_at = ARRAY_ELEM_PTR(cpu_started_at, cpu, nr_cpu_ids); + if (started_at) + *started_at = 0; +} + +static int central_timerfn(void *map, int *key, struct bpf_timer *timer) +{ + u64 now = bpf_ktime_get_ns(); + u64 nr_to_kick = nr_queued; + s32 i, curr_cpu; + + curr_cpu = bpf_get_smp_processor_id(); + if (timer_pinned && (curr_cpu != central_cpu)) { + scx_bpf_error("Central timer ran on CPU %d, not central CPU %d", + curr_cpu, central_cpu); + return 0; + } + + bpf_for(i, 0, nr_cpu_ids) { + s32 cpu = (nr_timers + i) % nr_cpu_ids; + u64 *started_at; + + if (cpu == central_cpu) + continue; + + /* kick iff the current one exhausted its slice */ + started_at = ARRAY_ELEM_PTR(cpu_started_at, cpu, nr_cpu_ids); + if (started_at && *started_at && + vtime_before(now, *started_at + slice_ns)) + continue; + + /* and there's something pending */ + if (scx_bpf_dsq_nr_queued(FALLBACK_DSQ_ID) || + scx_bpf_dsq_nr_queued(SCX_DSQ_LOCAL_ON | cpu)) + ; + else if (nr_to_kick) + nr_to_kick--; + else + continue; + + scx_bpf_kick_cpu(cpu, SCX_KICK_PREEMPT); + } + + bpf_timer_start(timer, TIMER_INTERVAL_NS, BPF_F_TIMER_CPU_PIN); + __sync_fetch_and_add(&nr_timers, 1); + return 0; +} + int BPF_STRUCT_OPS_SLEEPABLE(central_init) { - return scx_bpf_create_dsq(FALLBACK_DSQ_ID, -1); + u32 key = 0; + struct bpf_timer *timer; + int ret; + + ret = scx_bpf_create_dsq(FALLBACK_DSQ_ID, -1); + if (ret) + return ret; + + timer = bpf_map_lookup_elem(¢ral_timer, &key); + if (!timer) + return -ESRCH; + + if (bpf_get_smp_processor_id() != central_cpu) { + scx_bpf_error("init from non-central CPU"); + return -EINVAL; + } + + bpf_timer_init(timer, ¢ral_timer, CLOCK_MONOTONIC); + bpf_timer_set_callback(timer, central_timerfn); + + ret = bpf_timer_start(timer, TIMER_INTERVAL_NS, BPF_F_TIMER_CPU_PIN); + /* + * BPF_F_TIMER_CPU_PIN is pretty new (>=6.7). If we're running in a + * kernel which doesn't have it, bpf_timer_start() will return -EINVAL. + * Retry without the PIN. This would be the perfect use case for + * bpf_core_enum_value_exists() but the enum type doesn't have a name + * and can't be used with bpf_core_enum_value_exists(). Oh well... + */ + if (ret == -EINVAL) { + timer_pinned = false; + ret = bpf_timer_start(timer, TIMER_INTERVAL_NS, 0); + } + if (ret) + scx_bpf_error("bpf_timer_start failed (%d)", ret); + return ret; } void BPF_STRUCT_OPS(central_exit, struct scx_exit_info *ei) @@ -209,6 +354,8 @@ SCX_OPS_DEFINE(central_ops, .select_cpu = (void *)central_select_cpu, .enqueue = (void *)central_enqueue, .dispatch = (void *)central_dispatch, + .running = (void *)central_running, + .stopping = (void *)central_stopping, .init = (void *)central_init, .exit = (void *)central_exit, .name = "central"); diff --git a/tools/sched_ext/scx_central.c b/tools/sched_ext/scx_central.c index 5f09fc666a63..fb3f50886552 100644 --- a/tools/sched_ext/scx_central.c +++ b/tools/sched_ext/scx_central.c @@ -48,6 +48,7 @@ int main(int argc, char **argv) struct bpf_link *link; __u64 seq = 0; __s32 opt; + cpu_set_t *cpuset; libbpf_set_print(libbpf_print_fn); signal(SIGINT, sigint_handler); @@ -77,10 +78,35 @@ int main(int argc, char **argv) /* Resize arrays so their element count is equal to cpu count. */ RESIZE_ARRAY(skel, data, cpu_gimme_task, skel->rodata->nr_cpu_ids); + RESIZE_ARRAY(skel, data, cpu_started_at, skel->rodata->nr_cpu_ids); SCX_OPS_LOAD(skel, central_ops, scx_central, uei); + + /* + * Affinitize the loading thread to the central CPU, as: + * - That's where the BPF timer is first invoked in the BPF program. + * - We probably don't want this user space component to take up a core + * from a task that would benefit from avoiding preemption on one of + * the tickless cores. + * + * Until BPF supports pinning the timer, it's not guaranteed that it + * will always be invoked on the central CPU. In practice, this + * suffices the majority of the time. + */ + cpuset = CPU_ALLOC(skel->rodata->nr_cpu_ids); + SCX_BUG_ON(!cpuset, "Failed to allocate cpuset"); + CPU_ZERO(cpuset); + CPU_SET(skel->rodata->central_cpu, cpuset); + SCX_BUG_ON(sched_setaffinity(0, sizeof(cpuset), cpuset), + "Failed to affinitize to central CPU %d (max %d)", + skel->rodata->central_cpu, skel->rodata->nr_cpu_ids - 1); + CPU_FREE(cpuset); + link = SCX_OPS_ATTACH(skel, central_ops, scx_central); + if (!skel->data->timer_pinned) + printf("WARNING : BPF_F_TIMER_CPU_PIN not available, timer not pinned to central\n"); + while (!exit_req && !UEI_EXITED(skel, uei)) { printf("[SEQ %llu]\n", seq++); printf("total :%10" PRIu64 " local:%10" PRIu64 " queued:%10" PRIu64 " lost:%10" PRIu64 "\n", @@ -88,7 +114,8 @@ int main(int argc, char **argv) skel->bss->nr_locals, skel->bss->nr_queued, skel->bss->nr_lost_pids); - printf(" dispatch:%10" PRIu64 " mismatch:%10" PRIu64 " retry:%10" PRIu64 "\n", + printf("timer :%10" PRIu64 " dispatch:%10" PRIu64 " mismatch:%10" PRIu64 " retry:%10" PRIu64 "\n", + skel->bss->nr_timers, skel->bss->nr_dispatches, skel->bss->nr_mismatches, skel->bss->nr_retries); -- cgit v1.2.3 From 36454023f50b2aadd25b7f47c50b5edc0c59e1c0 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 18 Jun 2024 10:09:19 -1000 Subject: sched_ext: Track tasks that are subjects of the in-flight SCX operation When some SCX operations are in flight, it is known that the subject task's rq lock is held throughout which makes it safe to access certain fields of the task - e.g. its current task_group. We want to add SCX kfunc helpers that can make use of this guarantee - e.g. to help determining the currently associated CPU cgroup from the task's current task_group. As it'd be dangerous call such a helper on a task which isn't rq lock protected, the helper should be able to verify the input task and reject accordingly. This patch adds sched_ext_entity.kf_tasks[] that track the tasks which are currently being operated on by a terminal SCX operation. The new SCX_CALL_OP_[2]TASK[_RET]() can be used when invoking SCX operations which take tasks as arguments and the scx_kf_allowed_on_arg_tasks() can be used by kfunc helpers to verify the input task status. Note that as sched_ext_entity.kf_tasks[] can't handle nesting, the tracking is currently only limited to terminal SCX operations. If needed in the future, this restriction can be removed by moving the tracking to the task side with a couple per-task counters. v2: Updated to reflect the addition of SCX_KF_SELECT_CPU. Signed-off-by: Tejun Heo Reviewed-by: David Vernet --- include/linux/sched/ext.h | 2 ++ kernel/sched/ext.c | 91 ++++++++++++++++++++++++++++++++++++++--------- 2 files changed, 76 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index 6f1a4977e9f8..74341dbc6a19 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -106,6 +106,7 @@ enum scx_kf_mask { __SCX_KF_RQ_LOCKED = SCX_KF_DISPATCH | SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU | SCX_KF_REST, + __SCX_KF_TERMINAL = SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU | SCX_KF_REST, }; /* @@ -120,6 +121,7 @@ struct sched_ext_entity { s32 sticky_cpu; s32 holding_cpu; u32 kf_mask; /* see scx_kf_mask above */ + struct task_struct *kf_tasks[2]; /* see SCX_CALL_OP_TASK() */ atomic_long_t ops_state; struct list_head runnable_node; /* rq->scx.runnable_list */ diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index ce32fc6b05cd..838a96cb10ea 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -817,6 +817,47 @@ do { \ __ret; \ }) +/* + * Some kfuncs are allowed only on the tasks that are subjects of the + * in-progress scx_ops operation for, e.g., locking guarantees. To enforce such + * restrictions, the following SCX_CALL_OP_*() variants should be used when + * invoking scx_ops operations that take task arguments. These can only be used + * for non-nesting operations due to the way the tasks are tracked. + * + * kfuncs which can only operate on such tasks can in turn use + * scx_kf_allowed_on_arg_tasks() to test whether the invocation is allowed on + * the specific task. + */ +#define SCX_CALL_OP_TASK(mask, op, task, args...) \ +do { \ + BUILD_BUG_ON((mask) & ~__SCX_KF_TERMINAL); \ + current->scx.kf_tasks[0] = task; \ + SCX_CALL_OP(mask, op, task, ##args); \ + current->scx.kf_tasks[0] = NULL; \ +} while (0) + +#define SCX_CALL_OP_TASK_RET(mask, op, task, args...) \ +({ \ + __typeof__(scx_ops.op(task, ##args)) __ret; \ + BUILD_BUG_ON((mask) & ~__SCX_KF_TERMINAL); \ + current->scx.kf_tasks[0] = task; \ + __ret = SCX_CALL_OP_RET(mask, op, task, ##args); \ + current->scx.kf_tasks[0] = NULL; \ + __ret; \ +}) + +#define SCX_CALL_OP_2TASKS_RET(mask, op, task0, task1, args...) \ +({ \ + __typeof__(scx_ops.op(task0, task1, ##args)) __ret; \ + BUILD_BUG_ON((mask) & ~__SCX_KF_TERMINAL); \ + current->scx.kf_tasks[0] = task0; \ + current->scx.kf_tasks[1] = task1; \ + __ret = SCX_CALL_OP_RET(mask, op, task0, task1, ##args); \ + current->scx.kf_tasks[0] = NULL; \ + current->scx.kf_tasks[1] = NULL; \ + __ret; \ +}) + /* @mask is constant, always inline to cull unnecessary branches */ static __always_inline bool scx_kf_allowed(u32 mask) { @@ -846,6 +887,22 @@ static __always_inline bool scx_kf_allowed(u32 mask) return true; } +/* see SCX_CALL_OP_TASK() */ +static __always_inline bool scx_kf_allowed_on_arg_tasks(u32 mask, + struct task_struct *p) +{ + if (!scx_kf_allowed(mask)) + return false; + + if (unlikely((p != current->scx.kf_tasks[0] && + p != current->scx.kf_tasks[1]))) { + scx_ops_error("called on a task not being operated on"); + return false; + } + + return true; +} + /* * SCX task iterator. @@ -1342,7 +1399,7 @@ static void do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags, WARN_ON_ONCE(*ddsp_taskp); *ddsp_taskp = p; - SCX_CALL_OP(SCX_KF_ENQUEUE, enqueue, p, enq_flags); + SCX_CALL_OP_TASK(SCX_KF_ENQUEUE, enqueue, p, enq_flags); *ddsp_taskp = NULL; if (p->scx.ddsp_dsq_id != SCX_DSQ_INVALID) @@ -1427,7 +1484,7 @@ static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int enq_flags add_nr_running(rq, 1); if (SCX_HAS_OP(runnable)) - SCX_CALL_OP(SCX_KF_REST, runnable, p, enq_flags); + SCX_CALL_OP_TASK(SCX_KF_REST, runnable, p, enq_flags); do_enqueue_task(rq, p, enq_flags, sticky_cpu); } @@ -1453,7 +1510,7 @@ static void ops_dequeue(struct task_struct *p, u64 deq_flags) BUG(); case SCX_OPSS_QUEUED: if (SCX_HAS_OP(dequeue)) - SCX_CALL_OP(SCX_KF_REST, dequeue, p, deq_flags); + SCX_CALL_OP_TASK(SCX_KF_REST, dequeue, p, deq_flags); if (atomic_long_try_cmpxchg(&p->scx.ops_state, &opss, SCX_OPSS_NONE)) @@ -1502,11 +1559,11 @@ static void dequeue_task_scx(struct rq *rq, struct task_struct *p, int deq_flags */ if (SCX_HAS_OP(stopping) && task_current(rq, p)) { update_curr_scx(rq); - SCX_CALL_OP(SCX_KF_REST, stopping, p, false); + SCX_CALL_OP_TASK(SCX_KF_REST, stopping, p, false); } if (SCX_HAS_OP(quiescent)) - SCX_CALL_OP(SCX_KF_REST, quiescent, p, deq_flags); + SCX_CALL_OP_TASK(SCX_KF_REST, quiescent, p, deq_flags); if (deq_flags & SCX_DEQ_SLEEP) p->scx.flags |= SCX_TASK_DEQD_FOR_SLEEP; @@ -1525,7 +1582,7 @@ static void yield_task_scx(struct rq *rq) struct task_struct *p = rq->curr; if (SCX_HAS_OP(yield)) - SCX_CALL_OP_RET(SCX_KF_REST, yield, p, NULL); + SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, yield, p, NULL); else p->scx.slice = 0; } @@ -1535,7 +1592,7 @@ static bool yield_to_task_scx(struct rq *rq, struct task_struct *to) struct task_struct *from = rq->curr; if (SCX_HAS_OP(yield)) - return SCX_CALL_OP_RET(SCX_KF_REST, yield, from, to); + return SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, yield, from, to); else return false; } @@ -2091,7 +2148,7 @@ static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first) /* see dequeue_task_scx() on why we skip when !QUEUED */ if (SCX_HAS_OP(running) && (p->scx.flags & SCX_TASK_QUEUED)) - SCX_CALL_OP(SCX_KF_REST, running, p); + SCX_CALL_OP_TASK(SCX_KF_REST, running, p); clr_task_runnable(p, true); @@ -2155,7 +2212,7 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p) /* see dequeue_task_scx() on why we skip when !QUEUED */ if (SCX_HAS_OP(stopping) && (p->scx.flags & SCX_TASK_QUEUED)) - SCX_CALL_OP(SCX_KF_REST, stopping, p, true); + SCX_CALL_OP_TASK(SCX_KF_REST, stopping, p, true); /* * If we're being called from put_prev_task_balance(), balance_scx() may @@ -2377,8 +2434,8 @@ static int select_task_rq_scx(struct task_struct *p, int prev_cpu, int wake_flag WARN_ON_ONCE(*ddsp_taskp); *ddsp_taskp = p; - cpu = SCX_CALL_OP_RET(SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU, - select_cpu, p, prev_cpu, wake_flags); + cpu = SCX_CALL_OP_TASK_RET(SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU, + select_cpu, p, prev_cpu, wake_flags); *ddsp_taskp = NULL; if (ops_cpu_valid(cpu, "from ops.select_cpu()")) return cpu; @@ -2411,8 +2468,8 @@ static void set_cpus_allowed_scx(struct task_struct *p, * designation pointless. Cast it away when calling the operation. */ if (SCX_HAS_OP(set_cpumask)) - SCX_CALL_OP(SCX_KF_REST, set_cpumask, p, - (struct cpumask *)p->cpus_ptr); + SCX_CALL_OP_TASK(SCX_KF_REST, set_cpumask, p, + (struct cpumask *)p->cpus_ptr); } static void reset_idle_masks(void) @@ -2647,7 +2704,7 @@ static void scx_ops_enable_task(struct task_struct *p) */ set_task_scx_weight(p); if (SCX_HAS_OP(enable)) - SCX_CALL_OP(SCX_KF_REST, enable, p); + SCX_CALL_OP_TASK(SCX_KF_REST, enable, p); scx_set_task_state(p, SCX_TASK_ENABLED); if (SCX_HAS_OP(set_weight)) @@ -2801,7 +2858,7 @@ static void reweight_task_scx(struct rq *rq, struct task_struct *p, int newprio) set_task_scx_weight(p); if (SCX_HAS_OP(set_weight)) - SCX_CALL_OP(SCX_KF_REST, set_weight, p, p->scx.weight); + SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, p, p->scx.weight); } static void prio_changed_scx(struct rq *rq, struct task_struct *p, int oldprio) @@ -2817,8 +2874,8 @@ static void switching_to_scx(struct rq *rq, struct task_struct *p) * different scheduler class. Keep the BPF scheduler up-to-date. */ if (SCX_HAS_OP(set_cpumask)) - SCX_CALL_OP(SCX_KF_REST, set_cpumask, p, - (struct cpumask *)p->cpus_ptr); + SCX_CALL_OP_TASK(SCX_KF_REST, set_cpumask, p, + (struct cpumask *)p->cpus_ptr); } static void switched_from_scx(struct rq *rq, struct task_struct *p) -- cgit v1.2.3 From 245254f7081dbe1c8da54675d0e4ddbe74cee61b Mon Sep 17 00:00:00 2001 From: David Vernet Date: Tue, 18 Jun 2024 10:09:20 -1000 Subject: sched_ext: Implement sched_ext_ops.cpu_acquire/release() Scheduler classes are strictly ordered and when a higher priority class has tasks to run, the lower priority ones lose access to the CPU. Being able to monitor and act on these events are necessary for use cases includling strict core-scheduling and latency management. This patch adds two operations ops.cpu_acquire() and .cpu_release(). The former is invoked when a CPU becomes available to the BPF scheduler and the opposite for the latter. This patch also implements scx_bpf_reenqueue_local() which can be called from .cpu_release() to trigger requeueing of all tasks in the local dsq of the CPU so that the tasks can be reassigned to other available CPUs. scx_pair is updated to use .cpu_acquire/release() along with %SCX_KICK_WAIT to make the pair scheduling guarantee strict even when a CPU is preempted by a higher priority scheduler class. scx_qmap is updated to use .cpu_acquire/release() to empty the local dsq of a preempted CPU. A similar approach can be adopted by BPF schedulers that want to have a tight control over latency. v4: Use the new SCX_KICK_IDLE to wake up a CPU after re-enqueueing. v3: Drop the const qualifier from scx_cpu_release_args.task. BPF enforces access control through the verifier, so the qualifier isn't actually operative and only gets in the way when interacting with various helpers. v2: Add p->scx.kf_mask annotation to allow calling scx_bpf_reenqueue_local() from ops.cpu_release() nested inside ops.init() and other sleepable operations. Signed-off-by: David Vernet Reviewed-by: Tejun Heo Signed-off-by: Tejun Heo Acked-by: Josh Don Acked-by: Hao Luo Acked-by: Barret Rhoden --- include/linux/sched/ext.h | 4 +- kernel/sched/ext.c | 198 ++++++++++++++++++++++++++++++- kernel/sched/ext.h | 2 + kernel/sched/sched.h | 1 + tools/sched_ext/include/scx/common.bpf.h | 1 + tools/sched_ext/scx_qmap.bpf.c | 37 +++++- tools/sched_ext/scx_qmap.c | 4 +- 7 files changed, 240 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index 74341dbc6a19..21c627337e01 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -98,13 +98,15 @@ enum scx_kf_mask { SCX_KF_UNLOCKED = 0, /* not sleepable, not rq locked */ /* all non-sleepables may be nested inside SLEEPABLE */ SCX_KF_SLEEPABLE = 1 << 0, /* sleepable init operations */ + /* ENQUEUE and DISPATCH may be nested inside CPU_RELEASE */ + SCX_KF_CPU_RELEASE = 1 << 1, /* ops.cpu_release() */ /* ops.dequeue (in REST) may be nested inside DISPATCH */ SCX_KF_DISPATCH = 1 << 2, /* ops.dispatch() */ SCX_KF_ENQUEUE = 1 << 3, /* ops.enqueue() and ops.select_cpu() */ SCX_KF_SELECT_CPU = 1 << 4, /* ops.select_cpu() */ SCX_KF_REST = 1 << 5, /* other rq-locked operations */ - __SCX_KF_RQ_LOCKED = SCX_KF_DISPATCH | + __SCX_KF_RQ_LOCKED = SCX_KF_CPU_RELEASE | SCX_KF_DISPATCH | SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU | SCX_KF_REST, __SCX_KF_TERMINAL = SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU | SCX_KF_REST, }; diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 1ca3067b4e0a..686dab6ab592 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -110,6 +110,32 @@ struct scx_exit_task_args { bool cancelled; }; +enum scx_cpu_preempt_reason { + /* next task is being scheduled by &sched_class_rt */ + SCX_CPU_PREEMPT_RT, + /* next task is being scheduled by &sched_class_dl */ + SCX_CPU_PREEMPT_DL, + /* next task is being scheduled by &sched_class_stop */ + SCX_CPU_PREEMPT_STOP, + /* unknown reason for SCX being preempted */ + SCX_CPU_PREEMPT_UNKNOWN, +}; + +/* + * Argument container for ops->cpu_acquire(). Currently empty, but may be + * expanded in the future. + */ +struct scx_cpu_acquire_args {}; + +/* argument container for ops->cpu_release() */ +struct scx_cpu_release_args { + /* the reason the CPU was preempted */ + enum scx_cpu_preempt_reason reason; + + /* the task that's going to be scheduled on the CPU */ + struct task_struct *task; +}; + /* * Informational context provided to dump operations. */ @@ -335,6 +361,28 @@ struct sched_ext_ops { */ void (*update_idle)(s32 cpu, bool idle); + /** + * cpu_acquire - A CPU is becoming available to the BPF scheduler + * @cpu: The CPU being acquired by the BPF scheduler. + * @args: Acquire arguments, see the struct definition. + * + * A CPU that was previously released from the BPF scheduler is now once + * again under its control. + */ + void (*cpu_acquire)(s32 cpu, struct scx_cpu_acquire_args *args); + + /** + * cpu_release - A CPU is taken away from the BPF scheduler + * @cpu: The CPU being released by the BPF scheduler. + * @args: Release arguments, see the struct definition. + * + * The specified CPU is no longer under the control of the BPF + * scheduler. This could be because it was preempted by a higher + * priority sched_class, though there may be other reasons as well. The + * caller should consult @args->reason to determine the cause. + */ + void (*cpu_release)(s32 cpu, struct scx_cpu_release_args *args); + /** * init_task - Initialize a task to run in a BPF scheduler * @p: task to initialize for BPF scheduling @@ -487,6 +535,17 @@ enum scx_enq_flags { */ SCX_ENQ_PREEMPT = 1LLU << 32, + /* + * The task being enqueued was previously enqueued on the current CPU's + * %SCX_DSQ_LOCAL, but was removed from it in a call to the + * bpf_scx_reenqueue_local() kfunc. If bpf_scx_reenqueue_local() was + * invoked in a ->cpu_release() callback, and the task is again + * dispatched back to %SCX_LOCAL_DSQ by this current ->enqueue(), the + * task will not be scheduled on the CPU until at least the next invocation + * of the ->cpu_acquire() callback. + */ + SCX_ENQ_REENQ = 1LLU << 40, + /* * The task being enqueued is the only task available for the cpu. By * default, ext core keeps executing such tasks but when @@ -625,6 +684,7 @@ static bool scx_warned_zero_slice; static DEFINE_STATIC_KEY_FALSE(scx_ops_enq_last); static DEFINE_STATIC_KEY_FALSE(scx_ops_enq_exiting); +DEFINE_STATIC_KEY_FALSE(scx_ops_cpu_preempt); static DEFINE_STATIC_KEY_FALSE(scx_builtin_idle_enabled); struct static_key_false scx_has_op[SCX_OPI_END] = @@ -887,6 +947,12 @@ static __always_inline bool scx_kf_allowed(u32 mask) * inside ops.dispatch(). We don't need to check the SCX_KF_SLEEPABLE * boundary thanks to the above in_interrupt() check. */ + if (unlikely(highest_bit(mask) == SCX_KF_CPU_RELEASE && + (current->scx.kf_mask & higher_bits(SCX_KF_CPU_RELEASE)))) { + scx_ops_error("cpu_release kfunc called from a nested operation"); + return false; + } + if (unlikely(highest_bit(mask) == SCX_KF_DISPATCH && (current->scx.kf_mask & higher_bits(SCX_KF_DISPATCH)))) { scx_ops_error("dispatch kfunc called from a nested operation"); @@ -2070,6 +2136,19 @@ static int balance_scx(struct rq *rq, struct task_struct *prev, lockdep_assert_rq_held(rq); rq->scx.flags |= SCX_RQ_BALANCING; + if (static_branch_unlikely(&scx_ops_cpu_preempt) && + unlikely(rq->scx.cpu_released)) { + /* + * If the previous sched_class for the current CPU was not SCX, + * notify the BPF scheduler that it again has control of the + * core. This callback complements ->cpu_release(), which is + * emitted in scx_next_task_picked(). + */ + if (SCX_HAS_OP(cpu_acquire)) + SCX_CALL_OP(0, cpu_acquire, cpu_of(rq), NULL); + rq->scx.cpu_released = false; + } + if (prev_on_scx) { WARN_ON_ONCE(prev->scx.flags & SCX_TASK_BAL_KEEP); update_curr_scx(rq); @@ -2077,7 +2156,9 @@ static int balance_scx(struct rq *rq, struct task_struct *prev, /* * If @prev is runnable & has slice left, it has priority and * fetching more just increases latency for the fetched tasks. - * Tell put_prev_task_scx() to put @prev on local_dsq. + * Tell put_prev_task_scx() to put @prev on local_dsq. If the + * BPF scheduler wants to handle this explicitly, it should + * implement ->cpu_released(). * * See scx_ops_disable_workfn() for the explanation on the * bypassing test. @@ -2297,6 +2378,20 @@ static struct task_struct *pick_next_task_scx(struct rq *rq) return p; } +static enum scx_cpu_preempt_reason +preempt_reason_from_class(const struct sched_class *class) +{ +#ifdef CONFIG_SMP + if (class == &stop_sched_class) + return SCX_CPU_PREEMPT_STOP; +#endif + if (class == &dl_sched_class) + return SCX_CPU_PREEMPT_DL; + if (class == &rt_sched_class) + return SCX_CPU_PREEMPT_RT; + return SCX_CPU_PREEMPT_UNKNOWN; +} + void scx_next_task_picked(struct rq *rq, struct task_struct *p, const struct sched_class *active) { @@ -2312,6 +2407,40 @@ void scx_next_task_picked(struct rq *rq, struct task_struct *p, */ smp_store_release(&rq->scx.pnt_seq, rq->scx.pnt_seq + 1); #endif + if (!static_branch_unlikely(&scx_ops_cpu_preempt)) + return; + + /* + * The callback is conceptually meant to convey that the CPU is no + * longer under the control of SCX. Therefore, don't invoke the + * callback if the CPU is is staying on SCX, or going idle (in which + * case the SCX scheduler has actively decided not to schedule any + * tasks on the CPU). + */ + if (likely(active >= &ext_sched_class)) + return; + + /* + * At this point we know that SCX was preempted by a higher priority + * sched_class, so invoke the ->cpu_release() callback if we have not + * done so already. We only send the callback once between SCX being + * preempted, and it regaining control of the CPU. + * + * ->cpu_release() complements ->cpu_acquire(), which is emitted the + * next time that balance_scx() is invoked. + */ + if (!rq->scx.cpu_released) { + if (SCX_HAS_OP(cpu_release)) { + struct scx_cpu_release_args args = { + .reason = preempt_reason_from_class(active), + .task = p, + }; + + SCX_CALL_OP(SCX_KF_CPU_RELEASE, + cpu_release, cpu_of(rq), &args); + } + rq->scx.cpu_released = true; + } } #ifdef CONFIG_SMP @@ -3398,6 +3527,7 @@ static void scx_ops_disable_workfn(struct kthread_work *work) static_branch_disable_cpuslocked(&scx_has_op[i]); static_branch_disable_cpuslocked(&scx_ops_enq_last); static_branch_disable_cpuslocked(&scx_ops_enq_exiting); + static_branch_disable_cpuslocked(&scx_ops_cpu_preempt); static_branch_disable_cpuslocked(&scx_builtin_idle_enabled); synchronize_rcu(); @@ -3699,9 +3829,10 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len) seq_buf_init(&ns, buf, avail); dump_newline(&ns); - dump_line(&ns, "CPU %-4d: nr_run=%u flags=0x%x ops_qseq=%lu pnt_seq=%lu", + dump_line(&ns, "CPU %-4d: nr_run=%u flags=0x%x cpu_rel=%d ops_qseq=%lu pnt_seq=%lu", cpu, rq->scx.nr_running, rq->scx.flags, - rq->scx.ops_qseq, rq->scx.pnt_seq); + rq->scx.cpu_released, rq->scx.ops_qseq, + rq->scx.pnt_seq); dump_line(&ns, " curr=%s[%d] class=%ps", rq->curr->comm, rq->curr->pid, rq->curr->sched_class); @@ -3942,6 +4073,8 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) if (ops->flags & SCX_OPS_ENQ_EXITING) static_branch_enable_cpuslocked(&scx_ops_enq_exiting); + if (scx_ops.cpu_acquire || scx_ops.cpu_release) + static_branch_enable_cpuslocked(&scx_ops_cpu_preempt); if (!ops->update_idle || (ops->flags & SCX_OPS_KEEP_BUILTIN_IDLE)) { reset_idle_masks(); @@ -4318,6 +4451,8 @@ static bool yield_stub(struct task_struct *from, struct task_struct *to) { retur static void set_weight_stub(struct task_struct *p, u32 weight) {} static void set_cpumask_stub(struct task_struct *p, const struct cpumask *mask) {} static void update_idle_stub(s32 cpu, bool idle) {} +static void cpu_acquire_stub(s32 cpu, struct scx_cpu_acquire_args *args) {} +static void cpu_release_stub(s32 cpu, struct scx_cpu_release_args *args) {} static s32 init_task_stub(struct task_struct *p, struct scx_init_task_args *args) { return -EINVAL; } static void exit_task_stub(struct task_struct *p, struct scx_exit_task_args *args) {} static void enable_stub(struct task_struct *p) {} @@ -4338,6 +4473,8 @@ static struct sched_ext_ops __bpf_ops_sched_ext_ops = { .set_weight = set_weight_stub, .set_cpumask = set_cpumask_stub, .update_idle = update_idle_stub, + .cpu_acquire = cpu_acquire_stub, + .cpu_release = cpu_release_stub, .init_task = init_task_stub, .exit_task = exit_task_stub, .enable = enable_stub, @@ -4870,6 +5007,59 @@ static const struct btf_kfunc_id_set scx_kfunc_set_dispatch = { __bpf_kfunc_start_defs(); +/** + * scx_bpf_reenqueue_local - Re-enqueue tasks on a local DSQ + * + * Iterate over all of the tasks currently enqueued on the local DSQ of the + * caller's CPU, and re-enqueue them in the BPF scheduler. Returns the number of + * processed tasks. Can only be called from ops.cpu_release(). + */ +__bpf_kfunc u32 scx_bpf_reenqueue_local(void) +{ + u32 nr_enqueued, i; + struct rq *rq; + + if (!scx_kf_allowed(SCX_KF_CPU_RELEASE)) + return 0; + + rq = cpu_rq(smp_processor_id()); + lockdep_assert_rq_held(rq); + + /* + * Get the number of tasks on the local DSQ before iterating over it to + * pull off tasks. The enqueue callback below can signal that it wants + * the task to stay on the local DSQ, and we want to prevent the BPF + * scheduler from causing us to loop indefinitely. + */ + nr_enqueued = rq->scx.local_dsq.nr; + for (i = 0; i < nr_enqueued; i++) { + struct task_struct *p; + + p = first_local_task(rq); + WARN_ON_ONCE(atomic_long_read(&p->scx.ops_state) != + SCX_OPSS_NONE); + WARN_ON_ONCE(!(p->scx.flags & SCX_TASK_QUEUED)); + WARN_ON_ONCE(p->scx.holding_cpu != -1); + dispatch_dequeue(rq, p); + do_enqueue_task(rq, p, SCX_ENQ_REENQ, -1); + } + + return nr_enqueued; +} + +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(scx_kfunc_ids_cpu_release) +BTF_ID_FLAGS(func, scx_bpf_reenqueue_local) +BTF_KFUNCS_END(scx_kfunc_ids_cpu_release) + +static const struct btf_kfunc_id_set scx_kfunc_set_cpu_release = { + .owner = THIS_MODULE, + .set = &scx_kfunc_ids_cpu_release, +}; + +__bpf_kfunc_start_defs(); + /** * scx_bpf_kick_cpu - Trigger reschedule on a CPU * @cpu: cpu to kick @@ -5379,6 +5569,8 @@ static int __init scx_init(void) &scx_kfunc_set_enqueue_dispatch)) || (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &scx_kfunc_set_dispatch)) || + (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, + &scx_kfunc_set_cpu_release)) || (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &scx_kfunc_set_any)) || (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h index 0aeb1fda1794..4ebd1c2478f1 100644 --- a/kernel/sched/ext.h +++ b/kernel/sched/ext.h @@ -24,6 +24,8 @@ DECLARE_STATIC_KEY_FALSE(__scx_switched_all); #define scx_enabled() static_branch_unlikely(&__scx_ops_enabled) #define scx_switched_all() static_branch_unlikely(&__scx_switched_all) +DECLARE_STATIC_KEY_FALSE(scx_ops_cpu_preempt); + static inline bool task_on_scx(const struct task_struct *p) { return scx_enabled() && p->sched_class == &ext_sched_class; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 734206e13897..147d18cf01ce 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -737,6 +737,7 @@ struct scx_rq { u64 extra_enq_flags; /* see move_task_to_local_dsq() */ u32 nr_running; u32 flags; + bool cpu_released; cpumask_var_t cpus_to_kick; cpumask_var_t cpus_to_kick_if_idle; cpumask_var_t cpus_to_preempt; diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h index 421118bc56ff..8686f84497db 100644 --- a/tools/sched_ext/include/scx/common.bpf.h +++ b/tools/sched_ext/include/scx/common.bpf.h @@ -34,6 +34,7 @@ void scx_bpf_dispatch(struct task_struct *p, u64 dsq_id, u64 slice, u64 enq_flag u32 scx_bpf_dispatch_nr_slots(void) __ksym; void scx_bpf_dispatch_cancel(void) __ksym; bool scx_bpf_consume(u64 dsq_id) __ksym; +u32 scx_bpf_reenqueue_local(void) __ksym; void scx_bpf_kick_cpu(s32 cpu, u64 flags) __ksym; s32 scx_bpf_dsq_nr_queued(u64 dsq_id) __ksym; void scx_bpf_destroy_dsq(u64 dsq_id) __ksym; diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c index 879fc9c788e5..4a87377558c8 100644 --- a/tools/sched_ext/scx_qmap.bpf.c +++ b/tools/sched_ext/scx_qmap.bpf.c @@ -11,6 +11,8 @@ * * - BPF-side queueing using PIDs. * - Sleepable per-task storage allocation using ops.prep_enable(). + * - Using ops.cpu_release() to handle a higher priority scheduling class taking + * the CPU away. * * This scheduler is primarily for demonstration and testing of sched_ext * features and unlikely to be useful for actual workloads. @@ -90,7 +92,7 @@ struct { } cpu_ctx_stor SEC(".maps"); /* Statistics */ -u64 nr_enqueued, nr_dispatched, nr_dequeued; +u64 nr_enqueued, nr_dispatched, nr_reenqueued, nr_dequeued; s32 BPF_STRUCT_OPS(qmap_select_cpu, struct task_struct *p, s32 prev_cpu, u64 wake_flags) @@ -164,6 +166,22 @@ void BPF_STRUCT_OPS(qmap_enqueue, struct task_struct *p, u64 enq_flags) return; } + /* + * If the task was re-enqueued due to the CPU being preempted by a + * higher priority scheduling class, just re-enqueue the task directly + * on the global DSQ. As we want another CPU to pick it up, find and + * kick an idle CPU. + */ + if (enq_flags & SCX_ENQ_REENQ) { + s32 cpu; + + scx_bpf_dispatch(p, SHARED_DSQ, 0, enq_flags); + cpu = scx_bpf_pick_idle_cpu(p->cpus_ptr, 0); + if (cpu >= 0) + scx_bpf_kick_cpu(cpu, SCX_KICK_IDLE); + return; + } + ring = bpf_map_lookup_elem(&queue_arr, &idx); if (!ring) { scx_bpf_error("failed to find ring %d", idx); @@ -257,6 +275,22 @@ void BPF_STRUCT_OPS(qmap_dispatch, s32 cpu, struct task_struct *prev) } } +void BPF_STRUCT_OPS(qmap_cpu_release, s32 cpu, struct scx_cpu_release_args *args) +{ + u32 cnt; + + /* + * Called when @cpu is taken by a higher priority scheduling class. This + * makes @cpu no longer available for executing sched_ext tasks. As we + * don't want the tasks in @cpu's local dsq to sit there until @cpu + * becomes available again, re-enqueue them into the global dsq. See + * %SCX_ENQ_REENQ handling in qmap_enqueue(). + */ + cnt = scx_bpf_reenqueue_local(); + if (cnt) + __sync_fetch_and_add(&nr_reenqueued, cnt); +} + s32 BPF_STRUCT_OPS(qmap_init_task, struct task_struct *p, struct scx_init_task_args *args) { @@ -339,6 +373,7 @@ SCX_OPS_DEFINE(qmap_ops, .enqueue = (void *)qmap_enqueue, .dequeue = (void *)qmap_dequeue, .dispatch = (void *)qmap_dispatch, + .cpu_release = (void *)qmap_cpu_release, .init_task = (void *)qmap_init_task, .dump = (void *)qmap_dump, .dump_cpu = (void *)qmap_dump_cpu, diff --git a/tools/sched_ext/scx_qmap.c b/tools/sched_ext/scx_qmap.c index 594147a710a8..2a97421afe9a 100644 --- a/tools/sched_ext/scx_qmap.c +++ b/tools/sched_ext/scx_qmap.c @@ -112,9 +112,9 @@ int main(int argc, char **argv) long nr_enqueued = skel->bss->nr_enqueued; long nr_dispatched = skel->bss->nr_dispatched; - printf("stats : enq=%lu dsp=%lu delta=%ld deq=%"PRIu64"\n", + printf("stats : enq=%lu dsp=%lu delta=%ld reenq=%"PRIu64" deq=%"PRIu64"\n", nr_enqueued, nr_dispatched, nr_enqueued - nr_dispatched, - skel->bss->nr_dequeued); + skel->bss->nr_reenqueued, skel->bss->nr_dequeued); fflush(stdout); sleep(1); } -- cgit v1.2.3 From 7b0888b7cc1924b74ce660e02f6211df8dd46e7b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 18 Jun 2024 10:09:20 -1000 Subject: sched_ext: Implement core-sched support The core-sched support is composed of the following parts: - task_struct->scx.core_sched_at is added. This is a timestamp which can be used to order tasks. Depending on whether the BPF scheduler implements custom ordering, it tracks either global FIFO ordering of all tasks or local-DSQ ordering within the dispatched tasks on a CPU. - prio_less() is updated to call scx_prio_less() when comparing SCX tasks. scx_prio_less() calls ops.core_sched_before() if available or uses the core_sched_at timestamp. For global FIFO ordering, the BPF scheduler doesn't need to do anything. Otherwise, it should implement ops.core_sched_before() which reflects the ordering. - When core-sched is enabled, balance_scx() balances all SMT siblings so that they all have tasks dispatched if necessary before pick_task_scx() is called. pick_task_scx() picks between the current task and the first dispatched task on the local DSQ based on availability and the core_sched_at timestamps. Note that FIFO ordering is expected among the already dispatched tasks whether running or on the local DSQ, so this path always compares core_sched_at instead of calling into ops.core_sched_before(). qmap_core_sched_before() is added to scx_qmap. It scales the distances from the heads of the queues to compare the tasks across different priority queues and seems to behave as expected. v3: Fixed build error when !CONFIG_SCHED_SMT reported by Andrea Righi. v2: Sched core added the const qualifiers to prio_less task arguments. Explicitly drop them for ops.core_sched_before() task arguments. BPF enforces access control through the verifier, so the qualifier isn't actually operative and only gets in the way when interacting with various helpers. Signed-off-by: Tejun Heo Reviewed-by: David Vernet Reviewed-by: Josh Don Cc: Andrea Righi --- include/linux/sched/ext.h | 3 + kernel/Kconfig.preempt | 2 +- kernel/sched/core.c | 10 +- kernel/sched/ext.c | 250 +++++++++++++++++++++++++++++++++++++++-- kernel/sched/ext.h | 5 + tools/sched_ext/scx_qmap.bpf.c | 91 ++++++++++++++- tools/sched_ext/scx_qmap.c | 5 +- 7 files changed, 346 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index 21c627337e01..3db7b32b2d1d 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -129,6 +129,9 @@ struct sched_ext_entity { struct list_head runnable_node; /* rq->scx.runnable_list */ unsigned long runnable_at; +#ifdef CONFIG_SCHED_CORE + u64 core_sched_at; /* see scx_prio_less() */ +#endif u64 ddsp_dsq_id; u64 ddsp_enq_flags; diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt index 39ecfc2b5a1c..7dde5e424ac3 100644 --- a/kernel/Kconfig.preempt +++ b/kernel/Kconfig.preempt @@ -135,7 +135,7 @@ config SCHED_CORE config SCHED_CLASS_EXT bool "Extensible Scheduling Class" - depends on BPF_SYSCALL && BPF_JIT && !SCHED_CORE + depends on BPF_SYSCALL && BPF_JIT help This option enables a new scheduler class sched_ext (SCX), which allows scheduling policies to be implemented as BPF programs to diff --git a/kernel/sched/core.c b/kernel/sched/core.c index c798c847d57e..5eec6639773b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -169,7 +169,10 @@ static inline int __task_prio(const struct task_struct *p) if (p->sched_class == &idle_sched_class) return MAX_RT_PRIO + NICE_WIDTH; /* 140 */ - return MAX_RT_PRIO + MAX_NICE; /* 120, squash fair */ + if (task_on_scx(p)) + return MAX_RT_PRIO + MAX_NICE + 1; /* 120, squash ext */ + + return MAX_RT_PRIO + MAX_NICE; /* 119, squash fair */ } /* @@ -198,6 +201,11 @@ static inline bool prio_less(const struct task_struct *a, if (pa == MAX_RT_PRIO + MAX_NICE) /* fair */ return cfs_prio_less(a, b, in_fi); +#ifdef CONFIG_SCHED_CLASS_EXT + if (pa == MAX_RT_PRIO + MAX_NICE + 1) /* ext */ + return scx_prio_less(a, b, in_fi); +#endif + return false; } diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 26616cd0c5df..1feb690be9d8 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -344,6 +344,24 @@ struct sched_ext_ops { */ bool (*yield)(struct task_struct *from, struct task_struct *to); + /** + * core_sched_before - Task ordering for core-sched + * @a: task A + * @b: task B + * + * Used by core-sched to determine the ordering between two tasks. See + * Documentation/admin-guide/hw-vuln/core-scheduling.rst for details on + * core-sched. + * + * Both @a and @b are runnable and may or may not currently be queued on + * the BPF scheduler. Should return %true if @a should run before @b. + * %false if there's no required ordering or @b should run before @a. + * + * If not specified, the default is ordering them according to when they + * became runnable. + */ + bool (*core_sched_before)(struct task_struct *a, struct task_struct *b); + /** * set_weight - Set task weight * @p: task to set weight for @@ -625,6 +643,14 @@ enum scx_enq_flags { enum scx_deq_flags { /* expose select DEQUEUE_* flags as enums */ SCX_DEQ_SLEEP = DEQUEUE_SLEEP, + + /* high 32bits are SCX specific */ + + /* + * The generic core-sched layer decided to execute the task even though + * it hasn't been dispatched yet. Dequeue from the BPF side. + */ + SCX_DEQ_CORE_SCHED_EXEC = 1LLU << 32, }; enum scx_pick_idle_cpu_flags { @@ -1260,6 +1286,49 @@ static int ops_sanitize_err(const char *ops_name, s32 err) return -EPROTO; } +/** + * touch_core_sched - Update timestamp used for core-sched task ordering + * @rq: rq to read clock from, must be locked + * @p: task to update the timestamp for + * + * Update @p->scx.core_sched_at timestamp. This is used by scx_prio_less() to + * implement global or local-DSQ FIFO ordering for core-sched. Should be called + * when a task becomes runnable and its turn on the CPU ends (e.g. slice + * exhaustion). + */ +static void touch_core_sched(struct rq *rq, struct task_struct *p) +{ +#ifdef CONFIG_SCHED_CORE + /* + * It's okay to update the timestamp spuriously. Use + * sched_core_disabled() which is cheaper than enabled(). + */ + if (!sched_core_disabled()) + p->scx.core_sched_at = rq_clock_task(rq); +#endif +} + +/** + * touch_core_sched_dispatch - Update core-sched timestamp on dispatch + * @rq: rq to read clock from, must be locked + * @p: task being dispatched + * + * If the BPF scheduler implements custom core-sched ordering via + * ops.core_sched_before(), @p->scx.core_sched_at is used to implement FIFO + * ordering within each local DSQ. This function is called from dispatch paths + * and updates @p->scx.core_sched_at if custom core-sched ordering is in effect. + */ +static void touch_core_sched_dispatch(struct rq *rq, struct task_struct *p) +{ + lockdep_assert_rq_held(rq); + assert_clock_updated(rq); + +#ifdef CONFIG_SCHED_CORE + if (SCX_HAS_OP(core_sched_before)) + touch_core_sched(rq, p); +#endif +} + static void update_curr_scx(struct rq *rq) { struct task_struct *curr = rq->curr; @@ -1275,8 +1344,11 @@ static void update_curr_scx(struct rq *rq) account_group_exec_runtime(curr, delta_exec); cgroup_account_cputime(curr, delta_exec); - if (curr->scx.slice != SCX_SLICE_INF) + if (curr->scx.slice != SCX_SLICE_INF) { curr->scx.slice -= min(curr->scx.slice, delta_exec); + if (!curr->scx.slice) + touch_core_sched(rq, curr); + } } static void dsq_mod_nr(struct scx_dispatch_q *dsq, s32 delta) @@ -1469,6 +1541,8 @@ static void direct_dispatch(struct task_struct *p, u64 enq_flags) { struct scx_dispatch_q *dsq; + touch_core_sched_dispatch(task_rq(p), p); + enq_flags |= (p->scx.ddsp_enq_flags | SCX_ENQ_CLEAR_OPSS); dsq = find_dsq_for_dispatch(task_rq(p), p->scx.ddsp_dsq_id, p); dispatch_enqueue(dsq, p, enq_flags); @@ -1550,12 +1624,19 @@ direct: return; local: + /* + * For task-ordering, slice refill must be treated as implying the end + * of the current slice. Otherwise, the longer @p stays on the CPU, the + * higher priority it becomes from scx_prio_less()'s POV. + */ + touch_core_sched(rq, p); p->scx.slice = SCX_SLICE_DFL; local_norefill: dispatch_enqueue(&rq->scx.local_dsq, p, enq_flags); return; global: + touch_core_sched(rq, p); /* see the comment in local: */ p->scx.slice = SCX_SLICE_DFL; dispatch_enqueue(&scx_dsq_global, p, enq_flags); } @@ -1619,6 +1700,9 @@ static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int enq_flags if (SCX_HAS_OP(runnable)) SCX_CALL_OP_TASK(SCX_KF_REST, runnable, p, enq_flags); + if (enq_flags & SCX_ENQ_WAKEUP) + touch_core_sched(rq, p); + do_enqueue_task(rq, p, enq_flags, sticky_cpu); } @@ -2106,6 +2190,7 @@ static void finish_dispatch(struct rq *rq, struct rq_flags *rf, struct scx_dispatch_q *dsq; unsigned long opss; + touch_core_sched_dispatch(rq, p); retry: /* * No need for _acquire here. @p is accessed only after a successful @@ -2183,8 +2268,8 @@ static void flush_dispatch_buf(struct rq *rq, struct rq_flags *rf) dspc->cursor = 0; } -static int balance_scx(struct rq *rq, struct task_struct *prev, - struct rq_flags *rf) +static int balance_one(struct rq *rq, struct task_struct *prev, + struct rq_flags *rf, bool local) { struct scx_dsp_ctx *dspc = this_cpu_ptr(scx_dsp_ctx); bool prev_on_scx = prev->sched_class == &ext_sched_class; @@ -2208,7 +2293,7 @@ static int balance_scx(struct rq *rq, struct task_struct *prev, } if (prev_on_scx) { - WARN_ON_ONCE(prev->scx.flags & SCX_TASK_BAL_KEEP); + WARN_ON_ONCE(local && (prev->scx.flags & SCX_TASK_BAL_KEEP)); update_curr_scx(rq); /* @@ -2220,10 +2305,16 @@ static int balance_scx(struct rq *rq, struct task_struct *prev, * * See scx_ops_disable_workfn() for the explanation on the * bypassing test. + * + * When balancing a remote CPU for core-sched, there won't be a + * following put_prev_task_scx() call and we don't own + * %SCX_TASK_BAL_KEEP. Instead, pick_task_scx() will test the + * same conditions later and pick @rq->curr accordingly. */ if ((prev->scx.flags & SCX_TASK_QUEUED) && prev->scx.slice && !scx_ops_bypassing()) { - prev->scx.flags |= SCX_TASK_BAL_KEEP; + if (local) + prev->scx.flags |= SCX_TASK_BAL_KEEP; goto has_tasks; } } @@ -2285,10 +2376,56 @@ out: return has_tasks; } +static int balance_scx(struct rq *rq, struct task_struct *prev, + struct rq_flags *rf) +{ + int ret; + + ret = balance_one(rq, prev, rf, true); + +#ifdef CONFIG_SCHED_SMT + /* + * When core-sched is enabled, this ops.balance() call will be followed + * by put_prev_scx() and pick_task_scx() on this CPU and pick_task_scx() + * on the SMT siblings. Balance the siblings too. + */ + if (sched_core_enabled(rq)) { + const struct cpumask *smt_mask = cpu_smt_mask(cpu_of(rq)); + int scpu; + + for_each_cpu_andnot(scpu, smt_mask, cpumask_of(cpu_of(rq))) { + struct rq *srq = cpu_rq(scpu); + struct rq_flags srf; + struct task_struct *sprev = srq->curr; + + /* + * While core-scheduling, rq lock is shared among + * siblings but the debug annotations and rq clock + * aren't. Do pinning dance to transfer the ownership. + */ + WARN_ON_ONCE(__rq_lockp(rq) != __rq_lockp(srq)); + rq_unpin_lock(rq, rf); + rq_pin_lock(srq, &srf); + + update_rq_clock(srq); + balance_one(srq, sprev, &srf, false); + + rq_unpin_lock(srq, &srf); + rq_repin_lock(rq, rf); + } + } +#endif + return ret; +} + static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first) { if (p->scx.flags & SCX_TASK_QUEUED) { - WARN_ON_ONCE(atomic_long_read(&p->scx.ops_state) != SCX_OPSS_NONE); + /* + * Core-sched might decide to execute @p before it is + * dispatched. Call ops_dequeue() to notify the BPF scheduler. + */ + ops_dequeue(p, SCX_DEQ_CORE_SCHED_EXEC); dispatch_dequeue(rq, p); } @@ -2379,7 +2516,8 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p) /* * If @p has slice left and balance_scx() didn't tag it for * keeping, @p is getting preempted by a higher priority - * scheduler class. Leave it at the head of the local DSQ. + * scheduler class or core-sched forcing a different task. Leave + * it at the head of the local DSQ. */ if (p->scx.slice && !scx_ops_bypassing()) { dispatch_enqueue(&rq->scx.local_dsq, p, SCX_ENQ_HEAD); @@ -2436,6 +2574,84 @@ static struct task_struct *pick_next_task_scx(struct rq *rq) return p; } +#ifdef CONFIG_SCHED_CORE +/** + * scx_prio_less - Task ordering for core-sched + * @a: task A + * @b: task B + * + * Core-sched is implemented as an additional scheduling layer on top of the + * usual sched_class'es and needs to find out the expected task ordering. For + * SCX, core-sched calls this function to interrogate the task ordering. + * + * Unless overridden by ops.core_sched_before(), @p->scx.core_sched_at is used + * to implement the default task ordering. The older the timestamp, the higher + * prority the task - the global FIFO ordering matching the default scheduling + * behavior. + * + * When ops.core_sched_before() is enabled, @p->scx.core_sched_at is used to + * implement FIFO ordering within each local DSQ. See pick_task_scx(). + */ +bool scx_prio_less(const struct task_struct *a, const struct task_struct *b, + bool in_fi) +{ + /* + * The const qualifiers are dropped from task_struct pointers when + * calling ops.core_sched_before(). Accesses are controlled by the + * verifier. + */ + if (SCX_HAS_OP(core_sched_before) && !scx_ops_bypassing()) + return SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, core_sched_before, + (struct task_struct *)a, + (struct task_struct *)b); + else + return time_after64(a->scx.core_sched_at, b->scx.core_sched_at); +} + +/** + * pick_task_scx - Pick a candidate task for core-sched + * @rq: rq to pick the candidate task from + * + * Core-sched calls this function on each SMT sibling to determine the next + * tasks to run on the SMT siblings. balance_one() has been called on all + * siblings and put_prev_task_scx() has been called only for the current CPU. + * + * As put_prev_task_scx() hasn't been called on remote CPUs, we can't just look + * at the first task in the local dsq. @rq->curr has to be considered explicitly + * to mimic %SCX_TASK_BAL_KEEP. + */ +static struct task_struct *pick_task_scx(struct rq *rq) +{ + struct task_struct *curr = rq->curr; + struct task_struct *first = first_local_task(rq); + + if (curr->scx.flags & SCX_TASK_QUEUED) { + /* is curr the only runnable task? */ + if (!first) + return curr; + + /* + * Does curr trump first? We can always go by core_sched_at for + * this comparison as it represents global FIFO ordering when + * the default core-sched ordering is used and local-DSQ FIFO + * ordering otherwise. + * + * We can have a task with an earlier timestamp on the DSQ. For + * example, when a current task is preempted by a sibling + * picking a different cookie, the task would be requeued at the + * head of the local DSQ with an earlier timestamp than the + * core-sched picked next task. Besides, the BPF scheduler may + * dispatch any tasks to the local DSQ anytime. + */ + if (curr->scx.slice && time_before64(curr->scx.core_sched_at, + first->scx.core_sched_at)) + return curr; + } + + return first; /* this may be %NULL */ +} +#endif /* CONFIG_SCHED_CORE */ + static enum scx_cpu_preempt_reason preempt_reason_from_class(const struct sched_class *class) { @@ -2843,13 +3059,15 @@ static void task_tick_scx(struct rq *rq, struct task_struct *curr, int queued) update_curr_scx(rq); /* - * While bypassing, always resched as we can't trust the slice - * management. + * While disabling, always resched and refresh core-sched timestamp as + * we can't trust the slice management or ops.core_sched_before(). */ - if (scx_ops_bypassing()) + if (scx_ops_bypassing()) { curr->scx.slice = 0; - else if (SCX_HAS_OP(tick)) + touch_core_sched(rq, curr); + } else if (SCX_HAS_OP(tick)) { SCX_CALL_OP(SCX_KF_REST, tick, curr); + } if (!curr->scx.slice) resched_curr(rq); @@ -3203,6 +3421,10 @@ DEFINE_SCHED_CLASS(ext) = { .rq_offline = rq_offline_scx, #endif +#ifdef CONFIG_SCHED_CORE + .pick_task = pick_task_scx, +#endif + .task_tick = task_tick_scx, .switching_to = switching_to_scx, @@ -3416,12 +3638,14 @@ bool task_should_scx(struct task_struct *p) * * c. balance_scx() never sets %SCX_TASK_BAL_KEEP as the slice value can't be * trusted. Whenever a tick triggers, the running task is rotated to the tail - * of the queue. + * of the queue with core_sched_at touched. * * d. pick_next_task() suppresses zero slice warning. * * e. scx_bpf_kick_cpu() is disabled to avoid irq_work malfunction during PM * operations. + * + * f. scx_prio_less() reverts to the default core_sched_at order. */ static void scx_ops_bypass(bool bypass) { @@ -4583,6 +4807,7 @@ static void running_stub(struct task_struct *p) {} static void stopping_stub(struct task_struct *p, bool runnable) {} static void quiescent_stub(struct task_struct *p, u64 deq_flags) {} static bool yield_stub(struct task_struct *from, struct task_struct *to) { return false; } +static bool core_sched_before_stub(struct task_struct *a, struct task_struct *b) { return false; } static void set_weight_stub(struct task_struct *p, u32 weight) {} static void set_cpumask_stub(struct task_struct *p, const struct cpumask *mask) {} static void update_idle_stub(s32 cpu, bool idle) {} @@ -4607,6 +4832,7 @@ static struct sched_ext_ops __bpf_ops_sched_ext_ops = { .stopping = stopping_stub, .quiescent = quiescent_stub, .yield = yield_stub, + .core_sched_before = core_sched_before_stub, .set_weight = set_weight_stub, .set_cpumask = set_cpumask_stub, .update_idle = update_idle_stub, diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h index 037f9acdf443..6555878c5da3 100644 --- a/kernel/sched/ext.h +++ b/kernel/sched/ext.h @@ -70,6 +70,11 @@ static inline const struct sched_class *next_active_class(const struct sched_cla for_active_class_range(class, (prev_class) > &ext_sched_class ? \ &ext_sched_class : (prev_class), (end_class)) +#ifdef CONFIG_SCHED_CORE +bool scx_prio_less(const struct task_struct *a, const struct task_struct *b, + bool in_fi); +#endif + #else /* CONFIG_SCHED_CLASS_EXT */ #define scx_enabled() false diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c index 619078355bf5..c75c70d6a8eb 100644 --- a/tools/sched_ext/scx_qmap.bpf.c +++ b/tools/sched_ext/scx_qmap.bpf.c @@ -13,6 +13,7 @@ * - Sleepable per-task storage allocation using ops.prep_enable(). * - Using ops.cpu_release() to handle a higher priority scheduling class taking * the CPU away. + * - Core-sched support. * * This scheduler is primarily for demonstration and testing of sched_ext * features and unlikely to be useful for actual workloads. @@ -67,9 +68,21 @@ struct { }, }; +/* + * Per-queue sequence numbers to implement core-sched ordering. + * + * Tail seq is assigned to each queued task and incremented. Head seq tracks the + * sequence number of the latest dispatched task. The distance between the a + * task's seq and the associated queue's head seq is called the queue distance + * and used when comparing two tasks for ordering. See qmap_core_sched_before(). + */ +static u64 core_sched_head_seqs[5]; +static u64 core_sched_tail_seqs[5]; + /* Per-task scheduling context */ struct task_ctx { bool force_local; /* Dispatch directly to local_dsq */ + u64 core_sched_seq; }; struct { @@ -93,6 +106,7 @@ struct { /* Statistics */ u64 nr_enqueued, nr_dispatched, nr_reenqueued, nr_dequeued; +u64 nr_core_sched_execed; s32 BPF_STRUCT_OPS(qmap_select_cpu, struct task_struct *p, s32 prev_cpu, u64 wake_flags) @@ -159,8 +173,18 @@ void BPF_STRUCT_OPS(qmap_enqueue, struct task_struct *p, u64 enq_flags) return; } - /* Is select_cpu() is telling us to enqueue locally? */ - if (tctx->force_local) { + /* + * All enqueued tasks must have their core_sched_seq updated for correct + * core-sched ordering, which is why %SCX_OPS_ENQ_LAST is specified in + * qmap_ops.flags. + */ + tctx->core_sched_seq = core_sched_tail_seqs[idx]++; + + /* + * If qmap_select_cpu() is telling us to or this is the last runnable + * task on the CPU, enqueue locally. + */ + if (tctx->force_local || (enq_flags & SCX_ENQ_LAST)) { tctx->force_local = false; scx_bpf_dispatch(p, SCX_DSQ_LOCAL, slice_ns, enq_flags); return; @@ -204,6 +228,19 @@ void BPF_STRUCT_OPS(qmap_enqueue, struct task_struct *p, u64 enq_flags) void BPF_STRUCT_OPS(qmap_dequeue, struct task_struct *p, u64 deq_flags) { __sync_fetch_and_add(&nr_dequeued, 1); + if (deq_flags & SCX_DEQ_CORE_SCHED_EXEC) + __sync_fetch_and_add(&nr_core_sched_execed, 1); +} + +static void update_core_sched_head_seq(struct task_struct *p) +{ + struct task_ctx *tctx = bpf_task_storage_get(&task_ctx_stor, p, 0, 0); + int idx = weight_to_idx(p->scx.weight); + + if (tctx) + core_sched_head_seqs[idx] = tctx->core_sched_seq; + else + scx_bpf_error("task_ctx lookup failed"); } void BPF_STRUCT_OPS(qmap_dispatch, s32 cpu, struct task_struct *prev) @@ -258,6 +295,7 @@ void BPF_STRUCT_OPS(qmap_dispatch, s32 cpu, struct task_struct *prev) if (!p) continue; + update_core_sched_head_seq(p); __sync_fetch_and_add(&nr_dispatched, 1); scx_bpf_dispatch(p, SHARED_DSQ, slice_ns, 0); bpf_task_release(p); @@ -275,6 +313,49 @@ void BPF_STRUCT_OPS(qmap_dispatch, s32 cpu, struct task_struct *prev) } } +/* + * The distance from the head of the queue scaled by the weight of the queue. + * The lower the number, the older the task and the higher the priority. + */ +static s64 task_qdist(struct task_struct *p) +{ + int idx = weight_to_idx(p->scx.weight); + struct task_ctx *tctx; + s64 qdist; + + tctx = bpf_task_storage_get(&task_ctx_stor, p, 0, 0); + if (!tctx) { + scx_bpf_error("task_ctx lookup failed"); + return 0; + } + + qdist = tctx->core_sched_seq - core_sched_head_seqs[idx]; + + /* + * As queue index increments, the priority doubles. The queue w/ index 3 + * is dispatched twice more frequently than 2. Reflect the difference by + * scaling qdists accordingly. Note that the shift amount needs to be + * flipped depending on the sign to avoid flipping priority direction. + */ + if (qdist >= 0) + return qdist << (4 - idx); + else + return qdist << idx; +} + +/* + * This is called to determine the task ordering when core-sched is picking + * tasks to execute on SMT siblings and should encode about the same ordering as + * the regular scheduling path. Use the priority-scaled distances from the head + * of the queues to compare the two tasks which should be consistent with the + * dispatch path behavior. + */ +bool BPF_STRUCT_OPS(qmap_core_sched_before, + struct task_struct *a, struct task_struct *b) +{ + return task_qdist(a) > task_qdist(b); +} + void BPF_STRUCT_OPS(qmap_cpu_release, s32 cpu, struct scx_cpu_release_args *args) { u32 cnt; @@ -354,8 +435,8 @@ void BPF_STRUCT_OPS(qmap_dump_task, struct scx_dump_ctx *dctx, struct task_struc if (!(taskc = bpf_task_storage_get(&task_ctx_stor, p, 0, 0))) return; - scx_bpf_dump("QMAP: force_local=%d", - taskc->force_local); + scx_bpf_dump("QMAP: force_local=%d core_sched_seq=%llu", + taskc->force_local, taskc->core_sched_seq); } /* @@ -428,6 +509,7 @@ SCX_OPS_DEFINE(qmap_ops, .enqueue = (void *)qmap_enqueue, .dequeue = (void *)qmap_dequeue, .dispatch = (void *)qmap_dispatch, + .core_sched_before = (void *)qmap_core_sched_before, .cpu_release = (void *)qmap_cpu_release, .init_task = (void *)qmap_init_task, .dump = (void *)qmap_dump, @@ -437,5 +519,6 @@ SCX_OPS_DEFINE(qmap_ops, .cpu_offline = (void *)qmap_cpu_offline, .init = (void *)qmap_init, .exit = (void *)qmap_exit, + .flags = SCX_OPS_ENQ_LAST, .timeout_ms = 5000U, .name = "qmap"); diff --git a/tools/sched_ext/scx_qmap.c b/tools/sched_ext/scx_qmap.c index 920fb54f9c77..bc36ec4f88a7 100644 --- a/tools/sched_ext/scx_qmap.c +++ b/tools/sched_ext/scx_qmap.c @@ -112,9 +112,10 @@ int main(int argc, char **argv) long nr_enqueued = skel->bss->nr_enqueued; long nr_dispatched = skel->bss->nr_dispatched; - printf("stats : enq=%lu dsp=%lu delta=%ld reenq=%"PRIu64" deq=%"PRIu64"\n", + printf("stats : enq=%lu dsp=%lu delta=%ld reenq=%"PRIu64" deq=%"PRIu64" core=%"PRIu64"\n", nr_enqueued, nr_dispatched, nr_enqueued - nr_dispatched, - skel->bss->nr_reenqueued, skel->bss->nr_dequeued); + skel->bss->nr_reenqueued, skel->bss->nr_dequeued, + skel->bss->nr_core_sched_execed); fflush(stdout); sleep(1); } -- cgit v1.2.3 From 06e51be3d5e7a07aea5c9012773df8d5de01db6c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 18 Jun 2024 10:09:21 -1000 Subject: sched_ext: Add vtime-ordered priority queue to dispatch_q's Currently, a dsq is always a FIFO. A task which is dispatched earlier gets consumed or executed earlier. While this is sufficient when dsq's are used for simple staging areas for tasks which are ready to execute, it'd make dsq's a lot more useful if they can implement custom ordering. This patch adds a vtime-ordered priority queue to dsq's. When the BPF scheduler dispatches a task with the new scx_bpf_dispatch_vtime() helper, it can specify the vtime tha the task should be inserted at and the task is inserted into the priority queue in the dsq which is ordered according to time_before64() comparison of the vtime values. A DSQ can either be a FIFO or priority queue and automatically switches between the two depending on whether scx_bpf_dispatch() or scx_bpf_dispatch_vtime() is used. Using the wrong variant while the DSQ already has the other type queued is not allowed and triggers an ops error. Built-in DSQs must always be FIFOs. This makes it very easy for the BPF schedulers to implement proper vtime based scheduling within each dsq very easy and efficient at a negligible cost in terms of code complexity and overhead. scx_simple and scx_example_flatcg are updated to default to weighted vtime scheduling (the latter within each cgroup). FIFO scheduling can be selected with -f option. v4: - As allowing mixing priority queue and FIFO on the same DSQ sometimes led to unexpected starvations, DSQs now error out if both modes are used at the same time and the built-in DSQs are no longer allowed to be priority queues. - Explicit type struct scx_dsq_node added to contain fields needed to be linked on DSQs. This will be used to implement stateful iterator. - Tasks are now always linked on dsq->list whether the DSQ is in FIFO or PRIQ mode. This confines PRIQ related complexities to the enqueue and dequeue paths. Other paths only need to look at dsq->list. This will also ease implementing BPF iterator. - Print p->scx.dsq_flags in debug dump. v3: - SCX_TASK_DSQ_ON_PRIQ flag is moved from p->scx.flags into its own p->scx.dsq_flags. The flag is protected with the dsq lock unlike other flags in p->scx.flags. This led to flag corruption in some cases. - Add comments explaining the interaction between using consumption of p->scx.slice to determine vtime progress and yielding. v2: - p->scx.dsq_vtime was not initialized on load or across cgroup migrations leading to some tasks being stalled for extended period of time depending on how saturated the machine is. Fixed. Signed-off-by: Tejun Heo Reviewed-by: David Vernet --- include/linux/sched/ext.h | 29 +++++- init/init_task.c | 2 +- kernel/sched/ext.c | 156 +++++++++++++++++++++++++++---- tools/sched_ext/include/scx/common.bpf.h | 1 + tools/sched_ext/scx_simple.bpf.c | 97 ++++++++++++++++++- tools/sched_ext/scx_simple.c | 8 +- 6 files changed, 267 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index 3db7b32b2d1d..9cee193dab19 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -49,12 +49,15 @@ enum scx_dsq_id_flags { }; /* - * Dispatch queue (dsq) is a simple FIFO which is used to buffer between the - * scheduler core and the BPF scheduler. See the documentation for more details. + * A dispatch queue (DSQ) can be either a FIFO or p->scx.dsq_vtime ordered + * queue. A built-in DSQ is always a FIFO. The built-in local DSQs are used to + * buffer between the scheduler core and the BPF scheduler. See the + * documentation for more details. */ struct scx_dispatch_q { raw_spinlock_t lock; struct list_head list; /* tasks in dispatch order */ + struct rb_root priq; /* used to order by p->scx.dsq_vtime */ u32 nr; u64 id; struct rhash_head hash_node; @@ -86,6 +89,11 @@ enum scx_task_state { SCX_TASK_NR_STATES, }; +/* scx_entity.dsq_flags */ +enum scx_ent_dsq_flags { + SCX_TASK_DSQ_ON_PRIQ = 1 << 0, /* task is queued on the priority queue of a dsq */ +}; + /* * Mask bits for scx_entity.kf_mask. Not all kfuncs can be called from * everywhere and the following bits track which kfunc sets are currently @@ -111,13 +119,19 @@ enum scx_kf_mask { __SCX_KF_TERMINAL = SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU | SCX_KF_REST, }; +struct scx_dsq_node { + struct list_head list; /* dispatch order */ + struct rb_node priq; /* p->scx.dsq_vtime order */ + u32 flags; /* SCX_TASK_DSQ_* flags */ +}; + /* * The following is embedded in task_struct and contains all fields necessary * for a task to be scheduled by SCX. */ struct sched_ext_entity { struct scx_dispatch_q *dsq; - struct list_head dsq_node; + struct scx_dsq_node dsq_node; /* protected by dsq lock */ u32 flags; /* protected by rq lock */ u32 weight; s32 sticky_cpu; @@ -149,6 +163,15 @@ struct sched_ext_entity { */ u64 slice; + /* + * Used to order tasks when dispatching to the vtime-ordered priority + * queue of a dsq. This is usually set through scx_bpf_dispatch_vtime() + * but can also be modified directly by the BPF scheduler. Modifying it + * while a task is queued on a dsq may mangle the ordering and is not + * recommended. + */ + u64 dsq_vtime; + /* * If set, reject future sched_setscheduler(2) calls updating the policy * to %SCHED_EXT with -%EACCES. diff --git a/init/init_task.c b/init/init_task.c index 8a44c932d10f..5726b3a0eea9 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -102,7 +102,7 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = { #endif #ifdef CONFIG_SCHED_CLASS_EXT .scx = { - .dsq_node = LIST_HEAD_INIT(init_task.scx.dsq_node), + .dsq_node.list = LIST_HEAD_INIT(init_task.scx.dsq_node.list), .sticky_cpu = -1, .holding_cpu = -1, .runnable_node = LIST_HEAD_INIT(init_task.scx.runnable_node), diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 1feb690be9d8..f186c576e7d9 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -638,6 +638,7 @@ enum scx_enq_flags { __SCX_ENQ_INTERNAL_MASK = 0xffLLU << 56, SCX_ENQ_CLEAR_OPSS = 1LLU << 56, + SCX_ENQ_DSQ_PRIQ = 1LLU << 57, }; enum scx_deq_flags { @@ -1351,6 +1352,17 @@ static void update_curr_scx(struct rq *rq) } } +static bool scx_dsq_priq_less(struct rb_node *node_a, + const struct rb_node *node_b) +{ + const struct task_struct *a = + container_of(node_a, struct task_struct, scx.dsq_node.priq); + const struct task_struct *b = + container_of(node_b, struct task_struct, scx.dsq_node.priq); + + return time_before64(a->scx.dsq_vtime, b->scx.dsq_vtime); +} + static void dsq_mod_nr(struct scx_dispatch_q *dsq, s32 delta) { /* scx_bpf_dsq_nr_queued() reads ->nr without locking, use WRITE_ONCE() */ @@ -1362,7 +1374,9 @@ static void dispatch_enqueue(struct scx_dispatch_q *dsq, struct task_struct *p, { bool is_local = dsq->id == SCX_DSQ_LOCAL; - WARN_ON_ONCE(p->scx.dsq || !list_empty(&p->scx.dsq_node)); + WARN_ON_ONCE(p->scx.dsq || !list_empty(&p->scx.dsq_node.list)); + WARN_ON_ONCE((p->scx.dsq_node.flags & SCX_TASK_DSQ_ON_PRIQ) || + !RB_EMPTY_NODE(&p->scx.dsq_node.priq)); if (!is_local) { raw_spin_lock(&dsq->lock); @@ -1375,10 +1389,59 @@ static void dispatch_enqueue(struct scx_dispatch_q *dsq, struct task_struct *p, } } - if (enq_flags & (SCX_ENQ_HEAD | SCX_ENQ_PREEMPT)) - list_add(&p->scx.dsq_node, &dsq->list); - else - list_add_tail(&p->scx.dsq_node, &dsq->list); + if (unlikely((dsq->id & SCX_DSQ_FLAG_BUILTIN) && + (enq_flags & SCX_ENQ_DSQ_PRIQ))) { + /* + * SCX_DSQ_LOCAL and SCX_DSQ_GLOBAL DSQs always consume from + * their FIFO queues. To avoid confusion and accidentally + * starving vtime-dispatched tasks by FIFO-dispatched tasks, we + * disallow any internal DSQ from doing vtime ordering of + * tasks. + */ + scx_ops_error("cannot use vtime ordering for built-in DSQs"); + enq_flags &= ~SCX_ENQ_DSQ_PRIQ; + } + + if (enq_flags & SCX_ENQ_DSQ_PRIQ) { + struct rb_node *rbp; + + /* + * A PRIQ DSQ shouldn't be using FIFO enqueueing. As tasks are + * linked to both the rbtree and list on PRIQs, this can only be + * tested easily when adding the first task. + */ + if (unlikely(RB_EMPTY_ROOT(&dsq->priq) && + !list_empty(&dsq->list))) + scx_ops_error("DSQ ID 0x%016llx already had FIFO-enqueued tasks", + dsq->id); + + p->scx.dsq_node.flags |= SCX_TASK_DSQ_ON_PRIQ; + rb_add(&p->scx.dsq_node.priq, &dsq->priq, scx_dsq_priq_less); + + /* + * Find the previous task and insert after it on the list so + * that @dsq->list is vtime ordered. + */ + rbp = rb_prev(&p->scx.dsq_node.priq); + if (rbp) { + struct task_struct *prev = + container_of(rbp, struct task_struct, + scx.dsq_node.priq); + list_add(&p->scx.dsq_node.list, &prev->scx.dsq_node.list); + } else { + list_add(&p->scx.dsq_node.list, &dsq->list); + } + } else { + /* a FIFO DSQ shouldn't be using PRIQ enqueuing */ + if (unlikely(!RB_EMPTY_ROOT(&dsq->priq))) + scx_ops_error("DSQ ID 0x%016llx already had PRIQ-enqueued tasks", + dsq->id); + + if (enq_flags & (SCX_ENQ_HEAD | SCX_ENQ_PREEMPT)) + list_add(&p->scx.dsq_node.list, &dsq->list); + else + list_add_tail(&p->scx.dsq_node.list, &dsq->list); + } dsq_mod_nr(dsq, 1); p->scx.dsq = dsq; @@ -1417,13 +1480,30 @@ static void dispatch_enqueue(struct scx_dispatch_q *dsq, struct task_struct *p, } } +static void task_unlink_from_dsq(struct task_struct *p, + struct scx_dispatch_q *dsq) +{ + if (p->scx.dsq_node.flags & SCX_TASK_DSQ_ON_PRIQ) { + rb_erase(&p->scx.dsq_node.priq, &dsq->priq); + RB_CLEAR_NODE(&p->scx.dsq_node.priq); + p->scx.dsq_node.flags &= ~SCX_TASK_DSQ_ON_PRIQ; + } + + list_del_init(&p->scx.dsq_node.list); +} + +static bool task_linked_on_dsq(struct task_struct *p) +{ + return !list_empty(&p->scx.dsq_node.list); +} + static void dispatch_dequeue(struct rq *rq, struct task_struct *p) { struct scx_dispatch_q *dsq = p->scx.dsq; bool is_local = dsq == &rq->scx.local_dsq; if (!dsq) { - WARN_ON_ONCE(!list_empty(&p->scx.dsq_node)); + WARN_ON_ONCE(task_linked_on_dsq(p)); /* * When dispatching directly from the BPF scheduler to a local * DSQ, the task isn't associated with any DSQ but @@ -1444,8 +1524,8 @@ static void dispatch_dequeue(struct rq *rq, struct task_struct *p) */ if (p->scx.holding_cpu < 0) { /* @p must still be on @dsq, dequeue */ - WARN_ON_ONCE(list_empty(&p->scx.dsq_node)); - list_del_init(&p->scx.dsq_node); + WARN_ON_ONCE(!task_linked_on_dsq(p)); + task_unlink_from_dsq(p, dsq); dsq_mod_nr(dsq, -1); } else { /* @@ -1454,7 +1534,7 @@ static void dispatch_dequeue(struct rq *rq, struct task_struct *p) * holding_cpu which tells dispatch_to_local_dsq() that it lost * the race. */ - WARN_ON_ONCE(!list_empty(&p->scx.dsq_node)); + WARN_ON_ONCE(task_linked_on_dsq(p)); p->scx.holding_cpu = -1; } p->scx.dsq = NULL; @@ -1949,7 +2029,8 @@ static void consume_local_task(struct rq *rq, struct scx_dispatch_q *dsq, /* @dsq is locked and @p is on this rq */ WARN_ON_ONCE(p->scx.holding_cpu >= 0); - list_move_tail(&p->scx.dsq_node, &rq->scx.local_dsq.list); + task_unlink_from_dsq(p, dsq); + list_add_tail(&p->scx.dsq_node.list, &rq->scx.local_dsq.list); dsq_mod_nr(dsq, -1); dsq_mod_nr(&rq->scx.local_dsq, 1); p->scx.dsq = &rq->scx.local_dsq; @@ -1992,7 +2073,7 @@ static bool consume_remote_task(struct rq *rq, struct rq_flags *rf, * move_task_to_local_dsq(). */ WARN_ON_ONCE(p->scx.holding_cpu >= 0); - list_del_init(&p->scx.dsq_node); + task_unlink_from_dsq(p, dsq); dsq_mod_nr(dsq, -1); p->scx.holding_cpu = raw_smp_processor_id(); raw_spin_unlock(&dsq->lock); @@ -2024,7 +2105,7 @@ retry: raw_spin_lock(&dsq->lock); - list_for_each_entry(p, &dsq->list, scx.dsq_node) { + list_for_each_entry(p, &dsq->list, scx.dsq_node.list) { struct rq *task_rq = task_rq(p); if (rq == task_rq) { @@ -2543,7 +2624,7 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p) static struct task_struct *first_local_task(struct rq *rq) { return list_first_entry_or_null(&rq->scx.local_dsq.list, - struct task_struct, scx.dsq_node); + struct task_struct, scx.dsq_node.list); } static struct task_struct *pick_next_task_scx(struct rq *rq) @@ -3225,7 +3306,8 @@ void init_scx_entity(struct sched_ext_entity *scx) */ memset(scx, 0, offsetof(struct sched_ext_entity, tasks_node)); - INIT_LIST_HEAD(&scx->dsq_node); + INIT_LIST_HEAD(&scx->dsq_node.list); + RB_CLEAR_NODE(&scx->dsq_node.priq); scx->sticky_cpu = -1; scx->holding_cpu = -1; INIT_LIST_HEAD(&scx->runnable_node); @@ -4070,12 +4152,13 @@ static void scx_dump_task(struct seq_buf *s, struct scx_dump_ctx *dctx, dump_line(s, " %c%c %s[%d] %+ldms", marker, task_state_to_char(p), p->comm, p->pid, jiffies_delta_msecs(p->scx.runnable_at, dctx->at_jiffies)); - dump_line(s, " scx_state/flags=%u/0x%x ops_state/qseq=%lu/%lu", + dump_line(s, " scx_state/flags=%u/0x%x dsq_flags=0x%x ops_state/qseq=%lu/%lu", scx_get_task_state(p), p->scx.flags & ~SCX_TASK_STATE_MASK, - ops_state & SCX_OPSS_STATE_MASK, + p->scx.dsq_node.flags, ops_state & SCX_OPSS_STATE_MASK, ops_state >> SCX_OPSS_QSEQ_SHIFT); - dump_line(s, " sticky/holding_cpu=%d/%d dsq_id=%s", - p->scx.sticky_cpu, p->scx.holding_cpu, dsq_id_buf); + dump_line(s, " sticky/holding_cpu=%d/%d dsq_id=%s dsq_vtime=%llu", + p->scx.sticky_cpu, p->scx.holding_cpu, dsq_id_buf, + p->scx.dsq_vtime); dump_line(s, " cpus=%*pb", cpumask_pr_args(p->cpus_ptr)); if (SCX_HAS_OP(dump_task)) { @@ -4663,6 +4746,9 @@ static int bpf_scx_btf_struct_access(struct bpf_verifier_log *log, if (off >= offsetof(struct task_struct, scx.slice) && off + size <= offsetofend(struct task_struct, scx.slice)) return SCALAR_VALUE; + if (off >= offsetof(struct task_struct, scx.dsq_vtime) && + off + size <= offsetofend(struct task_struct, scx.dsq_vtime)) + return SCALAR_VALUE; if (off >= offsetof(struct task_struct, scx.disallow) && off + size <= offsetofend(struct task_struct, scx.disallow)) return SCALAR_VALUE; @@ -5298,10 +5384,44 @@ __bpf_kfunc void scx_bpf_dispatch(struct task_struct *p, u64 dsq_id, u64 slice, scx_dispatch_commit(p, dsq_id, enq_flags); } +/** + * scx_bpf_dispatch_vtime - Dispatch a task into the vtime priority queue of a DSQ + * @p: task_struct to dispatch + * @dsq_id: DSQ to dispatch to + * @slice: duration @p can run for in nsecs + * @vtime: @p's ordering inside the vtime-sorted queue of the target DSQ + * @enq_flags: SCX_ENQ_* + * + * Dispatch @p into the vtime priority queue of the DSQ identified by @dsq_id. + * Tasks queued into the priority queue are ordered by @vtime and always + * consumed after the tasks in the FIFO queue. All other aspects are identical + * to scx_bpf_dispatch(). + * + * @vtime ordering is according to time_before64() which considers wrapping. A + * numerically larger vtime may indicate an earlier position in the ordering and + * vice-versa. + */ +__bpf_kfunc void scx_bpf_dispatch_vtime(struct task_struct *p, u64 dsq_id, + u64 slice, u64 vtime, u64 enq_flags) +{ + if (!scx_dispatch_preamble(p, enq_flags)) + return; + + if (slice) + p->scx.slice = slice; + else + p->scx.slice = p->scx.slice ?: 1; + + p->scx.dsq_vtime = vtime; + + scx_dispatch_commit(p, dsq_id, enq_flags | SCX_ENQ_DSQ_PRIQ); +} + __bpf_kfunc_end_defs(); BTF_KFUNCS_START(scx_kfunc_ids_enqueue_dispatch) BTF_ID_FLAGS(func, scx_bpf_dispatch, KF_RCU) +BTF_ID_FLAGS(func, scx_bpf_dispatch_vtime, KF_RCU) BTF_KFUNCS_END(scx_kfunc_ids_enqueue_dispatch) static const struct btf_kfunc_id_set scx_kfunc_set_enqueue_dispatch = { diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h index 8686f84497db..3fa87084cf17 100644 --- a/tools/sched_ext/include/scx/common.bpf.h +++ b/tools/sched_ext/include/scx/common.bpf.h @@ -31,6 +31,7 @@ static inline void ___vmlinux_h_sanity_check___(void) s32 scx_bpf_create_dsq(u64 dsq_id, s32 node) __ksym; s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, bool *is_idle) __ksym; void scx_bpf_dispatch(struct task_struct *p, u64 dsq_id, u64 slice, u64 enq_flags) __ksym; +void scx_bpf_dispatch_vtime(struct task_struct *p, u64 dsq_id, u64 slice, u64 vtime, u64 enq_flags) __ksym; u32 scx_bpf_dispatch_nr_slots(void) __ksym; void scx_bpf_dispatch_cancel(void) __ksym; bool scx_bpf_consume(u64 dsq_id) __ksym; diff --git a/tools/sched_ext/scx_simple.bpf.c b/tools/sched_ext/scx_simple.bpf.c index 6bb13a3c801b..ed7e8d535fc5 100644 --- a/tools/sched_ext/scx_simple.bpf.c +++ b/tools/sched_ext/scx_simple.bpf.c @@ -2,11 +2,20 @@ /* * A simple scheduler. * - * A simple global FIFO scheduler. It also demonstrates the following niceties. + * By default, it operates as a simple global weighted vtime scheduler and can + * be switched to FIFO scheduling. It also demonstrates the following niceties. * * - Statistics tracking how many tasks are queued to local and global dsq's. * - Termination notification for userspace. * + * While very simple, this scheduler should work reasonably well on CPUs with a + * uniform L3 cache topology. While preemption is not implemented, the fact that + * the scheduling queue is shared across all CPUs means that whatever is at the + * front of the queue is likely to be executed fairly quickly given enough + * number of CPUs. The FIFO scheduling mode may be beneficial to some workloads + * but comes with the usual problems with FIFO scheduling where saturating + * threads can easily drown out interactive ones. + * * Copyright (c) 2022 Meta Platforms, Inc. and affiliates. * Copyright (c) 2022 Tejun Heo * Copyright (c) 2022 David Vernet @@ -15,8 +24,20 @@ char _license[] SEC("license") = "GPL"; +const volatile bool fifo_sched; + +static u64 vtime_now; UEI_DEFINE(uei); +/* + * Built-in DSQs such as SCX_DSQ_GLOBAL cannot be used as priority queues + * (meaning, cannot be dispatched to with scx_bpf_dispatch_vtime()). We + * therefore create a separate DSQ with ID 0 that we dispatch to and consume + * from. If scx_simple only supported global FIFO scheduling, then we could + * just use SCX_DSQ_GLOBAL. + */ +#define SHARED_DSQ 0 + struct { __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); __uint(key_size, sizeof(u32)); @@ -31,6 +52,11 @@ static void stat_inc(u32 idx) (*cnt_p)++; } +static inline bool vtime_before(u64 a, u64 b) +{ + return (s64)(a - b) < 0; +} + s32 BPF_STRUCT_OPS(simple_select_cpu, struct task_struct *p, s32 prev_cpu, u64 wake_flags) { bool is_idle = false; @@ -48,7 +74,69 @@ s32 BPF_STRUCT_OPS(simple_select_cpu, struct task_struct *p, s32 prev_cpu, u64 w void BPF_STRUCT_OPS(simple_enqueue, struct task_struct *p, u64 enq_flags) { stat_inc(1); /* count global queueing */ - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + + if (fifo_sched) { + scx_bpf_dispatch(p, SHARED_DSQ, SCX_SLICE_DFL, enq_flags); + } else { + u64 vtime = p->scx.dsq_vtime; + + /* + * Limit the amount of budget that an idling task can accumulate + * to one slice. + */ + if (vtime_before(vtime, vtime_now - SCX_SLICE_DFL)) + vtime = vtime_now - SCX_SLICE_DFL; + + scx_bpf_dispatch_vtime(p, SHARED_DSQ, SCX_SLICE_DFL, vtime, + enq_flags); + } +} + +void BPF_STRUCT_OPS(simple_dispatch, s32 cpu, struct task_struct *prev) +{ + scx_bpf_consume(SHARED_DSQ); +} + +void BPF_STRUCT_OPS(simple_running, struct task_struct *p) +{ + if (fifo_sched) + return; + + /* + * Global vtime always progresses forward as tasks start executing. The + * test and update can be performed concurrently from multiple CPUs and + * thus racy. Any error should be contained and temporary. Let's just + * live with it. + */ + if (vtime_before(vtime_now, p->scx.dsq_vtime)) + vtime_now = p->scx.dsq_vtime; +} + +void BPF_STRUCT_OPS(simple_stopping, struct task_struct *p, bool runnable) +{ + if (fifo_sched) + return; + + /* + * Scale the execution time by the inverse of the weight and charge. + * + * Note that the default yield implementation yields by setting + * @p->scx.slice to zero and the following would treat the yielding task + * as if it has consumed all its slice. If this penalizes yielding tasks + * too much, determine the execution time by taking explicit timestamps + * instead of depending on @p->scx.slice. + */ + p->scx.dsq_vtime += (SCX_SLICE_DFL - p->scx.slice) * 100 / p->scx.weight; +} + +void BPF_STRUCT_OPS(simple_enable, struct task_struct *p) +{ + p->scx.dsq_vtime = vtime_now; +} + +s32 BPF_STRUCT_OPS_SLEEPABLE(simple_init) +{ + return scx_bpf_create_dsq(SHARED_DSQ, -1); } void BPF_STRUCT_OPS(simple_exit, struct scx_exit_info *ei) @@ -59,5 +147,10 @@ void BPF_STRUCT_OPS(simple_exit, struct scx_exit_info *ei) SCX_OPS_DEFINE(simple_ops, .select_cpu = (void *)simple_select_cpu, .enqueue = (void *)simple_enqueue, + .dispatch = (void *)simple_dispatch, + .running = (void *)simple_running, + .stopping = (void *)simple_stopping, + .enable = (void *)simple_enable, + .init = (void *)simple_init, .exit = (void *)simple_exit, .name = "simple"); diff --git a/tools/sched_ext/scx_simple.c b/tools/sched_ext/scx_simple.c index bead482e1383..76d83199545c 100644 --- a/tools/sched_ext/scx_simple.c +++ b/tools/sched_ext/scx_simple.c @@ -17,8 +17,9 @@ const char help_fmt[] = "\n" "See the top-level comment in .bpf.c for more details.\n" "\n" -"Usage: %s [-v]\n" +"Usage: %s [-f] [-v]\n" "\n" +" -f Use FIFO scheduling instead of weighted vtime scheduling\n" " -v Print libbpf debug messages\n" " -h Display this help and exit\n"; @@ -70,8 +71,11 @@ int main(int argc, char **argv) restart: skel = SCX_OPS_OPEN(simple_ops, scx_simple); - while ((opt = getopt(argc, argv, "vh")) != -1) { + while ((opt = getopt(argc, argv, "fvh")) != -1) { switch (opt) { + case 'f': + skel->rodata->fifo_sched = true; + break; case 'v': verbose = true; break; -- cgit v1.2.3 From fa48e8d2c7b58d242c1db3a09c14f4274e055087 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 18 Jun 2024 10:09:21 -1000 Subject: sched_ext: Documentation: scheduler: Document extensible scheduler class Add Documentation/scheduler/sched-ext.rst which gives a high-level overview and pointers to the examples. v6: - Add paragraph explaining debug dump. v5: - Updated to reflect /sys/kernel interface change. Kconfig options added. v4: - README improved, reformatted in markdown and renamed to README.md. v3: - Added tools/sched_ext/README. - Dropped _example prefix from scheduler names. v2: - Apply minor edits suggested by Bagas. Caveats section dropped as all of them are addressed. Signed-off-by: Tejun Heo Reviewed-by: David Vernet Acked-by: Josh Don Acked-by: Hao Luo Acked-by: Barret Rhoden Cc: Bagas Sanjaya --- Documentation/scheduler/index.rst | 1 + Documentation/scheduler/sched-ext.rst | 314 ++++++++++++++++++++++++++++++++++ include/linux/sched/ext.h | 2 + kernel/Kconfig.preempt | 1 + kernel/sched/ext.c | 2 + kernel/sched/ext.h | 2 + tools/sched_ext/README.md | 258 ++++++++++++++++++++++++++++ 7 files changed, 580 insertions(+) create mode 100644 Documentation/scheduler/sched-ext.rst create mode 100644 tools/sched_ext/README.md (limited to 'include/linux') diff --git a/Documentation/scheduler/index.rst b/Documentation/scheduler/index.rst index 43bd8a145b7a..0611dc3dda8e 100644 --- a/Documentation/scheduler/index.rst +++ b/Documentation/scheduler/index.rst @@ -20,6 +20,7 @@ Scheduler sched-nice-design sched-rt-group sched-stats + sched-ext sched-debug text_files diff --git a/Documentation/scheduler/sched-ext.rst b/Documentation/scheduler/sched-ext.rst new file mode 100644 index 000000000000..497eeaa5ecbe --- /dev/null +++ b/Documentation/scheduler/sched-ext.rst @@ -0,0 +1,314 @@ +========================== +Extensible Scheduler Class +========================== + +sched_ext is a scheduler class whose behavior can be defined by a set of BPF +programs - the BPF scheduler. + +* sched_ext exports a full scheduling interface so that any scheduling + algorithm can be implemented on top. + +* The BPF scheduler can group CPUs however it sees fit and schedule them + together, as tasks aren't tied to specific CPUs at the time of wakeup. + +* The BPF scheduler can be turned on and off dynamically anytime. + +* The system integrity is maintained no matter what the BPF scheduler does. + The default scheduling behavior is restored anytime an error is detected, + a runnable task stalls, or on invoking the SysRq key sequence + :kbd:`SysRq-S`. + +* When the BPF scheduler triggers an error, debug information is dumped to + aid debugging. The debug dump is passed to and printed out by the + scheduler binary. The debug dump can also be accessed through the + `sched_ext_dump` tracepoint. The SysRq key sequence :kbd:`SysRq-D` + triggers a debug dump. This doesn't terminate the BPF scheduler and can + only be read through the tracepoint. + +Switching to and from sched_ext +=============================== + +``CONFIG_SCHED_CLASS_EXT`` is the config option to enable sched_ext and +``tools/sched_ext`` contains the example schedulers. The following config +options should be enabled to use sched_ext: + +.. code-block:: none + + CONFIG_BPF=y + CONFIG_SCHED_CLASS_EXT=y + CONFIG_BPF_SYSCALL=y + CONFIG_BPF_JIT=y + CONFIG_DEBUG_INFO_BTF=y + CONFIG_BPF_JIT_ALWAYS_ON=y + CONFIG_BPF_JIT_DEFAULT_ON=y + CONFIG_PAHOLE_HAS_SPLIT_BTF=y + CONFIG_PAHOLE_HAS_BTF_TAG=y + +sched_ext is used only when the BPF scheduler is loaded and running. + +If a task explicitly sets its scheduling policy to ``SCHED_EXT``, it will be +treated as ``SCHED_NORMAL`` and scheduled by CFS until the BPF scheduler is +loaded. On load, such tasks will be switched to and scheduled by sched_ext. + +The BPF scheduler can choose to schedule all normal and lower class tasks by +calling ``scx_bpf_switch_all()`` from its ``init()`` operation. In this +case, all ``SCHED_NORMAL``, ``SCHED_BATCH``, ``SCHED_IDLE`` and +``SCHED_EXT`` tasks are scheduled by sched_ext. In the example schedulers, +this mode can be selected with the ``-a`` option. + +Terminating the sched_ext scheduler program, triggering :kbd:`SysRq-S`, or +detection of any internal error including stalled runnable tasks aborts the +BPF scheduler and reverts all tasks back to CFS. + +.. code-block:: none + + # make -j16 -C tools/sched_ext + # tools/sched_ext/scx_simple + local=0 global=3 + local=5 global=24 + local=9 global=44 + local=13 global=56 + local=17 global=72 + ^CEXIT: BPF scheduler unregistered + +The current status of the BPF scheduler can be determined as follows: + +.. code-block:: none + + # cat /sys/kernel/sched_ext/state + enabled + # cat /sys/kernel/sched_ext/root/ops + simple + +``tools/sched_ext/scx_show_state.py`` is a drgn script which shows more +detailed information: + +.. code-block:: none + + # tools/sched_ext/scx_show_state.py + ops : simple + enabled : 1 + switching_all : 1 + switched_all : 1 + enable_state : enabled (2) + bypass_depth : 0 + nr_rejected : 0 + +If ``CONFIG_SCHED_DEBUG`` is set, whether a given task is on sched_ext can +be determined as follows: + +.. code-block:: none + + # grep ext /proc/self/sched + ext.enabled : 1 + +The Basics +========== + +Userspace can implement an arbitrary BPF scheduler by loading a set of BPF +programs that implement ``struct sched_ext_ops``. The only mandatory field +is ``ops.name`` which must be a valid BPF object name. All operations are +optional. The following modified excerpt is from +``tools/sched/scx_simple.bpf.c`` showing a minimal global FIFO scheduler. + +.. code-block:: c + + /* + * Decide which CPU a task should be migrated to before being + * enqueued (either at wakeup, fork time, or exec time). If an + * idle core is found by the default ops.select_cpu() implementation, + * then dispatch the task directly to SCX_DSQ_LOCAL and skip the + * ops.enqueue() callback. + * + * Note that this implementation has exactly the same behavior as the + * default ops.select_cpu implementation. The behavior of the scheduler + * would be exactly same if the implementation just didn't define the + * simple_select_cpu() struct_ops prog. + */ + s32 BPF_STRUCT_OPS(simple_select_cpu, struct task_struct *p, + s32 prev_cpu, u64 wake_flags) + { + s32 cpu; + /* Need to initialize or the BPF verifier will reject the program */ + bool direct = false; + + cpu = scx_bpf_select_cpu_dfl(p, prev_cpu, wake_flags, &direct); + + if (direct) + scx_bpf_dispatch(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, 0); + + return cpu; + } + + /* + * Do a direct dispatch of a task to the global DSQ. This ops.enqueue() + * callback will only be invoked if we failed to find a core to dispatch + * to in ops.select_cpu() above. + * + * Note that this implementation has exactly the same behavior as the + * default ops.enqueue implementation, which just dispatches the task + * to SCX_DSQ_GLOBAL. The behavior of the scheduler would be exactly same + * if the implementation just didn't define the simple_enqueue struct_ops + * prog. + */ + void BPF_STRUCT_OPS(simple_enqueue, struct task_struct *p, u64 enq_flags) + { + scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + } + + s32 BPF_STRUCT_OPS(simple_init) + { + /* + * All SCHED_OTHER, SCHED_IDLE, and SCHED_BATCH tasks should + * use sched_ext. + */ + scx_bpf_switch_all(); + return 0; + } + + void BPF_STRUCT_OPS(simple_exit, struct scx_exit_info *ei) + { + exit_type = ei->type; + } + + SEC(".struct_ops") + struct sched_ext_ops simple_ops = { + .select_cpu = (void *)simple_select_cpu, + .enqueue = (void *)simple_enqueue, + .init = (void *)simple_init, + .exit = (void *)simple_exit, + .name = "simple", + }; + +Dispatch Queues +--------------- + +To match the impedance between the scheduler core and the BPF scheduler, +sched_ext uses DSQs (dispatch queues) which can operate as both a FIFO and a +priority queue. By default, there is one global FIFO (``SCX_DSQ_GLOBAL``), +and one local dsq per CPU (``SCX_DSQ_LOCAL``). The BPF scheduler can manage +an arbitrary number of dsq's using ``scx_bpf_create_dsq()`` and +``scx_bpf_destroy_dsq()``. + +A CPU always executes a task from its local DSQ. A task is "dispatched" to a +DSQ. A non-local DSQ is "consumed" to transfer a task to the consuming CPU's +local DSQ. + +When a CPU is looking for the next task to run, if the local DSQ is not +empty, the first task is picked. Otherwise, the CPU tries to consume the +global DSQ. If that doesn't yield a runnable task either, ``ops.dispatch()`` +is invoked. + +Scheduling Cycle +---------------- + +The following briefly shows how a waking task is scheduled and executed. + +1. When a task is waking up, ``ops.select_cpu()`` is the first operation + invoked. This serves two purposes. First, CPU selection optimization + hint. Second, waking up the selected CPU if idle. + + The CPU selected by ``ops.select_cpu()`` is an optimization hint and not + binding. The actual decision is made at the last step of scheduling. + However, there is a small performance gain if the CPU + ``ops.select_cpu()`` returns matches the CPU the task eventually runs on. + + A side-effect of selecting a CPU is waking it up from idle. While a BPF + scheduler can wake up any cpu using the ``scx_bpf_kick_cpu()`` helper, + using ``ops.select_cpu()`` judiciously can be simpler and more efficient. + + A task can be immediately dispatched to a DSQ from ``ops.select_cpu()`` by + calling ``scx_bpf_dispatch()``. If the task is dispatched to + ``SCX_DSQ_LOCAL`` from ``ops.select_cpu()``, it will be dispatched to the + local DSQ of whichever CPU is returned from ``ops.select_cpu()``. + Additionally, dispatching directly from ``ops.select_cpu()`` will cause the + ``ops.enqueue()`` callback to be skipped. + + Note that the scheduler core will ignore an invalid CPU selection, for + example, if it's outside the allowed cpumask of the task. + +2. Once the target CPU is selected, ``ops.enqueue()`` is invoked (unless the + task was dispatched directly from ``ops.select_cpu()``). ``ops.enqueue()`` + can make one of the following decisions: + + * Immediately dispatch the task to either the global or local DSQ by + calling ``scx_bpf_dispatch()`` with ``SCX_DSQ_GLOBAL`` or + ``SCX_DSQ_LOCAL``, respectively. + + * Immediately dispatch the task to a custom DSQ by calling + ``scx_bpf_dispatch()`` with a DSQ ID which is smaller than 2^63. + + * Queue the task on the BPF side. + +3. When a CPU is ready to schedule, it first looks at its local DSQ. If + empty, it then looks at the global DSQ. If there still isn't a task to + run, ``ops.dispatch()`` is invoked which can use the following two + functions to populate the local DSQ. + + * ``scx_bpf_dispatch()`` dispatches a task to a DSQ. Any target DSQ can + be used - ``SCX_DSQ_LOCAL``, ``SCX_DSQ_LOCAL_ON | cpu``, + ``SCX_DSQ_GLOBAL`` or a custom DSQ. While ``scx_bpf_dispatch()`` + currently can't be called with BPF locks held, this is being worked on + and will be supported. ``scx_bpf_dispatch()`` schedules dispatching + rather than performing them immediately. There can be up to + ``ops.dispatch_max_batch`` pending tasks. + + * ``scx_bpf_consume()`` tranfers a task from the specified non-local DSQ + to the dispatching DSQ. This function cannot be called with any BPF + locks held. ``scx_bpf_consume()`` flushes the pending dispatched tasks + before trying to consume the specified DSQ. + +4. After ``ops.dispatch()`` returns, if there are tasks in the local DSQ, + the CPU runs the first one. If empty, the following steps are taken: + + * Try to consume the global DSQ. If successful, run the task. + + * If ``ops.dispatch()`` has dispatched any tasks, retry #3. + + * If the previous task is an SCX task and still runnable, keep executing + it (see ``SCX_OPS_ENQ_LAST``). + + * Go idle. + +Note that the BPF scheduler can always choose to dispatch tasks immediately +in ``ops.enqueue()`` as illustrated in the above simple example. If only the +built-in DSQs are used, there is no need to implement ``ops.dispatch()`` as +a task is never queued on the BPF scheduler and both the local and global +DSQs are consumed automatically. + +``scx_bpf_dispatch()`` queues the task on the FIFO of the target DSQ. Use +``scx_bpf_dispatch_vtime()`` for the priority queue. Internal DSQs such as +``SCX_DSQ_LOCAL`` and ``SCX_DSQ_GLOBAL`` do not support priority-queue +dispatching, and must be dispatched to with ``scx_bpf_dispatch()``. See the +function documentation and usage in ``tools/sched_ext/scx_simple.bpf.c`` for +more information. + +Where to Look +============= + +* ``include/linux/sched/ext.h`` defines the core data structures, ops table + and constants. + +* ``kernel/sched/ext.c`` contains sched_ext core implementation and helpers. + The functions prefixed with ``scx_bpf_`` can be called from the BPF + scheduler. + +* ``tools/sched_ext/`` hosts example BPF scheduler implementations. + + * ``scx_simple[.bpf].c``: Minimal global FIFO scheduler example using a + custom DSQ. + + * ``scx_qmap[.bpf].c``: A multi-level FIFO scheduler supporting five + levels of priority implemented with ``BPF_MAP_TYPE_QUEUE``. + +ABI Instability +=============== + +The APIs provided by sched_ext to BPF schedulers programs have no stability +guarantees. This includes the ops table callbacks and constants defined in +``include/linux/sched/ext.h``, as well as the ``scx_bpf_`` kfuncs defined in +``kernel/sched/ext.c``. + +While we will attempt to provide a relatively stable API surface when +possible, they are subject to change without warning between kernel +versions. diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index 9cee193dab19..fe9a67ffe6b1 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -1,5 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* + * BPF extensible scheduler class: Documentation/scheduler/sched-ext.rst + * * Copyright (c) 2022 Meta Platforms, Inc. and affiliates. * Copyright (c) 2022 Tejun Heo * Copyright (c) 2022 David Vernet diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt index 7dde5e424ac3..f035c87d02f1 100644 --- a/kernel/Kconfig.preempt +++ b/kernel/Kconfig.preempt @@ -156,4 +156,5 @@ config SCHED_CLASS_EXT similar to struct sched_class. For more information: + Documentation/scheduler/sched-ext.rst https://github.com/sched-ext/scx diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index f186c576e7d9..f814e84ceeb3 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -1,5 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* + * BPF extensible scheduler class: Documentation/scheduler/sched-ext.rst + * * Copyright (c) 2022 Meta Platforms, Inc. and affiliates. * Copyright (c) 2022 Tejun Heo * Copyright (c) 2022 David Vernet diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h index 6555878c5da3..c41d742b5d62 100644 --- a/kernel/sched/ext.h +++ b/kernel/sched/ext.h @@ -1,5 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* + * BPF extensible scheduler class: Documentation/scheduler/sched-ext.rst + * * Copyright (c) 2022 Meta Platforms, Inc. and affiliates. * Copyright (c) 2022 Tejun Heo * Copyright (c) 2022 David Vernet diff --git a/tools/sched_ext/README.md b/tools/sched_ext/README.md new file mode 100644 index 000000000000..8efe70cc4363 --- /dev/null +++ b/tools/sched_ext/README.md @@ -0,0 +1,258 @@ +SCHED_EXT EXAMPLE SCHEDULERS +============================ + +# Introduction + +This directory contains a number of example sched_ext schedulers. These +schedulers are meant to provide examples of different types of schedulers +that can be built using sched_ext, and illustrate how various features of +sched_ext can be used. + +Some of the examples are performant, production-ready schedulers. That is, for +the correct workload and with the correct tuning, they may be deployed in a +production environment with acceptable or possibly even improved performance. +Others are just examples that in practice, would not provide acceptable +performance (though they could be improved to get there). + +This README will describe these example schedulers, including describing the +types of workloads or scenarios they're designed to accommodate, and whether or +not they're production ready. For more details on any of these schedulers, +please see the header comment in their .bpf.c file. + + +# Compiling the examples + +There are a few toolchain dependencies for compiling the example schedulers. + +## Toolchain dependencies + +1. clang >= 16.0.0 + +The schedulers are BPF programs, and therefore must be compiled with clang. gcc +is actively working on adding a BPF backend compiler as well, but are still +missing some features such as BTF type tags which are necessary for using +kptrs. + +2. pahole >= 1.25 + +You may need pahole in order to generate BTF from DWARF. + +3. rust >= 1.70.0 + +Rust schedulers uses features present in the rust toolchain >= 1.70.0. You +should be able to use the stable build from rustup, but if that doesn't +work, try using the rustup nightly build. + +There are other requirements as well, such as make, but these are the main / +non-trivial ones. + +## Compiling the kernel + +In order to run a sched_ext scheduler, you'll have to run a kernel compiled +with the patches in this repository, and with a minimum set of necessary +Kconfig options: + +``` +CONFIG_BPF=y +CONFIG_SCHED_CLASS_EXT=y +CONFIG_BPF_SYSCALL=y +CONFIG_BPF_JIT=y +CONFIG_DEBUG_INFO_BTF=y +``` + +It's also recommended that you also include the following Kconfig options: + +``` +CONFIG_BPF_JIT_ALWAYS_ON=y +CONFIG_BPF_JIT_DEFAULT_ON=y +CONFIG_PAHOLE_HAS_SPLIT_BTF=y +CONFIG_PAHOLE_HAS_BTF_TAG=y +``` + +There is a `Kconfig` file in this directory whose contents you can append to +your local `.config` file, as long as there are no conflicts with any existing +options in the file. + +## Getting a vmlinux.h file + +You may notice that most of the example schedulers include a "vmlinux.h" file. +This is a large, auto-generated header file that contains all of the types +defined in some vmlinux binary that was compiled with +[BTF](https://docs.kernel.org/bpf/btf.html) (i.e. with the BTF-related Kconfig +options specified above). + +The header file is created using `bpftool`, by passing it a vmlinux binary +compiled with BTF as follows: + +```bash +$ bpftool btf dump file /path/to/vmlinux format c > vmlinux.h +``` + +`bpftool` analyzes all of the BTF encodings in the binary, and produces a +header file that can be included by BPF programs to access those types. For +example, using vmlinux.h allows a scheduler to access fields defined directly +in vmlinux as follows: + +```c +#include "vmlinux.h" +// vmlinux.h is also implicitly included by scx_common.bpf.h. +#include "scx_common.bpf.h" + +/* + * vmlinux.h provides definitions for struct task_struct and + * struct scx_enable_args. + */ +void BPF_STRUCT_OPS(example_enable, struct task_struct *p, + struct scx_enable_args *args) +{ + bpf_printk("Task %s enabled in example scheduler", p->comm); +} + +// vmlinux.h provides the definition for struct sched_ext_ops. +SEC(".struct_ops.link") +struct sched_ext_ops example_ops { + .enable = (void *)example_enable, + .name = "example", +} +``` + +The scheduler build system will generate this vmlinux.h file as part of the +scheduler build pipeline. It looks for a vmlinux file in the following +dependency order: + +1. If the O= environment variable is defined, at `$O/vmlinux` +2. If the KBUILD_OUTPUT= environment variable is defined, at + `$KBUILD_OUTPUT/vmlinux` +3. At `../../vmlinux` (i.e. at the root of the kernel tree where you're + compiling the schedulers) +3. `/sys/kernel/btf/vmlinux` +4. `/boot/vmlinux-$(uname -r)` + +In other words, if you have compiled a kernel in your local repo, its vmlinux +file will be used to generate vmlinux.h. Otherwise, it will be the vmlinux of +the kernel you're currently running on. This means that if you're running on a +kernel with sched_ext support, you may not need to compile a local kernel at +all. + +### Aside on CO-RE + +One of the cooler features of BPF is that it supports +[CO-RE](https://nakryiko.com/posts/bpf-core-reference-guide/) (Compile Once Run +Everywhere). This feature allows you to reference fields inside of structs with +types defined internal to the kernel, and not have to recompile if you load the +BPF program on a different kernel with the field at a different offset. In our +example above, we print out a task name with `p->comm`. CO-RE would perform +relocations for that access when the program is loaded to ensure that it's +referencing the correct offset for the currently running kernel. + +## Compiling the schedulers + +Once you have your toolchain setup, and a vmlinux that can be used to generate +a full vmlinux.h file, you can compile the schedulers using `make`: + +```bash +$ make -j($nproc) +``` + +# Example schedulers + +This directory contains the following example schedulers. These schedulers are +for testing and demonstrating different aspects of sched_ext. While some may be +useful in limited scenarios, they are not intended to be practical. + +For more scheduler implementations, tools and documentation, visit +https://github.com/sched-ext/scx. + +## scx_simple + +A simple scheduler that provides an example of a minimal sched_ext scheduler. +scx_simple can be run in either global weighted vtime mode, or FIFO mode. + +Though very simple, in limited scenarios, this scheduler can perform reasonably +well on single-socket systems with a unified L3 cache. + +## scx_qmap + +Another simple, yet slightly more complex scheduler that provides an example of +a basic weighted FIFO queuing policy. It also provides examples of some common +useful BPF features, such as sleepable per-task storage allocation in the +`ops.prep_enable()` callback, and using the `BPF_MAP_TYPE_QUEUE` map type to +enqueue tasks. It also illustrates how core-sched support could be implemented. + +## scx_central + +A "central" scheduler where scheduling decisions are made from a single CPU. +This scheduler illustrates how scheduling decisions can be dispatched from a +single CPU, allowing other cores to run with infinite slices, without timer +ticks, and without having to incur the overhead of making scheduling decisions. + +The approach demonstrated by this scheduler may be useful for any workload that +benefits from minimizing scheduling overhead and timer ticks. An example of +where this could be particularly useful is running VMs, where running with +infinite slices and no timer ticks allows the VM to avoid unnecessary expensive +vmexits. + + +# Troubleshooting + +There are a number of common issues that you may run into when building the +schedulers. We'll go over some of the common ones here. + +## Build Failures + +### Old version of clang + +``` +error: static assertion failed due to requirement 'SCX_DSQ_FLAG_BUILTIN': bpftool generated vmlinux.h is missing high bits for 64bit enums, upgrade clang and pahole + _Static_assert(SCX_DSQ_FLAG_BUILTIN, + ^~~~~~~~~~~~~~~~~~~~ +1 error generated. +``` + +This means you built the kernel or the schedulers with an older version of +clang than what's supported (i.e. older than 16.0.0). To remediate this: + +1. `which clang` to make sure you're using a sufficiently new version of clang. + +2. `make fullclean` in the root path of the repository, and rebuild the kernel + and schedulers. + +3. Rebuild the kernel, and then your example schedulers. + +The schedulers are also cleaned if you invoke `make mrproper` in the root +directory of the tree. + +### Stale kernel build / incomplete vmlinux.h file + +As described above, you'll need a `vmlinux.h` file that was generated from a +vmlinux built with BTF, and with sched_ext support enabled. If you don't, +you'll see errors such as the following which indicate that a type being +referenced in a scheduler is unknown: + +``` +/path/to/sched_ext/tools/sched_ext/user_exit_info.h:25:23: note: forward declaration of 'struct scx_exit_info' + +const struct scx_exit_info *ei) + +^ +``` + +In order to resolve this, please follow the steps above in +[Getting a vmlinux.h file](#getting-a-vmlinuxh-file) in order to ensure your +schedulers are using a vmlinux.h file that includes the requisite types. + +## Misc + +### llvm: [OFF] + +You may see the following output when building the schedulers: + +``` +Auto-detecting system features: +... clang-bpf-co-re: [ on ] +... llvm: [ OFF ] +... libcap: [ on ] +... libbfd: [ on ] +``` + +Seeing `llvm: [ OFF ]` here is not an issue. You can safely ignore. -- cgit v1.2.3 From d4af01c3731ff9c6e224d7183f8226a56d72b56c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 8 Jul 2024 14:30:55 -1000 Subject: sched_ext: Take out ->priq and ->flags from scx_dsq_node struct scx_dsq_node contains two data structure nodes to link the containing task to a DSQ and a flags field that is protected by the lock of the associated DSQ. One reason why they are grouped into a struct is to use the type independently as a cursor node when iterating tasks on a DSQ. However, when iterating, the cursor only needs to be linked on the FIFO list and the rb_node part ends up inflating the size of the iterator data structure unnecessarily making it potentially too expensive to place it on stack. Take ->priq and ->flags out of scx_dsq_node and put them in sched_ext_entity as ->dsq_priq and ->dsq_flags, respectively. scx_dsq_node is renamed to scx_dsq_list_node and the field names are renamed accordingly. This will help implementing DSQ task iterator that can be allocated on stack. No functional change intended. Signed-off-by: Tejun Heo Suggested-by: Alexei Starovoitov Acked-by: Alexei Starovoitov Cc: David Vernet --- include/linux/sched/ext.h | 10 ++++----- init/init_task.c | 2 +- kernel/sched/ext.c | 54 +++++++++++++++++++++++------------------------ 3 files changed, 33 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index fe9a67ffe6b1..eb9cfd18a923 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -121,10 +121,8 @@ enum scx_kf_mask { __SCX_KF_TERMINAL = SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU | SCX_KF_REST, }; -struct scx_dsq_node { - struct list_head list; /* dispatch order */ - struct rb_node priq; /* p->scx.dsq_vtime order */ - u32 flags; /* SCX_TASK_DSQ_* flags */ +struct scx_dsq_list_node { + struct list_head node; }; /* @@ -133,7 +131,9 @@ struct scx_dsq_node { */ struct sched_ext_entity { struct scx_dispatch_q *dsq; - struct scx_dsq_node dsq_node; /* protected by dsq lock */ + struct scx_dsq_list_node dsq_list; /* dispatch order */ + struct rb_node dsq_priq; /* p->scx.dsq_vtime order */ + u32 dsq_flags; /* protected by DSQ lock */ u32 flags; /* protected by rq lock */ u32 weight; s32 sticky_cpu; diff --git a/init/init_task.c b/init/init_task.c index 5726b3a0eea9..e222722e790b 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -102,7 +102,7 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = { #endif #ifdef CONFIG_SCHED_CLASS_EXT .scx = { - .dsq_node.list = LIST_HEAD_INIT(init_task.scx.dsq_node.list), + .dsq_list.node = LIST_HEAD_INIT(init_task.scx.dsq_list.node), .sticky_cpu = -1, .holding_cpu = -1, .runnable_node = LIST_HEAD_INIT(init_task.scx.runnable_node), diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index b7fad9bf27ae..069c2f33883c 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -1360,9 +1360,9 @@ static bool scx_dsq_priq_less(struct rb_node *node_a, const struct rb_node *node_b) { const struct task_struct *a = - container_of(node_a, struct task_struct, scx.dsq_node.priq); + container_of(node_a, struct task_struct, scx.dsq_priq); const struct task_struct *b = - container_of(node_b, struct task_struct, scx.dsq_node.priq); + container_of(node_b, struct task_struct, scx.dsq_priq); return time_before64(a->scx.dsq_vtime, b->scx.dsq_vtime); } @@ -1378,9 +1378,9 @@ static void dispatch_enqueue(struct scx_dispatch_q *dsq, struct task_struct *p, { bool is_local = dsq->id == SCX_DSQ_LOCAL; - WARN_ON_ONCE(p->scx.dsq || !list_empty(&p->scx.dsq_node.list)); - WARN_ON_ONCE((p->scx.dsq_node.flags & SCX_TASK_DSQ_ON_PRIQ) || - !RB_EMPTY_NODE(&p->scx.dsq_node.priq)); + WARN_ON_ONCE(p->scx.dsq || !list_empty(&p->scx.dsq_list.node)); + WARN_ON_ONCE((p->scx.dsq_flags & SCX_TASK_DSQ_ON_PRIQ) || + !RB_EMPTY_NODE(&p->scx.dsq_priq)); if (!is_local) { raw_spin_lock(&dsq->lock); @@ -1419,21 +1419,21 @@ static void dispatch_enqueue(struct scx_dispatch_q *dsq, struct task_struct *p, scx_ops_error("DSQ ID 0x%016llx already had FIFO-enqueued tasks", dsq->id); - p->scx.dsq_node.flags |= SCX_TASK_DSQ_ON_PRIQ; - rb_add(&p->scx.dsq_node.priq, &dsq->priq, scx_dsq_priq_less); + p->scx.dsq_flags |= SCX_TASK_DSQ_ON_PRIQ; + rb_add(&p->scx.dsq_priq, &dsq->priq, scx_dsq_priq_less); /* * Find the previous task and insert after it on the list so * that @dsq->list is vtime ordered. */ - rbp = rb_prev(&p->scx.dsq_node.priq); + rbp = rb_prev(&p->scx.dsq_priq); if (rbp) { struct task_struct *prev = container_of(rbp, struct task_struct, - scx.dsq_node.priq); - list_add(&p->scx.dsq_node.list, &prev->scx.dsq_node.list); + scx.dsq_priq); + list_add(&p->scx.dsq_list.node, &prev->scx.dsq_list.node); } else { - list_add(&p->scx.dsq_node.list, &dsq->list); + list_add(&p->scx.dsq_list.node, &dsq->list); } } else { /* a FIFO DSQ shouldn't be using PRIQ enqueuing */ @@ -1442,9 +1442,9 @@ static void dispatch_enqueue(struct scx_dispatch_q *dsq, struct task_struct *p, dsq->id); if (enq_flags & (SCX_ENQ_HEAD | SCX_ENQ_PREEMPT)) - list_add(&p->scx.dsq_node.list, &dsq->list); + list_add(&p->scx.dsq_list.node, &dsq->list); else - list_add_tail(&p->scx.dsq_node.list, &dsq->list); + list_add_tail(&p->scx.dsq_list.node, &dsq->list); } dsq_mod_nr(dsq, 1); @@ -1487,18 +1487,18 @@ static void dispatch_enqueue(struct scx_dispatch_q *dsq, struct task_struct *p, static void task_unlink_from_dsq(struct task_struct *p, struct scx_dispatch_q *dsq) { - if (p->scx.dsq_node.flags & SCX_TASK_DSQ_ON_PRIQ) { - rb_erase(&p->scx.dsq_node.priq, &dsq->priq); - RB_CLEAR_NODE(&p->scx.dsq_node.priq); - p->scx.dsq_node.flags &= ~SCX_TASK_DSQ_ON_PRIQ; + if (p->scx.dsq_flags & SCX_TASK_DSQ_ON_PRIQ) { + rb_erase(&p->scx.dsq_priq, &dsq->priq); + RB_CLEAR_NODE(&p->scx.dsq_priq); + p->scx.dsq_flags &= ~SCX_TASK_DSQ_ON_PRIQ; } - list_del_init(&p->scx.dsq_node.list); + list_del_init(&p->scx.dsq_list.node); } static bool task_linked_on_dsq(struct task_struct *p) { - return !list_empty(&p->scx.dsq_node.list); + return !list_empty(&p->scx.dsq_list.node); } static void dispatch_dequeue(struct rq *rq, struct task_struct *p) @@ -1523,8 +1523,8 @@ static void dispatch_dequeue(struct rq *rq, struct task_struct *p) raw_spin_lock(&dsq->lock); /* - * Now that we hold @dsq->lock, @p->holding_cpu and @p->scx.dsq_node - * can't change underneath us. + * Now that we hold @dsq->lock, @p->holding_cpu and @p->scx.dsq_* can't + * change underneath us. */ if (p->scx.holding_cpu < 0) { /* @p must still be on @dsq, dequeue */ @@ -2034,7 +2034,7 @@ static void consume_local_task(struct rq *rq, struct scx_dispatch_q *dsq, /* @dsq is locked and @p is on this rq */ WARN_ON_ONCE(p->scx.holding_cpu >= 0); task_unlink_from_dsq(p, dsq); - list_add_tail(&p->scx.dsq_node.list, &rq->scx.local_dsq.list); + list_add_tail(&p->scx.dsq_list.node, &rq->scx.local_dsq.list); dsq_mod_nr(dsq, -1); dsq_mod_nr(&rq->scx.local_dsq, 1); p->scx.dsq = &rq->scx.local_dsq; @@ -2109,7 +2109,7 @@ retry: raw_spin_lock(&dsq->lock); - list_for_each_entry(p, &dsq->list, scx.dsq_node.list) { + list_for_each_entry(p, &dsq->list, scx.dsq_list.node) { struct rq *task_rq = task_rq(p); if (rq == task_rq) { @@ -2628,7 +2628,7 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p) static struct task_struct *first_local_task(struct rq *rq) { return list_first_entry_or_null(&rq->scx.local_dsq.list, - struct task_struct, scx.dsq_node.list); + struct task_struct, scx.dsq_list.node); } static struct task_struct *pick_next_task_scx(struct rq *rq) @@ -3309,8 +3309,8 @@ void init_scx_entity(struct sched_ext_entity *scx) */ memset(scx, 0, offsetof(struct sched_ext_entity, tasks_node)); - INIT_LIST_HEAD(&scx->dsq_node.list); - RB_CLEAR_NODE(&scx->dsq_node.priq); + INIT_LIST_HEAD(&scx->dsq_list.node); + RB_CLEAR_NODE(&scx->dsq_priq); scx->sticky_cpu = -1; scx->holding_cpu = -1; INIT_LIST_HEAD(&scx->runnable_node); @@ -4160,7 +4160,7 @@ static void scx_dump_task(struct seq_buf *s, struct scx_dump_ctx *dctx, jiffies_delta_msecs(p->scx.runnable_at, dctx->at_jiffies)); dump_line(s, " scx_state/flags=%u/0x%x dsq_flags=0x%x ops_state/qseq=%lu/%lu", scx_get_task_state(p), p->scx.flags & ~SCX_TASK_STATE_MASK, - p->scx.dsq_node.flags, ops_state & SCX_OPSS_STATE_MASK, + p->scx.dsq_flags, ops_state & SCX_OPSS_STATE_MASK, ops_state >> SCX_OPSS_QSEQ_SHIFT); dump_line(s, " sticky/holding_cpu=%d/%d dsq_id=%s dsq_vtime=%llu", p->scx.sticky_cpu, p->scx.holding_cpu, dsq_id_buf, -- cgit v1.2.3 From 650ba21b131ed1f8ee57826b2c6295a3be221132 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 8 Jul 2024 14:30:55 -1000 Subject: sched_ext: Implement DSQ iterator DSQs are very opaque in the consumption path. The BPF scheduler has no way of knowing which tasks are being considered and which is picked. This patch adds BPF DSQ iterator. - Allows iterating tasks queued on a DSQ in the dispatch order or reverse from anywhere using bpf_for_each(scx_dsq) or calling the iterator kfuncs directly. - Has ordering guarantee where only tasks which were already queued when the iteration started are visible and consumable during the iteration. v5: - Add a comment to the naked list_empty(&dsq->list) test in consume_dispatch_q() to explain the reasoning behind the lockless test and by extension why nldsq_next_task() isn't used there. - scx_qmap changes separated into its own patch. v4: - bpf_iter_scx_dsq_new() declaration in common.bpf.h was using the wrong type for the last argument (bool rev instead of u64 flags). Fix it. v3: - Alexei pointed out that the iterator is too big to allocate on stack. Added a prep patch to reduce the size of the cursor. Now bpf_iter_scx_dsq is 48 bytes and bpf_iter_scx_dsq_kern is 40 bytes on 64bit. - u32_before() comparison factored out. v2: - scx_bpf_consume_task() is separated out into a separate patch. - DSQ seq and iter flags don't need to be u64. Use u32. Signed-off-by: Tejun Heo Reviewed-by: David Vernet Acked-by: Alexei Starovoitov Cc: bpf@vger.kernel.org --- include/linux/sched/ext.h | 3 + kernel/sched/ext.c | 192 ++++++++++++++++++++++++++++++- tools/sched_ext/include/scx/common.bpf.h | 3 + 3 files changed, 196 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index eb9cfd18a923..593d2f4909dd 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -61,6 +61,7 @@ struct scx_dispatch_q { struct list_head list; /* tasks in dispatch order */ struct rb_root priq; /* used to order by p->scx.dsq_vtime */ u32 nr; + u32 seq; /* used by BPF iter */ u64 id; struct rhash_head hash_node; struct llist_node free_node; @@ -123,6 +124,7 @@ enum scx_kf_mask { struct scx_dsq_list_node { struct list_head node; + bool is_bpf_iter_cursor; }; /* @@ -133,6 +135,7 @@ struct sched_ext_entity { struct scx_dispatch_q *dsq; struct scx_dsq_list_node dsq_list; /* dispatch order */ struct rb_node dsq_priq; /* p->scx.dsq_vtime order */ + u32 dsq_seq; u32 dsq_flags; /* protected by DSQ lock */ u32 flags; /* protected by rq lock */ u32 weight; diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 069c2f33883c..f16d72d72635 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -926,6 +926,11 @@ static u32 highest_bit(u32 flags) return ((u64)1 << bit) >> 1; } +static bool u32_before(u32 a, u32 b) +{ + return (s32)(a - b) < 0; +} + /* * scx_kf_mask enforcement. Some kfuncs can only be called from specific SCX * ops. When invoking SCX ops, SCX_CALL_OP[_RET]() should be used to indicate @@ -1066,6 +1071,73 @@ static __always_inline bool scx_kf_allowed_on_arg_tasks(u32 mask, return true; } +/** + * nldsq_next_task - Iterate to the next task in a non-local DSQ + * @dsq: user dsq being interated + * @cur: current position, %NULL to start iteration + * @rev: walk backwards + * + * Returns %NULL when iteration is finished. + */ +static struct task_struct *nldsq_next_task(struct scx_dispatch_q *dsq, + struct task_struct *cur, bool rev) +{ + struct list_head *list_node; + struct scx_dsq_list_node *dsq_lnode; + + lockdep_assert_held(&dsq->lock); + + if (cur) + list_node = &cur->scx.dsq_list.node; + else + list_node = &dsq->list; + + /* find the next task, need to skip BPF iteration cursors */ + do { + if (rev) + list_node = list_node->prev; + else + list_node = list_node->next; + + if (list_node == &dsq->list) + return NULL; + + dsq_lnode = container_of(list_node, struct scx_dsq_list_node, + node); + } while (dsq_lnode->is_bpf_iter_cursor); + + return container_of(dsq_lnode, struct task_struct, scx.dsq_list); +} + +#define nldsq_for_each_task(p, dsq) \ + for ((p) = nldsq_next_task((dsq), NULL, false); (p); \ + (p) = nldsq_next_task((dsq), (p), false)) + + +/* + * BPF DSQ iterator. Tasks in a non-local DSQ can be iterated in [reverse] + * dispatch order. BPF-visible iterator is opaque and larger to allow future + * changes without breaking backward compatibility. Can be used with + * bpf_for_each(). See bpf_iter_scx_dsq_*(). + */ +enum scx_dsq_iter_flags { + /* iterate in the reverse dispatch order */ + SCX_DSQ_ITER_REV = 1U << 0, + + __SCX_DSQ_ITER_ALL_FLAGS = SCX_DSQ_ITER_REV, +}; + +struct bpf_iter_scx_dsq_kern { + struct scx_dsq_list_node cursor; + struct scx_dispatch_q *dsq; + u32 dsq_seq; + u32 flags; +} __attribute__((aligned(8))); + +struct bpf_iter_scx_dsq { + u64 __opaque[6]; +} __attribute__((aligned(8))); + /* * SCX task iterator. @@ -1415,7 +1487,7 @@ static void dispatch_enqueue(struct scx_dispatch_q *dsq, struct task_struct *p, * tested easily when adding the first task. */ if (unlikely(RB_EMPTY_ROOT(&dsq->priq) && - !list_empty(&dsq->list))) + nldsq_next_task(dsq, NULL, false))) scx_ops_error("DSQ ID 0x%016llx already had FIFO-enqueued tasks", dsq->id); @@ -1447,6 +1519,10 @@ static void dispatch_enqueue(struct scx_dispatch_q *dsq, struct task_struct *p, list_add_tail(&p->scx.dsq_list.node, &dsq->list); } + /* seq records the order tasks are queued, used by BPF DSQ iterator */ + dsq->seq++; + p->scx.dsq_seq = dsq->seq; + dsq_mod_nr(dsq, 1); p->scx.dsq = dsq; @@ -2104,12 +2180,17 @@ static bool consume_dispatch_q(struct rq *rq, struct rq_flags *rf, { struct task_struct *p; retry: + /* + * The caller can't expect to successfully consume a task if the task's + * addition to @dsq isn't guaranteed to be visible somehow. Test + * @dsq->list without locking and skip if it seems empty. + */ if (list_empty(&dsq->list)) return false; raw_spin_lock(&dsq->lock); - list_for_each_entry(p, &dsq->list, scx.dsq_list.node) { + nldsq_for_each_task(p, dsq) { struct rq *task_rq = task_rq(p); if (rq == task_rq) { @@ -5705,6 +5786,110 @@ __bpf_kfunc void scx_bpf_destroy_dsq(u64 dsq_id) destroy_dsq(dsq_id); } +/** + * bpf_iter_scx_dsq_new - Create a DSQ iterator + * @it: iterator to initialize + * @dsq_id: DSQ to iterate + * @flags: %SCX_DSQ_ITER_* + * + * Initialize BPF iterator @it which can be used with bpf_for_each() to walk + * tasks in the DSQ specified by @dsq_id. Iteration using @it only includes + * tasks which are already queued when this function is invoked. + */ +__bpf_kfunc int bpf_iter_scx_dsq_new(struct bpf_iter_scx_dsq *it, u64 dsq_id, + u64 flags) +{ + struct bpf_iter_scx_dsq_kern *kit = (void *)it; + + BUILD_BUG_ON(sizeof(struct bpf_iter_scx_dsq_kern) > + sizeof(struct bpf_iter_scx_dsq)); + BUILD_BUG_ON(__alignof__(struct bpf_iter_scx_dsq_kern) != + __alignof__(struct bpf_iter_scx_dsq)); + + if (flags & ~__SCX_DSQ_ITER_ALL_FLAGS) + return -EINVAL; + + kit->dsq = find_non_local_dsq(dsq_id); + if (!kit->dsq) + return -ENOENT; + + INIT_LIST_HEAD(&kit->cursor.node); + kit->cursor.is_bpf_iter_cursor = true; + kit->dsq_seq = READ_ONCE(kit->dsq->seq); + kit->flags = flags; + + return 0; +} + +/** + * bpf_iter_scx_dsq_next - Progress a DSQ iterator + * @it: iterator to progress + * + * Return the next task. See bpf_iter_scx_dsq_new(). + */ +__bpf_kfunc struct task_struct *bpf_iter_scx_dsq_next(struct bpf_iter_scx_dsq *it) +{ + struct bpf_iter_scx_dsq_kern *kit = (void *)it; + bool rev = kit->flags & SCX_DSQ_ITER_REV; + struct task_struct *p; + unsigned long flags; + + if (!kit->dsq) + return NULL; + + raw_spin_lock_irqsave(&kit->dsq->lock, flags); + + if (list_empty(&kit->cursor.node)) + p = NULL; + else + p = container_of(&kit->cursor, struct task_struct, scx.dsq_list); + + /* + * Only tasks which were queued before the iteration started are + * visible. This bounds BPF iterations and guarantees that vtime never + * jumps in the other direction while iterating. + */ + do { + p = nldsq_next_task(kit->dsq, p, rev); + } while (p && unlikely(u32_before(kit->dsq_seq, p->scx.dsq_seq))); + + if (p) { + if (rev) + list_move_tail(&kit->cursor.node, &p->scx.dsq_list.node); + else + list_move(&kit->cursor.node, &p->scx.dsq_list.node); + } else { + list_del_init(&kit->cursor.node); + } + + raw_spin_unlock_irqrestore(&kit->dsq->lock, flags); + + return p; +} + +/** + * bpf_iter_scx_dsq_destroy - Destroy a DSQ iterator + * @it: iterator to destroy + * + * Undo scx_iter_scx_dsq_new(). + */ +__bpf_kfunc void bpf_iter_scx_dsq_destroy(struct bpf_iter_scx_dsq *it) +{ + struct bpf_iter_scx_dsq_kern *kit = (void *)it; + + if (!kit->dsq) + return; + + if (!list_empty(&kit->cursor.node)) { + unsigned long flags; + + raw_spin_lock_irqsave(&kit->dsq->lock, flags); + list_del_init(&kit->cursor.node); + raw_spin_unlock_irqrestore(&kit->dsq->lock, flags); + } + kit->dsq = NULL; +} + __bpf_kfunc_end_defs(); static s32 __bstr_format(u64 *data_buf, char *line_buf, size_t line_size, @@ -6138,6 +6323,9 @@ BTF_KFUNCS_START(scx_kfunc_ids_any) BTF_ID_FLAGS(func, scx_bpf_kick_cpu) BTF_ID_FLAGS(func, scx_bpf_dsq_nr_queued) BTF_ID_FLAGS(func, scx_bpf_destroy_dsq) +BTF_ID_FLAGS(func, bpf_iter_scx_dsq_new, KF_ITER_NEW | KF_RCU_PROTECTED) +BTF_ID_FLAGS(func, bpf_iter_scx_dsq_next, KF_ITER_NEXT | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_iter_scx_dsq_destroy, KF_ITER_DESTROY) BTF_ID_FLAGS(func, scx_bpf_exit_bstr, KF_TRUSTED_ARGS) BTF_ID_FLAGS(func, scx_bpf_error_bstr, KF_TRUSTED_ARGS) BTF_ID_FLAGS(func, scx_bpf_dump_bstr, KF_TRUSTED_ARGS) diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h index 965d20324114..20280df62857 100644 --- a/tools/sched_ext/include/scx/common.bpf.h +++ b/tools/sched_ext/include/scx/common.bpf.h @@ -39,6 +39,9 @@ u32 scx_bpf_reenqueue_local(void) __ksym; void scx_bpf_kick_cpu(s32 cpu, u64 flags) __ksym; s32 scx_bpf_dsq_nr_queued(u64 dsq_id) __ksym; void scx_bpf_destroy_dsq(u64 dsq_id) __ksym; +int bpf_iter_scx_dsq_new(struct bpf_iter_scx_dsq *it, u64 dsq_id, u64 flags) __ksym __weak; +struct task_struct *bpf_iter_scx_dsq_next(struct bpf_iter_scx_dsq *it) __ksym __weak; +void bpf_iter_scx_dsq_destroy(struct bpf_iter_scx_dsq *it) __ksym __weak; void scx_bpf_exit_bstr(s64 exit_code, char *fmt, unsigned long long *data, u32 data__sz) __ksym __weak; void scx_bpf_error_bstr(char *fmt, unsigned long long *data, u32 data_len) __ksym; void scx_bpf_dump_bstr(char *fmt, unsigned long long *data, u32 data_len) __ksym __weak; -- cgit v1.2.3 From e8858fc07eb8386b9b6436d3e86eeb4b81e4f660 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Sat, 13 Jul 2024 23:00:27 -0700 Subject: Input: msc5000_ts - remove the driver MCS-5000 belongs to the 1st generation of Melfas chips, manufactured in 2000-2007. The driver relies on custom platform data (no DT support) and there never were any users of this driver in the mainline kernel. The commit adding the driver mentioned that the driver was tested on S3C6410 NCP board (with Samsung S3C6410 SoC) but the touchscreen device was never added to the board file. This board was removed in v6.3 in commit 743c8fbb90ca ("ARM: s3c: remove most s3c64xx board support"). Remove the driver since there are no users. Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20240714060029.1528662-1-dmitry.torokhov@gmail.com Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/Kconfig | 12 -- drivers/input/touchscreen/Makefile | 1 - drivers/input/touchscreen/mcs5000_ts.c | 288 --------------------------------- include/linux/platform_data/mcs.h | 4 - 4 files changed, 305 deletions(-) delete mode 100644 drivers/input/touchscreen/mcs5000_ts.c (limited to 'include/linux') diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig index c821fe3ee794..0df90c3d743b 100644 --- a/drivers/input/touchscreen/Kconfig +++ b/drivers/input/touchscreen/Kconfig @@ -626,18 +626,6 @@ config TOUCHSCREEN_MAX11801 To compile this driver as a module, choose M here: the module will be called max11801_ts. -config TOUCHSCREEN_MCS5000 - tristate "MELFAS MCS-5000 touchscreen" - depends on I2C - help - Say Y here if you have the MELFAS MCS-5000 touchscreen controller - chip in your system. - - If unsure, say N. - - To compile this driver as a module, choose M here: the - module will be called mcs5000_ts. - config TOUCHSCREEN_MMS114 tristate "MELFAS MMS114 touchscreen" depends on I2C diff --git a/drivers/input/touchscreen/Makefile b/drivers/input/touchscreen/Makefile index a81cb5aa21a5..04dc8039341b 100644 --- a/drivers/input/touchscreen/Makefile +++ b/drivers/input/touchscreen/Makefile @@ -63,7 +63,6 @@ obj-$(CONFIG_TOUCHSCREEN_MAX11801) += max11801_ts.o obj-$(CONFIG_TOUCHSCREEN_MXS_LRADC) += mxs-lradc-ts.o obj-$(CONFIG_TOUCHSCREEN_MX25) += fsl-imx25-tcq.o obj-$(CONFIG_TOUCHSCREEN_MC13783) += mc13783_ts.o -obj-$(CONFIG_TOUCHSCREEN_MCS5000) += mcs5000_ts.o obj-$(CONFIG_TOUCHSCREEN_MELFAS_MIP4) += melfas_mip4.o obj-$(CONFIG_TOUCHSCREEN_MIGOR) += migor_ts.o obj-$(CONFIG_TOUCHSCREEN_MMS114) += mms114.o diff --git a/drivers/input/touchscreen/mcs5000_ts.c b/drivers/input/touchscreen/mcs5000_ts.c deleted file mode 100644 index 5aff8dcda0dc..000000000000 --- a/drivers/input/touchscreen/mcs5000_ts.c +++ /dev/null @@ -1,288 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * mcs5000_ts.c - Touchscreen driver for MELFAS MCS-5000 controller - * - * Copyright (C) 2009 Samsung Electronics Co.Ltd - * Author: Joonyoung Shim - * - * Based on wm97xx-core.c - */ - -#include -#include -#include -#include -#include -#include -#include - -/* Registers */ -#define MCS5000_TS_STATUS 0x00 -#define STATUS_OFFSET 0 -#define STATUS_NO (0 << STATUS_OFFSET) -#define STATUS_INIT (1 << STATUS_OFFSET) -#define STATUS_SENSING (2 << STATUS_OFFSET) -#define STATUS_COORD (3 << STATUS_OFFSET) -#define STATUS_GESTURE (4 << STATUS_OFFSET) -#define ERROR_OFFSET 4 -#define ERROR_NO (0 << ERROR_OFFSET) -#define ERROR_POWER_ON_RESET (1 << ERROR_OFFSET) -#define ERROR_INT_RESET (2 << ERROR_OFFSET) -#define ERROR_EXT_RESET (3 << ERROR_OFFSET) -#define ERROR_INVALID_REG_ADDRESS (8 << ERROR_OFFSET) -#define ERROR_INVALID_REG_VALUE (9 << ERROR_OFFSET) - -#define MCS5000_TS_OP_MODE 0x01 -#define RESET_OFFSET 0 -#define RESET_NO (0 << RESET_OFFSET) -#define RESET_EXT_SOFT (1 << RESET_OFFSET) -#define OP_MODE_OFFSET 1 -#define OP_MODE_SLEEP (0 << OP_MODE_OFFSET) -#define OP_MODE_ACTIVE (1 << OP_MODE_OFFSET) -#define GESTURE_OFFSET 4 -#define GESTURE_DISABLE (0 << GESTURE_OFFSET) -#define GESTURE_ENABLE (1 << GESTURE_OFFSET) -#define PROXIMITY_OFFSET 5 -#define PROXIMITY_DISABLE (0 << PROXIMITY_OFFSET) -#define PROXIMITY_ENABLE (1 << PROXIMITY_OFFSET) -#define SCAN_MODE_OFFSET 6 -#define SCAN_MODE_INTERRUPT (0 << SCAN_MODE_OFFSET) -#define SCAN_MODE_POLLING (1 << SCAN_MODE_OFFSET) -#define REPORT_RATE_OFFSET 7 -#define REPORT_RATE_40 (0 << REPORT_RATE_OFFSET) -#define REPORT_RATE_80 (1 << REPORT_RATE_OFFSET) - -#define MCS5000_TS_SENS_CTL 0x02 -#define MCS5000_TS_FILTER_CTL 0x03 -#define PRI_FILTER_OFFSET 0 -#define SEC_FILTER_OFFSET 4 - -#define MCS5000_TS_X_SIZE_UPPER 0x08 -#define MCS5000_TS_X_SIZE_LOWER 0x09 -#define MCS5000_TS_Y_SIZE_UPPER 0x0A -#define MCS5000_TS_Y_SIZE_LOWER 0x0B - -#define MCS5000_TS_INPUT_INFO 0x10 -#define INPUT_TYPE_OFFSET 0 -#define INPUT_TYPE_NONTOUCH (0 << INPUT_TYPE_OFFSET) -#define INPUT_TYPE_SINGLE (1 << INPUT_TYPE_OFFSET) -#define INPUT_TYPE_DUAL (2 << INPUT_TYPE_OFFSET) -#define INPUT_TYPE_PALM (3 << INPUT_TYPE_OFFSET) -#define INPUT_TYPE_PROXIMITY (7 << INPUT_TYPE_OFFSET) -#define GESTURE_CODE_OFFSET 3 -#define GESTURE_CODE_NO (0 << GESTURE_CODE_OFFSET) - -#define MCS5000_TS_X_POS_UPPER 0x11 -#define MCS5000_TS_X_POS_LOWER 0x12 -#define MCS5000_TS_Y_POS_UPPER 0x13 -#define MCS5000_TS_Y_POS_LOWER 0x14 -#define MCS5000_TS_Z_POS 0x15 -#define MCS5000_TS_WIDTH 0x16 -#define MCS5000_TS_GESTURE_VAL 0x17 -#define MCS5000_TS_MODULE_REV 0x20 -#define MCS5000_TS_FIRMWARE_VER 0x21 - -/* Touchscreen absolute values */ -#define MCS5000_MAX_XC 0x3ff -#define MCS5000_MAX_YC 0x3ff - -enum mcs5000_ts_read_offset { - READ_INPUT_INFO, - READ_X_POS_UPPER, - READ_X_POS_LOWER, - READ_Y_POS_UPPER, - READ_Y_POS_LOWER, - READ_BLOCK_SIZE, -}; - -/* Each client has this additional data */ -struct mcs5000_ts_data { - struct i2c_client *client; - struct input_dev *input_dev; - const struct mcs_platform_data *platform_data; -}; - -static irqreturn_t mcs5000_ts_interrupt(int irq, void *dev_id) -{ - struct mcs5000_ts_data *data = dev_id; - struct i2c_client *client = data->client; - u8 buffer[READ_BLOCK_SIZE]; - int err; - int x; - int y; - - err = i2c_smbus_read_i2c_block_data(client, MCS5000_TS_INPUT_INFO, - READ_BLOCK_SIZE, buffer); - if (err < 0) { - dev_err(&client->dev, "%s, err[%d]\n", __func__, err); - goto out; - } - - switch (buffer[READ_INPUT_INFO]) { - case INPUT_TYPE_NONTOUCH: - input_report_key(data->input_dev, BTN_TOUCH, 0); - input_sync(data->input_dev); - break; - - case INPUT_TYPE_SINGLE: - x = (buffer[READ_X_POS_UPPER] << 8) | buffer[READ_X_POS_LOWER]; - y = (buffer[READ_Y_POS_UPPER] << 8) | buffer[READ_Y_POS_LOWER]; - - input_report_key(data->input_dev, BTN_TOUCH, 1); - input_report_abs(data->input_dev, ABS_X, x); - input_report_abs(data->input_dev, ABS_Y, y); - input_sync(data->input_dev); - break; - - case INPUT_TYPE_DUAL: - /* TODO */ - break; - - case INPUT_TYPE_PALM: - /* TODO */ - break; - - case INPUT_TYPE_PROXIMITY: - /* TODO */ - break; - - default: - dev_err(&client->dev, "Unknown ts input type %d\n", - buffer[READ_INPUT_INFO]); - break; - } - - out: - return IRQ_HANDLED; -} - -static void mcs5000_ts_phys_init(struct mcs5000_ts_data *data, - const struct mcs_platform_data *platform_data) -{ - struct i2c_client *client = data->client; - - /* Touch reset & sleep mode */ - i2c_smbus_write_byte_data(client, MCS5000_TS_OP_MODE, - RESET_EXT_SOFT | OP_MODE_SLEEP); - - /* Touch size */ - i2c_smbus_write_byte_data(client, MCS5000_TS_X_SIZE_UPPER, - platform_data->x_size >> 8); - i2c_smbus_write_byte_data(client, MCS5000_TS_X_SIZE_LOWER, - platform_data->x_size & 0xff); - i2c_smbus_write_byte_data(client, MCS5000_TS_Y_SIZE_UPPER, - platform_data->y_size >> 8); - i2c_smbus_write_byte_data(client, MCS5000_TS_Y_SIZE_LOWER, - platform_data->y_size & 0xff); - - /* Touch active mode & 80 report rate */ - i2c_smbus_write_byte_data(data->client, MCS5000_TS_OP_MODE, - OP_MODE_ACTIVE | REPORT_RATE_80); -} - -static int mcs5000_ts_probe(struct i2c_client *client) -{ - const struct mcs_platform_data *pdata; - struct mcs5000_ts_data *data; - struct input_dev *input_dev; - int error; - - pdata = dev_get_platdata(&client->dev); - if (!pdata) - return -EINVAL; - - data = devm_kzalloc(&client->dev, sizeof(*data), GFP_KERNEL); - if (!data) { - dev_err(&client->dev, "Failed to allocate memory\n"); - return -ENOMEM; - } - - data->client = client; - - input_dev = devm_input_allocate_device(&client->dev); - if (!input_dev) { - dev_err(&client->dev, "Failed to allocate input device\n"); - return -ENOMEM; - } - - input_dev->name = "MELFAS MCS-5000 Touchscreen"; - input_dev->id.bustype = BUS_I2C; - input_dev->dev.parent = &client->dev; - - __set_bit(EV_ABS, input_dev->evbit); - __set_bit(EV_KEY, input_dev->evbit); - __set_bit(BTN_TOUCH, input_dev->keybit); - input_set_abs_params(input_dev, ABS_X, 0, MCS5000_MAX_XC, 0, 0); - input_set_abs_params(input_dev, ABS_Y, 0, MCS5000_MAX_YC, 0, 0); - - data->input_dev = input_dev; - - if (pdata->cfg_pin) - pdata->cfg_pin(); - - error = devm_request_threaded_irq(&client->dev, client->irq, - NULL, mcs5000_ts_interrupt, - IRQF_TRIGGER_LOW | IRQF_ONESHOT, - "mcs5000_ts", data); - if (error) { - dev_err(&client->dev, "Failed to register interrupt\n"); - return error; - } - - error = input_register_device(data->input_dev); - if (error) { - dev_err(&client->dev, "Failed to register input device\n"); - return error; - } - - mcs5000_ts_phys_init(data, pdata); - i2c_set_clientdata(client, data); - - return 0; -} - -static int mcs5000_ts_suspend(struct device *dev) -{ - struct i2c_client *client = to_i2c_client(dev); - - /* Touch sleep mode */ - i2c_smbus_write_byte_data(client, MCS5000_TS_OP_MODE, OP_MODE_SLEEP); - - return 0; -} - -static int mcs5000_ts_resume(struct device *dev) -{ - struct i2c_client *client = to_i2c_client(dev); - struct mcs5000_ts_data *data = i2c_get_clientdata(client); - const struct mcs_platform_data *pdata = dev_get_platdata(dev); - - mcs5000_ts_phys_init(data, pdata); - - return 0; -} - -static DEFINE_SIMPLE_DEV_PM_OPS(mcs5000_ts_pm, - mcs5000_ts_suspend, mcs5000_ts_resume); - -static const struct i2c_device_id mcs5000_ts_id[] = { - { "mcs5000_ts" }, - { } -}; -MODULE_DEVICE_TABLE(i2c, mcs5000_ts_id); - -static struct i2c_driver mcs5000_ts_driver = { - .probe = mcs5000_ts_probe, - .driver = { - .name = "mcs5000_ts", - .pm = pm_sleep_ptr(&mcs5000_ts_pm), - }, - .id_table = mcs5000_ts_id, -}; - -module_i2c_driver(mcs5000_ts_driver); - -/* Module information */ -MODULE_AUTHOR("Joonyoung Shim "); -MODULE_DESCRIPTION("Touchscreen driver for MELFAS MCS-5000 controller"); -MODULE_LICENSE("GPL"); diff --git a/include/linux/platform_data/mcs.h b/include/linux/platform_data/mcs.h index fcc6f2a1f5c3..f3b0749f1630 100644 --- a/include/linux/platform_data/mcs.h +++ b/include/linux/platform_data/mcs.h @@ -16,10 +16,6 @@ struct mcs_platform_data { void (*poweron)(bool); void (*cfg_pin)(void); - /* touchscreen */ - unsigned int x_size; - unsigned int y_size; - /* touchkey */ const u32 *keymap; unsigned int keymap_size; -- cgit v1.2.3 From dd29eadee1e8f07bbec57dddf4befbcd3e3c0af7 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Sat, 13 Jul 2024 23:00:28 -0700 Subject: Input: msc_touchkey - remove the driver MCS-5000/5080 chips belong to the 1st generation of Melfas chips, manufactured in 2000-2007. The driver relies on custom platform data (no DT support) and there never were any users of this driver in the mainline kernel. It is likely that the driver was (like mcs5000_ts driver) was tested on S3C6410 NCP board (with Samsung S3C6410 SoC), but the touchkey device was never added to the board file. This board was removed in v6.3 in commit 743c8fbb90ca ("ARM: s3c: remove most s3c64xx board support"). Remove the driver since there are no users. Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20240714060029.1528662-2-dmitry.torokhov@gmail.com Signed-off-by: Dmitry Torokhov --- drivers/input/keyboard/Kconfig | 12 -- drivers/input/keyboard/Makefile | 1 - drivers/input/keyboard/mcs_touchkey.c | 268 ---------------------------------- include/linux/platform_data/mcs.h | 26 ---- 4 files changed, 307 deletions(-) delete mode 100644 drivers/input/keyboard/mcs_touchkey.c delete mode 100644 include/linux/platform_data/mcs.h (limited to 'include/linux') diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig index 1d0c5f4c0f99..72f9552cb571 100644 --- a/drivers/input/keyboard/Kconfig +++ b/drivers/input/keyboard/Kconfig @@ -421,18 +421,6 @@ config KEYBOARD_MAX7359 To compile this driver as a module, choose M here: the module will be called max7359_keypad. -config KEYBOARD_MCS - tristate "MELFAS MCS Touchkey" - depends on I2C - help - Say Y here if you have the MELFAS MCS5000/5080 touchkey controller - chip in your system. - - If unsure, say N. - - To compile this driver as a module, choose M here: the - module will be called mcs_touchkey. - config KEYBOARD_MPR121 tristate "Freescale MPR121 Touchkey" depends on I2C diff --git a/drivers/input/keyboard/Makefile b/drivers/input/keyboard/Makefile index aecef00c5d09..b8d12a0524e0 100644 --- a/drivers/input/keyboard/Makefile +++ b/drivers/input/keyboard/Makefile @@ -41,7 +41,6 @@ obj-$(CONFIG_KEYBOARD_LPC32XX) += lpc32xx-keys.o obj-$(CONFIG_KEYBOARD_MAPLE) += maple_keyb.o obj-$(CONFIG_KEYBOARD_MATRIX) += matrix_keypad.o obj-$(CONFIG_KEYBOARD_MAX7359) += max7359_keypad.o -obj-$(CONFIG_KEYBOARD_MCS) += mcs_touchkey.o obj-$(CONFIG_KEYBOARD_MPR121) += mpr121_touchkey.o obj-$(CONFIG_KEYBOARD_MT6779) += mt6779-keypad.o obj-$(CONFIG_KEYBOARD_MTK_PMIC) += mtk-pmic-keys.o diff --git a/drivers/input/keyboard/mcs_touchkey.c b/drivers/input/keyboard/mcs_touchkey.c deleted file mode 100644 index 2410f676c7f9..000000000000 --- a/drivers/input/keyboard/mcs_touchkey.c +++ /dev/null @@ -1,268 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Touchkey driver for MELFAS MCS5000/5080 controller - * - * Copyright (C) 2010 Samsung Electronics Co.Ltd - * Author: HeungJun Kim - * Author: Joonyoung Shim - */ - -#include -#include -#include -#include -#include -#include -#include -#include - -/* MCS5000 Touchkey */ -#define MCS5000_TOUCHKEY_STATUS 0x04 -#define MCS5000_TOUCHKEY_STATUS_PRESS 7 -#define MCS5000_TOUCHKEY_FW 0x0a -#define MCS5000_TOUCHKEY_BASE_VAL 0x61 - -/* MCS5080 Touchkey */ -#define MCS5080_TOUCHKEY_STATUS 0x00 -#define MCS5080_TOUCHKEY_STATUS_PRESS 3 -#define MCS5080_TOUCHKEY_FW 0x01 -#define MCS5080_TOUCHKEY_BASE_VAL 0x1 - -enum mcs_touchkey_type { - MCS5000_TOUCHKEY, - MCS5080_TOUCHKEY, -}; - -struct mcs_touchkey_chip { - unsigned int status_reg; - unsigned int pressbit; - unsigned int press_invert; - unsigned int baseval; -}; - -struct mcs_touchkey_data { - void (*poweron)(bool); - - struct i2c_client *client; - struct input_dev *input_dev; - struct mcs_touchkey_chip chip; - unsigned int key_code; - unsigned int key_val; - unsigned short keycodes[]; -}; - -static irqreturn_t mcs_touchkey_interrupt(int irq, void *dev_id) -{ - struct mcs_touchkey_data *data = dev_id; - struct mcs_touchkey_chip *chip = &data->chip; - struct i2c_client *client = data->client; - struct input_dev *input = data->input_dev; - unsigned int key_val; - unsigned int pressed; - int val; - - val = i2c_smbus_read_byte_data(client, chip->status_reg); - if (val < 0) { - dev_err(&client->dev, "i2c read error [%d]\n", val); - goto out; - } - - pressed = (val & (1 << chip->pressbit)) >> chip->pressbit; - if (chip->press_invert) - pressed ^= chip->press_invert; - - /* key_val is 0 when released, so we should use key_val of press. */ - if (pressed) { - key_val = val & (0xff >> (8 - chip->pressbit)); - if (!key_val) - goto out; - key_val -= chip->baseval; - data->key_code = data->keycodes[key_val]; - data->key_val = key_val; - } - - input_event(input, EV_MSC, MSC_SCAN, data->key_val); - input_report_key(input, data->key_code, pressed); - input_sync(input); - - dev_dbg(&client->dev, "key %d %d %s\n", data->key_val, data->key_code, - pressed ? "pressed" : "released"); - - out: - return IRQ_HANDLED; -} - -static void mcs_touchkey_poweroff(void *data) -{ - struct mcs_touchkey_data *touchkey = data; - - touchkey->poweron(false); -} - -static int mcs_touchkey_probe(struct i2c_client *client) -{ - const struct i2c_device_id *id = i2c_client_get_device_id(client); - const struct mcs_platform_data *pdata; - struct mcs_touchkey_data *data; - struct input_dev *input_dev; - unsigned int fw_reg; - int fw_ver; - int error; - int i; - - pdata = dev_get_platdata(&client->dev); - if (!pdata) { - dev_err(&client->dev, "no platform data defined\n"); - return -EINVAL; - } - - data = devm_kzalloc(&client->dev, - struct_size(data, keycodes, pdata->key_maxval + 1), - GFP_KERNEL); - if (!data) - return -ENOMEM; - - input_dev = devm_input_allocate_device(&client->dev); - if (!input_dev) { - dev_err(&client->dev, "Failed to allocate input device\n"); - return -ENOMEM; - } - - data->client = client; - data->input_dev = input_dev; - - if (id->driver_data == MCS5000_TOUCHKEY) { - data->chip.status_reg = MCS5000_TOUCHKEY_STATUS; - data->chip.pressbit = MCS5000_TOUCHKEY_STATUS_PRESS; - data->chip.baseval = MCS5000_TOUCHKEY_BASE_VAL; - fw_reg = MCS5000_TOUCHKEY_FW; - } else { - data->chip.status_reg = MCS5080_TOUCHKEY_STATUS; - data->chip.pressbit = MCS5080_TOUCHKEY_STATUS_PRESS; - data->chip.press_invert = 1; - data->chip.baseval = MCS5080_TOUCHKEY_BASE_VAL; - fw_reg = MCS5080_TOUCHKEY_FW; - } - - fw_ver = i2c_smbus_read_byte_data(client, fw_reg); - if (fw_ver < 0) { - dev_err(&client->dev, "i2c read error[%d]\n", fw_ver); - return fw_ver; - } - dev_info(&client->dev, "Firmware version: %d\n", fw_ver); - - input_dev->name = "MELFAS MCS Touchkey"; - input_dev->id.bustype = BUS_I2C; - input_dev->evbit[0] = BIT_MASK(EV_KEY); - if (!pdata->no_autorepeat) - input_dev->evbit[0] |= BIT_MASK(EV_REP); - input_dev->keycode = data->keycodes; - input_dev->keycodesize = sizeof(data->keycodes[0]); - input_dev->keycodemax = pdata->key_maxval + 1; - - for (i = 0; i < pdata->keymap_size; i++) { - unsigned int val = MCS_KEY_VAL(pdata->keymap[i]); - unsigned int code = MCS_KEY_CODE(pdata->keymap[i]); - - data->keycodes[val] = code; - __set_bit(code, input_dev->keybit); - } - - input_set_capability(input_dev, EV_MSC, MSC_SCAN); - input_set_drvdata(input_dev, data); - - if (pdata->cfg_pin) - pdata->cfg_pin(); - - if (pdata->poweron) { - data->poweron = pdata->poweron; - data->poweron(true); - - error = devm_add_action_or_reset(&client->dev, - mcs_touchkey_poweroff, data); - if (error) - return error; - } - - error = devm_request_threaded_irq(&client->dev, client->irq, - NULL, mcs_touchkey_interrupt, - IRQF_TRIGGER_FALLING | IRQF_ONESHOT, - client->dev.driver->name, data); - if (error) { - dev_err(&client->dev, "Failed to register interrupt\n"); - return error; - } - - error = input_register_device(input_dev); - if (error) - return error; - - i2c_set_clientdata(client, data); - return 0; -} - -static void mcs_touchkey_shutdown(struct i2c_client *client) -{ - struct mcs_touchkey_data *data = i2c_get_clientdata(client); - - if (data->poweron) - data->poweron(false); -} - -static int mcs_touchkey_suspend(struct device *dev) -{ - struct mcs_touchkey_data *data = dev_get_drvdata(dev); - struct i2c_client *client = data->client; - - /* Disable the work */ - disable_irq(client->irq); - - /* Finally turn off the power */ - if (data->poweron) - data->poweron(false); - - return 0; -} - -static int mcs_touchkey_resume(struct device *dev) -{ - struct mcs_touchkey_data *data = dev_get_drvdata(dev); - struct i2c_client *client = data->client; - - /* Enable the device first */ - if (data->poweron) - data->poweron(true); - - /* Enable irq again */ - enable_irq(client->irq); - - return 0; -} - -static DEFINE_SIMPLE_DEV_PM_OPS(mcs_touchkey_pm_ops, - mcs_touchkey_suspend, mcs_touchkey_resume); - -static const struct i2c_device_id mcs_touchkey_id[] = { - { "mcs5000_touchkey", MCS5000_TOUCHKEY }, - { "mcs5080_touchkey", MCS5080_TOUCHKEY }, - { } -}; -MODULE_DEVICE_TABLE(i2c, mcs_touchkey_id); - -static struct i2c_driver mcs_touchkey_driver = { - .driver = { - .name = "mcs_touchkey", - .pm = pm_sleep_ptr(&mcs_touchkey_pm_ops), - }, - .probe = mcs_touchkey_probe, - .shutdown = mcs_touchkey_shutdown, - .id_table = mcs_touchkey_id, -}; - -module_i2c_driver(mcs_touchkey_driver); - -/* Module information */ -MODULE_AUTHOR("Joonyoung Shim "); -MODULE_AUTHOR("HeungJun Kim "); -MODULE_DESCRIPTION("Touchkey driver for MELFAS MCS5000/5080 controller"); -MODULE_LICENSE("GPL"); diff --git a/include/linux/platform_data/mcs.h b/include/linux/platform_data/mcs.h deleted file mode 100644 index f3b0749f1630..000000000000 --- a/include/linux/platform_data/mcs.h +++ /dev/null @@ -1,26 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Copyright (C) 2009 - 2010 Samsung Electronics Co.Ltd - * Author: Joonyoung Shim - * Author: HeungJun Kim - */ - -#ifndef __LINUX_MCS_H -#define __LINUX_MCS_H - -#define MCS_KEY_MAP(v, c) ((((v) & 0xff) << 16) | ((c) & 0xffff)) -#define MCS_KEY_VAL(v) (((v) >> 16) & 0xff) -#define MCS_KEY_CODE(v) ((v) & 0xffff) - -struct mcs_platform_data { - void (*poweron)(bool); - void (*cfg_pin)(void); - - /* touchkey */ - const u32 *keymap; - unsigned int keymap_size; - unsigned int key_maxval; - bool no_autorepeat; -}; - -#endif /* __LINUX_MCS_H */ -- cgit v1.2.3 From af22bbe1f4a514c80b89a27252beef033168f4e9 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 16 Jul 2024 13:35:48 +0200 Subject: virtio: create admin queues alongside other virtqueues Admin virtqueue is just another virtqueue nothing that special about it. The current implementation treats it somehow separate though in terms of creation and deletion. Unify the admin virtqueue creation and deletion flows to be aligned with the rest of virtqueues, creating it from vp_find_vqs_*() helpers. Let the admin virtqueue to be deleted by vp_del_vqs() as the rest. Call vp_find_one_vq_msix() with slow_path argument being "true" to make sure that in case of limited interrupt vectors the config vector is used for admin queue. Signed-off-by: Jiri Pirko Message-Id: <20240716113552.80599-10-jiri@resnulli.us> Signed-off-by: Michael S. Tsirkin --- drivers/virtio/virtio.c | 28 ++--------------- drivers/virtio/virtio_pci_common.c | 43 ++++++++++++++++++++++++-- drivers/virtio/virtio_pci_common.h | 4 +-- drivers/virtio/virtio_pci_modern.c | 63 ++------------------------------------ include/linux/virtio_config.h | 4 --- 5 files changed, 46 insertions(+), 96 deletions(-) (limited to 'include/linux') diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 396d3cd49a1b..835cfbcb59c8 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -305,15 +305,9 @@ static int virtio_dev_probe(struct device *_d) if (err) goto err; - if (dev->config->create_avq) { - err = dev->config->create_avq(dev); - if (err) - goto err; - } - err = drv->probe(dev); if (err) - goto err_probe; + goto err; /* If probe didn't do it, mark device DRIVER_OK ourselves. */ if (!(dev->config->get_status(dev) & VIRTIO_CONFIG_S_DRIVER_OK)) @@ -326,9 +320,6 @@ static int virtio_dev_probe(struct device *_d) return 0; -err_probe: - if (dev->config->destroy_avq) - dev->config->destroy_avq(dev); err: virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED); return err; @@ -344,9 +335,6 @@ static void virtio_dev_remove(struct device *_d) drv->remove(dev); - if (dev->config->destroy_avq) - dev->config->destroy_avq(dev); - /* Driver should have reset device. */ WARN_ON_ONCE(dev->config->get_status(dev)); @@ -524,9 +512,6 @@ int virtio_device_freeze(struct virtio_device *dev) } } - if (dev->config->destroy_avq) - dev->config->destroy_avq(dev); - return 0; } EXPORT_SYMBOL_GPL(virtio_device_freeze); @@ -562,16 +547,10 @@ int virtio_device_restore(struct virtio_device *dev) if (ret) goto err; - if (dev->config->create_avq) { - ret = dev->config->create_avq(dev); - if (ret) - goto err; - } - if (drv->restore) { ret = drv->restore(dev); if (ret) - goto err_restore; + goto err; } /* If restore didn't do it, mark device DRIVER_OK ourselves. */ @@ -582,9 +561,6 @@ int virtio_device_restore(struct virtio_device *dev) return 0; -err_restore: - if (dev->config->destroy_avq) - dev->config->destroy_avq(dev); err: virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED); return ret; diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c index 7c5516ae1f8a..267643bb1cd5 100644 --- a/drivers/virtio/virtio_pci_common.c +++ b/drivers/virtio/virtio_pci_common.c @@ -262,9 +262,6 @@ void vp_del_vqs(struct virtio_device *vdev) int i; list_for_each_entry_safe(vq, n, &vdev->vqs, list) { - if (vp_dev->is_avq && vp_dev->is_avq(vdev, vq->index)) - continue; - if (vp_dev->per_vq_vectors) { int v = vp_dev->vqs[vq->index]->msix_vector; @@ -371,14 +368,23 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned int nvqs, struct irq_affinity *desc) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); + struct virtio_pci_admin_vq *avq = &vp_dev->admin_vq; struct virtqueue_info *vqi; int i, err, nvectors, allocated_vectors, queue_idx = 0; + struct virtqueue *vq; bool per_vq_vectors; + u16 avq_num = 0; vp_dev->vqs = kcalloc(nvqs, sizeof(*vp_dev->vqs), GFP_KERNEL); if (!vp_dev->vqs) return -ENOMEM; + if (vp_dev->avq_index) { + err = vp_dev->avq_index(vdev, &avq->vq_index, &avq_num); + if (err) + goto error_find; + } + per_vq_vectors = vector_policy != VP_VQ_VECTOR_POLICY_SHARED; if (per_vq_vectors) { @@ -415,6 +421,18 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned int nvqs, goto error_find; } } + + if (!avq_num) + return 0; + sprintf(avq->name, "avq.%u", avq->vq_index); + vq = vp_find_one_vq_msix(vdev, avq->vq_index, NULL, avq->name, false, + true, &allocated_vectors, vector_policy, + &vp_dev->admin_vq.info); + if (IS_ERR(vq)) { + err = PTR_ERR(vq); + goto error_find; + } + return 0; error_find: @@ -427,12 +445,21 @@ static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned int nvqs, struct virtqueue_info vqs_info[]) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); + struct virtio_pci_admin_vq *avq = &vp_dev->admin_vq; int i, err, queue_idx = 0; + struct virtqueue *vq; + u16 avq_num = 0; vp_dev->vqs = kcalloc(nvqs, sizeof(*vp_dev->vqs), GFP_KERNEL); if (!vp_dev->vqs) return -ENOMEM; + if (vp_dev->avq_index) { + err = vp_dev->avq_index(vdev, &avq->vq_index, &avq_num); + if (err) + goto out_del_vqs; + } + err = request_irq(vp_dev->pci_dev->irq, vp_interrupt, IRQF_SHARED, dev_name(&vdev->dev), vp_dev); if (err) @@ -456,6 +483,16 @@ static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned int nvqs, } } + if (!avq_num) + return 0; + sprintf(avq->name, "avq.%u", avq->vq_index); + vq = vp_setup_vq(vdev, queue_idx++, NULL, avq->name, false, + VIRTIO_MSI_NO_VECTOR, &vp_dev->admin_vq.info); + if (IS_ERR(vq)) { + err = PTR_ERR(vq); + goto out_del_vqs; + } + return 0; out_del_vqs: vp_del_vqs(vdev); diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h index aa43875b6353..de59bb06ec3c 100644 --- a/drivers/virtio/virtio_pci_common.h +++ b/drivers/virtio/virtio_pci_common.h @@ -44,7 +44,7 @@ struct virtio_pci_vq_info { struct virtio_pci_admin_vq { /* Virtqueue info associated with this admin queue. */ - struct virtio_pci_vq_info info; + struct virtio_pci_vq_info *info; /* serializing admin commands execution. */ struct mutex cmd_lock; u64 supported_cmds; @@ -105,7 +105,7 @@ struct virtio_pci_device { void (*del_vq)(struct virtio_pci_vq_info *info); u16 (*config_vector)(struct virtio_pci_device *vp_dev, u16 vector); - bool (*is_avq)(struct virtio_device *vdev, unsigned int index); + int (*avq_index)(struct virtio_device *vdev, u16 *index, u16 *num); }; /* Constants for MSI-X */ diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index d704947b1aec..5ceb4b2c18df 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -63,7 +63,7 @@ static int virtqueue_exec_admin_cmd(struct virtio_pci_admin_vq *admin_vq, struct virtqueue *vq; int ret, len; - vq = admin_vq->info.vq; + vq = admin_vq->info->vq; if (!vq) return -EIO; @@ -203,27 +203,12 @@ end: static void vp_modern_avq_activate(struct virtio_device *vdev) { - struct virtio_pci_device *vp_dev = to_vp_device(vdev); - struct virtio_pci_admin_vq *admin_vq = &vp_dev->admin_vq; - if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ)) return; - __virtqueue_unbreak(admin_vq->info.vq); virtio_pci_admin_cmd_list_init(vdev); } -static void vp_modern_avq_deactivate(struct virtio_device *vdev) -{ - struct virtio_pci_device *vp_dev = to_vp_device(vdev); - struct virtio_pci_admin_vq *admin_vq = &vp_dev->admin_vq; - - if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ)) - return; - - __virtqueue_break(admin_vq->info.vq); -} - static void vp_transport_features(struct virtio_device *vdev, u64 features) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); @@ -418,8 +403,6 @@ static void vp_reset(struct virtio_device *vdev) while (vp_modern_get_status(mdev)) msleep(1); - vp_modern_avq_deactivate(vdev); - /* Flush pending VQ/configuration callbacks. */ vp_synchronize_vectors(vdev); } @@ -595,9 +578,6 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, goto err; } - if (is_avq) - vp_dev->admin_vq.info.vq = vq; - return vq; err: @@ -741,41 +721,6 @@ static bool vp_get_shm_region(struct virtio_device *vdev, return true; } -static int vp_modern_create_avq(struct virtio_device *vdev) -{ - struct virtio_pci_device *vp_dev = to_vp_device(vdev); - struct virtio_pci_admin_vq *avq = &vp_dev->admin_vq; - struct virtqueue *vq; - u16 num; - int err; - - err = vp_avq_index(vdev, &avq->vq_index, &num); - if (err || !num) - return err; - - sprintf(avq->name, "avq.%u", avq->vq_index); - vq = vp_dev->setup_vq(vp_dev, &vp_dev->admin_vq.info, avq->vq_index, NULL, - avq->name, NULL, VIRTIO_MSI_NO_VECTOR); - if (IS_ERR(vq)) { - dev_err(&vdev->dev, "failed to setup admin virtqueue, err=%ld", - PTR_ERR(vq)); - return PTR_ERR(vq); - } - - vp_modern_set_queue_enable(&vp_dev->mdev, avq->info.vq->index, true); - return 0; -} - -static void vp_modern_destroy_avq(struct virtio_device *vdev) -{ - struct virtio_pci_device *vp_dev = to_vp_device(vdev); - - if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ)) - return; - - vp_dev->del_vq(&vp_dev->admin_vq.info); -} - static const struct virtio_config_ops virtio_pci_config_nodev_ops = { .get = NULL, .set = NULL, @@ -794,8 +739,6 @@ static const struct virtio_config_ops virtio_pci_config_nodev_ops = { .get_shm_region = vp_get_shm_region, .disable_vq_and_reset = vp_modern_disable_vq_and_reset, .enable_vq_after_reset = vp_modern_enable_vq_after_reset, - .create_avq = vp_modern_create_avq, - .destroy_avq = vp_modern_destroy_avq, }; static const struct virtio_config_ops virtio_pci_config_ops = { @@ -816,8 +759,6 @@ static const struct virtio_config_ops virtio_pci_config_ops = { .get_shm_region = vp_get_shm_region, .disable_vq_and_reset = vp_modern_disable_vq_and_reset, .enable_vq_after_reset = vp_modern_enable_vq_after_reset, - .create_avq = vp_modern_create_avq, - .destroy_avq = vp_modern_destroy_avq, }; /* the PCI probing function */ @@ -841,7 +782,7 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev) vp_dev->config_vector = vp_config_vector; vp_dev->setup_vq = setup_vq; vp_dev->del_vq = del_vq; - vp_dev->is_avq = vp_is_avq; + vp_dev->avq_index = vp_avq_index; vp_dev->isr = mdev->isr; vp_dev->vdev.id = mdev->id; diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index ab4b9a3fef6b..169c7d367fac 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -104,8 +104,6 @@ struct virtqueue_info { * Returns 0 on success or error status * If disable_vq_and_reset is set, then enable_vq_after_reset must also be * set. - * @create_avq: create admin virtqueue resource. - * @destroy_avq: destroy admin virtqueue resource. */ struct virtio_config_ops { void (*get)(struct virtio_device *vdev, unsigned offset, @@ -133,8 +131,6 @@ struct virtio_config_ops { struct virtio_shm_region *region, u8 id); int (*disable_vq_and_reset)(struct virtqueue *vq); int (*enable_vq_after_reset)(struct virtqueue *vq); - int (*create_avq)(struct virtio_device *vdev); - void (*destroy_avq)(struct virtio_device *vdev); }; /* If driver didn't advertise the feature, it will never appear. */ -- cgit v1.2.3 From 4c3b54af907e709609d3d8beca92d65e2f0cfd83 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 16 Jul 2024 13:35:51 +0200 Subject: virtio_pci_modern: use completion instead of busy loop to wait on admin cmd result Currently, the code waits in a busy loop on every admin virtqueue issued command to get a reply. That prevents callers from issuing multiple commands in parallel. To overcome this limitation, introduce a virtqueue event callback for admin virtqueue. For every issued command, use completion mechanism to wait on a reply. In the event callback, trigger the completion is done for every incoming reply. Alongside with that, introduce a spin lock to protect the admin virtqueue operations. Signed-off-by: Jiri Pirko Message-Id: <20240716113552.80599-13-jiri@resnulli.us> Signed-off-by: Michael S. Tsirkin --- drivers/virtio/virtio_pci_common.c | 13 ++++--- drivers/virtio/virtio_pci_common.h | 3 ++ drivers/virtio/virtio_pci_modern.c | 74 ++++++++++++++++++++++++++++++++------ include/linux/virtio.h | 3 ++ 4 files changed, 77 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c index 267643bb1cd5..c44d8ba00c02 100644 --- a/drivers/virtio/virtio_pci_common.c +++ b/drivers/virtio/virtio_pci_common.c @@ -395,6 +395,8 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned int nvqs, if (vqi->name && vqi->callback) ++nvectors; } + if (avq_num && vector_policy == VP_VQ_VECTOR_POLICY_EACH) + ++nvectors; } else { /* Second best: one for change, shared for all vqs. */ nvectors = 2; @@ -425,9 +427,9 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned int nvqs, if (!avq_num) return 0; sprintf(avq->name, "avq.%u", avq->vq_index); - vq = vp_find_one_vq_msix(vdev, avq->vq_index, NULL, avq->name, false, - true, &allocated_vectors, vector_policy, - &vp_dev->admin_vq.info); + vq = vp_find_one_vq_msix(vdev, avq->vq_index, vp_modern_avq_done, + avq->name, false, true, &allocated_vectors, + vector_policy, &vp_dev->admin_vq.info); if (IS_ERR(vq)) { err = PTR_ERR(vq); goto error_find; @@ -486,8 +488,9 @@ static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned int nvqs, if (!avq_num) return 0; sprintf(avq->name, "avq.%u", avq->vq_index); - vq = vp_setup_vq(vdev, queue_idx++, NULL, avq->name, false, - VIRTIO_MSI_NO_VECTOR, &vp_dev->admin_vq.info); + vq = vp_setup_vq(vdev, queue_idx++, vp_modern_avq_done, avq->name, + false, VIRTIO_MSI_NO_VECTOR, + &vp_dev->admin_vq.info); if (IS_ERR(vq)) { err = PTR_ERR(vq); goto out_del_vqs; diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h index de59bb06ec3c..90df381fbbcf 100644 --- a/drivers/virtio/virtio_pci_common.h +++ b/drivers/virtio/virtio_pci_common.h @@ -47,6 +47,8 @@ struct virtio_pci_admin_vq { struct virtio_pci_vq_info *info; /* serializing admin commands execution. */ struct mutex cmd_lock; + /* Protects virtqueue access. */ + spinlock_t lock; u64 supported_cmds; /* Name of the admin queue: avq.$vq_index. */ char name[10]; @@ -178,6 +180,7 @@ struct virtio_device *virtio_pci_vf_get_pf_dev(struct pci_dev *pdev); #define VIRTIO_ADMIN_CMD_BITMAP 0 #endif +void vp_modern_avq_done(struct virtqueue *vq); int vp_modern_admin_cmd_exec(struct virtio_device *vdev, struct virtio_admin_cmd *cmd); diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index 0fd344d1eaf9..608df3263df1 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -53,6 +53,23 @@ static bool vp_is_avq(struct virtio_device *vdev, unsigned int index) return index == vp_dev->admin_vq.vq_index; } +void vp_modern_avq_done(struct virtqueue *vq) +{ + struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev); + struct virtio_pci_admin_vq *admin_vq = &vp_dev->admin_vq; + struct virtio_admin_cmd *cmd; + unsigned long flags; + unsigned int len; + + spin_lock_irqsave(&admin_vq->lock, flags); + do { + virtqueue_disable_cb(vq); + while ((cmd = virtqueue_get_buf(vq, &len))) + complete(&cmd->completion); + } while (!virtqueue_enable_cb(vq)); + spin_unlock_irqrestore(&admin_vq->lock, flags); +} + static int virtqueue_exec_admin_cmd(struct virtio_pci_admin_vq *admin_vq, u16 opcode, struct scatterlist **sgs, @@ -61,7 +78,8 @@ static int virtqueue_exec_admin_cmd(struct virtio_pci_admin_vq *admin_vq, struct virtio_admin_cmd *cmd) { struct virtqueue *vq; - int ret, len; + unsigned long flags; + int ret; vq = admin_vq->info->vq; if (!vq) @@ -72,21 +90,33 @@ static int virtqueue_exec_admin_cmd(struct virtio_pci_admin_vq *admin_vq, !((1ULL << opcode) & admin_vq->supported_cmds)) return -EOPNOTSUPP; - ret = virtqueue_add_sgs(vq, sgs, out_num, in_num, cmd, GFP_KERNEL); - if (ret < 0) - return -EIO; + init_completion(&cmd->completion); - if (unlikely(!virtqueue_kick(vq))) +again: + if (virtqueue_is_broken(vq)) return -EIO; - while (!virtqueue_get_buf(vq, &len) && - !virtqueue_is_broken(vq)) - cpu_relax(); + spin_lock_irqsave(&admin_vq->lock, flags); + ret = virtqueue_add_sgs(vq, sgs, out_num, in_num, cmd, GFP_KERNEL); + if (ret < 0) { + if (ret == -ENOSPC) { + spin_unlock_irqrestore(&admin_vq->lock, flags); + cpu_relax(); + goto again; + } + goto unlock_err; + } + if (!virtqueue_kick(vq)) + goto unlock_err; + spin_unlock_irqrestore(&admin_vq->lock, flags); - if (virtqueue_is_broken(vq)) - return -EIO; + wait_for_completion(&cmd->completion); - return 0; + return cmd->ret; + +unlock_err: + spin_unlock_irqrestore(&admin_vq->lock, flags); + return -EIO; } int vp_modern_admin_cmd_exec(struct virtio_device *vdev, @@ -209,6 +239,25 @@ static void vp_modern_avq_activate(struct virtio_device *vdev) virtio_pci_admin_cmd_list_init(vdev); } +static void vp_modern_avq_cleanup(struct virtio_device *vdev) +{ + struct virtio_pci_device *vp_dev = to_vp_device(vdev); + struct virtio_admin_cmd *cmd; + struct virtqueue *vq; + + if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ)) + return; + + vq = vp_dev->vqs[vp_dev->admin_vq.vq_index]->vq; + if (!vq) + return; + + while ((cmd = virtqueue_detach_unused_buf(vq))) { + cmd->ret = -EIO; + complete(&cmd->completion); + } +} + static void vp_transport_features(struct virtio_device *vdev, u64 features) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); @@ -403,6 +452,8 @@ static void vp_reset(struct virtio_device *vdev) while (vp_modern_get_status(mdev)) msleep(1); + vp_modern_avq_cleanup(vdev); + /* Flush pending VQ/configuration callbacks. */ vp_synchronize_vectors(vdev); } @@ -785,6 +836,7 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev) vp_dev->isr = mdev->isr; vp_dev->vdev.id = mdev->id; + spin_lock_init(&vp_dev->admin_vq.lock); mutex_init(&vp_dev->admin_vq.cmd_lock); return 0; } diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 96fea920873b..999ff5934392 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -10,6 +10,7 @@ #include #include #include +#include /** * struct virtqueue - a queue to register buffers for sending or receiving. @@ -109,6 +110,8 @@ struct virtio_admin_cmd { __le64 group_member_id; struct scatterlist *data_sg; struct scatterlist *result_sg; + struct completion completion; + int ret; }; /** -- cgit v1.2.3 From e1a261ba599eec97e1c5c7760d5c3698fc24e6a6 Mon Sep 17 00:00:00 2001 From: Jocelyn Falempe Date: Tue, 2 Jul 2024 14:26:04 +0200 Subject: printk: Add a short description string to kmsg_dump() kmsg_dump doesn't forward the panic reason string to the kmsg_dumper callback. This patch adds a new struct kmsg_dump_detail, that will hold the reason and description, and pass it to the dump() callback. To avoid updating all kmsg_dump() call, it adds a kmsg_dump_desc() function and a macro for backward compatibility. I've written this for drm_panic, but it can be useful for other kmsg_dumper. It allows to see the panic reason, like "sysrq triggered crash" or "VFS: Unable to mount root fs on xxxx" on the drm panic screen. v2: * Use a struct kmsg_dump_detail to hold the reason and description pointer, for more flexibility if we want to add other parameters. (Kees Cook) * Fix powerpc/nvram_64 build, as I didn't update the forward declaration of oops_to_nvram() Signed-off-by: Jocelyn Falempe Acked-by: Petr Mladek Acked-by: Michael Ellerman (powerpc) Acked-by: Kees Cook Link: https://patchwork.freedesktop.org/patch/msgid/20240702122639.248110-1-jfalempe@redhat.com --- arch/powerpc/kernel/nvram_64.c | 8 ++++---- arch/powerpc/platforms/powernv/opal-kmsg.c | 4 ++-- arch/um/kernel/kmsg_dump.c | 2 +- drivers/gpu/drm/drm_panic.c | 4 ++-- drivers/hv/hv_common.c | 4 ++-- drivers/mtd/mtdoops.c | 2 +- fs/pstore/platform.c | 10 +++++----- include/linux/kmsg_dump.h | 22 +++++++++++++++++++--- kernel/panic.c | 2 +- kernel/printk/printk.c | 11 ++++++++--- 10 files changed, 45 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index e385d3164648..f9c6568a9137 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -73,7 +73,7 @@ static const char *nvram_os_partitions[] = { }; static void oops_to_nvram(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason); + struct kmsg_dump_detail *detail); static struct kmsg_dumper nvram_kmsg_dumper = { .dump = oops_to_nvram @@ -643,7 +643,7 @@ void __init nvram_init_oops_partition(int rtas_partition_exists) * partition. If that's too much, go back and capture uncompressed text. */ static void oops_to_nvram(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason) + struct kmsg_dump_detail *detail) { struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf; static unsigned int oops_count = 0; @@ -655,7 +655,7 @@ static void oops_to_nvram(struct kmsg_dumper *dumper, unsigned int err_type = ERR_TYPE_KERNEL_PANIC_GZ; int rc = -1; - switch (reason) { + switch (detail->reason) { case KMSG_DUMP_SHUTDOWN: /* These are almost always orderly shutdowns. */ return; @@ -671,7 +671,7 @@ static void oops_to_nvram(struct kmsg_dumper *dumper, break; default: pr_err("%s: ignoring unrecognized KMSG_DUMP_* reason %d\n", - __func__, (int) reason); + __func__, (int) detail->reason); return; } diff --git a/arch/powerpc/platforms/powernv/opal-kmsg.c b/arch/powerpc/platforms/powernv/opal-kmsg.c index 6c3bc4b4da98..bb4218fa796e 100644 --- a/arch/powerpc/platforms/powernv/opal-kmsg.c +++ b/arch/powerpc/platforms/powernv/opal-kmsg.c @@ -20,13 +20,13 @@ * message, it just ensures that OPAL completely flushes the console buffer. */ static void kmsg_dump_opal_console_flush(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason) + struct kmsg_dump_detail *detail) { /* * Outside of a panic context the pollers will continue to run, * so we don't need to do any special flushing. */ - if (reason != KMSG_DUMP_PANIC) + if (detail->reason != KMSG_DUMP_PANIC) return; opal_flush_console(0); diff --git a/arch/um/kernel/kmsg_dump.c b/arch/um/kernel/kmsg_dump.c index 4382cf02a6d1..419021175272 100644 --- a/arch/um/kernel/kmsg_dump.c +++ b/arch/um/kernel/kmsg_dump.c @@ -8,7 +8,7 @@ #include static void kmsg_dumper_stdout(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason) + struct kmsg_dump_detail *detail) { static struct kmsg_dump_iter iter; static DEFINE_SPINLOCK(lock); diff --git a/drivers/gpu/drm/drm_panic.c b/drivers/gpu/drm/drm_panic.c index 948aed00595e..8794c7f6c0ee 100644 --- a/drivers/gpu/drm/drm_panic.c +++ b/drivers/gpu/drm/drm_panic.c @@ -655,11 +655,11 @@ static struct drm_plane *to_drm_plane(struct kmsg_dumper *kd) return container_of(kd, struct drm_plane, kmsg_panic); } -static void drm_panic(struct kmsg_dumper *dumper, enum kmsg_dump_reason reason) +static void drm_panic(struct kmsg_dumper *dumper, struct kmsg_dump_detail *detail) { struct drm_plane *plane = to_drm_plane(dumper); - if (reason == KMSG_DUMP_PANIC) + if (detail->reason == KMSG_DUMP_PANIC) draw_panic_plane(plane); } diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c index 9c452bfbd571..7a35c82976e0 100644 --- a/drivers/hv/hv_common.c +++ b/drivers/hv/hv_common.c @@ -207,13 +207,13 @@ static int hv_die_panic_notify_crash(struct notifier_block *self, * buffer and call into Hyper-V to transfer the data. */ static void hv_kmsg_dump(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason) + struct kmsg_dump_detail *detail) { struct kmsg_dump_iter iter; size_t bytes_written; /* We are only interested in panics. */ - if (reason != KMSG_DUMP_PANIC || !sysctl_record_panic_msg) + if (detail->reason != KMSG_DUMP_PANIC || !sysctl_record_panic_msg) return; /* diff --git a/drivers/mtd/mtdoops.c b/drivers/mtd/mtdoops.c index 2f11585b5613..86d49db9196d 100644 --- a/drivers/mtd/mtdoops.c +++ b/drivers/mtd/mtdoops.c @@ -298,7 +298,7 @@ static void find_next_position(struct mtdoops_context *cxt) } static void mtdoops_do_dump(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason) + struct kmsg_dump_detail *detail) { struct mtdoops_context *cxt = container_of(dumper, struct mtdoops_context, dump); diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 03425928d2fb..7f5810589a26 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -275,7 +275,7 @@ void pstore_record_init(struct pstore_record *record, * end of the buffer. */ static void pstore_dump(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason) + struct kmsg_dump_detail *detail) { struct kmsg_dump_iter iter; unsigned long total = 0; @@ -285,9 +285,9 @@ static void pstore_dump(struct kmsg_dumper *dumper, int saved_ret = 0; int ret; - why = kmsg_dump_reason_str(reason); + why = kmsg_dump_reason_str(detail->reason); - if (pstore_cannot_block_path(reason)) { + if (pstore_cannot_block_path(detail->reason)) { if (!spin_trylock_irqsave(&psinfo->buf_lock, flags)) { pr_err("dump skipped in %s path because of concurrent dump\n", in_nmi() ? "NMI" : why); @@ -311,7 +311,7 @@ static void pstore_dump(struct kmsg_dumper *dumper, pstore_record_init(&record, psinfo); record.type = PSTORE_TYPE_DMESG; record.count = oopscount; - record.reason = reason; + record.reason = detail->reason; record.part = part; record.buf = psinfo->buf; @@ -352,7 +352,7 @@ static void pstore_dump(struct kmsg_dumper *dumper, } ret = psinfo->write(&record); - if (ret == 0 && reason == KMSG_DUMP_OOPS) { + if (ret == 0 && detail->reason == KMSG_DUMP_OOPS) { pstore_new_entry = 1; pstore_timer_kick(); } else { diff --git a/include/linux/kmsg_dump.h b/include/linux/kmsg_dump.h index 906521c2329c..6055fc969877 100644 --- a/include/linux/kmsg_dump.h +++ b/include/linux/kmsg_dump.h @@ -39,6 +39,17 @@ struct kmsg_dump_iter { u64 next_seq; }; +/** + * struct kmsg_dump_detail - kernel crash detail + * @reason: reason for the crash, see kmsg_dump_reason. + * @description: optional short string, to provide additional information. + */ + +struct kmsg_dump_detail { + enum kmsg_dump_reason reason; + const char *description; +}; + /** * struct kmsg_dumper - kernel crash message dumper structure * @list: Entry in the dumper list (private) @@ -49,13 +60,13 @@ struct kmsg_dump_iter { */ struct kmsg_dumper { struct list_head list; - void (*dump)(struct kmsg_dumper *dumper, enum kmsg_dump_reason reason); + void (*dump)(struct kmsg_dumper *dumper, struct kmsg_dump_detail *detail); enum kmsg_dump_reason max_reason; bool registered; }; #ifdef CONFIG_PRINTK -void kmsg_dump(enum kmsg_dump_reason reason); +void kmsg_dump_desc(enum kmsg_dump_reason reason, const char *desc); bool kmsg_dump_get_line(struct kmsg_dump_iter *iter, bool syslog, char *line, size_t size, size_t *len); @@ -71,7 +82,7 @@ int kmsg_dump_unregister(struct kmsg_dumper *dumper); const char *kmsg_dump_reason_str(enum kmsg_dump_reason reason); #else -static inline void kmsg_dump(enum kmsg_dump_reason reason) +static inline void kmsg_dump_desc(enum kmsg_dump_reason reason, const char *desc) { } @@ -107,4 +118,9 @@ static inline const char *kmsg_dump_reason_str(enum kmsg_dump_reason reason) } #endif +static inline void kmsg_dump(enum kmsg_dump_reason reason) +{ + kmsg_dump_desc(reason, NULL); +} + #endif /* _LINUX_KMSG_DUMP_H */ diff --git a/kernel/panic.c b/kernel/panic.c index 8bff183d6180..d6219841f491 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -375,7 +375,7 @@ void panic(const char *fmt, ...) panic_print_sys_info(false); - kmsg_dump(KMSG_DUMP_PANIC); + kmsg_dump_desc(KMSG_DUMP_PANIC, buf); /* * If you doubt kdump always works fine in any situation, diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 420fd310129d..4310ff3f23e5 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -4126,16 +4126,21 @@ const char *kmsg_dump_reason_str(enum kmsg_dump_reason reason) EXPORT_SYMBOL_GPL(kmsg_dump_reason_str); /** - * kmsg_dump - dump kernel log to kernel message dumpers. + * kmsg_dump_desc - dump kernel log to kernel message dumpers. * @reason: the reason (oops, panic etc) for dumping + * @desc: a short string to describe what caused the panic or oops. Can be NULL + * if no additional description is available. * * Call each of the registered dumper's dump() callback, which can * retrieve the kmsg records with kmsg_dump_get_line() or * kmsg_dump_get_buffer(). */ -void kmsg_dump(enum kmsg_dump_reason reason) +void kmsg_dump_desc(enum kmsg_dump_reason reason, const char *desc) { struct kmsg_dumper *dumper; + struct kmsg_dump_detail detail = { + .reason = reason, + .description = desc}; rcu_read_lock(); list_for_each_entry_rcu(dumper, &dump_list, list) { @@ -4153,7 +4158,7 @@ void kmsg_dump(enum kmsg_dump_reason reason) continue; /* invoke dumper which will iterate over records */ - dumper->dump(dumper, reason); + dumper->dump(dumper, &detail); } rcu_read_unlock(); } -- cgit v1.2.3 From d20a9f568f99591886ec73b80ff7283486710643 Mon Sep 17 00:00:00 2001 From: Jocelyn Falempe Date: Wed, 17 Jul 2024 10:48:40 +0200 Subject: fbcon: Add an option to disable fbcon in panic This is required to avoid conflict between DRM_PANIC, and fbcon. If a drm device already handle panic with drm_panic, it should set the skip_panic field in fb_info, so that fbcon will stay quiet, and not overwrite the panic_screen. Signed-off-by: Jocelyn Falempe Reviewed-by: Javier Martinez Canillas Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20240717090102.968152-3-jfalempe@redhat.com --- drivers/video/fbdev/core/fbcon.c | 7 ++++++- include/linux/fb.h | 1 + 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 3f7333dca508..498d9c07df80 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -270,12 +270,17 @@ static int fbcon_get_rotate(struct fb_info *info) return (ops) ? ops->rotate : 0; } +static bool fbcon_skip_panic(struct fb_info *info) +{ + return (info->skip_panic && unlikely(atomic_read(&panic_cpu) != PANIC_CPU_INVALID)); +} + static inline int fbcon_is_inactive(struct vc_data *vc, struct fb_info *info) { struct fbcon_ops *ops = info->fbcon_par; return (info->state != FBINFO_STATE_RUNNING || - vc->vc_mode != KD_TEXT || ops->graphics); + vc->vc_mode != KD_TEXT || ops->graphics || fbcon_skip_panic(info)); } static int get_color(struct vc_data *vc, struct fb_info *info, diff --git a/include/linux/fb.h b/include/linux/fb.h index db7d97b10964..865dad03e73e 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -510,6 +510,7 @@ struct fb_info { void *par; bool skip_vt_switch; /* no VT switch on suspend/resume required */ + bool skip_panic; /* Do not write to the fb after a panic */ }; /* This will go away -- cgit v1.2.3 From a838e5dca63d1dc701e63b2b1176943c57485c45 Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Mon, 15 Jul 2024 21:05:32 +0800 Subject: quota: remove unneeded return value of register_quota_format The register_quota_format always returns 0, simply remove unneeded return value. Link: https://patch.msgid.link/20240715130534.2112678-3-shikemeng@huaweicloud.com Signed-off-by: Kemeng Shi Reviewed-by: Joseph Qi Signed-off-by: Jan Kara --- fs/ocfs2/super.c | 6 ++---- fs/quota/dquot.c | 3 +-- fs/quota/quota_v1.c | 3 ++- fs/quota/quota_v2.c | 9 +++------ include/linux/quota.h | 2 +- mm/shmem.c | 7 +------ 6 files changed, 10 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index afee70125ae3..73caa8914ebe 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1571,15 +1571,13 @@ static int __init ocfs2_init(void) ocfs2_set_locking_protocol(); - status = register_quota_format(&ocfs2_quota_format); - if (status < 0) - goto out3; + register_quota_format(&ocfs2_quota_format); + status = register_filesystem(&ocfs2_fs_type); if (!status) return 0; unregister_quota_format(&ocfs2_quota_format); -out3: debugfs_remove(ocfs2_debugfs_root); ocfs2_free_mem_caches(); out2: diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 104927804bec..1ddd1e9d1eeb 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -163,13 +163,12 @@ static struct quota_module_name module_names[] = INIT_QUOTA_MODULE_NAMES; /* SLAB cache for dquot structures */ static struct kmem_cache *dquot_cachep; -int register_quota_format(struct quota_format_type *fmt) +void register_quota_format(struct quota_format_type *fmt) { spin_lock(&dq_list_lock); fmt->qf_next = quota_formats; quota_formats = fmt; spin_unlock(&dq_list_lock); - return 0; } EXPORT_SYMBOL(register_quota_format); diff --git a/fs/quota/quota_v1.c b/fs/quota/quota_v1.c index 3f3e8acc05db..6f7f0b4afba9 100644 --- a/fs/quota/quota_v1.c +++ b/fs/quota/quota_v1.c @@ -235,7 +235,8 @@ static struct quota_format_type v1_quota_format = { static int __init init_v1_quota_format(void) { - return register_quota_format(&v1_quota_format); + register_quota_format(&v1_quota_format); + return 0; } static void __exit exit_v1_quota_format(void) diff --git a/fs/quota/quota_v2.c b/fs/quota/quota_v2.c index c48c233f3bef..1fda93dcbc1b 100644 --- a/fs/quota/quota_v2.c +++ b/fs/quota/quota_v2.c @@ -440,12 +440,9 @@ static struct quota_format_type v2r1_quota_format = { static int __init init_v2_quota_format(void) { - int ret; - - ret = register_quota_format(&v2r0_quota_format); - if (ret) - return ret; - return register_quota_format(&v2r1_quota_format); + register_quota_format(&v2r0_quota_format); + register_quota_format(&v2r1_quota_format); + return 0; } static void __exit exit_v2_quota_format(void) diff --git a/include/linux/quota.h b/include/linux/quota.h index 07071e64abf3..89a0d83ddad0 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -526,7 +526,7 @@ struct quota_info { const struct quota_format_ops *ops[MAXQUOTAS]; /* Operations for each type */ }; -int register_quota_format(struct quota_format_type *fmt); +void register_quota_format(struct quota_format_type *fmt); void unregister_quota_format(struct quota_format_type *fmt); struct quota_module_name { diff --git a/mm/shmem.c b/mm/shmem.c index 2faa9daaf54b..3b922d44e12c 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -4818,11 +4818,7 @@ void __init shmem_init(void) shmem_init_inodecache(); #ifdef CONFIG_TMPFS_QUOTA - error = register_quota_format(&shmem_quota_format); - if (error < 0) { - pr_err("Could not register quota format\n"); - goto out3; - } + register_quota_format(&shmem_quota_format); #endif error = register_filesystem(&shmem_fs_type); @@ -4857,7 +4853,6 @@ out1: out2: #ifdef CONFIG_TMPFS_QUOTA unregister_quota_format(&shmem_quota_format); -out3: #endif shmem_destroy_inodecache(); shm_mnt = ERR_PTR(error); -- cgit v1.2.3 From d5e79eeba3086a52593b295ac4bf6eddd64d4aad Mon Sep 17 00:00:00 2001 From: "T.J. Mercier" Date: Sat, 20 Jul 2024 15:15:42 +0800 Subject: dma-buf: heaps: Deduplicate docs and adopt common format MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The docs for dma_heap_get_name were incorrect, and since they were duplicated in the header they were wrong there too. The docs formatting was inconsistent so I tried to make it more consistent across functions since I'm already in here doing cleanup. Remove multiple unused includes and alphabetize. Signed-off-by: T.J. Mercier Signed-off-by: Yong Wu [Yong: Just add a comment for "priv" to mute build warning] Signed-off-by: Yunfei Dong Link: https://patchwork.freedesktop.org/patch/msgid/20240720071606.27930-5-yunfei.dong@mediatek.com Signed-off-by: Christian König --- drivers/dma-buf/dma-heap.c | 27 +++++++++++++++------------ include/linux/dma-heap.h | 21 +-------------------- 2 files changed, 16 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma-buf/dma-heap.c b/drivers/dma-buf/dma-heap.c index 2298ca5e112e..3cbe87d4a464 100644 --- a/drivers/dma-buf/dma-heap.c +++ b/drivers/dma-buf/dma-heap.c @@ -7,17 +7,15 @@ */ #include -#include #include #include +#include #include -#include #include -#include #include -#include #include -#include +#include +#include #include #define DEVNAME "dma_heap" @@ -28,9 +26,10 @@ * struct dma_heap - represents a dmabuf heap in the system * @name: used for debugging/device-node name * @ops: ops struct for this heap - * @heap_devt heap device node - * @list list head connecting to list of heaps - * @heap_cdev heap char device + * @priv: private data for this heap + * @heap_devt: heap device node + * @list: list head connecting to list of heaps + * @heap_cdev: heap char device * * Represents a heap of memory from which buffers can be made. */ @@ -193,11 +192,11 @@ static const struct file_operations dma_heap_fops = { }; /** - * dma_heap_get_drvdata() - get per-subdriver data for the heap + * dma_heap_get_drvdata - get per-heap driver data * @heap: DMA-Heap to retrieve private data for * * Returns: - * The per-subdriver data for the heap. + * The per-heap data for the heap. */ void *dma_heap_get_drvdata(struct dma_heap *heap) { @@ -205,8 +204,8 @@ void *dma_heap_get_drvdata(struct dma_heap *heap) } /** - * dma_heap_get_name() - get heap name - * @heap: DMA-Heap to retrieve private data for + * dma_heap_get_name - get heap name + * @heap: DMA-Heap to retrieve the name of * * Returns: * The char* for the heap name. @@ -216,6 +215,10 @@ const char *dma_heap_get_name(struct dma_heap *heap) return heap->name; } +/** + * dma_heap_add - adds a heap to dmabuf heaps + * @exp_info: information needed to register this heap + */ struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info) { struct dma_heap *heap, *h, *err_ret; diff --git a/include/linux/dma-heap.h b/include/linux/dma-heap.h index 064bad725061..27d15f60950a 100644 --- a/include/linux/dma-heap.h +++ b/include/linux/dma-heap.h @@ -9,14 +9,13 @@ #ifndef _DMA_HEAPS_H #define _DMA_HEAPS_H -#include #include struct dma_heap; /** * struct dma_heap_ops - ops to operate on a given heap - * @allocate: allocate dmabuf and return struct dma_buf ptr + * @allocate: allocate dmabuf and return struct dma_buf ptr * * allocate returns dmabuf on success, ERR_PTR(-errno) on error. */ @@ -41,28 +40,10 @@ struct dma_heap_export_info { void *priv; }; -/** - * dma_heap_get_drvdata() - get per-heap driver data - * @heap: DMA-Heap to retrieve private data for - * - * Returns: - * The per-heap data for the heap. - */ void *dma_heap_get_drvdata(struct dma_heap *heap); -/** - * dma_heap_get_name() - get heap name - * @heap: DMA-Heap to retrieve private data for - * - * Returns: - * The char* for the heap name. - */ const char *dma_heap_get_name(struct dma_heap *heap); -/** - * dma_heap_add - adds a heap to dmabuf heaps - * @exp_info: information needed to register this heap - */ struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info); #endif /* _DMA_HEAPS_H */ -- cgit v1.2.3 From 564429a6bd8d26065b2cccffcaa9485359f74de7 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 11 Jul 2024 18:27:47 -0400 Subject: KVM: rename CONFIG_HAVE_KVM_GMEM_* to CONFIG_HAVE_KVM_ARCH_GMEM_* Add "ARCH" to the symbols; shortly, the "prepare" phase will include both the arch-independent step to clear out contents left in the page by the host, and the arch-dependent step enabled by CONFIG_HAVE_KVM_GMEM_PREPARE. For consistency do the same for CONFIG_HAVE_KVM_GMEM_INVALIDATE as well. Reviewed-by: Michael Roth Signed-off-by: Paolo Bonzini --- arch/x86/kvm/Kconfig | 4 ++-- arch/x86/kvm/x86.c | 4 ++-- include/linux/kvm_host.h | 4 ++-- virt/kvm/Kconfig | 4 ++-- virt/kvm/guest_memfd.c | 6 +++--- 5 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 4287a8071a3a..472a1537b7a9 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -141,8 +141,8 @@ config KVM_AMD_SEV depends on CRYPTO_DEV_SP_PSP && !(KVM_AMD=y && CRYPTO_DEV_CCP_DD=m) select ARCH_HAS_CC_PLATFORM select KVM_GENERIC_PRIVATE_MEM - select HAVE_KVM_GMEM_PREPARE - select HAVE_KVM_GMEM_INVALIDATE + select HAVE_KVM_ARCH_GMEM_PREPARE + select HAVE_KVM_ARCH_GMEM_INVALIDATE help Provides support for launching Encrypted VMs (SEV) and Encrypted VMs with Encrypted State (SEV-ES) on AMD processors. diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 52778689cef4..4db18924b2f2 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -13644,7 +13644,7 @@ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_arch_no_poll); -#ifdef CONFIG_HAVE_KVM_GMEM_PREPARE +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE bool kvm_arch_gmem_prepare_needed(struct kvm *kvm) { return kvm->arch.vm_type == KVM_X86_SNP_VM; @@ -13656,7 +13656,7 @@ int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_ord } #endif -#ifdef CONFIG_HAVE_KVM_GMEM_INVALIDATE +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end) { kvm_x86_call(gmem_invalidate)(start, end); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 689e8be873a7..344d90771844 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -2445,7 +2445,7 @@ static inline int kvm_gmem_get_pfn(struct kvm *kvm, } #endif /* CONFIG_KVM_PRIVATE_MEM */ -#ifdef CONFIG_HAVE_KVM_GMEM_PREPARE +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order); bool kvm_arch_gmem_prepare_needed(struct kvm *kvm); #endif @@ -2477,7 +2477,7 @@ typedef int (*kvm_gmem_populate_cb)(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, long kvm_gmem_populate(struct kvm *kvm, gfn_t gfn, void __user *src, long npages, kvm_gmem_populate_cb post_populate, void *opaque); -#ifdef CONFIG_HAVE_KVM_GMEM_INVALIDATE +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end); #endif diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index b14e14cdbfb9..fd6a3010afa8 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -113,10 +113,10 @@ config KVM_GENERIC_PRIVATE_MEM select KVM_PRIVATE_MEM bool -config HAVE_KVM_GMEM_PREPARE +config HAVE_KVM_ARCH_GMEM_PREPARE bool depends on KVM_PRIVATE_MEM -config HAVE_KVM_GMEM_INVALIDATE +config HAVE_KVM_ARCH_GMEM_INVALIDATE bool depends on KVM_PRIVATE_MEM diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index 5221b584288f..76139332f2f3 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -27,7 +27,7 @@ static inline kvm_pfn_t folio_file_pfn(struct folio *folio, pgoff_t index) static int kvm_gmem_prepare_folio(struct inode *inode, pgoff_t index, struct folio *folio) { -#ifdef CONFIG_HAVE_KVM_GMEM_PREPARE +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE struct list_head *gmem_list = &inode->i_mapping->i_private_list; struct kvm_gmem *gmem; @@ -353,7 +353,7 @@ static int kvm_gmem_error_folio(struct address_space *mapping, struct folio *fol return MF_DELAYED; } -#ifdef CONFIG_HAVE_KVM_GMEM_INVALIDATE +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE static void kvm_gmem_free_folio(struct folio *folio) { struct page *page = folio_page(folio, 0); @@ -368,7 +368,7 @@ static const struct address_space_operations kvm_gmem_aops = { .dirty_folio = noop_dirty_folio, .migrate_folio = kvm_gmem_migrate_folio, .error_remove_folio = kvm_gmem_error_folio, -#ifdef CONFIG_HAVE_KVM_GMEM_INVALIDATE +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE .free_folio = kvm_gmem_free_folio, #endif }; -- cgit v1.2.3 From 7239ed74677af143857d1a96d402476446a0995a Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 11 Jul 2024 18:27:51 -0400 Subject: KVM: remove kvm_arch_gmem_prepare_needed() It is enough to return 0 if a guest need not do any preparation. This is in fact how sev_gmem_prepare() works for non-SNP guests, and it extends naturally to Intel hosts: the x86 callback for gmem_prepare is optional and returns 0 if not defined. Reviewed-by: Michael Roth Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 5 ----- include/linux/kvm_host.h | 1 - virt/kvm/guest_memfd.c | 13 +++---------- 3 files changed, 3 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4db18924b2f2..ef3d3511e4af 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -13645,11 +13645,6 @@ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) EXPORT_SYMBOL_GPL(kvm_arch_no_poll); #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE -bool kvm_arch_gmem_prepare_needed(struct kvm *kvm) -{ - return kvm->arch.vm_type == KVM_X86_SNP_VM; -} - int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order) { return kvm_x86_call(gmem_prepare)(kvm, pfn, gfn, max_order); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 344d90771844..45373d42f314 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -2447,7 +2447,6 @@ static inline int kvm_gmem_get_pfn(struct kvm *kvm, #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order); -bool kvm_arch_gmem_prepare_needed(struct kvm *kvm); #endif /** diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index 444ded162154..191fd42067c0 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -29,16 +29,9 @@ static int __kvm_gmem_prepare_folio(struct kvm *kvm, struct kvm_memory_slot *slo pgoff_t index, struct folio *folio) { #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE - kvm_pfn_t pfn; - gfn_t gfn; - int rc; - - if (!kvm_arch_gmem_prepare_needed(kvm)) - return 0; - - pfn = folio_file_pfn(folio, index); - gfn = slot->base_gfn + index - slot->gmem.pgoff; - rc = kvm_arch_gmem_prepare(kvm, gfn, pfn, folio_order(folio)); + kvm_pfn_t pfn = folio_file_pfn(folio, index); + gfn_t gfn = slot->base_gfn + index - slot->gmem.pgoff; + int rc = kvm_arch_gmem_prepare(kvm, gfn, pfn, folio_order(folio)); if (rc) { pr_warn_ratelimited("gmem: Failed to prepare folio for index %lx GFN %llx PFN %llx error %d.\n", index, gfn, pfn, rc); -- cgit v1.2.3 From 4b5f67120a88c713b82907d55a767693382e9e9d Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 11 Jul 2024 18:27:54 -0400 Subject: KVM: extend kvm_range_has_memory_attributes() to check subset of attributes While currently there is no other attribute than KVM_MEMORY_ATTRIBUTE_PRIVATE, KVM code such as kvm_mem_is_private() is written to expect their existence. Allow using kvm_range_has_memory_attributes() as a multi-page version of kvm_mem_is_private(), without it breaking later when more attributes are introduced. Reviewed-by: Michael Roth Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/mmu.c | 2 +- include/linux/kvm_host.h | 2 +- virt/kvm/kvm_main.c | 13 +++++++------ 3 files changed, 9 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 26ef5b6ac3c1..43a02891babb 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -7513,7 +7513,7 @@ static bool hugepage_has_attrs(struct kvm *kvm, struct kvm_memory_slot *slot, const unsigned long end = start + KVM_PAGES_PER_HPAGE(level); if (level == PG_LEVEL_2M) - return kvm_range_has_memory_attributes(kvm, start, end, attrs); + return kvm_range_has_memory_attributes(kvm, start, end, ~0, attrs); for (gfn = start; gfn < end; gfn += KVM_PAGES_PER_HPAGE(level - 1)) { if (hugepage_test_mixed(slot, gfn, level - 1) || diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 45373d42f314..c223b97df03e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -2414,7 +2414,7 @@ static inline unsigned long kvm_get_memory_attributes(struct kvm *kvm, gfn_t gfn } bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end, - unsigned long attrs); + unsigned long mask, unsigned long attrs); bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_arch_post_set_memory_attributes(struct kvm *kvm, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 30328ff2d840..92901656a0d4 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2408,21 +2408,21 @@ static u64 kvm_supported_mem_attributes(struct kvm *kvm) /* * Returns true if _all_ gfns in the range [@start, @end) have attributes - * matching @attrs. + * such that the bits in @mask match @attrs. */ bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end, - unsigned long attrs) + unsigned long mask, unsigned long attrs) { XA_STATE(xas, &kvm->mem_attr_array, start); - unsigned long mask = kvm_supported_mem_attributes(kvm); unsigned long index; void *entry; + mask &= kvm_supported_mem_attributes(kvm); if (attrs & ~mask) return false; if (end == start + 1) - return kvm_get_memory_attributes(kvm, start) == attrs; + return (kvm_get_memory_attributes(kvm, start) & mask) == attrs; guard(rcu)(); if (!attrs) @@ -2433,7 +2433,8 @@ bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end, entry = xas_next(&xas); } while (xas_retry(&xas, entry)); - if (xas.xa_index != index || xa_to_value(entry) != attrs) + if (xas.xa_index != index || + (xa_to_value(entry) & mask) != attrs) return false; } @@ -2532,7 +2533,7 @@ static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end, mutex_lock(&kvm->slots_lock); /* Nothing to do if the entire range as the desired attributes. */ - if (kvm_range_has_memory_attributes(kvm, start, end, attributes)) + if (kvm_range_has_memory_attributes(kvm, start, end, ~0, attributes)) goto out_unlock; /* -- cgit v1.2.3 From e4ee5447927377c55777b73fe497a2455a25f948 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 11 Jul 2024 18:27:55 -0400 Subject: KVM: guest_memfd: let kvm_gmem_populate() operate only on private gfns This check is currently performed by sev_gmem_post_populate(), but it applies to all callers of kvm_gmem_populate(): the point of the function is that the memory is being encrypted and some work has to be done on all the gfns in order to encrypt them. Therefore, check the KVM_MEMORY_ATTRIBUTE_PRIVATE attribute prior to invoking the callback, and stop the operation if a shared page is encountered. Because CONFIG_KVM_PRIVATE_MEM in principle does not require attributes, this makes kvm_gmem_populate() depend on CONFIG_KVM_GENERIC_PRIVATE_MEM (which does require them). Reviewed-by: Michael Roth Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/sev.c | 7 ------- include/linux/kvm_host.h | 2 ++ virt/kvm/guest_memfd.c | 12 ++++++++++++ 3 files changed, 14 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 752d2fff0f10..532df12b43c5 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2279,13 +2279,6 @@ static int sev_gmem_post_populate(struct kvm *kvm, gfn_t gfn_start, kvm_pfn_t pf bool assigned; int level; - if (!kvm_mem_is_private(kvm, gfn)) { - pr_debug("%s: Failed to ensure GFN 0x%llx has private memory attribute set\n", - __func__, gfn); - ret = -EINVAL; - goto err; - } - ret = snp_lookup_rmpentry((u64)pfn + i, &assigned, &level); if (ret || assigned) { pr_debug("%s: Failed to ensure GFN 0x%llx RMP entry is initial shared state, ret: %d assigned: %d\n", diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c223b97df03e..79a6b1a63027 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -2449,6 +2449,7 @@ static inline int kvm_gmem_get_pfn(struct kvm *kvm, int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order); #endif +#ifdef CONFIG_KVM_GENERIC_PRIVATE_MEM /** * kvm_gmem_populate() - Populate/prepare a GPA range with guest data * @@ -2475,6 +2476,7 @@ typedef int (*kvm_gmem_populate_cb)(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, long kvm_gmem_populate(struct kvm *kvm, gfn_t gfn, void __user *src, long npages, kvm_gmem_populate_cb post_populate, void *opaque); +#endif #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end); diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index 319ec491ca47..95e338a29910 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -612,6 +612,7 @@ out: } EXPORT_SYMBOL_GPL(kvm_gmem_get_pfn); +#ifdef CONFIG_KVM_GENERIC_PRIVATE_MEM long kvm_gmem_populate(struct kvm *kvm, gfn_t start_gfn, void __user *src, long npages, kvm_gmem_populate_cb post_populate, void *opaque) { @@ -665,11 +666,21 @@ long kvm_gmem_populate(struct kvm *kvm, gfn_t start_gfn, void __user *src, long (npages - i) < (1 << max_order)) max_order = 0; + ret = -EINVAL; + while (!kvm_range_has_memory_attributes(kvm, gfn, gfn + (1 << max_order), + KVM_MEMORY_ATTRIBUTE_PRIVATE, + KVM_MEMORY_ATTRIBUTE_PRIVATE)) { + if (!max_order) + goto put_folio_and_exit; + max_order--; + } + p = src ? src + i * PAGE_SIZE : NULL; ret = post_populate(kvm, gfn, pfn, p, max_order, opaque); if (!ret) folio_mark_uptodate(folio); +put_folio_and_exit: folio_put(folio); if (ret) break; @@ -681,3 +692,4 @@ long kvm_gmem_populate(struct kvm *kvm, gfn_t start_gfn, void __user *src, long return ret && !i ? ret : i; } EXPORT_SYMBOL_GPL(kvm_gmem_populate); +#endif -- cgit v1.2.3 From 23a55f4492fcf868d068da31a2cd30c15f46207d Mon Sep 17 00:00:00 2001 From: Ofir Gal Date: Thu, 18 Jul 2024 11:45:12 +0300 Subject: net: introduce helper sendpages_ok() Network drivers are using sendpage_ok() to check the first page of an iterator in order to disable MSG_SPLICE_PAGES. The iterator can represent list of contiguous pages. When MSG_SPLICE_PAGES is enabled skb_splice_from_iter() is being used, it requires all pages in the iterator to be sendable. Therefore it needs to check that each page is sendable. The patch introduces a helper sendpages_ok(), it returns true if all the contiguous pages are sendable. Drivers who want to send contiguous pages with MSG_SPLICE_PAGES may use this helper to check whether the page list is OK. If the helper does not return true, the driver should remove MSG_SPLICE_PAGES flag. Reviewed-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Signed-off-by: Ofir Gal Acked-by: Jakub Kicinski Link: https://lore.kernel.org/r/20240718084515.3833733-2-ofir.gal@volumez.com Signed-off-by: Jens Axboe --- include/linux/net.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 688320b79fcc..b75bc534c1b3 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -322,6 +322,25 @@ static inline bool sendpage_ok(struct page *page) return !PageSlab(page) && page_count(page) >= 1; } +/* + * Check sendpage_ok on contiguous pages. + */ +static inline bool sendpages_ok(struct page *page, size_t len, size_t offset) +{ + struct page *p = page + (offset >> PAGE_SHIFT); + size_t count = 0; + + while (count < len) { + if (!sendpage_ok(p)) + return false; + + p++; + count += PAGE_SIZE; + } + + return true; +} + int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len); int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg, -- cgit v1.2.3 From 1a251f52cfdc417c84411a056bc142cbd77baef4 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 28 Jul 2024 15:49:18 -0700 Subject: minmax: make generic MIN() and MAX() macros available everywhere This just standardizes the use of MIN() and MAX() macros, with the very traditional semantics. The goal is to use these for C constant expressions and for top-level / static initializers, and so be able to simplify the min()/max() macros. These macro names were used by various kernel code - they are very traditional, after all - and all such users have been fixed up, with a few different approaches: - trivial duplicated macro definitions have been removed Note that 'trivial' here means that it's obviously kernel code that already included all the major kernel headers, and thus gets the new generic MIN/MAX macros automatically. - non-trivial duplicated macro definitions are guarded with #ifndef This is the "yes, they define their own versions, but no, the include situation is not entirely obvious, and maybe they don't get the generic version automatically" case. - strange use case #1 A couple of drivers decided that the way they want to describe their versioning is with #define MAJ 1 #define MIN 2 #define DRV_VERSION __stringify(MAJ) "." __stringify(MIN) which adds zero value and I just did my Alexander the Great impersonation, and rewrote that pointless Gordian knot as #define DRV_VERSION "1.2" instead. - strange use case #2 A couple of drivers thought that it's a good idea to have a random 'MIN' or 'MAX' define for a value or index into a table, rather than the traditional macro that takes arguments. These values were re-written as C enum's instead. The new function-line macros only expand when followed by an open parenthesis, and thus don't clash with enum use. Happily, there weren't really all that many of these cases, and a lot of users already had the pattern of using '#ifndef' guarding (or in one case just using '#undef MIN') before defining their own private version that does the same thing. I left such cases alone. Cc: David Laight Cc: Lorenzo Stoakes Signed-off-by: Linus Torvalds --- arch/um/drivers/mconsole_user.c | 2 ++ drivers/edac/skx_common.h | 1 - drivers/gpu/drm/amd/display/dc/core/dc_stream.c | 2 ++ .../gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c | 2 ++ drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppevvmath.h | 14 +++++++++---- drivers/gpu/drm/radeon/evergreen_cs.c | 2 ++ drivers/hwmon/adt7475.c | 24 +++++++++++----------- drivers/media/dvb-frontends/stv0367_priv.h | 3 +++ drivers/net/fjes/fjes_main.c | 4 +--- drivers/nfc/pn544/i2c.c | 2 -- drivers/platform/x86/sony-laptop.c | 1 - drivers/scsi/isci/init.c | 6 +----- .../pci/hive_isp_css_include/math_support.h | 5 ----- include/linux/minmax.h | 2 ++ kernel/trace/preemptirq_delay_test.c | 2 -- lib/btree.c | 1 - lib/decompress_unlzma.c | 2 ++ mm/zsmalloc.c | 2 -- tools/testing/selftests/mm/mremap_test.c | 2 ++ tools/testing/selftests/seccomp/seccomp_bpf.c | 2 ++ 20 files changed, 43 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/arch/um/drivers/mconsole_user.c b/arch/um/drivers/mconsole_user.c index e24298a734be..a04cd13c6315 100644 --- a/arch/um/drivers/mconsole_user.c +++ b/arch/um/drivers/mconsole_user.c @@ -71,7 +71,9 @@ static struct mconsole_command *mconsole_parse(struct mc_request *req) return NULL; } +#ifndef MIN #define MIN(a,b) ((a)<(b) ? (a):(b)) +#endif #define STRINGX(x) #x #define STRING(x) STRINGX(x) diff --git a/drivers/edac/skx_common.h b/drivers/edac/skx_common.h index 11faf1db4fa4..473421ba7a18 100644 --- a/drivers/edac/skx_common.h +++ b/drivers/edac/skx_common.h @@ -45,7 +45,6 @@ #define I10NM_NUM_CHANNELS MAX(I10NM_NUM_DDR_CHANNELS, I10NM_NUM_HBM_CHANNELS) #define I10NM_NUM_DIMMS MAX(I10NM_NUM_DDR_DIMMS, I10NM_NUM_HBM_DIMMS) -#define MAX(a, b) ((a) > (b) ? (a) : (b)) #define NUM_IMC MAX(SKX_NUM_IMC, I10NM_NUM_IMC) #define NUM_CHANNELS MAX(SKX_NUM_CHANNELS, I10NM_NUM_CHANNELS) #define NUM_DIMMS MAX(SKX_NUM_DIMMS, I10NM_NUM_DIMMS) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c index be2638c763d7..9a406d74c0dd 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -35,8 +35,10 @@ #include "dc_stream_priv.h" #define DC_LOGGER dc->ctx->logger +#ifndef MIN #define MIN(X, Y) ((X) < (Y) ? (X) : (Y)) #define MAX(x, y) ((x > y) ? x : y) +#endif /******************************************************************************* * Private functions diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c index 7ecf76aea950..6e064e6ae949 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c @@ -25,7 +25,9 @@ #include "hdcp.h" +#ifndef MIN #define MIN(a, b) ((a) < (b) ? (a) : (b)) +#endif #define HDCP_I2C_ADDR 0x3a /* 0x74 >> 1*/ #define KSV_READ_SIZE 0xf /* 0x6803b - 0x6802c */ #define HDCP_MAX_AUX_TRANSACTION_SIZE 16 diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppevvmath.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppevvmath.h index 6f54c410c2f9..409aeec6baa9 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppevvmath.h +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppevvmath.h @@ -22,12 +22,18 @@ */ #include -#define SHIFT_AMOUNT 16 /* We multiply all original integers with 2^SHIFT_AMOUNT to get the fInt representation */ +enum ppevvmath_constants { + /* We multiply all original integers with 2^SHIFT_AMOUNT to get the fInt representation */ + SHIFT_AMOUNT = 16, -#define PRECISION 5 /* Change this value to change the number of decimal places in the final output - 5 is a good default */ + /* Change this value to change the number of decimal places in the final output - 5 is a good default */ + PRECISION = 5, -#define SHIFTED_2 (2 << SHIFT_AMOUNT) -#define MAX (1 << (SHIFT_AMOUNT - 1)) - 1 /* 32767 - Might change in the future */ + SHIFTED_2 = (2 << SHIFT_AMOUNT), + + /* 32767 - Might change in the future */ + MAX = (1 << (SHIFT_AMOUNT - 1)) - 1, +}; /* ------------------------------------------------------------------------------- * NEW TYPE - fINT diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c index 1fe6e0d883c7..e5577d2a19ef 100644 --- a/drivers/gpu/drm/radeon/evergreen_cs.c +++ b/drivers/gpu/drm/radeon/evergreen_cs.c @@ -33,8 +33,10 @@ #include "evergreen_reg_safe.h" #include "cayman_reg_safe.h" +#ifndef MIN #define MAX(a, b) (((a) > (b)) ? (a) : (b)) #define MIN(a, b) (((a) < (b)) ? (a) : (b)) +#endif #define REG_SAFE_BM_SIZE ARRAY_SIZE(evergreen_reg_safe_bm) diff --git a/drivers/hwmon/adt7475.c b/drivers/hwmon/adt7475.c index bc186c61a2c0..382a2bb9168a 100644 --- a/drivers/hwmon/adt7475.c +++ b/drivers/hwmon/adt7475.c @@ -22,23 +22,23 @@ #include /* Indexes for the sysfs hooks */ - -#define INPUT 0 -#define MIN 1 -#define MAX 2 -#define CONTROL 3 -#define OFFSET 3 -#define AUTOMIN 4 -#define THERM 5 -#define HYSTERSIS 6 - +enum adt_sysfs_id { + INPUT = 0, + MIN = 1, + MAX = 2, + CONTROL = 3, + OFFSET = 3, // Dup + AUTOMIN = 4, + THERM = 5, + HYSTERSIS = 6, /* * These are unique identifiers for the sysfs functions - unlike the * numbers above, these are not also indexes into an array */ + ALARM = 9, + FAULT = 10, +}; -#define ALARM 9 -#define FAULT 10 /* 7475 Common Registers */ diff --git a/drivers/media/dvb-frontends/stv0367_priv.h b/drivers/media/dvb-frontends/stv0367_priv.h index 617f605947b2..7f056d1cce82 100644 --- a/drivers/media/dvb-frontends/stv0367_priv.h +++ b/drivers/media/dvb-frontends/stv0367_priv.h @@ -25,8 +25,11 @@ #endif /* MACRO definitions */ +#ifndef MIN #define MAX(X, Y) ((X) >= (Y) ? (X) : (Y)) #define MIN(X, Y) ((X) <= (Y) ? (X) : (Y)) +#endif + #define INRANGE(X, Y, Z) \ ((((X) <= (Y)) && ((Y) <= (Z))) || \ (((Z) <= (Y)) && ((Y) <= (X))) ? 1 : 0) diff --git a/drivers/net/fjes/fjes_main.c b/drivers/net/fjes/fjes_main.c index b3ddc9a629d9..fad5b6564464 100644 --- a/drivers/net/fjes/fjes_main.c +++ b/drivers/net/fjes/fjes_main.c @@ -14,9 +14,7 @@ #include "fjes.h" #include "fjes_trace.h" -#define MAJ 1 -#define MIN 2 -#define DRV_VERSION __stringify(MAJ) "." __stringify(MIN) +#define DRV_VERSION "1.2" #define DRV_NAME "fjes" char fjes_driver_name[] = DRV_NAME; char fjes_driver_version[] = DRV_VERSION; diff --git a/drivers/nfc/pn544/i2c.c b/drivers/nfc/pn544/i2c.c index 9fe664960b38..e2a6575b9ff7 100644 --- a/drivers/nfc/pn544/i2c.c +++ b/drivers/nfc/pn544/i2c.c @@ -126,8 +126,6 @@ struct pn544_i2c_fw_secure_blob { #define PN544_FW_CMD_RESULT_COMMAND_REJECTED 0xE0 #define PN544_FW_CMD_RESULT_CHUNK_ERROR 0xE6 -#define MIN(X, Y) ((X) < (Y) ? (X) : (Y)) - #define PN544_FW_WRITE_BUFFER_MAX_LEN 0x9f7 #define PN544_FW_I2C_MAX_PAYLOAD PN544_HCI_I2C_LLC_MAX_SIZE #define PN544_FW_I2C_WRITE_FRAME_HEADER_LEN 8 diff --git a/drivers/platform/x86/sony-laptop.c b/drivers/platform/x86/sony-laptop.c index 3e94fdd1ea52..3197aaa69da7 100644 --- a/drivers/platform/x86/sony-laptop.c +++ b/drivers/platform/x86/sony-laptop.c @@ -757,7 +757,6 @@ static union acpi_object *__call_snc_method(acpi_handle handle, char *method, return result; } -#define MIN(a, b) (a > b ? b : a) static int sony_nc_buffer_call(acpi_handle handle, char *name, u64 *value, void *buffer, size_t buflen) { diff --git a/drivers/scsi/isci/init.c b/drivers/scsi/isci/init.c index d31884f82f2a..73085d2f5c43 100644 --- a/drivers/scsi/isci/init.c +++ b/drivers/scsi/isci/init.c @@ -65,11 +65,7 @@ #include "task.h" #include "probe_roms.h" -#define MAJ 1 -#define MIN 2 -#define BUILD 0 -#define DRV_VERSION __stringify(MAJ) "." __stringify(MIN) "." \ - __stringify(BUILD) +#define DRV_VERSION "1.2.0" MODULE_VERSION(DRV_VERSION); diff --git a/drivers/staging/media/atomisp/pci/hive_isp_css_include/math_support.h b/drivers/staging/media/atomisp/pci/hive_isp_css_include/math_support.h index 7349943bba2b..160c496784b7 100644 --- a/drivers/staging/media/atomisp/pci/hive_isp_css_include/math_support.h +++ b/drivers/staging/media/atomisp/pci/hive_isp_css_include/math_support.h @@ -22,11 +22,6 @@ /* force a value to a lower even value */ #define EVEN_FLOOR(x) ((x) & ~1) -/* for preprocessor and array sizing use MIN and MAX - otherwise use min and max */ -#define MAX(a, b) (((a) > (b)) ? (a) : (b)) -#define MIN(a, b) (((a) < (b)) ? (a) : (b)) - #define CEIL_DIV(a, b) (((b) != 0) ? ((a) + (b) - 1) / (b) : 0) #define CEIL_MUL(a, b) (CEIL_DIV(a, b) * (b)) #define CEIL_MUL2(a, b) (((a) + (b) - 1) & ~((b) - 1)) diff --git a/include/linux/minmax.h b/include/linux/minmax.h index 9c2848abc804..fc384714da45 100644 --- a/include/linux/minmax.h +++ b/include/linux/minmax.h @@ -277,6 +277,8 @@ static inline bool in_range32(u32 val, u32 start, u32 len) * Use these carefully: no type checking, and uses the arguments * multiple times. Use for obvious constants only. */ +#define MIN(a,b) __cmp(min,a,b) +#define MAX(a,b) __cmp(max,a,b) #define MIN_T(type,a,b) __cmp(min,(type)(a),(type)(b)) #define MAX_T(type,a,b) __cmp(max,(type)(a),(type)(b)) diff --git a/kernel/trace/preemptirq_delay_test.c b/kernel/trace/preemptirq_delay_test.c index cb0871fbdb07..314ffc143039 100644 --- a/kernel/trace/preemptirq_delay_test.c +++ b/kernel/trace/preemptirq_delay_test.c @@ -34,8 +34,6 @@ MODULE_PARM_DESC(cpu_affinity, "Cpu num test is running on"); static struct completion done; -#define MIN(x, y) ((x) < (y) ? (x) : (y)) - static void busy_wait(ulong time) { u64 start, end; diff --git a/lib/btree.c b/lib/btree.c index 49420cae3a83..bb81d3393ac5 100644 --- a/lib/btree.c +++ b/lib/btree.c @@ -43,7 +43,6 @@ #include #include -#define MAX(a, b) ((a) > (b) ? (a) : (b)) #define NODESIZE MAX(L1_CACHE_BYTES, 128) struct btree_geo { diff --git a/lib/decompress_unlzma.c b/lib/decompress_unlzma.c index 20a858031f12..9d34d35908da 100644 --- a/lib/decompress_unlzma.c +++ b/lib/decompress_unlzma.c @@ -37,7 +37,9 @@ #include +#ifndef MIN #define MIN(a, b) (((a) < (b)) ? (a) : (b)) +#endif static long long INIT read_int(unsigned char *ptr, int size) { diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 5d6581ab7c07..2d3163e4da96 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -120,8 +120,6 @@ #define CLASS_BITS 8 #define MAGIC_VAL_BITS 8 -#define MAX(a, b) ((a) >= (b) ? (a) : (b)) - #define ZS_MAX_PAGES_PER_ZSPAGE (_AC(CONFIG_ZSMALLOC_CHAIN_SIZE, UL)) /* ZS_MIN_ALLOC_SIZE must be multiple of ZS_ALIGN */ diff --git a/tools/testing/selftests/mm/mremap_test.c b/tools/testing/selftests/mm/mremap_test.c index 1b03bcfaefdf..5a3a9bcba640 100644 --- a/tools/testing/selftests/mm/mremap_test.c +++ b/tools/testing/selftests/mm/mremap_test.c @@ -22,8 +22,10 @@ #define VALIDATION_DEFAULT_THRESHOLD 4 /* 4MB */ #define VALIDATION_NO_THRESHOLD 0 /* Verify the entire region */ +#ifndef MIN #define MIN(X, Y) ((X) < (Y) ? (X) : (Y)) #define MAX(X, Y) ((X) > (Y) ? (X) : (Y)) +#endif #define SIZE_MB(m) ((size_t)m * (1024 * 1024)) #define SIZE_KB(k) ((size_t)k * 1024) diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index e3f97f90d8db..8c3a73461475 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -60,7 +60,9 @@ #define SKIP(s, ...) XFAIL(s, ##__VA_ARGS__) #endif +#ifndef MIN #define MIN(X, Y) ((X) < (Y) ? (X) : (Y)) +#endif #ifndef PR_SET_PTRACER # define PR_SET_PTRACER 0x59616d61 -- cgit v1.2.3 From 320f6693097bf89d67f9cabad24a2b911e23073f Mon Sep 17 00:00:00 2001 From: Marcelo Schmitt Date: Fri, 12 Jul 2024 16:21:03 -0300 Subject: spi: bitbang: Implement support for MOSI idle state configuration Some SPI peripherals may require strict MOSI line state when the controller is not clocking out data. Implement support for MOSI idle state configuration (low or high) by setting the data output line level on controller setup and after transfers. Bitbang operations now call controller specific set_mosi_idle() callback to set MOSI to its idle state. The MOSI line is kept at its idle state if no tx buffer is provided. Acked-by: Nuno Sa Reviewed-by: David Lechner Reviewed-by: Jonathan Cameron Signed-off-by: Marcelo Schmitt Link: https://patch.msgid.link/de61a600b56ed9cb714d5ea87afa88948e70041e.1720810545.git.marcelo.schmitt@analog.com Signed-off-by: Mark Brown --- drivers/spi/spi-bitbang.c | 24 ++++++++++++++++++++++++ include/linux/spi/spi_bitbang.h | 1 + 2 files changed, 25 insertions(+) (limited to 'include/linux') diff --git a/drivers/spi/spi-bitbang.c b/drivers/spi/spi-bitbang.c index afb1b1105ec2..ebe18f0b5d23 100644 --- a/drivers/spi/spi-bitbang.c +++ b/drivers/spi/spi-bitbang.c @@ -54,21 +54,28 @@ static unsigned int bitbang_txrx_8(struct spi_device *spi, struct spi_transfer *t, unsigned int flags) { + struct spi_bitbang *bitbang; unsigned int bits = t->bits_per_word; unsigned int count = t->len; const u8 *tx = t->tx_buf; u8 *rx = t->rx_buf; + bitbang = spi_controller_get_devdata(spi->controller); while (likely(count > 0)) { u8 word = 0; if (tx) word = *tx++; + else + word = spi->mode & SPI_MOSI_IDLE_HIGH ? 0xFF : 0; word = txrx_word(spi, ns, word, bits, flags); if (rx) *rx++ = word; count -= 1; } + if (bitbang->set_mosi_idle) + bitbang->set_mosi_idle(spi); + return t->len - count; } @@ -78,21 +85,28 @@ static unsigned int bitbang_txrx_16(struct spi_device *spi, struct spi_transfer *t, unsigned int flags) { + struct spi_bitbang *bitbang; unsigned int bits = t->bits_per_word; unsigned int count = t->len; const u16 *tx = t->tx_buf; u16 *rx = t->rx_buf; + bitbang = spi_controller_get_devdata(spi->controller); while (likely(count > 1)) { u16 word = 0; if (tx) word = *tx++; + else + word = spi->mode & SPI_MOSI_IDLE_HIGH ? 0xFFFF : 0; word = txrx_word(spi, ns, word, bits, flags); if (rx) *rx++ = word; count -= 2; } + if (bitbang->set_mosi_idle) + bitbang->set_mosi_idle(spi); + return t->len - count; } @@ -102,21 +116,28 @@ static unsigned int bitbang_txrx_32(struct spi_device *spi, struct spi_transfer *t, unsigned int flags) { + struct spi_bitbang *bitbang; unsigned int bits = t->bits_per_word; unsigned int count = t->len; const u32 *tx = t->tx_buf; u32 *rx = t->rx_buf; + bitbang = spi_controller_get_devdata(spi->controller); while (likely(count > 3)) { u32 word = 0; if (tx) word = *tx++; + else + word = spi->mode & SPI_MOSI_IDLE_HIGH ? 0xFFFFFFFF : 0; word = txrx_word(spi, ns, word, bits, flags); if (rx) *rx++ = word; count -= 4; } + if (bitbang->set_mosi_idle) + bitbang->set_mosi_idle(spi); + return t->len - count; } @@ -192,6 +213,9 @@ int spi_bitbang_setup(struct spi_device *spi) goto err_free; } + if (bitbang->set_mosi_idle) + bitbang->set_mosi_idle(spi); + dev_dbg(&spi->dev, "%s, %u nsec/bit\n", __func__, 2 * cs->nsecs); return 0; diff --git a/include/linux/spi/spi_bitbang.h b/include/linux/spi/spi_bitbang.h index d4cb83195f7a..c92cd43a47f4 100644 --- a/include/linux/spi/spi_bitbang.h +++ b/include/linux/spi/spi_bitbang.h @@ -24,6 +24,7 @@ struct spi_bitbang { #define BITBANG_CS_ACTIVE 1 /* normally nCS, active low */ #define BITBANG_CS_INACTIVE 0 + void (*set_mosi_idle)(struct spi_device *spi); /* txrx_bufs() may handle dma mapping for transfers that don't * already have one (transfer.{tx,rx}_dma is zero), or use PIO */ -- cgit v1.2.3 From d65d411c9259a2499081e1e7ed91088232666b57 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Tue, 25 Jul 2023 12:08:50 +0100 Subject: treewide: context_tracking: Rename CONTEXT_* into CT_STATE_* Context tracking state related symbols currently use a mix of the CONTEXT_ (e.g. CONTEXT_KERNEL) and CT_SATE_ (e.g. CT_STATE_MASK) prefixes. Clean up the naming and make the ctx_state enum use the CT_STATE_ prefix. Suggested-by: Frederic Weisbecker Signed-off-by: Valentin Schneider Acked-by: Frederic Weisbecker Acked-by: Thomas Gleixner Signed-off-by: Neeraj Upadhyay --- arch/Kconfig | 2 +- arch/arm64/kernel/entry-common.c | 2 +- arch/powerpc/include/asm/interrupt.h | 6 +++--- arch/powerpc/kernel/interrupt.c | 6 +++--- arch/powerpc/kernel/syscall.c | 2 +- arch/x86/entry/common.c | 2 +- include/linux/context_tracking.h | 16 ++++++++-------- include/linux/context_tracking_state.h | 20 ++++++++++---------- include/linux/entry-common.h | 2 +- kernel/context_tracking.c | 12 ++++++------ kernel/entry/common.c | 2 +- kernel/sched/core.c | 4 ++-- 12 files changed, 38 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/arch/Kconfig b/arch/Kconfig index 975dd22a2dbd..4e2eaba9e305 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -862,7 +862,7 @@ config HAVE_CONTEXT_TRACKING_USER_OFFSTACK Architecture neither relies on exception_enter()/exception_exit() nor on schedule_user(). Also preempt_schedule_notrace() and preempt_schedule_irq() can't be called in a preemptible section - while context tracking is CONTEXT_USER. This feature reflects a sane + while context tracking is CT_STATE_USER. This feature reflects a sane entry implementation where the following requirements are met on critical entry code, ie: before user_exit() or after user_enter(): diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index b77a15955f28..3fcd9d080bf2 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -103,7 +103,7 @@ static void noinstr exit_to_kernel_mode(struct pt_regs *regs) static __always_inline void __enter_from_user_mode(void) { lockdep_hardirqs_off(CALLER_ADDR0); - CT_WARN_ON(ct_state() != CONTEXT_USER); + CT_WARN_ON(ct_state() != CT_STATE_USER); user_exit_irqoff(); trace_hardirqs_off_finish(); mte_disable_tco_entry(current); diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h index 2d6c886b40f4..23638d4e73ac 100644 --- a/arch/powerpc/include/asm/interrupt.h +++ b/arch/powerpc/include/asm/interrupt.h @@ -177,7 +177,7 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs) if (user_mode(regs)) { kuap_lock(); - CT_WARN_ON(ct_state() != CONTEXT_USER); + CT_WARN_ON(ct_state() != CT_STATE_USER); user_exit_irqoff(); account_cpu_user_entry(); @@ -189,8 +189,8 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs) * so avoid recursion. */ if (TRAP(regs) != INTERRUPT_PROGRAM) - CT_WARN_ON(ct_state() != CONTEXT_KERNEL && - ct_state() != CONTEXT_IDLE); + CT_WARN_ON(ct_state() != CT_STATE_KERNEL && + ct_state() != CT_STATE_IDLE); INT_SOFT_MASK_BUG_ON(regs, is_implicit_soft_masked(regs)); INT_SOFT_MASK_BUG_ON(regs, arch_irq_disabled_regs(regs) && search_kernel_restart_table(regs->nip)); diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c index eca293794a1e..af62ec974b97 100644 --- a/arch/powerpc/kernel/interrupt.c +++ b/arch/powerpc/kernel/interrupt.c @@ -266,7 +266,7 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3, unsigned long ret = 0; bool is_not_scv = !IS_ENABLED(CONFIG_PPC_BOOK3S_64) || !scv; - CT_WARN_ON(ct_state() == CONTEXT_USER); + CT_WARN_ON(ct_state() == CT_STATE_USER); kuap_assert_locked(); @@ -344,7 +344,7 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs) BUG_ON(regs_is_unrecoverable(regs)); BUG_ON(arch_irq_disabled_regs(regs)); - CT_WARN_ON(ct_state() == CONTEXT_USER); + CT_WARN_ON(ct_state() == CT_STATE_USER); /* * We don't need to restore AMR on the way back to userspace for KUAP. @@ -386,7 +386,7 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs) if (!IS_ENABLED(CONFIG_PPC_BOOK3E_64) && TRAP(regs) != INTERRUPT_PROGRAM && TRAP(regs) != INTERRUPT_PERFMON) - CT_WARN_ON(ct_state() == CONTEXT_USER); + CT_WARN_ON(ct_state() == CT_STATE_USER); kuap = kuap_get_and_assert_locked(); diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c index f6f868e817e6..be159ad4b77b 100644 --- a/arch/powerpc/kernel/syscall.c +++ b/arch/powerpc/kernel/syscall.c @@ -27,7 +27,7 @@ notrace long system_call_exception(struct pt_regs *regs, unsigned long r0) trace_hardirqs_off(); /* finish reconciling */ - CT_WARN_ON(ct_state() == CONTEXT_KERNEL); + CT_WARN_ON(ct_state() == CT_STATE_KERNEL); user_exit_irqoff(); BUG_ON(regs_is_unrecoverable(regs)); diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 51cc9c7cb9bd..94941c5a10ac 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -150,7 +150,7 @@ early_param("ia32_emulation", ia32_emulation_override_cmdline); #endif /* - * Invoke a 32-bit syscall. Called with IRQs on in CONTEXT_KERNEL. + * Invoke a 32-bit syscall. Called with IRQs on in CT_STATE_KERNEL. */ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, int nr) { diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 6e76b9dba00e..28fcfa184903 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -26,26 +26,26 @@ extern void user_exit_callable(void); static inline void user_enter(void) { if (context_tracking_enabled()) - ct_user_enter(CONTEXT_USER); + ct_user_enter(CT_STATE_USER); } static inline void user_exit(void) { if (context_tracking_enabled()) - ct_user_exit(CONTEXT_USER); + ct_user_exit(CT_STATE_USER); } /* Called with interrupts disabled. */ static __always_inline void user_enter_irqoff(void) { if (context_tracking_enabled()) - __ct_user_enter(CONTEXT_USER); + __ct_user_enter(CT_STATE_USER); } static __always_inline void user_exit_irqoff(void) { if (context_tracking_enabled()) - __ct_user_exit(CONTEXT_USER); + __ct_user_exit(CT_STATE_USER); } static inline enum ctx_state exception_enter(void) @@ -57,7 +57,7 @@ static inline enum ctx_state exception_enter(void) return 0; prev_ctx = __ct_state(); - if (prev_ctx != CONTEXT_KERNEL) + if (prev_ctx != CT_STATE_KERNEL) ct_user_exit(prev_ctx); return prev_ctx; @@ -67,7 +67,7 @@ static inline void exception_exit(enum ctx_state prev_ctx) { if (!IS_ENABLED(CONFIG_HAVE_CONTEXT_TRACKING_USER_OFFSTACK) && context_tracking_enabled()) { - if (prev_ctx != CONTEXT_KERNEL) + if (prev_ctx != CT_STATE_KERNEL) ct_user_enter(prev_ctx); } } @@ -75,7 +75,7 @@ static inline void exception_exit(enum ctx_state prev_ctx) static __always_inline bool context_tracking_guest_enter(void) { if (context_tracking_enabled()) - __ct_user_enter(CONTEXT_GUEST); + __ct_user_enter(CT_STATE_GUEST); return context_tracking_enabled_this_cpu(); } @@ -83,7 +83,7 @@ static __always_inline bool context_tracking_guest_enter(void) static __always_inline void context_tracking_guest_exit(void) { if (context_tracking_enabled()) - __ct_user_exit(CONTEXT_GUEST); + __ct_user_exit(CT_STATE_GUEST); } #define CT_WARN_ON(cond) WARN_ON(context_tracking_enabled() && (cond)) diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index bbff5f7f8803..f1c53125edee 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -10,18 +10,18 @@ #define DYNTICK_IRQ_NONIDLE ((LONG_MAX / 2) + 1) enum ctx_state { - CONTEXT_DISABLED = -1, /* returned by ct_state() if unknown */ - CONTEXT_KERNEL = 0, - CONTEXT_IDLE = 1, - CONTEXT_USER = 2, - CONTEXT_GUEST = 3, - CONTEXT_MAX = 4, + CT_STATE_DISABLED = -1, /* returned by ct_state() if unknown */ + CT_STATE_KERNEL = 0, + CT_STATE_IDLE = 1, + CT_STATE_USER = 2, + CT_STATE_GUEST = 3, + CT_STATE_MAX = 4, }; /* Even value for idle, else odd. */ -#define RCU_DYNTICKS_IDX CONTEXT_MAX +#define RCU_DYNTICKS_IDX CT_STATE_MAX -#define CT_STATE_MASK (CONTEXT_MAX - 1) +#define CT_STATE_MASK (CT_STATE_MAX - 1) #define CT_DYNTICKS_MASK (~CT_STATE_MASK) struct context_tracking { @@ -123,14 +123,14 @@ static inline bool context_tracking_enabled_this_cpu(void) * * Returns the current cpu's context tracking state if context tracking * is enabled. If context tracking is disabled, returns - * CONTEXT_DISABLED. This should be used primarily for debugging. + * CT_STATE_DISABLED. This should be used primarily for debugging. */ static __always_inline int ct_state(void) { int ret; if (!context_tracking_enabled()) - return CONTEXT_DISABLED; + return CT_STATE_DISABLED; preempt_disable(); ret = __ct_state(); diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index b0fb775a600d..1e50cdb83ae5 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -108,7 +108,7 @@ static __always_inline void enter_from_user_mode(struct pt_regs *regs) arch_enter_from_user_mode(regs); lockdep_hardirqs_off(CALLER_ADDR0); - CT_WARN_ON(__ct_state() != CONTEXT_USER); + CT_WARN_ON(__ct_state() != CT_STATE_USER); user_exit_irqoff(); instrumentation_begin(); diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 24b1e1143260..4bb5751af994 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -317,7 +317,7 @@ void noinstr ct_nmi_enter(void) void noinstr ct_idle_enter(void) { WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !raw_irqs_disabled()); - ct_kernel_exit(false, RCU_DYNTICKS_IDX + CONTEXT_IDLE); + ct_kernel_exit(false, RCU_DYNTICKS_IDX + CT_STATE_IDLE); } EXPORT_SYMBOL_GPL(ct_idle_enter); @@ -335,7 +335,7 @@ void noinstr ct_idle_exit(void) unsigned long flags; raw_local_irq_save(flags); - ct_kernel_enter(false, RCU_DYNTICKS_IDX - CONTEXT_IDLE); + ct_kernel_enter(false, RCU_DYNTICKS_IDX - CT_STATE_IDLE); raw_local_irq_restore(flags); } EXPORT_SYMBOL_GPL(ct_idle_exit); @@ -485,7 +485,7 @@ void noinstr __ct_user_enter(enum ctx_state state) * user_exit() or ct_irq_enter(). Let's remove RCU's dependency * on the tick. */ - if (state == CONTEXT_USER) { + if (state == CT_STATE_USER) { instrumentation_begin(); trace_user_enter(0); vtime_user_enter(current); @@ -621,7 +621,7 @@ void noinstr __ct_user_exit(enum ctx_state state) * run a RCU read side critical section anytime. */ ct_kernel_enter(true, RCU_DYNTICKS_IDX - state); - if (state == CONTEXT_USER) { + if (state == CT_STATE_USER) { instrumentation_begin(); vtime_user_exit(current); trace_user_exit(0); @@ -634,12 +634,12 @@ void noinstr __ct_user_exit(enum ctx_state state) * In this we case we don't care about any concurrency/ordering. */ if (!IS_ENABLED(CONFIG_CONTEXT_TRACKING_IDLE)) - raw_atomic_set(&ct->state, CONTEXT_KERNEL); + raw_atomic_set(&ct->state, CT_STATE_KERNEL); } else { if (!IS_ENABLED(CONFIG_CONTEXT_TRACKING_IDLE)) { /* Tracking for vtime only, no concurrent RCU EQS accounting */ - raw_atomic_set(&ct->state, CONTEXT_KERNEL); + raw_atomic_set(&ct->state, CT_STATE_KERNEL); } else { /* * Tracking for vtime and RCU EQS. Make sure we don't race diff --git a/kernel/entry/common.c b/kernel/entry/common.c index 90843cc38588..5b6934e23c21 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -182,7 +182,7 @@ static void syscall_exit_to_user_mode_prepare(struct pt_regs *regs) unsigned long work = READ_ONCE(current_thread_info()->syscall_work); unsigned long nr = syscall_get_nr(current, regs); - CT_WARN_ON(ct_state() != CONTEXT_KERNEL); + CT_WARN_ON(ct_state() != CT_STATE_KERNEL); if (IS_ENABLED(CONFIG_PROVE_LOCKING)) { if (WARN(irqs_disabled(), "syscall %lu left IRQs disabled", nr)) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index a9f655025607..93a845fe8449 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5762,7 +5762,7 @@ static inline void schedule_debug(struct task_struct *prev, bool preempt) preempt_count_set(PREEMPT_DISABLED); } rcu_sleep_check(); - SCHED_WARN_ON(ct_state() == CONTEXT_USER); + SCHED_WARN_ON(ct_state() == CT_STATE_USER); profile_hit(SCHED_PROFILING, __builtin_return_address(0)); @@ -6658,7 +6658,7 @@ asmlinkage __visible void __sched schedule_user(void) * we find a better solution. * * NB: There are buggy callers of this function. Ideally we - * should warn if prev_state != CONTEXT_USER, but that will trigger + * should warn if prev_state != CT_STATE_USER, but that will trigger * too frequently to make sense yet. */ enum ctx_state prev_state = exception_enter(); -- cgit v1.2.3 From 4aa35e0db6d758e8f952ed30d7ac3117c376562c Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Tue, 25 Jul 2023 12:19:01 +0100 Subject: context_tracking, rcu: Rename RCU_DYNTICKS_IDX into CT_RCU_WATCHING The symbols relating to the CT_STATE part of context_tracking.state are now all prefixed with CT_STATE. The RCU dynticks counter part of that atomic variable still involves symbols with different prefixes, align them all to be prefixed with CT_RCU_WATCHING. Suggested-by: "Paul E. McKenney" Signed-off-by: Valentin Schneider Reviewed-by: Frederic Weisbecker Acked-by: Thomas Gleixner Signed-off-by: Neeraj Upadhyay --- include/linux/context_tracking.h | 6 +++--- include/linux/context_tracking_state.h | 12 ++++++------ kernel/context_tracking.c | 22 +++++++++++----------- kernel/rcu/tree.c | 12 ++++++------ 4 files changed, 26 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 28fcfa184903..a6c36780cc3b 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -119,7 +119,7 @@ extern void ct_idle_exit(void); */ static __always_inline bool rcu_dynticks_curr_cpu_in_eqs(void) { - return !(raw_atomic_read(this_cpu_ptr(&context_tracking.state)) & RCU_DYNTICKS_IDX); + return !(raw_atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_RCU_WATCHING); } /* @@ -142,7 +142,7 @@ static __always_inline bool warn_rcu_enter(void) preempt_disable_notrace(); if (rcu_dynticks_curr_cpu_in_eqs()) { ret = true; - ct_state_inc(RCU_DYNTICKS_IDX); + ct_state_inc(CT_RCU_WATCHING); } return ret; @@ -151,7 +151,7 @@ static __always_inline bool warn_rcu_enter(void) static __always_inline void warn_rcu_exit(bool rcu) { if (rcu) - ct_state_inc(RCU_DYNTICKS_IDX); + ct_state_inc(CT_RCU_WATCHING); preempt_enable_notrace(); } diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index f1c53125edee..94d6a935af3b 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -18,11 +18,11 @@ enum ctx_state { CT_STATE_MAX = 4, }; -/* Even value for idle, else odd. */ -#define RCU_DYNTICKS_IDX CT_STATE_MAX +/* Odd value for watching, else even. */ +#define CT_RCU_WATCHING CT_STATE_MAX #define CT_STATE_MASK (CT_STATE_MAX - 1) -#define CT_DYNTICKS_MASK (~CT_STATE_MASK) +#define CT_RCU_WATCHING_MASK (~CT_STATE_MASK) struct context_tracking { #ifdef CONFIG_CONTEXT_TRACKING_USER @@ -58,21 +58,21 @@ static __always_inline int __ct_state(void) #ifdef CONFIG_CONTEXT_TRACKING_IDLE static __always_inline int ct_dynticks(void) { - return atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_DYNTICKS_MASK; + return atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_RCU_WATCHING_MASK; } static __always_inline int ct_dynticks_cpu(int cpu) { struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); - return atomic_read(&ct->state) & CT_DYNTICKS_MASK; + return atomic_read(&ct->state) & CT_RCU_WATCHING_MASK; } static __always_inline int ct_dynticks_cpu_acquire(int cpu) { struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); - return atomic_read_acquire(&ct->state) & CT_DYNTICKS_MASK; + return atomic_read_acquire(&ct->state) & CT_RCU_WATCHING_MASK; } static __always_inline long ct_dynticks_nesting(void) diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 4bb5751af994..b2589bc59e18 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -31,7 +31,7 @@ DEFINE_PER_CPU(struct context_tracking, context_tracking) = { .dynticks_nesting = 1, .dynticks_nmi_nesting = DYNTICK_IRQ_NONIDLE, #endif - .state = ATOMIC_INIT(RCU_DYNTICKS_IDX), + .state = ATOMIC_INIT(CT_RCU_WATCHING), }; EXPORT_SYMBOL_GPL(context_tracking); @@ -90,7 +90,7 @@ static noinstr void ct_kernel_exit_state(int offset) rcu_dynticks_task_trace_enter(); // Before ->dynticks update! seq = ct_state_inc(offset); // RCU is no longer watching. Better be in extended quiescent state! - WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && (seq & RCU_DYNTICKS_IDX)); + WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && (seq & CT_RCU_WATCHING)); } /* @@ -110,7 +110,7 @@ static noinstr void ct_kernel_enter_state(int offset) seq = ct_state_inc(offset); // RCU is now watching. Better not be in an extended quiescent state! rcu_dynticks_task_trace_exit(); // After ->dynticks update! - WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !(seq & RCU_DYNTICKS_IDX)); + WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !(seq & CT_RCU_WATCHING)); } /* @@ -236,7 +236,7 @@ void noinstr ct_nmi_exit(void) instrumentation_end(); // RCU is watching here ... - ct_kernel_exit_state(RCU_DYNTICKS_IDX); + ct_kernel_exit_state(CT_RCU_WATCHING); // ... but is no longer watching here. if (!in_nmi()) @@ -277,7 +277,7 @@ void noinstr ct_nmi_enter(void) rcu_dynticks_task_exit(); // RCU is not watching here ... - ct_kernel_enter_state(RCU_DYNTICKS_IDX); + ct_kernel_enter_state(CT_RCU_WATCHING); // ... but is watching here. instrumentation_begin(); @@ -317,7 +317,7 @@ void noinstr ct_nmi_enter(void) void noinstr ct_idle_enter(void) { WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !raw_irqs_disabled()); - ct_kernel_exit(false, RCU_DYNTICKS_IDX + CT_STATE_IDLE); + ct_kernel_exit(false, CT_RCU_WATCHING + CT_STATE_IDLE); } EXPORT_SYMBOL_GPL(ct_idle_enter); @@ -335,7 +335,7 @@ void noinstr ct_idle_exit(void) unsigned long flags; raw_local_irq_save(flags); - ct_kernel_enter(false, RCU_DYNTICKS_IDX - CT_STATE_IDLE); + ct_kernel_enter(false, CT_RCU_WATCHING - CT_STATE_IDLE); raw_local_irq_restore(flags); } EXPORT_SYMBOL_GPL(ct_idle_exit); @@ -504,7 +504,7 @@ void noinstr __ct_user_enter(enum ctx_state state) * CPU doesn't need to maintain the tick for RCU maintenance purposes * when the CPU runs in userspace. */ - ct_kernel_exit(true, RCU_DYNTICKS_IDX + state); + ct_kernel_exit(true, CT_RCU_WATCHING + state); /* * Special case if we only track user <-> kernel transitions for tickless @@ -534,7 +534,7 @@ void noinstr __ct_user_enter(enum ctx_state state) /* * Tracking for vtime and RCU EQS. Make sure we don't race * with NMIs. OTOH we don't care about ordering here since - * RCU only requires RCU_DYNTICKS_IDX increments to be fully + * RCU only requires CT_RCU_WATCHING increments to be fully * ordered. */ raw_atomic_add(state, &ct->state); @@ -620,7 +620,7 @@ void noinstr __ct_user_exit(enum ctx_state state) * Exit RCU idle mode while entering the kernel because it can * run a RCU read side critical section anytime. */ - ct_kernel_enter(true, RCU_DYNTICKS_IDX - state); + ct_kernel_enter(true, CT_RCU_WATCHING - state); if (state == CT_STATE_USER) { instrumentation_begin(); vtime_user_exit(current); @@ -644,7 +644,7 @@ void noinstr __ct_user_exit(enum ctx_state state) /* * Tracking for vtime and RCU EQS. Make sure we don't race * with NMIs. OTOH we don't care about ordering here since - * RCU only requires RCU_DYNTICKS_IDX increments to be fully + * RCU only requires CT_RCU_WATCHING increments to be fully * ordered. */ raw_atomic_sub(state, &ct->state); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index e641cc681901..04f87c44385c 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -294,9 +294,9 @@ void rcu_softirq_qs(void) */ static void rcu_dynticks_eqs_online(void) { - if (ct_dynticks() & RCU_DYNTICKS_IDX) + if (ct_dynticks() & CT_RCU_WATCHING) return; - ct_state_inc(RCU_DYNTICKS_IDX); + ct_state_inc(CT_RCU_WATCHING); } /* @@ -305,7 +305,7 @@ static void rcu_dynticks_eqs_online(void) */ static bool rcu_dynticks_in_eqs(int snap) { - return !(snap & RCU_DYNTICKS_IDX); + return !(snap & CT_RCU_WATCHING); } /* @@ -335,7 +335,7 @@ bool rcu_dynticks_zero_in_eqs(int cpu, int *vp) int snap; // If not quiescent, force back to earlier extended quiescent state. - snap = ct_dynticks_cpu(cpu) & ~RCU_DYNTICKS_IDX; + snap = ct_dynticks_cpu(cpu) & ~CT_RCU_WATCHING; smp_rmb(); // Order ->dynticks and *vp reads. if (READ_ONCE(*vp)) return false; // Non-zero, so report failure; @@ -361,9 +361,9 @@ notrace void rcu_momentary_dyntick_idle(void) int seq; raw_cpu_write(rcu_data.rcu_need_heavy_qs, false); - seq = ct_state_inc(2 * RCU_DYNTICKS_IDX); + seq = ct_state_inc(2 * CT_RCU_WATCHING); /* It is illegal to call this from idle state. */ - WARN_ON_ONCE(!(seq & RCU_DYNTICKS_IDX)); + WARN_ON_ONCE(!(seq & CT_RCU_WATCHING)); rcu_preempt_deferred_qs(current); } EXPORT_SYMBOL_GPL(rcu_momentary_dyntick_idle); -- cgit v1.2.3 From a4a7921ec08d016f9d692752e2f82f66369c7ffa Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Tue, 16 Apr 2024 10:45:56 +0200 Subject: context_tracking, rcu: Rename ct_dynticks() into ct_rcu_watching() The context_tracking.state RCU_DYNTICKS subvariable has been renamed to RCU_WATCHING, reflect that change in the related helpers. Signed-off-by: Valentin Schneider Reviewed-by: Frederic Weisbecker Signed-off-by: Neeraj Upadhyay --- include/linux/context_tracking_state.h | 2 +- kernel/context_tracking.c | 10 +++++----- kernel/rcu/tree.c | 2 +- 3 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index 94d6a935af3b..cb90d8c17810 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -56,7 +56,7 @@ static __always_inline int __ct_state(void) #endif #ifdef CONFIG_CONTEXT_TRACKING_IDLE -static __always_inline int ct_dynticks(void) +static __always_inline int ct_rcu_watching(void) { return atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_RCU_WATCHING_MASK; } diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index b2589bc59e18..868ae0bcd4be 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -137,7 +137,7 @@ static void noinstr ct_kernel_exit(bool user, int offset) instrumentation_begin(); lockdep_assert_irqs_disabled(); - trace_rcu_dyntick(TPS("Start"), ct_dynticks_nesting(), 0, ct_dynticks()); + trace_rcu_dyntick(TPS("Start"), ct_dynticks_nesting(), 0, ct_rcu_watching()); WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current)); rcu_preempt_deferred_qs(current); @@ -182,7 +182,7 @@ static void noinstr ct_kernel_enter(bool user, int offset) // instrumentation for the noinstr ct_kernel_enter_state() instrument_atomic_write(&ct->state, sizeof(ct->state)); - trace_rcu_dyntick(TPS("End"), ct_dynticks_nesting(), 1, ct_dynticks()); + trace_rcu_dyntick(TPS("End"), ct_dynticks_nesting(), 1, ct_rcu_watching()); WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current)); WRITE_ONCE(ct->dynticks_nesting, 1); WARN_ON_ONCE(ct_dynticks_nmi_nesting()); @@ -220,7 +220,7 @@ void noinstr ct_nmi_exit(void) */ if (ct_dynticks_nmi_nesting() != 1) { trace_rcu_dyntick(TPS("--="), ct_dynticks_nmi_nesting(), ct_dynticks_nmi_nesting() - 2, - ct_dynticks()); + ct_rcu_watching()); WRITE_ONCE(ct->dynticks_nmi_nesting, /* No store tearing. */ ct_dynticks_nmi_nesting() - 2); instrumentation_end(); @@ -228,7 +228,7 @@ void noinstr ct_nmi_exit(void) } /* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */ - trace_rcu_dyntick(TPS("Startirq"), ct_dynticks_nmi_nesting(), 0, ct_dynticks()); + trace_rcu_dyntick(TPS("Startirq"), ct_dynticks_nmi_nesting(), 0, ct_rcu_watching()); WRITE_ONCE(ct->dynticks_nmi_nesting, 0); /* Avoid store tearing. */ // instrumentation for the noinstr ct_kernel_exit_state() @@ -296,7 +296,7 @@ void noinstr ct_nmi_enter(void) trace_rcu_dyntick(incby == 1 ? TPS("Endirq") : TPS("++="), ct_dynticks_nmi_nesting(), - ct_dynticks_nmi_nesting() + incby, ct_dynticks()); + ct_dynticks_nmi_nesting() + incby, ct_rcu_watching()); instrumentation_end(); WRITE_ONCE(ct->dynticks_nmi_nesting, /* Prevent store tearing. */ ct_dynticks_nmi_nesting() + incby); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 04f87c44385c..3a2f0325aa43 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -294,7 +294,7 @@ void rcu_softirq_qs(void) */ static void rcu_dynticks_eqs_online(void) { - if (ct_dynticks() & CT_RCU_WATCHING) + if (ct_rcu_watching() & CT_RCU_WATCHING) return; ct_state_inc(CT_RCU_WATCHING); } -- cgit v1.2.3 From a9fde9d1a5dd42edadf61cf4e64aa234b4c5bd3f Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Tue, 16 Apr 2024 10:47:14 +0200 Subject: context_tracking, rcu: Rename ct_dynticks_cpu() into ct_rcu_watching_cpu() The context_tracking.state RCU_DYNTICKS subvariable has been renamed to RCU_WATCHING, reflect that change in the related helpers. Signed-off-by: Valentin Schneider Reviewed-by: Frederic Weisbecker Signed-off-by: Neeraj Upadhyay --- include/linux/context_tracking_state.h | 2 +- kernel/rcu/tree.c | 10 +++++----- kernel/rcu/tree_stall.h | 4 ++-- 3 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index cb90d8c17810..ad5a06a42b4a 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -61,7 +61,7 @@ static __always_inline int ct_rcu_watching(void) return atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_RCU_WATCHING_MASK; } -static __always_inline int ct_dynticks_cpu(int cpu) +static __always_inline int ct_rcu_watching_cpu(int cpu) { struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 3a2f0325aa43..e7f612e9f7e5 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -335,14 +335,14 @@ bool rcu_dynticks_zero_in_eqs(int cpu, int *vp) int snap; // If not quiescent, force back to earlier extended quiescent state. - snap = ct_dynticks_cpu(cpu) & ~CT_RCU_WATCHING; - smp_rmb(); // Order ->dynticks and *vp reads. + snap = ct_rcu_watching_cpu(cpu) & ~CT_RCU_WATCHING; + smp_rmb(); // Order CT state and *vp reads. if (READ_ONCE(*vp)) return false; // Non-zero, so report failure; - smp_rmb(); // Order *vp read and ->dynticks re-read. + smp_rmb(); // Order *vp read and CT state re-read. // If still in the same extended quiescent state, we are good! - return snap == ct_dynticks_cpu(cpu); + return snap == ct_rcu_watching_cpu(cpu); } /* @@ -4805,7 +4805,7 @@ rcu_boot_init_percpu_data(int cpu) rdp->grpmask = leaf_node_cpu_bit(rdp->mynode, cpu); INIT_WORK(&rdp->strict_work, strict_work_handler); WARN_ON_ONCE(ct->dynticks_nesting != 1); - WARN_ON_ONCE(rcu_dynticks_in_eqs(ct_dynticks_cpu(cpu))); + WARN_ON_ONCE(rcu_dynticks_in_eqs(ct_rcu_watching_cpu(cpu))); rdp->barrier_seq_snap = rcu_state.barrier_sequence; rdp->rcu_ofl_gp_seq = rcu_state.gp_seq; rdp->rcu_ofl_gp_state = RCU_GP_CLEANED; diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index 4b0e9d7c4c68..d65974448e81 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -501,7 +501,7 @@ static void print_cpu_stall_info(int cpu) } delta = rcu_seq_ctr(rdp->mynode->gp_seq - rdp->rcu_iw_gp_seq); falsepositive = rcu_is_gp_kthread_starving(NULL) && - rcu_dynticks_in_eqs(ct_dynticks_cpu(cpu)); + rcu_dynticks_in_eqs(ct_rcu_watching_cpu(cpu)); rcuc_starved = rcu_is_rcuc_kthread_starving(rdp, &j); if (rcuc_starved) // Print signed value, as negative values indicate a probable bug. @@ -515,7 +515,7 @@ static void print_cpu_stall_info(int cpu) rdp->rcu_iw_pending ? (int)min(delta, 9UL) + '0' : "!."[!delta], ticks_value, ticks_title, - ct_dynticks_cpu(cpu) & 0xffff, + ct_rcu_watching_cpu(cpu) & 0xffff, ct_dynticks_nesting_cpu(cpu), ct_dynticks_nmi_nesting_cpu(cpu), rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu), data_race(rcu_state.n_force_qs) - rcu_state.n_force_qs_gpstart, -- cgit v1.2.3 From 125716c393889f9035567d4d78da239483f63ece Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Tue, 16 Apr 2024 14:47:12 +0200 Subject: context_tracking, rcu: Rename ct_dynticks_cpu_acquire() into ct_rcu_watching_cpu_acquire() The context_tracking.state RCU_DYNTICKS subvariable has been renamed to RCU_WATCHING, reflect that change in the related helpers. Signed-off-by: Valentin Schneider Reviewed-by: Frederic Weisbecker Signed-off-by: Neeraj Upadhyay --- Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst | 2 +- include/linux/context_tracking_state.h | 2 +- kernel/rcu/tree.c | 4 ++-- kernel/rcu/tree_exp.h | 2 +- 4 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst index 728b1e690c64..2d7036ad7476 100644 --- a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst +++ b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst @@ -149,7 +149,7 @@ This case is handled by calls to the strongly ordered ``atomic_add_return()`` read-modify-write atomic operation that is invoked within ``rcu_dynticks_eqs_enter()`` at idle-entry time and within ``rcu_dynticks_eqs_exit()`` at idle-exit time. -The grace-period kthread invokes first ``ct_dynticks_cpu_acquire()`` +The grace-period kthread invokes first ``ct_rcu_watching_cpu_acquire()`` (preceded by a full memory barrier) and ``rcu_dynticks_in_eqs_since()`` (both of which rely on acquire semantics) to detect idle CPUs. diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index ad5a06a42b4a..ad6570ffeff3 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -68,7 +68,7 @@ static __always_inline int ct_rcu_watching_cpu(int cpu) return atomic_read(&ct->state) & CT_RCU_WATCHING_MASK; } -static __always_inline int ct_dynticks_cpu_acquire(int cpu) +static __always_inline int ct_rcu_watching_cpu_acquire(int cpu) { struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index e7f612e9f7e5..45a9f3667c2a 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -323,7 +323,7 @@ static bool rcu_dynticks_in_eqs_since(struct rcu_data *rdp, int snap) * performed by the remote CPU prior to entering idle and therefore can * rely solely on acquire semantics. */ - return snap != ct_dynticks_cpu_acquire(rdp->cpu); + return snap != ct_rcu_watching_cpu_acquire(rdp->cpu); } /* @@ -782,7 +782,7 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp) * Ordering between remote CPU's pre idle accesses and post grace period * updater's accesses is enforced by the below acquire semantic. */ - rdp->dynticks_snap = ct_dynticks_cpu_acquire(rdp->cpu); + rdp->dynticks_snap = ct_rcu_watching_cpu_acquire(rdp->cpu); if (rcu_dynticks_in_eqs(rdp->dynticks_snap)) { trace_rcu_fqs(rcu_state.name, rdp->gp_seq, rdp->cpu, TPS("dti")); rcu_gpnum_ovf(rdp->mynode, rdp); diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index 4acd29d16fdb..daa87fec703f 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -376,7 +376,7 @@ static void __sync_rcu_exp_select_node_cpus(struct rcu_exp_work *rewp) * post grace period updater's accesses is enforced by the * below acquire semantic. */ - snap = ct_dynticks_cpu_acquire(cpu); + snap = ct_rcu_watching_cpu_acquire(cpu); if (rcu_dynticks_in_eqs(snap)) mask_ofl_test |= mask; else -- cgit v1.2.3 From 7aeba709a048d870c15940af8b620b16281c3b9e Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 30 May 2024 15:45:42 +0200 Subject: rcu/nocb: Introduce RCU_NOCB_LOCKDEP_WARN() Checking for races against concurrent (de-)offloading implies the creation of !CONFIG_RCU_NOCB_CPU stubs to check if each relevant lock is held. For now this only implies the nocb_lock but more are to be expected. Create instead a NOCB specific version of RCU_LOCKDEP_WARN() to avoid the proliferation of stubs. Signed-off-by: Frederic Weisbecker Signed-off-by: Paul E. McKenney Reviewed-by: Paul E. McKenney Signed-off-by: Neeraj Upadhyay --- include/linux/rcupdate.h | 7 +++++++ kernel/rcu/tree_nocb.h | 14 -------------- kernel/rcu/tree_plugin.h | 4 ++-- 3 files changed, 9 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 13f6f00aecf9..d48d3c237305 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -144,11 +144,18 @@ void rcu_init_nohz(void); int rcu_nocb_cpu_offload(int cpu); int rcu_nocb_cpu_deoffload(int cpu); void rcu_nocb_flush_deferred_wakeup(void); + +#define RCU_NOCB_LOCKDEP_WARN(c, s) RCU_LOCKDEP_WARN(c, s) + #else /* #ifdef CONFIG_RCU_NOCB_CPU */ + static inline void rcu_init_nohz(void) { } static inline int rcu_nocb_cpu_offload(int cpu) { return -EINVAL; } static inline int rcu_nocb_cpu_deoffload(int cpu) { return 0; } static inline void rcu_nocb_flush_deferred_wakeup(void) { } + +#define RCU_NOCB_LOCKDEP_WARN(c, s) + #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ /* diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h index 3ce30841119a..f4112fc663a7 100644 --- a/kernel/rcu/tree_nocb.h +++ b/kernel/rcu/tree_nocb.h @@ -16,10 +16,6 @@ #ifdef CONFIG_RCU_NOCB_CPU static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */ static bool __read_mostly rcu_nocb_poll; /* Offload kthread are to poll. */ -static inline int rcu_lockdep_is_held_nocb(struct rcu_data *rdp) -{ - return lockdep_is_held(&rdp->nocb_lock); -} static inline bool rcu_current_is_nocb_kthread(struct rcu_data *rdp) { @@ -1653,16 +1649,6 @@ static void show_rcu_nocb_state(struct rcu_data *rdp) #else /* #ifdef CONFIG_RCU_NOCB_CPU */ -static inline int rcu_lockdep_is_held_nocb(struct rcu_data *rdp) -{ - return 0; -} - -static inline bool rcu_current_is_nocb_kthread(struct rcu_data *rdp) -{ - return false; -} - /* No ->nocb_lock to acquire. */ static void rcu_nocb_lock(struct rcu_data *rdp) { diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index c569da65b421..f752b2a1d887 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -24,10 +24,10 @@ static bool rcu_rdp_is_offloaded(struct rcu_data *rdp) * timers have their own means of synchronization against the * offloaded state updaters. */ - RCU_LOCKDEP_WARN( + RCU_NOCB_LOCKDEP_WARN( !(lockdep_is_held(&rcu_state.barrier_mutex) || (IS_ENABLED(CONFIG_HOTPLUG_CPU) && lockdep_is_cpus_held()) || - rcu_lockdep_is_held_nocb(rdp) || + lockdep_is_held(&rdp->nocb_lock) || (!(IS_ENABLED(CONFIG_PREEMPT_COUNT) && preemptible()) && rdp == this_cpu_ptr(&rcu_data)) || rcu_current_is_nocb_kthread(rdp)), -- cgit v1.2.3 From bae6076ebbd14cc1f1bd4de65c2db21d3ab109d7 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 30 May 2024 15:45:50 +0200 Subject: rcu/nocb: Remove SEGCBLIST_RCU_CORE RCU core can't be running anymore while in the middle of (de-)offloading since this sort of transition now only applies to offline CPUs. The SEGCBLIST_RCU_CORE state can therefore be removed. Signed-off-by: Frederic Weisbecker Signed-off-by: Paul E. McKenney Reviewed-by: Paul E. McKenney Signed-off-by: Neeraj Upadhyay --- include/linux/rcu_segcblist.h | 9 ++++----- kernel/rcu/rcu_segcblist.h | 9 --------- kernel/rcu/tree.c | 3 --- kernel/rcu/tree_nocb.h | 9 --------- 4 files changed, 4 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcu_segcblist.h b/include/linux/rcu_segcblist.h index ba95c06675e1..5469c54cd778 100644 --- a/include/linux/rcu_segcblist.h +++ b/include/linux/rcu_segcblist.h @@ -185,11 +185,10 @@ struct rcu_cblist { * ---------------------------------------------------------------------------- */ #define SEGCBLIST_ENABLED BIT(0) -#define SEGCBLIST_RCU_CORE BIT(1) -#define SEGCBLIST_LOCKING BIT(2) -#define SEGCBLIST_KTHREAD_CB BIT(3) -#define SEGCBLIST_KTHREAD_GP BIT(4) -#define SEGCBLIST_OFFLOADED BIT(5) +#define SEGCBLIST_LOCKING BIT(1) +#define SEGCBLIST_KTHREAD_CB BIT(2) +#define SEGCBLIST_KTHREAD_GP BIT(3) +#define SEGCBLIST_OFFLOADED BIT(4) struct rcu_segcblist { struct rcu_head *head; diff --git a/kernel/rcu/rcu_segcblist.h b/kernel/rcu/rcu_segcblist.h index 4fe877f5f654..7a0962dfee86 100644 --- a/kernel/rcu/rcu_segcblist.h +++ b/kernel/rcu/rcu_segcblist.h @@ -95,15 +95,6 @@ static inline bool rcu_segcblist_is_offloaded(struct rcu_segcblist *rsclp) return false; } -static inline bool rcu_segcblist_completely_offloaded(struct rcu_segcblist *rsclp) -{ - if (IS_ENABLED(CONFIG_RCU_NOCB_CPU) && - !rcu_segcblist_test_flags(rsclp, SEGCBLIST_RCU_CORE)) - return true; - - return false; -} - /* * Are all segments following the specified segment of the specified * rcu_segcblist structure empty of callbacks? (The specified diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 1a272c678533..82e831b969e4 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -79,9 +79,6 @@ static void rcu_sr_normal_gp_cleanup_work(struct work_struct *); static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, rcu_data) = { .gpwrap = true, -#ifdef CONFIG_RCU_NOCB_CPU - .cblist.flags = SEGCBLIST_RCU_CORE, -#endif }; static struct rcu_state rcu_state = { .level = { &rcu_state.node[0] }, diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h index af44e75eb0cd..24daf606de0c 100644 --- a/kernel/rcu/tree_nocb.h +++ b/kernel/rcu/tree_nocb.h @@ -1060,7 +1060,6 @@ static int rcu_nocb_rdp_deoffload(struct rcu_data *rdp) WARN_ON_ONCE(rcu_cblist_n_cbs(&rdp->nocb_bypass)); WARN_ON_ONCE(rcu_segcblist_n_cbs(&rdp->cblist)); - rcu_segcblist_set_flags(cblist, SEGCBLIST_RCU_CORE); wake_gp = rdp_offload_toggle(rdp, false, flags); mutex_lock(&rdp_gp->nocb_gp_kthread_mutex); @@ -1168,13 +1167,6 @@ static int rcu_nocb_rdp_offload(struct rcu_data *rdp) swait_event_exclusive(rdp->nocb_state_wq, rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_GP)); - /* - * All kthreads are ready to work, we can finally enable nocb bypass. - */ - rcu_nocb_lock_irqsave(rdp, flags); - rcu_segcblist_clear_flags(cblist, SEGCBLIST_RCU_CORE); - rcu_nocb_unlock_irqrestore(rdp, flags); - return 0; } @@ -1350,7 +1342,6 @@ void __init rcu_init_nohz(void) rcu_segcblist_init(&rdp->cblist); rcu_segcblist_offload(&rdp->cblist, true); rcu_segcblist_set_flags(&rdp->cblist, SEGCBLIST_KTHREAD_GP); - rcu_segcblist_clear_flags(&rdp->cblist, SEGCBLIST_RCU_CORE); } rcu_organize_nocb_kthreads(); } -- cgit v1.2.3 From 91e43b9044a4f9b6976dc28b3f1446b733cc68de Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 30 May 2024 15:45:51 +0200 Subject: rcu/nocb: Remove SEGCBLIST_KTHREAD_CB This state excerpt from the (de-)offloading state machine was used to implement an ad-hoc kthread parking of rcuo kthreads. This code has been removed and therefore the related state can be erased as well. Signed-off-by: Frederic Weisbecker Signed-off-by: Paul E. McKenney Reviewed-by: Paul E. McKenney Signed-off-by: Neeraj Upadhyay --- include/linux/rcu_segcblist.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcu_segcblist.h b/include/linux/rcu_segcblist.h index 5469c54cd778..1ef1bb54853d 100644 --- a/include/linux/rcu_segcblist.h +++ b/include/linux/rcu_segcblist.h @@ -186,9 +186,8 @@ struct rcu_cblist { */ #define SEGCBLIST_ENABLED BIT(0) #define SEGCBLIST_LOCKING BIT(1) -#define SEGCBLIST_KTHREAD_CB BIT(2) -#define SEGCBLIST_KTHREAD_GP BIT(3) -#define SEGCBLIST_OFFLOADED BIT(4) +#define SEGCBLIST_KTHREAD_GP BIT(2) +#define SEGCBLIST_OFFLOADED BIT(3) struct rcu_segcblist { struct rcu_head *head; -- cgit v1.2.3 From dc1c8034e31b14a2e5e212104ec508aec44ce1b9 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 28 Jul 2024 20:24:12 -0700 Subject: minmax: simplify min()/max()/clamp() implementation Now that we no longer have any C constant expression contexts (ie array size declarations or static initializers) that use min() or max(), we can simpify the implementation by not having to worry about the result staying as a C constant expression. So now we can unconditionally just use temporary variables of the right type, and get rid of the excessive expansion that used to come from the use of __builtin_choose_expr(__is_constexpr(...), .. to pick the specialized code for constant expressions. Another expansion simplification is to pass the temporary variables (in addition to the original expression) to our __types_ok() macro. That may superficially look like it complicates the macro, but when we only want the type of the expression, expanding the temporary variable names is much simpler and smaller than expanding the potentially complicated original expression. As a result, on my machine, doing a $ time make drivers/staging/media/atomisp/pci/isp/kernels/ynr/ynr_1.0/ia_css_ynr.host.i goes from real 0m16.621s user 0m15.360s sys 0m1.221s to real 0m2.532s user 0m2.091s sys 0m0.452s because the token expansion goes down dramatically. In particular, the longest line expansion (which was line 71 of that 'ia_css_ynr.host.c' file) shrinks from 23,338kB (yes, 23MB for one single line) to "just" 1,444kB (now "only" 1.4MB). And yes, that line is still the line from hell, because it's doing multiple levels of "min()/max()" expansion thanks to some of them being hidden inside the uDIGIT_FITTING() macro. Lorenzo has a nice cleanup patch that makes that driver use inline functions instead of macros for sDIGIT_FITTING() and uDIGIT_FITTING(), which will fix that line once and for all, but the 16-fold reduction in this case does show why we need to simplify these helpers. Cc: David Laight Cc: Lorenzo Stoakes Signed-off-by: Linus Torvalds --- include/linux/minmax.h | 43 ++++++++++++++++++++----------------------- 1 file changed, 20 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/minmax.h b/include/linux/minmax.h index fc384714da45..e3e4353df983 100644 --- a/include/linux/minmax.h +++ b/include/linux/minmax.h @@ -35,10 +35,10 @@ #define __is_noneg_int(x) \ (__builtin_choose_expr(__is_constexpr(x) && __is_signed(x), x, -1) >= 0) -#define __types_ok(x, y) \ - (__is_signed(x) == __is_signed(y) || \ - __is_signed((x) + 0) == __is_signed((y) + 0) || \ - __is_noneg_int(x) || __is_noneg_int(y)) +#define __types_ok(x, y, ux, uy) \ + (__is_signed(ux) == __is_signed(uy) || \ + __is_signed((ux) + 0) == __is_signed((uy) + 0) || \ + __is_noneg_int(x) || __is_noneg_int(y)) #define __cmp_op_min < #define __cmp_op_max > @@ -51,34 +51,31 @@ #define __cmp_once(op, type, x, y) \ __cmp_once_unique(op, type, x, y, __UNIQUE_ID(x_), __UNIQUE_ID(y_)) -#define __careful_cmp_once(op, x, y) ({ \ - static_assert(__types_ok(x, y), \ +#define __careful_cmp_once(op, x, y, ux, uy) ({ \ + __auto_type ux = (x); __auto_type uy = (y); \ + static_assert(__types_ok(x, y, ux, uy), \ #op "(" #x ", " #y ") signedness error, fix types or consider u" #op "() before " #op "_t()"); \ - __cmp_once(op, __auto_type, x, y); }) + __cmp(op, ux, uy); }) -#define __careful_cmp(op, x, y) \ - __builtin_choose_expr(__is_constexpr((x) - (y)), \ - __cmp(op, x, y), __careful_cmp_once(op, x, y)) +#define __careful_cmp(op, x, y) \ + __careful_cmp_once(op, x, y, __UNIQUE_ID(x_), __UNIQUE_ID(y_)) #define __clamp(val, lo, hi) \ ((val) >= (hi) ? (hi) : ((val) <= (lo) ? (lo) : (val))) -#define __clamp_once(val, lo, hi, unique_val, unique_lo, unique_hi) ({ \ - typeof(val) unique_val = (val); \ - typeof(lo) unique_lo = (lo); \ - typeof(hi) unique_hi = (hi); \ +#define __clamp_once(val, lo, hi, uval, ulo, uhi) ({ \ + __auto_type uval = (val); \ + __auto_type ulo = (lo); \ + __auto_type uhi = (hi); \ static_assert(__builtin_choose_expr(__is_constexpr((lo) > (hi)), \ (lo) <= (hi), true), \ "clamp() low limit " #lo " greater than high limit " #hi); \ - static_assert(__types_ok(val, lo), "clamp() 'lo' signedness error"); \ - static_assert(__types_ok(val, hi), "clamp() 'hi' signedness error"); \ - __clamp(unique_val, unique_lo, unique_hi); }) - -#define __careful_clamp(val, lo, hi) ({ \ - __builtin_choose_expr(__is_constexpr((val) - (lo) + (hi)), \ - __clamp(val, lo, hi), \ - __clamp_once(val, lo, hi, __UNIQUE_ID(__val), \ - __UNIQUE_ID(__lo), __UNIQUE_ID(__hi))); }) + static_assert(__types_ok(uval, lo, uval, ulo), "clamp() 'lo' signedness error"); \ + static_assert(__types_ok(uval, hi, uval, uhi), "clamp() 'hi' signedness error"); \ + __clamp(uval, ulo, uhi); }) + +#define __careful_clamp(val, lo, hi) \ + __clamp_once(val, lo, hi, __UNIQUE_ID(v_), __UNIQUE_ID(l_), __UNIQUE_ID(h_)) /** * min - return minimum of two values of the same or compatible types -- cgit v1.2.3 From 59c34008d3bdeef4c8ebc0ed2426109b474334d4 Mon Sep 17 00:00:00 2001 From: Shyam Sundar S K Date: Mon, 22 Jul 2024 14:58:01 +0530 Subject: x86/amd_nb: Add new PCI IDs for AMD family 1Ah model 60h Add new PCI device IDs into the root IDs and miscellaneous IDs lists to provide support for the latest generation of AMD 1Ah family 60h processor models. Signed-off-by: Shyam Sundar S K Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Yazen Ghannam Link: https://lore.kernel.org/r/20240722092801.3480266-1-Shyam-sundar.S-k@amd.com --- arch/x86/kernel/amd_nb.c | 3 +++ drivers/hwmon/k10temp.c | 1 + include/linux/pci_ids.h | 1 + 3 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 059e5c16af05..61eadde08511 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -26,6 +26,7 @@ #define PCI_DEVICE_ID_AMD_19H_M70H_ROOT 0x14e8 #define PCI_DEVICE_ID_AMD_1AH_M00H_ROOT 0x153a #define PCI_DEVICE_ID_AMD_1AH_M20H_ROOT 0x1507 +#define PCI_DEVICE_ID_AMD_1AH_M60H_ROOT 0x1122 #define PCI_DEVICE_ID_AMD_MI200_ROOT 0x14bb #define PCI_DEVICE_ID_AMD_MI300_ROOT 0x14f8 @@ -63,6 +64,7 @@ static const struct pci_device_id amd_root_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M70H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M00H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M20H_ROOT) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M60H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI300_ROOT) }, {} @@ -95,6 +97,7 @@ static const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M78H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M00H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M20H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M60H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M70H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI300_DF_F3) }, diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c index 543526bac042..f96b91e43312 100644 --- a/drivers/hwmon/k10temp.c +++ b/drivers/hwmon/k10temp.c @@ -548,6 +548,7 @@ static const struct pci_device_id k10temp_id_table[] = { { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_19H_M78H_DF_F3) }, { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_1AH_M00H_DF_F3) }, { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_1AH_M20H_DF_F3) }, + { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_1AH_M60H_DF_F3) }, { PCI_VDEVICE(HYGON, PCI_DEVICE_ID_AMD_17H_DF_F3) }, {} }; diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index e388c8b1cbc2..91182aa1d2ec 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -580,6 +580,7 @@ #define PCI_DEVICE_ID_AMD_19H_M78H_DF_F3 0x12fb #define PCI_DEVICE_ID_AMD_1AH_M00H_DF_F3 0x12c3 #define PCI_DEVICE_ID_AMD_1AH_M20H_DF_F3 0x16fb +#define PCI_DEVICE_ID_AMD_1AH_M60H_DF_F3 0x124b #define PCI_DEVICE_ID_AMD_1AH_M70H_DF_F3 0x12bb #define PCI_DEVICE_ID_AMD_MI200_DF_F3 0x14d3 #define PCI_DEVICE_ID_AMD_MI300_DF_F3 0x152b -- cgit v1.2.3 From 52c3fb1a0f822fd64529ca64f3792095524de450 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 18 Jul 2024 10:21:49 +0200 Subject: perf/x86: Add hw_perf_event::aux_config Start a new section for AUX PMUs in hw_perf_event. Signed-off-by: Peter Zijlstra (Intel) --- arch/x86/events/intel/pt.c | 14 +++++++------- include/linux/perf_event.h | 3 +++ 2 files changed, 10 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index 2959970dd10e..fd4670a6694e 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -416,7 +416,7 @@ static bool pt_event_valid(struct perf_event *event) static void pt_config_start(struct perf_event *event) { struct pt *pt = this_cpu_ptr(&pt_ctx); - u64 ctl = event->hw.config; + u64 ctl = event->hw.aux_config; ctl |= RTIT_CTL_TRACEEN; if (READ_ONCE(pt->vmx_on)) @@ -424,7 +424,7 @@ static void pt_config_start(struct perf_event *event) else wrmsrl(MSR_IA32_RTIT_CTL, ctl); - WRITE_ONCE(event->hw.config, ctl); + WRITE_ONCE(event->hw.aux_config, ctl); } /* Address ranges and their corresponding msr configuration registers */ @@ -503,7 +503,7 @@ static void pt_config(struct perf_event *event) u64 reg; /* First round: clear STATUS, in particular the PSB byte counter. */ - if (!event->hw.config) { + if (!event->hw.aux_config) { perf_event_itrace_started(event); wrmsrl(MSR_IA32_RTIT_STATUS, 0); } @@ -533,14 +533,14 @@ static void pt_config(struct perf_event *event) reg |= (event->attr.config & PT_CONFIG_MASK); - event->hw.config = reg; + event->hw.aux_config = reg; pt_config_start(event); } static void pt_config_stop(struct perf_event *event) { struct pt *pt = this_cpu_ptr(&pt_ctx); - u64 ctl = READ_ONCE(event->hw.config); + u64 ctl = READ_ONCE(event->hw.aux_config); /* may be already stopped by a PMI */ if (!(ctl & RTIT_CTL_TRACEEN)) @@ -550,7 +550,7 @@ static void pt_config_stop(struct perf_event *event) if (!READ_ONCE(pt->vmx_on)) wrmsrl(MSR_IA32_RTIT_CTL, ctl); - WRITE_ONCE(event->hw.config, ctl); + WRITE_ONCE(event->hw.aux_config, ctl); /* * A wrmsr that disables trace generation serializes other PT @@ -1557,7 +1557,7 @@ void intel_pt_handle_vmx(int on) /* Turn PTs back on */ if (!on && event) - wrmsrl(MSR_IA32_RTIT_CTL, event->hw.config); + wrmsrl(MSR_IA32_RTIT_CTL, event->hw.aux_config); local_irq_restore(flags); } diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 1a8942277dda..6bb0c21d6335 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -168,6 +168,9 @@ struct hw_perf_event { struct hw_perf_event_extra extra_reg; struct hw_perf_event_extra branch_reg; }; + struct { /* aux / Intel-PT */ + u64 aux_config; + }; struct { /* software */ struct hrtimer hrtimer; }; -- cgit v1.2.3 From f23c042ce34ba265cf3129d530702b5d218e3f4b Mon Sep 17 00:00:00 2001 From: Daniel Bristot de Oliveira Date: Mon, 27 May 2024 14:06:47 +0200 Subject: sched/deadline: Comment sched_dl_entity::dl_server variable Add an explanation for the newly added variable. Fixes: 63ba8422f876 ("sched/deadline: Introduce deadline servers") Signed-off-by: Daniel Bristot de Oliveira Signed-off-by: Peter Zijlstra (Intel) Tested-by: Juri Lelli Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/147f7aa8cb8fd925f36aa8059af6a35aad08b45a.1716811044.git.bristot@kernel.org --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index f8d150343d42..1c771ea4481d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -639,6 +639,8 @@ struct sched_dl_entity { * * @dl_overrun tells if the task asked to be informed about runtime * overruns. + * + * @dl_server tells if this is a server entity. */ unsigned int dl_throttled : 1; unsigned int dl_yielded : 1; -- cgit v1.2.3 From a110a81c52a9de73e2e57e826dd3bf0fd4c22226 Mon Sep 17 00:00:00 2001 From: Daniel Bristot de Oliveira Date: Mon, 27 May 2024 14:06:51 +0200 Subject: sched/deadline: Deferrable dl server Among the motivations for the DL servers is the real-time throttling mechanism. This mechanism works by throttling the rt_rq after running for a long period without leaving space for fair tasks. The base dl server avoids this problem by boosting fair tasks instead of throttling the rt_rq. The point is that it boosts without waiting for potential starvation, causing some non-intuitive cases. For example, an IRQ dispatches two tasks on an idle system, a fair and an RT. The DL server will be activated, running the fair task before the RT one. This problem can be avoided by deferring the dl server activation. By setting the defer option, the dl_server will dispatch an SCHED_DEADLINE reservation with replenished runtime, but throttled. The dl_timer will be set for the defer time at (period - runtime) ns from start time. Thus boosting the fair rq at defer time. If the fair scheduler has the opportunity to run while waiting for defer time, the dl server runtime will be consumed. If the runtime is completely consumed before the defer time, the server will be replenished while still in a throttled state. Then, the dl_timer will be reset to the new defer time If the fair server reaches the defer time without consuming its runtime, the server will start running, following CBS rules (thus without breaking SCHED_DEADLINE). Then the server will continue the running state (without deferring) until it fair tasks are able to execute as regular fair scheduler (end of the starvation). Signed-off-by: Daniel Bristot de Oliveira Signed-off-by: Peter Zijlstra (Intel) Tested-by: Juri Lelli Link: https://lore.kernel.org/r/dd175943c72533cd9f0b87767c6499204879cc38.1716811044.git.bristot@kernel.org --- include/linux/sched.h | 12 ++ kernel/sched/deadline.c | 301 +++++++++++++++++++++++++++++++++++++++++------- kernel/sched/fair.c | 24 +++- kernel/sched/idle.c | 2 + kernel/sched/sched.h | 4 +- 5 files changed, 298 insertions(+), 45 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 1c771ea4481d..4edd7e2096fb 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -641,12 +641,24 @@ struct sched_dl_entity { * overruns. * * @dl_server tells if this is a server entity. + * + * @dl_defer tells if this is a deferred or regular server. For + * now only defer server exists. + * + * @dl_defer_armed tells if the deferrable server is waiting + * for the replenishment timer to activate it. + * + * @dl_defer_running tells if the deferrable server is actually + * running, skipping the defer phase. */ unsigned int dl_throttled : 1; unsigned int dl_yielded : 1; unsigned int dl_non_contending : 1; unsigned int dl_overrun : 1; unsigned int dl_server : 1; + unsigned int dl_defer : 1; + unsigned int dl_defer_armed : 1; + unsigned int dl_defer_running : 1; /* * Bandwidth enforcement timer. Each -deadline task has its diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index f5b531372e3f..1b295314bc93 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -771,6 +771,15 @@ static inline void replenish_dl_new_period(struct sched_dl_entity *dl_se, /* for non-boosted task, pi_of(dl_se) == dl_se */ dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline; dl_se->runtime = pi_of(dl_se)->dl_runtime; + + /* + * If it is a deferred reservation, and the server + * is not handling an starvation case, defer it. + */ + if (dl_se->dl_defer & !dl_se->dl_defer_running) { + dl_se->dl_throttled = 1; + dl_se->dl_defer_armed = 1; + } } /* @@ -809,6 +818,9 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se) replenish_dl_new_period(dl_se, rq); } +static int start_dl_timer(struct sched_dl_entity *dl_se); +static bool dl_entity_overflow(struct sched_dl_entity *dl_se, u64 t); + /* * Pure Earliest Deadline First (EDF) scheduling does not deal with the * possibility of a entity lasting more than what it declared, and thus @@ -837,9 +849,18 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se) /* * This could be the case for a !-dl task that is boosted. * Just go with full inherited parameters. + * + * Or, it could be the case of a deferred reservation that + * was not able to consume its runtime in background and + * reached this point with current u > U. + * + * In both cases, set a new period. */ - if (dl_se->dl_deadline == 0) - replenish_dl_new_period(dl_se, rq); + if (dl_se->dl_deadline == 0 || + (dl_se->dl_defer_armed && dl_entity_overflow(dl_se, rq_clock(rq)))) { + dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline; + dl_se->runtime = pi_of(dl_se)->dl_runtime; + } if (dl_se->dl_yielded && dl_se->runtime > 0) dl_se->runtime = 0; @@ -873,6 +894,44 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se) dl_se->dl_yielded = 0; if (dl_se->dl_throttled) dl_se->dl_throttled = 0; + + /* + * If this is the replenishment of a deferred reservation, + * clear the flag and return. + */ + if (dl_se->dl_defer_armed) { + dl_se->dl_defer_armed = 0; + return; + } + + /* + * A this point, if the deferred server is not armed, and the deadline + * is in the future, if it is not running already, throttle the server + * and arm the defer timer. + */ + if (dl_se->dl_defer && !dl_se->dl_defer_running && + dl_time_before(rq_clock(dl_se->rq), dl_se->deadline - dl_se->runtime)) { + if (!is_dl_boosted(dl_se) && dl_se->server_has_tasks(dl_se)) { + + /* + * Set dl_se->dl_defer_armed and dl_throttled variables to + * inform the start_dl_timer() that this is a deferred + * activation. + */ + dl_se->dl_defer_armed = 1; + dl_se->dl_throttled = 1; + if (!start_dl_timer(dl_se)) { + /* + * If for whatever reason (delays), a previous timer was + * queued but not serviced, cancel it and clean the + * deferrable server variables intended for start_dl_timer(). + */ + hrtimer_try_to_cancel(&dl_se->dl_timer); + dl_se->dl_defer_armed = 0; + dl_se->dl_throttled = 0; + } + } + } } /* @@ -1023,6 +1082,15 @@ static void update_dl_entity(struct sched_dl_entity *dl_se) } replenish_dl_new_period(dl_se, rq); + } else if (dl_server(dl_se) && dl_se->dl_defer) { + /* + * The server can still use its previous deadline, so check if + * it left the dl_defer_running state. + */ + if (!dl_se->dl_defer_running) { + dl_se->dl_defer_armed = 1; + dl_se->dl_throttled = 1; + } } } @@ -1055,8 +1123,21 @@ static int start_dl_timer(struct sched_dl_entity *dl_se) * We want the timer to fire at the deadline, but considering * that it is actually coming from rq->clock and not from * hrtimer's time base reading. + * + * The deferred reservation will have its timer set to + * (deadline - runtime). At that point, the CBS rule will decide + * if the current deadline can be used, or if a replenishment is + * required to avoid add too much pressure on the system + * (current u > U). */ - act = ns_to_ktime(dl_next_period(dl_se)); + if (dl_se->dl_defer_armed) { + WARN_ON_ONCE(!dl_se->dl_throttled); + act = ns_to_ktime(dl_se->deadline - dl_se->runtime); + } else { + /* act = deadline - rel-deadline + period */ + act = ns_to_ktime(dl_next_period(dl_se)); + } + now = hrtimer_cb_get_time(timer); delta = ktime_to_ns(now) - rq_clock(rq); act = ktime_add_ns(act, delta); @@ -1106,6 +1187,62 @@ static void __push_dl_task(struct rq *rq, struct rq_flags *rf) #endif } +/* a defer timer will not be reset if the runtime consumed was < dl_server_min_res */ +static const u64 dl_server_min_res = 1 * NSEC_PER_MSEC; + +static enum hrtimer_restart dl_server_timer(struct hrtimer *timer, struct sched_dl_entity *dl_se) +{ + struct rq *rq = rq_of_dl_se(dl_se); + u64 fw; + + scoped_guard (rq_lock, rq) { + struct rq_flags *rf = &scope.rf; + + if (!dl_se->dl_throttled || !dl_se->dl_runtime) + return HRTIMER_NORESTART; + + sched_clock_tick(); + update_rq_clock(rq); + + if (!dl_se->dl_runtime) + return HRTIMER_NORESTART; + + if (!dl_se->server_has_tasks(dl_se)) { + replenish_dl_entity(dl_se); + return HRTIMER_NORESTART; + } + + if (dl_se->dl_defer_armed) { + /* + * First check if the server could consume runtime in background. + * If so, it is possible to push the defer timer for this amount + * of time. The dl_server_min_res serves as a limit to avoid + * forwarding the timer for a too small amount of time. + */ + if (dl_time_before(rq_clock(dl_se->rq), + (dl_se->deadline - dl_se->runtime - dl_server_min_res))) { + + /* reset the defer timer */ + fw = dl_se->deadline - rq_clock(dl_se->rq) - dl_se->runtime; + + hrtimer_forward_now(timer, ns_to_ktime(fw)); + return HRTIMER_RESTART; + } + + dl_se->dl_defer_running = 1; + } + + enqueue_dl_entity(dl_se, ENQUEUE_REPLENISH); + + if (!dl_task(dl_se->rq->curr) || dl_entity_preempt(dl_se, &dl_se->rq->curr->dl)) + resched_curr(rq); + + __push_dl_task(rq, rf); + } + + return HRTIMER_NORESTART; +} + /* * This is the bandwidth enforcement timer callback. If here, we know * a task is not on its dl_rq, since the fact that the timer was running @@ -1128,28 +1265,8 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) struct rq_flags rf; struct rq *rq; - if (dl_server(dl_se)) { - struct rq *rq = rq_of_dl_se(dl_se); - struct rq_flags rf; - - rq_lock(rq, &rf); - if (dl_se->dl_throttled) { - sched_clock_tick(); - update_rq_clock(rq); - - if (dl_se->server_has_tasks(dl_se)) { - enqueue_dl_entity(dl_se, ENQUEUE_REPLENISH); - resched_curr(rq); - __push_dl_task(rq, &rf); - } else { - replenish_dl_entity(dl_se); - } - - } - rq_unlock(rq, &rf); - - return HRTIMER_NORESTART; - } + if (dl_server(dl_se)) + return dl_server_timer(timer, dl_se); p = dl_task_of(dl_se); rq = task_rq_lock(p, &rf); @@ -1319,22 +1436,10 @@ static u64 grub_reclaim(u64 delta, struct rq *rq, struct sched_dl_entity *dl_se) return (delta * u_act) >> BW_SHIFT; } -static inline void -update_stats_dequeue_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se, - int flags); -static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64 delta_exec) +s64 dl_scaled_delta_exec(struct rq *rq, struct sched_dl_entity *dl_se, s64 delta_exec) { s64 scaled_delta_exec; - if (unlikely(delta_exec <= 0)) { - if (unlikely(dl_se->dl_yielded)) - goto throttle; - return; - } - - if (dl_entity_is_special(dl_se)) - return; - /* * For tasks that participate in GRUB, we implement GRUB-PA: the * spare reclaimed bandwidth is used to clock down frequency. @@ -1353,8 +1458,64 @@ static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64 scaled_delta_exec = cap_scale(scaled_delta_exec, scale_cpu); } + return scaled_delta_exec; +} + +static inline void +update_stats_dequeue_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se, + int flags); +static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64 delta_exec) +{ + s64 scaled_delta_exec; + + if (unlikely(delta_exec <= 0)) { + if (unlikely(dl_se->dl_yielded)) + goto throttle; + return; + } + + if (dl_server(dl_se) && dl_se->dl_throttled && !dl_se->dl_defer) + return; + + if (dl_entity_is_special(dl_se)) + return; + + scaled_delta_exec = dl_scaled_delta_exec(rq, dl_se, delta_exec); + dl_se->runtime -= scaled_delta_exec; + /* + * The fair server can consume its runtime while throttled (not queued/ + * running as regular CFS). + * + * If the server consumes its entire runtime in this state. The server + * is not required for the current period. Thus, reset the server by + * starting a new period, pushing the activation. + */ + if (dl_se->dl_defer && dl_se->dl_throttled && dl_runtime_exceeded(dl_se)) { + /* + * If the server was previously activated - the starving condition + * took place, it this point it went away because the fair scheduler + * was able to get runtime in background. So return to the initial + * state. + */ + dl_se->dl_defer_running = 0; + + hrtimer_try_to_cancel(&dl_se->dl_timer); + + replenish_dl_new_period(dl_se, dl_se->rq); + + /* + * Not being able to start the timer seems problematic. If it could not + * be started for whatever reason, we need to "unthrottle" the DL server + * and queue right away. Otherwise nothing might queue it. That's similar + * to what enqueue_dl_entity() does on start_dl_timer==0. For now, just warn. + */ + WARN_ON_ONCE(!start_dl_timer(dl_se)); + + return; + } + throttle: if (dl_runtime_exceeded(dl_se) || dl_se->dl_yielded) { dl_se->dl_throttled = 1; @@ -1414,9 +1575,46 @@ throttle: } } +/* + * In the non-defer mode, the idle time is not accounted, as the + * server provides a guarantee. + * + * If the dl_server is in defer mode, the idle time is also considered + * as time available for the fair server, avoiding a penalty for the + * rt scheduler that did not consumed that time. + */ +void dl_server_update_idle_time(struct rq *rq, struct task_struct *p) +{ + s64 delta_exec, scaled_delta_exec; + + if (!rq->fair_server.dl_defer) + return; + + /* no need to discount more */ + if (rq->fair_server.runtime < 0) + return; + + delta_exec = rq_clock_task(rq) - p->se.exec_start; + if (delta_exec < 0) + return; + + scaled_delta_exec = dl_scaled_delta_exec(rq, &rq->fair_server, delta_exec); + + rq->fair_server.runtime -= scaled_delta_exec; + + if (rq->fair_server.runtime < 0) { + rq->fair_server.dl_defer_running = 0; + rq->fair_server.runtime = 0; + } + + p->se.exec_start = rq_clock_task(rq); +} + void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec) { - update_curr_dl_se(dl_se->rq, dl_se, delta_exec); + /* 0 runtime = fair server disabled */ + if (dl_se->dl_runtime) + update_curr_dl_se(dl_se->rq, dl_se, delta_exec); } void dl_server_start(struct sched_dl_entity *dl_se) @@ -1430,6 +1628,7 @@ void dl_server_start(struct sched_dl_entity *dl_se) dl_se->dl_period = 1000 * NSEC_PER_MSEC; dl_se->dl_server = 1; + dl_se->dl_defer = 1; setup_new_dl_entity(dl_se); } @@ -1447,6 +1646,9 @@ void dl_server_stop(struct sched_dl_entity *dl_se) return; dequeue_dl_entity(dl_se, DEQUEUE_SLEEP); + hrtimer_try_to_cancel(&dl_se->dl_timer); + dl_se->dl_defer_armed = 0; + dl_se->dl_throttled = 0; } void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq, @@ -1758,7 +1960,7 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags) * be counted in the active utilization; hence, we need to call * add_running_bw(). */ - if (dl_se->dl_throttled && !(flags & ENQUEUE_REPLENISH)) { + if (!dl_se->dl_defer && dl_se->dl_throttled && !(flags & ENQUEUE_REPLENISH)) { if (flags & ENQUEUE_WAKEUP) task_contending(dl_se, flags); @@ -1780,6 +1982,25 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags) setup_new_dl_entity(dl_se); } + /* + * If the reservation is still throttled, e.g., it got replenished but is a + * deferred task and still got to wait, don't enqueue. + */ + if (dl_se->dl_throttled && start_dl_timer(dl_se)) + return; + + /* + * We're about to enqueue, make sure we're not ->dl_throttled! + * In case the timer was not started, say because the defer time + * has passed, mark as not throttled and mark unarmed. + * Also cancel earlier timers, since letting those run is pointless. + */ + if (dl_se->dl_throttled) { + hrtimer_try_to_cancel(&dl_se->dl_timer); + dl_se->dl_defer_armed = 0; + dl_se->dl_throttled = 0; + } + __enqueue_dl_entity(dl_se); } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index aba23b08e52d..1ea5ec81431a 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1156,12 +1156,13 @@ s64 update_curr_common(struct rq *rq) static void update_curr(struct cfs_rq *cfs_rq) { struct sched_entity *curr = cfs_rq->curr; + struct rq *rq = rq_of(cfs_rq); s64 delta_exec; if (unlikely(!curr)) return; - delta_exec = update_curr_se(rq_of(cfs_rq), curr); + delta_exec = update_curr_se(rq, curr); if (unlikely(delta_exec <= 0)) return; @@ -1169,8 +1170,19 @@ static void update_curr(struct cfs_rq *cfs_rq) update_deadline(cfs_rq, curr); update_min_vruntime(cfs_rq); - if (entity_is_task(curr)) - update_curr_task(task_of(curr), delta_exec); + if (entity_is_task(curr)) { + struct task_struct *p = task_of(curr); + + update_curr_task(p, delta_exec); + + /* + * Any fair task that runs outside of fair_server should + * account against fair_server such that it can account for + * this time and possibly avoid running this period. + */ + if (p->dl_server != &rq->fair_server) + dl_server_update(&rq->fair_server, delta_exec); + } account_cfs_rq_runtime(cfs_rq, delta_exec); } @@ -6768,8 +6780,12 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) */ util_est_enqueue(&rq->cfs, p); - if (!throttled_hierarchy(task_cfs_rq(p)) && !rq->cfs.h_nr_running) + if (!throttled_hierarchy(task_cfs_rq(p)) && !rq->cfs.h_nr_running) { + /* Account for idle runtime */ + if (!rq->nr_running) + dl_server_update_idle_time(rq, rq->curr); dl_server_start(&rq->fair_server); + } /* * If in_iowait is set, the code below may not trigger any cpufreq diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 6e78d071beb5..d560f7ffa463 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -452,12 +452,14 @@ static void wakeup_preempt_idle(struct rq *rq, struct task_struct *p, int flags) static void put_prev_task_idle(struct rq *rq, struct task_struct *prev) { + dl_server_update_idle_time(rq, prev); } static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first) { update_idle_core(rq); schedstat_inc(rq->sched_goidle); + next->se.exec_start = rq_clock_task(rq); } #ifdef CONFIG_SMP diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 7416bcd2a549..64fb6776664e 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -335,7 +335,7 @@ extern bool __checkparam_dl(const struct sched_attr *attr); extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr); extern int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial); extern int dl_bw_check_overflow(int cpu); - +extern s64 dl_scaled_delta_exec(struct rq *rq, struct sched_dl_entity *dl_se, s64 delta_exec); /* * SCHED_DEADLINE supports servers (nested scheduling) with the following * interface: @@ -363,6 +363,8 @@ extern void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq, dl_server_has_tasks_f has_tasks, dl_server_pick_f pick); +extern void dl_server_update_idle_time(struct rq *rq, + struct task_struct *p); extern void fair_server_init(struct rq *rq); #ifdef CONFIG_CGROUP_SCHED -- cgit v1.2.3 From c8a85394cfdb4696b4e2f8a0f3066a1c921af426 Mon Sep 17 00:00:00 2001 From: "Joel Fernandes (Google)" Date: Mon, 27 May 2024 14:06:54 +0200 Subject: sched/core: Fix picking of tasks for core scheduling with DL server * Use simple CFS pick_task for DL pick_task DL server's pick_task calls CFS's pick_next_task_fair(), this is wrong because core scheduling's pick_task only calls CFS's pick_task() for evaluation / checking of the CFS task (comparing across CPUs), not for actually affirmatively picking the next task. This causes RB tree corruption issues in CFS that were found by syzbot. * Make pick_task_fair clear DL server A DL task pick might set ->dl_server, but it is possible the task will never run (say the other HT has a stop task). If the CFS task is picked in the future directly (say without DL server), ->dl_server will be set. So clear it in pick_task_fair(). This fixes the KASAN issue reported by syzbot in set_next_entity(). (DL refactoring suggestions by Vineeth Pillai). Reported-by: Suleiman Souhlal Signed-off-by: "Joel Fernandes (Google)" Signed-off-by: Daniel Bristot de Oliveira Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Vineeth Pillai Tested-by: Juri Lelli Link: https://lore.kernel.org/r/b10489ab1f03d23e08e6097acea47442e7d6466f.1716811044.git.bristot@kernel.org --- include/linux/sched.h | 3 ++- kernel/sched/deadline.c | 27 ++++++++++++++++++++++----- kernel/sched/fair.c | 23 +++++++++++++++++++++-- kernel/sched/sched.h | 3 ++- 4 files changed, 47 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4edd7e2096fb..2c1b4ee3234f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -686,7 +686,8 @@ struct sched_dl_entity { */ struct rq *rq; dl_server_has_tasks_f server_has_tasks; - dl_server_pick_f server_pick; + dl_server_pick_f server_pick_next; + dl_server_pick_f server_pick_task; #ifdef CONFIG_RT_MUTEXES /* diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 747c0c51d753..8571bc9b37cc 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1664,11 +1664,13 @@ void dl_server_stop(struct sched_dl_entity *dl_se) void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq, dl_server_has_tasks_f has_tasks, - dl_server_pick_f pick) + dl_server_pick_f pick_next, + dl_server_pick_f pick_task) { dl_se->rq = rq; dl_se->server_has_tasks = has_tasks; - dl_se->server_pick = pick; + dl_se->server_pick_next = pick_next; + dl_se->server_pick_task = pick_task; } void __dl_server_attach_root(struct sched_dl_entity *dl_se, struct rq *rq) @@ -2399,7 +2401,12 @@ static struct sched_dl_entity *pick_next_dl_entity(struct dl_rq *dl_rq) return __node_2_dle(left); } -static struct task_struct *pick_task_dl(struct rq *rq) +/* + * __pick_next_task_dl - Helper to pick the next -deadline task to run. + * @rq: The runqueue to pick the next task from. + * @peek: If true, just peek at the next task. Only relevant for dlserver. + */ +static struct task_struct *__pick_next_task_dl(struct rq *rq, bool peek) { struct sched_dl_entity *dl_se; struct dl_rq *dl_rq = &rq->dl; @@ -2413,7 +2420,10 @@ again: WARN_ON_ONCE(!dl_se); if (dl_server(dl_se)) { - p = dl_se->server_pick(dl_se); + if (IS_ENABLED(CONFIG_SMP) && peek) + p = dl_se->server_pick_task(dl_se); + else + p = dl_se->server_pick_next(dl_se); if (!p) { WARN_ON_ONCE(1); dl_se->dl_yielded = 1; @@ -2428,11 +2438,18 @@ again: return p; } +#ifdef CONFIG_SMP +static struct task_struct *pick_task_dl(struct rq *rq) +{ + return __pick_next_task_dl(rq, true); +} +#endif + static struct task_struct *pick_next_task_dl(struct rq *rq) { struct task_struct *p; - p = pick_task_dl(rq); + p = __pick_next_task_dl(rq, false); if (!p) return p; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 1ea5ec81431a..ee251ac50398 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -8479,6 +8479,14 @@ again: cfs_rq = group_cfs_rq(se); } while (cfs_rq); + /* + * This can be called from directly from CFS's ->pick_task() or indirectly + * from DL's ->pick_task when fair server is enabled. In the indirect case, + * DL will set ->dl_server just after this function is called, so its Ok to + * clear. In the direct case, we are picking directly so we must clear it. + */ + task_of(se)->dl_server = NULL; + return task_of(se); } #endif @@ -8638,7 +8646,16 @@ static bool fair_server_has_tasks(struct sched_dl_entity *dl_se) return !!dl_se->rq->cfs.nr_running; } -static struct task_struct *fair_server_pick(struct sched_dl_entity *dl_se) +static struct task_struct *fair_server_pick_task(struct sched_dl_entity *dl_se) +{ +#ifdef CONFIG_SMP + return pick_task_fair(dl_se->rq); +#else + return NULL; +#endif +} + +static struct task_struct *fair_server_pick_next(struct sched_dl_entity *dl_se) { return pick_next_task_fair(dl_se->rq, NULL, NULL); } @@ -8649,7 +8666,9 @@ void fair_server_init(struct rq *rq) init_dl_entity(dl_se); - dl_server_init(dl_se, rq, fair_server_has_tasks, fair_server_pick); + dl_server_init(dl_se, rq, fair_server_has_tasks, fair_server_pick_next, + fair_server_pick_task); + } /* diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index b777ac361543..f7e028b2e34e 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -361,7 +361,8 @@ extern void dl_server_start(struct sched_dl_entity *dl_se); extern void dl_server_stop(struct sched_dl_entity *dl_se); extern void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq, dl_server_has_tasks_f has_tasks, - dl_server_pick_f pick); + dl_server_pick_f pick_next, + dl_server_pick_f pick_task); extern void dl_server_update_idle_time(struct rq *rq, struct task_struct *p); -- cgit v1.2.3 From 5297bba507dc54045e6efeb9955c1271ca9aafe1 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Tue, 23 Jul 2024 15:27:01 +0200 Subject: genirq/msi: Silence 'set affinity failed' warning Various PCI controllers that mux MSIs onto a single IRQ line produce these "IRQ%d: set affinity failed" warnings when entering suspend. This has been discussed before [1] [2] and an example test case is included at the end of this commit message. Controller drivers that create MSI IRQ domain with MSI_FLAG_USE_DEF_CHIP_OPS and do not override the .irq_set_affinity() irqchip callback get assigned the default msi_domain_set_affinity() callback. That is not desired on controllers where it is not possible to set affinity of each MSI IRQ line to a specific CPU core due to hardware limitation. Introduce flag MSI_FLAG_NO_AFFINITY, which keeps .irq_set_affinity() unset if the controller driver did not assign it. This way, migrate_one_irq() can exit right away, without printing the warning. The .irq_set_affinity() implementations which only return -EINVAL can be removed from multiple controller drivers. $ grep 25 /proc/interrupts 25: 0 0 0 0 0 0 0 0 PCIe MSI 0 Edge PCIe PME $ echo core > /sys/power/pm_test ; echo mem > /sys/power/state ... Disabling non-boot CPUs ... IRQ25: set affinity failed(-22). <---------- This is being silenced here psci: CPU7 killed (polled 4 ms) ... [1] https://lore.kernel.org/all/d4a6eea3c5e33a3a4056885419df95a7@kernel.org/ [2] https://lore.kernel.org/all/5f4947b18bf381615a37aa81c2242477@kernel.org/ Link: https://lore.kernel.org/r/20240723132958.41320-2-marek.vasut+renesas@mailbox.org Signed-off-by: Marek Vasut [bhelgaas: commit log] Signed-off-by: Bjorn Helgaas Reviewed-by: Damien Le Moal Reviewed-by: Manivannan Sadhasivam Acked-by: Thomas Gleixner --- include/linux/msi.h | 2 ++ kernel/irq/msi.c | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index 944979763825..b10093c4d00e 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -554,6 +554,8 @@ enum { MSI_FLAG_MSIX_CONTIGUOUS = (1 << 19), /* PCI/MSI-X vectors can be dynamically allocated/freed post MSI-X enable */ MSI_FLAG_PCI_MSIX_ALLOC_DYN = (1 << 20), + /* PCI MSIs cannot be steered separately to CPU cores */ + MSI_FLAG_NO_AFFINITY = (1 << 21), }; /** diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 5fa0547ece0c..ca6e2ae6d6fc 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -832,7 +832,7 @@ static void msi_domain_update_chip_ops(struct msi_domain_info *info) struct irq_chip *chip = info->chip; BUG_ON(!chip || !chip->irq_mask || !chip->irq_unmask); - if (!chip->irq_set_affinity) + if (!chip->irq_set_affinity && !(info->flags & MSI_FLAG_NO_AFFINITY)) chip->irq_set_affinity = msi_domain_set_affinity; } -- cgit v1.2.3 From 2accfdb7eff65f390c4308b0e9cb7c3fe48ad63c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 29 Jul 2024 10:58:28 -0700 Subject: profiling: attempt to remove per-cpu profile flip buffer This is the really old legacy kernel profiling code, which has long since been obviated by "real profiling" (ie 'prof' and company), and mainly remains as a source of syzbot reports. There are anecdotal reports that people still use it for boot-time profiling, but it's unlikely that such use would care about the old NUMA optimizations in this code from 2004 (commit ad02973d42: "profile: 512x Altix timer interrupt livelock fix" in the BK import archive at [1]) So in order to head off future syzbot reports, let's try to simplify this code and get rid of the per-cpu profile buffers that are quite a large portion of the complexity footprint of this thing (including CPU hotplug callbacks etc). It's unlikely anybody will actually notice, or possibly, as Thomas put it: "Only people who indulge in nostalgia will notice :)". That said, if it turns out that this code is actually actively used by somebody, we can always revert this removal. Thus the "attempt" in the summary line. [ Note: in a small nod to "the profiling code can cause NUMA problems", this also removes the "increment the last entry in the profiling array on any unknown hits" logic. That would account any program counter in a module to that single counter location, and might exacerbate any NUMA cacheline bouncing issues ] Link: https://lore.kernel.org/all/CAHk-=wgs52BxT4Zjmjz8aNvHWKxf5_ThBY4bYL1Y6CTaNL2dTw@mail.gmail.com/ Link: https://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git [1] Cc: Thomas Gleixner Cc: Tetsuo Handa Signed-off-by: Linus Torvalds --- include/linux/cpuhotplug.h | 1 - kernel/profile.c | 183 +-------------------------------------------- 2 files changed, 2 insertions(+), 182 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 51ba681b915a..affdd890899e 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -100,7 +100,6 @@ enum cpuhp_state { CPUHP_WORKQUEUE_PREP, CPUHP_POWER_NUMA_PREPARE, CPUHP_HRTIMERS_PREPARE, - CPUHP_PROFILE_PREPARE, CPUHP_X2APIC_PREPARE, CPUHP_SMPCFD_PREPARE, CPUHP_RELAY_PREPARE, diff --git a/kernel/profile.c b/kernel/profile.c index 4654c6cd984e..2dfb0f4e755c 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -129,180 +129,13 @@ int __ref profile_init(void) return -ENOMEM; } -#if defined(CONFIG_SMP) && defined(CONFIG_PROC_FS) -/* - * Each cpu has a pair of open-addressed hashtables for pending - * profile hits. read_profile() IPI's all cpus to request them - * to flip buffers and flushes their contents to prof_buffer itself. - * Flip requests are serialized by the profile_flip_mutex. The sole - * use of having a second hashtable is for avoiding cacheline - * contention that would otherwise happen during flushes of pending - * profile hits required for the accuracy of reported profile hits - * and so resurrect the interrupt livelock issue. - * - * The open-addressed hashtables are indexed by profile buffer slot - * and hold the number of pending hits to that profile buffer slot on - * a cpu in an entry. When the hashtable overflows, all pending hits - * are accounted to their corresponding profile buffer slots with - * atomic_add() and the hashtable emptied. As numerous pending hits - * may be accounted to a profile buffer slot in a hashtable entry, - * this amortizes a number of atomic profile buffer increments likely - * to be far larger than the number of entries in the hashtable, - * particularly given that the number of distinct profile buffer - * positions to which hits are accounted during short intervals (e.g. - * several seconds) is usually very small. Exclusion from buffer - * flipping is provided by interrupt disablement (note that for - * SCHED_PROFILING or SLEEP_PROFILING profile_hit() may be called from - * process context). - * The hash function is meant to be lightweight as opposed to strong, - * and was vaguely inspired by ppc64 firmware-supported inverted - * pagetable hash functions, but uses a full hashtable full of finite - * collision chains, not just pairs of them. - * - * -- nyc - */ -static void __profile_flip_buffers(void *unused) -{ - int cpu = smp_processor_id(); - - per_cpu(cpu_profile_flip, cpu) = !per_cpu(cpu_profile_flip, cpu); -} - -static void profile_flip_buffers(void) -{ - int i, j, cpu; - - mutex_lock(&profile_flip_mutex); - j = per_cpu(cpu_profile_flip, get_cpu()); - put_cpu(); - on_each_cpu(__profile_flip_buffers, NULL, 1); - for_each_online_cpu(cpu) { - struct profile_hit *hits = per_cpu(cpu_profile_hits, cpu)[j]; - for (i = 0; i < NR_PROFILE_HIT; ++i) { - if (!hits[i].hits) { - if (hits[i].pc) - hits[i].pc = 0; - continue; - } - atomic_add(hits[i].hits, &prof_buffer[hits[i].pc]); - hits[i].hits = hits[i].pc = 0; - } - } - mutex_unlock(&profile_flip_mutex); -} - -static void profile_discard_flip_buffers(void) -{ - int i, cpu; - - mutex_lock(&profile_flip_mutex); - i = per_cpu(cpu_profile_flip, get_cpu()); - put_cpu(); - on_each_cpu(__profile_flip_buffers, NULL, 1); - for_each_online_cpu(cpu) { - struct profile_hit *hits = per_cpu(cpu_profile_hits, cpu)[i]; - memset(hits, 0, NR_PROFILE_HIT*sizeof(struct profile_hit)); - } - mutex_unlock(&profile_flip_mutex); -} - -static void do_profile_hits(int type, void *__pc, unsigned int nr_hits) -{ - unsigned long primary, secondary, flags, pc = (unsigned long)__pc; - int i, j, cpu; - struct profile_hit *hits; - - pc = min((pc - (unsigned long)_stext) >> prof_shift, prof_len - 1); - i = primary = (pc & (NR_PROFILE_GRP - 1)) << PROFILE_GRPSHIFT; - secondary = (~(pc << 1) & (NR_PROFILE_GRP - 1)) << PROFILE_GRPSHIFT; - cpu = get_cpu(); - hits = per_cpu(cpu_profile_hits, cpu)[per_cpu(cpu_profile_flip, cpu)]; - if (!hits) { - put_cpu(); - return; - } - /* - * We buffer the global profiler buffer into a per-CPU - * queue and thus reduce the number of global (and possibly - * NUMA-alien) accesses. The write-queue is self-coalescing: - */ - local_irq_save(flags); - do { - for (j = 0; j < PROFILE_GRPSZ; ++j) { - if (hits[i + j].pc == pc) { - hits[i + j].hits += nr_hits; - goto out; - } else if (!hits[i + j].hits) { - hits[i + j].pc = pc; - hits[i + j].hits = nr_hits; - goto out; - } - } - i = (i + secondary) & (NR_PROFILE_HIT - 1); - } while (i != primary); - - /* - * Add the current hit(s) and flush the write-queue out - * to the global buffer: - */ - atomic_add(nr_hits, &prof_buffer[pc]); - for (i = 0; i < NR_PROFILE_HIT; ++i) { - atomic_add(hits[i].hits, &prof_buffer[hits[i].pc]); - hits[i].pc = hits[i].hits = 0; - } -out: - local_irq_restore(flags); - put_cpu(); -} - -static int profile_dead_cpu(unsigned int cpu) -{ - struct page *page; - int i; - - for (i = 0; i < 2; i++) { - if (per_cpu(cpu_profile_hits, cpu)[i]) { - page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[i]); - per_cpu(cpu_profile_hits, cpu)[i] = NULL; - __free_page(page); - } - } - return 0; -} - -static int profile_prepare_cpu(unsigned int cpu) -{ - int i, node = cpu_to_mem(cpu); - struct page *page; - - per_cpu(cpu_profile_flip, cpu) = 0; - - for (i = 0; i < 2; i++) { - if (per_cpu(cpu_profile_hits, cpu)[i]) - continue; - - page = __alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0); - if (!page) { - profile_dead_cpu(cpu); - return -ENOMEM; - } - per_cpu(cpu_profile_hits, cpu)[i] = page_address(page); - - } - return 0; -} - -#else /* !CONFIG_SMP */ -#define profile_flip_buffers() do { } while (0) -#define profile_discard_flip_buffers() do { } while (0) - static void do_profile_hits(int type, void *__pc, unsigned int nr_hits) { unsigned long pc; pc = ((unsigned long)__pc - (unsigned long)_stext) >> prof_shift; - atomic_add(nr_hits, &prof_buffer[min(pc, prof_len - 1)]); + if (pc < prof_len) + atomic_add(nr_hits, &prof_buffer[pc]); } -#endif /* !CONFIG_SMP */ void profile_hits(int type, void *__pc, unsigned int nr_hits) { @@ -340,7 +173,6 @@ read_profile(struct file *file, char __user *buf, size_t count, loff_t *ppos) char *pnt; unsigned long sample_step = 1UL << prof_shift; - profile_flip_buffers(); if (p >= (prof_len+1)*sizeof(unsigned int)) return 0; if (count > (prof_len+1)*sizeof(unsigned int) - p) @@ -386,7 +218,6 @@ static ssize_t write_profile(struct file *file, const char __user *buf, return -EINVAL; } #endif - profile_discard_flip_buffers(); memset(prof_buffer, 0, prof_len * sizeof(atomic_t)); return count; } @@ -404,20 +235,10 @@ int __ref create_proc_profile(void) if (!prof_on) return 0; -#ifdef CONFIG_SMP - err = cpuhp_setup_state(CPUHP_PROFILE_PREPARE, "PROFILE_PREPARE", - profile_prepare_cpu, profile_dead_cpu); - if (err) - return err; -#endif entry = proc_create("profile", S_IWUSR | S_IRUGO, NULL, &profile_proc_ops); if (entry) proc_set_size(entry, (1 + prof_len) * sizeof(atomic_t)); -#ifdef CONFIG_SMP - else - cpuhp_remove_state(CPUHP_PROFILE_PREPARE); -#endif return err; } subsys_initcall(create_proc_profile); -- cgit v1.2.3 From de79583ffe794663c53b77f97be814522d4edc4f Mon Sep 17 00:00:00 2001 From: Nuno Sa Date: Tue, 2 Jul 2024 18:02:33 +0200 Subject: iio: core: add accessors 'masklength' 'masklength' is supposed to be an IIO private member. However, drivers (often in trigger handlers) need to access it to iterate over the enabled channels for example (there are other reasons). Hence, a couple of new accessors are being added: * iio_for_each_active_channel() - Iterates over the active channels; * iio_get_masklength() - Get length of the channels mask. The goal of these new accessors is to annotate 'masklength' as private as soon as all drivers accessing it are converted to use the new helpers. Signed-off-by: Nuno Sa Reviewed-by: Alexandru Ardelean Link: https://patch.msgid.link/20240702-dev-iio-masklength-private-v1-1-98193bf536a6@analog.com Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 894309294182..dd6bbc468283 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -855,6 +855,24 @@ static inline const struct iio_scan_type return &chan->scan_type; } +/** + * iio_get_masklength - Get length of the channels mask + * @indio_dev: the IIO device to get the masklength for + */ +static inline unsigned int iio_get_masklength(const struct iio_dev *indio_dev) +{ + return indio_dev->masklength; +} + +/** + * iio_for_each_active_channel - Iterated over active channels + * @indio_dev: the IIO device + * @chan: Holds the index of the enabled channel + */ +#define iio_for_each_active_channel(indio_dev, chan) \ + for_each_set_bit((chan), (indio_dev)->active_scan_mask, \ + iio_get_masklength(indio_dev)) + ssize_t iio_format_value(char *buf, unsigned int type, int size, int *vals); int iio_str_to_fixpoint(const char *str, int fract_mult, int *integer, -- cgit v1.2.3 From 4bf79f9be434e000c8e12fe83b2f4402480f1460 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Thu, 18 Jul 2024 13:23:53 -0700 Subject: bpf: Track equal scalars history on per-instruction level Use bpf_verifier_state->jmp_history to track which registers were updated by find_equal_scalars() (renamed to collect_linked_regs()) when conditional jump was verified. Use recorded information in backtrack_insn() to propagate precision. E.g. for the following program: while verifying instructions 1: r1 = r0 | 2: if r1 < 8 goto ... | push r0,r1 as linked registers in jmp_history 3: if r0 > 16 goto ... | push r0,r1 as linked registers in jmp_history 4: r2 = r10 | 5: r2 += r0 v mark_chain_precision(r0) while doing mark_chain_precision(r0) 5: r2 += r0 | mark r0 precise 4: r2 = r10 | 3: if r0 > 16 goto ... | mark r0,r1 as precise 2: if r1 < 8 goto ... | mark r0,r1 as precise 1: r1 = r0 v Technically, do this as follows: - Use 10 bits to identify each register that gains range because of sync_linked_regs(): - 3 bits for frame number; - 6 bits for register or stack slot number; - 1 bit to indicate if register is spilled. - Use u64 as a vector of 6 such records + 4 bits for vector length. - Augment struct bpf_jmp_history_entry with a field 'linked_regs' representing such vector. - When doing check_cond_jmp_op() remember up to 6 registers that gain range because of sync_linked_regs() in such a vector. - Don't propagate range information and reset IDs for registers that don't fit in 6-value vector. - Push a pair {instruction index, linked registers vector} to bpf_verifier_state->jmp_history. - When doing backtrack_insn() check if any of recorded linked registers is currently marked precise, if so mark all linked registers as precise. This also requires fixes for two test_verifier tests: - precise: test 1 - precise: test 2 Both tests contain the following instruction sequence: 19: (bf) r2 = r9 ; R2=scalar(id=3) R9=scalar(id=3) 20: (a5) if r2 < 0x8 goto pc+1 ; R2=scalar(id=3,umin=8) 21: (95) exit 22: (07) r2 += 1 ; R2_w=scalar(id=3+1,...) 23: (bf) r1 = r10 ; R1_w=fp0 R10=fp0 24: (07) r1 += -8 ; R1_w=fp-8 25: (b7) r3 = 0 ; R3_w=0 26: (85) call bpf_probe_read_kernel#113 The call to bpf_probe_read_kernel() at (26) forces r2 to be precise. Previously, this forced all registers with same id to become precise immediately when mark_chain_precision() is called. After this change, the precision is propagated to registers sharing same id only when 'if' instruction is backtracked. Hence verification log for both tests is changed: regs=r2,r9 -> regs=r2 for instructions 25..20. Fixes: 904e6ddf4133 ("bpf: Use scalar ids in mark_chain_precision()") Reported-by: Hao Sun Suggested-by: Andrii Nakryiko Signed-off-by: Eduard Zingerman Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20240718202357.1746514-2-eddyz87@gmail.com Closes: https://lore.kernel.org/bpf/CAEf4BzZ0xidVCqB47XnkXcNhkPWF6_nTV7yt+_Lf0kcFEut2Mg@mail.gmail.com/ --- include/linux/bpf_verifier.h | 4 + kernel/bpf/verifier.c | 245 +++++++++++++++++++-- .../bpf/progs/verifier_subprog_precision.c | 2 +- tools/testing/selftests/bpf/verifier/precise.c | 20 +- 4 files changed, 239 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 6503c85b10a3..731a0a4ac13c 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -371,6 +371,10 @@ struct bpf_jmp_history_entry { u32 prev_idx : 22; /* special flags, e.g., whether insn is doing register stack spill/load */ u32 flags : 10; + /* additional registers that need precision tracking when this + * jump is backtracked, vector of six 10-bit records + */ + u64 linked_regs; }; /* Maximum number of register states that can exist at once */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 4cb5441ad75f..8dade7b51430 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3335,9 +3335,87 @@ static bool is_jmp_point(struct bpf_verifier_env *env, int insn_idx) return env->insn_aux_data[insn_idx].jmp_point; } +#define LR_FRAMENO_BITS 3 +#define LR_SPI_BITS 6 +#define LR_ENTRY_BITS (LR_SPI_BITS + LR_FRAMENO_BITS + 1) +#define LR_SIZE_BITS 4 +#define LR_FRAMENO_MASK ((1ull << LR_FRAMENO_BITS) - 1) +#define LR_SPI_MASK ((1ull << LR_SPI_BITS) - 1) +#define LR_SIZE_MASK ((1ull << LR_SIZE_BITS) - 1) +#define LR_SPI_OFF LR_FRAMENO_BITS +#define LR_IS_REG_OFF (LR_SPI_BITS + LR_FRAMENO_BITS) +#define LINKED_REGS_MAX 6 + +struct linked_reg { + u8 frameno; + union { + u8 spi; + u8 regno; + }; + bool is_reg; +}; + +struct linked_regs { + int cnt; + struct linked_reg entries[LINKED_REGS_MAX]; +}; + +static struct linked_reg *linked_regs_push(struct linked_regs *s) +{ + if (s->cnt < LINKED_REGS_MAX) + return &s->entries[s->cnt++]; + + return NULL; +} + +/* Use u64 as a vector of 6 10-bit values, use first 4-bits to track + * number of elements currently in stack. + * Pack one history entry for linked registers as 10 bits in the following format: + * - 3-bits frameno + * - 6-bits spi_or_reg + * - 1-bit is_reg + */ +static u64 linked_regs_pack(struct linked_regs *s) +{ + u64 val = 0; + int i; + + for (i = 0; i < s->cnt; ++i) { + struct linked_reg *e = &s->entries[i]; + u64 tmp = 0; + + tmp |= e->frameno; + tmp |= e->spi << LR_SPI_OFF; + tmp |= (e->is_reg ? 1 : 0) << LR_IS_REG_OFF; + + val <<= LR_ENTRY_BITS; + val |= tmp; + } + val <<= LR_SIZE_BITS; + val |= s->cnt; + return val; +} + +static void linked_regs_unpack(u64 val, struct linked_regs *s) +{ + int i; + + s->cnt = val & LR_SIZE_MASK; + val >>= LR_SIZE_BITS; + + for (i = 0; i < s->cnt; ++i) { + struct linked_reg *e = &s->entries[i]; + + e->frameno = val & LR_FRAMENO_MASK; + e->spi = (val >> LR_SPI_OFF) & LR_SPI_MASK; + e->is_reg = (val >> LR_IS_REG_OFF) & 0x1; + val >>= LR_ENTRY_BITS; + } +} + /* for any branch, call, exit record the history of jmps in the given state */ static int push_jmp_history(struct bpf_verifier_env *env, struct bpf_verifier_state *cur, - int insn_flags) + int insn_flags, u64 linked_regs) { u32 cnt = cur->jmp_history_cnt; struct bpf_jmp_history_entry *p; @@ -3353,6 +3431,10 @@ static int push_jmp_history(struct bpf_verifier_env *env, struct bpf_verifier_st "verifier insn history bug: insn_idx %d cur flags %x new flags %x\n", env->insn_idx, env->cur_hist_ent->flags, insn_flags); env->cur_hist_ent->flags |= insn_flags; + WARN_ONCE(env->cur_hist_ent->linked_regs != 0, + "verifier insn history bug: insn_idx %d linked_regs != 0: %#llx\n", + env->insn_idx, env->cur_hist_ent->linked_regs); + env->cur_hist_ent->linked_regs = linked_regs; return 0; } @@ -3367,6 +3449,7 @@ static int push_jmp_history(struct bpf_verifier_env *env, struct bpf_verifier_st p->idx = env->insn_idx; p->prev_idx = env->prev_insn_idx; p->flags = insn_flags; + p->linked_regs = linked_regs; cur->jmp_history_cnt = cnt; env->cur_hist_ent = p; @@ -3532,6 +3615,11 @@ static inline bool bt_is_reg_set(struct backtrack_state *bt, u32 reg) return bt->reg_masks[bt->frame] & (1 << reg); } +static inline bool bt_is_frame_reg_set(struct backtrack_state *bt, u32 frame, u32 reg) +{ + return bt->reg_masks[frame] & (1 << reg); +} + static inline bool bt_is_frame_slot_set(struct backtrack_state *bt, u32 frame, u32 slot) { return bt->stack_masks[frame] & (1ull << slot); @@ -3576,6 +3664,42 @@ static void fmt_stack_mask(char *buf, ssize_t buf_sz, u64 stack_mask) } } +/* If any register R in hist->linked_regs is marked as precise in bt, + * do bt_set_frame_{reg,slot}(bt, R) for all registers in hist->linked_regs. + */ +static void bt_sync_linked_regs(struct backtrack_state *bt, struct bpf_jmp_history_entry *hist) +{ + struct linked_regs linked_regs; + bool some_precise = false; + int i; + + if (!hist || hist->linked_regs == 0) + return; + + linked_regs_unpack(hist->linked_regs, &linked_regs); + for (i = 0; i < linked_regs.cnt; ++i) { + struct linked_reg *e = &linked_regs.entries[i]; + + if ((e->is_reg && bt_is_frame_reg_set(bt, e->frameno, e->regno)) || + (!e->is_reg && bt_is_frame_slot_set(bt, e->frameno, e->spi))) { + some_precise = true; + break; + } + } + + if (!some_precise) + return; + + for (i = 0; i < linked_regs.cnt; ++i) { + struct linked_reg *e = &linked_regs.entries[i]; + + if (e->is_reg) + bt_set_frame_reg(bt, e->frameno, e->regno); + else + bt_set_frame_slot(bt, e->frameno, e->spi); + } +} + static bool calls_callback(struct bpf_verifier_env *env, int insn_idx); /* For given verifier state backtrack_insn() is called from the last insn to @@ -3615,6 +3739,12 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, print_bpf_insn(&cbs, insn, env->allow_ptr_leaks); } + /* If there is a history record that some registers gained range at this insn, + * propagate precision marks to those registers, so that bt_is_reg_set() + * accounts for these registers. + */ + bt_sync_linked_regs(bt, hist); + if (class == BPF_ALU || class == BPF_ALU64) { if (!bt_is_reg_set(bt, dreg)) return 0; @@ -3844,7 +3974,8 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, */ bt_set_reg(bt, dreg); bt_set_reg(bt, sreg); - /* else dreg K + } else if (BPF_SRC(insn->code) == BPF_K) { + /* dreg K * Only dreg still needs precision before * this insn, so for the K-based conditional * there is nothing new to be marked. @@ -3862,6 +3993,10 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, /* to be analyzed */ return -ENOTSUPP; } + /* Propagate precision marks to linked registers, to account for + * registers marked as precise in this function. + */ + bt_sync_linked_regs(bt, hist); return 0; } @@ -4456,7 +4591,7 @@ static void assign_scalar_id_before_mov(struct bpf_verifier_env *env, if (!src_reg->id && !tnum_is_const(src_reg->var_off)) /* Ensure that src_reg has a valid ID that will be copied to - * dst_reg and then will be used by find_equal_scalars() to + * dst_reg and then will be used by sync_linked_regs() to * propagate min/max range. */ src_reg->id = ++env->id_gen; @@ -4625,7 +4760,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, } if (insn_flags) - return push_jmp_history(env, env->cur_state, insn_flags); + return push_jmp_history(env, env->cur_state, insn_flags, 0); return 0; } @@ -4930,7 +5065,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, insn_flags = 0; /* we are not restoring spilled register */ } if (insn_flags) - return push_jmp_history(env, env->cur_state, insn_flags); + return push_jmp_history(env, env->cur_state, insn_flags, 0); return 0; } @@ -14099,7 +14234,7 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, u64 val = reg_const_value(src_reg, alu32); if ((dst_reg->id & BPF_ADD_CONST) || - /* prevent overflow in find_equal_scalars() later */ + /* prevent overflow in sync_linked_regs() later */ val > (u32)S32_MAX) { /* * If the register already went through rX += val @@ -14114,7 +14249,7 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, } else { /* * Make sure ID is cleared otherwise dst_reg min/max could be - * incorrectly propagated into other registers by find_equal_scalars() + * incorrectly propagated into other registers by sync_linked_regs() */ dst_reg->id = 0; } @@ -14264,7 +14399,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) copy_register_state(dst_reg, src_reg); /* Make sure ID is cleared if src_reg is not in u32 * range otherwise dst_reg min/max could be incorrectly - * propagated into src_reg by find_equal_scalars() + * propagated into src_reg by sync_linked_regs() */ if (!is_src_reg_u32) dst_reg->id = 0; @@ -15087,14 +15222,66 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn, return true; } -static void find_equal_scalars(struct bpf_verifier_state *vstate, - struct bpf_reg_state *known_reg) +static void __collect_linked_regs(struct linked_regs *reg_set, struct bpf_reg_state *reg, + u32 id, u32 frameno, u32 spi_or_reg, bool is_reg) +{ + struct linked_reg *e; + + if (reg->type != SCALAR_VALUE || (reg->id & ~BPF_ADD_CONST) != id) + return; + + e = linked_regs_push(reg_set); + if (e) { + e->frameno = frameno; + e->is_reg = is_reg; + e->regno = spi_or_reg; + } else { + reg->id = 0; + } +} + +/* For all R being scalar registers or spilled scalar registers + * in verifier state, save R in linked_regs if R->id == id. + * If there are too many Rs sharing same id, reset id for leftover Rs. + */ +static void collect_linked_regs(struct bpf_verifier_state *vstate, u32 id, + struct linked_regs *linked_regs) +{ + struct bpf_func_state *func; + struct bpf_reg_state *reg; + int i, j; + + id = id & ~BPF_ADD_CONST; + for (i = vstate->curframe; i >= 0; i--) { + func = vstate->frame[i]; + for (j = 0; j < BPF_REG_FP; j++) { + reg = &func->regs[j]; + __collect_linked_regs(linked_regs, reg, id, i, j, true); + } + for (j = 0; j < func->allocated_stack / BPF_REG_SIZE; j++) { + if (!is_spilled_reg(&func->stack[j])) + continue; + reg = &func->stack[j].spilled_ptr; + __collect_linked_regs(linked_regs, reg, id, i, j, false); + } + } +} + +/* For all R in linked_regs, copy known_reg range into R + * if R->id == known_reg->id. + */ +static void sync_linked_regs(struct bpf_verifier_state *vstate, struct bpf_reg_state *known_reg, + struct linked_regs *linked_regs) { struct bpf_reg_state fake_reg; - struct bpf_func_state *state; struct bpf_reg_state *reg; + struct linked_reg *e; + int i; - bpf_for_each_reg_in_vstate(vstate, state, reg, ({ + for (i = 0; i < linked_regs->cnt; ++i) { + e = &linked_regs->entries[i]; + reg = e->is_reg ? &vstate->frame[e->frameno]->regs[e->regno] + : &vstate->frame[e->frameno]->stack[e->spi].spilled_ptr; if (reg->type != SCALAR_VALUE || reg == known_reg) continue; if ((reg->id & ~BPF_ADD_CONST) != (known_reg->id & ~BPF_ADD_CONST)) @@ -15112,7 +15299,7 @@ static void find_equal_scalars(struct bpf_verifier_state *vstate, copy_register_state(reg, known_reg); /* * Must preserve off, id and add_const flag, - * otherwise another find_equal_scalars() will be incorrect. + * otherwise another sync_linked_regs() will be incorrect. */ reg->off = saved_off; @@ -15120,7 +15307,7 @@ static void find_equal_scalars(struct bpf_verifier_state *vstate, scalar_min_max_add(reg, &fake_reg); reg->var_off = tnum_add(reg->var_off, fake_reg.var_off); } - })); + } } static int check_cond_jmp_op(struct bpf_verifier_env *env, @@ -15131,6 +15318,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, struct bpf_reg_state *regs = this_branch->frame[this_branch->curframe]->regs; struct bpf_reg_state *dst_reg, *other_branch_regs, *src_reg = NULL; struct bpf_reg_state *eq_branch_regs; + struct linked_regs linked_regs = {}; u8 opcode = BPF_OP(insn->code); bool is_jmp32; int pred = -1; @@ -15245,6 +15433,21 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, return 0; } + /* Push scalar registers sharing same ID to jump history, + * do this before creating 'other_branch', so that both + * 'this_branch' and 'other_branch' share this history + * if parent state is created. + */ + if (BPF_SRC(insn->code) == BPF_X && src_reg->type == SCALAR_VALUE && src_reg->id) + collect_linked_regs(this_branch, src_reg->id, &linked_regs); + if (dst_reg->type == SCALAR_VALUE && dst_reg->id) + collect_linked_regs(this_branch, dst_reg->id, &linked_regs); + if (linked_regs.cnt > 1) { + err = push_jmp_history(env, this_branch, 0, linked_regs_pack(&linked_regs)); + if (err) + return err; + } + other_branch = push_stack(env, *insn_idx + insn->off + 1, *insn_idx, false); if (!other_branch) @@ -15275,13 +15478,13 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, if (BPF_SRC(insn->code) == BPF_X && src_reg->type == SCALAR_VALUE && src_reg->id && !WARN_ON_ONCE(src_reg->id != other_branch_regs[insn->src_reg].id)) { - find_equal_scalars(this_branch, src_reg); - find_equal_scalars(other_branch, &other_branch_regs[insn->src_reg]); + sync_linked_regs(this_branch, src_reg, &linked_regs); + sync_linked_regs(other_branch, &other_branch_regs[insn->src_reg], &linked_regs); } if (dst_reg->type == SCALAR_VALUE && dst_reg->id && !WARN_ON_ONCE(dst_reg->id != other_branch_regs[insn->dst_reg].id)) { - find_equal_scalars(this_branch, dst_reg); - find_equal_scalars(other_branch, &other_branch_regs[insn->dst_reg]); + sync_linked_regs(this_branch, dst_reg, &linked_regs); + sync_linked_regs(other_branch, &other_branch_regs[insn->dst_reg], &linked_regs); } /* if one pointer register is compared to another pointer @@ -16770,7 +16973,7 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, * * First verification path is [1-6]: * - at (4) same bpf_reg_state::id (b) would be assigned to r6 and r7; - * - at (5) r6 would be marked <= X, find_equal_scalars() would also mark + * - at (5) r6 would be marked <= X, sync_linked_regs() would also mark * r7 <= X, because r6 and r7 share same id. * Next verification path is [1-4, 6]. * @@ -17563,7 +17766,7 @@ hit: * the current state. */ if (is_jmp_point(env, env->insn_idx)) - err = err ? : push_jmp_history(env, cur, 0); + err = err ? : push_jmp_history(env, cur, 0, 0); err = err ? : propagate_precision(env, &sl->state); if (err) return err; @@ -17831,7 +18034,7 @@ static int do_check(struct bpf_verifier_env *env) } if (is_jmp_point(env, env->insn_idx)) { - err = push_jmp_history(env, state, 0); + err = push_jmp_history(env, state, 0, 0); if (err) return err; } diff --git a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c index 6a6fad625f7e..9d415f7ce599 100644 --- a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c +++ b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c @@ -278,7 +278,7 @@ __msg("mark_precise: frame0: last_idx 14 first_idx 9") __msg("mark_precise: frame0: regs=r6 stack= before 13: (bf) r1 = r7") __msg("mark_precise: frame0: regs=r6 stack= before 12: (27) r6 *= 4") __msg("mark_precise: frame0: regs=r6 stack= before 11: (25) if r6 > 0x3 goto pc+4") -__msg("mark_precise: frame0: regs=r6 stack= before 10: (bf) r6 = r0") +__msg("mark_precise: frame0: regs=r0,r6 stack= before 10: (bf) r6 = r0") __msg("mark_precise: frame0: regs=r0 stack= before 9: (85) call bpf_loop") /* State entering callback body popped from states stack */ __msg("from 9 to 17: frame1:") diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c index 90643ccc221d..64d722199e8f 100644 --- a/tools/testing/selftests/bpf/verifier/precise.c +++ b/tools/testing/selftests/bpf/verifier/precise.c @@ -39,11 +39,11 @@ .result = VERBOSE_ACCEPT, .errstr = "mark_precise: frame0: last_idx 26 first_idx 20\ - mark_precise: frame0: regs=r2,r9 stack= before 25\ - mark_precise: frame0: regs=r2,r9 stack= before 24\ - mark_precise: frame0: regs=r2,r9 stack= before 23\ - mark_precise: frame0: regs=r2,r9 stack= before 22\ - mark_precise: frame0: regs=r2,r9 stack= before 20\ + mark_precise: frame0: regs=r2 stack= before 25\ + mark_precise: frame0: regs=r2 stack= before 24\ + mark_precise: frame0: regs=r2 stack= before 23\ + mark_precise: frame0: regs=r2 stack= before 22\ + mark_precise: frame0: regs=r2 stack= before 20\ mark_precise: frame0: parent state regs=r2,r9 stack=:\ mark_precise: frame0: last_idx 19 first_idx 10\ mark_precise: frame0: regs=r2,r9 stack= before 19\ @@ -100,11 +100,11 @@ .errstr = "26: (85) call bpf_probe_read_kernel#113\ mark_precise: frame0: last_idx 26 first_idx 22\ - mark_precise: frame0: regs=r2,r9 stack= before 25\ - mark_precise: frame0: regs=r2,r9 stack= before 24\ - mark_precise: frame0: regs=r2,r9 stack= before 23\ - mark_precise: frame0: regs=r2,r9 stack= before 22\ - mark_precise: frame0: parent state regs=r2,r9 stack=:\ + mark_precise: frame0: regs=r2 stack= before 25\ + mark_precise: frame0: regs=r2 stack= before 24\ + mark_precise: frame0: regs=r2 stack= before 23\ + mark_precise: frame0: regs=r2 stack= before 22\ + mark_precise: frame0: parent state regs=r2 stack=:\ mark_precise: frame0: last_idx 20 first_idx 20\ mark_precise: frame0: regs=r2,r9 stack= before 20\ mark_precise: frame0: parent state regs=r2,r9 stack=:\ -- cgit v1.2.3 From e42ac14180554fa23a3312d4f921dc4ea7972fb7 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Mon, 22 Jul 2024 11:30:45 -0700 Subject: bpf: Check unsupported ops from the bpf_struct_ops's cfi_stubs The bpf_tcp_ca struct_ops currently uses a "u32 unsupported_ops[]" array to track which ops is not supported. After cfi_stubs had been added, the function pointer in cfi_stubs is also NULL for the unsupported ops. Thus, the "u32 unsupported_ops[]" becomes redundant. This observation was originally brought up in the bpf/cfi discussion: https://lore.kernel.org/bpf/CAADnVQJoEkdjyCEJRPASjBw1QGsKYrF33QdMGc1RZa9b88bAEA@mail.gmail.com/ The recent bpf qdisc patch (https://lore.kernel.org/bpf/20240714175130.4051012-6-amery.hung@bytedance.com/) also needs to specify quite many unsupported ops. It is a good time to clean it up. This patch removes the need of "u32 unsupported_ops[]" and tests for null-ness in the cfi_stubs instead. Testing the cfi_stubs is done in a new function bpf_struct_ops_supported(). The verifier will call bpf_struct_ops_supported() when loading the struct_ops program. The ".check_member" is removed from the bpf_tcp_ca in this patch. ".check_member" could still be useful for other subsytems to enforce other restrictions (e.g. sched_ext checks for prog->sleepable). To keep the same error return, ENOTSUPP is used. Cc: Amery Hung Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20240722183049.2254692-2-martin.lau@linux.dev Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko --- include/linux/bpf.h | 5 +++++ kernel/bpf/bpf_struct_ops.c | 7 +++++++ kernel/bpf/verifier.c | 10 +++++++++- net/ipv4/bpf_tcp_ca.c | 26 -------------------------- 4 files changed, 21 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 3b94ec161e8c..4c54864316ee 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1795,6 +1795,7 @@ struct bpf_struct_ops_common_value { #define BPF_MODULE_OWNER ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA)) bool bpf_struct_ops_get(const void *kdata); void bpf_struct_ops_put(const void *kdata); +int bpf_struct_ops_supported(const struct bpf_struct_ops *st_ops, u32 moff); int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, void *value); int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks, @@ -1851,6 +1852,10 @@ static inline void bpf_module_put(const void *data, struct module *owner) { module_put(owner); } +static inline int bpf_struct_ops_supported(const struct bpf_struct_ops *st_ops, u32 moff) +{ + return -ENOTSUPP; +} static inline int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, void *value) diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index bb3eabc0dc76..fda3dd2ee984 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -1040,6 +1040,13 @@ void bpf_struct_ops_put(const void *kdata) bpf_map_put(&st_map->map); } +int bpf_struct_ops_supported(const struct bpf_struct_ops *st_ops, u32 moff) +{ + void *func_ptr = *(void **)(st_ops->cfi_stubs + moff); + + return func_ptr ? 0 : -ENOTSUPP; +} + static bool bpf_struct_ops_valid_to_reg(struct bpf_map *map) { struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f8c474e8e597..247a038d3a14 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -21132,6 +21132,7 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) u32 btf_id, member_idx; struct btf *btf; const char *mname; + int err; if (!prog->gpl_compatible) { verbose(env, "struct ops programs must have a GPL compatible license\n"); @@ -21179,8 +21180,15 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) return -EINVAL; } + err = bpf_struct_ops_supported(st_ops, __btf_member_bit_offset(t, member) / 8); + if (err) { + verbose(env, "attach to unsupported member %s of struct %s\n", + mname, st_ops->name); + return err; + } + if (st_ops->check_member) { - int err = st_ops->check_member(t, member, prog); + err = st_ops->check_member(t, member, prog); if (err) { verbose(env, "attach to unsupported member %s of struct %s\n", diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 3f88d0961e5b..554804774628 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -14,10 +14,6 @@ /* "extern" is to avoid sparse warning. It is only used in bpf_struct_ops.c. */ static struct bpf_struct_ops bpf_tcp_congestion_ops; -static u32 unsupported_ops[] = { - offsetof(struct tcp_congestion_ops, get_info), -}; - static const struct btf_type *tcp_sock_type; static u32 tcp_sock_id, sock_id; static const struct btf_type *tcp_congestion_ops_type; @@ -45,18 +41,6 @@ static int bpf_tcp_ca_init(struct btf *btf) return 0; } -static bool is_unsupported(u32 member_offset) -{ - unsigned int i; - - for (i = 0; i < ARRAY_SIZE(unsupported_ops); i++) { - if (member_offset == unsupported_ops[i]) - return true; - } - - return false; -} - static bool bpf_tcp_ca_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, @@ -251,15 +235,6 @@ static int bpf_tcp_ca_init_member(const struct btf_type *t, return 0; } -static int bpf_tcp_ca_check_member(const struct btf_type *t, - const struct btf_member *member, - const struct bpf_prog *prog) -{ - if (is_unsupported(__btf_member_bit_offset(t, member) / 8)) - return -ENOTSUPP; - return 0; -} - static int bpf_tcp_ca_reg(void *kdata, struct bpf_link *link) { return tcp_register_congestion_control(kdata); @@ -354,7 +329,6 @@ static struct bpf_struct_ops bpf_tcp_congestion_ops = { .reg = bpf_tcp_ca_reg, .unreg = bpf_tcp_ca_unreg, .update = bpf_tcp_ca_update, - .check_member = bpf_tcp_ca_check_member, .init_member = bpf_tcp_ca_init_member, .init = bpf_tcp_ca_init, .validate = bpf_tcp_ca_validate, -- cgit v1.2.3 From 52dea0a15cc888e89f0144dca7b712fb56d12a28 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 10 Jun 2024 18:42:28 +0200 Subject: posix-timers: Convert timer list to hlist No requirement for a real list. Spare a few bytes. Signed-off-by: Thomas Gleixner Signed-off-by: Frederic Weisbecker Acked-by: Peter Zijlstra (Intel) --- fs/proc/base.c | 6 +++--- include/linux/posix-timers.h | 2 +- include/linux/sched/signal.h | 2 +- init/init_task.c | 2 +- kernel/fork.c | 2 +- kernel/time/posix-timers.c | 19 ++++++++----------- 6 files changed, 15 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/base.c b/fs/proc/base.c index 72a1acd03675..dd579332a7f8 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2456,13 +2456,13 @@ static void *timers_start(struct seq_file *m, loff_t *pos) if (!tp->sighand) return ERR_PTR(-ESRCH); - return seq_list_start(&tp->task->signal->posix_timers, *pos); + return seq_hlist_start(&tp->task->signal->posix_timers, *pos); } static void *timers_next(struct seq_file *m, void *v, loff_t *pos) { struct timers_private *tp = m->private; - return seq_list_next(v, &tp->task->signal->posix_timers, pos); + return seq_hlist_next(v, &tp->task->signal->posix_timers, pos); } static void timers_stop(struct seq_file *m, void *v) @@ -2491,7 +2491,7 @@ static int show_timer(struct seq_file *m, void *v) [SIGEV_THREAD] = "thread", }; - timer = list_entry((struct list_head *)v, struct k_itimer, list); + timer = hlist_entry((struct hlist_node *)v, struct k_itimer, list); notify = timer->it_sigev_notify; seq_printf(m, "ID: %d\n", timer->it_id); diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index dc7b738de299..453691710839 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -158,7 +158,7 @@ static inline void posix_cputimers_init_work(void) { } * @rcu: RCU head for freeing the timer. */ struct k_itimer { - struct list_head list; + struct hlist_node list; struct hlist_node t_hash; spinlock_t it_lock; const struct k_clock *kclock; diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 0a0e23c45406..622fdef78e14 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -137,7 +137,7 @@ struct signal_struct { /* POSIX.1b Interval Timers */ unsigned int next_posix_timer_id; - struct list_head posix_timers; + struct hlist_head posix_timers; /* ITIMER_REAL timer for the process */ struct hrtimer real_timer; diff --git a/init/init_task.c b/init/init_task.c index eeb110c65fe2..5d0399bc8d2f 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -29,7 +29,7 @@ static struct signal_struct init_signals = { .cred_guard_mutex = __MUTEX_INITIALIZER(init_signals.cred_guard_mutex), .exec_update_lock = __RWSEM_INITIALIZER(init_signals.exec_update_lock), #ifdef CONFIG_POSIX_TIMERS - .posix_timers = LIST_HEAD_INIT(init_signals.posix_timers), + .posix_timers = HLIST_HEAD_INIT, .cputimer = { .cputime_atomic = INIT_CPUTIME_ATOMIC, }, diff --git a/kernel/fork.c b/kernel/fork.c index cc760491f201..c1b343cba560 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1861,7 +1861,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) prev_cputime_init(&sig->prev_cputime); #ifdef CONFIG_POSIX_TIMERS - INIT_LIST_HEAD(&sig->posix_timers); + INIT_HLIST_HEAD(&sig->posix_timers); hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); sig->real_timer.function = it_real_fn; #endif diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 53a993e4dbfa..fa75e9493fd6 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -515,7 +515,7 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event, spin_lock_irq(¤t->sighand->siglock); /* This makes the timer valid in the hash table */ WRITE_ONCE(new_timer->it_signal, current->signal); - list_add(&new_timer->list, ¤t->signal->posix_timers); + hlist_add_head(&new_timer->list, ¤t->signal->posix_timers); spin_unlock_irq(¤t->sighand->siglock); /* * After unlocking sighand::siglock @new_timer is subject to @@ -1025,7 +1025,7 @@ retry_delete: } spin_lock(¤t->sighand->siglock); - list_del(&timer->list); + hlist_del(&timer->list); spin_unlock(¤t->sighand->siglock); /* * A concurrent lookup could check timer::it_signal lockless. It @@ -1075,7 +1075,7 @@ retry_delete: goto retry_delete; } - list_del(&timer->list); + hlist_del(&timer->list); /* * Setting timer::it_signal to NULL is technically not required @@ -1096,22 +1096,19 @@ retry_delete: */ void exit_itimers(struct task_struct *tsk) { - struct list_head timers; - struct k_itimer *tmr; + struct hlist_head timers; - if (list_empty(&tsk->signal->posix_timers)) + if (hlist_empty(&tsk->signal->posix_timers)) return; /* Protect against concurrent read via /proc/$PID/timers */ spin_lock_irq(&tsk->sighand->siglock); - list_replace_init(&tsk->signal->posix_timers, &timers); + hlist_move_list(&tsk->signal->posix_timers, &timers); spin_unlock_irq(&tsk->sighand->siglock); /* The timers are not longer accessible via tsk::signal */ - while (!list_empty(&timers)) { - tmr = list_first_entry(&timers, struct k_itimer, list); - itimer_delete(tmr); - } + while (!hlist_empty(&timers)) + itimer_delete(hlist_entry(timers.first, struct k_itimer, list)); } SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock, -- cgit v1.2.3 From a2b80ce87a87fc18c594e74d13031d5e347b69cb Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 10 Jun 2024 18:42:33 +0200 Subject: signal: Remove task argument from dequeue_signal() The task pointer which is handed to dequeue_signal() is always current. The argument along with the first comment about signalfd in that function is confusing at best. Remove it and use current internally. Update the stale comment for dequeue_signal() while at it. Signed-off-by: Thomas Gleixner Signed-off-by: Frederic Weisbecker Reviewed-by: Oleg Nesterov Acked-by: Peter Zijlstra (Intel) --- fs/signalfd.c | 4 ++-- include/linux/sched/signal.h | 5 ++--- kernel/signal.c | 23 ++++++++++------------- 3 files changed, 14 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/fs/signalfd.c b/fs/signalfd.c index ec7b2da2477a..d0333bce015e 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -159,7 +159,7 @@ static ssize_t signalfd_dequeue(struct signalfd_ctx *ctx, kernel_siginfo_t *info DECLARE_WAITQUEUE(wait, current); spin_lock_irq(¤t->sighand->siglock); - ret = dequeue_signal(current, &ctx->sigmask, info, &type); + ret = dequeue_signal(&ctx->sigmask, info, &type); switch (ret) { case 0: if (!nonblock) @@ -174,7 +174,7 @@ static ssize_t signalfd_dequeue(struct signalfd_ctx *ctx, kernel_siginfo_t *info add_wait_queue(¤t->sighand->signalfd_wqh, &wait); for (;;) { set_current_state(TASK_INTERRUPTIBLE); - ret = dequeue_signal(current, &ctx->sigmask, info, &type); + ret = dequeue_signal(&ctx->sigmask, info, &type); if (ret != 0) break; if (signal_pending(current)) { diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 622fdef78e14..c8ed09ac29ac 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -276,8 +276,7 @@ static inline void signal_set_stop_flags(struct signal_struct *sig, extern void flush_signals(struct task_struct *); extern void ignore_signals(struct task_struct *); extern void flush_signal_handlers(struct task_struct *, int force_default); -extern int dequeue_signal(struct task_struct *task, sigset_t *mask, - kernel_siginfo_t *info, enum pid_type *type); +extern int dequeue_signal(sigset_t *mask, kernel_siginfo_t *info, enum pid_type *type); static inline int kernel_dequeue_signal(void) { @@ -287,7 +286,7 @@ static inline int kernel_dequeue_signal(void) int ret; spin_lock_irq(&task->sighand->siglock); - ret = dequeue_signal(task, &task->blocked, &__info, &__type); + ret = dequeue_signal(&task->blocked, &__info, &__type); spin_unlock_irq(&task->sighand->siglock); return ret; diff --git a/kernel/signal.c b/kernel/signal.c index 60c737e423a1..897765b254f9 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -618,20 +618,18 @@ static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, } /* - * Dequeue a signal and return the element to the caller, which is - * expected to free it. - * - * All callers have to hold the siglock. + * Try to dequeue a signal. If a deliverable signal is found fill in the + * caller provided siginfo and return the signal number. Otherwise return + * 0. */ -int dequeue_signal(struct task_struct *tsk, sigset_t *mask, - kernel_siginfo_t *info, enum pid_type *type) +int dequeue_signal(sigset_t *mask, kernel_siginfo_t *info, enum pid_type *type) { + struct task_struct *tsk = current; bool resched_timer = false; int signr; - /* We only dequeue private signals from ourselves, we don't let - * signalfd steal them - */ + lockdep_assert_held(&tsk->sighand->siglock); + *type = PIDTYPE_PID; signr = __dequeue_signal(&tsk->pending, mask, info, &resched_timer); if (!signr) { @@ -2793,8 +2791,7 @@ relock: type = PIDTYPE_PID; signr = dequeue_synchronous_signal(&ksig->info); if (!signr) - signr = dequeue_signal(current, ¤t->blocked, - &ksig->info, &type); + signr = dequeue_signal(¤t->blocked, &ksig->info, &type); if (!signr) break; /* will return 0 */ @@ -3648,7 +3645,7 @@ static int do_sigtimedwait(const sigset_t *which, kernel_siginfo_t *info, signotset(&mask); spin_lock_irq(&tsk->sighand->siglock); - sig = dequeue_signal(tsk, &mask, info, &type); + sig = dequeue_signal(&mask, info, &type); if (!sig && timeout) { /* * None ready, temporarily unblock those we're interested @@ -3667,7 +3664,7 @@ static int do_sigtimedwait(const sigset_t *which, kernel_siginfo_t *info, spin_lock_irq(&tsk->sighand->siglock); __set_task_blocked(tsk, &tsk->real_blocked); sigemptyset(&tsk->real_blocked); - sig = dequeue_signal(tsk, &mask, info, &type); + sig = dequeue_signal(&mask, info, &type); } spin_unlock_irq(&tsk->sighand->siglock); -- cgit v1.2.3 From 5d99e198be279045e6ecefe220f5c52f8ce9bfd5 Mon Sep 17 00:00:00 2001 From: Xu Kuohai Date: Fri, 19 Jul 2024 19:00:52 +0800 Subject: bpf, lsm: Add check for BPF LSM return value A bpf prog returning a positive number attached to file_alloc_security hook makes kernel panic. This happens because file system can not filter out the positive number returned by the LSM prog using IS_ERR, and misinterprets this positive number as a file pointer. Given that hook file_alloc_security never returned positive number before the introduction of BPF LSM, and other BPF LSM hooks may encounter similar issues, this patch adds LSM return value check in verifier, to ensure no unexpected value is returned. Fixes: 520b7aa00d8c ("bpf: lsm: Initialize the BPF LSM hooks") Reported-by: Xin Liu Signed-off-by: Xu Kuohai Acked-by: Eduard Zingerman Link: https://lore.kernel.org/r/20240719110059.797546-3-xukuohai@huaweicloud.com Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko --- include/linux/bpf.h | 1 + include/linux/bpf_lsm.h | 8 +++++++ kernel/bpf/bpf_lsm.c | 34 +++++++++++++++++++++++++++- kernel/bpf/btf.c | 5 ++++- kernel/bpf/verifier.c | 60 +++++++++++++++++++++++++++++++++++++++++-------- 5 files changed, 97 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4c54864316ee..5739cc9986f8 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -927,6 +927,7 @@ struct bpf_insn_access_aux { }; }; struct bpf_verifier_log *log; /* for verbose logs */ + bool is_retval; /* is accessing function return value ? */ }; static inline void diff --git a/include/linux/bpf_lsm.h b/include/linux/bpf_lsm.h index 1de7ece5d36d..aefcd6564251 100644 --- a/include/linux/bpf_lsm.h +++ b/include/linux/bpf_lsm.h @@ -9,6 +9,7 @@ #include #include +#include #include #ifdef CONFIG_BPF_LSM @@ -45,6 +46,8 @@ void bpf_inode_storage_free(struct inode *inode); void bpf_lsm_find_cgroup_shim(const struct bpf_prog *prog, bpf_func_t *bpf_func); +int bpf_lsm_get_retval_range(const struct bpf_prog *prog, + struct bpf_retval_range *range); #else /* !CONFIG_BPF_LSM */ static inline bool bpf_lsm_is_sleepable_hook(u32 btf_id) @@ -78,6 +81,11 @@ static inline void bpf_lsm_find_cgroup_shim(const struct bpf_prog *prog, { } +static inline int bpf_lsm_get_retval_range(const struct bpf_prog *prog, + struct bpf_retval_range *range) +{ + return -EOPNOTSUPP; +} #endif /* CONFIG_BPF_LSM */ #endif /* _LINUX_BPF_LSM_H */ diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 1f596ad6257c..6292ac5f9bd1 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include @@ -417,3 +416,36 @@ const struct bpf_verifier_ops lsm_verifier_ops = { .get_func_proto = bpf_lsm_func_proto, .is_valid_access = btf_ctx_access, }; + +/* hooks return 0 or 1 */ +BTF_SET_START(bool_lsm_hooks) +#ifdef CONFIG_SECURITY_NETWORK_XFRM +BTF_ID(func, bpf_lsm_xfrm_state_pol_flow_match) +#endif +#ifdef CONFIG_AUDIT +BTF_ID(func, bpf_lsm_audit_rule_known) +#endif +BTF_ID(func, bpf_lsm_inode_xattr_skipcap) +BTF_SET_END(bool_lsm_hooks) + +int bpf_lsm_get_retval_range(const struct bpf_prog *prog, + struct bpf_retval_range *retval_range) +{ + /* no return value range for void hooks */ + if (!prog->aux->attach_func_proto->type) + return -EINVAL; + + if (btf_id_set_contains(&bool_lsm_hooks, prog->aux->attach_btf_id)) { + retval_range->minval = 0; + retval_range->maxval = 1; + } else { + /* All other available LSM hooks, except task_prctl, return 0 + * on success and negative error code on failure. + * To keep things simple, we only allow bpf progs to return 0 + * or negative errno for task_prctl too. + */ + retval_range->minval = -MAX_ERRNO; + retval_range->maxval = 0; + } + return 0; +} diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 520f49f422fe..95426d5b634e 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6416,8 +6416,11 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, if (arg == nr_args) { switch (prog->expected_attach_type) { - case BPF_LSM_CGROUP: case BPF_LSM_MAC: + /* mark we are accessing the return value */ + info->is_retval = true; + fallthrough; + case BPF_LSM_CGROUP: case BPF_TRACE_FEXIT: /* When LSM programs are attached to void LSM hooks * they use FEXIT trampolines and when attached to diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 247a038d3a14..8caa7322f031 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2334,6 +2334,25 @@ static void mark_reg_unknown(struct bpf_verifier_env *env, __mark_reg_unknown(env, regs + regno); } +static int __mark_reg_s32_range(struct bpf_verifier_env *env, + struct bpf_reg_state *regs, + u32 regno, + s32 s32_min, + s32 s32_max) +{ + struct bpf_reg_state *reg = regs + regno; + + reg->s32_min_value = max_t(s32, reg->s32_min_value, s32_min); + reg->s32_max_value = min_t(s32, reg->s32_max_value, s32_max); + + reg->smin_value = max_t(s64, reg->smin_value, s32_min); + reg->smax_value = min_t(s64, reg->smax_value, s32_max); + + reg_bounds_sync(reg); + + return reg_bounds_sanity_check(env, reg, "s32_range"); +} + static void __mark_reg_not_init(const struct bpf_verifier_env *env, struct bpf_reg_state *reg) { @@ -5607,11 +5626,12 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, /* check access to 'struct bpf_context' fields. Supports fixed offsets only */ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, int size, enum bpf_access_type t, enum bpf_reg_type *reg_type, - struct btf **btf, u32 *btf_id) + struct btf **btf, u32 *btf_id, bool *is_retval) { struct bpf_insn_access_aux info = { .reg_type = *reg_type, .log = &env->log, + .is_retval = false, }; if (env->ops->is_valid_access && @@ -5624,6 +5644,7 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, * type of narrower access. */ *reg_type = info.reg_type; + *is_retval = info.is_retval; if (base_type(*reg_type) == PTR_TO_BTF_ID) { *btf = info.btf; @@ -6792,6 +6813,17 @@ static int check_stack_access_within_bounds( return grow_stack_state(env, state, -min_off /* size */); } +static bool get_func_retval_range(struct bpf_prog *prog, + struct bpf_retval_range *range) +{ + if (prog->type == BPF_PROG_TYPE_LSM && + prog->expected_attach_type == BPF_LSM_MAC && + !bpf_lsm_get_retval_range(prog, range)) { + return true; + } + return false; +} + /* check whether memory at (regno + off) is accessible for t = (read | write) * if t==write, value_regno is a register which value is stored into memory * if t==read, value_regno is a register which will receive the value from memory @@ -6896,6 +6928,8 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (!err && value_regno >= 0 && (t == BPF_READ || rdonly_mem)) mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_CTX) { + bool is_retval = false; + struct bpf_retval_range range; enum bpf_reg_type reg_type = SCALAR_VALUE; struct btf *btf = NULL; u32 btf_id = 0; @@ -6911,7 +6945,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn return err; err = check_ctx_access(env, insn_idx, off, size, t, ®_type, &btf, - &btf_id); + &btf_id, &is_retval); if (err) verbose_linfo(env, insn_idx, "; "); if (!err && t == BPF_READ && value_regno >= 0) { @@ -6920,7 +6954,14 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn * case, we know the offset is zero. */ if (reg_type == SCALAR_VALUE) { - mark_reg_unknown(env, regs, value_regno); + if (is_retval && get_func_retval_range(env->prog, &range)) { + err = __mark_reg_s32_range(env, regs, value_regno, + range.minval, range.maxval); + if (err) + return err; + } else { + mark_reg_unknown(env, regs, value_regno); + } } else { mark_reg_known_zero(env, regs, value_regno); @@ -15762,12 +15803,13 @@ static int check_return_code(struct bpf_verifier_env *env, int regno, const char case BPF_PROG_TYPE_LSM: if (env->prog->expected_attach_type != BPF_LSM_CGROUP) { - /* Regular BPF_PROG_TYPE_LSM programs can return - * any value. - */ - return 0; - } - if (!env->prog->aux->attach_func_proto->type) { + /* no range found, any return value is allowed */ + if (!get_func_retval_range(env->prog, &range)) + return 0; + /* no restricted range, any return value is allowed */ + if (range.minval == S32_MIN && range.maxval == S32_MAX) + return 0; + } else if (!env->prog->aux->attach_func_proto->type) { /* Make sure programs that attach to void * hooks don't try to modify return value. */ -- cgit v1.2.3 From 28ead3eaabc16ecc907cfb71876da028080f6356 Mon Sep 17 00:00:00 2001 From: Xu Kuohai Date: Fri, 19 Jul 2024 19:00:53 +0800 Subject: bpf: Prevent tail call between progs attached to different hooks bpf progs can be attached to kernel functions, and the attached functions can take different parameters or return different return values. If prog attached to one kernel function tail calls prog attached to another kernel function, the ctx access or return value verification could be bypassed. For example, if prog1 is attached to func1 which takes only 1 parameter and prog2 is attached to func2 which takes two parameters. Since verifier assumes the bpf ctx passed to prog2 is constructed based on func2's prototype, verifier allows prog2 to access the second parameter from the bpf ctx passed to it. The problem is that verifier does not prevent prog1 from passing its bpf ctx to prog2 via tail call. In this case, the bpf ctx passed to prog2 is constructed from func1 instead of func2, that is, the assumption for ctx access verification is bypassed. Another example, if BPF LSM prog1 is attached to hook file_alloc_security, and BPF LSM prog2 is attached to hook bpf_lsm_audit_rule_known. Verifier knows the return value rules for these two hooks, e.g. it is legal for bpf_lsm_audit_rule_known to return positive number 1, and it is illegal for file_alloc_security to return positive number. So verifier allows prog2 to return positive number 1, but does not allow prog1 to return positive number. The problem is that verifier does not prevent prog1 from calling prog2 via tail call. In this case, prog2's return value 1 will be used as the return value for prog1's hook file_alloc_security. That is, the return value rule is bypassed. This patch adds restriction for tail call to prevent such bypasses. Signed-off-by: Xu Kuohai Link: https://lore.kernel.org/r/20240719110059.797546-4-xukuohai@huaweicloud.com Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko --- include/linux/bpf.h | 1 + kernel/bpf/core.c | 21 ++++++++++++++++++--- 2 files changed, 19 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 5739cc9986f8..f16d0753f518 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -294,6 +294,7 @@ struct bpf_map { * same prog type, JITed flag and xdp_has_frags flag. */ struct { + const struct btf_type *attach_func_proto; spinlock_t lock; enum bpf_prog_type type; bool jited; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 7ee62e38faf0..4e07cc057d6f 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2302,6 +2302,7 @@ bool bpf_prog_map_compatible(struct bpf_map *map, { enum bpf_prog_type prog_type = resolve_prog_type(fp); bool ret; + struct bpf_prog_aux *aux = fp->aux; if (fp->kprobe_override) return false; @@ -2311,7 +2312,7 @@ bool bpf_prog_map_compatible(struct bpf_map *map, * in the case of devmap and cpumap). Until device checks * are implemented, prohibit adding dev-bound programs to program maps. */ - if (bpf_prog_is_dev_bound(fp->aux)) + if (bpf_prog_is_dev_bound(aux)) return false; spin_lock(&map->owner.lock); @@ -2321,12 +2322,26 @@ bool bpf_prog_map_compatible(struct bpf_map *map, */ map->owner.type = prog_type; map->owner.jited = fp->jited; - map->owner.xdp_has_frags = fp->aux->xdp_has_frags; + map->owner.xdp_has_frags = aux->xdp_has_frags; + map->owner.attach_func_proto = aux->attach_func_proto; ret = true; } else { ret = map->owner.type == prog_type && map->owner.jited == fp->jited && - map->owner.xdp_has_frags == fp->aux->xdp_has_frags; + map->owner.xdp_has_frags == aux->xdp_has_frags; + if (ret && + map->owner.attach_func_proto != aux->attach_func_proto) { + switch (prog_type) { + case BPF_PROG_TYPE_TRACING: + case BPF_PROG_TYPE_LSM: + case BPF_PROG_TYPE_EXT: + case BPF_PROG_TYPE_STRUCT_OPS: + ret = false; + break; + default: + break; + } + } } spin_unlock(&map->owner.lock); -- cgit v1.2.3 From 2aff9d20d50ac45dd13a013ef5231f4fb8912356 Mon Sep 17 00:00:00 2001 From: Casey Schaufler Date: Wed, 10 Jul 2024 14:32:25 -0700 Subject: lsm: infrastructure management of the sock security Move management of the sock->sk_security blob out of the individual security modules and into the security infrastructure. Instead of allocating the blobs from within the modules the modules tell the infrastructure how much space is required, and the space is allocated there. Acked-by: Paul Moore Reviewed-by: Kees Cook Reviewed-by: John Johansen Acked-by: Stephen Smalley Signed-off-by: Casey Schaufler [PM: subject tweak] Signed-off-by: Paul Moore --- include/linux/lsm_hooks.h | 1 + security/apparmor/include/net.h | 3 +- security/apparmor/lsm.c | 17 +-------- security/apparmor/net.c | 2 +- security/security.c | 36 +++++++++++++++++- security/selinux/hooks.c | 80 ++++++++++++++++++--------------------- security/selinux/include/objsec.h | 5 +++ security/selinux/netlabel.c | 23 +++++------ security/smack/smack.h | 5 +++ security/smack/smack_lsm.c | 70 ++++++++++++++++------------------ security/smack/smack_netfilter.c | 4 +- 11 files changed, 133 insertions(+), 113 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index a2ade0ffe9e7..efd4a0655159 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -73,6 +73,7 @@ struct lsm_blob_sizes { int lbs_cred; int lbs_file; int lbs_inode; + int lbs_sock; int lbs_superblock; int lbs_ipc; int lbs_msg_msg; diff --git a/security/apparmor/include/net.h b/security/apparmor/include/net.h index 67bf888c3bd6..c42ed8a73f1c 100644 --- a/security/apparmor/include/net.h +++ b/security/apparmor/include/net.h @@ -51,10 +51,9 @@ struct aa_sk_ctx { struct aa_label *peer; }; -#define SK_CTX(X) ((X)->sk_security) static inline struct aa_sk_ctx *aa_sock(const struct sock *sk) { - return sk->sk_security; + return sk->sk_security + apparmor_blob_sizes.lbs_sock; } #define DEFINE_AUDIT_NET(NAME, OP, SK, F, T, P) \ diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 808060f9effb..f5d05297d59e 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -1058,27 +1058,12 @@ static int apparmor_userns_create(const struct cred *cred) return error; } -static int apparmor_sk_alloc_security(struct sock *sk, int family, gfp_t flags) -{ - struct aa_sk_ctx *ctx; - - ctx = kzalloc(sizeof(*ctx), flags); - if (!ctx) - return -ENOMEM; - - sk->sk_security = ctx; - - return 0; -} - static void apparmor_sk_free_security(struct sock *sk) { struct aa_sk_ctx *ctx = aa_sock(sk); - sk->sk_security = NULL; aa_put_label(ctx->label); aa_put_label(ctx->peer); - kfree(ctx); } /** @@ -1433,6 +1418,7 @@ struct lsm_blob_sizes apparmor_blob_sizes __ro_after_init = { .lbs_cred = sizeof(struct aa_label *), .lbs_file = sizeof(struct aa_file_ctx), .lbs_task = sizeof(struct aa_task_ctx), + .lbs_sock = sizeof(struct aa_sk_ctx), }; static const struct lsm_id apparmor_lsmid = { @@ -1478,7 +1464,6 @@ static struct security_hook_list apparmor_hooks[] __ro_after_init = { LSM_HOOK_INIT(getprocattr, apparmor_getprocattr), LSM_HOOK_INIT(setprocattr, apparmor_setprocattr), - LSM_HOOK_INIT(sk_alloc_security, apparmor_sk_alloc_security), LSM_HOOK_INIT(sk_free_security, apparmor_sk_free_security), LSM_HOOK_INIT(sk_clone_security, apparmor_sk_clone_security), diff --git a/security/apparmor/net.c b/security/apparmor/net.c index 87e934b2b548..77413a519117 100644 --- a/security/apparmor/net.c +++ b/security/apparmor/net.c @@ -151,7 +151,7 @@ static int aa_label_sk_perm(const struct cred *subj_cred, const char *op, u32 request, struct sock *sk) { - struct aa_sk_ctx *ctx = SK_CTX(sk); + struct aa_sk_ctx *ctx = aa_sock(sk); int error = 0; AA_BUG(!label); diff --git a/security/security.c b/security/security.c index 8cee5b6c6e6d..9c3fb2f60e2a 100644 --- a/security/security.c +++ b/security/security.c @@ -29,6 +29,7 @@ #include #include #include +#include /* How many LSMs were built into the kernel? */ #define LSM_COUNT (__end_lsm_info - __start_lsm_info) @@ -227,6 +228,7 @@ static void __init lsm_set_blob_sizes(struct lsm_blob_sizes *needed) lsm_set_blob_size(&needed->lbs_inode, &blob_sizes.lbs_inode); lsm_set_blob_size(&needed->lbs_ipc, &blob_sizes.lbs_ipc); lsm_set_blob_size(&needed->lbs_msg_msg, &blob_sizes.lbs_msg_msg); + lsm_set_blob_size(&needed->lbs_sock, &blob_sizes.lbs_sock); lsm_set_blob_size(&needed->lbs_superblock, &blob_sizes.lbs_superblock); lsm_set_blob_size(&needed->lbs_task, &blob_sizes.lbs_task); lsm_set_blob_size(&needed->lbs_xattr_count, @@ -401,6 +403,7 @@ static void __init ordered_lsm_init(void) init_debug("inode blob size = %d\n", blob_sizes.lbs_inode); init_debug("ipc blob size = %d\n", blob_sizes.lbs_ipc); init_debug("msg_msg blob size = %d\n", blob_sizes.lbs_msg_msg); + init_debug("sock blob size = %d\n", blob_sizes.lbs_sock); init_debug("superblock blob size = %d\n", blob_sizes.lbs_superblock); init_debug("task blob size = %d\n", blob_sizes.lbs_task); init_debug("xattr slots = %d\n", blob_sizes.lbs_xattr_count); @@ -4673,6 +4676,28 @@ int security_socket_getpeersec_dgram(struct socket *sock, } EXPORT_SYMBOL(security_socket_getpeersec_dgram); +/** + * lsm_sock_alloc - allocate a composite sock blob + * @sock: the sock that needs a blob + * @priority: allocation mode + * + * Allocate the sock blob for all the modules + * + * Returns 0, or -ENOMEM if memory can't be allocated. + */ +static int lsm_sock_alloc(struct sock *sock, gfp_t priority) +{ + if (blob_sizes.lbs_sock == 0) { + sock->sk_security = NULL; + return 0; + } + + sock->sk_security = kzalloc(blob_sizes.lbs_sock, priority); + if (sock->sk_security == NULL) + return -ENOMEM; + return 0; +} + /** * security_sk_alloc() - Allocate and initialize a sock's LSM blob * @sk: sock @@ -4686,7 +4711,14 @@ EXPORT_SYMBOL(security_socket_getpeersec_dgram); */ int security_sk_alloc(struct sock *sk, int family, gfp_t priority) { - return call_int_hook(sk_alloc_security, sk, family, priority); + int rc = lsm_sock_alloc(sk, priority); + + if (unlikely(rc)) + return rc; + rc = call_int_hook(sk_alloc_security, sk, family, priority); + if (unlikely(rc)) + security_sk_free(sk); + return rc; } /** @@ -4698,6 +4730,8 @@ int security_sk_alloc(struct sock *sk, int family, gfp_t priority) void security_sk_free(struct sock *sk) { call_void_hook(sk_free_security, sk); + kfree(sk->sk_security); + sk->sk_security = NULL; } /** diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 55c78c318ccd..e08ffb1ddd5a 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -4584,7 +4584,7 @@ static int socket_sockcreate_sid(const struct task_security_struct *tsec, static int sock_has_perm(struct sock *sk, u32 perms) { - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); struct common_audit_data ad; struct lsm_network_audit net; @@ -4652,7 +4652,7 @@ static int selinux_socket_post_create(struct socket *sock, int family, isec->initialized = LABEL_INITIALIZED; if (sock->sk) { - sksec = sock->sk->sk_security; + sksec = selinux_sock(sock->sk); sksec->sclass = sclass; sksec->sid = sid; /* Allows detection of the first association on this socket */ @@ -4668,8 +4668,8 @@ static int selinux_socket_post_create(struct socket *sock, int family, static int selinux_socket_socketpair(struct socket *socka, struct socket *sockb) { - struct sk_security_struct *sksec_a = socka->sk->sk_security; - struct sk_security_struct *sksec_b = sockb->sk->sk_security; + struct sk_security_struct *sksec_a = selinux_sock(socka->sk); + struct sk_security_struct *sksec_b = selinux_sock(sockb->sk); sksec_a->peer_sid = sksec_b->sid; sksec_b->peer_sid = sksec_a->sid; @@ -4684,7 +4684,7 @@ static int selinux_socket_socketpair(struct socket *socka, static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, int addrlen) { struct sock *sk = sock->sk; - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); u16 family; int err; @@ -4824,7 +4824,7 @@ static int selinux_socket_connect_helper(struct socket *sock, struct sockaddr *address, int addrlen) { struct sock *sk = sock->sk; - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); int err; err = sock_has_perm(sk, SOCKET__CONNECT); @@ -5002,9 +5002,9 @@ static int selinux_socket_unix_stream_connect(struct sock *sock, struct sock *other, struct sock *newsk) { - struct sk_security_struct *sksec_sock = sock->sk_security; - struct sk_security_struct *sksec_other = other->sk_security; - struct sk_security_struct *sksec_new = newsk->sk_security; + struct sk_security_struct *sksec_sock = selinux_sock(sock); + struct sk_security_struct *sksec_other = selinux_sock(other); + struct sk_security_struct *sksec_new = selinux_sock(newsk); struct common_audit_data ad; struct lsm_network_audit net; int err; @@ -5033,8 +5033,8 @@ static int selinux_socket_unix_stream_connect(struct sock *sock, static int selinux_socket_unix_may_send(struct socket *sock, struct socket *other) { - struct sk_security_struct *ssec = sock->sk->sk_security; - struct sk_security_struct *osec = other->sk->sk_security; + struct sk_security_struct *ssec = selinux_sock(sock->sk); + struct sk_security_struct *osec = selinux_sock(other->sk); struct common_audit_data ad; struct lsm_network_audit net; @@ -5071,7 +5071,7 @@ static int selinux_sock_rcv_skb_compat(struct sock *sk, struct sk_buff *skb, u16 family) { int err = 0; - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); u32 sk_sid = sksec->sid; struct common_audit_data ad; struct lsm_network_audit net; @@ -5100,7 +5100,7 @@ static int selinux_sock_rcv_skb_compat(struct sock *sk, struct sk_buff *skb, static int selinux_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) { int err, peerlbl_active, secmark_active; - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); u16 family = sk->sk_family; u32 sk_sid = sksec->sid; struct common_audit_data ad; @@ -5168,7 +5168,7 @@ static int selinux_socket_getpeersec_stream(struct socket *sock, int err = 0; char *scontext = NULL; u32 scontext_len; - struct sk_security_struct *sksec = sock->sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sock->sk); u32 peer_sid = SECSID_NULL; if (sksec->sclass == SECCLASS_UNIX_STREAM_SOCKET || @@ -5228,34 +5228,27 @@ static int selinux_socket_getpeersec_dgram(struct socket *sock, static int selinux_sk_alloc_security(struct sock *sk, int family, gfp_t priority) { - struct sk_security_struct *sksec; - - sksec = kzalloc(sizeof(*sksec), priority); - if (!sksec) - return -ENOMEM; + struct sk_security_struct *sksec = selinux_sock(sk); sksec->peer_sid = SECINITSID_UNLABELED; sksec->sid = SECINITSID_UNLABELED; sksec->sclass = SECCLASS_SOCKET; selinux_netlbl_sk_security_reset(sksec); - sk->sk_security = sksec; return 0; } static void selinux_sk_free_security(struct sock *sk) { - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); - sk->sk_security = NULL; selinux_netlbl_sk_security_free(sksec); - kfree(sksec); } static void selinux_sk_clone_security(const struct sock *sk, struct sock *newsk) { - struct sk_security_struct *sksec = sk->sk_security; - struct sk_security_struct *newsksec = newsk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); + struct sk_security_struct *newsksec = selinux_sock(newsk); newsksec->sid = sksec->sid; newsksec->peer_sid = sksec->peer_sid; @@ -5269,7 +5262,7 @@ static void selinux_sk_getsecid(const struct sock *sk, u32 *secid) if (!sk) *secid = SECINITSID_ANY_SOCKET; else { - const struct sk_security_struct *sksec = sk->sk_security; + const struct sk_security_struct *sksec = selinux_sock(sk); *secid = sksec->sid; } @@ -5279,7 +5272,7 @@ static void selinux_sock_graft(struct sock *sk, struct socket *parent) { struct inode_security_struct *isec = inode_security_novalidate(SOCK_INODE(parent)); - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); if (sk->sk_family == PF_INET || sk->sk_family == PF_INET6 || sk->sk_family == PF_UNIX) @@ -5296,7 +5289,7 @@ static int selinux_sctp_process_new_assoc(struct sctp_association *asoc, { struct sock *sk = asoc->base.sk; u16 family = sk->sk_family; - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); struct common_audit_data ad; struct lsm_network_audit net; int err; @@ -5351,7 +5344,7 @@ static int selinux_sctp_process_new_assoc(struct sctp_association *asoc, static int selinux_sctp_assoc_request(struct sctp_association *asoc, struct sk_buff *skb) { - struct sk_security_struct *sksec = asoc->base.sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(asoc->base.sk); u32 conn_sid; int err; @@ -5384,7 +5377,7 @@ static int selinux_sctp_assoc_request(struct sctp_association *asoc, static int selinux_sctp_assoc_established(struct sctp_association *asoc, struct sk_buff *skb) { - struct sk_security_struct *sksec = asoc->base.sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(asoc->base.sk); if (!selinux_policycap_extsockclass()) return 0; @@ -5483,8 +5476,8 @@ static int selinux_sctp_bind_connect(struct sock *sk, int optname, static void selinux_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, struct sock *newsk) { - struct sk_security_struct *sksec = sk->sk_security; - struct sk_security_struct *newsksec = newsk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); + struct sk_security_struct *newsksec = selinux_sock(newsk); /* If policy does not support SECCLASS_SCTP_SOCKET then call * the non-sctp clone version. @@ -5500,8 +5493,8 @@ static void selinux_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk static int selinux_mptcp_add_subflow(struct sock *sk, struct sock *ssk) { - struct sk_security_struct *ssksec = ssk->sk_security; - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *ssksec = selinux_sock(ssk); + struct sk_security_struct *sksec = selinux_sock(sk); ssksec->sclass = sksec->sclass; ssksec->sid = sksec->sid; @@ -5516,7 +5509,7 @@ static int selinux_mptcp_add_subflow(struct sock *sk, struct sock *ssk) static int selinux_inet_conn_request(const struct sock *sk, struct sk_buff *skb, struct request_sock *req) { - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); int err; u16 family = req->rsk_ops->family; u32 connsid; @@ -5537,7 +5530,7 @@ static int selinux_inet_conn_request(const struct sock *sk, struct sk_buff *skb, static void selinux_inet_csk_clone(struct sock *newsk, const struct request_sock *req) { - struct sk_security_struct *newsksec = newsk->sk_security; + struct sk_security_struct *newsksec = selinux_sock(newsk); newsksec->sid = req->secid; newsksec->peer_sid = req->peer_secid; @@ -5554,7 +5547,7 @@ static void selinux_inet_csk_clone(struct sock *newsk, static void selinux_inet_conn_established(struct sock *sk, struct sk_buff *skb) { u16 family = sk->sk_family; - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); /* handle mapped IPv4 packets arriving via IPv6 sockets */ if (family == PF_INET6 && skb->protocol == htons(ETH_P_IP)) @@ -5629,7 +5622,7 @@ static int selinux_tun_dev_attach_queue(void *security) static int selinux_tun_dev_attach(struct sock *sk, void *security) { struct tun_security_struct *tunsec = security; - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); /* we don't currently perform any NetLabel based labeling here and it * isn't clear that we would want to do so anyway; while we could apply @@ -5752,7 +5745,7 @@ static unsigned int selinux_ip_output(void *priv, struct sk_buff *skb, return NF_ACCEPT; /* standard practice, label using the parent socket */ - sksec = sk->sk_security; + sksec = selinux_sock(sk); sid = sksec->sid; } else sid = SECINITSID_KERNEL; @@ -5775,7 +5768,7 @@ static unsigned int selinux_ip_postroute_compat(struct sk_buff *skb, sk = skb_to_full_sk(skb); if (sk == NULL) return NF_ACCEPT; - sksec = sk->sk_security; + sksec = selinux_sock(sk); ad_net_init_from_iif(&ad, &net, state->out->ifindex, state->pf); if (selinux_parse_skb(skb, &ad, NULL, 0, &proto)) @@ -5864,7 +5857,7 @@ static unsigned int selinux_ip_postroute(void *priv, u32 skb_sid; struct sk_security_struct *sksec; - sksec = sk->sk_security; + sksec = selinux_sock(sk); if (selinux_skb_peerlbl_sid(skb, family, &skb_sid)) return NF_DROP; /* At this point, if the returned skb peerlbl is SECSID_NULL @@ -5893,7 +5886,7 @@ static unsigned int selinux_ip_postroute(void *priv, } else { /* Locally generated packet, fetch the security label from the * associated socket. */ - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); peer_sid = sksec->sid; secmark_perm = PACKET__SEND; } @@ -5936,7 +5929,7 @@ static int selinux_netlink_send(struct sock *sk, struct sk_buff *skb) unsigned int data_len = skb->len; unsigned char *data = skb->data; struct nlmsghdr *nlh; - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); u16 sclass = sksec->sclass; u32 perm; @@ -6994,6 +6987,7 @@ struct lsm_blob_sizes selinux_blob_sizes __ro_after_init = { .lbs_inode = sizeof(struct inode_security_struct), .lbs_ipc = sizeof(struct ipc_security_struct), .lbs_msg_msg = sizeof(struct msg_security_struct), + .lbs_sock = sizeof(struct sk_security_struct), .lbs_superblock = sizeof(struct superblock_security_struct), .lbs_xattr_count = SELINUX_INODE_INIT_XATTRS, }; diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h index dea1d6f3ed2d..b074099acbaf 100644 --- a/security/selinux/include/objsec.h +++ b/security/selinux/include/objsec.h @@ -195,4 +195,9 @@ selinux_superblock(const struct super_block *superblock) return superblock->s_security + selinux_blob_sizes.lbs_superblock; } +static inline struct sk_security_struct *selinux_sock(const struct sock *sock) +{ + return sock->sk_security + selinux_blob_sizes.lbs_sock; +} + #endif /* _SELINUX_OBJSEC_H_ */ diff --git a/security/selinux/netlabel.c b/security/selinux/netlabel.c index 55885634e880..fbe5f8c29f81 100644 --- a/security/selinux/netlabel.c +++ b/security/selinux/netlabel.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -68,7 +69,7 @@ static int selinux_netlbl_sidlookup_cached(struct sk_buff *skb, static struct netlbl_lsm_secattr *selinux_netlbl_sock_genattr(struct sock *sk) { int rc; - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); struct netlbl_lsm_secattr *secattr; if (sksec->nlbl_secattr != NULL) @@ -100,7 +101,7 @@ static struct netlbl_lsm_secattr *selinux_netlbl_sock_getattr( const struct sock *sk, u32 sid) { - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); struct netlbl_lsm_secattr *secattr = sksec->nlbl_secattr; if (secattr == NULL) @@ -240,7 +241,7 @@ int selinux_netlbl_skbuff_setsid(struct sk_buff *skb, * being labeled by it's parent socket, if it is just exit */ sk = skb_to_full_sk(skb); if (sk != NULL) { - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); if (sksec->nlbl_state != NLBL_REQSKB) return 0; @@ -277,7 +278,7 @@ int selinux_netlbl_sctp_assoc_request(struct sctp_association *asoc, { int rc; struct netlbl_lsm_secattr secattr; - struct sk_security_struct *sksec = asoc->base.sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(asoc->base.sk); struct sockaddr_in addr4; struct sockaddr_in6 addr6; @@ -356,7 +357,7 @@ inet_conn_request_return: */ void selinux_netlbl_inet_csk_clone(struct sock *sk, u16 family) { - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); if (family == PF_INET) sksec->nlbl_state = NLBL_LABELED; @@ -374,8 +375,8 @@ void selinux_netlbl_inet_csk_clone(struct sock *sk, u16 family) */ void selinux_netlbl_sctp_sk_clone(struct sock *sk, struct sock *newsk) { - struct sk_security_struct *sksec = sk->sk_security; - struct sk_security_struct *newsksec = newsk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); + struct sk_security_struct *newsksec = selinux_sock(newsk); newsksec->nlbl_state = sksec->nlbl_state; } @@ -393,7 +394,7 @@ void selinux_netlbl_sctp_sk_clone(struct sock *sk, struct sock *newsk) int selinux_netlbl_socket_post_create(struct sock *sk, u16 family) { int rc; - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); struct netlbl_lsm_secattr *secattr; if (family != PF_INET && family != PF_INET6) @@ -510,7 +511,7 @@ int selinux_netlbl_socket_setsockopt(struct socket *sock, { int rc = 0; struct sock *sk = sock->sk; - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); struct netlbl_lsm_secattr secattr; if (selinux_netlbl_option(level, optname) && @@ -548,7 +549,7 @@ static int selinux_netlbl_socket_connect_helper(struct sock *sk, struct sockaddr *addr) { int rc; - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); struct netlbl_lsm_secattr *secattr; /* connected sockets are allowed to disconnect when the address family @@ -587,7 +588,7 @@ static int selinux_netlbl_socket_connect_helper(struct sock *sk, int selinux_netlbl_socket_connect_locked(struct sock *sk, struct sockaddr *addr) { - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); if (sksec->nlbl_state != NLBL_REQSKB && sksec->nlbl_state != NLBL_CONNLABELED) diff --git a/security/smack/smack.h b/security/smack/smack.h index 041688e5a77a..297f21446f45 100644 --- a/security/smack/smack.h +++ b/security/smack/smack.h @@ -355,6 +355,11 @@ static inline struct superblock_smack *smack_superblock( return superblock->s_security + smack_blob_sizes.lbs_superblock; } +static inline struct socket_smack *smack_sock(const struct sock *sock) +{ + return sock->sk_security + smack_blob_sizes.lbs_sock; +} + /* * Is the directory transmuting? */ diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 4164699cd4f6..742ccbd67a57 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -1606,7 +1606,7 @@ static int smack_inode_getsecurity(struct mnt_idmap *idmap, if (sock == NULL || sock->sk == NULL) return -EOPNOTSUPP; - ssp = sock->sk->sk_security; + ssp = smack_sock(sock->sk); if (strcmp(name, XATTR_SMACK_IPIN) == 0) isp = ssp->smk_in; @@ -1994,7 +1994,7 @@ static int smack_file_receive(struct file *file) if (inode->i_sb->s_magic == SOCKFS_MAGIC) { sock = SOCKET_I(inode); - ssp = sock->sk->sk_security; + ssp = smack_sock(sock->sk); tsp = smack_cred(current_cred()); /* * If the receiving process can't write to the @@ -2409,11 +2409,7 @@ static void smack_task_to_inode(struct task_struct *p, struct inode *inode) static int smack_sk_alloc_security(struct sock *sk, int family, gfp_t gfp_flags) { struct smack_known *skp = smk_of_current(); - struct socket_smack *ssp; - - ssp = kzalloc(sizeof(struct socket_smack), gfp_flags); - if (ssp == NULL) - return -ENOMEM; + struct socket_smack *ssp = smack_sock(sk); /* * Sockets created by kernel threads receive web label. @@ -2427,11 +2423,10 @@ static int smack_sk_alloc_security(struct sock *sk, int family, gfp_t gfp_flags) } ssp->smk_packet = NULL; - sk->sk_security = ssp; - return 0; } +#ifdef SMACK_IPV6_PORT_LABELING /** * smack_sk_free_security - Free a socket blob * @sk: the socket @@ -2440,7 +2435,6 @@ static int smack_sk_alloc_security(struct sock *sk, int family, gfp_t gfp_flags) */ static void smack_sk_free_security(struct sock *sk) { -#ifdef SMACK_IPV6_PORT_LABELING struct smk_port_label *spp; if (sk->sk_family == PF_INET6) { @@ -2453,9 +2447,8 @@ static void smack_sk_free_security(struct sock *sk) } rcu_read_unlock(); } -#endif - kfree(sk->sk_security); } +#endif /** * smack_sk_clone_security - Copy security context @@ -2466,8 +2459,8 @@ static void smack_sk_free_security(struct sock *sk) */ static void smack_sk_clone_security(const struct sock *sk, struct sock *newsk) { - struct socket_smack *ssp_old = sk->sk_security; - struct socket_smack *ssp_new = newsk->sk_security; + struct socket_smack *ssp_old = smack_sock(sk); + struct socket_smack *ssp_new = smack_sock(newsk); *ssp_new = *ssp_old; } @@ -2583,7 +2576,7 @@ static struct smack_known *smack_ipv6host_label(struct sockaddr_in6 *sip) */ static int smack_netlbl_add(struct sock *sk) { - struct socket_smack *ssp = sk->sk_security; + struct socket_smack *ssp = smack_sock(sk); struct smack_known *skp = ssp->smk_out; int rc; @@ -2616,7 +2609,7 @@ static int smack_netlbl_add(struct sock *sk) */ static void smack_netlbl_delete(struct sock *sk) { - struct socket_smack *ssp = sk->sk_security; + struct socket_smack *ssp = smack_sock(sk); /* * Take the label off the socket if one is set. @@ -2648,7 +2641,7 @@ static int smk_ipv4_check(struct sock *sk, struct sockaddr_in *sap) struct smack_known *skp; int rc = 0; struct smack_known *hkp; - struct socket_smack *ssp = sk->sk_security; + struct socket_smack *ssp = smack_sock(sk); struct smk_audit_info ad; rcu_read_lock(); @@ -2721,7 +2714,7 @@ static void smk_ipv6_port_label(struct socket *sock, struct sockaddr *address) { struct sock *sk = sock->sk; struct sockaddr_in6 *addr6; - struct socket_smack *ssp = sock->sk->sk_security; + struct socket_smack *ssp = smack_sock(sock->sk); struct smk_port_label *spp; unsigned short port = 0; @@ -2809,7 +2802,7 @@ static int smk_ipv6_port_check(struct sock *sk, struct sockaddr_in6 *address, int act) { struct smk_port_label *spp; - struct socket_smack *ssp = sk->sk_security; + struct socket_smack *ssp = smack_sock(sk); struct smack_known *skp = NULL; unsigned short port; struct smack_known *object; @@ -2912,7 +2905,7 @@ static int smack_inode_setsecurity(struct inode *inode, const char *name, if (sock == NULL || sock->sk == NULL) return -EOPNOTSUPP; - ssp = sock->sk->sk_security; + ssp = smack_sock(sock->sk); if (strcmp(name, XATTR_SMACK_IPIN) == 0) ssp->smk_in = skp; @@ -2960,7 +2953,7 @@ static int smack_socket_post_create(struct socket *sock, int family, * Sockets created by kernel threads receive web label. */ if (unlikely(current->flags & PF_KTHREAD)) { - ssp = sock->sk->sk_security; + ssp = smack_sock(sock->sk); ssp->smk_in = &smack_known_web; ssp->smk_out = &smack_known_web; } @@ -2985,8 +2978,8 @@ static int smack_socket_post_create(struct socket *sock, int family, static int smack_socket_socketpair(struct socket *socka, struct socket *sockb) { - struct socket_smack *asp = socka->sk->sk_security; - struct socket_smack *bsp = sockb->sk->sk_security; + struct socket_smack *asp = smack_sock(socka->sk); + struct socket_smack *bsp = smack_sock(sockb->sk); asp->smk_packet = bsp->smk_out; bsp->smk_packet = asp->smk_out; @@ -3049,7 +3042,7 @@ static int smack_socket_connect(struct socket *sock, struct sockaddr *sap, if (__is_defined(SMACK_IPV6_SECMARK_LABELING)) rsp = smack_ipv6host_label(sip); if (rsp != NULL) { - struct socket_smack *ssp = sock->sk->sk_security; + struct socket_smack *ssp = smack_sock(sock->sk); rc = smk_ipv6_check(ssp->smk_out, rsp, sip, SMK_CONNECTING); @@ -3844,9 +3837,9 @@ static int smack_unix_stream_connect(struct sock *sock, { struct smack_known *skp; struct smack_known *okp; - struct socket_smack *ssp = sock->sk_security; - struct socket_smack *osp = other->sk_security; - struct socket_smack *nsp = newsk->sk_security; + struct socket_smack *ssp = smack_sock(sock); + struct socket_smack *osp = smack_sock(other); + struct socket_smack *nsp = smack_sock(newsk); struct smk_audit_info ad; int rc = 0; #ifdef CONFIG_AUDIT @@ -3898,8 +3891,8 @@ static int smack_unix_stream_connect(struct sock *sock, */ static int smack_unix_may_send(struct socket *sock, struct socket *other) { - struct socket_smack *ssp = sock->sk->sk_security; - struct socket_smack *osp = other->sk->sk_security; + struct socket_smack *ssp = smack_sock(sock->sk); + struct socket_smack *osp = smack_sock(other->sk); struct smk_audit_info ad; int rc; @@ -3936,7 +3929,7 @@ static int smack_socket_sendmsg(struct socket *sock, struct msghdr *msg, struct sockaddr_in6 *sap = (struct sockaddr_in6 *) msg->msg_name; #endif #ifdef SMACK_IPV6_SECMARK_LABELING - struct socket_smack *ssp = sock->sk->sk_security; + struct socket_smack *ssp = smack_sock(sock->sk); struct smack_known *rsp; #endif int rc = 0; @@ -4148,7 +4141,7 @@ static struct smack_known *smack_from_netlbl(const struct sock *sk, u16 family, netlbl_secattr_init(&secattr); if (sk) - ssp = sk->sk_security; + ssp = smack_sock(sk); if (netlbl_skbuff_getattr(skb, family, &secattr) == 0) { skp = smack_from_secattr(&secattr, ssp); @@ -4170,7 +4163,7 @@ static struct smack_known *smack_from_netlbl(const struct sock *sk, u16 family, */ static int smack_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) { - struct socket_smack *ssp = sk->sk_security; + struct socket_smack *ssp = smack_sock(sk); struct smack_known *skp = NULL; int rc = 0; struct smk_audit_info ad; @@ -4274,7 +4267,7 @@ static int smack_socket_getpeersec_stream(struct socket *sock, u32 slen = 1; int rc = 0; - ssp = sock->sk->sk_security; + ssp = smack_sock(sock->sk); if (ssp->smk_packet != NULL) { rcp = ssp->smk_packet->smk_known; slen = strlen(rcp) + 1; @@ -4324,7 +4317,7 @@ static int smack_socket_getpeersec_dgram(struct socket *sock, switch (family) { case PF_UNIX: - ssp = sock->sk->sk_security; + ssp = smack_sock(sock->sk); s = ssp->smk_out->smk_secid; break; case PF_INET: @@ -4373,7 +4366,7 @@ static void smack_sock_graft(struct sock *sk, struct socket *parent) (sk->sk_family != PF_INET && sk->sk_family != PF_INET6)) return; - ssp = sk->sk_security; + ssp = smack_sock(sk); ssp->smk_in = skp; ssp->smk_out = skp; /* cssp->smk_packet is already set in smack_inet_csk_clone() */ @@ -4393,7 +4386,7 @@ static int smack_inet_conn_request(const struct sock *sk, struct sk_buff *skb, { u16 family = sk->sk_family; struct smack_known *skp; - struct socket_smack *ssp = sk->sk_security; + struct socket_smack *ssp = smack_sock(sk); struct sockaddr_in addr; struct iphdr *hdr; struct smack_known *hskp; @@ -4479,7 +4472,7 @@ static int smack_inet_conn_request(const struct sock *sk, struct sk_buff *skb, static void smack_inet_csk_clone(struct sock *sk, const struct request_sock *req) { - struct socket_smack *ssp = sk->sk_security; + struct socket_smack *ssp = smack_sock(sk); struct smack_known *skp; if (req->peer_secid != 0) { @@ -5049,6 +5042,7 @@ struct lsm_blob_sizes smack_blob_sizes __ro_after_init = { .lbs_inode = sizeof(struct inode_smack), .lbs_ipc = sizeof(struct smack_known *), .lbs_msg_msg = sizeof(struct smack_known *), + .lbs_sock = sizeof(struct socket_smack), .lbs_superblock = sizeof(struct superblock_smack), .lbs_xattr_count = SMACK_INODE_INIT_XATTRS, }; @@ -5173,7 +5167,9 @@ static struct security_hook_list smack_hooks[] __ro_after_init = { LSM_HOOK_INIT(socket_getpeersec_stream, smack_socket_getpeersec_stream), LSM_HOOK_INIT(socket_getpeersec_dgram, smack_socket_getpeersec_dgram), LSM_HOOK_INIT(sk_alloc_security, smack_sk_alloc_security), +#ifdef SMACK_IPV6_PORT_LABELING LSM_HOOK_INIT(sk_free_security, smack_sk_free_security), +#endif LSM_HOOK_INIT(sk_clone_security, smack_sk_clone_security), LSM_HOOK_INIT(sock_graft, smack_sock_graft), LSM_HOOK_INIT(inet_conn_request, smack_inet_conn_request), diff --git a/security/smack/smack_netfilter.c b/security/smack/smack_netfilter.c index b945c1d3a743..bad71b7e648d 100644 --- a/security/smack/smack_netfilter.c +++ b/security/smack/smack_netfilter.c @@ -26,8 +26,8 @@ static unsigned int smack_ip_output(void *priv, struct socket_smack *ssp; struct smack_known *skp; - if (sk && sk->sk_security) { - ssp = sk->sk_security; + if (sk) { + ssp = smack_sock(sk); skp = ssp->smk_out; skb->secmark = skp->smk_secid; } -- cgit v1.2.3 From 5f8d28f6d7d568dbbc8c5bce94894474c07afd4f Mon Sep 17 00:00:00 2001 From: Casey Schaufler Date: Wed, 10 Jul 2024 14:32:26 -0700 Subject: lsm: infrastructure management of the key security blob Move management of the key->security blob out of the individual security modules and into the security infrastructure. Instead of allocating the blobs from within the modules the modules tell the infrastructure how much space is required, and the space is allocated there. There are no existing modules that require a key_free hook, so the call to it and the definition for it have been removed. Signed-off-by: Casey Schaufler Reviewed-by: John Johansen [PM: subject tweak] Signed-off-by: Paul Moore --- include/linux/lsm_hook_defs.h | 1 - include/linux/lsm_hooks.h | 1 + security/security.c | 39 +++++++++++++++++++++++++++++++++++++-- security/selinux/hooks.c | 21 ++++----------------- security/selinux/include/objsec.h | 7 +++++++ security/smack/smack.h | 7 +++++++ security/smack/smack_lsm.c | 31 +++++++++++++------------------ 7 files changed, 69 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 855db460e08b..8cc60644f3bd 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -403,7 +403,6 @@ LSM_HOOK(int, 0, xfrm_decode_session, struct sk_buff *skb, u32 *secid, #ifdef CONFIG_KEYS LSM_HOOK(int, 0, key_alloc, struct key *key, const struct cred *cred, unsigned long flags) -LSM_HOOK(void, LSM_RET_VOID, key_free, struct key *key) LSM_HOOK(int, 0, key_permission, key_ref_t key_ref, const struct cred *cred, enum key_need_perm need_perm) LSM_HOOK(int, 0, key_getsecurity, struct key *key, char **buffer) diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index efd4a0655159..7233bc0737be 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -76,6 +76,7 @@ struct lsm_blob_sizes { int lbs_sock; int lbs_superblock; int lbs_ipc; + int lbs_key; int lbs_msg_msg; int lbs_task; int lbs_xattr_count; /* number of xattr slots in new_xattrs array */ diff --git a/security/security.c b/security/security.c index 9c3fb2f60e2a..dfb7fea6080c 100644 --- a/security/security.c +++ b/security/security.c @@ -227,6 +227,7 @@ static void __init lsm_set_blob_sizes(struct lsm_blob_sizes *needed) blob_sizes.lbs_inode = sizeof(struct rcu_head); lsm_set_blob_size(&needed->lbs_inode, &blob_sizes.lbs_inode); lsm_set_blob_size(&needed->lbs_ipc, &blob_sizes.lbs_ipc); + lsm_set_blob_size(&needed->lbs_key, &blob_sizes.lbs_key); lsm_set_blob_size(&needed->lbs_msg_msg, &blob_sizes.lbs_msg_msg); lsm_set_blob_size(&needed->lbs_sock, &blob_sizes.lbs_sock); lsm_set_blob_size(&needed->lbs_superblock, &blob_sizes.lbs_superblock); @@ -402,6 +403,9 @@ static void __init ordered_lsm_init(void) init_debug("file blob size = %d\n", blob_sizes.lbs_file); init_debug("inode blob size = %d\n", blob_sizes.lbs_inode); init_debug("ipc blob size = %d\n", blob_sizes.lbs_ipc); +#ifdef CONFIG_KEYS + init_debug("key blob size = %d\n", blob_sizes.lbs_key); +#endif /* CONFIG_KEYS */ init_debug("msg_msg blob size = %d\n", blob_sizes.lbs_msg_msg); init_debug("sock blob size = %d\n", blob_sizes.lbs_sock); init_debug("superblock blob size = %d\n", blob_sizes.lbs_superblock); @@ -718,6 +722,29 @@ static int lsm_ipc_alloc(struct kern_ipc_perm *kip) return 0; } +#ifdef CONFIG_KEYS +/** + * lsm_key_alloc - allocate a composite key blob + * @key: the key that needs a blob + * + * Allocate the key blob for all the modules + * + * Returns 0, or -ENOMEM if memory can't be allocated. + */ +static int lsm_key_alloc(struct key *key) +{ + if (blob_sizes.lbs_key == 0) { + key->security = NULL; + return 0; + } + + key->security = kzalloc(blob_sizes.lbs_key, GFP_KERNEL); + if (key->security == NULL) + return -ENOMEM; + return 0; +} +#endif /* CONFIG_KEYS */ + /** * lsm_msg_msg_alloc - allocate a composite msg_msg blob * @mp: the msg_msg that needs a blob @@ -5316,7 +5343,14 @@ EXPORT_SYMBOL(security_skb_classify_flow); int security_key_alloc(struct key *key, const struct cred *cred, unsigned long flags) { - return call_int_hook(key_alloc, key, cred, flags); + int rc = lsm_key_alloc(key); + + if (unlikely(rc)) + return rc; + rc = call_int_hook(key_alloc, key, cred, flags); + if (unlikely(rc)) + security_key_free(key); + return rc; } /** @@ -5327,7 +5361,8 @@ int security_key_alloc(struct key *key, const struct cred *cred, */ void security_key_free(struct key *key) { - call_void_hook(key_free, key); + kfree(key->security); + key->security = NULL; } /** diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index e08ffb1ddd5a..7dbf169f733f 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -6663,11 +6663,7 @@ static int selinux_key_alloc(struct key *k, const struct cred *cred, unsigned long flags) { const struct task_security_struct *tsec; - struct key_security_struct *ksec; - - ksec = kzalloc(sizeof(struct key_security_struct), GFP_KERNEL); - if (!ksec) - return -ENOMEM; + struct key_security_struct *ksec = selinux_key(k); tsec = selinux_cred(cred); if (tsec->keycreate_sid) @@ -6675,18 +6671,9 @@ static int selinux_key_alloc(struct key *k, const struct cred *cred, else ksec->sid = tsec->sid; - k->security = ksec; return 0; } -static void selinux_key_free(struct key *k) -{ - struct key_security_struct *ksec = k->security; - - k->security = NULL; - kfree(ksec); -} - static int selinux_key_permission(key_ref_t key_ref, const struct cred *cred, enum key_need_perm need_perm) @@ -6727,14 +6714,14 @@ static int selinux_key_permission(key_ref_t key_ref, sid = cred_sid(cred); key = key_ref_to_ptr(key_ref); - ksec = key->security; + ksec = selinux_key(key); return avc_has_perm(sid, ksec->sid, SECCLASS_KEY, perm, NULL); } static int selinux_key_getsecurity(struct key *key, char **_buffer) { - struct key_security_struct *ksec = key->security; + struct key_security_struct *ksec = selinux_key(key); char *context = NULL; unsigned len; int rc; @@ -6986,6 +6973,7 @@ struct lsm_blob_sizes selinux_blob_sizes __ro_after_init = { .lbs_file = sizeof(struct file_security_struct), .lbs_inode = sizeof(struct inode_security_struct), .lbs_ipc = sizeof(struct ipc_security_struct), + .lbs_key = sizeof(struct key_security_struct), .lbs_msg_msg = sizeof(struct msg_security_struct), .lbs_sock = sizeof(struct sk_security_struct), .lbs_superblock = sizeof(struct superblock_security_struct), @@ -7324,7 +7312,6 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = { #endif #ifdef CONFIG_KEYS - LSM_HOOK_INIT(key_free, selinux_key_free), LSM_HOOK_INIT(key_permission, selinux_key_permission), LSM_HOOK_INIT(key_getsecurity, selinux_key_getsecurity), #ifdef CONFIG_KEY_NOTIFICATIONS diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h index b074099acbaf..83b9443d6919 100644 --- a/security/selinux/include/objsec.h +++ b/security/selinux/include/objsec.h @@ -195,6 +195,13 @@ selinux_superblock(const struct super_block *superblock) return superblock->s_security + selinux_blob_sizes.lbs_superblock; } +#ifdef CONFIG_KEYS +static inline struct key_security_struct *selinux_key(const struct key *key) +{ + return key->security + selinux_blob_sizes.lbs_key; +} +#endif /* CONFIG_KEYS */ + static inline struct sk_security_struct *selinux_sock(const struct sock *sock) { return sock->sk_security + selinux_blob_sizes.lbs_sock; diff --git a/security/smack/smack.h b/security/smack/smack.h index 297f21446f45..dbf8d7226eb5 100644 --- a/security/smack/smack.h +++ b/security/smack/smack.h @@ -360,6 +360,13 @@ static inline struct socket_smack *smack_sock(const struct sock *sock) return sock->sk_security + smack_blob_sizes.lbs_sock; } +#ifdef CONFIG_KEYS +static inline struct smack_known **smack_key(const struct key *key) +{ + return key->security + smack_blob_sizes.lbs_key; +} +#endif /* CONFIG_KEYS */ + /* * Is the directory transmuting? */ diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 742ccbd67a57..d690bfda893a 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -4504,23 +4504,13 @@ static void smack_inet_csk_clone(struct sock *sk, static int smack_key_alloc(struct key *key, const struct cred *cred, unsigned long flags) { + struct smack_known **blob = smack_key(key); struct smack_known *skp = smk_of_task(smack_cred(cred)); - key->security = skp; + *blob = skp; return 0; } -/** - * smack_key_free - Clear the key security blob - * @key: the object - * - * Clear the blob pointer - */ -static void smack_key_free(struct key *key) -{ - key->security = NULL; -} - /** * smack_key_permission - Smack access on a key * @key_ref: gets to the object @@ -4534,6 +4524,8 @@ static int smack_key_permission(key_ref_t key_ref, const struct cred *cred, enum key_need_perm need_perm) { + struct smack_known **blob; + struct smack_known *skp; struct key *keyp; struct smk_audit_info ad; struct smack_known *tkp = smk_of_task(smack_cred(cred)); @@ -4571,7 +4563,9 @@ static int smack_key_permission(key_ref_t key_ref, * If the key hasn't been initialized give it access so that * it may do so. */ - if (keyp->security == NULL) + blob = smack_key(keyp); + skp = *blob; + if (skp == NULL) return 0; /* * This should not occur @@ -4587,8 +4581,8 @@ static int smack_key_permission(key_ref_t key_ref, ad.a.u.key_struct.key = keyp->serial; ad.a.u.key_struct.key_desc = keyp->description; #endif - rc = smk_access(tkp, keyp->security, request, &ad); - rc = smk_bu_note("key access", tkp, keyp->security, request, rc); + rc = smk_access(tkp, skp, request, &ad); + rc = smk_bu_note("key access", tkp, skp, request, rc); return rc; } @@ -4603,11 +4597,12 @@ static int smack_key_permission(key_ref_t key_ref, */ static int smack_key_getsecurity(struct key *key, char **_buffer) { - struct smack_known *skp = key->security; + struct smack_known **blob = smack_key(key); + struct smack_known *skp = *blob; size_t length; char *copy; - if (key->security == NULL) { + if (skp == NULL) { *_buffer = NULL; return 0; } @@ -5041,6 +5036,7 @@ struct lsm_blob_sizes smack_blob_sizes __ro_after_init = { .lbs_file = sizeof(struct smack_known *), .lbs_inode = sizeof(struct inode_smack), .lbs_ipc = sizeof(struct smack_known *), + .lbs_key = sizeof(struct smack_known *), .lbs_msg_msg = sizeof(struct smack_known *), .lbs_sock = sizeof(struct socket_smack), .lbs_superblock = sizeof(struct superblock_smack), @@ -5178,7 +5174,6 @@ static struct security_hook_list smack_hooks[] __ro_after_init = { /* key management security hooks */ #ifdef CONFIG_KEYS LSM_HOOK_INIT(key_alloc, smack_key_alloc), - LSM_HOOK_INIT(key_free, smack_key_free), LSM_HOOK_INIT(key_permission, smack_key_permission), LSM_HOOK_INIT(key_getsecurity, smack_key_getsecurity), #ifdef CONFIG_KEY_NOTIFICATIONS -- cgit v1.2.3 From a39c0f77dbbe083f3eec6c3b32d90f168f7575eb Mon Sep 17 00:00:00 2001 From: Casey Schaufler Date: Wed, 10 Jul 2024 14:32:28 -0700 Subject: lsm: infrastructure management of the dev_tun blob Move management of the dev_tun security blob out of the individual security modules and into the LSM infrastructure. The security modules tell the infrastructure how much space they require at initialization. There are no longer any modules that require the dev_tun_free hook. The hook definition has been removed. Signed-off-by: Casey Schaufler Reviewed-by: John Johansen [PM: subject tweak, selinux style fixes] Signed-off-by: Paul Moore --- include/linux/lsm_hook_defs.h | 3 +-- include/linux/lsm_hooks.h | 1 + security/security.c | 17 +++++++++++++++-- security/selinux/hooks.c | 22 ++++++---------------- security/selinux/include/objsec.h | 5 +++++ 5 files changed, 28 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 8cc60644f3bd..22c475f530ae 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -353,8 +353,7 @@ LSM_HOOK(void, LSM_RET_VOID, secmark_refcount_inc, void) LSM_HOOK(void, LSM_RET_VOID, secmark_refcount_dec, void) LSM_HOOK(void, LSM_RET_VOID, req_classify_flow, const struct request_sock *req, struct flowi_common *flic) -LSM_HOOK(int, 0, tun_dev_alloc_security, void **security) -LSM_HOOK(void, LSM_RET_VOID, tun_dev_free_security, void *security) +LSM_HOOK(int, 0, tun_dev_alloc_security, void *security) LSM_HOOK(int, 0, tun_dev_create, void) LSM_HOOK(int, 0, tun_dev_attach_queue, void *security) LSM_HOOK(int, 0, tun_dev_attach, struct sock *sk, void *security) diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 7233bc0737be..0ff14ff128c8 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -80,6 +80,7 @@ struct lsm_blob_sizes { int lbs_msg_msg; int lbs_task; int lbs_xattr_count; /* number of xattr slots in new_xattrs array */ + int lbs_tun_dev; }; /** diff --git a/security/security.c b/security/security.c index 15efcf43e168..137a1f7e0e8b 100644 --- a/security/security.c +++ b/security/security.c @@ -232,6 +232,7 @@ static void __init lsm_set_blob_sizes(struct lsm_blob_sizes *needed) lsm_set_blob_size(&needed->lbs_sock, &blob_sizes.lbs_sock); lsm_set_blob_size(&needed->lbs_superblock, &blob_sizes.lbs_superblock); lsm_set_blob_size(&needed->lbs_task, &blob_sizes.lbs_task); + lsm_set_blob_size(&needed->lbs_tun_dev, &blob_sizes.lbs_tun_dev); lsm_set_blob_size(&needed->lbs_xattr_count, &blob_sizes.lbs_xattr_count); } @@ -410,6 +411,7 @@ static void __init ordered_lsm_init(void) init_debug("sock blob size = %d\n", blob_sizes.lbs_sock); init_debug("superblock blob size = %d\n", blob_sizes.lbs_superblock); init_debug("task blob size = %d\n", blob_sizes.lbs_task); + init_debug("tun device blob size = %d\n", blob_sizes.lbs_tun_dev); init_debug("xattr slots = %d\n", blob_sizes.lbs_xattr_count); /* @@ -4875,7 +4877,18 @@ EXPORT_SYMBOL(security_secmark_refcount_dec); */ int security_tun_dev_alloc_security(void **security) { - return call_int_hook(tun_dev_alloc_security, security); + int rc; + + rc = lsm_blob_alloc(security, blob_sizes.lbs_tun_dev, GFP_KERNEL); + if (rc) + return rc; + + rc = call_int_hook(tun_dev_alloc_security, *security); + if (rc) { + kfree(*security); + *security = NULL; + } + return rc; } EXPORT_SYMBOL(security_tun_dev_alloc_security); @@ -4887,7 +4900,7 @@ EXPORT_SYMBOL(security_tun_dev_alloc_security); */ void security_tun_dev_free_security(void *security) { - call_void_hook(tun_dev_free_security, security); + kfree(security); } EXPORT_SYMBOL(security_tun_dev_free_security); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 7dbf169f733f..793cfdc4c0ef 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -5578,24 +5578,14 @@ static void selinux_req_classify_flow(const struct request_sock *req, flic->flowic_secid = req->secid; } -static int selinux_tun_dev_alloc_security(void **security) +static int selinux_tun_dev_alloc_security(void *security) { - struct tun_security_struct *tunsec; + struct tun_security_struct *tunsec = selinux_tun_dev(security); - tunsec = kzalloc(sizeof(*tunsec), GFP_KERNEL); - if (!tunsec) - return -ENOMEM; tunsec->sid = current_sid(); - - *security = tunsec; return 0; } -static void selinux_tun_dev_free_security(void *security) -{ - kfree(security); -} - static int selinux_tun_dev_create(void) { u32 sid = current_sid(); @@ -5613,7 +5603,7 @@ static int selinux_tun_dev_create(void) static int selinux_tun_dev_attach_queue(void *security) { - struct tun_security_struct *tunsec = security; + struct tun_security_struct *tunsec = selinux_tun_dev(security); return avc_has_perm(current_sid(), tunsec->sid, SECCLASS_TUN_SOCKET, TUN_SOCKET__ATTACH_QUEUE, NULL); @@ -5621,7 +5611,7 @@ static int selinux_tun_dev_attach_queue(void *security) static int selinux_tun_dev_attach(struct sock *sk, void *security) { - struct tun_security_struct *tunsec = security; + struct tun_security_struct *tunsec = selinux_tun_dev(security); struct sk_security_struct *sksec = selinux_sock(sk); /* we don't currently perform any NetLabel based labeling here and it @@ -5639,7 +5629,7 @@ static int selinux_tun_dev_attach(struct sock *sk, void *security) static int selinux_tun_dev_open(void *security) { - struct tun_security_struct *tunsec = security; + struct tun_security_struct *tunsec = selinux_tun_dev(security); u32 sid = current_sid(); int err; @@ -6978,6 +6968,7 @@ struct lsm_blob_sizes selinux_blob_sizes __ro_after_init = { .lbs_sock = sizeof(struct sk_security_struct), .lbs_superblock = sizeof(struct superblock_security_struct), .lbs_xattr_count = SELINUX_INODE_INIT_XATTRS, + .lbs_tun_dev = sizeof(struct tun_security_struct), }; #ifdef CONFIG_PERF_EVENTS @@ -7289,7 +7280,6 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = { LSM_HOOK_INIT(secmark_refcount_inc, selinux_secmark_refcount_inc), LSM_HOOK_INIT(secmark_refcount_dec, selinux_secmark_refcount_dec), LSM_HOOK_INIT(req_classify_flow, selinux_req_classify_flow), - LSM_HOOK_INIT(tun_dev_free_security, selinux_tun_dev_free_security), LSM_HOOK_INIT(tun_dev_create, selinux_tun_dev_create), LSM_HOOK_INIT(tun_dev_attach_queue, selinux_tun_dev_attach_queue), LSM_HOOK_INIT(tun_dev_attach, selinux_tun_dev_attach), diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h index 83b9443d6919..b7d4b1fc8fee 100644 --- a/security/selinux/include/objsec.h +++ b/security/selinux/include/objsec.h @@ -207,4 +207,9 @@ static inline struct sk_security_struct *selinux_sock(const struct sock *sock) return sock->sk_security + selinux_blob_sizes.lbs_sock; } +static inline struct tun_security_struct *selinux_tun_dev(void *security) +{ + return security + selinux_blob_sizes.lbs_tun_dev; +} + #endif /* _SELINUX_OBJSEC_H_ */ -- cgit v1.2.3 From 66de33a0bbb59ef3909d2c65dbbb7fc503d573bd Mon Sep 17 00:00:00 2001 From: Casey Schaufler Date: Wed, 10 Jul 2024 14:32:29 -0700 Subject: lsm: infrastructure management of the infiniband blob Move management of the infiniband security blob out of the individual security modules and into the LSM infrastructure. The security modules tell the infrastructure how much space they require at initialization. There are no longer any modules that require the ib_free() hook. The hook definition has been removed. Signed-off-by: Casey Schaufler Reviewed-by: John Johansen [PM: subject tweak, selinux style fixes] Signed-off-by: Paul Moore --- include/linux/lsm_hook_defs.h | 3 +-- include/linux/lsm_hooks.h | 1 + security/security.c | 17 +++++++++++++++-- security/selinux/hooks.c | 16 +++------------- security/selinux/include/objsec.h | 5 +++++ 5 files changed, 25 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 22c475f530ae..4fcbc5b3f58c 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -373,8 +373,7 @@ LSM_HOOK(int, 0, mptcp_add_subflow, struct sock *sk, struct sock *ssk) LSM_HOOK(int, 0, ib_pkey_access, void *sec, u64 subnet_prefix, u16 pkey) LSM_HOOK(int, 0, ib_endport_manage_subnet, void *sec, const char *dev_name, u8 port_num) -LSM_HOOK(int, 0, ib_alloc_security, void **sec) -LSM_HOOK(void, LSM_RET_VOID, ib_free_security, void *sec) +LSM_HOOK(int, 0, ib_alloc_security, void *sec) #endif /* CONFIG_SECURITY_INFINIBAND */ #ifdef CONFIG_SECURITY_NETWORK_XFRM diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 0ff14ff128c8..b6fc6ac88723 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -72,6 +72,7 @@ struct security_hook_list { struct lsm_blob_sizes { int lbs_cred; int lbs_file; + int lbs_ib; int lbs_inode; int lbs_sock; int lbs_superblock; diff --git a/security/security.c b/security/security.c index 137a1f7e0e8b..80dc58d60aab 100644 --- a/security/security.c +++ b/security/security.c @@ -219,6 +219,7 @@ static void __init lsm_set_blob_sizes(struct lsm_blob_sizes *needed) lsm_set_blob_size(&needed->lbs_cred, &blob_sizes.lbs_cred); lsm_set_blob_size(&needed->lbs_file, &blob_sizes.lbs_file); + lsm_set_blob_size(&needed->lbs_ib, &blob_sizes.lbs_ib); /* * The inode blob gets an rcu_head in addition to * what the modules might need. @@ -402,6 +403,7 @@ static void __init ordered_lsm_init(void) init_debug("cred blob size = %d\n", blob_sizes.lbs_cred); init_debug("file blob size = %d\n", blob_sizes.lbs_file); + init_debug("ib blob size = %d\n", blob_sizes.lbs_ib); init_debug("inode blob size = %d\n", blob_sizes.lbs_inode); init_debug("ipc blob size = %d\n", blob_sizes.lbs_ipc); #ifdef CONFIG_KEYS @@ -5096,7 +5098,18 @@ EXPORT_SYMBOL(security_ib_endport_manage_subnet); */ int security_ib_alloc_security(void **sec) { - return call_int_hook(ib_alloc_security, sec); + int rc; + + rc = lsm_blob_alloc(sec, blob_sizes.lbs_ib, GFP_KERNEL); + if (rc) + return rc; + + rc = call_int_hook(ib_alloc_security, *sec); + if (rc) { + kfree(*sec); + *sec = NULL; + } + return rc; } EXPORT_SYMBOL(security_ib_alloc_security); @@ -5108,7 +5121,7 @@ EXPORT_SYMBOL(security_ib_alloc_security); */ void security_ib_free_security(void *sec) { - call_void_hook(ib_free_security, sec); + kfree(sec); } EXPORT_SYMBOL(security_ib_free_security); #endif /* CONFIG_SECURITY_INFINIBAND */ diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 793cfdc4c0ef..675c69ebb77c 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -6781,23 +6781,13 @@ static int selinux_ib_endport_manage_subnet(void *ib_sec, const char *dev_name, INFINIBAND_ENDPORT__MANAGE_SUBNET, &ad); } -static int selinux_ib_alloc_security(void **ib_sec) +static int selinux_ib_alloc_security(void *ib_sec) { - struct ib_security_struct *sec; + struct ib_security_struct *sec = selinux_ib(ib_sec); - sec = kzalloc(sizeof(*sec), GFP_KERNEL); - if (!sec) - return -ENOMEM; sec->sid = current_sid(); - - *ib_sec = sec; return 0; } - -static void selinux_ib_free_security(void *ib_sec) -{ - kfree(ib_sec); -} #endif #ifdef CONFIG_BPF_SYSCALL @@ -6969,6 +6959,7 @@ struct lsm_blob_sizes selinux_blob_sizes __ro_after_init = { .lbs_superblock = sizeof(struct superblock_security_struct), .lbs_xattr_count = SELINUX_INODE_INIT_XATTRS, .lbs_tun_dev = sizeof(struct tun_security_struct), + .lbs_ib = sizeof(struct ib_security_struct), }; #ifdef CONFIG_PERF_EVENTS @@ -7288,7 +7279,6 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = { LSM_HOOK_INIT(ib_pkey_access, selinux_ib_pkey_access), LSM_HOOK_INIT(ib_endport_manage_subnet, selinux_ib_endport_manage_subnet), - LSM_HOOK_INIT(ib_free_security, selinux_ib_free_security), #endif #ifdef CONFIG_SECURITY_NETWORK_XFRM LSM_HOOK_INIT(xfrm_policy_free_security, selinux_xfrm_policy_free), diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h index b7d4b1fc8fee..ed9e37f3c9b5 100644 --- a/security/selinux/include/objsec.h +++ b/security/selinux/include/objsec.h @@ -212,4 +212,9 @@ static inline struct tun_security_struct *selinux_tun_dev(void *security) return security + selinux_blob_sizes.lbs_tun_dev; } +static inline struct ib_security_struct *selinux_ib(void *ib_sec) +{ + return ib_sec + selinux_blob_sizes.lbs_ib; +} + #endif /* _SELINUX_OBJSEC_H_ */ -- cgit v1.2.3 From 61a1dcdceb44d79e5ab511295791b88ea178c045 Mon Sep 17 00:00:00 2001 From: Casey Schaufler Date: Wed, 10 Jul 2024 14:32:30 -0700 Subject: lsm: infrastructure management of the perf_event security blob Move management of the perf_event->security blob out of the individual security modules and into the security infrastructure. Instead of allocating the blobs from within the modules the modules tell the infrastructure how much space is required, and the space is allocated there. There are no longer any modules that require the perf_event_free() hook. The hook definition has been removed. Signed-off-by: Casey Schaufler Reviewed-by: John Johansen [PM: subject tweak] Signed-off-by: Paul Moore --- include/linux/lsm_hook_defs.h | 1 - include/linux/lsm_hooks.h | 1 + security/security.c | 20 ++++++++++++++++++-- security/selinux/hooks.c | 18 ++++-------------- security/selinux/include/objsec.h | 6 ++++++ 5 files changed, 29 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 4fcbc5b3f58c..12c81be78eb9 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -439,7 +439,6 @@ LSM_HOOK(int, 0, locked_down, enum lockdown_reason what) #ifdef CONFIG_PERF_EVENTS LSM_HOOK(int, 0, perf_event_open, struct perf_event_attr *attr, int type) LSM_HOOK(int, 0, perf_event_alloc, struct perf_event *event) -LSM_HOOK(void, LSM_RET_VOID, perf_event_free, struct perf_event *event) LSM_HOOK(int, 0, perf_event_read, struct perf_event *event) LSM_HOOK(int, 0, perf_event_write, struct perf_event *event) #endif /* CONFIG_PERF_EVENTS */ diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index b6fc6ac88723..f1ca8082075a 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -79,6 +79,7 @@ struct lsm_blob_sizes { int lbs_ipc; int lbs_key; int lbs_msg_msg; + int lbs_perf_event; int lbs_task; int lbs_xattr_count; /* number of xattr slots in new_xattrs array */ int lbs_tun_dev; diff --git a/security/security.c b/security/security.c index 80dc58d60aab..93ed7670fbc9 100644 --- a/security/security.c +++ b/security/security.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include @@ -230,6 +231,7 @@ static void __init lsm_set_blob_sizes(struct lsm_blob_sizes *needed) lsm_set_blob_size(&needed->lbs_ipc, &blob_sizes.lbs_ipc); lsm_set_blob_size(&needed->lbs_key, &blob_sizes.lbs_key); lsm_set_blob_size(&needed->lbs_msg_msg, &blob_sizes.lbs_msg_msg); + lsm_set_blob_size(&needed->lbs_perf_event, &blob_sizes.lbs_perf_event); lsm_set_blob_size(&needed->lbs_sock, &blob_sizes.lbs_sock); lsm_set_blob_size(&needed->lbs_superblock, &blob_sizes.lbs_superblock); lsm_set_blob_size(&needed->lbs_task, &blob_sizes.lbs_task); @@ -412,6 +414,7 @@ static void __init ordered_lsm_init(void) init_debug("msg_msg blob size = %d\n", blob_sizes.lbs_msg_msg); init_debug("sock blob size = %d\n", blob_sizes.lbs_sock); init_debug("superblock blob size = %d\n", blob_sizes.lbs_superblock); + init_debug("perf event blob size = %d\n", blob_sizes.lbs_perf_event); init_debug("task blob size = %d\n", blob_sizes.lbs_task); init_debug("tun device blob size = %d\n", blob_sizes.lbs_tun_dev); init_debug("xattr slots = %d\n", blob_sizes.lbs_xattr_count); @@ -5685,7 +5688,19 @@ int security_perf_event_open(struct perf_event_attr *attr, int type) */ int security_perf_event_alloc(struct perf_event *event) { - return call_int_hook(perf_event_alloc, event); + int rc; + + rc = lsm_blob_alloc(&event->security, blob_sizes.lbs_perf_event, + GFP_KERNEL); + if (rc) + return rc; + + rc = call_int_hook(perf_event_alloc, event); + if (rc) { + kfree(event->security); + event->security = NULL; + } + return rc; } /** @@ -5696,7 +5711,8 @@ int security_perf_event_alloc(struct perf_event *event) */ void security_perf_event_free(struct perf_event *event) { - call_void_hook(perf_event_free, event); + kfree(event->security); + event->security = NULL; } /** diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 675c69ebb77c..0939816e9671 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -6955,6 +6955,9 @@ struct lsm_blob_sizes selinux_blob_sizes __ro_after_init = { .lbs_ipc = sizeof(struct ipc_security_struct), .lbs_key = sizeof(struct key_security_struct), .lbs_msg_msg = sizeof(struct msg_security_struct), +#ifdef CONFIG_PERF_EVENTS + .lbs_perf_event = sizeof(struct perf_event_security_struct), +#endif .lbs_sock = sizeof(struct sk_security_struct), .lbs_superblock = sizeof(struct superblock_security_struct), .lbs_xattr_count = SELINUX_INODE_INIT_XATTRS, @@ -6986,24 +6989,12 @@ static int selinux_perf_event_alloc(struct perf_event *event) { struct perf_event_security_struct *perfsec; - perfsec = kzalloc(sizeof(*perfsec), GFP_KERNEL); - if (!perfsec) - return -ENOMEM; - + perfsec = selinux_perf_event(event->security); perfsec->sid = current_sid(); - event->security = perfsec; return 0; } -static void selinux_perf_event_free(struct perf_event *event) -{ - struct perf_event_security_struct *perfsec = event->security; - - event->security = NULL; - kfree(perfsec); -} - static int selinux_perf_event_read(struct perf_event *event) { struct perf_event_security_struct *perfsec = event->security; @@ -7316,7 +7307,6 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = { #ifdef CONFIG_PERF_EVENTS LSM_HOOK_INIT(perf_event_open, selinux_perf_event_open), - LSM_HOOK_INIT(perf_event_free, selinux_perf_event_free), LSM_HOOK_INIT(perf_event_read, selinux_perf_event_read), LSM_HOOK_INIT(perf_event_write, selinux_perf_event_write), #endif diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h index ed9e37f3c9b5..c88cae81ee4c 100644 --- a/security/selinux/include/objsec.h +++ b/security/selinux/include/objsec.h @@ -217,4 +217,10 @@ static inline struct ib_security_struct *selinux_ib(void *ib_sec) return ib_sec + selinux_blob_sizes.lbs_ib; } +static inline struct perf_event_security_struct * +selinux_perf_event(void *perf_event) +{ + return perf_event + selinux_blob_sizes.lbs_perf_event; +} + #endif /* _SELINUX_OBJSEC_H_ */ -- cgit v1.2.3 From 92de36080c93296ef9005690705cba260b9bd68a Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 23 Jul 2024 08:34:39 -0700 Subject: bpf: Fail verification for sign-extension of packet data/data_end/data_meta syzbot reported a kernel crash due to commit 1f1e864b6555 ("bpf: Handle sign-extenstin ctx member accesses"). The reason is due to sign-extension of 32-bit load for packet data/data_end/data_meta uapi field. The original code looks like: r2 = *(s32 *)(r1 + 76) /* load __sk_buff->data */ r3 = *(u32 *)(r1 + 80) /* load __sk_buff->data_end */ r0 = r2 r0 += 8 if r3 > r0 goto +1 ... Note that __sk_buff->data load has 32-bit sign extension. After verification and convert_ctx_accesses(), the final asm code looks like: r2 = *(u64 *)(r1 +208) r2 = (s32)r2 r3 = *(u64 *)(r1 +80) r0 = r2 r0 += 8 if r3 > r0 goto pc+1 ... Note that 'r2 = (s32)r2' may make the kernel __sk_buff->data address invalid which may cause runtime failure. Currently, in C code, typically we have void *data = (void *)(long)skb->data; void *data_end = (void *)(long)skb->data_end; ... and it will generate r2 = *(u64 *)(r1 +208) r3 = *(u64 *)(r1 +80) r0 = r2 r0 += 8 if r3 > r0 goto pc+1 If we allow sign-extension, void *data = (void *)(long)(int)skb->data; void *data_end = (void *)(long)skb->data_end; ... the generated code looks like r2 = *(u64 *)(r1 +208) r2 <<= 32 r2 s>>= 32 r3 = *(u64 *)(r1 +80) r0 = r2 r0 += 8 if r3 > r0 goto pc+1 and this will cause verification failure since "r2 <<= 32" is not allowed as "r2" is a packet pointer. To fix this issue for case r2 = *(s32 *)(r1 + 76) /* load __sk_buff->data */ this patch added additional checking in is_valid_access() callback function for packet data/data_end/data_meta access. If those accesses are with sign-extenstion, the verification will fail. [1] https://lore.kernel.org/bpf/000000000000c90eee061d236d37@google.com/ Reported-by: syzbot+ad9ec60c8eaf69e6f99c@syzkaller.appspotmail.com Fixes: 1f1e864b6555 ("bpf: Handle sign-extenstin ctx member accesses") Acked-by: Eduard Zingerman Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20240723153439.2429035-1-yonghong.song@linux.dev Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko --- include/linux/bpf.h | 1 + kernel/bpf/verifier.c | 5 +++-- net/core/filter.c | 21 ++++++++++++++++----- 3 files changed, 20 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f16d0753f518..f560ea0c2b36 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -920,6 +920,7 @@ static_assert(__BPF_REG_TYPE_MAX <= BPF_BASE_TYPE_LIMIT); */ struct bpf_insn_access_aux { enum bpf_reg_type reg_type; + bool is_ldsx; union { int ctx_field_size; struct { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c419005a29dc..2ab59db5837f 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5626,12 +5626,13 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, /* check access to 'struct bpf_context' fields. Supports fixed offsets only */ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, int size, enum bpf_access_type t, enum bpf_reg_type *reg_type, - struct btf **btf, u32 *btf_id, bool *is_retval) + struct btf **btf, u32 *btf_id, bool *is_retval, bool is_ldsx) { struct bpf_insn_access_aux info = { .reg_type = *reg_type, .log = &env->log, .is_retval = false, + .is_ldsx = is_ldsx, }; if (env->ops->is_valid_access && @@ -6945,7 +6946,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn return err; err = check_ctx_access(env, insn_idx, off, size, t, ®_type, &btf, - &btf_id, &is_retval); + &btf_id, &is_retval, is_ldsx); if (err) verbose_linfo(env, insn_idx, "; "); if (!err && t == BPF_READ && value_regno >= 0) { diff --git a/net/core/filter.c b/net/core/filter.c index f3c72cf86099..78a6f746ea0b 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -8579,13 +8579,16 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type if (off + size > offsetofend(struct __sk_buff, cb[4])) return false; break; + case bpf_ctx_range(struct __sk_buff, data): + case bpf_ctx_range(struct __sk_buff, data_meta): + case bpf_ctx_range(struct __sk_buff, data_end): + if (info->is_ldsx || size != size_default) + return false; + break; case bpf_ctx_range_till(struct __sk_buff, remote_ip6[0], remote_ip6[3]): case bpf_ctx_range_till(struct __sk_buff, local_ip6[0], local_ip6[3]): case bpf_ctx_range_till(struct __sk_buff, remote_ip4, remote_ip4): case bpf_ctx_range_till(struct __sk_buff, local_ip4, local_ip4): - case bpf_ctx_range(struct __sk_buff, data): - case bpf_ctx_range(struct __sk_buff, data_meta): - case bpf_ctx_range(struct __sk_buff, data_end): if (size != size_default) return false; break; @@ -9029,6 +9032,14 @@ static bool xdp_is_valid_access(int off, int size, } } return false; + } else { + switch (off) { + case offsetof(struct xdp_md, data_meta): + case offsetof(struct xdp_md, data): + case offsetof(struct xdp_md, data_end): + if (info->is_ldsx) + return false; + } } switch (off) { @@ -9354,12 +9365,12 @@ static bool flow_dissector_is_valid_access(int off, int size, switch (off) { case bpf_ctx_range(struct __sk_buff, data): - if (size != size_default) + if (info->is_ldsx || size != size_default) return false; info->reg_type = PTR_TO_PACKET; return true; case bpf_ctx_range(struct __sk_buff, data_end): - if (size != size_default) + if (info->is_ldsx || size != size_default) return false; info->reg_type = PTR_TO_PACKET_END; return true; -- cgit v1.2.3 From 5b5f51bff1b66cedb62b5ba74a1878341204e057 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Mon, 22 Jul 2024 16:38:36 -0700 Subject: bpf: no_caller_saved_registers attribute for helper calls GCC and LLVM define a no_caller_saved_registers function attribute. This attribute means that function scratches only some of the caller saved registers defined by ABI. For BPF the set of such registers could be defined as follows: - R0 is scratched only if function is non-void; - R1-R5 are scratched only if corresponding parameter type is defined in the function prototype. This commit introduces flag bpf_func_prot->allow_nocsr. If this flag is set for some helper function, verifier assumes that it follows no_caller_saved_registers calling convention. The contract between kernel and clang allows to simultaneously use such functions and maintain backwards compatibility with old kernels that don't understand no_caller_saved_registers calls (nocsr for short): - clang generates a simple pattern for nocsr calls, e.g.: r1 = 1; r2 = 2; *(u64 *)(r10 - 8) = r1; *(u64 *)(r10 - 16) = r2; call %[to_be_inlined] r2 = *(u64 *)(r10 - 16); r1 = *(u64 *)(r10 - 8); r0 = r1; r0 += r2; exit; - kernel removes unnecessary spills and fills, if called function is inlined by verifier or current JIT (with assumption that patch inserted by verifier or JIT honors nocsr contract, e.g. does not scratch r3-r5 for the example above), e.g. the code above would be transformed to: r1 = 1; r2 = 2; call %[to_be_inlined] r0 = r1; r0 += r2; exit; Technically, the transformation is split into the following phases: - function mark_nocsr_patterns(), called from bpf_check() searches and marks potential patterns in instruction auxiliary data; - upon stack read or write access, function check_nocsr_stack_contract() is used to verify if stack offsets, presumably reserved for nocsr patterns, are used only from those patterns; - function remove_nocsr_spills_fills(), called from bpf_check(), applies the rewrite for valid patterns. See comment in mark_nocsr_pattern_for_call() for more details. Suggested-by: Alexei Starovoitov Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20240722233844.1406874-3-eddyz87@gmail.com Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko --- include/linux/bpf.h | 6 + include/linux/bpf_verifier.h | 14 ++ kernel/bpf/verifier.c | 317 ++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 334 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f560ea0c2b36..b9425e410bcb 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -808,6 +808,12 @@ struct bpf_func_proto { bool gpl_only; bool pkt_access; bool might_sleep; + /* set to true if helper follows contract for gcc/llvm + * attribute no_caller_saved_registers: + * - void functions do not scratch r0 + * - functions taking N arguments scratch only registers r1-rN + */ + bool allow_nocsr; enum bpf_return_type ret_type; union { struct { diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 731a0a4ac13c..5cea15c81b8a 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -576,6 +576,14 @@ struct bpf_insn_aux_data { bool is_iter_next; /* bpf_iter__next() kfunc call */ bool call_with_percpu_alloc_ptr; /* {this,per}_cpu_ptr() with prog percpu alloc */ u8 alu_state; /* used in combination with alu_limit */ + /* true if STX or LDX instruction is a part of a spill/fill + * pattern for a no_caller_saved_registers call. + */ + u8 nocsr_pattern:1; + /* for CALL instructions, a number of spill/fill pairs in the + * no_caller_saved_registers pattern. + */ + u8 nocsr_spills_num:3; /* below fields are initialized once */ unsigned int orig_idx; /* original instruction index */ @@ -645,6 +653,10 @@ struct bpf_subprog_info { u32 linfo_idx; /* The idx to the main_prog->aux->linfo */ u16 stack_depth; /* max. stack depth used by this function */ u16 stack_extra; + /* offsets in range [stack_depth .. nocsr_stack_off) + * are used for no_caller_saved_registers spills and fills. + */ + s16 nocsr_stack_off; bool has_tail_call: 1; bool tail_call_reachable: 1; bool has_ld_abs: 1; @@ -652,6 +664,8 @@ struct bpf_subprog_info { bool is_async_cb: 1; bool is_exception_cb: 1; bool args_cached: 1; + /* true if nocsr stack region is used by functions that can't be inlined */ + bool keep_nocsr_stack: 1; u8 arg_cnt; struct bpf_subprog_arg_info args[MAX_BPF_FUNC_REG_ARGS]; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 3ed67452f8c6..7587336967cc 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4579,6 +4579,31 @@ static int get_reg_width(struct bpf_reg_state *reg) return fls64(reg->umax_value); } +/* See comment for mark_nocsr_pattern_for_call() */ +static void check_nocsr_stack_contract(struct bpf_verifier_env *env, struct bpf_func_state *state, + int insn_idx, int off) +{ + struct bpf_subprog_info *subprog = &env->subprog_info[state->subprogno]; + struct bpf_insn_aux_data *aux = env->insn_aux_data; + int i; + + if (subprog->nocsr_stack_off <= off || aux[insn_idx].nocsr_pattern) + return; + /* access to the region [max_stack_depth .. nocsr_stack_off) + * from something that is not a part of the nocsr pattern, + * disable nocsr rewrites for current subprogram by setting + * nocsr_stack_off to a value smaller than any possible offset. + */ + subprog->nocsr_stack_off = S16_MIN; + /* reset nocsr aux flags within subprogram, + * happens at most once per subprogram + */ + for (i = subprog->start; i < (subprog + 1)->start; ++i) { + aux[i].nocsr_spills_num = 0; + aux[i].nocsr_pattern = 0; + } +} + /* check_stack_{read,write}_fixed_off functions track spill/fill of registers, * stack boundary and alignment are checked in check_mem_access() */ @@ -4627,6 +4652,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, if (err) return err; + check_nocsr_stack_contract(env, state, insn_idx, off); mark_stack_slot_scratched(env, spi); if (reg && !(off % BPF_REG_SIZE) && reg->type == SCALAR_VALUE && env->bpf_capable) { bool reg_value_fits; @@ -4761,6 +4787,7 @@ static int check_stack_write_var_off(struct bpf_verifier_env *env, return err; } + check_nocsr_stack_contract(env, state, insn_idx, min_off); /* Variable offset writes destroy any spilled pointers in range. */ for (i = min_off; i < max_off; i++) { u8 new_type, *stype; @@ -4899,6 +4926,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, reg = ®_state->stack[spi].spilled_ptr; mark_stack_slot_scratched(env, spi); + check_nocsr_stack_contract(env, state, env->insn_idx, off); if (is_spilled_reg(®_state->stack[spi])) { u8 spill_size = 1; @@ -5059,6 +5087,7 @@ static int check_stack_read_var_off(struct bpf_verifier_env *env, min_off = reg->smin_value + off; max_off = reg->smax_value + off; mark_reg_stack_read(env, ptr_state, min_off, max_off + size, dst_regno); + check_nocsr_stack_contract(env, ptr_state, env->insn_idx, min_off); return 0; } @@ -6772,10 +6801,20 @@ static int check_stack_slot_within_bounds(struct bpf_verifier_env *env, struct bpf_func_state *state, enum bpf_access_type t) { - int min_valid_off; + struct bpf_insn_aux_data *aux = &env->insn_aux_data[env->insn_idx]; + int min_valid_off, max_bpf_stack; + + /* If accessing instruction is a spill/fill from nocsr pattern, + * add room for all caller saved registers below MAX_BPF_STACK. + * In case if nocsr rewrite won't happen maximal stack depth + * would be checked by check_max_stack_depth_subprog(). + */ + max_bpf_stack = MAX_BPF_STACK; + if (aux->nocsr_pattern) + max_bpf_stack += CALLER_SAVED_REGS * BPF_REG_SIZE; if (t == BPF_WRITE || env->allow_uninit_stack) - min_valid_off = -MAX_BPF_STACK; + min_valid_off = -max_bpf_stack; else min_valid_off = -state->allocated_stack; @@ -16061,6 +16100,232 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns, return ret; } +/* Bitmask with 1s for all caller saved registers */ +#define ALL_CALLER_SAVED_REGS ((1u << CALLER_SAVED_REGS) - 1) + +/* Return a bitmask specifying which caller saved registers are + * clobbered by a call to a helper *as if* this helper follows + * no_caller_saved_registers contract: + * - includes R0 if function is non-void; + * - includes R1-R5 if corresponding parameter has is described + * in the function prototype. + */ +static u32 helper_nocsr_clobber_mask(const struct bpf_func_proto *fn) +{ + u8 mask; + int i; + + mask = 0; + if (fn->ret_type != RET_VOID) + mask |= BIT(BPF_REG_0); + for (i = 0; i < ARRAY_SIZE(fn->arg_type); ++i) + if (fn->arg_type[i] != ARG_DONTCARE) + mask |= BIT(BPF_REG_1 + i); + return mask; +} + +/* True if do_misc_fixups() replaces calls to helper number 'imm', + * replacement patch is presumed to follow no_caller_saved_registers contract + * (see mark_nocsr_pattern_for_call() below). + */ +static bool verifier_inlines_helper_call(struct bpf_verifier_env *env, s32 imm) +{ + return false; +} + +/* GCC and LLVM define a no_caller_saved_registers function attribute. + * This attribute means that function scratches only some of + * the caller saved registers defined by ABI. + * For BPF the set of such registers could be defined as follows: + * - R0 is scratched only if function is non-void; + * - R1-R5 are scratched only if corresponding parameter type is defined + * in the function prototype. + * + * The contract between kernel and clang allows to simultaneously use + * such functions and maintain backwards compatibility with old + * kernels that don't understand no_caller_saved_registers calls + * (nocsr for short): + * + * - for nocsr calls clang allocates registers as-if relevant r0-r5 + * registers are not scratched by the call; + * + * - as a post-processing step, clang visits each nocsr call and adds + * spill/fill for every live r0-r5; + * + * - stack offsets used for the spill/fill are allocated as lowest + * stack offsets in whole function and are not used for any other + * purposes; + * + * - when kernel loads a program, it looks for such patterns + * (nocsr function surrounded by spills/fills) and checks if + * spill/fill stack offsets are used exclusively in nocsr patterns; + * + * - if so, and if verifier or current JIT inlines the call to the + * nocsr function (e.g. a helper call), kernel removes unnecessary + * spill/fill pairs; + * + * - when old kernel loads a program, presence of spill/fill pairs + * keeps BPF program valid, albeit slightly less efficient. + * + * For example: + * + * r1 = 1; + * r2 = 2; + * *(u64 *)(r10 - 8) = r1; r1 = 1; + * *(u64 *)(r10 - 16) = r2; r2 = 2; + * call %[to_be_inlined] --> call %[to_be_inlined] + * r2 = *(u64 *)(r10 - 16); r0 = r1; + * r1 = *(u64 *)(r10 - 8); r0 += r2; + * r0 = r1; exit; + * r0 += r2; + * exit; + * + * The purpose of mark_nocsr_pattern_for_call is to: + * - look for such patterns; + * - mark spill and fill instructions in env->insn_aux_data[*].nocsr_pattern; + * - mark set env->insn_aux_data[*].nocsr_spills_num for call instruction; + * - update env->subprog_info[*]->nocsr_stack_off to find an offset + * at which nocsr spill/fill stack slots start; + * - update env->subprog_info[*]->keep_nocsr_stack. + * + * The .nocsr_pattern and .nocsr_stack_off are used by + * check_nocsr_stack_contract() to check if every stack access to + * nocsr spill/fill stack slot originates from spill/fill + * instructions, members of nocsr patterns. + * + * If such condition holds true for a subprogram, nocsr patterns could + * be rewritten by remove_nocsr_spills_fills(). + * Otherwise nocsr patterns are not changed in the subprogram + * (code, presumably, generated by an older clang version). + * + * For example, it is *not* safe to remove spill/fill below: + * + * r1 = 1; + * *(u64 *)(r10 - 8) = r1; r1 = 1; + * call %[to_be_inlined] --> call %[to_be_inlined] + * r1 = *(u64 *)(r10 - 8); r0 = *(u64 *)(r10 - 8); <---- wrong !!! + * r0 = *(u64 *)(r10 - 8); r0 += r1; + * r0 += r1; exit; + * exit; + */ +static void mark_nocsr_pattern_for_call(struct bpf_verifier_env *env, + struct bpf_subprog_info *subprog, + int insn_idx, s16 lowest_off) +{ + struct bpf_insn *insns = env->prog->insnsi, *stx, *ldx; + struct bpf_insn *call = &env->prog->insnsi[insn_idx]; + const struct bpf_func_proto *fn; + u32 clobbered_regs_mask = ALL_CALLER_SAVED_REGS; + u32 expected_regs_mask; + bool can_be_inlined = false; + s16 off; + int i; + + if (bpf_helper_call(call)) { + if (get_helper_proto(env, call->imm, &fn) < 0) + /* error would be reported later */ + return; + clobbered_regs_mask = helper_nocsr_clobber_mask(fn); + can_be_inlined = fn->allow_nocsr && + (verifier_inlines_helper_call(env, call->imm) || + bpf_jit_inlines_helper_call(call->imm)); + } + + if (clobbered_regs_mask == ALL_CALLER_SAVED_REGS) + return; + + /* e.g. if helper call clobbers r{0,1}, expect r{2,3,4,5} in the pattern */ + expected_regs_mask = ~clobbered_regs_mask & ALL_CALLER_SAVED_REGS; + + /* match pairs of form: + * + * *(u64 *)(r10 - Y) = rX (where Y % 8 == 0) + * ... + * call %[to_be_inlined] + * ... + * rX = *(u64 *)(r10 - Y) + */ + for (i = 1, off = lowest_off; i <= ARRAY_SIZE(caller_saved); ++i, off += BPF_REG_SIZE) { + if (insn_idx - i < 0 || insn_idx + i >= env->prog->len) + break; + stx = &insns[insn_idx - i]; + ldx = &insns[insn_idx + i]; + /* must be a stack spill/fill pair */ + if (stx->code != (BPF_STX | BPF_MEM | BPF_DW) || + ldx->code != (BPF_LDX | BPF_MEM | BPF_DW) || + stx->dst_reg != BPF_REG_10 || + ldx->src_reg != BPF_REG_10) + break; + /* must be a spill/fill for the same reg */ + if (stx->src_reg != ldx->dst_reg) + break; + /* must be one of the previously unseen registers */ + if ((BIT(stx->src_reg) & expected_regs_mask) == 0) + break; + /* must be a spill/fill for the same expected offset, + * no need to check offset alignment, BPF_DW stack access + * is always 8-byte aligned. + */ + if (stx->off != off || ldx->off != off) + break; + expected_regs_mask &= ~BIT(stx->src_reg); + env->insn_aux_data[insn_idx - i].nocsr_pattern = 1; + env->insn_aux_data[insn_idx + i].nocsr_pattern = 1; + } + if (i == 1) + return; + + /* Conditionally set 'nocsr_spills_num' to allow forward + * compatibility when more helper functions are marked as + * nocsr at compile time than current kernel supports, e.g: + * + * 1: *(u64 *)(r10 - 8) = r1 + * 2: call A ;; assume A is nocsr for current kernel + * 3: r1 = *(u64 *)(r10 - 8) + * 4: *(u64 *)(r10 - 8) = r1 + * 5: call B ;; assume B is not nocsr for current kernel + * 6: r1 = *(u64 *)(r10 - 8) + * + * There is no need to block nocsr rewrite for such program. + * Set 'nocsr_pattern' for both calls to keep check_nocsr_stack_contract() happy, + * don't set 'nocsr_spills_num' for call B so that remove_nocsr_spills_fills() + * does not remove spill/fill pair {4,6}. + */ + if (can_be_inlined) + env->insn_aux_data[insn_idx].nocsr_spills_num = i - 1; + else + subprog->keep_nocsr_stack = 1; + subprog->nocsr_stack_off = min(subprog->nocsr_stack_off, off); +} + +static int mark_nocsr_patterns(struct bpf_verifier_env *env) +{ + struct bpf_subprog_info *subprog = env->subprog_info; + struct bpf_insn *insn; + s16 lowest_off; + int s, i; + + for (s = 0; s < env->subprog_cnt; ++s, ++subprog) { + /* find lowest stack spill offset used in this subprog */ + lowest_off = 0; + for (i = subprog->start; i < (subprog + 1)->start; ++i) { + insn = env->prog->insnsi + i; + if (insn->code != (BPF_STX | BPF_MEM | BPF_DW) || + insn->dst_reg != BPF_REG_10) + continue; + lowest_off = min(lowest_off, insn->off); + } + /* use this offset to find nocsr patterns */ + for (i = subprog->start; i < (subprog + 1)->start; ++i) { + insn = env->prog->insnsi + i; + if (insn->code != (BPF_JMP | BPF_CALL)) + continue; + mark_nocsr_pattern_for_call(env, subprog, i, lowest_off); + } + } + return 0; +} + /* Visits the instruction at index t and returns one of the following: * < 0 - an error occurred * DONE_EXPLORING - the instruction was fully explored @@ -19209,9 +19474,11 @@ static int opt_remove_dead_code(struct bpf_verifier_env *env) return 0; } +static const struct bpf_insn NOP = BPF_JMP_IMM(BPF_JA, 0, 0, 0); + static int opt_remove_nops(struct bpf_verifier_env *env) { - const struct bpf_insn ja = BPF_JMP_IMM(BPF_JA, 0, 0, 0); + const struct bpf_insn ja = NOP; struct bpf_insn *insn = env->prog->insnsi; int insn_cnt = env->prog->len; int i, err; @@ -20957,6 +21224,40 @@ static int optimize_bpf_loop(struct bpf_verifier_env *env) return 0; } +/* Remove unnecessary spill/fill pairs, members of nocsr pattern, + * adjust subprograms stack depth when possible. + */ +static int remove_nocsr_spills_fills(struct bpf_verifier_env *env) +{ + struct bpf_subprog_info *subprog = env->subprog_info; + struct bpf_insn_aux_data *aux = env->insn_aux_data; + struct bpf_insn *insn = env->prog->insnsi; + int insn_cnt = env->prog->len; + u32 spills_num; + bool modified = false; + int i, j; + + for (i = 0; i < insn_cnt; i++, insn++) { + if (aux[i].nocsr_spills_num > 0) { + spills_num = aux[i].nocsr_spills_num; + /* NOPs would be removed by opt_remove_nops() */ + for (j = 1; j <= spills_num; ++j) { + *(insn - j) = NOP; + *(insn + j) = NOP; + } + modified = true; + } + if ((subprog + 1)->start == i + 1) { + if (modified && !subprog->keep_nocsr_stack) + subprog->stack_depth = -subprog->nocsr_stack_off; + subprog++; + modified = false; + } + } + + return 0; +} + static void free_states(struct bpf_verifier_env *env) { struct bpf_verifier_state_list *sl, *sln; @@ -21871,6 +22172,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 if (ret < 0) goto skip_full_check; + ret = mark_nocsr_patterns(env); + if (ret < 0) + goto skip_full_check; + ret = do_check_main(env); ret = ret ?: do_check_subprogs(env); @@ -21880,6 +22185,12 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 skip_full_check: kvfree(env->explored_states); + /* might decrease stack depth, keep it before passes that + * allocate additional slots. + */ + if (ret == 0) + ret = remove_nocsr_spills_fills(env); + if (ret == 0) ret = check_max_stack_depth(env); -- cgit v1.2.3 From 7ebd8c5acad5f8ca41f37b36dc62570e1fa13d8b Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 18 Jul 2024 16:59:06 +0900 Subject: ata: libata: Use QUIRK instead of HORKAGE According to Wiktionary, the verb "hork" is computing slang defined as "To foul up; to be occupied with difficulty, tangle, or unpleasantness; to be broken" (https://en.wiktionary.org/wiki/hork#Verb). libata uses this with the term "horkage" to refer to broken device features. Given that this term is not widely used and its meaning unknown to many, rename it to the more commonly used term "quirk", similar to many other places in the kernel. The renaming done is: 1) Rename all ATA_HORKAGE_XXX flags to ATA_QUIRK_XXX 2) Rename struct ata_device horkage field to quirks 3) Rename struct ata_blacklist_entry to struct ata_dev_quirks_entry. The array of these structures defining quirks for known devices is renamed __ata_dev_quirks. 4) The functions ata_dev_blacklisted() and ata_force_horkage() are renamed to ata_dev_quirks() and ata_force_quirks() respectively. 5) All the force_horkage_xxx() macros are renamed to force_quirk_xxx() And while at it, make sure that the type "unsigned int" is used consistantly for quirk flags variables and data structure fields. Signed-off-by: Damien Le Moal Reviewed-by: Niklas Cassel Reviewed-by: Igor Pylypiv --- drivers/ata/libata-core.c | 490 ++++++++++++++++++++--------------------- drivers/ata/libata-sata.c | 2 +- drivers/ata/libata-scsi.c | 9 +- drivers/ata/libata-sff.c | 10 +- drivers/ata/libata-transport.c | 6 +- drivers/ata/pata_it821x.c | 4 +- drivers/ata/sata_sil.c | 2 +- include/linux/libata.h | 71 +++--- 8 files changed, 297 insertions(+), 297 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index f1e5055e33fe..19b041bd7588 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -84,7 +84,7 @@ static unsigned int ata_dev_init_params(struct ata_device *dev, u16 heads, u16 sectors); static unsigned int ata_dev_set_xfermode(struct ata_device *dev); static void ata_dev_xfermask(struct ata_device *dev); -static unsigned long ata_dev_blacklisted(const struct ata_device *dev); +static unsigned int ata_dev_quirks(const struct ata_device *dev); static DEFINE_IDA(ata_ida); @@ -94,8 +94,8 @@ struct ata_force_param { u8 cbl; u8 spd_limit; unsigned int xfer_mask; - unsigned int horkage_on; - unsigned int horkage_off; + unsigned int quirk_on; + unsigned int quirk_off; u16 lflags_on; u16 lflags_off; }; @@ -457,17 +457,17 @@ static void ata_force_xfermask(struct ata_device *dev) } /** - * ata_force_horkage - force horkage according to libata.force + * ata_force_quirks - force quirks according to libata.force * @dev: ATA device of interest * - * Force horkage according to libata.force and whine about it. + * Force quirks according to libata.force and whine about it. * For consistency with link selection, device number 15 selects * the first device connected to the host link. * * LOCKING: * EH context. */ -static void ata_force_horkage(struct ata_device *dev) +static void ata_force_quirks(struct ata_device *dev) { int devno = dev->link->pmp + dev->devno; int alt_devno = devno; @@ -487,21 +487,21 @@ static void ata_force_horkage(struct ata_device *dev) fe->device != alt_devno) continue; - if (!(~dev->horkage & fe->param.horkage_on) && - !(dev->horkage & fe->param.horkage_off)) + if (!(~dev->quirks & fe->param.quirk_on) && + !(dev->quirks & fe->param.quirk_off)) continue; - dev->horkage |= fe->param.horkage_on; - dev->horkage &= ~fe->param.horkage_off; + dev->quirks |= fe->param.quirk_on; + dev->quirks &= ~fe->param.quirk_off; - ata_dev_notice(dev, "FORCE: horkage modified (%s)\n", + ata_dev_notice(dev, "FORCE: modified (%s)\n", fe->param.name); } } #else static inline void ata_force_link_limits(struct ata_link *link) { } static inline void ata_force_xfermask(struct ata_device *dev) { } -static inline void ata_force_horkage(struct ata_device *dev) { } +static inline void ata_force_quirks(struct ata_device *dev) { } #endif /** @@ -1221,7 +1221,7 @@ static int ata_read_native_max_address(struct ata_device *dev, u64 *max_sectors) *max_sectors = ata_tf_to_lba48(&tf) + 1; else *max_sectors = ata_tf_to_lba(&tf) + 1; - if (dev->horkage & ATA_HORKAGE_HPA_SIZE) + if (dev->quirks & ATA_QUIRK_HPA_SIZE) (*max_sectors)--; return 0; } @@ -1306,7 +1306,7 @@ static int ata_hpa_resize(struct ata_device *dev) /* do we need to do it? */ if ((dev->class != ATA_DEV_ATA && dev->class != ATA_DEV_ZAC) || !ata_id_has_lba(dev->id) || !ata_id_hpa_enabled(dev->id) || - (dev->horkage & ATA_HORKAGE_BROKEN_HPA)) + (dev->quirks & ATA_QUIRK_BROKEN_HPA)) return 0; /* read native max address */ @@ -1318,7 +1318,7 @@ static int ata_hpa_resize(struct ata_device *dev) if (rc == -EACCES || !unlock_hpa) { ata_dev_warn(dev, "HPA support seems broken, skipping HPA handling\n"); - dev->horkage |= ATA_HORKAGE_BROKEN_HPA; + dev->quirks |= ATA_QUIRK_BROKEN_HPA; /* we can continue if device aborted the command */ if (rc == -EACCES) @@ -1355,7 +1355,7 @@ static int ata_hpa_resize(struct ata_device *dev) "device aborted resize (%llu -> %llu), skipping HPA handling\n", (unsigned long long)sectors, (unsigned long long)native_sectors); - dev->horkage |= ATA_HORKAGE_BROKEN_HPA; + dev->quirks |= ATA_QUIRK_BROKEN_HPA; return 0; } else if (rc) return rc; @@ -1835,7 +1835,7 @@ retry: goto err_out; } - if (dev->horkage & ATA_HORKAGE_DUMP_ID) { + if (dev->quirks & ATA_QUIRK_DUMP_ID) { ata_dev_info(dev, "dumping IDENTIFY data, " "class=%d may_fallback=%d tried_spinup=%d\n", class, may_fallback, tried_spinup); @@ -2104,7 +2104,7 @@ unsigned int ata_read_log_page(struct ata_device *dev, u8 log, retry: ata_tf_init(dev, &tf); if (ata_dma_enabled(dev) && ata_id_has_read_log_dma_ext(dev->id) && - !(dev->horkage & ATA_HORKAGE_NO_DMA_LOG)) { + !(dev->quirks & ATA_QUIRK_NO_DMA_LOG)) { tf.command = ATA_CMD_READ_LOG_DMA_EXT; tf.protocol = ATA_PROT_DMA; dma = true; @@ -2124,7 +2124,7 @@ retry: if (err_mask) { if (dma) { - dev->horkage |= ATA_HORKAGE_NO_DMA_LOG; + dev->quirks |= ATA_QUIRK_NO_DMA_LOG; if (!ata_port_is_frozen(dev->link->ap)) goto retry; } @@ -2140,7 +2140,7 @@ static int ata_log_supported(struct ata_device *dev, u8 log) { struct ata_port *ap = dev->link->ap; - if (dev->horkage & ATA_HORKAGE_NO_LOG_DIR) + if (dev->quirks & ATA_QUIRK_NO_LOG_DIR) return 0; if (ata_read_log_page(dev, ATA_LOG_DIRECTORY, 0, ap->sector_buf, 1)) @@ -2153,7 +2153,7 @@ static bool ata_identify_page_supported(struct ata_device *dev, u8 page) struct ata_port *ap = dev->link->ap; unsigned int err, i; - if (dev->horkage & ATA_HORKAGE_NO_ID_DEV_LOG) + if (dev->quirks & ATA_QUIRK_NO_ID_DEV_LOG) return false; if (!ata_log_supported(dev, ATA_LOG_IDENTIFY_DEVICE)) { @@ -2165,7 +2165,7 @@ static bool ata_identify_page_supported(struct ata_device *dev, u8 page) if (ata_id_major_version(dev->id) >= 10) ata_dev_warn(dev, "ATA Identify Device Log not supported\n"); - dev->horkage |= ATA_HORKAGE_NO_ID_DEV_LOG; + dev->quirks |= ATA_QUIRK_NO_ID_DEV_LOG; return false; } @@ -2186,7 +2186,7 @@ static bool ata_identify_page_supported(struct ata_device *dev, u8 page) return false; } -static int ata_do_link_spd_horkage(struct ata_device *dev) +static int ata_do_link_spd_quirk(struct ata_device *dev) { struct ata_link *plink = ata_dev_phys_link(dev); u32 target, target_limit; @@ -2194,7 +2194,7 @@ static int ata_do_link_spd_horkage(struct ata_device *dev) if (!sata_scr_valid(plink)) return 0; - if (dev->horkage & ATA_HORKAGE_1_5_GBPS) + if (dev->quirks & ATA_QUIRK_1_5_GBPS) target = 1; else return 0; @@ -2212,7 +2212,7 @@ static int ata_do_link_spd_horkage(struct ata_device *dev) * guaranteed by setting sata_spd_limit to target_limit above. */ if (plink->sata_spd > target) { - ata_dev_info(dev, "applying link speed limit horkage to %s\n", + ata_dev_info(dev, "applying link speed limit quirk to %s\n", sata_spd_string(target)); return -EAGAIN; } @@ -2223,7 +2223,7 @@ static inline bool ata_dev_knobble(struct ata_device *dev) { struct ata_port *ap = dev->link->ap; - if (ata_dev_blacklisted(dev) & ATA_HORKAGE_BRIDGE_OK) + if (ata_dev_quirks(dev) & ATA_QUIRK_BRIDGE_OK) return false; return ((ap->cbl == ATA_CBL_SATA) && (!ata_id_is_sata(dev->id))); @@ -2246,7 +2246,7 @@ static void ata_dev_config_ncq_send_recv(struct ata_device *dev) dev->flags |= ATA_DFLAG_NCQ_SEND_RECV; memcpy(cmds, ap->sector_buf, ATA_LOG_NCQ_SEND_RECV_SIZE); - if (dev->horkage & ATA_HORKAGE_NO_NCQ_TRIM) { + if (dev->quirks & ATA_QUIRK_NO_NCQ_TRIM) { ata_dev_dbg(dev, "disabling queued TRIM support\n"); cmds[ATA_LOG_NCQ_SEND_RECV_DSM_OFFSET] &= ~ATA_LOG_NCQ_SEND_RECV_DSM_TRIM; @@ -2334,12 +2334,12 @@ static int ata_dev_config_ncq(struct ata_device *dev, } if (!IS_ENABLED(CONFIG_SATA_HOST)) return 0; - if (dev->horkage & ATA_HORKAGE_NONCQ) { + if (dev->quirks & ATA_QUIRK_NONCQ) { snprintf(desc, desc_sz, "NCQ (not used)"); return 0; } - if (dev->horkage & ATA_HORKAGE_NO_NCQ_ON_ATI && + if (dev->quirks & ATA_QUIRK_NO_NCQ_ON_ATI && ata_dev_check_adapter(dev, PCI_VENDOR_ID_ATI)) { snprintf(desc, desc_sz, "NCQ (not used)"); return 0; @@ -2350,7 +2350,7 @@ static int ata_dev_config_ncq(struct ata_device *dev, dev->flags |= ATA_DFLAG_NCQ; } - if (!(dev->horkage & ATA_HORKAGE_BROKEN_FPDMA_AA) && + if (!(dev->quirks & ATA_QUIRK_BROKEN_FPDMA_AA) && (ap->flags & ATA_FLAG_FPDMA_AA) && ata_id_has_fpdma_aa(dev->id)) { err_mask = ata_dev_set_feature(dev, SETFEATURES_SATA_ENABLE, @@ -2360,7 +2360,7 @@ static int ata_dev_config_ncq(struct ata_device *dev, "failed to enable AA (error_mask=0x%x)\n", err_mask); if (err_mask != AC_ERR_DEV) { - dev->horkage |= ATA_HORKAGE_BROKEN_FPDMA_AA; + dev->quirks |= ATA_QUIRK_BROKEN_FPDMA_AA; return -EIO; } } else @@ -2689,7 +2689,7 @@ static void ata_dev_config_fua(struct ata_device *dev) goto nofua; /* Ignore known bad devices and devices that lack NCQ support */ - if (!ata_ncq_supported(dev) || (dev->horkage & ATA_HORKAGE_NO_FUA)) + if (!ata_ncq_supported(dev) || (dev->quirks & ATA_QUIRK_NO_FUA)) goto nofua; dev->flags |= ATA_DFLAG_FUA; @@ -2829,11 +2829,11 @@ int ata_dev_configure(struct ata_device *dev) return 0; } - /* set horkage */ - dev->horkage |= ata_dev_blacklisted(dev); - ata_force_horkage(dev); + /* Set quirks */ + dev->quirks |= ata_dev_quirks(dev); + ata_force_quirks(dev); - if (dev->horkage & ATA_HORKAGE_DISABLE) { + if (dev->quirks & ATA_QUIRK_DISABLE) { ata_dev_info(dev, "unsupported device, disabling\n"); ata_dev_disable(dev); return 0; @@ -2848,19 +2848,19 @@ int ata_dev_configure(struct ata_device *dev) return 0; } - rc = ata_do_link_spd_horkage(dev); + rc = ata_do_link_spd_quirk(dev); if (rc) return rc; /* some WD SATA-1 drives have issues with LPM, turn on NOLPM for them */ - if ((dev->horkage & ATA_HORKAGE_WD_BROKEN_LPM) && + if ((dev->quirks & ATA_QUIRK_WD_BROKEN_LPM) && (id[ATA_ID_SATA_CAPABILITY] & 0xe) == 0x2) - dev->horkage |= ATA_HORKAGE_NOLPM; + dev->quirks |= ATA_QUIRK_NOLPM; if (ap->flags & ATA_FLAG_NO_LPM) - dev->horkage |= ATA_HORKAGE_NOLPM; + dev->quirks |= ATA_QUIRK_NOLPM; - if (dev->horkage & ATA_HORKAGE_NOLPM) { + if (dev->quirks & ATA_QUIRK_NOLPM) { ata_dev_warn(dev, "LPM support broken, forcing max_power\n"); dev->link->ap->target_lpm_policy = ATA_LPM_MAX_POWER; } @@ -3006,7 +3006,8 @@ int ata_dev_configure(struct ata_device *dev) cdb_intr_string = ", CDB intr"; } - if (atapi_dmadir || (dev->horkage & ATA_HORKAGE_ATAPI_DMADIR) || atapi_id_dmadir(dev->id)) { + if (atapi_dmadir || (dev->quirks & ATA_QUIRK_ATAPI_DMADIR) || + atapi_id_dmadir(dev->id)) { dev->flags |= ATA_DFLAG_DMADIR; dma_dir_string = ", DMADIR"; } @@ -3043,24 +3044,24 @@ int ata_dev_configure(struct ata_device *dev) if ((dev->class == ATA_DEV_ATAPI) && (atapi_command_packet_set(id) == TYPE_TAPE)) { dev->max_sectors = ATA_MAX_SECTORS_TAPE; - dev->horkage |= ATA_HORKAGE_STUCK_ERR; + dev->quirks |= ATA_QUIRK_STUCK_ERR; } - if (dev->horkage & ATA_HORKAGE_MAX_SEC_128) + if (dev->quirks & ATA_QUIRK_MAX_SEC_128) dev->max_sectors = min_t(unsigned int, ATA_MAX_SECTORS_128, dev->max_sectors); - if (dev->horkage & ATA_HORKAGE_MAX_SEC_1024) + if (dev->quirks & ATA_QUIRK_MAX_SEC_1024) dev->max_sectors = min_t(unsigned int, ATA_MAX_SECTORS_1024, dev->max_sectors); - if (dev->horkage & ATA_HORKAGE_MAX_SEC_LBA48) + if (dev->quirks & ATA_QUIRK_MAX_SEC_LBA48) dev->max_sectors = ATA_MAX_SECTORS_LBA48; if (ap->ops->dev_config) ap->ops->dev_config(dev); - if (dev->horkage & ATA_HORKAGE_DIAGNOSTIC) { + if (dev->quirks & ATA_QUIRK_DIAGNOSTIC) { /* Let the user know. We don't want to disallow opens for rescue purposes, or in case the vendor is just a blithering idiot. Do this after the dev_config call as some controllers @@ -3075,7 +3076,7 @@ int ata_dev_configure(struct ata_device *dev) } } - if ((dev->horkage & ATA_HORKAGE_FIRMWARE_WARN) && print_info) { + if ((dev->quirks & ATA_QUIRK_FIRMWARE_WARN) && print_info) { ata_dev_warn(dev, "WARNING: device requires firmware update to be fully functional\n"); ata_dev_warn(dev, " contact the vendor or visit http://ata.wiki.kernel.org\n"); } @@ -3425,7 +3426,7 @@ static int ata_dev_set_mode(struct ata_device *dev) { struct ata_port *ap = dev->link->ap; struct ata_eh_context *ehc = &dev->link->eh_context; - const bool nosetxfer = dev->horkage & ATA_HORKAGE_NOSETXFER; + const bool nosetxfer = dev->quirks & ATA_QUIRK_NOSETXFER; const char *dev_err_whine = ""; int ign_dev_err = 0; unsigned int err_mask = 0; @@ -3969,7 +3970,7 @@ int ata_dev_revalidate(struct ata_device *dev, unsigned int new_class, */ if (dev->n_native_sectors == n_native_sectors && dev->n_sectors < n_sectors && n_sectors == n_native_sectors && - !(dev->horkage & ATA_HORKAGE_BROKEN_HPA)) { + !(dev->quirks & ATA_QUIRK_BROKEN_HPA)) { ata_dev_warn(dev, "old n_sectors matches native, probably " "late HPA lock, will try to unlock HPA\n"); @@ -3987,223 +3988,223 @@ int ata_dev_revalidate(struct ata_device *dev, unsigned int new_class, return rc; } -struct ata_blacklist_entry { +struct ata_dev_quirks_entry { const char *model_num; const char *model_rev; - unsigned long horkage; + unsigned int quirks; }; -static const struct ata_blacklist_entry ata_device_blacklist [] = { +static const struct ata_dev_quirks_entry __ata_dev_quirks[] = { /* Devices with DMA related problems under Linux */ - { "WDC AC11000H", NULL, ATA_HORKAGE_NODMA }, - { "WDC AC22100H", NULL, ATA_HORKAGE_NODMA }, - { "WDC AC32500H", NULL, ATA_HORKAGE_NODMA }, - { "WDC AC33100H", NULL, ATA_HORKAGE_NODMA }, - { "WDC AC31600H", NULL, ATA_HORKAGE_NODMA }, - { "WDC AC32100H", "24.09P07", ATA_HORKAGE_NODMA }, - { "WDC AC23200L", "21.10N21", ATA_HORKAGE_NODMA }, - { "Compaq CRD-8241B", NULL, ATA_HORKAGE_NODMA }, - { "CRD-8400B", NULL, ATA_HORKAGE_NODMA }, - { "CRD-848[02]B", NULL, ATA_HORKAGE_NODMA }, - { "CRD-84", NULL, ATA_HORKAGE_NODMA }, - { "SanDisk SDP3B", NULL, ATA_HORKAGE_NODMA }, - { "SanDisk SDP3B-64", NULL, ATA_HORKAGE_NODMA }, - { "SANYO CD-ROM CRD", NULL, ATA_HORKAGE_NODMA }, - { "HITACHI CDR-8", NULL, ATA_HORKAGE_NODMA }, - { "HITACHI CDR-8[34]35",NULL, ATA_HORKAGE_NODMA }, - { "Toshiba CD-ROM XM-6202B", NULL, ATA_HORKAGE_NODMA }, - { "TOSHIBA CD-ROM XM-1702BC", NULL, ATA_HORKAGE_NODMA }, - { "CD-532E-A", NULL, ATA_HORKAGE_NODMA }, - { "E-IDE CD-ROM CR-840",NULL, ATA_HORKAGE_NODMA }, - { "CD-ROM Drive/F5A", NULL, ATA_HORKAGE_NODMA }, - { "WPI CDD-820", NULL, ATA_HORKAGE_NODMA }, - { "SAMSUNG CD-ROM SC-148C", NULL, ATA_HORKAGE_NODMA }, - { "SAMSUNG CD-ROM SC", NULL, ATA_HORKAGE_NODMA }, - { "ATAPI CD-ROM DRIVE 40X MAXIMUM",NULL,ATA_HORKAGE_NODMA }, - { "_NEC DV5800A", NULL, ATA_HORKAGE_NODMA }, - { "SAMSUNG CD-ROM SN-124", "N001", ATA_HORKAGE_NODMA }, - { "Seagate STT20000A", NULL, ATA_HORKAGE_NODMA }, - { " 2GB ATA Flash Disk", "ADMA428M", ATA_HORKAGE_NODMA }, - { "VRFDFC22048UCHC-TE*", NULL, ATA_HORKAGE_NODMA }, + { "WDC AC11000H", NULL, ATA_QUIRK_NODMA }, + { "WDC AC22100H", NULL, ATA_QUIRK_NODMA }, + { "WDC AC32500H", NULL, ATA_QUIRK_NODMA }, + { "WDC AC33100H", NULL, ATA_QUIRK_NODMA }, + { "WDC AC31600H", NULL, ATA_QUIRK_NODMA }, + { "WDC AC32100H", "24.09P07", ATA_QUIRK_NODMA }, + { "WDC AC23200L", "21.10N21", ATA_QUIRK_NODMA }, + { "Compaq CRD-8241B", NULL, ATA_QUIRK_NODMA }, + { "CRD-8400B", NULL, ATA_QUIRK_NODMA }, + { "CRD-848[02]B", NULL, ATA_QUIRK_NODMA }, + { "CRD-84", NULL, ATA_QUIRK_NODMA }, + { "SanDisk SDP3B", NULL, ATA_QUIRK_NODMA }, + { "SanDisk SDP3B-64", NULL, ATA_QUIRK_NODMA }, + { "SANYO CD-ROM CRD", NULL, ATA_QUIRK_NODMA }, + { "HITACHI CDR-8", NULL, ATA_QUIRK_NODMA }, + { "HITACHI CDR-8[34]35", NULL, ATA_QUIRK_NODMA }, + { "Toshiba CD-ROM XM-6202B", NULL, ATA_QUIRK_NODMA }, + { "TOSHIBA CD-ROM XM-1702BC", NULL, ATA_QUIRK_NODMA }, + { "CD-532E-A", NULL, ATA_QUIRK_NODMA }, + { "E-IDE CD-ROM CR-840", NULL, ATA_QUIRK_NODMA }, + { "CD-ROM Drive/F5A", NULL, ATA_QUIRK_NODMA }, + { "WPI CDD-820", NULL, ATA_QUIRK_NODMA }, + { "SAMSUNG CD-ROM SC-148C", NULL, ATA_QUIRK_NODMA }, + { "SAMSUNG CD-ROM SC", NULL, ATA_QUIRK_NODMA }, + { "ATAPI CD-ROM DRIVE 40X MAXIMUM", NULL, ATA_QUIRK_NODMA }, + { "_NEC DV5800A", NULL, ATA_QUIRK_NODMA }, + { "SAMSUNG CD-ROM SN-124", "N001", ATA_QUIRK_NODMA }, + { "Seagate STT20000A", NULL, ATA_QUIRK_NODMA }, + { " 2GB ATA Flash Disk", "ADMA428M", ATA_QUIRK_NODMA }, + { "VRFDFC22048UCHC-TE*", NULL, ATA_QUIRK_NODMA }, /* Odd clown on sil3726/4726 PMPs */ - { "Config Disk", NULL, ATA_HORKAGE_DISABLE }, + { "Config Disk", NULL, ATA_QUIRK_DISABLE }, /* Similar story with ASMedia 1092 */ - { "ASMT109x- Config", NULL, ATA_HORKAGE_DISABLE }, + { "ASMT109x- Config", NULL, ATA_QUIRK_DISABLE }, /* Weird ATAPI devices */ - { "TORiSAN DVD-ROM DRD-N216", NULL, ATA_HORKAGE_MAX_SEC_128 }, - { "QUANTUM DAT DAT72-000", NULL, ATA_HORKAGE_ATAPI_MOD16_DMA }, - { "Slimtype DVD A DS8A8SH", NULL, ATA_HORKAGE_MAX_SEC_LBA48 }, - { "Slimtype DVD A DS8A9SH", NULL, ATA_HORKAGE_MAX_SEC_LBA48 }, + { "TORiSAN DVD-ROM DRD-N216", NULL, ATA_QUIRK_MAX_SEC_128 }, + { "QUANTUM DAT DAT72-000", NULL, ATA_QUIRK_ATAPI_MOD16_DMA }, + { "Slimtype DVD A DS8A8SH", NULL, ATA_QUIRK_MAX_SEC_LBA48 }, + { "Slimtype DVD A DS8A9SH", NULL, ATA_QUIRK_MAX_SEC_LBA48 }, /* * Causes silent data corruption with higher max sects. * http://lkml.kernel.org/g/x49wpy40ysk.fsf@segfault.boston.devel.redhat.com */ - { "ST380013AS", "3.20", ATA_HORKAGE_MAX_SEC_1024 }, + { "ST380013AS", "3.20", ATA_QUIRK_MAX_SEC_1024 }, /* * These devices time out with higher max sects. * https://bugzilla.kernel.org/show_bug.cgi?id=121671 */ - { "LITEON CX1-JB*-HP", NULL, ATA_HORKAGE_MAX_SEC_1024 }, - { "LITEON EP1-*", NULL, ATA_HORKAGE_MAX_SEC_1024 }, + { "LITEON CX1-JB*-HP", NULL, ATA_QUIRK_MAX_SEC_1024 }, + { "LITEON EP1-*", NULL, ATA_QUIRK_MAX_SEC_1024 }, /* Devices we expect to fail diagnostics */ /* Devices where NCQ should be avoided */ /* NCQ is slow */ - { "WDC WD740ADFD-00", NULL, ATA_HORKAGE_NONCQ }, - { "WDC WD740ADFD-00NLR1", NULL, ATA_HORKAGE_NONCQ }, + { "WDC WD740ADFD-00", NULL, ATA_QUIRK_NONCQ }, + { "WDC WD740ADFD-00NLR1", NULL, ATA_QUIRK_NONCQ }, /* http://thread.gmane.org/gmane.linux.ide/14907 */ - { "FUJITSU MHT2060BH", NULL, ATA_HORKAGE_NONCQ }, + { "FUJITSU MHT2060BH", NULL, ATA_QUIRK_NONCQ }, /* NCQ is broken */ - { "Maxtor *", "BANC*", ATA_HORKAGE_NONCQ }, - { "Maxtor 7V300F0", "VA111630", ATA_HORKAGE_NONCQ }, - { "ST380817AS", "3.42", ATA_HORKAGE_NONCQ }, - { "ST3160023AS", "3.42", ATA_HORKAGE_NONCQ }, - { "OCZ CORE_SSD", "02.10104", ATA_HORKAGE_NONCQ }, + { "Maxtor *", "BANC*", ATA_QUIRK_NONCQ }, + { "Maxtor 7V300F0", "VA111630", ATA_QUIRK_NONCQ }, + { "ST380817AS", "3.42", ATA_QUIRK_NONCQ }, + { "ST3160023AS", "3.42", ATA_QUIRK_NONCQ }, + { "OCZ CORE_SSD", "02.10104", ATA_QUIRK_NONCQ }, /* Seagate NCQ + FLUSH CACHE firmware bug */ - { "ST31500341AS", "SD1[5-9]", ATA_HORKAGE_NONCQ | - ATA_HORKAGE_FIRMWARE_WARN }, + { "ST31500341AS", "SD1[5-9]", ATA_QUIRK_NONCQ | + ATA_QUIRK_FIRMWARE_WARN }, - { "ST31000333AS", "SD1[5-9]", ATA_HORKAGE_NONCQ | - ATA_HORKAGE_FIRMWARE_WARN }, + { "ST31000333AS", "SD1[5-9]", ATA_QUIRK_NONCQ | + ATA_QUIRK_FIRMWARE_WARN }, - { "ST3640[36]23AS", "SD1[5-9]", ATA_HORKAGE_NONCQ | - ATA_HORKAGE_FIRMWARE_WARN }, + { "ST3640[36]23AS", "SD1[5-9]", ATA_QUIRK_NONCQ | + ATA_QUIRK_FIRMWARE_WARN }, - { "ST3320[68]13AS", "SD1[5-9]", ATA_HORKAGE_NONCQ | - ATA_HORKAGE_FIRMWARE_WARN }, + { "ST3320[68]13AS", "SD1[5-9]", ATA_QUIRK_NONCQ | + ATA_QUIRK_FIRMWARE_WARN }, /* drives which fail FPDMA_AA activation (some may freeze afterwards) the ST disks also have LPM issues */ - { "ST1000LM024 HN-M101MBB", NULL, ATA_HORKAGE_BROKEN_FPDMA_AA | - ATA_HORKAGE_NOLPM }, - { "VB0250EAVER", "HPG7", ATA_HORKAGE_BROKEN_FPDMA_AA }, + { "ST1000LM024 HN-M101MBB", NULL, ATA_QUIRK_BROKEN_FPDMA_AA | + ATA_QUIRK_NOLPM }, + { "VB0250EAVER", "HPG7", ATA_QUIRK_BROKEN_FPDMA_AA }, /* Blacklist entries taken from Silicon Image 3124/3132 Windows driver .inf file - also several Linux problem reports */ - { "HTS541060G9SA00", "MB3OC60D", ATA_HORKAGE_NONCQ }, - { "HTS541080G9SA00", "MB4OC60D", ATA_HORKAGE_NONCQ }, - { "HTS541010G9SA00", "MBZOC60D", ATA_HORKAGE_NONCQ }, + { "HTS541060G9SA00", "MB3OC60D", ATA_QUIRK_NONCQ }, + { "HTS541080G9SA00", "MB4OC60D", ATA_QUIRK_NONCQ }, + { "HTS541010G9SA00", "MBZOC60D", ATA_QUIRK_NONCQ }, /* https://bugzilla.kernel.org/show_bug.cgi?id=15573 */ - { "C300-CTFDDAC128MAG", "0001", ATA_HORKAGE_NONCQ }, + { "C300-CTFDDAC128MAG", "0001", ATA_QUIRK_NONCQ }, /* Sandisk SD7/8/9s lock up hard on large trims */ - { "SanDisk SD[789]*", NULL, ATA_HORKAGE_MAX_TRIM_128M }, + { "SanDisk SD[789]*", NULL, ATA_QUIRK_MAX_TRIM_128M }, /* devices which puke on READ_NATIVE_MAX */ - { "HDS724040KLSA80", "KFAOA20N", ATA_HORKAGE_BROKEN_HPA }, - { "WDC WD3200JD-00KLB0", "WD-WCAMR1130137", ATA_HORKAGE_BROKEN_HPA }, - { "WDC WD2500JD-00HBB0", "WD-WMAL71490727", ATA_HORKAGE_BROKEN_HPA }, - { "MAXTOR 6L080L4", "A93.0500", ATA_HORKAGE_BROKEN_HPA }, + { "HDS724040KLSA80", "KFAOA20N", ATA_QUIRK_BROKEN_HPA }, + { "WDC WD3200JD-00KLB0", "WD-WCAMR1130137", ATA_QUIRK_BROKEN_HPA }, + { "WDC WD2500JD-00HBB0", "WD-WMAL71490727", ATA_QUIRK_BROKEN_HPA }, + { "MAXTOR 6L080L4", "A93.0500", ATA_QUIRK_BROKEN_HPA }, /* this one allows HPA unlocking but fails IOs on the area */ - { "OCZ-VERTEX", "1.30", ATA_HORKAGE_BROKEN_HPA }, + { "OCZ-VERTEX", "1.30", ATA_QUIRK_BROKEN_HPA }, /* Devices which report 1 sector over size HPA */ - { "ST340823A", NULL, ATA_HORKAGE_HPA_SIZE }, - { "ST320413A", NULL, ATA_HORKAGE_HPA_SIZE }, - { "ST310211A", NULL, ATA_HORKAGE_HPA_SIZE }, + { "ST340823A", NULL, ATA_QUIRK_HPA_SIZE }, + { "ST320413A", NULL, ATA_QUIRK_HPA_SIZE }, + { "ST310211A", NULL, ATA_QUIRK_HPA_SIZE }, /* Devices which get the IVB wrong */ - { "QUANTUM FIREBALLlct10 05", "A03.0900", ATA_HORKAGE_IVB }, - /* Maybe we should just blacklist TSSTcorp... */ - { "TSSTcorp CDDVDW SH-S202[HJN]", "SB0[01]", ATA_HORKAGE_IVB }, + { "QUANTUM FIREBALLlct10 05", "A03.0900", ATA_QUIRK_IVB }, + /* Maybe we should just add all TSSTcorp devices... */ + { "TSSTcorp CDDVDW SH-S202[HJN]", "SB0[01]", ATA_QUIRK_IVB }, /* Devices that do not need bridging limits applied */ - { "MTRON MSP-SATA*", NULL, ATA_HORKAGE_BRIDGE_OK }, - { "BUFFALO HD-QSU2/R5", NULL, ATA_HORKAGE_BRIDGE_OK }, + { "MTRON MSP-SATA*", NULL, ATA_QUIRK_BRIDGE_OK }, + { "BUFFALO HD-QSU2/R5", NULL, ATA_QUIRK_BRIDGE_OK }, /* Devices which aren't very happy with higher link speeds */ - { "WD My Book", NULL, ATA_HORKAGE_1_5_GBPS }, - { "Seagate FreeAgent GoFlex", NULL, ATA_HORKAGE_1_5_GBPS }, + { "WD My Book", NULL, ATA_QUIRK_1_5_GBPS }, + { "Seagate FreeAgent GoFlex", NULL, ATA_QUIRK_1_5_GBPS }, /* * Devices which choke on SETXFER. Applies only if both the * device and controller are SATA. */ - { "PIONEER DVD-RW DVRTD08", NULL, ATA_HORKAGE_NOSETXFER }, - { "PIONEER DVD-RW DVRTD08A", NULL, ATA_HORKAGE_NOSETXFER }, - { "PIONEER DVD-RW DVR-215", NULL, ATA_HORKAGE_NOSETXFER }, - { "PIONEER DVD-RW DVR-212D", NULL, ATA_HORKAGE_NOSETXFER }, - { "PIONEER DVD-RW DVR-216D", NULL, ATA_HORKAGE_NOSETXFER }, + { "PIONEER DVD-RW DVRTD08", NULL, ATA_QUIRK_NOSETXFER }, + { "PIONEER DVD-RW DVRTD08A", NULL, ATA_QUIRK_NOSETXFER }, + { "PIONEER DVD-RW DVR-215", NULL, ATA_QUIRK_NOSETXFER }, + { "PIONEER DVD-RW DVR-212D", NULL, ATA_QUIRK_NOSETXFER }, + { "PIONEER DVD-RW DVR-216D", NULL, ATA_QUIRK_NOSETXFER }, /* These specific Pioneer models have LPM issues */ - { "PIONEER BD-RW BDR-207M", NULL, ATA_HORKAGE_NOLPM }, - { "PIONEER BD-RW BDR-205", NULL, ATA_HORKAGE_NOLPM }, + { "PIONEER BD-RW BDR-207M", NULL, ATA_QUIRK_NOLPM }, + { "PIONEER BD-RW BDR-205", NULL, ATA_QUIRK_NOLPM }, /* Crucial devices with broken LPM support */ - { "CT*0BX*00SSD1", NULL, ATA_HORKAGE_NOLPM }, + { "CT*0BX*00SSD1", NULL, ATA_QUIRK_NOLPM }, /* 512GB MX100 with MU01 firmware has both queued TRIM and LPM issues */ - { "Crucial_CT512MX100*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM | - ATA_HORKAGE_NOLPM }, + { "Crucial_CT512MX100*", "MU01", ATA_QUIRK_NO_NCQ_TRIM | + ATA_QUIRK_ZERO_AFTER_TRIM | + ATA_QUIRK_NOLPM }, /* 512GB MX100 with newer firmware has only LPM issues */ - { "Crucial_CT512MX100*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM | - ATA_HORKAGE_NOLPM }, + { "Crucial_CT512MX100*", NULL, ATA_QUIRK_ZERO_AFTER_TRIM | + ATA_QUIRK_NOLPM }, /* 480GB+ M500 SSDs have both queued TRIM and LPM issues */ - { "Crucial_CT480M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM | - ATA_HORKAGE_NOLPM }, - { "Crucial_CT960M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM | - ATA_HORKAGE_NOLPM }, + { "Crucial_CT480M500*", NULL, ATA_QUIRK_NO_NCQ_TRIM | + ATA_QUIRK_ZERO_AFTER_TRIM | + ATA_QUIRK_NOLPM }, + { "Crucial_CT960M500*", NULL, ATA_QUIRK_NO_NCQ_TRIM | + ATA_QUIRK_ZERO_AFTER_TRIM | + ATA_QUIRK_NOLPM }, /* AMD Radeon devices with broken LPM support */ - { "R3SL240G", NULL, ATA_HORKAGE_NOLPM }, + { "R3SL240G", NULL, ATA_QUIRK_NOLPM }, /* Apacer models with LPM issues */ - { "Apacer AS340*", NULL, ATA_HORKAGE_NOLPM }, + { "Apacer AS340*", NULL, ATA_QUIRK_NOLPM }, /* These specific Samsung models/firmware-revs do not handle LPM well */ - { "SAMSUNG MZMPC128HBFU-000MV", "CXM14M1Q", ATA_HORKAGE_NOLPM }, - { "SAMSUNG SSD PM830 mSATA *", "CXM13D1Q", ATA_HORKAGE_NOLPM }, - { "SAMSUNG MZ7TD256HAFV-000L9", NULL, ATA_HORKAGE_NOLPM }, - { "SAMSUNG MZ7TE512HMHP-000L1", "EXT06L0Q", ATA_HORKAGE_NOLPM }, + { "SAMSUNG MZMPC128HBFU-000MV", "CXM14M1Q", ATA_QUIRK_NOLPM }, + { "SAMSUNG SSD PM830 mSATA *", "CXM13D1Q", ATA_QUIRK_NOLPM }, + { "SAMSUNG MZ7TD256HAFV-000L9", NULL, ATA_QUIRK_NOLPM }, + { "SAMSUNG MZ7TE512HMHP-000L1", "EXT06L0Q", ATA_QUIRK_NOLPM }, /* devices that don't properly handle queued TRIM commands */ - { "Micron_M500IT_*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM }, - { "Micron_M500_*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM }, - { "Micron_M5[15]0_*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM }, - { "Micron_1100_*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM, }, - { "Crucial_CT*M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM }, - { "Crucial_CT*M550*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM }, - { "Crucial_CT*MX100*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM }, - { "Samsung SSD 840 EVO*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_NO_DMA_LOG | - ATA_HORKAGE_ZERO_AFTER_TRIM }, - { "Samsung SSD 840*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM }, - { "Samsung SSD 850*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM }, - { "Samsung SSD 860*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM | - ATA_HORKAGE_NO_NCQ_ON_ATI }, - { "Samsung SSD 870*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM | - ATA_HORKAGE_NO_NCQ_ON_ATI }, - { "SAMSUNG*MZ7LH*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM | - ATA_HORKAGE_NO_NCQ_ON_ATI, }, - { "FCCT*M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM }, + { "Micron_M500IT_*", "MU01", ATA_QUIRK_NO_NCQ_TRIM | + ATA_QUIRK_ZERO_AFTER_TRIM }, + { "Micron_M500_*", NULL, ATA_QUIRK_NO_NCQ_TRIM | + ATA_QUIRK_ZERO_AFTER_TRIM }, + { "Micron_M5[15]0_*", "MU01", ATA_QUIRK_NO_NCQ_TRIM | + ATA_QUIRK_ZERO_AFTER_TRIM }, + { "Micron_1100_*", NULL, ATA_QUIRK_NO_NCQ_TRIM | + ATA_QUIRK_ZERO_AFTER_TRIM, }, + { "Crucial_CT*M500*", NULL, ATA_QUIRK_NO_NCQ_TRIM | + ATA_QUIRK_ZERO_AFTER_TRIM }, + { "Crucial_CT*M550*", "MU01", ATA_QUIRK_NO_NCQ_TRIM | + ATA_QUIRK_ZERO_AFTER_TRIM }, + { "Crucial_CT*MX100*", "MU01", ATA_QUIRK_NO_NCQ_TRIM | + ATA_QUIRK_ZERO_AFTER_TRIM }, + { "Samsung SSD 840 EVO*", NULL, ATA_QUIRK_NO_NCQ_TRIM | + ATA_QUIRK_NO_DMA_LOG | + ATA_QUIRK_ZERO_AFTER_TRIM }, + { "Samsung SSD 840*", NULL, ATA_QUIRK_NO_NCQ_TRIM | + ATA_QUIRK_ZERO_AFTER_TRIM }, + { "Samsung SSD 850*", NULL, ATA_QUIRK_NO_NCQ_TRIM | + ATA_QUIRK_ZERO_AFTER_TRIM }, + { "Samsung SSD 860*", NULL, ATA_QUIRK_NO_NCQ_TRIM | + ATA_QUIRK_ZERO_AFTER_TRIM | + ATA_QUIRK_NO_NCQ_ON_ATI }, + { "Samsung SSD 870*", NULL, ATA_QUIRK_NO_NCQ_TRIM | + ATA_QUIRK_ZERO_AFTER_TRIM | + ATA_QUIRK_NO_NCQ_ON_ATI }, + { "SAMSUNG*MZ7LH*", NULL, ATA_QUIRK_NO_NCQ_TRIM | + ATA_QUIRK_ZERO_AFTER_TRIM | + ATA_QUIRK_NO_NCQ_ON_ATI, }, + { "FCCT*M500*", NULL, ATA_QUIRK_NO_NCQ_TRIM | + ATA_QUIRK_ZERO_AFTER_TRIM }, /* devices that don't properly handle TRIM commands */ - { "SuperSSpeed S238*", NULL, ATA_HORKAGE_NOTRIM }, - { "M88V29*", NULL, ATA_HORKAGE_NOTRIM }, + { "SuperSSpeed S238*", NULL, ATA_QUIRK_NOTRIM }, + { "M88V29*", NULL, ATA_QUIRK_NOTRIM }, /* * As defined, the DRAT (Deterministic Read After Trim) and RZAT @@ -4223,14 +4224,14 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { */ { "INTEL*SSDSC2MH*", NULL, 0 }, - { "Micron*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM }, - { "Crucial*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM }, - { "INTEL*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM }, - { "SSD*INTEL*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM }, - { "Samsung*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM }, - { "SAMSUNG*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM }, - { "SAMSUNG*MZ7KM*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM }, - { "ST[1248][0248]0[FH]*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM }, + { "Micron*", NULL, ATA_QUIRK_ZERO_AFTER_TRIM }, + { "Crucial*", NULL, ATA_QUIRK_ZERO_AFTER_TRIM }, + { "INTEL*SSD*", NULL, ATA_QUIRK_ZERO_AFTER_TRIM }, + { "SSD*INTEL*", NULL, ATA_QUIRK_ZERO_AFTER_TRIM }, + { "Samsung*SSD*", NULL, ATA_QUIRK_ZERO_AFTER_TRIM }, + { "SAMSUNG*SSD*", NULL, ATA_QUIRK_ZERO_AFTER_TRIM }, + { "SAMSUNG*MZ7KM*", NULL, ATA_QUIRK_ZERO_AFTER_TRIM }, + { "ST[1248][0248]0[FH]*", NULL, ATA_QUIRK_ZERO_AFTER_TRIM }, /* * Some WD SATA-I drives spin up and down erratically when the link @@ -4241,36 +4242,36 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { * * https://bugzilla.kernel.org/show_bug.cgi?id=57211 */ - { "WDC WD800JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM }, - { "WDC WD1200JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM }, - { "WDC WD1600JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM }, - { "WDC WD2000JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM }, - { "WDC WD2500JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM }, - { "WDC WD3000JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM }, - { "WDC WD3200JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM }, + { "WDC WD800JD-*", NULL, ATA_QUIRK_WD_BROKEN_LPM }, + { "WDC WD1200JD-*", NULL, ATA_QUIRK_WD_BROKEN_LPM }, + { "WDC WD1600JD-*", NULL, ATA_QUIRK_WD_BROKEN_LPM }, + { "WDC WD2000JD-*", NULL, ATA_QUIRK_WD_BROKEN_LPM }, + { "WDC WD2500JD-*", NULL, ATA_QUIRK_WD_BROKEN_LPM }, + { "WDC WD3000JD-*", NULL, ATA_QUIRK_WD_BROKEN_LPM }, + { "WDC WD3200JD-*", NULL, ATA_QUIRK_WD_BROKEN_LPM }, /* * This sata dom device goes on a walkabout when the ATA_LOG_DIRECTORY * log page is accessed. Ensure we never ask for this log page with * these devices. */ - { "SATADOM-ML 3ME", NULL, ATA_HORKAGE_NO_LOG_DIR }, + { "SATADOM-ML 3ME", NULL, ATA_QUIRK_NO_LOG_DIR }, /* Buggy FUA */ - { "Maxtor", "BANC1G10", ATA_HORKAGE_NO_FUA }, - { "WDC*WD2500J*", NULL, ATA_HORKAGE_NO_FUA }, - { "OCZ-VERTEX*", NULL, ATA_HORKAGE_NO_FUA }, - { "INTEL*SSDSC2CT*", NULL, ATA_HORKAGE_NO_FUA }, + { "Maxtor", "BANC1G10", ATA_QUIRK_NO_FUA }, + { "WDC*WD2500J*", NULL, ATA_QUIRK_NO_FUA }, + { "OCZ-VERTEX*", NULL, ATA_QUIRK_NO_FUA }, + { "INTEL*SSDSC2CT*", NULL, ATA_QUIRK_NO_FUA }, /* End Marker */ { } }; -static unsigned long ata_dev_blacklisted(const struct ata_device *dev) +static unsigned int ata_dev_quirks(const struct ata_device *dev) { unsigned char model_num[ATA_ID_PROD_LEN + 1]; unsigned char model_rev[ATA_ID_FW_REV_LEN + 1]; - const struct ata_blacklist_entry *ad = ata_device_blacklist; + const struct ata_dev_quirks_entry *ad = __ata_dev_quirks; ata_id_c_string(dev->id, model_num, ATA_ID_PROD, sizeof(model_num)); ata_id_c_string(dev->id, model_rev, ATA_ID_FW_REV, sizeof(model_rev)); @@ -4278,9 +4279,9 @@ static unsigned long ata_dev_blacklisted(const struct ata_device *dev) while (ad->model_num) { if (glob_match(ad->model_num, model_num)) { if (ad->model_rev == NULL) - return ad->horkage; + return ad->quirks; if (glob_match(ad->model_rev, model_rev)) - return ad->horkage; + return ad->quirks; } ad++; } @@ -4297,7 +4298,7 @@ static bool ata_dev_nodma(const struct ata_device *dev) if ((dev->link->ap->flags & ATA_FLAG_PIO_POLLING) && (dev->flags & ATA_DFLAG_CDB_INTR)) return true; - return dev->horkage & ATA_HORKAGE_NODMA; + return dev->quirks & ATA_QUIRK_NODMA; } /** @@ -4310,7 +4311,7 @@ static bool ata_dev_nodma(const struct ata_device *dev) static int ata_is_40wire(struct ata_device *dev) { - if (dev->horkage & ATA_HORKAGE_IVB) + if (dev->quirks & ATA_QUIRK_IVB) return ata_drive_40wire_relaxed(dev->id); return ata_drive_40wire(dev->id); } @@ -4372,8 +4373,7 @@ static int cable_is_40wire(struct ata_port *ap) * * Compute supported xfermask of @dev and store it in * dev->*_mask. This function is responsible for applying all - * known limits including host controller limits, device - * blacklist, etc... + * known limits including host controller limits, device quirks, etc... * * LOCKING: * None. @@ -4589,7 +4589,7 @@ int atapi_check_dma(struct ata_queued_cmd *qc) /* Don't allow DMA if it isn't multiple of 16 bytes. Quite a * few ATAPI devices choke on such DMA requests. */ - if (!(qc->dev->horkage & ATA_HORKAGE_ATAPI_MOD16_DMA) && + if (!(qc->dev->quirks & ATA_QUIRK_ATAPI_MOD16_DMA) && unlikely(qc->nbytes & 15)) return 1; @@ -5369,7 +5369,7 @@ void ata_dev_init(struct ata_device *dev) */ spin_lock_irqsave(ap->lock, flags); dev->flags &= ~ATA_DFLAG_INIT_MASK; - dev->horkage = 0; + dev->quirks = 0; spin_unlock_irqrestore(ap->lock, flags); memset((void *)dev + ATA_DEVICE_CLEAR_BEGIN, 0, @@ -6298,12 +6298,12 @@ EXPORT_SYMBOL_GPL(ata_platform_remove_one); { "no" #name, .lflags_on = (flags) }, \ { #name, .lflags_off = (flags) } -#define force_horkage_on(name, flag) \ - { #name, .horkage_on = (flag) } +#define force_quirk_on(name, flag) \ + { #name, .quirk_on = (flag) } -#define force_horkage_onoff(name, flag) \ - { "no" #name, .horkage_on = (flag) }, \ - { #name, .horkage_off = (flag) } +#define force_quirk_onoff(name, flag) \ + { "no" #name, .quirk_on = (flag) }, \ + { #name, .quirk_off = (flag) } static const struct ata_force_param force_tbl[] __initconst = { force_cbl(40c, ATA_CBL_PATA40), @@ -6357,32 +6357,32 @@ static const struct ata_force_param force_tbl[] __initconst = { force_lflag_on(rstonce, ATA_LFLAG_RST_ONCE), force_lflag_onoff(dbdelay, ATA_LFLAG_NO_DEBOUNCE_DELAY), - force_horkage_onoff(ncq, ATA_HORKAGE_NONCQ), - force_horkage_onoff(ncqtrim, ATA_HORKAGE_NO_NCQ_TRIM), - force_horkage_onoff(ncqati, ATA_HORKAGE_NO_NCQ_ON_ATI), + force_quirk_onoff(ncq, ATA_QUIRK_NONCQ), + force_quirk_onoff(ncqtrim, ATA_QUIRK_NO_NCQ_TRIM), + force_quirk_onoff(ncqati, ATA_QUIRK_NO_NCQ_ON_ATI), - force_horkage_onoff(trim, ATA_HORKAGE_NOTRIM), - force_horkage_on(trim_zero, ATA_HORKAGE_ZERO_AFTER_TRIM), - force_horkage_on(max_trim_128m, ATA_HORKAGE_MAX_TRIM_128M), + force_quirk_onoff(trim, ATA_QUIRK_NOTRIM), + force_quirk_on(trim_zero, ATA_QUIRK_ZERO_AFTER_TRIM), + force_quirk_on(max_trim_128m, ATA_QUIRK_MAX_TRIM_128M), - force_horkage_onoff(dma, ATA_HORKAGE_NODMA), - force_horkage_on(atapi_dmadir, ATA_HORKAGE_ATAPI_DMADIR), - force_horkage_on(atapi_mod16_dma, ATA_HORKAGE_ATAPI_MOD16_DMA), + force_quirk_onoff(dma, ATA_QUIRK_NODMA), + force_quirk_on(atapi_dmadir, ATA_QUIRK_ATAPI_DMADIR), + force_quirk_on(atapi_mod16_dma, ATA_QUIRK_ATAPI_MOD16_DMA), - force_horkage_onoff(dmalog, ATA_HORKAGE_NO_DMA_LOG), - force_horkage_onoff(iddevlog, ATA_HORKAGE_NO_ID_DEV_LOG), - force_horkage_onoff(logdir, ATA_HORKAGE_NO_LOG_DIR), + force_quirk_onoff(dmalog, ATA_QUIRK_NO_DMA_LOG), + force_quirk_onoff(iddevlog, ATA_QUIRK_NO_ID_DEV_LOG), + force_quirk_onoff(logdir, ATA_QUIRK_NO_LOG_DIR), - force_horkage_on(max_sec_128, ATA_HORKAGE_MAX_SEC_128), - force_horkage_on(max_sec_1024, ATA_HORKAGE_MAX_SEC_1024), - force_horkage_on(max_sec_lba48, ATA_HORKAGE_MAX_SEC_LBA48), + force_quirk_on(max_sec_128, ATA_QUIRK_MAX_SEC_128), + force_quirk_on(max_sec_1024, ATA_QUIRK_MAX_SEC_1024), + force_quirk_on(max_sec_lba48, ATA_QUIRK_MAX_SEC_LBA48), - force_horkage_onoff(lpm, ATA_HORKAGE_NOLPM), - force_horkage_onoff(setxfer, ATA_HORKAGE_NOSETXFER), - force_horkage_on(dump_id, ATA_HORKAGE_DUMP_ID), - force_horkage_onoff(fua, ATA_HORKAGE_NO_FUA), + force_quirk_onoff(lpm, ATA_QUIRK_NOLPM), + force_quirk_onoff(setxfer, ATA_QUIRK_NOSETXFER), + force_quirk_on(dump_id, ATA_QUIRK_DUMP_ID), + force_quirk_onoff(fua, ATA_QUIRK_NO_FUA), - force_horkage_on(disable, ATA_HORKAGE_DISABLE), + force_quirk_on(disable, ATA_QUIRK_DISABLE), }; static int __init ata_parse_force_one(char **cur, diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c index 48660d445602..ecd37649d4d4 100644 --- a/drivers/ata/libata-sata.c +++ b/drivers/ata/libata-sata.c @@ -818,7 +818,7 @@ static ssize_t ata_scsi_lpm_store(struct device *device, ata_for_each_link(link, ap, EDGE) { ata_for_each_dev(dev, &ap->link, ENABLED) { - if (dev->horkage & ATA_HORKAGE_NOLPM) { + if (dev->quirks & ATA_QUIRK_NOLPM) { count = -EOPNOTSUPP; goto out_unlock; } diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index d6f5e25e1ed8..3a442f564b0d 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -2083,7 +2083,7 @@ static unsigned int ata_scsiop_inq_b0(struct ata_scsi_args *args, u8 *rbuf) if (ata_id_has_trim(args->id)) { u64 max_blocks = 65535 * ATA_MAX_TRIM_RNUM; - if (dev->horkage & ATA_HORKAGE_MAX_TRIM_128M) + if (dev->quirks & ATA_QUIRK_MAX_TRIM_128M) max_blocks = 128 << (20 - SECTOR_SHIFT); put_unaligned_be64(max_blocks, &rbuf[36]); @@ -2561,11 +2561,11 @@ static unsigned int ata_scsiop_read_cap(struct ata_scsi_args *args, u8 *rbuf) rbuf[15] = lowest_aligned; if (ata_id_has_trim(args->id) && - !(dev->horkage & ATA_HORKAGE_NOTRIM)) { + !(dev->quirks & ATA_QUIRK_NOTRIM)) { rbuf[14] |= 0x80; /* LBPME */ if (ata_id_has_zero_after_trim(args->id) && - dev->horkage & ATA_HORKAGE_ZERO_AFTER_TRIM) { + dev->quirks & ATA_QUIRK_ZERO_AFTER_TRIM) { ata_dev_info(dev, "Enabling discard_zeroes_data\n"); rbuf[14] |= 0x40; /* LBPRZ */ } @@ -3229,8 +3229,7 @@ static unsigned int ata_scsi_write_same_xlat(struct ata_queued_cmd *qc) } scsi_16_lba_len(cdb, &block, &n_block); - if (!unmap || - (dev->horkage & ATA_HORKAGE_NOTRIM) || + if (!unmap || (dev->quirks & ATA_QUIRK_NOTRIM) || !ata_id_has_trim(dev->id)) { fp = 1; bp = 3; diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index 250f7dae05fd..06868ec5b1fd 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -970,7 +970,7 @@ fsm_start: * We ignore ERR here to workaround and proceed sending * the CDB. */ - if (!(qc->dev->horkage & ATA_HORKAGE_STUCK_ERR)) { + if (!(qc->dev->quirks & ATA_QUIRK_STUCK_ERR)) { ata_ehi_push_desc(ehi, "ST_FIRST: " "DRQ=1 with device error, " "dev_stat 0x%X", status); @@ -1045,8 +1045,8 @@ fsm_start: * IDENTIFY, it's likely a phantom * device. Mark hint. */ - if (qc->dev->horkage & - ATA_HORKAGE_DIAGNOSTIC) + if (qc->dev->quirks & + ATA_QUIRK_DIAGNOSTIC) qc->err_mask |= AC_ERR_NODEV_HINT; } else { @@ -1762,7 +1762,7 @@ unsigned int ata_sff_dev_classify(struct ata_device *dev, int present, /* see if device passed diags: continue and warn later */ if (err == 0) /* diagnostic fail : do nothing _YET_ */ - dev->horkage |= ATA_HORKAGE_DIAGNOSTIC; + dev->quirks |= ATA_QUIRK_DIAGNOSTIC; else if (err == 1) /* do nothing */ ; else if ((dev->devno == 0) && (err == 0x81)) @@ -1781,7 +1781,7 @@ unsigned int ata_sff_dev_classify(struct ata_device *dev, int present, * device signature is invalid with diagnostic * failure. */ - if (present && (dev->horkage & ATA_HORKAGE_DIAGNOSTIC)) + if (present && (dev->quirks & ATA_QUIRK_DIAGNOSTIC)) class = ATA_DEV_ATA; else class = ATA_DEV_NONE; diff --git a/drivers/ata/libata-transport.c b/drivers/ata/libata-transport.c index 9e24c33388f9..48800cd0e75d 100644 --- a/drivers/ata/libata-transport.c +++ b/drivers/ata/libata-transport.c @@ -617,10 +617,10 @@ show_ata_dev_trim(struct device *dev, if (!ata_id_has_trim(ata_dev->id)) mode = "unsupported"; - else if (ata_dev->horkage & ATA_HORKAGE_NOTRIM) + else if (ata_dev->quirks & ATA_QUIRK_NOTRIM) mode = "forced_unsupported"; - else if (ata_dev->horkage & ATA_HORKAGE_NO_NCQ_TRIM) - mode = "forced_unqueued"; + else if (ata_dev->quirks & ATA_QUIRK_NO_NCQ_TRIM) + mode = "forced_unqueued"; else if (ata_fpdma_dsm_supported(ata_dev)) mode = "queued"; else diff --git a/drivers/ata/pata_it821x.c b/drivers/ata/pata_it821x.c index 2fe3fb6102ce..042f6ad1f7c6 100644 --- a/drivers/ata/pata_it821x.c +++ b/drivers/ata/pata_it821x.c @@ -519,9 +519,9 @@ static void it821x_dev_config(struct ata_device *adev) } /* This is a controller firmware triggered funny, don't report the drive faulty! */ - adev->horkage &= ~ATA_HORKAGE_DIAGNOSTIC; + adev->quirks &= ~ATA_QUIRK_DIAGNOSTIC; /* No HPA in 'smart' mode */ - adev->horkage |= ATA_HORKAGE_BROKEN_HPA; + adev->quirks |= ATA_QUIRK_BROKEN_HPA; } /** diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c index cc77c0248284..354b68ef91bc 100644 --- a/drivers/ata/sata_sil.c +++ b/drivers/ata/sata_sil.c @@ -616,7 +616,7 @@ static void sil_dev_config(struct ata_device *dev) unsigned char model_num[ATA_ID_PROD_LEN + 1]; /* This controller doesn't support trim */ - dev->horkage |= ATA_HORKAGE_NOTRIM; + dev->quirks |= ATA_QUIRK_NOTRIM; ata_id_c_string(dev->id, model_num, ATA_ID_PROD, sizeof(model_num)); diff --git a/include/linux/libata.h b/include/linux/libata.h index 17394098bee9..05dd7038ab30 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -362,40 +362,41 @@ enum { */ ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 8, - /* Horkage types. May be set by libata or controller on drives - (some horkage may be drive/controller pair dependent */ - - ATA_HORKAGE_DIAGNOSTIC = (1 << 0), /* Failed boot diag */ - ATA_HORKAGE_NODMA = (1 << 1), /* DMA problems */ - ATA_HORKAGE_NONCQ = (1 << 2), /* Don't use NCQ */ - ATA_HORKAGE_MAX_SEC_128 = (1 << 3), /* Limit max sects to 128 */ - ATA_HORKAGE_BROKEN_HPA = (1 << 4), /* Broken HPA */ - ATA_HORKAGE_DISABLE = (1 << 5), /* Disable it */ - ATA_HORKAGE_HPA_SIZE = (1 << 6), /* native size off by one */ - ATA_HORKAGE_IVB = (1 << 8), /* cbl det validity bit bugs */ - ATA_HORKAGE_STUCK_ERR = (1 << 9), /* stuck ERR on next PACKET */ - ATA_HORKAGE_BRIDGE_OK = (1 << 10), /* no bridge limits */ - ATA_HORKAGE_ATAPI_MOD16_DMA = (1 << 11), /* use ATAPI DMA for commands - not multiple of 16 bytes */ - ATA_HORKAGE_FIRMWARE_WARN = (1 << 12), /* firmware update warning */ - ATA_HORKAGE_1_5_GBPS = (1 << 13), /* force 1.5 Gbps */ - ATA_HORKAGE_NOSETXFER = (1 << 14), /* skip SETXFER, SATA only */ - ATA_HORKAGE_BROKEN_FPDMA_AA = (1 << 15), /* skip AA */ - ATA_HORKAGE_DUMP_ID = (1 << 16), /* dump IDENTIFY data */ - ATA_HORKAGE_MAX_SEC_LBA48 = (1 << 17), /* Set max sects to 65535 */ - ATA_HORKAGE_ATAPI_DMADIR = (1 << 18), /* device requires dmadir */ - ATA_HORKAGE_NO_NCQ_TRIM = (1 << 19), /* don't use queued TRIM */ - ATA_HORKAGE_NOLPM = (1 << 20), /* don't use LPM */ - ATA_HORKAGE_WD_BROKEN_LPM = (1 << 21), /* some WDs have broken LPM */ - ATA_HORKAGE_ZERO_AFTER_TRIM = (1 << 22),/* guarantees zero after trim */ - ATA_HORKAGE_NO_DMA_LOG = (1 << 23), /* don't use DMA for log read */ - ATA_HORKAGE_NOTRIM = (1 << 24), /* don't use TRIM */ - ATA_HORKAGE_MAX_SEC_1024 = (1 << 25), /* Limit max sects to 1024 */ - ATA_HORKAGE_MAX_TRIM_128M = (1 << 26), /* Limit max trim size to 128M */ - ATA_HORKAGE_NO_NCQ_ON_ATI = (1 << 27), /* Disable NCQ on ATI chipset */ - ATA_HORKAGE_NO_ID_DEV_LOG = (1 << 28), /* Identify device log missing */ - ATA_HORKAGE_NO_LOG_DIR = (1 << 29), /* Do not read log directory */ - ATA_HORKAGE_NO_FUA = (1 << 30), /* Do not use FUA */ + /* + * Quirk flags: may be set by libata or controller drivers on drives. + * Some quirks may be drive/controller pair dependent. + */ + ATA_QUIRK_DIAGNOSTIC = (1 << 0), /* Failed boot diag */ + ATA_QUIRK_NODMA = (1 << 1), /* DMA problems */ + ATA_QUIRK_NONCQ = (1 << 2), /* Do not use NCQ */ + ATA_QUIRK_MAX_SEC_128 = (1 << 3), /* Limit max sects to 128 */ + ATA_QUIRK_BROKEN_HPA = (1 << 4), /* Broken HPA */ + ATA_QUIRK_DISABLE = (1 << 5), /* Disable it */ + ATA_QUIRK_HPA_SIZE = (1 << 6), /* Native size off by one */ + ATA_QUIRK_IVB = (1 << 8), /* CBL det validity bit bugs */ + ATA_QUIRK_STUCK_ERR = (1 << 9), /* Stuck ERR on next PACKET */ + ATA_QUIRK_BRIDGE_OK = (1 << 10), /* No bridge limits */ + ATA_QUIRK_ATAPI_MOD16_DMA = (1 << 11), /* Use ATAPI DMA for commands */ + /* not multiple of 16 bytes */ + ATA_QUIRK_FIRMWARE_WARN = (1 << 12), /* Firmware update warning */ + ATA_QUIRK_1_5_GBPS = (1 << 13), /* Force 1.5 Gbps */ + ATA_QUIRK_NOSETXFER = (1 << 14), /* Skip SETXFER, SATA only */ + ATA_QUIRK_BROKEN_FPDMA_AA = (1 << 15), /* Skip AA */ + ATA_QUIRK_DUMP_ID = (1 << 16), /* Dump IDENTIFY data */ + ATA_QUIRK_MAX_SEC_LBA48 = (1 << 17), /* Set max sects to 65535 */ + ATA_QUIRK_ATAPI_DMADIR = (1 << 18), /* Device requires dmadir */ + ATA_QUIRK_NO_NCQ_TRIM = (1 << 19), /* Do not use queued TRIM */ + ATA_QUIRK_NOLPM = (1 << 20), /* Do not use LPM */ + ATA_QUIRK_WD_BROKEN_LPM = (1 << 21), /* Some WDs have broken LPM */ + ATA_QUIRK_ZERO_AFTER_TRIM = (1 << 22), /* Guarantees zero after trim */ + ATA_QUIRK_NO_DMA_LOG = (1 << 23), /* Do not use DMA for log read */ + ATA_QUIRK_NOTRIM = (1 << 24), /* Do not use TRIM */ + ATA_QUIRK_MAX_SEC_1024 = (1 << 25), /* Limit max sects to 1024 */ + ATA_QUIRK_MAX_TRIM_128M = (1 << 26), /* Limit max trim size to 128M */ + ATA_QUIRK_NO_NCQ_ON_ATI = (1 << 27), /* Disable NCQ on ATI chipset */ + ATA_QUIRK_NO_ID_DEV_LOG = (1 << 28), /* Identify device log missing */ + ATA_QUIRK_NO_LOG_DIR = (1 << 29), /* Do not read log directory */ + ATA_QUIRK_NO_FUA = (1 << 30), /* Do not use FUA */ /* DMA mask for user DMA control: User visible values; DO NOT renumber */ @@ -663,7 +664,7 @@ struct ata_cpr_log { struct ata_device { struct ata_link *link; unsigned int devno; /* 0 or 1 */ - unsigned int horkage; /* List of broken features */ + unsigned int quirks; /* List of broken features */ unsigned long flags; /* ATA_DFLAG_xxx */ struct scsi_device *sdev; /* attached SCSI device */ void *private_data; -- cgit v1.2.3 From 58157d607aecb4e05ab793408038b014c84e466f Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 18 Jul 2024 16:54:03 +0900 Subject: ata: libata: Print quirks applied to devices Introduce the function ata_dev_print_quirks() to print the quirk flags that will be applied to a scanned device. This new function is called from ata_dev_quirks() when a match on a device model or device model and revision is found for a device in the __ata_dev_quirks array. To implement this function, the ATA_QUIRK_ flags are redefined using the new enum ata_quirk which defines the bit shift for each quirk flag. The array of strings ata_quirk_names is used to define the name of each flag, which are printed by ata_dev_print_quirks(). Example output for a device listed in the __ata_dev_quirks array and which has the ATA_QUIRK_DISABLE flag applied: [10193.461270] ata1: SATA link up 6.0 Gbps (SStatus 133 SControl 300) [10193.469190] ata1.00: Model 'ASMT109x- Config', rev '2143 5', applying quirks: disable [10193.469195] ata1.00: unsupported device, disabling [10193.481564] ata1.00: disable device enum ata_quirk also defines the __ATA_QUIRK_MAX value as one plus the last quirk flag defined. This value is used in ata_dev_quirks() to add a build time check that all quirk flags fit within the unsigned int (32-bits) quirks field of struct ata_device. Signed-off-by: Damien Le Moal Reviewed-by: Igor Pylypiv Reviewed-by: Niklas Cassel --- drivers/ata/libata-core.c | 76 ++++++++++++++++++++++++++++++--- include/linux/libata.h | 106 +++++++++++++++++++++++++++++++--------------- 2 files changed, 143 insertions(+), 39 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 19b041bd7588..fc9fcfda42b8 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -3988,6 +3988,69 @@ int ata_dev_revalidate(struct ata_device *dev, unsigned int new_class, return rc; } +static const char * const ata_quirk_names[] = { + [__ATA_QUIRK_DIAGNOSTIC] = "diagnostic", + [__ATA_QUIRK_NODMA] = "nodma", + [__ATA_QUIRK_NONCQ] = "noncq", + [__ATA_QUIRK_MAX_SEC_128] = "maxsec128", + [__ATA_QUIRK_BROKEN_HPA] = "brokenhpa", + [__ATA_QUIRK_DISABLE] = "disable", + [__ATA_QUIRK_HPA_SIZE] = "hpasize", + [__ATA_QUIRK_IVB] = "ivb", + [__ATA_QUIRK_STUCK_ERR] = "stuckerr", + [__ATA_QUIRK_BRIDGE_OK] = "bridgeok", + [__ATA_QUIRK_ATAPI_MOD16_DMA] = "atapimod16dma", + [__ATA_QUIRK_FIRMWARE_WARN] = "firmwarewarn", + [__ATA_QUIRK_1_5_GBPS] = "1.5gbps", + [__ATA_QUIRK_NOSETXFER] = "nosetxfer", + [__ATA_QUIRK_BROKEN_FPDMA_AA] = "brokenfpdmaaa", + [__ATA_QUIRK_DUMP_ID] = "dumpid", + [__ATA_QUIRK_MAX_SEC_LBA48] = "maxseclba48", + [__ATA_QUIRK_ATAPI_DMADIR] = "atapidmadir", + [__ATA_QUIRK_NO_NCQ_TRIM] = "noncqtrim", + [__ATA_QUIRK_NOLPM] = "nolpm", + [__ATA_QUIRK_WD_BROKEN_LPM] = "wdbrokenlpm", + [__ATA_QUIRK_ZERO_AFTER_TRIM] = "zeroaftertrim", + [__ATA_QUIRK_NO_DMA_LOG] = "nodmalog", + [__ATA_QUIRK_NOTRIM] = "notrim", + [__ATA_QUIRK_MAX_SEC_1024] = "maxsec1024", + [__ATA_QUIRK_MAX_TRIM_128M] = "maxtrim128m", + [__ATA_QUIRK_NO_NCQ_ON_ATI] = "noncqonati", + [__ATA_QUIRK_NO_ID_DEV_LOG] = "noiddevlog", + [__ATA_QUIRK_NO_LOG_DIR] = "nologdir", + [__ATA_QUIRK_NO_FUA] = "nofua", +}; + +static void ata_dev_print_quirks(const struct ata_device *dev, + const char *model, const char *rev, + unsigned int quirks) +{ + int n = 0, i; + size_t sz; + char *str; + + if (!quirks) + return; + + sz = 64 + ARRAY_SIZE(ata_quirk_names) * 16; + str = kmalloc(sz, GFP_KERNEL); + if (!str) + return; + + n = snprintf(str, sz, "Model '%s', rev '%s', applying quirks:", + model, rev); + + for (i = 0; i < ARRAY_SIZE(ata_quirk_names); i++) { + if (quirks & (1U << i)) + n += snprintf(str + n, sz - n, + " %s", ata_quirk_names[i]); + } + + ata_dev_warn(dev, "%s\n", str); + + kfree(str); +} + struct ata_dev_quirks_entry { const char *model_num; const char *model_rev; @@ -4273,15 +4336,18 @@ static unsigned int ata_dev_quirks(const struct ata_device *dev) unsigned char model_rev[ATA_ID_FW_REV_LEN + 1]; const struct ata_dev_quirks_entry *ad = __ata_dev_quirks; + /* dev->quirks is an unsigned int. */ + BUILD_BUG_ON(__ATA_QUIRK_MAX > 32); + ata_id_c_string(dev->id, model_num, ATA_ID_PROD, sizeof(model_num)); ata_id_c_string(dev->id, model_rev, ATA_ID_FW_REV, sizeof(model_rev)); while (ad->model_num) { - if (glob_match(ad->model_num, model_num)) { - if (ad->model_rev == NULL) - return ad->quirks; - if (glob_match(ad->model_rev, model_rev)) - return ad->quirks; + if (glob_match(ad->model_num, model_num) && + (!ad->model_rev || glob_match(ad->model_rev, model_rev))) { + ata_dev_print_quirks(dev, model_num, model_rev, + ad->quirks); + return ad->quirks; } ad++; } diff --git a/include/linux/libata.h b/include/linux/libata.h index 05dd7038ab30..d598ef690e50 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -55,6 +55,46 @@ /* defines only for the constants which don't work well as enums */ #define ATA_TAG_POISON 0xfafbfcfdU +/* + * Quirk flags bits. + * ata_device->quirks is an unsigned int, so __ATA_QUIRK_MAX must not exceed 32. + */ +enum ata_quirks { + __ATA_QUIRK_DIAGNOSTIC, /* Failed boot diag */ + __ATA_QUIRK_NODMA, /* DMA problems */ + __ATA_QUIRK_NONCQ, /* Don't use NCQ */ + __ATA_QUIRK_MAX_SEC_128, /* Limit max sects to 128 */ + __ATA_QUIRK_BROKEN_HPA, /* Broken HPA */ + __ATA_QUIRK_DISABLE, /* Disable it */ + __ATA_QUIRK_HPA_SIZE, /* Native size off by one */ + __ATA_QUIRK_IVB, /* cbl det validity bit bugs */ + __ATA_QUIRK_STUCK_ERR, /* Stuck ERR on next PACKET */ + __ATA_QUIRK_BRIDGE_OK, /* No bridge limits */ + __ATA_QUIRK_ATAPI_MOD16_DMA, /* Use ATAPI DMA for commands that */ + /* are not a multiple of 16 bytes */ + __ATA_QUIRK_FIRMWARE_WARN, /* Firmware update warning */ + __ATA_QUIRK_1_5_GBPS, /* Force 1.5 Gbps */ + __ATA_QUIRK_NOSETXFER, /* Skip SETXFER, SATA only */ + __ATA_QUIRK_BROKEN_FPDMA_AA, /* Skip AA */ + __ATA_QUIRK_DUMP_ID, /* Dump IDENTIFY data */ + __ATA_QUIRK_MAX_SEC_LBA48, /* Set max sects to 65535 */ + __ATA_QUIRK_ATAPI_DMADIR, /* Device requires dmadir */ + __ATA_QUIRK_NO_NCQ_TRIM, /* Do not use queued TRIM */ + __ATA_QUIRK_NOLPM, /* Do not use LPM */ + __ATA_QUIRK_WD_BROKEN_LPM, /* Some WDs have broken LPM */ + __ATA_QUIRK_ZERO_AFTER_TRIM, /* Guarantees zero after trim */ + __ATA_QUIRK_NO_DMA_LOG, /* Do not use DMA for log read */ + __ATA_QUIRK_NOTRIM, /* Do not use TRIM */ + __ATA_QUIRK_MAX_SEC_1024, /* Limit max sects to 1024 */ + __ATA_QUIRK_MAX_TRIM_128M, /* Limit max trim size to 128M */ + __ATA_QUIRK_NO_NCQ_ON_ATI, /* Disable NCQ on ATI chipset */ + __ATA_QUIRK_NO_ID_DEV_LOG, /* Identify device log missing */ + __ATA_QUIRK_NO_LOG_DIR, /* Do not read log directory */ + __ATA_QUIRK_NO_FUA, /* Do not use FUA */ + + __ATA_QUIRK_MAX, +}; + enum { /* various global constants */ LIBATA_MAX_PRD = ATA_MAX_PRD / 2, @@ -366,40 +406,38 @@ enum { * Quirk flags: may be set by libata or controller drivers on drives. * Some quirks may be drive/controller pair dependent. */ - ATA_QUIRK_DIAGNOSTIC = (1 << 0), /* Failed boot diag */ - ATA_QUIRK_NODMA = (1 << 1), /* DMA problems */ - ATA_QUIRK_NONCQ = (1 << 2), /* Do not use NCQ */ - ATA_QUIRK_MAX_SEC_128 = (1 << 3), /* Limit max sects to 128 */ - ATA_QUIRK_BROKEN_HPA = (1 << 4), /* Broken HPA */ - ATA_QUIRK_DISABLE = (1 << 5), /* Disable it */ - ATA_QUIRK_HPA_SIZE = (1 << 6), /* Native size off by one */ - ATA_QUIRK_IVB = (1 << 8), /* CBL det validity bit bugs */ - ATA_QUIRK_STUCK_ERR = (1 << 9), /* Stuck ERR on next PACKET */ - ATA_QUIRK_BRIDGE_OK = (1 << 10), /* No bridge limits */ - ATA_QUIRK_ATAPI_MOD16_DMA = (1 << 11), /* Use ATAPI DMA for commands */ - /* not multiple of 16 bytes */ - ATA_QUIRK_FIRMWARE_WARN = (1 << 12), /* Firmware update warning */ - ATA_QUIRK_1_5_GBPS = (1 << 13), /* Force 1.5 Gbps */ - ATA_QUIRK_NOSETXFER = (1 << 14), /* Skip SETXFER, SATA only */ - ATA_QUIRK_BROKEN_FPDMA_AA = (1 << 15), /* Skip AA */ - ATA_QUIRK_DUMP_ID = (1 << 16), /* Dump IDENTIFY data */ - ATA_QUIRK_MAX_SEC_LBA48 = (1 << 17), /* Set max sects to 65535 */ - ATA_QUIRK_ATAPI_DMADIR = (1 << 18), /* Device requires dmadir */ - ATA_QUIRK_NO_NCQ_TRIM = (1 << 19), /* Do not use queued TRIM */ - ATA_QUIRK_NOLPM = (1 << 20), /* Do not use LPM */ - ATA_QUIRK_WD_BROKEN_LPM = (1 << 21), /* Some WDs have broken LPM */ - ATA_QUIRK_ZERO_AFTER_TRIM = (1 << 22), /* Guarantees zero after trim */ - ATA_QUIRK_NO_DMA_LOG = (1 << 23), /* Do not use DMA for log read */ - ATA_QUIRK_NOTRIM = (1 << 24), /* Do not use TRIM */ - ATA_QUIRK_MAX_SEC_1024 = (1 << 25), /* Limit max sects to 1024 */ - ATA_QUIRK_MAX_TRIM_128M = (1 << 26), /* Limit max trim size to 128M */ - ATA_QUIRK_NO_NCQ_ON_ATI = (1 << 27), /* Disable NCQ on ATI chipset */ - ATA_QUIRK_NO_ID_DEV_LOG = (1 << 28), /* Identify device log missing */ - ATA_QUIRK_NO_LOG_DIR = (1 << 29), /* Do not read log directory */ - ATA_QUIRK_NO_FUA = (1 << 30), /* Do not use FUA */ - - /* DMA mask for user DMA control: User visible values; DO NOT - renumber */ + ATA_QUIRK_DIAGNOSTIC = (1U << __ATA_QUIRK_DIAGNOSTIC), + ATA_QUIRK_NODMA = (1U << __ATA_QUIRK_NODMA), + ATA_QUIRK_NONCQ = (1U << __ATA_QUIRK_NONCQ), + ATA_QUIRK_MAX_SEC_128 = (1U << __ATA_QUIRK_MAX_SEC_128), + ATA_QUIRK_BROKEN_HPA = (1U << __ATA_QUIRK_BROKEN_HPA), + ATA_QUIRK_DISABLE = (1U << __ATA_QUIRK_DISABLE), + ATA_QUIRK_HPA_SIZE = (1U << __ATA_QUIRK_HPA_SIZE), + ATA_QUIRK_IVB = (1U << __ATA_QUIRK_IVB), + ATA_QUIRK_STUCK_ERR = (1U << __ATA_QUIRK_STUCK_ERR), + ATA_QUIRK_BRIDGE_OK = (1U << __ATA_QUIRK_BRIDGE_OK), + ATA_QUIRK_ATAPI_MOD16_DMA = (1U << __ATA_QUIRK_ATAPI_MOD16_DMA), + ATA_QUIRK_FIRMWARE_WARN = (1U << __ATA_QUIRK_FIRMWARE_WARN), + ATA_QUIRK_1_5_GBPS = (1U << __ATA_QUIRK_1_5_GBPS), + ATA_QUIRK_NOSETXFER = (1U << __ATA_QUIRK_NOSETXFER), + ATA_QUIRK_BROKEN_FPDMA_AA = (1U << __ATA_QUIRK_BROKEN_FPDMA_AA), + ATA_QUIRK_DUMP_ID = (1U << __ATA_QUIRK_DUMP_ID), + ATA_QUIRK_MAX_SEC_LBA48 = (1U << __ATA_QUIRK_MAX_SEC_LBA48), + ATA_QUIRK_ATAPI_DMADIR = (1U << __ATA_QUIRK_ATAPI_DMADIR), + ATA_QUIRK_NO_NCQ_TRIM = (1U << __ATA_QUIRK_NO_NCQ_TRIM), + ATA_QUIRK_NOLPM = (1U << __ATA_QUIRK_NOLPM), + ATA_QUIRK_WD_BROKEN_LPM = (1U << __ATA_QUIRK_WD_BROKEN_LPM), + ATA_QUIRK_ZERO_AFTER_TRIM = (1U << __ATA_QUIRK_ZERO_AFTER_TRIM), + ATA_QUIRK_NO_DMA_LOG = (1U << __ATA_QUIRK_NO_DMA_LOG), + ATA_QUIRK_NOTRIM = (1U << __ATA_QUIRK_NOTRIM), + ATA_QUIRK_MAX_SEC_1024 = (1U << __ATA_QUIRK_MAX_SEC_1024), + ATA_QUIRK_MAX_TRIM_128M = (1U << __ATA_QUIRK_MAX_TRIM_128M), + ATA_QUIRK_NO_NCQ_ON_ATI = (1U << __ATA_QUIRK_NO_NCQ_ON_ATI), + ATA_QUIRK_NO_ID_DEV_LOG = (1U << __ATA_QUIRK_NO_ID_DEV_LOG), + ATA_QUIRK_NO_LOG_DIR = (1U << __ATA_QUIRK_NO_LOG_DIR), + ATA_QUIRK_NO_FUA = (1U << __ATA_QUIRK_NO_FUA), + + /* User visible DMA mask for DMA control. DO NOT renumber. */ ATA_DMA_MASK_ATA = (1 << 0), /* DMA on ATA Disk */ ATA_DMA_MASK_ATAPI = (1 << 1), /* DMA on ATAPI */ ATA_DMA_MASK_CFA = (1 << 2), /* DMA on CF Card */ -- cgit v1.2.3 From 22f5468731491e53356ba7c028f0fdea20b18e2c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 30 Jul 2024 10:36:47 -0700 Subject: minmax: improve macro expansion and type checking This clarifies the rules for min()/max()/clamp() type checking and makes them a much more efficient macro expansion. In particular, we now look at the type and range of the inputs to see whether they work together, generating a mask of acceptable comparisons, and then just verifying that the inputs have a shared case: - an expression with a signed type can be used for (1) signed comparisons (2) unsigned comparisons if it is statically known to have a non-negative value - an expression with an unsigned type can be used for (3) unsigned comparison (4) signed comparisons if the type is smaller than 'int' and thus the C integer promotion rules will make it signed anyway Here rule (1) and (3) are obvious, and rule (2) is important in order to allow obvious trivial constants to be used together with unsigned values. Rule (4) is not necessarily a good idea, but matches what we used to do, and we have extant cases of this situation in the kernel. Notably with bcachefs having an expression like min(bch2_bucket_sectors_dirty(a), ca->mi.bucket_size) where bch2_bucket_sectors_dirty() returns an 's64', and 'ca->mi.bucket_size' is of type 'u16'. Technically that bcachefs comparison is clearly sensible on a C type level, because the 'u16' will go through the normal C integer promotion, and become 'int', and then we're comparing two signed values and everything looks sane. However, it's not entirely clear that a 'min(s64,u16)' operation makes a lot of conceptual sense, and it's possible that we will remove rule (4). After all, the _reason_ we have these complicated type checks is exactly that the C type promotion rules are not very intuitive. But at least for now the rule is in place for backwards compatibility. Also note that rule (2) existed before, but is hugely relaxed by this commit. It used to be true only for the simplest compile-time non-negative integer constants. The new macro model will allow cases where the compiler can trivially see that an expression is non-negative even if it isn't necessarily a constant. For example, the amdgpu driver does min_t(size_t, sizeof(fru_info->serial), pia[addr] & 0x3F)); because our old 'min()' macro would see that 'pia[addr] & 0x3F' is of type 'int' and clearly not a C constant expression, so doing a 'min()' with a 'size_t' is a signedness violation. Our new 'min()' macro still sees that 'pia[addr] & 0x3F' is of type 'int', but is smart enough to also see that it is clearly non-negative, and thus would allow that case without any complaints. Cc: Arnd Bergmann Cc: David Laight Cc: Lorenzo Stoakes Signed-off-by: Linus Torvalds --- include/linux/compiler.h | 9 ++++++ include/linux/minmax.h | 74 ++++++++++++++++++++++++++++++++++++++---------- 2 files changed, 68 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 2594553bb30b..2df665fa2964 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -296,6 +296,15 @@ static inline void *offset_to_ptr(const int *off) #define is_signed_type(type) (((type)(-1)) < (__force type)1) #define is_unsigned_type(type) (!is_signed_type(type)) +/* + * Useful shorthand for "is this condition known at compile-time?" + * + * Note that the condition may involve non-constant values, + * but the compiler may know enough about the details of the + * values to determine that the condition is statically true. + */ +#define statically_true(x) (__builtin_constant_p(x) && (x)) + /* * This is needed in functions which generate the stack canary, see * arch/x86/kernel/smpboot.c::start_secondary() for an example. diff --git a/include/linux/minmax.h b/include/linux/minmax.h index e3e4353df983..41da6f85a407 100644 --- a/include/linux/minmax.h +++ b/include/linux/minmax.h @@ -26,19 +26,63 @@ #define __typecheck(x, y) \ (!!(sizeof((typeof(x) *)1 == (typeof(y) *)1))) -/* is_signed_type() isn't a constexpr for pointer types */ -#define __is_signed(x) \ - __builtin_choose_expr(__is_constexpr(is_signed_type(typeof(x))), \ - is_signed_type(typeof(x)), 0) +/* + * __sign_use for integer expressions: + * bit #0 set if ok for unsigned comparisons + * bit #1 set if ok for signed comparisons + * + * In particular, statically non-negative signed integer + * expressions are ok for both. + * + * NOTE! Unsigned types smaller than 'int' are implicitly + * converted to 'int' in expressions, and are accepted for + * signed conversions for now. This is debatable. + * + * Note that 'x' is the original expression, and 'ux' is + * the unique variable that contains the value. + * + * We use 'ux' for pure type checking, and 'x' for when + * we need to look at the value (but without evaluating + * it for side effects! Careful to only ever evaluate it + * with sizeof() or __builtin_constant_p() etc). + * + * Pointers end up being checked by the normal C type + * rules at the actual comparison, and these expressions + * only need to be careful to not cause warnings for + * pointer use. + */ +#define __signed_type_use(x,ux) (2+__is_nonneg(x,ux)) +#define __unsigned_type_use(x,ux) (1+2*(sizeof(ux)<4)) +#define __sign_use(x,ux) (is_signed_type(typeof(ux))? \ + __signed_type_use(x,ux):__unsigned_type_use(x,ux)) + +/* + * To avoid warnings about casting pointers to integers + * of different sizes, we need that special sign type. + * + * On 64-bit we can just always use 'long', since any + * integer or pointer type can just be cast to that. + * + * This does not work for 128-bit signed integers since + * the cast would truncate them, but we do not use s128 + * types in the kernel (we do use 'u128', but they will + * be handled by the !is_signed_type() case). + * + * NOTE! The cast is there only to avoid any warnings + * from when values that aren't signed integer types. + */ +#ifdef CONFIG_64BIT + #define __signed_type(ux) long +#else + #define __signed_type(ux) typeof(__builtin_choose_expr(sizeof(ux)>4,1LL,1L)) +#endif +#define __is_nonneg(x,ux) statically_true((__signed_type(ux))(x)>=0) -/* True for a non-negative signed int constant */ -#define __is_noneg_int(x) \ - (__builtin_choose_expr(__is_constexpr(x) && __is_signed(x), x, -1) >= 0) +#define __types_ok(x,y,ux,uy) \ + (__sign_use(x,ux) & __sign_use(y,uy)) -#define __types_ok(x, y, ux, uy) \ - (__is_signed(ux) == __is_signed(uy) || \ - __is_signed((ux) + 0) == __is_signed((uy) + 0) || \ - __is_noneg_int(x) || __is_noneg_int(y)) +#define __types_ok3(x,y,z,ux,uy,uz) \ + (__sign_use(x,ux) & __sign_use(y,uy) & __sign_use(z,uz)) #define __cmp_op_min < #define __cmp_op_max > @@ -53,8 +97,8 @@ #define __careful_cmp_once(op, x, y, ux, uy) ({ \ __auto_type ux = (x); __auto_type uy = (y); \ - static_assert(__types_ok(x, y, ux, uy), \ - #op "(" #x ", " #y ") signedness error, fix types or consider u" #op "() before " #op "_t()"); \ + BUILD_BUG_ON_MSG(!__types_ok(x,y,ux,uy), \ + #op"("#x", "#y") signedness error"); \ __cmp(op, ux, uy); }) #define __careful_cmp(op, x, y) \ @@ -70,8 +114,8 @@ static_assert(__builtin_choose_expr(__is_constexpr((lo) > (hi)), \ (lo) <= (hi), true), \ "clamp() low limit " #lo " greater than high limit " #hi); \ - static_assert(__types_ok(uval, lo, uval, ulo), "clamp() 'lo' signedness error"); \ - static_assert(__types_ok(uval, hi, uval, uhi), "clamp() 'hi' signedness error"); \ + BUILD_BUG_ON_MSG(!__types_ok3(val,lo,hi,uval,ulo,uhi), \ + "clamp("#val", "#lo", "#hi") signedness error"); \ __clamp(uval, ulo, uhi); }) #define __careful_clamp(val, lo, hi) \ -- cgit v1.2.3 From 1cbe8143fd2f588031a5f157d15ae15ce12215e2 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Tue, 30 Jul 2024 13:37:33 +0800 Subject: bpf: kprobe: Remove unused declaring of bpf_kprobe_override After the commit 66665ad2f102 ("tracing/kprobe: bpf: Compare instruction pointer with original one"), "bpf_kprobe_override" is not used anywhere anymore, and we can remove it now. Fixes: 66665ad2f102 ("tracing/kprobe: bpf: Compare instruction pointer with original one") Signed-off-by: Menglong Dong Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20240730053733.885785-1-dongml2@chinatelecom.cn --- include/linux/trace_events.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 9df3e2973626..9435185c10ef 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -880,7 +880,6 @@ do { \ struct perf_event; DECLARE_PER_CPU(struct pt_regs, perf_trace_regs); -DECLARE_PER_CPU(int, bpf_kprobe_override); extern int perf_trace_init(struct perf_event *event); extern void perf_trace_destroy(struct perf_event *event); -- cgit v1.2.3 From c149c4a48b19afbf0c383614e57b452d39b154de Mon Sep 17 00:00:00 2001 From: Xiu Jianfeng Date: Sat, 13 Jul 2024 08:59:16 +0000 Subject: cgroup/cpuset: Remove cpuset_slab_spread_rotor Since the SLAB implementation was removed in v6.8, so the cpuset_slab_spread_rotor is no longer used and can be removed. Signed-off-by: Xiu Jianfeng Reviewed-by: Waiman Long Signed-off-by: Tejun Heo --- include/linux/cpuset.h | 6 ------ include/linux/sched.h | 1 - kernel/cgroup/cpuset.c | 13 ------------- kernel/fork.c | 1 - 4 files changed, 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index de4cf0ee96f7..2a6981eeebf8 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -113,7 +113,6 @@ extern int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk); extern int cpuset_mem_spread_node(void); -extern int cpuset_slab_spread_node(void); static inline int cpuset_do_page_mem_spread(void) { @@ -246,11 +245,6 @@ static inline int cpuset_mem_spread_node(void) return 0; } -static inline int cpuset_slab_spread_node(void) -{ - return 0; -} - static inline int cpuset_do_page_mem_spread(void) { return 0; diff --git a/include/linux/sched.h b/include/linux/sched.h index f8d150343d42..3773c1c8f099 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1243,7 +1243,6 @@ struct task_struct { /* Sequence number to catch updates: */ seqcount_spinlock_t mems_allowed_seq; int cpuset_mem_spread_rotor; - int cpuset_slab_spread_rotor; #endif #ifdef CONFIG_CGROUPS /* Control Group info protected by css_set_lock: */ diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 918268bc03a7..9f9e626dabb0 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -5012,19 +5012,6 @@ int cpuset_mem_spread_node(void) return cpuset_spread_node(¤t->cpuset_mem_spread_rotor); } -/** - * cpuset_slab_spread_node() - On which node to begin search for a slab page - */ -int cpuset_slab_spread_node(void) -{ - if (current->cpuset_slab_spread_rotor == NUMA_NO_NODE) - current->cpuset_slab_spread_rotor = - node_random(¤t->mems_allowed); - - return cpuset_spread_node(¤t->cpuset_slab_spread_rotor); -} -EXPORT_SYMBOL_GPL(cpuset_mem_spread_node); - /** * cpuset_mems_allowed_intersects - Does @tsk1's mems_allowed intersect @tsk2's? * @tsk1: pointer to task_struct of some task. diff --git a/kernel/fork.c b/kernel/fork.c index cc760491f201..6ed634f09621 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2311,7 +2311,6 @@ __latent_entropy struct task_struct *copy_process( #endif #ifdef CONFIG_CPUSETS p->cpuset_mem_spread_rotor = NUMA_NO_NODE; - p->cpuset_slab_spread_rotor = NUMA_NO_NODE; seqcount_spinlock_init(&p->mems_allowed_seq, &p->alloc_lock); #endif #ifdef CONFIG_TRACE_IRQFLAGS -- cgit v1.2.3 From 93c8332c8373fee415bd79f08d5ba4ba7ca5ad15 Mon Sep 17 00:00:00 2001 From: Xavier Date: Thu, 4 Jul 2024 14:24:43 +0800 Subject: Union-Find: add a new module in kernel library This patch implements a union-find data structure in the kernel library, which includes operations for allocating nodes, freeing nodes, finding the root of a node, and merging two nodes. Signed-off-by: Xavier Signed-off-by: Tejun Heo --- Documentation/core-api/union_find.rst | 102 +++++++++++++++++++++ .../translations/zh_CN/core-api/union_find.rst | 87 ++++++++++++++++++ MAINTAINERS | 9 ++ include/linux/union_find.h | 41 +++++++++ lib/Makefile | 2 +- lib/union_find.c | 49 ++++++++++ 6 files changed, 289 insertions(+), 1 deletion(-) create mode 100644 Documentation/core-api/union_find.rst create mode 100644 Documentation/translations/zh_CN/core-api/union_find.rst create mode 100644 include/linux/union_find.h create mode 100644 lib/union_find.c (limited to 'include/linux') diff --git a/Documentation/core-api/union_find.rst b/Documentation/core-api/union_find.rst new file mode 100644 index 000000000000..2bf0290c9184 --- /dev/null +++ b/Documentation/core-api/union_find.rst @@ -0,0 +1,102 @@ +.. SPDX-License-Identifier: GPL-2.0 + +==================== +Union-Find in Linux +==================== + + +:Date: June 21, 2024 +:Author: Xavier + +What is union-find, and what is it used for? +------------------------------------------------ + +Union-find is a data structure used to handle the merging and querying +of disjoint sets. The primary operations supported by union-find are: + + Initialization: Resetting each element as an individual set, with + each set's initial parent node pointing to itself. + Find: Determine which set a particular element belongs to, usually by + returning a “representative element” of that set. This operation + is used to check if two elements are in the same set. + Union: Merge two sets into one. + +As a data structure used to maintain sets (groups), union-find is commonly +utilized to solve problems related to offline queries, dynamic connectivity, +and graph theory. It is also a key component in Kruskal's algorithm for +computing the minimum spanning tree, which is crucial in scenarios like +network routing. Consequently, union-find is widely referenced. Additionally, +union-find has applications in symbolic computation, register allocation, +and more. + +Space Complexity: O(n), where n is the number of nodes. + +Time Complexity: Using path compression can reduce the time complexity of +the find operation, and using union by rank can reduce the time complexity +of the union operation. These optimizations reduce the average time +complexity of each find and union operation to O(α(n)), where α(n) is the +inverse Ackermann function. This can be roughly considered a constant time +complexity for practical purposes. + +This document covers use of the Linux union-find implementation. For more +information on the nature and implementation of union-find, see: + + Wikipedia entry on union-find + https://en.wikipedia.org/wiki/Disjoint-set_data_structure + +Linux implementation of union-find +----------------------------------- + +Linux's union-find implementation resides in the file "lib/union_find.c". +To use it, "#include ". + +The union-find data structure is defined as follows:: + + struct uf_node { + struct uf_node *parent; + unsigned int rank; + }; + +In this structure, parent points to the parent node of the current node. +The rank field represents the height of the current tree. During a union +operation, the tree with the smaller rank is attached under the tree with the +larger rank to maintain balance. + +Initializing union-find +-------------------- + +You can complete the initialization using either static or initialization +interface. Initialize the parent pointer to point to itself and set the rank +to 0. +Example:: + + struct uf_node my_node = UF_INIT_NODE(my_node); +or + uf_node_init(&my_node); + +Find the Root Node of union-find +-------------------------------- + +This operation is mainly used to determine whether two nodes belong to the same +set in the union-find. If they have the same root, they are in the same set. +During the find operation, path compression is performed to improve the +efficiency of subsequent find operations. +Example:: + + int connected; + struct uf_node *root1 = uf_find(&node_1); + struct uf_node *root2 = uf_find(&node_2); + if (root1 == root2) + connected = 1; + else + connected = 0; + +Union Two Sets in union-find +---------------------------- + +To union two sets in the union-find, you first find their respective root nodes +and then link the smaller node to the larger node based on the rank of the root +nodes. +Example:: + + uf_union(&node_1, &node_2); diff --git a/Documentation/translations/zh_CN/core-api/union_find.rst b/Documentation/translations/zh_CN/core-api/union_find.rst new file mode 100644 index 000000000000..a56de57147e9 --- /dev/null +++ b/Documentation/translations/zh_CN/core-api/union_find.rst @@ -0,0 +1,87 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. include:: ../disclaimer-zh_CN.rst + +:Original: Documentation/core-api/union_find.rst + +=========================== +Linux中的并查集（Union-Find） +=========================== + + +:日期: 2024年6月21日 +:作者: Xavier + +何为并查集，它有什么用？ +--------------------- + +并查集是一种数据结构，用于处理一些不交集的合并及查询问题。并查集支持的主要操作： + 初始化：将每个元素初始化为单独的集合，每个集合的初始父节点指向自身 + 查询：查询某个元素属于哪个集合，通常是返回集合中的一个“代表元素”。这个操作是为 + 了判断两个元素是否在同一个集合之中。 + 合并：将两个集合合并为一个。 + +并查集作为一种用于维护集合（组）的数据结构，它通常用于解决一些离线查询、动态连通性和 +图论等相关问题，同时也是用于计算最小生成树的克鲁斯克尔算法中的关键，由于最小生成树在 +网络路由等场景下十分重要，并查集也得到了广泛的引用。此外，并查集在符号计算，寄存器分 +配等方面也有应用。 + +空间复杂度: O(n)，n为节点数。 + +时间复杂度：使用路径压缩可以减少查找操作的时间复杂度，使用按秩合并可以减少合并操作的 +时间复杂度，使得并查集每个查询和合并操作的平均时间复杂度仅为O(α(n))，其中α(n)是反阿 +克曼函数，可以粗略地认为并查集的操作有常数的时间复杂度。 + +本文档涵盖了对Linux并查集实现的使用方法。更多关于并查集的性质和实现的信息，参见： + + 维基百科并查集词条 + https://en.wikipedia.org/wiki/Disjoint-set_data_structure + +并查集的Linux实现 +---------------- + +Linux的并查集实现在文件“lib/union_find.c”中。要使用它，需要 +“#include ”。 + +并查集的数据结构定义如下:: + + struct uf_node { + struct uf_node *parent; + unsigned int rank; + }; +其中parent为当前节点的父节点，rank为当前树的高度，在合并时将rank小的节点接到rank大 +的节点下面以增加平衡性。 + +初始化并查集 +--------- + +可以采用静态或初始化接口完成初始化操作。初始化时，parent 指针指向自身，rank 设置 +为 0。 +示例:: + + struct uf_node my_node = UF_INIT_NODE(my_node); +或 + uf_node_init(&my_node); + +查找并查集的根节点 +---------------- + +主要用于判断两个并查集是否属于一个集合，如果根相同，那么他们就是一个集合。在查找过程中 +会对路径进行压缩，提高后续查找效率。 +示例:: + + int connected; + struct uf_node *root1 = uf_find(&node_1); + struct uf_node *root2 = uf_find(&node_2); + if (root1 == root2) + connected = 1; + else + connected = 0; + +合并两个并查集 +------------- + +对于两个相交的并查集进行合并，会首先查找它们各自的根节点，然后根据根节点秩大小，将小的 +节点连接到大的节点下面。 +示例:: + + uf_union(&node_1, &node_2); diff --git a/MAINTAINERS b/MAINTAINERS index 42decde38320..82e3924816d2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -23458,6 +23458,15 @@ F: drivers/cdrom/cdrom.c F: include/linux/cdrom.h F: include/uapi/linux/cdrom.h +UNION-FIND +M: Xavier +L: linux-kernel@vger.kernel.org +S: Maintained +F: Documentation/core-api/union_find.rst +F: Documentation/translations/zh_CN/core-api/union_find.rst +F: include/linux/union_find.h +F: lib/union_find.c + UNIVERSAL FLASH STORAGE HOST CONTROLLER DRIVER R: Alim Akhtar R: Avri Altman diff --git a/include/linux/union_find.h b/include/linux/union_find.h new file mode 100644 index 000000000000..cfd49263c138 --- /dev/null +++ b/include/linux/union_find.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_UNION_FIND_H +#define __LINUX_UNION_FIND_H +/** + * union_find.h - union-find data structure implementation + * + * This header provides functions and structures to implement the union-find + * data structure. The union-find data structure is used to manage disjoint + * sets and supports efficient union and find operations. + * + * See Documentation/core-api/union_find.rst for documentation and samples. + */ + +struct uf_node { + struct uf_node *parent; + unsigned int rank; +}; + +/* This macro is used for static initialization of a union-find node. */ +#define UF_INIT_NODE(node) {.parent = &node, .rank = 0} + +/** + * uf_node_init - Initialize a union-find node + * @node: pointer to the union-find node to be initialized + * + * This function sets the parent of the node to itself and + * initializes its rank to 0. + */ +static inline void uf_node_init(struct uf_node *node) +{ + node->parent = node; + node->rank = 0; +} + +/* find the root of a node */ +struct uf_node *uf_find(struct uf_node *node); + +/* Merge two intersecting nodes */ +void uf_union(struct uf_node *node1, struct uf_node *node2); + +#endif /* __LINUX_UNION_FIND_H */ diff --git a/lib/Makefile b/lib/Makefile index 322bb127b4dc..a5e3c1d5b6f9 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -34,7 +34,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \ is_single_threaded.o plist.o decompress.o kobject_uevent.o \ earlycpio.o seq_buf.o siphash.o dec_and_lock.o \ nmi_backtrace.o win_minmax.o memcat_p.o \ - buildid.o objpool.o + buildid.o objpool.o union_find.o lib-$(CONFIG_PRINTK) += dump_stack.o lib-$(CONFIG_SMP) += cpumask.o diff --git a/lib/union_find.c b/lib/union_find.c new file mode 100644 index 000000000000..413b0f8adf7a --- /dev/null +++ b/lib/union_find.c @@ -0,0 +1,49 @@ +// SPDX-License-Identifier: GPL-2.0 +#include + +/** + * uf_find - Find the root of a node and perform path compression + * @node: the node to find the root of + * + * This function returns the root of the node by following the parent + * pointers. It also performs path compression, making the tree shallower. + * + * Returns the root node of the set containing node. + */ +struct uf_node *uf_find(struct uf_node *node) +{ + struct uf_node *parent; + + while (node->parent != node) { + parent = node->parent; + node->parent = parent->parent; + node = parent; + } + return node; +} + +/** + * uf_union - Merge two sets, using union by rank + * @node1: the first node + * @node2: the second node + * + * This function merges the sets containing node1 and node2, by comparing + * the ranks to keep the tree balanced. + */ +void uf_union(struct uf_node *node1, struct uf_node *node2) +{ + struct uf_node *root1 = uf_find(node1); + struct uf_node *root2 = uf_find(node2); + + if (root1 == root2) + return; + + if (root1->rank < root2->rank) { + root1->parent = root2; + } else if (root1->rank > root2->rank) { + root2->parent = root1; + } else { + root2->parent = root1; + root1->rank++; + } +} -- cgit v1.2.3 From 89add40066f9ed9abe5f7f886fe5789ff7e0c50e Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Mon, 29 Jul 2024 16:10:12 -0400 Subject: net: drop bad gso csum_start and offset in virtio_net_hdr Tighten csum_start and csum_offset checks in virtio_net_hdr_to_skb for GSO packets. The function already checks that a checksum requested with VIRTIO_NET_HDR_F_NEEDS_CSUM is in skb linear. But for GSO packets this might not hold for segs after segmentation. Syzkaller demonstrated to reach this warning in skb_checksum_help offset = skb_checksum_start_offset(skb); ret = -EINVAL; if (WARN_ON_ONCE(offset >= skb_headlen(skb))) By injecting a TSO packet: WARNING: CPU: 1 PID: 3539 at net/core/dev.c:3284 skb_checksum_help+0x3d0/0x5b0 ip_do_fragment+0x209/0x1b20 net/ipv4/ip_output.c:774 ip_finish_output_gso net/ipv4/ip_output.c:279 [inline] __ip_finish_output+0x2bd/0x4b0 net/ipv4/ip_output.c:301 iptunnel_xmit+0x50c/0x930 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x2296/0x2c70 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x759/0xa60 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4850 [inline] netdev_start_xmit include/linux/netdevice.h:4864 [inline] xmit_one net/core/dev.c:3595 [inline] dev_hard_start_xmit+0x261/0x8c0 net/core/dev.c:3611 __dev_queue_xmit+0x1b97/0x3c90 net/core/dev.c:4261 packet_snd net/packet/af_packet.c:3073 [inline] The geometry of the bad input packet at tcp_gso_segment: [ 52.003050][ T8403] skb len=12202 headroom=244 headlen=12093 tailroom=0 [ 52.003050][ T8403] mac=(168,24) mac_len=24 net=(192,52) trans=244 [ 52.003050][ T8403] shinfo(txflags=0 nr_frags=1 gso(size=1552 type=3 segs=0)) [ 52.003050][ T8403] csum(0x60000c7 start=199 offset=1536 ip_summed=3 complete_sw=0 valid=0 level=0) Mitigate with stricter input validation. csum_offset: for GSO packets, deduce the correct value from gso_type. This is already done for USO. Extend it to TSO. Let UFO be: udp[46]_ufo_fragment ignores these fields and always computes the checksum in software. csum_start: finding the real offset requires parsing to the transport header. Do not add a parser, use existing segmentation parsing. Thanks to SKB_GSO_DODGY, that also catches bad packets that are hw offloaded. Again test both TSO and USO. Do not test UFO for the above reason, and do not test UDP tunnel offload. GSO packet are almost always CHECKSUM_PARTIAL. USO packets may be CHECKSUM_NONE since commit 10154dbded6d6 ("udp: Allow GSO transmit from devices with no checksum offload"), but then still these fields are initialized correctly in udp4_hwcsum/udp6_hwcsum_outgoing. So no need to test for ip_summed == CHECKSUM_PARTIAL first. This revises an existing fix mentioned in the Fixes tag, which broke small packets with GSO offload, as detected by kselftests. Link: https://syzkaller.appspot.com/bug?extid=e1db31216c789f552871 Link: https://lore.kernel.org/netdev/20240723223109.2196886-1-kuba@kernel.org Fixes: e269d79c7d35 ("net: missing check virtio") Cc: stable@vger.kernel.org Signed-off-by: Willem de Bruijn Link: https://patch.msgid.link/20240729201108.1615114-1-willemdebruijn.kernel@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/virtio_net.h | 16 +++++----------- net/ipv4/tcp_offload.c | 3 +++ net/ipv4/udp_offload.c | 4 ++++ 3 files changed, 12 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index d1d7825318c3..6c395a2600e8 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -56,7 +56,6 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, unsigned int thlen = 0; unsigned int p_off = 0; unsigned int ip_proto; - u64 ret, remainder, gso_size; if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { @@ -99,16 +98,6 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, u32 off = __virtio16_to_cpu(little_endian, hdr->csum_offset); u32 needed = start + max_t(u32, thlen, off + sizeof(__sum16)); - if (hdr->gso_size) { - gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size); - ret = div64_u64_rem(skb->len, gso_size, &remainder); - if (!(ret && (hdr->gso_size > needed) && - ((remainder > needed) || (remainder == 0)))) { - return -EINVAL; - } - skb_shinfo(skb)->tx_flags |= SKBFL_SHARED_FRAG; - } - if (!pskb_may_pull(skb, needed)) return -EINVAL; @@ -182,6 +171,11 @@ retry: if (gso_type != SKB_GSO_UDP_L4) return -EINVAL; break; + case SKB_GSO_TCPV4: + case SKB_GSO_TCPV6: + if (skb->csum_offset != offsetof(struct tcphdr, check)) + return -EINVAL; + break; } /* Kernel has a special handling for GSO_BY_FRAGS. */ diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 4b791e74529e..e4ad3311e148 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -140,6 +140,9 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, if (thlen < sizeof(*th)) goto out; + if (unlikely(skb_checksum_start(skb) != skb_transport_header(skb))) + goto out; + if (!pskb_may_pull(skb, thlen)) goto out; diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index aa2e0a28ca61..bc8a9da750fe 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -278,6 +278,10 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, if (gso_skb->len <= sizeof(*uh) + mss) return ERR_PTR(-EINVAL); + if (unlikely(skb_checksum_start(gso_skb) != + skb_transport_header(gso_skb))) + return ERR_PTR(-EINVAL); + if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) { /* Packet is from an untrusted source, reset gso_segs. */ skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh), -- cgit v1.2.3 From 6dfbafd8a1d51a52a623d912a2219e9982020854 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 12 Jul 2024 16:08:00 +0200 Subject: soundwire: bus: drop unused driver name field The soundwire driver name field is not currently used by any driver (and even appears to never have been used) so drop it. Signed-off-by: Johan Hovold Reviewed-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20240712140801.24267-3-johan+linaro@kernel.org Signed-off-by: Vinod Koul --- drivers/soundwire/bus_type.c | 9 ++------- include/linux/soundwire/sdw.h | 2 -- 2 files changed, 2 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/soundwire/bus_type.c b/drivers/soundwire/bus_type.c index 6b1c8c817102..fe08f7644f0e 100644 --- a/drivers/soundwire/bus_type.c +++ b/drivers/soundwire/bus_type.c @@ -198,16 +198,11 @@ static void sdw_drv_shutdown(struct device *dev) */ int __sdw_register_driver(struct sdw_driver *drv, struct module *owner) { - const char *name; - drv->driver.bus = &sdw_bus_type; if (!drv->probe) { - name = drv->name; - if (!name) - name = drv->driver.name; - - pr_err("driver %s didn't provide SDW probe routine\n", name); + pr_err("driver %s didn't provide SDW probe routine\n", + drv->driver.name); return -EINVAL; } diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 94fc1b57c57b..5e0dd47a0412 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -704,8 +704,6 @@ struct sdw_master_device { container_of(d, struct sdw_master_device, dev) struct sdw_driver { - const char *name; - int (*probe)(struct sdw_slave *sdw, const struct sdw_device_id *id); int (*remove)(struct sdw_slave *sdw); -- cgit v1.2.3 From 990c304930138dcd7a49763417e6e5313b81293e Mon Sep 17 00:00:00 2001 From: Patrick Rohr Date: Mon, 29 Jul 2024 15:00:59 -0700 Subject: Add support for PIO p flag MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit draft-ietf-6man-pio-pflag is adding a new flag to the Prefix Information Option to signal that the network can allocate a unique IPv6 prefix per client via DHCPv6-PD (see draft-ietf-v6ops-dhcp-pd-per-device). When ra_honor_pio_pflag is enabled, the presence of a P-flag causes SLAAC autoconfiguration to be disabled for that particular PIO. An automated test has been added in Android (r.android.com/3195335) to go along with this change. Cc: Maciej Żenczykowski Cc: Lorenzo Colitti Cc: David Lamparter Cc: Simon Horman Signed-off-by: Patrick Rohr Reviewed-by: Maciej Żenczykowski Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.rst | 14 ++++++++++++++ include/linux/ipv6.h | 1 + include/net/addrconf.h | 10 +++++++--- net/ipv6/addrconf.c | 15 ++++++++++++++- 4 files changed, 36 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 3616389c8c2d..eacf8983e230 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -2362,6 +2362,20 @@ ra_honor_pio_life - BOOLEAN Default: 0 (disabled) +ra_honor_pio_pflag - BOOLEAN + The Prefix Information Option P-flag indicates the network can + allocate a unique IPv6 prefix per client using DHCPv6-PD. + This sysctl can be enabled when a userspace DHCPv6-PD client + is running to cause the P-flag to take effect: i.e. the + P-flag suppresses any effects of the A-flag within the same + PIO. For a given PIO, P=1 and A=1 is treated as A=0. + + - If disabled, the P-flag is ignored. + - If enabled, the P-flag will disable SLAAC autoconfiguration + for the given Prefix Information Option. + + Default: 0 (disabled) + accept_ra_rt_info_min_plen - INTEGER Minimum prefix length of Route Information in RA. diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 383a0ea2ab91..a6e2aadbb91b 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -89,6 +89,7 @@ struct ipv6_devconf { __u8 ioam6_enabled; __u8 ndisc_evict_nocarrier; __u8 ra_honor_pio_life; + __u8 ra_honor_pio_pflag; struct ctl_table_header *sysctl_header; }; diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 62a407db1bf5..b18e81f0c9e1 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -37,10 +37,14 @@ struct prefix_info { struct __packed { #if defined(__BIG_ENDIAN_BITFIELD) __u8 onlink : 1, - autoconf : 1, - reserved : 6; + autoconf : 1, + routeraddr : 1, + preferpd : 1, + reserved : 4; #elif defined(__LITTLE_ENDIAN_BITFIELD) - __u8 reserved : 6, + __u8 reserved : 4, + preferpd : 1, + routeraddr : 1, autoconf : 1, onlink : 1; #else diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index f70d8757af1a..c87d008aefa4 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -239,6 +239,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .ioam6_id_wide = IOAM6_DEFAULT_IF_ID_WIDE, .ndisc_evict_nocarrier = 1, .ra_honor_pio_life = 0, + .ra_honor_pio_pflag = 0, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -302,6 +303,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .ioam6_id_wide = IOAM6_DEFAULT_IF_ID_WIDE, .ndisc_evict_nocarrier = 1, .ra_honor_pio_life = 0, + .ra_honor_pio_pflag = 0, }; /* Check if link is ready: is it up and is a valid qdisc available */ @@ -2762,6 +2764,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) u32 addr_flags = 0; struct inet6_dev *in6_dev; struct net *net = dev_net(dev); + bool ignore_autoconf = false; pinfo = (struct prefix_info *) opt; @@ -2864,7 +2867,8 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) /* Try to figure out our local address for this prefix */ - if (pinfo->autoconf && in6_dev->cnf.autoconf) { + ignore_autoconf = READ_ONCE(in6_dev->cnf.ra_honor_pio_pflag) && pinfo->preferpd; + if (pinfo->autoconf && in6_dev->cnf.autoconf && !ignore_autoconf) { struct in6_addr addr; bool tokenized = false, dev_addr_generated = false; @@ -6926,6 +6930,15 @@ static const struct ctl_table addrconf_sysctl[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, + { + .procname = "ra_honor_pio_pflag", + .data = &ipv6_devconf.ra_honor_pio_pflag, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, #ifdef CONFIG_IPV6_ROUTER_PREF { .procname = "accept_ra_rtr_pref", -- cgit v1.2.3 From 9aed3b51fd6186582a95abd9fa67782982540749 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 2 Jul 2024 18:49:35 -0700 Subject: rcu: Better define "atomic" for list replacement The kernel-doc headers for list_replace_rcu() and hlist_replace_rcu() claim that the replacement is atomic, which it is, but only for readers. Avoid confusion by making it clear that the atomic nature of these functions applies only to readers, not to concurrent updaters. Signed-off-by: Paul E. McKenney Signed-off-by: Neeraj Upadhyay --- include/linux/rculist.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 3dc1e58865f7..14dfa6008467 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -191,7 +191,10 @@ static inline void hlist_del_init_rcu(struct hlist_node *n) * @old : the element to be replaced * @new : the new element to insert * - * The @old entry will be replaced with the @new entry atomically. + * The @old entry will be replaced with the @new entry atomically from + * the perspective of concurrent readers. It is the caller's responsibility + * to synchronize with concurrent updaters, if any. + * * Note: @old should not be empty. */ static inline void list_replace_rcu(struct list_head *old, @@ -519,7 +522,9 @@ static inline void hlist_del_rcu(struct hlist_node *n) * @old : the element to be replaced * @new : the new element to insert * - * The @old entry will be replaced with the @new entry atomically. + * The @old entry will be replaced with the @new entry atomically from + * the perspective of concurrent readers. It is the caller's responsibility + * to synchronize with concurrent updaters, if any. */ static inline void hlist_replace_rcu(struct hlist_node *old, struct hlist_node *new) -- cgit v1.2.3 From 21b136cc63d2a9ddd60d4699552b69c214b32964 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 30 Jul 2024 15:44:16 -0700 Subject: minmax: fix up min3() and max3() too David Laight pointed out that we should deal with the min3() and max3() mess too, which still does excessive expansion. And our current macros are actually rather broken. In particular, the macros did this: #define min3(x, y, z) min((typeof(x))min(x, y), z) #define max3(x, y, z) max((typeof(x))max(x, y), z) and that not only is a nested expansion of possibly very complex arguments with all that involves, the typing with that "typeof()" cast is completely wrong. For example, imagine what happens in max3() if 'x' happens to be a 'unsigned char', but 'y' and 'z' are 'unsigned long'. The types are compatible, and there's no warning - but the result is just random garbage. No, I don't think we've ever hit that issue in practice, but since we now have sane infrastructure for doing this right, let's just use it. It fixes any excessive expansion, and also avoids these kinds of broken type issues. Requested-by: David Laight Acked-by: Arnd Bergmann Signed-off-by: Linus Torvalds --- include/linux/minmax.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/minmax.h b/include/linux/minmax.h index 41da6f85a407..98008dd92153 100644 --- a/include/linux/minmax.h +++ b/include/linux/minmax.h @@ -152,13 +152,20 @@ #define umax(x, y) \ __careful_cmp(max, (x) + 0u + 0ul + 0ull, (y) + 0u + 0ul + 0ull) +#define __careful_op3(op, x, y, z, ux, uy, uz) ({ \ + __auto_type ux = (x); __auto_type uy = (y);__auto_type uz = (z);\ + BUILD_BUG_ON_MSG(!__types_ok3(x,y,z,ux,uy,uz), \ + #op"3("#x", "#y", "#z") signedness error"); \ + __cmp(op, ux, __cmp(op, uy, uz)); }) + /** * min3 - return minimum of three values * @x: first value * @y: second value * @z: third value */ -#define min3(x, y, z) min((typeof(x))min(x, y), z) +#define min3(x, y, z) \ + __careful_op3(min, x, y, z, __UNIQUE_ID(x_), __UNIQUE_ID(y_), __UNIQUE_ID(z_)) /** * max3 - return maximum of three values @@ -166,7 +173,8 @@ * @y: second value * @z: third value */ -#define max3(x, y, z) max((typeof(x))max(x, y), z) +#define max3(x, y, z) \ + __careful_op3(max, x, y, z, __UNIQUE_ID(x_), __UNIQUE_ID(y_), __UNIQUE_ID(z_)) /** * min_not_zero - return the minimum that is _not_ zero, unless both are zero -- cgit v1.2.3 From ab03125268679e058e1e7b6612f6d12610761769 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Mon, 15 Jul 2024 11:00:34 -0400 Subject: cgroup: Show # of subsystem CSSes in cgroup.stat MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Cgroup subsystem state (CSS) is an abstraction in the cgroup layer to help manage different structures in various cgroup subsystems by being an embedded element inside a larger structure like cpuset or mem_cgroup. The /proc/cgroups file shows the number of cgroups for each of the subsystems. With cgroup v1, the number of CSSes is the same as the number of cgroups. That is not the case anymore with cgroup v2. The /proc/cgroups file cannot show the actual number of CSSes for the subsystems that are bound to cgroup v2. So if a v2 cgroup subsystem is leaking cgroups (usually memory cgroup), we can't tell by looking at /proc/cgroups which cgroup subsystems may be responsible. As cgroup v2 had deprecated the use of /proc/cgroups, the hierarchical cgroup.stat file is now being extended to show the number of live and dying CSSes associated with all the non-inhibited cgroup subsystems that have been bound to cgroup v2. The number includes CSSes in the current cgroup as well as in all the descendants underneath it. This will help us pinpoint which subsystems are responsible for the increasing number of dying (nr_dying_descendants) cgroups. The CSSes dying counts are stored in the cgroup structure itself instead of inside the CSS as suggested by Johannes. This will allow us to accurately track dying counts of cgroup subsystems that have recently been disabled in a cgroup. It is now possible that a zero subsystem number is coupled with a non-zero dying subsystem number. The cgroup-v2.rst file is updated to discuss this new behavior. With this patch applied, a sample output from root cgroup.stat file was shown below. nr_descendants 56 nr_subsys_cpuset 1 nr_subsys_cpu 43 nr_subsys_io 43 nr_subsys_memory 56 nr_subsys_perf_event 57 nr_subsys_hugetlb 1 nr_subsys_pids 56 nr_subsys_rdma 1 nr_subsys_misc 1 nr_dying_descendants 30 nr_dying_subsys_cpuset 0 nr_dying_subsys_cpu 0 nr_dying_subsys_io 0 nr_dying_subsys_memory 30 nr_dying_subsys_perf_event 0 nr_dying_subsys_hugetlb 0 nr_dying_subsys_pids 0 nr_dying_subsys_rdma 0 nr_dying_subsys_misc 0 Another sample output from system.slice/cgroup.stat was: nr_descendants 34 nr_subsys_cpuset 0 nr_subsys_cpu 32 nr_subsys_io 32 nr_subsys_memory 34 nr_subsys_perf_event 35 nr_subsys_hugetlb 0 nr_subsys_pids 34 nr_subsys_rdma 0 nr_subsys_misc 0 nr_dying_descendants 30 nr_dying_subsys_cpuset 0 nr_dying_subsys_cpu 0 nr_dying_subsys_io 0 nr_dying_subsys_memory 30 nr_dying_subsys_perf_event 0 nr_dying_subsys_hugetlb 0 nr_dying_subsys_pids 0 nr_dying_subsys_rdma 0 nr_dying_subsys_misc 0 Note that 'debug' controller wasn't used to provide this information because the controller is not recommended in productions kernels, also many of them won't enable CONFIG_CGROUP_DEBUG by default. Similar information could be retrieved with debuggers like drgn but that's also not always available (e.g. lockdown) and the additional cost of runtime tracking here is deemed marginal. tj: Added Michal's paragraphs on why this is not added the debug controller to the commit message. Signed-off-by: Waiman Long Acked-by: Johannes Weiner Acked-by: Roman Gushchin Reviewed-by: Kamalesh Babulal Cc: Michal Koutný Link: http://lkml.kernel.org/r/20240715150034.2583772-1-longman@redhat.com Signed-off-by: Tejun Heo --- Documentation/admin-guide/cgroup-v2.rst | 12 +++++-- include/linux/cgroup-defs.h | 14 +++++++++ kernel/cgroup/cgroup.c | 55 +++++++++++++++++++++++++++++++-- 3 files changed, 77 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 86311c2907cd..70cefccd07ce 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -981,6 +981,14 @@ All cgroup core files are prefixed with "cgroup." A dying cgroup can consume system resources not exceeding limits, which were active at the moment of cgroup deletion. + nr_subsys_ + Total number of live cgroup subsystems (e.g memory + cgroup) at and beneath the current cgroup. + + nr_dying_subsys_ + Total number of dying cgroup subsystems (e.g. memory + cgroup) at and beneath the current cgroup. + cgroup.freeze A read-write single value file which exists on non-root cgroups. Allowed values are "0" and "1". The default is "0". @@ -2939,8 +2947,8 @@ Deprecated v1 Core Features - "cgroup.clone_children" is removed. -- /proc/cgroups is meaningless for v2. Use "cgroup.controllers" file - at the root instead. +- /proc/cgroups is meaningless for v2. Use "cgroup.controllers" or + "cgroup.stat" files at the root instead. Issues with v1 and Rationales for v2 diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index ae04035b6cbe..eb0f6f349496 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -210,6 +210,14 @@ struct cgroup_subsys_state { * fields of the containing structure. */ struct cgroup_subsys_state *parent; + + /* + * Keep track of total numbers of visible descendant CSSes. + * The total number of dying CSSes is tracked in + * css->cgroup->nr_dying_subsys[ssid]. + * Protected by cgroup_mutex. + */ + int nr_descendants; }; /* @@ -470,6 +478,12 @@ struct cgroup { /* Private pointers for each registered subsystem */ struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT]; + /* + * Keep track of total number of dying CSSes at and below this cgroup. + * Protected by cgroup_mutex. + */ + int nr_dying_subsys[CGROUP_SUBSYS_COUNT]; + struct cgroup_root *root; /* diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index c8e4b62b436a..601600afdd20 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3669,12 +3669,40 @@ static int cgroup_events_show(struct seq_file *seq, void *v) static int cgroup_stat_show(struct seq_file *seq, void *v) { struct cgroup *cgroup = seq_css(seq)->cgroup; + struct cgroup_subsys_state *css; + int dying_cnt[CGROUP_SUBSYS_COUNT]; + int ssid; seq_printf(seq, "nr_descendants %d\n", cgroup->nr_descendants); + + /* + * Show the number of live and dying csses associated with each of + * non-inhibited cgroup subsystems that is bound to cgroup v2. + * + * Without proper lock protection, racing is possible. So the + * numbers may not be consistent when that happens. + */ + rcu_read_lock(); + for (ssid = 0; ssid < CGROUP_SUBSYS_COUNT; ssid++) { + dying_cnt[ssid] = -1; + if ((BIT(ssid) & cgrp_dfl_inhibit_ss_mask) || + (cgroup_subsys[ssid]->root != &cgrp_dfl_root)) + continue; + css = rcu_dereference_raw(cgroup->subsys[ssid]); + dying_cnt[ssid] = cgroup->nr_dying_subsys[ssid]; + seq_printf(seq, "nr_subsys_%s %d\n", cgroup_subsys[ssid]->name, + css ? (css->nr_descendants + 1) : 0); + } + seq_printf(seq, "nr_dying_descendants %d\n", cgroup->nr_dying_descendants); - + for (ssid = 0; ssid < CGROUP_SUBSYS_COUNT; ssid++) { + if (dying_cnt[ssid] >= 0) + seq_printf(seq, "nr_dying_subsys_%s %d\n", + cgroup_subsys[ssid]->name, dying_cnt[ssid]); + } + rcu_read_unlock(); return 0; } @@ -5424,6 +5452,8 @@ static void css_release_work_fn(struct work_struct *work) list_del_rcu(&css->sibling); if (ss) { + struct cgroup *parent_cgrp; + /* css release path */ if (!list_empty(&css->rstat_css_node)) { cgroup_rstat_flush(cgrp); @@ -5433,6 +5463,14 @@ static void css_release_work_fn(struct work_struct *work) cgroup_idr_replace(&ss->css_idr, NULL, css->id); if (ss->css_released) ss->css_released(css); + + cgrp->nr_dying_subsys[ss->id]--; + WARN_ON_ONCE(css->nr_descendants || cgrp->nr_dying_subsys[ss->id]); + parent_cgrp = cgroup_parent(cgrp); + while (parent_cgrp) { + parent_cgrp->nr_dying_subsys[ss->id]--; + parent_cgrp = cgroup_parent(parent_cgrp); + } } else { struct cgroup *tcgrp; @@ -5517,8 +5555,11 @@ static int online_css(struct cgroup_subsys_state *css) rcu_assign_pointer(css->cgroup->subsys[ss->id], css); atomic_inc(&css->online_cnt); - if (css->parent) + if (css->parent) { atomic_inc(&css->parent->online_cnt); + while ((css = css->parent)) + css->nr_descendants++; + } } return ret; } @@ -5540,6 +5581,16 @@ static void offline_css(struct cgroup_subsys_state *css) RCU_INIT_POINTER(css->cgroup->subsys[ss->id], NULL); wake_up_all(&css->cgroup->offline_waitq); + + css->cgroup->nr_dying_subsys[ss->id]++; + /* + * Parent css and cgroup cannot be freed until after the freeing + * of child css, see css_free_rwork_fn(). + */ + while ((css = css->parent)) { + css->nr_descendants--; + css->cgroup->nr_dying_subsys[ss->id]++; + } } /** -- cgit v1.2.3 From f81489a136ac2c18a7b9bb22cf37c0a6f6d58545 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Fri, 12 Jul 2024 13:57:13 -0700 Subject: hwmon: (max6697) Drop platform data support Platform data is not used anywhere in the upstram kernel. Drop support for it to simplify code maintenance. Reviewed-by: Tzung-Bi Shih Signed-off-by: Guenter Roeck --- drivers/hwmon/max6697.c | 176 ++++++++++++++++------------------ include/linux/platform_data/max6697.h | 33 ------- 2 files changed, 82 insertions(+), 127 deletions(-) delete mode 100644 include/linux/platform_data/max6697.h (limited to 'include/linux') diff --git a/drivers/hwmon/max6697.c b/drivers/hwmon/max6697.c index 9a2a21230c7d..b9766533d876 100644 --- a/drivers/hwmon/max6697.c +++ b/drivers/hwmon/max6697.c @@ -17,8 +17,6 @@ #include #include -#include - enum chips { max6581, max6602, max6622, max6636, max6689, max6693, max6694, max6697, max6698, max6699 }; @@ -558,54 +556,97 @@ static const struct attribute_group max6697_group = { }; __ATTRIBUTE_GROUPS(max6697); -static void max6697_get_config_of(struct device_node *node, - struct max6697_platform_data *pdata) +static int max6697_config_of(struct max6697_data *data, struct i2c_client *client) { - int len; - const __be32 *prop; - - pdata->smbus_timeout_disable = - of_property_read_bool(node, "smbus-timeout-disable"); - pdata->extended_range_enable = - of_property_read_bool(node, "extended-range-enable"); - pdata->beta_compensation = - of_property_read_bool(node, "beta-compensation-enable"); - - prop = of_get_property(node, "alert-mask", &len); - if (prop && len == sizeof(u32)) - pdata->alert_mask = be32_to_cpu(prop[0]); - prop = of_get_property(node, "over-temperature-mask", &len); - if (prop && len == sizeof(u32)) - pdata->over_temperature_mask = be32_to_cpu(prop[0]); - prop = of_get_property(node, "resistance-cancellation", &len); - if (prop) { - if (len == sizeof(u32)) - pdata->resistance_cancellation = be32_to_cpu(prop[0]); - else - pdata->resistance_cancellation = 0xfe; + const struct max6697_chip_data *chip = data->chip; + struct device_node *node = client->dev.of_node; + int ret, confreg; + int factor = 0; + u32 vals[2]; + + confreg = 0; + if (of_property_read_bool(node, "smbus-timeout-disable") && + (chip->valid_conf & MAX6697_CONF_TIMEOUT)) { + confreg |= MAX6697_CONF_TIMEOUT; + } + if (of_property_read_bool(node, "extended-range-enable") && + (chip->valid_conf & MAX6581_CONF_EXTENDED)) { + confreg |= MAX6581_CONF_EXTENDED; + data->temp_offset = 64; + } + if (of_property_read_bool(node, "beta-compensation-enable") && + (chip->valid_conf & MAX6693_CONF_BETA)) { + confreg |= MAX6693_CONF_BETA; } - prop = of_get_property(node, "transistor-ideality", &len); - if (prop && len == 2 * sizeof(u32)) { - pdata->ideality_mask = be32_to_cpu(prop[0]); - pdata->ideality_value = be32_to_cpu(prop[1]); + + if (of_property_read_u32(node, "alert-mask", vals)) + vals[0] = 0; + ret = i2c_smbus_write_byte_data(client, MAX6697_REG_ALERT_MASK, + MAX6697_ALERT_MAP_BITS(vals[0])); + if (ret) + return ret; + + if (of_property_read_u32(node, "over-temperature-mask", vals)) + vals[0] = 0; + ret = i2c_smbus_write_byte_data(client, MAX6697_REG_OVERT_MASK, + MAX6697_OVERT_MAP_BITS(vals[0])); + if (ret) + return ret; + + if (data->type != max6581) { + if (of_property_read_bool(node, "resistance-cancellation") && + chip->valid_conf & MAX6697_CONF_RESISTANCE) { + confreg |= MAX6697_CONF_RESISTANCE; + factor = 1; + } + } else { + if (of_property_read_u32(node, "resistance-cancellation", &vals[0])) { + if (of_property_read_bool(node, "resistance-cancellation")) + vals[0] = 0xfe; + else + vals[0] = 0; + } + + vals[0] &= 0xfe; + factor = hweight8(vals[0]); + ret = i2c_smbus_write_byte_data(client, MAX6581_REG_RESISTANCE, + vals[0] >> 1); + if (ret < 0) + return ret; + + if (of_property_read_u32_array(node, "transistor-ideality", vals, 2)) { + vals[0] = 0; + vals[1] = 0; + } + + ret = i2c_smbus_write_byte_data(client, MAX6581_REG_IDEALITY, + vals[1]); + if (ret < 0) + return ret; + ret = i2c_smbus_write_byte_data(client, + MAX6581_REG_IDEALITY_SELECT, + (vals[0] & 0xfe) >> 1); + if (ret < 0) + return ret; } + ret = i2c_smbus_write_byte_data(client, MAX6697_REG_CONFIG, confreg); + if (ret < 0) + return ret; + return factor; } static int max6697_init_chip(struct max6697_data *data, struct i2c_client *client) { - struct max6697_platform_data *pdata = dev_get_platdata(&client->dev); - struct max6697_platform_data p; const struct max6697_chip_data *chip = data->chip; int factor = chip->channels; int ret, reg; /* - * Don't touch configuration if neither platform data nor OF - * configuration was specified. If that is the case, use the - * current chip configuration. + * Don't touch configuration if there is no devicetree configuration. + * If that is the case, use the current chip configuration. */ - if (!pdata && !client->dev.of_node) { + if (!client->dev.of_node) { reg = i2c_smbus_read_byte_data(client, MAX6697_REG_CONFIG); if (reg < 0) return reg; @@ -621,67 +662,14 @@ static int max6697_init_chip(struct max6697_data *data, if (reg & MAX6697_CONF_RESISTANCE) factor++; } - goto done; - } - - if (client->dev.of_node) { - memset(&p, 0, sizeof(p)); - max6697_get_config_of(client->dev.of_node, &p); - pdata = &p; - } - - reg = 0; - if (pdata->smbus_timeout_disable && - (chip->valid_conf & MAX6697_CONF_TIMEOUT)) { - reg |= MAX6697_CONF_TIMEOUT; - } - if (pdata->extended_range_enable && - (chip->valid_conf & MAX6581_CONF_EXTENDED)) { - reg |= MAX6581_CONF_EXTENDED; - data->temp_offset = 64; - } - if (pdata->resistance_cancellation && - (chip->valid_conf & MAX6697_CONF_RESISTANCE)) { - reg |= MAX6697_CONF_RESISTANCE; - factor++; - } - if (pdata->beta_compensation && - (chip->valid_conf & MAX6693_CONF_BETA)) { - reg |= MAX6693_CONF_BETA; - } - - ret = i2c_smbus_write_byte_data(client, MAX6697_REG_CONFIG, reg); - if (ret < 0) - return ret; - - ret = i2c_smbus_write_byte_data(client, MAX6697_REG_ALERT_MASK, - MAX6697_ALERT_MAP_BITS(pdata->alert_mask)); - if (ret < 0) - return ret; - - ret = i2c_smbus_write_byte_data(client, MAX6697_REG_OVERT_MASK, - MAX6697_OVERT_MAP_BITS(pdata->over_temperature_mask)); - if (ret < 0) - return ret; - - if (data->type == max6581) { - factor += hweight8(pdata->resistance_cancellation >> 1); - ret = i2c_smbus_write_byte_data(client, MAX6581_REG_RESISTANCE, - pdata->resistance_cancellation >> 1); - if (ret < 0) - return ret; - ret = i2c_smbus_write_byte_data(client, MAX6581_REG_IDEALITY, - pdata->ideality_value); - if (ret < 0) - return ret; - ret = i2c_smbus_write_byte_data(client, - MAX6581_REG_IDEALITY_SELECT, - pdata->ideality_mask >> 1); + data->update_interval = factor * MAX6697_CONV_TIME; + } else { + ret = max6697_config_of(data, client); if (ret < 0) return ret; + data->update_interval = (factor + ret) * MAX6697_CONV_TIME; } -done: - data->update_interval = factor * MAX6697_CONV_TIME; + return 0; } diff --git a/include/linux/platform_data/max6697.h b/include/linux/platform_data/max6697.h deleted file mode 100644 index 6fbb70005541..000000000000 --- a/include/linux/platform_data/max6697.h +++ /dev/null @@ -1,33 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * max6697.h - * Copyright (c) 2012 Guenter Roeck - */ - -#ifndef MAX6697_H -#define MAX6697_H - -#include - -/* - * For all bit masks: - * bit 0: local temperature - * bit 1..7: remote temperatures - */ -struct max6697_platform_data { - bool smbus_timeout_disable; /* set to disable SMBus timeouts */ - bool extended_range_enable; /* set to enable extended temp range */ - bool beta_compensation; /* set to enable beta compensation */ - u8 alert_mask; /* set bit to 1 to disable alert */ - u8 over_temperature_mask; /* set bit to 1 to disable */ - u8 resistance_cancellation; /* set bit to 0 to disable - * bit mask for MAX6581, - * boolean for other chips - */ - u8 ideality_mask; /* set bit to 0 to disable */ - u8 ideality_value; /* transistor ideality as per - * MAX6581 datasheet - */ -}; - -#endif /* MAX6697_H */ -- cgit v1.2.3 From 298dec19bdeb6e33ac220502504d969272b50cf6 Mon Sep 17 00:00:00 2001 From: David Vernet Date: Wed, 31 Jul 2024 00:14:36 -0500 Subject: scx: Allow calling sleepable kfuncs from BPF_PROG_TYPE_SYSCALL We currently only allow calling sleepable scx kfuncs (i.e. scx_bpf_create_dsq()) from BPF_PROG_TYPE_STRUCT_OPS progs. The idea here was that we'd never have to call scx_bpf_create_dsq() outside of a sched_ext struct_ops callback, but that might not actually be true. For example, a scheduler could do something like the following: 1. Open and load (not yet attach) a scheduler skel 2. Synchronously call into a BPF_PROG_TYPE_SYSCALL prog from user space. For example, to initialize an LLC domain, or some other global, read-only state. 3. Attach the skel, which actually enables the scheduler The advantage of doing this is that it can preclude having to do pretty ugly boilerplate like initializing a read-only, statically sized array of u64[]'s which the kernel consumes literally once at init time to then create struct bpf_cpumask objects which are actually queried at runtime. Doing the above is already possible given that we can invoke core BPF kfuncs, such as bpf_cpumask_create(), from BPF_PROG_TYPE_SYSCALL progs. We already allow many scx kfuncs to be called from BPF_PROG_TYPE_SYSCALL progs (e.g. scx_bpf_kick_cpu()). Let's allow the sleepable kfuncs as well. Signed-off-by: David Vernet Signed-off-by: Tejun Heo --- include/linux/sched/ext.h | 14 ++++++-------- kernel/sched/ext.c | 27 +++++++++++---------------- 2 files changed, 17 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index 593d2f4909dd..26e1c33bc844 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -106,16 +106,14 @@ enum scx_ent_dsq_flags { * mechanism. See scx_kf_allow(). */ enum scx_kf_mask { - SCX_KF_UNLOCKED = 0, /* not sleepable, not rq locked */ - /* all non-sleepables may be nested inside SLEEPABLE */ - SCX_KF_SLEEPABLE = 1 << 0, /* sleepable init operations */ + SCX_KF_UNLOCKED = 0, /* sleepable and not rq locked */ /* ENQUEUE and DISPATCH may be nested inside CPU_RELEASE */ - SCX_KF_CPU_RELEASE = 1 << 1, /* ops.cpu_release() */ + SCX_KF_CPU_RELEASE = 1 << 0, /* ops.cpu_release() */ /* ops.dequeue (in REST) may be nested inside DISPATCH */ - SCX_KF_DISPATCH = 1 << 2, /* ops.dispatch() */ - SCX_KF_ENQUEUE = 1 << 3, /* ops.enqueue() and ops.select_cpu() */ - SCX_KF_SELECT_CPU = 1 << 4, /* ops.select_cpu() */ - SCX_KF_REST = 1 << 5, /* other rq-locked operations */ + SCX_KF_DISPATCH = 1 << 1, /* ops.dispatch() */ + SCX_KF_ENQUEUE = 1 << 2, /* ops.enqueue() and ops.select_cpu() */ + SCX_KF_SELECT_CPU = 1 << 3, /* ops.select_cpu() */ + SCX_KF_REST = 1 << 4, /* other rq-locked operations */ __SCX_KF_RQ_LOCKED = SCX_KF_CPU_RELEASE | SCX_KF_DISPATCH | SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU | SCX_KF_REST, diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index da9cac6b6cc2..4a07deb30c44 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -1029,16 +1029,12 @@ static __always_inline bool scx_kf_allowed(u32 mask) return false; } - if (unlikely((mask & SCX_KF_SLEEPABLE) && in_interrupt())) { - scx_ops_error("sleepable kfunc called from non-sleepable context"); - return false; - } - /* * Enforce nesting boundaries. e.g. A kfunc which can be called from * DISPATCH must not be called if we're running DEQUEUE which is nested - * inside ops.dispatch(). We don't need to check the SCX_KF_SLEEPABLE - * boundary thanks to the above in_interrupt() check. + * inside ops.dispatch(). We don't need to check boundaries for any + * blocking kfuncs as the verifier ensures they're only called from + * sleepable progs. */ if (unlikely(highest_bit(mask) == SCX_KF_CPU_RELEASE && (current->scx.kf_mask & higher_bits(SCX_KF_CPU_RELEASE)))) { @@ -3224,9 +3220,9 @@ static void handle_hotplug(struct rq *rq, bool online) atomic_long_inc(&scx_hotplug_seq); if (online && SCX_HAS_OP(cpu_online)) - SCX_CALL_OP(SCX_KF_SLEEPABLE, cpu_online, cpu); + SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_online, cpu); else if (!online && SCX_HAS_OP(cpu_offline)) - SCX_CALL_OP(SCX_KF_SLEEPABLE, cpu_offline, cpu); + SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_offline, cpu); else scx_ops_exit(SCX_ECODE_ACT_RESTART | SCX_ECODE_RSN_HOTPLUG, "cpu %d going %s, exiting scheduler", cpu, @@ -3390,7 +3386,7 @@ static int scx_ops_init_task(struct task_struct *p, struct task_group *tg, bool .fork = fork, }; - ret = SCX_CALL_OP_RET(SCX_KF_SLEEPABLE, init_task, p, &args); + ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init_task, p, &args); if (unlikely(ret)) { ret = ops_sanitize_err("init_task", ret); return ret; @@ -4648,7 +4644,7 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) cpus_read_lock(); if (scx_ops.init) { - ret = SCX_CALL_OP_RET(SCX_KF_SLEEPABLE, init); + ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init); if (ret) { ret = ops_sanitize_err("init", ret); goto err_disable_unlock_cpus; @@ -5424,14 +5420,11 @@ __bpf_kfunc_start_defs(); * @dsq_id: DSQ to create * @node: NUMA node to allocate from * - * Create a custom DSQ identified by @dsq_id. Can be called from ops.init() and - * ops.init_task(). + * Create a custom DSQ identified by @dsq_id. Can be called from any sleepable + * scx callback, and any BPF_PROG_TYPE_SYSCALL prog. */ __bpf_kfunc s32 scx_bpf_create_dsq(u64 dsq_id, s32 node) { - if (!scx_kf_allowed(SCX_KF_SLEEPABLE)) - return -EINVAL; - if (unlikely(node >= (int)nr_node_ids || (node < 0 && node != NUMA_NO_NODE))) return -EINVAL; @@ -6490,6 +6483,8 @@ static int __init scx_init(void) */ if ((ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &scx_kfunc_set_sleepable)) || + (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, + &scx_kfunc_set_sleepable)) || (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &scx_kfunc_set_select_cpu)) || (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, -- cgit v1.2.3 From be72a57527fde6c80061c5f9d0e28762eb817b03 Mon Sep 17 00:00:00 2001 From: Xu Kuohai Date: Wed, 24 Jul 2024 10:06:58 +0800 Subject: lsm: Refactor return value of LSM hook vm_enough_memory To be consistent with most LSM hooks, convert the return value of hook vm_enough_memory to 0 or a negative error code. Before: - Hook vm_enough_memory returns 1 if permission is granted, 0 if not. - LSM_RET_DEFAULT(vm_enough_memory_mm) is 1. After: - Hook vm_enough_memory reutrns 0 if permission is granted, negative error code if not. - LSM_RET_DEFAULT(vm_enough_memory_mm) is 0. Signed-off-by: Xu Kuohai Reviewed-by: Casey Schaufler Signed-off-by: Paul Moore --- include/linux/lsm_hook_defs.h | 2 +- include/linux/security.h | 2 +- security/commoncap.c | 11 +++-------- security/security.c | 11 +++++------ security/selinux/hooks.c | 15 ++++----------- 5 files changed, 14 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 12c81be78eb9..63e2656d1d56 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -48,7 +48,7 @@ LSM_HOOK(int, 0, quota_on, struct dentry *dentry) LSM_HOOK(int, 0, syslog, int type) LSM_HOOK(int, 0, settime, const struct timespec64 *ts, const struct timezone *tz) -LSM_HOOK(int, 1, vm_enough_memory, struct mm_struct *mm, long pages) +LSM_HOOK(int, 0, vm_enough_memory, struct mm_struct *mm, long pages) LSM_HOOK(int, 0, bprm_creds_for_exec, struct linux_binprm *bprm) LSM_HOOK(int, 0, bprm_creds_from_file, struct linux_binprm *bprm, const struct file *file) LSM_HOOK(int, 0, bprm_check_security, struct linux_binprm *bprm) diff --git a/include/linux/security.h b/include/linux/security.h index 1390f1efb4f0..62233fec8ead 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -634,7 +634,7 @@ static inline int security_settime64(const struct timespec64 *ts, static inline int security_vm_enough_memory_mm(struct mm_struct *mm, long pages) { - return __vm_enough_memory(mm, pages, cap_vm_enough_memory(mm, pages)); + return __vm_enough_memory(mm, pages, !cap_vm_enough_memory(mm, pages)); } static inline int security_bprm_creds_for_exec(struct linux_binprm *bprm) diff --git a/security/commoncap.c b/security/commoncap.c index 162d96b3a676..cefad323a0b1 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -1396,17 +1396,12 @@ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3, * Determine whether the allocation of a new virtual mapping by the current * task is permitted. * - * Return: 1 if permission is granted, 0 if not. + * Return: 0 if permission granted, negative error code if not. */ int cap_vm_enough_memory(struct mm_struct *mm, long pages) { - int cap_sys_admin = 0; - - if (cap_capable(current_cred(), &init_user_ns, - CAP_SYS_ADMIN, CAP_OPT_NOAUDIT) == 0) - cap_sys_admin = 1; - - return cap_sys_admin; + return cap_capable(current_cred(), &init_user_ns, CAP_SYS_ADMIN, + CAP_OPT_NOAUDIT); } /** diff --git a/security/security.c b/security/security.c index 93ed7670fbc9..b2f0e9a57864 100644 --- a/security/security.c +++ b/security/security.c @@ -1129,15 +1129,14 @@ int security_vm_enough_memory_mm(struct mm_struct *mm, long pages) int rc; /* - * The module will respond with a positive value if - * it thinks the __vm_enough_memory() call should be - * made with the cap_sys_admin set. If all of the modules - * agree that it should be set it will. If any module - * thinks it should not be set it won't. + * The module will respond with 0 if it thinks the __vm_enough_memory() + * call should be made with the cap_sys_admin set. If all of the modules + * agree that it should be set it will. If any module thinks it should + * not be set it won't. */ hlist_for_each_entry(hp, &security_hook_heads.vm_enough_memory, list) { rc = hp->hook.vm_enough_memory(mm, pages); - if (rc <= 0) { + if (rc < 0) { cap_sys_admin = 0; break; } diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 0939816e9671..af7467cdd181 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -2202,23 +2202,16 @@ static int selinux_syslog(int type) } /* - * Check that a process has enough memory to allocate a new virtual - * mapping. 0 means there is enough memory for the allocation to - * succeed and -ENOMEM implies there is not. + * Check permission for allocating a new virtual mapping. Returns + * 0 if permission is granted, negative error code if not. * * Do not audit the selinux permission check, as this is applied to all * processes that allocate mappings. */ static int selinux_vm_enough_memory(struct mm_struct *mm, long pages) { - int rc, cap_sys_admin = 0; - - rc = cred_has_capability(current_cred(), CAP_SYS_ADMIN, - CAP_OPT_NOAUDIT, true); - if (rc == 0) - cap_sys_admin = 1; - - return cap_sys_admin; + return cred_has_capability(current_cred(), CAP_SYS_ADMIN, + CAP_OPT_NOAUDIT, true); } /* binprm security operations */ -- cgit v1.2.3 From c9c0ee5f20c593faf289fa8850c3ed84031dd12a Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Mon, 29 Jul 2024 03:47:40 -0700 Subject: net: skbuff: Skip early return in skb_unref when debugging This patch modifies the skb_unref function to skip the early return optimization when CONFIG_DEBUG_NET is enabled. The change ensures that the reference count decrement always occurs in debug builds, allowing for more thorough checking of SKB reference counting. Previously, when the SKB's reference count was 1 and CONFIG_DEBUG_NET was not set, the function would return early after a memory barrier (smp_rmb()) without decrementing the reference count. This optimization assumes it's safe to proceed with freeing the SKB without the overhead of an atomic decrement from 1 to 0. With this change: - In non-debug builds (CONFIG_DEBUG_NET not set), behavior remains unchanged, preserving the performance optimization. - In debug builds (CONFIG_DEBUG_NET set), the reference count is always decremented, even when it's 1, allowing for consistent behavior and potentially catching subtle SKB management bugs. This modification enhances debugging capabilities for networking code without impacting performance in production kernels. It helps kernel developers identify and diagnose issues related to SKB management and reference counting in the network stack. Cc: Chris Mason Suggested-by: Jakub Kicinski Signed-off-by: Breno Leitao Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20240729104741.370327-1-leitao@debian.org Signed-off-by: Paolo Abeni --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 29c3ea5b6e93..cf8f6ce06742 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1225,7 +1225,7 @@ static inline bool skb_unref(struct sk_buff *skb) { if (unlikely(!skb)) return false; - if (likely(refcount_read(&skb->users) == 1)) + if (!IS_ENABLED(CONFIG_DEBUG_NET) && likely(refcount_read(&skb->users) == 1)) smp_rmb(); else if (likely(!refcount_dec_and_test(&skb->users))) return false; -- cgit v1.2.3 From f0fcdd2cb0db62605d85f3b97a1b443e7c91f886 Mon Sep 17 00:00:00 2001 From: John Allen Date: Tue, 30 Jul 2024 15:17:30 +0000 Subject: ACPI: PRM: Add PRM handler direct call support Platform Runtime Mechanism (PRM) handlers can be invoked from either the AML interpreter or directly by an OS driver. Implement the latter. [ bp: Massage commit message. ] Signed-off-by: John Allen Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Yazen Ghannam Reviewed-by: Ard Biesheuvel Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20240730151731.15363-2-john.allen@amd.com --- drivers/acpi/prmt.c | 24 ++++++++++++++++++++++++ include/linux/prmt.h | 5 +++++ 2 files changed, 29 insertions(+) (limited to 'include/linux') diff --git a/drivers/acpi/prmt.c b/drivers/acpi/prmt.c index c78453c74ef5..1cfaa5957ac4 100644 --- a/drivers/acpi/prmt.c +++ b/drivers/acpi/prmt.c @@ -214,6 +214,30 @@ static struct prm_handler_info *find_prm_handler(const guid_t *guid) #define UPDATE_LOCK_ALREADY_HELD 4 #define UPDATE_UNLOCK_WITHOUT_LOCK 5 +int acpi_call_prm_handler(guid_t handler_guid, void *param_buffer) +{ + struct prm_handler_info *handler = find_prm_handler(&handler_guid); + struct prm_module_info *module = find_prm_module(&handler_guid); + struct prm_context_buffer context; + efi_status_t status; + + if (!module || !handler) + return -ENODEV; + + memset(&context, 0, sizeof(context)); + ACPI_COPY_NAMESEG(context.signature, "PRMC"); + context.identifier = handler->guid; + context.static_data_buffer = handler->static_data_buffer_addr; + context.mmio_ranges = module->mmio_info; + + status = efi_call_acpi_prm_handler(handler->handler_addr, + (u64)param_buffer, + &context); + + return efi_status_to_err(status); +} +EXPORT_SYMBOL_GPL(acpi_call_prm_handler); + /* * This is the PlatformRtMechanism opregion space handler. * @function: indicates the read/write. In fact as the PlatformRtMechanism diff --git a/include/linux/prmt.h b/include/linux/prmt.h index 24da8364b919..9c094294403f 100644 --- a/include/linux/prmt.h +++ b/include/linux/prmt.h @@ -2,6 +2,11 @@ #ifdef CONFIG_ACPI_PRMT void init_prmt(void); +int acpi_call_prm_handler(guid_t handler_guid, void *param_buffer); #else static inline void init_prmt(void) { } +static inline int acpi_call_prm_handler(guid_t handler_guid, void *param_buffer) +{ + return -EOPNOTSUPP; +} #endif -- cgit v1.2.3 From 6b08d07cac64c0dcf1dbb4584bdf95d0f789a520 Mon Sep 17 00:00:00 2001 From: Lukasz Majewski Date: Wed, 10 Jul 2024 12:06:51 +0200 Subject: leds: trigger: netdev: Add support for tx_err and rx_err notification with LEDs This patch provides support for enabling blinking of LEDs when RX or TX errors are detected. Approach taken in this patch is similar to one for TX or RX data transmission indication (i.e. TRIGGER_NETDEV_TX/RX attribute). One can inspect transmission errors with: ip -s link show eth0 Example LED configuration: cd /sys/devices/platform/amba_pl@0/a001a000.leds/leds/ echo netdev > mode:blue/trigger && \ echo eth0 > mode:blue/device_name && \ echo 1 > mode:blue/tx_err Signed-off-by: Lukasz Majewski Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20240710100651.4059887-1-lukma@denx.de Signed-off-by: Lee Jones --- drivers/leds/trigger/ledtrig-netdev.c | 24 +++++++++++++++++++++--- include/linux/leds.h | 2 ++ 2 files changed, 23 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/leds/trigger/ledtrig-netdev.c b/drivers/leds/trigger/ledtrig-netdev.c index 22bba8e97642..4b0863db901a 100644 --- a/drivers/leds/trigger/ledtrig-netdev.c +++ b/drivers/leds/trigger/ledtrig-netdev.c @@ -39,6 +39,8 @@ * (has carrier) or not * tx - LED blinks on transmitted data * rx - LED blinks on receive data + * tx_err - LED blinks on transmit error + * rx_err - LED blinks on receive error * * Note: If the user selects a mode that is not supported by hw, default * behavior is to fall back to software control of the LED. However not every @@ -144,7 +146,9 @@ static void set_baseline_state(struct led_netdev_data *trigger_data) * checking stats */ if (test_bit(TRIGGER_NETDEV_TX, &trigger_data->mode) || - test_bit(TRIGGER_NETDEV_RX, &trigger_data->mode)) + test_bit(TRIGGER_NETDEV_RX, &trigger_data->mode) || + test_bit(TRIGGER_NETDEV_TX_ERR, &trigger_data->mode) || + test_bit(TRIGGER_NETDEV_RX_ERR, &trigger_data->mode)) schedule_delayed_work(&trigger_data->work, 0); } } @@ -337,6 +341,8 @@ static ssize_t netdev_led_attr_show(struct device *dev, char *buf, case TRIGGER_NETDEV_FULL_DUPLEX: case TRIGGER_NETDEV_TX: case TRIGGER_NETDEV_RX: + case TRIGGER_NETDEV_TX_ERR: + case TRIGGER_NETDEV_RX_ERR: bit = attr; break; default: @@ -371,6 +377,8 @@ static ssize_t netdev_led_attr_store(struct device *dev, const char *buf, case TRIGGER_NETDEV_FULL_DUPLEX: case TRIGGER_NETDEV_TX: case TRIGGER_NETDEV_RX: + case TRIGGER_NETDEV_TX_ERR: + case TRIGGER_NETDEV_RX_ERR: bit = attr; break; default: @@ -429,6 +437,8 @@ DEFINE_NETDEV_TRIGGER(half_duplex, TRIGGER_NETDEV_HALF_DUPLEX); DEFINE_NETDEV_TRIGGER(full_duplex, TRIGGER_NETDEV_FULL_DUPLEX); DEFINE_NETDEV_TRIGGER(tx, TRIGGER_NETDEV_TX); DEFINE_NETDEV_TRIGGER(rx, TRIGGER_NETDEV_RX); +DEFINE_NETDEV_TRIGGER(tx_err, TRIGGER_NETDEV_TX_ERR); +DEFINE_NETDEV_TRIGGER(rx_err, TRIGGER_NETDEV_RX_ERR); static ssize_t interval_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -538,6 +548,8 @@ static struct attribute *netdev_trig_attrs[] = { &dev_attr_half_duplex.attr, &dev_attr_rx.attr, &dev_attr_tx.attr, + &dev_attr_rx_err.attr, + &dev_attr_tx_err.attr, &dev_attr_interval.attr, &dev_attr_offloaded.attr, NULL @@ -628,7 +640,9 @@ static void netdev_trig_work(struct work_struct *work) /* If we are not looking for RX/TX then return */ if (!test_bit(TRIGGER_NETDEV_TX, &trigger_data->mode) && - !test_bit(TRIGGER_NETDEV_RX, &trigger_data->mode)) + !test_bit(TRIGGER_NETDEV_RX, &trigger_data->mode) && + !test_bit(TRIGGER_NETDEV_TX_ERR, &trigger_data->mode) && + !test_bit(TRIGGER_NETDEV_RX_ERR, &trigger_data->mode)) return; dev_stats = dev_get_stats(trigger_data->net_dev, &temp); @@ -636,7 +650,11 @@ static void netdev_trig_work(struct work_struct *work) (test_bit(TRIGGER_NETDEV_TX, &trigger_data->mode) ? dev_stats->tx_packets : 0) + (test_bit(TRIGGER_NETDEV_RX, &trigger_data->mode) ? - dev_stats->rx_packets : 0); + dev_stats->rx_packets : 0) + + (test_bit(TRIGGER_NETDEV_TX_ERR, &trigger_data->mode) ? + dev_stats->tx_errors : 0) + + (test_bit(TRIGGER_NETDEV_RX_ERR, &trigger_data->mode) ? + dev_stats->rx_errors : 0); if (trigger_data->last_activity != new_activity) { led_stop_software_blink(trigger_data->led_cdev); diff --git a/include/linux/leds.h b/include/linux/leds.h index 6885603f211b..e5968c3ed4ae 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -611,6 +611,8 @@ enum led_trigger_netdev_modes { TRIGGER_NETDEV_FULL_DUPLEX, TRIGGER_NETDEV_TX, TRIGGER_NETDEV_RX, + TRIGGER_NETDEV_TX_ERR, + TRIGGER_NETDEV_RX_ERR, /* Keep last */ __TRIGGER_NETDEV_MAX, -- cgit v1.2.3 From 480a8ad683d7a54e8d38c9c7778fb6b15aac241a Mon Sep 17 00:00:00 2001 From: Haibo Chen Date: Mon, 22 Jul 2024 15:10:58 +0300 Subject: mfd: adp5585: Add Analog Devices ADP5585 core support The ADP5585 is a 10/11 input/output port expander with a built in keypad matrix decoder, programmable logic, reset generator, and PWM generator. This driver supports the chip by modelling it as an MFD device, with two child devices for the GPIO and PWM functions. The driver is derived from an initial implementation from NXP, available in commit 8059835bee19 ("MLK-25917-1 mfd: adp5585: add ADI adp5585 core support") in their BSP kernel tree. It has been extensively rewritten. Signed-off-by: Haibo Chen Signed-off-by: Laurent Pinchart Reviewed-by: Frank Li Link: https://lore.kernel.org/r/20240722121100.2855-3-laurent.pinchart@ideasonboard.com Signed-off-by: Lee Jones --- MAINTAINERS | 2 + drivers/mfd/Kconfig | 12 +++ drivers/mfd/Makefile | 1 + drivers/mfd/adp5585.c | 205 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/mfd/adp5585.h | 126 +++++++++++++++++++++++++++ 5 files changed, 346 insertions(+) create mode 100644 drivers/mfd/adp5585.c create mode 100644 include/linux/mfd/adp5585.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 9c381b4a1db4..af152de0436b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -543,6 +543,8 @@ L: linux-gpio@vger.kernel.org L: linux-pwm@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/*/adi,adp5585*.yaml +F: drivers/mfd/adp5585.c +F: include/linux/mfd/adp5585.h ADP5588 QWERTY KEYPAD AND IO EXPANDER DRIVER (ADP5588/ADP5587) M: Michael Hennerich diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index bc8be2e593b6..f9325bcce1b9 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -20,6 +20,18 @@ config MFD_CS5535 This is the core driver for CS5535/CS5536 MFD functions. This is necessary for using the board's GPIO and MFGPT functionality. +config MFD_ADP5585 + tristate "Analog Devices ADP5585 keypad decoder and I/O expander driver" + select MFD_CORE + select REGMAP_I2C + depends on I2C + depends on OF || COMPILE_TEST + help + Say yes here to add support for the Analog Devices ADP5585 GPIO + expander, PWM and keypad controller. This includes the I2C driver and + the core APIs _only_, you have to select individual components like + the GPIO and PWM functions under the corresponding menus. + config MFD_ALTERA_A10SR bool "Altera Arria10 DevKit System Resource chip" depends on ARCH_INTEL_SOCFPGA && SPI_MASTER=y && OF diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile index 02b651cd7535..2a9f91e81af8 100644 --- a/drivers/mfd/Makefile +++ b/drivers/mfd/Makefile @@ -193,6 +193,7 @@ obj-$(CONFIG_MFD_DB8500_PRCMU) += db8500-prcmu.o obj-$(CONFIG_AB8500_CORE) += ab8500-core.o ab8500-sysctrl.o obj-$(CONFIG_MFD_TIMBERDALE) += timberdale.o obj-$(CONFIG_PMIC_ADP5520) += adp5520.o +obj-$(CONFIG_MFD_ADP5585) += adp5585.o obj-$(CONFIG_MFD_KEMPLD) += kempld-core.o obj-$(CONFIG_MFD_INTEL_QUARK_I2C_GPIO) += intel_quark_i2c_gpio.o obj-$(CONFIG_LPC_SCH) += lpc_sch.o diff --git a/drivers/mfd/adp5585.c b/drivers/mfd/adp5585.c new file mode 100644 index 000000000000..160e0b38106a --- /dev/null +++ b/drivers/mfd/adp5585.c @@ -0,0 +1,205 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Analog Devices ADP5585 I/O expander, PWM controller and keypad controller + * + * Copyright 2022 NXP + * Copyright 2024 Ideas on Board Oy + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static const struct mfd_cell adp5585_devs[] = { + { .name = "adp5585-gpio", }, + { .name = "adp5585-pwm", }, +}; + +static const struct regmap_range adp5585_volatile_ranges[] = { + regmap_reg_range(ADP5585_ID, ADP5585_GPI_STATUS_B), +}; + +static const struct regmap_access_table adp5585_volatile_regs = { + .yes_ranges = adp5585_volatile_ranges, + .n_yes_ranges = ARRAY_SIZE(adp5585_volatile_ranges), +}; + +/* + * Chip variants differ in the default configuration of pull-up and pull-down + * resistors, and therefore have different default register values: + * + * - The -00, -01 and -03 variants (collectively referred to as + * ADP5585_REGMAP_00) have pull-up on all GPIO pins by default. + * - The -02 variant has no default pull-up or pull-down resistors. + * - The -04 variant has default pull-down resistors on all GPIO pins. + */ + +static const u8 adp5585_regmap_defaults_00[ADP5585_MAX_REG + 1] = { + /* 0x00 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + /* 0x08 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + /* 0x10 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + /* 0x18 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + /* 0x20 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + /* 0x28 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + /* 0x30 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + /* 0x38 */ 0x00, 0x00, 0x00, 0x00, 0x00, +}; + +static const u8 adp5585_regmap_defaults_02[ADP5585_MAX_REG + 1] = { + /* 0x00 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + /* 0x08 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + /* 0x10 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, + /* 0x18 */ 0x03, 0x00, 0x03, 0x00, 0x00, 0x00, 0x00, 0x00, + /* 0x20 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + /* 0x28 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + /* 0x30 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + /* 0x38 */ 0x00, 0x00, 0x00, 0x00, 0x00, +}; + +static const u8 adp5585_regmap_defaults_04[ADP5585_MAX_REG + 1] = { + /* 0x00 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + /* 0x08 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + /* 0x10 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x55, + /* 0x18 */ 0x05, 0x55, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, + /* 0x20 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + /* 0x28 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + /* 0x30 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + /* 0x38 */ 0x00, 0x00, 0x00, 0x00, 0x00, +}; + +enum adp5585_regmap_type { + ADP5585_REGMAP_00, + ADP5585_REGMAP_02, + ADP5585_REGMAP_04, +}; + +static const struct regmap_config adp5585_regmap_configs[] = { + [ADP5585_REGMAP_00] = { + .reg_bits = 8, + .val_bits = 8, + .max_register = ADP5585_MAX_REG, + .volatile_table = &adp5585_volatile_regs, + .cache_type = REGCACHE_MAPLE, + .reg_defaults_raw = adp5585_regmap_defaults_00, + .num_reg_defaults_raw = sizeof(adp5585_regmap_defaults_00), + }, + [ADP5585_REGMAP_02] = { + .reg_bits = 8, + .val_bits = 8, + .max_register = ADP5585_MAX_REG, + .volatile_table = &adp5585_volatile_regs, + .cache_type = REGCACHE_MAPLE, + .reg_defaults_raw = adp5585_regmap_defaults_02, + .num_reg_defaults_raw = sizeof(adp5585_regmap_defaults_02), + }, + [ADP5585_REGMAP_04] = { + .reg_bits = 8, + .val_bits = 8, + .max_register = ADP5585_MAX_REG, + .volatile_table = &adp5585_volatile_regs, + .cache_type = REGCACHE_MAPLE, + .reg_defaults_raw = adp5585_regmap_defaults_04, + .num_reg_defaults_raw = sizeof(adp5585_regmap_defaults_04), + }, +}; + +static int adp5585_i2c_probe(struct i2c_client *i2c) +{ + const struct regmap_config *regmap_config; + struct adp5585_dev *adp5585; + unsigned int id; + int ret; + + adp5585 = devm_kzalloc(&i2c->dev, sizeof(*adp5585), GFP_KERNEL); + if (!adp5585) + return -ENOMEM; + + i2c_set_clientdata(i2c, adp5585); + + regmap_config = i2c_get_match_data(i2c); + adp5585->regmap = devm_regmap_init_i2c(i2c, regmap_config); + if (IS_ERR(adp5585->regmap)) + return dev_err_probe(&i2c->dev, PTR_ERR(adp5585->regmap), + "Failed to initialize register map\n"); + + ret = regmap_read(adp5585->regmap, ADP5585_ID, &id); + if (ret) + return dev_err_probe(&i2c->dev, ret, + "Failed to read device ID\n"); + + if ((id & ADP5585_MAN_ID_MASK) != ADP5585_MAN_ID_VALUE) + return dev_err_probe(&i2c->dev, -ENODEV, + "Invalid device ID 0x%02x\n", id); + + ret = devm_mfd_add_devices(&i2c->dev, PLATFORM_DEVID_AUTO, + adp5585_devs, ARRAY_SIZE(adp5585_devs), + NULL, 0, NULL); + if (ret) + return dev_err_probe(&i2c->dev, ret, + "Failed to add child devices\n"); + + return 0; +} + +static int adp5585_suspend(struct device *dev) +{ + struct adp5585_dev *adp5585 = dev_get_drvdata(dev); + + regcache_cache_only(adp5585->regmap, true); + + return 0; +} + +static int adp5585_resume(struct device *dev) +{ + struct adp5585_dev *adp5585 = dev_get_drvdata(dev); + + regcache_cache_only(adp5585->regmap, false); + regcache_mark_dirty(adp5585->regmap); + + return regcache_sync(adp5585->regmap); +} + +static DEFINE_SIMPLE_DEV_PM_OPS(adp5585_pm, adp5585_suspend, adp5585_resume); + +static const struct of_device_id adp5585_of_match[] = { + { + .compatible = "adi,adp5585-00", + .data = &adp5585_regmap_configs[ADP5585_REGMAP_00], + }, { + .compatible = "adi,adp5585-01", + .data = &adp5585_regmap_configs[ADP5585_REGMAP_00], + }, { + .compatible = "adi,adp5585-02", + .data = &adp5585_regmap_configs[ADP5585_REGMAP_02], + }, { + .compatible = "adi,adp5585-03", + .data = &adp5585_regmap_configs[ADP5585_REGMAP_00], + }, { + .compatible = "adi,adp5585-04", + .data = &adp5585_regmap_configs[ADP5585_REGMAP_04], + }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, adp5585_of_match); + +static struct i2c_driver adp5585_i2c_driver = { + .driver = { + .name = "adp5585", + .of_match_table = adp5585_of_match, + .pm = pm_sleep_ptr(&adp5585_pm), + }, + .probe = adp5585_i2c_probe, +}; +module_i2c_driver(adp5585_i2c_driver); + +MODULE_DESCRIPTION("ADP5585 core driver"); +MODULE_AUTHOR("Haibo Chen "); +MODULE_LICENSE("GPL"); diff --git a/include/linux/mfd/adp5585.h b/include/linux/mfd/adp5585.h new file mode 100644 index 000000000000..016033cd68e4 --- /dev/null +++ b/include/linux/mfd/adp5585.h @@ -0,0 +1,126 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Analog Devices ADP5585 I/O expander, PWM controller and keypad controller + * + * Copyright 2022 NXP + * Copyright 2024 Ideas on Board Oy + */ + +#ifndef __MFD_ADP5585_H_ +#define __MFD_ADP5585_H_ + +#include + +#define ADP5585_ID 0x00 +#define ADP5585_MAN_ID_VALUE 0x20 +#define ADP5585_MAN_ID_MASK GENMASK(7, 4) +#define ADP5585_INT_STATUS 0x01 +#define ADP5585_STATUS 0x02 +#define ADP5585_FIFO_1 0x03 +#define ADP5585_FIFO_2 0x04 +#define ADP5585_FIFO_3 0x05 +#define ADP5585_FIFO_4 0x06 +#define ADP5585_FIFO_5 0x07 +#define ADP5585_FIFO_6 0x08 +#define ADP5585_FIFO_7 0x09 +#define ADP5585_FIFO_8 0x0a +#define ADP5585_FIFO_9 0x0b +#define ADP5585_FIFO_10 0x0c +#define ADP5585_FIFO_11 0x0d +#define ADP5585_FIFO_12 0x0e +#define ADP5585_FIFO_13 0x0f +#define ADP5585_FIFO_14 0x10 +#define ADP5585_FIFO_15 0x11 +#define ADP5585_FIFO_16 0x12 +#define ADP5585_GPI_INT_STAT_A 0x13 +#define ADP5585_GPI_INT_STAT_B 0x14 +#define ADP5585_GPI_STATUS_A 0x15 +#define ADP5585_GPI_STATUS_B 0x16 +#define ADP5585_RPULL_CONFIG_A 0x17 +#define ADP5585_RPULL_CONFIG_B 0x18 +#define ADP5585_RPULL_CONFIG_C 0x19 +#define ADP5585_RPULL_CONFIG_D 0x1a +#define ADP5585_Rx_PULL_CFG_PU_300K 0 +#define ADP5585_Rx_PULL_CFG_PD_300K 1 +#define ADP5585_Rx_PULL_CFG_PU_100K 2 +#define ADP5585_Rx_PULL_CFG_DISABLE 3 +#define ADP5585_Rx_PULL_CFG_MASK 3 +#define ADP5585_GPI_INT_LEVEL_A 0x1b +#define ADP5585_GPI_INT_LEVEL_B 0x1c +#define ADP5585_GPI_EVENT_EN_A 0x1d +#define ADP5585_GPI_EVENT_EN_B 0x1e +#define ADP5585_GPI_INTERRUPT_EN_A 0x1f +#define ADP5585_GPI_INTERRUPT_EN_B 0x20 +#define ADP5585_DEBOUNCE_DIS_A 0x21 +#define ADP5585_DEBOUNCE_DIS_B 0x22 +#define ADP5585_GPO_DATA_OUT_A 0x23 +#define ADP5585_GPO_DATA_OUT_B 0x24 +#define ADP5585_GPO_OUT_MODE_A 0x25 +#define ADP5585_GPO_OUT_MODE_B 0x26 +#define ADP5585_GPIO_DIRECTION_A 0x27 +#define ADP5585_GPIO_DIRECTION_B 0x28 +#define ADP5585_RESET1_EVENT_A 0x29 +#define ADP5585_RESET1_EVENT_B 0x2a +#define ADP5585_RESET1_EVENT_C 0x2b +#define ADP5585_RESET2_EVENT_A 0x2c +#define ADP5585_RESET2_EVENT_B 0x2d +#define ADP5585_RESET_CFG 0x2e +#define ADP5585_PWM_OFFT_LOW 0x2f +#define ADP5585_PWM_OFFT_HIGH 0x30 +#define ADP5585_PWM_ONT_LOW 0x31 +#define ADP5585_PWM_ONT_HIGH 0x32 +#define ADP5585_PWM_CFG 0x33 +#define ADP5585_PWM_IN_AND BIT(2) +#define ADP5585_PWM_MODE BIT(1) +#define ADP5585_PWM_EN BIT(0) +#define ADP5585_LOGIC_CFG 0x34 +#define ADP5585_LOGIC_FF_CFG 0x35 +#define ADP5585_LOGIC_INT_EVENT_EN 0x36 +#define ADP5585_POLL_PTIME_CFG 0x37 +#define ADP5585_PIN_CONFIG_A 0x38 +#define ADP5585_PIN_CONFIG_B 0x39 +#define ADP5585_PIN_CONFIG_C 0x3a +#define ADP5585_PULL_SELECT BIT(7) +#define ADP5585_C4_EXTEND_CFG_GPIO11 (0U << 6) +#define ADP5585_C4_EXTEND_CFG_RESET2 (1U << 6) +#define ADP5585_C4_EXTEND_CFG_MASK GENMASK(6, 6) +#define ADP5585_R4_EXTEND_CFG_GPIO5 (0U << 5) +#define ADP5585_R4_EXTEND_CFG_RESET1 (1U << 5) +#define ADP5585_R4_EXTEND_CFG_MASK GENMASK(5, 5) +#define ADP5585_R3_EXTEND_CFG_GPIO4 (0U << 2) +#define ADP5585_R3_EXTEND_CFG_LC (1U << 2) +#define ADP5585_R3_EXTEND_CFG_PWM_OUT (2U << 2) +#define ADP5585_R3_EXTEND_CFG_MASK GENMASK(3, 2) +#define ADP5585_R0_EXTEND_CFG_GPIO1 (0U << 0) +#define ADP5585_R0_EXTEND_CFG_LY (1U << 0) +#define ADP5585_R0_EXTEND_CFG_MASK GENMASK(0, 0) +#define ADP5585_GENERAL_CFG 0x3b +#define ADP5585_OSC_EN BIT(7) +#define ADP5585_OSC_FREQ_50KHZ (0U << 5) +#define ADP5585_OSC_FREQ_100KHZ (1U << 5) +#define ADP5585_OSC_FREQ_200KHZ (2U << 5) +#define ADP5585_OSC_FREQ_500KHZ (3U << 5) +#define ADP5585_OSC_FREQ_MASK GENMASK(6, 5) +#define ADP5585_INT_CFG BIT(1) +#define ADP5585_RST_CFG BIT(0) +#define ADP5585_INT_EN 0x3c + +#define ADP5585_MAX_REG ADP5585_INT_EN + +/* + * Bank 0 covers pins "GPIO 1/R0" to "GPIO 6/R5", numbered 0 to 5 by the + * driver, and bank 1 covers pins "GPIO 7/C0" to "GPIO 11/C4", numbered 6 to + * 10. Some variants of the ADP5585 don't support "GPIO 6/R5". As the driver + * uses identical GPIO numbering for all variants to avoid confusion, GPIO 5 is + * marked as reserved in the device tree for variants that don't support it. + */ +#define ADP5585_BANK(n) ((n) >= 6 ? 1 : 0) +#define ADP5585_BIT(n) ((n) >= 6 ? BIT((n) - 6) : BIT(n)) + +struct regmap; + +struct adp5585_dev { + struct regmap *regmap; +}; + +#endif -- cgit v1.2.3 From bcbfcebda2cbc6a10a347d726e4a4f69e43a864e Mon Sep 17 00:00:00 2001 From: Mohamed Ghanmi Date: Sun, 9 Jun 2024 15:48:49 +0100 Subject: platform/x86: asus-wmi: add support for vivobook fan profiles Add support for vivobook fan profiles wmi call on the ASUS VIVOBOOK to adjust power limits. These fan profiles have a different device id than the ROG series and different order. This reorders the existing modes. As part of keeping the patch clean the throttle_thermal_policy_available boolean stored in the driver struct is removed and throttle_thermal_policy_dev is used in place (as on init it is zeroed). Co-developed-by: Luke D. Jones Signed-off-by: Luke D. Jones Signed-off-by: Mohamed Ghanmi Reviewed-by: Luke D. Jones Link: https://lore.kernel.org/r/20240609144849.2532-2-mohamed.ghanmi@supcom.tn Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede --- drivers/platform/x86/asus-wmi.c | 120 +++++++++++++++++------------ include/linux/platform_data/x86/asus-wmi.h | 1 + 2 files changed, 71 insertions(+), 50 deletions(-) (limited to 'include/linux') diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index cc735931f97b..00669cf678fb 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -97,6 +97,12 @@ module_param(fnlock_default, bool, 0444); #define ASUS_THROTTLE_THERMAL_POLICY_OVERBOOST 1 #define ASUS_THROTTLE_THERMAL_POLICY_SILENT 2 +#define ASUS_THROTTLE_THERMAL_POLICY_DEFAULT_VIVO 0 +#define ASUS_THROTTLE_THERMAL_POLICY_SILENT_VIVO 1 +#define ASUS_THROTTLE_THERMAL_POLICY_OVERBOOST_VIVO 2 + +#define PLATFORM_PROFILE_MAX 2 + #define USB_INTEL_XUSB2PR 0xD0 #define PCI_DEVICE_ID_INTEL_LYNXPOINT_LP_XHCI 0x9c31 @@ -286,8 +292,8 @@ struct asus_wmi { u32 kbd_rgb_dev; bool kbd_rgb_state_available; - bool throttle_thermal_policy_available; u8 throttle_thermal_policy_mode; + u32 throttle_thermal_policy_dev; bool cpu_fan_curve_available; bool gpu_fan_curve_available; @@ -3162,7 +3168,7 @@ static int fan_curve_get_factory_default(struct asus_wmi *asus, u32 fan_dev) int err, fan_idx; u8 mode = 0; - if (asus->throttle_thermal_policy_available) + if (asus->throttle_thermal_policy_dev) mode = asus->throttle_thermal_policy_mode; /* DEVID_PU_FAN_CURVE is switched for OVERBOOST vs SILENT */ if (mode == 2) @@ -3369,7 +3375,7 @@ static ssize_t fan_curve_enable_store(struct device *dev, * For machines with throttle this is the only way to reset fans * to default mode of operation (does not erase curve data). */ - if (asus->throttle_thermal_policy_available) { + if (asus->throttle_thermal_policy_dev) { err = throttle_thermal_policy_write(asus); if (err) return err; @@ -3586,8 +3592,8 @@ static const struct attribute_group asus_fan_curve_attr_group = { __ATTRIBUTE_GROUPS(asus_fan_curve_attr); /* - * Must be initialised after throttle_thermal_policy_check_present() as - * we check the status of throttle_thermal_policy_available during init. + * Must be initialised after throttle_thermal_policy_dev is set as + * we check the status of throttle_thermal_policy_dev during init. */ static int asus_wmi_custom_fan_curve_init(struct asus_wmi *asus) { @@ -3628,38 +3634,13 @@ static int asus_wmi_custom_fan_curve_init(struct asus_wmi *asus) } /* Throttle thermal policy ****************************************************/ - -static int throttle_thermal_policy_check_present(struct asus_wmi *asus) -{ - u32 result; - int err; - - asus->throttle_thermal_policy_available = false; - - err = asus_wmi_get_devstate(asus, - ASUS_WMI_DEVID_THROTTLE_THERMAL_POLICY, - &result); - if (err) { - if (err == -ENODEV) - return 0; - return err; - } - - if (result & ASUS_WMI_DSTS_PRESENCE_BIT) - asus->throttle_thermal_policy_available = true; - - return 0; -} - static int throttle_thermal_policy_write(struct asus_wmi *asus) { - int err; - u8 value; + u8 value = asus->throttle_thermal_policy_mode; u32 retval; + int err; - value = asus->throttle_thermal_policy_mode; - - err = asus_wmi_set_devstate(ASUS_WMI_DEVID_THROTTLE_THERMAL_POLICY, + err = asus_wmi_set_devstate(asus->throttle_thermal_policy_dev, value, &retval); sysfs_notify(&asus->platform_device->dev.kobj, NULL, @@ -3689,7 +3670,7 @@ static int throttle_thermal_policy_write(struct asus_wmi *asus) static int throttle_thermal_policy_set_default(struct asus_wmi *asus) { - if (!asus->throttle_thermal_policy_available) + if (!asus->throttle_thermal_policy_dev) return 0; asus->throttle_thermal_policy_mode = ASUS_THROTTLE_THERMAL_POLICY_DEFAULT; @@ -3701,7 +3682,7 @@ static int throttle_thermal_policy_switch_next(struct asus_wmi *asus) u8 new_mode = asus->throttle_thermal_policy_mode + 1; int err; - if (new_mode > ASUS_THROTTLE_THERMAL_POLICY_SILENT) + if (new_mode > PLATFORM_PROFILE_MAX) new_mode = ASUS_THROTTLE_THERMAL_POLICY_DEFAULT; asus->throttle_thermal_policy_mode = new_mode; @@ -3740,7 +3721,7 @@ static ssize_t throttle_thermal_policy_store(struct device *dev, if (result < 0) return result; - if (new_mode > ASUS_THROTTLE_THERMAL_POLICY_SILENT) + if (new_mode > PLATFORM_PROFILE_MAX) return -EINVAL; asus->throttle_thermal_policy_mode = new_mode; @@ -3757,10 +3738,52 @@ static ssize_t throttle_thermal_policy_store(struct device *dev, return count; } -// Throttle thermal policy: 0 - default, 1 - overboost, 2 - silent +/* + * Throttle thermal policy: 0 - default, 1 - overboost, 2 - silent + */ static DEVICE_ATTR_RW(throttle_thermal_policy); /* Platform profile ***********************************************************/ +static int asus_wmi_platform_profile_to_vivo(struct asus_wmi *asus, int mode) +{ + bool vivo; + + vivo = asus->throttle_thermal_policy_dev == ASUS_WMI_DEVID_THROTTLE_THERMAL_POLICY_VIVO; + + if (vivo) { + switch (mode) { + case ASUS_THROTTLE_THERMAL_POLICY_DEFAULT: + return ASUS_THROTTLE_THERMAL_POLICY_DEFAULT_VIVO; + case ASUS_THROTTLE_THERMAL_POLICY_OVERBOOST: + return ASUS_THROTTLE_THERMAL_POLICY_OVERBOOST_VIVO; + case ASUS_THROTTLE_THERMAL_POLICY_SILENT: + return ASUS_THROTTLE_THERMAL_POLICY_SILENT_VIVO; + } + } + + return mode; +} + +static int asus_wmi_platform_profile_mode_from_vivo(struct asus_wmi *asus, int mode) +{ + bool vivo; + + vivo = asus->throttle_thermal_policy_dev == ASUS_WMI_DEVID_THROTTLE_THERMAL_POLICY_VIVO; + + if (vivo) { + switch (mode) { + case ASUS_THROTTLE_THERMAL_POLICY_DEFAULT_VIVO: + return ASUS_THROTTLE_THERMAL_POLICY_DEFAULT; + case ASUS_THROTTLE_THERMAL_POLICY_OVERBOOST_VIVO: + return ASUS_THROTTLE_THERMAL_POLICY_OVERBOOST; + case ASUS_THROTTLE_THERMAL_POLICY_SILENT_VIVO: + return ASUS_THROTTLE_THERMAL_POLICY_SILENT; + } + } + + return mode; +} + static int asus_wmi_platform_profile_get(struct platform_profile_handler *pprof, enum platform_profile_option *profile) { @@ -3768,10 +3791,9 @@ static int asus_wmi_platform_profile_get(struct platform_profile_handler *pprof, int tp; asus = container_of(pprof, struct asus_wmi, platform_profile_handler); - tp = asus->throttle_thermal_policy_mode; - switch (tp) { + switch (asus_wmi_platform_profile_mode_from_vivo(asus, tp)) { case ASUS_THROTTLE_THERMAL_POLICY_DEFAULT: *profile = PLATFORM_PROFILE_BALANCED; break; @@ -3810,7 +3832,7 @@ static int asus_wmi_platform_profile_set(struct platform_profile_handler *pprof, return -EOPNOTSUPP; } - asus->throttle_thermal_policy_mode = tp; + asus->throttle_thermal_policy_mode = asus_wmi_platform_profile_to_vivo(asus, tp); return throttle_thermal_policy_write(asus); } @@ -3823,7 +3845,7 @@ static int platform_profile_setup(struct asus_wmi *asus) * Not an error if a component platform_profile relies on is unavailable * so early return, skipping the setup of platform_profile. */ - if (!asus->throttle_thermal_policy_available) + if (!asus->throttle_thermal_policy_dev) return 0; dev_info(dev, "Using throttle_thermal_policy for platform_profile support\n"); @@ -4238,7 +4260,7 @@ static void asus_wmi_handle_event_code(int code, struct asus_wmi *asus) if (code == NOTIFY_KBD_FBM || code == NOTIFY_KBD_TTP) { if (asus->fan_boost_mode_available) fan_boost_mode_switch_next(asus); - if (asus->throttle_thermal_policy_available) + if (asus->throttle_thermal_policy_dev) throttle_thermal_policy_switch_next(asus); return; @@ -4410,7 +4432,7 @@ static umode_t asus_sysfs_is_visible(struct kobject *kobj, else if (attr == &dev_attr_fan_boost_mode.attr) ok = asus->fan_boost_mode_available; else if (attr == &dev_attr_throttle_thermal_policy.attr) - ok = asus->throttle_thermal_policy_available; + ok = asus->throttle_thermal_policy_dev != 0; else if (attr == &dev_attr_ppt_pl2_sppt.attr) devid = ASUS_WMI_DEVID_PPT_PL2_SPPT; else if (attr == &dev_attr_ppt_pl1_spl.attr) @@ -4702,16 +4724,15 @@ static int asus_wmi_add(struct platform_device *pdev) else if (asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_TUF_RGB_MODE2)) asus->kbd_rgb_dev = ASUS_WMI_DEVID_TUF_RGB_MODE2; + if (asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_THROTTLE_THERMAL_POLICY)) + asus->throttle_thermal_policy_dev = ASUS_WMI_DEVID_THROTTLE_THERMAL_POLICY; + else if (asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_THROTTLE_THERMAL_POLICY_VIVO)) + asus->throttle_thermal_policy_dev = ASUS_WMI_DEVID_THROTTLE_THERMAL_POLICY_VIVO; + err = fan_boost_mode_check_present(asus); if (err) goto fail_fan_boost_mode; - err = throttle_thermal_policy_check_present(asus); - if (err) - goto fail_throttle_thermal_policy; - else - throttle_thermal_policy_set_default(asus); - err = platform_profile_setup(asus); if (err) goto fail_platform_profile_setup; @@ -4806,7 +4827,6 @@ fail_hwmon: fail_input: asus_wmi_sysfs_exit(asus->platform_device); fail_sysfs: -fail_throttle_thermal_policy: fail_custom_fan_curve: fail_platform_profile_setup: if (asus->platform_profile_support) diff --git a/include/linux/platform_data/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h index 0aeeae1c1943..5e6f407b2def 100644 --- a/include/linux/platform_data/x86/asus-wmi.h +++ b/include/linux/platform_data/x86/asus-wmi.h @@ -68,6 +68,7 @@ #define ASUS_WMI_DEVID_SCREENPAD_LIGHT 0x00050032 #define ASUS_WMI_DEVID_FAN_BOOST_MODE 0x00110018 #define ASUS_WMI_DEVID_THROTTLE_THERMAL_POLICY 0x00120075 +#define ASUS_WMI_DEVID_THROTTLE_THERMAL_POLICY_VIVO 0x00110019 /* Misc */ #define ASUS_WMI_DEVID_PANEL_OD 0x00050019 -- cgit v1.2.3 From 3908ba2e0b2476e2ec13e15967bf6a37e449f2af Mon Sep 17 00:00:00 2001 From: Nick Hu Date: Wed, 17 Jul 2024 11:17:14 +0800 Subject: RISC-V: Enable the IPI before workqueue_online_cpu() Sometimes the hotplug cpu stalls at the arch_cpu_idle() for a while after workqueue_online_cpu(). When cpu stalls at the idle loop, the reschedule IPI is pending. However the enable bit is not enabled yet so the cpu stalls at WFI until watchdog timeout. Therefore enable the IPI before the workqueue_online_cpu() to fix the issue. Fixes: 63c5484e7495 ("workqueue: Add multiple affinity scopes and interface to select them") Signed-off-by: Nick Hu Reviewed-by: Anup Patel Link: https://lore.kernel.org/r/20240717031714.1946036-1-nick.hu@sifive.com Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/sbi-ipi.c | 2 +- include/linux/cpuhotplug.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/arch/riscv/kernel/sbi-ipi.c b/arch/riscv/kernel/sbi-ipi.c index 1026e22955cc..0cc5559c08d8 100644 --- a/arch/riscv/kernel/sbi-ipi.c +++ b/arch/riscv/kernel/sbi-ipi.c @@ -71,7 +71,7 @@ void __init sbi_ipi_init(void) * the masking/unmasking of virtual IPIs is done * via generic IPI-Mux */ - cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, + cpuhp_setup_state(CPUHP_AP_IRQ_RISCV_SBI_IPI_STARTING, "irqchip/sbi-ipi:starting", sbi_ipi_starting_cpu, NULL); diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 51ba681b915a..e30d93b807d5 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -148,6 +148,7 @@ enum cpuhp_state { CPUHP_AP_IRQ_LOONGARCH_STARTING, CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING, CPUHP_AP_IRQ_RISCV_IMSIC_STARTING, + CPUHP_AP_IRQ_RISCV_SBI_IPI_STARTING, CPUHP_AP_ARM_MVEBU_COHERENCY, CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING, CPUHP_AP_PERF_X86_STARTING, -- cgit v1.2.3 From b40824500eaa77668026b6d1ade6924901a680f9 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Tue, 30 Jul 2024 14:38:07 +0900 Subject: ata: libata: Remove ata_noop_qc_prep() The function ata_noop_qc_prep(), as its name implies, does nothing and simply returns AC_ERR_OK. For drivers that do not need any special preparations of queued commands, we can avoid having to define struct ata_port qc_prep operation by simply testing if that operation is defined or not in ata_qc_issue(). Make this change and remove ata_noop_qc_prep(). Signed-off-by: Damien Le Moal Reviewed-by: John Garry Reviewed-by: Sergey Shtylyov --- drivers/ata/libata-core.c | 18 +++++++----------- drivers/ata/libata-sff.c | 1 - drivers/ata/pata_ep93xx.c | 2 -- drivers/ata/pata_icside.c | 2 -- drivers/ata/pata_mpc52xx.c | 1 - drivers/ata/pata_octeon_cf.c | 1 - drivers/scsi/libsas/sas_ata.c | 1 - include/linux/libata.h | 1 - 8 files changed, 7 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index fc9fcfda42b8..b4fdb78579c8 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4696,12 +4696,6 @@ int ata_std_qc_defer(struct ata_queued_cmd *qc) } EXPORT_SYMBOL_GPL(ata_std_qc_defer); -enum ata_completion_errors ata_noop_qc_prep(struct ata_queued_cmd *qc) -{ - return AC_ERR_OK; -} -EXPORT_SYMBOL_GPL(ata_noop_qc_prep); - /** * ata_sg_init - Associate command with scatter-gather table. * @qc: Command to be associated @@ -5088,10 +5082,13 @@ void ata_qc_issue(struct ata_queued_cmd *qc) return; } - trace_ata_qc_prep(qc); - qc->err_mask |= ap->ops->qc_prep(qc); - if (unlikely(qc->err_mask)) - goto err; + if (ap->ops->qc_prep) { + trace_ata_qc_prep(qc); + qc->err_mask |= ap->ops->qc_prep(qc); + if (unlikely(qc->err_mask)) + goto err; + } + trace_ata_qc_issue(qc); qc->err_mask |= ap->ops->qc_issue(qc); if (unlikely(qc->err_mask)) @@ -6724,7 +6721,6 @@ static void ata_dummy_error_handler(struct ata_port *ap) } struct ata_port_operations ata_dummy_port_ops = { - .qc_prep = ata_noop_qc_prep, .qc_issue = ata_dummy_qc_issue, .error_handler = ata_dummy_error_handler, .sched_eh = ata_std_sched_eh, diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index 06868ec5b1fd..67f277e1c3bf 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -26,7 +26,6 @@ static struct workqueue_struct *ata_sff_wq; const struct ata_port_operations ata_sff_port_ops = { .inherits = &ata_base_port_ops, - .qc_prep = ata_noop_qc_prep, .qc_issue = ata_sff_qc_issue, .qc_fill_rtf = ata_sff_qc_fill_rtf, diff --git a/drivers/ata/pata_ep93xx.c b/drivers/ata/pata_ep93xx.c index c84a20892f1b..a34e56a9d535 100644 --- a/drivers/ata/pata_ep93xx.c +++ b/drivers/ata/pata_ep93xx.c @@ -884,8 +884,6 @@ static const struct scsi_host_template ep93xx_pata_sht = { static struct ata_port_operations ep93xx_pata_port_ops = { .inherits = &ata_bmdma_port_ops, - .qc_prep = ata_noop_qc_prep, - .softreset = ep93xx_pata_softreset, .hardreset = ATA_OP_NULL, diff --git a/drivers/ata/pata_icside.c b/drivers/ata/pata_icside.c index 9cfb064782c3..61d8760f09d9 100644 --- a/drivers/ata/pata_icside.c +++ b/drivers/ata/pata_icside.c @@ -328,8 +328,6 @@ static void pata_icside_postreset(struct ata_link *link, unsigned int *classes) static struct ata_port_operations pata_icside_port_ops = { .inherits = &ata_bmdma_port_ops, - /* no need to build any PRD tables for DMA */ - .qc_prep = ata_noop_qc_prep, .sff_data_xfer = ata_sff_data_xfer32, .bmdma_setup = pata_icside_bmdma_setup, .bmdma_start = pata_icside_bmdma_start, diff --git a/drivers/ata/pata_mpc52xx.c b/drivers/ata/pata_mpc52xx.c index 6c317a461a1f..3f9258677915 100644 --- a/drivers/ata/pata_mpc52xx.c +++ b/drivers/ata/pata_mpc52xx.c @@ -620,7 +620,6 @@ static struct ata_port_operations mpc52xx_ata_port_ops = { .bmdma_start = mpc52xx_bmdma_start, .bmdma_stop = mpc52xx_bmdma_stop, .bmdma_status = mpc52xx_bmdma_status, - .qc_prep = ata_noop_qc_prep, }; static int mpc52xx_ata_init_one(struct device *dev, diff --git a/drivers/ata/pata_octeon_cf.c b/drivers/ata/pata_octeon_cf.c index 2884acfc4863..0bb9607e7348 100644 --- a/drivers/ata/pata_octeon_cf.c +++ b/drivers/ata/pata_octeon_cf.c @@ -789,7 +789,6 @@ static unsigned int octeon_cf_qc_issue(struct ata_queued_cmd *qc) static struct ata_port_operations octeon_cf_ops = { .inherits = &ata_sff_port_ops, .check_atapi_dma = octeon_cf_check_atapi_dma, - .qc_prep = ata_noop_qc_prep, .qc_issue = octeon_cf_qc_issue, .sff_dev_select = octeon_cf_dev_select, .sff_irq_on = octeon_cf_ata_port_noaction, diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c index 88714b7b0dba..7b4e7a61965a 100644 --- a/drivers/scsi/libsas/sas_ata.c +++ b/drivers/scsi/libsas/sas_ata.c @@ -564,7 +564,6 @@ static struct ata_port_operations sas_sata_ops = { .error_handler = ata_std_error_handler, .post_internal_cmd = sas_ata_post_internal, .qc_defer = ata_std_qc_defer, - .qc_prep = ata_noop_qc_prep, .qc_issue = sas_ata_qc_issue, .qc_fill_rtf = sas_ata_qc_fill_rtf, .set_dmamode = sas_ata_set_dmamode, diff --git a/include/linux/libata.h b/include/linux/libata.h index d598ef690e50..d5446e18d9df 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1168,7 +1168,6 @@ extern int ata_xfer_mode2shift(u8 xfer_mode); extern const char *ata_mode_string(unsigned int xfer_mask); extern unsigned int ata_id_xfermask(const u16 *id); extern int ata_std_qc_defer(struct ata_queued_cmd *qc); -extern enum ata_completion_errors ata_noop_qc_prep(struct ata_queued_cmd *qc); extern void ata_sg_init(struct ata_queued_cmd *qc, struct scatterlist *sg, unsigned int n_elem); extern unsigned int ata_dev_classify(const struct ata_taskfile *tf); -- cgit v1.2.3 From bf1807c6ee1f66608c7835f6f9d9139c9c477942 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 1 Aug 2024 18:04:22 +0900 Subject: ata: libata: Print device quirks only once In ata_dev_print_quirks(), return early if ata_dev_print_info() returns false or if we already printed quirk information. This is to avoid printing a device quirks multiple times (that is, each time ata_dev_revalidate() is called). To remember if ata_dev_print_quirks() was already executed, define the EH context flag ATA_EHI_DID_PRINT_QUIRKS and set this flag in ata_dev_print_quirks(). Reported-by: Geert Uytterhoeven Fixes: 58157d607aec ("ata: libata: Print quirks applied to devices") Signed-off-by: Damien Le Moal Tested-by: Geert Uytterhoeven --- drivers/ata/libata-core.c | 8 +++++++- include/linux/libata.h | 1 + 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index b4fdb78579c8..e4023fc288ac 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -160,7 +160,7 @@ MODULE_DESCRIPTION("Library module for ATA devices"); MODULE_LICENSE("GPL"); MODULE_VERSION(DRV_VERSION); -static inline bool ata_dev_print_info(struct ata_device *dev) +static inline bool ata_dev_print_info(const struct ata_device *dev) { struct ata_eh_context *ehc = &dev->link->eh_context; @@ -4025,10 +4025,16 @@ static void ata_dev_print_quirks(const struct ata_device *dev, const char *model, const char *rev, unsigned int quirks) { + struct ata_eh_context *ehc = &dev->link->eh_context; int n = 0, i; size_t sz; char *str; + if (!ata_dev_print_info(dev) || ehc->i.flags & ATA_EHI_DID_PRINT_QUIRKS) + return; + + ehc->i.flags |= ATA_EHI_DID_PRINT_QUIRKS; + if (!quirks) return; diff --git a/include/linux/libata.h b/include/linux/libata.h index d5446e18d9df..0279c0a6302f 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -378,6 +378,7 @@ enum { ATA_EHI_PRINTINFO = (1 << 18), /* print configuration info */ ATA_EHI_SETMODE = (1 << 19), /* configure transfer mode */ ATA_EHI_POST_SETMODE = (1 << 20), /* revalidating after setmode */ + ATA_EHI_DID_PRINT_QUIRKS = (1 << 21), /* already printed quirks info */ ATA_EHI_DID_RESET = ATA_EHI_DID_SOFTRESET | ATA_EHI_DID_HARDRESET, -- cgit v1.2.3 From e6ab45005772014ce49a693a63f928203c0cbbb0 Mon Sep 17 00:00:00 2001 From: Luigi Leonardi Date: Tue, 30 Jul 2024 21:43:07 +0200 Subject: vsock/virtio: add SIOCOUTQ support for all virtio based transports Introduce support for virtio_transport_unsent_bytes ioctl for virtio_transport, vhost_vsock and vsock_loopback. For all transports the unsent bytes counter is incremented in virtio_transport_get_credit. In virtio_transport (G2H) and in vhost-vsock (H2G) the counter is decremented when the skbuff is consumed. In vsock_loopback the same skbuff is passed from the transmitter to the receiver, so the counter is decremented before queuing the skbuff to the receiver. Signed-off-by: Luigi Leonardi Reviewed-by: Stefano Garzarella Signed-off-by: David S. Miller --- drivers/vhost/vsock.c | 4 +++- include/linux/virtio_vsock.h | 6 ++++++ net/vmw_vsock/virtio_transport.c | 4 +++- net/vmw_vsock/virtio_transport_common.c | 35 +++++++++++++++++++++++++++++++++ net/vmw_vsock/vsock_loopback.c | 6 ++++++ 5 files changed, 53 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index bf664ec9341b..802153e23073 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -244,7 +244,7 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, restart_tx = true; } - consume_skb(skb); + virtio_transport_consume_skb_sent(skb, true); } } while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len))); if (added) @@ -451,6 +451,8 @@ static struct virtio_transport vhost_transport = { .notify_buffer_size = virtio_transport_notify_buffer_size, .notify_set_rcvlowat = virtio_transport_notify_set_rcvlowat, + .unsent_bytes = virtio_transport_unsent_bytes, + .read_skb = virtio_transport_read_skb, }, diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index c82089dee0c8..0387d64e2c66 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -133,6 +133,7 @@ struct virtio_vsock_sock { u32 tx_cnt; u32 peer_fwd_cnt; u32 peer_buf_alloc; + size_t bytes_unsent; /* Protected by rx_lock */ u32 fwd_cnt; @@ -193,6 +194,11 @@ s64 virtio_transport_stream_has_data(struct vsock_sock *vsk); s64 virtio_transport_stream_has_space(struct vsock_sock *vsk); u32 virtio_transport_seqpacket_has_data(struct vsock_sock *vsk); +ssize_t virtio_transport_unsent_bytes(struct vsock_sock *vsk); + +void virtio_transport_consume_skb_sent(struct sk_buff *skb, + bool consume); + int virtio_transport_do_socket_init(struct vsock_sock *vsk, struct vsock_sock *psk); int diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 64a07acfef12..e0160da4ef43 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -311,7 +311,7 @@ static void virtio_transport_tx_work(struct work_struct *work) virtqueue_disable_cb(vq); while ((skb = virtqueue_get_buf(vq, &len)) != NULL) { - consume_skb(skb); + virtio_transport_consume_skb_sent(skb, true); added = true; } } while (!virtqueue_enable_cb(vq)); @@ -540,6 +540,8 @@ static struct virtio_transport virtio_transport = { .notify_buffer_size = virtio_transport_notify_buffer_size, .notify_set_rcvlowat = virtio_transport_notify_set_rcvlowat, + .unsent_bytes = virtio_transport_unsent_bytes, + .read_skb = virtio_transport_read_skb, }, diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 16ff976a86e3..884ee128851e 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -463,6 +463,26 @@ void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct sk_buff * } EXPORT_SYMBOL_GPL(virtio_transport_inc_tx_pkt); +void virtio_transport_consume_skb_sent(struct sk_buff *skb, bool consume) +{ + struct sock *s = skb->sk; + + if (s && skb->len) { + struct vsock_sock *vs = vsock_sk(s); + struct virtio_vsock_sock *vvs; + + vvs = vs->trans; + + spin_lock_bh(&vvs->tx_lock); + vvs->bytes_unsent -= skb->len; + spin_unlock_bh(&vvs->tx_lock); + } + + if (consume) + consume_skb(skb); +} +EXPORT_SYMBOL_GPL(virtio_transport_consume_skb_sent); + u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 credit) { u32 ret; @@ -475,6 +495,7 @@ u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 credit) if (ret > credit) ret = credit; vvs->tx_cnt += ret; + vvs->bytes_unsent += ret; spin_unlock_bh(&vvs->tx_lock); return ret; @@ -488,6 +509,7 @@ void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit) spin_lock_bh(&vvs->tx_lock); vvs->tx_cnt -= credit; + vvs->bytes_unsent -= credit; spin_unlock_bh(&vvs->tx_lock); } EXPORT_SYMBOL_GPL(virtio_transport_put_credit); @@ -1090,6 +1112,19 @@ void virtio_transport_destruct(struct vsock_sock *vsk) } EXPORT_SYMBOL_GPL(virtio_transport_destruct); +ssize_t virtio_transport_unsent_bytes(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + size_t ret; + + spin_lock_bh(&vvs->tx_lock); + ret = vvs->bytes_unsent; + spin_unlock_bh(&vvs->tx_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(virtio_transport_unsent_bytes); + static int virtio_transport_reset(struct vsock_sock *vsk, struct sk_buff *skb) { diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c index 6dea6119f5b2..6e78927a598e 100644 --- a/net/vmw_vsock/vsock_loopback.c +++ b/net/vmw_vsock/vsock_loopback.c @@ -98,6 +98,8 @@ static struct virtio_transport loopback_transport = { .notify_buffer_size = virtio_transport_notify_buffer_size, .notify_set_rcvlowat = virtio_transport_notify_set_rcvlowat, + .unsent_bytes = virtio_transport_unsent_bytes, + .read_skb = virtio_transport_read_skb, }, @@ -123,6 +125,10 @@ static void vsock_loopback_work(struct work_struct *work) spin_unlock_bh(&vsock->pkt_queue.lock); while ((skb = __skb_dequeue(&pkts))) { + /* Decrement the bytes_unsent counter without deallocating skb + * It is freed by the receiver. + */ + virtio_transport_consume_skb_sent(skb, false); virtio_transport_deliver_tap_pkt(skb); virtio_transport_recv_pkt(&loopback_transport, skb); } -- cgit v1.2.3 From 79bd233010859463e46a0a4b3926eaaba25a6110 Mon Sep 17 00:00:00 2001 From: Ben Gainey Date: Tue, 30 Jul 2024 09:44:14 +0100 Subject: perf: Rename perf_event_context.nr_pending to nr_no_switch_fast. nr_pending counts the number of events in the context that either pending_sigtrap or pending_work, but it is used to prevent taking the fast path in perf_event_context_sched_out. Renamed to reflect what it is used for, rather than what it counts. This change allows using the field to track other event properties that also require skipping the fast path without possible confusion over the name. Signed-off-by: Ben Gainey Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20240730084417.7693-2-ben.gainey@arm.com --- include/linux/perf_event.h | 5 +++-- kernel/events/core.c | 12 ++++++------ 2 files changed, 9 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 6bb0c21d6335..655f66b18418 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -966,12 +966,13 @@ struct perf_event_context { struct rcu_head rcu_head; /* - * Sum (event->pending_work + event->pending_work) + * The count of events for which using the switch-out fast path + * should be avoided. * * The SIGTRAP is targeted at ctx->task, as such it won't do changing * that until the signal is delivered. */ - local_t nr_pending; + local_t nr_no_switch_fast; }; struct perf_cpu_pmu_context { diff --git a/kernel/events/core.c b/kernel/events/core.c index aa3450bdc227..e6cc354a3cee 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3516,9 +3516,9 @@ perf_event_context_sched_out(struct task_struct *task, struct task_struct *next) perf_ctx_disable(ctx, false); - /* PMIs are disabled; ctx->nr_pending is stable. */ - if (local_read(&ctx->nr_pending) || - local_read(&next_ctx->nr_pending)) { + /* PMIs are disabled; ctx->nr_no_switch_fast is stable. */ + if (local_read(&ctx->nr_no_switch_fast) || + local_read(&next_ctx->nr_no_switch_fast)) { /* * Must not swap out ctx when there's pending * events that rely on the ctx->task relation. @@ -5204,7 +5204,7 @@ static void perf_pending_task_sync(struct perf_event *event) */ if (task_work_cancel(current, head)) { event->pending_work = 0; - local_dec(&event->ctx->nr_pending); + local_dec(&event->ctx->nr_no_switch_fast); return; } @@ -6868,7 +6868,7 @@ static void perf_pending_task(struct callback_head *head) if (event->pending_work) { event->pending_work = 0; perf_sigtrap(event); - local_dec(&event->ctx->nr_pending); + local_dec(&event->ctx->nr_no_switch_fast); rcuwait_wake_up(&event->pending_work_wait); } rcu_read_unlock(); @@ -9740,7 +9740,7 @@ static int __perf_event_overflow(struct perf_event *event, if (!event->pending_work && !task_work_add(current, &event->pending_task, notify_mode)) { event->pending_work = pending_id; - local_inc(&event->ctx->nr_pending); + local_inc(&event->ctx->nr_no_switch_fast); event->pending_addr = 0; if (valid_sample && (data->sample_flags & PERF_SAMPLE_ADDR)) -- cgit v1.2.3 From 7e8b255650fcfa1d05a57e4093d8405e6d8dd488 Mon Sep 17 00:00:00 2001 From: Ben Gainey Date: Tue, 30 Jul 2024 09:44:15 +0100 Subject: perf: Support PERF_SAMPLE_READ with inherit This change allows events to use PERF_SAMPLE_READ with inherit so long as PERF_SAMPLE_TID is also set. This enables sample based profiling of a group of counters over a hierarchy of processes or threads. This is useful, for example, for collecting per-thread counters/metrics, event based sampling of multiple counters as a unit, access to the enabled and running time when using multiplexing and so on. Prior to this, users were restricted to either collecting aggregate statistics for a multi-threaded/-process application (e.g. with "perf stat"), or to sample individual threads, or to profile the entire system (which requires root or CAP_PERFMON, and may produce much more data than is required). Theoretically a tool could poll for or otherwise monitor thread/process creation and construct whatever events the user is interested in using perf_event_open, for each new thread or process, but this is racy, can lead to file-descriptor exhaustion, and ultimately just replicates the behaviour of inherit, but in userspace. This configuration differs from inherit without PERF_SAMPLE_READ in that the accumulated event count, and consequently any sample (such as if triggered by overflow of sample_period) will be on a per-thread rather than on an aggregate basis. The meaning of read_format::value field of both PERF_RECORD_READ and PERF_RECORD_SAMPLE is changed such that if the sampled event uses this new configuration then the values reported will be per-thread rather than the global aggregate value. This is a change from the existing semantics of read_format (where PERF_SAMPLE_READ is used without inherit), but it is necessary to expose the per-thread counter values, and it avoids reinventing a separate "read_format_thread" field that otherwise replicates the same behaviour. This change should not break existing tools, since this configuration was not previously valid and was rejected by the kernel. Tools that opt into this new mode will need to account for this when calculating the counter delta for a given sample. Tools that wish to have both the per-thread and aggregate value can perform the global aggregation themselves from the per-thread values. The change to read_format::value does not affect existing valid perf_event_attr configurations, nor does it change the behaviour of calls to "read" on an event descriptor. Both continue to report the aggregate value for the entire thread/process hierarchy. The difference between the results reported by "read" and PERF_RECORD_SAMPLE in this new configuration is justified on the basis that it is not (easily) possible for "read" to target a specific thread (the caller only has the fd for the original parent event). Signed-off-by: Ben Gainey Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20240730084417.7693-3-ben.gainey@arm.com --- include/linux/perf_event.h | 3 +++ kernel/events/core.c | 55 ++++++++++++++++++++++++++++++++++------------ 2 files changed, 44 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 655f66b18418..701549967c18 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -969,6 +969,9 @@ struct perf_event_context { * The count of events for which using the switch-out fast path * should be avoided. * + * Sum (event->pending_work + events with + * (attr->inherit && (attr->sample_type & PERF_SAMPLE_READ))) + * * The SIGTRAP is targeted at ctx->task, as such it won't do changing * that until the signal is delivered. */ diff --git a/kernel/events/core.c b/kernel/events/core.c index e6cc354a3cee..c01a32687dad 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1767,6 +1767,14 @@ perf_event_groups_next(struct perf_event *event, struct pmu *pmu) event = rb_entry_safe(rb_next(&event->group_node), \ typeof(*event), group_node)) +/* + * Does the event attribute request inherit with PERF_SAMPLE_READ + */ +static inline bool has_inherit_and_sample_read(struct perf_event_attr *attr) +{ + return attr->inherit && (attr->sample_type & PERF_SAMPLE_READ); +} + /* * Add an event from the lists for its context. * Must be called with ctx->mutex and ctx->lock held. @@ -1797,6 +1805,8 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx) ctx->nr_user++; if (event->attr.inherit_stat) ctx->nr_stat++; + if (has_inherit_and_sample_read(&event->attr)) + local_inc(&ctx->nr_no_switch_fast); if (event->state > PERF_EVENT_STATE_OFF) perf_cgroup_event_enable(event, ctx); @@ -2021,6 +2031,8 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx) ctx->nr_user--; if (event->attr.inherit_stat) ctx->nr_stat--; + if (has_inherit_and_sample_read(&event->attr)) + local_dec(&ctx->nr_no_switch_fast); list_del_rcu(&event->event_entry); @@ -3522,6 +3534,11 @@ perf_event_context_sched_out(struct task_struct *task, struct task_struct *next) /* * Must not swap out ctx when there's pending * events that rely on the ctx->task relation. + * + * Likewise, when a context contains inherit + + * SAMPLE_READ events they should be switched + * out using the slow path so that they are + * treated as if they were distinct contexts. */ raw_spin_unlock(&next_ctx->lock); rcu_read_unlock(); @@ -4538,8 +4555,11 @@ unlock: raw_spin_unlock(&ctx->lock); } -static inline u64 perf_event_count(struct perf_event *event) +static inline u64 perf_event_count(struct perf_event *event, bool self) { + if (self) + return local64_read(&event->count); + return local64_read(&event->count) + atomic64_read(&event->child_count); } @@ -5498,7 +5518,7 @@ static u64 __perf_event_read_value(struct perf_event *event, u64 *enabled, u64 * mutex_lock(&event->child_mutex); (void)perf_event_read(event, false); - total += perf_event_count(event); + total += perf_event_count(event, false); *enabled += event->total_time_enabled + atomic64_read(&event->child_total_time_enabled); @@ -5507,7 +5527,7 @@ static u64 __perf_event_read_value(struct perf_event *event, u64 *enabled, u64 * list_for_each_entry(child, &event->child_list, child_list) { (void)perf_event_read(child, false); - total += perf_event_count(child); + total += perf_event_count(child, false); *enabled += child->total_time_enabled; *running += child->total_time_running; } @@ -5589,14 +5609,14 @@ static int __perf_read_group_add(struct perf_event *leader, /* * Write {count,id} tuples for every sibling. */ - values[n++] += perf_event_count(leader); + values[n++] += perf_event_count(leader, false); if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(leader); if (read_format & PERF_FORMAT_LOST) values[n++] = atomic64_read(&leader->lost_samples); for_each_sibling_event(sub, leader) { - values[n++] += perf_event_count(sub); + values[n++] += perf_event_count(sub, false); if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(sub); if (read_format & PERF_FORMAT_LOST) @@ -6176,7 +6196,7 @@ void perf_event_update_userpage(struct perf_event *event) ++userpg->lock; barrier(); userpg->index = perf_event_index(event); - userpg->offset = perf_event_count(event); + userpg->offset = perf_event_count(event, false); if (userpg->index) userpg->offset -= local64_read(&event->hw.prev_count); @@ -7250,7 +7270,7 @@ static void perf_output_read_one(struct perf_output_handle *handle, u64 values[5]; int n = 0; - values[n++] = perf_event_count(event); + values[n++] = perf_event_count(event, has_inherit_and_sample_read(&event->attr)); if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) { values[n++] = enabled + atomic64_read(&event->child_total_time_enabled); @@ -7268,14 +7288,15 @@ static void perf_output_read_one(struct perf_output_handle *handle, } static void perf_output_read_group(struct perf_output_handle *handle, - struct perf_event *event, - u64 enabled, u64 running) + struct perf_event *event, + u64 enabled, u64 running) { struct perf_event *leader = event->group_leader, *sub; u64 read_format = event->attr.read_format; unsigned long flags; u64 values[6]; int n = 0; + bool self = has_inherit_and_sample_read(&event->attr); /* * Disabling interrupts avoids all counter scheduling @@ -7295,7 +7316,7 @@ static void perf_output_read_group(struct perf_output_handle *handle, (leader->state == PERF_EVENT_STATE_ACTIVE)) leader->pmu->read(leader); - values[n++] = perf_event_count(leader); + values[n++] = perf_event_count(leader, self); if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(leader); if (read_format & PERF_FORMAT_LOST) @@ -7310,7 +7331,7 @@ static void perf_output_read_group(struct perf_output_handle *handle, (sub->state == PERF_EVENT_STATE_ACTIVE)) sub->pmu->read(sub); - values[n++] = perf_event_count(sub); + values[n++] = perf_event_count(sub, self); if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(sub); if (read_format & PERF_FORMAT_LOST) @@ -7331,6 +7352,10 @@ static void perf_output_read_group(struct perf_output_handle *handle, * The problem is that its both hard and excessively expensive to iterate the * child list, not to mention that its impossible to IPI the children running * on another CPU, from interrupt/NMI context. + * + * Instead the combination of PERF_SAMPLE_READ and inherit will track per-thread + * counts rather than attempting to accumulate some value across all children on + * all cores. */ static void perf_output_read(struct perf_output_handle *handle, struct perf_event *event) @@ -12057,10 +12082,12 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, local64_set(&hwc->period_left, hwc->sample_period); /* - * We currently do not support PERF_SAMPLE_READ on inherited events. + * We do not support PERF_SAMPLE_READ on inherited events unless + * PERF_SAMPLE_TID is also selected, which allows inherited events to + * collect per-thread samples. * See perf_output_read(). */ - if (attr->inherit && (attr->sample_type & PERF_SAMPLE_READ)) + if (has_inherit_and_sample_read(attr) && !(attr->sample_type & PERF_SAMPLE_TID)) goto err_ns; if (!has_branch_stack(event)) @@ -13084,7 +13111,7 @@ static void sync_child_event(struct perf_event *child_event) perf_event_read_event(child_event, task); } - child_val = perf_event_count(child_event); + child_val = perf_event_count(child_event, false); /* * Add back the child's count to the parent's count: -- cgit v1.2.3 From cfa7f3d2c526c224a6271cc78a4a27a0de06f4f0 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 29 Jul 2024 10:52:23 -0700 Subject: perf,x86: avoid missing caller address in stack traces captured in uprobe When tracing user functions with uprobe functionality, it's common to install the probe (e.g., a BPF program) at the first instruction of the function. This is often going to be `push %rbp` instruction in function preamble, which means that within that function frame pointer hasn't been established yet. This leads to consistently missing an actual caller of the traced function, because perf_callchain_user() only records current IP (capturing traced function) and then following frame pointer chain (which would be caller's frame, containing the address of caller's caller). So when we have target_1 -> target_2 -> target_3 call chain and we are tracing an entry to target_3, captured stack trace will report target_1 -> target_3 call chain, which is wrong and confusing. This patch proposes a x86-64-specific heuristic to detect `push %rbp` (`push %ebp` on 32-bit architecture) instruction being traced. Given entire kernel implementation of user space stack trace capturing works under assumption that user space code was compiled with frame pointer register (%rbp/%ebp) preservation, it seems pretty reasonable to use this instruction as a strong indicator that this is the entry to the function. In that case, return address is still pointed to by %rsp/%esp, so we fetch it and add to stack trace before proceeding to unwind the rest using frame pointer-based logic. We also check for `endbr64` (for 64-bit modes) as another common pattern for function entry, as suggested by Josh Poimboeuf. Even if we get this wrong sometimes for uprobes attached not at the function entry, it's OK because stack trace will still be overall meaningful, just with one extra bogus entry. If we don't detect this, we end up with guaranteed to be missing caller function entry in the stack trace, which is worse overall. Signed-off-by: Andrii Nakryiko Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20240729175223.23914-1-andrii@kernel.org --- arch/x86/events/core.c | 63 +++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/uprobes.h | 2 ++ kernel/events/uprobes.c | 2 ++ 3 files changed, 67 insertions(+) (limited to 'include/linux') diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 12f2a0c14d33..e6d133dda70f 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -41,6 +41,8 @@ #include #include #include +#include +#include #include "perf_event.h" @@ -2814,6 +2816,46 @@ static unsigned long get_segment_base(unsigned int segment) return get_desc_base(desc); } +#ifdef CONFIG_UPROBES +/* + * Heuristic-based check if uprobe is installed at the function entry. + * + * Under assumption of user code being compiled with frame pointers, + * `push %rbp/%ebp` is a good indicator that we indeed are. + * + * Similarly, `endbr64` (assuming 64-bit mode) is also a common pattern. + * If we get this wrong, captured stack trace might have one extra bogus + * entry, but the rest of stack trace will still be meaningful. + */ +static bool is_uprobe_at_func_entry(struct pt_regs *regs) +{ + struct arch_uprobe *auprobe; + + if (!current->utask) + return false; + + auprobe = current->utask->auprobe; + if (!auprobe) + return false; + + /* push %rbp/%ebp */ + if (auprobe->insn[0] == 0x55) + return true; + + /* endbr64 (64-bit only) */ + if (user_64bit_mode(regs) && is_endbr(*(u32 *)auprobe->insn)) + return true; + + return false; +} + +#else +static bool is_uprobe_at_func_entry(struct pt_regs *regs) +{ + return false; +} +#endif /* CONFIG_UPROBES */ + #ifdef CONFIG_IA32_EMULATION #include @@ -2825,6 +2867,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent unsigned long ss_base, cs_base; struct stack_frame_ia32 frame; const struct stack_frame_ia32 __user *fp; + u32 ret_addr; if (user_64bit_mode(regs)) return 0; @@ -2834,6 +2877,12 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent fp = compat_ptr(ss_base + regs->bp); pagefault_disable(); + + /* see perf_callchain_user() below for why we do this */ + if (is_uprobe_at_func_entry(regs) && + !get_user(ret_addr, (const u32 __user *)regs->sp)) + perf_callchain_store(entry, ret_addr); + while (entry->nr < entry->max_stack) { if (!valid_user_frame(fp, sizeof(frame))) break; @@ -2862,6 +2911,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs { struct stack_frame frame; const struct stack_frame __user *fp; + unsigned long ret_addr; if (perf_guest_state()) { /* TODO: We don't support guest os callchain now */ @@ -2885,6 +2935,19 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs return; pagefault_disable(); + + /* + * If we are called from uprobe handler, and we are indeed at the very + * entry to user function (which is normally a `push %rbp` instruction, + * under assumption of application being compiled with frame pointers), + * we should read return address from *regs->sp before proceeding + * to follow frame pointers, otherwise we'll skip immediate caller + * as %rbp is not yet setup. + */ + if (is_uprobe_at_func_entry(regs) && + !get_user(ret_addr, (const unsigned long __user *)regs->sp)) + perf_callchain_store(entry, ret_addr); + while (entry->nr < entry->max_stack) { if (!valid_user_frame(fp, sizeof(frame))) break; diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index b503fafb7fb3..a270a5892ab4 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -76,6 +76,8 @@ struct uprobe_task { struct uprobe *active_uprobe; unsigned long xol_vaddr; + struct arch_uprobe *auprobe; + struct return_instance *return_instances; unsigned int depth; }; diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 73cc47708679..f69ecd39b1a8 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -2082,6 +2082,7 @@ static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs) bool need_prep = false; /* prepare return uprobe, when needed */ down_read(&uprobe->register_rwsem); + current->utask->auprobe = &uprobe->arch; for (uc = uprobe->consumers; uc; uc = uc->next) { int rc = 0; @@ -2096,6 +2097,7 @@ static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs) remove &= rc; } + current->utask->auprobe = NULL; if (need_prep && !remove) prepare_uretprobe(uprobe, regs); /* put bp at return */ -- cgit v1.2.3 From e04332ebc8ac128fa551e83f1161ab1c094d13a9 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 1 Aug 2024 15:27:28 +0200 Subject: uprobes: kill uprobe_register_refctr() It doesn't make any sense to have 2 versions of _register(). Note that trace_uprobe_enable(), the only user of uprobe_register(), doesn't need to check tu->ref_ctr_offset to decide which one should be used, it could safely pass ref_ctr_offset == 0 to uprobe_register_refctr(). Add this argument to uprobe_register(), update the callers, and kill uprobe_register_refctr(). Signed-off-by: Oleg Nesterov Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Jiri Olsa Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20240801132728.GA8800@redhat.com --- include/linux/uprobes.h | 9 ++------ kernel/events/uprobes.c | 24 ++++++---------------- kernel/trace/bpf_trace.c | 8 ++++---- kernel/trace/trace_uprobe.c | 7 +------ .../selftests/bpf/bpf_testmod/bpf_testmod.c | 4 ++-- 5 files changed, 15 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index a270a5892ab4..788813c0b8fc 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -112,8 +112,7 @@ extern bool is_trap_insn(uprobe_opcode_t *insn); extern unsigned long uprobe_get_swbp_addr(struct pt_regs *regs); extern unsigned long uprobe_get_trap_addr(struct pt_regs *regs); extern int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t); -extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc); -extern int uprobe_register_refctr(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc); +extern int uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc); extern int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool); extern void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc); extern int uprobe_mmap(struct vm_area_struct *vma); @@ -154,11 +153,7 @@ static inline void uprobes_init(void) #define uprobe_get_trap_addr(regs) instruction_pointer(regs) static inline int -uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc) -{ - return -ENOSYS; -} -static inline int uprobe_register_refctr(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc) +uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc) { return -ENOSYS; } diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index e9b092acc71b..3a80154bc4c7 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1121,25 +1121,26 @@ void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consume EXPORT_SYMBOL_GPL(uprobe_unregister); /* - * __uprobe_register - register a probe + * uprobe_register - register a probe * @inode: the file in which the probe has to be placed. * @offset: offset from the start of the file. + * @ref_ctr_offset: offset of SDT marker / reference counter * @uc: information on howto handle the probe.. * - * Apart from the access refcount, __uprobe_register() takes a creation + * Apart from the access refcount, uprobe_register() takes a creation * refcount (thro alloc_uprobe) if and only if this @uprobe is getting * inserted into the rbtree (i.e first consumer for a @inode:@offset * tuple). Creation refcount stops uprobe_unregister from freeing the * @uprobe even before the register operation is complete. Creation * refcount is released when the last @uc for the @uprobe - * unregisters. Caller of __uprobe_register() is required to keep @inode + * unregisters. Caller of uprobe_register() is required to keep @inode * (and the containing mount) referenced. * * Return errno if it cannot successully install probes * else return 0 (success) */ -static int __uprobe_register(struct inode *inode, loff_t offset, - loff_t ref_ctr_offset, struct uprobe_consumer *uc) +int uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, + struct uprobe_consumer *uc) { struct uprobe *uprobe; int ret; @@ -1189,21 +1190,8 @@ static int __uprobe_register(struct inode *inode, loff_t offset, goto retry; return ret; } - -int uprobe_register(struct inode *inode, loff_t offset, - struct uprobe_consumer *uc) -{ - return __uprobe_register(inode, offset, 0, uc); -} EXPORT_SYMBOL_GPL(uprobe_register); -int uprobe_register_refctr(struct inode *inode, loff_t offset, - loff_t ref_ctr_offset, struct uprobe_consumer *uc) -{ - return __uprobe_register(inode, offset, ref_ctr_offset, uc); -} -EXPORT_SYMBOL_GPL(uprobe_register_refctr); - /* * uprobe_apply - unregister an already registered probe. * @inode: the file in which the probe has to be removed. diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index cd098846e251..afa909e17824 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -3480,10 +3480,10 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr &bpf_uprobe_multi_link_lops, prog); for (i = 0; i < cnt; i++) { - err = uprobe_register_refctr(d_real_inode(link->path.dentry), - uprobes[i].offset, - uprobes[i].ref_ctr_offset, - &uprobes[i].consumer); + err = uprobe_register(d_real_inode(link->path.dentry), + uprobes[i].offset, + uprobes[i].ref_ctr_offset, + &uprobes[i].consumer); if (err) { bpf_uprobe_unregister(&path, uprobes, i); goto error_free; diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index c98e3b3386ba..1f590f989c1e 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1089,12 +1089,7 @@ static int trace_uprobe_enable(struct trace_uprobe *tu, filter_func_t filter) tu->consumer.filter = filter; tu->inode = d_real_inode(tu->path.dentry); - if (tu->ref_ctr_offset) - ret = uprobe_register_refctr(tu->inode, tu->offset, - tu->ref_ctr_offset, &tu->consumer); - else - ret = uprobe_register(tu->inode, tu->offset, &tu->consumer); - + ret = uprobe_register(tu->inode, tu->offset, tu->ref_ctr_offset, &tu->consumer); if (ret) tu->inode = NULL; diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index 72f565af4f82..55f6905de743 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -458,8 +458,8 @@ static int testmod_register_uprobe(loff_t offset) if (err) goto out; - err = uprobe_register_refctr(d_real_inode(uprobe.path.dentry), - offset, 0, &uprobe.consumer); + err = uprobe_register(d_real_inode(uprobe.path.dentry), + offset, 0, &uprobe.consumer); if (err) path_put(&uprobe.path); else -- cgit v1.2.3 From 3c83a9ad0295eb63bdeb81d821b8c3b9417fbcac Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 1 Aug 2024 15:27:34 +0200 Subject: uprobes: make uprobe_register() return struct uprobe * This way uprobe_unregister() and uprobe_apply() can use "struct uprobe *" rather than inode + offset. This simplifies the code and allows to avoid the unnecessary find_uprobe() + put_uprobe() in these functions. TODO: uprobe_unregister() still needs get_uprobe/put_uprobe to ensure that this uprobe can't be freed before up_write(&uprobe->register_rwsem). Co-developed-by: Andrii Nakryiko Signed-off-by: Andrii Nakryiko Signed-off-by: Oleg Nesterov Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Jiri Olsa Link: https://lore.kernel.org/r/20240801132734.GA8803@redhat.com --- include/linux/uprobes.h | 15 +++--- kernel/events/uprobes.c | 56 +++++++++------------- kernel/trace/bpf_trace.c | 25 +++++----- kernel/trace/trace_uprobe.c | 26 +++++----- .../selftests/bpf/bpf_testmod/bpf_testmod.c | 25 +++++----- 5 files changed, 67 insertions(+), 80 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index 788813c0b8fc..f50df1fa93e7 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -16,6 +16,7 @@ #include #include +struct uprobe; struct vm_area_struct; struct mm_struct; struct inode; @@ -112,9 +113,9 @@ extern bool is_trap_insn(uprobe_opcode_t *insn); extern unsigned long uprobe_get_swbp_addr(struct pt_regs *regs); extern unsigned long uprobe_get_trap_addr(struct pt_regs *regs); extern int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t); -extern int uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc); -extern int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool); -extern void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc); +extern struct uprobe *uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc); +extern int uprobe_apply(struct uprobe *uprobe, struct uprobe_consumer *uc, bool); +extern void uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc); extern int uprobe_mmap(struct vm_area_struct *vma); extern void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern void uprobe_start_dup_mmap(void); @@ -152,18 +153,18 @@ static inline void uprobes_init(void) #define uprobe_get_trap_addr(regs) instruction_pointer(regs) -static inline int +static inline struct uprobe * uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc) { - return -ENOSYS; + return ERR_PTR(-ENOSYS); } static inline int -uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool add) +uprobe_apply(struct uprobe* uprobe, struct uprobe_consumer *uc, bool add) { return -ENOSYS; } static inline void -uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc) +uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc) { } static inline int uprobe_mmap(struct vm_area_struct *vma) diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 3a80154bc4c7..b33f1397dae0 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1099,20 +1099,14 @@ __uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc) delete_uprobe(uprobe); } -/* +/** * uprobe_unregister - unregister an already registered probe. - * @inode: the file in which the probe has to be removed. - * @offset: offset from the start of the file. + * @uprobe: uprobe to remove * @uc: identify which probe if multiple probes are colocated. */ -void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc) +void uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc) { - struct uprobe *uprobe; - - uprobe = find_uprobe(inode, offset); - if (WARN_ON(!uprobe)) - return; - + get_uprobe(uprobe); down_write(&uprobe->register_rwsem); __uprobe_unregister(uprobe, uc); up_write(&uprobe->register_rwsem); @@ -1120,7 +1114,7 @@ void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consume } EXPORT_SYMBOL_GPL(uprobe_unregister); -/* +/** * uprobe_register - register a probe * @inode: the file in which the probe has to be placed. * @offset: offset from the start of the file. @@ -1136,40 +1130,40 @@ EXPORT_SYMBOL_GPL(uprobe_unregister); * unregisters. Caller of uprobe_register() is required to keep @inode * (and the containing mount) referenced. * - * Return errno if it cannot successully install probes - * else return 0 (success) + * Return: pointer to the new uprobe on success or an ERR_PTR on failure. */ -int uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, - struct uprobe_consumer *uc) +struct uprobe *uprobe_register(struct inode *inode, + loff_t offset, loff_t ref_ctr_offset, + struct uprobe_consumer *uc) { struct uprobe *uprobe; int ret; /* Uprobe must have at least one set consumer */ if (!uc->handler && !uc->ret_handler) - return -EINVAL; + return ERR_PTR(-EINVAL); /* copy_insn() uses read_mapping_page() or shmem_read_mapping_page() */ if (!inode->i_mapping->a_ops->read_folio && !shmem_mapping(inode->i_mapping)) - return -EIO; + return ERR_PTR(-EIO); /* Racy, just to catch the obvious mistakes */ if (offset > i_size_read(inode)) - return -EINVAL; + return ERR_PTR(-EINVAL); /* * This ensures that copy_from_page(), copy_to_page() and * __update_ref_ctr() can't cross page boundary. */ if (!IS_ALIGNED(offset, UPROBE_SWBP_INSN_SIZE)) - return -EINVAL; + return ERR_PTR(-EINVAL); if (!IS_ALIGNED(ref_ctr_offset, sizeof(short))) - return -EINVAL; + return ERR_PTR(-EINVAL); retry: uprobe = alloc_uprobe(inode, offset, ref_ctr_offset); if (IS_ERR(uprobe)) - return PTR_ERR(uprobe); + return uprobe; /* * We can race with uprobe_unregister()->delete_uprobe(). @@ -1188,35 +1182,29 @@ int uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, if (unlikely(ret == -EAGAIN)) goto retry; - return ret; + + return ret ? ERR_PTR(ret) : uprobe; } EXPORT_SYMBOL_GPL(uprobe_register); -/* - * uprobe_apply - unregister an already registered probe. - * @inode: the file in which the probe has to be removed. - * @offset: offset from the start of the file. +/** + * uprobe_apply - add or remove the breakpoints according to @uc->filter + * @uprobe: uprobe which "owns" the breakpoint * @uc: consumer which wants to add more or remove some breakpoints * @add: add or remove the breakpoints + * Return: 0 on success or negative error code. */ -int uprobe_apply(struct inode *inode, loff_t offset, - struct uprobe_consumer *uc, bool add) +int uprobe_apply(struct uprobe *uprobe, struct uprobe_consumer *uc, bool add) { - struct uprobe *uprobe; struct uprobe_consumer *con; int ret = -ENOENT; - uprobe = find_uprobe(inode, offset); - if (WARN_ON(!uprobe)) - return ret; - down_write(&uprobe->register_rwsem); for (con = uprobe->consumers; con && con != uc ; con = con->next) ; if (con) ret = register_for_each_vma(uprobe, add ? uc : NULL); up_write(&uprobe->register_rwsem); - put_uprobe(uprobe); return ret; } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index afa909e17824..4e391daafa64 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -3160,6 +3160,7 @@ struct bpf_uprobe { loff_t offset; unsigned long ref_ctr_offset; u64 cookie; + struct uprobe *uprobe; struct uprobe_consumer consumer; }; @@ -3178,15 +3179,12 @@ struct bpf_uprobe_multi_run_ctx { struct bpf_uprobe *uprobe; }; -static void bpf_uprobe_unregister(struct path *path, struct bpf_uprobe *uprobes, - u32 cnt) +static void bpf_uprobe_unregister(struct bpf_uprobe *uprobes, u32 cnt) { u32 i; - for (i = 0; i < cnt; i++) { - uprobe_unregister(d_real_inode(path->dentry), uprobes[i].offset, - &uprobes[i].consumer); - } + for (i = 0; i < cnt; i++) + uprobe_unregister(uprobes[i].uprobe, &uprobes[i].consumer); } static void bpf_uprobe_multi_link_release(struct bpf_link *link) @@ -3194,7 +3192,7 @@ static void bpf_uprobe_multi_link_release(struct bpf_link *link) struct bpf_uprobe_multi_link *umulti_link; umulti_link = container_of(link, struct bpf_uprobe_multi_link, link); - bpf_uprobe_unregister(&umulti_link->path, umulti_link->uprobes, umulti_link->cnt); + bpf_uprobe_unregister(umulti_link->uprobes, umulti_link->cnt); if (umulti_link->task) put_task_struct(umulti_link->task); path_put(&umulti_link->path); @@ -3480,12 +3478,13 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr &bpf_uprobe_multi_link_lops, prog); for (i = 0; i < cnt; i++) { - err = uprobe_register(d_real_inode(link->path.dentry), - uprobes[i].offset, - uprobes[i].ref_ctr_offset, - &uprobes[i].consumer); - if (err) { - bpf_uprobe_unregister(&path, uprobes, i); + uprobes[i].uprobe = uprobe_register(d_real_inode(link->path.dentry), + uprobes[i].offset, + uprobes[i].ref_ctr_offset, + &uprobes[i].consumer); + if (IS_ERR(uprobes[i].uprobe)) { + err = PTR_ERR(uprobes[i].uprobe); + bpf_uprobe_unregister(uprobes, i); goto error_free; } } diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 1f590f989c1e..52e76a73fa7c 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -58,8 +58,8 @@ struct trace_uprobe { struct dyn_event devent; struct uprobe_consumer consumer; struct path path; - struct inode *inode; char *filename; + struct uprobe *uprobe; unsigned long offset; unsigned long ref_ctr_offset; unsigned long nhit; @@ -1084,16 +1084,16 @@ typedef bool (*filter_func_t)(struct uprobe_consumer *self, static int trace_uprobe_enable(struct trace_uprobe *tu, filter_func_t filter) { - int ret; + struct inode *inode = d_real_inode(tu->path.dentry); + struct uprobe *uprobe; tu->consumer.filter = filter; - tu->inode = d_real_inode(tu->path.dentry); - - ret = uprobe_register(tu->inode, tu->offset, tu->ref_ctr_offset, &tu->consumer); - if (ret) - tu->inode = NULL; + uprobe = uprobe_register(inode, tu->offset, tu->ref_ctr_offset, &tu->consumer); + if (IS_ERR(uprobe)) + return PTR_ERR(uprobe); - return ret; + tu->uprobe = uprobe; + return 0; } static void __probe_event_disable(struct trace_probe *tp) @@ -1104,11 +1104,11 @@ static void __probe_event_disable(struct trace_probe *tp) WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter)); list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) { - if (!tu->inode) + if (!tu->uprobe) continue; - uprobe_unregister(tu->inode, tu->offset, &tu->consumer); - tu->inode = NULL; + uprobe_unregister(tu->uprobe, &tu->consumer); + tu->uprobe = NULL; } } @@ -1305,7 +1305,7 @@ static int uprobe_perf_close(struct trace_event_call *call, return 0; list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) { - ret = uprobe_apply(tu->inode, tu->offset, &tu->consumer, false); + ret = uprobe_apply(tu->uprobe, &tu->consumer, false); if (ret) break; } @@ -1329,7 +1329,7 @@ static int uprobe_perf_open(struct trace_event_call *call, return 0; list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) { - err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true); + err = uprobe_apply(tu->uprobe, &tu->consumer, true); if (err) { uprobe_perf_close(call, event); break; diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index 55f6905de743..3c0515a27842 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -432,7 +432,7 @@ uprobe_ret_handler(struct uprobe_consumer *self, unsigned long func, struct testmod_uprobe { struct path path; - loff_t offset; + struct uprobe *uprobe; struct uprobe_consumer consumer; }; @@ -446,25 +446,25 @@ static int testmod_register_uprobe(loff_t offset) { int err = -EBUSY; - if (uprobe.offset) + if (uprobe.uprobe) return -EBUSY; mutex_lock(&testmod_uprobe_mutex); - if (uprobe.offset) + if (uprobe.uprobe) goto out; err = kern_path("/proc/self/exe", LOOKUP_FOLLOW, &uprobe.path); if (err) goto out; - err = uprobe_register(d_real_inode(uprobe.path.dentry), - offset, 0, &uprobe.consumer); - if (err) + uprobe.uprobe = uprobe_register(d_real_inode(uprobe.path.dentry), + offset, 0, &uprobe.consumer); + if (IS_ERR(uprobe.uprobe)) { + err = PTR_ERR(uprobe.uprobe); path_put(&uprobe.path); - else - uprobe.offset = offset; - + uprobe.uprobe = NULL; + } out: mutex_unlock(&testmod_uprobe_mutex); return err; @@ -474,11 +474,10 @@ static void testmod_unregister_uprobe(void) { mutex_lock(&testmod_uprobe_mutex); - if (uprobe.offset) { - uprobe_unregister(d_real_inode(uprobe.path.dentry), - uprobe.offset, &uprobe.consumer); + if (uprobe.uprobe) { + uprobe_unregister(uprobe.uprobe, &uprobe.consumer); path_put(&uprobe.path); - uprobe.offset = 0; + uprobe.uprobe = NULL; } mutex_unlock(&testmod_uprobe_mutex); -- cgit v1.2.3 From 6edb8cd87cca5dd4389d4ea2d84b66ea94341bbd Mon Sep 17 00:00:00 2001 From: Kerem Karabay Date: Fri, 5 Jul 2024 11:17:42 +0000 Subject: HID: core: add helper for finding a field with a certain usage This helper will allow HID drivers to easily determine if they should bind to a hid_device by checking for the prescence of a certain field when its ID is not enough, which can be the case on USB devices with multiple interfaces and/or configurations. Convert google-hammer driver to use it, and remove now superfluous hammer_has_usage(). [jkosina@suse.com: expand changelog with the information about google-hammer being added as user of this API ] Signed-off-by: Kerem Karabay Signed-off-by: Aditya Garg Signed-off-by: Jiri Kosina --- drivers/hid/hid-core.c | 25 +++++++++++++++++++++++++ drivers/hid/hid-google-hammer.c | 27 ++------------------------- include/linux/hid.h | 2 ++ 3 files changed, 29 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 988d0acbdf04..caeba5487b69 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1912,6 +1912,31 @@ int hid_set_field(struct hid_field *field, unsigned offset, __s32 value) } EXPORT_SYMBOL_GPL(hid_set_field); +struct hid_field *hid_find_field(struct hid_device *hdev, unsigned int report_type, + unsigned int application, unsigned int usage) +{ + struct list_head *report_list = &hdev->report_enum[report_type].report_list; + struct hid_report *report; + int i, j; + + list_for_each_entry(report, report_list, list) { + if (report->application != application) + continue; + + for (i = 0; i < report->maxfield; i++) { + struct hid_field *field = report->field[i]; + + for (j = 0; j < field->maxusage; j++) { + if (field->usage[j].hid == usage) + return field; + } + } + } + + return NULL; +} +EXPORT_SYMBOL_GPL(hid_find_field); + static struct hid_report *hid_get_report(struct hid_report_enum *report_enum, const u8 *data) { diff --git a/drivers/hid/hid-google-hammer.c b/drivers/hid/hid-google-hammer.c index 6e4ebc349e45..4e79fafeeafa 100644 --- a/drivers/hid/hid-google-hammer.c +++ b/drivers/hid/hid-google-hammer.c @@ -418,38 +418,15 @@ static int hammer_event(struct hid_device *hid, struct hid_field *field, return 0; } -static bool hammer_has_usage(struct hid_device *hdev, unsigned int report_type, - unsigned application, unsigned usage) -{ - struct hid_report_enum *re = &hdev->report_enum[report_type]; - struct hid_report *report; - int i, j; - - list_for_each_entry(report, &re->report_list, list) { - if (report->application != application) - continue; - - for (i = 0; i < report->maxfield; i++) { - struct hid_field *field = report->field[i]; - - for (j = 0; j < field->maxusage; j++) - if (field->usage[j].hid == usage) - return true; - } - } - - return false; -} - static bool hammer_has_folded_event(struct hid_device *hdev) { - return hammer_has_usage(hdev, HID_INPUT_REPORT, + return !!hid_find_field(hdev, HID_INPUT_REPORT, HID_GD_KEYBOARD, HID_USAGE_KBD_FOLDED); } static bool hammer_has_backlight_control(struct hid_device *hdev) { - return hammer_has_usage(hdev, HID_OUTPUT_REPORT, + return !!hid_find_field(hdev, HID_OUTPUT_REPORT, HID_GD_KEYBOARD, HID_AD_BRIGHTNESS); } diff --git a/include/linux/hid.h b/include/linux/hid.h index 1533c9dcd3a6..2deff79f39a1 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -940,6 +940,8 @@ extern void hidinput_report_event(struct hid_device *hid, struct hid_report *rep extern int hidinput_connect(struct hid_device *hid, unsigned int force); extern void hidinput_disconnect(struct hid_device *); +struct hid_field *hid_find_field(struct hid_device *hdev, unsigned int report_type, + unsigned int application, unsigned int usage); int hid_set_field(struct hid_field *, unsigned, __s32); int hid_input_report(struct hid_device *hid, enum hid_report_type type, u8 *data, u32 size, int interrupt); -- cgit v1.2.3 From 79f194dd54cef3a0212914cd79dda1f91b7bf7f6 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 29 Jul 2024 18:11:29 +0200 Subject: thermal: trip: Get rid of thermal_zone_get_num_trips() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The only existing caller of thermal_zone_get_num_trips(), which is rcar_gen3_thermal_probe(), uses this function to put the number of trip points into a kernel log message, but this information is also available from the thermal sysfs interface. For this reason, remove the thermal_zone_get_num_trips() call from rcar_gen3_thermal_probe() and drop the former altogether. Signed-off-by: Rafael J. Wysocki Reviewed-by: Niklas Söderlund Reviewed-by: Lukasz Luba Link: https://patch.msgid.link/2636988.Lt9SDvczpP@rjwysocki.net --- drivers/thermal/renesas/rcar_gen3_thermal.c | 6 +----- drivers/thermal/thermal_trip.c | 6 ------ include/linux/thermal.h | 1 - 3 files changed, 1 insertion(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/thermal/renesas/rcar_gen3_thermal.c b/drivers/thermal/renesas/rcar_gen3_thermal.c index 5c769871753a..810f86677461 100644 --- a/drivers/thermal/renesas/rcar_gen3_thermal.c +++ b/drivers/thermal/renesas/rcar_gen3_thermal.c @@ -563,11 +563,7 @@ static int rcar_gen3_thermal_probe(struct platform_device *pdev) if (ret) goto error_unregister; - ret = thermal_zone_get_num_trips(tsc->zone); - if (ret < 0) - goto error_unregister; - - dev_info(dev, "Sensor %u: Loaded %d trip points\n", i, ret); + dev_info(dev, "Sensor %u: Loaded\n", i); } if (!priv->num_tscs) { diff --git a/drivers/thermal/thermal_trip.c b/drivers/thermal/thermal_trip.c index 06a0554ddc38..e64d045d1603 100644 --- a/drivers/thermal/thermal_trip.c +++ b/drivers/thermal/thermal_trip.c @@ -55,12 +55,6 @@ int thermal_zone_for_each_trip(struct thermal_zone_device *tz, } EXPORT_SYMBOL_GPL(thermal_zone_for_each_trip); -int thermal_zone_get_num_trips(struct thermal_zone_device *tz) -{ - return tz->num_trips; -} -EXPORT_SYMBOL_GPL(thermal_zone_get_num_trips); - /** * thermal_zone_set_trips - Computes the next trip points for the driver * @tz: a pointer to a thermal zone device structure diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 25fbf960b474..4fdfd5abd2c4 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -210,7 +210,6 @@ int for_each_thermal_trip(struct thermal_zone_device *tz, int thermal_zone_for_each_trip(struct thermal_zone_device *tz, int (*cb)(struct thermal_trip *, void *), void *data); -int thermal_zone_get_num_trips(struct thermal_zone_device *tz); void thermal_zone_set_trip_temp(struct thermal_zone_device *tz, struct thermal_trip *trip, int temp); -- cgit v1.2.3 From 8ecd953ca5850d2f83f548d4bbcf672d2d2cd0ca Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 29 Jul 2024 18:12:45 +0200 Subject: thermal: trip: Drop thermal_zone_get_trip() There are no more callers of thermal_zone_get_trip() in the tree, so drop it. No functional impact. Signed-off-by: Rafael J. Wysocki Reviewed-by: Lukasz Luba Link: https://patch.msgid.link/2220301.Mh6RI2rZIc@rjwysocki.net --- drivers/thermal/thermal_trip.c | 14 -------------- include/linux/thermal.h | 2 -- 2 files changed, 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/thermal/thermal_trip.c b/drivers/thermal/thermal_trip.c index e64d045d1603..079e5e452eeb 100644 --- a/drivers/thermal/thermal_trip.c +++ b/drivers/thermal/thermal_trip.c @@ -108,20 +108,6 @@ void thermal_zone_set_trips(struct thermal_zone_device *tz) dev_err(&tz->device, "Failed to set trips: %d\n", ret); } -int thermal_zone_get_trip(struct thermal_zone_device *tz, int trip_id, - struct thermal_trip *trip) -{ - if (!tz || !trip || trip_id < 0 || trip_id >= tz->num_trips) - return -EINVAL; - - mutex_lock(&tz->lock); - *trip = tz->trips[trip_id].trip; - mutex_unlock(&tz->lock); - - return 0; -} -EXPORT_SYMBOL_GPL(thermal_zone_get_trip); - int thermal_zone_trip_id(const struct thermal_zone_device *tz, const struct thermal_trip *trip) { diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 4fdfd5abd2c4..db44a57a7474 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -202,8 +202,6 @@ static inline void devm_thermal_of_zone_unregister(struct device *dev, } #endif -int thermal_zone_get_trip(struct thermal_zone_device *tz, int trip_id, - struct thermal_trip *trip); int for_each_thermal_trip(struct thermal_zone_device *tz, int (*cb)(struct thermal_trip *, void *), void *data); -- cgit v1.2.3 From 37c6dccd683797a5a4ec85d2e94939bf829d3499 Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Sun, 28 Jul 2024 20:26:59 +0100 Subject: cpufreq: Remove LATENCY_MULTIPLIER The current LATENCY_MULTIPLIER which has been around for nearly 20 years causes rate_limit_us to be always in ms range. On M1 mac mini I get 50 and 56us transition latency, but due to the 1000 multiplier we end up setting rate_limit_us to 50 and 56ms, which gets capped into 2ms and was 10ms before e13aa799c2a6 ("cpufreq: Change default transition delay to 2ms") On Intel I5 system transition latency is 20us but due to the multiplier we end up with 20ms that again is capped to 2ms. Given how good modern hardware and how modern workloads require systems to be more responsive to cater for sudden changes in workload (tasks sleeping/wakeup/migrating, uclamp causing a sudden boost or cap) and that 2ms is quarter of the time of 120Hz refresh rate system, drop the old logic in favour of providing 50% headroom. rate_limit_us = 1.5 * latency. I considered not adding any headroom which could mean that we can end up with infinite back-to-back requests. I also considered providing a constant headroom (e.g: 100us) assuming that any h/w or f/w dealing with the request shouldn't require a large headroom when transition_latency is actually high. But for both cases I wasn't sure if h/w or f/w can end up being overwhelmed dealing with the freq requests in a potentially busy system. So I opted for providing 50% breathing room. This is expected to impact schedutil only as the other user, dbs_governor, takes the max(2*tick, transition_delay_us) and the former was at least 2ms on 1ms TICK, which is equivalent to the max_delay_us before applying this patch. For systems with TICK of 4ms, this value would have almost always ended up with 8ms sampling rate. For systems that report 0 transition latency, we still default to returning 1ms as transition delay. This helps in eliminating a source of latency for applying requests as mentioned in [1]. For example if we have a 1ms tick, most systems will miss sending an update at tick when updating the util_avg for a task/CPU (rate_limit_us will be 2ms for most systems). Link: https://lore.kernel.org/lkml/20240724212255.mfr2ybiv2j2uqek7@airbuntu/ # [1] Link: https://lore.kernel.org/lkml/20240205022500.2232124-1-qyousef@layalina.io/ Signed-off-by: Qais Yousef Link: https://patch.msgid.link/20240728192659.58115-1-qyousef@layalina.io [ rjw: Subject edits ] Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/cpufreq.c | 27 ++++----------------------- include/linux/cpufreq.h | 6 ------ 2 files changed, 4 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 04fc786dd2c0..f98c9438760c 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -575,30 +575,11 @@ unsigned int cpufreq_policy_transition_delay_us(struct cpufreq_policy *policy) return policy->transition_delay_us; latency = policy->cpuinfo.transition_latency / NSEC_PER_USEC; - if (latency) { - unsigned int max_delay_us = 2 * MSEC_PER_SEC; + if (latency) + /* Give a 50% breathing room between updates */ + return latency + (latency >> 1); - /* - * If the platform already has high transition_latency, use it - * as-is. - */ - if (latency > max_delay_us) - return latency; - - /* - * For platforms that can change the frequency very fast (< 2 - * us), the above formula gives a decent transition delay. But - * for platforms where transition_latency is in milliseconds, it - * ends up giving unrealistic values. - * - * Cap the default transition delay to 2 ms, which seems to be - * a reasonable amount of time after which we should reevaluate - * the frequency. - */ - return min(latency * LATENCY_MULTIPLIER, max_delay_us); - } - - return LATENCY_MULTIPLIER; + return USEC_PER_MSEC; } EXPORT_SYMBOL_GPL(cpufreq_policy_transition_delay_us); diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index d4d2f4d1d7cb..e0e19d9c1323 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -577,12 +577,6 @@ static inline unsigned long cpufreq_scale(unsigned long old, u_int div, #define CPUFREQ_POLICY_POWERSAVE (1) #define CPUFREQ_POLICY_PERFORMANCE (2) -/* - * The polling frequency depends on the capability of the processor. Default - * polling frequency is 1000 times the transition latency of the processor. - */ -#define LATENCY_MULTIPLIER (1000) - struct cpufreq_governor { char name[CPUFREQ_NAME_LEN]; int (*init)(struct cpufreq_policy *policy); -- cgit v1.2.3 From 70e6b7d9ae3c63df90a7bba7700e8d5c300c3c60 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Fri, 2 Aug 2024 14:55:54 +0100 Subject: x86/i8253: Disable PIT timer 0 when not in use Leaving the PIT interrupt running can cause noticeable steal time for virtual guests. The VMM generally has a timer which toggles the IRQ input to the PIC and I/O APIC, which takes CPU time away from the guest. Even on real hardware, running the counter may use power needlessly (albeit not much). Make sure it's turned off if it isn't going to be used. Signed-off-by: David Woodhouse Signed-off-by: Thomas Gleixner Tested-by: Michael Kelley Link: https://lore.kernel.org/all/20240802135555.564941-1-dwmw2@infradead.org --- arch/x86/kernel/i8253.c | 11 +++++++++-- drivers/clocksource/i8253.c | 13 +++++++++---- include/linux/i8253.h | 1 + 3 files changed, 19 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c index 2b7999a1a50a..80e262bb627f 100644 --- a/arch/x86/kernel/i8253.c +++ b/arch/x86/kernel/i8253.c @@ -8,6 +8,7 @@ #include #include +#include #include #include #include @@ -39,9 +40,15 @@ static bool __init use_pit(void) bool __init pit_timer_init(void) { - if (!use_pit()) + if (!use_pit()) { + /* + * Don't just ignore the PIT. Ensure it's stopped, because + * VMMs otherwise steal CPU time just to pointlessly waggle + * the (masked) IRQ. + */ + clockevent_i8253_disable(); return false; - + } clockevent_i8253_init(true); global_clock_event = &i8253_clockevent; return true; diff --git a/drivers/clocksource/i8253.c b/drivers/clocksource/i8253.c index d4350bb10b83..cb215e6f2e83 100644 --- a/drivers/clocksource/i8253.c +++ b/drivers/clocksource/i8253.c @@ -108,11 +108,8 @@ int __init clocksource_i8253_init(void) #endif #ifdef CONFIG_CLKEVT_I8253 -static int pit_shutdown(struct clock_event_device *evt) +void clockevent_i8253_disable(void) { - if (!clockevent_state_oneshot(evt) && !clockevent_state_periodic(evt)) - return 0; - raw_spin_lock(&i8253_lock); outb_p(0x30, PIT_MODE); @@ -123,6 +120,14 @@ static int pit_shutdown(struct clock_event_device *evt) } raw_spin_unlock(&i8253_lock); +} + +static int pit_shutdown(struct clock_event_device *evt) +{ + if (!clockevent_state_oneshot(evt) && !clockevent_state_periodic(evt)) + return 0; + + clockevent_i8253_disable(); return 0; } diff --git a/include/linux/i8253.h b/include/linux/i8253.h index 8336b2f6f834..bf169cfef7f1 100644 --- a/include/linux/i8253.h +++ b/include/linux/i8253.h @@ -24,6 +24,7 @@ extern raw_spinlock_t i8253_lock; extern bool i8253_clear_counter_on_shutdown; extern struct clock_event_device i8253_clockevent; extern void clockevent_i8253_init(bool oneshot); +extern void clockevent_i8253_disable(void); extern void setup_pit_timer(void); -- cgit v1.2.3 From 531b2ca0a940ac9db03f246c8b77c4201de72b00 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Fri, 2 Aug 2024 14:55:55 +0100 Subject: clockevents/drivers/i8253: Fix stop sequence for timer 0 According to the data sheet, writing the MODE register should stop the counter (and thus the interrupts). This appears to work on real hardware, at least modern Intel and AMD systems. It should also work on Hyper-V. However, on some buggy virtual machines the mode change doesn't have any effect until the counter is subsequently loaded (or perhaps when the IRQ next fires). So, set MODE 0 and then load the counter, to ensure that those buggy VMs do the right thing and the interrupts stop. And then write MODE 0 *again* to stop the counter on compliant implementations too. Apparently, Hyper-V keeps firing the IRQ *repeatedly* even in mode zero when it should only happen once, but the second MODE write stops that too. Userspace test program (mostly written by tglx): ===== #include #include #include #include #include static __always_inline void __out##bwl(type value, uint16_t port) \ { \ asm volatile("out" #bwl " %" #bw "0, %w1" \ : : "a"(value), "Nd"(port)); \ } \ \ static __always_inline type __in##bwl(uint16_t port) \ { \ type value; \ asm volatile("in" #bwl " %w1, %" #bw "0" \ : "=a"(value) : "Nd"(port)); \ return value; \ } BUILDIO(b, b, uint8_t) #define inb __inb #define outb __outb #define PIT_MODE 0x43 #define PIT_CH0 0x40 #define PIT_CH2 0x42 static int is8254; static void dump_pit(void) { if (is8254) { // Latch and output counter and status outb(0xC2, PIT_MODE); printf("%02x %02x %02x\n", inb(PIT_CH0), inb(PIT_CH0), inb(PIT_CH0)); } else { // Latch and output counter outb(0x0, PIT_MODE); printf("%02x %02x\n", inb(PIT_CH0), inb(PIT_CH0)); } } int main(int argc, char* argv[]) { int nr_counts = 2; if (argc > 1) nr_counts = atoi(argv[1]); if (argc > 2) is8254 = 1; if (ioperm(0x40, 4, 1) != 0) return 1; dump_pit(); printf("Set oneshot\n"); outb(0x38, PIT_MODE); outb(0x00, PIT_CH0); outb(0x0F, PIT_CH0); dump_pit(); usleep(1000); dump_pit(); printf("Set periodic\n"); outb(0x34, PIT_MODE); outb(0x00, PIT_CH0); outb(0x0F, PIT_CH0); dump_pit(); usleep(1000); dump_pit(); dump_pit(); usleep(100000); dump_pit(); usleep(100000); dump_pit(); printf("Set stop (%d counter writes)\n", nr_counts); outb(0x30, PIT_MODE); while (nr_counts--) outb(0xFF, PIT_CH0); dump_pit(); usleep(100000); dump_pit(); usleep(100000); dump_pit(); printf("Set MODE 0\n"); outb(0x30, PIT_MODE); dump_pit(); usleep(100000); dump_pit(); usleep(100000); dump_pit(); return 0; } ===== Suggested-by: Sean Christopherson Co-developed-by: Li RongQing Signed-off-by: Li RongQing Signed-off-by: David Woodhouse Signed-off-by: Thomas Gleixner Tested-by: Michael Kelley Link: https://lore.kernel.org/all/20240802135555.564941-2-dwmw2@infradead.org --- arch/x86/kernel/cpu/mshyperv.c | 11 ----------- drivers/clocksource/i8253.c | 36 +++++++++++++++++++++++++----------- include/linux/i8253.h | 1 - 3 files changed, 25 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index e0fd57a8ba84..3d4237f27569 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -16,7 +16,6 @@ #include #include #include -#include #include #include #include @@ -522,16 +521,6 @@ static void __init ms_hyperv_init_platform(void) if (efi_enabled(EFI_BOOT)) x86_platform.get_nmi_reason = hv_get_nmi_reason; - /* - * Hyper-V VMs have a PIT emulation quirk such that zeroing the - * counter register during PIT shutdown restarts the PIT. So it - * continues to interrupt @18.2 HZ. Setting i8253_clear_counter - * to false tells pit_shutdown() not to zero the counter so that - * the PIT really is shutdown. Generation 2 VMs don't have a PIT, - * and setting this value has no effect. - */ - i8253_clear_counter_on_shutdown = false; - #if IS_ENABLED(CONFIG_HYPERV) if ((hv_get_isolation_type() == HV_ISOLATION_TYPE_VBS) || ms_hyperv.paravisor_present) diff --git a/drivers/clocksource/i8253.c b/drivers/clocksource/i8253.c index cb215e6f2e83..39f7c2d736d1 100644 --- a/drivers/clocksource/i8253.c +++ b/drivers/clocksource/i8253.c @@ -20,13 +20,6 @@ DEFINE_RAW_SPINLOCK(i8253_lock); EXPORT_SYMBOL(i8253_lock); -/* - * Handle PIT quirk in pit_shutdown() where zeroing the counter register - * restarts the PIT, negating the shutdown. On platforms with the quirk, - * platform specific code can set this to false. - */ -bool i8253_clear_counter_on_shutdown __ro_after_init = true; - #ifdef CONFIG_CLKSRC_I8253 /* * Since the PIT overflows every tick, its not very useful @@ -112,12 +105,33 @@ void clockevent_i8253_disable(void) { raw_spin_lock(&i8253_lock); + /* + * Writing the MODE register should stop the counter, according to + * the datasheet. This appears to work on real hardware (well, on + * modern Intel and AMD boxes; I didn't dig the Pegasos out of the + * shed). + * + * However, some virtual implementations differ, and the MODE change + * doesn't have any effect until either the counter is written (KVM + * in-kernel PIT) or the next interrupt (QEMU). And in those cases, + * it may not stop the *count*, only the interrupts. Although in + * the virt case, that probably doesn't matter, as the value of the + * counter will only be calculated on demand if the guest reads it; + * it's the interrupts which cause steal time. + * + * Hyper-V apparently has a bug where even in mode 0, the IRQ keeps + * firing repeatedly if the counter is running. But it *does* do the + * right thing when the MODE register is written. + * + * So: write the MODE and then load the counter, which ensures that + * the IRQ is stopped on those buggy virt implementations. And then + * write the MODE again, which is the right way to stop it. + */ outb_p(0x30, PIT_MODE); + outb_p(0, PIT_CH0); + outb_p(0, PIT_CH0); - if (i8253_clear_counter_on_shutdown) { - outb_p(0, PIT_CH0); - outb_p(0, PIT_CH0); - } + outb_p(0x30, PIT_MODE); raw_spin_unlock(&i8253_lock); } diff --git a/include/linux/i8253.h b/include/linux/i8253.h index bf169cfef7f1..56c280eb2d4f 100644 --- a/include/linux/i8253.h +++ b/include/linux/i8253.h @@ -21,7 +21,6 @@ #define PIT_LATCH ((PIT_TICK_RATE + HZ/2) / HZ) extern raw_spinlock_t i8253_lock; -extern bool i8253_clear_counter_on_shutdown; extern struct clock_event_device i8253_clockevent; extern void clockevent_i8253_init(bool oneshot); extern void clockevent_i8253_disable(void); -- cgit v1.2.3 From 90ec3a8a7fd0d43026fcca979713e077d4883b56 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Fri, 2 Aug 2024 16:22:13 +0100 Subject: spi: Add empty versions of ACPI functions Provide empty versions of acpi_spi_count_resources(), acpi_spi_device_alloc() and acpi_spi_find_controller_by_adev() if the real functions are not being built. This commit fixes two problems with the original definitions: 1) There wasn't an empty version of these functions 2) The #if only depended on CONFIG_ACPI. But the functions are implemented in the core spi.c so CONFIG_SPI_MASTER must also be enabled for the real functions to exist. Signed-off-by: Richard Fitzgerald Link: https://patch.msgid.link/20240802152215.20831-2-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index e4f3f3d30a03..d47d5f14ff99 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -902,12 +902,29 @@ extern int devm_spi_register_controller(struct device *dev, struct spi_controller *ctlr); extern void spi_unregister_controller(struct spi_controller *ctlr); -#if IS_ENABLED(CONFIG_ACPI) +#if IS_ENABLED(CONFIG_ACPI) && IS_ENABLED(CONFIG_SPI_MASTER) extern struct spi_controller *acpi_spi_find_controller_by_adev(struct acpi_device *adev); extern struct spi_device *acpi_spi_device_alloc(struct spi_controller *ctlr, struct acpi_device *adev, int index); int acpi_spi_count_resources(struct acpi_device *adev); +#else +static inline struct spi_controller *acpi_spi_find_controller_by_adev(struct acpi_device *adev) +{ + return NULL; +} + +static inline struct spi_device *acpi_spi_device_alloc(struct spi_controller *ctlr, + struct acpi_device *adev, + int index) +{ + return ERR_PTR(-ENODEV); +} + +static inline int acpi_spi_count_resources(struct acpi_device *adev) +{ + return 0; +} #endif /* -- cgit v1.2.3 From e99129e5dbf7ca87233d31ad19348f6ce8627b38 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 1 Aug 2024 13:32:59 -1000 Subject: sched_ext: Allow p->scx.disallow only while loading From 1232da7eced620537a78f19c8cf3d4a3508e2419 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 31 Jul 2024 09:14:52 -1000 p->scx.disallow provides a way for the BPF scheduler to reject certain tasks from attaching. It's currently allowed for both the load and fork paths; however, the latter doesn't actually work as p->sched_class is already set by the time scx_ops_init_task() is called during fork. This is a convenience feature which is mostly useful from the load path anyway. Allow it only from the load path. v2: Trigger scx_ops_error() iff @p->policy == SCHED_EXT to make it a bit easier for the BPF scheduler (David). Signed-off-by: Tejun Heo Reported-by: "Zhangqiao (2012 lab)" Link: http://lkml.kernel.org/r/20240711110720.1285-1-zhangqiao22@huawei.com Fixes: 7bb6f0810ecf ("sched_ext: Allow BPF schedulers to disallow specific tasks from joining SCHED_EXT") Acked-by: David Vernet Signed-off-by: Tejun Heo --- include/linux/sched/ext.h | 11 ++++++----- kernel/sched/ext.c | 35 ++++++++++++++++++++--------------- 2 files changed, 26 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index 26e1c33bc844..69f68e2121a8 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -179,11 +179,12 @@ struct sched_ext_entity { * If set, reject future sched_setscheduler(2) calls updating the policy * to %SCHED_EXT with -%EACCES. * - * If set from ops.init_task() and the task's policy is already - * %SCHED_EXT, which can happen while the BPF scheduler is being loaded - * or by inhering the parent's policy during fork, the task's policy is - * rejected and forcefully reverted to %SCHED_NORMAL. The number of - * such events are reported through /sys/kernel/debug/sched_ext::nr_rejected. + * Can be set from ops.init_task() while the BPF scheduler is being + * loaded (!scx_init_task_args->fork). If set and the task's policy is + * already %SCHED_EXT, the task's policy is rejected and forcefully + * reverted to %SCHED_NORMAL. The number of such events are reported + * through /sys/kernel/debug/sched_ext::nr_rejected. Setting this flag + * during fork is not allowed. */ bool disallow; /* reject switching into SCX */ diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 6f7c7d8b56de..938830121a32 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -3396,24 +3396,29 @@ static int scx_ops_init_task(struct task_struct *p, struct task_group *tg, bool scx_set_task_state(p, SCX_TASK_INIT); if (p->scx.disallow) { - struct rq *rq; - struct rq_flags rf; + if (!fork) { + struct rq *rq; + struct rq_flags rf; - rq = task_rq_lock(p, &rf); + rq = task_rq_lock(p, &rf); - /* - * We're either in fork or load path and @p->policy will be - * applied right after. Reverting @p->policy here and rejecting - * %SCHED_EXT transitions from scx_check_setscheduler() - * guarantees that if ops.init_task() sets @p->disallow, @p can - * never be in SCX. - */ - if (p->policy == SCHED_EXT) { - p->policy = SCHED_NORMAL; - atomic_long_inc(&scx_nr_rejected); - } + /* + * We're in the load path and @p->policy will be applied + * right after. Reverting @p->policy here and rejecting + * %SCHED_EXT transitions from scx_check_setscheduler() + * guarantees that if ops.init_task() sets @p->disallow, + * @p can never be in SCX. + */ + if (p->policy == SCHED_EXT) { + p->policy = SCHED_NORMAL; + atomic_long_inc(&scx_nr_rejected); + } - task_rq_unlock(rq, p, &rf); + task_rq_unlock(rq, p, &rf); + } else if (p->policy == SCHED_EXT) { + scx_ops_error("ops.init_task() set task->scx.disallow for %s[%d] during fork", + p->comm, p->pid); + } } p->scx.flags |= SCX_TASK_RESET_RUNNABLE_AT; -- cgit v1.2.3 From 49675f5bdf9ae2624b430dafda4cb29024521625 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 1 Aug 2024 09:34:01 -0700 Subject: net: remove IFF_* re-definition We re-define values of enum netdev_priv_flags as preprocessor macros with the same name. I guess this was done to avoid breaking out of tree modules which may use #ifdef X for kernel compatibility? Commit 7aa98047df95 ("net: move net_device priv_flags out from UAPI") which added the enum doesn't say. In any case, the flags with defines are quite old now, and defines for new flags don't get added. OOT drivers have to resort to code greps for compat detection, anyway. Let's delete these defines, save LoC, help LXR link to the right place. Reviewed-by: Simon Horman Reviewed-by: Jiri Pirko Link: https://patch.msgid.link/20240801163401.378723-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 32 -------------------------------- 1 file changed, 32 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 607009150b5f..0ef3eaa23f4b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1689,38 +1689,6 @@ enum netdev_priv_flags { IFF_SEE_ALL_HWTSTAMP_REQUESTS = BIT_ULL(33), }; -#define IFF_802_1Q_VLAN IFF_802_1Q_VLAN -#define IFF_EBRIDGE IFF_EBRIDGE -#define IFF_BONDING IFF_BONDING -#define IFF_ISATAP IFF_ISATAP -#define IFF_WAN_HDLC IFF_WAN_HDLC -#define IFF_XMIT_DST_RELEASE IFF_XMIT_DST_RELEASE -#define IFF_DONT_BRIDGE IFF_DONT_BRIDGE -#define IFF_DISABLE_NETPOLL IFF_DISABLE_NETPOLL -#define IFF_MACVLAN_PORT IFF_MACVLAN_PORT -#define IFF_BRIDGE_PORT IFF_BRIDGE_PORT -#define IFF_OVS_DATAPATH IFF_OVS_DATAPATH -#define IFF_TX_SKB_SHARING IFF_TX_SKB_SHARING -#define IFF_UNICAST_FLT IFF_UNICAST_FLT -#define IFF_TEAM_PORT IFF_TEAM_PORT -#define IFF_SUPP_NOFCS IFF_SUPP_NOFCS -#define IFF_LIVE_ADDR_CHANGE IFF_LIVE_ADDR_CHANGE -#define IFF_MACVLAN IFF_MACVLAN -#define IFF_XMIT_DST_RELEASE_PERM IFF_XMIT_DST_RELEASE_PERM -#define IFF_L3MDEV_MASTER IFF_L3MDEV_MASTER -#define IFF_NO_QUEUE IFF_NO_QUEUE -#define IFF_OPENVSWITCH IFF_OPENVSWITCH -#define IFF_L3MDEV_SLAVE IFF_L3MDEV_SLAVE -#define IFF_TEAM IFF_TEAM -#define IFF_RXFH_CONFIGURED IFF_RXFH_CONFIGURED -#define IFF_PHONY_HEADROOM IFF_PHONY_HEADROOM -#define IFF_MACSEC IFF_MACSEC -#define IFF_NO_RX_HANDLER IFF_NO_RX_HANDLER -#define IFF_FAILOVER IFF_FAILOVER -#define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE -#define IFF_L3MDEV_RX_HANDLER IFF_L3MDEV_RX_HANDLER -#define IFF_TX_SKB_NO_LINEAR IFF_TX_SKB_NO_LINEAR - /* Specifies the type of the struct net_device::ml_priv pointer */ enum netdev_ml_priv_type { ML_PRIV_NONE, -- cgit v1.2.3 From 7e1d512dab5042aa1c2224ed362be79e3f22a15e Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Thu, 1 Aug 2024 21:00:03 +0100 Subject: linkmode: Change return type of linkmode_andnot to bool linkmode_andnot() simply returns the result of bitmap_andnot(). And the return type of bitmap_andnot() is bool. So it makes sense for the return type of linkmode_andnot() to also be bool. I checked all call-sites and they either ignore the return value or treat it as a bool. Compile tested only. Link: https://lore.kernel.org/netdev/68088998-4486-4930-90a4-96a32f08c490@lunn.ch/ Signed-off-by: Simon Horman Link: https://patch.msgid.link/20240801-linkfield-bowl-v1-1-d58f68967802@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/linkmode.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index d94bfd9ac8cc..3b9de09871f6 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -37,8 +37,9 @@ static inline bool linkmode_empty(const unsigned long *src) return bitmap_empty(src, __ETHTOOL_LINK_MODE_MASK_NBITS); } -static inline int linkmode_andnot(unsigned long *dst, const unsigned long *src1, - const unsigned long *src2) +static inline bool linkmode_andnot(unsigned long *dst, + const unsigned long *src1, + const unsigned long *src2) { return bitmap_andnot(dst, src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS); } -- cgit v1.2.3 From 8585632a8600d26d4e6b7246d375a9c3a344f0d2 Mon Sep 17 00:00:00 2001 From: Nuno Sa Date: Tue, 9 Jul 2024 13:14:28 +0200 Subject: iio: backend: remove unused parameter Indio_dev was not being used in iio_backend_extend_chan_spec() so remove it. Signed-off-by: Nuno Sa Link: https://patch.msgid.link/20240709-dev-iio-backend-add-debugfs-v1-1-fb4b8f2373c7@analog.com Signed-off-by: Jonathan Cameron --- drivers/iio/dac/ad9739a.c | 3 +-- drivers/iio/industrialio-backend.c | 4 +--- include/linux/iio/backend.h | 3 +-- 3 files changed, 3 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/iio/dac/ad9739a.c b/drivers/iio/dac/ad9739a.c index f56eabe53723..9b1570e788b6 100644 --- a/drivers/iio/dac/ad9739a.c +++ b/drivers/iio/dac/ad9739a.c @@ -413,8 +413,7 @@ static int ad9739a_probe(struct spi_device *spi) if (ret) return ret; - ret = iio_backend_extend_chan_spec(indio_dev, st->back, - &ad9739a_channels[0]); + ret = iio_backend_extend_chan_spec(st->back, &ad9739a_channels[0]); if (ret) return ret; diff --git a/drivers/iio/industrialio-backend.c b/drivers/iio/industrialio-backend.c index efe05be284b6..65a42944d090 100644 --- a/drivers/iio/industrialio-backend.c +++ b/drivers/iio/industrialio-backend.c @@ -451,7 +451,6 @@ EXPORT_SYMBOL_NS_GPL(iio_backend_ext_info_set, IIO_BACKEND); /** * iio_backend_extend_chan_spec - Extend an IIO channel - * @indio_dev: IIO device * @back: Backend device * @chan: IIO channel * @@ -461,8 +460,7 @@ EXPORT_SYMBOL_NS_GPL(iio_backend_ext_info_set, IIO_BACKEND); * RETURNS: * 0 on success, negative error number on failure. */ -int iio_backend_extend_chan_spec(struct iio_dev *indio_dev, - struct iio_backend *back, +int iio_backend_extend_chan_spec(struct iio_backend *back, struct iio_chan_spec *chan) { const struct iio_chan_spec_ext_info *frontend_ext_info = chan->ext_info; diff --git a/include/linux/iio/backend.h b/include/linux/iio/backend.h index 8099759d7242..4e81931703ab 100644 --- a/include/linux/iio/backend.h +++ b/include/linux/iio/backend.h @@ -142,8 +142,7 @@ ssize_t iio_backend_ext_info_set(struct iio_dev *indio_dev, uintptr_t private, ssize_t iio_backend_ext_info_get(struct iio_dev *indio_dev, uintptr_t private, const struct iio_chan_spec *chan, char *buf); -int iio_backend_extend_chan_spec(struct iio_dev *indio_dev, - struct iio_backend *back, +int iio_backend_extend_chan_spec(struct iio_backend *back, struct iio_chan_spec *chan); void *iio_backend_get_priv(const struct iio_backend *conv); struct iio_backend *devm_iio_backend_get(struct device *dev, const char *name); -- cgit v1.2.3 From 2477d7b179d3295c9978420027750f047976bd04 Mon Sep 17 00:00:00 2001 From: David Lechner Date: Fri, 26 Jul 2024 15:18:40 -0500 Subject: iio: backend: spelling: continuous -> continuous This fixes the spelling in IIO_BACKEND_INTERNAL_CONTINUOUS_WAVE. Signed-off-by: David Lechner Link: https://patch.msgid.link/20240726-iio-backend-spelling-continuous-v1-1-467c6e3f78ff@baylibre.com Signed-off-by: Jonathan Cameron --- drivers/iio/dac/ad9739a.c | 2 +- drivers/iio/dac/adi-axi-dac.c | 2 +- include/linux/iio/backend.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/iio/dac/ad9739a.c b/drivers/iio/dac/ad9739a.c index 9b1570e788b6..799387f21b9f 100644 --- a/drivers/iio/dac/ad9739a.c +++ b/drivers/iio/dac/ad9739a.c @@ -145,7 +145,7 @@ static int ad9739a_buffer_postdisable(struct iio_dev *indio_dev) struct ad9739a_state *st = iio_priv(indio_dev); return iio_backend_data_source_set(st->back, 0, - IIO_BACKEND_INTERNAL_CONTINUOS_WAVE); + IIO_BACKEND_INTERNAL_CONTINUOUS_WAVE); } static bool ad9739a_reg_accessible(struct device *dev, unsigned int reg) diff --git a/drivers/iio/dac/adi-axi-dac.c b/drivers/iio/dac/adi-axi-dac.c index 6d56428e623d..e44463f48bf5 100644 --- a/drivers/iio/dac/adi-axi-dac.c +++ b/drivers/iio/dac/adi-axi-dac.c @@ -452,7 +452,7 @@ static int axi_dac_data_source_set(struct iio_backend *back, unsigned int chan, struct axi_dac_state *st = iio_backend_get_priv(back); switch (data) { - case IIO_BACKEND_INTERNAL_CONTINUOS_WAVE: + case IIO_BACKEND_INTERNAL_CONTINUOUS_WAVE: return regmap_update_bits(st->regmap, AXI_DAC_REG_CHAN_CNTRL_7(chan), AXI_DAC_DATA_SEL, diff --git a/include/linux/iio/backend.h b/include/linux/iio/backend.h index 4e81931703ab..29c4cf0bd761 100644 --- a/include/linux/iio/backend.h +++ b/include/linux/iio/backend.h @@ -17,7 +17,7 @@ enum iio_backend_data_type { }; enum iio_backend_data_source { - IIO_BACKEND_INTERNAL_CONTINUOS_WAVE, + IIO_BACKEND_INTERNAL_CONTINUOUS_WAVE, IIO_BACKEND_EXTERNAL, IIO_BACKEND_DATA_SOURCE_MAX }; -- cgit v1.2.3 From f44e94afbb340be90100f8a172ebb14a9e717c8b Mon Sep 17 00:00:00 2001 From: Nuno Sa Date: Fri, 26 Jul 2024 10:23:15 +0200 Subject: iio: core: annotate masklength as __private Now that all users are using the proper accessors, we can mark masklength as __private so that no one tries to write. We also get help from checkers in warning us in case someone does it. To access the private field from IIO core code, we need to use the ACCESS_PRIVATE() macro. Signed-off-by: Nuno Sa Link: https://patch.msgid.link/20240726-dev-iio-masklength-private3-v1-23-82913fc0fb87@analog.com Signed-off-by: Jonathan Cameron --- drivers/iio/industrialio-buffer.c | 2 +- include/linux/iio/iio.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c index 3d0b1d25fdd7..8104696cd475 100644 --- a/drivers/iio/industrialio-buffer.c +++ b/drivers/iio/industrialio-buffer.c @@ -2269,7 +2269,7 @@ int iio_buffers_alloc_sysfs_and_mask(struct iio_dev *indio_dev) for (i = 0; i < indio_dev->num_channels; i++) ml = max(ml, channels[i].scan_index + 1); - indio_dev->masklength = ml; + ACCESS_PRIVATE(indio_dev, masklength) = ml; } if (!iio_dev_opaque->attached_buffers_cnt) diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index dd6bbc468283..f6c0499853bb 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -609,7 +609,7 @@ struct iio_dev { int scan_bytes; const unsigned long *available_scan_masks; - unsigned masklength; + unsigned __private masklength; const unsigned long *active_scan_mask; bool scan_timestamp; struct iio_trigger *trig; @@ -861,7 +861,7 @@ static inline const struct iio_scan_type */ static inline unsigned int iio_get_masklength(const struct iio_dev *indio_dev) { - return indio_dev->masklength; + return ACCESS_PRIVATE(indio_dev, masklength); } /** -- cgit v1.2.3 From d092b6869817208326005df0a656e3bb9724d89f Mon Sep 17 00:00:00 2001 From: Julien Stephan Date: Wed, 31 Jul 2024 09:05:43 +0200 Subject: iio: core: add function to retrieve active_scan_mask index Add a function to retrieve the index of the active scan mask inside the available scan masks array. As in iio_scan_mask_match and iio_sanity_check_avail_scan_masks, this function does not handle multi-long masks correctly. It only checks the first long to be zero, and will use such mask as a terminator even if there was bits set after the first long. This should be fine since the available_scan_mask has already been sanity tested using iio_sanity_check_avail_scan_masks. See iio_scan_mask_match and iio_sanity_check_avail_scan_masks for more details Signed-off-by: Julien Stephan Reviewed-by: David Lechner Link: https://patch.msgid.link/20240731-ad7380-add-single-ended-chips-v2-2-cd63bf05744c@baylibre.com Signed-off-by: Jonathan Cameron --- drivers/iio/industrialio-core.c | 43 +++++++++++++++++++++++++++++++++++++++++ include/linux/iio/iio.h | 2 ++ 2 files changed, 45 insertions(+) (limited to 'include/linux') diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index e6fad8a6a1fc..f18f48c7eb03 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -1965,6 +1965,49 @@ static void iio_sanity_check_avail_scan_masks(struct iio_dev *indio_dev) } } +/** + * iio_active_scan_mask_index - Get index of the active scan mask inside the + * available scan masks array + * @indio_dev: the IIO device containing the active and available scan masks + * + * Returns: the index or -EINVAL if active_scan_mask is not set + */ +int iio_active_scan_mask_index(struct iio_dev *indio_dev) + +{ + const unsigned long *av_masks; + unsigned int masklength = iio_get_masklength(indio_dev); + int i = 0; + + if (!indio_dev->active_scan_mask) + return -EINVAL; + + /* + * As in iio_scan_mask_match and iio_sanity_check_avail_scan_masks, + * the condition here do not handle multi-long masks correctly. + * It only checks the first long to be zero, and will use such mask + * as a terminator even if there was bits set after the first long. + * + * This should be fine since the available_scan_mask has already been + * sanity tested using iio_sanity_check_avail_scan_masks. + * + * See iio_scan_mask_match and iio_sanity_check_avail_scan_masks for + * more details + */ + av_masks = indio_dev->available_scan_masks; + while (*av_masks) { + if (indio_dev->active_scan_mask == av_masks) + return i; + av_masks += BITS_TO_LONGS(masklength); + i++; + } + + dev_warn(indio_dev->dev.parent, + "active scan mask is not part of the avaialable scan masks\n"); + return -EINVAL; +} +EXPORT_SYMBOL_GPL(iio_active_scan_mask_index); + int __iio_device_register(struct iio_dev *indio_dev, struct module *this_mod) { struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev); diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index f6c0499853bb..3a735a9a9eae 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -864,6 +864,8 @@ static inline unsigned int iio_get_masklength(const struct iio_dev *indio_dev) return ACCESS_PRIVATE(indio_dev, masklength); } +int iio_active_scan_mask_index(struct iio_dev *indio_dev); + /** * iio_for_each_active_channel - Iterated over active channels * @indio_dev: the IIO device -- cgit v1.2.3 From 2256f37e24b1979f9a97de0b76cabbf8544a8aff Mon Sep 17 00:00:00 2001 From: Nuno Sa Date: Fri, 2 Aug 2024 16:26:59 +0200 Subject: iio: backend: introduce struct iio_backend_info Instead of only passing the backend ops when calling devm_iio_backend_register(), pass an info like structure that will contains the ops and additional information. Fow now, the backend name is being added as that will be used by the debugFS interface introduced in a later patch. It also opens the door for further customizations passed by backends. All users of devm_iio_backend_register() were updated accordingly. Signed-off-by: Nuno Sa Link: https://patch.msgid.link/20240802-dev-iio-backend-add-debugfs-v2-1-4cb62852f0d0@analog.com Signed-off-by: Jonathan Cameron --- drivers/iio/adc/adi-axi-adc.c | 7 ++++++- drivers/iio/dac/adi-axi-dac.c | 7 ++++++- drivers/iio/industrialio-backend.c | 10 +++++----- include/linux/iio/backend.h | 12 +++++++++++- 4 files changed, 28 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/iio/adc/adi-axi-adc.c b/drivers/iio/adc/adi-axi-adc.c index 21ce7564e83d..0a9d7433da30 100644 --- a/drivers/iio/adc/adi-axi-adc.c +++ b/drivers/iio/adc/adi-axi-adc.c @@ -273,7 +273,7 @@ static const struct regmap_config axi_adc_regmap_config = { .reg_stride = 4, }; -static const struct iio_backend_ops adi_axi_adc_generic = { +static const struct iio_backend_ops adi_axi_adc_ops = { .enable = axi_adc_enable, .disable = axi_adc_disable, .data_format_set = axi_adc_data_format_set, @@ -287,6 +287,11 @@ static const struct iio_backend_ops adi_axi_adc_generic = { .chan_status = axi_adc_chan_status, }; +static const struct iio_backend_info adi_axi_adc_generic = { + .name = "axi-adc", + .ops = &adi_axi_adc_ops, +}; + static int adi_axi_adc_probe(struct platform_device *pdev) { const unsigned int *expected_ver; diff --git a/drivers/iio/dac/adi-axi-dac.c b/drivers/iio/dac/adi-axi-dac.c index e44463f48bf5..9655705b158b 100644 --- a/drivers/iio/dac/adi-axi-dac.c +++ b/drivers/iio/dac/adi-axi-dac.c @@ -507,7 +507,7 @@ static int axi_dac_set_sample_rate(struct iio_backend *back, unsigned int chan, return 0; } -static const struct iio_backend_ops axi_dac_generic = { +static const struct iio_backend_ops axi_dac_generic_ops = { .enable = axi_dac_enable, .disable = axi_dac_disable, .request_buffer = axi_dac_request_buffer, @@ -519,6 +519,11 @@ static const struct iio_backend_ops axi_dac_generic = { .set_sample_rate = axi_dac_set_sample_rate, }; +static const struct iio_backend_info axi_dac_generic = { + .name = "axi-dac", + .ops = &axi_dac_generic_ops, +}; + static const struct regmap_config axi_dac_regmap_config = { .val_bits = 32, .reg_bits = 32, diff --git a/drivers/iio/industrialio-backend.c b/drivers/iio/industrialio-backend.c index f9da635cdfea..0cf80ffd2e61 100644 --- a/drivers/iio/industrialio-backend.c +++ b/drivers/iio/industrialio-backend.c @@ -641,20 +641,20 @@ static void iio_backend_unregister(void *arg) /** * devm_iio_backend_register - Device managed backend device register * @dev: Backend device being registered - * @ops: Backend ops + * @info: Backend info * @priv: Device private data * - * @ops is mandatory. Not providing it results in -EINVAL. + * @info is mandatory. Not providing it results in -EINVAL. * * RETURNS: * 0 on success, negative error number on failure. */ int devm_iio_backend_register(struct device *dev, - const struct iio_backend_ops *ops, void *priv) + const struct iio_backend_info *info, void *priv) { struct iio_backend *back; - if (!ops) + if (!info || !info->ops) return dev_err_probe(dev, -EINVAL, "No backend ops given\n"); /* @@ -667,7 +667,7 @@ int devm_iio_backend_register(struct device *dev, if (!back) return -ENOMEM; - back->ops = ops; + back->ops = info->ops; back->owner = dev->driver->owner; back->dev = dev; back->priv = priv; diff --git a/include/linux/iio/backend.h b/include/linux/iio/backend.h index 29c4cf0bd761..f120fa2e0a43 100644 --- a/include/linux/iio/backend.h +++ b/include/linux/iio/backend.h @@ -115,6 +115,16 @@ struct iio_backend_ops { const struct iio_chan_spec *chan, char *buf); }; +/** + * struct iio_backend_info - info structure for an iio_backend + * @name: Backend name. + * @ops: Backend operations. + */ +struct iio_backend_info { + const char *name; + const struct iio_backend_ops *ops; +}; + int iio_backend_chan_enable(struct iio_backend *back, unsigned int chan); int iio_backend_chan_disable(struct iio_backend *back, unsigned int chan); int devm_iio_backend_enable(struct device *dev, struct iio_backend *back); @@ -151,6 +161,6 @@ __devm_iio_backend_get_from_fwnode_lookup(struct device *dev, struct fwnode_handle *fwnode); int devm_iio_backend_register(struct device *dev, - const struct iio_backend_ops *ops, void *priv); + const struct iio_backend_info *info, void *priv); #endif -- cgit v1.2.3 From cdf01e0809a4c6c7877ea52401c2a6679df7aed6 Mon Sep 17 00:00:00 2001 From: Nuno Sa Date: Fri, 2 Aug 2024 16:27:00 +0200 Subject: iio: backend: add debugFs interface This adds a basic debugfs interface for backends. Two new ops are being added: * debugfs_reg_access: Analogous to the core IIO one but for backend devices. * debugfs_print_chan_status: One useful usecase for this one is for testing test tones in a digital interface and "ask" the backend to dump more details on why a test tone might have errors. Signed-off-by: Nuno Sa Link: https://patch.msgid.link/20240802-dev-iio-backend-add-debugfs-v2-2-4cb62852f0d0@analog.com Signed-off-by: Jonathan Cameron --- Documentation/ABI/testing/debugfs-iio-backend | 20 ++++ MAINTAINERS | 1 + drivers/iio/industrialio-backend.c | 145 ++++++++++++++++++++++++++ include/linux/iio/backend.h | 14 +++ 4 files changed, 180 insertions(+) create mode 100644 Documentation/ABI/testing/debugfs-iio-backend (limited to 'include/linux') diff --git a/Documentation/ABI/testing/debugfs-iio-backend b/Documentation/ABI/testing/debugfs-iio-backend new file mode 100644 index 000000000000..01ab94469432 --- /dev/null +++ b/Documentation/ABI/testing/debugfs-iio-backend @@ -0,0 +1,20 @@ +What: /sys/kernel/debug/iio/iio:deviceX/backendY/name +KernelVersion: 6.11 +Contact: linux-iio@vger.kernel.org +Description: + Name of Backend Y connected to device X. + +What: /sys/kernel/debug/iio/iio:deviceX/backendY/direct_reg_access +KernelVersion: 6.11 +Contact: linux-iio@vger.kernel.org +Description: + Directly access the registers of backend Y. Typical usage is: + + Reading address 0x50 + echo 0x50 > direct_reg_access + cat direct_reg_access + + Writing address 0x50 + echo 0x50 0x3 > direct_reg_access + //readback address 0x50 + cat direct_reg_access diff --git a/MAINTAINERS b/MAINTAINERS index 34281931a649..2708a9e9fc95 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10894,6 +10894,7 @@ M: Nuno Sa R: Olivier Moysan L: linux-iio@vger.kernel.org S: Maintained +F: Documentation/ABI/testing/debugfs-iio-backend F: drivers/iio/industrialio-backend.c F: include/linux/iio/backend.h diff --git a/drivers/iio/industrialio-backend.c b/drivers/iio/industrialio-backend.c index 0cf80ffd2e61..468eadeaf23d 100644 --- a/drivers/iio/industrialio-backend.c +++ b/drivers/iio/industrialio-backend.c @@ -32,6 +32,7 @@ #define dev_fmt(fmt) "iio-backend: " fmt #include +#include #include #include #include @@ -53,6 +54,14 @@ struct iio_backend { struct device *dev; struct module *owner; void *priv; + const char *name; + unsigned int cached_reg_addr; + /* + * This index is relative to the frontend. Meaning that for + * frontends with multiple backends, this will be the index of this + * backend. Used for the debugfs directory name. + */ + u8 idx; }; /* @@ -117,6 +126,138 @@ static DEFINE_MUTEX(iio_back_lock); __stringify(op)); \ } +static ssize_t iio_backend_debugfs_read_reg(struct file *file, + char __user *userbuf, + size_t count, loff_t *ppos) +{ + struct iio_backend *back = file->private_data; + char read_buf[20]; + unsigned int val; + int ret, len; + + ret = iio_backend_op_call(back, debugfs_reg_access, + back->cached_reg_addr, 0, &val); + if (ret) + return ret; + + len = scnprintf(read_buf, sizeof(read_buf), "0x%X\n", val); + + return simple_read_from_buffer(userbuf, count, ppos, read_buf, len); +} + +static ssize_t iio_backend_debugfs_write_reg(struct file *file, + const char __user *userbuf, + size_t count, loff_t *ppos) +{ + struct iio_backend *back = file->private_data; + unsigned int val; + char buf[80]; + ssize_t rc; + int ret; + + rc = simple_write_to_buffer(buf, sizeof(buf), ppos, userbuf, count); + if (rc < 0) + return rc; + + ret = sscanf(buf, "%i %i", &back->cached_reg_addr, &val); + + switch (ret) { + case 1: + return count; + case 2: + ret = iio_backend_op_call(back, debugfs_reg_access, + back->cached_reg_addr, val, NULL); + if (ret) + return ret; + return count; + default: + return -EINVAL; + } +} + +static const struct file_operations iio_backend_debugfs_reg_fops = { + .open = simple_open, + .read = iio_backend_debugfs_read_reg, + .write = iio_backend_debugfs_write_reg, +}; + +static ssize_t iio_backend_debugfs_read_name(struct file *file, + char __user *userbuf, + size_t count, loff_t *ppos) +{ + struct iio_backend *back = file->private_data; + char name[128]; + int len; + + len = scnprintf(name, sizeof(name), "%s\n", back->name); + + return simple_read_from_buffer(userbuf, count, ppos, name, len); +} + +static const struct file_operations iio_backend_debugfs_name_fops = { + .open = simple_open, + .read = iio_backend_debugfs_read_name, +}; + +/** + * iio_backend_debugfs_add - Add debugfs interfaces for Backends + * @back: Backend device + * @indio_dev: IIO device + */ +void iio_backend_debugfs_add(struct iio_backend *back, + struct iio_dev *indio_dev) +{ + struct dentry *d = iio_get_debugfs_dentry(indio_dev); + struct dentry *back_d; + char name[128]; + + if (!IS_ENABLED(CONFIG_DEBUG_FS) || !d) + return; + if (!back->ops->debugfs_reg_access && !back->name) + return; + + snprintf(name, sizeof(name), "backend%d", back->idx); + + back_d = debugfs_create_dir(name, d); + if (!back_d) + return; + + if (back->ops->debugfs_reg_access) + debugfs_create_file("direct_reg_access", 0600, back_d, back, + &iio_backend_debugfs_reg_fops); + + if (back->name) + debugfs_create_file("name", 0400, back_d, back, + &iio_backend_debugfs_name_fops); +} +EXPORT_SYMBOL_NS_GPL(iio_backend_debugfs_add, IIO_BACKEND); + +/** + * iio_backend_debugfs_print_chan_status - Print channel status + * @back: Backend device + * @chan: Channel number + * @buf: Buffer where to print the status + * @len: Available space + * + * One usecase where this is useful is for testing test tones in a digital + * interface and "ask" the backend to dump more details on why a test tone might + * have errors. + * + * RETURNS: + * Number of copied bytes on success, negative error code on failure. + */ +ssize_t iio_backend_debugfs_print_chan_status(struct iio_backend *back, + unsigned int chan, char *buf, + size_t len) +{ + if (!IS_ENABLED(CONFIG_DEBUG_FS)) + return -ENODEV; + + return iio_backend_op_call(back, debugfs_print_chan_status, chan, buf, + len); +} +EXPORT_SYMBOL_NS_GPL(iio_backend_debugfs_print_chan_status, IIO_BACKEND); + /** * iio_backend_chan_enable - Enable a backend channel * @back: Backend device @@ -577,6 +718,9 @@ struct iio_backend *devm_iio_backend_get(struct device *dev, const char *name) if (ret) return ERR_PTR(ret); + if (name) + back->idx = index; + return back; } @@ -668,6 +812,7 @@ int devm_iio_backend_register(struct device *dev, return -ENOMEM; back->ops = info->ops; + back->name = info->name; back->owner = dev->driver->owner; back->dev = dev; back->priv = priv; diff --git a/include/linux/iio/backend.h b/include/linux/iio/backend.h index f120fa2e0a43..9d0dba7ab9e7 100644 --- a/include/linux/iio/backend.h +++ b/include/linux/iio/backend.h @@ -22,6 +22,8 @@ enum iio_backend_data_source { IIO_BACKEND_DATA_SOURCE_MAX }; +#define iio_backend_debugfs_ptr(ptr) PTR_IF(IS_ENABLED(CONFIG_DEBUG_FS), ptr) + /** * IIO_BACKEND_EX_INFO - Helper for an IIO extended channel attribute * @_name: Attribute name @@ -81,6 +83,8 @@ enum iio_backend_sample_trigger { * @extend_chan_spec: Extend an IIO channel. * @ext_info_set: Extended info setter. * @ext_info_get: Extended info getter. + * @debugfs_print_chan_status: Print channel status into a buffer. + * @debugfs_reg_access: Read or write register value of backend. **/ struct iio_backend_ops { int (*enable)(struct iio_backend *back); @@ -113,6 +117,11 @@ struct iio_backend_ops { const char *buf, size_t len); int (*ext_info_get)(struct iio_backend *back, uintptr_t private, const struct iio_chan_spec *chan, char *buf); + int (*debugfs_print_chan_status)(struct iio_backend *back, + unsigned int chan, char *buf, + size_t len); + int (*debugfs_reg_access)(struct iio_backend *back, unsigned int reg, + unsigned int writeval, unsigned int *readval); }; /** @@ -163,4 +172,9 @@ __devm_iio_backend_get_from_fwnode_lookup(struct device *dev, int devm_iio_backend_register(struct device *dev, const struct iio_backend_info *info, void *priv); +ssize_t iio_backend_debugfs_print_chan_status(struct iio_backend *back, + unsigned int chan, char *buf, + size_t len); +void iio_backend_debugfs_add(struct iio_backend *back, + struct iio_dev *indio_dev); #endif -- cgit v1.2.3 From b001635a7c3014fe7745a507840c5d8f58235c04 Mon Sep 17 00:00:00 2001 From: Nuno Sa Date: Fri, 2 Aug 2024 16:27:01 +0200 Subject: iio: backend: add a modified prbs23 support Support ADI specific prb23 sequence that can be used both for calibrating or debugging digital interfaces. Signed-off-by: Nuno Sa Link: https://patch.msgid.link/20240802-dev-iio-backend-add-debugfs-v2-3-4cb62852f0d0@analog.com Signed-off-by: Jonathan Cameron --- include/linux/iio/backend.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/backend.h b/include/linux/iio/backend.h index 9d0dba7ab9e7..2b9d1aa86552 100644 --- a/include/linux/iio/backend.h +++ b/include/linux/iio/backend.h @@ -56,6 +56,8 @@ enum iio_backend_test_pattern { IIO_BACKEND_NO_TEST_PATTERN, /* modified prbs9 */ IIO_BACKEND_ADI_PRBS_9A = 32, + /* modified prbs23 */ + IIO_BACKEND_ADI_PRBS_23A, IIO_BACKEND_TEST_PATTERN_MAX }; -- cgit v1.2.3 From d21fe1e9a6a44e752e227d3a43f41aed790dad95 Mon Sep 17 00:00:00 2001 From: Inochi Amaoto Date: Thu, 18 Jul 2024 10:23:54 +0800 Subject: pinctrl: pinconf-generic: Add support for "input-schmitt-microvolt" property Add "input-schmitt-microvolt" property to generic options used for DT parsing files. This enables drivers, which use generic pin configurations, to get the value passed to this property. Signed-off-by: Inochi Amaoto Link: https://lore.kernel.org/IA1PR20MB4953806785BA04E075DC4F03BBAC2@IA1PR20MB4953.namprd20.prod.outlook.com Signed-off-by: Linus Walleij --- drivers/pinctrl/pinconf-generic.c | 2 ++ include/linux/pinctrl/pinconf-generic.h | 3 +++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/drivers/pinctrl/pinconf-generic.c b/drivers/pinctrl/pinconf-generic.c index a499b8af5c1f..0b13d7f17b32 100644 --- a/drivers/pinctrl/pinconf-generic.c +++ b/drivers/pinctrl/pinconf-generic.c @@ -44,6 +44,7 @@ static const struct pin_config_item conf_items[] = { PCONFDUMP(PIN_CONFIG_INPUT_DEBOUNCE, "input debounce", "usec", true), PCONFDUMP(PIN_CONFIG_INPUT_ENABLE, "input enabled", NULL, false), PCONFDUMP(PIN_CONFIG_INPUT_SCHMITT, "input schmitt trigger", NULL, false), + PCONFDUMP(PIN_CONFIG_INPUT_SCHMITT_UV, "input schmitt threshold", "uV", true), PCONFDUMP(PIN_CONFIG_INPUT_SCHMITT_ENABLE, "input schmitt enabled", NULL, false), PCONFDUMP(PIN_CONFIG_MODE_LOW_POWER, "pin low power", "mode", true), PCONFDUMP(PIN_CONFIG_OUTPUT_ENABLE, "output enabled", NULL, false), @@ -177,6 +178,7 @@ static const struct pinconf_generic_params dt_params[] = { { "input-schmitt", PIN_CONFIG_INPUT_SCHMITT, 0 }, { "input-schmitt-disable", PIN_CONFIG_INPUT_SCHMITT_ENABLE, 0 }, { "input-schmitt-enable", PIN_CONFIG_INPUT_SCHMITT_ENABLE, 1 }, + { "input-schmitt-microvolts", PIN_CONFIG_INPUT_SCHMITT_UV, 0 }, { "low-power-disable", PIN_CONFIG_MODE_LOW_POWER, 0 }, { "low-power-enable", PIN_CONFIG_MODE_LOW_POWER, 1 }, { "output-disable", PIN_CONFIG_OUTPUT_ENABLE, 0 }, diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h index a65d3d078e58..53cfde98433d 100644 --- a/include/linux/pinctrl/pinconf-generic.h +++ b/include/linux/pinctrl/pinconf-generic.h @@ -81,6 +81,8 @@ struct pinctrl_map; * @PIN_CONFIG_INPUT_SCHMITT_ENABLE: control schmitt-trigger mode on the pin. * If the argument != 0, schmitt-trigger mode is enabled. If it's 0, * schmitt-trigger mode is disabled. + * @PIN_CONFIG_INPUT_SCHMITT_UV: this will configure an input pin to run in + * schmitt-trigger mode. The argument is in uV. * @PIN_CONFIG_MODE_LOW_POWER: this will configure the pin for low power * operation, if several modes of operation are supported these can be * passed in the argument on a custom form, else just use argument 1 @@ -132,6 +134,7 @@ enum pin_config_param { PIN_CONFIG_INPUT_ENABLE, PIN_CONFIG_INPUT_SCHMITT, PIN_CONFIG_INPUT_SCHMITT_ENABLE, + PIN_CONFIG_INPUT_SCHMITT_UV, PIN_CONFIG_MODE_LOW_POWER, PIN_CONFIG_MODE_PWM, PIN_CONFIG_OUTPUT, -- cgit v1.2.3 From f17c06c6608ad4ecd2ccf321753fb511812d821b Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Fri, 2 Aug 2024 16:22:14 +0100 Subject: i2c: Fix conditional for substituting empty ACPI functions Add IS_ENABLED(CONFIG_I2C) to the conditional around a bunch of ACPI functions. The conditional around these functions depended only on CONFIG_ACPI. But the functions are implemented in I2C core, so are only present if CONFIG_I2C is enabled. Signed-off-by: Richard Fitzgerald Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 07e33bbc9256..7eedd0c662da 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -1066,7 +1066,7 @@ static inline int of_i2c_get_board_info(struct device *dev, struct acpi_resource; struct acpi_resource_i2c_serialbus; -#if IS_ENABLED(CONFIG_ACPI) +#if IS_ENABLED(CONFIG_ACPI) && IS_ENABLED(CONFIG_I2C) bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares, struct acpi_resource_i2c_serialbus **i2c); int i2c_acpi_client_count(struct acpi_device *adev); -- cgit v1.2.3 From b88f55389ad27f05ed84af9e1026aa64dbfabc9a Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Sun, 4 Aug 2024 18:48:10 +0900 Subject: profiling: remove profile=sleep support The kernel sleep profile is no longer working due to a recursive locking bug introduced by commit 42a20f86dc19 ("sched: Add wrapper for get_wchan() to keep task blocked") Booting with the 'profile=sleep' kernel command line option added or executing # echo -n sleep > /sys/kernel/profiling after boot causes the system to lock up. Lockdep reports kthreadd/3 is trying to acquire lock: ffff93ac82e08d58 (&p->pi_lock){....}-{2:2}, at: get_wchan+0x32/0x70 but task is already holding lock: ffff93ac82e08d58 (&p->pi_lock){....}-{2:2}, at: try_to_wake_up+0x53/0x370 with the call trace being lock_acquire+0xc8/0x2f0 get_wchan+0x32/0x70 __update_stats_enqueue_sleeper+0x151/0x430 enqueue_entity+0x4b0/0x520 enqueue_task_fair+0x92/0x6b0 ttwu_do_activate+0x73/0x140 try_to_wake_up+0x213/0x370 swake_up_locked+0x20/0x50 complete+0x2f/0x40 kthread+0xfb/0x180 However, since nobody noticed this regression for more than two years, let's remove 'profile=sleep' support based on the assumption that nobody needs this functionality. Fixes: 42a20f86dc19 ("sched: Add wrapper for get_wchan() to keep task blocked") Cc: stable@vger.kernel.org # v5.16+ Signed-off-by: Tetsuo Handa Signed-off-by: Linus Torvalds --- Documentation/admin-guide/kernel-parameters.txt | 4 +--- include/linux/profile.h | 1 - kernel/profile.c | 11 +---------- kernel/sched/stats.c | 10 ---------- 4 files changed, 2 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index f1384c7b59c9..09126bb8cc9f 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -4798,11 +4798,9 @@ profile= [KNL] Enable kernel profiling via /proc/profile Format: [,] - Param: : "schedule", "sleep", or "kvm" + Param: : "schedule" or "kvm" [defaults to kernel profiling] Param: "schedule" - profile schedule points. - Param: "sleep" - profile D-state sleeping (millisecs). - Requires CONFIG_SCHEDSTATS Param: "kvm" - profile VM exits. Param: - step/bucket size as a power of 2 for statistical time based profiling. diff --git a/include/linux/profile.h b/include/linux/profile.h index 2fb487f61d12..3f53cdb0c27c 100644 --- a/include/linux/profile.h +++ b/include/linux/profile.h @@ -10,7 +10,6 @@ #define CPU_PROFILING 1 #define SCHED_PROFILING 2 -#define SLEEP_PROFILING 3 #define KVM_PROFILING 4 struct proc_dir_entry; diff --git a/kernel/profile.c b/kernel/profile.c index ff68d3816182..1fcf1adcf4eb 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -50,20 +50,11 @@ EXPORT_SYMBOL_GPL(prof_on); int profile_setup(char *str) { static const char schedstr[] = "schedule"; - static const char sleepstr[] = "sleep"; static const char kvmstr[] = "kvm"; const char *select = NULL; int par; - if (!strncmp(str, sleepstr, strlen(sleepstr))) { -#ifdef CONFIG_SCHEDSTATS - force_schedstat_enabled(); - prof_on = SLEEP_PROFILING; - select = sleepstr; -#else - pr_warn("kernel sleep profiling requires CONFIG_SCHEDSTATS\n"); -#endif /* CONFIG_SCHEDSTATS */ - } else if (!strncmp(str, schedstr, strlen(schedstr))) { + if (!strncmp(str, schedstr, strlen(schedstr))) { prof_on = SCHED_PROFILING; select = schedstr; } else if (!strncmp(str, kvmstr, strlen(kvmstr))) { diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c index 78e48f5426ee..eb0cdcd4d921 100644 --- a/kernel/sched/stats.c +++ b/kernel/sched/stats.c @@ -92,16 +92,6 @@ void __update_stats_enqueue_sleeper(struct rq *rq, struct task_struct *p, trace_sched_stat_blocked(p, delta); - /* - * Blocking time is in units of nanosecs, so shift by - * 20 to get a milliseconds-range estimation of the - * amount of time that the task spent sleeping: - */ - if (unlikely(prof_on == SLEEP_PROFILING)) { - profile_hits(SLEEP_PROFILING, - (void *)get_wchan(p), - delta >> 20); - } account_scheduler_latency(p, delta >> 10, 0); } } -- cgit v1.2.3 From 0e8b53979ac86eddb3fd76264025a70071a25574 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Mon, 5 Aug 2024 14:01:21 +0900 Subject: bpf: kprobe: remove unused declaring of bpf_kprobe_override After the commit 66665ad2f102 ("tracing/kprobe: bpf: Compare instruction pointer with original one"), "bpf_kprobe_override" is not used anywhere anymore, and we can remove it now. Link: https://lore.kernel.org/all/20240710085939.11520-1-dongml2@chinatelecom.cn/ Fixes: 66665ad2f102 ("tracing/kprobe: bpf: Compare instruction pointer with original one") Signed-off-by: Menglong Dong Acked-by: Jiri Olsa Signed-off-by: Masami Hiramatsu (Google) --- include/linux/trace_events.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 9df3e2973626..9435185c10ef 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -880,7 +880,6 @@ do { \ struct perf_event; DECLARE_PER_CPU(struct pt_regs, perf_trace_regs); -DECLARE_PER_CPU(int, bpf_kprobe_override); extern int perf_trace_init(struct perf_event *event); extern void perf_trace_destroy(struct perf_event *event); -- cgit v1.2.3 From d7bdb8e6aabe218fd980768a1486434e42761539 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Mon, 27 May 2024 16:25:51 +0200 Subject: pmdomain: core: Enable s2idle for CPU PM domains on PREEMPT_RT To allow a genpd provider for a CPU PM domain to enter a domain-idle-state during s2idle on a PREEMPT_RT based configuration, we can't use the regular spinlock, as they are turned into sleepable locks on PREEMPT_RT. To address this problem, let's convert into using the raw spinlock, but only for genpd providers that have the GENPD_FLAG_CPU_DOMAIN bit set. In this way, the lock can still be acquired/released in atomic context, which is needed in the idle-path for PREEMPT_RT. Do note that the genpd power-on/off notifiers may also be fired during s2idle, but these are already prepared for PREEMPT_RT as they are based on the raw notifiers. However, consumers of them may need to adopt accordingly to work properly on PREEMPT_RT. Signed-off-by: Ulf Hansson Tested-by: Raghavendra Kakarla # qcm6490 with PREEMPT_RT set Acked-by: Sebastian Andrzej Siewior Link: https://lore.kernel.org/r/20240527142557.321610-2-ulf.hansson@linaro.org --- drivers/pmdomain/core.c | 47 ++++++++++++++++++++++++++++++++++++++++++++++- include/linux/pm_domain.h | 5 ++++- 2 files changed, 50 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/pmdomain/core.c b/drivers/pmdomain/core.c index 7a61aa88c061..8c798a46ffec 100644 --- a/drivers/pmdomain/core.c +++ b/drivers/pmdomain/core.c @@ -117,6 +117,48 @@ static const struct genpd_lock_ops genpd_spin_ops = { .unlock = genpd_unlock_spin, }; +static void genpd_lock_raw_spin(struct generic_pm_domain *genpd) + __acquires(&genpd->raw_slock) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&genpd->raw_slock, flags); + genpd->raw_lock_flags = flags; +} + +static void genpd_lock_nested_raw_spin(struct generic_pm_domain *genpd, + int depth) + __acquires(&genpd->raw_slock) +{ + unsigned long flags; + + raw_spin_lock_irqsave_nested(&genpd->raw_slock, flags, depth); + genpd->raw_lock_flags = flags; +} + +static int genpd_lock_interruptible_raw_spin(struct generic_pm_domain *genpd) + __acquires(&genpd->raw_slock) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&genpd->raw_slock, flags); + genpd->raw_lock_flags = flags; + return 0; +} + +static void genpd_unlock_raw_spin(struct generic_pm_domain *genpd) + __releases(&genpd->raw_slock) +{ + raw_spin_unlock_irqrestore(&genpd->raw_slock, genpd->raw_lock_flags); +} + +static const struct genpd_lock_ops genpd_raw_spin_ops = { + .lock = genpd_lock_raw_spin, + .lock_nested = genpd_lock_nested_raw_spin, + .lock_interruptible = genpd_lock_interruptible_raw_spin, + .unlock = genpd_unlock_raw_spin, +}; + #define genpd_lock(p) p->lock_ops->lock(p) #define genpd_lock_nested(p, d) p->lock_ops->lock_nested(p, d) #define genpd_lock_interruptible(p) p->lock_ops->lock_interruptible(p) @@ -2143,7 +2185,10 @@ static void genpd_free_data(struct generic_pm_domain *genpd) static void genpd_lock_init(struct generic_pm_domain *genpd) { - if (genpd_is_irq_safe(genpd)) { + if (genpd_is_cpu_domain(genpd)) { + raw_spin_lock_init(&genpd->raw_slock); + genpd->lock_ops = &genpd_raw_spin_ops; + } else if (genpd_is_irq_safe(genpd)) { spin_lock_init(&genpd->slock); genpd->lock_ops = &genpd_spin_ops; } else { diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 858c8e7851fb..b86bb52858ac 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -198,8 +198,11 @@ struct generic_pm_domain { spinlock_t slock; unsigned long lock_flags; }; + struct { + raw_spinlock_t raw_slock; + unsigned long raw_lock_flags; + }; }; - }; static inline struct generic_pm_domain *pd_to_genpd(struct dev_pm_domain *pd) -- cgit v1.2.3 From d5934e76316e84eced836b6b2bafae1837d1cd58 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 29 Mar 2024 16:48:48 -0700 Subject: cleanup: Add usage and style documentation When proposing that PCI grow some new cleanup helpers for pci_dev_put() and pci_dev_{lock,unlock} [1], Bjorn had some fundamental questions about expectations and best practices. Upon reviewing an updated changelog with those details he recommended adding them to documentation in the header file itself. Add that documentation and link it into the rendering for Documentation/core-api/. Signed-off-by: Dan Williams Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Jonathan Cameron Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/171175585714.2192972.12661675876300167762.stgit@dwillia2-xfh.jf.intel.com --- Documentation/core-api/cleanup.rst | 8 +++ Documentation/core-api/index.rst | 1 + include/linux/cleanup.h | 136 +++++++++++++++++++++++++++++++++++++ 3 files changed, 145 insertions(+) create mode 100644 Documentation/core-api/cleanup.rst (limited to 'include/linux') diff --git a/Documentation/core-api/cleanup.rst b/Documentation/core-api/cleanup.rst new file mode 100644 index 000000000000..527eb2f8ec6e --- /dev/null +++ b/Documentation/core-api/cleanup.rst @@ -0,0 +1,8 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=========================== +Scope-based Cleanup Helpers +=========================== + +.. kernel-doc:: include/linux/cleanup.h + :doc: scope-based cleanup helpers diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst index f147854700e4..b99d2fb3e2f1 100644 --- a/Documentation/core-api/index.rst +++ b/Documentation/core-api/index.rst @@ -35,6 +35,7 @@ Library functionality that is used throughout the kernel. kobject kref + cleanup assoc_array xarray maple_tree diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h index d9e613803df1..9c6b4f2c0176 100644 --- a/include/linux/cleanup.h +++ b/include/linux/cleanup.h @@ -4,6 +4,142 @@ #include +/** + * DOC: scope-based cleanup helpers + * + * The "goto error" pattern is notorious for introducing subtle resource + * leaks. It is tedious and error prone to add new resource acquisition + * constraints into code paths that already have several unwind + * conditions. The "cleanup" helpers enable the compiler to help with + * this tedium and can aid in maintaining LIFO (last in first out) + * unwind ordering to avoid unintentional leaks. + * + * As drivers make up the majority of the kernel code base, here is an + * example of using these helpers to clean up PCI drivers. The target of + * the cleanups are occasions where a goto is used to unwind a device + * reference (pci_dev_put()), or unlock the device (pci_dev_unlock()) + * before returning. + * + * The DEFINE_FREE() macro can arrange for PCI device references to be + * dropped when the associated variable goes out of scope:: + * + * DEFINE_FREE(pci_dev_put, struct pci_dev *, if (_T) pci_dev_put(_T)) + * ... + * struct pci_dev *dev __free(pci_dev_put) = + * pci_get_slot(parent, PCI_DEVFN(0, 0)); + * + * The above will automatically call pci_dev_put() if @dev is non-NULL + * when @dev goes out of scope (automatic variable scope). If a function + * wants to invoke pci_dev_put() on error, but return @dev (i.e. without + * freeing it) on success, it can do:: + * + * return no_free_ptr(dev); + * + * ...or:: + * + * return_ptr(dev); + * + * The DEFINE_GUARD() macro can arrange for the PCI device lock to be + * dropped when the scope where guard() is invoked ends:: + * + * DEFINE_GUARD(pci_dev, struct pci_dev *, pci_dev_lock(_T), pci_dev_unlock(_T)) + * ... + * guard(pci_dev)(dev); + * + * The lifetime of the lock obtained by the guard() helper follows the + * scope of automatic variable declaration. Take the following example:: + * + * func(...) + * { + * if (...) { + * ... + * guard(pci_dev)(dev); // pci_dev_lock() invoked here + * ... + * } // <- implied pci_dev_unlock() triggered here + * } + * + * Observe the lock is held for the remainder of the "if ()" block not + * the remainder of "func()". + * + * Now, when a function uses both __free() and guard(), or multiple + * instances of __free(), the LIFO order of variable definition order + * matters. GCC documentation says: + * + * "When multiple variables in the same scope have cleanup attributes, + * at exit from the scope their associated cleanup functions are run in + * reverse order of definition (last defined, first cleanup)." + * + * When the unwind order matters it requires that variables be defined + * mid-function scope rather than at the top of the file. Take the + * following example and notice the bug highlighted by "!!":: + * + * LIST_HEAD(list); + * DEFINE_MUTEX(lock); + * + * struct object { + * struct list_head node; + * }; + * + * static struct object *alloc_add(void) + * { + * struct object *obj; + * + * lockdep_assert_held(&lock); + * obj = kzalloc(sizeof(*obj), GFP_KERNEL); + * if (obj) { + * LIST_HEAD_INIT(&obj->node); + * list_add(obj->node, &list): + * } + * return obj; + * } + * + * static void remove_free(struct object *obj) + * { + * lockdep_assert_held(&lock); + * list_del(&obj->node); + * kfree(obj); + * } + * + * DEFINE_FREE(remove_free, struct object *, if (_T) remove_free(_T)) + * static int init(void) + * { + * struct object *obj __free(remove_free) = NULL; + * int err; + * + * guard(mutex)(&lock); + * obj = alloc_add(); + * + * if (!obj) + * return -ENOMEM; + * + * err = other_init(obj); + * if (err) + * return err; // remove_free() called without the lock!! + * + * no_free_ptr(obj); + * return 0; + * } + * + * That bug is fixed by changing init() to call guard() and define + + * initialize @obj in this order:: + * + * guard(mutex)(&lock); + * struct object *obj __free(remove_free) = alloc_add(); + * + * Given that the "__free(...) = NULL" pattern for variables defined at + * the top of the function poses this potential interdependency problem + * the recommendation is to always define and assign variables in one + * statement and not group variable definitions at the top of the + * function when __free() is used. + * + * Lastly, given that the benefit of cleanup helpers is removal of + * "goto", and that the "goto" statement can jump between scopes, the + * expectation is that usage of "goto" and cleanup helpers is never + * mixed in the same function. I.e. for a given routine, convert all + * resources that need a "goto" cleanup to scope-based cleanup, or + * convert none of them. + */ + /* * DEFINE_FREE(name, type, free): * simple helper macro that defines the required wrapper for a __free() -- cgit v1.2.3 From a720dee5e039238a44c0142dfccdc0e35c1125f7 Mon Sep 17 00:00:00 2001 From: "Luke D. Jones" Date: Sat, 13 Jul 2024 19:47:33 +1200 Subject: hid-asus: use hid for brightness control on keyboard On almost all ASUS ROG series laptops the MCU used for the USB keyboard also has a HID packet used for setting the brightness. This is usually the same as the WMI method. But in some laptops the WMI method either is missing or doesn't work, so we should default to the HID control. Signed-off-by: Luke D. Jones Acked-by: Benjamin Tissoires Link: https://lore.kernel.org/r/20240713074733.77334-2-luke@ljones.dev Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede --- drivers/hid/hid-asus.c | 7 ++++++ drivers/platform/x86/asus-wmi.c | 3 ++- include/linux/platform_data/x86/asus-wmi.h | 36 ++++++++++++++++++++++++++++++ 3 files changed, 45 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index 37e6d25593c2..af57a5f03193 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -492,12 +492,19 @@ static void asus_kbd_backlight_work(struct work_struct *work) */ static bool asus_kbd_wmi_led_control_present(struct hid_device *hdev) { + struct asus_drvdata *drvdata = hid_get_drvdata(hdev); u32 value; int ret; if (!IS_ENABLED(CONFIG_ASUS_WMI)) return false; + if (drvdata->quirks & QUIRK_ROG_NKEY_KEYBOARD && + dmi_check_system(asus_use_hid_led_dmi_ids)) { + hid_info(hdev, "using HID for asus::kbd_backlight\n"); + return false; + } + ret = asus_wmi_evaluate_method(ASUS_WMI_METHODID_DSTS, ASUS_WMI_DEVID_KBD_BACKLIGHT, 0, &value); hid_dbg(hdev, "WMI backlight check: rc %d value %x", ret, value); diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 00669cf678fb..35ebb37f68bf 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -1714,7 +1714,8 @@ static int asus_wmi_led_init(struct asus_wmi *asus) goto error; } - if (!kbd_led_read(asus, &led_val, NULL)) { + if (!kbd_led_read(asus, &led_val, NULL) && !dmi_check_system(asus_use_hid_led_dmi_ids)) { + pr_info("using asus-wmi for asus::kbd_backlight\n"); asus->kbd_led_wk = led_val; asus->kbd_led.name = "asus::kbd_backlight"; asus->kbd_led.flags = LED_BRIGHT_HW_CHANGED; diff --git a/include/linux/platform_data/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h index 5e6f407b2def..b601b245a035 100644 --- a/include/linux/platform_data/x86/asus-wmi.h +++ b/include/linux/platform_data/x86/asus-wmi.h @@ -4,6 +4,7 @@ #include #include +#include /* WMI Methods */ #define ASUS_WMI_METHODID_SPEC 0x43455053 /* BIOS SPECification */ @@ -165,4 +166,39 @@ static inline int asus_wmi_evaluate_method(u32 method_id, u32 arg0, u32 arg1, } #endif +/* To be used by both hid-asus and asus-wmi to determine which controls kbd_brightness */ +static const struct dmi_system_id asus_use_hid_led_dmi_ids[] = { + { + .matches = { + DMI_MATCH(DMI_PRODUCT_FAMILY, "ROG Zephyrus"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_PRODUCT_FAMILY, "ROG Strix"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_PRODUCT_FAMILY, "ROG Flow"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GA403U"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GU605M"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "RC71L"), + }, + }, + { }, +}; + #endif /* __PLATFORM_DATA_X86_ASUS_WMI_H */ -- cgit v1.2.3 From 25162a4f64f8ba0065f300977589fe1f6af332f0 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Sun, 4 Aug 2024 17:16:25 -0700 Subject: Input: cyttsp4 - remove driver The cyttsp4 touchscreen driver was contributed in 2013 and since then has seen no updates. The driver uses platform data (no device tree support) and there are no users of it in the mainline kernel. There were occasional fixes to it for issues either found by static code analysis tools or via visual inspection, but otherwise the driver is completely untested. Remove the driver. Reviewed-by: Linus Walleij Reviewed-by: Javier Martinez Canillas Link: https://lore.kernel.org/r/ZrAZ2cUow_z838tp@google.com Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/Kconfig | 30 - drivers/input/touchscreen/Makefile | 5 +- drivers/input/touchscreen/cyttsp4_core.c | 2174 ------------------------- drivers/input/touchscreen/cyttsp4_core.h | 448 ----- drivers/input/touchscreen/cyttsp4_i2c.c | 72 - drivers/input/touchscreen/cyttsp4_spi.c | 187 --- drivers/input/touchscreen/cyttsp_core.h | 4 - drivers/input/touchscreen/cyttsp_i2c.c | 55 + drivers/input/touchscreen/cyttsp_i2c_common.c | 86 - include/linux/platform_data/cyttsp4.h | 62 - 10 files changed, 56 insertions(+), 3067 deletions(-) delete mode 100644 drivers/input/touchscreen/cyttsp4_core.c delete mode 100644 drivers/input/touchscreen/cyttsp4_core.h delete mode 100644 drivers/input/touchscreen/cyttsp4_i2c.c delete mode 100644 drivers/input/touchscreen/cyttsp4_spi.c delete mode 100644 drivers/input/touchscreen/cyttsp_i2c_common.c delete mode 100644 include/linux/platform_data/cyttsp4.h (limited to 'include/linux') diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig index 0df90c3d743b..1ac26fc2e3eb 100644 --- a/drivers/input/touchscreen/Kconfig +++ b/drivers/input/touchscreen/Kconfig @@ -254,36 +254,6 @@ config TOUCHSCREEN_CYTTSP_SPI To compile this driver as a module, choose M here: the module will be called cyttsp_spi. -config TOUCHSCREEN_CYTTSP4_CORE - tristate "Cypress TrueTouch Gen4 Touchscreen Driver" - help - Core driver for Cypress TrueTouch(tm) Standard Product - Generation4 touchscreen controllers. - - Say Y here if you have a Cypress Gen4 touchscreen. - - If unsure, say N. - - To compile this driver as a module, choose M here. - -config TOUCHSCREEN_CYTTSP4_I2C - tristate "support I2C bus connection" - depends on TOUCHSCREEN_CYTTSP4_CORE && I2C - help - Say Y here if the touchscreen is connected via I2C bus. - - To compile this driver as a module, choose M here: the - module will be called cyttsp4_i2c. - -config TOUCHSCREEN_CYTTSP4_SPI - tristate "support SPI bus connection" - depends on TOUCHSCREEN_CYTTSP4_CORE && SPI_MASTER - help - Say Y here if the touchscreen is connected via SPI bus. - - To compile this driver as a module, choose M here: the - module will be called cyttsp4_spi. - config TOUCHSCREEN_CYTTSP5 tristate "Cypress TrueTouch Gen5 Touchscreen Driver" depends on I2C diff --git a/drivers/input/touchscreen/Makefile b/drivers/input/touchscreen/Makefile index 04dc8039341b..82bc837ca01e 100644 --- a/drivers/input/touchscreen/Makefile +++ b/drivers/input/touchscreen/Makefile @@ -25,11 +25,8 @@ obj-$(CONFIG_TOUCHSCREEN_CHIPONE_ICN8505) += chipone_icn8505.o obj-$(CONFIG_TOUCHSCREEN_CY8CTMA140) += cy8ctma140.o obj-$(CONFIG_TOUCHSCREEN_CY8CTMG110) += cy8ctmg110_ts.o obj-$(CONFIG_TOUCHSCREEN_CYTTSP_CORE) += cyttsp_core.o -obj-$(CONFIG_TOUCHSCREEN_CYTTSP_I2C) += cyttsp_i2c.o cyttsp_i2c_common.o +obj-$(CONFIG_TOUCHSCREEN_CYTTSP_I2C) += cyttsp_i2c.o obj-$(CONFIG_TOUCHSCREEN_CYTTSP_SPI) += cyttsp_spi.o -obj-$(CONFIG_TOUCHSCREEN_CYTTSP4_CORE) += cyttsp4_core.o -obj-$(CONFIG_TOUCHSCREEN_CYTTSP4_I2C) += cyttsp4_i2c.o cyttsp_i2c_common.o -obj-$(CONFIG_TOUCHSCREEN_CYTTSP4_SPI) += cyttsp4_spi.o obj-$(CONFIG_TOUCHSCREEN_CYTTSP5) += cyttsp5.o obj-$(CONFIG_TOUCHSCREEN_DA9034) += da9034-ts.o obj-$(CONFIG_TOUCHSCREEN_DA9052) += da9052_tsi.o diff --git a/drivers/input/touchscreen/cyttsp4_core.c b/drivers/input/touchscreen/cyttsp4_core.c deleted file mode 100644 index 7cb26929dc73..000000000000 --- a/drivers/input/touchscreen/cyttsp4_core.c +++ /dev/null @@ -1,2174 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * cyttsp4_core.c - * Cypress TrueTouch(TM) Standard Product V4 Core driver module. - * For use with Cypress Txx4xx parts. - * Supported parts include: - * TMA4XX - * TMA1036 - * - * Copyright (C) 2012 Cypress Semiconductor - * - * Contact Cypress Semiconductor at www.cypress.com - */ - -#include "cyttsp4_core.h" -#include -#include -#include -#include -#include -#include -#include - -/* Timeout in ms. */ -#define CY_CORE_REQUEST_EXCLUSIVE_TIMEOUT 500 -#define CY_CORE_SLEEP_REQUEST_EXCLUSIVE_TIMEOUT 5000 -#define CY_CORE_MODE_CHANGE_TIMEOUT 1000 -#define CY_CORE_RESET_AND_WAIT_TIMEOUT 500 -#define CY_CORE_WAKEUP_TIMEOUT 500 - -#define CY_CORE_STARTUP_RETRY_COUNT 3 - -static const char * const cyttsp4_tch_abs_string[] = { - [CY_TCH_X] = "X", - [CY_TCH_Y] = "Y", - [CY_TCH_P] = "P", - [CY_TCH_T] = "T", - [CY_TCH_E] = "E", - [CY_TCH_O] = "O", - [CY_TCH_W] = "W", - [CY_TCH_MAJ] = "MAJ", - [CY_TCH_MIN] = "MIN", - [CY_TCH_OR] = "OR", - [CY_TCH_NUM_ABS] = "INVALID" -}; - -static const u8 ldr_exit[] = { - 0xFF, 0x01, 0x3B, 0x00, 0x00, 0x4F, 0x6D, 0x17 -}; - -static const u8 ldr_err_app[] = { - 0x01, 0x02, 0x00, 0x00, 0x55, 0xDD, 0x17 -}; - -static inline size_t merge_bytes(u8 high, u8 low) -{ - return (high << 8) + low; -} - -#ifdef VERBOSE_DEBUG -static void cyttsp4_pr_buf(struct device *dev, u8 *pr_buf, u8 *dptr, int size, - const char *data_name) -{ - int i, k; - const char fmt[] = "%02X "; - int max; - - if (!size) - return; - - max = (CY_MAX_PRBUF_SIZE - 1) - sizeof(CY_PR_TRUNCATED); - - pr_buf[0] = 0; - for (i = k = 0; i < size && k < max; i++, k += 3) - scnprintf(pr_buf + k, CY_MAX_PRBUF_SIZE, fmt, dptr[i]); - - dev_vdbg(dev, "%s: %s[0..%d]=%s%s\n", __func__, data_name, size - 1, - pr_buf, size <= max ? "" : CY_PR_TRUNCATED); -} -#else -#define cyttsp4_pr_buf(dev, pr_buf, dptr, size, data_name) do { } while (0) -#endif - -static int cyttsp4_load_status_regs(struct cyttsp4 *cd) -{ - struct cyttsp4_sysinfo *si = &cd->sysinfo; - struct device *dev = cd->dev; - int rc; - - rc = cyttsp4_adap_read(cd, CY_REG_BASE, si->si_ofs.mode_size, - si->xy_mode); - if (rc < 0) - dev_err(dev, "%s: fail read mode regs r=%d\n", - __func__, rc); - else - cyttsp4_pr_buf(dev, cd->pr_buf, si->xy_mode, - si->si_ofs.mode_size, "xy_mode"); - - return rc; -} - -static int cyttsp4_handshake(struct cyttsp4 *cd, u8 mode) -{ - u8 cmd = mode ^ CY_HST_TOGGLE; - int rc; - - /* - * Mode change issued, handshaking now will cause endless mode change - * requests, for sync mode modechange will do same with handshake - * */ - if (mode & CY_HST_MODE_CHANGE) - return 0; - - rc = cyttsp4_adap_write(cd, CY_REG_BASE, sizeof(cmd), &cmd); - if (rc < 0) - dev_err(cd->dev, "%s: bus write fail on handshake (ret=%d)\n", - __func__, rc); - - return rc; -} - -static int cyttsp4_hw_soft_reset(struct cyttsp4 *cd) -{ - u8 cmd = CY_HST_RESET; - int rc = cyttsp4_adap_write(cd, CY_REG_BASE, sizeof(cmd), &cmd); - if (rc < 0) { - dev_err(cd->dev, "%s: FAILED to execute SOFT reset\n", - __func__); - return rc; - } - return 0; -} - -static int cyttsp4_hw_hard_reset(struct cyttsp4 *cd) -{ - if (cd->cpdata->xres) { - cd->cpdata->xres(cd->cpdata, cd->dev); - dev_dbg(cd->dev, "%s: execute HARD reset\n", __func__); - return 0; - } - dev_err(cd->dev, "%s: FAILED to execute HARD reset\n", __func__); - return -ENOSYS; -} - -static int cyttsp4_hw_reset(struct cyttsp4 *cd) -{ - int rc = cyttsp4_hw_hard_reset(cd); - if (rc == -ENOSYS) - rc = cyttsp4_hw_soft_reset(cd); - return rc; -} - -/* - * Gets number of bits for a touch filed as parameter, - * sets maximum value for field which is used as bit mask - * and returns number of bytes required for that field - */ -static int cyttsp4_bits_2_bytes(unsigned int nbits, size_t *max) -{ - *max = 1UL << nbits; - return (nbits + 7) / 8; -} - -static int cyttsp4_si_data_offsets(struct cyttsp4 *cd) -{ - struct cyttsp4_sysinfo *si = &cd->sysinfo; - int rc = cyttsp4_adap_read(cd, CY_REG_BASE, sizeof(si->si_data), - &si->si_data); - if (rc < 0) { - dev_err(cd->dev, "%s: fail read sysinfo data offsets r=%d\n", - __func__, rc); - return rc; - } - - /* Print sysinfo data offsets */ - cyttsp4_pr_buf(cd->dev, cd->pr_buf, (u8 *)&si->si_data, - sizeof(si->si_data), "sysinfo_data_offsets"); - - /* convert sysinfo data offset bytes into integers */ - - si->si_ofs.map_sz = merge_bytes(si->si_data.map_szh, - si->si_data.map_szl); - si->si_ofs.map_sz = merge_bytes(si->si_data.map_szh, - si->si_data.map_szl); - si->si_ofs.cydata_ofs = merge_bytes(si->si_data.cydata_ofsh, - si->si_data.cydata_ofsl); - si->si_ofs.test_ofs = merge_bytes(si->si_data.test_ofsh, - si->si_data.test_ofsl); - si->si_ofs.pcfg_ofs = merge_bytes(si->si_data.pcfg_ofsh, - si->si_data.pcfg_ofsl); - si->si_ofs.opcfg_ofs = merge_bytes(si->si_data.opcfg_ofsh, - si->si_data.opcfg_ofsl); - si->si_ofs.ddata_ofs = merge_bytes(si->si_data.ddata_ofsh, - si->si_data.ddata_ofsl); - si->si_ofs.mdata_ofs = merge_bytes(si->si_data.mdata_ofsh, - si->si_data.mdata_ofsl); - return rc; -} - -static int cyttsp4_si_get_cydata(struct cyttsp4 *cd) -{ - struct cyttsp4_sysinfo *si = &cd->sysinfo; - int read_offset; - int mfgid_sz, calc_mfgid_sz; - void *p; - int rc; - - if (si->si_ofs.test_ofs <= si->si_ofs.cydata_ofs) { - dev_err(cd->dev, - "%s: invalid offset test_ofs: %zu, cydata_ofs: %zu\n", - __func__, si->si_ofs.test_ofs, si->si_ofs.cydata_ofs); - return -EINVAL; - } - - si->si_ofs.cydata_size = si->si_ofs.test_ofs - si->si_ofs.cydata_ofs; - dev_dbg(cd->dev, "%s: cydata size: %zd\n", __func__, - si->si_ofs.cydata_size); - - p = krealloc(si->si_ptrs.cydata, si->si_ofs.cydata_size, GFP_KERNEL); - if (p == NULL) { - dev_err(cd->dev, "%s: failed to allocate cydata memory\n", - __func__); - return -ENOMEM; - } - si->si_ptrs.cydata = p; - - read_offset = si->si_ofs.cydata_ofs; - - /* Read the CYDA registers up to MFGID field */ - rc = cyttsp4_adap_read(cd, read_offset, - offsetof(struct cyttsp4_cydata, mfgid_sz) - + sizeof(si->si_ptrs.cydata->mfgid_sz), - si->si_ptrs.cydata); - if (rc < 0) { - dev_err(cd->dev, "%s: fail read cydata r=%d\n", - __func__, rc); - return rc; - } - - /* Check MFGID size */ - mfgid_sz = si->si_ptrs.cydata->mfgid_sz; - calc_mfgid_sz = si->si_ofs.cydata_size - sizeof(struct cyttsp4_cydata); - if (mfgid_sz != calc_mfgid_sz) { - dev_err(cd->dev, "%s: mismatch in MFGID size, reported:%d calculated:%d\n", - __func__, mfgid_sz, calc_mfgid_sz); - return -EINVAL; - } - - read_offset += offsetof(struct cyttsp4_cydata, mfgid_sz) - + sizeof(si->si_ptrs.cydata->mfgid_sz); - - /* Read the CYDA registers for MFGID field */ - rc = cyttsp4_adap_read(cd, read_offset, si->si_ptrs.cydata->mfgid_sz, - si->si_ptrs.cydata->mfg_id); - if (rc < 0) { - dev_err(cd->dev, "%s: fail read cydata r=%d\n", - __func__, rc); - return rc; - } - - read_offset += si->si_ptrs.cydata->mfgid_sz; - - /* Read the rest of the CYDA registers */ - rc = cyttsp4_adap_read(cd, read_offset, - sizeof(struct cyttsp4_cydata) - - offsetof(struct cyttsp4_cydata, cyito_idh), - &si->si_ptrs.cydata->cyito_idh); - if (rc < 0) { - dev_err(cd->dev, "%s: fail read cydata r=%d\n", - __func__, rc); - return rc; - } - - cyttsp4_pr_buf(cd->dev, cd->pr_buf, (u8 *)si->si_ptrs.cydata, - si->si_ofs.cydata_size, "sysinfo_cydata"); - return rc; -} - -static int cyttsp4_si_get_test_data(struct cyttsp4 *cd) -{ - struct cyttsp4_sysinfo *si = &cd->sysinfo; - void *p; - int rc; - - if (si->si_ofs.pcfg_ofs <= si->si_ofs.test_ofs) { - dev_err(cd->dev, - "%s: invalid offset pcfg_ofs: %zu, test_ofs: %zu\n", - __func__, si->si_ofs.pcfg_ofs, si->si_ofs.test_ofs); - return -EINVAL; - } - - si->si_ofs.test_size = si->si_ofs.pcfg_ofs - si->si_ofs.test_ofs; - - p = krealloc(si->si_ptrs.test, si->si_ofs.test_size, GFP_KERNEL); - if (p == NULL) { - dev_err(cd->dev, "%s: failed to allocate test memory\n", - __func__); - return -ENOMEM; - } - si->si_ptrs.test = p; - - rc = cyttsp4_adap_read(cd, si->si_ofs.test_ofs, si->si_ofs.test_size, - si->si_ptrs.test); - if (rc < 0) { - dev_err(cd->dev, "%s: fail read test data r=%d\n", - __func__, rc); - return rc; - } - - cyttsp4_pr_buf(cd->dev, cd->pr_buf, - (u8 *)si->si_ptrs.test, si->si_ofs.test_size, - "sysinfo_test_data"); - if (si->si_ptrs.test->post_codel & - CY_POST_CODEL_WDG_RST) - dev_info(cd->dev, "%s: %s codel=%02X\n", - __func__, "Reset was a WATCHDOG RESET", - si->si_ptrs.test->post_codel); - - if (!(si->si_ptrs.test->post_codel & - CY_POST_CODEL_CFG_DATA_CRC_FAIL)) - dev_info(cd->dev, "%s: %s codel=%02X\n", __func__, - "Config Data CRC FAIL", - si->si_ptrs.test->post_codel); - - if (!(si->si_ptrs.test->post_codel & - CY_POST_CODEL_PANEL_TEST_FAIL)) - dev_info(cd->dev, "%s: %s codel=%02X\n", - __func__, "PANEL TEST FAIL", - si->si_ptrs.test->post_codel); - - dev_info(cd->dev, "%s: SCANNING is %s codel=%02X\n", - __func__, si->si_ptrs.test->post_codel & 0x08 ? - "ENABLED" : "DISABLED", - si->si_ptrs.test->post_codel); - return rc; -} - -static int cyttsp4_si_get_pcfg_data(struct cyttsp4 *cd) -{ - struct cyttsp4_sysinfo *si = &cd->sysinfo; - void *p; - int rc; - - if (si->si_ofs.opcfg_ofs <= si->si_ofs.pcfg_ofs) { - dev_err(cd->dev, - "%s: invalid offset opcfg_ofs: %zu, pcfg_ofs: %zu\n", - __func__, si->si_ofs.opcfg_ofs, si->si_ofs.pcfg_ofs); - return -EINVAL; - } - - si->si_ofs.pcfg_size = si->si_ofs.opcfg_ofs - si->si_ofs.pcfg_ofs; - - p = krealloc(si->si_ptrs.pcfg, si->si_ofs.pcfg_size, GFP_KERNEL); - if (p == NULL) { - dev_err(cd->dev, "%s: failed to allocate pcfg memory\n", - __func__); - return -ENOMEM; - } - si->si_ptrs.pcfg = p; - - rc = cyttsp4_adap_read(cd, si->si_ofs.pcfg_ofs, si->si_ofs.pcfg_size, - si->si_ptrs.pcfg); - if (rc < 0) { - dev_err(cd->dev, "%s: fail read pcfg data r=%d\n", - __func__, rc); - return rc; - } - - si->si_ofs.max_x = merge_bytes((si->si_ptrs.pcfg->res_xh - & CY_PCFG_RESOLUTION_X_MASK), si->si_ptrs.pcfg->res_xl); - si->si_ofs.x_origin = !!(si->si_ptrs.pcfg->res_xh - & CY_PCFG_ORIGIN_X_MASK); - si->si_ofs.max_y = merge_bytes((si->si_ptrs.pcfg->res_yh - & CY_PCFG_RESOLUTION_Y_MASK), si->si_ptrs.pcfg->res_yl); - si->si_ofs.y_origin = !!(si->si_ptrs.pcfg->res_yh - & CY_PCFG_ORIGIN_Y_MASK); - si->si_ofs.max_p = merge_bytes(si->si_ptrs.pcfg->max_zh, - si->si_ptrs.pcfg->max_zl); - - cyttsp4_pr_buf(cd->dev, cd->pr_buf, - (u8 *)si->si_ptrs.pcfg, - si->si_ofs.pcfg_size, "sysinfo_pcfg_data"); - return rc; -} - -static int cyttsp4_si_get_opcfg_data(struct cyttsp4 *cd) -{ - struct cyttsp4_sysinfo *si = &cd->sysinfo; - struct cyttsp4_tch_abs_params *tch; - struct cyttsp4_tch_rec_params *tch_old, *tch_new; - enum cyttsp4_tch_abs abs; - int i; - void *p; - int rc; - - if (si->si_ofs.ddata_ofs <= si->si_ofs.opcfg_ofs) { - dev_err(cd->dev, - "%s: invalid offset ddata_ofs: %zu, opcfg_ofs: %zu\n", - __func__, si->si_ofs.ddata_ofs, si->si_ofs.opcfg_ofs); - return -EINVAL; - } - - si->si_ofs.opcfg_size = si->si_ofs.ddata_ofs - si->si_ofs.opcfg_ofs; - - p = krealloc(si->si_ptrs.opcfg, si->si_ofs.opcfg_size, GFP_KERNEL); - if (p == NULL) { - dev_err(cd->dev, "%s: failed to allocate opcfg memory\n", - __func__); - return -ENOMEM; - } - si->si_ptrs.opcfg = p; - - rc = cyttsp4_adap_read(cd, si->si_ofs.opcfg_ofs, si->si_ofs.opcfg_size, - si->si_ptrs.opcfg); - if (rc < 0) { - dev_err(cd->dev, "%s: fail read opcfg data r=%d\n", - __func__, rc); - return rc; - } - si->si_ofs.cmd_ofs = si->si_ptrs.opcfg->cmd_ofs; - si->si_ofs.rep_ofs = si->si_ptrs.opcfg->rep_ofs; - si->si_ofs.rep_sz = (si->si_ptrs.opcfg->rep_szh * 256) + - si->si_ptrs.opcfg->rep_szl; - si->si_ofs.num_btns = si->si_ptrs.opcfg->num_btns; - si->si_ofs.num_btn_regs = (si->si_ofs.num_btns + - CY_NUM_BTN_PER_REG - 1) / CY_NUM_BTN_PER_REG; - si->si_ofs.tt_stat_ofs = si->si_ptrs.opcfg->tt_stat_ofs; - si->si_ofs.obj_cfg0 = si->si_ptrs.opcfg->obj_cfg0; - si->si_ofs.max_tchs = si->si_ptrs.opcfg->max_tchs & - CY_BYTE_OFS_MASK; - si->si_ofs.tch_rec_size = si->si_ptrs.opcfg->tch_rec_size & - CY_BYTE_OFS_MASK; - - /* Get the old touch fields */ - for (abs = CY_TCH_X; abs < CY_NUM_TCH_FIELDS; abs++) { - tch = &si->si_ofs.tch_abs[abs]; - tch_old = &si->si_ptrs.opcfg->tch_rec_old[abs]; - - tch->ofs = tch_old->loc & CY_BYTE_OFS_MASK; - tch->size = cyttsp4_bits_2_bytes(tch_old->size, - &tch->max); - tch->bofs = (tch_old->loc & CY_BOFS_MASK) >> CY_BOFS_SHIFT; - } - - /* button fields */ - si->si_ofs.btn_rec_size = si->si_ptrs.opcfg->btn_rec_size; - si->si_ofs.btn_diff_ofs = si->si_ptrs.opcfg->btn_diff_ofs; - si->si_ofs.btn_diff_size = si->si_ptrs.opcfg->btn_diff_size; - - if (si->si_ofs.tch_rec_size > CY_TMA1036_TCH_REC_SIZE) { - /* Get the extended touch fields */ - for (i = 0; i < CY_NUM_EXT_TCH_FIELDS; abs++, i++) { - tch = &si->si_ofs.tch_abs[abs]; - tch_new = &si->si_ptrs.opcfg->tch_rec_new[i]; - - tch->ofs = tch_new->loc & CY_BYTE_OFS_MASK; - tch->size = cyttsp4_bits_2_bytes(tch_new->size, - &tch->max); - tch->bofs = (tch_new->loc & CY_BOFS_MASK) >> CY_BOFS_SHIFT; - } - } - - for (abs = 0; abs < CY_TCH_NUM_ABS; abs++) { - dev_dbg(cd->dev, "%s: tch_rec_%s\n", __func__, - cyttsp4_tch_abs_string[abs]); - dev_dbg(cd->dev, "%s: ofs =%2zd\n", __func__, - si->si_ofs.tch_abs[abs].ofs); - dev_dbg(cd->dev, "%s: siz =%2zd\n", __func__, - si->si_ofs.tch_abs[abs].size); - dev_dbg(cd->dev, "%s: max =%2zd\n", __func__, - si->si_ofs.tch_abs[abs].max); - dev_dbg(cd->dev, "%s: bofs=%2zd\n", __func__, - si->si_ofs.tch_abs[abs].bofs); - } - - si->si_ofs.mode_size = si->si_ofs.tt_stat_ofs + 1; - si->si_ofs.data_size = si->si_ofs.max_tchs * - si->si_ptrs.opcfg->tch_rec_size; - - cyttsp4_pr_buf(cd->dev, cd->pr_buf, (u8 *)si->si_ptrs.opcfg, - si->si_ofs.opcfg_size, "sysinfo_opcfg_data"); - - return 0; -} - -static int cyttsp4_si_get_ddata(struct cyttsp4 *cd) -{ - struct cyttsp4_sysinfo *si = &cd->sysinfo; - void *p; - int rc; - - si->si_ofs.ddata_size = si->si_ofs.mdata_ofs - si->si_ofs.ddata_ofs; - - p = krealloc(si->si_ptrs.ddata, si->si_ofs.ddata_size, GFP_KERNEL); - if (p == NULL) { - dev_err(cd->dev, "%s: fail alloc ddata memory\n", __func__); - return -ENOMEM; - } - si->si_ptrs.ddata = p; - - rc = cyttsp4_adap_read(cd, si->si_ofs.ddata_ofs, si->si_ofs.ddata_size, - si->si_ptrs.ddata); - if (rc < 0) - dev_err(cd->dev, "%s: fail read ddata data r=%d\n", - __func__, rc); - else - cyttsp4_pr_buf(cd->dev, cd->pr_buf, - (u8 *)si->si_ptrs.ddata, - si->si_ofs.ddata_size, "sysinfo_ddata"); - return rc; -} - -static int cyttsp4_si_get_mdata(struct cyttsp4 *cd) -{ - struct cyttsp4_sysinfo *si = &cd->sysinfo; - void *p; - int rc; - - si->si_ofs.mdata_size = si->si_ofs.map_sz - si->si_ofs.mdata_ofs; - - p = krealloc(si->si_ptrs.mdata, si->si_ofs.mdata_size, GFP_KERNEL); - if (p == NULL) { - dev_err(cd->dev, "%s: fail alloc mdata memory\n", __func__); - return -ENOMEM; - } - si->si_ptrs.mdata = p; - - rc = cyttsp4_adap_read(cd, si->si_ofs.mdata_ofs, si->si_ofs.mdata_size, - si->si_ptrs.mdata); - if (rc < 0) - dev_err(cd->dev, "%s: fail read mdata data r=%d\n", - __func__, rc); - else - cyttsp4_pr_buf(cd->dev, cd->pr_buf, - (u8 *)si->si_ptrs.mdata, - si->si_ofs.mdata_size, "sysinfo_mdata"); - return rc; -} - -static int cyttsp4_si_get_btn_data(struct cyttsp4 *cd) -{ - struct cyttsp4_sysinfo *si = &cd->sysinfo; - int btn; - int num_defined_keys; - u16 *key_table; - void *p; - int rc = 0; - - if (si->si_ofs.num_btns) { - si->si_ofs.btn_keys_size = si->si_ofs.num_btns * - sizeof(struct cyttsp4_btn); - - p = krealloc(si->btn, si->si_ofs.btn_keys_size, - GFP_KERNEL|__GFP_ZERO); - if (p == NULL) { - dev_err(cd->dev, "%s: %s\n", __func__, - "fail alloc btn_keys memory"); - return -ENOMEM; - } - si->btn = p; - - if (cd->cpdata->sett[CY_IC_GRPNUM_BTN_KEYS] == NULL) - num_defined_keys = 0; - else if (cd->cpdata->sett[CY_IC_GRPNUM_BTN_KEYS]->data == NULL) - num_defined_keys = 0; - else - num_defined_keys = cd->cpdata->sett - [CY_IC_GRPNUM_BTN_KEYS]->size; - - for (btn = 0; btn < si->si_ofs.num_btns && - btn < num_defined_keys; btn++) { - key_table = (u16 *)cd->cpdata->sett - [CY_IC_GRPNUM_BTN_KEYS]->data; - si->btn[btn].key_code = key_table[btn]; - si->btn[btn].state = CY_BTN_RELEASED; - si->btn[btn].enabled = true; - } - for (; btn < si->si_ofs.num_btns; btn++) { - si->btn[btn].key_code = KEY_RESERVED; - si->btn[btn].state = CY_BTN_RELEASED; - si->btn[btn].enabled = true; - } - - return rc; - } - - si->si_ofs.btn_keys_size = 0; - kfree(si->btn); - si->btn = NULL; - return rc; -} - -static int cyttsp4_si_get_op_data_ptrs(struct cyttsp4 *cd) -{ - struct cyttsp4_sysinfo *si = &cd->sysinfo; - void *p; - - p = krealloc(si->xy_mode, si->si_ofs.mode_size, GFP_KERNEL|__GFP_ZERO); - if (p == NULL) - return -ENOMEM; - si->xy_mode = p; - - p = krealloc(si->xy_data, si->si_ofs.data_size, GFP_KERNEL|__GFP_ZERO); - if (p == NULL) - return -ENOMEM; - si->xy_data = p; - - p = krealloc(si->btn_rec_data, - si->si_ofs.btn_rec_size * si->si_ofs.num_btns, - GFP_KERNEL|__GFP_ZERO); - if (p == NULL) - return -ENOMEM; - si->btn_rec_data = p; - - return 0; -} - -static void cyttsp4_si_put_log_data(struct cyttsp4 *cd) -{ - struct cyttsp4_sysinfo *si = &cd->sysinfo; - dev_dbg(cd->dev, "%s: cydata_ofs =%4zd siz=%4zd\n", __func__, - si->si_ofs.cydata_ofs, si->si_ofs.cydata_size); - dev_dbg(cd->dev, "%s: test_ofs =%4zd siz=%4zd\n", __func__, - si->si_ofs.test_ofs, si->si_ofs.test_size); - dev_dbg(cd->dev, "%s: pcfg_ofs =%4zd siz=%4zd\n", __func__, - si->si_ofs.pcfg_ofs, si->si_ofs.pcfg_size); - dev_dbg(cd->dev, "%s: opcfg_ofs =%4zd siz=%4zd\n", __func__, - si->si_ofs.opcfg_ofs, si->si_ofs.opcfg_size); - dev_dbg(cd->dev, "%s: ddata_ofs =%4zd siz=%4zd\n", __func__, - si->si_ofs.ddata_ofs, si->si_ofs.ddata_size); - dev_dbg(cd->dev, "%s: mdata_ofs =%4zd siz=%4zd\n", __func__, - si->si_ofs.mdata_ofs, si->si_ofs.mdata_size); - - dev_dbg(cd->dev, "%s: cmd_ofs =%4zd\n", __func__, - si->si_ofs.cmd_ofs); - dev_dbg(cd->dev, "%s: rep_ofs =%4zd\n", __func__, - si->si_ofs.rep_ofs); - dev_dbg(cd->dev, "%s: rep_sz =%4zd\n", __func__, - si->si_ofs.rep_sz); - dev_dbg(cd->dev, "%s: num_btns =%4zd\n", __func__, - si->si_ofs.num_btns); - dev_dbg(cd->dev, "%s: num_btn_regs =%4zd\n", __func__, - si->si_ofs.num_btn_regs); - dev_dbg(cd->dev, "%s: tt_stat_ofs =%4zd\n", __func__, - si->si_ofs.tt_stat_ofs); - dev_dbg(cd->dev, "%s: tch_rec_size =%4zd\n", __func__, - si->si_ofs.tch_rec_size); - dev_dbg(cd->dev, "%s: max_tchs =%4zd\n", __func__, - si->si_ofs.max_tchs); - dev_dbg(cd->dev, "%s: mode_size =%4zd\n", __func__, - si->si_ofs.mode_size); - dev_dbg(cd->dev, "%s: data_size =%4zd\n", __func__, - si->si_ofs.data_size); - dev_dbg(cd->dev, "%s: map_sz =%4zd\n", __func__, - si->si_ofs.map_sz); - - dev_dbg(cd->dev, "%s: btn_rec_size =%2zd\n", __func__, - si->si_ofs.btn_rec_size); - dev_dbg(cd->dev, "%s: btn_diff_ofs =%2zd\n", __func__, - si->si_ofs.btn_diff_ofs); - dev_dbg(cd->dev, "%s: btn_diff_size =%2zd\n", __func__, - si->si_ofs.btn_diff_size); - - dev_dbg(cd->dev, "%s: max_x = 0x%04zX (%zd)\n", __func__, - si->si_ofs.max_x, si->si_ofs.max_x); - dev_dbg(cd->dev, "%s: x_origin = %zd (%s)\n", __func__, - si->si_ofs.x_origin, - si->si_ofs.x_origin == CY_NORMAL_ORIGIN ? - "left corner" : "right corner"); - dev_dbg(cd->dev, "%s: max_y = 0x%04zX (%zd)\n", __func__, - si->si_ofs.max_y, si->si_ofs.max_y); - dev_dbg(cd->dev, "%s: y_origin = %zd (%s)\n", __func__, - si->si_ofs.y_origin, - si->si_ofs.y_origin == CY_NORMAL_ORIGIN ? - "upper corner" : "lower corner"); - dev_dbg(cd->dev, "%s: max_p = 0x%04zX (%zd)\n", __func__, - si->si_ofs.max_p, si->si_ofs.max_p); - - dev_dbg(cd->dev, "%s: xy_mode=%p xy_data=%p\n", __func__, - si->xy_mode, si->xy_data); -} - -static int cyttsp4_get_sysinfo_regs(struct cyttsp4 *cd) -{ - struct cyttsp4_sysinfo *si = &cd->sysinfo; - int rc; - - rc = cyttsp4_si_data_offsets(cd); - if (rc < 0) - return rc; - - rc = cyttsp4_si_get_cydata(cd); - if (rc < 0) - return rc; - - rc = cyttsp4_si_get_test_data(cd); - if (rc < 0) - return rc; - - rc = cyttsp4_si_get_pcfg_data(cd); - if (rc < 0) - return rc; - - rc = cyttsp4_si_get_opcfg_data(cd); - if (rc < 0) - return rc; - - rc = cyttsp4_si_get_ddata(cd); - if (rc < 0) - return rc; - - rc = cyttsp4_si_get_mdata(cd); - if (rc < 0) - return rc; - - rc = cyttsp4_si_get_btn_data(cd); - if (rc < 0) - return rc; - - rc = cyttsp4_si_get_op_data_ptrs(cd); - if (rc < 0) { - dev_err(cd->dev, "%s: failed to get_op_data\n", - __func__); - return rc; - } - - cyttsp4_si_put_log_data(cd); - - /* provide flow control handshake */ - rc = cyttsp4_handshake(cd, si->si_data.hst_mode); - if (rc < 0) - dev_err(cd->dev, "%s: handshake fail on sysinfo reg\n", - __func__); - - si->ready = true; - return rc; -} - -static void cyttsp4_queue_startup_(struct cyttsp4 *cd) -{ - if (cd->startup_state == STARTUP_NONE) { - cd->startup_state = STARTUP_QUEUED; - schedule_work(&cd->startup_work); - dev_dbg(cd->dev, "%s: cyttsp4_startup queued\n", __func__); - } else { - dev_dbg(cd->dev, "%s: startup_state = %d\n", __func__, - cd->startup_state); - } -} - -static void cyttsp4_report_slot_liftoff(struct cyttsp4_mt_data *md, - int max_slots) -{ - int t; - - if (md->num_prv_tch == 0) - return; - - for (t = 0; t < max_slots; t++) { - input_mt_slot(md->input, t); - input_mt_report_slot_inactive(md->input); - } -} - -static void cyttsp4_lift_all(struct cyttsp4_mt_data *md) -{ - if (!md->si) - return; - - if (md->num_prv_tch != 0) { - cyttsp4_report_slot_liftoff(md, - md->si->si_ofs.tch_abs[CY_TCH_T].max); - input_sync(md->input); - md->num_prv_tch = 0; - } -} - -static void cyttsp4_get_touch_axis(struct cyttsp4_mt_data *md, - int *axis, int size, int max, u8 *xy_data, int bofs) -{ - int nbyte; - int next; - - for (nbyte = 0, *axis = 0, next = 0; nbyte < size; nbyte++) { - dev_vdbg(&md->input->dev, - "%s: *axis=%02X(%d) size=%d max=%08X xy_data=%p" - " xy_data[%d]=%02X(%d) bofs=%d\n", - __func__, *axis, *axis, size, max, xy_data, next, - xy_data[next], xy_data[next], bofs); - *axis = (*axis * 256) + (xy_data[next] >> bofs); - next++; - } - - *axis &= max - 1; - - dev_vdbg(&md->input->dev, - "%s: *axis=%02X(%d) size=%d max=%08X xy_data=%p" - " xy_data[%d]=%02X(%d)\n", - __func__, *axis, *axis, size, max, xy_data, next, - xy_data[next], xy_data[next]); -} - -static void cyttsp4_get_touch(struct cyttsp4_mt_data *md, - struct cyttsp4_touch *touch, u8 *xy_data) -{ - struct device *dev = &md->input->dev; - struct cyttsp4_sysinfo *si = md->si; - enum cyttsp4_tch_abs abs; - bool flipped; - - for (abs = CY_TCH_X; abs < CY_TCH_NUM_ABS; abs++) { - cyttsp4_get_touch_axis(md, &touch->abs[abs], - si->si_ofs.tch_abs[abs].size, - si->si_ofs.tch_abs[abs].max, - xy_data + si->si_ofs.tch_abs[abs].ofs, - si->si_ofs.tch_abs[abs].bofs); - dev_vdbg(dev, "%s: get %s=%04X(%d)\n", __func__, - cyttsp4_tch_abs_string[abs], - touch->abs[abs], touch->abs[abs]); - } - - if (md->pdata->flags & CY_FLAG_FLIP) { - swap(touch->abs[CY_TCH_X], touch->abs[CY_TCH_Y]); - flipped = true; - } else - flipped = false; - - if (md->pdata->flags & CY_FLAG_INV_X) { - if (flipped) - touch->abs[CY_TCH_X] = md->si->si_ofs.max_y - - touch->abs[CY_TCH_X]; - else - touch->abs[CY_TCH_X] = md->si->si_ofs.max_x - - touch->abs[CY_TCH_X]; - } - if (md->pdata->flags & CY_FLAG_INV_Y) { - if (flipped) - touch->abs[CY_TCH_Y] = md->si->si_ofs.max_x - - touch->abs[CY_TCH_Y]; - else - touch->abs[CY_TCH_Y] = md->si->si_ofs.max_y - - touch->abs[CY_TCH_Y]; - } - - dev_vdbg(dev, "%s: flip=%s inv-x=%s inv-y=%s x=%04X(%d) y=%04X(%d)\n", - __func__, flipped ? "true" : "false", - md->pdata->flags & CY_FLAG_INV_X ? "true" : "false", - md->pdata->flags & CY_FLAG_INV_Y ? "true" : "false", - touch->abs[CY_TCH_X], touch->abs[CY_TCH_X], - touch->abs[CY_TCH_Y], touch->abs[CY_TCH_Y]); -} - -static void cyttsp4_final_sync(struct input_dev *input, int max_slots, int *ids) -{ - int t; - - for (t = 0; t < max_slots; t++) { - if (ids[t]) - continue; - input_mt_slot(input, t); - input_mt_report_slot_inactive(input); - } - - input_sync(input); -} - -static void cyttsp4_get_mt_touches(struct cyttsp4_mt_data *md, int num_cur_tch) -{ - struct device *dev = &md->input->dev; - struct cyttsp4_sysinfo *si = md->si; - struct cyttsp4_touch tch; - int sig; - int i, j, t = 0; - int ids[max(CY_TMA1036_MAX_TCH, CY_TMA4XX_MAX_TCH)]; - - memset(ids, 0, si->si_ofs.tch_abs[CY_TCH_T].max * sizeof(int)); - for (i = 0; i < num_cur_tch; i++) { - cyttsp4_get_touch(md, &tch, si->xy_data + - (i * si->si_ofs.tch_rec_size)); - if ((tch.abs[CY_TCH_T] < md->pdata->frmwrk->abs - [(CY_ABS_ID_OST * CY_NUM_ABS_SET) + CY_MIN_OST]) || - (tch.abs[CY_TCH_T] > md->pdata->frmwrk->abs - [(CY_ABS_ID_OST * CY_NUM_ABS_SET) + CY_MAX_OST])) { - dev_err(dev, "%s: tch=%d -> bad trk_id=%d max_id=%d\n", - __func__, i, tch.abs[CY_TCH_T], - md->pdata->frmwrk->abs[(CY_ABS_ID_OST * - CY_NUM_ABS_SET) + CY_MAX_OST]); - continue; - } - - /* use 0 based track id's */ - sig = md->pdata->frmwrk->abs - [(CY_ABS_ID_OST * CY_NUM_ABS_SET) + 0]; - if (sig != CY_IGNORE_VALUE) { - t = tch.abs[CY_TCH_T] - md->pdata->frmwrk->abs - [(CY_ABS_ID_OST * CY_NUM_ABS_SET) + CY_MIN_OST]; - if (tch.abs[CY_TCH_E] == CY_EV_LIFTOFF) { - dev_dbg(dev, "%s: t=%d e=%d lift-off\n", - __func__, t, tch.abs[CY_TCH_E]); - goto cyttsp4_get_mt_touches_pr_tch; - } - input_mt_slot(md->input, t); - input_mt_report_slot_state(md->input, MT_TOOL_FINGER, - true); - ids[t] = true; - } - - /* all devices: position and pressure fields */ - for (j = 0; j <= CY_ABS_W_OST; j++) { - sig = md->pdata->frmwrk->abs[((CY_ABS_X_OST + j) * - CY_NUM_ABS_SET) + 0]; - if (sig != CY_IGNORE_VALUE) - input_report_abs(md->input, sig, - tch.abs[CY_TCH_X + j]); - } - if (si->si_ofs.tch_rec_size > CY_TMA1036_TCH_REC_SIZE) { - /* - * TMA400 size and orientation fields: - * if pressure is non-zero and major touch - * signal is zero, then set major and minor touch - * signals to minimum non-zero value - */ - if (tch.abs[CY_TCH_P] > 0 && tch.abs[CY_TCH_MAJ] == 0) - tch.abs[CY_TCH_MAJ] = tch.abs[CY_TCH_MIN] = 1; - - /* Get the extended touch fields */ - for (j = 0; j < CY_NUM_EXT_TCH_FIELDS; j++) { - sig = md->pdata->frmwrk->abs - [((CY_ABS_MAJ_OST + j) * - CY_NUM_ABS_SET) + 0]; - if (sig != CY_IGNORE_VALUE) - input_report_abs(md->input, sig, - tch.abs[CY_TCH_MAJ + j]); - } - } - -cyttsp4_get_mt_touches_pr_tch: - if (si->si_ofs.tch_rec_size > CY_TMA1036_TCH_REC_SIZE) - dev_dbg(dev, - "%s: t=%d x=%d y=%d z=%d M=%d m=%d o=%d e=%d\n", - __func__, t, - tch.abs[CY_TCH_X], - tch.abs[CY_TCH_Y], - tch.abs[CY_TCH_P], - tch.abs[CY_TCH_MAJ], - tch.abs[CY_TCH_MIN], - tch.abs[CY_TCH_OR], - tch.abs[CY_TCH_E]); - else - dev_dbg(dev, - "%s: t=%d x=%d y=%d z=%d e=%d\n", __func__, - t, - tch.abs[CY_TCH_X], - tch.abs[CY_TCH_Y], - tch.abs[CY_TCH_P], - tch.abs[CY_TCH_E]); - } - - cyttsp4_final_sync(md->input, si->si_ofs.tch_abs[CY_TCH_T].max, ids); - - md->num_prv_tch = num_cur_tch; - - return; -} - -/* read xy_data for all current touches */ -static int cyttsp4_xy_worker(struct cyttsp4 *cd) -{ - struct cyttsp4_mt_data *md = &cd->md; - struct device *dev = &md->input->dev; - struct cyttsp4_sysinfo *si = md->si; - u8 num_cur_tch; - u8 hst_mode; - u8 rep_len; - u8 rep_stat; - u8 tt_stat; - int rc = 0; - - /* - * Get event data from cyttsp4 device. - * The event data includes all data - * for all active touches. - * Event data also includes button data - */ - /* - * Use 2 reads: - * 1st read to get mode + button bytes + touch count (core) - * 2nd read (optional) to get touch 1 - touch n data - */ - hst_mode = si->xy_mode[CY_REG_BASE]; - rep_len = si->xy_mode[si->si_ofs.rep_ofs]; - rep_stat = si->xy_mode[si->si_ofs.rep_ofs + 1]; - tt_stat = si->xy_mode[si->si_ofs.tt_stat_ofs]; - dev_vdbg(dev, "%s: %s%02X %s%d %s%02X %s%02X\n", __func__, - "hst_mode=", hst_mode, "rep_len=", rep_len, - "rep_stat=", rep_stat, "tt_stat=", tt_stat); - - num_cur_tch = GET_NUM_TOUCHES(tt_stat); - dev_vdbg(dev, "%s: num_cur_tch=%d\n", __func__, num_cur_tch); - - if (rep_len == 0 && num_cur_tch > 0) { - dev_err(dev, "%s: report length error rep_len=%d num_tch=%d\n", - __func__, rep_len, num_cur_tch); - goto cyttsp4_xy_worker_exit; - } - - /* read touches */ - if (num_cur_tch > 0) { - rc = cyttsp4_adap_read(cd, si->si_ofs.tt_stat_ofs + 1, - num_cur_tch * si->si_ofs.tch_rec_size, - si->xy_data); - if (rc < 0) { - dev_err(dev, "%s: read fail on touch regs r=%d\n", - __func__, rc); - goto cyttsp4_xy_worker_exit; - } - } - - /* print xy data */ - cyttsp4_pr_buf(dev, cd->pr_buf, si->xy_data, num_cur_tch * - si->si_ofs.tch_rec_size, "xy_data"); - - /* check any error conditions */ - if (IS_BAD_PKT(rep_stat)) { - dev_dbg(dev, "%s: Invalid buffer detected\n", __func__); - rc = 0; - goto cyttsp4_xy_worker_exit; - } - - if (IS_LARGE_AREA(tt_stat)) - dev_dbg(dev, "%s: Large area detected\n", __func__); - - if (num_cur_tch > si->si_ofs.max_tchs) { - dev_err(dev, "%s: too many tch; set to max tch (n=%d c=%zd)\n", - __func__, num_cur_tch, si->si_ofs.max_tchs); - num_cur_tch = si->si_ofs.max_tchs; - } - - /* extract xy_data for all currently reported touches */ - dev_vdbg(dev, "%s: extract data num_cur_tch=%d\n", __func__, - num_cur_tch); - if (num_cur_tch) - cyttsp4_get_mt_touches(md, num_cur_tch); - else - cyttsp4_lift_all(md); - - rc = 0; - -cyttsp4_xy_worker_exit: - return rc; -} - -static int cyttsp4_mt_attention(struct cyttsp4 *cd) -{ - struct device *dev = cd->dev; - struct cyttsp4_mt_data *md = &cd->md; - int rc = 0; - - if (!md->si) - return 0; - - mutex_lock(&md->report_lock); - if (!md->is_suspended) { - /* core handles handshake */ - rc = cyttsp4_xy_worker(cd); - } else { - dev_vdbg(dev, "%s: Ignoring report while suspended\n", - __func__); - } - mutex_unlock(&md->report_lock); - if (rc < 0) - dev_err(dev, "%s: xy_worker error r=%d\n", __func__, rc); - - return rc; -} - -static irqreturn_t cyttsp4_irq(int irq, void *handle) -{ - struct cyttsp4 *cd = handle; - struct device *dev = cd->dev; - enum cyttsp4_mode cur_mode; - u8 cmd_ofs = cd->sysinfo.si_ofs.cmd_ofs; - u8 mode[3]; - int rc; - - /* - * Check whether this IRQ should be ignored (external) - * This should be the very first thing to check since - * ignore_irq may be set for a very short period of time - */ - if (atomic_read(&cd->ignore_irq)) { - dev_vdbg(dev, "%s: Ignoring IRQ\n", __func__); - return IRQ_HANDLED; - } - - dev_dbg(dev, "%s int:0x%x\n", __func__, cd->int_status); - - mutex_lock(&cd->system_lock); - - /* Just to debug */ - if (cd->sleep_state == SS_SLEEP_ON || cd->sleep_state == SS_SLEEPING) - dev_vdbg(dev, "%s: Received IRQ while in sleep\n", __func__); - - rc = cyttsp4_adap_read(cd, CY_REG_BASE, sizeof(mode), mode); - if (rc) { - dev_err(cd->dev, "%s: Fail read adapter r=%d\n", __func__, rc); - goto cyttsp4_irq_exit; - } - dev_vdbg(dev, "%s mode[0-2]:0x%X 0x%X 0x%X\n", __func__, - mode[0], mode[1], mode[2]); - - if (IS_BOOTLOADER(mode[0], mode[1])) { - cur_mode = CY_MODE_BOOTLOADER; - dev_vdbg(dev, "%s: bl running\n", __func__); - if (cd->mode == CY_MODE_BOOTLOADER) { - /* Signal bootloader heartbeat heard */ - wake_up(&cd->wait_q); - goto cyttsp4_irq_exit; - } - - /* switch to bootloader */ - dev_dbg(dev, "%s: restart switch to bl m=%d -> m=%d\n", - __func__, cd->mode, cur_mode); - - /* catch operation->bl glitch */ - if (cd->mode != CY_MODE_UNKNOWN) { - /* Incase startup_state do not let startup_() */ - cd->mode = CY_MODE_UNKNOWN; - cyttsp4_queue_startup_(cd); - goto cyttsp4_irq_exit; - } - - /* - * do not wake thread on this switch since - * it is possible to get an early heartbeat - * prior to performing the reset - */ - cd->mode = cur_mode; - - goto cyttsp4_irq_exit; - } - - switch (mode[0] & CY_HST_MODE) { - case CY_HST_OPERATE: - cur_mode = CY_MODE_OPERATIONAL; - dev_vdbg(dev, "%s: operational\n", __func__); - break; - case CY_HST_CAT: - cur_mode = CY_MODE_CAT; - dev_vdbg(dev, "%s: CaT\n", __func__); - break; - case CY_HST_SYSINFO: - cur_mode = CY_MODE_SYSINFO; - dev_vdbg(dev, "%s: sysinfo\n", __func__); - break; - default: - cur_mode = CY_MODE_UNKNOWN; - dev_err(dev, "%s: unknown HST mode 0x%02X\n", __func__, - mode[0]); - break; - } - - /* Check whether this IRQ should be ignored (internal) */ - if (cd->int_status & CY_INT_IGNORE) { - dev_vdbg(dev, "%s: Ignoring IRQ\n", __func__); - goto cyttsp4_irq_exit; - } - - /* Check for wake up interrupt */ - if (cd->int_status & CY_INT_AWAKE) { - cd->int_status &= ~CY_INT_AWAKE; - wake_up(&cd->wait_q); - dev_vdbg(dev, "%s: Received wake up interrupt\n", __func__); - goto cyttsp4_irq_handshake; - } - - /* Expecting mode change interrupt */ - if ((cd->int_status & CY_INT_MODE_CHANGE) - && (mode[0] & CY_HST_MODE_CHANGE) == 0) { - cd->int_status &= ~CY_INT_MODE_CHANGE; - dev_dbg(dev, "%s: finish mode switch m=%d -> m=%d\n", - __func__, cd->mode, cur_mode); - cd->mode = cur_mode; - wake_up(&cd->wait_q); - goto cyttsp4_irq_handshake; - } - - /* compare current core mode to current device mode */ - dev_vdbg(dev, "%s: cd->mode=%d cur_mode=%d\n", - __func__, cd->mode, cur_mode); - if ((mode[0] & CY_HST_MODE_CHANGE) == 0 && cd->mode != cur_mode) { - /* Unexpected mode change occurred */ - dev_err(dev, "%s %d->%d 0x%x\n", __func__, cd->mode, - cur_mode, cd->int_status); - dev_dbg(dev, "%s: Unexpected mode change, startup\n", - __func__); - cyttsp4_queue_startup_(cd); - goto cyttsp4_irq_exit; - } - - /* Expecting command complete interrupt */ - dev_vdbg(dev, "%s: command byte:0x%x\n", __func__, mode[cmd_ofs]); - if ((cd->int_status & CY_INT_EXEC_CMD) - && mode[cmd_ofs] & CY_CMD_COMPLETE) { - cd->int_status &= ~CY_INT_EXEC_CMD; - dev_vdbg(dev, "%s: Received command complete interrupt\n", - __func__); - wake_up(&cd->wait_q); - /* - * It is possible to receive a single interrupt for - * command complete and touch/button status report. - * Continue processing for a possible status report. - */ - } - - /* This should be status report, read status regs */ - if (cd->mode == CY_MODE_OPERATIONAL) { - dev_vdbg(dev, "%s: Read status registers\n", __func__); - rc = cyttsp4_load_status_regs(cd); - if (rc < 0) - dev_err(dev, "%s: fail read mode regs r=%d\n", - __func__, rc); - } - - cyttsp4_mt_attention(cd); - -cyttsp4_irq_handshake: - /* handshake the event */ - dev_vdbg(dev, "%s: Handshake mode=0x%02X r=%d\n", - __func__, mode[0], rc); - rc = cyttsp4_handshake(cd, mode[0]); - if (rc < 0) - dev_err(dev, "%s: Fail handshake mode=0x%02X r=%d\n", - __func__, mode[0], rc); - - /* - * a non-zero udelay period is required for using - * IRQF_TRIGGER_LOW in order to delay until the - * device completes isr deassert - */ - udelay(cd->cpdata->level_irq_udelay); - -cyttsp4_irq_exit: - mutex_unlock(&cd->system_lock); - return IRQ_HANDLED; -} - -static void cyttsp4_start_wd_timer(struct cyttsp4 *cd) -{ - if (!CY_WATCHDOG_TIMEOUT) - return; - - mod_timer(&cd->watchdog_timer, jiffies + - msecs_to_jiffies(CY_WATCHDOG_TIMEOUT)); -} - -static void cyttsp4_stop_wd_timer(struct cyttsp4 *cd) -{ - if (!CY_WATCHDOG_TIMEOUT) - return; - - /* - * Ensure we wait until the watchdog timer - * running on a different CPU finishes - */ - timer_shutdown_sync(&cd->watchdog_timer); - cancel_work_sync(&cd->watchdog_work); -} - -static void cyttsp4_watchdog_timer(struct timer_list *t) -{ - struct cyttsp4 *cd = from_timer(cd, t, watchdog_timer); - - dev_vdbg(cd->dev, "%s: Watchdog timer triggered\n", __func__); - - schedule_work(&cd->watchdog_work); - - return; -} - -static int cyttsp4_request_exclusive(struct cyttsp4 *cd, void *ownptr, - int timeout_ms) -{ - int t = msecs_to_jiffies(timeout_ms); - bool with_timeout = (timeout_ms != 0); - - mutex_lock(&cd->system_lock); - if (!cd->exclusive_dev && cd->exclusive_waits == 0) { - cd->exclusive_dev = ownptr; - goto exit; - } - - cd->exclusive_waits++; -wait: - mutex_unlock(&cd->system_lock); - if (with_timeout) { - t = wait_event_timeout(cd->wait_q, !cd->exclusive_dev, t); - if (IS_TMO(t)) { - dev_err(cd->dev, "%s: tmo waiting exclusive access\n", - __func__); - mutex_lock(&cd->system_lock); - cd->exclusive_waits--; - mutex_unlock(&cd->system_lock); - return -ETIME; - } - } else { - wait_event(cd->wait_q, !cd->exclusive_dev); - } - mutex_lock(&cd->system_lock); - if (cd->exclusive_dev) - goto wait; - cd->exclusive_dev = ownptr; - cd->exclusive_waits--; -exit: - mutex_unlock(&cd->system_lock); - - return 0; -} - -/* - * returns error if was not owned - */ -static int cyttsp4_release_exclusive(struct cyttsp4 *cd, void *ownptr) -{ - mutex_lock(&cd->system_lock); - if (cd->exclusive_dev != ownptr) { - mutex_unlock(&cd->system_lock); - return -EINVAL; - } - - dev_vdbg(cd->dev, "%s: exclusive_dev %p freed\n", - __func__, cd->exclusive_dev); - cd->exclusive_dev = NULL; - wake_up(&cd->wait_q); - mutex_unlock(&cd->system_lock); - return 0; -} - -static int cyttsp4_wait_bl_heartbeat(struct cyttsp4 *cd) -{ - long t; - int rc = 0; - - /* wait heartbeat */ - dev_vdbg(cd->dev, "%s: wait heartbeat...\n", __func__); - t = wait_event_timeout(cd->wait_q, cd->mode == CY_MODE_BOOTLOADER, - msecs_to_jiffies(CY_CORE_RESET_AND_WAIT_TIMEOUT)); - if (IS_TMO(t)) { - dev_err(cd->dev, "%s: tmo waiting bl heartbeat cd->mode=%d\n", - __func__, cd->mode); - rc = -ETIME; - } - - return rc; -} - -static int cyttsp4_wait_sysinfo_mode(struct cyttsp4 *cd) -{ - long t; - - dev_vdbg(cd->dev, "%s: wait sysinfo...\n", __func__); - - t = wait_event_timeout(cd->wait_q, cd->mode == CY_MODE_SYSINFO, - msecs_to_jiffies(CY_CORE_MODE_CHANGE_TIMEOUT)); - if (IS_TMO(t)) { - dev_err(cd->dev, "%s: tmo waiting exit bl cd->mode=%d\n", - __func__, cd->mode); - mutex_lock(&cd->system_lock); - cd->int_status &= ~CY_INT_MODE_CHANGE; - mutex_unlock(&cd->system_lock); - return -ETIME; - } - - return 0; -} - -static int cyttsp4_reset_and_wait(struct cyttsp4 *cd) -{ - int rc; - - /* reset hardware */ - mutex_lock(&cd->system_lock); - dev_dbg(cd->dev, "%s: reset hw...\n", __func__); - rc = cyttsp4_hw_reset(cd); - cd->mode = CY_MODE_UNKNOWN; - mutex_unlock(&cd->system_lock); - if (rc < 0) { - dev_err(cd->dev, "%s:Fail hw reset r=%d\n", __func__, rc); - return rc; - } - - return cyttsp4_wait_bl_heartbeat(cd); -} - -/* - * returns err if refused or timeout; block until mode change complete - * bit is set (mode change interrupt) - */ -static int cyttsp4_set_mode(struct cyttsp4 *cd, int new_mode) -{ - u8 new_dev_mode; - u8 mode; - long t; - int rc; - - switch (new_mode) { - case CY_MODE_OPERATIONAL: - new_dev_mode = CY_HST_OPERATE; - break; - case CY_MODE_SYSINFO: - new_dev_mode = CY_HST_SYSINFO; - break; - case CY_MODE_CAT: - new_dev_mode = CY_HST_CAT; - break; - default: - dev_err(cd->dev, "%s: invalid mode: %02X(%d)\n", - __func__, new_mode, new_mode); - return -EINVAL; - } - - /* change mode */ - dev_dbg(cd->dev, "%s: %s=%p new_dev_mode=%02X new_mode=%d\n", - __func__, "have exclusive", cd->exclusive_dev, - new_dev_mode, new_mode); - - mutex_lock(&cd->system_lock); - rc = cyttsp4_adap_read(cd, CY_REG_BASE, sizeof(mode), &mode); - if (rc < 0) { - mutex_unlock(&cd->system_lock); - dev_err(cd->dev, "%s: Fail read mode r=%d\n", - __func__, rc); - goto exit; - } - - /* Clear device mode bits and set to new mode */ - mode &= ~CY_HST_MODE; - mode |= new_dev_mode | CY_HST_MODE_CHANGE; - - cd->int_status |= CY_INT_MODE_CHANGE; - rc = cyttsp4_adap_write(cd, CY_REG_BASE, sizeof(mode), &mode); - mutex_unlock(&cd->system_lock); - if (rc < 0) { - dev_err(cd->dev, "%s: Fail write mode change r=%d\n", - __func__, rc); - goto exit; - } - - /* wait for mode change done interrupt */ - t = wait_event_timeout(cd->wait_q, - (cd->int_status & CY_INT_MODE_CHANGE) == 0, - msecs_to_jiffies(CY_CORE_MODE_CHANGE_TIMEOUT)); - dev_dbg(cd->dev, "%s: back from wait t=%ld cd->mode=%d\n", - __func__, t, cd->mode); - - if (IS_TMO(t)) { - dev_err(cd->dev, "%s: %s\n", __func__, - "tmo waiting mode change"); - mutex_lock(&cd->system_lock); - cd->int_status &= ~CY_INT_MODE_CHANGE; - mutex_unlock(&cd->system_lock); - rc = -EINVAL; - } - -exit: - return rc; -} - -static void cyttsp4_watchdog_work(struct work_struct *work) -{ - struct cyttsp4 *cd = - container_of(work, struct cyttsp4, watchdog_work); - u8 *mode; - int retval; - - mutex_lock(&cd->system_lock); - retval = cyttsp4_load_status_regs(cd); - if (retval < 0) { - dev_err(cd->dev, - "%s: failed to access device in watchdog timer r=%d\n", - __func__, retval); - cyttsp4_queue_startup_(cd); - goto cyttsp4_timer_watchdog_exit_error; - } - mode = &cd->sysinfo.xy_mode[CY_REG_BASE]; - if (IS_BOOTLOADER(mode[0], mode[1])) { - dev_err(cd->dev, - "%s: device found in bootloader mode when operational mode\n", - __func__); - cyttsp4_queue_startup_(cd); - goto cyttsp4_timer_watchdog_exit_error; - } - - cyttsp4_start_wd_timer(cd); -cyttsp4_timer_watchdog_exit_error: - mutex_unlock(&cd->system_lock); - return; -} - -static int cyttsp4_core_sleep_(struct cyttsp4 *cd) -{ - enum cyttsp4_sleep_state ss = SS_SLEEP_ON; - enum cyttsp4_int_state int_status = CY_INT_IGNORE; - int rc = 0; - u8 mode[2]; - - /* Already in sleep mode? */ - mutex_lock(&cd->system_lock); - if (cd->sleep_state == SS_SLEEP_ON) { - mutex_unlock(&cd->system_lock); - return 0; - } - cd->sleep_state = SS_SLEEPING; - mutex_unlock(&cd->system_lock); - - cyttsp4_stop_wd_timer(cd); - - /* Wait until currently running IRQ handler exits and disable IRQ */ - disable_irq(cd->irq); - - dev_vdbg(cd->dev, "%s: write DEEP SLEEP...\n", __func__); - mutex_lock(&cd->system_lock); - rc = cyttsp4_adap_read(cd, CY_REG_BASE, sizeof(mode), &mode); - if (rc) { - mutex_unlock(&cd->system_lock); - dev_err(cd->dev, "%s: Fail read adapter r=%d\n", __func__, rc); - goto error; - } - - if (IS_BOOTLOADER(mode[0], mode[1])) { - mutex_unlock(&cd->system_lock); - dev_err(cd->dev, "%s: Device in BOOTLOADER mode.\n", __func__); - rc = -EINVAL; - goto error; - } - - mode[0] |= CY_HST_SLEEP; - rc = cyttsp4_adap_write(cd, CY_REG_BASE, sizeof(mode[0]), &mode[0]); - mutex_unlock(&cd->system_lock); - if (rc) { - dev_err(cd->dev, "%s: Fail write adapter r=%d\n", __func__, rc); - goto error; - } - dev_vdbg(cd->dev, "%s: write DEEP SLEEP succeeded\n", __func__); - - if (cd->cpdata->power) { - dev_dbg(cd->dev, "%s: Power down HW\n", __func__); - rc = cd->cpdata->power(cd->cpdata, 0, cd->dev, &cd->ignore_irq); - } else { - dev_dbg(cd->dev, "%s: No power function\n", __func__); - rc = 0; - } - if (rc < 0) { - dev_err(cd->dev, "%s: HW Power down fails r=%d\n", - __func__, rc); - goto error; - } - - /* Give time to FW to sleep */ - msleep(50); - - goto exit; - -error: - ss = SS_SLEEP_OFF; - int_status = CY_INT_NONE; - cyttsp4_start_wd_timer(cd); - -exit: - mutex_lock(&cd->system_lock); - cd->sleep_state = ss; - cd->int_status |= int_status; - mutex_unlock(&cd->system_lock); - enable_irq(cd->irq); - return rc; -} - -static int cyttsp4_startup_(struct cyttsp4 *cd) -{ - int retry = CY_CORE_STARTUP_RETRY_COUNT; - int rc; - - cyttsp4_stop_wd_timer(cd); - -reset: - if (retry != CY_CORE_STARTUP_RETRY_COUNT) - dev_dbg(cd->dev, "%s: Retry %d\n", __func__, - CY_CORE_STARTUP_RETRY_COUNT - retry); - - /* reset hardware and wait for heartbeat */ - rc = cyttsp4_reset_and_wait(cd); - if (rc < 0) { - dev_err(cd->dev, "%s: Error on h/w reset r=%d\n", __func__, rc); - if (retry--) - goto reset; - goto exit; - } - - /* exit bl into sysinfo mode */ - dev_vdbg(cd->dev, "%s: write exit ldr...\n", __func__); - mutex_lock(&cd->system_lock); - cd->int_status &= ~CY_INT_IGNORE; - cd->int_status |= CY_INT_MODE_CHANGE; - - rc = cyttsp4_adap_write(cd, CY_REG_BASE, sizeof(ldr_exit), - (u8 *)ldr_exit); - mutex_unlock(&cd->system_lock); - if (rc < 0) { - dev_err(cd->dev, "%s: Fail write r=%d\n", __func__, rc); - if (retry--) - goto reset; - goto exit; - } - - rc = cyttsp4_wait_sysinfo_mode(cd); - if (rc < 0) { - u8 buf[sizeof(ldr_err_app)]; - int rc1; - - /* Check for invalid/corrupted touch application */ - rc1 = cyttsp4_adap_read(cd, CY_REG_BASE, sizeof(ldr_err_app), - buf); - if (rc1) { - dev_err(cd->dev, "%s: Fail read r=%d\n", __func__, rc1); - } else if (!memcmp(buf, ldr_err_app, sizeof(ldr_err_app))) { - dev_err(cd->dev, "%s: Error launching touch application\n", - __func__); - mutex_lock(&cd->system_lock); - cd->invalid_touch_app = true; - mutex_unlock(&cd->system_lock); - goto exit_no_wd; - } - - if (retry--) - goto reset; - goto exit; - } - - mutex_lock(&cd->system_lock); - cd->invalid_touch_app = false; - mutex_unlock(&cd->system_lock); - - /* read sysinfo data */ - dev_vdbg(cd->dev, "%s: get sysinfo regs..\n", __func__); - rc = cyttsp4_get_sysinfo_regs(cd); - if (rc < 0) { - dev_err(cd->dev, "%s: failed to get sysinfo regs rc=%d\n", - __func__, rc); - if (retry--) - goto reset; - goto exit; - } - - rc = cyttsp4_set_mode(cd, CY_MODE_OPERATIONAL); - if (rc < 0) { - dev_err(cd->dev, "%s: failed to set mode to operational rc=%d\n", - __func__, rc); - if (retry--) - goto reset; - goto exit; - } - - cyttsp4_lift_all(&cd->md); - - /* restore to sleep if was suspended */ - mutex_lock(&cd->system_lock); - if (cd->sleep_state == SS_SLEEP_ON) { - cd->sleep_state = SS_SLEEP_OFF; - mutex_unlock(&cd->system_lock); - cyttsp4_core_sleep_(cd); - goto exit_no_wd; - } - mutex_unlock(&cd->system_lock); - -exit: - cyttsp4_start_wd_timer(cd); -exit_no_wd: - return rc; -} - -static int cyttsp4_startup(struct cyttsp4 *cd) -{ - int rc; - - mutex_lock(&cd->system_lock); - cd->startup_state = STARTUP_RUNNING; - mutex_unlock(&cd->system_lock); - - rc = cyttsp4_request_exclusive(cd, cd->dev, - CY_CORE_REQUEST_EXCLUSIVE_TIMEOUT); - if (rc < 0) { - dev_err(cd->dev, "%s: fail get exclusive ex=%p own=%p\n", - __func__, cd->exclusive_dev, cd->dev); - goto exit; - } - - rc = cyttsp4_startup_(cd); - - if (cyttsp4_release_exclusive(cd, cd->dev) < 0) - /* Don't return fail code, mode is already changed. */ - dev_err(cd->dev, "%s: fail to release exclusive\n", __func__); - else - dev_vdbg(cd->dev, "%s: pass release exclusive\n", __func__); - -exit: - mutex_lock(&cd->system_lock); - cd->startup_state = STARTUP_NONE; - mutex_unlock(&cd->system_lock); - - /* Wake the waiters for end of startup */ - wake_up(&cd->wait_q); - - return rc; -} - -static void cyttsp4_startup_work_function(struct work_struct *work) -{ - struct cyttsp4 *cd = container_of(work, struct cyttsp4, startup_work); - int rc; - - rc = cyttsp4_startup(cd); - if (rc < 0) - dev_err(cd->dev, "%s: Fail queued startup r=%d\n", - __func__, rc); -} - -static void cyttsp4_free_si_ptrs(struct cyttsp4 *cd) -{ - struct cyttsp4_sysinfo *si = &cd->sysinfo; - - if (!si) - return; - - kfree(si->si_ptrs.cydata); - kfree(si->si_ptrs.test); - kfree(si->si_ptrs.pcfg); - kfree(si->si_ptrs.opcfg); - kfree(si->si_ptrs.ddata); - kfree(si->si_ptrs.mdata); - kfree(si->btn); - kfree(si->xy_mode); - kfree(si->xy_data); - kfree(si->btn_rec_data); -} - -static int cyttsp4_core_sleep(struct cyttsp4 *cd) -{ - int rc; - - rc = cyttsp4_request_exclusive(cd, cd->dev, - CY_CORE_SLEEP_REQUEST_EXCLUSIVE_TIMEOUT); - if (rc < 0) { - dev_err(cd->dev, "%s: fail get exclusive ex=%p own=%p\n", - __func__, cd->exclusive_dev, cd->dev); - return 0; - } - - rc = cyttsp4_core_sleep_(cd); - - if (cyttsp4_release_exclusive(cd, cd->dev) < 0) - dev_err(cd->dev, "%s: fail to release exclusive\n", __func__); - else - dev_vdbg(cd->dev, "%s: pass release exclusive\n", __func__); - - return rc; -} - -static int cyttsp4_core_wake_(struct cyttsp4 *cd) -{ - struct device *dev = cd->dev; - int rc; - u8 mode; - int t; - - /* Already woken? */ - mutex_lock(&cd->system_lock); - if (cd->sleep_state == SS_SLEEP_OFF) { - mutex_unlock(&cd->system_lock); - return 0; - } - cd->int_status &= ~CY_INT_IGNORE; - cd->int_status |= CY_INT_AWAKE; - cd->sleep_state = SS_WAKING; - - if (cd->cpdata->power) { - dev_dbg(dev, "%s: Power up HW\n", __func__); - rc = cd->cpdata->power(cd->cpdata, 1, dev, &cd->ignore_irq); - } else { - dev_dbg(dev, "%s: No power function\n", __func__); - rc = -ENOSYS; - } - if (rc < 0) { - dev_err(dev, "%s: HW Power up fails r=%d\n", - __func__, rc); - - /* Initiate a read transaction to wake up */ - cyttsp4_adap_read(cd, CY_REG_BASE, sizeof(mode), &mode); - } else - dev_vdbg(cd->dev, "%s: HW power up succeeds\n", - __func__); - mutex_unlock(&cd->system_lock); - - t = wait_event_timeout(cd->wait_q, - (cd->int_status & CY_INT_AWAKE) == 0, - msecs_to_jiffies(CY_CORE_WAKEUP_TIMEOUT)); - if (IS_TMO(t)) { - dev_err(dev, "%s: TMO waiting for wakeup\n", __func__); - mutex_lock(&cd->system_lock); - cd->int_status &= ~CY_INT_AWAKE; - /* Try starting up */ - cyttsp4_queue_startup_(cd); - mutex_unlock(&cd->system_lock); - } - - mutex_lock(&cd->system_lock); - cd->sleep_state = SS_SLEEP_OFF; - mutex_unlock(&cd->system_lock); - - cyttsp4_start_wd_timer(cd); - - return 0; -} - -static int cyttsp4_core_wake(struct cyttsp4 *cd) -{ - int rc; - - rc = cyttsp4_request_exclusive(cd, cd->dev, - CY_CORE_REQUEST_EXCLUSIVE_TIMEOUT); - if (rc < 0) { - dev_err(cd->dev, "%s: fail get exclusive ex=%p own=%p\n", - __func__, cd->exclusive_dev, cd->dev); - return 0; - } - - rc = cyttsp4_core_wake_(cd); - - if (cyttsp4_release_exclusive(cd, cd->dev) < 0) - dev_err(cd->dev, "%s: fail to release exclusive\n", __func__); - else - dev_vdbg(cd->dev, "%s: pass release exclusive\n", __func__); - - return rc; -} - -static int cyttsp4_core_suspend(struct device *dev) -{ - struct cyttsp4 *cd = dev_get_drvdata(dev); - struct cyttsp4_mt_data *md = &cd->md; - int rc; - - md->is_suspended = true; - - rc = cyttsp4_core_sleep(cd); - if (rc < 0) { - dev_err(dev, "%s: Error on sleep\n", __func__); - return -EAGAIN; - } - return 0; -} - -static int cyttsp4_core_resume(struct device *dev) -{ - struct cyttsp4 *cd = dev_get_drvdata(dev); - struct cyttsp4_mt_data *md = &cd->md; - int rc; - - md->is_suspended = false; - - rc = cyttsp4_core_wake(cd); - if (rc < 0) { - dev_err(dev, "%s: Error on wake\n", __func__); - return -EAGAIN; - } - - return 0; -} - -EXPORT_GPL_RUNTIME_DEV_PM_OPS(cyttsp4_pm_ops, - cyttsp4_core_suspend, cyttsp4_core_resume, NULL); - -static int cyttsp4_mt_open(struct input_dev *input) -{ - pm_runtime_get(input->dev.parent); - return 0; -} - -static void cyttsp4_mt_close(struct input_dev *input) -{ - struct cyttsp4_mt_data *md = input_get_drvdata(input); - mutex_lock(&md->report_lock); - if (!md->is_suspended) - pm_runtime_put(input->dev.parent); - mutex_unlock(&md->report_lock); -} - - -static int cyttsp4_setup_input_device(struct cyttsp4 *cd) -{ - struct device *dev = cd->dev; - struct cyttsp4_mt_data *md = &cd->md; - int signal = CY_IGNORE_VALUE; - int max_x, max_y, max_p, min, max; - int max_x_tmp, max_y_tmp; - int i; - int rc; - - dev_vdbg(dev, "%s: Initialize event signals\n", __func__); - __set_bit(EV_ABS, md->input->evbit); - __set_bit(EV_REL, md->input->evbit); - __set_bit(EV_KEY, md->input->evbit); - - max_x_tmp = md->si->si_ofs.max_x; - max_y_tmp = md->si->si_ofs.max_y; - - /* get maximum values from the sysinfo data */ - if (md->pdata->flags & CY_FLAG_FLIP) { - max_x = max_y_tmp - 1; - max_y = max_x_tmp - 1; - } else { - max_x = max_x_tmp - 1; - max_y = max_y_tmp - 1; - } - max_p = md->si->si_ofs.max_p; - - /* set event signal capabilities */ - for (i = 0; i < (md->pdata->frmwrk->size / CY_NUM_ABS_SET); i++) { - signal = md->pdata->frmwrk->abs - [(i * CY_NUM_ABS_SET) + CY_SIGNAL_OST]; - if (signal != CY_IGNORE_VALUE) { - __set_bit(signal, md->input->absbit); - min = md->pdata->frmwrk->abs - [(i * CY_NUM_ABS_SET) + CY_MIN_OST]; - max = md->pdata->frmwrk->abs - [(i * CY_NUM_ABS_SET) + CY_MAX_OST]; - if (i == CY_ABS_ID_OST) { - /* shift track ids down to start at 0 */ - max = max - min; - min = min - min; - } else if (i == CY_ABS_X_OST) - max = max_x; - else if (i == CY_ABS_Y_OST) - max = max_y; - else if (i == CY_ABS_P_OST) - max = max_p; - input_set_abs_params(md->input, signal, min, max, - md->pdata->frmwrk->abs - [(i * CY_NUM_ABS_SET) + CY_FUZZ_OST], - md->pdata->frmwrk->abs - [(i * CY_NUM_ABS_SET) + CY_FLAT_OST]); - dev_dbg(dev, "%s: register signal=%02X min=%d max=%d\n", - __func__, signal, min, max); - if ((i == CY_ABS_ID_OST) && - (md->si->si_ofs.tch_rec_size < - CY_TMA4XX_TCH_REC_SIZE)) - break; - } - } - - input_mt_init_slots(md->input, md->si->si_ofs.tch_abs[CY_TCH_T].max, - INPUT_MT_DIRECT); - rc = input_register_device(md->input); - if (rc < 0) - dev_err(dev, "%s: Error, failed register input device r=%d\n", - __func__, rc); - return rc; -} - -static int cyttsp4_mt_probe(struct cyttsp4 *cd) -{ - struct device *dev = cd->dev; - struct cyttsp4_mt_data *md = &cd->md; - struct cyttsp4_mt_platform_data *pdata = cd->pdata->mt_pdata; - int rc = 0; - - mutex_init(&md->report_lock); - md->pdata = pdata; - /* Create the input device and register it. */ - dev_vdbg(dev, "%s: Create the input device and register it\n", - __func__); - md->input = input_allocate_device(); - if (md->input == NULL) { - dev_err(dev, "%s: Error, failed to allocate input device\n", - __func__); - rc = -ENOSYS; - goto error_alloc_failed; - } - - md->input->name = pdata->inp_dev_name; - scnprintf(md->phys, sizeof(md->phys)-1, "%s", dev_name(dev)); - md->input->phys = md->phys; - md->input->id.bustype = cd->bus_ops->bustype; - md->input->dev.parent = dev; - md->input->open = cyttsp4_mt_open; - md->input->close = cyttsp4_mt_close; - input_set_drvdata(md->input, md); - - /* get sysinfo */ - md->si = &cd->sysinfo; - - rc = cyttsp4_setup_input_device(cd); - if (rc) - goto error_init_input; - - return 0; - -error_init_input: - input_free_device(md->input); -error_alloc_failed: - dev_err(dev, "%s failed.\n", __func__); - return rc; -} - -struct cyttsp4 *cyttsp4_probe(const struct cyttsp4_bus_ops *ops, - struct device *dev, u16 irq, size_t xfer_buf_size) -{ - struct cyttsp4 *cd; - struct cyttsp4_platform_data *pdata = dev_get_platdata(dev); - unsigned long irq_flags; - int rc = 0; - - if (!pdata || !pdata->core_pdata || !pdata->mt_pdata) { - dev_err(dev, "%s: Missing platform data\n", __func__); - rc = -ENODEV; - goto error_no_pdata; - } - - cd = kzalloc(sizeof(*cd), GFP_KERNEL); - if (!cd) { - dev_err(dev, "%s: Error, kzalloc\n", __func__); - rc = -ENOMEM; - goto error_alloc_data; - } - - cd->xfer_buf = kzalloc(xfer_buf_size, GFP_KERNEL); - if (!cd->xfer_buf) { - dev_err(dev, "%s: Error, kzalloc\n", __func__); - rc = -ENOMEM; - goto error_free_cd; - } - - /* Initialize device info */ - cd->dev = dev; - cd->pdata = pdata; - cd->cpdata = pdata->core_pdata; - cd->bus_ops = ops; - - /* Initialize mutexes and spinlocks */ - mutex_init(&cd->system_lock); - mutex_init(&cd->adap_lock); - - /* Initialize wait queue */ - init_waitqueue_head(&cd->wait_q); - - /* Initialize works */ - INIT_WORK(&cd->startup_work, cyttsp4_startup_work_function); - INIT_WORK(&cd->watchdog_work, cyttsp4_watchdog_work); - - /* Initialize IRQ */ - cd->irq = gpio_to_irq(cd->cpdata->irq_gpio); - if (cd->irq < 0) { - rc = -EINVAL; - goto error_free_xfer; - } - - dev_set_drvdata(dev, cd); - - /* Call platform init function */ - if (cd->cpdata->init) { - dev_dbg(cd->dev, "%s: Init HW\n", __func__); - rc = cd->cpdata->init(cd->cpdata, 1, cd->dev); - } else { - dev_dbg(cd->dev, "%s: No HW INIT function\n", __func__); - rc = 0; - } - if (rc < 0) - dev_err(cd->dev, "%s: HW Init fail r=%d\n", __func__, rc); - - dev_dbg(dev, "%s: initialize threaded irq=%d\n", __func__, cd->irq); - if (cd->cpdata->level_irq_udelay > 0) - /* use level triggered interrupts */ - irq_flags = IRQF_TRIGGER_LOW | IRQF_ONESHOT; - else - /* use edge triggered interrupts */ - irq_flags = IRQF_TRIGGER_FALLING | IRQF_ONESHOT; - - rc = request_threaded_irq(cd->irq, NULL, cyttsp4_irq, irq_flags, - dev_name(dev), cd); - if (rc < 0) { - dev_err(dev, "%s: Error, could not request irq\n", __func__); - goto error_request_irq; - } - - /* Setup watchdog timer */ - timer_setup(&cd->watchdog_timer, cyttsp4_watchdog_timer, 0); - - /* - * call startup directly to ensure that the device - * is tested before leaving the probe - */ - rc = cyttsp4_startup(cd); - - /* Do not fail probe if startup fails but the device is detected */ - if (rc < 0 && cd->mode == CY_MODE_UNKNOWN) { - dev_err(cd->dev, "%s: Fail initial startup r=%d\n", - __func__, rc); - goto error_startup; - } - - rc = cyttsp4_mt_probe(cd); - if (rc < 0) { - dev_err(dev, "%s: Error, fail mt probe\n", __func__); - goto error_startup; - } - - pm_runtime_enable(dev); - - return cd; - -error_startup: - cancel_work_sync(&cd->startup_work); - cyttsp4_stop_wd_timer(cd); - pm_runtime_disable(dev); - cyttsp4_free_si_ptrs(cd); - free_irq(cd->irq, cd); -error_request_irq: - if (cd->cpdata->init) - cd->cpdata->init(cd->cpdata, 0, dev); -error_free_xfer: - kfree(cd->xfer_buf); -error_free_cd: - kfree(cd); -error_alloc_data: -error_no_pdata: - dev_err(dev, "%s failed.\n", __func__); - return ERR_PTR(rc); -} -EXPORT_SYMBOL_GPL(cyttsp4_probe); - -static void cyttsp4_mt_release(struct cyttsp4_mt_data *md) -{ - input_unregister_device(md->input); - input_set_drvdata(md->input, NULL); -} - -int cyttsp4_remove(struct cyttsp4 *cd) -{ - struct device *dev = cd->dev; - - cyttsp4_mt_release(&cd->md); - - /* - * Suspend the device before freeing the startup_work and stopping - * the watchdog since sleep function restarts watchdog on failure - */ - pm_runtime_suspend(dev); - pm_runtime_disable(dev); - - cancel_work_sync(&cd->startup_work); - - cyttsp4_stop_wd_timer(cd); - - free_irq(cd->irq, cd); - if (cd->cpdata->init) - cd->cpdata->init(cd->cpdata, 0, dev); - cyttsp4_free_si_ptrs(cd); - kfree(cd); - return 0; -} -EXPORT_SYMBOL_GPL(cyttsp4_remove); - -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("Cypress TrueTouch(R) Standard touchscreen core driver"); -MODULE_AUTHOR("Cypress"); diff --git a/drivers/input/touchscreen/cyttsp4_core.h b/drivers/input/touchscreen/cyttsp4_core.h deleted file mode 100644 index 6262f6e45075..000000000000 --- a/drivers/input/touchscreen/cyttsp4_core.h +++ /dev/null @@ -1,448 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * cyttsp4_core.h - * Cypress TrueTouch(TM) Standard Product V4 Core driver module. - * For use with Cypress Txx4xx parts. - * Supported parts include: - * TMA4XX - * TMA1036 - * - * Copyright (C) 2012 Cypress Semiconductor - * - * Contact Cypress Semiconductor at www.cypress.com - */ - -#ifndef _LINUX_CYTTSP4_CORE_H -#define _LINUX_CYTTSP4_CORE_H - -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#define CY_REG_BASE 0x00 - -#define CY_POST_CODEL_WDG_RST 0x01 -#define CY_POST_CODEL_CFG_DATA_CRC_FAIL 0x02 -#define CY_POST_CODEL_PANEL_TEST_FAIL 0x04 - -#define CY_NUM_BTN_PER_REG 4 - -/* touch record system information offset masks and shifts */ -#define CY_BYTE_OFS_MASK 0x1F -#define CY_BOFS_MASK 0xE0 -#define CY_BOFS_SHIFT 5 - -#define CY_TMA1036_TCH_REC_SIZE 6 -#define CY_TMA4XX_TCH_REC_SIZE 9 -#define CY_TMA1036_MAX_TCH 0x0E -#define CY_TMA4XX_MAX_TCH 0x1E - -#define CY_NORMAL_ORIGIN 0 /* upper, left corner */ -#define CY_INVERT_ORIGIN 1 /* lower, right corner */ - -/* helpers */ -#define GET_NUM_TOUCHES(x) ((x) & 0x1F) -#define IS_LARGE_AREA(x) ((x) & 0x20) -#define IS_BAD_PKT(x) ((x) & 0x20) -#define IS_BOOTLOADER(hst_mode, reset_detect) \ - ((hst_mode) & 0x01 || (reset_detect) != 0) -#define IS_TMO(t) ((t) == 0) - - -enum cyttsp_cmd_bits { - CY_CMD_COMPLETE = (1 << 6), -}; - -/* Timeout in ms. */ -#define CY_WATCHDOG_TIMEOUT 1000 - -#define CY_MAX_PRINT_SIZE 512 -#ifdef VERBOSE_DEBUG -#define CY_MAX_PRBUF_SIZE PIPE_BUF -#define CY_PR_TRUNCATED " truncated..." -#endif - -enum cyttsp4_ic_grpnum { - CY_IC_GRPNUM_RESERVED, - CY_IC_GRPNUM_CMD_REGS, - CY_IC_GRPNUM_TCH_REP, - CY_IC_GRPNUM_DATA_REC, - CY_IC_GRPNUM_TEST_REC, - CY_IC_GRPNUM_PCFG_REC, - CY_IC_GRPNUM_TCH_PARM_VAL, - CY_IC_GRPNUM_TCH_PARM_SIZE, - CY_IC_GRPNUM_RESERVED1, - CY_IC_GRPNUM_RESERVED2, - CY_IC_GRPNUM_OPCFG_REC, - CY_IC_GRPNUM_DDATA_REC, - CY_IC_GRPNUM_MDATA_REC, - CY_IC_GRPNUM_TEST_REGS, - CY_IC_GRPNUM_BTN_KEYS, - CY_IC_GRPNUM_TTHE_REGS, - CY_IC_GRPNUM_NUM -}; - -enum cyttsp4_int_state { - CY_INT_NONE, - CY_INT_IGNORE = (1 << 0), - CY_INT_MODE_CHANGE = (1 << 1), - CY_INT_EXEC_CMD = (1 << 2), - CY_INT_AWAKE = (1 << 3), -}; - -enum cyttsp4_mode { - CY_MODE_UNKNOWN, - CY_MODE_BOOTLOADER = (1 << 1), - CY_MODE_OPERATIONAL = (1 << 2), - CY_MODE_SYSINFO = (1 << 3), - CY_MODE_CAT = (1 << 4), - CY_MODE_STARTUP = (1 << 5), - CY_MODE_LOADER = (1 << 6), - CY_MODE_CHANGE_MODE = (1 << 7), - CY_MODE_CHANGED = (1 << 8), - CY_MODE_CMD_COMPLETE = (1 << 9), -}; - -enum cyttsp4_sleep_state { - SS_SLEEP_OFF, - SS_SLEEP_ON, - SS_SLEEPING, - SS_WAKING, -}; - -enum cyttsp4_startup_state { - STARTUP_NONE, - STARTUP_QUEUED, - STARTUP_RUNNING, -}; - -#define CY_NUM_REVCTRL 8 -struct cyttsp4_cydata { - u8 ttpidh; - u8 ttpidl; - u8 fw_ver_major; - u8 fw_ver_minor; - u8 revctrl[CY_NUM_REVCTRL]; - u8 blver_major; - u8 blver_minor; - u8 jtag_si_id3; - u8 jtag_si_id2; - u8 jtag_si_id1; - u8 jtag_si_id0; - u8 mfgid_sz; - u8 cyito_idh; - u8 cyito_idl; - u8 cyito_verh; - u8 cyito_verl; - u8 ttsp_ver_major; - u8 ttsp_ver_minor; - u8 device_info; - u8 mfg_id[]; -} __packed; - -struct cyttsp4_test { - u8 post_codeh; - u8 post_codel; -} __packed; - -struct cyttsp4_pcfg { - u8 electrodes_x; - u8 electrodes_y; - u8 len_xh; - u8 len_xl; - u8 len_yh; - u8 len_yl; - u8 res_xh; - u8 res_xl; - u8 res_yh; - u8 res_yl; - u8 max_zh; - u8 max_zl; - u8 panel_info0; -} __packed; - -struct cyttsp4_tch_rec_params { - u8 loc; - u8 size; -} __packed; - -#define CY_NUM_TCH_FIELDS 7 -#define CY_NUM_EXT_TCH_FIELDS 3 -struct cyttsp4_opcfg { - u8 cmd_ofs; - u8 rep_ofs; - u8 rep_szh; - u8 rep_szl; - u8 num_btns; - u8 tt_stat_ofs; - u8 obj_cfg0; - u8 max_tchs; - u8 tch_rec_size; - struct cyttsp4_tch_rec_params tch_rec_old[CY_NUM_TCH_FIELDS]; - u8 btn_rec_size; /* btn record size (in bytes) */ - u8 btn_diff_ofs; /* btn data loc, diff counts */ - u8 btn_diff_size; /* btn size of diff counts (in bits) */ - struct cyttsp4_tch_rec_params tch_rec_new[CY_NUM_EXT_TCH_FIELDS]; -} __packed; - -struct cyttsp4_sysinfo_ptr { - struct cyttsp4_cydata *cydata; - struct cyttsp4_test *test; - struct cyttsp4_pcfg *pcfg; - struct cyttsp4_opcfg *opcfg; - struct cyttsp4_ddata *ddata; - struct cyttsp4_mdata *mdata; -} __packed; - -struct cyttsp4_sysinfo_data { - u8 hst_mode; - u8 reserved; - u8 map_szh; - u8 map_szl; - u8 cydata_ofsh; - u8 cydata_ofsl; - u8 test_ofsh; - u8 test_ofsl; - u8 pcfg_ofsh; - u8 pcfg_ofsl; - u8 opcfg_ofsh; - u8 opcfg_ofsl; - u8 ddata_ofsh; - u8 ddata_ofsl; - u8 mdata_ofsh; - u8 mdata_ofsl; -} __packed; - -enum cyttsp4_tch_abs { /* for ordering within the extracted touch data array */ - CY_TCH_X, /* X */ - CY_TCH_Y, /* Y */ - CY_TCH_P, /* P (Z) */ - CY_TCH_T, /* TOUCH ID */ - CY_TCH_E, /* EVENT ID */ - CY_TCH_O, /* OBJECT ID */ - CY_TCH_W, /* SIZE */ - CY_TCH_MAJ, /* TOUCH_MAJOR */ - CY_TCH_MIN, /* TOUCH_MINOR */ - CY_TCH_OR, /* ORIENTATION */ - CY_TCH_NUM_ABS -}; - -struct cyttsp4_touch { - int abs[CY_TCH_NUM_ABS]; -}; - -struct cyttsp4_tch_abs_params { - size_t ofs; /* abs byte offset */ - size_t size; /* size in bits */ - size_t max; /* max value */ - size_t bofs; /* bit offset */ -}; - -struct cyttsp4_sysinfo_ofs { - size_t chip_type; - size_t cmd_ofs; - size_t rep_ofs; - size_t rep_sz; - size_t num_btns; - size_t num_btn_regs; /* ceil(num_btns/4) */ - size_t tt_stat_ofs; - size_t tch_rec_size; - size_t obj_cfg0; - size_t max_tchs; - size_t mode_size; - size_t data_size; - size_t map_sz; - size_t max_x; - size_t x_origin; /* left or right corner */ - size_t max_y; - size_t y_origin; /* upper or lower corner */ - size_t max_p; - size_t cydata_ofs; - size_t test_ofs; - size_t pcfg_ofs; - size_t opcfg_ofs; - size_t ddata_ofs; - size_t mdata_ofs; - size_t cydata_size; - size_t test_size; - size_t pcfg_size; - size_t opcfg_size; - size_t ddata_size; - size_t mdata_size; - size_t btn_keys_size; - struct cyttsp4_tch_abs_params tch_abs[CY_TCH_NUM_ABS]; - size_t btn_rec_size; /* btn record size (in bytes) */ - size_t btn_diff_ofs;/* btn data loc ,diff counts, (Op-Mode byte ofs) */ - size_t btn_diff_size;/* btn size of diff counts (in bits) */ -}; - -enum cyttsp4_btn_state { - CY_BTN_RELEASED, - CY_BTN_PRESSED, - CY_BTN_NUM_STATE -}; - -struct cyttsp4_btn { - bool enabled; - int state; /* CY_BTN_PRESSED, CY_BTN_RELEASED */ - int key_code; -}; - -struct cyttsp4_sysinfo { - bool ready; - struct cyttsp4_sysinfo_data si_data; - struct cyttsp4_sysinfo_ptr si_ptrs; - struct cyttsp4_sysinfo_ofs si_ofs; - struct cyttsp4_btn *btn; /* button states */ - u8 *btn_rec_data; /* button diff count data */ - u8 *xy_mode; /* operational mode and status regs */ - u8 *xy_data; /* operational touch regs */ -}; - -struct cyttsp4_mt_data { - struct cyttsp4_mt_platform_data *pdata; - struct cyttsp4_sysinfo *si; - struct input_dev *input; - struct mutex report_lock; - bool is_suspended; - char phys[NAME_MAX]; - int num_prv_tch; -}; - -struct cyttsp4 { - struct device *dev; - struct mutex system_lock; - struct mutex adap_lock; - enum cyttsp4_mode mode; - enum cyttsp4_sleep_state sleep_state; - enum cyttsp4_startup_state startup_state; - int int_status; - wait_queue_head_t wait_q; - int irq; - struct work_struct startup_work; - struct work_struct watchdog_work; - struct timer_list watchdog_timer; - struct cyttsp4_sysinfo sysinfo; - void *exclusive_dev; - int exclusive_waits; - atomic_t ignore_irq; - bool invalid_touch_app; - struct cyttsp4_mt_data md; - struct cyttsp4_platform_data *pdata; - struct cyttsp4_core_platform_data *cpdata; - const struct cyttsp4_bus_ops *bus_ops; - u8 *xfer_buf; -#ifdef VERBOSE_DEBUG - u8 pr_buf[CY_MAX_PRBUF_SIZE]; -#endif -}; - -struct cyttsp4_bus_ops { - u16 bustype; - int (*write)(struct device *dev, u8 *xfer_buf, u16 addr, u8 length, - const void *values); - int (*read)(struct device *dev, u8 *xfer_buf, u16 addr, u8 length, - void *values); -}; - -enum cyttsp4_hst_mode_bits { - CY_HST_TOGGLE = (1 << 7), - CY_HST_MODE_CHANGE = (1 << 3), - CY_HST_MODE = (7 << 4), - CY_HST_OPERATE = (0 << 4), - CY_HST_SYSINFO = (1 << 4), - CY_HST_CAT = (2 << 4), - CY_HST_LOWPOW = (1 << 2), - CY_HST_SLEEP = (1 << 1), - CY_HST_RESET = (1 << 0), -}; - -/* abs settings */ -#define CY_IGNORE_VALUE 0xFFFF - -/* abs signal capabilities offsets in the frameworks array */ -enum cyttsp4_sig_caps { - CY_SIGNAL_OST, - CY_MIN_OST, - CY_MAX_OST, - CY_FUZZ_OST, - CY_FLAT_OST, - CY_NUM_ABS_SET /* number of signal capability fields */ -}; - -/* abs axis signal offsets in the framworks array */ -enum cyttsp4_sig_ost { - CY_ABS_X_OST, - CY_ABS_Y_OST, - CY_ABS_P_OST, - CY_ABS_W_OST, - CY_ABS_ID_OST, - CY_ABS_MAJ_OST, - CY_ABS_MIN_OST, - CY_ABS_OR_OST, - CY_NUM_ABS_OST /* number of abs signals */ -}; - -enum cyttsp4_flags { - CY_FLAG_NONE = 0x00, - CY_FLAG_HOVER = 0x04, - CY_FLAG_FLIP = 0x08, - CY_FLAG_INV_X = 0x10, - CY_FLAG_INV_Y = 0x20, - CY_FLAG_VKEYS = 0x40, -}; - -enum cyttsp4_object_id { - CY_OBJ_STANDARD_FINGER, - CY_OBJ_LARGE_OBJECT, - CY_OBJ_STYLUS, - CY_OBJ_HOVER, -}; - -enum cyttsp4_event_id { - CY_EV_NO_EVENT, - CY_EV_TOUCHDOWN, - CY_EV_MOVE, /* significant displacement (> act dist) */ - CY_EV_LIFTOFF, /* record reports last position */ -}; - -/* x-axis resolution of panel in pixels */ -#define CY_PCFG_RESOLUTION_X_MASK 0x7F - -/* y-axis resolution of panel in pixels */ -#define CY_PCFG_RESOLUTION_Y_MASK 0x7F - -/* x-axis, 0:origin is on left side of panel, 1: right */ -#define CY_PCFG_ORIGIN_X_MASK 0x80 - -/* y-axis, 0:origin is on top side of panel, 1: bottom */ -#define CY_PCFG_ORIGIN_Y_MASK 0x80 - -static inline int cyttsp4_adap_read(struct cyttsp4 *ts, u16 addr, int size, - void *buf) -{ - return ts->bus_ops->read(ts->dev, ts->xfer_buf, addr, size, buf); -} - -static inline int cyttsp4_adap_write(struct cyttsp4 *ts, u16 addr, int size, - const void *buf) -{ - return ts->bus_ops->write(ts->dev, ts->xfer_buf, addr, size, buf); -} - -extern struct cyttsp4 *cyttsp4_probe(const struct cyttsp4_bus_ops *ops, - struct device *dev, u16 irq, size_t xfer_buf_size); -extern int cyttsp4_remove(struct cyttsp4 *ts); -int cyttsp_i2c_write_block_data(struct device *dev, u8 *xfer_buf, u16 addr, - u8 length, const void *values); -int cyttsp_i2c_read_block_data(struct device *dev, u8 *xfer_buf, u16 addr, - u8 length, void *values); -extern const struct dev_pm_ops cyttsp4_pm_ops; - -#endif /* _LINUX_CYTTSP4_CORE_H */ diff --git a/drivers/input/touchscreen/cyttsp4_i2c.c b/drivers/input/touchscreen/cyttsp4_i2c.c deleted file mode 100644 index da32c151def5..000000000000 --- a/drivers/input/touchscreen/cyttsp4_i2c.c +++ /dev/null @@ -1,72 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * cyttsp_i2c.c - * Cypress TrueTouch(TM) Standard Product (TTSP) I2C touchscreen driver. - * For use with Cypress Txx4xx parts. - * Supported parts include: - * TMA4XX - * TMA1036 - * - * Copyright (C) 2009, 2010, 2011 Cypress Semiconductor, Inc. - * Copyright (C) 2012 Javier Martinez Canillas - * Copyright (C) 2013 Cypress Semiconductor - * - * Contact Cypress Semiconductor at www.cypress.com - */ - -#include "cyttsp4_core.h" - -#include -#include - -#define CYTTSP4_I2C_DATA_SIZE (3 * 256) - -static const struct cyttsp4_bus_ops cyttsp4_i2c_bus_ops = { - .bustype = BUS_I2C, - .write = cyttsp_i2c_write_block_data, - .read = cyttsp_i2c_read_block_data, -}; - -static int cyttsp4_i2c_probe(struct i2c_client *client) -{ - struct cyttsp4 *ts; - - if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) { - dev_err(&client->dev, "I2C functionality not Supported\n"); - return -EIO; - } - - ts = cyttsp4_probe(&cyttsp4_i2c_bus_ops, &client->dev, client->irq, - CYTTSP4_I2C_DATA_SIZE); - - return PTR_ERR_OR_ZERO(ts); -} - -static void cyttsp4_i2c_remove(struct i2c_client *client) -{ - struct cyttsp4 *ts = i2c_get_clientdata(client); - - cyttsp4_remove(ts); -} - -static const struct i2c_device_id cyttsp4_i2c_id[] = { - { CYTTSP4_I2C_NAME }, - { } -}; -MODULE_DEVICE_TABLE(i2c, cyttsp4_i2c_id); - -static struct i2c_driver cyttsp4_i2c_driver = { - .driver = { - .name = CYTTSP4_I2C_NAME, - .pm = pm_ptr(&cyttsp4_pm_ops), - }, - .probe = cyttsp4_i2c_probe, - .remove = cyttsp4_i2c_remove, - .id_table = cyttsp4_i2c_id, -}; - -module_i2c_driver(cyttsp4_i2c_driver); - -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("Cypress TrueTouch(R) Standard Product (TTSP) I2C driver"); -MODULE_AUTHOR("Cypress"); diff --git a/drivers/input/touchscreen/cyttsp4_spi.c b/drivers/input/touchscreen/cyttsp4_spi.c deleted file mode 100644 index 944fbbe9113e..000000000000 --- a/drivers/input/touchscreen/cyttsp4_spi.c +++ /dev/null @@ -1,187 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Source for: - * Cypress TrueTouch(TM) Standard Product (TTSP) SPI touchscreen driver. - * For use with Cypress Txx4xx parts. - * Supported parts include: - * TMA4XX - * TMA1036 - * - * Copyright (C) 2009, 2010, 2011 Cypress Semiconductor, Inc. - * Copyright (C) 2012 Javier Martinez Canillas - * Copyright (C) 2013 Cypress Semiconductor - * - * Contact Cypress Semiconductor at www.cypress.com - */ - -#include "cyttsp4_core.h" - -#include -#include -#include - -#define CY_SPI_WR_OP 0x00 /* r/~w */ -#define CY_SPI_RD_OP 0x01 -#define CY_SPI_BITS_PER_WORD 8 -#define CY_SPI_A8_BIT 0x02 -#define CY_SPI_WR_HEADER_BYTES 2 -#define CY_SPI_RD_HEADER_BYTES 1 -#define CY_SPI_CMD_BYTES 2 -#define CY_SPI_SYNC_BYTE 0 -#define CY_SPI_SYNC_ACK 0x62 /* from TRM *A protocol */ -#define CY_SPI_DATA_SIZE (2 * 256) - -#define CY_SPI_DATA_BUF_SIZE (CY_SPI_CMD_BYTES + CY_SPI_DATA_SIZE) - -static int cyttsp_spi_xfer(struct device *dev, u8 *xfer_buf, - u8 op, u16 reg, u8 *buf, int length) -{ - struct spi_device *spi = to_spi_device(dev); - struct spi_message msg; - struct spi_transfer xfer[2]; - u8 *wr_buf = &xfer_buf[0]; - u8 rd_buf[CY_SPI_CMD_BYTES]; - int retval; - int i; - - if (length > CY_SPI_DATA_SIZE) { - dev_err(dev, "%s: length %d is too big.\n", - __func__, length); - return -EINVAL; - } - - memset(wr_buf, 0, CY_SPI_DATA_BUF_SIZE); - memset(rd_buf, 0, CY_SPI_CMD_BYTES); - - wr_buf[0] = op + (((reg >> 8) & 0x1) ? CY_SPI_A8_BIT : 0); - if (op == CY_SPI_WR_OP) { - wr_buf[1] = reg & 0xFF; - if (length > 0) - memcpy(wr_buf + CY_SPI_CMD_BYTES, buf, length); - } - - memset(xfer, 0, sizeof(xfer)); - spi_message_init(&msg); - - /* - We set both TX and RX buffers because Cypress TTSP - requires full duplex operation. - */ - xfer[0].tx_buf = wr_buf; - xfer[0].rx_buf = rd_buf; - switch (op) { - case CY_SPI_WR_OP: - xfer[0].len = length + CY_SPI_CMD_BYTES; - spi_message_add_tail(&xfer[0], &msg); - break; - - case CY_SPI_RD_OP: - xfer[0].len = CY_SPI_RD_HEADER_BYTES; - spi_message_add_tail(&xfer[0], &msg); - - xfer[1].rx_buf = buf; - xfer[1].len = length; - spi_message_add_tail(&xfer[1], &msg); - break; - - default: - dev_err(dev, "%s: bad operation code=%d\n", __func__, op); - return -EINVAL; - } - - retval = spi_sync(spi, &msg); - if (retval < 0) { - dev_dbg(dev, "%s: spi_sync() error %d, len=%d, op=%d\n", - __func__, retval, xfer[1].len, op); - - /* - * do not return here since was a bad ACK sequence - * let the following ACK check handle any errors and - * allow silent retries - */ - } - - if (rd_buf[CY_SPI_SYNC_BYTE] != CY_SPI_SYNC_ACK) { - dev_dbg(dev, "%s: operation %d failed\n", __func__, op); - - for (i = 0; i < CY_SPI_CMD_BYTES; i++) - dev_dbg(dev, "%s: test rd_buf[%d]:0x%02x\n", - __func__, i, rd_buf[i]); - for (i = 0; i < length; i++) - dev_dbg(dev, "%s: test buf[%d]:0x%02x\n", - __func__, i, buf[i]); - - return -EIO; - } - - return 0; -} - -static int cyttsp_spi_read_block_data(struct device *dev, u8 *xfer_buf, - u16 addr, u8 length, void *data) -{ - int rc; - - rc = cyttsp_spi_xfer(dev, xfer_buf, CY_SPI_WR_OP, addr, NULL, 0); - if (rc) - return rc; - else - return cyttsp_spi_xfer(dev, xfer_buf, CY_SPI_RD_OP, addr, data, - length); -} - -static int cyttsp_spi_write_block_data(struct device *dev, u8 *xfer_buf, - u16 addr, u8 length, const void *data) -{ - return cyttsp_spi_xfer(dev, xfer_buf, CY_SPI_WR_OP, addr, (void *)data, - length); -} - -static const struct cyttsp4_bus_ops cyttsp_spi_bus_ops = { - .bustype = BUS_SPI, - .write = cyttsp_spi_write_block_data, - .read = cyttsp_spi_read_block_data, -}; - -static int cyttsp4_spi_probe(struct spi_device *spi) -{ - struct cyttsp4 *ts; - int error; - - /* Set up SPI*/ - spi->bits_per_word = CY_SPI_BITS_PER_WORD; - spi->mode = SPI_MODE_0; - error = spi_setup(spi); - if (error < 0) { - dev_err(&spi->dev, "%s: SPI setup error %d\n", - __func__, error); - return error; - } - - ts = cyttsp4_probe(&cyttsp_spi_bus_ops, &spi->dev, spi->irq, - CY_SPI_DATA_BUF_SIZE); - - return PTR_ERR_OR_ZERO(ts); -} - -static void cyttsp4_spi_remove(struct spi_device *spi) -{ - struct cyttsp4 *ts = spi_get_drvdata(spi); - cyttsp4_remove(ts); -} - -static struct spi_driver cyttsp4_spi_driver = { - .driver = { - .name = CYTTSP4_SPI_NAME, - .pm = pm_ptr(&cyttsp4_pm_ops), - }, - .probe = cyttsp4_spi_probe, - .remove = cyttsp4_spi_remove, -}; - -module_spi_driver(cyttsp4_spi_driver); - -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("Cypress TrueTouch(R) Standard Product (TTSP) SPI driver"); -MODULE_AUTHOR("Cypress"); -MODULE_ALIAS("spi:cyttsp4"); diff --git a/drivers/input/touchscreen/cyttsp_core.h b/drivers/input/touchscreen/cyttsp_core.h index cd3b80401970..40a605d20285 100644 --- a/drivers/input/touchscreen/cyttsp_core.h +++ b/drivers/input/touchscreen/cyttsp_core.h @@ -136,10 +136,6 @@ struct cyttsp { struct cyttsp *cyttsp_probe(const struct cyttsp_bus_ops *bus_ops, struct device *dev, int irq, size_t xfer_buf_size); -int cyttsp_i2c_write_block_data(struct device *dev, u8 *xfer_buf, u16 addr, - u8 length, const void *values); -int cyttsp_i2c_read_block_data(struct device *dev, u8 *xfer_buf, u16 addr, - u8 length, void *values); extern const struct dev_pm_ops cyttsp_pm_ops; #endif /* __CYTTSP_CORE_H__ */ diff --git a/drivers/input/touchscreen/cyttsp_i2c.c b/drivers/input/touchscreen/cyttsp_i2c.c index bf13b3448a6b..cb15600549cd 100644 --- a/drivers/input/touchscreen/cyttsp_i2c.c +++ b/drivers/input/touchscreen/cyttsp_i2c.c @@ -22,6 +22,61 @@ #define CY_I2C_DATA_SIZE 128 +static int cyttsp_i2c_read_block_data(struct device *dev, u8 *xfer_buf, + u16 addr, u8 length, void *values) +{ + struct i2c_client *client = to_i2c_client(dev); + u8 client_addr = client->addr | ((addr >> 8) & 0x1); + u8 addr_lo = addr & 0xFF; + struct i2c_msg msgs[] = { + { + .addr = client_addr, + .flags = 0, + .len = 1, + .buf = &addr_lo, + }, + { + .addr = client_addr, + .flags = I2C_M_RD, + .len = length, + .buf = values, + }, + }; + int retval; + + retval = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs)); + if (retval < 0) + return retval; + + return retval != ARRAY_SIZE(msgs) ? -EIO : 0; +} + +static int cyttsp_i2c_write_block_data(struct device *dev, u8 *xfer_buf, + u16 addr, u8 length, const void *values) +{ + struct i2c_client *client = to_i2c_client(dev); + u8 client_addr = client->addr | ((addr >> 8) & 0x1); + u8 addr_lo = addr & 0xFF; + struct i2c_msg msgs[] = { + { + .addr = client_addr, + .flags = 0, + .len = length + 1, + .buf = xfer_buf, + }, + }; + int retval; + + xfer_buf[0] = addr_lo; + memcpy(&xfer_buf[1], values, length); + + retval = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs)); + if (retval < 0) + return retval; + + return retval != ARRAY_SIZE(msgs) ? -EIO : 0; +} + static const struct cyttsp_bus_ops cyttsp_i2c_bus_ops = { .bustype = BUS_I2C, .write = cyttsp_i2c_write_block_data, diff --git a/drivers/input/touchscreen/cyttsp_i2c_common.c b/drivers/input/touchscreen/cyttsp_i2c_common.c deleted file mode 100644 index 7e752fb9fad7..000000000000 --- a/drivers/input/touchscreen/cyttsp_i2c_common.c +++ /dev/null @@ -1,86 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * cyttsp_i2c_common.c - * Cypress TrueTouch(TM) Standard Product (TTSP) I2C touchscreen driver. - * For use with Cypress Txx3xx and Txx4xx parts. - * Supported parts include: - * CY8CTST341 - * CY8CTMA340 - * TMA4XX - * TMA1036 - * - * Copyright (C) 2009, 2010, 2011 Cypress Semiconductor, Inc. - * Copyright (C) 2012 Javier Martinez Canillas - * - * Contact Cypress Semiconductor at www.cypress.com - */ - -#include -#include -#include -#include -#include - -#include "cyttsp4_core.h" - -int cyttsp_i2c_read_block_data(struct device *dev, u8 *xfer_buf, - u16 addr, u8 length, void *values) -{ - struct i2c_client *client = to_i2c_client(dev); - u8 client_addr = client->addr | ((addr >> 8) & 0x1); - u8 addr_lo = addr & 0xFF; - struct i2c_msg msgs[] = { - { - .addr = client_addr, - .flags = 0, - .len = 1, - .buf = &addr_lo, - }, - { - .addr = client_addr, - .flags = I2C_M_RD, - .len = length, - .buf = values, - }, - }; - int retval; - - retval = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs)); - if (retval < 0) - return retval; - - return retval != ARRAY_SIZE(msgs) ? -EIO : 0; -} -EXPORT_SYMBOL_GPL(cyttsp_i2c_read_block_data); - -int cyttsp_i2c_write_block_data(struct device *dev, u8 *xfer_buf, - u16 addr, u8 length, const void *values) -{ - struct i2c_client *client = to_i2c_client(dev); - u8 client_addr = client->addr | ((addr >> 8) & 0x1); - u8 addr_lo = addr & 0xFF; - struct i2c_msg msgs[] = { - { - .addr = client_addr, - .flags = 0, - .len = length + 1, - .buf = xfer_buf, - }, - }; - int retval; - - xfer_buf[0] = addr_lo; - memcpy(&xfer_buf[1], values, length); - - retval = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs)); - if (retval < 0) - return retval; - - return retval != ARRAY_SIZE(msgs) ? -EIO : 0; -} -EXPORT_SYMBOL_GPL(cyttsp_i2c_write_block_data); - - -MODULE_DESCRIPTION("Cypress TrueTouch(TM) Standard Product (TTSP) I2C touchscreen driver"); -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Cypress"); diff --git a/include/linux/platform_data/cyttsp4.h b/include/linux/platform_data/cyttsp4.h deleted file mode 100644 index 5dc9d2be384b..000000000000 --- a/include/linux/platform_data/cyttsp4.h +++ /dev/null @@ -1,62 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Header file for: - * Cypress TrueTouch(TM) Standard Product (TTSP) touchscreen drivers. - * For use with Cypress Txx3xx parts. - * Supported parts include: - * CY8CTST341 - * CY8CTMA340 - * - * Copyright (C) 2009, 2010, 2011 Cypress Semiconductor, Inc. - * Copyright (C) 2012 Javier Martinez Canillas - * - * Contact Cypress Semiconductor at www.cypress.com (kev@cypress.com) - */ -#ifndef _CYTTSP4_H_ -#define _CYTTSP4_H_ - -#define CYTTSP4_MT_NAME "cyttsp4_mt" -#define CYTTSP4_I2C_NAME "cyttsp4_i2c_adapter" -#define CYTTSP4_SPI_NAME "cyttsp4_spi_adapter" - -#define CY_TOUCH_SETTINGS_MAX 32 - -struct touch_framework { - const uint16_t *abs; - uint8_t size; - uint8_t enable_vkeys; -} __packed; - -struct cyttsp4_mt_platform_data { - struct touch_framework *frmwrk; - unsigned short flags; - char const *inp_dev_name; -}; - -struct touch_settings { - const uint8_t *data; - uint32_t size; - uint8_t tag; -} __packed; - -struct cyttsp4_core_platform_data { - int irq_gpio; - int rst_gpio; - int level_irq_udelay; - int (*xres)(struct cyttsp4_core_platform_data *pdata, - struct device *dev); - int (*init)(struct cyttsp4_core_platform_data *pdata, - int on, struct device *dev); - int (*power)(struct cyttsp4_core_platform_data *pdata, - int on, struct device *dev, atomic_t *ignore_irq); - int (*irq_stat)(struct cyttsp4_core_platform_data *pdata, - struct device *dev); - struct touch_settings *sett[CY_TOUCH_SETTINGS_MAX]; -}; - -struct cyttsp4_platform_data { - struct cyttsp4_core_platform_data *core_pdata; - struct cyttsp4_mt_platform_data *mt_pdata; -}; - -#endif /* _CYTTSP4_H_ */ -- cgit v1.2.3 From f91f7ac900e7342e0fd66093dfbf7cb8cb585a99 Mon Sep 17 00:00:00 2001 From: Petr Pavlu Date: Wed, 17 Jul 2024 15:00:23 +0200 Subject: refcount: Report UAF for refcount_sub_and_test(0) when counter==0 When a reference counter is at zero and refcount_sub_and_test() is invoked to subtract zero, the function accepts this request without any warning and returns true. This behavior does not seem ideal because the counter being already at zero indicates a use-after-free. Furthermore, returning true by refcount_sub_and_test() in this case potentially results in a double-free done by its caller. Modify the underlying function __refcount_sub_and_test() to warn about this case as a use-after-free and have it return false to avoid the potential double-free. Signed-off-by: Petr Pavlu Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20240717130023.5675-1-petr.pavlu@suse.com Signed-off-by: Kees Cook --- drivers/misc/lkdtm/refcount.c | 16 ++++++++++++++++ include/linux/refcount.h | 4 ++-- 2 files changed, 18 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/misc/lkdtm/refcount.c b/drivers/misc/lkdtm/refcount.c index 5cd488f54cfa..8f744bee6fbd 100644 --- a/drivers/misc/lkdtm/refcount.c +++ b/drivers/misc/lkdtm/refcount.c @@ -182,6 +182,21 @@ static void lkdtm_REFCOUNT_SUB_AND_TEST_NEGATIVE(void) check_negative(&neg, 3); } +/* + * A refcount_sub_and_test() by zero when the counter is at zero should act like + * refcount_sub_and_test() above when going negative. + */ +static void lkdtm_REFCOUNT_SUB_AND_TEST_ZERO(void) +{ + refcount_t neg = REFCOUNT_INIT(0); + + pr_info("attempting bad refcount_sub_and_test() at zero\n"); + if (refcount_sub_and_test(0, &neg)) + pr_warn("Weird: refcount_sub_and_test() reported zero\n"); + + check_negative(&neg, 0); +} + static void check_from_zero(refcount_t *ref) { switch (refcount_read(ref)) { @@ -400,6 +415,7 @@ static struct crashtype crashtypes[] = { CRASHTYPE(REFCOUNT_DEC_NEGATIVE), CRASHTYPE(REFCOUNT_DEC_AND_TEST_NEGATIVE), CRASHTYPE(REFCOUNT_SUB_AND_TEST_NEGATIVE), + CRASHTYPE(REFCOUNT_SUB_AND_TEST_ZERO), CRASHTYPE(REFCOUNT_INC_ZERO), CRASHTYPE(REFCOUNT_ADD_ZERO), CRASHTYPE(REFCOUNT_INC_SATURATED), diff --git a/include/linux/refcount.h b/include/linux/refcount.h index 59b3b752394d..35f039ecb272 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -266,12 +266,12 @@ bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp) if (oldp) *oldp = old; - if (old == i) { + if (old > 0 && old == i) { smp_acquire__after_ctrl_dep(); return true; } - if (unlikely(old < 0 || old - i < 0)) + if (unlikely(old <= 0 || old - i < 0)) refcount_warn_saturate(r, REFCOUNT_SUB_UAF); return false; -- cgit v1.2.3 From d4433e8b405a882fa2ef29601c4ad262ba6e5526 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Aug 2024 13:40:26 +0000 Subject: inet: constify 'struct net' parameter of various lookup helpers Following helpers do not touch their struct net argument: - bpf_sk_lookup_run_v4() - inet_lookup_reuseport() - inet_lhash2_lookup() - inet_lookup_run_sk_lookup() - __inet_lookup_listener() - __inet_lookup_established() Signed-off-by: Eric Dumazet Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240802134029.3748005-3-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/linux/filter.h | 2 +- include/net/inet_hashtables.h | 8 ++++---- net/ipv4/inet_hashtables.c | 10 +++++----- 3 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index b6672ff61407..4acd1da4dac6 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1616,7 +1616,7 @@ extern struct static_key_false bpf_sk_lookup_enabled; _all_pass || _selected_sk ? SK_PASS : SK_DROP; \ }) -static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol, +static inline bool bpf_sk_lookup_run_v4(const struct net *net, int protocol, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 dport, const int ifindex, struct sock **psk) diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 1cc8b7ca20a1..5eea47f135a4 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -304,7 +304,7 @@ int __inet_hash(struct sock *sk, struct sock *osk); int inet_hash(struct sock *sk); void inet_unhash(struct sock *sk); -struct sock *__inet_lookup_listener(struct net *net, +struct sock *__inet_lookup_listener(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const __be32 saddr, const __be16 sport, @@ -368,7 +368,7 @@ static inline bool inet_match(const struct net *net, const struct sock *sk, /* Sockets in TCP_CLOSE state are _always_ taken out of the hash, so we need * not check it for lookups anymore, thanks Alexey. -DaveM */ -struct sock *__inet_lookup_established(struct net *net, +struct sock *__inet_lookup_established(const struct net *net, struct inet_hashinfo *hashinfo, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 hnum, @@ -382,13 +382,13 @@ inet_ehashfn_t inet_ehashfn; INDIRECT_CALLABLE_DECLARE(inet_ehashfn_t udp_ehashfn); -struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk, +struct sock *inet_lookup_reuseport(const struct net *net, struct sock *sk, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, __be32 daddr, unsigned short hnum, inet_ehashfn_t *ehashfn); -struct sock *inet_lookup_run_sk_lookup(struct net *net, +struct sock *inet_lookup_run_sk_lookup(const struct net *net, int protocol, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 3d913dbd0284..9bfcfd016e18 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -348,7 +348,7 @@ static inline int compute_score(struct sock *sk, const struct net *net, * Return: NULL if sk doesn't have SO_REUSEPORT set, otherwise a pointer to * the selected sock or an error. */ -struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk, +struct sock *inet_lookup_reuseport(const struct net *net, struct sock *sk, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, __be32 daddr, unsigned short hnum, @@ -374,7 +374,7 @@ EXPORT_SYMBOL_GPL(inet_lookup_reuseport); */ /* called with rcu_read_lock() : No refcount taken on the socket */ -static struct sock *inet_lhash2_lookup(struct net *net, +static struct sock *inet_lhash2_lookup(const struct net *net, struct inet_listen_hashbucket *ilb2, struct sk_buff *skb, int doff, const __be32 saddr, __be16 sport, @@ -401,7 +401,7 @@ static struct sock *inet_lhash2_lookup(struct net *net, return result; } -struct sock *inet_lookup_run_sk_lookup(struct net *net, +struct sock *inet_lookup_run_sk_lookup(const struct net *net, int protocol, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, @@ -423,7 +423,7 @@ struct sock *inet_lookup_run_sk_lookup(struct net *net, return sk; } -struct sock *__inet_lookup_listener(struct net *net, +struct sock *__inet_lookup_listener(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const __be32 saddr, __be16 sport, @@ -488,7 +488,7 @@ void sock_edemux(struct sk_buff *skb) } EXPORT_SYMBOL(sock_edemux); -struct sock *__inet_lookup_established(struct net *net, +struct sock *__inet_lookup_established(const struct net *net, struct inet_hashinfo *hashinfo, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 hnum, -- cgit v1.2.3 From 9a2fa1472083580b6c66bdaf291f591e1170123a Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 3 Aug 2024 18:02:00 -0400 Subject: fix bitmap corruption on close_range() with CLOSE_RANGE_UNSHARE copy_fd_bitmaps(new, old, count) is expected to copy the first count/BITS_PER_LONG bits from old->full_fds_bits[] and fill the rest with zeroes. What it does is copying enough words (BITS_TO_LONGS(count/BITS_PER_LONG)), then memsets the rest. That works fine, *if* all bits past the cutoff point are clear. Otherwise we are risking garbage from the last word we'd copied. For most of the callers that is true - expand_fdtable() has count equal to old->max_fds, so there's no open descriptors past count, let alone fully occupied words in ->open_fds[], which is what bits in ->full_fds_bits[] correspond to. The other caller (dup_fd()) passes sane_fdtable_size(old_fdt, max_fds), which is the smallest multiple of BITS_PER_LONG that covers all opened descriptors below max_fds. In the common case (copying on fork()) max_fds is ~0U, so all opened descriptors will be below it and we are fine, by the same reasons why the call in expand_fdtable() is safe. Unfortunately, there is a case where max_fds is less than that and where we might, indeed, end up with junk in ->full_fds_bits[] - close_range(from, to, CLOSE_RANGE_UNSHARE) with * descriptor table being currently shared * 'to' being above the current capacity of descriptor table * 'from' being just under some chunk of opened descriptors. In that case we end up with observably wrong behaviour - e.g. spawn a child with CLONE_FILES, get all descriptors in range 0..127 open, then close_range(64, ~0U, CLOSE_RANGE_UNSHARE) and watch dup(0) ending up with descriptor #128, despite #64 being observably not open. The minimally invasive fix would be to deal with that in dup_fd(). If this proves to add measurable overhead, we can go that way, but let's try to fix copy_fd_bitmaps() first. * new helper: bitmap_copy_and_expand(to, from, bits_to_copy, size). * make copy_fd_bitmaps() take the bitmap size in words, rather than bits; it's 'count' argument is always a multiple of BITS_PER_LONG, so we are not losing any information, and that way we can use the same helper for all three bitmaps - compiler will see that count is a multiple of BITS_PER_LONG for the large ones, so it'll generate plain memcpy()+memset(). Reproducer added to tools/testing/selftests/core/close_range_test.c Cc: stable@vger.kernel.org Signed-off-by: Al Viro --- fs/file.c | 30 +++++++++------------ include/linux/bitmap.h | 12 +++++++++ tools/testing/selftests/core/close_range_test.c | 35 +++++++++++++++++++++++++ 3 files changed, 60 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/fs/file.c b/fs/file.c index a11e59b5d602..655338effe9c 100644 --- a/fs/file.c +++ b/fs/file.c @@ -46,27 +46,23 @@ static void free_fdtable_rcu(struct rcu_head *rcu) #define BITBIT_NR(nr) BITS_TO_LONGS(BITS_TO_LONGS(nr)) #define BITBIT_SIZE(nr) (BITBIT_NR(nr) * sizeof(long)) +#define fdt_words(fdt) ((fdt)->max_fds / BITS_PER_LONG) // words in ->open_fds /* * Copy 'count' fd bits from the old table to the new table and clear the extra * space if any. This does not copy the file pointers. Called with the files * spinlock held for write. */ -static void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, - unsigned int count) +static inline void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, + unsigned int copy_words) { - unsigned int cpy, set; - - cpy = count / BITS_PER_BYTE; - set = (nfdt->max_fds - count) / BITS_PER_BYTE; - memcpy(nfdt->open_fds, ofdt->open_fds, cpy); - memset((char *)nfdt->open_fds + cpy, 0, set); - memcpy(nfdt->close_on_exec, ofdt->close_on_exec, cpy); - memset((char *)nfdt->close_on_exec + cpy, 0, set); - - cpy = BITBIT_SIZE(count); - set = BITBIT_SIZE(nfdt->max_fds) - cpy; - memcpy(nfdt->full_fds_bits, ofdt->full_fds_bits, cpy); - memset((char *)nfdt->full_fds_bits + cpy, 0, set); + unsigned int nwords = fdt_words(nfdt); + + bitmap_copy_and_extend(nfdt->open_fds, ofdt->open_fds, + copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); + bitmap_copy_and_extend(nfdt->close_on_exec, ofdt->close_on_exec, + copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); + bitmap_copy_and_extend(nfdt->full_fds_bits, ofdt->full_fds_bits, + copy_words, nwords); } /* @@ -84,7 +80,7 @@ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt) memcpy(nfdt->fd, ofdt->fd, cpy); memset((char *)nfdt->fd + cpy, 0, set); - copy_fd_bitmaps(nfdt, ofdt, ofdt->max_fds); + copy_fd_bitmaps(nfdt, ofdt, fdt_words(ofdt)); } /* @@ -379,7 +375,7 @@ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int open_files = sane_fdtable_size(old_fdt, max_fds); } - copy_fd_bitmaps(new_fdt, old_fdt, open_files); + copy_fd_bitmaps(new_fdt, old_fdt, open_files / BITS_PER_LONG); old_fds = old_fdt->fd; new_fds = new_fdt->fd; diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 8c4768c44a01..d3b66d77df7a 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -270,6 +270,18 @@ static inline void bitmap_copy_clear_tail(unsigned long *dst, dst[nbits / BITS_PER_LONG] &= BITMAP_LAST_WORD_MASK(nbits); } +static inline void bitmap_copy_and_extend(unsigned long *to, + const unsigned long *from, + unsigned int count, unsigned int size) +{ + unsigned int copy = BITS_TO_LONGS(count); + + memcpy(to, from, copy * sizeof(long)); + if (count % BITS_PER_LONG) + to[copy - 1] &= BITMAP_LAST_WORD_MASK(count); + memset(to + copy, 0, bitmap_size(size) - copy * sizeof(long)); +} + /* * On 32-bit systems bitmaps are represented as u32 arrays internally. On LE64 * machines the order of hi and lo parts of numbers match the bitmap structure. diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c index 991c473e3859..12b4eb9d0434 100644 --- a/tools/testing/selftests/core/close_range_test.c +++ b/tools/testing/selftests/core/close_range_test.c @@ -589,4 +589,39 @@ TEST(close_range_cloexec_unshare_syzbot) EXPECT_EQ(close(fd3), 0); } +TEST(close_range_bitmap_corruption) +{ + pid_t pid; + int status; + struct __clone_args args = { + .flags = CLONE_FILES, + .exit_signal = SIGCHLD, + }; + + /* get the first 128 descriptors open */ + for (int i = 2; i < 128; i++) + EXPECT_GE(dup2(0, i), 0); + + /* get descriptor table shared */ + pid = sys_clone3(&args, sizeof(args)); + ASSERT_GE(pid, 0); + + if (pid == 0) { + /* unshare and truncate descriptor table down to 64 */ + if (sys_close_range(64, ~0U, CLOSE_RANGE_UNSHARE)) + exit(EXIT_FAILURE); + + ASSERT_EQ(fcntl(64, F_GETFD), -1); + /* ... and verify that the range 64..127 is not + stuck "fully used" according to secondary bitmap */ + EXPECT_EQ(dup(0), 64) + exit(EXIT_FAILURE); + exit(EXIT_SUCCESS); + } + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); +} + TEST_HARNESS_MAIN -- cgit v1.2.3 From 10b2a44ccb0cdf85480b6f73a23530aa3ac722de Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Aug 2024 13:40:28 +0000 Subject: inet6: constify 'struct net' parameter of various lookup helpers Following helpers do not touch their struct net argument: - bpf_sk_lookup_run_v6() - __inet6_lookup_established() - inet6_lookup_reuseport() - inet6_lookup_listener() - inet6_lookup_run_sk_lookup() - __inet6_lookup() - inet6_lookup() Signed-off-by: Eric Dumazet Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240802134029.3748005-5-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/linux/filter.h | 2 +- include/net/inet6_hashtables.h | 12 ++++++------ net/ipv6/inet6_hashtables.c | 13 +++++++------ 3 files changed, 14 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 4acd1da4dac6..64e1506fefb8 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1653,7 +1653,7 @@ static inline bool bpf_sk_lookup_run_v4(const struct net *net, int protocol, } #if IS_ENABLED(CONFIG_IPV6) -static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol, +static inline bool bpf_sk_lookup_run_v6(const struct net *net, int protocol, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 591cbf5e4d5f..74dd90ff5f12 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -40,7 +40,7 @@ static inline unsigned int __inet6_ehashfn(const u32 lhash, * * The sockhash lock must be held as a reader here. */ -struct sock *__inet6_lookup_established(struct net *net, +struct sock *__inet6_lookup_established(const struct net *net, struct inet_hashinfo *hashinfo, const struct in6_addr *saddr, const __be16 sport, @@ -56,7 +56,7 @@ inet6_ehashfn_t inet6_ehashfn; INDIRECT_CALLABLE_DECLARE(inet6_ehashfn_t udp6_ehashfn); -struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, +struct sock *inet6_lookup_reuseport(const struct net *net, struct sock *sk, struct sk_buff *skb, int doff, const struct in6_addr *saddr, __be16 sport, @@ -64,7 +64,7 @@ struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, unsigned short hnum, inet6_ehashfn_t *ehashfn); -struct sock *inet6_lookup_listener(struct net *net, +struct sock *inet6_lookup_listener(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, @@ -73,7 +73,7 @@ struct sock *inet6_lookup_listener(struct net *net, const unsigned short hnum, const int dif, const int sdif); -struct sock *inet6_lookup_run_sk_lookup(struct net *net, +struct sock *inet6_lookup_run_sk_lookup(const struct net *net, int protocol, struct sk_buff *skb, int doff, const struct in6_addr *saddr, @@ -82,7 +82,7 @@ struct sock *inet6_lookup_run_sk_lookup(struct net *net, const u16 hnum, const int dif, inet6_ehashfn_t *ehashfn); -static inline struct sock *__inet6_lookup(struct net *net, +static inline struct sock *__inet6_lookup(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, @@ -167,7 +167,7 @@ static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo, iif, sdif, refcounted); } -struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, +struct sock *inet6_lookup(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const __be16 dport, diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index f29f094e57a4..9ec05e354baa 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -46,7 +46,7 @@ EXPORT_SYMBOL_GPL(inet6_ehashfn); * * The sockhash lock must be held as a reader here. */ -struct sock *__inet6_lookup_established(struct net *net, +struct sock *__inet6_lookup_established(const struct net *net, struct inet_hashinfo *hashinfo, const struct in6_addr *saddr, const __be16 sport, @@ -126,7 +126,7 @@ static inline int compute_score(struct sock *sk, const struct net *net, * Return: NULL if sk doesn't have SO_REUSEPORT set, otherwise a pointer to * the selected sock or an error. */ -struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, +struct sock *inet6_lookup_reuseport(const struct net *net, struct sock *sk, struct sk_buff *skb, int doff, const struct in6_addr *saddr, __be16 sport, @@ -147,7 +147,7 @@ struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, EXPORT_SYMBOL_GPL(inet6_lookup_reuseport); /* called with rcu_read_lock() */ -static struct sock *inet6_lhash2_lookup(struct net *net, +static struct sock *inet6_lhash2_lookup(const struct net *net, struct inet_listen_hashbucket *ilb2, struct sk_buff *skb, int doff, const struct in6_addr *saddr, @@ -174,7 +174,7 @@ static struct sock *inet6_lhash2_lookup(struct net *net, return result; } -struct sock *inet6_lookup_run_sk_lookup(struct net *net, +struct sock *inet6_lookup_run_sk_lookup(const struct net *net, int protocol, struct sk_buff *skb, int doff, const struct in6_addr *saddr, @@ -199,7 +199,7 @@ struct sock *inet6_lookup_run_sk_lookup(struct net *net, } EXPORT_SYMBOL_GPL(inet6_lookup_run_sk_lookup); -struct sock *inet6_lookup_listener(struct net *net, +struct sock *inet6_lookup_listener(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, @@ -243,7 +243,8 @@ done: } EXPORT_SYMBOL_GPL(inet6_lookup_listener); -struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, +struct sock *inet6_lookup(const struct net *net, + struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const __be16 dport, -- cgit v1.2.3 From 7e45c1e9edc0004b914e2d5a33245908a06f072c Mon Sep 17 00:00:00 2001 From: Rahul Rameshbabu Date: Tue, 30 Jul 2024 16:40:52 +0300 Subject: net/mlx5: Add support for MTPTM and MTCTR registers Make Management Precision Time Measurement (MTPTM) register and Management Cross Timestamp (MTCTR) register usable in mlx5 driver. Signed-off-by: Rahul Rameshbabu Signed-off-by: Tariq Toukan Reviewed-by: Wojciech Drewek Tested-by: Vadim Fedorenko Link: https://patch.msgid.link/20240730134055.1835261-2-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/fw.c | 1 + include/linux/mlx5/device.h | 7 ++++- include/linux/mlx5/driver.h | 2 ++ include/linux/mlx5/mlx5_ifc.h | 43 ++++++++++++++++++++++++++++ 4 files changed, 52 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index b61b7d966114..76ad46bf477d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -224,6 +224,7 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) if (MLX5_CAP_GEN(dev, mcam_reg)) { mlx5_get_mcam_access_reg_group(dev, MLX5_MCAM_REGS_FIRST_128); mlx5_get_mcam_access_reg_group(dev, MLX5_MCAM_REGS_0x9100_0x917F); + mlx5_get_mcam_access_reg_group(dev, MLX5_MCAM_REGS_0x9180_0x91FF); } if (MLX5_CAP_GEN(dev, qcam_reg)) diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index ba875a619b97..a94bc9e3af96 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1243,7 +1243,8 @@ enum mlx5_pcam_feature_groups { enum mlx5_mcam_reg_groups { MLX5_MCAM_REGS_FIRST_128 = 0x0, MLX5_MCAM_REGS_0x9100_0x917F = 0x2, - MLX5_MCAM_REGS_NUM = 0x3, + MLX5_MCAM_REGS_0x9180_0x91FF = 0x3, + MLX5_MCAM_REGS_NUM = 0x4, }; enum mlx5_mcam_feature_groups { @@ -1392,6 +1393,10 @@ enum mlx5_qcam_feature_groups { MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_0x9100_0x917F], \ mng_access_reg_cap_mask.access_regs2.reg) +#define MLX5_CAP_MCAM_REG3(mdev, reg) \ + MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_0x9180_0x91FF], \ + mng_access_reg_cap_mask.access_regs3.reg) + #define MLX5_CAP_MCAM_FEATURE(mdev, fld) \ MLX5_GET(mcam_reg, (mdev)->caps.mcam, mng_feature_cap_mask.enhanced_features.fld) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index a96438ded15f..9f42834f57c5 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -159,6 +159,8 @@ enum { MLX5_REG_MSECQ = 0x9155, MLX5_REG_MSEES = 0x9156, MLX5_REG_MIRC = 0x9162, + MLX5_REG_MTPTM = 0x9180, + MLX5_REG_MTCTR = 0x9181, MLX5_REG_SBCAM = 0xB01F, MLX5_REG_RESOURCE_DUMP = 0xC000, MLX5_REG_DTOR = 0xC00E, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index cab228cf51c6..234ad6f16e92 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -10401,6 +10401,18 @@ struct mlx5_ifc_mcam_access_reg_bits2 { u8 regs_31_to_0[0x20]; }; +struct mlx5_ifc_mcam_access_reg_bits3 { + u8 regs_127_to_96[0x20]; + + u8 regs_95_to_64[0x20]; + + u8 regs_63_to_32[0x20]; + + u8 regs_31_to_2[0x1e]; + u8 mtctr[0x1]; + u8 mtptm[0x1]; +}; + struct mlx5_ifc_mcam_reg_bits { u8 reserved_at_0[0x8]; u8 feature_group[0x8]; @@ -10413,6 +10425,7 @@ struct mlx5_ifc_mcam_reg_bits { struct mlx5_ifc_mcam_access_reg_bits access_regs; struct mlx5_ifc_mcam_access_reg_bits1 access_regs1; struct mlx5_ifc_mcam_access_reg_bits2 access_regs2; + struct mlx5_ifc_mcam_access_reg_bits3 access_regs3; u8 reserved_at_0[0x80]; } mng_access_reg_cap_mask; @@ -11166,6 +11179,34 @@ struct mlx5_ifc_mtmp_reg_bits { u8 sensor_name_lo[0x20]; }; +struct mlx5_ifc_mtptm_reg_bits { + u8 reserved_at_0[0x10]; + u8 psta[0x1]; + u8 reserved_at_11[0xf]; + + u8 reserved_at_20[0x60]; +}; + +enum { + MLX5_MTCTR_REQUEST_NOP = 0x0, + MLX5_MTCTR_REQUEST_PTM_ROOT_CLOCK = 0x1, + MLX5_MTCTR_REQUEST_FREE_RUNNING_COUNTER = 0x2, + MLX5_MTCTR_REQUEST_REAL_TIME_CLOCK = 0x3, +}; + +struct mlx5_ifc_mtctr_reg_bits { + u8 first_clock_timestamp_request[0x8]; + u8 second_clock_timestamp_request[0x8]; + u8 reserved_at_10[0x10]; + + u8 first_clock_valid[0x1]; + u8 second_clock_valid[0x1]; + u8 reserved_at_22[0x1e]; + + u8 first_clock_timestamp[0x40]; + u8 second_clock_timestamp[0x40]; +}; + union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_bufferx_reg_bits bufferx_reg; struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits eth_2819_cntrs_grp_data_layout; @@ -11230,6 +11271,8 @@ union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_mrtc_reg_bits mrtc_reg; struct mlx5_ifc_mtcap_reg_bits mtcap_reg; struct mlx5_ifc_mtmp_reg_bits mtmp_reg; + struct mlx5_ifc_mtptm_reg_bits mtptm_reg; + struct mlx5_ifc_mtctr_reg_bits mtctr_reg; u8 reserved_at_0[0x60e0]; }; -- cgit v1.2.3 From c114e9948c2b6a0b400266e59cc656b59e795bca Mon Sep 17 00:00:00 2001 From: Roman Kisel Date: Thu, 18 Jul 2024 11:27:24 -0700 Subject: coredump: Standartize and fix logging The coredump code does not log the process ID and the comm consistently, logs unescaped comm when it does log it, and does not always use the ratelimited logging. That makes it harder to analyze logs and puts the system at the risk of spamming the system log incase something crashes many times over and over again. Fix that by logging TGID and comm (escaped) consistently and using the ratelimited logging always. Signed-off-by: Roman Kisel Tested-by: Allen Pais Link: https://lore.kernel.org/r/20240718182743.1959160-2-romank@linux.microsoft.com Signed-off-by: Kees Cook --- fs/coredump.c | 43 ++++++++++++++++--------------------------- include/linux/coredump.h | 22 ++++++++++++++++++++++ 2 files changed, 38 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/fs/coredump.c b/fs/coredump.c index 7f12ff6ad1d3..87ff71a59fbe 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -586,8 +586,7 @@ void do_coredump(const kernel_siginfo_t *siginfo) struct subprocess_info *sub_info; if (ispipe < 0) { - printk(KERN_WARNING "format_corename failed\n"); - printk(KERN_WARNING "Aborting core\n"); + coredump_report_failure("format_corename failed, aborting core"); goto fail_unlock; } @@ -607,27 +606,21 @@ void do_coredump(const kernel_siginfo_t *siginfo) * right pid if a thread in a multi-threaded * core_pattern process dies. */ - printk(KERN_WARNING - "Process %d(%s) has RLIMIT_CORE set to 1\n", - task_tgid_vnr(current), current->comm); - printk(KERN_WARNING "Aborting core\n"); + coredump_report_failure("RLIMIT_CORE is set to 1, aborting core"); goto fail_unlock; } cprm.limit = RLIM_INFINITY; dump_count = atomic_inc_return(&core_dump_count); if (core_pipe_limit && (core_pipe_limit < dump_count)) { - printk(KERN_WARNING "Pid %d(%s) over core_pipe_limit\n", - task_tgid_vnr(current), current->comm); - printk(KERN_WARNING "Skipping core dump\n"); + coredump_report_failure("over core_pipe_limit, skipping core dump"); goto fail_dropcount; } helper_argv = kmalloc_array(argc + 1, sizeof(*helper_argv), GFP_KERNEL); if (!helper_argv) { - printk(KERN_WARNING "%s failed to allocate memory\n", - __func__); + coredump_report_failure("%s failed to allocate memory", __func__); goto fail_dropcount; } for (argi = 0; argi < argc; argi++) @@ -644,8 +637,7 @@ void do_coredump(const kernel_siginfo_t *siginfo) kfree(helper_argv); if (retval) { - printk(KERN_INFO "Core dump to |%s pipe failed\n", - cn.corename); + coredump_report_failure("|%s pipe failed", cn.corename); goto close_fail; } } else { @@ -658,10 +650,8 @@ void do_coredump(const kernel_siginfo_t *siginfo) goto fail_unlock; if (need_suid_safe && cn.corename[0] != '/') { - printk(KERN_WARNING "Pid %d(%s) can only dump core "\ - "to fully qualified path!\n", - task_tgid_vnr(current), current->comm); - printk(KERN_WARNING "Skipping core dump\n"); + coredump_report_failure( + "this process can only dump core to a fully qualified path, skipping core dump"); goto fail_unlock; } @@ -730,13 +720,13 @@ void do_coredump(const kernel_siginfo_t *siginfo) idmap = file_mnt_idmap(cprm.file); if (!vfsuid_eq_kuid(i_uid_into_vfsuid(idmap, inode), current_fsuid())) { - pr_info_ratelimited("Core dump to %s aborted: cannot preserve file owner\n", - cn.corename); + coredump_report_failure("Core dump to %s aborted: " + "cannot preserve file owner", cn.corename); goto close_fail; } if ((inode->i_mode & 0677) != 0600) { - pr_info_ratelimited("Core dump to %s aborted: cannot preserve file permissions\n", - cn.corename); + coredump_report_failure("Core dump to %s aborted: " + "cannot preserve file permissions", cn.corename); goto close_fail; } if (!(cprm.file->f_mode & FMODE_CAN_WRITE)) @@ -757,7 +747,7 @@ void do_coredump(const kernel_siginfo_t *siginfo) * have this set to NULL. */ if (!cprm.file) { - pr_info("Core dump to |%s disabled\n", cn.corename); + coredump_report_failure("Core dump to |%s disabled", cn.corename); goto close_fail; } if (!dump_vma_snapshot(&cprm)) @@ -983,11 +973,10 @@ void validate_coredump_safety(void) { if (suid_dumpable == SUID_DUMP_ROOT && core_pattern[0] != '/' && core_pattern[0] != '|') { - pr_warn( -"Unsafe core_pattern used with fs.suid_dumpable=2.\n" -"Pipe handler or fully qualified core dump path required.\n" -"Set kernel.core_pattern before fs.suid_dumpable.\n" - ); + + coredump_report_failure("Unsafe core_pattern used with fs.suid_dumpable=2: " + "pipe handler or fully qualified core dump path required. " + "Set kernel.core_pattern before fs.suid_dumpable."); } } diff --git a/include/linux/coredump.h b/include/linux/coredump.h index 0904ba010341..45e598fe3476 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -43,8 +43,30 @@ extern int dump_align(struct coredump_params *cprm, int align); int dump_user_range(struct coredump_params *cprm, unsigned long start, unsigned long len); extern void do_coredump(const kernel_siginfo_t *siginfo); + +/* + * Logging for the coredump code, ratelimited. + * The TGID and comm fields are added to the message. + */ + +#define __COREDUMP_PRINTK(Level, Format, ...) \ + do { \ + char comm[TASK_COMM_LEN]; \ + \ + get_task_comm(comm, current); \ + printk_ratelimited(Level "coredump: %d(%*pE): " Format "\n", \ + task_tgid_vnr(current), (int)strlen(comm), comm, ##__VA_ARGS__); \ + } while (0) \ + +#define coredump_report(fmt, ...) __COREDUMP_PRINTK(KERN_INFO, fmt, ##__VA_ARGS__) +#define coredump_report_failure(fmt, ...) __COREDUMP_PRINTK(KERN_WARNING, fmt, ##__VA_ARGS__) + #else static inline void do_coredump(const kernel_siginfo_t *siginfo) {} + +#define coredump_report(...) +#define coredump_report_failure(...) + #endif #if defined(CONFIG_COREDUMP) && defined(CONFIG_SYSCTL) -- cgit v1.2.3 From fb97d2eb542faf19a8725afbd75cbc2518903210 Mon Sep 17 00:00:00 2001 From: Roman Kisel Date: Thu, 18 Jul 2024 11:27:25 -0700 Subject: binfmt_elf, coredump: Log the reason of the failed core dumps Missing, failed, or corrupted core dumps might impede crash investigations. To improve reliability of that process and consequently the programs themselves, one needs to trace the path from producing a core dumpfile to analyzing it. That path starts from the core dump file written to the disk by the kernel or to the standard input of a user mode helper program to which the kernel streams the coredump contents. There are cases where the kernel will interrupt writing the core out or produce a truncated/not-well-formed core dump without leaving a note. Add logging for the core dump collection failure paths to be able to reason what has gone wrong when the core dump is malformed or missing. Report the size of the data written to aid in diagnosing the user mode helper. Signed-off-by: Roman Kisel Link: https://lore.kernel.org/r/20240718182743.1959160-3-romank@linux.microsoft.com Signed-off-by: Kees Cook --- fs/binfmt_elf.c | 48 +++++++++++++++------ fs/coredump.c | 107 ++++++++++++++++++++++++++++++++++++++--------- include/linux/coredump.h | 8 +++- kernel/signal.c | 21 +++++++++- 4 files changed, 150 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 19fa49cd9907..bf9bfd1a0007 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -2027,8 +2027,10 @@ static int elf_core_dump(struct coredump_params *cprm) * Collect all the non-memory information about the process for the * notes. This also sets up the file header. */ - if (!fill_note_info(&elf, e_phnum, &info, cprm)) + if (!fill_note_info(&elf, e_phnum, &info, cprm)) { + coredump_report_failure("Error collecting note info"); goto end_coredump; + } has_dumped = 1; @@ -2043,8 +2045,10 @@ static int elf_core_dump(struct coredump_params *cprm) sz += elf_coredump_extra_notes_size(); phdr4note = kmalloc(sizeof(*phdr4note), GFP_KERNEL); - if (!phdr4note) + if (!phdr4note) { + coredump_report_failure("Error allocating program headers note entry"); goto end_coredump; + } fill_elf_note_phdr(phdr4note, sz, offset); offset += sz; @@ -2058,18 +2062,24 @@ static int elf_core_dump(struct coredump_params *cprm) if (e_phnum == PN_XNUM) { shdr4extnum = kmalloc(sizeof(*shdr4extnum), GFP_KERNEL); - if (!shdr4extnum) + if (!shdr4extnum) { + coredump_report_failure("Error allocating extra program headers"); goto end_coredump; + } fill_extnum_info(&elf, shdr4extnum, e_shoff, segs); } offset = dataoff; - if (!dump_emit(cprm, &elf, sizeof(elf))) + if (!dump_emit(cprm, &elf, sizeof(elf))) { + coredump_report_failure("Error emitting the ELF headers"); goto end_coredump; + } - if (!dump_emit(cprm, phdr4note, sizeof(*phdr4note))) + if (!dump_emit(cprm, phdr4note, sizeof(*phdr4note))) { + coredump_report_failure("Error emitting the program header for notes"); goto end_coredump; + } /* Write program headers for segments dump */ for (i = 0; i < cprm->vma_count; i++) { @@ -2092,20 +2102,28 @@ static int elf_core_dump(struct coredump_params *cprm) phdr.p_flags |= PF_X; phdr.p_align = ELF_EXEC_PAGESIZE; - if (!dump_emit(cprm, &phdr, sizeof(phdr))) + if (!dump_emit(cprm, &phdr, sizeof(phdr))) { + coredump_report_failure("Error emitting program headers"); goto end_coredump; + } } - if (!elf_core_write_extra_phdrs(cprm, offset)) + if (!elf_core_write_extra_phdrs(cprm, offset)) { + coredump_report_failure("Error writing out extra program headers"); goto end_coredump; + } /* write out the notes section */ - if (!write_note_info(&info, cprm)) + if (!write_note_info(&info, cprm)) { + coredump_report_failure("Error writing out notes"); goto end_coredump; + } /* For cell spufs */ - if (elf_coredump_extra_notes_write(cprm)) + if (elf_coredump_extra_notes_write(cprm)) { + coredump_report_failure("Error writing out extra notes"); goto end_coredump; + } /* Align to page */ dump_skip_to(cprm, dataoff); @@ -2113,16 +2131,22 @@ static int elf_core_dump(struct coredump_params *cprm) for (i = 0; i < cprm->vma_count; i++) { struct core_vma_metadata *meta = cprm->vma_meta + i; - if (!dump_user_range(cprm, meta->start, meta->dump_size)) + if (!dump_user_range(cprm, meta->start, meta->dump_size)) { + coredump_report_failure("Error writing out the process memory"); goto end_coredump; + } } - if (!elf_core_write_extra_data(cprm)) + if (!elf_core_write_extra_data(cprm)) { + coredump_report_failure("Error writing out extra data"); goto end_coredump; + } if (e_phnum == PN_XNUM) { - if (!dump_emit(cprm, shdr4extnum, sizeof(*shdr4extnum))) + if (!dump_emit(cprm, shdr4extnum, sizeof(*shdr4extnum))) { + coredump_report_failure("Error emitting extra program headers"); goto end_coredump; + } } end_coredump: diff --git a/fs/coredump.c b/fs/coredump.c index 87ff71a59fbe..5814a6d781ce 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -464,7 +464,17 @@ static bool dump_interrupted(void) * but then we need to teach dump_write() to restart and clear * TIF_SIGPENDING. */ - return fatal_signal_pending(current) || freezing(current); + if (fatal_signal_pending(current)) { + coredump_report_failure("interrupted: fatal signal pending"); + return true; + } + + if (freezing(current)) { + coredump_report_failure("interrupted: freezing"); + return true; + } + + return false; } static void wait_for_dump_helpers(struct file *file) @@ -519,7 +529,7 @@ static int umh_pipe_setup(struct subprocess_info *info, struct cred *new) return err; } -void do_coredump(const kernel_siginfo_t *siginfo) +int do_coredump(const kernel_siginfo_t *siginfo) { struct core_state core_state; struct core_name cn; @@ -527,7 +537,7 @@ void do_coredump(const kernel_siginfo_t *siginfo) struct linux_binfmt * binfmt; const struct cred *old_cred; struct cred *cred; - int retval = 0; + int retval; int ispipe; size_t *argv = NULL; int argc = 0; @@ -551,14 +561,20 @@ void do_coredump(const kernel_siginfo_t *siginfo) audit_core_dumps(siginfo->si_signo); binfmt = mm->binfmt; - if (!binfmt || !binfmt->core_dump) + if (!binfmt || !binfmt->core_dump) { + retval = -ENOEXEC; goto fail; - if (!__get_dumpable(cprm.mm_flags)) + } + if (!__get_dumpable(cprm.mm_flags)) { + retval = -EACCES; goto fail; + } cred = prepare_creds(); - if (!cred) + if (!cred) { + retval = -EPERM; goto fail; + } /* * We cannot trust fsuid as being the "true" uid of the process * nor do we know its entire history. We only know it was tainted @@ -587,6 +603,7 @@ void do_coredump(const kernel_siginfo_t *siginfo) if (ispipe < 0) { coredump_report_failure("format_corename failed, aborting core"); + retval = ispipe; goto fail_unlock; } @@ -607,6 +624,7 @@ void do_coredump(const kernel_siginfo_t *siginfo) * core_pattern process dies. */ coredump_report_failure("RLIMIT_CORE is set to 1, aborting core"); + retval = -EPERM; goto fail_unlock; } cprm.limit = RLIM_INFINITY; @@ -614,6 +632,7 @@ void do_coredump(const kernel_siginfo_t *siginfo) dump_count = atomic_inc_return(&core_dump_count); if (core_pipe_limit && (core_pipe_limit < dump_count)) { coredump_report_failure("over core_pipe_limit, skipping core dump"); + retval = -E2BIG; goto fail_dropcount; } @@ -621,6 +640,7 @@ void do_coredump(const kernel_siginfo_t *siginfo) GFP_KERNEL); if (!helper_argv) { coredump_report_failure("%s failed to allocate memory", __func__); + retval = -ENOMEM; goto fail_dropcount; } for (argi = 0; argi < argc; argi++) @@ -646,12 +666,16 @@ void do_coredump(const kernel_siginfo_t *siginfo) int open_flags = O_CREAT | O_WRONLY | O_NOFOLLOW | O_LARGEFILE | O_EXCL; - if (cprm.limit < binfmt->min_coredump) + if (cprm.limit < binfmt->min_coredump) { + coredump_report_failure("over coredump resource limit, skipping core dump"); + retval = -E2BIG; goto fail_unlock; + } if (need_suid_safe && cn.corename[0] != '/') { coredump_report_failure( "this process can only dump core to a fully qualified path, skipping core dump"); + retval = -EPERM; goto fail_unlock; } @@ -697,20 +721,28 @@ void do_coredump(const kernel_siginfo_t *siginfo) } else { cprm.file = filp_open(cn.corename, open_flags, 0600); } - if (IS_ERR(cprm.file)) + if (IS_ERR(cprm.file)) { + retval = PTR_ERR(cprm.file); goto fail_unlock; + } inode = file_inode(cprm.file); - if (inode->i_nlink > 1) + if (inode->i_nlink > 1) { + retval = -EMLINK; goto close_fail; - if (d_unhashed(cprm.file->f_path.dentry)) + } + if (d_unhashed(cprm.file->f_path.dentry)) { + retval = -EEXIST; goto close_fail; + } /* * AK: actually i see no reason to not allow this for named * pipes etc, but keep the previous behaviour for now. */ - if (!S_ISREG(inode->i_mode)) + if (!S_ISREG(inode->i_mode)) { + retval = -EISDIR; goto close_fail; + } /* * Don't dump core if the filesystem changed owner or mode * of the file during file creation. This is an issue when @@ -722,17 +754,22 @@ void do_coredump(const kernel_siginfo_t *siginfo) current_fsuid())) { coredump_report_failure("Core dump to %s aborted: " "cannot preserve file owner", cn.corename); + retval = -EPERM; goto close_fail; } if ((inode->i_mode & 0677) != 0600) { coredump_report_failure("Core dump to %s aborted: " "cannot preserve file permissions", cn.corename); + retval = -EPERM; goto close_fail; } - if (!(cprm.file->f_mode & FMODE_CAN_WRITE)) + if (!(cprm.file->f_mode & FMODE_CAN_WRITE)) { + retval = -EACCES; goto close_fail; - if (do_truncate(idmap, cprm.file->f_path.dentry, - 0, 0, cprm.file)) + } + retval = do_truncate(idmap, cprm.file->f_path.dentry, + 0, 0, cprm.file); + if (retval) goto close_fail; } @@ -748,10 +785,15 @@ void do_coredump(const kernel_siginfo_t *siginfo) */ if (!cprm.file) { coredump_report_failure("Core dump to |%s disabled", cn.corename); + retval = -EPERM; goto close_fail; } - if (!dump_vma_snapshot(&cprm)) + if (!dump_vma_snapshot(&cprm)) { + coredump_report_failure("Can't get VMA snapshot for core dump |%s", + cn.corename); + retval = -EACCES; goto close_fail; + } file_start_write(cprm.file); core_dumped = binfmt->core_dump(&cprm); @@ -767,9 +809,21 @@ void do_coredump(const kernel_siginfo_t *siginfo) } file_end_write(cprm.file); free_vma_snapshot(&cprm); + } else { + coredump_report_failure("Core dump to %s%s has been interrupted", + ispipe ? "|" : "", cn.corename); + retval = -EAGAIN; + goto fail; } + coredump_report( + "written to %s%s: VMAs: %d, size %zu; core: %lld bytes, pos %lld", + ispipe ? "|" : "", cn.corename, + cprm.vma_count, cprm.vma_data_size, cprm.written, cprm.pos); if (ispipe && core_pipe_limit) wait_for_dump_helpers(cprm.file); + + retval = 0; + close_fail: if (cprm.file) filp_close(cprm.file, NULL); @@ -784,7 +838,7 @@ fail_unlock: fail_creds: put_cred(cred); fail: - return; + return retval; } /* @@ -804,8 +858,16 @@ static int __dump_emit(struct coredump_params *cprm, const void *addr, int nr) if (dump_interrupted()) return 0; n = __kernel_write(file, addr, nr, &pos); - if (n != nr) + if (n != nr) { + if (n < 0) + coredump_report_failure("failed when writing out, error %zd", n); + else + coredump_report_failure( + "partially written out, only %zd(of %d) bytes written", + n, nr); + return 0; + } file->f_pos = pos; cprm->written += n; cprm->pos += n; @@ -818,9 +880,16 @@ static int __dump_skip(struct coredump_params *cprm, size_t nr) static char zeroes[PAGE_SIZE]; struct file *file = cprm->file; if (file->f_mode & FMODE_LSEEK) { - if (dump_interrupted() || - vfs_llseek(file, nr, SEEK_CUR) < 0) + int ret; + + if (dump_interrupted()) return 0; + + ret = vfs_llseek(file, nr, SEEK_CUR); + if (ret < 0) { + coredump_report_failure("failed when seeking, error %d", ret); + return 0; + } cprm->pos += nr; return 1; } else { diff --git a/include/linux/coredump.h b/include/linux/coredump.h index 45e598fe3476..edeb8532ce0f 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -42,7 +42,7 @@ extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr); extern int dump_align(struct coredump_params *cprm, int align); int dump_user_range(struct coredump_params *cprm, unsigned long start, unsigned long len); -extern void do_coredump(const kernel_siginfo_t *siginfo); +extern int do_coredump(const kernel_siginfo_t *siginfo); /* * Logging for the coredump code, ratelimited. @@ -62,7 +62,11 @@ extern void do_coredump(const kernel_siginfo_t *siginfo); #define coredump_report_failure(fmt, ...) __COREDUMP_PRINTK(KERN_WARNING, fmt, ##__VA_ARGS__) #else -static inline void do_coredump(const kernel_siginfo_t *siginfo) {} +static inline int do_coredump(const kernel_siginfo_t *siginfo) +{ + /* Coredump support is not available, can't fail. */ + return 0; +} #define coredump_report(...) #define coredump_report_failure(...) diff --git a/kernel/signal.c b/kernel/signal.c index 60c737e423a1..8c3417550d71 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2888,6 +2888,8 @@ relock: current->flags |= PF_SIGNALED; if (sig_kernel_coredump(signr)) { + int ret; + if (print_fatal_signals) print_fatal_signal(signr); proc_coredump_connector(current); @@ -2899,7 +2901,24 @@ relock: * first and our do_group_exit call below will use * that value and ignore the one we pass it. */ - do_coredump(&ksig->info); + ret = do_coredump(&ksig->info); + if (ret) + coredump_report_failure("coredump has not been created, error %d", + ret); + else if (!IS_ENABLED(CONFIG_COREDUMP)) { + /* + * Coredumps are not available, can't fail collecting + * the coredump. + * + * Leave a note though that the coredump is going to be + * not created. This is not an error or a warning as disabling + * support in the kernel for coredumps isn't commonplace, and + * the user must've built the kernel with the custom config so + * let them know all works as desired. + */ + coredump_report("no coredump collected as " + "that is disabled in the kernel configuration"); + } } /* -- cgit v1.2.3 From 7424fc6b86c8980a87169e005f5cd4438d18efe6 Mon Sep 17 00:00:00 2001 From: Gatlin Newhouse Date: Wed, 24 Jul 2024 00:01:55 +0000 Subject: x86/traps: Enable UBSAN traps on x86 Currently ARM64 extracts which specific sanitizer has caused a trap via encoded data in the trap instruction. Clang on x86 currently encodes the same data in the UD1 instruction but x86 handle_bug() and is_valid_bugaddr() currently only look at UD2. Bring x86 to parity with ARM64, similar to commit 25b84002afb9 ("arm64: Support Clang UBSAN trap codes for better reporting"). See the llvm links for information about the code generation. Enable the reporting of UBSAN sanitizer details on x86 compiled with clang when CONFIG_UBSAN_TRAP=y by analysing UD1 and retrieving the type immediate which is encoded by the compiler after the UD1. [ tglx: Simplified it by moving the printk() into handle_bug() ] Signed-off-by: Gatlin Newhouse Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Cc: Kees Cook Link: https://lore.kernel.org/all/20240724000206.451425-1-gatlin.newhouse@gmail.com Link: https://github.com/llvm/llvm-project/commit/c5978f42ec8e9#diff-bb68d7cd885f41cfc35843998b0f9f534adb60b415f647109e597ce448e92d9f Link: https://github.com/llvm/llvm-project/blob/main/llvm/lib/Target/X86/X86InstrSystem.td#L27 --- arch/x86/include/asm/bug.h | 12 ++++++++++ arch/x86/kernel/traps.c | 59 ++++++++++++++++++++++++++++++++++++++++++---- include/linux/ubsan.h | 5 ++++ lib/Kconfig.ubsan | 4 ++-- 4 files changed, 73 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index a3ec87d198ac..806649c7f23d 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -13,6 +13,18 @@ #define INSN_UD2 0x0b0f #define LEN_UD2 2 +/* + * In clang we have UD1s reporting UBSAN failures on X86, 64 and 32bit. + */ +#define INSN_ASOP 0x67 +#define OPCODE_ESCAPE 0x0f +#define SECOND_BYTE_OPCODE_UD1 0xb9 +#define SECOND_BYTE_OPCODE_UD2 0x0b + +#define BUG_NONE 0xffff +#define BUG_UD1 0xfffe +#define BUG_UD2 0xfffd + #ifdef CONFIG_GENERIC_BUG #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 4fa0b17e5043..415881607c5d 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include @@ -91,6 +92,47 @@ __always_inline int is_valid_bugaddr(unsigned long addr) return *(unsigned short *)addr == INSN_UD2; } +/* + * Check for UD1 or UD2, accounting for Address Size Override Prefixes. + * If it's a UD1, get the ModRM byte to pass along to UBSan. + */ +__always_inline int decode_bug(unsigned long addr, u32 *imm) +{ + u8 v; + + if (addr < TASK_SIZE_MAX) + return BUG_NONE; + + v = *(u8 *)(addr++); + if (v == INSN_ASOP) + v = *(u8 *)(addr++); + if (v != OPCODE_ESCAPE) + return BUG_NONE; + + v = *(u8 *)(addr++); + if (v == SECOND_BYTE_OPCODE_UD2) + return BUG_UD2; + + if (!IS_ENABLED(CONFIG_UBSAN_TRAP) || v != SECOND_BYTE_OPCODE_UD1) + return BUG_NONE; + + /* Retrieve the immediate (type value) for the UBSAN UD1 */ + v = *(u8 *)(addr++); + if (X86_MODRM_RM(v) == 4) + addr++; + + *imm = 0; + if (X86_MODRM_MOD(v) == 1) + *imm = *(u8 *)addr; + else if (X86_MODRM_MOD(v) == 2) + *imm = *(u32 *)addr; + else + WARN_ONCE(1, "Unexpected MODRM_MOD: %u\n", X86_MODRM_MOD(v)); + + return BUG_UD1; +} + + static nokprobe_inline int do_trap_no_signal(struct task_struct *tsk, int trapnr, const char *str, struct pt_regs *regs, long error_code) @@ -216,6 +258,8 @@ static inline void handle_invalid_op(struct pt_regs *regs) static noinstr bool handle_bug(struct pt_regs *regs) { bool handled = false; + int ud_type; + u32 imm; /* * Normally @regs are unpoisoned by irqentry_enter(), but handle_bug() @@ -223,7 +267,8 @@ static noinstr bool handle_bug(struct pt_regs *regs) * irqentry_enter(). */ kmsan_unpoison_entry_regs(regs); - if (!is_valid_bugaddr(regs->ip)) + ud_type = decode_bug(regs->ip, &imm); + if (ud_type == BUG_NONE) return handled; /* @@ -236,10 +281,14 @@ static noinstr bool handle_bug(struct pt_regs *regs) */ if (regs->flags & X86_EFLAGS_IF) raw_local_irq_enable(); - if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN || - handle_cfi_failure(regs) == BUG_TRAP_TYPE_WARN) { - regs->ip += LEN_UD2; - handled = true; + if (ud_type == BUG_UD2) { + if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN || + handle_cfi_failure(regs) == BUG_TRAP_TYPE_WARN) { + regs->ip += LEN_UD2; + handled = true; + } + } else if (IS_ENABLED(CONFIG_UBSAN_TRAP)) { + pr_crit("%s at %pS\n", report_ubsan_failure(regs, imm), (void *)regs->ip); } if (regs->flags & X86_EFLAGS_IF) raw_local_irq_disable(); diff --git a/include/linux/ubsan.h b/include/linux/ubsan.h index bff7445498de..d8219cbe09ff 100644 --- a/include/linux/ubsan.h +++ b/include/linux/ubsan.h @@ -4,6 +4,11 @@ #ifdef CONFIG_UBSAN_TRAP const char *report_ubsan_failure(struct pt_regs *regs, u32 check_type); +#else +static inline const char *report_ubsan_failure(struct pt_regs *regs, u32 check_type) +{ + return NULL; +} #endif #endif diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan index bdda600f8dfb..1d4aa7a83b3a 100644 --- a/lib/Kconfig.ubsan +++ b/lib/Kconfig.ubsan @@ -29,8 +29,8 @@ config UBSAN_TRAP Also note that selecting Y will cause your kernel to Oops with an "illegal instruction" error with no further details - when a UBSAN violation occurs. (Except on arm64, which will - report which Sanitizer failed.) This may make it hard to + when a UBSAN violation occurs. (Except on arm64 and x86, which + will report which Sanitizer failed.) This may make it hard to determine whether an Oops was caused by UBSAN or to figure out the details of a UBSAN violation. It makes the kernel log output less useful for bug reports. -- cgit v1.2.3 From 97edbc02b2efdb0cd0f507b6a45fc509acc861bb Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 10 Jul 2024 14:51:11 -0400 Subject: buffer: Convert block_write_end() to take a folio All callers now have a folio, so pass it in instead of converting from a folio to a page and back to a folio again. Saves a call to compound_head(). Reviewed-by: Josef Bacik Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Christian Brauner --- block/fops.c | 2 +- fs/buffer.c | 5 ++--- fs/ext2/dir.c | 2 +- fs/ext4/inode.c | 4 ++-- fs/iomap/buffered-io.c | 2 +- fs/minix/dir.c | 2 +- fs/nilfs2/dir.c | 2 +- fs/nilfs2/recovery.c | 2 +- fs/sysv/dir.c | 2 +- fs/ufs/dir.c | 2 +- include/linux/buffer_head.h | 4 ++-- 11 files changed, 14 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/block/fops.c b/block/fops.c index da44fedb23e5..df0e762cf397 100644 --- a/block/fops.c +++ b/block/fops.c @@ -462,7 +462,7 @@ static int blkdev_write_end(struct file *file, struct address_space *mapping, { struct folio *folio = page_folio(page); int ret; - ret = block_write_end(file, mapping, pos, len, copied, page, fsdata); + ret = block_write_end(file, mapping, pos, len, copied, folio, fsdata); folio_unlock(folio); folio_put(folio); diff --git a/fs/buffer.c b/fs/buffer.c index 448338810802..acba3dfe55d8 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2247,9 +2247,8 @@ EXPORT_SYMBOL(block_write_begin); int block_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { - struct folio *folio = page_folio(page); size_t start = pos - folio_pos(folio); if (unlikely(copied < len)) { @@ -2288,7 +2287,7 @@ int generic_write_end(struct file *file, struct address_space *mapping, loff_t old_size = inode->i_size; bool i_size_changed = false; - copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); + copied = block_write_end(file, mapping, pos, len, copied, folio, fsdata); /* * No need to use i_size_read() here, the i_size cannot change under us diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c index 087457061c6e..60605fbdd0eb 100644 --- a/fs/ext2/dir.c +++ b/fs/ext2/dir.c @@ -87,7 +87,7 @@ static void ext2_commit_chunk(struct folio *folio, loff_t pos, unsigned len) struct inode *dir = mapping->host; inode_inc_iversion(dir); - block_write_end(NULL, mapping, pos, len, len, &folio->page, NULL); + block_write_end(NULL, mapping, pos, len, len, folio, NULL); if (pos+len > dir->i_size) { i_size_write(dir, pos+len); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 941c1c0d5c6e..1e4831d83adc 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1315,7 +1315,7 @@ static int ext4_write_end(struct file *file, return ext4_write_inline_data_end(inode, pos, len, copied, folio); - copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); + copied = block_write_end(file, mapping, pos, len, copied, folio, fsdata); /* * it's important to update i_size while still holding folio lock: * page writeout could otherwise come in and zero beyond i_size. @@ -3029,7 +3029,7 @@ static int ext4_da_do_write_end(struct address_space *mapping, * flag, which all that's needed to trigger page writeback. */ copied = block_write_end(NULL, mapping, pos, len, copied, - &folio->page, NULL); + folio, NULL); new_i_size = pos + copied; /* diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index f420c53d86ac..9b4ca3811a24 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -900,7 +900,7 @@ static bool iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len, size_t bh_written; bh_written = block_write_end(NULL, iter->inode->i_mapping, pos, - len, copied, &folio->page, NULL); + len, copied, folio, NULL); WARN_ON_ONCE(bh_written != copied && bh_written != 0); return bh_written == copied; } diff --git a/fs/minix/dir.c b/fs/minix/dir.c index 5f9e2fc91003..dd2a425b41f0 100644 --- a/fs/minix/dir.c +++ b/fs/minix/dir.c @@ -45,7 +45,7 @@ static void dir_commit_chunk(struct folio *folio, loff_t pos, unsigned len) struct address_space *mapping = folio->mapping; struct inode *dir = mapping->host; - block_write_end(NULL, mapping, pos, len, len, &folio->page, NULL); + block_write_end(NULL, mapping, pos, len, len, folio, NULL); if (pos+len > dir->i_size) { i_size_write(dir, pos+len); diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index 4a29b0138d75..66af42f88ca7 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -96,7 +96,7 @@ static void nilfs_commit_chunk(struct folio *folio, int err; nr_dirty = nilfs_page_count_clean_buffers(&folio->page, from, to); - copied = block_write_end(NULL, mapping, pos, len, len, &folio->page, NULL); + copied = block_write_end(NULL, mapping, pos, len, len, folio, NULL); if (pos + copied > dir->i_size) i_size_write(dir, pos + copied); if (IS_DIRSYNC(dir)) diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c index 15653701b1c8..40c5dfbc9d41 100644 --- a/fs/nilfs2/recovery.c +++ b/fs/nilfs2/recovery.c @@ -533,7 +533,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs, goto failed_page; block_write_end(NULL, inode->i_mapping, pos, blocksize, - blocksize, page, NULL); + blocksize, folio, NULL); folio_unlock(folio); folio_put(folio); diff --git a/fs/sysv/dir.c b/fs/sysv/dir.c index 27eaa5273ba7..639307e2ff8c 100644 --- a/fs/sysv/dir.c +++ b/fs/sysv/dir.c @@ -33,7 +33,7 @@ static void dir_commit_chunk(struct folio *folio, loff_t pos, unsigned len) struct address_space *mapping = folio->mapping; struct inode *dir = mapping->host; - block_write_end(NULL, mapping, pos, len, len, &folio->page, NULL); + block_write_end(NULL, mapping, pos, len, len, folio, NULL); if (pos+len > dir->i_size) { i_size_write(dir, pos+len); mark_inode_dirty(dir); diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c index 3b3cd84f1f7f..1579561118f5 100644 --- a/fs/ufs/dir.c +++ b/fs/ufs/dir.c @@ -48,7 +48,7 @@ static void ufs_commit_chunk(struct folio *folio, loff_t pos, unsigned len) struct inode *dir = mapping->host; inode_inc_iversion(dir); - block_write_end(NULL, mapping, pos, len, len, &folio->page, NULL); + block_write_end(NULL, mapping, pos, len, len, folio, NULL); if (pos+len > dir->i_size) { i_size_write(dir, pos+len); mark_inode_dirty(dir); diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 14acf1bbe0ce..3a3fec154536 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -262,8 +262,8 @@ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, int __block_write_begin(struct page *page, loff_t pos, unsigned len, get_block_t *get_block); int block_write_end(struct file *, struct address_space *, - loff_t, unsigned, unsigned, - struct page *, void *); + loff_t, unsigned len, unsigned copied, + struct folio *, void *); int generic_write_end(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page *, void *); -- cgit v1.2.3 From a225800f322a3d6cc8b8b6c7dc4d5281f2f5375b Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 10 Jul 2024 15:45:32 -0400 Subject: fs: Convert aops->write_end to take a folio Most callers have a folio, and most implementations operate on a folio, so remove the conversion from folio->page->folio to fit through this interface. Reviewed-by: Josef Bacik Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Christian Brauner --- Documentation/filesystems/locking.rst | 2 +- Documentation/filesystems/vfs.rst | 6 +++--- block/fops.c | 3 +-- drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 4 ++-- fs/affs/file.c | 9 ++++----- fs/bcachefs/fs-io-buffered.c | 3 +-- fs/bcachefs/fs-io-buffered.h | 2 +- fs/buffer.c | 9 ++++----- fs/ceph/addr.c | 3 +-- fs/ecryptfs/mmap.c | 5 ++--- fs/exfat/file.c | 2 +- fs/exfat/inode.c | 4 ++-- fs/ext2/inode.c | 4 ++-- fs/ext4/inode.c | 11 ++++------- fs/ext4/verity.c | 2 +- fs/f2fs/data.c | 3 +-- fs/f2fs/super.c | 2 +- fs/f2fs/verity.c | 2 +- fs/fat/inode.c | 4 ++-- fs/fuse/file.c | 3 +-- fs/hfs/extent.c | 2 +- fs/hfsplus/extents.c | 2 +- fs/hostfs/hostfs_kern.c | 3 +-- fs/hpfs/file.c | 4 ++-- fs/hugetlbfs/inode.c | 2 +- fs/jffs2/file.c | 5 ++--- fs/jfs/inode.c | 4 ++-- fs/libfs.c | 9 ++++----- fs/namei.c | 2 +- fs/nfs/file.c | 3 +-- fs/nilfs2/inode.c | 6 +++--- fs/ntfs3/file.c | 2 +- fs/ntfs3/inode.c | 5 ++--- fs/ntfs3/ntfs_fs.h | 2 +- fs/ocfs2/aops.c | 2 +- fs/orangefs/inode.c | 4 ++-- fs/reiserfs/inode.c | 11 +++++------ fs/ubifs/file.c | 3 +-- fs/udf/inode.c | 6 ++---- fs/ufs/inode.c | 4 ++-- fs/vboxsf/file.c | 7 +++---- include/linux/buffer_head.h | 4 ++-- include/linux/fs.h | 2 +- mm/filemap.c | 2 +- mm/shmem.c | 3 +-- 45 files changed, 80 insertions(+), 102 deletions(-) (limited to 'include/linux') diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst index e664061ed55d..827fb5a073b7 100644 --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -254,7 +254,7 @@ prototypes:: struct page **pagep, void **fsdata); int (*write_end)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata); + struct folio *folio, void *fsdata); sector_t (*bmap)(struct address_space *, sector_t); void (*invalidate_folio) (struct folio *, size_t start, size_t len); bool (*release_folio)(struct folio *, gfp_t); diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst index 6e903a903f8f..0e24f770c568 100644 --- a/Documentation/filesystems/vfs.rst +++ b/Documentation/filesystems/vfs.rst @@ -810,7 +810,7 @@ cache in your filesystem. The following members are defined: struct page **pagep, void **fsdata); int (*write_end)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata); + struct folio *folio, void *fsdata); sector_t (*bmap)(struct address_space *, sector_t); void (*invalidate_folio) (struct folio *, size_t start, size_t len); bool (*release_folio)(struct folio *, gfp_t); @@ -944,8 +944,8 @@ cache in your filesystem. The following members are defined: called. len is the original len passed to write_begin, and copied is the amount that was able to be copied. - The filesystem must take care of unlocking the page and - releasing it refcount, and updating i_size. + The filesystem must take care of unlocking the folio, + decrementing its refcount, and updating i_size. Returns < 0 on failure, otherwise the number of bytes (<= 'copied') that were able to be copied into pagecache. diff --git a/block/fops.c b/block/fops.c index df0e762cf397..cd96a6f17119 100644 --- a/block/fops.c +++ b/block/fops.c @@ -457,10 +457,9 @@ static int blkdev_write_begin(struct file *file, struct address_space *mapping, } static int blkdev_write_end(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, struct page *page, + loff_t pos, unsigned len, unsigned copied, struct folio *folio, void *fsdata) { - struct folio *folio = page_folio(page); int ret; ret = block_write_end(file, mapping, pos, len, copied, folio, fsdata); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c index c5e1c718a6d2..3513165a2964 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c @@ -494,7 +494,7 @@ shmem_pwrite(struct drm_i915_gem_object *obj, kunmap_local(vaddr); err = aops->write_end(obj->base.filp, mapping, offset, len, - len - unwritten, page, data); + len - unwritten, page_folio(page), data); if (err < 0) return err; @@ -688,7 +688,7 @@ i915_gem_object_create_shmem_from_data(struct drm_i915_private *i915, kunmap(page); err = aops->write_end(file, file->f_mapping, offset, len, len, - page, pgdata); + page_folio(page), pgdata); if (err < 0) goto fail; diff --git a/fs/affs/file.c b/fs/affs/file.c index 04c018e19602..6a6c5bc41b8f 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -433,12 +433,12 @@ static int affs_write_begin(struct file *file, struct address_space *mapping, static int affs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned int len, unsigned int copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { struct inode *inode = mapping->host; int ret; - ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata); + ret = generic_write_end(file, mapping, pos, len, copied, folio, fsdata); /* Clear Archived bit on file writes, as AmigaOS would do */ if (AFFS_I(inode)->i_protect & FIBF_ARCHIVED) { @@ -687,9 +687,8 @@ static int affs_write_begin_ofs(struct file *file, struct address_space *mapping static int affs_write_end_ofs(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { - struct folio *folio = page_folio(page); struct inode *inode = mapping->host; struct super_block *sb = inode->i_sb; struct buffer_head *bh, *prev_bh; @@ -889,7 +888,7 @@ affs_truncate(struct inode *inode) res = mapping->a_ops->write_begin(NULL, mapping, isize, 0, &page, &fsdata); if (!res) - res = mapping->a_ops->write_end(NULL, mapping, isize, 0, 0, page, fsdata); + res = mapping->a_ops->write_end(NULL, mapping, isize, 0, 0, page_folio(page), fsdata); else inode->i_size = AFFS_I(inode)->mmu_private; mark_inode_dirty(inode); diff --git a/fs/bcachefs/fs-io-buffered.c b/fs/bcachefs/fs-io-buffered.c index cc33d763f722..46ae9ef3589a 100644 --- a/fs/bcachefs/fs-io-buffered.c +++ b/fs/bcachefs/fs-io-buffered.c @@ -743,12 +743,11 @@ err_unlock: int bch2_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { struct bch_inode_info *inode = to_bch_ei(mapping->host); struct bch_fs *c = inode->v.i_sb->s_fs_info; struct bch2_folio_reservation *res = fsdata; - struct folio *folio = page_folio(page); unsigned offset = pos - folio_pos(folio); lockdep_assert_held(&inode->v.i_rwsem); diff --git a/fs/bcachefs/fs-io-buffered.h b/fs/bcachefs/fs-io-buffered.h index a6126ff790e6..16569b9874e0 100644 --- a/fs/bcachefs/fs-io-buffered.h +++ b/fs/bcachefs/fs-io-buffered.h @@ -13,7 +13,7 @@ void bch2_readahead(struct readahead_control *); int bch2_write_begin(struct file *, struct address_space *, loff_t, unsigned, struct page **, void **); int bch2_write_end(struct file *, struct address_space *, loff_t, - unsigned, unsigned, struct page *, void *); + unsigned len, unsigned copied, struct folio *, void *); ssize_t bch2_write_iter(struct kiocb *, struct iov_iter *); diff --git a/fs/buffer.c b/fs/buffer.c index acba3dfe55d8..1a0f2f65e890 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2280,9 +2280,8 @@ EXPORT_SYMBOL(block_write_end); int generic_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { - struct folio *folio = page_folio(page); struct inode *inode = mapping->host; loff_t old_size = inode->i_size; bool i_size_changed = false; @@ -2480,7 +2479,7 @@ int generic_cont_expand_simple(struct inode *inode, loff_t size) if (err) goto out; - err = aops->write_end(NULL, mapping, size, 0, 0, page, fsdata); + err = aops->write_end(NULL, mapping, size, 0, 0, page_folio(page), fsdata); BUG_ON(err > 0); out: @@ -2518,7 +2517,7 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping, goto out; zero_user(page, zerofrom, len); err = aops->write_end(file, mapping, curpos, len, len, - page, fsdata); + page_folio(page), fsdata); if (err < 0) goto out; BUG_ON(err != len); @@ -2551,7 +2550,7 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping, goto out; zero_user(page, zerofrom, len); err = aops->write_end(file, mapping, curpos, len, len, - page, fsdata); + page_folio(page), fsdata); if (err < 0) goto out; BUG_ON(err != len); diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 8c16bc5250ef..87369e2659c7 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1509,9 +1509,8 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping, */ static int ceph_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *subpage, void *fsdata) + struct folio *folio, void *fsdata) { - struct folio *folio = page_folio(subpage); struct inode *inode = file_inode(file); struct ceph_client *cl = ceph_inode_to_client(inode); bool check_cap = false; diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c index 75ce28d757b7..f43e42ede75e 100644 --- a/fs/ecryptfs/mmap.c +++ b/fs/ecryptfs/mmap.c @@ -458,15 +458,14 @@ int ecryptfs_write_inode_size_to_metadata(struct inode *ecryptfs_inode) * @pos: The file position * @len: The length of the data (unused) * @copied: The amount of data copied - * @page: The eCryptfs page + * @folio: The eCryptfs folio * @fsdata: The fsdata (unused) */ static int ecryptfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { - struct folio *folio = page_folio(page); pgoff_t index = pos >> PAGE_SHIFT; unsigned from = pos & (PAGE_SIZE - 1); unsigned to = from + copied; diff --git a/fs/exfat/file.c b/fs/exfat/file.c index 64c31867bc76..7144472d092e 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -548,7 +548,7 @@ static int exfat_file_zeroed_range(struct file *file, loff_t start, loff_t end) zero_user_segment(page, zerofrom, zerofrom + len); - err = ops->write_end(file, mapping, start, len, len, page, NULL); + err = ops->write_end(file, mapping, start, len, len, page_folio(page), NULL); if (err < 0) goto out; start += len; diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c index dd894e558c91..871e9e3e407e 100644 --- a/fs/exfat/inode.c +++ b/fs/exfat/inode.c @@ -463,13 +463,13 @@ static int exfat_write_begin(struct file *file, struct address_space *mapping, static int exfat_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned int len, unsigned int copied, - struct page *pagep, void *fsdata) + struct folio *folio, void *fsdata) { struct inode *inode = mapping->host; struct exfat_inode_info *ei = EXFAT_I(inode); int err; - err = generic_write_end(file, mapping, pos, len, copied, pagep, fsdata); + err = generic_write_end(file, mapping, pos, len, copied, folio, fsdata); if (ei->i_size_aligned < i_size_read(inode)) { exfat_fs_error(inode->i_sb, diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 0caa1650cee8..aba41f6150e5 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -928,11 +928,11 @@ ext2_write_begin(struct file *file, struct address_space *mapping, static int ext2_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { int ret; - ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata); + ret = generic_write_end(file, mapping, pos, len, copied, folio, fsdata); if (ret < len) ext2_write_failed(mapping, pos + len); return ret; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 1e4831d83adc..e19ac0a82bdc 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1298,9 +1298,8 @@ static int write_end_fn(handle_t *handle, struct inode *inode, static int ext4_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { - struct folio *folio = page_folio(page); handle_t *handle = ext4_journal_current_handle(); struct inode *inode = mapping->host; loff_t old_size = inode->i_size; @@ -1402,9 +1401,8 @@ static void ext4_journalled_zero_new_buffers(handle_t *handle, static int ext4_journalled_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { - struct folio *folio = page_folio(page); handle_t *handle = ext4_journal_current_handle(); struct inode *inode = mapping->host; loff_t old_size = inode->i_size; @@ -3080,15 +3078,14 @@ static int ext4_da_do_write_end(struct address_space *mapping, static int ext4_da_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { struct inode *inode = mapping->host; int write_mode = (int)(unsigned long)fsdata; - struct folio *folio = page_folio(page); if (write_mode == FALL_BACK_TO_NONDELALLOC) return ext4_write_end(file, mapping, pos, - len, copied, &folio->page, fsdata); + len, copied, folio, fsdata); trace_ext4_da_write_end(inode, pos, len, copied); diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c index 2f37e1ea3955..86ef272296ab 100644 --- a/fs/ext4/verity.c +++ b/fs/ext4/verity.c @@ -86,7 +86,7 @@ static int pagecache_write(struct inode *inode, const void *buf, size_t count, memcpy_to_page(page, offset_in_page(pos), buf, n); - res = aops->write_end(NULL, mapping, pos, n, n, page, fsdata); + res = aops->write_end(NULL, mapping, pos, n, n, page_folio(page), fsdata); if (res < 0) return res; if (res != n) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 9a45f9fb8a64..4c32e2cfc403 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -3689,9 +3689,8 @@ fail: static int f2fs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { - struct folio *folio = page_folio(page); struct inode *inode = folio->mapping->host; trace_f2fs_write_end(inode, pos, len, copied); diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 3959fd137cc9..cfd38cd4f82c 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -2700,7 +2700,7 @@ retry: memcpy_to_page(page, offset, data, tocopy); a_ops->write_end(NULL, mapping, off, tocopy, tocopy, - page, fsdata); + page_folio(page), fsdata); offset = 0; towrite -= tocopy; off += tocopy; diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c index f7bb0c54502c..486512144bf1 100644 --- a/fs/f2fs/verity.c +++ b/fs/f2fs/verity.c @@ -90,7 +90,7 @@ static int pagecache_write(struct inode *inode, const void *buf, size_t count, memcpy_to_page(page, offset_in_page(pos), buf, n); - res = aops->write_end(NULL, mapping, pos, n, n, page, fsdata); + res = aops->write_end(NULL, mapping, pos, n, n, page_folio(page), fsdata); if (res < 0) return res; if (res != n) diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 19115fd2d2a4..8ed02b17d591 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -236,11 +236,11 @@ static int fat_write_begin(struct file *file, struct address_space *mapping, static int fat_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *pagep, void *fsdata) + struct folio *folio, void *fsdata) { struct inode *inode = mapping->host; int err; - err = generic_write_end(file, mapping, pos, len, copied, pagep, fsdata); + err = generic_write_end(file, mapping, pos, len, copied, folio, fsdata); if (err < len) fat_write_failed(mapping, pos + len); if (!(err < 0) && !(MSDOS_I(inode)->i_attrs & ATTR_ARCH)) { diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 137485999d3d..a5cd6e4f9b2b 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2433,9 +2433,8 @@ error: static int fuse_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { - struct folio *folio = page_folio(page); struct inode *inode = folio->mapping->host; /* Haven't copied anything? Skip zeroing, size extending, dirtying. */ diff --git a/fs/hfs/extent.c b/fs/hfs/extent.c index 6d1878b99b30..30512dbb79f0 100644 --- a/fs/hfs/extent.c +++ b/fs/hfs/extent.c @@ -495,7 +495,7 @@ void hfs_file_truncate(struct inode *inode) &fsdata); if (!res) { res = generic_write_end(NULL, mapping, size + 1, 0, 0, - page, fsdata); + page_folio(page), fsdata); } if (res) inode->i_size = HFS_I(inode)->phys_size; diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c index 9c51867dddc5..776c0ea722cb 100644 --- a/fs/hfsplus/extents.c +++ b/fs/hfsplus/extents.c @@ -563,7 +563,7 @@ void hfsplus_file_truncate(struct inode *inode) if (res) return; res = generic_write_end(NULL, mapping, size, 0, 0, - page, fsdata); + page_folio(page), fsdata); if (res < 0) return; mark_inode_dirty(inode); diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 805cfe39c40f..d0cbc5ece952 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -477,9 +477,8 @@ static int hostfs_write_begin(struct file *file, struct address_space *mapping, static int hostfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { - struct folio *folio = page_folio(page); struct inode *inode = mapping->host; void *buffer; size_t from = offset_in_folio(folio, pos); diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c index 1bb8d97cd9ae..11e2d9e612ac 100644 --- a/fs/hpfs/file.c +++ b/fs/hpfs/file.c @@ -206,11 +206,11 @@ static int hpfs_write_begin(struct file *file, struct address_space *mapping, static int hpfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *pagep, void *fsdata) + struct folio *folio, void *fsdata) { struct inode *inode = mapping->host; int err; - err = generic_write_end(file, mapping, pos, len, copied, pagep, fsdata); + err = generic_write_end(file, mapping, pos, len, copied, folio, fsdata); if (err < len) hpfs_write_failed(mapping, pos + len); if (!(err < 0)) { diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 9f6cff356796..b7a30055e6f4 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -395,7 +395,7 @@ static int hugetlbfs_write_begin(struct file *file, static int hugetlbfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { BUG(); return -EINVAL; diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index ee8f7f029b45..b6fe1f1e8ea9 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -23,7 +23,7 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *pg, void *fsdata); + struct folio *folio, void *fsdata); static int jffs2_write_begin(struct file *filp, struct address_space *mapping, loff_t pos, unsigned len, struct page **pagep, void **fsdata); @@ -239,9 +239,8 @@ out_err: static int jffs2_write_end(struct file *filp, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *pg, void *fsdata) + struct folio *folio, void *fsdata) { - struct folio *folio = page_folio(pg); /* Actually commit the write from the page cache page we're looking at. * For now, we write the full page out each time. It sucks, but it's simple */ diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index 1a6b5921d17a..d63494182548 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -304,12 +304,12 @@ static int jfs_write_begin(struct file *file, struct address_space *mapping, } static int jfs_write_end(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, struct page *page, + loff_t pos, unsigned len, unsigned copied, struct folio *folio, void *fsdata) { int ret; - ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata); + ret = generic_write_end(file, mapping, pos, len, copied, folio, fsdata); if (ret < len) jfs_write_failed(mapping, pos + len); return ret; diff --git a/fs/libfs.c b/fs/libfs.c index 8aa34870449f..4581be1d5b32 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -929,11 +929,11 @@ EXPORT_SYMBOL(simple_write_begin); * @pos: " * @len: " * @copied: " - * @page: " + * @folio: " * @fsdata: " * - * simple_write_end does the minimum needed for updating a page after writing is - * done. It has the same API signature as the .write_end of + * simple_write_end does the minimum needed for updating a folio after + * writing is done. It has the same API signature as the .write_end of * address_space_operations vector. So it can just be set onto .write_end for * FSes that don't need any other processing. i_mutex is assumed to be held. * Block based filesystems should use generic_write_end(). @@ -946,9 +946,8 @@ EXPORT_SYMBOL(simple_write_begin); */ static int simple_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { - struct folio *folio = page_folio(page); struct inode *inode = folio->mapping->host; loff_t last_pos = pos + copied; diff --git a/fs/namei.c b/fs/namei.c index 5512cb10fa89..fb7055245e68 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -5321,7 +5321,7 @@ retry: memcpy(page_address(page), symname, len-1); err = aops->write_end(NULL, mapping, 0, len-1, len-1, - page, fsdata); + page_folio(page), fsdata); if (err < 0) goto fail; if (err < len-1) diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 61a8cdb9f1e1..fe583dbebe54 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -372,10 +372,9 @@ start: static int nfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { struct nfs_open_context *ctx = nfs_file_open_context(file); - struct folio *folio = page_folio(page); unsigned offset = offset_in_folio(folio, pos); int status; diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 7340a01d80e1..25841b75415a 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -269,16 +269,16 @@ static int nilfs_write_begin(struct file *file, struct address_space *mapping, static int nilfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { struct inode *inode = mapping->host; unsigned int start = pos & (PAGE_SIZE - 1); unsigned int nr_dirty; int err; - nr_dirty = nilfs_page_count_clean_buffers(page, start, + nr_dirty = nilfs_page_count_clean_buffers(&folio->page, start, start + copied); - copied = generic_write_end(file, mapping, pos, len, copied, page, + copied = generic_write_end(file, mapping, pos, len, copied, folio, fsdata); nilfs_set_file_dirty(inode, nr_dirty); err = nilfs_transaction_commit(inode->i_sb); diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index ca1ddc46bd86..88a7d81cf2ba 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -215,7 +215,7 @@ static int ntfs_extend_initialized_size(struct file *file, zero_user_segment(page, zerofrom, PAGE_SIZE); /* This function in any case puts page. */ - err = ntfs_write_end(file, mapping, pos, len, len, page, NULL); + err = ntfs_write_end(file, mapping, pos, len, len, page_folio(page), NULL); if (err < 0) goto out; pos += len; diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index 8eaaf9e465d4..9efd3f7c59d6 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -947,9 +947,8 @@ out: * ntfs_write_end - Address_space_operations::write_end. */ int ntfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, - u32 len, u32 copied, struct page *page, void *fsdata) + u32 len, u32 copied, struct folio *folio, void *fsdata) { - struct folio *folio = page_folio(page); struct inode *inode = mapping->host; struct ntfs_inode *ni = ntfs_i(inode); u64 valid = ni->i_valid; @@ -979,7 +978,7 @@ int ntfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, folio_unlock(folio); folio_put(folio); } else { - err = generic_write_end(file, mapping, pos, len, copied, page, + err = generic_write_end(file, mapping, pos, len, copied, folio, fsdata); } diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index 4e363b8342d6..53517281f26b 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -713,7 +713,7 @@ int ntfs_get_block(struct inode *inode, sector_t vbn, int ntfs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, u32 len, struct page **pagep, void **fsdata); int ntfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, - u32 len, u32 copied, struct page *page, void *fsdata); + u32 len, u32 copied, struct folio *folio, void *fsdata); int ntfs3_write_inode(struct inode *inode, struct writeback_control *wbc); int ntfs_sync_inode(struct inode *inode); int ntfs_flush_inodes(struct super_block *sb, struct inode *i1, diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 6be175a1ab3c..9d8aa417e8da 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -2076,7 +2076,7 @@ out: static int ocfs2_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { int ret; struct inode *inode = mapping->host; diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index e8440fa7d73c..69b507a611f8 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -361,9 +361,9 @@ okay: } static int orangefs_write_end(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) + loff_t pos, unsigned len, unsigned copied, struct folio *folio, + void *fsdata) { - struct folio *folio = page_folio(page); struct inode *inode = folio->mapping->host; loff_t last_pos = pos + copied; diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 33da519c9767..f4b9db4b4df2 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -2862,10 +2862,9 @@ static sector_t reiserfs_aop_bmap(struct address_space *as, sector_t block) static int reiserfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { - struct folio *folio = page_folio(page); - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; int ret = 0; int update_sd = 0; struct reiserfs_transaction_handle *th; @@ -2887,7 +2886,7 @@ static int reiserfs_write_end(struct file *file, struct address_space *mapping, } flush_dcache_folio(folio); - reiserfs_commit_page(inode, page, start, start + copied); + reiserfs_commit_page(inode, &folio->page, start, start + copied); /* * generic_commit_write does this for us, but does not update the @@ -2942,8 +2941,8 @@ static int reiserfs_write_end(struct file *file, struct address_space *mapping, out: if (locked) reiserfs_write_unlock(inode->i_sb); - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); if (pos + len > inode->i_size) reiserfs_truncate_failed_write(inode); diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 68e104423a48..baa3eecc32fe 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -524,9 +524,8 @@ static void cancel_budget(struct ubifs_info *c, struct folio *folio, static int ubifs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { - struct folio *folio = page_folio(page); struct inode *inode = mapping->host; struct ubifs_inode *ui = ubifs_inode(inode); struct ubifs_info *c = inode->i_sb->s_fs_info; diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 4726a4d014b6..fdf024e0b772 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -273,16 +273,14 @@ static int udf_write_begin(struct file *file, struct address_space *mapping, static int udf_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { struct inode *inode = file_inode(file); - struct folio *folio; loff_t last_pos; if (UDF_I(inode)->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) - return generic_write_end(file, mapping, pos, len, copied, page, + return generic_write_end(file, mapping, pos, len, copied, folio, fsdata); - folio = page_folio(page); last_pos = pos + copied; if (last_pos > inode->i_size) i_size_write(inode, last_pos); diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index 0e608fc0d0fd..69adb198c634 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -511,11 +511,11 @@ static int ufs_write_begin(struct file *file, struct address_space *mapping, static int ufs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { int ret; - ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata); + ret = generic_write_end(file, mapping, pos, len, copied, folio, fsdata); if (ret < len) ufs_write_failed(mapping, pos + len); return ret; diff --git a/fs/vboxsf/file.c b/fs/vboxsf/file.c index 029f106d56d9..b780deb81b02 100644 --- a/fs/vboxsf/file.c +++ b/fs/vboxsf/file.c @@ -300,9 +300,8 @@ static int vboxsf_writepage(struct page *page, struct writeback_control *wbc) static int vboxsf_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned int len, unsigned int copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { - struct folio *folio = page_folio(page); struct inode *inode = mapping->host; struct vboxsf_handle *sf_handle = file->private_data; size_t from = offset_in_folio(folio, pos); @@ -314,10 +313,10 @@ static int vboxsf_write_end(struct file *file, struct address_space *mapping, if (!folio_test_uptodate(folio) && copied < len) folio_zero_range(folio, from + copied, len - copied); - buf = kmap(page); + buf = kmap(&folio->page); err = vboxsf_write(sf_handle->root, sf_handle->handle, pos, &nwritten, buf + from); - kunmap(page); + kunmap(&folio->page); if (err) { nwritten = 0; diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 3a3fec154536..165e859664a5 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -265,8 +265,8 @@ int block_write_end(struct file *, struct address_space *, loff_t, unsigned len, unsigned copied, struct folio *, void *); int generic_write_end(struct file *, struct address_space *, - loff_t, unsigned, unsigned, - struct page *, void *); + loff_t, unsigned len, unsigned copied, + struct folio *, void *); void folio_zero_new_buffers(struct folio *folio, size_t from, size_t to); int cont_write_begin(struct file *, struct address_space *, loff_t, unsigned, struct page **, void **, diff --git a/include/linux/fs.h b/include/linux/fs.h index fd34b5755c0b..1af3373c7cd2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -411,7 +411,7 @@ struct address_space_operations { struct page **pagep, void **fsdata); int (*write_end)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata); + struct folio *folio, void *fsdata); /* Unfortunately this kludge is needed for FIBMAP. Don't use it */ sector_t (*bmap)(struct address_space *, sector_t); diff --git a/mm/filemap.c b/mm/filemap.c index d62150418b91..fab6b0c3044e 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -4033,7 +4033,7 @@ retry: flush_dcache_folio(folio); status = a_ops->write_end(file, mapping, pos, bytes, copied, - page, fsdata); + folio, fsdata); if (unlikely(status != copied)) { iov_iter_revert(i, copied - max(status, 0L)); if (unlikely(status < 0)) diff --git a/mm/shmem.c b/mm/shmem.c index 2faa9daaf54b..1116f147d788 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2917,9 +2917,8 @@ shmem_write_begin(struct file *file, struct address_space *mapping, static int shmem_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { - struct folio *folio = page_folio(page); struct inode *inode = mapping->host; if (pos + copied > inode->i_size) -- cgit v1.2.3 From 1da86618bdce301d23e89ecce92161f9d3b3c5e7 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 15 Jul 2024 14:24:01 -0400 Subject: fs: Convert aops->write_begin to take a folio Convert all callers from working on a page to working on one page of a folio (support for working on an entire folio can come later). Removes a lot of folio->page->folio conversions. Reviewed-by: Josef Bacik Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Christian Brauner --- Documentation/filesystems/locking.rst | 4 +-- Documentation/filesystems/vfs.rst | 6 ++-- block/fops.c | 4 +-- drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 47 +++++++++++++++---------------- fs/adfs/inode.c | 5 ++-- fs/affs/file.c | 15 +++++----- fs/bcachefs/fs-io-buffered.c | 5 ++-- fs/bcachefs/fs-io-buffered.h | 4 +-- fs/bfs/file.c | 4 +-- fs/buffer.c | 28 +++++++++--------- fs/ceph/addr.c | 10 +++---- fs/ecryptfs/mmap.c | 7 ++--- fs/exfat/file.c | 8 +++--- fs/exfat/inode.c | 5 ++-- fs/ext2/inode.c | 4 +-- fs/ext4/ext4.h | 4 +-- fs/ext4/inline.c | 8 +++--- fs/ext4/inode.c | 14 ++++----- fs/ext4/verity.c | 8 +++--- fs/f2fs/data.c | 8 ++++-- fs/f2fs/super.c | 8 +++--- fs/f2fs/verity.c | 8 +++--- fs/fat/inode.c | 5 ++-- fs/fuse/file.c | 4 +-- fs/hfs/extent.c | 6 ++-- fs/hfs/hfs_fs.h | 2 +- fs/hfs/inode.c | 5 ++-- fs/hfsplus/extents.c | 6 ++-- fs/hfsplus/hfsplus_fs.h | 2 +- fs/hfsplus/inode.c | 5 ++-- fs/hostfs/hostfs_kern.c | 7 +++-- fs/hpfs/file.c | 5 ++-- fs/hugetlbfs/inode.c | 2 +- fs/jffs2/file.c | 6 ++-- fs/jfs/inode.c | 4 +-- fs/libfs.c | 4 +-- fs/minix/inode.c | 4 +-- fs/namei.c | 10 +++---- fs/nfs/file.c | 4 +-- fs/nilfs2/inode.c | 4 +-- fs/nilfs2/recovery.c | 6 ++-- fs/ntfs3/file.c | 9 +++--- fs/ntfs3/inode.c | 7 ++--- fs/ntfs3/ntfs_fs.h | 2 +- fs/ocfs2/aops.c | 10 +++---- fs/ocfs2/aops.h | 2 +- fs/ocfs2/mmap.c | 6 ++-- fs/omfs/file.c | 4 +-- fs/orangefs/inode.c | 4 +-- fs/reiserfs/inode.c | 4 +-- fs/sysv/itree.c | 4 +-- fs/ubifs/file.c | 10 +++---- fs/udf/inode.c | 6 ++-- fs/ufs/inode.c | 4 +-- include/linux/buffer_head.h | 4 +-- include/linux/fs.h | 4 +-- mm/filemap.c | 4 +-- mm/shmem.c | 8 +++--- 58 files changed, 190 insertions(+), 207 deletions(-) (limited to 'include/linux') diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst index 827fb5a073b7..f5e3676db954 100644 --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -251,7 +251,7 @@ prototypes:: void (*readahead)(struct readahead_control *); int (*write_begin)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata); + struct folio **foliop, void **fsdata); int (*write_end)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct folio *folio, void *fsdata); @@ -280,7 +280,7 @@ read_folio: yes, unlocks shared writepages: dirty_folio: maybe readahead: yes, unlocks shared -write_begin: locks the page exclusive +write_begin: locks the folio exclusive write_end: yes, unlocks exclusive bmap: invalidate_folio: yes exclusive diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst index 0e24f770c568..4f67b5ea0568 100644 --- a/Documentation/filesystems/vfs.rst +++ b/Documentation/filesystems/vfs.rst @@ -926,12 +926,12 @@ cache in your filesystem. The following members are defined: (if they haven't been read already) so that the updated blocks can be written out properly. - The filesystem must return the locked pagecache page for the - specified offset, in ``*pagep``, for the caller to write into. + The filesystem must return the locked pagecache folio for the + specified offset, in ``*foliop``, for the caller to write into. It must be able to cope with short writes (where the length passed to write_begin is greater than the number of bytes copied - into the page). + into the folio). A void * may be returned in fsdata, which then gets passed into write_end. diff --git a/block/fops.c b/block/fops.c index cd96a6f17119..dacbd61fda29 100644 --- a/block/fops.c +++ b/block/fops.c @@ -451,9 +451,9 @@ static void blkdev_readahead(struct readahead_control *rac) } static int blkdev_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, struct page **pagep, void **fsdata) + loff_t pos, unsigned len, struct folio **foliop, void **fsdata) { - return block_write_begin(mapping, pos, len, pagep, blkdev_get_block); + return block_write_begin(mapping, pos, len, foliop, blkdev_get_block); } static int blkdev_write_end(struct file *file, struct address_space *mapping, diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c index 3513165a2964..fe69f2c8527d 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c @@ -424,7 +424,8 @@ shmem_pwrite(struct drm_i915_gem_object *obj, struct address_space *mapping = obj->base.filp->f_mapping; const struct address_space_operations *aops = mapping->a_ops; char __user *user_data = u64_to_user_ptr(arg->data_ptr); - u64 remain, offset; + u64 remain; + loff_t pos; unsigned int pg; /* Caller already validated user args */ @@ -457,12 +458,12 @@ shmem_pwrite(struct drm_i915_gem_object *obj, */ remain = arg->size; - offset = arg->offset; - pg = offset_in_page(offset); + pos = arg->offset; + pg = offset_in_page(pos); do { unsigned int len, unwritten; - struct page *page; + struct folio *folio; void *data, *vaddr; int err; char __maybe_unused c; @@ -480,21 +481,19 @@ shmem_pwrite(struct drm_i915_gem_object *obj, if (err) return err; - err = aops->write_begin(obj->base.filp, mapping, offset, len, - &page, &data); + err = aops->write_begin(obj->base.filp, mapping, pos, len, + &folio, &data); if (err < 0) return err; - vaddr = kmap_local_page(page); + vaddr = kmap_local_folio(folio, offset_in_folio(folio, pos)); pagefault_disable(); - unwritten = __copy_from_user_inatomic(vaddr + pg, - user_data, - len); + unwritten = __copy_from_user_inatomic(vaddr, user_data, len); pagefault_enable(); kunmap_local(vaddr); - err = aops->write_end(obj->base.filp, mapping, offset, len, - len - unwritten, page_folio(page), data); + err = aops->write_end(obj->base.filp, mapping, pos, len, + len - unwritten, folio, data); if (err < 0) return err; @@ -504,7 +503,7 @@ shmem_pwrite(struct drm_i915_gem_object *obj, remain -= len; user_data += len; - offset += len; + pos += len; pg = 0; } while (remain); @@ -660,7 +659,7 @@ i915_gem_object_create_shmem_from_data(struct drm_i915_private *i915, struct drm_i915_gem_object *obj; struct file *file; const struct address_space_operations *aops; - resource_size_t offset; + loff_t pos; int err; GEM_WARN_ON(IS_DGFX(i915)); @@ -672,29 +671,27 @@ i915_gem_object_create_shmem_from_data(struct drm_i915_private *i915, file = obj->base.filp; aops = file->f_mapping->a_ops; - offset = 0; + pos = 0; do { unsigned int len = min_t(typeof(size), size, PAGE_SIZE); - struct page *page; - void *pgdata, *vaddr; + struct folio *folio; + void *fsdata; - err = aops->write_begin(file, file->f_mapping, offset, len, - &page, &pgdata); + err = aops->write_begin(file, file->f_mapping, pos, len, + &folio, &fsdata); if (err < 0) goto fail; - vaddr = kmap(page); - memcpy(vaddr, data, len); - kunmap(page); + memcpy_to_folio(folio, offset_in_folio(folio, pos), data, len); - err = aops->write_end(file, file->f_mapping, offset, len, len, - page_folio(page), pgdata); + err = aops->write_end(file, file->f_mapping, pos, len, len, + folio, fsdata); if (err < 0) goto fail; size -= len; data += len; - offset += len; + pos += len; } while (size); return obj; diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c index a183e213a4a5..21527189e430 100644 --- a/fs/adfs/inode.c +++ b/fs/adfs/inode.c @@ -55,12 +55,11 @@ static void adfs_write_failed(struct address_space *mapping, loff_t to) static int adfs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { int ret; - *pagep = NULL; - ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata, + ret = cont_write_begin(file, mapping, pos, len, foliop, fsdata, adfs_get_block, &ADFS_I(mapping->host)->mmu_private); if (unlikely(ret)) diff --git a/fs/affs/file.c b/fs/affs/file.c index 6a6c5bc41b8f..a5a861dd5223 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -417,12 +417,11 @@ affs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) static int affs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { int ret; - *pagep = NULL; - ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata, + ret = cont_write_begin(file, mapping, pos, len, foliop, fsdata, affs_get_block, &AFFS_I(mapping->host)->mmu_private); if (unlikely(ret)) @@ -648,7 +647,7 @@ static int affs_read_folio_ofs(struct file *file, struct folio *folio) static int affs_write_begin_ofs(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { struct inode *inode = mapping->host; struct folio *folio; @@ -671,7 +670,7 @@ static int affs_write_begin_ofs(struct file *file, struct address_space *mapping mapping_gfp_mask(mapping)); if (IS_ERR(folio)) return PTR_ERR(folio); - *pagep = &folio->page; + *foliop = folio; if (folio_test_uptodate(folio)) return 0; @@ -881,14 +880,14 @@ affs_truncate(struct inode *inode) if (inode->i_size > AFFS_I(inode)->mmu_private) { struct address_space *mapping = inode->i_mapping; - struct page *page; + struct folio *folio; void *fsdata = NULL; loff_t isize = inode->i_size; int res; - res = mapping->a_ops->write_begin(NULL, mapping, isize, 0, &page, &fsdata); + res = mapping->a_ops->write_begin(NULL, mapping, isize, 0, &folio, &fsdata); if (!res) - res = mapping->a_ops->write_end(NULL, mapping, isize, 0, 0, page_folio(page), fsdata); + res = mapping->a_ops->write_end(NULL, mapping, isize, 0, 0, folio, fsdata); else inode->i_size = AFFS_I(inode)->mmu_private; mark_inode_dirty(inode); diff --git a/fs/bcachefs/fs-io-buffered.c b/fs/bcachefs/fs-io-buffered.c index 46ae9ef3589a..3d410d801825 100644 --- a/fs/bcachefs/fs-io-buffered.c +++ b/fs/bcachefs/fs-io-buffered.c @@ -659,7 +659,7 @@ int bch2_writepages(struct address_space *mapping, struct writeback_control *wbc int bch2_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { struct bch_inode_info *inode = to_bch_ei(mapping->host); struct bch_fs *c = inode->v.i_sb->s_fs_info; @@ -728,12 +728,11 @@ out: goto err; } - *pagep = &folio->page; + *foliop = folio; return 0; err: folio_unlock(folio); folio_put(folio); - *pagep = NULL; err_unlock: bch2_pagecache_add_put(inode); kfree(res); diff --git a/fs/bcachefs/fs-io-buffered.h b/fs/bcachefs/fs-io-buffered.h index 16569b9874e0..3207ebbb4ab4 100644 --- a/fs/bcachefs/fs-io-buffered.h +++ b/fs/bcachefs/fs-io-buffered.h @@ -10,8 +10,8 @@ int bch2_read_folio(struct file *, struct folio *); int bch2_writepages(struct address_space *, struct writeback_control *); void bch2_readahead(struct readahead_control *); -int bch2_write_begin(struct file *, struct address_space *, loff_t, - unsigned, struct page **, void **); +int bch2_write_begin(struct file *, struct address_space *, loff_t pos, + unsigned len, struct folio **, void **); int bch2_write_end(struct file *, struct address_space *, loff_t, unsigned len, unsigned copied, struct folio *, void *); diff --git a/fs/bfs/file.c b/fs/bfs/file.c index a778411574a9..fa66a09e496a 100644 --- a/fs/bfs/file.c +++ b/fs/bfs/file.c @@ -172,11 +172,11 @@ static void bfs_write_failed(struct address_space *mapping, loff_t to) static int bfs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { int ret; - ret = block_write_begin(mapping, pos, len, pagep, bfs_get_block); + ret = block_write_begin(mapping, pos, len, foliop, bfs_get_block); if (unlikely(ret)) bfs_write_failed(mapping, pos + len); diff --git a/fs/buffer.c b/fs/buffer.c index 1a0f2f65e890..d52a740f7fca 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2222,7 +2222,7 @@ static void __block_commit_write(struct folio *folio, size_t from, size_t to) * The filesystem needs to handle block truncation upon failure. */ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, get_block_t *get_block) + struct folio **foliop, get_block_t *get_block) { pgoff_t index = pos >> PAGE_SHIFT; struct folio *folio; @@ -2240,7 +2240,7 @@ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, folio = NULL; } - *pagep = &folio->page; + *foliop = folio; return status; } EXPORT_SYMBOL(block_write_begin); @@ -2467,7 +2467,7 @@ int generic_cont_expand_simple(struct inode *inode, loff_t size) { struct address_space *mapping = inode->i_mapping; const struct address_space_operations *aops = mapping->a_ops; - struct page *page; + struct folio *folio; void *fsdata = NULL; int err; @@ -2475,11 +2475,11 @@ int generic_cont_expand_simple(struct inode *inode, loff_t size) if (err) goto out; - err = aops->write_begin(NULL, mapping, size, 0, &page, &fsdata); + err = aops->write_begin(NULL, mapping, size, 0, &folio, &fsdata); if (err) goto out; - err = aops->write_end(NULL, mapping, size, 0, 0, page_folio(page), fsdata); + err = aops->write_end(NULL, mapping, size, 0, 0, folio, fsdata); BUG_ON(err > 0); out: @@ -2493,7 +2493,7 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping, struct inode *inode = mapping->host; const struct address_space_operations *aops = mapping->a_ops; unsigned int blocksize = i_blocksize(inode); - struct page *page; + struct folio *folio; void *fsdata = NULL; pgoff_t index, curidx; loff_t curpos; @@ -2512,12 +2512,12 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping, len = PAGE_SIZE - zerofrom; err = aops->write_begin(file, mapping, curpos, len, - &page, &fsdata); + &folio, &fsdata); if (err) goto out; - zero_user(page, zerofrom, len); + folio_zero_range(folio, offset_in_folio(folio, curpos), len); err = aops->write_end(file, mapping, curpos, len, len, - page_folio(page), fsdata); + folio, fsdata); if (err < 0) goto out; BUG_ON(err != len); @@ -2545,12 +2545,12 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping, len = offset - zerofrom; err = aops->write_begin(file, mapping, curpos, len, - &page, &fsdata); + &folio, &fsdata); if (err) goto out; - zero_user(page, zerofrom, len); + folio_zero_range(folio, offset_in_folio(folio, curpos), len); err = aops->write_end(file, mapping, curpos, len, len, - page_folio(page), fsdata); + folio, fsdata); if (err < 0) goto out; BUG_ON(err != len); @@ -2566,7 +2566,7 @@ out: */ int cont_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata, + struct folio **foliop, void **fsdata, get_block_t *get_block, loff_t *bytes) { struct inode *inode = mapping->host; @@ -2584,7 +2584,7 @@ int cont_write_begin(struct file *file, struct address_space *mapping, (*bytes)++; } - return block_write_begin(mapping, pos, len, pagep, get_block); + return block_write_begin(mapping, pos, len, foliop, get_block); } EXPORT_SYMBOL(cont_write_begin); diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 87369e2659c7..4402cddf82b5 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1486,20 +1486,18 @@ static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned */ static int ceph_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { struct inode *inode = file_inode(file); struct ceph_inode_info *ci = ceph_inode(inode); - struct folio *folio = NULL; int r; - r = netfs_write_begin(&ci->netfs, file, inode->i_mapping, pos, len, &folio, NULL); + r = netfs_write_begin(&ci->netfs, file, inode->i_mapping, pos, len, foliop, NULL); if (r < 0) return r; - folio_wait_private_2(folio); /* [DEPRECATED] */ - WARN_ON_ONCE(!folio_test_locked(folio)); - *pagep = &folio->page; + folio_wait_private_2(*foliop); /* [DEPRECATED] */ + WARN_ON_ONCE(!folio_test_locked(*foliop)); return 0; } diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c index f43e42ede75e..287e5d407f08 100644 --- a/fs/ecryptfs/mmap.c +++ b/fs/ecryptfs/mmap.c @@ -255,7 +255,7 @@ out: * @mapping: The eCryptfs object * @pos: The file offset at which to start writing * @len: Length of the write - * @pagep: Pointer to return the page + * @foliop: Pointer to return the folio * @fsdata: Pointer to return fs data (unused) * * This function must zero any hole we create @@ -265,7 +265,7 @@ out: static int ecryptfs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { pgoff_t index = pos >> PAGE_SHIFT; struct folio *folio; @@ -276,7 +276,7 @@ static int ecryptfs_write_begin(struct file *file, mapping_gfp_mask(mapping)); if (IS_ERR(folio)) return PTR_ERR(folio); - *pagep = &folio->page; + *foliop = folio; prev_page_end_size = ((loff_t)index << PAGE_SHIFT); if (!folio_test_uptodate(folio)) { @@ -365,7 +365,6 @@ out: if (unlikely(rc)) { folio_unlock(folio); folio_put(folio); - *pagep = NULL; } return rc; } diff --git a/fs/exfat/file.c b/fs/exfat/file.c index 7144472d092e..e19469e88000 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -535,20 +535,20 @@ static int exfat_file_zeroed_range(struct file *file, loff_t start, loff_t end) while (start < end) { u32 zerofrom, len; - struct page *page = NULL; + struct folio *folio; zerofrom = start & (PAGE_SIZE - 1); len = PAGE_SIZE - zerofrom; if (start + len > end) len = end - start; - err = ops->write_begin(file, mapping, start, len, &page, NULL); + err = ops->write_begin(file, mapping, start, len, &folio, NULL); if (err) goto out; - zero_user_segment(page, zerofrom, zerofrom + len); + folio_zero_range(folio, offset_in_folio(folio, start), len); - err = ops->write_end(file, mapping, start, len, len, page_folio(page), NULL); + err = ops->write_end(file, mapping, start, len, len, folio, NULL); if (err < 0) goto out; start += len; diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c index 871e9e3e407e..05f0e07b01d0 100644 --- a/fs/exfat/inode.c +++ b/fs/exfat/inode.c @@ -448,12 +448,11 @@ static void exfat_write_failed(struct address_space *mapping, loff_t to) static int exfat_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned int len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { int ret; - *pagep = NULL; - ret = block_write_begin(mapping, pos, len, pagep, exfat_get_block); + ret = block_write_begin(mapping, pos, len, foliop, exfat_get_block); if (ret < 0) exfat_write_failed(mapping, pos+len); diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index aba41f6150e5..30f8201c155f 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -916,11 +916,11 @@ static void ext2_readahead(struct readahead_control *rac) static int ext2_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, struct page **pagep, void **fsdata) + loff_t pos, unsigned len, struct folio **foliop, void **fsdata) { int ret; - ret = block_write_begin(mapping, pos, len, pagep, ext2_get_block); + ret = block_write_begin(mapping, pos, len, foliop, ext2_get_block); if (ret < 0) ext2_write_failed(mapping, pos + len); return ret; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 08acd152261e..c3429b664b8d 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -3563,13 +3563,13 @@ int ext4_readpage_inline(struct inode *inode, struct folio *folio); extern int ext4_try_to_write_inline_data(struct address_space *mapping, struct inode *inode, loff_t pos, unsigned len, - struct page **pagep); + struct folio **foliop); int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len, unsigned copied, struct folio *folio); extern int ext4_da_write_inline_data_begin(struct address_space *mapping, struct inode *inode, loff_t pos, unsigned len, - struct page **pagep, + struct folio **foliop, void **fsdata); extern int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname, diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index e7a09a99837b..b7ea9cb4c398 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -660,7 +660,7 @@ out_nofolio: int ext4_try_to_write_inline_data(struct address_space *mapping, struct inode *inode, loff_t pos, unsigned len, - struct page **pagep) + struct folio **foliop) { int ret; handle_t *handle; @@ -708,7 +708,7 @@ int ext4_try_to_write_inline_data(struct address_space *mapping, goto out; } - *pagep = &folio->page; + *foliop = folio; down_read(&EXT4_I(inode)->xattr_sem); if (!ext4_has_inline_data(inode)) { ret = 0; @@ -891,7 +891,7 @@ out: int ext4_da_write_inline_data_begin(struct address_space *mapping, struct inode *inode, loff_t pos, unsigned len, - struct page **pagep, + struct folio **foliop, void **fsdata) { int ret; @@ -954,7 +954,7 @@ retry_journal: goto out_release_page; up_read(&EXT4_I(inode)->xattr_sem); - *pagep = &folio->page; + *foliop = folio; brelse(iloc.bh); return 1; out_release_page: diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index e19ac0a82bdc..90ef8ec5c59b 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1145,7 +1145,7 @@ static int ext4_block_write_begin(struct folio *folio, loff_t pos, unsigned len, */ static int ext4_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { struct inode *inode = mapping->host; int ret, needed_blocks; @@ -1170,7 +1170,7 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping, if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { ret = ext4_try_to_write_inline_data(mapping, inode, pos, len, - pagep); + foliop); if (ret < 0) return ret; if (ret == 1) @@ -1270,7 +1270,7 @@ retry_journal: folio_put(folio); return ret; } - *pagep = &folio->page; + *foliop = folio; return ret; } @@ -2924,7 +2924,7 @@ static int ext4_nonda_switch(struct super_block *sb) static int ext4_da_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { int ret, retries = 0; struct folio *folio; @@ -2939,14 +2939,14 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, if (ext4_nonda_switch(inode->i_sb) || ext4_verity_in_progress(inode)) { *fsdata = (void *)FALL_BACK_TO_NONDELALLOC; return ext4_write_begin(file, mapping, pos, - len, pagep, fsdata); + len, foliop, fsdata); } *fsdata = (void *)0; trace_ext4_da_write_begin(inode, pos, len); if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { ret = ext4_da_write_inline_data_begin(mapping, inode, pos, len, - pagep, fsdata); + foliop, fsdata); if (ret < 0) return ret; if (ret == 1) @@ -2981,7 +2981,7 @@ retry: return ret; } - *pagep = &folio->page; + *foliop = folio; return ret; } diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c index 86ef272296ab..d9203228ce97 100644 --- a/fs/ext4/verity.c +++ b/fs/ext4/verity.c @@ -76,17 +76,17 @@ static int pagecache_write(struct inode *inode, const void *buf, size_t count, while (count) { size_t n = min_t(size_t, count, PAGE_SIZE - offset_in_page(pos)); - struct page *page; + struct folio *folio; void *fsdata = NULL; int res; - res = aops->write_begin(NULL, mapping, pos, n, &page, &fsdata); + res = aops->write_begin(NULL, mapping, pos, n, &folio, &fsdata); if (res) return res; - memcpy_to_page(page, offset_in_page(pos), buf, n); + memcpy_to_folio(folio, offset_in_folio(folio, pos), buf, n); - res = aops->write_end(NULL, mapping, pos, n, n, page_folio(page), fsdata); + res = aops->write_end(NULL, mapping, pos, n, n, folio, fsdata); if (res < 0) return res; if (res != n) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 4c32e2cfc403..5dfa0207ad8f 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -3552,7 +3552,7 @@ reserve_block: } static int f2fs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, struct page **pagep, void **fsdata) + loff_t pos, unsigned len, struct folio **foliop, void **fsdata) { struct inode *inode = mapping->host; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); @@ -3584,18 +3584,20 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping, #ifdef CONFIG_F2FS_FS_COMPRESSION if (f2fs_compressed_file(inode)) { int ret; + struct page *page; *fsdata = NULL; if (len == PAGE_SIZE && !(f2fs_is_atomic_file(inode))) goto repeat; - ret = f2fs_prepare_compress_overwrite(inode, pagep, + ret = f2fs_prepare_compress_overwrite(inode, &page, index, fsdata); if (ret < 0) { err = ret; goto fail; } else if (ret) { + *foliop = page_folio(page); return 0; } } @@ -3615,7 +3617,7 @@ repeat: /* TODO: cluster can be compressed due to race with .writepage */ - *pagep = &folio->page; + *foliop = folio; if (f2fs_is_atomic_file(inode)) err = prepare_atomic_write_begin(sbi, &folio->page, pos, len, diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index cfd38cd4f82c..176b5177c89d 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -2677,7 +2677,7 @@ static ssize_t f2fs_quota_write(struct super_block *sb, int type, const struct address_space_operations *a_ops = mapping->a_ops; int offset = off & (sb->s_blocksize - 1); size_t towrite = len; - struct page *page; + struct folio *folio; void *fsdata = NULL; int err = 0; int tocopy; @@ -2687,7 +2687,7 @@ static ssize_t f2fs_quota_write(struct super_block *sb, int type, towrite); retry: err = a_ops->write_begin(NULL, mapping, off, tocopy, - &page, &fsdata); + &folio, &fsdata); if (unlikely(err)) { if (err == -ENOMEM) { f2fs_io_schedule_timeout(DEFAULT_IO_TIMEOUT); @@ -2697,10 +2697,10 @@ retry: break; } - memcpy_to_page(page, offset, data, tocopy); + memcpy_to_folio(folio, offset_in_folio(folio, off), data, tocopy); a_ops->write_end(NULL, mapping, off, tocopy, tocopy, - page_folio(page), fsdata); + folio, fsdata); offset = 0; towrite -= tocopy; off += tocopy; diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c index 486512144bf1..84a33fe49bed 100644 --- a/fs/f2fs/verity.c +++ b/fs/f2fs/verity.c @@ -80,17 +80,17 @@ static int pagecache_write(struct inode *inode, const void *buf, size_t count, while (count) { size_t n = min_t(size_t, count, PAGE_SIZE - offset_in_page(pos)); - struct page *page; + struct folio *folio; void *fsdata = NULL; int res; - res = aops->write_begin(NULL, mapping, pos, n, &page, &fsdata); + res = aops->write_begin(NULL, mapping, pos, n, &folio, &fsdata); if (res) return res; - memcpy_to_page(page, offset_in_page(pos), buf, n); + memcpy_to_folio(folio, offset_in_folio(folio, pos), buf, n); - res = aops->write_end(NULL, mapping, pos, n, n, page_folio(page), fsdata); + res = aops->write_end(NULL, mapping, pos, n, n, folio, fsdata); if (res < 0) return res; if (res != n) diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 8ed02b17d591..75722bbd6b5f 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -221,13 +221,12 @@ static void fat_write_failed(struct address_space *mapping, loff_t to) static int fat_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { int err; - *pagep = NULL; err = cont_write_begin(file, mapping, pos, len, - pagep, fsdata, fat_get_block, + foliop, fsdata, fat_get_block, &MSDOS_I(mapping->host)->mmu_private); if (err < 0) fat_write_failed(mapping, pos + len); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index a5cd6e4f9b2b..bc49b2eeadf3 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2387,7 +2387,7 @@ out: * but how to implement it without killing performance need more thinking. */ static int fuse_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, struct page **pagep, void **fsdata) + loff_t pos, unsigned len, struct folio **foliop, void **fsdata) { pgoff_t index = pos >> PAGE_SHIFT; struct fuse_conn *fc = get_fuse_conn(file_inode(file)); @@ -2421,7 +2421,7 @@ static int fuse_write_begin(struct file *file, struct address_space *mapping, if (err) goto cleanup; success: - *pagep = &folio->page; + *foliop = folio; return 0; cleanup: diff --git a/fs/hfs/extent.c b/fs/hfs/extent.c index 30512dbb79f0..4a0ce131e233 100644 --- a/fs/hfs/extent.c +++ b/fs/hfs/extent.c @@ -487,15 +487,15 @@ void hfs_file_truncate(struct inode *inode) if (inode->i_size > HFS_I(inode)->phys_size) { struct address_space *mapping = inode->i_mapping; void *fsdata = NULL; - struct page *page; + struct folio *folio; /* XXX: Can use generic_cont_expand? */ size = inode->i_size - 1; - res = hfs_write_begin(NULL, mapping, size + 1, 0, &page, + res = hfs_write_begin(NULL, mapping, size + 1, 0, &folio, &fsdata); if (!res) { res = generic_write_end(NULL, mapping, size + 1, 0, 0, - page_folio(page), fsdata); + folio, fsdata); } if (res) inode->i_size = HFS_I(inode)->phys_size; diff --git a/fs/hfs/hfs_fs.h b/fs/hfs/hfs_fs.h index b5a6ad5df357..a0c7cb0f79fc 100644 --- a/fs/hfs/hfs_fs.h +++ b/fs/hfs/hfs_fs.h @@ -202,7 +202,7 @@ extern const struct address_space_operations hfs_aops; extern const struct address_space_operations hfs_btree_aops; int hfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, struct page **pagep, void **fsdata); + loff_t pos, unsigned len, struct folio **foliop, void **fsdata); extern struct inode *hfs_new_inode(struct inode *, const struct qstr *, umode_t); extern void hfs_inode_write_fork(struct inode *, struct hfs_extent *, __be32 *, __be32 *); extern int hfs_write_inode(struct inode *, struct writeback_control *); diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 744e10b46904..a81ce7a740b9 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -45,12 +45,11 @@ static void hfs_write_failed(struct address_space *mapping, loff_t to) } int hfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, struct page **pagep, void **fsdata) + loff_t pos, unsigned len, struct folio **foliop, void **fsdata) { int ret; - *pagep = NULL; - ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata, + ret = cont_write_begin(file, mapping, pos, len, foliop, fsdata, hfs_get_block, &HFS_I(mapping->host)->phys_size); if (unlikely(ret)) diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c index 776c0ea722cb..a6d61685ae79 100644 --- a/fs/hfsplus/extents.c +++ b/fs/hfsplus/extents.c @@ -554,16 +554,16 @@ void hfsplus_file_truncate(struct inode *inode) if (inode->i_size > hip->phys_size) { struct address_space *mapping = inode->i_mapping; - struct page *page; + struct folio *folio; void *fsdata = NULL; loff_t size = inode->i_size; res = hfsplus_write_begin(NULL, mapping, size, 0, - &page, &fsdata); + &folio, &fsdata); if (res) return; res = generic_write_end(NULL, mapping, size, 0, 0, - page_folio(page), fsdata); + folio, fsdata); if (res < 0) return; mark_inode_dirty(inode); diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index 9e78f181c24f..59ce81dca73f 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -472,7 +472,7 @@ extern const struct address_space_operations hfsplus_btree_aops; extern const struct dentry_operations hfsplus_dentry_operations; int hfsplus_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, struct page **pagep, void **fsdata); + loff_t pos, unsigned len, struct folio **foliop, void **fsdata); struct inode *hfsplus_new_inode(struct super_block *sb, struct inode *dir, umode_t mode); void hfsplus_delete_inode(struct inode *inode); diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 3d326926c195..f331e9574217 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -39,12 +39,11 @@ static void hfsplus_write_failed(struct address_space *mapping, loff_t to) } int hfsplus_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, struct page **pagep, void **fsdata) + loff_t pos, unsigned len, struct folio **foliop, void **fsdata) { int ret; - *pagep = NULL; - ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata, + ret = cont_write_begin(file, mapping, pos, len, foliop, fsdata, hfsplus_get_block, &HFSPLUS_I(mapping->host)->phys_size); if (unlikely(ret)) diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index d0cbc5ece952..6d1cf2436ead 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -465,12 +465,13 @@ static int hostfs_read_folio(struct file *file, struct folio *folio) static int hostfs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { pgoff_t index = pos >> PAGE_SHIFT; - *pagep = grab_cache_page_write_begin(mapping, index); - if (!*pagep) + *foliop = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN, + mapping_gfp_mask(mapping)); + if (!*foliop) return -ENOMEM; return 0; } diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c index 11e2d9e612ac..449a3fc1b8d9 100644 --- a/fs/hpfs/file.c +++ b/fs/hpfs/file.c @@ -190,12 +190,11 @@ static void hpfs_write_failed(struct address_space *mapping, loff_t to) static int hpfs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { int ret; - *pagep = NULL; - ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata, + ret = cont_write_begin(file, mapping, pos, len, foliop, fsdata, hpfs_get_block, &hpfs_i(mapping->host)->mmu_private); if (unlikely(ret)) diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index b7a30055e6f4..5cf327337e22 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -388,7 +388,7 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to) static int hugetlbfs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { return -EINVAL; } diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index b6fe1f1e8ea9..ada572c466f8 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -26,7 +26,7 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping, struct folio *folio, void *fsdata); static int jffs2_write_begin(struct file *filp, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata); + struct folio **foliop, void **fsdata); static int jffs2_read_folio(struct file *filp, struct folio *folio); int jffs2_fsync(struct file *filp, loff_t start, loff_t end, int datasync) @@ -125,7 +125,7 @@ static int jffs2_read_folio(struct file *file, struct folio *folio) static int jffs2_write_begin(struct file *filp, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { struct folio *folio; struct inode *inode = mapping->host; @@ -212,7 +212,7 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, ret = PTR_ERR(folio); goto release_sem; } - *pagep = &folio->page; + *foliop = folio; /* * Read in the folio if it wasn't already present. Cannot optimize away diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index d63494182548..07cfdc440596 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -292,11 +292,11 @@ static void jfs_write_failed(struct address_space *mapping, loff_t to) static int jfs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { int ret; - ret = block_write_begin(mapping, pos, len, pagep, jfs_get_block); + ret = block_write_begin(mapping, pos, len, foliop, jfs_get_block); if (unlikely(ret)) jfs_write_failed(mapping, pos + len); diff --git a/fs/libfs.c b/fs/libfs.c index 4581be1d5b32..1a776edb39de 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -901,7 +901,7 @@ static int simple_read_folio(struct file *file, struct folio *folio) int simple_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { struct folio *folio; @@ -910,7 +910,7 @@ int simple_write_begin(struct file *file, struct address_space *mapping, if (IS_ERR(folio)) return PTR_ERR(folio); - *pagep = &folio->page; + *foliop = folio; if (!folio_test_uptodate(folio) && (len != folio_size(folio))) { size_t from = offset_in_folio(folio, pos); diff --git a/fs/minix/inode.c b/fs/minix/inode.c index 0002337977e0..abb190c46c04 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -444,11 +444,11 @@ static void minix_write_failed(struct address_space *mapping, loff_t to) static int minix_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { int ret; - ret = block_write_begin(mapping, pos, len, pagep, minix_get_block); + ret = block_write_begin(mapping, pos, len, foliop, minix_get_block); if (unlikely(ret)) minix_write_failed(mapping, pos + len); diff --git a/fs/namei.c b/fs/namei.c index fb7055245e68..1bf081959066 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -5304,7 +5304,7 @@ int page_symlink(struct inode *inode, const char *symname, int len) struct address_space *mapping = inode->i_mapping; const struct address_space_operations *aops = mapping->a_ops; bool nofs = !mapping_gfp_constraint(mapping, __GFP_FS); - struct page *page; + struct folio *folio; void *fsdata = NULL; int err; unsigned int flags; @@ -5312,16 +5312,16 @@ int page_symlink(struct inode *inode, const char *symname, int len) retry: if (nofs) flags = memalloc_nofs_save(); - err = aops->write_begin(NULL, mapping, 0, len-1, &page, &fsdata); + err = aops->write_begin(NULL, mapping, 0, len-1, &folio, &fsdata); if (nofs) memalloc_nofs_restore(flags); if (err) goto fail; - memcpy(page_address(page), symname, len-1); + memcpy(folio_address(folio), symname, len - 1); - err = aops->write_end(NULL, mapping, 0, len-1, len-1, - page_folio(page), fsdata); + err = aops->write_end(NULL, mapping, 0, len - 1, len - 1, + folio, fsdata); if (err < 0) goto fail; if (err < len-1) diff --git a/fs/nfs/file.c b/fs/nfs/file.c index fe583dbebe54..6800ee92d742 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -336,7 +336,7 @@ static bool nfs_want_read_modify_write(struct file *file, struct folio *folio, * increment the page use counts until he is done with the page. */ static int nfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, struct page **pagep, + loff_t pos, unsigned len, struct folio **foliop, void **fsdata) { fgf_t fgp = FGP_WRITEBEGIN; @@ -353,7 +353,7 @@ start: mapping_gfp_mask(mapping)); if (IS_ERR(folio)) return PTR_ERR(folio); - *pagep = &folio->page; + *foliop = folio; ret = nfs_flush_incompatible(file, folio); if (ret) { diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 25841b75415a..8661f452dba6 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -250,7 +250,7 @@ void nilfs_write_failed(struct address_space *mapping, loff_t to) static int nilfs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { struct inode *inode = mapping->host; @@ -259,7 +259,7 @@ static int nilfs_write_begin(struct file *file, struct address_space *mapping, if (unlikely(err)) return err; - err = block_write_begin(mapping, pos, len, pagep, nilfs_get_block); + err = block_write_begin(mapping, pos, len, foliop, nilfs_get_block); if (unlikely(err)) { nilfs_write_failed(mapping, pos + len); nilfs_transaction_abort(inode->i_sb); diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c index 40c5dfbc9d41..c2e60a6bd060 100644 --- a/fs/nilfs2/recovery.c +++ b/fs/nilfs2/recovery.c @@ -498,7 +498,6 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs, struct inode *inode; struct nilfs_recovery_block *rb, *n; unsigned int blocksize = nilfs->ns_blocksize; - struct page *page; struct folio *folio; loff_t pos; int err = 0, err2 = 0; @@ -513,7 +512,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs, pos = rb->blkoff << inode->i_blkbits; err = block_write_begin(inode->i_mapping, pos, blocksize, - &page, nilfs_get_block); + &folio, nilfs_get_block); if (unlikely(err)) { loff_t isize = inode->i_size; @@ -523,8 +522,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs, goto failed_inode; } - folio = page_folio(page); - err = nilfs_recovery_copy_block(nilfs, rb, pos, page); + err = nilfs_recovery_copy_block(nilfs, rb, pos, &folio->page); if (unlikely(err)) goto failed_page; diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index 88a7d81cf2ba..6202895a4542 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -182,7 +182,7 @@ static int ntfs_extend_initialized_size(struct file *file, for (;;) { u32 zerofrom, len; - struct page *page; + struct folio *folio; u8 bits; CLST vcn, lcn, clen; @@ -208,14 +208,13 @@ static int ntfs_extend_initialized_size(struct file *file, if (pos + len > new_valid) len = new_valid - pos; - err = ntfs_write_begin(file, mapping, pos, len, &page, NULL); + err = ntfs_write_begin(file, mapping, pos, len, &folio, NULL); if (err) goto out; - zero_user_segment(page, zerofrom, PAGE_SIZE); + folio_zero_range(folio, zerofrom, folio_size(folio)); - /* This function in any case puts page. */ - err = ntfs_write_end(file, mapping, pos, len, len, page_folio(page), NULL); + err = ntfs_write_end(file, mapping, pos, len, len, folio, NULL); if (err < 0) goto out; pos += len; diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index 9efd3f7c59d6..f672072e6bd4 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -901,7 +901,7 @@ static int ntfs_get_block_write_begin(struct inode *inode, sector_t vbn, } int ntfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, u32 len, struct page **pagep, void **fsdata) + loff_t pos, u32 len, struct folio **foliop, void **fsdata) { int err; struct inode *inode = mapping->host; @@ -910,7 +910,6 @@ int ntfs_write_begin(struct file *file, struct address_space *mapping, if (unlikely(ntfs3_forced_shutdown(inode->i_sb))) return -EIO; - *pagep = NULL; if (is_resident(ni)) { struct folio *folio = __filemap_get_folio( mapping, pos >> PAGE_SHIFT, FGP_WRITEBEGIN, @@ -926,7 +925,7 @@ int ntfs_write_begin(struct file *file, struct address_space *mapping, ni_unlock(ni); if (!err) { - *pagep = &folio->page; + *foliop = folio; goto out; } folio_unlock(folio); @@ -936,7 +935,7 @@ int ntfs_write_begin(struct file *file, struct address_space *mapping, goto out; } - err = block_write_begin(mapping, pos, len, pagep, + err = block_write_begin(mapping, pos, len, foliop, ntfs_get_block_write_begin); out: diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index 53517281f26b..584f814715f4 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -711,7 +711,7 @@ int ntfs_set_size(struct inode *inode, u64 new_size); int ntfs_get_block(struct inode *inode, sector_t vbn, struct buffer_head *bh_result, int create); int ntfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, u32 len, struct page **pagep, void **fsdata); + loff_t pos, u32 len, struct folio **foliop, void **fsdata); int ntfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, u32 len, u32 copied, struct folio *folio, void *fsdata); int ntfs3_write_inode(struct inode *inode, struct writeback_control *wbc); diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 9d8aa417e8da..d6c985cc6353 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -1643,7 +1643,7 @@ static int ocfs2_zero_tail(struct inode *inode, struct buffer_head *di_bh, int ocfs2_write_begin_nolock(struct address_space *mapping, loff_t pos, unsigned len, ocfs2_write_type_t type, - struct page **pagep, void **fsdata, + struct folio **foliop, void **fsdata, struct buffer_head *di_bh, struct page *mmap_page) { int ret, cluster_of_pages, credits = OCFS2_INODE_UPDATE_CREDITS; @@ -1826,8 +1826,8 @@ try_again: ocfs2_free_alloc_context(meta_ac); success: - if (pagep) - *pagep = wc->w_target_page; + if (foliop) + *foliop = page_folio(wc->w_target_page); *fsdata = wc; return 0; out_quota: @@ -1879,7 +1879,7 @@ out: static int ocfs2_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { int ret; struct buffer_head *di_bh = NULL; @@ -1901,7 +1901,7 @@ static int ocfs2_write_begin(struct file *file, struct address_space *mapping, down_write(&OCFS2_I(inode)->ip_alloc_sem); ret = ocfs2_write_begin_nolock(mapping, pos, len, OCFS2_WRITE_BUFFER, - pagep, fsdata, di_bh, NULL); + foliop, fsdata, di_bh, NULL); if (ret) { mlog_errno(ret); goto out_fail; diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h index 3a520117fa59..45db1781ea73 100644 --- a/fs/ocfs2/aops.h +++ b/fs/ocfs2/aops.h @@ -38,7 +38,7 @@ typedef enum { int ocfs2_write_begin_nolock(struct address_space *mapping, loff_t pos, unsigned len, ocfs2_write_type_t type, - struct page **pagep, void **fsdata, + struct folio **foliop, void **fsdata, struct buffer_head *di_bh, struct page *mmap_page); int ocfs2_read_inline_data(struct inode *inode, struct page *page, diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c index 1834f26522ed..6ef4cb045ccd 100644 --- a/fs/ocfs2/mmap.c +++ b/fs/ocfs2/mmap.c @@ -53,7 +53,7 @@ static vm_fault_t __ocfs2_page_mkwrite(struct file *file, loff_t pos = page_offset(page); unsigned int len = PAGE_SIZE; pgoff_t last_index; - struct page *locked_page = NULL; + struct folio *locked_folio = NULL; void *fsdata; loff_t size = i_size_read(inode); @@ -91,7 +91,7 @@ static vm_fault_t __ocfs2_page_mkwrite(struct file *file, len = ((size - 1) & ~PAGE_MASK) + 1; err = ocfs2_write_begin_nolock(mapping, pos, len, OCFS2_WRITE_MMAP, - &locked_page, &fsdata, di_bh, page); + &locked_folio, &fsdata, di_bh, page); if (err) { if (err != -ENOSPC) mlog_errno(err); @@ -99,7 +99,7 @@ static vm_fault_t __ocfs2_page_mkwrite(struct file *file, goto out; } - if (!locked_page) { + if (!locked_folio) { ret = VM_FAULT_NOPAGE; goto out; } diff --git a/fs/omfs/file.c b/fs/omfs/file.c index 6b580b9da8e3..98358d405b6a 100644 --- a/fs/omfs/file.c +++ b/fs/omfs/file.c @@ -312,11 +312,11 @@ static void omfs_write_failed(struct address_space *mapping, loff_t to) static int omfs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { int ret; - ret = block_write_begin(mapping, pos, len, pagep, omfs_get_block); + ret = block_write_begin(mapping, pos, len, foliop, omfs_get_block); if (unlikely(ret)) omfs_write_failed(mapping, pos + len); diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index 69b507a611f8..aae6d2b8767d 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -309,7 +309,7 @@ static int orangefs_read_folio(struct file *file, struct folio *folio) static int orangefs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { struct orangefs_write_range *wr; struct folio *folio; @@ -320,7 +320,7 @@ static int orangefs_write_begin(struct file *file, if (IS_ERR(folio)) return PTR_ERR(folio); - *pagep = &folio->page; + *foliop = folio; if (folio_test_dirty(folio) && !folio_test_private(folio)) { /* diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index f4b9db4b4df2..ea23872ba24f 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -2735,7 +2735,7 @@ static void reiserfs_truncate_failed_write(struct inode *inode) static int reiserfs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { struct inode *inode; struct folio *folio; @@ -2749,7 +2749,7 @@ static int reiserfs_write_begin(struct file *file, mapping_gfp_mask(mapping)); if (IS_ERR(folio)) return PTR_ERR(folio); - *pagep = &folio->page; + *foliop = folio; reiserfs_wait_on_write_block(inode->i_sb); fix_tail_page_for_writing(&folio->page); diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c index c8511e286673..8864438817a6 100644 --- a/fs/sysv/itree.c +++ b/fs/sysv/itree.c @@ -483,11 +483,11 @@ static void sysv_write_failed(struct address_space *mapping, loff_t to) static int sysv_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { int ret; - ret = block_write_begin(mapping, pos, len, pagep, get_block); + ret = block_write_begin(mapping, pos, len, foliop, get_block); if (unlikely(ret)) sysv_write_failed(mapping, pos + len); diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index baa3eecc32fe..5130123005e4 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -211,7 +211,7 @@ static void release_existing_page_budget(struct ubifs_info *c) } static int write_begin_slow(struct address_space *mapping, - loff_t pos, unsigned len, struct page **pagep) + loff_t pos, unsigned len, struct folio **foliop) { struct inode *inode = mapping->host; struct ubifs_info *c = inode->i_sb->s_fs_info; @@ -298,7 +298,7 @@ static int write_begin_slow(struct address_space *mapping, ubifs_release_dirty_inode_budget(c, ui); } - *pagep = &folio->page; + *foliop = folio; return 0; } @@ -414,7 +414,7 @@ static int allocate_budget(struct ubifs_info *c, struct folio *folio, */ static int ubifs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { struct inode *inode = mapping->host; struct ubifs_info *c = inode->i_sb->s_fs_info; @@ -483,7 +483,7 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping, folio_unlock(folio); folio_put(folio); - return write_begin_slow(mapping, pos, len, pagep); + return write_begin_slow(mapping, pos, len, foliop); } /* @@ -492,7 +492,7 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping, * with @ui->ui_mutex locked if we are appending pages, and unlocked * otherwise. This is an optimization (slightly hacky though). */ - *pagep = &folio->page; + *foliop = folio; return 0; } diff --git a/fs/udf/inode.c b/fs/udf/inode.c index fdf024e0b772..eaee57b91c6c 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -246,14 +246,14 @@ static void udf_readahead(struct readahead_control *rac) static int udf_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { struct udf_inode_info *iinfo = UDF_I(file_inode(file)); struct folio *folio; int ret; if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) { - ret = block_write_begin(mapping, pos, len, pagep, + ret = block_write_begin(mapping, pos, len, foliop, udf_get_block); if (unlikely(ret)) udf_write_failed(mapping, pos + len); @@ -265,7 +265,7 @@ static int udf_write_begin(struct file *file, struct address_space *mapping, mapping_gfp_mask(mapping)); if (IS_ERR(folio)) return PTR_ERR(folio); - *pagep = &folio->page; + *foliop = folio; if (!folio_test_uptodate(folio)) udf_adinicb_read_folio(folio); return 0; diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index 69adb198c634..f43461652d9f 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -498,11 +498,11 @@ static void ufs_write_failed(struct address_space *mapping, loff_t to) static int ufs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { int ret; - ret = block_write_begin(mapping, pos, len, pagep, ufs_getfrag_block); + ret = block_write_begin(mapping, pos, len, foliop, ufs_getfrag_block); if (unlikely(ret)) ufs_write_failed(mapping, pos + len); diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 165e859664a5..254563a2a9de 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -258,7 +258,7 @@ int __block_write_full_folio(struct inode *inode, struct folio *folio, int block_read_full_folio(struct folio *, get_block_t *); bool block_is_partially_uptodate(struct folio *, size_t from, size_t count); int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, get_block_t *get_block); + struct folio **foliop, get_block_t *get_block); int __block_write_begin(struct page *page, loff_t pos, unsigned len, get_block_t *get_block); int block_write_end(struct file *, struct address_space *, @@ -269,7 +269,7 @@ int generic_write_end(struct file *, struct address_space *, struct folio *, void *); void folio_zero_new_buffers(struct folio *folio, size_t from, size_t to); int cont_write_begin(struct file *, struct address_space *, loff_t, - unsigned, struct page **, void **, + unsigned, struct folio **, void **, get_block_t *, loff_t *); int generic_cont_expand_simple(struct inode *inode, loff_t size); void block_commit_write(struct page *page, unsigned int from, unsigned int to); diff --git a/include/linux/fs.h b/include/linux/fs.h index 1af3373c7cd2..7a79b88a8f5a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -408,7 +408,7 @@ struct address_space_operations { int (*write_begin)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata); + struct folio **foliop, void **fsdata); int (*write_end)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct folio *folio, void *fsdata); @@ -3331,7 +3331,7 @@ extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter); extern int simple_empty(struct dentry *); extern int simple_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata); + struct folio **foliop, void **fsdata); extern const struct address_space_operations ram_aops; extern int always_delete_dentry(const struct dentry *); extern struct inode *alloc_anon_inode(struct super_block *); diff --git a/mm/filemap.c b/mm/filemap.c index fab6b0c3044e..29fec1fccd0a 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3987,7 +3987,6 @@ ssize_t generic_perform_write(struct kiocb *iocb, struct iov_iter *i) ssize_t written = 0; do { - struct page *page; struct folio *folio; size_t offset; /* Offset into folio */ size_t bytes; /* Bytes to write to folio */ @@ -4017,11 +4016,10 @@ retry: } status = a_ops->write_begin(file, mapping, pos, bytes, - &page, &fsdata); + &folio, &fsdata); if (unlikely(status < 0)) break; - folio = page_folio(page); offset = offset_in_folio(folio, pos); if (bytes > folio_size(folio) - offset) bytes = folio_size(folio) - offset; diff --git a/mm/shmem.c b/mm/shmem.c index 1116f147d788..dbc351b4b153 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2882,7 +2882,7 @@ static const struct inode_operations shmem_short_symlink_operations; static int shmem_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata) + struct folio **foliop, void **fsdata) { struct inode *inode = mapping->host; struct shmem_inode_info *info = SHMEM_I(inode); @@ -2903,14 +2903,14 @@ shmem_write_begin(struct file *file, struct address_space *mapping, if (ret) return ret; - *pagep = folio_file_page(folio, index); - if (PageHWPoison(*pagep)) { + if (folio_test_hwpoison(folio) || + (folio_test_large(folio) && folio_test_has_hwpoisoned(folio))) { folio_unlock(folio); folio_put(folio); - *pagep = NULL; return -EIO; } + *foliop = folio; return 0; } -- cgit v1.2.3 From 9f04609f74ec7a439e1ac42da5db9e6ddf4f7b13 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 10 Jul 2024 23:09:04 -0400 Subject: buffer: Convert __block_write_begin() to take a folio Almost all callers have a folio now, so change __block_write_begin() to take a folio and remove a call to compound_head(). Reviewed-by: Josef Bacik Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Christian Brauner --- fs/buffer.c | 5 ++--- fs/ext2/dir.c | 2 +- fs/ext4/inline.c | 6 +++--- fs/ext4/inode.c | 8 ++++---- fs/minix/inode.c | 2 +- fs/nilfs2/dir.c | 2 +- fs/ocfs2/file.c | 2 +- fs/reiserfs/inode.c | 6 +++--- fs/sysv/itree.c | 2 +- fs/udf/file.c | 2 +- fs/ufs/inode.c | 2 +- include/linux/buffer_head.h | 2 +- 12 files changed, 20 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/fs/buffer.c b/fs/buffer.c index d52a740f7fca..45eb06cb1a4e 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2168,11 +2168,10 @@ int __block_write_begin_int(struct folio *folio, loff_t pos, unsigned len, return err; } -int __block_write_begin(struct page *page, loff_t pos, unsigned len, +int __block_write_begin(struct folio *folio, loff_t pos, unsigned len, get_block_t *get_block) { - return __block_write_begin_int(page_folio(page), pos, len, get_block, - NULL); + return __block_write_begin_int(folio, pos, len, get_block, NULL); } EXPORT_SYMBOL(__block_write_begin); diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c index 60605fbdd0eb..2f3042d0174c 100644 --- a/fs/ext2/dir.c +++ b/fs/ext2/dir.c @@ -434,7 +434,7 @@ int ext2_inode_by_name(struct inode *dir, const struct qstr *child, ino_t *ino) static int ext2_prepare_chunk(struct folio *folio, loff_t pos, unsigned len) { - return __block_write_begin(&folio->page, pos, len, ext2_get_block); + return __block_write_begin(folio, pos, len, ext2_get_block); } static int ext2_handle_dirsync(struct inode *dir) diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index b7ea9cb4c398..d5c2f3b75084 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -601,10 +601,10 @@ retry: goto out; if (ext4_should_dioread_nolock(inode)) { - ret = __block_write_begin(&folio->page, from, to, + ret = __block_write_begin(folio, from, to, ext4_get_block_unwritten); } else - ret = __block_write_begin(&folio->page, from, to, ext4_get_block); + ret = __block_write_begin(folio, from, to, ext4_get_block); if (!ret && ext4_should_journal_data(inode)) { ret = ext4_walk_page_buffers(handle, inode, @@ -856,7 +856,7 @@ static int ext4_da_convert_inline_data_to_extent(struct address_space *mapping, goto out; } - ret = __block_write_begin(&folio->page, 0, inline_size, + ret = __block_write_begin(folio, 0, inline_size, ext4_da_get_block_prep); if (ret) { up_read(&EXT4_I(inode)->xattr_sem); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 90ef8ec5c59b..03374dc215d1 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1224,10 +1224,10 @@ retry_journal: ret = ext4_block_write_begin(folio, pos, len, ext4_get_block); #else if (ext4_should_dioread_nolock(inode)) - ret = __block_write_begin(&folio->page, pos, len, + ret = __block_write_begin(folio, pos, len, ext4_get_block_unwritten); else - ret = __block_write_begin(&folio->page, pos, len, ext4_get_block); + ret = __block_write_begin(folio, pos, len, ext4_get_block); #endif if (!ret && ext4_should_journal_data(inode)) { ret = ext4_walk_page_buffers(handle, inode, @@ -2962,7 +2962,7 @@ retry: #ifdef CONFIG_FS_ENCRYPTION ret = ext4_block_write_begin(folio, pos, len, ext4_da_get_block_prep); #else - ret = __block_write_begin(&folio->page, pos, len, ext4_da_get_block_prep); + ret = __block_write_begin(folio, pos, len, ext4_da_get_block_prep); #endif if (ret < 0) { folio_unlock(folio); @@ -6216,7 +6216,7 @@ retry_alloc: if (folio_pos(folio) + len > size) len = size - folio_pos(folio); - err = __block_write_begin(&folio->page, 0, len, ext4_get_block); + err = __block_write_begin(folio, 0, len, ext4_get_block); if (!err) { ret = VM_FAULT_SIGBUS; if (ext4_journal_folio_buffers(handle, folio, len)) diff --git a/fs/minix/inode.c b/fs/minix/inode.c index abb190c46c04..f007e389d5d2 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -429,7 +429,7 @@ static int minix_read_folio(struct file *file, struct folio *folio) int minix_prepare_chunk(struct folio *folio, loff_t pos, unsigned len) { - return __block_write_begin(&folio->page, pos, len, minix_get_block); + return __block_write_begin(folio, pos, len, minix_get_block); } static void minix_write_failed(struct address_space *mapping, loff_t to) diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index 66af42f88ca7..4b3e19d74925 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -83,7 +83,7 @@ static int nilfs_prepare_chunk(struct folio *folio, unsigned int from, { loff_t pos = folio_pos(folio) + from; - return __block_write_begin(&folio->page, pos, to - from, nilfs_get_block); + return __block_write_begin(folio, pos, to - from, nilfs_get_block); } static void nilfs_commit_chunk(struct folio *folio, diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index cfec1782ac2a..d058eb30cfc2 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -804,7 +804,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, * __block_write_begin and block_commit_write to zero the * whole block. */ - ret = __block_write_begin(&folio->page, block_start + 1, 0, + ret = __block_write_begin(folio, block_start + 1, 0, ocfs2_get_block); if (ret < 0) { mlog_errno(ret); diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index ea23872ba24f..72c53129c952 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -2198,7 +2198,7 @@ static int grab_tail_page(struct inode *inode, /* start within the page of the last block in the file */ start = (offset / blocksize) * blocksize; - error = __block_write_begin(&folio->page, start, offset - start, + error = __block_write_begin(folio, start, offset - start, reiserfs_get_block_create_0); if (error) goto unlock; @@ -2762,7 +2762,7 @@ static int reiserfs_write_begin(struct file *file, old_ref = th->t_refcount; th->t_refcount++; } - ret = __block_write_begin(&folio->page, pos, len, reiserfs_get_block); + ret = __block_write_begin(folio, pos, len, reiserfs_get_block); if (ret && reiserfs_transaction_running(inode->i_sb)) { struct reiserfs_transaction_handle *th = current->journal_info; /* @@ -2822,7 +2822,7 @@ int __reiserfs_write_begin(struct page *page, unsigned from, unsigned len) th->t_refcount++; } - ret = __block_write_begin(page, from, len, reiserfs_get_block); + ret = __block_write_begin(page_folio(page), from, len, reiserfs_get_block); if (ret && reiserfs_transaction_running(inode->i_sb)) { struct reiserfs_transaction_handle *th = current->journal_info; /* diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c index 8864438817a6..451e95f474fa 100644 --- a/fs/sysv/itree.c +++ b/fs/sysv/itree.c @@ -468,7 +468,7 @@ static int sysv_read_folio(struct file *file, struct folio *folio) int sysv_prepare_chunk(struct folio *folio, loff_t pos, unsigned len) { - return __block_write_begin(&folio->page, pos, len, get_block); + return __block_write_begin(folio, pos, len, get_block); } static void sysv_write_failed(struct address_space *mapping, loff_t to) diff --git a/fs/udf/file.c b/fs/udf/file.c index 3a4179de316b..412fe7c4d348 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -62,7 +62,7 @@ static vm_fault_t udf_page_mkwrite(struct vm_fault *vmf) end = size & ~PAGE_MASK; else end = PAGE_SIZE; - err = __block_write_begin(&folio->page, 0, end, udf_get_block); + err = __block_write_begin(folio, 0, end, udf_get_block); if (err) { folio_unlock(folio); ret = vmf_fs_error(err); diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index f43461652d9f..5331ae7ebf3e 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -481,7 +481,7 @@ static int ufs_read_folio(struct file *file, struct folio *folio) int ufs_prepare_chunk(struct folio *folio, loff_t pos, unsigned len) { - return __block_write_begin(&folio->page, pos, len, ufs_getfrag_block); + return __block_write_begin(folio, pos, len, ufs_getfrag_block); } static void ufs_truncate_blocks(struct inode *); diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 254563a2a9de..c85e65fd4cdc 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -259,7 +259,7 @@ int block_read_full_folio(struct folio *, get_block_t *); bool block_is_partially_uptodate(struct folio *, size_t from, size_t count); int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, get_block_t *get_block); -int __block_write_begin(struct page *page, loff_t pos, unsigned len, +int __block_write_begin(struct folio *folio, loff_t pos, unsigned len, get_block_t *get_block); int block_write_end(struct file *, struct address_space *, loff_t, unsigned len, unsigned copied, -- cgit v1.2.3 From 07a83512fa5be3f3d46369eee6352102fd9fb505 Mon Sep 17 00:00:00 2001 From: André Draszik Date: Wed, 10 Jul 2024 11:36:08 +0100 Subject: usb: typec: tcpci: fix a comment typo MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit autonously -> autonomously Signed-off-by: André Draszik Reviewed-by: Heikki Krogerus Link: https://lore.kernel.org/r/20240710-tcpc-cleanup-v1-1-0ec1f41f4263@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/tcpci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/tcpci.h b/include/linux/usb/tcpci.h index 0ab39b6ea205..d27fe0c22a8b 100644 --- a/include/linux/usb/tcpci.h +++ b/include/linux/usb/tcpci.h @@ -190,7 +190,7 @@ struct tcpci; * Optional; Callback to perform chip specific operations when FRS * is sourcing vbus. * @auto_discharge_disconnect: - * Optional; Enables TCPC to autonously discharge vbus on disconnect. + * Optional; Enables TCPC to autonomously discharge vbus on disconnect. * @vbus_vsafe0v: * optional; Set when TCPC can detect whether vbus is at VSAFE0V. * @set_partner_usb_comm_capable: -- cgit v1.2.3 From f523aa6d72598bcd2946c7e02d29f33f94806a15 Mon Sep 17 00:00:00 2001 From: André Draszik Date: Wed, 10 Jul 2024 11:36:10 +0100 Subject: usb: typec: tcpci: use GENMASK() for TCPC_CC_STATUS_CC[12] MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The existing code here, particularly in maxim_contaminant.c, is arguably quite hard to read due to the open-coded masking and shifting spanning multiple lines. Use GENMASK() and FIELD_GET() instead, which arguably make the code much easier to follow. While at it, use the symbolic name TCPC_CC_STATE_SRC_OPEN for one instance of open-coded 0x0. Signed-off-by: André Draszik Reviewed-by: Heikki Krogerus Link: https://lore.kernel.org/r/20240710-tcpc-cleanup-v1-3-0ec1f41f4263@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tcpm/maxim_contaminant.c | 8 +++----- drivers/usb/typec/tcpm/tcpci.c | 7 +++---- drivers/usb/typec/tcpm/tcpci_rt1711h.c | 7 +++---- include/linux/usb/tcpci.h | 8 +++----- 4 files changed, 12 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/typec/tcpm/maxim_contaminant.c b/drivers/usb/typec/tcpm/maxim_contaminant.c index f8504a90da26..e7687aeb69c0 100644 --- a/drivers/usb/typec/tcpm/maxim_contaminant.c +++ b/drivers/usb/typec/tcpm/maxim_contaminant.c @@ -5,6 +5,7 @@ * USB-C module to reduce wakeups due to contaminants. */ +#include #include #include #include @@ -48,11 +49,8 @@ enum fladc_select { #define STATUS_CHECK(reg, mask, val) (((reg) & (mask)) == (val)) #define IS_CC_OPEN(cc_status) \ - (STATUS_CHECK((cc_status), TCPC_CC_STATUS_CC1_MASK << TCPC_CC_STATUS_CC1_SHIFT, \ - TCPC_CC_STATE_SRC_OPEN) && STATUS_CHECK((cc_status), \ - TCPC_CC_STATUS_CC2_MASK << \ - TCPC_CC_STATUS_CC2_SHIFT, \ - TCPC_CC_STATE_SRC_OPEN)) + (FIELD_GET(TCPC_CC_STATUS_CC1, cc_status) == TCPC_CC_STATE_SRC_OPEN \ + && FIELD_GET(TCPC_CC_STATUS_CC2, cc_status) == TCPC_CC_STATE_SRC_OPEN) static int max_contaminant_adc_to_mv(struct max_tcpci_chip *chip, enum fladc_select channel, bool ua_src, u8 fladc) diff --git a/drivers/usb/typec/tcpm/tcpci.c b/drivers/usb/typec/tcpm/tcpci.c index b862fdf3fe1d..477f41632ed4 100644 --- a/drivers/usb/typec/tcpm/tcpci.c +++ b/drivers/usb/typec/tcpm/tcpci.c @@ -5,6 +5,7 @@ * USB Type-C Port Controller Interface. */ +#include #include #include #include @@ -241,12 +242,10 @@ static int tcpci_get_cc(struct tcpc_dev *tcpc, if (ret < 0) return ret; - *cc1 = tcpci_to_typec_cc((reg >> TCPC_CC_STATUS_CC1_SHIFT) & - TCPC_CC_STATUS_CC1_MASK, + *cc1 = tcpci_to_typec_cc(FIELD_GET(TCPC_CC_STATUS_CC1, reg), reg & TCPC_CC_STATUS_TERM || tcpc_presenting_rd(role_control, CC1)); - *cc2 = tcpci_to_typec_cc((reg >> TCPC_CC_STATUS_CC2_SHIFT) & - TCPC_CC_STATUS_CC2_MASK, + *cc2 = tcpci_to_typec_cc(FIELD_GET(TCPC_CC_STATUS_CC2, reg), reg & TCPC_CC_STATUS_TERM || tcpc_presenting_rd(role_control, CC2)); diff --git a/drivers/usb/typec/tcpm/tcpci_rt1711h.c b/drivers/usb/typec/tcpm/tcpci_rt1711h.c index 67422d45eb54..c6dbccf6b17a 100644 --- a/drivers/usb/typec/tcpm/tcpci_rt1711h.c +++ b/drivers/usb/typec/tcpm/tcpci_rt1711h.c @@ -5,6 +5,7 @@ * Richtek RT1711H Type-C Chip Driver */ +#include #include #include #include @@ -195,12 +196,10 @@ static inline int rt1711h_init_cc_params(struct rt1711h_chip *chip, u8 status) if (ret < 0) return ret; - cc1 = tcpci_to_typec_cc((status >> TCPC_CC_STATUS_CC1_SHIFT) & - TCPC_CC_STATUS_CC1_MASK, + cc1 = tcpci_to_typec_cc(FIELD_GET(TCPC_CC_STATUS_CC1, status), status & TCPC_CC_STATUS_TERM || tcpc_presenting_rd(role, CC1)); - cc2 = tcpci_to_typec_cc((status >> TCPC_CC_STATUS_CC2_SHIFT) & - TCPC_CC_STATUS_CC2_MASK, + cc2 = tcpci_to_typec_cc(FIELD_GET(TCPC_CC_STATUS_CC2, status), status & TCPC_CC_STATUS_TERM || tcpc_presenting_rd(role, CC2)); diff --git a/include/linux/usb/tcpci.h b/include/linux/usb/tcpci.h index d27fe0c22a8b..31d21ccf662b 100644 --- a/include/linux/usb/tcpci.h +++ b/include/linux/usb/tcpci.h @@ -92,11 +92,9 @@ #define TCPC_CC_STATUS_TERM BIT(4) #define TCPC_CC_STATUS_TERM_RP 0 #define TCPC_CC_STATUS_TERM_RD 1 +#define TCPC_CC_STATUS_CC2 GENMASK(3, 2) +#define TCPC_CC_STATUS_CC1 GENMASK(1, 0) #define TCPC_CC_STATE_SRC_OPEN 0 -#define TCPC_CC_STATUS_CC2_SHIFT 2 -#define TCPC_CC_STATUS_CC2_MASK 0x3 -#define TCPC_CC_STATUS_CC1_SHIFT 0 -#define TCPC_CC_STATUS_CC1_MASK 0x3 #define TCPC_POWER_STATUS 0x1e #define TCPC_POWER_STATUS_DBG_ACC_CON BIT(7) @@ -256,7 +254,7 @@ static inline enum typec_cc_status tcpci_to_typec_cc(unsigned int cc, bool sink) if (sink) return TYPEC_CC_RP_3_0; fallthrough; - case 0x0: + case TCPC_CC_STATE_SRC_OPEN: default: return TYPEC_CC_OPEN; } -- cgit v1.2.3 From 83b254c13ac093810e1058d9cb1bbb4b7ef9c246 Mon Sep 17 00:00:00 2001 From: André Draszik Date: Wed, 10 Jul 2024 11:36:11 +0100 Subject: usb: typec: tcpci: use GENMASK() for TCPC_ROLE_CTRL_CC[12] MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit All this open-coded shifting and masking is quite hard to read, in particular the if-statement in tcpci_apply_rc(). Declare TCPC_ROLE_CTRL_CC[12] using GENMASK() which allows using FIELD_GET() and FIELD_PREP() to arguably make the code more legible. Signed-off-by: André Draszik Reviewed-by: Heikki Krogerus Link: https://lore.kernel.org/r/20240710-tcpc-cleanup-v1-4-0ec1f41f4263@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/anx7411.c | 5 ++- drivers/usb/typec/tcpm/tcpci.c | 73 +++++++++++++++------------------- drivers/usb/typec/tcpm/tcpci_rt1711h.c | 8 ++-- include/linux/usb/tcpci.h | 9 ++--- 4 files changed, 43 insertions(+), 52 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/typec/anx7411.c b/drivers/usb/typec/anx7411.c index 5a5bf3532ad7..1a35c6d6f36b 100644 --- a/drivers/usb/typec/anx7411.c +++ b/drivers/usb/typec/anx7411.c @@ -6,6 +6,7 @@ * Copyright(c) 2022, Analogix Semiconductor. All rights reserved. * */ +#include #include #include #include @@ -884,8 +885,8 @@ static void anx7411_chip_standby(struct anx7411_data *ctx) OCM_RESET); ret |= anx7411_reg_write(ctx->tcpc_client, ANALOG_CTRL_10, 0x80); /* Set TCPC to RD and DRP enable */ - cc1 = TCPC_ROLE_CTRL_CC_RD << TCPC_ROLE_CTRL_CC1_SHIFT; - cc2 = TCPC_ROLE_CTRL_CC_RD << TCPC_ROLE_CTRL_CC2_SHIFT; + cc1 = FIELD_PREP(TCPC_ROLE_CTRL_CC1, TCPC_ROLE_CTRL_CC_RD); + cc2 = FIELD_PREP(TCPC_ROLE_CTRL_CC2, TCPC_ROLE_CTRL_CC_RD); ret |= anx7411_reg_write(ctx->tcpc_client, TCPC_ROLE_CTRL, TCPC_ROLE_CTRL_DRP | cc1 | cc2); diff --git a/drivers/usb/typec/tcpm/tcpci.c b/drivers/usb/typec/tcpm/tcpci.c index 477f41632ed4..c9a7e3fcc1b7 100644 --- a/drivers/usb/typec/tcpm/tcpci.c +++ b/drivers/usb/typec/tcpm/tcpci.c @@ -104,45 +104,42 @@ static int tcpci_set_cc(struct tcpc_dev *tcpc, enum typec_cc_status cc) switch (cc) { case TYPEC_CC_RA: - reg = (TCPC_ROLE_CTRL_CC_RA << TCPC_ROLE_CTRL_CC1_SHIFT) | - (TCPC_ROLE_CTRL_CC_RA << TCPC_ROLE_CTRL_CC2_SHIFT); + reg = (FIELD_PREP(TCPC_ROLE_CTRL_CC1, TCPC_ROLE_CTRL_CC_RA) + | FIELD_PREP(TCPC_ROLE_CTRL_CC2, TCPC_ROLE_CTRL_CC_RA)); break; case TYPEC_CC_RD: - reg = (TCPC_ROLE_CTRL_CC_RD << TCPC_ROLE_CTRL_CC1_SHIFT) | - (TCPC_ROLE_CTRL_CC_RD << TCPC_ROLE_CTRL_CC2_SHIFT); + reg = (FIELD_PREP(TCPC_ROLE_CTRL_CC1, TCPC_ROLE_CTRL_CC_RD) + | FIELD_PREP(TCPC_ROLE_CTRL_CC2, TCPC_ROLE_CTRL_CC_RD)); break; case TYPEC_CC_RP_DEF: - reg = (TCPC_ROLE_CTRL_CC_RP << TCPC_ROLE_CTRL_CC1_SHIFT) | - (TCPC_ROLE_CTRL_CC_RP << TCPC_ROLE_CTRL_CC2_SHIFT) | - (TCPC_ROLE_CTRL_RP_VAL_DEF << - TCPC_ROLE_CTRL_RP_VAL_SHIFT); + reg = (FIELD_PREP(TCPC_ROLE_CTRL_CC1, TCPC_ROLE_CTRL_CC_RP) + | FIELD_PREP(TCPC_ROLE_CTRL_CC2, TCPC_ROLE_CTRL_CC_RP) + | (TCPC_ROLE_CTRL_RP_VAL_DEF << TCPC_ROLE_CTRL_RP_VAL_SHIFT)); break; case TYPEC_CC_RP_1_5: - reg = (TCPC_ROLE_CTRL_CC_RP << TCPC_ROLE_CTRL_CC1_SHIFT) | - (TCPC_ROLE_CTRL_CC_RP << TCPC_ROLE_CTRL_CC2_SHIFT) | - (TCPC_ROLE_CTRL_RP_VAL_1_5 << - TCPC_ROLE_CTRL_RP_VAL_SHIFT); + reg = (FIELD_PREP(TCPC_ROLE_CTRL_CC1, TCPC_ROLE_CTRL_CC_RP) + | FIELD_PREP(TCPC_ROLE_CTRL_CC2, TCPC_ROLE_CTRL_CC_RP) + | (TCPC_ROLE_CTRL_RP_VAL_1_5 << TCPC_ROLE_CTRL_RP_VAL_SHIFT)); break; case TYPEC_CC_RP_3_0: - reg = (TCPC_ROLE_CTRL_CC_RP << TCPC_ROLE_CTRL_CC1_SHIFT) | - (TCPC_ROLE_CTRL_CC_RP << TCPC_ROLE_CTRL_CC2_SHIFT) | - (TCPC_ROLE_CTRL_RP_VAL_3_0 << - TCPC_ROLE_CTRL_RP_VAL_SHIFT); + reg = (FIELD_PREP(TCPC_ROLE_CTRL_CC1, TCPC_ROLE_CTRL_CC_RP) + | FIELD_PREP(TCPC_ROLE_CTRL_CC2, TCPC_ROLE_CTRL_CC_RP) + | (TCPC_ROLE_CTRL_RP_VAL_3_0 << TCPC_ROLE_CTRL_RP_VAL_SHIFT)); break; case TYPEC_CC_OPEN: default: - reg = (TCPC_ROLE_CTRL_CC_OPEN << TCPC_ROLE_CTRL_CC1_SHIFT) | - (TCPC_ROLE_CTRL_CC_OPEN << TCPC_ROLE_CTRL_CC2_SHIFT); + reg = (FIELD_PREP(TCPC_ROLE_CTRL_CC1, TCPC_ROLE_CTRL_CC_OPEN) + | FIELD_PREP(TCPC_ROLE_CTRL_CC2, TCPC_ROLE_CTRL_CC_OPEN)); break; } if (vconn_pres) { if (polarity == TYPEC_POLARITY_CC2) { - reg &= ~(TCPC_ROLE_CTRL_CC1_MASK << TCPC_ROLE_CTRL_CC1_SHIFT); - reg |= (TCPC_ROLE_CTRL_CC_OPEN << TCPC_ROLE_CTRL_CC1_SHIFT); + reg &= ~TCPC_ROLE_CTRL_CC1; + reg |= FIELD_PREP(TCPC_ROLE_CTRL_CC1, TCPC_ROLE_CTRL_CC_OPEN); } else { - reg &= ~(TCPC_ROLE_CTRL_CC2_MASK << TCPC_ROLE_CTRL_CC2_SHIFT); - reg |= (TCPC_ROLE_CTRL_CC_OPEN << TCPC_ROLE_CTRL_CC2_SHIFT); + reg &= ~TCPC_ROLE_CTRL_CC2; + reg |= FIELD_PREP(TCPC_ROLE_CTRL_CC2, TCPC_ROLE_CTRL_CC_OPEN); } } @@ -168,15 +165,11 @@ static int tcpci_apply_rc(struct tcpc_dev *tcpc, enum typec_cc_status cc, * APPLY_RC state is when ROLE_CONTROL.CC1 != ROLE_CONTROL.CC2 and vbus autodischarge on * disconnect is disabled. Bail out when ROLE_CONTROL.CC1 != ROLE_CONTROL.CC2. */ - if (((reg & (TCPC_ROLE_CTRL_CC2_MASK << TCPC_ROLE_CTRL_CC2_SHIFT)) >> - TCPC_ROLE_CTRL_CC2_SHIFT) != - ((reg & (TCPC_ROLE_CTRL_CC1_MASK << TCPC_ROLE_CTRL_CC1_SHIFT)) >> - TCPC_ROLE_CTRL_CC1_SHIFT)) + if (FIELD_GET(TCPC_ROLE_CTRL_CC2, reg) != FIELD_GET(TCPC_ROLE_CTRL_CC1, reg)) return 0; return regmap_update_bits(tcpci->regmap, TCPC_ROLE_CTRL, polarity == TYPEC_POLARITY_CC1 ? - TCPC_ROLE_CTRL_CC2_MASK << TCPC_ROLE_CTRL_CC2_SHIFT : - TCPC_ROLE_CTRL_CC1_MASK << TCPC_ROLE_CTRL_CC1_SHIFT, + TCPC_ROLE_CTRL_CC2 : TCPC_ROLE_CTRL_CC1, TCPC_ROLE_CTRL_CC_OPEN); } @@ -215,11 +208,11 @@ static int tcpci_start_toggling(struct tcpc_dev *tcpc, } if (cc == TYPEC_CC_RD) - reg |= (TCPC_ROLE_CTRL_CC_RD << TCPC_ROLE_CTRL_CC1_SHIFT) | - (TCPC_ROLE_CTRL_CC_RD << TCPC_ROLE_CTRL_CC2_SHIFT); + reg |= (FIELD_PREP(TCPC_ROLE_CTRL_CC1, TCPC_ROLE_CTRL_CC_RD) + | FIELD_PREP(TCPC_ROLE_CTRL_CC2, TCPC_ROLE_CTRL_CC_RD)); else - reg |= (TCPC_ROLE_CTRL_CC_RP << TCPC_ROLE_CTRL_CC1_SHIFT) | - (TCPC_ROLE_CTRL_CC_RP << TCPC_ROLE_CTRL_CC2_SHIFT); + reg |= (FIELD_PREP(TCPC_ROLE_CTRL_CC1, TCPC_ROLE_CTRL_CC_RP) + | FIELD_PREP(TCPC_ROLE_CTRL_CC2, TCPC_ROLE_CTRL_CC_RP)); ret = regmap_write(tcpci->regmap, TCPC_ROLE_CTRL, reg); if (ret < 0) return ret; @@ -281,28 +274,28 @@ static int tcpci_set_polarity(struct tcpc_dev *tcpc, reg = reg & ~TCPC_ROLE_CTRL_DRP; if (polarity == TYPEC_POLARITY_CC2) { - reg &= ~(TCPC_ROLE_CTRL_CC2_MASK << TCPC_ROLE_CTRL_CC2_SHIFT); + reg &= ~TCPC_ROLE_CTRL_CC2; /* Local port is source */ if (cc2 == TYPEC_CC_RD) /* Role control would have the Rp setting when DRP was enabled */ - reg |= TCPC_ROLE_CTRL_CC_RP << TCPC_ROLE_CTRL_CC2_SHIFT; + reg |= FIELD_PREP(TCPC_ROLE_CTRL_CC2, TCPC_ROLE_CTRL_CC_RP); else - reg |= TCPC_ROLE_CTRL_CC_RD << TCPC_ROLE_CTRL_CC2_SHIFT; + reg |= FIELD_PREP(TCPC_ROLE_CTRL_CC2, TCPC_ROLE_CTRL_CC_RD); } else { - reg &= ~(TCPC_ROLE_CTRL_CC1_MASK << TCPC_ROLE_CTRL_CC1_SHIFT); + reg &= ~TCPC_ROLE_CTRL_CC1; /* Local port is source */ if (cc1 == TYPEC_CC_RD) /* Role control would have the Rp setting when DRP was enabled */ - reg |= TCPC_ROLE_CTRL_CC_RP << TCPC_ROLE_CTRL_CC1_SHIFT; + reg |= FIELD_PREP(TCPC_ROLE_CTRL_CC1, TCPC_ROLE_CTRL_CC_RP); else - reg |= TCPC_ROLE_CTRL_CC_RD << TCPC_ROLE_CTRL_CC1_SHIFT; + reg |= FIELD_PREP(TCPC_ROLE_CTRL_CC1, TCPC_ROLE_CTRL_CC_RD); } } if (polarity == TYPEC_POLARITY_CC2) - reg |= TCPC_ROLE_CTRL_CC_OPEN << TCPC_ROLE_CTRL_CC1_SHIFT; + reg |= FIELD_PREP(TCPC_ROLE_CTRL_CC1, TCPC_ROLE_CTRL_CC_OPEN); else - reg |= TCPC_ROLE_CTRL_CC_OPEN << TCPC_ROLE_CTRL_CC2_SHIFT; + reg |= FIELD_PREP(TCPC_ROLE_CTRL_CC2, TCPC_ROLE_CTRL_CC_OPEN); ret = regmap_write(tcpci->regmap, TCPC_ROLE_CTRL, reg); if (ret < 0) return ret; diff --git a/drivers/usb/typec/tcpm/tcpci_rt1711h.c b/drivers/usb/typec/tcpm/tcpci_rt1711h.c index c6dbccf6b17a..bdb78d08b5b5 100644 --- a/drivers/usb/typec/tcpm/tcpci_rt1711h.c +++ b/drivers/usb/typec/tcpm/tcpci_rt1711h.c @@ -246,11 +246,11 @@ static int rt1711h_start_drp_toggling(struct tcpci *tcpci, } if (cc == TYPEC_CC_RD) - reg |= (TCPC_ROLE_CTRL_CC_RD << TCPC_ROLE_CTRL_CC1_SHIFT) | - (TCPC_ROLE_CTRL_CC_RD << TCPC_ROLE_CTRL_CC2_SHIFT); + reg |= (FIELD_PREP(TCPC_ROLE_CTRL_CC1, TCPC_ROLE_CTRL_CC_RD) + | FIELD_PREP(TCPC_ROLE_CTRL_CC2, TCPC_ROLE_CTRL_CC_RD)); else - reg |= (TCPC_ROLE_CTRL_CC_RP << TCPC_ROLE_CTRL_CC1_SHIFT) | - (TCPC_ROLE_CTRL_CC_RP << TCPC_ROLE_CTRL_CC2_SHIFT); + reg |= (FIELD_PREP(TCPC_ROLE_CTRL_CC1, TCPC_ROLE_CTRL_CC_RP) + | FIELD_PREP(TCPC_ROLE_CTRL_CC2, TCPC_ROLE_CTRL_CC_RP)); ret = rt1711h_write8(chip, TCPC_ROLE_CTRL, reg); if (ret < 0) diff --git a/include/linux/usb/tcpci.h b/include/linux/usb/tcpci.h index 31d21ccf662b..552d074429f0 100644 --- a/include/linux/usb/tcpci.h +++ b/include/linux/usb/tcpci.h @@ -68,10 +68,8 @@ #define TCPC_ROLE_CTRL_RP_VAL_DEF 0x0 #define TCPC_ROLE_CTRL_RP_VAL_1_5 0x1 #define TCPC_ROLE_CTRL_RP_VAL_3_0 0x2 -#define TCPC_ROLE_CTRL_CC2_SHIFT 2 -#define TCPC_ROLE_CTRL_CC2_MASK 0x3 -#define TCPC_ROLE_CTRL_CC1_SHIFT 0 -#define TCPC_ROLE_CTRL_CC1_MASK 0x3 +#define TCPC_ROLE_CTRL_CC2 GENMASK(3, 2) +#define TCPC_ROLE_CTRL_CC1 GENMASK(1, 0) #define TCPC_ROLE_CTRL_CC_RA 0x0 #define TCPC_ROLE_CTRL_CC_RP 0x1 #define TCPC_ROLE_CTRL_CC_RD 0x2 @@ -176,8 +174,7 @@ #define tcpc_presenting_rd(reg, cc) \ (!(TCPC_ROLE_CTRL_DRP & (reg)) && \ - (((reg) & (TCPC_ROLE_CTRL_## cc ##_MASK << TCPC_ROLE_CTRL_## cc ##_SHIFT)) == \ - (TCPC_ROLE_CTRL_CC_RD << TCPC_ROLE_CTRL_## cc ##_SHIFT))) + FIELD_GET(TCPC_ROLE_CTRL_## cc, reg) == TCPC_ROLE_CTRL_CC_RD) struct tcpci; -- cgit v1.2.3 From 46b1e0f87ba89f0a06ffbde5fe8d13c5af93f94e Mon Sep 17 00:00:00 2001 From: André Draszik Date: Wed, 10 Jul 2024 11:36:12 +0100 Subject: usb: typec: tcpci: use GENMASK() for TCPC_ROLE_CTRL_RP_VAL MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Align the last remaining field TCPC_ROLE_CTRL_RP_VAL with the other fields in the TCPC_ROLE_CTRL register by using GENMASK() and FIELD_PREP(). Signed-off-by: André Draszik Reviewed-by: Heikki Krogerus Link: https://lore.kernel.org/r/20240710-tcpc-cleanup-v1-5-0ec1f41f4263@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tcpm/tcpci.c | 21 ++++++++++++--------- drivers/usb/typec/tcpm/tcpci_rt1711h.c | 12 ++++++------ include/linux/usb/tcpci.h | 3 +-- 3 files changed, 19 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/typec/tcpm/tcpci.c b/drivers/usb/typec/tcpm/tcpci.c index c9a7e3fcc1b7..9477ee813fa5 100644 --- a/drivers/usb/typec/tcpm/tcpci.c +++ b/drivers/usb/typec/tcpm/tcpci.c @@ -114,17 +114,20 @@ static int tcpci_set_cc(struct tcpc_dev *tcpc, enum typec_cc_status cc) case TYPEC_CC_RP_DEF: reg = (FIELD_PREP(TCPC_ROLE_CTRL_CC1, TCPC_ROLE_CTRL_CC_RP) | FIELD_PREP(TCPC_ROLE_CTRL_CC2, TCPC_ROLE_CTRL_CC_RP) - | (TCPC_ROLE_CTRL_RP_VAL_DEF << TCPC_ROLE_CTRL_RP_VAL_SHIFT)); + | FIELD_PREP(TCPC_ROLE_CTRL_RP_VAL, + TCPC_ROLE_CTRL_RP_VAL_DEF)); break; case TYPEC_CC_RP_1_5: reg = (FIELD_PREP(TCPC_ROLE_CTRL_CC1, TCPC_ROLE_CTRL_CC_RP) | FIELD_PREP(TCPC_ROLE_CTRL_CC2, TCPC_ROLE_CTRL_CC_RP) - | (TCPC_ROLE_CTRL_RP_VAL_1_5 << TCPC_ROLE_CTRL_RP_VAL_SHIFT)); + | FIELD_PREP(TCPC_ROLE_CTRL_RP_VAL, + TCPC_ROLE_CTRL_RP_VAL_1_5)); break; case TYPEC_CC_RP_3_0: reg = (FIELD_PREP(TCPC_ROLE_CTRL_CC1, TCPC_ROLE_CTRL_CC_RP) | FIELD_PREP(TCPC_ROLE_CTRL_CC2, TCPC_ROLE_CTRL_CC_RP) - | (TCPC_ROLE_CTRL_RP_VAL_3_0 << TCPC_ROLE_CTRL_RP_VAL_SHIFT)); + | FIELD_PREP(TCPC_ROLE_CTRL_RP_VAL, + TCPC_ROLE_CTRL_RP_VAL_3_0)); break; case TYPEC_CC_OPEN: default: @@ -194,16 +197,16 @@ static int tcpci_start_toggling(struct tcpc_dev *tcpc, switch (cc) { default: case TYPEC_CC_RP_DEF: - reg |= (TCPC_ROLE_CTRL_RP_VAL_DEF << - TCPC_ROLE_CTRL_RP_VAL_SHIFT); + reg |= FIELD_PREP(TCPC_ROLE_CTRL_RP_VAL, + TCPC_ROLE_CTRL_RP_VAL_DEF); break; case TYPEC_CC_RP_1_5: - reg |= (TCPC_ROLE_CTRL_RP_VAL_1_5 << - TCPC_ROLE_CTRL_RP_VAL_SHIFT); + reg |= FIELD_PREP(TCPC_ROLE_CTRL_RP_VAL, + TCPC_ROLE_CTRL_RP_VAL_1_5); break; case TYPEC_CC_RP_3_0: - reg |= (TCPC_ROLE_CTRL_RP_VAL_3_0 << - TCPC_ROLE_CTRL_RP_VAL_SHIFT); + reg |= FIELD_PREP(TCPC_ROLE_CTRL_RP_VAL, + TCPC_ROLE_CTRL_RP_VAL_3_0); break; } diff --git a/drivers/usb/typec/tcpm/tcpci_rt1711h.c b/drivers/usb/typec/tcpm/tcpci_rt1711h.c index bdb78d08b5b5..64f6dd0dc660 100644 --- a/drivers/usb/typec/tcpm/tcpci_rt1711h.c +++ b/drivers/usb/typec/tcpm/tcpci_rt1711h.c @@ -232,16 +232,16 @@ static int rt1711h_start_drp_toggling(struct tcpci *tcpci, switch (cc) { default: case TYPEC_CC_RP_DEF: - reg |= (TCPC_ROLE_CTRL_RP_VAL_DEF << - TCPC_ROLE_CTRL_RP_VAL_SHIFT); + reg |= FIELD_PREP(TCPC_ROLE_CTRL_RP_VAL, + TCPC_ROLE_CTRL_RP_VAL_DEF); break; case TYPEC_CC_RP_1_5: - reg |= (TCPC_ROLE_CTRL_RP_VAL_1_5 << - TCPC_ROLE_CTRL_RP_VAL_SHIFT); + reg |= FIELD_PREP(TCPC_ROLE_CTRL_RP_VAL, + TCPC_ROLE_CTRL_RP_VAL_1_5); break; case TYPEC_CC_RP_3_0: - reg |= (TCPC_ROLE_CTRL_RP_VAL_3_0 << - TCPC_ROLE_CTRL_RP_VAL_SHIFT); + reg |= FIELD_PREP(TCPC_ROLE_CTRL_RP_VAL, + TCPC_ROLE_CTRL_RP_VAL_3_0); break; } diff --git a/include/linux/usb/tcpci.h b/include/linux/usb/tcpci.h index 552d074429f0..80652d4f722e 100644 --- a/include/linux/usb/tcpci.h +++ b/include/linux/usb/tcpci.h @@ -63,8 +63,7 @@ #define TCPC_ROLE_CTRL 0x1a #define TCPC_ROLE_CTRL_DRP BIT(6) -#define TCPC_ROLE_CTRL_RP_VAL_SHIFT 4 -#define TCPC_ROLE_CTRL_RP_VAL_MASK 0x3 +#define TCPC_ROLE_CTRL_RP_VAL GENMASK(5, 4) #define TCPC_ROLE_CTRL_RP_VAL_DEF 0x0 #define TCPC_ROLE_CTRL_RP_VAL_1_5 0x1 #define TCPC_ROLE_CTRL_RP_VAL_3_0 0x2 -- cgit v1.2.3 From aee4568f42e0d7526207a10944bb89bb45522b59 Mon Sep 17 00:00:00 2001 From: André Draszik Date: Wed, 10 Jul 2024 11:36:13 +0100 Subject: usb: typec: tcpci: use GENMASK() for TCPC_MSG_HDR_INFO_REV MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Convert field TCPC_MSG_HDR_INFO_REV from register TCPC_MSG_HDR_INFO to using GENMASK() and FIELD_PREP() so as to keep using a similar approach for all fields. Signed-off-by: André Draszik Reviewed-by: Heikki Krogerus Link: https://lore.kernel.org/r/20240710-tcpc-cleanup-v1-6-0ec1f41f4263@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tcpm/tcpci.c | 2 +- include/linux/usb/tcpci.h | 3 +-- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/typec/tcpm/tcpci.c b/drivers/usb/typec/tcpm/tcpci.c index 9477ee813fa5..929d0b7c64ca 100644 --- a/drivers/usb/typec/tcpm/tcpci.c +++ b/drivers/usb/typec/tcpm/tcpci.c @@ -456,7 +456,7 @@ static int tcpci_set_roles(struct tcpc_dev *tcpc, bool attached, unsigned int reg; int ret; - reg = PD_REV20 << TCPC_MSG_HDR_INFO_REV_SHIFT; + reg = FIELD_PREP(TCPC_MSG_HDR_INFO_REV, PD_REV20); if (role == TYPEC_SOURCE) reg |= TCPC_MSG_HDR_INFO_PWR_ROLE; if (data == TYPEC_HOST) diff --git a/include/linux/usb/tcpci.h b/include/linux/usb/tcpci.h index 80652d4f722e..3cd61e9f73b3 100644 --- a/include/linux/usb/tcpci.h +++ b/include/linux/usb/tcpci.h @@ -129,9 +129,8 @@ #define TCPC_MSG_HDR_INFO 0x2e #define TCPC_MSG_HDR_INFO_DATA_ROLE BIT(3) +#define TCPC_MSG_HDR_INFO_REV GENMASK(2, 1) #define TCPC_MSG_HDR_INFO_PWR_ROLE BIT(0) -#define TCPC_MSG_HDR_INFO_REV_SHIFT 1 -#define TCPC_MSG_HDR_INFO_REV_MASK 0x3 #define TCPC_RX_DETECT 0x2f #define TCPC_RX_DETECT_HARD_RESET BIT(5) -- cgit v1.2.3 From 7cd41974d2c81055f61ba9f69e31c02e866716e0 Mon Sep 17 00:00:00 2001 From: André Draszik Date: Wed, 10 Jul 2024 11:36:14 +0100 Subject: usb: typec: tcpci: use GENMASK() for TCPC_TRANSMIT register fields MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Convert all fields from register TCPC_TRANSMIT to using GENMASK() and FIELD_PREP() so as to keep using a similar approach throughout the code base and make it arguably easier to read. Signed-off-by: André Draszik Reviewed-by: Heikki Krogerus Link: https://lore.kernel.org/r/20240710-tcpc-cleanup-v1-7-0ec1f41f4263@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tcpm/tcpci.c | 7 +++++-- include/linux/usb/tcpci.h | 6 ++---- 2 files changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/typec/tcpm/tcpci.c b/drivers/usb/typec/tcpm/tcpci.c index 929d0b7c64ca..aed223edf76a 100644 --- a/drivers/usb/typec/tcpm/tcpci.c +++ b/drivers/usb/typec/tcpm/tcpci.c @@ -607,8 +607,11 @@ static int tcpci_pd_transmit(struct tcpc_dev *tcpc, enum tcpm_transmit_type type } /* nRetryCount is 3 in PD2.0 spec where 2 in PD3.0 spec */ - reg = ((negotiated_rev > PD_REV20 ? PD_RETRY_COUNT_3_0_OR_HIGHER : PD_RETRY_COUNT_DEFAULT) - << TCPC_TRANSMIT_RETRY_SHIFT) | (type << TCPC_TRANSMIT_TYPE_SHIFT); + reg = FIELD_PREP(TCPC_TRANSMIT_RETRY, + (negotiated_rev > PD_REV20 + ? PD_RETRY_COUNT_3_0_OR_HIGHER + : PD_RETRY_COUNT_DEFAULT)); + reg |= FIELD_PREP(TCPC_TRANSMIT_TYPE, type); ret = regmap_write(tcpci->regmap, TCPC_TRANSMIT, reg); if (ret < 0) return ret; diff --git a/include/linux/usb/tcpci.h b/include/linux/usb/tcpci.h index 3cd61e9f73b3..f7f5cfbdef12 100644 --- a/include/linux/usb/tcpci.h +++ b/include/linux/usb/tcpci.h @@ -148,10 +148,8 @@ #define TCPC_RX_DATA 0x34 /* through 0x4f */ #define TCPC_TRANSMIT 0x50 -#define TCPC_TRANSMIT_RETRY_SHIFT 4 -#define TCPC_TRANSMIT_RETRY_MASK 0x3 -#define TCPC_TRANSMIT_TYPE_SHIFT 0 -#define TCPC_TRANSMIT_TYPE_MASK 0x7 +#define TCPC_TRANSMIT_RETRY GENMASK(5, 4) +#define TCPC_TRANSMIT_TYPE GENMASK(2, 0) #define TCPC_TX_BYTE_CNT 0x51 #define TCPC_TX_HDR 0x52 -- cgit v1.2.3 From 08d6fd691bdd5d6e7881ce42ca6774ed92b10896 Mon Sep 17 00:00:00 2001 From: Akash Kumar Date: Thu, 1 Aug 2024 11:00:03 +0530 Subject: usb: gadget: Increase max configuration interface to 32 Currently, max configuration interfaces are limited to 16, which fails for compositions containing 10 UVC configurations with interrupt ep disabled along with other configurations , and we see bind failures while allocating interface ID in uvc bind. Increase max configuration interface to 32 to support any large compositions limited to same size as usb device endpoints as interfaces cannot be more than endpoints. Signed-off-by: Akash Kumar Link: https://lore.kernel.org/r/20240801053003.15153-1-quic_akakum@quicinc.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/composite.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index af3cd2aae4bc..6e38fb9d2117 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -256,7 +256,7 @@ int config_ep_by_speed(struct usb_gadget *g, struct usb_function *f, struct usb_ep *_ep); int usb_func_wakeup(struct usb_function *func); -#define MAX_CONFIG_INTERFACES 16 /* arbitrary; max 255 */ +#define MAX_CONFIG_INTERFACES 32 /** * struct usb_configuration - represents one gadget configuration -- cgit v1.2.3 From 259b46204885431f2853afa2a2bffa63f3705e67 Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Mon, 5 Aug 2024 12:20:37 +0200 Subject: serial: remove quot_frac from serial8250_do_set_divisor() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit quot_frac is unused in serial8250_do_set_divisor() since commit b2b4b8ed3c06 (serial: 8250_exar: Move custom divisor support out from 8250_port). So no point to pass it. Signed-off-by: Jiri Slaby (SUSE) Cc: Ilpo Järvinen Cc: Andy Shevchenko Cc: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20240805102046.307511-5-jirislaby@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_dwlib.c | 2 +- drivers/tty/serial/8250/8250_exar.c | 2 +- drivers/tty/serial/8250/8250_pci.c | 2 +- drivers/tty/serial/8250/8250_port.c | 4 ++-- include/linux/serial_8250.h | 2 +- 5 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/serial/8250/8250_dwlib.c b/drivers/tty/serial/8250/8250_dwlib.c index 5a2520943dfd..b055d89cfb39 100644 --- a/drivers/tty/serial/8250/8250_dwlib.c +++ b/drivers/tty/serial/8250/8250_dwlib.c @@ -89,7 +89,7 @@ static void dw8250_set_divisor(struct uart_port *p, unsigned int baud, unsigned int quot, unsigned int quot_frac) { dw8250_writel_ext(p, DW_UART_DLF, quot_frac); - serial8250_do_set_divisor(p, baud, quot, quot_frac); + serial8250_do_set_divisor(p, baud, quot); } void dw8250_do_set_termios(struct uart_port *p, struct ktermios *termios, diff --git a/drivers/tty/serial/8250/8250_exar.c b/drivers/tty/serial/8250/8250_exar.c index 616128254bbd..b7a75db15249 100644 --- a/drivers/tty/serial/8250/8250_exar.c +++ b/drivers/tty/serial/8250/8250_exar.c @@ -500,7 +500,7 @@ static unsigned int xr17v35x_get_divisor(struct uart_port *p, unsigned int baud, static void xr17v35x_set_divisor(struct uart_port *p, unsigned int baud, unsigned int quot, unsigned int quot_frac) { - serial8250_do_set_divisor(p, baud, quot, quot_frac); + serial8250_do_set_divisor(p, baud, quot); /* Preserve bits not related to baudrate; DLD[7:4]. */ quot_frac |= serial_port_in(p, 0x2) & 0xf0; diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index e1d7aa2fa347..6709b6a5f301 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -1277,7 +1277,7 @@ static void pci_oxsemi_tornado_set_divisor(struct uart_port *port, serial_icr_write(up, UART_TCR, tcr); serial_icr_write(up, UART_CPR, cpr); serial_icr_write(up, UART_CKS, cpr2); - serial8250_do_set_divisor(port, baud, quot, 0); + serial8250_do_set_divisor(port, baud, quot); } /* diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 2786918aea98..3509af7dc52b 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -2609,7 +2609,7 @@ static unsigned char serial8250_compute_lcr(struct uart_8250_port *up, } void serial8250_do_set_divisor(struct uart_port *port, unsigned int baud, - unsigned int quot, unsigned int quot_frac) + unsigned int quot) { struct uart_8250_port *up = up_to_u8250p(port); @@ -2641,7 +2641,7 @@ static void serial8250_set_divisor(struct uart_port *port, unsigned int baud, if (port->set_divisor) port->set_divisor(port, baud, quot, quot_frac); else - serial8250_do_set_divisor(port, baud, quot, quot_frac); + serial8250_do_set_divisor(port, baud, quot); } static unsigned int serial8250_get_baud_rate(struct uart_port *port, diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index fd59ed2cca53..e0717c8393d7 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -193,7 +193,7 @@ void serial8250_do_pm(struct uart_port *port, unsigned int state, unsigned int oldstate); void serial8250_do_set_mctrl(struct uart_port *port, unsigned int mctrl); void serial8250_do_set_divisor(struct uart_port *port, unsigned int baud, - unsigned int quot, unsigned int quot_frac); + unsigned int quot); int fsl8250_handle_irq(struct uart_port *port); int serial8250_handle_irq(struct uart_port *port, unsigned int iir); u16 serial8250_rx_chars(struct uart_8250_port *up, u16 lsr); -- cgit v1.2.3 From 130fd056dd82b02db9a661c013071af35309be1a Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Mon, 10 Jun 2024 20:20:16 +0100 Subject: sched/rt: Clean up usage of rt_task() rt_task() checks if a task has RT priority. But depends on your dictionary, this could mean it belongs to RT class, or is a 'realtime' task, which includes RT and DL classes. Since this has caused some confusion already on discussion [1], it seemed a clean up is due. I define the usage of rt_task() to be tasks that belong to RT class. Make sure that it returns true only for RT class and audit the users and replace the ones required the old behavior with the new realtime_task() which returns true for RT and DL classes. Introduce similar realtime_prio() to create similar distinction to rt_prio() and update the users that required the old behavior to use the new function. Move MAX_DL_PRIO to prio.h so it can be used in the new definitions. Document the functions to make it more obvious what is the difference between them. PI-boosted tasks is a factor that must be taken into account when choosing which function to use. Rename task_is_realtime() to realtime_task_policy() as the old name is confusing against the new realtime_task(). No functional changes were intended. [1] https://lore.kernel.org/lkml/20240506100509.GL40213@noisy.programming.kicks-ass.net/ Signed-off-by: Qais Yousef Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Phil Auld Reviewed-by: "Steven Rostedt (Google)" Reviewed-by: Sebastian Andrzej Siewior Link: https://lore.kernel.org/r/20240610192018.1567075-2-qyousef@layalina.io --- fs/bcachefs/six.c | 2 +- fs/select.c | 2 +- include/linux/ioprio.h | 2 +- include/linux/sched/deadline.h | 6 ++++-- include/linux/sched/prio.h | 1 + include/linux/sched/rt.h | 27 ++++++++++++++++++++++++++- kernel/locking/rtmutex.c | 4 ++-- kernel/locking/rwsem.c | 4 ++-- kernel/locking/ww_mutex.h | 2 +- kernel/sched/core.c | 4 ++-- kernel/sched/syscalls.c | 2 +- kernel/time/hrtimer.c | 6 +++--- kernel/trace/trace_sched_wakeup.c | 2 +- mm/page-writeback.c | 4 ++-- mm/page_alloc.c | 2 +- 15 files changed, 49 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/fs/bcachefs/six.c b/fs/bcachefs/six.c index 3a494c5d1247..b30870bf7e4a 100644 --- a/fs/bcachefs/six.c +++ b/fs/bcachefs/six.c @@ -335,7 +335,7 @@ static inline bool six_owner_running(struct six_lock *lock) */ rcu_read_lock(); struct task_struct *owner = READ_ONCE(lock->owner); - bool ret = owner ? owner_on_cpu(owner) : !rt_task(current); + bool ret = owner ? owner_on_cpu(owner) : !realtime_task(current); rcu_read_unlock(); return ret; diff --git a/fs/select.c b/fs/select.c index 9515c3fa1a03..8d5c1419416c 100644 --- a/fs/select.c +++ b/fs/select.c @@ -82,7 +82,7 @@ u64 select_estimate_accuracy(struct timespec64 *tv) * Realtime tasks get a slack of 0 for obvious reasons. */ - if (rt_task(current)) + if (realtime_task(current)) return 0; ktime_get_ts64(&now); diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h index db1249cd9692..75859b78d540 100644 --- a/include/linux/ioprio.h +++ b/include/linux/ioprio.h @@ -40,7 +40,7 @@ static inline int task_nice_ioclass(struct task_struct *task) { if (task->policy == SCHED_IDLE) return IOPRIO_CLASS_IDLE; - else if (task_is_realtime(task)) + else if (realtime_task_policy(task)) return IOPRIO_CLASS_RT; else return IOPRIO_CLASS_BE; diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h index df3aca89d4f5..5cb88b748ad6 100644 --- a/include/linux/sched/deadline.h +++ b/include/linux/sched/deadline.h @@ -10,8 +10,6 @@ #include -#define MAX_DL_PRIO 0 - static inline int dl_prio(int prio) { if (unlikely(prio < MAX_DL_PRIO)) @@ -19,6 +17,10 @@ static inline int dl_prio(int prio) return 0; } +/* + * Returns true if a task has a priority that belongs to DL class. PI-boosted + * tasks will return true. Use dl_policy() to ignore PI-boosted tasks. + */ static inline int dl_task(struct task_struct *p) { return dl_prio(p->prio); diff --git a/include/linux/sched/prio.h b/include/linux/sched/prio.h index ab83d85e1183..6ab43b4f72f9 100644 --- a/include/linux/sched/prio.h +++ b/include/linux/sched/prio.h @@ -14,6 +14,7 @@ */ #define MAX_RT_PRIO 100 +#define MAX_DL_PRIO 0 #define MAX_PRIO (MAX_RT_PRIO + NICE_WIDTH) #define DEFAULT_PRIO (MAX_RT_PRIO + NICE_WIDTH / 2) diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h index b2b9e6eb9683..a055dd68a77c 100644 --- a/include/linux/sched/rt.h +++ b/include/linux/sched/rt.h @@ -7,18 +7,43 @@ struct task_struct; static inline int rt_prio(int prio) +{ + if (unlikely(prio < MAX_RT_PRIO && prio >= MAX_DL_PRIO)) + return 1; + return 0; +} + +static inline int realtime_prio(int prio) { if (unlikely(prio < MAX_RT_PRIO)) return 1; return 0; } +/* + * Returns true if a task has a priority that belongs to RT class. PI-boosted + * tasks will return true. Use rt_policy() to ignore PI-boosted tasks. + */ static inline int rt_task(struct task_struct *p) { return rt_prio(p->prio); } -static inline bool task_is_realtime(struct task_struct *tsk) +/* + * Returns true if a task has a priority that belongs to RT or DL classes. + * PI-boosted tasks will return true. Use realtime_task_policy() to ignore + * PI-boosted tasks. + */ +static inline int realtime_task(struct task_struct *p) +{ + return realtime_prio(p->prio); +} + +/* + * Returns true if a task has a policy that belongs to RT or DL classes. + * PI-boosted tasks will return false. + */ +static inline bool realtime_task_policy(struct task_struct *tsk) { int policy = tsk->policy; diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 88d08eeb8bc0..55c9dab37f33 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -347,7 +347,7 @@ static __always_inline int __waiter_prio(struct task_struct *task) { int prio = task->prio; - if (!rt_prio(prio)) + if (!realtime_prio(prio)) return DEFAULT_PRIO; return prio; @@ -435,7 +435,7 @@ static inline bool rt_mutex_steal(struct rt_mutex_waiter *waiter, * Note that RT tasks are excluded from same priority (lateral) * steals to prevent the introduction of an unbounded latency. */ - if (rt_prio(waiter->tree.prio) || dl_prio(waiter->tree.prio)) + if (realtime_prio(waiter->tree.prio)) return false; return rt_waiter_node_equal(&waiter->tree, &top_waiter->tree); diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index 33cac79e3994..516174a64fa5 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -631,7 +631,7 @@ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem, * if it is an RT task or wait in the wait queue * for too long. */ - if (has_handoff || (!rt_task(waiter->task) && + if (has_handoff || (!realtime_task(waiter->task) && !time_after(jiffies, waiter->timeout))) return false; @@ -914,7 +914,7 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem) if (owner_state != OWNER_WRITER) { if (need_resched()) break; - if (rt_task(current) && + if (realtime_task(current) && (prev_owner_state != OWNER_WRITER)) break; } diff --git a/kernel/locking/ww_mutex.h b/kernel/locking/ww_mutex.h index 3ad2cc4823e5..fa4b416a1f62 100644 --- a/kernel/locking/ww_mutex.h +++ b/kernel/locking/ww_mutex.h @@ -237,7 +237,7 @@ __ww_ctx_less(struct ww_acquire_ctx *a, struct ww_acquire_ctx *b) int a_prio = a->task->prio; int b_prio = b->task->prio; - if (rt_prio(a_prio) || rt_prio(b_prio)) { + if (realtime_prio(a_prio) || realtime_prio(b_prio)) { if (a_prio > b_prio) return true; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 29fde993d3f8..673cbeb7ad48 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -166,7 +166,7 @@ static inline int __task_prio(const struct task_struct *p) if (p->dl_server) return -1; /* deadline */ - if (rt_prio(p->prio)) /* includes deadline */ + if (realtime_prio(p->prio)) /* includes deadline */ return p->prio; /* [-1, 99] */ if (p->sched_class == &idle_sched_class) @@ -8590,7 +8590,7 @@ void normalize_rt_tasks(void) schedstat_set(p->stats.sleep_start, 0); schedstat_set(p->stats.block_start, 0); - if (!dl_task(p) && !rt_task(p)) { + if (!realtime_task(p)) { /* * Renice negative nice level userspace * tasks back to 0: diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c index ae1b42775ef9..6d60326d73e4 100644 --- a/kernel/sched/syscalls.c +++ b/kernel/sched/syscalls.c @@ -57,7 +57,7 @@ static int effective_prio(struct task_struct *p) * keep the priority unchanged. Otherwise, update priority * to the normal priority: */ - if (!rt_prio(p->prio)) + if (!realtime_prio(p->prio)) return p->normal_prio; return p->prio; } diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index b8ee320208d4..a1d1d8d886a8 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1975,7 +1975,7 @@ static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl, * expiry. */ if (IS_ENABLED(CONFIG_PREEMPT_RT)) { - if (task_is_realtime(current) && !(mode & HRTIMER_MODE_SOFT)) + if (realtime_task_policy(current) && !(mode & HRTIMER_MODE_SOFT)) mode |= HRTIMER_MODE_HARD; } @@ -2075,7 +2075,7 @@ long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode, u64 slack; slack = current->timer_slack_ns; - if (rt_task(current)) + if (realtime_task(current)) slack = 0; hrtimer_init_sleeper_on_stack(&t, clockid, mode); @@ -2280,7 +2280,7 @@ schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta, * Override any slack passed by the user if under * rt contraints. */ - if (rt_task(current)) + if (realtime_task(current)) delta = 0; hrtimer_init_sleeper_on_stack(&t, clock_id, mode); diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 130ca7e7787e..1824e17c93c7 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -547,7 +547,7 @@ probe_wakeup(void *ignore, struct task_struct *p) * - wakeup_dl handles tasks belonging to sched_dl class only. */ if (tracing_dl || (wakeup_dl && !dl_task(p)) || - (wakeup_rt && !dl_task(p) && !rt_task(p)) || + (wakeup_rt && !realtime_task(p)) || (!dl_task(p) && (p->prio >= wakeup_prio || p->prio >= current->prio))) return; diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 4430ac68e4c4..78dcad729703 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -418,7 +418,7 @@ static void domain_dirty_limits(struct dirty_throttle_control *dtc) bg_thresh = (bg_ratio * available_memory) / PAGE_SIZE; tsk = current; - if (rt_task(tsk)) { + if (realtime_task(tsk)) { bg_thresh += bg_thresh / 4 + global_wb_domain.dirty_limit / 32; thresh += thresh / 4 + global_wb_domain.dirty_limit / 32; } @@ -477,7 +477,7 @@ static unsigned long node_dirty_limit(struct pglist_data *pgdat) else dirty = vm_dirty_ratio * node_memory / 100; - if (rt_task(tsk)) + if (realtime_task(tsk)) dirty += dirty / 4; /* diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 28f80daf5c04..54274e468d51 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4002,7 +4002,7 @@ gfp_to_alloc_flags(gfp_t gfp_mask, unsigned int order) */ if (alloc_flags & ALLOC_MIN_RESERVE) alloc_flags &= ~ALLOC_CPUSET; - } else if (unlikely(rt_task(current)) && in_task()) + } else if (unlikely(realtime_task(current)) && in_task()) alloc_flags |= ALLOC_MIN_RESERVE; alloc_flags = gfp_to_alloc_flags_cma(gfp_mask, alloc_flags); -- cgit v1.2.3 From b166af3db70fdcecf125662a2360471bb20be203 Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Mon, 10 Jun 2024 20:20:17 +0100 Subject: sched/rt, dl: Convert functions to return bool {rt, realtime, dl}_{task, prio}() functions' return value is actually a bool. Convert their return type to reflect that. Suggested-by: "Steven Rostedt (Google)" Signed-off-by: Qais Yousef Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Sebastian Andrzej Siewior Reviewed-by: "Steven Rostedt (Google)" Reviewed-by: Metin Kaya Link: https://lore.kernel.org/r/20240610192018.1567075-3-qyousef@layalina.io --- include/linux/sched/deadline.h | 8 +++----- include/linux/sched/rt.h | 16 ++++++---------- 2 files changed, 9 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h index 5cb88b748ad6..3a912ab42bb5 100644 --- a/include/linux/sched/deadline.h +++ b/include/linux/sched/deadline.h @@ -10,18 +10,16 @@ #include -static inline int dl_prio(int prio) +static inline bool dl_prio(int prio) { - if (unlikely(prio < MAX_DL_PRIO)) - return 1; - return 0; + return unlikely(prio < MAX_DL_PRIO); } /* * Returns true if a task has a priority that belongs to DL class. PI-boosted * tasks will return true. Use dl_policy() to ignore PI-boosted tasks. */ -static inline int dl_task(struct task_struct *p) +static inline bool dl_task(struct task_struct *p) { return dl_prio(p->prio); } diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h index a055dd68a77c..91ef1ef2019f 100644 --- a/include/linux/sched/rt.h +++ b/include/linux/sched/rt.h @@ -6,25 +6,21 @@ struct task_struct; -static inline int rt_prio(int prio) +static inline bool rt_prio(int prio) { - if (unlikely(prio < MAX_RT_PRIO && prio >= MAX_DL_PRIO)) - return 1; - return 0; + return unlikely(prio < MAX_RT_PRIO && prio >= MAX_DL_PRIO); } -static inline int realtime_prio(int prio) +static inline bool realtime_prio(int prio) { - if (unlikely(prio < MAX_RT_PRIO)) - return 1; - return 0; + return unlikely(prio < MAX_RT_PRIO); } /* * Returns true if a task has a priority that belongs to RT class. PI-boosted * tasks will return true. Use rt_policy() to ignore PI-boosted tasks. */ -static inline int rt_task(struct task_struct *p) +static inline bool rt_task(struct task_struct *p) { return rt_prio(p->prio); } @@ -34,7 +30,7 @@ static inline int rt_task(struct task_struct *p) * PI-boosted tasks will return true. Use realtime_task_policy() to ignore * PI-boosted tasks. */ -static inline int realtime_task(struct task_struct *p) +static inline bool realtime_task(struct task_struct *p) { return realtime_prio(p->prio); } -- cgit v1.2.3 From ae04f69de0bef93c7086cf2983dbc8e8fd624ebe Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Mon, 10 Jun 2024 20:20:18 +0100 Subject: sched/rt: Rename realtime_{prio, task}() to rt_or_dl_{prio, task}() Some find the name realtime overloaded. Use rt_or_dl() as an alternative, hopefully better, name. Suggested-by: Daniel Bristot de Oliveira Signed-off-by: Qais Yousef Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20240610192018.1567075-4-qyousef@layalina.io --- fs/bcachefs/six.c | 2 +- fs/select.c | 2 +- include/linux/ioprio.h | 2 +- include/linux/sched/rt.h | 10 +++++----- kernel/locking/rtmutex.c | 4 ++-- kernel/locking/rwsem.c | 4 ++-- kernel/locking/ww_mutex.h | 2 +- kernel/sched/core.c | 4 ++-- kernel/sched/syscalls.c | 2 +- kernel/time/hrtimer.c | 6 +++--- kernel/trace/trace_sched_wakeup.c | 2 +- mm/page-writeback.c | 4 ++-- mm/page_alloc.c | 2 +- 13 files changed, 23 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/fs/bcachefs/six.c b/fs/bcachefs/six.c index b30870bf7e4a..9cbd3c14c94f 100644 --- a/fs/bcachefs/six.c +++ b/fs/bcachefs/six.c @@ -335,7 +335,7 @@ static inline bool six_owner_running(struct six_lock *lock) */ rcu_read_lock(); struct task_struct *owner = READ_ONCE(lock->owner); - bool ret = owner ? owner_on_cpu(owner) : !realtime_task(current); + bool ret = owner ? owner_on_cpu(owner) : !rt_or_dl_task(current); rcu_read_unlock(); return ret; diff --git a/fs/select.c b/fs/select.c index 8d5c1419416c..73fce145eb72 100644 --- a/fs/select.c +++ b/fs/select.c @@ -82,7 +82,7 @@ u64 select_estimate_accuracy(struct timespec64 *tv) * Realtime tasks get a slack of 0 for obvious reasons. */ - if (realtime_task(current)) + if (rt_or_dl_task(current)) return 0; ktime_get_ts64(&now); diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h index 75859b78d540..b25377b6ea98 100644 --- a/include/linux/ioprio.h +++ b/include/linux/ioprio.h @@ -40,7 +40,7 @@ static inline int task_nice_ioclass(struct task_struct *task) { if (task->policy == SCHED_IDLE) return IOPRIO_CLASS_IDLE; - else if (realtime_task_policy(task)) + else if (rt_or_dl_task_policy(task)) return IOPRIO_CLASS_RT; else return IOPRIO_CLASS_BE; diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h index 91ef1ef2019f..4e3338103654 100644 --- a/include/linux/sched/rt.h +++ b/include/linux/sched/rt.h @@ -11,7 +11,7 @@ static inline bool rt_prio(int prio) return unlikely(prio < MAX_RT_PRIO && prio >= MAX_DL_PRIO); } -static inline bool realtime_prio(int prio) +static inline bool rt_or_dl_prio(int prio) { return unlikely(prio < MAX_RT_PRIO); } @@ -27,19 +27,19 @@ static inline bool rt_task(struct task_struct *p) /* * Returns true if a task has a priority that belongs to RT or DL classes. - * PI-boosted tasks will return true. Use realtime_task_policy() to ignore + * PI-boosted tasks will return true. Use rt_or_dl_task_policy() to ignore * PI-boosted tasks. */ -static inline bool realtime_task(struct task_struct *p) +static inline bool rt_or_dl_task(struct task_struct *p) { - return realtime_prio(p->prio); + return rt_or_dl_prio(p->prio); } /* * Returns true if a task has a policy that belongs to RT or DL classes. * PI-boosted tasks will return false. */ -static inline bool realtime_task_policy(struct task_struct *tsk) +static inline bool rt_or_dl_task_policy(struct task_struct *tsk) { int policy = tsk->policy; diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 55c9dab37f33..c2a530d704b4 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -347,7 +347,7 @@ static __always_inline int __waiter_prio(struct task_struct *task) { int prio = task->prio; - if (!realtime_prio(prio)) + if (!rt_or_dl_prio(prio)) return DEFAULT_PRIO; return prio; @@ -435,7 +435,7 @@ static inline bool rt_mutex_steal(struct rt_mutex_waiter *waiter, * Note that RT tasks are excluded from same priority (lateral) * steals to prevent the introduction of an unbounded latency. */ - if (realtime_prio(waiter->tree.prio)) + if (rt_or_dl_prio(waiter->tree.prio)) return false; return rt_waiter_node_equal(&waiter->tree, &top_waiter->tree); diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index 516174a64fa5..5ded7dff46ef 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -631,7 +631,7 @@ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem, * if it is an RT task or wait in the wait queue * for too long. */ - if (has_handoff || (!realtime_task(waiter->task) && + if (has_handoff || (!rt_or_dl_task(waiter->task) && !time_after(jiffies, waiter->timeout))) return false; @@ -914,7 +914,7 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem) if (owner_state != OWNER_WRITER) { if (need_resched()) break; - if (realtime_task(current) && + if (rt_or_dl_task(current) && (prev_owner_state != OWNER_WRITER)) break; } diff --git a/kernel/locking/ww_mutex.h b/kernel/locking/ww_mutex.h index fa4b416a1f62..76d204b7d29c 100644 --- a/kernel/locking/ww_mutex.h +++ b/kernel/locking/ww_mutex.h @@ -237,7 +237,7 @@ __ww_ctx_less(struct ww_acquire_ctx *a, struct ww_acquire_ctx *b) int a_prio = a->task->prio; int b_prio = b->task->prio; - if (realtime_prio(a_prio) || realtime_prio(b_prio)) { + if (rt_or_dl_prio(a_prio) || rt_or_dl_prio(b_prio)) { if (a_prio > b_prio) return true; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 673cbeb7ad48..ab50100363ca 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -166,7 +166,7 @@ static inline int __task_prio(const struct task_struct *p) if (p->dl_server) return -1; /* deadline */ - if (realtime_prio(p->prio)) /* includes deadline */ + if (rt_or_dl_prio(p->prio)) return p->prio; /* [-1, 99] */ if (p->sched_class == &idle_sched_class) @@ -8590,7 +8590,7 @@ void normalize_rt_tasks(void) schedstat_set(p->stats.sleep_start, 0); schedstat_set(p->stats.block_start, 0); - if (!realtime_task(p)) { + if (!rt_or_dl_task(p)) { /* * Renice negative nice level userspace * tasks back to 0: diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c index 6d60326d73e4..60e70c889d91 100644 --- a/kernel/sched/syscalls.c +++ b/kernel/sched/syscalls.c @@ -57,7 +57,7 @@ static int effective_prio(struct task_struct *p) * keep the priority unchanged. Otherwise, update priority * to the normal priority: */ - if (!realtime_prio(p->prio)) + if (!rt_or_dl_prio(p->prio)) return p->normal_prio; return p->prio; } diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index a1d1d8d886a8..f4be3abbb47b 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1975,7 +1975,7 @@ static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl, * expiry. */ if (IS_ENABLED(CONFIG_PREEMPT_RT)) { - if (realtime_task_policy(current) && !(mode & HRTIMER_MODE_SOFT)) + if (rt_or_dl_task_policy(current) && !(mode & HRTIMER_MODE_SOFT)) mode |= HRTIMER_MODE_HARD; } @@ -2075,7 +2075,7 @@ long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode, u64 slack; slack = current->timer_slack_ns; - if (realtime_task(current)) + if (rt_or_dl_task(current)) slack = 0; hrtimer_init_sleeper_on_stack(&t, clockid, mode); @@ -2280,7 +2280,7 @@ schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta, * Override any slack passed by the user if under * rt contraints. */ - if (realtime_task(current)) + if (rt_or_dl_task(current)) delta = 0; hrtimer_init_sleeper_on_stack(&t, clock_id, mode); diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 1824e17c93c7..ae2ace5e515a 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -547,7 +547,7 @@ probe_wakeup(void *ignore, struct task_struct *p) * - wakeup_dl handles tasks belonging to sched_dl class only. */ if (tracing_dl || (wakeup_dl && !dl_task(p)) || - (wakeup_rt && !realtime_task(p)) || + (wakeup_rt && !rt_or_dl_task(p)) || (!dl_task(p) && (p->prio >= wakeup_prio || p->prio >= current->prio))) return; diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 78dcad729703..7a04cb1918fd 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -418,7 +418,7 @@ static void domain_dirty_limits(struct dirty_throttle_control *dtc) bg_thresh = (bg_ratio * available_memory) / PAGE_SIZE; tsk = current; - if (realtime_task(tsk)) { + if (rt_or_dl_task(tsk)) { bg_thresh += bg_thresh / 4 + global_wb_domain.dirty_limit / 32; thresh += thresh / 4 + global_wb_domain.dirty_limit / 32; } @@ -477,7 +477,7 @@ static unsigned long node_dirty_limit(struct pglist_data *pgdat) else dirty = vm_dirty_ratio * node_memory / 100; - if (realtime_task(tsk)) + if (rt_or_dl_task(tsk)) dirty += dirty / 4; /* diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 54274e468d51..36f8abde3751 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4002,7 +4002,7 @@ gfp_to_alloc_flags(gfp_t gfp_mask, unsigned int order) */ if (alloc_flags & ALLOC_MIN_RESERVE) alloc_flags &= ~ALLOC_CPUSET; - } else if (unlikely(realtime_task(current)) && in_task()) + } else if (unlikely(rt_or_dl_task(current)) && in_task()) alloc_flags |= ALLOC_MIN_RESERVE; alloc_flags = gfp_to_alloc_flags_cma(gfp_mask, alloc_flags); -- cgit v1.2.3 From 6e2fdceffdc6bd7b8ba314a1d1b976721533c8f9 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 26 Jul 2024 14:42:08 -0400 Subject: tracing: Use refcount for trace_event_file reference counter Instead of using an atomic counter for the trace_event_file reference counter, use the refcount interface. It has various checks to make sure the reference counting is correct, and will warn if it detects an error (like refcount_inc() on '0'). Cc: Mathieu Desnoyers Link: https://lore.kernel.org/20240726144208.687cce24@rorschach.local.home Acked-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- include/linux/trace_events.h | 2 +- kernel/trace/trace_events.c | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 9df3e2973626..fed58e54f15e 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -680,7 +680,7 @@ struct trace_event_file { * caching and such. Which is mostly OK ;-) */ unsigned long flags; - atomic_t ref; /* ref count for opened files */ + refcount_t ref; /* ref count for opened files */ atomic_t sm_ref; /* soft-mode reference counter */ atomic_t tm_ref; /* trigger-mode reference counter */ }; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index f08fbaf8cad6..7266ec2a4eea 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -992,18 +992,18 @@ static void remove_subsystem(struct trace_subsystem_dir *dir) void event_file_get(struct trace_event_file *file) { - atomic_inc(&file->ref); + refcount_inc(&file->ref); } void event_file_put(struct trace_event_file *file) { - if (WARN_ON_ONCE(!atomic_read(&file->ref))) { + if (WARN_ON_ONCE(!refcount_read(&file->ref))) { if (file->flags & EVENT_FILE_FL_FREED) kmem_cache_free(file_cachep, file); return; } - if (atomic_dec_and_test(&file->ref)) { + if (refcount_dec_and_test(&file->ref)) { /* Count should only go to zero when it is freed */ if (WARN_ON_ONCE(!(file->flags & EVENT_FILE_FL_FREED))) return; @@ -3003,7 +3003,7 @@ trace_create_new_event(struct trace_event_call *call, atomic_set(&file->tm_ref, 0); INIT_LIST_HEAD(&file->triggers); list_add(&file->list, &tr->events); - event_file_get(file); + refcount_set(&file->ref, 1); return file; } -- cgit v1.2.3 From 58f7e4d7ba32758b861807e77535853cacc1f426 Mon Sep 17 00:00:00 2001 From: Jianhui Zhou <912460177@qq.com> Date: Mon, 5 Aug 2024 19:36:31 +0800 Subject: ring-buffer: Remove unused function ring_buffer_nr_pages() Because ring_buffer_nr_pages() is not an inline function and user accesses buffer->buffers[cpu]->nr_pages directly, the function ring_buffer_nr_pages is removed. Signed-off-by: Jianhui Zhou <912460177@qq.com> Link: https://lore.kernel.org/tencent_F4A7E9AB337F44E0F4B858D07D19EF460708@qq.com Signed-off-by: Steven Rostedt (Google) --- include/linux/ring_buffer.h | 1 - kernel/trace/ring_buffer.c | 12 ------------ 2 files changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 96d2140b471e..fd35d4ec12e1 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -193,7 +193,6 @@ void ring_buffer_set_clock(struct trace_buffer *buffer, void ring_buffer_set_time_stamp_abs(struct trace_buffer *buffer, bool abs); bool ring_buffer_time_stamp_abs(struct trace_buffer *buffer); -size_t ring_buffer_nr_pages(struct trace_buffer *buffer, int cpu); size_t ring_buffer_nr_dirty_pages(struct trace_buffer *buffer, int cpu); struct buffer_data_read_page; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 28853966aa9a..cebd879a30cb 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -692,18 +692,6 @@ u64 ring_buffer_event_time_stamp(struct trace_buffer *buffer, return ts; } -/** - * ring_buffer_nr_pages - get the number of buffer pages in the ring buffer - * @buffer: The ring_buffer to get the number of pages from - * @cpu: The cpu of the ring_buffer to get the number of pages from - * - * Returns the number of pages used by a per_cpu buffer of the ring buffer. - */ -size_t ring_buffer_nr_pages(struct trace_buffer *buffer, int cpu) -{ - return buffer->buffers[cpu]->nr_pages; -} - /** * ring_buffer_nr_dirty_pages - get the number of used pages in the ring buffer * @buffer: The ring_buffer to get the number of pages from -- cgit v1.2.3 From c772a2c690182410642ead740f7a84b3a7544b2b Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 1 Aug 2024 15:05:10 +0300 Subject: net/mlx5: Add IFC related stuff for data direct Add IFC related stuff for data direct. Signed-off-by: Yishai Hadas Link: https://patch.msgid.link/82da7f578a567909bb5858a64ba844fe4cc298fa.1722512548.git.leon@kernel.org Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 51 ++++++++++++++++++++++++++++++++++++++----- 1 file changed, 46 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index cab228cf51c6..970c9d8473ef 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -313,6 +313,7 @@ enum { MLX5_CMD_OP_MODIFY_VHCA_STATE = 0xb0e, MLX5_CMD_OP_SYNC_CRYPTO = 0xb12, MLX5_CMD_OP_ALLOW_OTHER_VHCA_ACCESS = 0xb16, + MLX5_CMD_OPCODE_QUERY_VUID = 0xb22, MLX5_CMD_OP_MAX }; @@ -1885,7 +1886,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_5a0[0x10]; u8 enhanced_cqe_compression[0x1]; - u8 reserved_at_5b1[0x2]; + u8 reserved_at_5b1[0x1]; + u8 crossing_vhca_mkey[0x1]; u8 log_max_dek[0x5]; u8 reserved_at_5b8[0x4]; u8 mini_cqe_resp_stride_index[0x1]; @@ -1954,7 +1956,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 dynamic_msix_table_size[0xc]; u8 reserved_at_740[0xc]; u8 min_dynamic_vf_msix_table_size[0x4]; - u8 reserved_at_750[0x4]; + u8 reserved_at_750[0x2]; + u8 data_direct[0x1]; + u8 reserved_at_753[0x1]; u8 max_dynamic_vf_msix_table_size[0xc]; u8 reserved_at_760[0x3]; @@ -1982,7 +1986,9 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 reserved_at_0[0x80]; u8 migratable[0x1]; - u8 reserved_at_81[0x1f]; + u8 reserved_at_81[0x11]; + u8 query_vuid[0x1]; + u8 reserved_at_93[0xd]; u8 max_reformat_insert_size[0x8]; u8 max_reformat_insert_offset[0x8]; @@ -4154,6 +4160,7 @@ enum { MLX5_MKC_ACCESS_MODE_KSM = 0x3, MLX5_MKC_ACCESS_MODE_SW_ICM = 0x4, MLX5_MKC_ACCESS_MODE_MEMIC = 0x5, + MLX5_MKC_ACCESS_MODE_CROSSING = 0x6, }; struct mlx5_ifc_mkc_bits { @@ -4196,7 +4203,10 @@ struct mlx5_ifc_mkc_bits { u8 bsf_octword_size[0x20]; - u8 reserved_at_120[0x80]; + u8 reserved_at_120[0x60]; + + u8 crossing_target_vhca_id[0x10]; + u8 reserved_at_190[0x10]; u8 translations_octword_size[0x20]; @@ -5124,6 +5134,36 @@ struct mlx5_ifc_query_vport_state_out_bits { u8 state[0x4]; }; +struct mlx5_ifc_array1024_auto_bits { + u8 array1024_auto[32][0x20]; +}; + +struct mlx5_ifc_query_vuid_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x40]; + + u8 query_vfs_vuid[0x1]; + u8 data_direct[0x1]; + u8 reserved_at_62[0xe]; + u8 vhca_id[0x10]; +}; + +struct mlx5_ifc_query_vuid_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x1a0]; + + u8 reserved_at_1e0[0x10]; + u8 num_of_entries[0x10]; + + struct mlx5_ifc_array1024_auto_bits vuid[]; +}; + enum { MLX5_VPORT_STATE_OP_MOD_VNIC_VPORT = 0x0, MLX5_VPORT_STATE_OP_MOD_ESW_VPORT = 0x1, @@ -8989,7 +9029,8 @@ struct mlx5_ifc_create_mkey_in_bits { u8 pg_access[0x1]; u8 mkey_umem_valid[0x1]; - u8 reserved_at_62[0x1e]; + u8 data_direct[0x1]; + u8 reserved_at_63[0x1d]; struct mlx5_ifc_mkc_bits memory_key_mkey_entry; -- cgit v1.2.3 From a09cdb8f564613769142a60400bb5160864c3269 Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Thu, 8 Aug 2024 12:41:17 +0200 Subject: genirq: Remove unused irq_chip_generic:: {type,polarity}_cache The type_cache and polarity_cache members of struct irq_chip_generic are unused. Remove them both along with their kernel-doc. Found by https://github.com/jirislaby/clang-struct. Signed-off-by: Jiri Slaby (SUSE) Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/all/20240808104118.430670-2-jirislaby@kernel.org --- include/linux/irq.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 1f5dbf1f92c9..00490d6ead65 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -1040,8 +1040,6 @@ struct irq_chip_type { * @irq_base: Interrupt base nr for this chip * @irq_cnt: Number of interrupts handled by this chip * @mask_cache: Cached mask register shared between all chip types - * @type_cache: Cached type register - * @polarity_cache: Cached polarity register * @wake_enabled: Interrupt can wakeup from suspend * @wake_active: Interrupt is marked as an wakeup from suspend source * @num_ct: Number of available irq_chip_type instances (usually 1) @@ -1068,8 +1066,6 @@ struct irq_chip_generic { unsigned int irq_base; unsigned int irq_cnt; u32 mask_cache; - u32 type_cache; - u32 polarity_cache; u32 wake_enabled; u32 wake_active; unsigned int num_ct; -- cgit v1.2.3 From 60029162a0458832ab2bcfc6fd4986bfd9ca0f55 Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Thu, 8 Aug 2024 12:41:18 +0200 Subject: genirq: Remove irq_chip_regs:: Polarity The polarity member of struct irq_chip_regs is unused. Remove it along with its kernel-doc. Found by https://github.com/jirislaby/clang-struct. Signed-off-by: Jiri Slaby (SUSE) Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/all/20240808104118.430670-3-jirislaby@kernel.org --- include/linux/irq.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 00490d6ead65..fa711f80957b 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -991,7 +991,6 @@ void irq_init_desc(unsigned int irq); * @ack: Ack register offset to reg_base * @eoi: Eoi register offset to reg_base * @type: Type configuration register offset to reg_base - * @polarity: Polarity configuration register offset to reg_base */ struct irq_chip_regs { unsigned long enable; @@ -1000,7 +999,6 @@ struct irq_chip_regs { unsigned long ack; unsigned long eoi; unsigned long type; - unsigned long polarity; }; /** -- cgit v1.2.3 From b54de55990b0467538c6bb33523b28816384958a Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Wed, 7 Aug 2024 17:06:12 +0100 Subject: net: ethtool: fix off-by-one error in max RSS context IDs Both ethtool_ops.rxfh_max_context_id and the default value used when it's not specified are supposed to be exclusive maxima (the former is documented as such; the latter, U32_MAX, cannot be used as an ID since it equals ETH_RXFH_CONTEXT_ALLOC), but xa_alloc() expects an inclusive maximum. Subtract one from 'limit' to produce an inclusive maximum, and pass that to xa_alloc(). Increase bnxt's max by one to prevent a (very minor) regression, as BNXT_MAX_ETH_RSS_CTX is an inclusive max. This is safe since bnxt is not actually hard-limited; BNXT_MAX_ETH_RSS_CTX is just a leftover from old driver code that managed context IDs itself. Rename rxfh_max_context_id to rxfh_max_num_contexts to make its semantics (hopefully) more obvious. Fixes: 847a8ab18676 ("net: ethtool: let the core choose RSS context IDs") Signed-off-by: Edward Cree Link: https://patch.msgid.link/5a2d11a599aa5b0cc6141072c01accfb7758650c.1723045898.git.ecree.xilinx@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 2 +- include/linux/ethtool.h | 10 +++++----- net/ethtool/ioctl.c | 5 +++-- 3 files changed, 9 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index ab8e3f197e7b..9dadc89378f0 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -5290,7 +5290,7 @@ void bnxt_ethtool_free(struct bnxt *bp) const struct ethtool_ops bnxt_ethtool_ops = { .cap_link_lanes_supported = 1, .cap_rss_ctx_supported = 1, - .rxfh_max_context_id = BNXT_MAX_ETH_RSS_CTX, + .rxfh_max_num_contexts = BNXT_MAX_ETH_RSS_CTX + 1, .rxfh_indir_space = BNXT_MAX_RSS_TABLE_ENTRIES_P5, .rxfh_priv_size = sizeof(struct bnxt_rss_ctx), .supported_coalesce_params = ETHTOOL_COALESCE_USECS | diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 303fda54ef17..989c94eddb2b 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -736,10 +736,10 @@ struct kernel_ethtool_ts_info { * @rxfh_key_space: same as @rxfh_indir_space, but for the key. * @rxfh_priv_size: size of the driver private data area the core should * allocate for an RSS context (in &struct ethtool_rxfh_context). - * @rxfh_max_context_id: maximum (exclusive) supported RSS context ID. If this - * is zero then the core may choose any (nonzero) ID, otherwise the core - * will only use IDs strictly less than this value, as the @rss_context - * argument to @create_rxfh_context and friends. + * @rxfh_max_num_contexts: maximum (exclusive) supported RSS context ID. + * If this is zero then the core may choose any (nonzero) ID, otherwise + * the core will only use IDs strictly less than this value, as the + * @rss_context argument to @create_rxfh_context and friends. * @supported_coalesce_params: supported types of interrupt coalescing. * @supported_ring_params: supported ring params. * @get_drvinfo: Report driver/device information. Modern drivers no @@ -954,7 +954,7 @@ struct ethtool_ops { u32 rxfh_indir_space; u16 rxfh_key_space; u16 rxfh_priv_size; - u32 rxfh_max_context_id; + u32 rxfh_max_num_contexts; u32 supported_coalesce_params; u32 supported_ring_params; void (*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *); diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 8ca13208d240..a8e276ecf723 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1449,12 +1449,13 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, } if (ops->create_rxfh_context) { - u32 limit = ops->rxfh_max_context_id ?: U32_MAX; + u32 limit = ops->rxfh_max_num_contexts ?: U32_MAX; u32 ctx_id; /* driver uses new API, core allocates ID */ ret = xa_alloc(&dev->ethtool->rss_ctx, &ctx_id, ctx, - XA_LIMIT(1, limit), GFP_KERNEL_ACCOUNT); + XA_LIMIT(1, limit - 1), + GFP_KERNEL_ACCOUNT); if (ret < 0) { kfree(ctx); goto out; -- cgit v1.2.3 From 5819e464a17587e6830cfab05f3e91a9a8753a41 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Thu, 8 Aug 2024 14:08:08 +1000 Subject: cpumask: Fix crash on updating CPU enabled mask The CPU enabled mask instead of the CPU possible mask should be used by set_cpu_enabled(). Otherwise, we run into crash due to write to the read-only CPU possible mask when vCPU is hot added on ARM64. (qemu) device_add host-arm-cpu,id=cpu1,socket-id=1 Unable to handle kernel write to read-only memory at virtual address ffff800080fa7190 : Call trace: register_cpu+0x1a4/0x2e8 arch_register_cpu+0x84/0xd8 acpi_processor_add+0x480/0x5b0 acpi_bus_attach+0x1c4/0x300 acpi_dev_for_one_check+0x3c/0x50 device_for_each_child+0x68/0xc8 acpi_dev_for_each_child+0x48/0x80 acpi_bus_attach+0x84/0x300 acpi_bus_scan+0x74/0x220 acpi_scan_rescan_bus+0x54/0x88 acpi_device_hotplug+0x208/0x478 acpi_hotplug_work_fn+0x2c/0x50 process_one_work+0x15c/0x3c0 worker_thread+0x2ec/0x400 kthread+0x120/0x130 ret_from_fork+0x10/0x20 Fix it by passing the CPU enabled mask instead of the CPU possible mask to set_cpu_enabled(). Fixes: 51c4767503d5 ("Merge tag 'bitmap-6.11-rc1' of https://github.com:/norov/linux") Signed-off-by: Gavin Shan Reviewed-by: Jonathan Cameron Signed-off-by: Yury Norov --- include/linux/cpumask.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 801a7e524113..53158de44b83 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -1037,7 +1037,7 @@ void init_cpu_online(const struct cpumask *src); assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val)) #define set_cpu_possible(cpu, possible) assign_cpu((cpu), &__cpu_possible_mask, (possible)) -#define set_cpu_enabled(cpu, enabled) assign_cpu((cpu), &__cpu_possible_mask, (enabled)) +#define set_cpu_enabled(cpu, enabled) assign_cpu((cpu), &__cpu_enabled_mask, (enabled)) #define set_cpu_present(cpu, present) assign_cpu((cpu), &__cpu_present_mask, (present)) #define set_cpu_active(cpu, active) assign_cpu((cpu), &__cpu_active_mask, (active)) #define set_cpu_dying(cpu, dying) assign_cpu((cpu), &__cpu_dying_mask, (dying)) -- cgit v1.2.3 From 09612576046a3cd29bd2b2b88c5813b1dfe96775 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Wed, 7 Aug 2024 14:22:26 +0200 Subject: net: sungem_phy: Constify struct mii_phy_def 'struct mii_phy_def' are not modified in this driver. Constifying these structures moves some data to a read-only section, so increase overall security. While at it fix the checkpatch warning related to this patch (some missing newlines and spaces around *) On a x86_64, with allmodconfig: Before: ====== 27709 928 0 28637 6fdd drivers/net/sungem_phy.o After: ===== text data bss dec hex filename 28157 476 0 28633 6fd9 drivers/net/sungem_phy.o Signed-off-by: Christophe JAILLET Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/54c3b30930f80f4895e6fa2f4234714fdea4ef4e.1723033266.git.christophe.jaillet@wanadoo.fr Signed-off-by: Jakub Kicinski --- drivers/net/sungem_phy.c | 35 +++++++++++++++++++---------------- include/linux/sungem_phy.h | 2 +- 2 files changed, 20 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/sungem_phy.c b/drivers/net/sungem_phy.c index d591e33268e5..55aa8d0c8e1f 100644 --- a/drivers/net/sungem_phy.c +++ b/drivers/net/sungem_phy.c @@ -893,7 +893,7 @@ static const struct mii_phy_ops bcm5201_phy_ops = { .read_link = genmii_read_link, }; -static struct mii_phy_def bcm5201_phy_def = { +static const struct mii_phy_def bcm5201_phy_def = { .phy_id = 0x00406210, .phy_id_mask = 0xfffffff0, .name = "BCM5201", @@ -912,7 +912,7 @@ static const struct mii_phy_ops bcm5221_phy_ops = { .read_link = genmii_read_link, }; -static struct mii_phy_def bcm5221_phy_def = { +static const struct mii_phy_def bcm5221_phy_def = { .phy_id = 0x004061e0, .phy_id_mask = 0xfffffff0, .name = "BCM5221", @@ -930,7 +930,8 @@ static const struct mii_phy_ops bcm5241_phy_ops = { .poll_link = genmii_poll_link, .read_link = genmii_read_link, }; -static struct mii_phy_def bcm5241_phy_def = { + +static const struct mii_phy_def bcm5241_phy_def = { .phy_id = 0x0143bc30, .phy_id_mask = 0xfffffff0, .name = "BCM5241", @@ -949,7 +950,7 @@ static const struct mii_phy_ops bcm5400_phy_ops = { .read_link = bcm54xx_read_link, }; -static struct mii_phy_def bcm5400_phy_def = { +static const struct mii_phy_def bcm5400_phy_def = { .phy_id = 0x00206040, .phy_id_mask = 0xfffffff0, .name = "BCM5400", @@ -968,7 +969,7 @@ static const struct mii_phy_ops bcm5401_phy_ops = { .read_link = bcm54xx_read_link, }; -static struct mii_phy_def bcm5401_phy_def = { +static const struct mii_phy_def bcm5401_phy_def = { .phy_id = 0x00206050, .phy_id_mask = 0xfffffff0, .name = "BCM5401", @@ -987,7 +988,7 @@ static const struct mii_phy_ops bcm5411_phy_ops = { .read_link = bcm54xx_read_link, }; -static struct mii_phy_def bcm5411_phy_def = { +static const struct mii_phy_def bcm5411_phy_def = { .phy_id = 0x00206070, .phy_id_mask = 0xfffffff0, .name = "BCM5411", @@ -1007,7 +1008,7 @@ static const struct mii_phy_ops bcm5421_phy_ops = { .enable_fiber = bcm5421_enable_fiber, }; -static struct mii_phy_def bcm5421_phy_def = { +static const struct mii_phy_def bcm5421_phy_def = { .phy_id = 0x002060e0, .phy_id_mask = 0xfffffff0, .name = "BCM5421", @@ -1026,7 +1027,7 @@ static const struct mii_phy_ops bcm5421k2_phy_ops = { .read_link = bcm54xx_read_link, }; -static struct mii_phy_def bcm5421k2_phy_def = { +static const struct mii_phy_def bcm5421k2_phy_def = { .phy_id = 0x002062e0, .phy_id_mask = 0xfffffff0, .name = "BCM5421-K2", @@ -1045,7 +1046,7 @@ static const struct mii_phy_ops bcm5461_phy_ops = { .enable_fiber = bcm5461_enable_fiber, }; -static struct mii_phy_def bcm5461_phy_def = { +static const struct mii_phy_def bcm5461_phy_def = { .phy_id = 0x002060c0, .phy_id_mask = 0xfffffff0, .name = "BCM5461", @@ -1064,7 +1065,7 @@ static const struct mii_phy_ops bcm5462V_phy_ops = { .read_link = bcm54xx_read_link, }; -static struct mii_phy_def bcm5462V_phy_def = { +static const struct mii_phy_def bcm5462V_phy_def = { .phy_id = 0x002060d0, .phy_id_mask = 0xfffffff0, .name = "BCM5462-Vesta", @@ -1094,7 +1095,7 @@ static const struct mii_phy_ops marvell88e1111_phy_ops = { /* two revs in darwin for the 88e1101 ... I could use a datasheet * to get the proper names... */ -static struct mii_phy_def marvell88e1101v1_phy_def = { +static const struct mii_phy_def marvell88e1101v1_phy_def = { .phy_id = 0x01410c20, .phy_id_mask = 0xfffffff0, .name = "Marvell 88E1101v1", @@ -1102,7 +1103,8 @@ static struct mii_phy_def marvell88e1101v1_phy_def = { .magic_aneg = 1, .ops = &marvell88e1101_phy_ops }; -static struct mii_phy_def marvell88e1101v2_phy_def = { + +static const struct mii_phy_def marvell88e1101v2_phy_def = { .phy_id = 0x01410c60, .phy_id_mask = 0xfffffff0, .name = "Marvell 88E1101v2", @@ -1110,7 +1112,8 @@ static struct mii_phy_def marvell88e1101v2_phy_def = { .magic_aneg = 1, .ops = &marvell88e1101_phy_ops }; -static struct mii_phy_def marvell88e1111_phy_def = { + +static const struct mii_phy_def marvell88e1111_phy_def = { .phy_id = 0x01410cc0, .phy_id_mask = 0xfffffff0, .name = "Marvell 88E1111", @@ -1127,7 +1130,7 @@ static const struct mii_phy_ops generic_phy_ops = { .read_link = genmii_read_link }; -static struct mii_phy_def genmii_phy_def = { +static const struct mii_phy_def genmii_phy_def = { .phy_id = 0x00000000, .phy_id_mask = 0x00000000, .name = "Generic MII", @@ -1136,7 +1139,7 @@ static struct mii_phy_def genmii_phy_def = { .ops = &generic_phy_ops }; -static struct mii_phy_def* mii_phy_table[] = { +static const struct mii_phy_def *mii_phy_table[] = { &bcm5201_phy_def, &bcm5221_phy_def, &bcm5241_phy_def, @@ -1156,9 +1159,9 @@ static struct mii_phy_def* mii_phy_table[] = { int sungem_phy_probe(struct mii_phy *phy, int mii_id) { + const struct mii_phy_def *def; int rc; u32 id; - struct mii_phy_def* def; int i; /* We do not reset the mii_phy structure as the driver diff --git a/include/linux/sungem_phy.h b/include/linux/sungem_phy.h index c505f30e8b68..eecc7eb63bfb 100644 --- a/include/linux/sungem_phy.h +++ b/include/linux/sungem_phy.h @@ -40,7 +40,7 @@ enum { /* An instance of a PHY, partially borrowed from mii_if_info */ struct mii_phy { - struct mii_phy_def* def; + const struct mii_phy_def *def; u32 advertising; int mii_id; -- cgit v1.2.3 From 5fcf329676cf9d132842d9871f83a091c32f3bfc Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 19 Jul 2024 13:41:50 +0200 Subject: fs: add put_mnt_ns() cleanup helper Add a simple helper to put a mount namespace reference. Link: https://lore.kernel.org/r/20240719-work-mount-namespace-v1-3-834113cab0d2@kernel.org Reviewed-by: Josef Bacik Reviewed-by: Jeff Layton Signed-off-by: Christian Brauner --- include/linux/mnt_namespace.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mnt_namespace.h b/include/linux/mnt_namespace.h index 8f882f5881e8..70b366b64816 100644 --- a/include/linux/mnt_namespace.h +++ b/include/linux/mnt_namespace.h @@ -3,6 +3,9 @@ #define _NAMESPACE_H_ #ifdef __KERNEL__ +#include +#include + struct mnt_namespace; struct fs_struct; struct user_namespace; @@ -11,6 +14,7 @@ struct ns_common; extern struct mnt_namespace *copy_mnt_ns(unsigned long, struct mnt_namespace *, struct user_namespace *, struct fs_struct *); extern void put_mnt_ns(struct mnt_namespace *ns); +DEFINE_FREE(put_mnt_ns, struct mnt_namespace *, if (!IS_ERR_OR_NULL(_T)) put_mnt_ns(_T)) extern struct ns_common *from_mnt_ns(struct mnt_namespace *); extern const struct file_operations proc_mounts_operations; -- cgit v1.2.3 From 257b1c2c78c25643526609dee0c15f1544eb3252 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 19 Jul 2024 13:41:51 +0200 Subject: file: add fput() cleanup helper Add a simple helper to put a file reference. Link: https://lore.kernel.org/r/20240719-work-mount-namespace-v1-4-834113cab0d2@kernel.org Reviewed-by: Josef Bacik Reviewed-by: Jeff Layton Signed-off-by: Christian Brauner --- include/linux/file.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/file.h b/include/linux/file.h index 237931f20739..d1e768b06069 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -11,6 +11,7 @@ #include #include #include +#include struct file; @@ -96,6 +97,7 @@ extern void put_unused_fd(unsigned int fd); DEFINE_CLASS(get_unused_fd, int, if (_T >= 0) put_unused_fd(_T), get_unused_fd_flags(flags), unsigned flags) +DEFINE_FREE(fput, struct file *, if (!IS_ERR_OR_NULL(_T)) fput(_T)) /* * take_fd() will take care to set @fd to -EBADF ensuring that -- cgit v1.2.3 From 7ff7509fa52397455e04bd44982e9dfbbd19457f Mon Sep 17 00:00:00 2001 From: Philipp Stanner Date: Mon, 29 Jul 2024 11:36:26 +0200 Subject: PCI: Make pcim_request_region() a public function pcim_request_region() is the managed counterpart of pci_request_region(). It is currently only used internally for PCI. It can be useful for a number of drivers and exporting it is a step towards deprecating more complicated functions. Make pcim_request_region() a public function. Link: https://lore.kernel.org/r/20240729093625.17561-4-pstanner@redhat.com Signed-off-by: Philipp Stanner Signed-off-by: Bjorn Helgaas Tested-by: Hans de Goede Reviewed-by: Hans de Goede Acked-by: Hans de Goede --- drivers/pci/devres.c | 1 + drivers/pci/pci.h | 2 -- include/linux/pci.h | 1 + 3 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/devres.c b/drivers/pci/devres.c index 3780a9f9ec00..0127ca58c6e5 100644 --- a/drivers/pci/devres.c +++ b/drivers/pci/devres.c @@ -863,6 +863,7 @@ int pcim_request_region(struct pci_dev *pdev, int bar, const char *name) { return _pcim_request_region(pdev, bar, name, 0); } +EXPORT_SYMBOL(pcim_request_region); /** * pcim_request_region_exclusive - Request a PCI BAR exclusively diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 79c8398f3938..2fe6055a334d 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -887,8 +887,6 @@ static inline pci_power_t mid_pci_get_power_state(struct pci_dev *pdev) #endif int pcim_intx(struct pci_dev *dev, int enable); - -int pcim_request_region(struct pci_dev *pdev, int bar, const char *name); int pcim_request_region_exclusive(struct pci_dev *pdev, int bar, const char *name); void pcim_release_region(struct pci_dev *pdev, int bar); diff --git a/include/linux/pci.h b/include/linux/pci.h index 4cf89a4b4cbc..4246cb790c7b 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2292,6 +2292,7 @@ static inline void pci_fixup_device(enum pci_fixup_pass pass, void __iomem *pcim_iomap(struct pci_dev *pdev, int bar, unsigned long maxlen); void pcim_iounmap(struct pci_dev *pdev, void __iomem *addr); void __iomem * const *pcim_iomap_table(struct pci_dev *pdev); +int pcim_request_region(struct pci_dev *pdev, int bar, const char *name); int pcim_iomap_regions(struct pci_dev *pdev, int mask, const char *name); int pcim_iomap_regions_request_all(struct pci_dev *pdev, int mask, const char *name); -- cgit v1.2.3 From d140f80f603584d8282817994c0c6241e736bef4 Mon Sep 17 00:00:00 2001 From: Philipp Stanner Date: Wed, 7 Aug 2024 10:30:18 +0200 Subject: PCI: Deprecate pcim_iomap_regions() in favor of pcim_iomap_region() pcim_iomap_regions() is a complicated function that uses a bit mask to determine the BARs the user wishes to request and ioremap. Almost all users only ever set a single bit in that mask, making that mechanism questionable. pcim_iomap_region() is now available as a more simple replacement. Make pcim_iomap_region() a public function. Mark pcim_iomap_regions() as deprecated. Link: https://lore.kernel.org/r/20240807083018.8734-2-pstanner@redhat.com Signed-off-by: Philipp Stanner Signed-off-by: Bjorn Helgaas --- drivers/pci/devres.c | 8 ++++++-- include/linux/pci.h | 2 ++ 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/devres.c b/drivers/pci/devres.c index 0127ca58c6e5..b97589e99fad 100644 --- a/drivers/pci/devres.c +++ b/drivers/pci/devres.c @@ -728,7 +728,7 @@ EXPORT_SYMBOL(pcim_iounmap); * Mapping and region will get automatically released on driver detach. If * desired, release manually only with pcim_iounmap_region(). */ -static void __iomem *pcim_iomap_region(struct pci_dev *pdev, int bar, +void __iomem *pcim_iomap_region(struct pci_dev *pdev, int bar, const char *name) { int ret; @@ -761,6 +761,7 @@ err_region: return IOMEM_ERR_PTR(ret); } +EXPORT_SYMBOL(pcim_iomap_region); /** * pcim_iounmap_region - Unmap and release a PCI BAR @@ -783,7 +784,7 @@ static void pcim_iounmap_region(struct pci_dev *pdev, int bar) } /** - * pcim_iomap_regions - Request and iomap PCI BARs + * pcim_iomap_regions - Request and iomap PCI BARs (DEPRECATED) * @pdev: PCI device to map IO resources for * @mask: Mask of BARs to request and iomap * @name: Name associated with the requests @@ -791,6 +792,9 @@ static void pcim_iounmap_region(struct pci_dev *pdev, int bar) * Returns: 0 on success, negative error code on failure. * * Request and iomap regions specified by @mask. + * + * This function is DEPRECATED. Do not use it in new code. + * Use pcim_iomap_region() instead. */ int pcim_iomap_regions(struct pci_dev *pdev, int mask, const char *name) { diff --git a/include/linux/pci.h b/include/linux/pci.h index 4246cb790c7b..aa9ef7890c50 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2290,6 +2290,8 @@ static inline void pci_fixup_device(enum pci_fixup_pass pass, #endif void __iomem *pcim_iomap(struct pci_dev *pdev, int bar, unsigned long maxlen); +void __iomem *pcim_iomap_region(struct pci_dev *pdev, int bar, + const char *name); void pcim_iounmap(struct pci_dev *pdev, void __iomem *addr); void __iomem * const *pcim_iomap_table(struct pci_dev *pdev); int pcim_request_region(struct pci_dev *pdev, int bar, const char *name); -- cgit v1.2.3 From 70114e7f7585ef078c2b7033ee14218f95f55e22 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Thu, 8 Aug 2024 15:34:02 +0300 Subject: irqdomain: Simplify simple and legacy domain creation irq_domain_create_simple() and irq_domain_create_legacy() use __irq_domain_instantiate(), but have extra handling of allocating interrupt descriptors and associating interrupts in them. Some of that is duplicated. There are also call sites which have conditonals to invoke different interrupt domain creator functions, where one of them is usually irq_domain_create_legacy(). Alternatively they associate the interrupts for the legacy case after creating the domain. Moving the extra logic of irq_domain_create_simple()/legacy() into __irq_domain_instantiate() allows to consolidate that. Introduce hwirq_base and virq_base members in the irq_domain_info structure, which allows to transport the required information and add the conditional interrupt descriptor allocation and interrupt association into __irq_domain_instantiate(). This reduces irq_domain_create_legacy() and irq_domain_create_simple() to trivial wrappers which fill in the info structure and allows call sites which must support the legacy case along with more modern mechanism to select the domain type via the parameters of the info struct. [ tglx: Massaged change log ] Suggested-by: Thomas Gleixner Signed-off-by: Matti Vaittinen Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/all/32d07bd79eb2b5416e24da9e9e8fe5955423dcf9.1723120028.git.mazziesaccount@gmail.com --- include/linux/irqdomain.h | 5 ++++ kernel/irq/irqdomain.c | 74 ++++++++++++++++++++++++++--------------------- 2 files changed, 46 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index de6105f68fec..bfcffa2c7047 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -291,6 +291,9 @@ struct irq_domain_chip_generic_info; * @hwirq_max: Maximum number of interrupts supported by controller * @direct_max: Maximum value of direct maps; * Use ~0 for no limit; 0 for no direct mapping + * @hwirq_base: The first hardware interrupt number (legacy domains only) + * @virq_base: The first Linux interrupt number for legacy domains to + * immediately associate the interrupts after domain creation * @bus_token: Domain bus token * @ops: Domain operation callbacks * @host_data: Controller private data pointer @@ -307,6 +310,8 @@ struct irq_domain_info { unsigned int size; irq_hw_number_t hwirq_max; int direct_max; + unsigned int hwirq_base; + unsigned int virq_base; enum irq_domain_bus_token bus_token; const struct irq_domain_ops *ops; void *host_data; diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index cea8f6874b1f..7625e424f85a 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -267,13 +267,20 @@ static void irq_domain_free(struct irq_domain *domain) kfree(domain); } -/** - * irq_domain_instantiate() - Instantiate a new irq domain data structure - * @info: Domain information pointer pointing to the information for this domain - * - * Return: A pointer to the instantiated irq domain or an ERR_PTR value. - */ -struct irq_domain *irq_domain_instantiate(const struct irq_domain_info *info) +static void irq_domain_instantiate_descs(const struct irq_domain_info *info) +{ + if (!IS_ENABLED(CONFIG_SPARSE_IRQ)) + return; + + if (irq_alloc_descs(info->virq_base, info->virq_base, info->size, + of_node_to_nid(to_of_node(info->fwnode))) < 0) { + pr_info("Cannot allocate irq_descs @ IRQ%d, assuming pre-allocated\n", + info->virq_base); + } +} + +static struct irq_domain *__irq_domain_instantiate(const struct irq_domain_info *info, + bool cond_alloc_descs) { struct irq_domain *domain; int err; @@ -306,6 +313,15 @@ struct irq_domain *irq_domain_instantiate(const struct irq_domain_info *info) __irq_domain_publish(domain); + if (cond_alloc_descs && info->virq_base > 0) + irq_domain_instantiate_descs(info); + + /* Legacy interrupt domains have a fixed Linux interrupt number */ + if (info->virq_base > 0) { + irq_domain_associate_many(domain, info->virq_base, info->hwirq_base, + info->size - info->hwirq_base); + } + return domain; err_domain_gc_remove: @@ -315,6 +331,17 @@ err_domain_free: irq_domain_free(domain); return ERR_PTR(err); } + +/** + * irq_domain_instantiate() - Instantiate a new irq domain data structure + * @info: Domain information pointer pointing to the information for this domain + * + * Return: A pointer to the instantiated irq domain or an ERR_PTR value. + */ +struct irq_domain *irq_domain_instantiate(const struct irq_domain_info *info) +{ + return __irq_domain_instantiate(info, false); +} EXPORT_SYMBOL_GPL(irq_domain_instantiate); /** @@ -413,28 +440,13 @@ struct irq_domain *irq_domain_create_simple(struct fwnode_handle *fwnode, .fwnode = fwnode, .size = size, .hwirq_max = size, + .virq_base = first_irq, .ops = ops, .host_data = host_data, }; - struct irq_domain *domain; - - domain = irq_domain_instantiate(&info); - if (IS_ERR(domain)) - return NULL; + struct irq_domain *domain = __irq_domain_instantiate(&info, true); - if (first_irq > 0) { - if (IS_ENABLED(CONFIG_SPARSE_IRQ)) { - /* attempt to allocated irq_descs */ - int rc = irq_alloc_descs(first_irq, first_irq, size, - of_node_to_nid(to_of_node(fwnode))); - if (rc < 0) - pr_info("Cannot allocate irq_descs @ IRQ%d, assuming pre-allocated\n", - first_irq); - } - irq_domain_associate_many(domain, first_irq, 0, size); - } - - return domain; + return IS_ERR(domain) ? NULL : domain; } EXPORT_SYMBOL_GPL(irq_domain_create_simple); @@ -476,18 +488,14 @@ struct irq_domain *irq_domain_create_legacy(struct fwnode_handle *fwnode, .fwnode = fwnode, .size = first_hwirq + size, .hwirq_max = first_hwirq + size, + .hwirq_base = first_hwirq, + .virq_base = first_irq, .ops = ops, .host_data = host_data, }; - struct irq_domain *domain; + struct irq_domain *domain = irq_domain_instantiate(&info); - domain = irq_domain_instantiate(&info); - if (IS_ERR(domain)) - return NULL; - - irq_domain_associate_many(domain, first_irq, first_hwirq, size); - - return domain; + return IS_ERR(domain) ? NULL : domain; } EXPORT_SYMBOL_GPL(irq_domain_create_legacy); -- cgit v1.2.3 From 1e7c05292531e5b6bebe409cd531ed4ec0b2ff56 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Thu, 8 Aug 2024 22:23:06 +0200 Subject: irqdomain: Allow giving name suffix for domain Devices can provide multiple interrupt lines. One reason for this is that a device has multiple subfunctions, each providing its own interrupt line. Another reason is that a device can be designed to be used (also) on a system where some of the interrupts can be routed to another processor. A line often further acts as a demultiplex for specific interrupts and has it's respective set of interrupt (status, mask, ack, ...) registers. Regmap supports the handling of these registers and demultiplexing interrupts, but the interrupt domain code ends up assigning the same name for the per interrupt line domains. This causes a naming collision in the debugFS code and leads to confusion, as /proc/interrupts shows two separate interrupts with the same domain name and hardware interrupt number. Instead of adding a workaround in regmap or driver code, allow giving a name suffix for the domain name when the domain is created. Add a name_suffix field in the irq_domain_info structure and make irq_domain_instantiate() use this suffix if it is given when a domain is created. [ tglx: Adopt it to the cleanup patch and fixup the invalid NULL return ] Signed-off-by: Matti Vaittinen Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/all/871q2yvk5x.ffs@tglx --- include/linux/irqdomain.h | 3 +++ kernel/irq/irqdomain.c | 30 +++++++++++++++++++++++------- 2 files changed, 26 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index bfcffa2c7047..e432b6a12a32 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -295,6 +295,8 @@ struct irq_domain_chip_generic_info; * @virq_base: The first Linux interrupt number for legacy domains to * immediately associate the interrupts after domain creation * @bus_token: Domain bus token + * @name_suffix: Optional name suffix to avoid collisions when multiple + * domains are added using same fwnode * @ops: Domain operation callbacks * @host_data: Controller private data pointer * @dgc_info: Geneneric chip information structure pointer used to @@ -313,6 +315,7 @@ struct irq_domain_info { unsigned int hwirq_base; unsigned int virq_base; enum irq_domain_bus_token bus_token; + const char *name_suffix; const struct irq_domain_ops *ops; void *host_data; #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 72ab60187103..01001eb615ec 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -140,11 +140,14 @@ static int alloc_name(struct irq_domain *domain, char *base, enum irq_domain_bus } static int alloc_fwnode_name(struct irq_domain *domain, const struct fwnode_handle *fwnode, - enum irq_domain_bus_token bus_token) + enum irq_domain_bus_token bus_token, const char *suffix) { - char *name = bus_token ? kasprintf(GFP_KERNEL, "%pfw-%d", fwnode, bus_token) : - kasprintf(GFP_KERNEL, "%pfw", fwnode); + const char *sep = suffix ? "-" : ""; + const char *suf = suffix ? : ""; + char *name; + name = bus_token ? kasprintf(GFP_KERNEL, "%pfw-%s%s%d", fwnode, suf, sep, bus_token) : + kasprintf(GFP_KERNEL, "%pfw-%s", fwnode, suf); if (!name) return -ENOMEM; @@ -172,12 +175,25 @@ static int alloc_unknown_name(struct irq_domain *domain, enum irq_domain_bus_tok return 0; } -static int irq_domain_set_name(struct irq_domain *domain, const struct fwnode_handle *fwnode, - enum irq_domain_bus_token bus_token) +static int irq_domain_set_name(struct irq_domain *domain, const struct irq_domain_info *info) { + enum irq_domain_bus_token bus_token = info->bus_token; + const struct fwnode_handle *fwnode = info->fwnode; + if (is_fwnode_irqchip(fwnode)) { struct irqchip_fwid *fwid = container_of(fwnode, struct irqchip_fwid, fwnode); + /* + * The name_suffix is only intended to be used to avoid a name + * collision when multiple domains are created for a single + * device and the name is picked using a real device node. + * (Typical use-case is regmap-IRQ controllers for devices + * providing more than one physical IRQ.) There should be no + * need to use name_suffix with irqchip-fwnode. + */ + if (info->name_suffix) + return -EINVAL; + switch (fwid->type) { case IRQCHIP_FWNODE_NAMED: case IRQCHIP_FWNODE_NAMED_ID: @@ -189,7 +205,7 @@ static int irq_domain_set_name(struct irq_domain *domain, const struct fwnode_ha } } else if (is_of_node(fwnode) || is_acpi_device_node(fwnode) || is_software_node(fwnode)) { - return alloc_fwnode_name(domain, fwnode, bus_token); + return alloc_fwnode_name(domain, fwnode, bus_token, info->name_suffix); } if (domain->name) @@ -215,7 +231,7 @@ static struct irq_domain *__irq_domain_create(const struct irq_domain_info *info if (!domain) return ERR_PTR(-ENOMEM); - err = irq_domain_set_name(domain, info->fwnode, info->bus_token); + err = irq_domain_set_name(domain, info); if (err) { kfree(domain); return ERR_PTR(err); -- cgit v1.2.3 From da4fe6815aca25603944a64b0965310512e867d0 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Fri, 2 Aug 2024 14:09:00 +0800 Subject: Revert "lib/mpi: Introduce ec implementation to MPI library" This reverts commit d58bb7e55a8a65894cc02f27c3e2bf9403e7c40f. It's no longer needed since sm2 has been removed. Signed-off-by: Herbert Xu --- include/linux/mpi.h | 105 ---- lib/crypto/mpi/Makefile | 1 - lib/crypto/mpi/ec.c | 1507 ----------------------------------------------- 3 files changed, 1613 deletions(-) delete mode 100644 lib/crypto/mpi/ec.c (limited to 'include/linux') diff --git a/include/linux/mpi.h b/include/linux/mpi.h index eb0d1c1db208..89b720893e12 100644 --- a/include/linux/mpi.h +++ b/include/linux/mpi.h @@ -157,111 +157,6 @@ void mpi_fdiv_q(MPI quot, MPI dividend, MPI divisor); /*-- mpi-inv.c --*/ int mpi_invm(MPI x, MPI a, MPI n); -/*-- ec.c --*/ - -/* Object to represent a point in projective coordinates */ -struct gcry_mpi_point { - MPI x; - MPI y; - MPI z; -}; - -typedef struct gcry_mpi_point *MPI_POINT; - -/* Models describing an elliptic curve */ -enum gcry_mpi_ec_models { - /* The Short Weierstrass equation is - * y^2 = x^3 + ax + b - */ - MPI_EC_WEIERSTRASS = 0, - /* The Montgomery equation is - * by^2 = x^3 + ax^2 + x - */ - MPI_EC_MONTGOMERY, - /* The Twisted Edwards equation is - * ax^2 + y^2 = 1 + bx^2y^2 - * Note that we use 'b' instead of the commonly used 'd'. - */ - MPI_EC_EDWARDS -}; - -/* Dialects used with elliptic curves */ -enum ecc_dialects { - ECC_DIALECT_STANDARD = 0, - ECC_DIALECT_ED25519, - ECC_DIALECT_SAFECURVE -}; - -/* This context is used with all our EC functions. */ -struct mpi_ec_ctx { - enum gcry_mpi_ec_models model; /* The model describing this curve. */ - enum ecc_dialects dialect; /* The ECC dialect used with the curve. */ - int flags; /* Public key flags (not always used). */ - unsigned int nbits; /* Number of bits. */ - - /* Domain parameters. Note that they may not all be set and if set - * the MPIs may be flagged as constant. - */ - MPI p; /* Prime specifying the field GF(p). */ - MPI a; /* First coefficient of the Weierstrass equation. */ - MPI b; /* Second coefficient of the Weierstrass equation. */ - MPI_POINT G; /* Base point (generator). */ - MPI n; /* Order of G. */ - unsigned int h; /* Cofactor. */ - - /* The actual key. May not be set. */ - MPI_POINT Q; /* Public key. */ - MPI d; /* Private key. */ - - const char *name; /* Name of the curve. */ - - /* This structure is private to mpi/ec.c! */ - struct { - struct { - unsigned int a_is_pminus3:1; - unsigned int two_inv_p:1; - } valid; /* Flags to help setting the helper vars below. */ - - int a_is_pminus3; /* True if A = P - 3. */ - - MPI two_inv_p; - - mpi_barrett_t p_barrett; - - /* Scratch variables. */ - MPI scratch[11]; - - /* Helper for fast reduction. */ - /* int nist_nbits; /\* If this is a NIST curve, the # of bits. *\/ */ - /* MPI s[10]; */ - /* MPI c; */ - } t; - - /* Curve specific computation routines for the field. */ - void (*addm)(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx); - void (*subm)(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ec); - void (*mulm)(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx); - void (*pow2)(MPI w, const MPI b, struct mpi_ec_ctx *ctx); - void (*mul2)(MPI w, MPI u, struct mpi_ec_ctx *ctx); -}; - -void mpi_ec_init(struct mpi_ec_ctx *ctx, enum gcry_mpi_ec_models model, - enum ecc_dialects dialect, - int flags, MPI p, MPI a, MPI b); -void mpi_ec_deinit(struct mpi_ec_ctx *ctx); -MPI_POINT mpi_point_new(unsigned int nbits); -void mpi_point_release(MPI_POINT p); -void mpi_point_init(MPI_POINT p); -void mpi_point_free_parts(MPI_POINT p); -int mpi_ec_get_affine(MPI x, MPI y, MPI_POINT point, struct mpi_ec_ctx *ctx); -void mpi_ec_add_points(MPI_POINT result, - MPI_POINT p1, MPI_POINT p2, - struct mpi_ec_ctx *ctx); -void mpi_ec_mul_point(MPI_POINT result, - MPI scalar, MPI_POINT point, - struct mpi_ec_ctx *ctx); -int mpi_ec_curve_point(MPI_POINT point, struct mpi_ec_ctx *ctx); - /* inline functions */ /** diff --git a/lib/crypto/mpi/Makefile b/lib/crypto/mpi/Makefile index 6e6ef9a34fe1..477debd7ed50 100644 --- a/lib/crypto/mpi/Makefile +++ b/lib/crypto/mpi/Makefile @@ -13,7 +13,6 @@ mpi-y = \ generic_mpih-rshift.o \ generic_mpih-sub1.o \ generic_mpih-add1.o \ - ec.o \ mpicoder.o \ mpi-add.o \ mpi-bit.o \ diff --git a/lib/crypto/mpi/ec.c b/lib/crypto/mpi/ec.c deleted file mode 100644 index 4781f00982ef..000000000000 --- a/lib/crypto/mpi/ec.c +++ /dev/null @@ -1,1507 +0,0 @@ -/* ec.c - Elliptic Curve functions - * Copyright (C) 2007 Free Software Foundation, Inc. - * Copyright (C) 2013 g10 Code GmbH - * - * This file is part of Libgcrypt. - * - * Libgcrypt is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as - * published by the Free Software Foundation; either version 2.1 of - * the License, or (at your option) any later version. - * - * Libgcrypt is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this program; if not, see . - */ - -#include "mpi-internal.h" -#include "longlong.h" - -#define point_init(a) mpi_point_init((a)) -#define point_free(a) mpi_point_free_parts((a)) - -#define log_error(fmt, ...) pr_err(fmt, ##__VA_ARGS__) -#define log_fatal(fmt, ...) pr_err(fmt, ##__VA_ARGS__) - -#define DIM(v) (sizeof(v)/sizeof((v)[0])) - - -/* Create a new point option. NBITS gives the size in bits of one - * coordinate; it is only used to pre-allocate some resources and - * might also be passed as 0 to use a default value. - */ -MPI_POINT mpi_point_new(unsigned int nbits) -{ - MPI_POINT p; - - (void)nbits; /* Currently not used. */ - - p = kmalloc(sizeof(*p), GFP_KERNEL); - if (p) - mpi_point_init(p); - return p; -} -EXPORT_SYMBOL_GPL(mpi_point_new); - -/* Release the point object P. P may be NULL. */ -void mpi_point_release(MPI_POINT p) -{ - if (p) { - mpi_point_free_parts(p); - kfree(p); - } -} -EXPORT_SYMBOL_GPL(mpi_point_release); - -/* Initialize the fields of a point object. gcry_mpi_point_free_parts - * may be used to release the fields. - */ -void mpi_point_init(MPI_POINT p) -{ - p->x = mpi_new(0); - p->y = mpi_new(0); - p->z = mpi_new(0); -} -EXPORT_SYMBOL_GPL(mpi_point_init); - -/* Release the parts of a point object. */ -void mpi_point_free_parts(MPI_POINT p) -{ - mpi_free(p->x); p->x = NULL; - mpi_free(p->y); p->y = NULL; - mpi_free(p->z); p->z = NULL; -} -EXPORT_SYMBOL_GPL(mpi_point_free_parts); - -/* Set the value from S into D. */ -static void point_set(MPI_POINT d, MPI_POINT s) -{ - mpi_set(d->x, s->x); - mpi_set(d->y, s->y); - mpi_set(d->z, s->z); -} - -static void point_resize(MPI_POINT p, struct mpi_ec_ctx *ctx) -{ - size_t nlimbs = ctx->p->nlimbs; - - mpi_resize(p->x, nlimbs); - p->x->nlimbs = nlimbs; - mpi_resize(p->z, nlimbs); - p->z->nlimbs = nlimbs; - - if (ctx->model != MPI_EC_MONTGOMERY) { - mpi_resize(p->y, nlimbs); - p->y->nlimbs = nlimbs; - } -} - -static void point_swap_cond(MPI_POINT d, MPI_POINT s, unsigned long swap, - struct mpi_ec_ctx *ctx) -{ - mpi_swap_cond(d->x, s->x, swap); - if (ctx->model != MPI_EC_MONTGOMERY) - mpi_swap_cond(d->y, s->y, swap); - mpi_swap_cond(d->z, s->z, swap); -} - - -/* W = W mod P. */ -static void ec_mod(MPI w, struct mpi_ec_ctx *ec) -{ - if (ec->t.p_barrett) - mpi_mod_barrett(w, w, ec->t.p_barrett); - else - mpi_mod(w, w, ec->p); -} - -static void ec_addm(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx) -{ - mpi_add(w, u, v); - ec_mod(w, ctx); -} - -static void ec_subm(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ec) -{ - mpi_sub(w, u, v); - while (w->sign) - mpi_add(w, w, ec->p); - /*ec_mod(w, ec);*/ -} - -static void ec_mulm(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx) -{ - mpi_mul(w, u, v); - ec_mod(w, ctx); -} - -/* W = 2 * U mod P. */ -static void ec_mul2(MPI w, MPI u, struct mpi_ec_ctx *ctx) -{ - mpi_lshift(w, u, 1); - ec_mod(w, ctx); -} - -static void ec_powm(MPI w, const MPI b, const MPI e, - struct mpi_ec_ctx *ctx) -{ - mpi_powm(w, b, e, ctx->p); - /* mpi_abs(w); */ -} - -/* Shortcut for - * ec_powm(B, B, mpi_const(MPI_C_TWO), ctx); - * for easier optimization. - */ -static void ec_pow2(MPI w, const MPI b, struct mpi_ec_ctx *ctx) -{ - /* Using mpi_mul is slightly faster (at least on amd64). */ - /* mpi_powm(w, b, mpi_const(MPI_C_TWO), ctx->p); */ - ec_mulm(w, b, b, ctx); -} - -/* Shortcut for - * ec_powm(B, B, mpi_const(MPI_C_THREE), ctx); - * for easier optimization. - */ -static void ec_pow3(MPI w, const MPI b, struct mpi_ec_ctx *ctx) -{ - mpi_powm(w, b, mpi_const(MPI_C_THREE), ctx->p); -} - -static void ec_invm(MPI x, MPI a, struct mpi_ec_ctx *ctx) -{ - if (!mpi_invm(x, a, ctx->p)) - log_error("ec_invm: inverse does not exist:\n"); -} - -static void mpih_set_cond(mpi_ptr_t wp, mpi_ptr_t up, - mpi_size_t usize, unsigned long set) -{ - mpi_size_t i; - mpi_limb_t mask = ((mpi_limb_t)0) - set; - mpi_limb_t x; - - for (i = 0; i < usize; i++) { - x = mask & (wp[i] ^ up[i]); - wp[i] = wp[i] ^ x; - } -} - -/* Routines for 2^255 - 19. */ - -#define LIMB_SIZE_25519 ((256+BITS_PER_MPI_LIMB-1)/BITS_PER_MPI_LIMB) - -static void ec_addm_25519(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx) -{ - mpi_ptr_t wp, up, vp; - mpi_size_t wsize = LIMB_SIZE_25519; - mpi_limb_t n[LIMB_SIZE_25519]; - mpi_limb_t borrow; - - if (w->nlimbs != wsize || u->nlimbs != wsize || v->nlimbs != wsize) - log_bug("addm_25519: different sizes\n"); - - memset(n, 0, sizeof(n)); - up = u->d; - vp = v->d; - wp = w->d; - - mpihelp_add_n(wp, up, vp, wsize); - borrow = mpihelp_sub_n(wp, wp, ctx->p->d, wsize); - mpih_set_cond(n, ctx->p->d, wsize, (borrow != 0UL)); - mpihelp_add_n(wp, wp, n, wsize); - wp[LIMB_SIZE_25519-1] &= ~((mpi_limb_t)1 << (255 % BITS_PER_MPI_LIMB)); -} - -static void ec_subm_25519(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx) -{ - mpi_ptr_t wp, up, vp; - mpi_size_t wsize = LIMB_SIZE_25519; - mpi_limb_t n[LIMB_SIZE_25519]; - mpi_limb_t borrow; - - if (w->nlimbs != wsize || u->nlimbs != wsize || v->nlimbs != wsize) - log_bug("subm_25519: different sizes\n"); - - memset(n, 0, sizeof(n)); - up = u->d; - vp = v->d; - wp = w->d; - - borrow = mpihelp_sub_n(wp, up, vp, wsize); - mpih_set_cond(n, ctx->p->d, wsize, (borrow != 0UL)); - mpihelp_add_n(wp, wp, n, wsize); - wp[LIMB_SIZE_25519-1] &= ~((mpi_limb_t)1 << (255 % BITS_PER_MPI_LIMB)); -} - -static void ec_mulm_25519(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx) -{ - mpi_ptr_t wp, up, vp; - mpi_size_t wsize = LIMB_SIZE_25519; - mpi_limb_t n[LIMB_SIZE_25519*2]; - mpi_limb_t m[LIMB_SIZE_25519+1]; - mpi_limb_t cy; - int msb; - - (void)ctx; - if (w->nlimbs != wsize || u->nlimbs != wsize || v->nlimbs != wsize) - log_bug("mulm_25519: different sizes\n"); - - up = u->d; - vp = v->d; - wp = w->d; - - mpihelp_mul_n(n, up, vp, wsize); - memcpy(wp, n, wsize * BYTES_PER_MPI_LIMB); - wp[LIMB_SIZE_25519-1] &= ~((mpi_limb_t)1 << (255 % BITS_PER_MPI_LIMB)); - - memcpy(m, n+LIMB_SIZE_25519-1, (wsize+1) * BYTES_PER_MPI_LIMB); - mpihelp_rshift(m, m, LIMB_SIZE_25519+1, (255 % BITS_PER_MPI_LIMB)); - - memcpy(n, m, wsize * BYTES_PER_MPI_LIMB); - cy = mpihelp_lshift(m, m, LIMB_SIZE_25519, 4); - m[LIMB_SIZE_25519] = cy; - cy = mpihelp_add_n(m, m, n, wsize); - m[LIMB_SIZE_25519] += cy; - cy = mpihelp_add_n(m, m, n, wsize); - m[LIMB_SIZE_25519] += cy; - cy = mpihelp_add_n(m, m, n, wsize); - m[LIMB_SIZE_25519] += cy; - - cy = mpihelp_add_n(wp, wp, m, wsize); - m[LIMB_SIZE_25519] += cy; - - memset(m, 0, wsize * BYTES_PER_MPI_LIMB); - msb = (wp[LIMB_SIZE_25519-1] >> (255 % BITS_PER_MPI_LIMB)); - m[0] = (m[LIMB_SIZE_25519] * 2 + msb) * 19; - wp[LIMB_SIZE_25519-1] &= ~((mpi_limb_t)1 << (255 % BITS_PER_MPI_LIMB)); - mpihelp_add_n(wp, wp, m, wsize); - - m[0] = 0; - cy = mpihelp_sub_n(wp, wp, ctx->p->d, wsize); - mpih_set_cond(m, ctx->p->d, wsize, (cy != 0UL)); - mpihelp_add_n(wp, wp, m, wsize); -} - -static void ec_mul2_25519(MPI w, MPI u, struct mpi_ec_ctx *ctx) -{ - ec_addm_25519(w, u, u, ctx); -} - -static void ec_pow2_25519(MPI w, const MPI b, struct mpi_ec_ctx *ctx) -{ - ec_mulm_25519(w, b, b, ctx); -} - -/* Routines for 2^448 - 2^224 - 1. */ - -#define LIMB_SIZE_448 ((448+BITS_PER_MPI_LIMB-1)/BITS_PER_MPI_LIMB) -#define LIMB_SIZE_HALF_448 ((LIMB_SIZE_448+1)/2) - -static void ec_addm_448(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx) -{ - mpi_ptr_t wp, up, vp; - mpi_size_t wsize = LIMB_SIZE_448; - mpi_limb_t n[LIMB_SIZE_448]; - mpi_limb_t cy; - - if (w->nlimbs != wsize || u->nlimbs != wsize || v->nlimbs != wsize) - log_bug("addm_448: different sizes\n"); - - memset(n, 0, sizeof(n)); - up = u->d; - vp = v->d; - wp = w->d; - - cy = mpihelp_add_n(wp, up, vp, wsize); - mpih_set_cond(n, ctx->p->d, wsize, (cy != 0UL)); - mpihelp_sub_n(wp, wp, n, wsize); -} - -static void ec_subm_448(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx) -{ - mpi_ptr_t wp, up, vp; - mpi_size_t wsize = LIMB_SIZE_448; - mpi_limb_t n[LIMB_SIZE_448]; - mpi_limb_t borrow; - - if (w->nlimbs != wsize || u->nlimbs != wsize || v->nlimbs != wsize) - log_bug("subm_448: different sizes\n"); - - memset(n, 0, sizeof(n)); - up = u->d; - vp = v->d; - wp = w->d; - - borrow = mpihelp_sub_n(wp, up, vp, wsize); - mpih_set_cond(n, ctx->p->d, wsize, (borrow != 0UL)); - mpihelp_add_n(wp, wp, n, wsize); -} - -static void ec_mulm_448(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx) -{ - mpi_ptr_t wp, up, vp; - mpi_size_t wsize = LIMB_SIZE_448; - mpi_limb_t n[LIMB_SIZE_448*2]; - mpi_limb_t a2[LIMB_SIZE_HALF_448]; - mpi_limb_t a3[LIMB_SIZE_HALF_448]; - mpi_limb_t b0[LIMB_SIZE_HALF_448]; - mpi_limb_t b1[LIMB_SIZE_HALF_448]; - mpi_limb_t cy; - int i; -#if (LIMB_SIZE_HALF_448 > LIMB_SIZE_448/2) - mpi_limb_t b1_rest, a3_rest; -#endif - - if (w->nlimbs != wsize || u->nlimbs != wsize || v->nlimbs != wsize) - log_bug("mulm_448: different sizes\n"); - - up = u->d; - vp = v->d; - wp = w->d; - - mpihelp_mul_n(n, up, vp, wsize); - - for (i = 0; i < (wsize + 1) / 2; i++) { - b0[i] = n[i]; - b1[i] = n[i+wsize/2]; - a2[i] = n[i+wsize]; - a3[i] = n[i+wsize+wsize/2]; - } - -#if (LIMB_SIZE_HALF_448 > LIMB_SIZE_448/2) - b0[LIMB_SIZE_HALF_448-1] &= ((mpi_limb_t)1UL << 32)-1; - a2[LIMB_SIZE_HALF_448-1] &= ((mpi_limb_t)1UL << 32)-1; - - b1_rest = 0; - a3_rest = 0; - - for (i = (wsize + 1) / 2 - 1; i >= 0; i--) { - mpi_limb_t b1v, a3v; - b1v = b1[i]; - a3v = a3[i]; - b1[i] = (b1_rest << 32) | (b1v >> 32); - a3[i] = (a3_rest << 32) | (a3v >> 32); - b1_rest = b1v & (((mpi_limb_t)1UL << 32)-1); - a3_rest = a3v & (((mpi_limb_t)1UL << 32)-1); - } -#endif - - cy = mpihelp_add_n(b0, b0, a2, LIMB_SIZE_HALF_448); - cy += mpihelp_add_n(b0, b0, a3, LIMB_SIZE_HALF_448); - for (i = 0; i < (wsize + 1) / 2; i++) - wp[i] = b0[i]; -#if (LIMB_SIZE_HALF_448 > LIMB_SIZE_448/2) - wp[LIMB_SIZE_HALF_448-1] &= (((mpi_limb_t)1UL << 32)-1); -#endif - -#if (LIMB_SIZE_HALF_448 > LIMB_SIZE_448/2) - cy = b0[LIMB_SIZE_HALF_448-1] >> 32; -#endif - - cy = mpihelp_add_1(b1, b1, LIMB_SIZE_HALF_448, cy); - cy += mpihelp_add_n(b1, b1, a2, LIMB_SIZE_HALF_448); - cy += mpihelp_add_n(b1, b1, a3, LIMB_SIZE_HALF_448); - cy += mpihelp_add_n(b1, b1, a3, LIMB_SIZE_HALF_448); -#if (LIMB_SIZE_HALF_448 > LIMB_SIZE_448/2) - b1_rest = 0; - for (i = (wsize + 1) / 2 - 1; i >= 0; i--) { - mpi_limb_t b1v = b1[i]; - b1[i] = (b1_rest << 32) | (b1v >> 32); - b1_rest = b1v & (((mpi_limb_t)1UL << 32)-1); - } - wp[LIMB_SIZE_HALF_448-1] |= (b1_rest << 32); -#endif - for (i = 0; i < wsize / 2; i++) - wp[i+(wsize + 1) / 2] = b1[i]; - -#if (LIMB_SIZE_HALF_448 > LIMB_SIZE_448/2) - cy = b1[LIMB_SIZE_HALF_448-1]; -#endif - - memset(n, 0, wsize * BYTES_PER_MPI_LIMB); - -#if (LIMB_SIZE_HALF_448 > LIMB_SIZE_448/2) - n[LIMB_SIZE_HALF_448-1] = cy << 32; -#else - n[LIMB_SIZE_HALF_448] = cy; -#endif - n[0] = cy; - mpihelp_add_n(wp, wp, n, wsize); - - memset(n, 0, wsize * BYTES_PER_MPI_LIMB); - cy = mpihelp_sub_n(wp, wp, ctx->p->d, wsize); - mpih_set_cond(n, ctx->p->d, wsize, (cy != 0UL)); - mpihelp_add_n(wp, wp, n, wsize); -} - -static void ec_mul2_448(MPI w, MPI u, struct mpi_ec_ctx *ctx) -{ - ec_addm_448(w, u, u, ctx); -} - -static void ec_pow2_448(MPI w, const MPI b, struct mpi_ec_ctx *ctx) -{ - ec_mulm_448(w, b, b, ctx); -} - -struct field_table { - const char *p; - - /* computation routines for the field. */ - void (*addm)(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx); - void (*subm)(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx); - void (*mulm)(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx); - void (*mul2)(MPI w, MPI u, struct mpi_ec_ctx *ctx); - void (*pow2)(MPI w, const MPI b, struct mpi_ec_ctx *ctx); -}; - -static const struct field_table field_table[] = { - { - "0x7FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFED", - ec_addm_25519, - ec_subm_25519, - ec_mulm_25519, - ec_mul2_25519, - ec_pow2_25519 - }, - { - "0xFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFE" - "FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF", - ec_addm_448, - ec_subm_448, - ec_mulm_448, - ec_mul2_448, - ec_pow2_448 - }, - { NULL, NULL, NULL, NULL, NULL, NULL }, -}; - -/* Force recomputation of all helper variables. */ -static void mpi_ec_get_reset(struct mpi_ec_ctx *ec) -{ - ec->t.valid.a_is_pminus3 = 0; - ec->t.valid.two_inv_p = 0; -} - -/* Accessor for helper variable. */ -static int ec_get_a_is_pminus3(struct mpi_ec_ctx *ec) -{ - MPI tmp; - - if (!ec->t.valid.a_is_pminus3) { - ec->t.valid.a_is_pminus3 = 1; - tmp = mpi_alloc_like(ec->p); - mpi_sub_ui(tmp, ec->p, 3); - ec->t.a_is_pminus3 = !mpi_cmp(ec->a, tmp); - mpi_free(tmp); - } - - return ec->t.a_is_pminus3; -} - -/* Accessor for helper variable. */ -static MPI ec_get_two_inv_p(struct mpi_ec_ctx *ec) -{ - if (!ec->t.valid.two_inv_p) { - ec->t.valid.two_inv_p = 1; - if (!ec->t.two_inv_p) - ec->t.two_inv_p = mpi_alloc(0); - ec_invm(ec->t.two_inv_p, mpi_const(MPI_C_TWO), ec); - } - return ec->t.two_inv_p; -} - -static const char *const curve25519_bad_points[] = { - "0x7fffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffed", - "0x0000000000000000000000000000000000000000000000000000000000000000", - "0x0000000000000000000000000000000000000000000000000000000000000001", - "0x00b8495f16056286fdb1329ceb8d09da6ac49ff1fae35616aeb8413b7c7aebe0", - "0x57119fd0dd4e22d8868e1c58c45c44045bef839c55b1d0b1248c50a3bc959c5f", - "0x7fffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffec", - "0x7fffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffee", - NULL -}; - -static const char *const curve448_bad_points[] = { - "0xfffffffffffffffffffffffffffffffffffffffffffffffffffffffe" - "ffffffffffffffffffffffffffffffffffffffffffffffffffffffff", - "0x00000000000000000000000000000000000000000000000000000000" - "00000000000000000000000000000000000000000000000000000000", - "0x00000000000000000000000000000000000000000000000000000000" - "00000000000000000000000000000000000000000000000000000001", - "0xfffffffffffffffffffffffffffffffffffffffffffffffffffffffe" - "fffffffffffffffffffffffffffffffffffffffffffffffffffffffe", - "0xffffffffffffffffffffffffffffffffffffffffffffffffffffffff" - "00000000000000000000000000000000000000000000000000000000", - NULL -}; - -static const char *const *bad_points_table[] = { - curve25519_bad_points, - curve448_bad_points, -}; - -static void mpi_ec_coefficient_normalize(MPI a, MPI p) -{ - if (a->sign) { - mpi_resize(a, p->nlimbs); - mpihelp_sub_n(a->d, p->d, a->d, p->nlimbs); - a->nlimbs = p->nlimbs; - a->sign = 0; - } -} - -/* This function initialized a context for elliptic curve based on the - * field GF(p). P is the prime specifying this field, A is the first - * coefficient. CTX is expected to be zeroized. - */ -void mpi_ec_init(struct mpi_ec_ctx *ctx, enum gcry_mpi_ec_models model, - enum ecc_dialects dialect, - int flags, MPI p, MPI a, MPI b) -{ - int i; - static int use_barrett = -1 /* TODO: 1 or -1 */; - - mpi_ec_coefficient_normalize(a, p); - mpi_ec_coefficient_normalize(b, p); - - /* Fixme: Do we want to check some constraints? e.g. a < p */ - - ctx->model = model; - ctx->dialect = dialect; - ctx->flags = flags; - if (dialect == ECC_DIALECT_ED25519) - ctx->nbits = 256; - else - ctx->nbits = mpi_get_nbits(p); - ctx->p = mpi_copy(p); - ctx->a = mpi_copy(a); - ctx->b = mpi_copy(b); - - ctx->d = NULL; - ctx->t.two_inv_p = NULL; - - ctx->t.p_barrett = use_barrett > 0 ? mpi_barrett_init(ctx->p, 0) : NULL; - - mpi_ec_get_reset(ctx); - - if (model == MPI_EC_MONTGOMERY) { - for (i = 0; i < DIM(bad_points_table); i++) { - MPI p_candidate = mpi_scanval(bad_points_table[i][0]); - int match_p = !mpi_cmp(ctx->p, p_candidate); - int j; - - mpi_free(p_candidate); - if (!match_p) - continue; - - for (j = 0; i < DIM(ctx->t.scratch) && bad_points_table[i][j]; j++) - ctx->t.scratch[j] = mpi_scanval(bad_points_table[i][j]); - } - } else { - /* Allocate scratch variables. */ - for (i = 0; i < DIM(ctx->t.scratch); i++) - ctx->t.scratch[i] = mpi_alloc_like(ctx->p); - } - - ctx->addm = ec_addm; - ctx->subm = ec_subm; - ctx->mulm = ec_mulm; - ctx->mul2 = ec_mul2; - ctx->pow2 = ec_pow2; - - for (i = 0; field_table[i].p; i++) { - MPI f_p; - - f_p = mpi_scanval(field_table[i].p); - if (!f_p) - break; - - if (!mpi_cmp(p, f_p)) { - ctx->addm = field_table[i].addm; - ctx->subm = field_table[i].subm; - ctx->mulm = field_table[i].mulm; - ctx->mul2 = field_table[i].mul2; - ctx->pow2 = field_table[i].pow2; - mpi_free(f_p); - - mpi_resize(ctx->a, ctx->p->nlimbs); - ctx->a->nlimbs = ctx->p->nlimbs; - - mpi_resize(ctx->b, ctx->p->nlimbs); - ctx->b->nlimbs = ctx->p->nlimbs; - - for (i = 0; i < DIM(ctx->t.scratch) && ctx->t.scratch[i]; i++) - ctx->t.scratch[i]->nlimbs = ctx->p->nlimbs; - - break; - } - - mpi_free(f_p); - } -} -EXPORT_SYMBOL_GPL(mpi_ec_init); - -void mpi_ec_deinit(struct mpi_ec_ctx *ctx) -{ - int i; - - mpi_barrett_free(ctx->t.p_barrett); - - /* Domain parameter. */ - mpi_free(ctx->p); - mpi_free(ctx->a); - mpi_free(ctx->b); - mpi_point_release(ctx->G); - mpi_free(ctx->n); - - /* The key. */ - mpi_point_release(ctx->Q); - mpi_free(ctx->d); - - /* Private data of ec.c. */ - mpi_free(ctx->t.two_inv_p); - - for (i = 0; i < DIM(ctx->t.scratch); i++) - mpi_free(ctx->t.scratch[i]); -} -EXPORT_SYMBOL_GPL(mpi_ec_deinit); - -/* Compute the affine coordinates from the projective coordinates in - * POINT. Set them into X and Y. If one coordinate is not required, - * X or Y may be passed as NULL. CTX is the usual context. Returns: 0 - * on success or !0 if POINT is at infinity. - */ -int mpi_ec_get_affine(MPI x, MPI y, MPI_POINT point, struct mpi_ec_ctx *ctx) -{ - if (!mpi_cmp_ui(point->z, 0)) - return -1; - - switch (ctx->model) { - case MPI_EC_WEIERSTRASS: /* Using Jacobian coordinates. */ - { - MPI z1, z2, z3; - - z1 = mpi_new(0); - z2 = mpi_new(0); - ec_invm(z1, point->z, ctx); /* z1 = z^(-1) mod p */ - ec_mulm(z2, z1, z1, ctx); /* z2 = z^(-2) mod p */ - - if (x) - ec_mulm(x, point->x, z2, ctx); - - if (y) { - z3 = mpi_new(0); - ec_mulm(z3, z2, z1, ctx); /* z3 = z^(-3) mod p */ - ec_mulm(y, point->y, z3, ctx); - mpi_free(z3); - } - - mpi_free(z2); - mpi_free(z1); - } - return 0; - - case MPI_EC_MONTGOMERY: - { - if (x) - mpi_set(x, point->x); - - if (y) { - log_fatal("%s: Getting Y-coordinate on %s is not supported\n", - "mpi_ec_get_affine", "Montgomery"); - return -1; - } - } - return 0; - - case MPI_EC_EDWARDS: - { - MPI z; - - z = mpi_new(0); - ec_invm(z, point->z, ctx); - - mpi_resize(z, ctx->p->nlimbs); - z->nlimbs = ctx->p->nlimbs; - - if (x) { - mpi_resize(x, ctx->p->nlimbs); - x->nlimbs = ctx->p->nlimbs; - ctx->mulm(x, point->x, z, ctx); - } - if (y) { - mpi_resize(y, ctx->p->nlimbs); - y->nlimbs = ctx->p->nlimbs; - ctx->mulm(y, point->y, z, ctx); - } - - mpi_free(z); - } - return 0; - - default: - return -1; - } -} -EXPORT_SYMBOL_GPL(mpi_ec_get_affine); - -/* RESULT = 2 * POINT (Weierstrass version). */ -static void dup_point_weierstrass(MPI_POINT result, - MPI_POINT point, struct mpi_ec_ctx *ctx) -{ -#define x3 (result->x) -#define y3 (result->y) -#define z3 (result->z) -#define t1 (ctx->t.scratch[0]) -#define t2 (ctx->t.scratch[1]) -#define t3 (ctx->t.scratch[2]) -#define l1 (ctx->t.scratch[3]) -#define l2 (ctx->t.scratch[4]) -#define l3 (ctx->t.scratch[5]) - - if (!mpi_cmp_ui(point->y, 0) || !mpi_cmp_ui(point->z, 0)) { - /* P_y == 0 || P_z == 0 => [1:1:0] */ - mpi_set_ui(x3, 1); - mpi_set_ui(y3, 1); - mpi_set_ui(z3, 0); - } else { - if (ec_get_a_is_pminus3(ctx)) { - /* Use the faster case. */ - /* L1 = 3(X - Z^2)(X + Z^2) */ - /* T1: used for Z^2. */ - /* T2: used for the right term. */ - ec_pow2(t1, point->z, ctx); - ec_subm(l1, point->x, t1, ctx); - ec_mulm(l1, l1, mpi_const(MPI_C_THREE), ctx); - ec_addm(t2, point->x, t1, ctx); - ec_mulm(l1, l1, t2, ctx); - } else { - /* Standard case. */ - /* L1 = 3X^2 + aZ^4 */ - /* T1: used for aZ^4. */ - ec_pow2(l1, point->x, ctx); - ec_mulm(l1, l1, mpi_const(MPI_C_THREE), ctx); - ec_powm(t1, point->z, mpi_const(MPI_C_FOUR), ctx); - ec_mulm(t1, t1, ctx->a, ctx); - ec_addm(l1, l1, t1, ctx); - } - /* Z3 = 2YZ */ - ec_mulm(z3, point->y, point->z, ctx); - ec_mul2(z3, z3, ctx); - - /* L2 = 4XY^2 */ - /* T2: used for Y2; required later. */ - ec_pow2(t2, point->y, ctx); - ec_mulm(l2, t2, point->x, ctx); - ec_mulm(l2, l2, mpi_const(MPI_C_FOUR), ctx); - - /* X3 = L1^2 - 2L2 */ - /* T1: used for L2^2. */ - ec_pow2(x3, l1, ctx); - ec_mul2(t1, l2, ctx); - ec_subm(x3, x3, t1, ctx); - - /* L3 = 8Y^4 */ - /* T2: taken from above. */ - ec_pow2(t2, t2, ctx); - ec_mulm(l3, t2, mpi_const(MPI_C_EIGHT), ctx); - - /* Y3 = L1(L2 - X3) - L3 */ - ec_subm(y3, l2, x3, ctx); - ec_mulm(y3, y3, l1, ctx); - ec_subm(y3, y3, l3, ctx); - } - -#undef x3 -#undef y3 -#undef z3 -#undef t1 -#undef t2 -#undef t3 -#undef l1 -#undef l2 -#undef l3 -} - -/* RESULT = 2 * POINT (Montgomery version). */ -static void dup_point_montgomery(MPI_POINT result, - MPI_POINT point, struct mpi_ec_ctx *ctx) -{ - (void)result; - (void)point; - (void)ctx; - log_fatal("%s: %s not yet supported\n", - "mpi_ec_dup_point", "Montgomery"); -} - -/* RESULT = 2 * POINT (Twisted Edwards version). */ -static void dup_point_edwards(MPI_POINT result, - MPI_POINT point, struct mpi_ec_ctx *ctx) -{ -#define X1 (point->x) -#define Y1 (point->y) -#define Z1 (point->z) -#define X3 (result->x) -#define Y3 (result->y) -#define Z3 (result->z) -#define B (ctx->t.scratch[0]) -#define C (ctx->t.scratch[1]) -#define D (ctx->t.scratch[2]) -#define E (ctx->t.scratch[3]) -#define F (ctx->t.scratch[4]) -#define H (ctx->t.scratch[5]) -#define J (ctx->t.scratch[6]) - - /* Compute: (X_3 : Y_3 : Z_3) = 2( X_1 : Y_1 : Z_1 ) */ - - /* B = (X_1 + Y_1)^2 */ - ctx->addm(B, X1, Y1, ctx); - ctx->pow2(B, B, ctx); - - /* C = X_1^2 */ - /* D = Y_1^2 */ - ctx->pow2(C, X1, ctx); - ctx->pow2(D, Y1, ctx); - - /* E = aC */ - if (ctx->dialect == ECC_DIALECT_ED25519) - ctx->subm(E, ctx->p, C, ctx); - else - ctx->mulm(E, ctx->a, C, ctx); - - /* F = E + D */ - ctx->addm(F, E, D, ctx); - - /* H = Z_1^2 */ - ctx->pow2(H, Z1, ctx); - - /* J = F - 2H */ - ctx->mul2(J, H, ctx); - ctx->subm(J, F, J, ctx); - - /* X_3 = (B - C - D) · J */ - ctx->subm(X3, B, C, ctx); - ctx->subm(X3, X3, D, ctx); - ctx->mulm(X3, X3, J, ctx); - - /* Y_3 = F · (E - D) */ - ctx->subm(Y3, E, D, ctx); - ctx->mulm(Y3, Y3, F, ctx); - - /* Z_3 = F · J */ - ctx->mulm(Z3, F, J, ctx); - -#undef X1 -#undef Y1 -#undef Z1 -#undef X3 -#undef Y3 -#undef Z3 -#undef B -#undef C -#undef D -#undef E -#undef F -#undef H -#undef J -} - -/* RESULT = 2 * POINT */ -static void -mpi_ec_dup_point(MPI_POINT result, MPI_POINT point, struct mpi_ec_ctx *ctx) -{ - switch (ctx->model) { - case MPI_EC_WEIERSTRASS: - dup_point_weierstrass(result, point, ctx); - break; - case MPI_EC_MONTGOMERY: - dup_point_montgomery(result, point, ctx); - break; - case MPI_EC_EDWARDS: - dup_point_edwards(result, point, ctx); - break; - } -} - -/* RESULT = P1 + P2 (Weierstrass version).*/ -static void add_points_weierstrass(MPI_POINT result, - MPI_POINT p1, MPI_POINT p2, - struct mpi_ec_ctx *ctx) -{ -#define x1 (p1->x) -#define y1 (p1->y) -#define z1 (p1->z) -#define x2 (p2->x) -#define y2 (p2->y) -#define z2 (p2->z) -#define x3 (result->x) -#define y3 (result->y) -#define z3 (result->z) -#define l1 (ctx->t.scratch[0]) -#define l2 (ctx->t.scratch[1]) -#define l3 (ctx->t.scratch[2]) -#define l4 (ctx->t.scratch[3]) -#define l5 (ctx->t.scratch[4]) -#define l6 (ctx->t.scratch[5]) -#define l7 (ctx->t.scratch[6]) -#define l8 (ctx->t.scratch[7]) -#define l9 (ctx->t.scratch[8]) -#define t1 (ctx->t.scratch[9]) -#define t2 (ctx->t.scratch[10]) - - if ((!mpi_cmp(x1, x2)) && (!mpi_cmp(y1, y2)) && (!mpi_cmp(z1, z2))) { - /* Same point; need to call the duplicate function. */ - mpi_ec_dup_point(result, p1, ctx); - } else if (!mpi_cmp_ui(z1, 0)) { - /* P1 is at infinity. */ - mpi_set(x3, p2->x); - mpi_set(y3, p2->y); - mpi_set(z3, p2->z); - } else if (!mpi_cmp_ui(z2, 0)) { - /* P2 is at infinity. */ - mpi_set(x3, p1->x); - mpi_set(y3, p1->y); - mpi_set(z3, p1->z); - } else { - int z1_is_one = !mpi_cmp_ui(z1, 1); - int z2_is_one = !mpi_cmp_ui(z2, 1); - - /* l1 = x1 z2^2 */ - /* l2 = x2 z1^2 */ - if (z2_is_one) - mpi_set(l1, x1); - else { - ec_pow2(l1, z2, ctx); - ec_mulm(l1, l1, x1, ctx); - } - if (z1_is_one) - mpi_set(l2, x2); - else { - ec_pow2(l2, z1, ctx); - ec_mulm(l2, l2, x2, ctx); - } - /* l3 = l1 - l2 */ - ec_subm(l3, l1, l2, ctx); - /* l4 = y1 z2^3 */ - ec_powm(l4, z2, mpi_const(MPI_C_THREE), ctx); - ec_mulm(l4, l4, y1, ctx); - /* l5 = y2 z1^3 */ - ec_powm(l5, z1, mpi_const(MPI_C_THREE), ctx); - ec_mulm(l5, l5, y2, ctx); - /* l6 = l4 - l5 */ - ec_subm(l6, l4, l5, ctx); - - if (!mpi_cmp_ui(l3, 0)) { - if (!mpi_cmp_ui(l6, 0)) { - /* P1 and P2 are the same - use duplicate function. */ - mpi_ec_dup_point(result, p1, ctx); - } else { - /* P1 is the inverse of P2. */ - mpi_set_ui(x3, 1); - mpi_set_ui(y3, 1); - mpi_set_ui(z3, 0); - } - } else { - /* l7 = l1 + l2 */ - ec_addm(l7, l1, l2, ctx); - /* l8 = l4 + l5 */ - ec_addm(l8, l4, l5, ctx); - /* z3 = z1 z2 l3 */ - ec_mulm(z3, z1, z2, ctx); - ec_mulm(z3, z3, l3, ctx); - /* x3 = l6^2 - l7 l3^2 */ - ec_pow2(t1, l6, ctx); - ec_pow2(t2, l3, ctx); - ec_mulm(t2, t2, l7, ctx); - ec_subm(x3, t1, t2, ctx); - /* l9 = l7 l3^2 - 2 x3 */ - ec_mul2(t1, x3, ctx); - ec_subm(l9, t2, t1, ctx); - /* y3 = (l9 l6 - l8 l3^3)/2 */ - ec_mulm(l9, l9, l6, ctx); - ec_powm(t1, l3, mpi_const(MPI_C_THREE), ctx); /* fixme: Use saved value*/ - ec_mulm(t1, t1, l8, ctx); - ec_subm(y3, l9, t1, ctx); - ec_mulm(y3, y3, ec_get_two_inv_p(ctx), ctx); - } - } - -#undef x1 -#undef y1 -#undef z1 -#undef x2 -#undef y2 -#undef z2 -#undef x3 -#undef y3 -#undef z3 -#undef l1 -#undef l2 -#undef l3 -#undef l4 -#undef l5 -#undef l6 -#undef l7 -#undef l8 -#undef l9 -#undef t1 -#undef t2 -} - -/* RESULT = P1 + P2 (Montgomery version).*/ -static void add_points_montgomery(MPI_POINT result, - MPI_POINT p1, MPI_POINT p2, - struct mpi_ec_ctx *ctx) -{ - (void)result; - (void)p1; - (void)p2; - (void)ctx; - log_fatal("%s: %s not yet supported\n", - "mpi_ec_add_points", "Montgomery"); -} - -/* RESULT = P1 + P2 (Twisted Edwards version).*/ -static void add_points_edwards(MPI_POINT result, - MPI_POINT p1, MPI_POINT p2, - struct mpi_ec_ctx *ctx) -{ -#define X1 (p1->x) -#define Y1 (p1->y) -#define Z1 (p1->z) -#define X2 (p2->x) -#define Y2 (p2->y) -#define Z2 (p2->z) -#define X3 (result->x) -#define Y3 (result->y) -#define Z3 (result->z) -#define A (ctx->t.scratch[0]) -#define B (ctx->t.scratch[1]) -#define C (ctx->t.scratch[2]) -#define D (ctx->t.scratch[3]) -#define E (ctx->t.scratch[4]) -#define F (ctx->t.scratch[5]) -#define G (ctx->t.scratch[6]) -#define tmp (ctx->t.scratch[7]) - - point_resize(result, ctx); - - /* Compute: (X_3 : Y_3 : Z_3) = (X_1 : Y_1 : Z_1) + (X_2 : Y_2 : Z_3) */ - - /* A = Z1 · Z2 */ - ctx->mulm(A, Z1, Z2, ctx); - - /* B = A^2 */ - ctx->pow2(B, A, ctx); - - /* C = X1 · X2 */ - ctx->mulm(C, X1, X2, ctx); - - /* D = Y1 · Y2 */ - ctx->mulm(D, Y1, Y2, ctx); - - /* E = d · C · D */ - ctx->mulm(E, ctx->b, C, ctx); - ctx->mulm(E, E, D, ctx); - - /* F = B - E */ - ctx->subm(F, B, E, ctx); - - /* G = B + E */ - ctx->addm(G, B, E, ctx); - - /* X_3 = A · F · ((X_1 + Y_1) · (X_2 + Y_2) - C - D) */ - ctx->addm(tmp, X1, Y1, ctx); - ctx->addm(X3, X2, Y2, ctx); - ctx->mulm(X3, X3, tmp, ctx); - ctx->subm(X3, X3, C, ctx); - ctx->subm(X3, X3, D, ctx); - ctx->mulm(X3, X3, F, ctx); - ctx->mulm(X3, X3, A, ctx); - - /* Y_3 = A · G · (D - aC) */ - if (ctx->dialect == ECC_DIALECT_ED25519) { - ctx->addm(Y3, D, C, ctx); - } else { - ctx->mulm(Y3, ctx->a, C, ctx); - ctx->subm(Y3, D, Y3, ctx); - } - ctx->mulm(Y3, Y3, G, ctx); - ctx->mulm(Y3, Y3, A, ctx); - - /* Z_3 = F · G */ - ctx->mulm(Z3, F, G, ctx); - - -#undef X1 -#undef Y1 -#undef Z1 -#undef X2 -#undef Y2 -#undef Z2 -#undef X3 -#undef Y3 -#undef Z3 -#undef A -#undef B -#undef C -#undef D -#undef E -#undef F -#undef G -#undef tmp -} - -/* Compute a step of Montgomery Ladder (only use X and Z in the point). - * Inputs: P1, P2, and x-coordinate of DIF = P1 - P1. - * Outputs: PRD = 2 * P1 and SUM = P1 + P2. - */ -static void montgomery_ladder(MPI_POINT prd, MPI_POINT sum, - MPI_POINT p1, MPI_POINT p2, MPI dif_x, - struct mpi_ec_ctx *ctx) -{ - ctx->addm(sum->x, p2->x, p2->z, ctx); - ctx->subm(p2->z, p2->x, p2->z, ctx); - ctx->addm(prd->x, p1->x, p1->z, ctx); - ctx->subm(p1->z, p1->x, p1->z, ctx); - ctx->mulm(p2->x, p1->z, sum->x, ctx); - ctx->mulm(p2->z, prd->x, p2->z, ctx); - ctx->pow2(p1->x, prd->x, ctx); - ctx->pow2(p1->z, p1->z, ctx); - ctx->addm(sum->x, p2->x, p2->z, ctx); - ctx->subm(p2->z, p2->x, p2->z, ctx); - ctx->mulm(prd->x, p1->x, p1->z, ctx); - ctx->subm(p1->z, p1->x, p1->z, ctx); - ctx->pow2(sum->x, sum->x, ctx); - ctx->pow2(sum->z, p2->z, ctx); - ctx->mulm(prd->z, p1->z, ctx->a, ctx); /* CTX->A: (a-2)/4 */ - ctx->mulm(sum->z, sum->z, dif_x, ctx); - ctx->addm(prd->z, p1->x, prd->z, ctx); - ctx->mulm(prd->z, prd->z, p1->z, ctx); -} - -/* RESULT = P1 + P2 */ -void mpi_ec_add_points(MPI_POINT result, - MPI_POINT p1, MPI_POINT p2, - struct mpi_ec_ctx *ctx) -{ - switch (ctx->model) { - case MPI_EC_WEIERSTRASS: - add_points_weierstrass(result, p1, p2, ctx); - break; - case MPI_EC_MONTGOMERY: - add_points_montgomery(result, p1, p2, ctx); - break; - case MPI_EC_EDWARDS: - add_points_edwards(result, p1, p2, ctx); - break; - } -} -EXPORT_SYMBOL_GPL(mpi_ec_add_points); - -/* Scalar point multiplication - the main function for ECC. If takes - * an integer SCALAR and a POINT as well as the usual context CTX. - * RESULT will be set to the resulting point. - */ -void mpi_ec_mul_point(MPI_POINT result, - MPI scalar, MPI_POINT point, - struct mpi_ec_ctx *ctx) -{ - MPI x1, y1, z1, k, h, yy; - unsigned int i, loops; - struct gcry_mpi_point p1, p2, p1inv; - - if (ctx->model == MPI_EC_EDWARDS) { - /* Simple left to right binary method. Algorithm 3.27 from - * {author={Hankerson, Darrel and Menezes, Alfred J. and Vanstone, Scott}, - * title = {Guide to Elliptic Curve Cryptography}, - * year = {2003}, isbn = {038795273X}, - * url = {http://www.cacr.math.uwaterloo.ca/ecc/}, - * publisher = {Springer-Verlag New York, Inc.}} - */ - unsigned int nbits; - int j; - - if (mpi_cmp(scalar, ctx->p) >= 0) - nbits = mpi_get_nbits(scalar); - else - nbits = mpi_get_nbits(ctx->p); - - mpi_set_ui(result->x, 0); - mpi_set_ui(result->y, 1); - mpi_set_ui(result->z, 1); - point_resize(point, ctx); - - point_resize(result, ctx); - point_resize(point, ctx); - - for (j = nbits-1; j >= 0; j--) { - mpi_ec_dup_point(result, result, ctx); - if (mpi_test_bit(scalar, j)) - mpi_ec_add_points(result, result, point, ctx); - } - return; - } else if (ctx->model == MPI_EC_MONTGOMERY) { - unsigned int nbits; - int j; - struct gcry_mpi_point p1_, p2_; - MPI_POINT q1, q2, prd, sum; - unsigned long sw; - mpi_size_t rsize; - - /* Compute scalar point multiplication with Montgomery Ladder. - * Note that we don't use Y-coordinate in the points at all. - * RESULT->Y will be filled by zero. - */ - - nbits = mpi_get_nbits(scalar); - point_init(&p1); - point_init(&p2); - point_init(&p1_); - point_init(&p2_); - mpi_set_ui(p1.x, 1); - mpi_free(p2.x); - p2.x = mpi_copy(point->x); - mpi_set_ui(p2.z, 1); - - point_resize(&p1, ctx); - point_resize(&p2, ctx); - point_resize(&p1_, ctx); - point_resize(&p2_, ctx); - - mpi_resize(point->x, ctx->p->nlimbs); - point->x->nlimbs = ctx->p->nlimbs; - - q1 = &p1; - q2 = &p2; - prd = &p1_; - sum = &p2_; - - for (j = nbits-1; j >= 0; j--) { - sw = mpi_test_bit(scalar, j); - point_swap_cond(q1, q2, sw, ctx); - montgomery_ladder(prd, sum, q1, q2, point->x, ctx); - point_swap_cond(prd, sum, sw, ctx); - swap(q1, prd); - swap(q2, sum); - } - - mpi_clear(result->y); - sw = (nbits & 1); - point_swap_cond(&p1, &p1_, sw, ctx); - - rsize = p1.z->nlimbs; - MPN_NORMALIZE(p1.z->d, rsize); - if (rsize == 0) { - mpi_set_ui(result->x, 1); - mpi_set_ui(result->z, 0); - } else { - z1 = mpi_new(0); - ec_invm(z1, p1.z, ctx); - ec_mulm(result->x, p1.x, z1, ctx); - mpi_set_ui(result->z, 1); - mpi_free(z1); - } - - point_free(&p1); - point_free(&p2); - point_free(&p1_); - point_free(&p2_); - return; - } - - x1 = mpi_alloc_like(ctx->p); - y1 = mpi_alloc_like(ctx->p); - h = mpi_alloc_like(ctx->p); - k = mpi_copy(scalar); - yy = mpi_copy(point->y); - - if (mpi_has_sign(k)) { - k->sign = 0; - ec_invm(yy, yy, ctx); - } - - if (!mpi_cmp_ui(point->z, 1)) { - mpi_set(x1, point->x); - mpi_set(y1, yy); - } else { - MPI z2, z3; - - z2 = mpi_alloc_like(ctx->p); - z3 = mpi_alloc_like(ctx->p); - ec_mulm(z2, point->z, point->z, ctx); - ec_mulm(z3, point->z, z2, ctx); - ec_invm(z2, z2, ctx); - ec_mulm(x1, point->x, z2, ctx); - ec_invm(z3, z3, ctx); - ec_mulm(y1, yy, z3, ctx); - mpi_free(z2); - mpi_free(z3); - } - z1 = mpi_copy(mpi_const(MPI_C_ONE)); - - mpi_mul(h, k, mpi_const(MPI_C_THREE)); /* h = 3k */ - loops = mpi_get_nbits(h); - if (loops < 2) { - /* If SCALAR is zero, the above mpi_mul sets H to zero and thus - * LOOPs will be zero. To avoid an underflow of I in the main - * loop we set LOOP to 2 and the result to (0,0,0). - */ - loops = 2; - mpi_clear(result->x); - mpi_clear(result->y); - mpi_clear(result->z); - } else { - mpi_set(result->x, point->x); - mpi_set(result->y, yy); - mpi_set(result->z, point->z); - } - mpi_free(yy); yy = NULL; - - p1.x = x1; x1 = NULL; - p1.y = y1; y1 = NULL; - p1.z = z1; z1 = NULL; - point_init(&p2); - point_init(&p1inv); - - /* Invert point: y = p - y mod p */ - point_set(&p1inv, &p1); - ec_subm(p1inv.y, ctx->p, p1inv.y, ctx); - - for (i = loops-2; i > 0; i--) { - mpi_ec_dup_point(result, result, ctx); - if (mpi_test_bit(h, i) == 1 && mpi_test_bit(k, i) == 0) { - point_set(&p2, result); - mpi_ec_add_points(result, &p2, &p1, ctx); - } - if (mpi_test_bit(h, i) == 0 && mpi_test_bit(k, i) == 1) { - point_set(&p2, result); - mpi_ec_add_points(result, &p2, &p1inv, ctx); - } - } - - point_free(&p1); - point_free(&p2); - point_free(&p1inv); - mpi_free(h); - mpi_free(k); -} -EXPORT_SYMBOL_GPL(mpi_ec_mul_point); - -/* Return true if POINT is on the curve described by CTX. */ -int mpi_ec_curve_point(MPI_POINT point, struct mpi_ec_ctx *ctx) -{ - int res = 0; - MPI x, y, w; - - x = mpi_new(0); - y = mpi_new(0); - w = mpi_new(0); - - /* Check that the point is in range. This needs to be done here and - * not after conversion to affine coordinates. - */ - if (mpi_cmpabs(point->x, ctx->p) >= 0) - goto leave; - if (mpi_cmpabs(point->y, ctx->p) >= 0) - goto leave; - if (mpi_cmpabs(point->z, ctx->p) >= 0) - goto leave; - - switch (ctx->model) { - case MPI_EC_WEIERSTRASS: - { - MPI xxx; - - if (mpi_ec_get_affine(x, y, point, ctx)) - goto leave; - - xxx = mpi_new(0); - - /* y^2 == x^3 + a·x + b */ - ec_pow2(y, y, ctx); - - ec_pow3(xxx, x, ctx); - ec_mulm(w, ctx->a, x, ctx); - ec_addm(w, w, ctx->b, ctx); - ec_addm(w, w, xxx, ctx); - - if (!mpi_cmp(y, w)) - res = 1; - - mpi_free(xxx); - } - break; - - case MPI_EC_MONTGOMERY: - { -#define xx y - /* With Montgomery curve, only X-coordinate is valid. */ - if (mpi_ec_get_affine(x, NULL, point, ctx)) - goto leave; - - /* The equation is: b * y^2 == x^3 + a · x^2 + x */ - /* We check if right hand is quadratic residue or not by - * Euler's criterion. - */ - /* CTX->A has (a-2)/4 and CTX->B has b^-1 */ - ec_mulm(w, ctx->a, mpi_const(MPI_C_FOUR), ctx); - ec_addm(w, w, mpi_const(MPI_C_TWO), ctx); - ec_mulm(w, w, x, ctx); - ec_pow2(xx, x, ctx); - ec_addm(w, w, xx, ctx); - ec_addm(w, w, mpi_const(MPI_C_ONE), ctx); - ec_mulm(w, w, x, ctx); - ec_mulm(w, w, ctx->b, ctx); -#undef xx - /* Compute Euler's criterion: w^(p-1)/2 */ -#define p_minus1 y - ec_subm(p_minus1, ctx->p, mpi_const(MPI_C_ONE), ctx); - mpi_rshift(p_minus1, p_minus1, 1); - ec_powm(w, w, p_minus1, ctx); - - res = !mpi_cmp_ui(w, 1); -#undef p_minus1 - } - break; - - case MPI_EC_EDWARDS: - { - if (mpi_ec_get_affine(x, y, point, ctx)) - goto leave; - - mpi_resize(w, ctx->p->nlimbs); - w->nlimbs = ctx->p->nlimbs; - - /* a · x^2 + y^2 - 1 - b · x^2 · y^2 == 0 */ - ctx->pow2(x, x, ctx); - ctx->pow2(y, y, ctx); - if (ctx->dialect == ECC_DIALECT_ED25519) - ctx->subm(w, ctx->p, x, ctx); - else - ctx->mulm(w, ctx->a, x, ctx); - ctx->addm(w, w, y, ctx); - ctx->mulm(x, x, y, ctx); - ctx->mulm(x, x, ctx->b, ctx); - ctx->subm(w, w, x, ctx); - if (!mpi_cmp_ui(w, 1)) - res = 1; - } - break; - } - -leave: - mpi_free(w); - mpi_free(x); - mpi_free(y); - - return res; -} -EXPORT_SYMBOL_GPL(mpi_ec_curve_point); -- cgit v1.2.3 From 0737158aabc278526c784f63b8dd8963cdc558a9 Mon Sep 17 00:00:00 2001 From: Olivier Moysan Date: Tue, 30 Jul 2024 10:46:31 +0200 Subject: iio: add read scale and offset services to iio backend framework Add iio_backend_read_scale() and iio_backend_read_offset() services to read channel scale and offset from an IIO backbend device. Also add a read_raw callback which replicates the read_raw callback of the IIO framework, and is intended to request miscellaneous channel attributes from the backend device. Both scale and offset helpers use this callback. Signed-off-by: Olivier Moysan Reviewed-by: Nuno Sa Link: https://patch.msgid.link/20240730084640.1307938-2-olivier.moysan@foss.st.com Signed-off-by: Jonathan Cameron --- drivers/iio/industrialio-backend.c | 19 +++++++++++++++++++ include/linux/iio/backend.h | 24 +++++++++++++++++++++++- 2 files changed, 42 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/iio/industrialio-backend.c b/drivers/iio/industrialio-backend.c index 468eadeaf23d..dfaa5f34a7a5 100644 --- a/drivers/iio/industrialio-backend.c +++ b/drivers/iio/industrialio-backend.c @@ -502,6 +502,25 @@ int devm_iio_backend_request_buffer(struct device *dev, } EXPORT_SYMBOL_NS_GPL(devm_iio_backend_request_buffer, IIO_BACKEND); +/** + * iio_backend_read_raw - Read a channel attribute from a backend device. + * @back: Backend device + * @chan: IIO channel reference + * @val: First returned value + * @val2: Second returned value + * @mask: Specify the attribute to return + * + * RETURNS: + * 0 on success, negative error number on failure. + */ +int iio_backend_read_raw(struct iio_backend *back, + struct iio_chan_spec const *chan, int *val, int *val2, + long mask) +{ + return iio_backend_op_call(back, read_raw, chan, val, val2, mask); +} +EXPORT_SYMBOL_NS_GPL(iio_backend_read_raw, IIO_BACKEND); + static struct iio_backend *iio_backend_from_indio_dev_parent(const struct device *dev) { struct iio_backend *back = ERR_PTR(-ENODEV), *iter; diff --git a/include/linux/iio/backend.h b/include/linux/iio/backend.h index 2b9d1aa86552..838092b0de3d 100644 --- a/include/linux/iio/backend.h +++ b/include/linux/iio/backend.h @@ -3,6 +3,7 @@ #define _IIO_BACKEND_H_ #include +#include struct iio_chan_spec; struct fwnode_handle; @@ -85,6 +86,7 @@ enum iio_backend_sample_trigger { * @extend_chan_spec: Extend an IIO channel. * @ext_info_set: Extended info setter. * @ext_info_get: Extended info getter. + * @read_raw: Read a channel attribute from a backend device * @debugfs_print_chan_status: Print channel status into a buffer. * @debugfs_reg_access: Read or write register value of backend. **/ @@ -119,6 +121,9 @@ struct iio_backend_ops { const char *buf, size_t len); int (*ext_info_get)(struct iio_backend *back, uintptr_t private, const struct iio_chan_spec *chan, char *buf); + int (*read_raw)(struct iio_backend *back, + struct iio_chan_spec const *chan, int *val, int *val2, + long mask); int (*debugfs_print_chan_status)(struct iio_backend *back, unsigned int chan, char *buf, size_t len); @@ -162,7 +167,9 @@ ssize_t iio_backend_ext_info_set(struct iio_dev *indio_dev, uintptr_t private, const char *buf, size_t len); ssize_t iio_backend_ext_info_get(struct iio_dev *indio_dev, uintptr_t private, const struct iio_chan_spec *chan, char *buf); - +int iio_backend_read_raw(struct iio_backend *back, + struct iio_chan_spec const *chan, int *val, int *val2, + long mask); int iio_backend_extend_chan_spec(struct iio_backend *back, struct iio_chan_spec *chan); void *iio_backend_get_priv(const struct iio_backend *conv); @@ -174,6 +181,21 @@ __devm_iio_backend_get_from_fwnode_lookup(struct device *dev, int devm_iio_backend_register(struct device *dev, const struct iio_backend_info *info, void *priv); +static inline int iio_backend_read_scale(struct iio_backend *back, + struct iio_chan_spec const *chan, + int *val, int *val2) +{ + return iio_backend_read_raw(back, chan, val, val2, IIO_CHAN_INFO_SCALE); +} + +static inline int iio_backend_read_offset(struct iio_backend *back, + struct iio_chan_spec const *chan, + int *val, int *val2) +{ + return iio_backend_read_raw(back, chan, val, val2, + IIO_CHAN_INFO_OFFSET); +} + ssize_t iio_backend_debugfs_print_chan_status(struct iio_backend *back, unsigned int chan, char *buf, size_t len); -- cgit v1.2.3 From 2530d7d44ca6dc0c1c059f143cdcb2be8600c59a Mon Sep 17 00:00:00 2001 From: Olivier Moysan Date: Tue, 30 Jul 2024 10:46:32 +0200 Subject: iio: add enable and disable services to iio backend framework Add iio_backend_disable() and iio_backend_enable() APIs to allow IIO backend consumer to request backend disabling and enabling. Signed-off-by: Olivier Moysan Reviewed-by: Nuno Sa Link: https://patch.msgid.link/20240730084640.1307938-3-olivier.moysan@foss.st.com Signed-off-by: Jonathan Cameron --- drivers/iio/industrialio-backend.c | 25 ++++++++++++++++++++++++- include/linux/iio/backend.h | 2 ++ 2 files changed, 26 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/iio/industrialio-backend.c b/drivers/iio/industrialio-backend.c index dfaa5f34a7a5..8a7ff783ae29 100644 --- a/drivers/iio/industrialio-backend.c +++ b/drivers/iio/industrialio-backend.c @@ -291,6 +291,29 @@ static void __iio_backend_disable(void *back) iio_backend_void_op_call(back, disable); } +/** + * iio_backend_disable - Backend disable + * @back: Backend device + */ +void iio_backend_disable(struct iio_backend *back) +{ + __iio_backend_disable(back); +} +EXPORT_SYMBOL_NS_GPL(iio_backend_disable, IIO_BACKEND); + +/** + * iio_backend_enable - Backend enable + * @back: Backend device + * + * RETURNS: + * 0 on success, negative error number on failure. + */ +int iio_backend_enable(struct iio_backend *back) +{ + return iio_backend_op_call(back, enable); +} +EXPORT_SYMBOL_NS_GPL(iio_backend_enable, IIO_BACKEND); + /** * devm_iio_backend_enable - Device managed backend enable * @dev: Consumer device for the backend @@ -303,7 +326,7 @@ int devm_iio_backend_enable(struct device *dev, struct iio_backend *back) { int ret; - ret = iio_backend_op_call(back, enable); + ret = iio_backend_enable(back); if (ret) return ret; diff --git a/include/linux/iio/backend.h b/include/linux/iio/backend.h index 838092b0de3d..b0b663163ff4 100644 --- a/include/linux/iio/backend.h +++ b/include/linux/iio/backend.h @@ -144,6 +144,8 @@ struct iio_backend_info { int iio_backend_chan_enable(struct iio_backend *back, unsigned int chan); int iio_backend_chan_disable(struct iio_backend *back, unsigned int chan); int devm_iio_backend_enable(struct device *dev, struct iio_backend *back); +int iio_backend_enable(struct iio_backend *back); +void iio_backend_disable(struct iio_backend *back); int iio_backend_data_format_set(struct iio_backend *back, unsigned int chan, const struct iio_backend_data_fmt *data); int iio_backend_data_source_set(struct iio_backend *back, unsigned int chan, -- cgit v1.2.3 From c464cc610f51f6eb5f27bf905d4c1ab1896b2725 Mon Sep 17 00:00:00 2001 From: Olivier Moysan Date: Tue, 30 Jul 2024 10:46:33 +0200 Subject: iio: add child nodes support in iio backend framework Add an API to support IIO generic channels binding: http://devicetree.org/schemas/iio/adc/adc.yaml# This new API is needed, as generic channel DT node isn't populated as a device. Add devm_iio_backend_fwnode_get() to allow an IIO device backend consumer to reference backend phandles in its child nodes. Signed-off-by: Olivier Moysan Reviewed-by: Nuno Sa Link: https://patch.msgid.link/20240730084640.1307938-4-olivier.moysan@foss.st.com Signed-off-by: Jonathan Cameron --- drivers/iio/industrialio-backend.c | 57 +++++++++++++++++++++++++++----------- include/linux/iio/backend.h | 3 ++ 2 files changed, 44 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/iio/industrialio-backend.c b/drivers/iio/industrialio-backend.c index 8a7ff783ae29..a52a6b61c8b5 100644 --- a/drivers/iio/industrialio-backend.c +++ b/drivers/iio/industrialio-backend.c @@ -718,19 +718,10 @@ static int __devm_iio_backend_get(struct device *dev, struct iio_backend *back) return 0; } -/** - * devm_iio_backend_get - Device managed backend device get - * @dev: Consumer device for the backend - * @name: Backend name - * - * Get's the backend associated with @dev. - * - * RETURNS: - * A backend pointer, negative error pointer otherwise. - */ -struct iio_backend *devm_iio_backend_get(struct device *dev, const char *name) +static struct iio_backend *__devm_iio_backend_fwnode_get(struct device *dev, const char *name, + struct fwnode_handle *fwnode) { - struct fwnode_handle *fwnode; + struct fwnode_handle *fwnode_back; struct iio_backend *back; unsigned int index; int ret; @@ -745,17 +736,17 @@ struct iio_backend *devm_iio_backend_get(struct device *dev, const char *name) index = 0; } - fwnode = fwnode_find_reference(dev_fwnode(dev), "io-backends", index); + fwnode_back = fwnode_find_reference(fwnode, "io-backends", index); if (IS_ERR(fwnode)) return dev_err_cast_probe(dev, fwnode, "Cannot get Firmware reference\n"); guard(mutex)(&iio_back_lock); list_for_each_entry(back, &iio_back_list, entry) { - if (!device_match_fwnode(back->dev, fwnode)) + if (!device_match_fwnode(back->dev, fwnode_back)) continue; - fwnode_handle_put(fwnode); + fwnode_handle_put(fwnode_back); ret = __devm_iio_backend_get(dev, back); if (ret) return ERR_PTR(ret); @@ -766,11 +757,45 @@ struct iio_backend *devm_iio_backend_get(struct device *dev, const char *name) return back; } - fwnode_handle_put(fwnode); + fwnode_handle_put(fwnode_back); return ERR_PTR(-EPROBE_DEFER); } + +/** + * devm_iio_backend_get - Device managed backend device get + * @dev: Consumer device for the backend + * @name: Backend name + * + * Get's the backend associated with @dev. + * + * RETURNS: + * A backend pointer, negative error pointer otherwise. + */ +struct iio_backend *devm_iio_backend_get(struct device *dev, const char *name) +{ + return __devm_iio_backend_fwnode_get(dev, name, dev_fwnode(dev)); +} EXPORT_SYMBOL_NS_GPL(devm_iio_backend_get, IIO_BACKEND); +/** + * devm_iio_backend_fwnode_get - Device managed backend firmware node get + * @dev: Consumer device for the backend + * @name: Backend name + * @fwnode: Firmware node of the backend consumer + * + * Get's the backend associated with a firmware node. + * + * RETURNS: + * A backend pointer, negative error pointer otherwise. + */ +struct iio_backend *devm_iio_backend_fwnode_get(struct device *dev, + const char *name, + struct fwnode_handle *fwnode) +{ + return __devm_iio_backend_fwnode_get(dev, name, fwnode); +} +EXPORT_SYMBOL_NS_GPL(devm_iio_backend_fwnode_get, IIO_BACKEND); + /** * __devm_iio_backend_get_from_fwnode_lookup - Device managed fwnode backend device get * @dev: Consumer device for the backend diff --git a/include/linux/iio/backend.h b/include/linux/iio/backend.h index b0b663163ff4..37d56914d485 100644 --- a/include/linux/iio/backend.h +++ b/include/linux/iio/backend.h @@ -176,6 +176,9 @@ int iio_backend_extend_chan_spec(struct iio_backend *back, struct iio_chan_spec *chan); void *iio_backend_get_priv(const struct iio_backend *conv); struct iio_backend *devm_iio_backend_get(struct device *dev, const char *name); +struct iio_backend *devm_iio_backend_fwnode_get(struct device *dev, + const char *name, + struct fwnode_handle *fwnode); struct iio_backend * __devm_iio_backend_get_from_fwnode_lookup(struct device *dev, struct fwnode_handle *fwnode); -- cgit v1.2.3 From 2837efdc7cef5b86b0c4d94a7410bc03cc2f003f Mon Sep 17 00:00:00 2001 From: Denis Benato Date: Wed, 7 Aug 2024 20:56:18 +0200 Subject: iio: trigger: allow devices to suspend/resume theirs associated trigger When a machine enters a sleep state while a trigger is associated to an iio device that trigger is not resumed after exiting the sleep state: provide iio device drivers a way to suspend and resume the associated trigger to solve the aforementioned bug. Each iio driver supporting external triggers is expected to call iio_device_suspend_triggering before suspending, and iio_device_resume_triggering upon resuming. Signed-off-by: Denis Benato Link: https://patch.msgid.link/20240807185619.7261-2-benato.denis96@gmail.com Signed-off-by: Jonathan Cameron --- drivers/iio/industrialio-trigger.c | 27 +++++++++++++++++++++++++++ include/linux/iio/iio.h | 17 +++++++++++++++++ 2 files changed, 44 insertions(+) (limited to 'include/linux') diff --git a/drivers/iio/industrialio-trigger.c b/drivers/iio/industrialio-trigger.c index 2e84776f4fbd..54416a384232 100644 --- a/drivers/iio/industrialio-trigger.c +++ b/drivers/iio/industrialio-trigger.c @@ -347,6 +347,7 @@ int iio_trigger_detach_poll_func(struct iio_trigger *trig, iio_trigger_put_irq(trig, pf->irq); free_irq(pf->irq, pf); module_put(iio_dev_opaque->driver_module); + pf->irq = 0; return ret; } @@ -770,3 +771,29 @@ void iio_device_unregister_trigger_consumer(struct iio_dev *indio_dev) if (indio_dev->trig) iio_trigger_put(indio_dev->trig); } + +int iio_device_suspend_triggering(struct iio_dev *indio_dev) +{ + struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev); + + guard(mutex)(&iio_dev_opaque->mlock); + + if ((indio_dev->pollfunc) && (indio_dev->pollfunc->irq > 0)) + disable_irq(indio_dev->pollfunc->irq); + + return 0; +} +EXPORT_SYMBOL(iio_device_suspend_triggering); + +int iio_device_resume_triggering(struct iio_dev *indio_dev) +{ + struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev); + + guard(mutex)(&iio_dev_opaque->mlock); + + if ((indio_dev->pollfunc) && (indio_dev->pollfunc->irq > 0)) + enable_irq(indio_dev->pollfunc->irq); + + return 0; +} +EXPORT_SYMBOL(iio_device_resume_triggering); diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 3a735a9a9eae..18779b631e90 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -810,6 +810,23 @@ static inline struct dentry *iio_get_debugfs_dentry(struct iio_dev *indio_dev) } #endif +/** + * iio_device_suspend_triggering() - suspend trigger attached to an iio_dev + * @indio_dev: iio_dev associated with the device that will have triggers suspended + * + * Return 0 if successful, negative otherwise + **/ +int iio_device_suspend_triggering(struct iio_dev *indio_dev); + +/** + * iio_device_resume_triggering() - resume trigger attached to an iio_dev + * that was previously suspended with iio_device_suspend_triggering() + * @indio_dev: iio_dev associated with the device that will have triggers resumed + * + * Return 0 if successful, negative otherwise + **/ +int iio_device_resume_triggering(struct iio_dev *indio_dev); + #ifdef CONFIG_ACPI bool iio_read_acpi_mount_matrix(struct device *dev, struct iio_mount_matrix *orientation, -- cgit v1.2.3 From bf66471987b4bd537bc800353ca7d39bfd1d1022 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Tue, 16 Apr 2024 10:51:10 +0200 Subject: context_tracking, rcu: Rename struct context_tracking .dynticks_nesting into .nesting The context_tracking.state RCU_DYNTICKS subvariable has been renamed to RCU_WATCHING, reflect that change in the related helpers. [ neeraj.upadhyay: Fix htmldocs build error reported by Stephen Rothwell ] Suggested-by: Frederic Weisbecker Signed-off-by: Valentin Schneider Reviewed-by: Frederic Weisbecker Signed-off-by: Neeraj Upadhyay --- Documentation/RCU/Design/Data-Structures/Data-Structures.rst | 10 +++++----- include/linux/context_tracking_state.h | 6 +++--- include/trace/events/rcu.h | 2 +- kernel/context_tracking.c | 10 +++++----- kernel/rcu/tree.c | 8 ++++---- 5 files changed, 18 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/Documentation/RCU/Design/Data-Structures/Data-Structures.rst b/Documentation/RCU/Design/Data-Structures/Data-Structures.rst index b34990c7c377..69860bbec202 100644 --- a/Documentation/RCU/Design/Data-Structures/Data-Structures.rst +++ b/Documentation/RCU/Design/Data-Structures/Data-Structures.rst @@ -935,7 +935,7 @@ This portion of the rcu_data structure is declared as follows: :: - 1 long dynticks_nesting; + 1 long nesting; 2 long dynticks_nmi_nesting; 3 atomic_t dynticks; 4 bool rcu_need_heavy_qs; @@ -945,7 +945,7 @@ These fields in the rcu_data structure maintain the per-CPU dyntick-idle state for the corresponding CPU. The fields may be accessed only from the corresponding CPU (and from tracing) unless otherwise stated. -The ``->dynticks_nesting`` field counts the nesting depth of process +The ``->nesting`` field counts the nesting depth of process execution, so that in normal circumstances this counter has value zero or one. NMIs, irqs, and tracers are counted by the ``->dynticks_nmi_nesting`` field. Because NMIs cannot be masked, changes @@ -960,9 +960,9 @@ process-level transitions. However, it turns out that when running in non-idle kernel context, the Linux kernel is fully capable of entering interrupt handlers that never exit and perhaps also vice versa. Therefore, whenever the -``->dynticks_nesting`` field is incremented up from zero, the +``->nesting`` field is incremented up from zero, the ``->dynticks_nmi_nesting`` field is set to a large positive number, and -whenever the ``->dynticks_nesting`` field is decremented down to zero, +whenever the ``->nesting`` field is decremented down to zero, the ``->dynticks_nmi_nesting`` field is set to zero. Assuming that the number of misnested interrupts is not sufficient to overflow the counter, this approach corrects the ``->dynticks_nmi_nesting`` field @@ -992,7 +992,7 @@ code. +-----------------------------------------------------------------------+ | **Quick Quiz**: | +-----------------------------------------------------------------------+ -| Why not simply combine the ``->dynticks_nesting`` and | +| Why not simply combine the ``->nesting`` and | | ``->dynticks_nmi_nesting`` counters into a single counter that just | | counts the number of reasons that the corresponding CPU is non-idle? | +-----------------------------------------------------------------------+ diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index ad6570ffeff3..65290e7677e6 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -39,7 +39,7 @@ struct context_tracking { atomic_t state; #endif #ifdef CONFIG_CONTEXT_TRACKING_IDLE - long dynticks_nesting; /* Track process nesting level. */ + long nesting; /* Track process nesting level. */ long dynticks_nmi_nesting; /* Track irq/NMI nesting level. */ #endif }; @@ -77,14 +77,14 @@ static __always_inline int ct_rcu_watching_cpu_acquire(int cpu) static __always_inline long ct_dynticks_nesting(void) { - return __this_cpu_read(context_tracking.dynticks_nesting); + return __this_cpu_read(context_tracking.nesting); } static __always_inline long ct_dynticks_nesting_cpu(int cpu) { struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); - return ct->dynticks_nesting; + return ct->nesting; } static __always_inline long ct_dynticks_nmi_nesting(void) diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index 31b3e0d3e65f..4066b6d51e46 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -469,7 +469,7 @@ TRACE_EVENT(rcu_stall_warning, * polarity: "Start", "End", "StillNonIdle" for entering, exiting or still not * being in dyntick-idle mode. * context: "USER" or "IDLE" or "IRQ". - * NMIs nested in IRQs are inferred with dynticks_nesting > 1 in IRQ context. + * NMIs nested in IRQs are inferred with nesting > 1 in IRQ context. * * These events also take a pair of numbers, which indicate the nesting * depth before and after the event of interest, and a third number that is diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 868ae0bcd4be..5cfdfc03b401 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -28,7 +28,7 @@ DEFINE_PER_CPU(struct context_tracking, context_tracking) = { #ifdef CONFIG_CONTEXT_TRACKING_IDLE - .dynticks_nesting = 1, + .nesting = 1, .dynticks_nmi_nesting = DYNTICK_IRQ_NONIDLE, #endif .state = ATOMIC_INIT(CT_RCU_WATCHING), @@ -131,7 +131,7 @@ static void noinstr ct_kernel_exit(bool user, int offset) ct_dynticks_nesting() == 0); if (ct_dynticks_nesting() != 1) { // RCU will still be watching, so just do accounting and leave. - ct->dynticks_nesting--; + ct->nesting--; return; } @@ -145,7 +145,7 @@ static void noinstr ct_kernel_exit(bool user, int offset) instrument_atomic_write(&ct->state, sizeof(ct->state)); instrumentation_end(); - WRITE_ONCE(ct->dynticks_nesting, 0); /* Avoid irq-access tearing. */ + WRITE_ONCE(ct->nesting, 0); /* Avoid irq-access tearing. */ // RCU is watching here ... ct_kernel_exit_state(offset); // ... but is no longer watching here. @@ -170,7 +170,7 @@ static void noinstr ct_kernel_enter(bool user, int offset) WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && oldval < 0); if (oldval) { // RCU was already watching, so just do accounting and leave. - ct->dynticks_nesting++; + ct->nesting++; return; } rcu_dynticks_task_exit(); @@ -184,7 +184,7 @@ static void noinstr ct_kernel_enter(bool user, int offset) trace_rcu_dyntick(TPS("End"), ct_dynticks_nesting(), 1, ct_rcu_watching()); WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current)); - WRITE_ONCE(ct->dynticks_nesting, 1); + WRITE_ONCE(ct->nesting, 1); WARN_ON_ONCE(ct_dynticks_nmi_nesting()); WRITE_ONCE(ct->dynticks_nmi_nesting, DYNTICK_IRQ_NONIDLE); instrumentation_end(); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 45a9f3667c2a..0d5a539acd58 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -389,7 +389,7 @@ static int rcu_is_cpu_rrupt_from_idle(void) /* Check for counter underflows */ RCU_LOCKDEP_WARN(ct_dynticks_nesting() < 0, - "RCU dynticks_nesting counter underflow!"); + "RCU nesting counter underflow!"); RCU_LOCKDEP_WARN(ct_dynticks_nmi_nesting() <= 0, "RCU dynticks_nmi_nesting counter underflow/zero!"); @@ -597,7 +597,7 @@ void rcu_irq_exit_check_preempt(void) lockdep_assert_irqs_disabled(); RCU_LOCKDEP_WARN(ct_dynticks_nesting() <= 0, - "RCU dynticks_nesting counter underflow/zero!"); + "RCU nesting counter underflow/zero!"); RCU_LOCKDEP_WARN(ct_dynticks_nmi_nesting() != DYNTICK_IRQ_NONIDLE, "Bad RCU dynticks_nmi_nesting counter\n"); @@ -4804,7 +4804,7 @@ rcu_boot_init_percpu_data(int cpu) /* Set up local state, ensuring consistent view of global state. */ rdp->grpmask = leaf_node_cpu_bit(rdp->mynode, cpu); INIT_WORK(&rdp->strict_work, strict_work_handler); - WARN_ON_ONCE(ct->dynticks_nesting != 1); + WARN_ON_ONCE(ct->nesting != 1); WARN_ON_ONCE(rcu_dynticks_in_eqs(ct_rcu_watching_cpu(cpu))); rdp->barrier_seq_snap = rcu_state.barrier_sequence; rdp->rcu_ofl_gp_seq = rcu_state.gp_seq; @@ -4898,7 +4898,7 @@ int rcutree_prepare_cpu(unsigned int cpu) rdp->qlen_last_fqs_check = 0; rdp->n_force_qs_snap = READ_ONCE(rcu_state.n_force_qs); rdp->blimit = blimit; - ct->dynticks_nesting = 1; /* CPU not up, no tearing. */ + ct->nesting = 1; /* CPU not up, no tearing. */ raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ /* -- cgit v1.2.3 From 1089c0078b69bce0c2d540e3cc43470ba9e5dcfd Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Tue, 16 Apr 2024 14:45:30 +0200 Subject: context_tracking, rcu: Rename ct_dynticks_nesting() into ct_nesting() The context_tracking.state RCU_DYNTICKS subvariable has been renamed to RCU_WATCHING, reflect that change in the related helpers. Suggested-by: Frederic Weisbecker Signed-off-by: Valentin Schneider Reviewed-by: Frederic Weisbecker Signed-off-by: Neeraj Upadhyay --- include/linux/context_tracking_state.h | 2 +- kernel/context_tracking.c | 10 +++++----- kernel/rcu/tree.c | 6 +++--- 3 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index 65290e7677e6..586c1ff22c2e 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -75,7 +75,7 @@ static __always_inline int ct_rcu_watching_cpu_acquire(int cpu) return atomic_read_acquire(&ct->state) & CT_RCU_WATCHING_MASK; } -static __always_inline long ct_dynticks_nesting(void) +static __always_inline long ct_nesting(void) { return __this_cpu_read(context_tracking.nesting); } diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 5cfdfc03b401..a951bde0bbcb 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -128,8 +128,8 @@ static void noinstr ct_kernel_exit(bool user, int offset) WARN_ON_ONCE(ct_dynticks_nmi_nesting() != DYNTICK_IRQ_NONIDLE); WRITE_ONCE(ct->dynticks_nmi_nesting, 0); WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && - ct_dynticks_nesting() == 0); - if (ct_dynticks_nesting() != 1) { + ct_nesting() == 0); + if (ct_nesting() != 1) { // RCU will still be watching, so just do accounting and leave. ct->nesting--; return; @@ -137,7 +137,7 @@ static void noinstr ct_kernel_exit(bool user, int offset) instrumentation_begin(); lockdep_assert_irqs_disabled(); - trace_rcu_dyntick(TPS("Start"), ct_dynticks_nesting(), 0, ct_rcu_watching()); + trace_rcu_dyntick(TPS("Start"), ct_nesting(), 0, ct_rcu_watching()); WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current)); rcu_preempt_deferred_qs(current); @@ -166,7 +166,7 @@ static void noinstr ct_kernel_enter(bool user, int offset) long oldval; WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !raw_irqs_disabled()); - oldval = ct_dynticks_nesting(); + oldval = ct_nesting(); WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && oldval < 0); if (oldval) { // RCU was already watching, so just do accounting and leave. @@ -182,7 +182,7 @@ static void noinstr ct_kernel_enter(bool user, int offset) // instrumentation for the noinstr ct_kernel_enter_state() instrument_atomic_write(&ct->state, sizeof(ct->state)); - trace_rcu_dyntick(TPS("End"), ct_dynticks_nesting(), 1, ct_rcu_watching()); + trace_rcu_dyntick(TPS("End"), ct_nesting(), 1, ct_rcu_watching()); WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current)); WRITE_ONCE(ct->nesting, 1); WARN_ON_ONCE(ct_dynticks_nmi_nesting()); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 0d5a539acd58..cf69a234080f 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -388,7 +388,7 @@ static int rcu_is_cpu_rrupt_from_idle(void) lockdep_assert_irqs_disabled(); /* Check for counter underflows */ - RCU_LOCKDEP_WARN(ct_dynticks_nesting() < 0, + RCU_LOCKDEP_WARN(ct_nesting() < 0, "RCU nesting counter underflow!"); RCU_LOCKDEP_WARN(ct_dynticks_nmi_nesting() <= 0, "RCU dynticks_nmi_nesting counter underflow/zero!"); @@ -404,7 +404,7 @@ static int rcu_is_cpu_rrupt_from_idle(void) WARN_ON_ONCE(!nesting && !is_idle_task(current)); /* Does CPU appear to be idle from an RCU standpoint? */ - return ct_dynticks_nesting() == 0; + return ct_nesting() == 0; } #define DEFAULT_RCU_BLIMIT (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) ? 1000 : 10) @@ -596,7 +596,7 @@ void rcu_irq_exit_check_preempt(void) { lockdep_assert_irqs_disabled(); - RCU_LOCKDEP_WARN(ct_dynticks_nesting() <= 0, + RCU_LOCKDEP_WARN(ct_nesting() <= 0, "RCU nesting counter underflow/zero!"); RCU_LOCKDEP_WARN(ct_dynticks_nmi_nesting() != DYNTICK_IRQ_NONIDLE, -- cgit v1.2.3 From bca9455da531a3c2520c28ff349d0dab4e471d28 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Tue, 16 Apr 2024 14:48:26 +0200 Subject: context_tracking, rcu: Rename ct_dynticks_nesting_cpu() into ct_nesting_cpu() The context_tracking.state RCU_DYNTICKS subvariable has been renamed to RCU_WATCHING, and the 'dynticks' prefix can be dropped without losing any meaning. Suggested-by: Frederic Weisbecker Signed-off-by: Valentin Schneider Reviewed-by: Frederic Weisbecker Signed-off-by: Neeraj Upadhyay --- include/linux/context_tracking_state.h | 2 +- kernel/rcu/tree_stall.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index 586c1ff22c2e..fd42d8120ac2 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -80,7 +80,7 @@ static __always_inline long ct_nesting(void) return __this_cpu_read(context_tracking.nesting); } -static __always_inline long ct_dynticks_nesting_cpu(int cpu) +static __always_inline long ct_nesting_cpu(int cpu) { struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index d65974448e81..59b1d84a4749 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -516,7 +516,7 @@ static void print_cpu_stall_info(int cpu) "!."[!delta], ticks_value, ticks_title, ct_rcu_watching_cpu(cpu) & 0xffff, - ct_dynticks_nesting_cpu(cpu), ct_dynticks_nmi_nesting_cpu(cpu), + ct_nesting_cpu(cpu), ct_dynticks_nmi_nesting_cpu(cpu), rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu), data_race(rcu_state.n_force_qs) - rcu_state.n_force_qs_gpstart, rcuc_starved ? buf : "", -- cgit v1.2.3 From dc5fface4b30508933b515a4985401c8c8f6bcfd Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Tue, 16 Apr 2024 10:52:03 +0200 Subject: context_tracking, rcu: Rename struct context_tracking .dynticks_nmi_nesting into .nmi_nesting The context_tracking.state RCU_DYNTICKS subvariable has been renamed to RCU_WATCHING, and the 'dynticks' prefix can be dropped without losing any meaning. [ neeraj.upadhyay: Fix htmldocs build error reported by Stephen Rothwell ] Suggested-by: Frederic Weisbecker Signed-off-by: Valentin Schneider Reviewed-by: Frederic Weisbecker Signed-off-by: Neeraj Upadhyay --- .../RCU/Design/Data-Structures/Data-Structures.rst | 14 +++++----- include/linux/context_tracking_state.h | 6 ++--- kernel/context_tracking.c | 30 +++++++++++----------- kernel/rcu/tree.c | 4 +-- 4 files changed, 27 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/Documentation/RCU/Design/Data-Structures/Data-Structures.rst b/Documentation/RCU/Design/Data-Structures/Data-Structures.rst index 69860bbec202..28d9f9e1783f 100644 --- a/Documentation/RCU/Design/Data-Structures/Data-Structures.rst +++ b/Documentation/RCU/Design/Data-Structures/Data-Structures.rst @@ -936,7 +936,7 @@ This portion of the rcu_data structure is declared as follows: :: 1 long nesting; - 2 long dynticks_nmi_nesting; + 2 long nmi_nesting; 3 atomic_t dynticks; 4 bool rcu_need_heavy_qs; 5 bool rcu_urgent_qs; @@ -948,11 +948,11 @@ the corresponding CPU (and from tracing) unless otherwise stated. The ``->nesting`` field counts the nesting depth of process execution, so that in normal circumstances this counter has value zero or one. NMIs, irqs, and tracers are counted by the -``->dynticks_nmi_nesting`` field. Because NMIs cannot be masked, changes +``->nmi_nesting`` field. Because NMIs cannot be masked, changes to this variable have to be undertaken carefully using an algorithm provided by Andy Lutomirski. The initial transition from idle adds one, and nested transitions add two, so that a nesting level of five is -represented by a ``->dynticks_nmi_nesting`` value of nine. This counter +represented by a ``->nmi_nesting`` value of nine. This counter can therefore be thought of as counting the number of reasons why this CPU cannot be permitted to enter dyntick-idle mode, aside from process-level transitions. @@ -961,11 +961,11 @@ However, it turns out that when running in non-idle kernel context, the Linux kernel is fully capable of entering interrupt handlers that never exit and perhaps also vice versa. Therefore, whenever the ``->nesting`` field is incremented up from zero, the -``->dynticks_nmi_nesting`` field is set to a large positive number, and +``->nmi_nesting`` field is set to a large positive number, and whenever the ``->nesting`` field is decremented down to zero, -the ``->dynticks_nmi_nesting`` field is set to zero. Assuming that +the ``->nmi_nesting`` field is set to zero. Assuming that the number of misnested interrupts is not sufficient to overflow the -counter, this approach corrects the ``->dynticks_nmi_nesting`` field +counter, this approach corrects the ``->nmi_nesting`` field every time the corresponding CPU enters the idle loop from process context. @@ -993,7 +993,7 @@ code. | **Quick Quiz**: | +-----------------------------------------------------------------------+ | Why not simply combine the ``->nesting`` and | -| ``->dynticks_nmi_nesting`` counters into a single counter that just | +| ``->nmi_nesting`` counters into a single counter that just | | counts the number of reasons that the corresponding CPU is non-idle? | +-----------------------------------------------------------------------+ | **Answer**: | diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index fd42d8120ac2..12d00adf29e1 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -40,7 +40,7 @@ struct context_tracking { #endif #ifdef CONFIG_CONTEXT_TRACKING_IDLE long nesting; /* Track process nesting level. */ - long dynticks_nmi_nesting; /* Track irq/NMI nesting level. */ + long nmi_nesting; /* Track irq/NMI nesting level. */ #endif }; @@ -89,14 +89,14 @@ static __always_inline long ct_nesting_cpu(int cpu) static __always_inline long ct_dynticks_nmi_nesting(void) { - return __this_cpu_read(context_tracking.dynticks_nmi_nesting); + return __this_cpu_read(context_tracking.nmi_nesting); } static __always_inline long ct_dynticks_nmi_nesting_cpu(int cpu) { struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); - return ct->dynticks_nmi_nesting; + return ct->nmi_nesting; } #endif /* #ifdef CONFIG_CONTEXT_TRACKING_IDLE */ diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index a951bde0bbcb..ae94215aa132 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -29,7 +29,7 @@ DEFINE_PER_CPU(struct context_tracking, context_tracking) = { #ifdef CONFIG_CONTEXT_TRACKING_IDLE .nesting = 1, - .dynticks_nmi_nesting = DYNTICK_IRQ_NONIDLE, + .nmi_nesting = DYNTICK_IRQ_NONIDLE, #endif .state = ATOMIC_INIT(CT_RCU_WATCHING), }; @@ -117,7 +117,7 @@ static noinstr void ct_kernel_enter_state(int offset) * Enter an RCU extended quiescent state, which can be either the * idle loop or adaptive-tickless usermode execution. * - * We crowbar the ->dynticks_nmi_nesting field to zero to allow for + * We crowbar the ->nmi_nesting field to zero to allow for * the possibility of usermode upcalls having messed up our count * of interrupt nesting level during the prior busy period. */ @@ -126,7 +126,7 @@ static void noinstr ct_kernel_exit(bool user, int offset) struct context_tracking *ct = this_cpu_ptr(&context_tracking); WARN_ON_ONCE(ct_dynticks_nmi_nesting() != DYNTICK_IRQ_NONIDLE); - WRITE_ONCE(ct->dynticks_nmi_nesting, 0); + WRITE_ONCE(ct->nmi_nesting, 0); WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && ct_nesting() == 0); if (ct_nesting() != 1) { @@ -156,7 +156,7 @@ static void noinstr ct_kernel_exit(bool user, int offset) * Exit an RCU extended quiescent state, which can be either the * idle loop or adaptive-tickless usermode execution. * - * We crowbar the ->dynticks_nmi_nesting field to DYNTICK_IRQ_NONIDLE to + * We crowbar the ->nmi_nesting field to DYNTICK_IRQ_NONIDLE to * allow for the possibility of usermode upcalls messing up our count of * interrupt nesting level during the busy period that is just now starting. */ @@ -186,7 +186,7 @@ static void noinstr ct_kernel_enter(bool user, int offset) WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current)); WRITE_ONCE(ct->nesting, 1); WARN_ON_ONCE(ct_dynticks_nmi_nesting()); - WRITE_ONCE(ct->dynticks_nmi_nesting, DYNTICK_IRQ_NONIDLE); + WRITE_ONCE(ct->nmi_nesting, DYNTICK_IRQ_NONIDLE); instrumentation_end(); } @@ -194,7 +194,7 @@ static void noinstr ct_kernel_enter(bool user, int offset) * ct_nmi_exit - inform RCU of exit from NMI context * * If we are returning from the outermost NMI handler that interrupted an - * RCU-idle period, update ct->state and ct->dynticks_nmi_nesting + * RCU-idle period, update ct->state and ct->nmi_nesting * to let the RCU grace-period handling know that the CPU is back to * being RCU-idle. * @@ -207,7 +207,7 @@ void noinstr ct_nmi_exit(void) instrumentation_begin(); /* - * Check for ->dynticks_nmi_nesting underflow and bad ->dynticks. + * Check for ->nmi_nesting underflow and bad ->dynticks. * (We are exiting an NMI handler, so RCU better be paying attention * to us!) */ @@ -221,7 +221,7 @@ void noinstr ct_nmi_exit(void) if (ct_dynticks_nmi_nesting() != 1) { trace_rcu_dyntick(TPS("--="), ct_dynticks_nmi_nesting(), ct_dynticks_nmi_nesting() - 2, ct_rcu_watching()); - WRITE_ONCE(ct->dynticks_nmi_nesting, /* No store tearing. */ + WRITE_ONCE(ct->nmi_nesting, /* No store tearing. */ ct_dynticks_nmi_nesting() - 2); instrumentation_end(); return; @@ -229,7 +229,7 @@ void noinstr ct_nmi_exit(void) /* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */ trace_rcu_dyntick(TPS("Startirq"), ct_dynticks_nmi_nesting(), 0, ct_rcu_watching()); - WRITE_ONCE(ct->dynticks_nmi_nesting, 0); /* Avoid store tearing. */ + WRITE_ONCE(ct->nmi_nesting, 0); /* Avoid store tearing. */ // instrumentation for the noinstr ct_kernel_exit_state() instrument_atomic_write(&ct->state, sizeof(ct->state)); @@ -247,7 +247,7 @@ void noinstr ct_nmi_exit(void) * ct_nmi_enter - inform RCU of entry to NMI context * * If the CPU was idle from RCU's viewpoint, update ct->state and - * ct->dynticks_nmi_nesting to let the RCU grace-period handling know + * ct->nmi_nesting to let the RCU grace-period handling know * that the CPU is active. This implementation permits nested NMIs, as * long as the nesting level does not overflow an int. (You will probably * run out of stack space first.) @@ -264,10 +264,10 @@ void noinstr ct_nmi_enter(void) WARN_ON_ONCE(ct_dynticks_nmi_nesting() < 0); /* - * If idle from RCU viewpoint, atomically increment ->dynticks - * to mark non-idle and increment ->dynticks_nmi_nesting by one. - * Otherwise, increment ->dynticks_nmi_nesting by two. This means - * if ->dynticks_nmi_nesting is equal to one, we are guaranteed + * If idle from RCU viewpoint, atomically increment CT state + * to mark non-idle and increment ->nmi_nesting by one. + * Otherwise, increment ->nmi_nesting by two. This means + * if ->nmi_nesting is equal to one, we are guaranteed * to be in the outermost NMI handler that interrupted an RCU-idle * period (observation due to Andy Lutomirski). */ @@ -298,7 +298,7 @@ void noinstr ct_nmi_enter(void) ct_dynticks_nmi_nesting(), ct_dynticks_nmi_nesting() + incby, ct_rcu_watching()); instrumentation_end(); - WRITE_ONCE(ct->dynticks_nmi_nesting, /* Prevent store tearing. */ + WRITE_ONCE(ct->nmi_nesting, /* Prevent store tearing. */ ct_dynticks_nmi_nesting() + incby); barrier(); } diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index cf69a234080f..934f6b34a551 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -391,7 +391,7 @@ static int rcu_is_cpu_rrupt_from_idle(void) RCU_LOCKDEP_WARN(ct_nesting() < 0, "RCU nesting counter underflow!"); RCU_LOCKDEP_WARN(ct_dynticks_nmi_nesting() <= 0, - "RCU dynticks_nmi_nesting counter underflow/zero!"); + "RCU nmi_nesting counter underflow/zero!"); /* Are we at first interrupt nesting level? */ nesting = ct_dynticks_nmi_nesting(); @@ -600,7 +600,7 @@ void rcu_irq_exit_check_preempt(void) "RCU nesting counter underflow/zero!"); RCU_LOCKDEP_WARN(ct_dynticks_nmi_nesting() != DYNTICK_IRQ_NONIDLE, - "Bad RCU dynticks_nmi_nesting counter\n"); + "Bad RCU nmi_nesting counter\n"); RCU_LOCKDEP_WARN(rcu_dynticks_curr_cpu_in_eqs(), "RCU in extended quiescent state!"); } -- cgit v1.2.3 From 8375cb260d7e43610934af63748d1a51201449f8 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Tue, 16 Apr 2024 14:46:14 +0200 Subject: context_tracking, rcu: Rename ct_dynticks_nmi_nesting() into ct_nmi_nesting() The context_tracking.state RCU_DYNTICKS subvariable has been renamed to RCU_WATCHING, and the 'dynticks' prefix can be dropped without losing any meaning. Suggested-by: Frederic Weisbecker Signed-off-by: Valentin Schneider Reviewed-by: Frederic Weisbecker Signed-off-by: Neeraj Upadhyay --- include/linux/context_tracking_state.h | 2 +- kernel/context_tracking.c | 24 ++++++++++++------------ kernel/rcu/tree.c | 6 +++--- 3 files changed, 16 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index 12d00adf29e1..8f32fe599c5c 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -87,7 +87,7 @@ static __always_inline long ct_nesting_cpu(int cpu) return ct->nesting; } -static __always_inline long ct_dynticks_nmi_nesting(void) +static __always_inline long ct_nmi_nesting(void) { return __this_cpu_read(context_tracking.nmi_nesting); } diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index ae94215aa132..115843eeb030 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -125,7 +125,7 @@ static void noinstr ct_kernel_exit(bool user, int offset) { struct context_tracking *ct = this_cpu_ptr(&context_tracking); - WARN_ON_ONCE(ct_dynticks_nmi_nesting() != DYNTICK_IRQ_NONIDLE); + WARN_ON_ONCE(ct_nmi_nesting() != DYNTICK_IRQ_NONIDLE); WRITE_ONCE(ct->nmi_nesting, 0); WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && ct_nesting() == 0); @@ -185,7 +185,7 @@ static void noinstr ct_kernel_enter(bool user, int offset) trace_rcu_dyntick(TPS("End"), ct_nesting(), 1, ct_rcu_watching()); WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current)); WRITE_ONCE(ct->nesting, 1); - WARN_ON_ONCE(ct_dynticks_nmi_nesting()); + WARN_ON_ONCE(ct_nmi_nesting()); WRITE_ONCE(ct->nmi_nesting, DYNTICK_IRQ_NONIDLE); instrumentation_end(); } @@ -207,28 +207,28 @@ void noinstr ct_nmi_exit(void) instrumentation_begin(); /* - * Check for ->nmi_nesting underflow and bad ->dynticks. + * Check for ->nmi_nesting underflow and bad CT state. * (We are exiting an NMI handler, so RCU better be paying attention * to us!) */ - WARN_ON_ONCE(ct_dynticks_nmi_nesting() <= 0); + WARN_ON_ONCE(ct_nmi_nesting() <= 0); WARN_ON_ONCE(rcu_dynticks_curr_cpu_in_eqs()); /* * If the nesting level is not 1, the CPU wasn't RCU-idle, so * leave it in non-RCU-idle state. */ - if (ct_dynticks_nmi_nesting() != 1) { - trace_rcu_dyntick(TPS("--="), ct_dynticks_nmi_nesting(), ct_dynticks_nmi_nesting() - 2, + if (ct_nmi_nesting() != 1) { + trace_rcu_dyntick(TPS("--="), ct_nmi_nesting(), ct_nmi_nesting() - 2, ct_rcu_watching()); WRITE_ONCE(ct->nmi_nesting, /* No store tearing. */ - ct_dynticks_nmi_nesting() - 2); + ct_nmi_nesting() - 2); instrumentation_end(); return; } /* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */ - trace_rcu_dyntick(TPS("Startirq"), ct_dynticks_nmi_nesting(), 0, ct_rcu_watching()); + trace_rcu_dyntick(TPS("Startirq"), ct_nmi_nesting(), 0, ct_rcu_watching()); WRITE_ONCE(ct->nmi_nesting, 0); /* Avoid store tearing. */ // instrumentation for the noinstr ct_kernel_exit_state() @@ -261,7 +261,7 @@ void noinstr ct_nmi_enter(void) struct context_tracking *ct = this_cpu_ptr(&context_tracking); /* Complain about underflow. */ - WARN_ON_ONCE(ct_dynticks_nmi_nesting() < 0); + WARN_ON_ONCE(ct_nmi_nesting() < 0); /* * If idle from RCU viewpoint, atomically increment CT state @@ -295,11 +295,11 @@ void noinstr ct_nmi_enter(void) } trace_rcu_dyntick(incby == 1 ? TPS("Endirq") : TPS("++="), - ct_dynticks_nmi_nesting(), - ct_dynticks_nmi_nesting() + incby, ct_rcu_watching()); + ct_nmi_nesting(), + ct_nmi_nesting() + incby, ct_rcu_watching()); instrumentation_end(); WRITE_ONCE(ct->nmi_nesting, /* Prevent store tearing. */ - ct_dynticks_nmi_nesting() + incby); + ct_nmi_nesting() + incby); barrier(); } diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 934f6b34a551..14cc314eedad 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -390,11 +390,11 @@ static int rcu_is_cpu_rrupt_from_idle(void) /* Check for counter underflows */ RCU_LOCKDEP_WARN(ct_nesting() < 0, "RCU nesting counter underflow!"); - RCU_LOCKDEP_WARN(ct_dynticks_nmi_nesting() <= 0, + RCU_LOCKDEP_WARN(ct_nmi_nesting() <= 0, "RCU nmi_nesting counter underflow/zero!"); /* Are we at first interrupt nesting level? */ - nesting = ct_dynticks_nmi_nesting(); + nesting = ct_nmi_nesting(); if (nesting > 1) return false; @@ -598,7 +598,7 @@ void rcu_irq_exit_check_preempt(void) RCU_LOCKDEP_WARN(ct_nesting() <= 0, "RCU nesting counter underflow/zero!"); - RCU_LOCKDEP_WARN(ct_dynticks_nmi_nesting() != + RCU_LOCKDEP_WARN(ct_nmi_nesting() != DYNTICK_IRQ_NONIDLE, "Bad RCU nmi_nesting counter\n"); RCU_LOCKDEP_WARN(rcu_dynticks_curr_cpu_in_eqs(), -- cgit v1.2.3 From 2ef2890b7a94fbbfa8fdf0a90499ae1df476b8e8 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Tue, 16 Apr 2024 14:49:13 +0200 Subject: context_tracking, rcu: Rename ct_dynticks_nmi_nesting_cpu() into ct_nmi_nesting_cpu() The context_tracking.state RCU_DYNTICKS subvariable has been renamed to RCU_WATCHING, and the 'dynticks' prefix can be dropped without losing any meaning. Suggested-by: Frederic Weisbecker Signed-off-by: Valentin Schneider Reviewed-by: Frederic Weisbecker Signed-off-by: Neeraj Upadhyay --- include/linux/context_tracking_state.h | 2 +- kernel/rcu/tree_stall.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index 8f32fe599c5c..34fd504e53a8 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -92,7 +92,7 @@ static __always_inline long ct_nmi_nesting(void) return __this_cpu_read(context_tracking.nmi_nesting); } -static __always_inline long ct_dynticks_nmi_nesting_cpu(int cpu) +static __always_inline long ct_nmi_nesting_cpu(int cpu) { struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index 59b1d84a4749..ec49f0155bec 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -516,7 +516,7 @@ static void print_cpu_stall_info(int cpu) "!."[!delta], ticks_value, ticks_title, ct_rcu_watching_cpu(cpu) & 0xffff, - ct_nesting_cpu(cpu), ct_dynticks_nmi_nesting_cpu(cpu), + ct_nesting_cpu(cpu), ct_nmi_nesting_cpu(cpu), rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu), data_race(rcu_state.n_force_qs) - rcu_state.n_force_qs_gpstart, rcuc_starved ? buf : "", -- cgit v1.2.3 From e1de438336222dbe27f2d4baa8c01074fcac2bef Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Mon, 29 Apr 2024 15:52:32 +0200 Subject: context_tracking, rcu: Rename DYNTICK_IRQ_NONIDLE into CT_NESTING_IRQ_NONIDLE The context_tracking.state RCU_DYNTICKS subvariable has been renamed to RCU_WATCHING, and the 'dynticks' prefix can be dropped without losing any meaning. Signed-off-by: Valentin Schneider Reviewed-by: Frederic Weisbecker Signed-off-by: Neeraj Upadhyay --- include/linux/context_tracking_state.h | 2 +- kernel/context_tracking.c | 8 ++++---- kernel/rcu/tree.c | 2 +- 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index 34fd504e53a8..0dbda59c9f37 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -7,7 +7,7 @@ #include /* Offset to allow distinguishing irq vs. task-based idle entry/exit. */ -#define DYNTICK_IRQ_NONIDLE ((LONG_MAX / 2) + 1) +#define CT_NESTING_IRQ_NONIDLE ((LONG_MAX / 2) + 1) enum ctx_state { CT_STATE_DISABLED = -1, /* returned by ct_state() if unknown */ diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 115843eeb030..8262f57a4363 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -29,7 +29,7 @@ DEFINE_PER_CPU(struct context_tracking, context_tracking) = { #ifdef CONFIG_CONTEXT_TRACKING_IDLE .nesting = 1, - .nmi_nesting = DYNTICK_IRQ_NONIDLE, + .nmi_nesting = CT_NESTING_IRQ_NONIDLE, #endif .state = ATOMIC_INIT(CT_RCU_WATCHING), }; @@ -125,7 +125,7 @@ static void noinstr ct_kernel_exit(bool user, int offset) { struct context_tracking *ct = this_cpu_ptr(&context_tracking); - WARN_ON_ONCE(ct_nmi_nesting() != DYNTICK_IRQ_NONIDLE); + WARN_ON_ONCE(ct_nmi_nesting() != CT_NESTING_IRQ_NONIDLE); WRITE_ONCE(ct->nmi_nesting, 0); WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && ct_nesting() == 0); @@ -156,7 +156,7 @@ static void noinstr ct_kernel_exit(bool user, int offset) * Exit an RCU extended quiescent state, which can be either the * idle loop or adaptive-tickless usermode execution. * - * We crowbar the ->nmi_nesting field to DYNTICK_IRQ_NONIDLE to + * We crowbar the ->nmi_nesting field to CT_NESTING_IRQ_NONIDLE to * allow for the possibility of usermode upcalls messing up our count of * interrupt nesting level during the busy period that is just now starting. */ @@ -186,7 +186,7 @@ static void noinstr ct_kernel_enter(bool user, int offset) WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current)); WRITE_ONCE(ct->nesting, 1); WARN_ON_ONCE(ct_nmi_nesting()); - WRITE_ONCE(ct->nmi_nesting, DYNTICK_IRQ_NONIDLE); + WRITE_ONCE(ct->nmi_nesting, CT_NESTING_IRQ_NONIDLE); instrumentation_end(); } diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 14cc314eedad..4778c873f4ac 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -599,7 +599,7 @@ void rcu_irq_exit_check_preempt(void) RCU_LOCKDEP_WARN(ct_nesting() <= 0, "RCU nesting counter underflow/zero!"); RCU_LOCKDEP_WARN(ct_nmi_nesting() != - DYNTICK_IRQ_NONIDLE, + CT_NESTING_IRQ_NONIDLE, "Bad RCU nmi_nesting counter\n"); RCU_LOCKDEP_WARN(rcu_dynticks_curr_cpu_in_eqs(), "RCU in extended quiescent state!"); -- cgit v1.2.3 From aa9fbc5dd9da9e095a8b1a58540cf20cb06f595f Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Thu, 8 Aug 2024 12:41:17 +0100 Subject: net: mii: constify advertising mask Constify the advertising mask to linkmode functions that only read from the advertising mask. Signed-off-by: Russell King (Oracle) Signed-off-by: David S. Miller --- include/linux/mii.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mii.h b/include/linux/mii.h index d5a959ce4877..b8f26d4513c3 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -140,7 +140,7 @@ static inline u32 ethtool_adv_to_mii_adv_t(u32 ethadv) * settings to phy autonegotiation advertisements for the * MII_ADVERTISE register. */ -static inline u32 linkmode_adv_to_mii_adv_t(unsigned long *advertising) +static inline u32 linkmode_adv_to_mii_adv_t(const unsigned long *advertising) { u32 result = 0; @@ -215,7 +215,8 @@ static inline u32 ethtool_adv_to_mii_ctrl1000_t(u32 ethadv) * settings to phy autonegotiation advertisements for the * MII_CTRL1000 register when in 1000T mode. */ -static inline u32 linkmode_adv_to_mii_ctrl1000_t(unsigned long *advertising) +static inline u32 +linkmode_adv_to_mii_ctrl1000_t(const unsigned long *advertising) { u32 result = 0; @@ -453,7 +454,7 @@ static inline void mii_ctrl1000_mod_linkmode_adv_t(unsigned long *advertising, * A small helper function that translates linkmode advertising to LVL * pause capabilities. */ -static inline u32 linkmode_adv_to_lcl_adv_t(unsigned long *advertising) +static inline u32 linkmode_adv_to_lcl_adv_t(const unsigned long *advertising) { u32 lcl_adv = 0; -- cgit v1.2.3 From d0f8a8973f265f6a276f99d091af99edfb2b87de Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Thu, 8 Aug 2024 00:14:13 +0000 Subject: mm/memblock: introduce a new helper memblock_estimated_nr_free_pages() During bootup, system may need the number of free pages in the whole system to do some calculation before all pages are freed to buddy system. Usually this number is get from totalram_pages(). Since we plan to move the free pages accounting in __free_pages_core(), this value may not represent total free pages at the early stage, especially when CONFIG_DEFERRED_STRUCT_PAGE_INIT is enabled. Instead of using raw memblock api, let's introduce a new helper for user to get the estimated number of free pages from memblock point of view. Signed-off-by: Wei Yang CC: David Hildenbrand Reviewed-by: David Hildenbrand Link: https://lore.kernel.org/r/20240808001415.6298-1-richard.weiyang@gmail.com Signed-off-by: Mike Rapoport (Microsoft) --- include/linux/memblock.h | 1 + mm/memblock.c | 17 +++++++++++++++++ tools/include/linux/pfn.h | 1 + 3 files changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index fc4d75c6cec3..673d5cae7c81 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -467,6 +467,7 @@ static inline __init_memblock bool memblock_bottom_up(void) phys_addr_t memblock_phys_mem_size(void); phys_addr_t memblock_reserved_size(void); +unsigned long memblock_estimated_nr_free_pages(void); phys_addr_t memblock_start_of_DRAM(void); phys_addr_t memblock_end_of_DRAM(void); void memblock_enforce_memory_limit(phys_addr_t memory_limit); diff --git a/mm/memblock.c b/mm/memblock.c index 3b9dc2d89b8a..213057603b65 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1731,6 +1731,23 @@ phys_addr_t __init_memblock memblock_reserved_size(void) return memblock.reserved.total_size; } +/** + * memblock_estimated_nr_free_pages - return estimated number of free pages + * from memblock point of view + * + * During bootup, subsystems might need a rough estimate of the number of free + * pages in the whole system, before precise numbers are available from the + * buddy. Especially with CONFIG_DEFERRED_STRUCT_PAGE_INIT, the numbers + * obtained from the buddy might be very imprecise during bootup. + * + * Return: + * An estimated number of free pages from memblock point of view. + */ +unsigned long __init memblock_estimated_nr_free_pages(void) +{ + return PHYS_PFN(memblock_phys_mem_size() - memblock_reserved_size()); +} + /* lowest address */ phys_addr_t __init_memblock memblock_start_of_DRAM(void) { diff --git a/tools/include/linux/pfn.h b/tools/include/linux/pfn.h index 7512a58189eb..f77a30d70152 100644 --- a/tools/include/linux/pfn.h +++ b/tools/include/linux/pfn.h @@ -7,4 +7,5 @@ #define PFN_UP(x) (((x) + PAGE_SIZE - 1) >> PAGE_SHIFT) #define PFN_DOWN(x) ((x) >> PAGE_SHIFT) #define PFN_PHYS(x) ((phys_addr_t)(x) << PAGE_SHIFT) +#define PHYS_PFN(x) ((unsigned long)((x) >> PAGE_SHIFT)) #endif -- cgit v1.2.3 From 8c38617722bdf57a90e6c77ed9ee5ebb60958d2a Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 9 Aug 2024 16:15:54 +0200 Subject: memory: ti-aemif: remove platform data support There are no longer any users of the ti-aemif driver that set up platform data from board files. We can shrink the driver by removing support for it. Signed-off-by: Bartosz Golaszewski Link: https://lore.kernel.org/r/20240809-ti-aemif-v1-1-27b1e5001390@linaro.org Signed-off-by: Krzysztof Kozlowski --- drivers/memory/ti-aemif.c | 25 +------------------ include/linux/platform_data/ti-aemif.h | 45 ---------------------------------- 2 files changed, 1 insertion(+), 69 deletions(-) delete mode 100644 include/linux/platform_data/ti-aemif.h (limited to 'include/linux') diff --git a/drivers/memory/ti-aemif.c b/drivers/memory/ti-aemif.c index e192db9e0e4b..b92cab455cbb 100644 --- a/drivers/memory/ti-aemif.c +++ b/drivers/memory/ti-aemif.c @@ -17,7 +17,6 @@ #include #include #include -#include #define TA_SHIFT 2 #define RHOLD_SHIFT 4 @@ -332,16 +331,11 @@ static int aemif_probe(struct platform_device *pdev) struct device_node *np = dev->of_node; struct device_node *child_np; struct aemif_device *aemif; - struct aemif_platform_data *pdata; - struct of_dev_auxdata *dev_lookup; aemif = devm_kzalloc(dev, sizeof(*aemif), GFP_KERNEL); if (!aemif) return -ENOMEM; - pdata = dev_get_platdata(&pdev->dev); - dev_lookup = pdata ? pdata->dev_lookup : NULL; - platform_set_drvdata(pdev, aemif); aemif->clk = devm_clk_get(dev, NULL); @@ -358,8 +352,6 @@ static int aemif_probe(struct platform_device *pdev) if (np && of_device_is_compatible(np, "ti,da850-aemif")) aemif->cs_offset = 2; - else if (pdata) - aemif->cs_offset = pdata->cs_offset; aemif->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(aemif->base)) { @@ -381,11 +373,6 @@ static int aemif_probe(struct platform_device *pdev) goto error; } } - } else if (pdata && pdata->num_abus_data > 0) { - for (i = 0; i < pdata->num_abus_data; i++, aemif->num_cs++) { - aemif->cs_data[i].cs = pdata->abus_data[i].cs; - aemif_get_hw_params(pdev, i); - } } for (i = 0; i < aemif->num_cs; i++) { @@ -403,22 +390,12 @@ static int aemif_probe(struct platform_device *pdev) */ if (np) { for_each_available_child_of_node(np, child_np) { - ret = of_platform_populate(child_np, NULL, - dev_lookup, dev); + ret = of_platform_populate(child_np, NULL, NULL, dev); if (ret < 0) { of_node_put(child_np); goto error; } } - } else if (pdata) { - for (i = 0; i < pdata->num_sub_devices; i++) { - pdata->sub_devices[i].dev.parent = dev; - ret = platform_device_register(&pdata->sub_devices[i]); - if (ret) { - dev_warn(dev, "Error register sub device %s\n", - pdata->sub_devices[i].name); - } - } } return 0; diff --git a/include/linux/platform_data/ti-aemif.h b/include/linux/platform_data/ti-aemif.h deleted file mode 100644 index 77625251df07..000000000000 --- a/include/linux/platform_data/ti-aemif.h +++ /dev/null @@ -1,45 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * TI DaVinci AEMIF platform glue. - * - * Copyright (C) 2017 BayLibre SAS - * - * Author: - * Bartosz Golaszewski - */ - -#ifndef __TI_DAVINCI_AEMIF_DATA_H__ -#define __TI_DAVINCI_AEMIF_DATA_H__ - -#include - -/** - * struct aemif_abus_data - Async bus configuration parameters. - * - * @cs - Chip-select number. - */ -struct aemif_abus_data { - u32 cs; -}; - -/** - * struct aemif_platform_data - Data to set up the TI aemif driver. - * - * @dev_lookup: of_dev_auxdata passed to of_platform_populate() for aemif - * subdevices. - * @cs_offset: Lowest allowed chip-select number. - * @abus_data: Array of async bus configuration entries. - * @num_abus_data: Number of abus entries. - * @sub_devices: Array of platform subdevices. - * @num_sub_devices: Number of subdevices. - */ -struct aemif_platform_data { - struct of_dev_auxdata *dev_lookup; - u32 cs_offset; - struct aemif_abus_data *abus_data; - size_t num_abus_data; - struct platform_device *sub_devices; - size_t num_sub_devices; -}; - -#endif /* __TI_DAVINCI_AEMIF_DATA_H__ */ -- cgit v1.2.3 From ce056504e2e53b22c1f789cff2ad6a0a135dc24d Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 9 Aug 2024 22:37:20 -0700 Subject: ethtool: make ethtool_ops::cap_rss_ctx_supported optional cap_rss_ctx_supported was created because the API for creating and configuring additional contexts is mux'ed with the normal RSS API. Presence of ops does not imply driver can actually support rss_context != 0 (in fact drivers mostly ignore that field). cap_rss_ctx_supported lets core check that the driver is context-aware before calling it. Now that we have .create_rxfh_context, there is no such ambiguity. We can depend on presence of the op. Make setting the bit optional. Reviewed-by: Gal Pressman Reviewed-by: Edward Cree Reviewed-by: Joe Damato Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/ethtool.h | 3 ++- net/ethtool/ioctl.c | 6 ++++-- net/ethtool/rss.c | 3 ++- 3 files changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 989c94eddb2b..a149485904d8 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -727,7 +727,8 @@ struct kernel_ethtool_ts_info { * @cap_link_lanes_supported: indicates if the driver supports lanes * parameter. * @cap_rss_ctx_supported: indicates if the driver supports RSS - * contexts. + * contexts via legacy API, drivers implementing @create_rxfh_context + * do not have to set this bit. * @cap_rss_sym_xor_supported: indicates if the driver supports symmetric-xor * RSS. * @rxfh_indir_space: max size of RSS indirection tables, if indirection table diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index ba8630eb02ef..1698b73812ce 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1227,7 +1227,8 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev, if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd32) return -EINVAL; /* Most drivers don't handle rss_context, check it's 0 as well */ - if (rxfh.rss_context && !ops->cap_rss_ctx_supported) + if (rxfh.rss_context && !(ops->cap_rss_ctx_supported || + ops->create_rxfh_context)) return -EOPNOTSUPP; rxfh.indir_size = rxfh_dev.indir_size; @@ -1357,7 +1358,8 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd32) return -EINVAL; /* Most drivers don't handle rss_context, check it's 0 as well */ - if (rxfh.rss_context && !ops->cap_rss_ctx_supported) + if (rxfh.rss_context && !(ops->cap_rss_ctx_supported || + ops->create_rxfh_context)) return -EOPNOTSUPP; /* Check input data transformation capabilities */ if (rxfh.input_xfrm && rxfh.input_xfrm != RXH_XFRM_SYM_XOR && diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c index 5c4c4505ab9a..a06bdac8b8a2 100644 --- a/net/ethtool/rss.c +++ b/net/ethtool/rss.c @@ -60,7 +60,8 @@ rss_prepare_data(const struct ethnl_req_info *req_base, return -EOPNOTSUPP; /* Some drivers don't handle rss_context */ - if (request->rss_context && !ops->cap_rss_ctx_supported) + if (request->rss_context && !(ops->cap_rss_ctx_supported || + ops->create_rxfh_context)) return -EOPNOTSUPP; ret = ethnl_ops_begin(dev); -- cgit v1.2.3 From ec6e57beaf8bc64ea0c2dc0cc360afcc7f504425 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 9 Aug 2024 22:37:22 -0700 Subject: ethtool: rss: don't report key if device doesn't support it marvell/otx2 and mvpp2 do not support setting different keys for different RSS contexts. Contexts have separate indirection tables but key is shared with all other contexts. This is likely fine, indirection table is the most important piece. Don't report the key-related parameters from such drivers. This prevents driver-errors, e.g. otx2 always writes the main key, even when user asks to change per-context key. The second reason is that without this change tracking the keys by the core gets complicated. Even if the driver correctly reject setting key with rss_context != 0, change of the main key would have to be reflected in the XArray for all additional contexts. Since the additional contexts don't have their own keys not including the attributes (in Netlink speak) seems intuitive. ethtool CLI seems to deal with it just fine. Having to set the flag in majority of the drivers is a bit tedious but not reporting the key is a safer default. Reviewed-by: Edward Cree Reviewed-by: Joe Damato Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 1 + drivers/net/ethernet/intel/ice/ice_ethtool.c | 1 + .../net/ethernet/mellanox/mlx5/core/en_ethtool.c | 1 + drivers/net/ethernet/sfc/ef100_ethtool.c | 1 + drivers/net/ethernet/sfc/ethtool.c | 1 + include/linux/ethtool.h | 4 ++++ net/ethtool/ioctl.c | 25 ++++++++++++++++++---- net/ethtool/rss.c | 21 ++++++++++++------ 8 files changed, 45 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 44076e4ebf1a..61d6afc3cacb 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -5289,6 +5289,7 @@ void bnxt_ethtool_free(struct bnxt *bp) const struct ethtool_ops bnxt_ethtool_ops = { .cap_link_lanes_supported = 1, + .rxfh_per_ctx_key = 1, .rxfh_max_num_contexts = BNXT_MAX_ETH_RSS_CTX + 1, .rxfh_indir_space = BNXT_MAX_RSS_TABLE_ENTRIES_P5, .rxfh_priv_size = sizeof(struct bnxt_rss_ctx), diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index bc79ba974e49..c7641d326ba5 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -4725,6 +4725,7 @@ static const struct ethtool_ops ice_ethtool_ops = { ETHTOOL_COALESCE_USE_ADAPTIVE | ETHTOOL_COALESCE_RX_USECS_HIGH, .cap_rss_sym_xor_supported = true, + .rxfh_per_ctx_key = true, .get_link_ksettings = ice_get_link_ksettings, .set_link_ksettings = ice_set_link_ksettings, .get_fec_stats = ice_get_fec_stats, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 8af509397f63..4d123dae912c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -2595,6 +2595,7 @@ static void mlx5e_get_ts_stats(struct net_device *netdev, const struct ethtool_ops mlx5e_ethtool_ops = { .cap_rss_ctx_supported = true, + .rxfh_per_ctx_key = true, .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_MAX_FRAMES | ETHTOOL_COALESCE_USE_ADAPTIVE | diff --git a/drivers/net/ethernet/sfc/ef100_ethtool.c b/drivers/net/ethernet/sfc/ef100_ethtool.c index 746b5314acb5..5c2551369812 100644 --- a/drivers/net/ethernet/sfc/ef100_ethtool.c +++ b/drivers/net/ethernet/sfc/ef100_ethtool.c @@ -58,6 +58,7 @@ const struct ethtool_ops ef100_ethtool_ops = { .get_rxfh_indir_size = efx_ethtool_get_rxfh_indir_size, .get_rxfh_key_size = efx_ethtool_get_rxfh_key_size, + .rxfh_per_ctx_key = true, .rxfh_priv_size = sizeof(struct efx_rss_context_priv), .get_rxfh = efx_ethtool_get_rxfh, .set_rxfh = efx_ethtool_set_rxfh, diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c index 15245720c949..848b1923133a 100644 --- a/drivers/net/ethernet/sfc/ethtool.c +++ b/drivers/net/ethernet/sfc/ethtool.c @@ -267,6 +267,7 @@ const struct ethtool_ops efx_ethtool_ops = { .set_rxnfc = efx_ethtool_set_rxnfc, .get_rxfh_indir_size = efx_ethtool_get_rxfh_indir_size, .get_rxfh_key_size = efx_ethtool_get_rxfh_key_size, + .rxfh_per_ctx_key = true, .rxfh_priv_size = sizeof(struct efx_rss_context_priv), .get_rxfh = efx_ethtool_get_rxfh, .set_rxfh = efx_ethtool_set_rxfh, diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index a149485904d8..12f6dc567598 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -731,6 +731,9 @@ struct kernel_ethtool_ts_info { * do not have to set this bit. * @cap_rss_sym_xor_supported: indicates if the driver supports symmetric-xor * RSS. + * @rxfh_per_ctx_key: device supports setting different RSS key for each + * additional context. Netlink API should report hfunc, key, and input_xfrm + * for every context, not just context 0. * @rxfh_indir_space: max size of RSS indirection tables, if indirection table * size as returned by @get_rxfh_indir_size may change during lifetime * of the device. Leave as 0 if the table size is constant. @@ -952,6 +955,7 @@ struct ethtool_ops { u32 cap_link_lanes_supported:1; u32 cap_rss_ctx_supported:1; u32 cap_rss_sym_xor_supported:1; + u32 rxfh_per_ctx_key:1; u32 rxfh_indir_space; u16 rxfh_key_space; u16 rxfh_priv_size; diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 1698b73812ce..18cf9fa32ae3 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1261,10 +1261,15 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev, if (rxfh_dev.indir) memcpy(rxfh_dev.indir, ethtool_rxfh_context_indir(ctx), indir_bytes); - if (rxfh_dev.key) - memcpy(rxfh_dev.key, ethtool_rxfh_context_key(ctx), - user_key_size); - rxfh_dev.hfunc = ctx->hfunc; + if (!ops->rxfh_per_ctx_key) { + rxfh_dev.key_size = 0; + } else { + if (rxfh_dev.key) + memcpy(rxfh_dev.key, + ethtool_rxfh_context_key(ctx), + user_key_size); + rxfh_dev.hfunc = ctx->hfunc; + } rxfh_dev.input_xfrm = ctx->input_xfrm; ret = 0; } else { @@ -1281,6 +1286,11 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev, &rxfh_dev.input_xfrm, sizeof(rxfh.input_xfrm))) { ret = -EFAULT; + } else if (copy_to_user(useraddr + + offsetof(struct ethtool_rxfh, key_size), + &rxfh_dev.key_size, + sizeof(rxfh.key_size))) { + ret = -EFAULT; } else if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh, rss_config[0]), rss_config, total_size)) { @@ -1389,6 +1399,13 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, indir_bytes = dev_indir_size * sizeof(rxfh_dev.indir[0]); + /* Check settings which may be global rather than per RSS-context */ + if (rxfh.rss_context && !ops->rxfh_per_ctx_key) + if (rxfh.key_size || + (rxfh.hfunc && rxfh.hfunc != ETH_RSS_HASH_NO_CHANGE) || + (rxfh.input_xfrm && rxfh.input_xfrm != RXH_XFRM_NO_CHANGE)) + return -EOPNOTSUPP; + rss_config = kzalloc(indir_bytes + dev_key_size, GFP_USER); if (!rss_config) return -ENOMEM; diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c index a06bdac8b8a2..cd8100d81919 100644 --- a/net/ethtool/rss.c +++ b/net/ethtool/rss.c @@ -10,6 +10,7 @@ struct rss_req_info { struct rss_reply_data { struct ethnl_reply_data base; + bool no_key_fields; u32 indir_size; u32 hkey_size; u32 hfunc; @@ -60,9 +61,12 @@ rss_prepare_data(const struct ethnl_req_info *req_base, return -EOPNOTSUPP; /* Some drivers don't handle rss_context */ - if (request->rss_context && !(ops->cap_rss_ctx_supported || - ops->create_rxfh_context)) - return -EOPNOTSUPP; + if (request->rss_context) { + if (!ops->cap_rss_ctx_supported && !ops->create_rxfh_context) + return -EOPNOTSUPP; + + data->no_key_fields = !ops->rxfh_per_ctx_key; + } ret = ethnl_ops_begin(dev); if (ret < 0) @@ -132,13 +136,18 @@ rss_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, nla_put_u32(skb, ETHTOOL_A_RSS_CONTEXT, request->rss_context)) return -EMSGSIZE; + if ((data->indir_size && + nla_put(skb, ETHTOOL_A_RSS_INDIR, + sizeof(u32) * data->indir_size, data->indir_table))) + return -EMSGSIZE; + + if (data->no_key_fields) + return 0; + if ((data->hfunc && nla_put_u32(skb, ETHTOOL_A_RSS_HFUNC, data->hfunc)) || (data->input_xfrm && nla_put_u32(skb, ETHTOOL_A_RSS_INPUT_XFRM, data->input_xfrm)) || - (data->indir_size && - nla_put(skb, ETHTOOL_A_RSS_INDIR, - sizeof(u32) * data->indir_size, data->indir_table)) || (data->hkey_size && nla_put(skb, ETHTOOL_A_RSS_HKEY, data->hkey_size, data->hkey))) return -EMSGSIZE; -- cgit v1.2.3 From fc9aef4382c02774662da3d7e1de8ba224e04f80 Mon Sep 17 00:00:00 2001 From: "David E. Box" Date: Thu, 25 Jul 2024 08:23:40 -0400 Subject: platform/x86/intel/vsec.h: Move to include/linux MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some drivers outside of PDX86 need access to the vsec header. Move it to include/linux to make it easier to include. Reviewed-by: Ilpo Järvinen Reviewed-by: Michael J. Ruhl Signed-off-by: David E. Box Link: https://lore.kernel.org/r/20240725122346.4063913-2-michael.j.ruhl@intel.com Signed-off-by: Hans de Goede --- MAINTAINERS | 3 +- drivers/platform/x86/intel/pmc/core_ssram.c | 2 +- drivers/platform/x86/intel/pmt/class.c | 2 +- drivers/platform/x86/intel/pmt/class.h | 2 +- drivers/platform/x86/intel/pmt/crashlog.c | 2 +- drivers/platform/x86/intel/pmt/telemetry.c | 2 +- drivers/platform/x86/intel/sdsi.c | 3 +- drivers/platform/x86/intel/tpmi.c | 3 +- drivers/platform/x86/intel/vsec.c | 7 +- drivers/platform/x86/intel/vsec.h | 108 ---------------------- include/linux/intel_vsec.h | 134 ++++++++++++++++++++++++++++ 11 files changed, 146 insertions(+), 122 deletions(-) delete mode 100644 drivers/platform/x86/intel/vsec.h create mode 100644 include/linux/intel_vsec.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 42decde38320..894608f6555c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11599,7 +11599,8 @@ F: drivers/platform/x86/intel/uncore-frequency/ INTEL VENDOR SPECIFIC EXTENDED CAPABILITIES DRIVER M: David E. Box S: Supported -F: drivers/platform/x86/intel/vsec.* +F: drivers/platform/x86/intel/vsec.c +F: include/linux/intel_vsec.h INTEL VIRTUAL BUTTON DRIVER M: AceLan Kao diff --git a/drivers/platform/x86/intel/pmc/core_ssram.c b/drivers/platform/x86/intel/pmc/core_ssram.c index 1bde86c54eb9..baddaaec25ee 100644 --- a/drivers/platform/x86/intel/pmc/core_ssram.c +++ b/drivers/platform/x86/intel/pmc/core_ssram.c @@ -9,11 +9,11 @@ */ #include +#include #include #include #include "core.h" -#include "../vsec.h" #include "../pmt/telemetry.h" #define SSRAM_HDR_SIZE 0x100 diff --git a/drivers/platform/x86/intel/pmt/class.c b/drivers/platform/x86/intel/pmt/class.c index 4b53940a64e2..d7939b28e937 100644 --- a/drivers/platform/x86/intel/pmt/class.c +++ b/drivers/platform/x86/intel/pmt/class.c @@ -9,12 +9,12 @@ */ #include +#include #include #include #include #include -#include "../vsec.h" #include "class.h" #define PMT_XA_START 1 diff --git a/drivers/platform/x86/intel/pmt/class.h b/drivers/platform/x86/intel/pmt/class.h index d23c63b73ab7..d6f9ccaf28c8 100644 --- a/drivers/platform/x86/intel/pmt/class.h +++ b/drivers/platform/x86/intel/pmt/class.h @@ -2,13 +2,13 @@ #ifndef _INTEL_PMT_CLASS_H #define _INTEL_PMT_CLASS_H +#include #include #include #include #include #include -#include "../vsec.h" #include "telemetry.h" /* PMT access types */ diff --git a/drivers/platform/x86/intel/pmt/crashlog.c b/drivers/platform/x86/intel/pmt/crashlog.c index 4014c02cafdb..9079d5dffc03 100644 --- a/drivers/platform/x86/intel/pmt/crashlog.c +++ b/drivers/platform/x86/intel/pmt/crashlog.c @@ -9,6 +9,7 @@ */ #include +#include #include #include #include @@ -16,7 +17,6 @@ #include #include -#include "../vsec.h" #include "class.h" /* Crashlog discovery header types */ diff --git a/drivers/platform/x86/intel/pmt/telemetry.c b/drivers/platform/x86/intel/pmt/telemetry.c index 09258564dfc4..3478f891ea0b 100644 --- a/drivers/platform/x86/intel/pmt/telemetry.c +++ b/drivers/platform/x86/intel/pmt/telemetry.c @@ -9,6 +9,7 @@ */ #include +#include #include #include #include @@ -16,7 +17,6 @@ #include #include -#include "../vsec.h" #include "class.h" #define TELEM_SIZE_OFFSET 0x0 diff --git a/drivers/platform/x86/intel/sdsi.c b/drivers/platform/x86/intel/sdsi.c index 277e4f4b20ac..9d137621f0e6 100644 --- a/drivers/platform/x86/intel/sdsi.c +++ b/drivers/platform/x86/intel/sdsi.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -22,8 +23,6 @@ #include #include -#include "vsec.h" - #define ACCESS_TYPE_BARID 2 #define ACCESS_TYPE_LOCAL 3 diff --git a/drivers/platform/x86/intel/tpmi.c b/drivers/platform/x86/intel/tpmi.c index 83e8b1fe53b3..486ddc9b3592 100644 --- a/drivers/platform/x86/intel/tpmi.c +++ b/drivers/platform/x86/intel/tpmi.c @@ -51,6 +51,7 @@ #include #include #include +#include #include #include #include @@ -59,8 +60,6 @@ #include #include -#include "vsec.h" - /** * struct intel_tpmi_pfs_entry - TPMI PM Feature Structure (PFS) entry * @tpmi_id: TPMI feature identifier (what the feature is and its data format). diff --git a/drivers/platform/x86/intel/vsec.c b/drivers/platform/x86/intel/vsec.c index 0fdfaf3a4f5c..2b46807f868b 100644 --- a/drivers/platform/x86/intel/vsec.c +++ b/drivers/platform/x86/intel/vsec.c @@ -17,14 +17,13 @@ #include #include #include -#include #include +#include +#include #include #include #include -#include "vsec.h" - #define PMT_XA_START 0 #define PMT_XA_MAX INT_MAX #define PMT_XA_LIMIT XA_LIMIT(PMT_XA_START, PMT_XA_MAX) @@ -341,7 +340,7 @@ static bool intel_vsec_walk_vsec(struct pci_dev *pdev, void intel_vsec_register(struct pci_dev *pdev, struct intel_vsec_platform_info *info) { - if (!pdev || !info) + if (!pdev || !info || !info->headers) return; intel_vsec_walk_header(pdev, info); diff --git a/drivers/platform/x86/intel/vsec.h b/drivers/platform/x86/intel/vsec.h deleted file mode 100644 index e23e76129691..000000000000 --- a/drivers/platform/x86/intel/vsec.h +++ /dev/null @@ -1,108 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _VSEC_H -#define _VSEC_H - -#include -#include - -#define VSEC_CAP_TELEMETRY BIT(0) -#define VSEC_CAP_WATCHER BIT(1) -#define VSEC_CAP_CRASHLOG BIT(2) -#define VSEC_CAP_SDSI BIT(3) -#define VSEC_CAP_TPMI BIT(4) - -/* Intel DVSEC offsets */ -#define INTEL_DVSEC_ENTRIES 0xA -#define INTEL_DVSEC_SIZE 0xB -#define INTEL_DVSEC_TABLE 0xC -#define INTEL_DVSEC_TABLE_BAR(x) ((x) & GENMASK(2, 0)) -#define INTEL_DVSEC_TABLE_OFFSET(x) ((x) & GENMASK(31, 3)) -#define TABLE_OFFSET_SHIFT 3 - -struct pci_dev; -struct resource; - -enum intel_vsec_id { - VSEC_ID_TELEMETRY = 2, - VSEC_ID_WATCHER = 3, - VSEC_ID_CRASHLOG = 4, - VSEC_ID_SDSI = 65, - VSEC_ID_TPMI = 66, -}; - -/** - * struct intel_vsec_header - Common fields of Intel VSEC and DVSEC registers. - * @rev: Revision ID of the VSEC/DVSEC register space - * @length: Length of the VSEC/DVSEC register space - * @id: ID of the feature - * @num_entries: Number of instances of the feature - * @entry_size: Size of the discovery table for each feature - * @tbir: BAR containing the discovery tables - * @offset: BAR offset of start of the first discovery table - */ -struct intel_vsec_header { - u8 rev; - u16 length; - u16 id; - u8 num_entries; - u8 entry_size; - u8 tbir; - u32 offset; -}; - -enum intel_vsec_quirks { - /* Watcher feature not supported */ - VSEC_QUIRK_NO_WATCHER = BIT(0), - - /* Crashlog feature not supported */ - VSEC_QUIRK_NO_CRASHLOG = BIT(1), - - /* Use shift instead of mask to read discovery table offset */ - VSEC_QUIRK_TABLE_SHIFT = BIT(2), - - /* DVSEC not present (provided in driver data) */ - VSEC_QUIRK_NO_DVSEC = BIT(3), - - /* Platforms requiring quirk in the auxiliary driver */ - VSEC_QUIRK_EARLY_HW = BIT(4), -}; - -/* Platform specific data */ -struct intel_vsec_platform_info { - struct device *parent; - struct intel_vsec_header **headers; - unsigned long caps; - unsigned long quirks; - u64 base_addr; -}; - -struct intel_vsec_device { - struct auxiliary_device auxdev; - struct pci_dev *pcidev; - struct resource *resource; - struct ida *ida; - int num_resources; - int id; /* xa */ - void *priv_data; - size_t priv_data_size; - unsigned long quirks; - u64 base_addr; -}; - -int intel_vsec_add_aux(struct pci_dev *pdev, struct device *parent, - struct intel_vsec_device *intel_vsec_dev, - const char *name); - -static inline struct intel_vsec_device *dev_to_ivdev(struct device *dev) -{ - return container_of(dev, struct intel_vsec_device, auxdev.dev); -} - -static inline struct intel_vsec_device *auxdev_to_ivdev(struct auxiliary_device *auxdev) -{ - return container_of(auxdev, struct intel_vsec_device, auxdev); -} - -void intel_vsec_register(struct pci_dev *pdev, - struct intel_vsec_platform_info *info); -#endif diff --git a/include/linux/intel_vsec.h b/include/linux/intel_vsec.h new file mode 100644 index 000000000000..6495e37c9079 --- /dev/null +++ b/include/linux/intel_vsec.h @@ -0,0 +1,134 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _INTEL_VSEC_H +#define _INTEL_VSEC_H + +#include +#include + +#define VSEC_CAP_TELEMETRY BIT(0) +#define VSEC_CAP_WATCHER BIT(1) +#define VSEC_CAP_CRASHLOG BIT(2) +#define VSEC_CAP_SDSI BIT(3) +#define VSEC_CAP_TPMI BIT(4) + +/* Intel DVSEC offsets */ +#define INTEL_DVSEC_ENTRIES 0xA +#define INTEL_DVSEC_SIZE 0xB +#define INTEL_DVSEC_TABLE 0xC +#define INTEL_DVSEC_TABLE_BAR(x) ((x) & GENMASK(2, 0)) +#define INTEL_DVSEC_TABLE_OFFSET(x) ((x) & GENMASK(31, 3)) +#define TABLE_OFFSET_SHIFT 3 + +struct pci_dev; +struct resource; + +enum intel_vsec_id { + VSEC_ID_TELEMETRY = 2, + VSEC_ID_WATCHER = 3, + VSEC_ID_CRASHLOG = 4, + VSEC_ID_SDSI = 65, + VSEC_ID_TPMI = 66, +}; + +/** + * struct intel_vsec_header - Common fields of Intel VSEC and DVSEC registers. + * @rev: Revision ID of the VSEC/DVSEC register space + * @length: Length of the VSEC/DVSEC register space + * @id: ID of the feature + * @num_entries: Number of instances of the feature + * @entry_size: Size of the discovery table for each feature + * @tbir: BAR containing the discovery tables + * @offset: BAR offset of start of the first discovery table + */ +struct intel_vsec_header { + u8 rev; + u16 length; + u16 id; + u8 num_entries; + u8 entry_size; + u8 tbir; + u32 offset; +}; + +enum intel_vsec_quirks { + /* Watcher feature not supported */ + VSEC_QUIRK_NO_WATCHER = BIT(0), + + /* Crashlog feature not supported */ + VSEC_QUIRK_NO_CRASHLOG = BIT(1), + + /* Use shift instead of mask to read discovery table offset */ + VSEC_QUIRK_TABLE_SHIFT = BIT(2), + + /* DVSEC not present (provided in driver data) */ + VSEC_QUIRK_NO_DVSEC = BIT(3), + + /* Platforms requiring quirk in the auxiliary driver */ + VSEC_QUIRK_EARLY_HW = BIT(4), +}; + +/** + * struct intel_vsec_platform_info - Platform specific data + * @parent: parent device in the auxbus chain + * @headers: list of headers to define the PMT client devices to create + * @caps: bitmask of PMT capabilities for the given headers + * @quirks: bitmask of VSEC device quirks + * @base_addr: allow a base address to be specified (rather than derived) + */ +struct intel_vsec_platform_info { + struct device *parent; + struct intel_vsec_header **headers; + unsigned long caps; + unsigned long quirks; + u64 base_addr; +}; + +/** + * struct intel_sec_device - Auxbus specific device information + * @auxdev: auxbus device struct for auxbus access + * @pcidev: pci device associated with the device + * @resource: any resources shared by the parent + * @ida: id reference + * @num_resources: number of resources + * @id: xarray id + * @priv_data: any private data needed + * @quirks: specified quirks + * @base_addr: base address of entries (if specified) + */ +struct intel_vsec_device { + struct auxiliary_device auxdev; + struct pci_dev *pcidev; + struct resource *resource; + struct ida *ida; + int num_resources; + int id; /* xa */ + void *priv_data; + size_t priv_data_size; + unsigned long quirks; + u64 base_addr; +}; + +int intel_vsec_add_aux(struct pci_dev *pdev, struct device *parent, + struct intel_vsec_device *intel_vsec_dev, + const char *name); + +static inline struct intel_vsec_device *dev_to_ivdev(struct device *dev) +{ + return container_of(dev, struct intel_vsec_device, auxdev.dev); +} + +static inline struct intel_vsec_device *auxdev_to_ivdev(struct auxiliary_device *auxdev) +{ + return container_of(auxdev, struct intel_vsec_device, auxdev); +} + +#if IS_ENABLED(CONFIG_INTEL_VSEC) +void intel_vsec_register(struct pci_dev *pdev, + struct intel_vsec_platform_info *info); +#else +static inline void intel_vsec_register(struct pci_dev *pdev, + struct intel_vsec_platform_info *info) +{ +} +#endif +#endif -- cgit v1.2.3 From e92affc74cd8624a548b380af7364be037adef35 Mon Sep 17 00:00:00 2001 From: "David E. Box" Date: Thu, 25 Jul 2024 08:23:41 -0400 Subject: platform/x86/intel/vsec: Add PMT read callbacks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some PMT providers require device specific actions before their telemetry can be read. Provide assignable PMT read callbacks to allow providers to perform those actions. Reviewed-by: Ilpo Järvinen Reviewed-by: Michael J. Ruhl Signed-off-by: David E. Box Link: https://lore.kernel.org/r/20240725122346.4063913-3-michael.j.ruhl@intel.com Signed-off-by: Hans de Goede --- drivers/platform/x86/intel/vsec.c | 1 + include/linux/intel_vsec.h | 15 +++++++++++++++ 2 files changed, 16 insertions(+) (limited to 'include/linux') diff --git a/drivers/platform/x86/intel/vsec.c b/drivers/platform/x86/intel/vsec.c index 2b46807f868b..7b5cc9993974 100644 --- a/drivers/platform/x86/intel/vsec.c +++ b/drivers/platform/x86/intel/vsec.c @@ -212,6 +212,7 @@ static int intel_vsec_add_dev(struct pci_dev *pdev, struct intel_vsec_header *he intel_vsec_dev->num_resources = header->num_entries; intel_vsec_dev->quirks = info->quirks; intel_vsec_dev->base_addr = info->base_addr; + intel_vsec_dev->priv_data = info->priv_data; if (header->id == VSEC_ID_SDSI) intel_vsec_dev->ida = &intel_vsec_sdsi_ida; diff --git a/include/linux/intel_vsec.h b/include/linux/intel_vsec.h index 6495e37c9079..11ee185566c3 100644 --- a/include/linux/intel_vsec.h +++ b/include/linux/intel_vsec.h @@ -67,10 +67,24 @@ enum intel_vsec_quirks { VSEC_QUIRK_EARLY_HW = BIT(4), }; +/** + * struct pmt_callbacks - Callback infrastructure for PMT devices + * ->read_telem() when specified, called by client driver to access PMT data (instead + * of direct copy). + * @pdev: PCI device reference for the callback's use + * @guid: ID of data to acccss + * @data: buffer for the data to be copied + * @count: size of buffer + */ +struct pmt_callbacks { + int (*read_telem)(struct pci_dev *pdev, u32 guid, u64 *data, u32 count); +}; + /** * struct intel_vsec_platform_info - Platform specific data * @parent: parent device in the auxbus chain * @headers: list of headers to define the PMT client devices to create + * @priv_data: private data, usable by parent devices, currently a callback * @caps: bitmask of PMT capabilities for the given headers * @quirks: bitmask of VSEC device quirks * @base_addr: allow a base address to be specified (rather than derived) @@ -78,6 +92,7 @@ enum intel_vsec_quirks { struct intel_vsec_platform_info { struct device *parent; struct intel_vsec_header **headers; + void *priv_data; unsigned long caps; unsigned long quirks; u64 base_addr; -- cgit v1.2.3 From 29bc83e4d90546aa794a9584786086b141a6ba4d Mon Sep 17 00:00:00 2001 From: JP Kobryn Date: Mon, 15 Jul 2024 16:23:24 -0700 Subject: srcu: faster gp seq wrap-around Using a higher value for the initial gp sequence counters allows for wrapping to occur faster. It can help with surfacing any issues that may be happening as a result of the wrap around. Signed-off-by: JP Kobryn Tested-by: Paul E. McKenney Signed-off-by: Neeraj Upadhyay --- include/linux/rcupdate.h | 3 +++ include/linux/srcutree.h | 15 ++++++++++++++- kernel/rcu/rcu.h | 3 --- kernel/rcu/srcutree.c | 7 ++++--- 4 files changed, 21 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 13f6f00aecf9..8d56db70d417 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -34,6 +34,9 @@ #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) +#define RCU_SEQ_CTR_SHIFT 2 +#define RCU_SEQ_STATE_MASK ((1 << RCU_SEQ_CTR_SHIFT) - 1) + /* Exported common interfaces */ void call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier_tasks(void); diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 8f3f72480e78..ed57598394de 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -129,10 +129,23 @@ struct srcu_struct { #define SRCU_STATE_SCAN1 1 #define SRCU_STATE_SCAN2 2 +/* + * Values for initializing gp sequence fields. Higher values allow wrap arounds to + * occur earlier. + * The second value with state is useful in the case of static initialization of + * srcu_usage where srcu_gp_seq_needed is expected to have some state value in its + * lower bits (or else it will appear to be already initialized within + * the call check_init_srcu_struct()). + */ +#define SRCU_GP_SEQ_INITIAL_VAL ((0UL - 100UL) << RCU_SEQ_CTR_SHIFT) +#define SRCU_GP_SEQ_INITIAL_VAL_WITH_STATE (SRCU_GP_SEQ_INITIAL_VAL - 1) + #define __SRCU_USAGE_INIT(name) \ { \ .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ - .srcu_gp_seq_needed = -1UL, \ + .srcu_gp_seq = SRCU_GP_SEQ_INITIAL_VAL, \ + .srcu_gp_seq_needed = SRCU_GP_SEQ_INITIAL_VAL_WITH_STATE, \ + .srcu_gp_seq_needed_exp = SRCU_GP_SEQ_INITIAL_VAL, \ .work = __DELAYED_WORK_INITIALIZER(name.work, NULL, 0), \ } diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index 38238e595a61..2bfed9855d67 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -54,9 +54,6 @@ * grace-period sequence number. */ -#define RCU_SEQ_CTR_SHIFT 2 -#define RCU_SEQ_STATE_MASK ((1 << RCU_SEQ_CTR_SHIFT) - 1) - /* Low-order bit definition for polled grace-period APIs. */ #define RCU_GET_STATE_COMPLETED 0x1 diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index b24db425f16d..6fd9c914ce64 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -247,7 +247,7 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static) mutex_init(&ssp->srcu_sup->srcu_cb_mutex); mutex_init(&ssp->srcu_sup->srcu_gp_mutex); ssp->srcu_idx = 0; - ssp->srcu_sup->srcu_gp_seq = 0; + ssp->srcu_sup->srcu_gp_seq = SRCU_GP_SEQ_INITIAL_VAL; ssp->srcu_sup->srcu_barrier_seq = 0; mutex_init(&ssp->srcu_sup->srcu_barrier_mutex); atomic_set(&ssp->srcu_sup->srcu_barrier_cpu_cnt, 0); @@ -258,7 +258,7 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static) if (!ssp->sda) goto err_free_sup; init_srcu_struct_data(ssp); - ssp->srcu_sup->srcu_gp_seq_needed_exp = 0; + ssp->srcu_sup->srcu_gp_seq_needed_exp = SRCU_GP_SEQ_INITIAL_VAL; ssp->srcu_sup->srcu_last_gp_end = ktime_get_mono_fast_ns(); if (READ_ONCE(ssp->srcu_sup->srcu_size_state) == SRCU_SIZE_SMALL && SRCU_SIZING_IS_INIT()) { if (!init_srcu_struct_nodes(ssp, GFP_ATOMIC)) @@ -266,7 +266,8 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static) WRITE_ONCE(ssp->srcu_sup->srcu_size_state, SRCU_SIZE_BIG); } ssp->srcu_sup->srcu_ssp = ssp; - smp_store_release(&ssp->srcu_sup->srcu_gp_seq_needed, 0); /* Init done. */ + smp_store_release(&ssp->srcu_sup->srcu_gp_seq_needed, + SRCU_GP_SEQ_INITIAL_VAL); /* Init done. */ return 0; err_free_sda: -- cgit v1.2.3 From 711f5c5ce6c2c640c1b3b569ab2a8847be5ab21f Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Mon, 15 Jul 2024 21:22:51 -0400 Subject: lsm: cleanup lsm_hooks.h Some cleanup and style corrections for lsm_hooks.h. * Drop the lsm_inode_alloc() extern declaration, it is not needed. * Relocate lsm_get_xattr_slot() and extern variables in the file to improve grouping of related objects. * Don't use tabs to needlessly align structure fields. Reviewed-by: Casey Schaufler Signed-off-by: Paul Moore --- include/linux/lsm_hooks.h | 87 +++++++++++++++++++++++------------------------ security/security.c | 2 +- 2 files changed, 44 insertions(+), 45 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index f1ca8082075a..11ea0063228f 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -51,8 +51,8 @@ struct security_hook_heads { * Contains the information that identifies the LSM. */ struct lsm_id { - const char *name; - u64 id; + const char *name; + u64 id; }; /* @@ -60,49 +60,31 @@ struct lsm_id { * For use with generic list macros for common operations. */ struct security_hook_list { - struct hlist_node list; - struct hlist_head *head; - union security_list_options hook; - const struct lsm_id *lsmid; + struct hlist_node list; + struct hlist_head *head; + union security_list_options hook; + const struct lsm_id *lsmid; } __randomize_layout; /* * Security blob size or offset data. */ struct lsm_blob_sizes { - int lbs_cred; - int lbs_file; - int lbs_ib; - int lbs_inode; - int lbs_sock; - int lbs_superblock; - int lbs_ipc; - int lbs_key; - int lbs_msg_msg; - int lbs_perf_event; - int lbs_task; - int lbs_xattr_count; /* number of xattr slots in new_xattrs array */ - int lbs_tun_dev; + int lbs_cred; + int lbs_file; + int lbs_ib; + int lbs_inode; + int lbs_sock; + int lbs_superblock; + int lbs_ipc; + int lbs_key; + int lbs_msg_msg; + int lbs_perf_event; + int lbs_task; + int lbs_xattr_count; /* number of xattr slots in new_xattrs array */ + int lbs_tun_dev; }; -/** - * lsm_get_xattr_slot - Return the next available slot and increment the index - * @xattrs: array storing LSM-provided xattrs - * @xattr_count: number of already stored xattrs (updated) - * - * Retrieve the first available slot in the @xattrs array to fill with an xattr, - * and increment @xattr_count. - * - * Return: The slot to fill in @xattrs if non-NULL, NULL otherwise. - */ -static inline struct xattr *lsm_get_xattr_slot(struct xattr *xattrs, - int *xattr_count) -{ - if (unlikely(!xattrs)) - return NULL; - return &xattrs[(*xattr_count)++]; -} - /* * LSM_RET_VOID is used as the default value in LSM_HOOK definitions for void * LSM hooks (in include/linux/lsm_hook_defs.h). @@ -118,9 +100,6 @@ static inline struct xattr *lsm_get_xattr_slot(struct xattr *xattrs, #define LSM_HOOK_INIT(HEAD, HOOK) \ { .head = &security_hook_heads.HEAD, .hook = { .HEAD = HOOK } } -extern struct security_hook_heads security_hook_heads; -extern char *lsm_names; - extern void security_add_hooks(struct security_hook_list *hooks, int count, const struct lsm_id *lsmid); @@ -142,9 +121,6 @@ struct lsm_info { struct lsm_blob_sizes *blobs; /* Optional: for blob sharing. */ }; -extern struct lsm_info __start_lsm_info[], __end_lsm_info[]; -extern struct lsm_info __start_early_lsm_info[], __end_early_lsm_info[]; - #define DEFINE_LSM(lsm) \ static struct lsm_info __lsm_##lsm \ __used __section(".lsm_info.init") \ @@ -155,6 +131,29 @@ extern struct lsm_info __start_early_lsm_info[], __end_early_lsm_info[]; __used __section(".early_lsm_info.init") \ __aligned(sizeof(unsigned long)) -extern int lsm_inode_alloc(struct inode *inode); +/* DO NOT tamper with these variables outside of the LSM framework */ +extern char *lsm_names; +extern struct security_hook_heads security_hook_heads; +extern struct lsm_static_calls_table static_calls_table __ro_after_init; +extern struct lsm_info __start_lsm_info[], __end_lsm_info[]; +extern struct lsm_info __start_early_lsm_info[], __end_early_lsm_info[]; + +/** + * lsm_get_xattr_slot - Return the next available slot and increment the index + * @xattrs: array storing LSM-provided xattrs + * @xattr_count: number of already stored xattrs (updated) + * + * Retrieve the first available slot in the @xattrs array to fill with an xattr, + * and increment @xattr_count. + * + * Return: The slot to fill in @xattrs if non-NULL, NULL otherwise. + */ +static inline struct xattr *lsm_get_xattr_slot(struct xattr *xattrs, + int *xattr_count) +{ + if (unlikely(!xattrs)) + return NULL; + return &xattrs[(*xattr_count)++]; +} #endif /* ! __LINUX_LSM_HOOKS_H */ diff --git a/security/security.c b/security/security.c index 338e0d243a3c..b316e6586be2 100644 --- a/security/security.c +++ b/security/security.c @@ -689,7 +689,7 @@ static int lsm_file_alloc(struct file *file) * * Returns 0, or -ENOMEM if memory can't be allocated. */ -int lsm_inode_alloc(struct inode *inode) +static int lsm_inode_alloc(struct inode *inode) { if (!lsm_inode_cache) { inode->i_security = NULL; -- cgit v1.2.3 From 63dff3e48871b0583be5032ff8fb7260c349a18c Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Tue, 9 Jul 2024 19:43:06 -0400 Subject: lsm: add the inode_free_security_rcu() LSM implementation hook The LSM framework has an existing inode_free_security() hook which is used by LSMs that manage state associated with an inode, but due to the use of RCU to protect the inode, special care must be taken to ensure that the LSMs do not fully release the inode state until it is safe from a RCU perspective. This patch implements a new inode_free_security_rcu() implementation hook which is called when it is safe to free the LSM's internal inode state. Unfortunately, this new hook does not have access to the inode itself as it may already be released, so the existing inode_free_security() hook is retained for those LSMs which require access to the inode. Cc: stable@vger.kernel.org Reported-by: syzbot+5446fbf332b0602ede0b@syzkaller.appspotmail.com Closes: https://lore.kernel.org/r/00000000000076ba3b0617f65cc8@google.com Signed-off-by: Paul Moore --- include/linux/lsm_hook_defs.h | 1 + security/integrity/ima/ima.h | 2 +- security/integrity/ima/ima_iint.c | 20 ++++++++------------ security/integrity/ima/ima_main.c | 2 +- security/landlock/fs.c | 9 ++++++--- security/security.c | 32 ++++++++++++++++---------------- 6 files changed, 33 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 63e2656d1d56..520730fe2d94 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -114,6 +114,7 @@ LSM_HOOK(int, 0, path_notify, const struct path *path, u64 mask, unsigned int obj_type) LSM_HOOK(int, 0, inode_alloc_security, struct inode *inode) LSM_HOOK(void, LSM_RET_VOID, inode_free_security, struct inode *inode) +LSM_HOOK(void, LSM_RET_VOID, inode_free_security_rcu, void *inode_security) LSM_HOOK(int, -EOPNOTSUPP, inode_init_security, struct inode *inode, struct inode *dir, const struct qstr *qstr, struct xattr *xattrs, int *xattr_count) diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h index c51e24d24d1e..3c323ca213d4 100644 --- a/security/integrity/ima/ima.h +++ b/security/integrity/ima/ima.h @@ -223,7 +223,7 @@ static inline void ima_inode_set_iint(const struct inode *inode, struct ima_iint_cache *ima_iint_find(struct inode *inode); struct ima_iint_cache *ima_inode_get(struct inode *inode); -void ima_inode_free(struct inode *inode); +void ima_inode_free_rcu(void *inode_security); void __init ima_iintcache_init(void); extern const int read_idmap[]; diff --git a/security/integrity/ima/ima_iint.c b/security/integrity/ima/ima_iint.c index e23412a2c56b..00b249101f98 100644 --- a/security/integrity/ima/ima_iint.c +++ b/security/integrity/ima/ima_iint.c @@ -109,22 +109,18 @@ struct ima_iint_cache *ima_inode_get(struct inode *inode) } /** - * ima_inode_free - Called on inode free - * @inode: Pointer to the inode + * ima_inode_free_rcu - Called to free an inode via a RCU callback + * @inode_security: The inode->i_security pointer * - * Free the iint associated with an inode. + * Free the IMA data associated with an inode. */ -void ima_inode_free(struct inode *inode) +void ima_inode_free_rcu(void *inode_security) { - struct ima_iint_cache *iint; - - if (!IS_IMA(inode)) - return; - - iint = ima_iint_find(inode); - ima_inode_set_iint(inode, NULL); + struct ima_iint_cache **iint_p = inode_security + ima_blob_sizes.lbs_inode; - ima_iint_free(iint); + /* *iint_p should be NULL if !IS_IMA(inode) */ + if (*iint_p) + ima_iint_free(*iint_p); } static void ima_iint_init_once(void *foo) diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index f04f43af651c..5b3394864b21 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -1193,7 +1193,7 @@ static struct security_hook_list ima_hooks[] __ro_after_init = { #ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS LSM_HOOK_INIT(kernel_module_request, ima_kernel_module_request), #endif - LSM_HOOK_INIT(inode_free_security, ima_inode_free), + LSM_HOOK_INIT(inode_free_security_rcu, ima_inode_free_rcu), }; static const struct lsm_id ima_lsmid = { diff --git a/security/landlock/fs.c b/security/landlock/fs.c index 7877a64cc6b8..0804f76a67be 100644 --- a/security/landlock/fs.c +++ b/security/landlock/fs.c @@ -1207,13 +1207,16 @@ static int current_check_refer_path(struct dentry *const old_dentry, /* Inode hooks */ -static void hook_inode_free_security(struct inode *const inode) +static void hook_inode_free_security_rcu(void *inode_security) { + struct landlock_inode_security *inode_sec; + /* * All inodes must already have been untied from their object by * release_inode() or hook_sb_delete(). */ - WARN_ON_ONCE(landlock_inode(inode)->object); + inode_sec = inode_security + landlock_blob_sizes.lbs_inode; + WARN_ON_ONCE(inode_sec->object); } /* Super-block hooks */ @@ -1637,7 +1640,7 @@ static int hook_file_ioctl_compat(struct file *file, unsigned int cmd, } static struct security_hook_list landlock_hooks[] __ro_after_init = { - LSM_HOOK_INIT(inode_free_security, hook_inode_free_security), + LSM_HOOK_INIT(inode_free_security_rcu, hook_inode_free_security_rcu), LSM_HOOK_INIT(sb_delete, hook_sb_delete), LSM_HOOK_INIT(sb_mount, hook_sb_mount), diff --git a/security/security.c b/security/security.c index b316e6586be2..611d3c124ba6 100644 --- a/security/security.c +++ b/security/security.c @@ -1609,9 +1609,8 @@ int security_inode_alloc(struct inode *inode) static void inode_free_by_rcu(struct rcu_head *head) { - /* - * The rcu head is at the start of the inode blob - */ + /* The rcu head is at the start of the inode blob */ + call_void_hook(inode_free_security_rcu, head); kmem_cache_free(lsm_inode_cache, head); } @@ -1619,23 +1618,24 @@ static void inode_free_by_rcu(struct rcu_head *head) * security_inode_free() - Free an inode's LSM blob * @inode: the inode * - * Deallocate the inode security structure and set @inode->i_security to NULL. + * Release any LSM resources associated with @inode, although due to the + * inode's RCU protections it is possible that the resources will not be + * fully released until after the current RCU grace period has elapsed. + * + * It is important for LSMs to note that despite being present in a call to + * security_inode_free(), @inode may still be referenced in a VFS path walk + * and calls to security_inode_permission() may be made during, or after, + * a call to security_inode_free(). For this reason the inode->i_security + * field is released via a call_rcu() callback and any LSMs which need to + * retain inode state for use in security_inode_permission() should only + * release that state in the inode_free_security_rcu() LSM hook callback. */ void security_inode_free(struct inode *inode) { call_void_hook(inode_free_security, inode); - /* - * The inode may still be referenced in a path walk and - * a call to security_inode_permission() can be made - * after inode_free_security() is called. Ideally, the VFS - * wouldn't do this, but fixing that is a much harder - * job. For now, simply free the i_security via RCU, and - * leave the current inode->i_security pointer intact. - * The inode will be freed after the RCU grace period too. - */ - if (inode->i_security) - call_rcu((struct rcu_head *)inode->i_security, - inode_free_by_rcu); + if (!inode->i_security) + return; + call_rcu((struct rcu_head *)inode->i_security, inode_free_by_rcu); } /** -- cgit v1.2.3 From 86509e38a80da34d7800985fa2be183475242c8c Mon Sep 17 00:00:00 2001 From: Mathias Krause Date: Fri, 9 Aug 2024 15:50:35 +0200 Subject: file: fix typo in take_fd() comment The explanatory comment above take_fd() contains a typo, fix that to not confuse readers. Signed-off-by: Mathias Krause Link: https://lore.kernel.org/r/20240809135035.748109-1-minipli@grsecurity.net Signed-off-by: Christian Brauner --- include/linux/file.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/file.h b/include/linux/file.h index 237931f20739..59b146a14dca 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -110,7 +110,7 @@ DEFINE_CLASS(get_unused_fd, int, if (_T >= 0) put_unused_fd(_T), * * f = dentry_open(&path, O_RDONLY, current_cred()); * if (IS_ERR(f)) - * return PTR_ERR(fd); + * return PTR_ERR(f); * * fd_install(fd, f); * return take_fd(fd); -- cgit v1.2.3 From 7b589a9b45ae32aa9d7bece597490e141198d7a6 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 7 Aug 2024 19:38:46 +0100 Subject: netfs: Fix handling of USE_PGPRIV2 and WRITE_TO_CACHE flags The NETFS_RREQ_USE_PGPRIV2 and NETFS_RREQ_WRITE_TO_CACHE flags aren't used correctly. The problem is that we try to set them up in the request initialisation, but we the cache may be in the process of setting up still, and so the state may not be correct. Further, we secondarily sample the cache state and make contradictory decisions later. The issue arises because we set up the cache resources, which allows the cache's ->prepare_read() to switch on NETFS_SREQ_COPY_TO_CACHE - which triggers cache writing even if we didn't set the flags when allocating. Fix this in the following way: (1) Drop NETFS_ICTX_USE_PGPRIV2 and instead set NETFS_RREQ_USE_PGPRIV2 in ->init_request() rather than trying to juggle that in netfs_alloc_request(). (2) Repurpose NETFS_RREQ_USE_PGPRIV2 to merely indicate that if caching is to be done, then PG_private_2 is to be used rather than only setting it if we decide to cache and then having netfs_rreq_unlock_folios() set the non-PG_private_2 writeback-to-cache if it wasn't set. (3) Split netfs_rreq_unlock_folios() into two functions, one of which contains the deprecated code for using PG_private_2 to avoid accidentally doing the writeback path - and always use it if USE_PGPRIV2 is set. (4) As NETFS_ICTX_USE_PGPRIV2 is removed, make netfs_write_begin() always wait for PG_private_2. This function is deprecated and only used by ceph anyway, and so label it so. (5) Drop the NETFS_RREQ_WRITE_TO_CACHE flag and use fscache_operation_valid() on the cache_resources instead. This has the advantage of picking up the result of netfs_begin_cache_read() and fscache_begin_write_operation() - which are called after the object is initialised and will wait for the cache to come to a usable state. Just reverting ae678317b95e[1] isn't a sufficient fix, so this need to be applied on top of that. Without this as well, things like: rcu: INFO: rcu_sched detected expedited stalls on CPUs/tasks: { and: WARNING: CPU: 13 PID: 3621 at fs/ceph/caps.c:3386 may happen, along with some UAFs due to PG_private_2 not getting used to wait on writeback completion. Fixes: 2ff1e97587f4 ("netfs: Replace PG_fscache by setting folio->private and marking dirty") Reported-by: Max Kellermann Signed-off-by: David Howells cc: Ilya Dryomov cc: Xiubo Li cc: Hristo Venev cc: Jeff Layton cc: Matthew Wilcox cc: ceph-devel@vger.kernel.org cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org Link: https://lore.kernel.org/r/3575457.1722355300@warthog.procyon.org.uk/ [1] Link: https://lore.kernel.org/r/1173209.1723152682@warthog.procyon.org.uk Signed-off-by: Christian Brauner --- fs/ceph/addr.c | 3 ++ fs/ceph/inode.c | 2 - fs/netfs/buffered_read.c | 125 ++++++++++++++++++++++++++++++++++++------- fs/netfs/objects.c | 10 ---- fs/netfs/write_issue.c | 4 +- fs/nfs/fscache.c | 2 + fs/nfs/fscache.h | 2 - include/linux/netfs.h | 3 -- include/trace/events/netfs.h | 1 + 9 files changed, 116 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 73b5a07bf94d..cc0a2240de98 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -424,6 +424,9 @@ static int ceph_init_request(struct netfs_io_request *rreq, struct file *file) struct ceph_netfs_request_data *priv; int ret = 0; + /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */ + __set_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags); + if (rreq->origin != NETFS_READAHEAD) return 0; diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 8f8de8f33abb..71cd70514efa 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -577,8 +577,6 @@ struct inode *ceph_alloc_inode(struct super_block *sb) /* Set parameters for the netfs library */ netfs_inode_init(&ci->netfs, &ceph_netfs_ops, false); - /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */ - __set_bit(NETFS_ICTX_USE_PGPRIV2, &ci->netfs.flags); spin_lock_init(&ci->i_ceph_lock); diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 424048f9ed1f..27c750d39476 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -9,6 +9,97 @@ #include #include "internal.h" +/* + * [DEPRECATED] Unlock the folios in a read operation for when the filesystem + * is using PG_private_2 and direct writing to the cache from here rather than + * marking the page for writeback. + * + * Note that we don't touch folio->private in this code. + */ +static void netfs_rreq_unlock_folios_pgpriv2(struct netfs_io_request *rreq, + size_t *account) +{ + struct netfs_io_subrequest *subreq; + struct folio *folio; + pgoff_t start_page = rreq->start / PAGE_SIZE; + pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1; + bool subreq_failed = false; + + XA_STATE(xas, &rreq->mapping->i_pages, start_page); + + /* Walk through the pagecache and the I/O request lists simultaneously. + * We may have a mixture of cached and uncached sections and we only + * really want to write out the uncached sections. This is slightly + * complicated by the possibility that we might have huge pages with a + * mixture inside. + */ + subreq = list_first_entry(&rreq->subrequests, + struct netfs_io_subrequest, rreq_link); + subreq_failed = (subreq->error < 0); + + trace_netfs_rreq(rreq, netfs_rreq_trace_unlock_pgpriv2); + + rcu_read_lock(); + xas_for_each(&xas, folio, last_page) { + loff_t pg_end; + bool pg_failed = false; + bool folio_started = false; + + if (xas_retry(&xas, folio)) + continue; + + pg_end = folio_pos(folio) + folio_size(folio) - 1; + + for (;;) { + loff_t sreq_end; + + if (!subreq) { + pg_failed = true; + break; + } + + if (!folio_started && + test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags) && + fscache_operation_valid(&rreq->cache_resources)) { + trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); + folio_start_private_2(folio); + folio_started = true; + } + + pg_failed |= subreq_failed; + sreq_end = subreq->start + subreq->len - 1; + if (pg_end < sreq_end) + break; + + *account += subreq->transferred; + if (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) { + subreq = list_next_entry(subreq, rreq_link); + subreq_failed = (subreq->error < 0); + } else { + subreq = NULL; + subreq_failed = false; + } + + if (pg_end == sreq_end) + break; + } + + if (!pg_failed) { + flush_dcache_folio(folio); + folio_mark_uptodate(folio); + } + + if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) { + if (folio->index == rreq->no_unlock_folio && + test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) + _debug("no unlock"); + else + folio_unlock(folio); + } + } + rcu_read_unlock(); +} + /* * Unlock the folios in a read operation. We need to set PG_writeback on any * folios we're going to write back before we unlock them. @@ -35,6 +126,12 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) } } + /* Handle deprecated PG_private_2 case. */ + if (test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) { + netfs_rreq_unlock_folios_pgpriv2(rreq, &account); + goto out; + } + /* Walk through the pagecache and the I/O request lists simultaneously. * We may have a mixture of cached and uncached sections and we only * really want to write out the uncached sections. This is slightly @@ -52,7 +149,6 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) loff_t pg_end; bool pg_failed = false; bool wback_to_cache = false; - bool folio_started = false; if (xas_retry(&xas, folio)) continue; @@ -66,17 +162,8 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) pg_failed = true; break; } - if (test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) { - if (!folio_started && test_bit(NETFS_SREQ_COPY_TO_CACHE, - &subreq->flags)) { - trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); - folio_start_private_2(folio); - folio_started = true; - } - } else { - wback_to_cache |= - test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); - } + + wback_to_cache |= test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); pg_failed |= subreq_failed; sreq_end = subreq->start + subreq->len - 1; if (pg_end < sreq_end) @@ -124,6 +211,7 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) } rcu_read_unlock(); +out: task_io_account_read(account); if (rreq->netfs_ops->done) rreq->netfs_ops->done(rreq); @@ -395,7 +483,7 @@ zero_out: } /** - * netfs_write_begin - Helper to prepare for writing + * netfs_write_begin - Helper to prepare for writing [DEPRECATED] * @ctx: The netfs context * @file: The file to read from * @mapping: The mapping to read from @@ -426,6 +514,9 @@ zero_out: * inode before calling this. * * This is usable whether or not caching is enabled. + * + * Note that this should be considered deprecated and netfs_perform_write() + * used instead. */ int netfs_write_begin(struct netfs_inode *ctx, struct file *file, struct address_space *mapping, @@ -507,11 +598,9 @@ retry: netfs_put_request(rreq, false, netfs_rreq_trace_put_return); have_folio: - if (test_bit(NETFS_ICTX_USE_PGPRIV2, &ctx->flags)) { - ret = folio_wait_private_2_killable(folio); - if (ret < 0) - goto error; - } + ret = folio_wait_private_2_killable(folio); + if (ret < 0) + goto error; have_folio_no_wait: *_folio = folio; _leave(" = 0"); diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c index f4a642727479..0294df70c3ff 100644 --- a/fs/netfs/objects.c +++ b/fs/netfs/objects.c @@ -24,10 +24,6 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, struct netfs_io_request *rreq; mempool_t *mempool = ctx->ops->request_pool ?: &netfs_request_pool; struct kmem_cache *cache = mempool->pool_data; - bool is_unbuffered = (origin == NETFS_UNBUFFERED_WRITE || - origin == NETFS_DIO_READ || - origin == NETFS_DIO_WRITE); - bool cached = !is_unbuffered && netfs_is_cache_enabled(ctx); int ret; for (;;) { @@ -56,12 +52,6 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, refcount_set(&rreq->ref, 1); __set_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags); - if (cached) { - __set_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags); - if (test_bit(NETFS_ICTX_USE_PGPRIV2, &ctx->flags)) - /* Filesystem uses deprecated PG_private_2 marking. */ - __set_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags); - } if (file && file->f_flags & O_NONBLOCK) __set_bit(NETFS_RREQ_NONBLOCK, &rreq->flags); if (rreq->netfs_ops->init_request) { diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 9258d30cffe3..3f7e37e50c7d 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -94,6 +94,8 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, { struct netfs_io_request *wreq; struct netfs_inode *ictx; + bool is_buffered = (origin == NETFS_WRITEBACK || + origin == NETFS_WRITETHROUGH); wreq = netfs_alloc_request(mapping, file, start, 0, origin); if (IS_ERR(wreq)) @@ -102,7 +104,7 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, _enter("R=%x", wreq->debug_id); ictx = netfs_inode(wreq->inode); - if (test_bit(NETFS_RREQ_WRITE_TO_CACHE, &wreq->flags)) + if (is_buffered && netfs_is_cache_enabled(ictx)) fscache_begin_write_operation(&wreq->cache_resources, netfs_i_cookie(ictx)); wreq->contiguity = wreq->start; diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index 7202ce84d0eb..bf29a65c5027 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -265,6 +265,8 @@ static int nfs_netfs_init_request(struct netfs_io_request *rreq, struct file *fi { rreq->netfs_priv = get_nfs_open_context(nfs_file_open_context(file)); rreq->debug_id = atomic_inc_return(&nfs_netfs_debug_id); + /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */ + __set_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags); return 0; } diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h index fbed0027996f..e8adae1bc260 100644 --- a/fs/nfs/fscache.h +++ b/fs/nfs/fscache.h @@ -81,8 +81,6 @@ static inline void nfs_netfs_put(struct nfs_netfs_io_data *netfs) static inline void nfs_netfs_inode_init(struct nfs_inode *nfsi) { netfs_inode_init(&nfsi->netfs, &nfs_netfs_ops, false); - /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */ - __set_bit(NETFS_ICTX_USE_PGPRIV2, &nfsi->netfs.flags); } extern void nfs_netfs_initiate_read(struct nfs_pgio_header *hdr); extern void nfs_netfs_read_completion(struct nfs_pgio_header *hdr); diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 5d0288938cc2..983816608f15 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -73,8 +73,6 @@ struct netfs_inode { #define NETFS_ICTX_ODIRECT 0 /* The file has DIO in progress */ #define NETFS_ICTX_UNBUFFERED 1 /* I/O should not use the pagecache */ #define NETFS_ICTX_WRITETHROUGH 2 /* Write-through caching */ -#define NETFS_ICTX_USE_PGPRIV2 31 /* [DEPRECATED] Use PG_private_2 to mark - * write to cache on read */ }; /* @@ -269,7 +267,6 @@ struct netfs_io_request { #define NETFS_RREQ_DONT_UNLOCK_FOLIOS 3 /* Don't unlock the folios on completion */ #define NETFS_RREQ_FAILED 4 /* The request failed */ #define NETFS_RREQ_IN_PROGRESS 5 /* Unlocked when the request completes */ -#define NETFS_RREQ_WRITE_TO_CACHE 7 /* Need to write to the cache */ #define NETFS_RREQ_UPLOAD_TO_SERVER 8 /* Need to write to the server */ #define NETFS_RREQ_NONBLOCK 9 /* Don't block if possible (O_NONBLOCK) */ #define NETFS_RREQ_BLOCKED 10 /* We blocked */ diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 24ec3434d32e..606b4a0f92da 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -51,6 +51,7 @@ EM(netfs_rreq_trace_resubmit, "RESUBMT") \ EM(netfs_rreq_trace_set_pause, "PAUSE ") \ EM(netfs_rreq_trace_unlock, "UNLOCK ") \ + EM(netfs_rreq_trace_unlock_pgpriv2, "UNLCK-2") \ EM(netfs_rreq_trace_unmark, "UNMARK ") \ EM(netfs_rreq_trace_wait_ip, "WAIT-IP") \ EM(netfs_rreq_trace_wait_pause, "WT-PAUS") \ -- cgit v1.2.3 From fdad456cbcca739bae1849549c7a999857c56f88 Mon Sep 17 00:00:00 2001 From: Leon Hwang Date: Sun, 28 Jul 2024 19:46:11 +0800 Subject: bpf: Fix updating attached freplace prog in prog_array map MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The commit f7866c358733 ("bpf: Fix null pointer dereference in resolve_prog_type() for BPF_PROG_TYPE_EXT") fixed a NULL pointer dereference panic, but didn't fix the issue that fails to update attached freplace prog to prog_array map. Since commit 1c123c567fb1 ("bpf: Resolve fext program type when checking map compatibility"), freplace prog and its target prog are able to tail call each other. And the commit 3aac1ead5eb6 ("bpf: Move prog->aux->linked_prog and trampoline into bpf_link on attach") sets prog->aux->dst_prog as NULL after attaching freplace prog to its target prog. After loading freplace the prog_array's owner type is BPF_PROG_TYPE_SCHED_CLS. Then, after attaching freplace its prog->aux->dst_prog is NULL. Then, while updating freplace in prog_array the bpf_prog_map_compatible() incorrectly returns false because resolve_prog_type() returns BPF_PROG_TYPE_EXT instead of BPF_PROG_TYPE_SCHED_CLS. After this patch the resolve_prog_type() returns BPF_PROG_TYPE_SCHED_CLS and update to prog_array can succeed. Fixes: f7866c358733 ("bpf: Fix null pointer dereference in resolve_prog_type() for BPF_PROG_TYPE_EXT") Cc: Toke Høiland-Jørgensen Cc: Martin KaFai Lau Acked-by: Yonghong Song Signed-off-by: Leon Hwang Link: https://lore.kernel.org/r/20240728114612.48486-2-leon.hwang@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 6503c85b10a3..7b776dae36e5 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -856,8 +856,8 @@ static inline u32 type_flag(u32 type) /* only use after check_attach_btf_id() */ static inline enum bpf_prog_type resolve_prog_type(const struct bpf_prog *prog) { - return (prog->type == BPF_PROG_TYPE_EXT && prog->aux->dst_prog) ? - prog->aux->dst_prog->type : prog->type; + return (prog->type == BPF_PROG_TYPE_EXT && prog->aux->saved_dst_prog_type) ? + prog->aux->saved_dst_prog_type : prog->type; } static inline bool bpf_prog_check_recur(const struct bpf_prog *prog) -- cgit v1.2.3 From 1da91ea87aefe2c25b68c9f96947a9271ba6325d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 31 May 2024 14:12:01 -0400 Subject: introduce fd_file(), convert all accessors to it. For any changes of struct fd representation we need to turn existing accesses to fields into calls of wrappers. Accesses to struct fd::flags are very few (3 in linux/file.h, 1 in net/socket.c, 3 in fs/overlayfs/file.c and 3 more in explicit initializers). Those can be dealt with in the commit converting to new layout; accesses to struct fd::file are too many for that. This commit converts (almost) all of f.file to fd_file(f). It's not entirely mechanical ('file' is used as a member name more than just in struct fd) and it does not even attempt to distinguish the uses in pointer context from those in boolean context; the latter will be eventually turned into a separate helper (fd_empty()). NOTE: mass conversion to fd_empty(), tempting as it might be, is a bad idea; better do that piecewise in commit that convert from fdget...() to CLASS(...). [conflicts in fs/fhandle.c, kernel/bpf/syscall.c, mm/memcontrol.c caught by git; fs/stat.c one got caught by git grep] [fs/xattr.c conflict] Reviewed-by: Christian Brauner Signed-off-by: Al Viro --- arch/alpha/kernel/osf_sys.c | 4 +- arch/arm/kernel/sys_oabi-compat.c | 10 +-- arch/powerpc/kvm/book3s_64_vio.c | 4 +- arch/powerpc/kvm/powerpc.c | 12 +-- arch/powerpc/platforms/cell/spu_syscalls.c | 8 +- arch/x86/kernel/cpu/sgx/main.c | 4 +- arch/x86/kvm/svm/sev.c | 16 ++-- drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c | 8 +- drivers/gpu/drm/drm_syncobj.c | 6 +- drivers/infiniband/core/ucma.c | 6 +- drivers/infiniband/core/uverbs_cmd.c | 8 +- drivers/media/mc/mc-request.c | 6 +- drivers/media/rc/lirc_dev.c | 8 +- drivers/vfio/group.c | 6 +- drivers/vfio/virqfd.c | 6 +- drivers/virt/acrn/irqfd.c | 6 +- drivers/xen/privcmd.c | 10 +-- fs/btrfs/ioctl.c | 4 +- fs/coda/inode.c | 4 +- fs/eventfd.c | 4 +- fs/eventpoll.c | 30 ++++---- fs/ext4/ioctl.c | 6 +- fs/f2fs/file.c | 6 +- fs/fcntl.c | 38 +++++----- fs/fhandle.c | 4 +- fs/fsopen.c | 6 +- fs/fuse/dev.c | 6 +- fs/ioctl.c | 30 ++++---- fs/kernel_read_file.c | 4 +- fs/locks.c | 14 ++-- fs/namei.c | 10 +-- fs/namespace.c | 12 +-- fs/notify/fanotify/fanotify_user.c | 12 +-- fs/notify/inotify/inotify_user.c | 12 +-- fs/ocfs2/cluster/heartbeat.c | 6 +- fs/open.c | 24 +++--- fs/overlayfs/file.c | 40 +++++----- fs/quota/quota.c | 8 +- fs/read_write.c | 118 ++++++++++++++--------------- fs/readdir.c | 20 ++--- fs/remap_range.c | 2 +- fs/select.c | 8 +- fs/signalfd.c | 6 +- fs/smb/client/ioctl.c | 8 +- fs/splice.c | 22 +++--- fs/stat.c | 8 +- fs/statfs.c | 4 +- fs/sync.c | 14 ++-- fs/timerfd.c | 8 +- fs/utimes.c | 4 +- fs/xattr.c | 36 ++++----- fs/xfs/xfs_exchrange.c | 4 +- fs/xfs/xfs_handle.c | 4 +- fs/xfs/xfs_ioctl.c | 28 +++---- include/linux/cleanup.h | 2 +- include/linux/file.h | 6 +- io_uring/sqpoll.c | 10 +-- ipc/mqueue.c | 50 ++++++------ kernel/bpf/bpf_inode_storage.c | 14 ++-- kernel/bpf/btf.c | 6 +- kernel/bpf/syscall.c | 42 +++++----- kernel/bpf/token.c | 10 +-- kernel/cgroup/cgroup.c | 4 +- kernel/events/core.c | 12 +-- kernel/module/main.c | 2 +- kernel/nsproxy.c | 12 +-- kernel/pid.c | 10 +-- kernel/signal.c | 6 +- kernel/sys.c | 10 +-- kernel/taskstats.c | 4 +- kernel/watch_queue.c | 4 +- mm/fadvise.c | 4 +- mm/filemap.c | 6 +- mm/memcontrol-v1.c | 12 +-- mm/readahead.c | 10 +-- net/core/net_namespace.c | 6 +- net/socket.c | 12 +-- security/integrity/ima/ima_main.c | 4 +- security/landlock/syscalls.c | 22 +++--- security/loadpin/loadpin.c | 4 +- sound/core/pcm_native.c | 6 +- virt/kvm/eventfd.c | 6 +- virt/kvm/vfio.c | 8 +- 83 files changed, 504 insertions(+), 502 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index e5f881bc8288..56fea57f9642 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -160,10 +160,10 @@ SYSCALL_DEFINE4(osf_getdirentries, unsigned int, fd, .count = count }; - if (!arg.file) + if (!fd_file(arg)) return -EBADF; - error = iterate_dir(arg.file, &buf.ctx); + error = iterate_dir(fd_file(arg), &buf.ctx); if (error >= 0) error = buf.error; if (count != buf.count) diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c index d00f4040a9f5..f5781ff54a5c 100644 --- a/arch/arm/kernel/sys_oabi-compat.c +++ b/arch/arm/kernel/sys_oabi-compat.c @@ -239,19 +239,19 @@ asmlinkage long sys_oabi_fcntl64(unsigned int fd, unsigned int cmd, struct flock64 flock; long err = -EBADF; - if (!f.file) + if (!fd_file(f)) goto out; switch (cmd) { case F_GETLK64: case F_OFD_GETLK: - err = security_file_fcntl(f.file, cmd, arg); + err = security_file_fcntl(fd_file(f), cmd, arg); if (err) break; err = get_oabi_flock(&flock, argp); if (err) break; - err = fcntl_getlk64(f.file, cmd, &flock); + err = fcntl_getlk64(fd_file(f), cmd, &flock); if (!err) err = put_oabi_flock(&flock, argp); break; @@ -259,13 +259,13 @@ asmlinkage long sys_oabi_fcntl64(unsigned int fd, unsigned int cmd, case F_SETLKW64: case F_OFD_SETLK: case F_OFD_SETLKW: - err = security_file_fcntl(f.file, cmd, arg); + err = security_file_fcntl(fd_file(f), cmd, arg); if (err) break; err = get_oabi_flock(&flock, argp); if (err) break; - err = fcntl_setlk64(fd, f.file, cmd, &flock); + err = fcntl_setlk64(fd, fd_file(f), cmd, &flock); break; default: err = sys_fcntl64(fd, cmd, arg); diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index 3ff3de9a52ac..34c0adb9fdbf 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -118,12 +118,12 @@ long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, struct fd f; f = fdget(tablefd); - if (!f.file) + if (!fd_file(f)) return -EBADF; rcu_read_lock(); list_for_each_entry_rcu(stt, &kvm->arch.spapr_tce_tables, list) { - if (stt == f.file->private_data) { + if (stt == fd_file(f)->private_data) { found = true; break; } diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 5e6c7b527677..f14329989e9a 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -1938,11 +1938,11 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, r = -EBADF; f = fdget(cap->args[0]); - if (!f.file) + if (!fd_file(f)) break; r = -EPERM; - dev = kvm_device_from_filp(f.file); + dev = kvm_device_from_filp(fd_file(f)); if (dev) r = kvmppc_mpic_connect_vcpu(dev, vcpu, cap->args[1]); @@ -1957,11 +1957,11 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, r = -EBADF; f = fdget(cap->args[0]); - if (!f.file) + if (!fd_file(f)) break; r = -EPERM; - dev = kvm_device_from_filp(f.file); + dev = kvm_device_from_filp(fd_file(f)); if (dev) { if (xics_on_xive()) r = kvmppc_xive_connect_vcpu(dev, vcpu, cap->args[1]); @@ -1980,7 +1980,7 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, r = -EBADF; f = fdget(cap->args[0]); - if (!f.file) + if (!fd_file(f)) break; r = -ENXIO; @@ -1990,7 +1990,7 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, } r = -EPERM; - dev = kvm_device_from_filp(f.file); + dev = kvm_device_from_filp(fd_file(f)); if (dev) r = kvmppc_xive_native_connect_vcpu(dev, vcpu, cap->args[1]); diff --git a/arch/powerpc/platforms/cell/spu_syscalls.c b/arch/powerpc/platforms/cell/spu_syscalls.c index 87ad7d563cfa..cd7d42fc12a6 100644 --- a/arch/powerpc/platforms/cell/spu_syscalls.c +++ b/arch/powerpc/platforms/cell/spu_syscalls.c @@ -66,8 +66,8 @@ SYSCALL_DEFINE4(spu_create, const char __user *, name, unsigned int, flags, if (flags & SPU_CREATE_AFFINITY_SPU) { struct fd neighbor = fdget(neighbor_fd); ret = -EBADF; - if (neighbor.file) { - ret = calls->create_thread(name, flags, mode, neighbor.file); + if (fd_file(neighbor)) { + ret = calls->create_thread(name, flags, mode, fd_file(neighbor)); fdput(neighbor); } } else @@ -89,8 +89,8 @@ SYSCALL_DEFINE3(spu_run,int, fd, __u32 __user *, unpc, __u32 __user *, ustatus) ret = -EBADF; arg = fdget(fd); - if (arg.file) { - ret = calls->spu_run(arg.file, unpc, ustatus); + if (fd_file(arg)) { + ret = calls->spu_run(fd_file(arg), unpc, ustatus); fdput(arg); } diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index 27892e57c4ef..d01deb386395 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -895,10 +895,10 @@ int sgx_set_attribute(unsigned long *allowed_attributes, { struct fd f = fdget(attribute_fd); - if (!f.file) + if (!fd_file(f)) return -EINVAL; - if (f.file->f_op != &sgx_provision_fops) { + if (fd_file(f)->f_op != &sgx_provision_fops) { fdput(f); return -EINVAL; } diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index a16c873b3232..0e38b5223263 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -534,10 +534,10 @@ static int __sev_issue_cmd(int fd, int id, void *data, int *error) int ret; f = fdget(fd); - if (!f.file) + if (!fd_file(f)) return -EBADF; - ret = sev_issue_cmd_external_user(f.file, id, data, error); + ret = sev_issue_cmd_external_user(fd_file(f), id, data, error); fdput(f); return ret; @@ -2078,15 +2078,15 @@ int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd) bool charged = false; int ret; - if (!f.file) + if (!fd_file(f)) return -EBADF; - if (!file_is_kvm(f.file)) { + if (!file_is_kvm(fd_file(f))) { ret = -EBADF; goto out_fput; } - source_kvm = f.file->private_data; + source_kvm = fd_file(f)->private_data; ret = sev_lock_two_vms(kvm, source_kvm); if (ret) goto out_fput; @@ -2801,15 +2801,15 @@ int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd) struct kvm_sev_info *source_sev, *mirror_sev; int ret; - if (!f.file) + if (!fd_file(f)) return -EBADF; - if (!file_is_kvm(f.file)) { + if (!file_is_kvm(fd_file(f))) { ret = -EBADF; goto e_source_fput; } - source_kvm = f.file->private_data; + source_kvm = fd_file(f)->private_data; ret = sev_lock_two_vms(kvm, source_kvm); if (ret) goto e_source_fput; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c index 863b2a34b2d6..a9298cb8d19a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c @@ -43,10 +43,10 @@ static int amdgpu_sched_process_priority_override(struct amdgpu_device *adev, uint32_t id; int r; - if (!f.file) + if (!fd_file(f)) return -EINVAL; - r = amdgpu_file_to_fpriv(f.file, &fpriv); + r = amdgpu_file_to_fpriv(fd_file(f), &fpriv); if (r) { fdput(f); return r; @@ -72,10 +72,10 @@ static int amdgpu_sched_context_priority_override(struct amdgpu_device *adev, struct amdgpu_ctx *ctx; int r; - if (!f.file) + if (!fd_file(f)) return -EINVAL; - r = amdgpu_file_to_fpriv(f.file, &fpriv); + r = amdgpu_file_to_fpriv(fd_file(f), &fpriv); if (r) { fdput(f); return r; diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c index a0e94217b511..7fb31ca3b5fc 100644 --- a/drivers/gpu/drm/drm_syncobj.c +++ b/drivers/gpu/drm/drm_syncobj.c @@ -715,16 +715,16 @@ static int drm_syncobj_fd_to_handle(struct drm_file *file_private, struct fd f = fdget(fd); int ret; - if (!f.file) + if (!fd_file(f)) return -EINVAL; - if (f.file->f_op != &drm_syncobj_file_fops) { + if (fd_file(f)->f_op != &drm_syncobj_file_fops) { fdput(f); return -EINVAL; } /* take a reference to put in the idr */ - syncobj = f.file->private_data; + syncobj = fd_file(f)->private_data; drm_syncobj_get(syncobj); idr_preload(GFP_KERNEL); diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index 5f5ad8faf86e..dc57d07a1f45 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -1624,13 +1624,13 @@ static ssize_t ucma_migrate_id(struct ucma_file *new_file, /* Get current fd to protect against it being closed */ f = fdget(cmd.fd); - if (!f.file) + if (!fd_file(f)) return -ENOENT; - if (f.file->f_op != &ucma_fops) { + if (fd_file(f)->f_op != &ucma_fops) { ret = -EINVAL; goto file_put; } - cur_file = f.file->private_data; + cur_file = fd_file(f)->private_data; /* Validate current fd and prevent destruction of id. */ ctx = ucma_get_ctx(cur_file, cmd.id); diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 1b3ea71f2c33..3f85575cf971 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -584,12 +584,12 @@ static int ib_uverbs_open_xrcd(struct uverbs_attr_bundle *attrs) if (cmd.fd != -1) { /* search for file descriptor */ f = fdget(cmd.fd); - if (!f.file) { + if (!fd_file(f)) { ret = -EBADF; goto err_tree_mutex_unlock; } - inode = file_inode(f.file); + inode = file_inode(fd_file(f)); xrcd = find_xrcd(ibudev, inode); if (!xrcd && !(cmd.oflags & O_CREAT)) { /* no file descriptor. Need CREATE flag */ @@ -632,7 +632,7 @@ static int ib_uverbs_open_xrcd(struct uverbs_attr_bundle *attrs) atomic_inc(&xrcd->usecnt); } - if (f.file) + if (fd_file(f)) fdput(f); mutex_unlock(&ibudev->xrcd_tree_mutex); @@ -648,7 +648,7 @@ err: uobj_alloc_abort(&obj->uobject, attrs); err_tree_mutex_unlock: - if (f.file) + if (fd_file(f)) fdput(f); mutex_unlock(&ibudev->xrcd_tree_mutex); diff --git a/drivers/media/mc/mc-request.c b/drivers/media/mc/mc-request.c index addb8f2d8939..e064914c476e 100644 --- a/drivers/media/mc/mc-request.c +++ b/drivers/media/mc/mc-request.c @@ -254,12 +254,12 @@ media_request_get_by_fd(struct media_device *mdev, int request_fd) return ERR_PTR(-EBADR); f = fdget(request_fd); - if (!f.file) + if (!fd_file(f)) goto err_no_req_fd; - if (f.file->f_op != &request_fops) + if (fd_file(f)->f_op != &request_fops) goto err_fput; - req = f.file->private_data; + req = fd_file(f)->private_data; if (req->mdev != mdev) goto err_fput; diff --git a/drivers/media/rc/lirc_dev.c b/drivers/media/rc/lirc_dev.c index 717c441b4a86..b8dfd530fab7 100644 --- a/drivers/media/rc/lirc_dev.c +++ b/drivers/media/rc/lirc_dev.c @@ -820,20 +820,20 @@ struct rc_dev *rc_dev_get_from_fd(int fd, bool write) struct lirc_fh *fh; struct rc_dev *dev; - if (!f.file) + if (!fd_file(f)) return ERR_PTR(-EBADF); - if (f.file->f_op != &lirc_fops) { + if (fd_file(f)->f_op != &lirc_fops) { fdput(f); return ERR_PTR(-EINVAL); } - if (write && !(f.file->f_mode & FMODE_WRITE)) { + if (write && !(fd_file(f)->f_mode & FMODE_WRITE)) { fdput(f); return ERR_PTR(-EPERM); } - fh = f.file->private_data; + fh = fd_file(f)->private_data; dev = fh->rc; get_device(&dev->dev); diff --git a/drivers/vfio/group.c b/drivers/vfio/group.c index ded364588d29..95b336de8a17 100644 --- a/drivers/vfio/group.c +++ b/drivers/vfio/group.c @@ -112,7 +112,7 @@ static int vfio_group_ioctl_set_container(struct vfio_group *group, return -EFAULT; f = fdget(fd); - if (!f.file) + if (!fd_file(f)) return -EBADF; mutex_lock(&group->group_lock); @@ -125,13 +125,13 @@ static int vfio_group_ioctl_set_container(struct vfio_group *group, goto out_unlock; } - container = vfio_container_from_file(f.file); + container = vfio_container_from_file(fd_file(f)); if (container) { ret = vfio_container_attach_group(container, group); goto out_unlock; } - iommufd = iommufd_ctx_from_file(f.file); + iommufd = iommufd_ctx_from_file(fd_file(f)); if (!IS_ERR(iommufd)) { if (IS_ENABLED(CONFIG_VFIO_NOIOMMU) && group->type == VFIO_NO_IOMMU) diff --git a/drivers/vfio/virqfd.c b/drivers/vfio/virqfd.c index 532269133801..d22881245e89 100644 --- a/drivers/vfio/virqfd.c +++ b/drivers/vfio/virqfd.c @@ -134,12 +134,12 @@ int vfio_virqfd_enable(void *opaque, INIT_WORK(&virqfd->flush_inject, virqfd_flush_inject); irqfd = fdget(fd); - if (!irqfd.file) { + if (!fd_file(irqfd)) { ret = -EBADF; goto err_fd; } - ctx = eventfd_ctx_fileget(irqfd.file); + ctx = eventfd_ctx_fileget(fd_file(irqfd)); if (IS_ERR(ctx)) { ret = PTR_ERR(ctx); goto err_ctx; @@ -171,7 +171,7 @@ int vfio_virqfd_enable(void *opaque, init_waitqueue_func_entry(&virqfd->wait, virqfd_wakeup); init_poll_funcptr(&virqfd->pt, virqfd_ptable_queue_proc); - events = vfs_poll(irqfd.file, &virqfd->pt); + events = vfs_poll(fd_file(irqfd), &virqfd->pt); /* * Check if there was an event already pending on the eventfd diff --git a/drivers/virt/acrn/irqfd.c b/drivers/virt/acrn/irqfd.c index d4ad211dce7a..9994d818bb7e 100644 --- a/drivers/virt/acrn/irqfd.c +++ b/drivers/virt/acrn/irqfd.c @@ -125,12 +125,12 @@ static int acrn_irqfd_assign(struct acrn_vm *vm, struct acrn_irqfd *args) INIT_WORK(&irqfd->shutdown, hsm_irqfd_shutdown_work); f = fdget(args->fd); - if (!f.file) { + if (!fd_file(f)) { ret = -EBADF; goto out; } - eventfd = eventfd_ctx_fileget(f.file); + eventfd = eventfd_ctx_fileget(fd_file(f)); if (IS_ERR(eventfd)) { ret = PTR_ERR(eventfd); goto fail; @@ -157,7 +157,7 @@ static int acrn_irqfd_assign(struct acrn_vm *vm, struct acrn_irqfd *args) mutex_unlock(&vm->irqfds_lock); /* Check the pending event in this stage */ - events = vfs_poll(f.file, &irqfd->pt); + events = vfs_poll(fd_file(f), &irqfd->pt); if (events & EPOLLIN) acrn_irqfd_inject(irqfd); diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c index 9563650dfbaf..54e4f285c0f4 100644 --- a/drivers/xen/privcmd.c +++ b/drivers/xen/privcmd.c @@ -959,12 +959,12 @@ static int privcmd_irqfd_assign(struct privcmd_irqfd *irqfd) INIT_WORK(&kirqfd->shutdown, irqfd_shutdown); f = fdget(irqfd->fd); - if (!f.file) { + if (!fd_file(f)) { ret = -EBADF; goto error_kfree; } - kirqfd->eventfd = eventfd_ctx_fileget(f.file); + kirqfd->eventfd = eventfd_ctx_fileget(fd_file(f)); if (IS_ERR(kirqfd->eventfd)) { ret = PTR_ERR(kirqfd->eventfd); goto error_fd_put; @@ -995,7 +995,7 @@ static int privcmd_irqfd_assign(struct privcmd_irqfd *irqfd) * Check if there was an event already pending on the eventfd before we * registered, and trigger it as if we didn't miss it. */ - events = vfs_poll(f.file, &kirqfd->pt); + events = vfs_poll(fd_file(f), &kirqfd->pt); if (events & EPOLLIN) irqfd_inject(kirqfd); @@ -1345,12 +1345,12 @@ static int privcmd_ioeventfd_assign(struct privcmd_ioeventfd *ioeventfd) return -ENOMEM; f = fdget(ioeventfd->event_fd); - if (!f.file) { + if (!fd_file(f)) { ret = -EBADF; goto error_kfree; } - kioeventfd->eventfd = eventfd_ctx_fileget(f.file); + kioeventfd->eventfd = eventfd_ctx_fileget(fd_file(f)); fdput(f); if (IS_ERR(kioeventfd->eventfd)) { diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index e0a664b8a46a..32ddd3d31719 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1312,12 +1312,12 @@ static noinline int __btrfs_ioctl_snap_create(struct file *file, } else { struct fd src = fdget(fd); struct inode *src_inode; - if (!src.file) { + if (!fd_file(src)) { ret = -EINVAL; goto out_drop_write; } - src_inode = file_inode(src.file); + src_inode = file_inode(fd_file(src)); if (src_inode->i_sb != file_inode(file)->i_sb) { btrfs_info(BTRFS_I(file_inode(file))->root->fs_info, "Snapshot src from another FS"); diff --git a/fs/coda/inode.c b/fs/coda/inode.c index 6898dc621011..7d56b6d1e4c3 100644 --- a/fs/coda/inode.c +++ b/fs/coda/inode.c @@ -127,9 +127,9 @@ static int coda_parse_fd(struct fs_context *fc, int fd) int idx; f = fdget(fd); - if (!f.file) + if (!fd_file(f)) return -EBADF; - inode = file_inode(f.file); + inode = file_inode(fd_file(f)); if (!S_ISCHR(inode->i_mode) || imajor(inode) != CODA_PSDEV_MAJOR) { fdput(f); return invalf(fc, "code: Not coda psdev"); diff --git a/fs/eventfd.c b/fs/eventfd.c index 9afdb722fa92..22c934f3a080 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -349,9 +349,9 @@ struct eventfd_ctx *eventfd_ctx_fdget(int fd) { struct eventfd_ctx *ctx; struct fd f = fdget(fd); - if (!f.file) + if (!fd_file(f)) return ERR_PTR(-EBADF); - ctx = eventfd_ctx_fileget(f.file); + ctx = eventfd_ctx_fileget(fd_file(f)); fdput(f); return ctx; } diff --git a/fs/eventpoll.c b/fs/eventpoll.c index f53ca4f7fced..28d1a754cf33 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -2266,17 +2266,17 @@ int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, error = -EBADF; f = fdget(epfd); - if (!f.file) + if (!fd_file(f)) goto error_return; /* Get the "struct file *" for the target file */ tf = fdget(fd); - if (!tf.file) + if (!fd_file(tf)) goto error_fput; /* The target file descriptor must support poll */ error = -EPERM; - if (!file_can_poll(tf.file)) + if (!file_can_poll(fd_file(tf))) goto error_tgt_fput; /* Check if EPOLLWAKEUP is allowed */ @@ -2289,7 +2289,7 @@ int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, * adding an epoll file descriptor inside itself. */ error = -EINVAL; - if (f.file == tf.file || !is_file_epoll(f.file)) + if (fd_file(f) == fd_file(tf) || !is_file_epoll(fd_file(f))) goto error_tgt_fput; /* @@ -2300,7 +2300,7 @@ int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, if (ep_op_has_event(op) && (epds->events & EPOLLEXCLUSIVE)) { if (op == EPOLL_CTL_MOD) goto error_tgt_fput; - if (op == EPOLL_CTL_ADD && (is_file_epoll(tf.file) || + if (op == EPOLL_CTL_ADD && (is_file_epoll(fd_file(tf)) || (epds->events & ~EPOLLEXCLUSIVE_OK_BITS))) goto error_tgt_fput; } @@ -2309,7 +2309,7 @@ int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, * At this point it is safe to assume that the "private_data" contains * our own data structure. */ - ep = f.file->private_data; + ep = fd_file(f)->private_data; /* * When we insert an epoll file descriptor inside another epoll file @@ -2330,16 +2330,16 @@ int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, if (error) goto error_tgt_fput; if (op == EPOLL_CTL_ADD) { - if (READ_ONCE(f.file->f_ep) || ep->gen == loop_check_gen || - is_file_epoll(tf.file)) { + if (READ_ONCE(fd_file(f)->f_ep) || ep->gen == loop_check_gen || + is_file_epoll(fd_file(tf))) { mutex_unlock(&ep->mtx); error = epoll_mutex_lock(&epnested_mutex, 0, nonblock); if (error) goto error_tgt_fput; loop_check_gen++; full_check = 1; - if (is_file_epoll(tf.file)) { - tep = tf.file->private_data; + if (is_file_epoll(fd_file(tf))) { + tep = fd_file(tf)->private_data; error = -ELOOP; if (ep_loop_check(ep, tep) != 0) goto error_tgt_fput; @@ -2355,14 +2355,14 @@ int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, * above, we can be sure to be able to use the item looked up by * ep_find() till we release the mutex. */ - epi = ep_find(ep, tf.file, fd); + epi = ep_find(ep, fd_file(tf), fd); error = -EINVAL; switch (op) { case EPOLL_CTL_ADD: if (!epi) { epds->events |= EPOLLERR | EPOLLHUP; - error = ep_insert(ep, epds, tf.file, fd, full_check); + error = ep_insert(ep, epds, fd_file(tf), fd, full_check); } else error = -EEXIST; break; @@ -2443,7 +2443,7 @@ static int do_epoll_wait(int epfd, struct epoll_event __user *events, /* Get the "struct file *" for the eventpoll file */ f = fdget(epfd); - if (!f.file) + if (!fd_file(f)) return -EBADF; /* @@ -2451,14 +2451,14 @@ static int do_epoll_wait(int epfd, struct epoll_event __user *events, * the user passed to us _is_ an eventpoll file. */ error = -EINVAL; - if (!is_file_epoll(f.file)) + if (!is_file_epoll(fd_file(f))) goto error_fput; /* * At this point it is safe to assume that the "private_data" contains * our own data structure. */ - ep = f.file->private_data; + ep = fd_file(f)->private_data; /* Time to fish for events ... */ error = ep_poll(ep, events, maxevents, to); diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index e8bf5972dd47..1c77400bd88e 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -1343,10 +1343,10 @@ group_extend_out: me.moved_len = 0; donor = fdget(me.donor_fd); - if (!donor.file) + if (!fd_file(donor)) return -EBADF; - if (!(donor.file->f_mode & FMODE_WRITE)) { + if (!(fd_file(donor)->f_mode & FMODE_WRITE)) { err = -EBADF; goto mext_out; } @@ -1367,7 +1367,7 @@ group_extend_out: if (err) goto mext_out; - err = ext4_move_extents(filp, donor.file, me.orig_start, + err = ext4_move_extents(filp, fd_file(donor), me.orig_start, me.donor_start, me.len, &me.moved_len); mnt_drop_write_file(filp); diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 168f08507004..903337f8d21a 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -3014,10 +3014,10 @@ static int __f2fs_ioc_move_range(struct file *filp, return -EBADF; dst = fdget(range->dst_fd); - if (!dst.file) + if (!fd_file(dst)) return -EBADF; - if (!(dst.file->f_mode & FMODE_WRITE)) { + if (!(fd_file(dst)->f_mode & FMODE_WRITE)) { err = -EBADF; goto err_out; } @@ -3026,7 +3026,7 @@ static int __f2fs_ioc_move_range(struct file *filp, if (err) goto err_out; - err = f2fs_move_file_range(filp, range->pos_in, dst.file, + err = f2fs_move_file_range(filp, range->pos_in, fd_file(dst), range->pos_out, range->len); mnt_drop_write_file(filp); diff --git a/fs/fcntl.c b/fs/fcntl.c index 300e5d9ad913..2b5616762354 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -340,7 +340,7 @@ static long f_dupfd_query(int fd, struct file *filp) * overkill, but given our lockless file pointer lookup, the * alternatives are complicated. */ - return f.file == filp; + return fd_file(f) == filp; } static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, @@ -479,17 +479,17 @@ SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) struct fd f = fdget_raw(fd); long err = -EBADF; - if (!f.file) + if (!fd_file(f)) goto out; - if (unlikely(f.file->f_mode & FMODE_PATH)) { + if (unlikely(fd_file(f)->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) goto out1; } - err = security_file_fcntl(f.file, cmd, arg); + err = security_file_fcntl(fd_file(f), cmd, arg); if (!err) - err = do_fcntl(fd, cmd, arg, f.file); + err = do_fcntl(fd, cmd, arg, fd_file(f)); out1: fdput(f); @@ -506,15 +506,15 @@ SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, struct flock64 flock; long err = -EBADF; - if (!f.file) + if (!fd_file(f)) goto out; - if (unlikely(f.file->f_mode & FMODE_PATH)) { + if (unlikely(fd_file(f)->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) goto out1; } - err = security_file_fcntl(f.file, cmd, arg); + err = security_file_fcntl(fd_file(f), cmd, arg); if (err) goto out1; @@ -524,7 +524,7 @@ SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, err = -EFAULT; if (copy_from_user(&flock, argp, sizeof(flock))) break; - err = fcntl_getlk64(f.file, cmd, &flock); + err = fcntl_getlk64(fd_file(f), cmd, &flock); if (!err && copy_to_user(argp, &flock, sizeof(flock))) err = -EFAULT; break; @@ -535,10 +535,10 @@ SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, err = -EFAULT; if (copy_from_user(&flock, argp, sizeof(flock))) break; - err = fcntl_setlk64(fd, f.file, cmd, &flock); + err = fcntl_setlk64(fd, fd_file(f), cmd, &flock); break; default: - err = do_fcntl(fd, cmd, arg, f.file); + err = do_fcntl(fd, cmd, arg, fd_file(f)); break; } out1: @@ -643,15 +643,15 @@ static long do_compat_fcntl64(unsigned int fd, unsigned int cmd, struct flock flock; long err = -EBADF; - if (!f.file) + if (!fd_file(f)) return err; - if (unlikely(f.file->f_mode & FMODE_PATH)) { + if (unlikely(fd_file(f)->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) goto out_put; } - err = security_file_fcntl(f.file, cmd, arg); + err = security_file_fcntl(fd_file(f), cmd, arg); if (err) goto out_put; @@ -660,7 +660,7 @@ static long do_compat_fcntl64(unsigned int fd, unsigned int cmd, err = get_compat_flock(&flock, compat_ptr(arg)); if (err) break; - err = fcntl_getlk(f.file, convert_fcntl_cmd(cmd), &flock); + err = fcntl_getlk(fd_file(f), convert_fcntl_cmd(cmd), &flock); if (err) break; err = fixup_compat_flock(&flock); @@ -672,7 +672,7 @@ static long do_compat_fcntl64(unsigned int fd, unsigned int cmd, err = get_compat_flock64(&flock, compat_ptr(arg)); if (err) break; - err = fcntl_getlk(f.file, convert_fcntl_cmd(cmd), &flock); + err = fcntl_getlk(fd_file(f), convert_fcntl_cmd(cmd), &flock); if (!err) err = put_compat_flock64(&flock, compat_ptr(arg)); break; @@ -681,7 +681,7 @@ static long do_compat_fcntl64(unsigned int fd, unsigned int cmd, err = get_compat_flock(&flock, compat_ptr(arg)); if (err) break; - err = fcntl_setlk(fd, f.file, convert_fcntl_cmd(cmd), &flock); + err = fcntl_setlk(fd, fd_file(f), convert_fcntl_cmd(cmd), &flock); break; case F_SETLK64: case F_SETLKW64: @@ -690,10 +690,10 @@ static long do_compat_fcntl64(unsigned int fd, unsigned int cmd, err = get_compat_flock64(&flock, compat_ptr(arg)); if (err) break; - err = fcntl_setlk(fd, f.file, convert_fcntl_cmd(cmd), &flock); + err = fcntl_setlk(fd, fd_file(f), convert_fcntl_cmd(cmd), &flock); break; default: - err = do_fcntl(fd, cmd, arg, f.file); + err = do_fcntl(fd, cmd, arg, fd_file(f)); break; } out_put: diff --git a/fs/fhandle.c b/fs/fhandle.c index 6e8cea16790e..3f07b52874a8 100644 --- a/fs/fhandle.c +++ b/fs/fhandle.c @@ -125,9 +125,9 @@ static int get_path_from_fd(int fd, struct path *root) spin_unlock(&fs->lock); } else { struct fd f = fdget(fd); - if (!f.file) + if (!fd_file(f)) return -EBADF; - *root = f.file->f_path; + *root = fd_file(f)->f_path; path_get(root); fdput(f); } diff --git a/fs/fsopen.c b/fs/fsopen.c index ed2dd000622e..ee92ca58429e 100644 --- a/fs/fsopen.c +++ b/fs/fsopen.c @@ -394,13 +394,13 @@ SYSCALL_DEFINE5(fsconfig, } f = fdget(fd); - if (!f.file) + if (!fd_file(f)) return -EBADF; ret = -EINVAL; - if (f.file->f_op != &fscontext_fops) + if (fd_file(f)->f_op != &fscontext_fops) goto out_f; - fc = f.file->private_data; + fc = fd_file(f)->private_data; if (fc->ops == &legacy_fs_context_ops) { switch (cmd) { case FSCONFIG_SET_BINARY: diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 9eb191b5c4de..991b9ae8e7c9 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -2321,15 +2321,15 @@ static long fuse_dev_ioctl_clone(struct file *file, __u32 __user *argp) return -EFAULT; f = fdget(oldfd); - if (!f.file) + if (!fd_file(f)) return -EINVAL; /* * Check against file->f_op because CUSE * uses the same ioctl handler. */ - if (f.file->f_op == file->f_op) - fud = fuse_get_dev(f.file); + if (fd_file(f)->f_op == file->f_op) + fud = fuse_get_dev(fd_file(f)); res = -EINVAL; if (fud) { diff --git a/fs/ioctl.c b/fs/ioctl.c index 64776891120c..6e0c954388d4 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -235,9 +235,9 @@ static long ioctl_file_clone(struct file *dst_file, unsigned long srcfd, loff_t cloned; int ret; - if (!src_file.file) + if (!fd_file(src_file)) return -EBADF; - cloned = vfs_clone_file_range(src_file.file, off, dst_file, destoff, + cloned = vfs_clone_file_range(fd_file(src_file), off, dst_file, destoff, olen, 0); if (cloned < 0) ret = cloned; @@ -895,16 +895,16 @@ SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) struct fd f = fdget(fd); int error; - if (!f.file) + if (!fd_file(f)) return -EBADF; - error = security_file_ioctl(f.file, cmd, arg); + error = security_file_ioctl(fd_file(f), cmd, arg); if (error) goto out; - error = do_vfs_ioctl(f.file, fd, cmd, arg); + error = do_vfs_ioctl(fd_file(f), fd, cmd, arg); if (error == -ENOIOCTLCMD) - error = vfs_ioctl(f.file, cmd, arg); + error = vfs_ioctl(fd_file(f), cmd, arg); out: fdput(f); @@ -953,32 +953,32 @@ COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, struct fd f = fdget(fd); int error; - if (!f.file) + if (!fd_file(f)) return -EBADF; - error = security_file_ioctl_compat(f.file, cmd, arg); + error = security_file_ioctl_compat(fd_file(f), cmd, arg); if (error) goto out; switch (cmd) { /* FICLONE takes an int argument, so don't use compat_ptr() */ case FICLONE: - error = ioctl_file_clone(f.file, arg, 0, 0, 0); + error = ioctl_file_clone(fd_file(f), arg, 0, 0, 0); break; #if defined(CONFIG_X86_64) /* these get messy on amd64 due to alignment differences */ case FS_IOC_RESVSP_32: case FS_IOC_RESVSP64_32: - error = compat_ioctl_preallocate(f.file, 0, compat_ptr(arg)); + error = compat_ioctl_preallocate(fd_file(f), 0, compat_ptr(arg)); break; case FS_IOC_UNRESVSP_32: case FS_IOC_UNRESVSP64_32: - error = compat_ioctl_preallocate(f.file, FALLOC_FL_PUNCH_HOLE, + error = compat_ioctl_preallocate(fd_file(f), FALLOC_FL_PUNCH_HOLE, compat_ptr(arg)); break; case FS_IOC_ZERO_RANGE_32: - error = compat_ioctl_preallocate(f.file, FALLOC_FL_ZERO_RANGE, + error = compat_ioctl_preallocate(fd_file(f), FALLOC_FL_ZERO_RANGE, compat_ptr(arg)); break; #endif @@ -998,13 +998,13 @@ COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, * argument. */ default: - error = do_vfs_ioctl(f.file, fd, cmd, + error = do_vfs_ioctl(fd_file(f), fd, cmd, (unsigned long)compat_ptr(arg)); if (error != -ENOIOCTLCMD) break; - if (f.file->f_op->compat_ioctl) - error = f.file->f_op->compat_ioctl(f.file, cmd, arg); + if (fd_file(f)->f_op->compat_ioctl) + error = fd_file(f)->f_op->compat_ioctl(fd_file(f), cmd, arg); if (error == -ENOIOCTLCMD) error = -ENOTTY; break; diff --git a/fs/kernel_read_file.c b/fs/kernel_read_file.c index c429c42a6867..9ff37ae650ea 100644 --- a/fs/kernel_read_file.c +++ b/fs/kernel_read_file.c @@ -178,10 +178,10 @@ ssize_t kernel_read_file_from_fd(int fd, loff_t offset, void **buf, struct fd f = fdget(fd); ssize_t ret = -EBADF; - if (!f.file || !(f.file->f_mode & FMODE_READ)) + if (!fd_file(f) || !(fd_file(f)->f_mode & FMODE_READ)) goto out; - ret = kernel_read_file(f.file, offset, buf, buf_size, file_size, id); + ret = kernel_read_file(fd_file(f), offset, buf, buf_size, file_size, id); out: fdput(f); return ret; diff --git a/fs/locks.c b/fs/locks.c index 9afb16e0683f..239759a356e9 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -2153,15 +2153,15 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd) error = -EBADF; f = fdget(fd); - if (!f.file) + if (!fd_file(f)) return error; - if (type != F_UNLCK && !(f.file->f_mode & (FMODE_READ | FMODE_WRITE))) + if (type != F_UNLCK && !(fd_file(f)->f_mode & (FMODE_READ | FMODE_WRITE))) goto out_putf; - flock_make_lock(f.file, &fl, type); + flock_make_lock(fd_file(f), &fl, type); - error = security_file_lock(f.file, fl.c.flc_type); + error = security_file_lock(fd_file(f), fl.c.flc_type); if (error) goto out_putf; @@ -2169,12 +2169,12 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd) if (can_sleep) fl.c.flc_flags |= FL_SLEEP; - if (f.file->f_op->flock) - error = f.file->f_op->flock(f.file, + if (fd_file(f)->f_op->flock) + error = fd_file(f)->f_op->flock(fd_file(f), (can_sleep) ? F_SETLKW : F_SETLK, &fl); else - error = locks_lock_file_wait(f.file, &fl); + error = locks_lock_file_wait(fd_file(f), &fl); locks_release_private(&fl); out_putf: diff --git a/fs/namei.c b/fs/namei.c index 5512cb10fa89..af86e3330594 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2492,25 +2492,25 @@ static const char *path_init(struct nameidata *nd, unsigned flags) struct fd f = fdget_raw(nd->dfd); struct dentry *dentry; - if (!f.file) + if (!fd_file(f)) return ERR_PTR(-EBADF); if (flags & LOOKUP_LINKAT_EMPTY) { - if (f.file->f_cred != current_cred() && - !ns_capable(f.file->f_cred->user_ns, CAP_DAC_READ_SEARCH)) { + if (fd_file(f)->f_cred != current_cred() && + !ns_capable(fd_file(f)->f_cred->user_ns, CAP_DAC_READ_SEARCH)) { fdput(f); return ERR_PTR(-ENOENT); } } - dentry = f.file->f_path.dentry; + dentry = fd_file(f)->f_path.dentry; if (*s && unlikely(!d_can_lookup(dentry))) { fdput(f); return ERR_PTR(-ENOTDIR); } - nd->path = f.file->f_path; + nd->path = fd_file(f)->f_path; if (flags & LOOKUP_RCU) { nd->inode = nd->path.dentry->d_inode; nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq); diff --git a/fs/namespace.c b/fs/namespace.c index 328087a4df8a..c46d48bb38cd 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -4099,14 +4099,14 @@ SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags, } f = fdget(fs_fd); - if (!f.file) + if (!fd_file(f)) return -EBADF; ret = -EINVAL; - if (f.file->f_op != &fscontext_fops) + if (fd_file(f)->f_op != &fscontext_fops) goto err_fsfd; - fc = f.file->private_data; + fc = fd_file(f)->private_data; ret = mutex_lock_interruptible(&fc->uapi_mutex); if (ret < 0) @@ -4649,15 +4649,15 @@ static int build_mount_idmapped(const struct mount_attr *attr, size_t usize, return -EINVAL; f = fdget(attr->userns_fd); - if (!f.file) + if (!fd_file(f)) return -EBADF; - if (!proc_ns_file(f.file)) { + if (!proc_ns_file(fd_file(f))) { err = -EINVAL; goto out_fput; } - ns = get_proc_ns(file_inode(f.file)); + ns = get_proc_ns(file_inode(fd_file(f))); if (ns->ops->type != CLONE_NEWUSER) { err = -EINVAL; goto out_fput; diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 9ec313e9f6e1..13454e5fd3fb 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -1006,17 +1006,17 @@ static int fanotify_find_path(int dfd, const char __user *filename, struct fd f = fdget(dfd); ret = -EBADF; - if (!f.file) + if (!fd_file(f)) goto out; ret = -ENOTDIR; if ((flags & FAN_MARK_ONLYDIR) && - !(S_ISDIR(file_inode(f.file)->i_mode))) { + !(S_ISDIR(file_inode(fd_file(f))->i_mode))) { fdput(f); goto out; } - *path = f.file->f_path; + *path = fd_file(f)->f_path; path_get(path); fdput(f); } else { @@ -1753,14 +1753,14 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, } f = fdget(fanotify_fd); - if (unlikely(!f.file)) + if (unlikely(!fd_file(f))) return -EBADF; /* verify that this is indeed an fanotify instance */ ret = -EINVAL; - if (unlikely(f.file->f_op != &fanotify_fops)) + if (unlikely(fd_file(f)->f_op != &fanotify_fops)) goto fput_and_out; - group = f.file->private_data; + group = fd_file(f)->private_data; /* * An unprivileged user is not allowed to setup mount nor filesystem diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 4ffc30606e0b..c7e451d5bd51 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -753,7 +753,7 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname, return -EINVAL; f = fdget(fd); - if (unlikely(!f.file)) + if (unlikely(!fd_file(f))) return -EBADF; /* IN_MASK_ADD and IN_MASK_CREATE don't make sense together */ @@ -763,7 +763,7 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname, } /* verify that this is indeed an inotify instance */ - if (unlikely(f.file->f_op != &inotify_fops)) { + if (unlikely(fd_file(f)->f_op != &inotify_fops)) { ret = -EINVAL; goto fput_and_out; } @@ -780,7 +780,7 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname, /* inode held in place by reference to path; group by fget on fd */ inode = path.dentry->d_inode; - group = f.file->private_data; + group = fd_file(f)->private_data; /* create/update an inode mark */ ret = inotify_update_watch(group, inode, mask); @@ -798,14 +798,14 @@ SYSCALL_DEFINE2(inotify_rm_watch, int, fd, __s32, wd) int ret = -EINVAL; f = fdget(fd); - if (unlikely(!f.file)) + if (unlikely(!fd_file(f))) return -EBADF; /* verify that this is indeed an inotify instance */ - if (unlikely(f.file->f_op != &inotify_fops)) + if (unlikely(fd_file(f)->f_op != &inotify_fops)) goto out; - group = f.file->private_data; + group = fd_file(f)->private_data; i_mark = inotify_idr_find(group, wd); if (unlikely(!i_mark)) diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 1bde1281d514..4b9f45d7049e 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -1785,17 +1785,17 @@ static ssize_t o2hb_region_dev_store(struct config_item *item, goto out; f = fdget(fd); - if (f.file == NULL) + if (fd_file(f) == NULL) goto out; if (reg->hr_blocks == 0 || reg->hr_start_block == 0 || reg->hr_block_bytes == 0) goto out2; - if (!S_ISBLK(f.file->f_mapping->host->i_mode)) + if (!S_ISBLK(fd_file(f)->f_mapping->host->i_mode)) goto out2; - reg->hr_bdev_file = bdev_file_open_by_dev(f.file->f_mapping->host->i_rdev, + reg->hr_bdev_file = bdev_file_open_by_dev(fd_file(f)->f_mapping->host->i_rdev, BLK_OPEN_WRITE | BLK_OPEN_READ, NULL, NULL); if (IS_ERR(reg->hr_bdev_file)) { ret = PTR_ERR(reg->hr_bdev_file); diff --git a/fs/open.c b/fs/open.c index 22adbef7ecc2..a388828ccd22 100644 --- a/fs/open.c +++ b/fs/open.c @@ -193,10 +193,10 @@ long do_sys_ftruncate(unsigned int fd, loff_t length, int small) if (length < 0) return -EINVAL; f = fdget(fd); - if (!f.file) + if (!fd_file(f)) return -EBADF; - error = do_ftruncate(f.file, length, small); + error = do_ftruncate(fd_file(f), length, small); fdput(f); return error; @@ -353,8 +353,8 @@ int ksys_fallocate(int fd, int mode, loff_t offset, loff_t len) struct fd f = fdget(fd); int error = -EBADF; - if (f.file) { - error = vfs_fallocate(f.file, mode, offset, len); + if (fd_file(f)) { + error = vfs_fallocate(fd_file(f), mode, offset, len); fdput(f); } return error; @@ -585,16 +585,16 @@ SYSCALL_DEFINE1(fchdir, unsigned int, fd) int error; error = -EBADF; - if (!f.file) + if (!fd_file(f)) goto out; error = -ENOTDIR; - if (!d_can_lookup(f.file->f_path.dentry)) + if (!d_can_lookup(fd_file(f)->f_path.dentry)) goto out_putf; - error = file_permission(f.file, MAY_EXEC | MAY_CHDIR); + error = file_permission(fd_file(f), MAY_EXEC | MAY_CHDIR); if (!error) - set_fs_pwd(current->fs, &f.file->f_path); + set_fs_pwd(current->fs, &fd_file(f)->f_path); out_putf: fdput(f); out: @@ -675,8 +675,8 @@ SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode) struct fd f = fdget(fd); int err = -EBADF; - if (f.file) { - err = vfs_fchmod(f.file, mode); + if (fd_file(f)) { + err = vfs_fchmod(fd_file(f), mode); fdput(f); } return err; @@ -869,8 +869,8 @@ int ksys_fchown(unsigned int fd, uid_t user, gid_t group) struct fd f = fdget(fd); int error = -EBADF; - if (f.file) { - error = vfs_fchown(f.file, user, group); + if (fd_file(f)) { + error = vfs_fchown(fd_file(f), user, group); fdput(f); } return error; diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 1a411cae57ed..c4963d0c5549 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -209,13 +209,13 @@ static loff_t ovl_llseek(struct file *file, loff_t offset, int whence) * files, so we use the real file to perform seeks. */ ovl_inode_lock(inode); - real.file->f_pos = file->f_pos; + fd_file(real)->f_pos = file->f_pos; old_cred = ovl_override_creds(inode->i_sb); - ret = vfs_llseek(real.file, offset, whence); + ret = vfs_llseek(fd_file(real), offset, whence); revert_creds(old_cred); - file->f_pos = real.file->f_pos; + file->f_pos = fd_file(real)->f_pos; ovl_inode_unlock(inode); fdput(real); @@ -275,7 +275,7 @@ static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter) if (ret) return ret; - ret = backing_file_read_iter(real.file, iter, iocb, iocb->ki_flags, + ret = backing_file_read_iter(fd_file(real), iter, iocb, iocb->ki_flags, &ctx); fdput(real); @@ -314,7 +314,7 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter) * this property in case it is set by the issuer. */ ifl &= ~IOCB_DIO_CALLER_COMP; - ret = backing_file_write_iter(real.file, iter, iocb, ifl, &ctx); + ret = backing_file_write_iter(fd_file(real), iter, iocb, ifl, &ctx); fdput(real); out_unlock: @@ -339,7 +339,7 @@ static ssize_t ovl_splice_read(struct file *in, loff_t *ppos, if (ret) return ret; - ret = backing_file_splice_read(real.file, ppos, pipe, len, flags, &ctx); + ret = backing_file_splice_read(fd_file(real), ppos, pipe, len, flags, &ctx); fdput(real); return ret; @@ -348,7 +348,7 @@ static ssize_t ovl_splice_read(struct file *in, loff_t *ppos, /* * Calling iter_file_splice_write() directly from overlay's f_op may deadlock * due to lock order inversion between pipe->mutex in iter_file_splice_write() - * and file_start_write(real.file) in ovl_write_iter(). + * and file_start_write(fd_file(real)) in ovl_write_iter(). * * So do everything ovl_write_iter() does and call iter_file_splice_write() on * the real file. @@ -373,7 +373,7 @@ static ssize_t ovl_splice_write(struct pipe_inode_info *pipe, struct file *out, if (ret) goto out_unlock; - ret = backing_file_splice_write(pipe, real.file, ppos, len, flags, &ctx); + ret = backing_file_splice_write(pipe, fd_file(real), ppos, len, flags, &ctx); fdput(real); out_unlock: @@ -397,9 +397,9 @@ static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync) return ret; /* Don't sync lower file for fear of receiving EROFS error */ - if (file_inode(real.file) == ovl_inode_upper(file_inode(file))) { + if (file_inode(fd_file(real)) == ovl_inode_upper(file_inode(file))) { old_cred = ovl_override_creds(file_inode(file)->i_sb); - ret = vfs_fsync_range(real.file, start, end, datasync); + ret = vfs_fsync_range(fd_file(real), start, end, datasync); revert_creds(old_cred); } @@ -439,7 +439,7 @@ static long ovl_fallocate(struct file *file, int mode, loff_t offset, loff_t len goto out_unlock; old_cred = ovl_override_creds(file_inode(file)->i_sb); - ret = vfs_fallocate(real.file, mode, offset, len); + ret = vfs_fallocate(fd_file(real), mode, offset, len); revert_creds(old_cred); /* Update size */ @@ -464,7 +464,7 @@ static int ovl_fadvise(struct file *file, loff_t offset, loff_t len, int advice) return ret; old_cred = ovl_override_creds(file_inode(file)->i_sb); - ret = vfs_fadvise(real.file, offset, len, advice); + ret = vfs_fadvise(fd_file(real), offset, len, advice); revert_creds(old_cred); fdput(real); @@ -509,18 +509,18 @@ static loff_t ovl_copyfile(struct file *file_in, loff_t pos_in, old_cred = ovl_override_creds(file_inode(file_out)->i_sb); switch (op) { case OVL_COPY: - ret = vfs_copy_file_range(real_in.file, pos_in, - real_out.file, pos_out, len, flags); + ret = vfs_copy_file_range(fd_file(real_in), pos_in, + fd_file(real_out), pos_out, len, flags); break; case OVL_CLONE: - ret = vfs_clone_file_range(real_in.file, pos_in, - real_out.file, pos_out, len, flags); + ret = vfs_clone_file_range(fd_file(real_in), pos_in, + fd_file(real_out), pos_out, len, flags); break; case OVL_DEDUPE: - ret = vfs_dedupe_file_range_one(real_in.file, pos_in, - real_out.file, pos_out, len, + ret = vfs_dedupe_file_range_one(fd_file(real_in), pos_in, + fd_file(real_out), pos_out, len, flags); break; } @@ -583,9 +583,9 @@ static int ovl_flush(struct file *file, fl_owner_t id) if (err) return err; - if (real.file->f_op->flush) { + if (fd_file(real)->f_op->flush) { old_cred = ovl_override_creds(file_inode(file)->i_sb); - err = real.file->f_op->flush(real.file, id); + err = fd_file(real)->f_op->flush(fd_file(real), id); revert_creds(old_cred); } fdput(real); diff --git a/fs/quota/quota.c b/fs/quota/quota.c index 0e41fb84060f..290157bc7bec 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -980,7 +980,7 @@ SYSCALL_DEFINE4(quotactl_fd, unsigned int, fd, unsigned int, cmd, int ret; f = fdget_raw(fd); - if (!f.file) + if (!fd_file(f)) return -EBADF; ret = -EINVAL; @@ -988,12 +988,12 @@ SYSCALL_DEFINE4(quotactl_fd, unsigned int, fd, unsigned int, cmd, goto out; if (quotactl_cmd_write(cmds)) { - ret = mnt_want_write(f.file->f_path.mnt); + ret = mnt_want_write(fd_file(f)->f_path.mnt); if (ret) goto out; } - sb = f.file->f_path.mnt->mnt_sb; + sb = fd_file(f)->f_path.mnt->mnt_sb; if (quotactl_cmd_onoff(cmds)) down_write(&sb->s_umount); else @@ -1007,7 +1007,7 @@ SYSCALL_DEFINE4(quotactl_fd, unsigned int, fd, unsigned int, cmd, up_read(&sb->s_umount); if (quotactl_cmd_write(cmds)) - mnt_drop_write(f.file->f_path.mnt); + mnt_drop_write(fd_file(f)->f_path.mnt); out: fdput(f); return ret; diff --git a/fs/read_write.c b/fs/read_write.c index 90e283b31ca1..59d6d0dee579 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -294,12 +294,12 @@ static off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence) { off_t retval; struct fd f = fdget_pos(fd); - if (!f.file) + if (!fd_file(f)) return -EBADF; retval = -EINVAL; if (whence <= SEEK_MAX) { - loff_t res = vfs_llseek(f.file, offset, whence); + loff_t res = vfs_llseek(fd_file(f), offset, whence); retval = res; if (res != (loff_t)retval) retval = -EOVERFLOW; /* LFS: should only happen on 32 bit platforms */ @@ -330,14 +330,14 @@ SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high, struct fd f = fdget_pos(fd); loff_t offset; - if (!f.file) + if (!fd_file(f)) return -EBADF; retval = -EINVAL; if (whence > SEEK_MAX) goto out_putf; - offset = vfs_llseek(f.file, ((loff_t) offset_high << 32) | offset_low, + offset = vfs_llseek(fd_file(f), ((loff_t) offset_high << 32) | offset_low, whence); retval = (int)offset; @@ -610,15 +610,15 @@ ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count) struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; - if (f.file) { - loff_t pos, *ppos = file_ppos(f.file); + if (fd_file(f)) { + loff_t pos, *ppos = file_ppos(fd_file(f)); if (ppos) { pos = *ppos; ppos = &pos; } - ret = vfs_read(f.file, buf, count, ppos); + ret = vfs_read(fd_file(f), buf, count, ppos); if (ret >= 0 && ppos) - f.file->f_pos = pos; + fd_file(f)->f_pos = pos; fdput_pos(f); } return ret; @@ -634,15 +634,15 @@ ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count) struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; - if (f.file) { - loff_t pos, *ppos = file_ppos(f.file); + if (fd_file(f)) { + loff_t pos, *ppos = file_ppos(fd_file(f)); if (ppos) { pos = *ppos; ppos = &pos; } - ret = vfs_write(f.file, buf, count, ppos); + ret = vfs_write(fd_file(f), buf, count, ppos); if (ret >= 0 && ppos) - f.file->f_pos = pos; + fd_file(f)->f_pos = pos; fdput_pos(f); } @@ -665,10 +665,10 @@ ssize_t ksys_pread64(unsigned int fd, char __user *buf, size_t count, return -EINVAL; f = fdget(fd); - if (f.file) { + if (fd_file(f)) { ret = -ESPIPE; - if (f.file->f_mode & FMODE_PREAD) - ret = vfs_read(f.file, buf, count, &pos); + if (fd_file(f)->f_mode & FMODE_PREAD) + ret = vfs_read(fd_file(f), buf, count, &pos); fdput(f); } @@ -699,10 +699,10 @@ ssize_t ksys_pwrite64(unsigned int fd, const char __user *buf, return -EINVAL; f = fdget(fd); - if (f.file) { + if (fd_file(f)) { ret = -ESPIPE; - if (f.file->f_mode & FMODE_PWRITE) - ret = vfs_write(f.file, buf, count, &pos); + if (fd_file(f)->f_mode & FMODE_PWRITE) + ret = vfs_write(fd_file(f), buf, count, &pos); fdput(f); } @@ -985,15 +985,15 @@ static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec, struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; - if (f.file) { - loff_t pos, *ppos = file_ppos(f.file); + if (fd_file(f)) { + loff_t pos, *ppos = file_ppos(fd_file(f)); if (ppos) { pos = *ppos; ppos = &pos; } - ret = vfs_readv(f.file, vec, vlen, ppos, flags); + ret = vfs_readv(fd_file(f), vec, vlen, ppos, flags); if (ret >= 0 && ppos) - f.file->f_pos = pos; + fd_file(f)->f_pos = pos; fdput_pos(f); } @@ -1009,15 +1009,15 @@ static ssize_t do_writev(unsigned long fd, const struct iovec __user *vec, struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; - if (f.file) { - loff_t pos, *ppos = file_ppos(f.file); + if (fd_file(f)) { + loff_t pos, *ppos = file_ppos(fd_file(f)); if (ppos) { pos = *ppos; ppos = &pos; } - ret = vfs_writev(f.file, vec, vlen, ppos, flags); + ret = vfs_writev(fd_file(f), vec, vlen, ppos, flags); if (ret >= 0 && ppos) - f.file->f_pos = pos; + fd_file(f)->f_pos = pos; fdput_pos(f); } @@ -1043,10 +1043,10 @@ static ssize_t do_preadv(unsigned long fd, const struct iovec __user *vec, return -EINVAL; f = fdget(fd); - if (f.file) { + if (fd_file(f)) { ret = -ESPIPE; - if (f.file->f_mode & FMODE_PREAD) - ret = vfs_readv(f.file, vec, vlen, &pos, flags); + if (fd_file(f)->f_mode & FMODE_PREAD) + ret = vfs_readv(fd_file(f), vec, vlen, &pos, flags); fdput(f); } @@ -1066,10 +1066,10 @@ static ssize_t do_pwritev(unsigned long fd, const struct iovec __user *vec, return -EINVAL; f = fdget(fd); - if (f.file) { + if (fd_file(f)) { ret = -ESPIPE; - if (f.file->f_mode & FMODE_PWRITE) - ret = vfs_writev(f.file, vec, vlen, &pos, flags); + if (fd_file(f)->f_mode & FMODE_PWRITE) + ret = vfs_writev(fd_file(f), vec, vlen, &pos, flags); fdput(f); } @@ -1235,19 +1235,19 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, */ retval = -EBADF; in = fdget(in_fd); - if (!in.file) + if (!fd_file(in)) goto out; - if (!(in.file->f_mode & FMODE_READ)) + if (!(fd_file(in)->f_mode & FMODE_READ)) goto fput_in; retval = -ESPIPE; if (!ppos) { - pos = in.file->f_pos; + pos = fd_file(in)->f_pos; } else { pos = *ppos; - if (!(in.file->f_mode & FMODE_PREAD)) + if (!(fd_file(in)->f_mode & FMODE_PREAD)) goto fput_in; } - retval = rw_verify_area(READ, in.file, &pos, count); + retval = rw_verify_area(READ, fd_file(in), &pos, count); if (retval < 0) goto fput_in; if (count > MAX_RW_COUNT) @@ -1258,13 +1258,13 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, */ retval = -EBADF; out = fdget(out_fd); - if (!out.file) + if (!fd_file(out)) goto fput_in; - if (!(out.file->f_mode & FMODE_WRITE)) + if (!(fd_file(out)->f_mode & FMODE_WRITE)) goto fput_out; - in_inode = file_inode(in.file); - out_inode = file_inode(out.file); - out_pos = out.file->f_pos; + in_inode = file_inode(fd_file(in)); + out_inode = file_inode(fd_file(out)); + out_pos = fd_file(out)->f_pos; if (!max) max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes); @@ -1284,33 +1284,33 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, * and the application is arguably buggy if it doesn't expect * EAGAIN on a non-blocking file descriptor. */ - if (in.file->f_flags & O_NONBLOCK) + if (fd_file(in)->f_flags & O_NONBLOCK) fl = SPLICE_F_NONBLOCK; #endif - opipe = get_pipe_info(out.file, true); + opipe = get_pipe_info(fd_file(out), true); if (!opipe) { - retval = rw_verify_area(WRITE, out.file, &out_pos, count); + retval = rw_verify_area(WRITE, fd_file(out), &out_pos, count); if (retval < 0) goto fput_out; - retval = do_splice_direct(in.file, &pos, out.file, &out_pos, + retval = do_splice_direct(fd_file(in), &pos, fd_file(out), &out_pos, count, fl); } else { - if (out.file->f_flags & O_NONBLOCK) + if (fd_file(out)->f_flags & O_NONBLOCK) fl |= SPLICE_F_NONBLOCK; - retval = splice_file_to_pipe(in.file, opipe, &pos, count, fl); + retval = splice_file_to_pipe(fd_file(in), opipe, &pos, count, fl); } if (retval > 0) { add_rchar(current, retval); add_wchar(current, retval); - fsnotify_access(in.file); - fsnotify_modify(out.file); - out.file->f_pos = out_pos; + fsnotify_access(fd_file(in)); + fsnotify_modify(fd_file(out)); + fd_file(out)->f_pos = out_pos; if (ppos) *ppos = pos; else - in.file->f_pos = pos; + fd_file(in)->f_pos = pos; } inc_syscr(current); @@ -1583,11 +1583,11 @@ SYSCALL_DEFINE6(copy_file_range, int, fd_in, loff_t __user *, off_in, ssize_t ret = -EBADF; f_in = fdget(fd_in); - if (!f_in.file) + if (!fd_file(f_in)) goto out2; f_out = fdget(fd_out); - if (!f_out.file) + if (!fd_file(f_out)) goto out1; ret = -EFAULT; @@ -1595,21 +1595,21 @@ SYSCALL_DEFINE6(copy_file_range, int, fd_in, loff_t __user *, off_in, if (copy_from_user(&pos_in, off_in, sizeof(loff_t))) goto out; } else { - pos_in = f_in.file->f_pos; + pos_in = fd_file(f_in)->f_pos; } if (off_out) { if (copy_from_user(&pos_out, off_out, sizeof(loff_t))) goto out; } else { - pos_out = f_out.file->f_pos; + pos_out = fd_file(f_out)->f_pos; } ret = -EINVAL; if (flags != 0) goto out; - ret = vfs_copy_file_range(f_in.file, pos_in, f_out.file, pos_out, len, + ret = vfs_copy_file_range(fd_file(f_in), pos_in, fd_file(f_out), pos_out, len, flags); if (ret > 0) { pos_in += ret; @@ -1619,14 +1619,14 @@ SYSCALL_DEFINE6(copy_file_range, int, fd_in, loff_t __user *, off_in, if (copy_to_user(off_in, &pos_in, sizeof(loff_t))) ret = -EFAULT; } else { - f_in.file->f_pos = pos_in; + fd_file(f_in)->f_pos = pos_in; } if (off_out) { if (copy_to_user(off_out, &pos_out, sizeof(loff_t))) ret = -EFAULT; } else { - f_out.file->f_pos = pos_out; + fd_file(f_out)->f_pos = pos_out; } } diff --git a/fs/readdir.c b/fs/readdir.c index d6c82421902a..6d29cab8576e 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -225,10 +225,10 @@ SYSCALL_DEFINE3(old_readdir, unsigned int, fd, .dirent = dirent }; - if (!f.file) + if (!fd_file(f)) return -EBADF; - error = iterate_dir(f.file, &buf.ctx); + error = iterate_dir(fd_file(f), &buf.ctx); if (buf.result) error = buf.result; @@ -318,10 +318,10 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd, int error; f = fdget_pos(fd); - if (!f.file) + if (!fd_file(f)) return -EBADF; - error = iterate_dir(f.file, &buf.ctx); + error = iterate_dir(fd_file(f), &buf.ctx); if (error >= 0) error = buf.error; if (buf.prev_reclen) { @@ -401,10 +401,10 @@ SYSCALL_DEFINE3(getdents64, unsigned int, fd, int error; f = fdget_pos(fd); - if (!f.file) + if (!fd_file(f)) return -EBADF; - error = iterate_dir(f.file, &buf.ctx); + error = iterate_dir(fd_file(f), &buf.ctx); if (error >= 0) error = buf.error; if (buf.prev_reclen) { @@ -483,10 +483,10 @@ COMPAT_SYSCALL_DEFINE3(old_readdir, unsigned int, fd, .dirent = dirent }; - if (!f.file) + if (!fd_file(f)) return -EBADF; - error = iterate_dir(f.file, &buf.ctx); + error = iterate_dir(fd_file(f), &buf.ctx); if (buf.result) error = buf.result; @@ -569,10 +569,10 @@ COMPAT_SYSCALL_DEFINE3(getdents, unsigned int, fd, int error; f = fdget_pos(fd); - if (!f.file) + if (!fd_file(f)) return -EBADF; - error = iterate_dir(f.file, &buf.ctx); + error = iterate_dir(fd_file(f), &buf.ctx); if (error >= 0) error = buf.error; if (buf.prev_reclen) { diff --git a/fs/remap_range.c b/fs/remap_range.c index 28246dfc8485..4403d5c68fcb 100644 --- a/fs/remap_range.c +++ b/fs/remap_range.c @@ -537,7 +537,7 @@ int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same) for (i = 0, info = same->info; i < count; i++, info++) { struct fd dst_fd = fdget(info->dest_fd); - struct file *dst_file = dst_fd.file; + struct file *dst_file = fd_file(dst_fd); if (!dst_file) { info->status = -EBADF; diff --git a/fs/select.c b/fs/select.c index 9515c3fa1a03..97e1009dde00 100644 --- a/fs/select.c +++ b/fs/select.c @@ -532,10 +532,10 @@ static noinline_for_stack int do_select(int n, fd_set_bits *fds, struct timespec continue; mask = EPOLLNVAL; f = fdget(i); - if (f.file) { + if (fd_file(f)) { wait_key_set(wait, in, out, bit, busy_flag); - mask = vfs_poll(f.file, wait); + mask = vfs_poll(fd_file(f), wait); fdput(f); } @@ -864,13 +864,13 @@ static inline __poll_t do_pollfd(struct pollfd *pollfd, poll_table *pwait, goto out; mask = EPOLLNVAL; f = fdget(fd); - if (!f.file) + if (!fd_file(f)) goto out; /* userland u16 ->events contains POLL... bitmap */ filter = demangle_poll(pollfd->events) | EPOLLERR | EPOLLHUP; pwait->_key = filter | busy_flag; - mask = vfs_poll(f.file, pwait); + mask = vfs_poll(fd_file(f), pwait); if (mask & busy_flag) *can_busy_poll = true; mask &= filter; /* Mask out unneeded events. */ diff --git a/fs/signalfd.c b/fs/signalfd.c index ec7b2da2477a..777e889ab0e8 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -289,10 +289,10 @@ static int do_signalfd4(int ufd, sigset_t *mask, int flags) fd_install(ufd, file); } else { struct fd f = fdget(ufd); - if (!f.file) + if (!fd_file(f)) return -EBADF; - ctx = f.file->private_data; - if (f.file->f_op != &signalfd_fops) { + ctx = fd_file(f)->private_data; + if (fd_file(f)->f_op != &signalfd_fops) { fdput(f); return -EINVAL; } diff --git a/fs/smb/client/ioctl.c b/fs/smb/client/ioctl.c index 855ac5a62edf..94bf2e5014d9 100644 --- a/fs/smb/client/ioctl.c +++ b/fs/smb/client/ioctl.c @@ -90,23 +90,23 @@ static long cifs_ioctl_copychunk(unsigned int xid, struct file *dst_file, } src_file = fdget(srcfd); - if (!src_file.file) { + if (!fd_file(src_file)) { rc = -EBADF; goto out_drop_write; } - if (src_file.file->f_op->unlocked_ioctl != cifs_ioctl) { + if (fd_file(src_file)->f_op->unlocked_ioctl != cifs_ioctl) { rc = -EBADF; cifs_dbg(VFS, "src file seems to be from a different filesystem type\n"); goto out_fput; } - src_inode = file_inode(src_file.file); + src_inode = file_inode(fd_file(src_file)); rc = -EINVAL; if (S_ISDIR(src_inode->i_mode)) goto out_fput; - rc = cifs_file_copychunk_range(xid, src_file.file, 0, dst_file, 0, + rc = cifs_file_copychunk_range(xid, fd_file(src_file), 0, dst_file, 0, src_inode->i_size, 0); if (rc > 0) rc = 0; diff --git a/fs/splice.c b/fs/splice.c index 60aed8de21f8..06232d7e505f 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1566,11 +1566,11 @@ static ssize_t vmsplice_to_pipe(struct file *file, struct iov_iter *iter, static int vmsplice_type(struct fd f, int *type) { - if (!f.file) + if (!fd_file(f)) return -EBADF; - if (f.file->f_mode & FMODE_WRITE) { + if (fd_file(f)->f_mode & FMODE_WRITE) { *type = ITER_SOURCE; - } else if (f.file->f_mode & FMODE_READ) { + } else if (fd_file(f)->f_mode & FMODE_READ) { *type = ITER_DEST; } else { fdput(f); @@ -1621,9 +1621,9 @@ SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, uiov, if (!iov_iter_count(&iter)) error = 0; else if (type == ITER_SOURCE) - error = vmsplice_to_pipe(f.file, &iter, flags); + error = vmsplice_to_pipe(fd_file(f), &iter, flags); else - error = vmsplice_to_user(f.file, &iter, flags); + error = vmsplice_to_user(fd_file(f), &iter, flags); kfree(iov); out_fdput: @@ -1646,10 +1646,10 @@ SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in, error = -EBADF; in = fdget(fd_in); - if (in.file) { + if (fd_file(in)) { out = fdget(fd_out); - if (out.file) { - error = __do_splice(in.file, off_in, out.file, off_out, + if (fd_file(out)) { + error = __do_splice(fd_file(in), off_in, fd_file(out), off_out, len, flags); fdput(out); } @@ -2016,10 +2016,10 @@ SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags) error = -EBADF; in = fdget(fdin); - if (in.file) { + if (fd_file(in)) { out = fdget(fdout); - if (out.file) { - error = do_tee(in.file, out.file, len, flags); + if (fd_file(out)) { + error = do_tee(fd_file(in), fd_file(out), len, flags); fdput(out); } fdput(in); diff --git a/fs/stat.c b/fs/stat.c index 89ce1be56310..41e598376d7e 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -224,9 +224,9 @@ int vfs_fstat(int fd, struct kstat *stat) int error; f = fdget_raw(fd); - if (!f.file) + if (!fd_file(f)) return -EBADF; - error = vfs_getattr(&f.file->f_path, stat, STATX_BASIC_STATS, 0); + error = vfs_getattr(&fd_file(f)->f_path, stat, STATX_BASIC_STATS, 0); fdput(f); return error; } @@ -277,9 +277,9 @@ static int vfs_statx_fd(int fd, int flags, struct kstat *stat, u32 request_mask) { CLASS(fd_raw, f)(fd); - if (!f.file) + if (!fd_file(f)) return -EBADF; - return vfs_statx_path(&f.file->f_path, flags, stat, request_mask); + return vfs_statx_path(&fd_file(f)->f_path, flags, stat, request_mask); } /** diff --git a/fs/statfs.c b/fs/statfs.c index 96d1c3edf289..9c7bb27e7932 100644 --- a/fs/statfs.c +++ b/fs/statfs.c @@ -116,8 +116,8 @@ int fd_statfs(int fd, struct kstatfs *st) { struct fd f = fdget_raw(fd); int error = -EBADF; - if (f.file) { - error = vfs_statfs(&f.file->f_path, st); + if (fd_file(f)) { + error = vfs_statfs(&fd_file(f)->f_path, st); fdput(f); } return error; diff --git a/fs/sync.c b/fs/sync.c index dc725914e1ed..67df255eb189 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -152,15 +152,15 @@ SYSCALL_DEFINE1(syncfs, int, fd) struct super_block *sb; int ret, ret2; - if (!f.file) + if (!fd_file(f)) return -EBADF; - sb = f.file->f_path.dentry->d_sb; + sb = fd_file(f)->f_path.dentry->d_sb; down_read(&sb->s_umount); ret = sync_filesystem(sb); up_read(&sb->s_umount); - ret2 = errseq_check_and_advance(&sb->s_wb_err, &f.file->f_sb_err); + ret2 = errseq_check_and_advance(&sb->s_wb_err, &fd_file(f)->f_sb_err); fdput(f); return ret ? ret : ret2; @@ -208,8 +208,8 @@ static int do_fsync(unsigned int fd, int datasync) struct fd f = fdget(fd); int ret = -EBADF; - if (f.file) { - ret = vfs_fsync(f.file, datasync); + if (fd_file(f)) { + ret = vfs_fsync(fd_file(f), datasync); fdput(f); } return ret; @@ -360,8 +360,8 @@ int ksys_sync_file_range(int fd, loff_t offset, loff_t nbytes, ret = -EBADF; f = fdget(fd); - if (f.file) - ret = sync_file_range(f.file, offset, nbytes, flags); + if (fd_file(f)) + ret = sync_file_range(fd_file(f), offset, nbytes, flags); fdput(f); return ret; diff --git a/fs/timerfd.c b/fs/timerfd.c index 4bf2f8bfec11..137523e0bb21 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -397,9 +397,9 @@ static const struct file_operations timerfd_fops = { static int timerfd_fget(int fd, struct fd *p) { struct fd f = fdget(fd); - if (!f.file) + if (!fd_file(f)) return -EBADF; - if (f.file->f_op != &timerfd_fops) { + if (fd_file(f)->f_op != &timerfd_fops) { fdput(f); return -EINVAL; } @@ -482,7 +482,7 @@ static int do_timerfd_settime(int ufd, int flags, ret = timerfd_fget(ufd, &f); if (ret) return ret; - ctx = f.file->private_data; + ctx = fd_file(f)->private_data; if (isalarm(ctx) && !capable(CAP_WAKE_ALARM)) { fdput(f); @@ -546,7 +546,7 @@ static int do_timerfd_gettime(int ufd, struct itimerspec64 *t) int ret = timerfd_fget(ufd, &f); if (ret) return ret; - ctx = f.file->private_data; + ctx = fd_file(f)->private_data; spin_lock_irq(&ctx->wqh.lock); if (ctx->expired && ctx->tintv) { diff --git a/fs/utimes.c b/fs/utimes.c index 3701b3946f88..99b26f792b89 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -115,9 +115,9 @@ static int do_utimes_fd(int fd, struct timespec64 *times, int flags) return -EINVAL; f = fdget(fd); - if (!f.file) + if (!fd_file(f)) return -EBADF; - error = vfs_utimes(&f.file->f_path, times); + error = vfs_utimes(&fd_file(f)->f_path, times); fdput(f); return error; } diff --git a/fs/xattr.c b/fs/xattr.c index 7672ce5486c5..05ec7e7d9e87 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -697,19 +697,19 @@ SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name, int error; CLASS(fd, f)(fd); - if (!f.file) + if (!fd_file(f)) return -EBADF; - audit_file(f.file); + audit_file(fd_file(f)); error = setxattr_copy(name, &ctx); if (error) return error; - error = mnt_want_write_file(f.file); + error = mnt_want_write_file(fd_file(f)); if (!error) { - error = do_setxattr(file_mnt_idmap(f.file), - f.file->f_path.dentry, &ctx); - mnt_drop_write_file(f.file); + error = do_setxattr(file_mnt_idmap(fd_file(f)), + fd_file(f)->f_path.dentry, &ctx); + mnt_drop_write_file(fd_file(f)); } kvfree(ctx.kvalue); return error; @@ -812,10 +812,10 @@ SYSCALL_DEFINE4(fgetxattr, int, fd, const char __user *, name, struct fd f = fdget(fd); ssize_t error = -EBADF; - if (!f.file) + if (!fd_file(f)) return error; - audit_file(f.file); - error = getxattr(file_mnt_idmap(f.file), f.file->f_path.dentry, + audit_file(fd_file(f)); + error = getxattr(file_mnt_idmap(fd_file(f)), fd_file(f)->f_path.dentry, name, value, size); fdput(f); return error; @@ -888,10 +888,10 @@ SYSCALL_DEFINE3(flistxattr, int, fd, char __user *, list, size_t, size) struct fd f = fdget(fd); ssize_t error = -EBADF; - if (!f.file) + if (!fd_file(f)) return error; - audit_file(f.file); - error = listxattr(f.file->f_path.dentry, list, size); + audit_file(fd_file(f)); + error = listxattr(fd_file(f)->f_path.dentry, list, size); fdput(f); return error; } @@ -954,9 +954,9 @@ SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name) char kname[XATTR_NAME_MAX + 1]; int error = -EBADF; - if (!f.file) + if (!fd_file(f)) return error; - audit_file(f.file); + audit_file(fd_file(f)); error = strncpy_from_user(kname, name, sizeof(kname)); if (error == 0 || error == sizeof(kname)) @@ -964,11 +964,11 @@ SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name) if (error < 0) return error; - error = mnt_want_write_file(f.file); + error = mnt_want_write_file(fd_file(f)); if (!error) { - error = removexattr(file_mnt_idmap(f.file), - f.file->f_path.dentry, kname); - mnt_drop_write_file(f.file); + error = removexattr(file_mnt_idmap(fd_file(f)), + fd_file(f)->f_path.dentry, kname); + mnt_drop_write_file(fd_file(f)); } fdput(f); return error; diff --git a/fs/xfs/xfs_exchrange.c b/fs/xfs/xfs_exchrange.c index c8a655c92c92..9790e0f45d14 100644 --- a/fs/xfs/xfs_exchrange.c +++ b/fs/xfs/xfs_exchrange.c @@ -794,9 +794,9 @@ xfs_ioc_exchange_range( fxr.flags = args.flags; file1 = fdget(args.file1_fd); - if (!file1.file) + if (!fd_file(file1)) return -EBADF; - fxr.file1 = file1.file; + fxr.file1 = fd_file(file1); error = xfs_exchange_range(&fxr); fdput(file1); diff --git a/fs/xfs/xfs_handle.c b/fs/xfs/xfs_handle.c index cf5acbd3c7ca..7bcc4f519cb8 100644 --- a/fs/xfs/xfs_handle.c +++ b/fs/xfs/xfs_handle.c @@ -92,9 +92,9 @@ xfs_find_handle( if (cmd == XFS_IOC_FD_TO_HANDLE) { f = fdget(hreq->fd); - if (!f.file) + if (!fd_file(f)) return -EBADF; - inode = file_inode(f.file); + inode = file_inode(fd_file(f)); } else { error = user_path_at(AT_FDCWD, hreq->path, 0, &path); if (error) diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 4e933db75b12..95641817370b 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1005,33 +1005,33 @@ xfs_ioc_swapext( /* Pull information for the target fd */ f = fdget((int)sxp->sx_fdtarget); - if (!f.file) { + if (!fd_file(f)) { error = -EINVAL; goto out; } - if (!(f.file->f_mode & FMODE_WRITE) || - !(f.file->f_mode & FMODE_READ) || - (f.file->f_flags & O_APPEND)) { + if (!(fd_file(f)->f_mode & FMODE_WRITE) || + !(fd_file(f)->f_mode & FMODE_READ) || + (fd_file(f)->f_flags & O_APPEND)) { error = -EBADF; goto out_put_file; } tmp = fdget((int)sxp->sx_fdtmp); - if (!tmp.file) { + if (!fd_file(tmp)) { error = -EINVAL; goto out_put_file; } - if (!(tmp.file->f_mode & FMODE_WRITE) || - !(tmp.file->f_mode & FMODE_READ) || - (tmp.file->f_flags & O_APPEND)) { + if (!(fd_file(tmp)->f_mode & FMODE_WRITE) || + !(fd_file(tmp)->f_mode & FMODE_READ) || + (fd_file(tmp)->f_flags & O_APPEND)) { error = -EBADF; goto out_put_tmp_file; } - if (IS_SWAPFILE(file_inode(f.file)) || - IS_SWAPFILE(file_inode(tmp.file))) { + if (IS_SWAPFILE(file_inode(fd_file(f))) || + IS_SWAPFILE(file_inode(fd_file(tmp)))) { error = -EINVAL; goto out_put_tmp_file; } @@ -1041,14 +1041,14 @@ xfs_ioc_swapext( * before we cast and access them as XFS structures as we have no * control over what the user passes us here. */ - if (f.file->f_op != &xfs_file_operations || - tmp.file->f_op != &xfs_file_operations) { + if (fd_file(f)->f_op != &xfs_file_operations || + fd_file(tmp)->f_op != &xfs_file_operations) { error = -EINVAL; goto out_put_tmp_file; } - ip = XFS_I(file_inode(f.file)); - tip = XFS_I(file_inode(tmp.file)); + ip = XFS_I(file_inode(fd_file(f))); + tip = XFS_I(file_inode(fd_file(tmp))); if (ip->i_mount != tip->i_mount) { error = -EINVAL; diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h index d9e613803df1..a3d3e888cf1f 100644 --- a/include/linux/cleanup.h +++ b/include/linux/cleanup.h @@ -98,7 +98,7 @@ const volatile void * __must_check_fn(const volatile void *val) * DEFINE_CLASS(fdget, struct fd, fdput(_T), fdget(fd), int fd) * * CLASS(fdget, f)(fd); - * if (!f.file) + * if (!fd_file(f)) * return -EBADF; * * // use 'f' without concern diff --git a/include/linux/file.h b/include/linux/file.h index 237931f20739..0f3f369f2450 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -42,10 +42,12 @@ struct fd { #define FDPUT_FPUT 1 #define FDPUT_POS_UNLOCK 2 +#define fd_file(f) ((f).file) + static inline void fdput(struct fd fd) { if (fd.flags & FDPUT_FPUT) - fput(fd.file); + fput(fd_file(fd)); } extern struct file *fget(unsigned int fd); @@ -79,7 +81,7 @@ static inline struct fd fdget_pos(int fd) static inline void fdput_pos(struct fd f) { if (f.flags & FDPUT_POS_UNLOCK) - __f_unlock_pos(f.file); + __f_unlock_pos(fd_file(f)); fdput(f); } diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c index b3722e5275e7..ffa7d341bd95 100644 --- a/io_uring/sqpoll.c +++ b/io_uring/sqpoll.c @@ -108,14 +108,14 @@ static struct io_sq_data *io_attach_sq_data(struct io_uring_params *p) struct fd f; f = fdget(p->wq_fd); - if (!f.file) + if (!fd_file(f)) return ERR_PTR(-ENXIO); - if (!io_is_uring_fops(f.file)) { + if (!io_is_uring_fops(fd_file(f))) { fdput(f); return ERR_PTR(-EINVAL); } - ctx_attach = f.file->private_data; + ctx_attach = fd_file(f)->private_data; sqd = ctx_attach->sq_data; if (!sqd) { fdput(f); @@ -418,9 +418,9 @@ __cold int io_sq_offload_create(struct io_ring_ctx *ctx, struct fd f; f = fdget(p->wq_fd); - if (!f.file) + if (!fd_file(f)) return -ENXIO; - if (!io_is_uring_fops(f.file)) { + if (!io_is_uring_fops(fd_file(f))) { fdput(f); return -EINVAL; } diff --git a/ipc/mqueue.c b/ipc/mqueue.c index a7cbd69efbef..34fa0bd8bb11 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -1085,20 +1085,20 @@ static int do_mq_timedsend(mqd_t mqdes, const char __user *u_msg_ptr, audit_mq_sendrecv(mqdes, msg_len, msg_prio, ts); f = fdget(mqdes); - if (unlikely(!f.file)) { + if (unlikely(!fd_file(f))) { ret = -EBADF; goto out; } - inode = file_inode(f.file); - if (unlikely(f.file->f_op != &mqueue_file_operations)) { + inode = file_inode(fd_file(f)); + if (unlikely(fd_file(f)->f_op != &mqueue_file_operations)) { ret = -EBADF; goto out_fput; } info = MQUEUE_I(inode); - audit_file(f.file); + audit_file(fd_file(f)); - if (unlikely(!(f.file->f_mode & FMODE_WRITE))) { + if (unlikely(!(fd_file(f)->f_mode & FMODE_WRITE))) { ret = -EBADF; goto out_fput; } @@ -1138,7 +1138,7 @@ static int do_mq_timedsend(mqd_t mqdes, const char __user *u_msg_ptr, } if (info->attr.mq_curmsgs == info->attr.mq_maxmsg) { - if (f.file->f_flags & O_NONBLOCK) { + if (fd_file(f)->f_flags & O_NONBLOCK) { ret = -EAGAIN; } else { wait.task = current; @@ -1199,20 +1199,20 @@ static int do_mq_timedreceive(mqd_t mqdes, char __user *u_msg_ptr, audit_mq_sendrecv(mqdes, msg_len, 0, ts); f = fdget(mqdes); - if (unlikely(!f.file)) { + if (unlikely(!fd_file(f))) { ret = -EBADF; goto out; } - inode = file_inode(f.file); - if (unlikely(f.file->f_op != &mqueue_file_operations)) { + inode = file_inode(fd_file(f)); + if (unlikely(fd_file(f)->f_op != &mqueue_file_operations)) { ret = -EBADF; goto out_fput; } info = MQUEUE_I(inode); - audit_file(f.file); + audit_file(fd_file(f)); - if (unlikely(!(f.file->f_mode & FMODE_READ))) { + if (unlikely(!(fd_file(f)->f_mode & FMODE_READ))) { ret = -EBADF; goto out_fput; } @@ -1242,7 +1242,7 @@ static int do_mq_timedreceive(mqd_t mqdes, char __user *u_msg_ptr, } if (info->attr.mq_curmsgs == 0) { - if (f.file->f_flags & O_NONBLOCK) { + if (fd_file(f)->f_flags & O_NONBLOCK) { spin_unlock(&info->lock); ret = -EAGAIN; } else { @@ -1356,11 +1356,11 @@ static int do_mq_notify(mqd_t mqdes, const struct sigevent *notification) /* and attach it to the socket */ retry: f = fdget(notification->sigev_signo); - if (!f.file) { + if (!fd_file(f)) { ret = -EBADF; goto out; } - sock = netlink_getsockbyfilp(f.file); + sock = netlink_getsockbyfilp(fd_file(f)); fdput(f); if (IS_ERR(sock)) { ret = PTR_ERR(sock); @@ -1379,13 +1379,13 @@ retry: } f = fdget(mqdes); - if (!f.file) { + if (!fd_file(f)) { ret = -EBADF; goto out; } - inode = file_inode(f.file); - if (unlikely(f.file->f_op != &mqueue_file_operations)) { + inode = file_inode(fd_file(f)); + if (unlikely(fd_file(f)->f_op != &mqueue_file_operations)) { ret = -EBADF; goto out_fput; } @@ -1460,31 +1460,31 @@ static int do_mq_getsetattr(int mqdes, struct mq_attr *new, struct mq_attr *old) return -EINVAL; f = fdget(mqdes); - if (!f.file) + if (!fd_file(f)) return -EBADF; - if (unlikely(f.file->f_op != &mqueue_file_operations)) { + if (unlikely(fd_file(f)->f_op != &mqueue_file_operations)) { fdput(f); return -EBADF; } - inode = file_inode(f.file); + inode = file_inode(fd_file(f)); info = MQUEUE_I(inode); spin_lock(&info->lock); if (old) { *old = info->attr; - old->mq_flags = f.file->f_flags & O_NONBLOCK; + old->mq_flags = fd_file(f)->f_flags & O_NONBLOCK; } if (new) { audit_mq_getsetattr(mqdes, new); - spin_lock(&f.file->f_lock); + spin_lock(&fd_file(f)->f_lock); if (new->mq_flags & O_NONBLOCK) - f.file->f_flags |= O_NONBLOCK; + fd_file(f)->f_flags |= O_NONBLOCK; else - f.file->f_flags &= ~O_NONBLOCK; - spin_unlock(&f.file->f_lock); + fd_file(f)->f_flags &= ~O_NONBLOCK; + spin_unlock(&fd_file(f)->f_lock); inode_set_atime_to_ts(inode, inode_set_ctime_current(inode)); } diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c index b0ef45db207c..0a79aee6523d 100644 --- a/kernel/bpf/bpf_inode_storage.c +++ b/kernel/bpf/bpf_inode_storage.c @@ -80,10 +80,10 @@ static void *bpf_fd_inode_storage_lookup_elem(struct bpf_map *map, void *key) struct bpf_local_storage_data *sdata; struct fd f = fdget_raw(*(int *)key); - if (!f.file) + if (!fd_file(f)) return ERR_PTR(-EBADF); - sdata = inode_storage_lookup(file_inode(f.file), map, true); + sdata = inode_storage_lookup(file_inode(fd_file(f)), map, true); fdput(f); return sdata ? sdata->data : NULL; } @@ -94,14 +94,14 @@ static long bpf_fd_inode_storage_update_elem(struct bpf_map *map, void *key, struct bpf_local_storage_data *sdata; struct fd f = fdget_raw(*(int *)key); - if (!f.file) + if (!fd_file(f)) return -EBADF; - if (!inode_storage_ptr(file_inode(f.file))) { + if (!inode_storage_ptr(file_inode(fd_file(f)))) { fdput(f); return -EBADF; } - sdata = bpf_local_storage_update(file_inode(f.file), + sdata = bpf_local_storage_update(file_inode(fd_file(f)), (struct bpf_local_storage_map *)map, value, map_flags, GFP_ATOMIC); fdput(f); @@ -126,10 +126,10 @@ static long bpf_fd_inode_storage_delete_elem(struct bpf_map *map, void *key) struct fd f = fdget_raw(*(int *)key); int err; - if (!f.file) + if (!fd_file(f)) return -EBADF; - err = inode_storage_delete(file_inode(f.file), map); + err = inode_storage_delete(file_inode(fd_file(f)), map); fdput(f); return err; } diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 520f49f422fe..4de1e3dc2284 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -7677,15 +7677,15 @@ struct btf *btf_get_by_fd(int fd) f = fdget(fd); - if (!f.file) + if (!fd_file(f)) return ERR_PTR(-EBADF); - if (f.file->f_op != &btf_fops) { + if (fd_file(f)->f_op != &btf_fops) { fdput(f); return ERR_PTR(-EINVAL); } - btf = f.file->private_data; + btf = fd_file(f)->private_data; refcount_inc(&btf->refcnt); fdput(f); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index bf6c5f685ea2..3093bf2cc266 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -829,7 +829,7 @@ static int bpf_map_release(struct inode *inode, struct file *filp) static fmode_t map_get_sys_perms(struct bpf_map *map, struct fd f) { - fmode_t mode = f.file->f_mode; + fmode_t mode = fd_file(f)->f_mode; /* Our file permissions may have been overridden by global * map permissions facing syscall side. @@ -1423,14 +1423,14 @@ put_token: */ struct bpf_map *__bpf_map_get(struct fd f) { - if (!f.file) + if (!fd_file(f)) return ERR_PTR(-EBADF); - if (f.file->f_op != &bpf_map_fops) { + if (fd_file(f)->f_op != &bpf_map_fops) { fdput(f); return ERR_PTR(-EINVAL); } - return f.file->private_data; + return fd_file(f)->private_data; } void bpf_map_inc(struct bpf_map *map) @@ -1651,7 +1651,7 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr) goto free_key; } - err = bpf_map_update_value(map, f.file, key, value, attr->flags); + err = bpf_map_update_value(map, fd_file(f), key, value, attr->flags); if (!err) maybe_wait_bpf_programs(map); @@ -2409,14 +2409,14 @@ int bpf_prog_new_fd(struct bpf_prog *prog) static struct bpf_prog *____bpf_prog_get(struct fd f) { - if (!f.file) + if (!fd_file(f)) return ERR_PTR(-EBADF); - if (f.file->f_op != &bpf_prog_fops) { + if (fd_file(f)->f_op != &bpf_prog_fops) { fdput(f); return ERR_PTR(-EINVAL); } - return f.file->private_data; + return fd_file(f)->private_data; } void bpf_prog_add(struct bpf_prog *prog, int i) @@ -3259,14 +3259,14 @@ struct bpf_link *bpf_link_get_from_fd(u32 ufd) struct fd f = fdget(ufd); struct bpf_link *link; - if (!f.file) + if (!fd_file(f)) return ERR_PTR(-EBADF); - if (f.file->f_op != &bpf_link_fops && f.file->f_op != &bpf_link_fops_poll) { + if (fd_file(f)->f_op != &bpf_link_fops && fd_file(f)->f_op != &bpf_link_fops_poll) { fdput(f); return ERR_PTR(-EINVAL); } - link = f.file->private_data; + link = fd_file(f)->private_data; bpf_link_inc(link); fdput(f); @@ -4982,19 +4982,19 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, return -EINVAL; f = fdget(ufd); - if (!f.file) + if (!fd_file(f)) return -EBADFD; - if (f.file->f_op == &bpf_prog_fops) - err = bpf_prog_get_info_by_fd(f.file, f.file->private_data, attr, + if (fd_file(f)->f_op == &bpf_prog_fops) + err = bpf_prog_get_info_by_fd(fd_file(f), fd_file(f)->private_data, attr, uattr); - else if (f.file->f_op == &bpf_map_fops) - err = bpf_map_get_info_by_fd(f.file, f.file->private_data, attr, + else if (fd_file(f)->f_op == &bpf_map_fops) + err = bpf_map_get_info_by_fd(fd_file(f), fd_file(f)->private_data, attr, uattr); - else if (f.file->f_op == &btf_fops) - err = bpf_btf_get_info_by_fd(f.file, f.file->private_data, attr, uattr); - else if (f.file->f_op == &bpf_link_fops || f.file->f_op == &bpf_link_fops_poll) - err = bpf_link_get_info_by_fd(f.file, f.file->private_data, + else if (fd_file(f)->f_op == &btf_fops) + err = bpf_btf_get_info_by_fd(fd_file(f), fd_file(f)->private_data, attr, uattr); + else if (fd_file(f)->f_op == &bpf_link_fops || fd_file(f)->f_op == &bpf_link_fops_poll) + err = bpf_link_get_info_by_fd(fd_file(f), fd_file(f)->private_data, attr, uattr); else err = -EINVAL; @@ -5215,7 +5215,7 @@ static int bpf_map_do_batch(const union bpf_attr *attr, else if (cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) BPF_DO_BATCH(map->ops->map_lookup_and_delete_batch, map, attr, uattr); else if (cmd == BPF_MAP_UPDATE_BATCH) - BPF_DO_BATCH(map->ops->map_update_batch, map, f.file, attr, uattr); + BPF_DO_BATCH(map->ops->map_update_batch, map, fd_file(f), attr, uattr); else BPF_DO_BATCH(map->ops->map_delete_batch, map, attr, uattr); err_put: diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c index d6ccf8d00eab..9a1d356e79ed 100644 --- a/kernel/bpf/token.c +++ b/kernel/bpf/token.c @@ -122,10 +122,10 @@ int bpf_token_create(union bpf_attr *attr) int err, fd; f = fdget(attr->token_create.bpffs_fd); - if (!f.file) + if (!fd_file(f)) return -EBADF; - path = f.file->f_path; + path = fd_file(f)->f_path; path_get(&path); fdput(f); @@ -235,14 +235,14 @@ struct bpf_token *bpf_token_get_from_fd(u32 ufd) struct fd f = fdget(ufd); struct bpf_token *token; - if (!f.file) + if (!fd_file(f)) return ERR_PTR(-EBADF); - if (f.file->f_op != &bpf_token_fops) { + if (fd_file(f)->f_op != &bpf_token_fops) { fdput(f); return ERR_PTR(-EINVAL); } - token = f.file->private_data; + token = fd_file(f)->private_data; bpf_token_inc(token); fdput(f); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index c8e4b62b436a..b96489277f70 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -6901,10 +6901,10 @@ struct cgroup *cgroup_v1v2_get_from_fd(int fd) { struct cgroup *cgrp; struct fd f = fdget_raw(fd); - if (!f.file) + if (!fd_file(f)) return ERR_PTR(-EBADF); - cgrp = cgroup_v1v2_get_from_file(f.file); + cgrp = cgroup_v1v2_get_from_file(fd_file(f)); fdput(f); return cgrp; } diff --git a/kernel/events/core.c b/kernel/events/core.c index aa3450bdc227..17b19d3e74ba 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -933,10 +933,10 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event, struct fd f = fdget(fd); int ret = 0; - if (!f.file) + if (!fd_file(f)) return -EBADF; - css = css_tryget_online_from_dir(f.file->f_path.dentry, + css = css_tryget_online_from_dir(fd_file(f)->f_path.dentry, &perf_event_cgrp_subsys); if (IS_ERR(css)) { ret = PTR_ERR(css); @@ -5898,10 +5898,10 @@ static const struct file_operations perf_fops; static inline int perf_fget_light(int fd, struct fd *p) { struct fd f = fdget(fd); - if (!f.file) + if (!fd_file(f)) return -EBADF; - if (f.file->f_op != &perf_fops) { + if (fd_file(f)->f_op != &perf_fops) { fdput(f); return -EBADF; } @@ -5961,7 +5961,7 @@ static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned lon ret = perf_fget_light(arg, &output); if (ret) return ret; - output_event = output.file->private_data; + output_event = fd_file(output)->private_data; ret = perf_event_set_output(event, output_event); fdput(output); } else { @@ -12549,7 +12549,7 @@ SYSCALL_DEFINE5(perf_event_open, err = perf_fget_light(group_fd, &group); if (err) goto err_fd; - group_leader = group.file->private_data; + group_leader = fd_file(group)->private_data; if (flags & PERF_FLAG_FD_OUTPUT) output_event = group_leader; if (flags & PERF_FLAG_FD_NO_GROUP) diff --git a/kernel/module/main.c b/kernel/module/main.c index d9592195c5bb..6ed334eecc14 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -3211,7 +3211,7 @@ SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) return -EINVAL; f = fdget(fd); - err = idempotent_init_module(f.file, uargs, flags); + err = idempotent_init_module(fd_file(f), uargs, flags); fdput(f); return err; } diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index 6ec3deec68c2..dc952c3b05af 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -550,15 +550,15 @@ SYSCALL_DEFINE2(setns, int, fd, int, flags) struct nsset nsset = {}; int err = 0; - if (!f.file) + if (!fd_file(f)) return -EBADF; - if (proc_ns_file(f.file)) { - ns = get_proc_ns(file_inode(f.file)); + if (proc_ns_file(fd_file(f))) { + ns = get_proc_ns(file_inode(fd_file(f))); if (flags && (ns->ops->type != flags)) err = -EINVAL; flags = ns->ops->type; - } else if (!IS_ERR(pidfd_pid(f.file))) { + } else if (!IS_ERR(pidfd_pid(fd_file(f)))) { err = check_setns_flags(flags); } else { err = -EINVAL; @@ -570,10 +570,10 @@ SYSCALL_DEFINE2(setns, int, fd, int, flags) if (err) goto out; - if (proc_ns_file(f.file)) + if (proc_ns_file(fd_file(f))) err = validate_ns(&nsset, ns); else - err = validate_nsset(&nsset, pidfd_pid(f.file)); + err = validate_nsset(&nsset, pidfd_pid(fd_file(f))); if (!err) { commit_nsset(&nsset); perf_event_namespaces(current); diff --git a/kernel/pid.c b/kernel/pid.c index da76ed1873f7..2715afb77eab 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -540,13 +540,13 @@ struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags) struct pid *pid; f = fdget(fd); - if (!f.file) + if (!fd_file(f)) return ERR_PTR(-EBADF); - pid = pidfd_pid(f.file); + pid = pidfd_pid(fd_file(f)); if (!IS_ERR(pid)) { get_pid(pid); - *flags = f.file->f_flags; + *flags = fd_file(f)->f_flags; } fdput(f); @@ -755,10 +755,10 @@ SYSCALL_DEFINE3(pidfd_getfd, int, pidfd, int, fd, return -EINVAL; f = fdget(pidfd); - if (!f.file) + if (!fd_file(f)) return -EBADF; - pid = pidfd_pid(f.file); + pid = pidfd_pid(fd_file(f)); if (IS_ERR(pid)) ret = PTR_ERR(pid); else diff --git a/kernel/signal.c b/kernel/signal.c index 60c737e423a1..cc5d87cfa7c0 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -3922,11 +3922,11 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, return -EINVAL; f = fdget(pidfd); - if (!f.file) + if (!fd_file(f)) return -EBADF; /* Is this a pidfd? */ - pid = pidfd_to_pid(f.file); + pid = pidfd_to_pid(fd_file(f)); if (IS_ERR(pid)) { ret = PTR_ERR(pid); goto err; @@ -3939,7 +3939,7 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, switch (flags) { case 0: /* Infer scope from the type of pidfd. */ - if (f.file->f_flags & PIDFD_THREAD) + if (fd_file(f)->f_flags & PIDFD_THREAD) type = PIDTYPE_PID; else type = PIDTYPE_TGID; diff --git a/kernel/sys.c b/kernel/sys.c index 3a2df1bd9f64..a4be1e568ff5 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1916,10 +1916,10 @@ static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd) int err; exe = fdget(fd); - if (!exe.file) + if (!fd_file(exe)) return -EBADF; - inode = file_inode(exe.file); + inode = file_inode(fd_file(exe)); /* * Because the original mm->exe_file points to executable file, make @@ -1927,14 +1927,14 @@ static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd) * overall picture. */ err = -EACCES; - if (!S_ISREG(inode->i_mode) || path_noexec(&exe.file->f_path)) + if (!S_ISREG(inode->i_mode) || path_noexec(&fd_file(exe)->f_path)) goto exit; - err = file_permission(exe.file, MAY_EXEC); + err = file_permission(fd_file(exe), MAY_EXEC); if (err) goto exit; - err = replace_mm_exe_file(mm, exe.file); + err = replace_mm_exe_file(mm, fd_file(exe)); exit: fdput(exe); return err; diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 4354ea231fab..0700f40c53ac 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -419,7 +419,7 @@ static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info) fd = nla_get_u32(info->attrs[CGROUPSTATS_CMD_ATTR_FD]); f = fdget(fd); - if (!f.file) + if (!fd_file(f)) return 0; size = nla_total_size(sizeof(struct cgroupstats)); @@ -440,7 +440,7 @@ static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info) stats = nla_data(na); memset(stats, 0, sizeof(*stats)); - rc = cgroupstats_build(stats, f.file->f_path.dentry); + rc = cgroupstats_build(stats, fd_file(f)->f_path.dentry); if (rc < 0) { nlmsg_free(rep_skb); goto err; diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c index 03b90d7d2175..d36242fd4936 100644 --- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -666,8 +666,8 @@ struct watch_queue *get_watch_queue(int fd) struct fd f; f = fdget(fd); - if (f.file) { - pipe = get_pipe_info(f.file, false); + if (fd_file(f)) { + pipe = get_pipe_info(fd_file(f), false); if (pipe && pipe->watch_queue) { wqueue = pipe->watch_queue; kref_get(&wqueue->usage); diff --git a/mm/fadvise.c b/mm/fadvise.c index 6c39d42f16dc..532dee205c6e 100644 --- a/mm/fadvise.c +++ b/mm/fadvise.c @@ -193,10 +193,10 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) struct fd f = fdget(fd); int ret; - if (!f.file) + if (!fd_file(f)) return -EBADF; - ret = vfs_fadvise(f.file, offset, len, advice); + ret = vfs_fadvise(fd_file(f), offset, len, advice); fdput(f); return ret; diff --git a/mm/filemap.c b/mm/filemap.c index d62150418b91..0b5cbd644fdd 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -4393,7 +4393,7 @@ SYSCALL_DEFINE4(cachestat, unsigned int, fd, struct cachestat cs; pgoff_t first_index, last_index; - if (!f.file) + if (!fd_file(f)) return -EBADF; if (copy_from_user(&csr, cstat_range, @@ -4403,7 +4403,7 @@ SYSCALL_DEFINE4(cachestat, unsigned int, fd, } /* hugetlbfs is not supported */ - if (is_file_hugepages(f.file)) { + if (is_file_hugepages(fd_file(f))) { fdput(f); return -EOPNOTSUPP; } @@ -4417,7 +4417,7 @@ SYSCALL_DEFINE4(cachestat, unsigned int, fd, last_index = csr.len == 0 ? ULONG_MAX : (csr.off + csr.len - 1) >> PAGE_SHIFT; memset(&cs, 0, sizeof(struct cachestat)); - mapping = f.file->f_mapping; + mapping = fd_file(f)->f_mapping; filemap_cachestat(mapping, first_index, last_index, &cs); fdput(f); diff --git a/mm/memcontrol-v1.c b/mm/memcontrol-v1.c index 2aeea4d8bf8e..da626ddccffd 100644 --- a/mm/memcontrol-v1.c +++ b/mm/memcontrol-v1.c @@ -1857,26 +1857,26 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, INIT_WORK(&event->remove, memcg_event_remove); efile = fdget(efd); - if (!efile.file) { + if (!fd_file(efile)) { ret = -EBADF; goto out_kfree; } - event->eventfd = eventfd_ctx_fileget(efile.file); + event->eventfd = eventfd_ctx_fileget(fd_file(efile)); if (IS_ERR(event->eventfd)) { ret = PTR_ERR(event->eventfd); goto out_put_efile; } cfile = fdget(cfd); - if (!cfile.file) { + if (!fd_file(cfile)) { ret = -EBADF; goto out_put_eventfd; } /* the process need read permission on control file */ /* AV: shouldn't we check that it's been opened for read instead? */ - ret = file_permission(cfile.file, MAY_READ); + ret = file_permission(fd_file(cfile), MAY_READ); if (ret < 0) goto out_put_cfile; @@ -1884,7 +1884,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, * The control file must be a regular cgroup1 file. As a regular cgroup * file can't be renamed, it's safe to access its name afterwards. */ - cdentry = cfile.file->f_path.dentry; + cdentry = fd_file(cfile)->f_path.dentry; if (cdentry->d_sb->s_type != &cgroup_fs_type || !d_is_reg(cdentry)) { ret = -EINVAL; goto out_put_cfile; @@ -1936,7 +1936,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, if (ret) goto out_put_css; - vfs_poll(efile.file, &event->pt); + vfs_poll(fd_file(efile), &event->pt); spin_lock_irq(&memcg->event_list_lock); list_add(&event->list, &memcg->event_list); diff --git a/mm/readahead.c b/mm/readahead.c index 517c0be7ce66..e83fe1c6e5ac 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -646,7 +646,7 @@ ssize_t ksys_readahead(int fd, loff_t offset, size_t count) ret = -EBADF; f = fdget(fd); - if (!f.file || !(f.file->f_mode & FMODE_READ)) + if (!fd_file(f) || !(fd_file(f)->f_mode & FMODE_READ)) goto out; /* @@ -655,12 +655,12 @@ ssize_t ksys_readahead(int fd, loff_t offset, size_t count) * on this file, then we must return -EINVAL. */ ret = -EINVAL; - if (!f.file->f_mapping || !f.file->f_mapping->a_ops || - (!S_ISREG(file_inode(f.file)->i_mode) && - !S_ISBLK(file_inode(f.file)->i_mode))) + if (!fd_file(f)->f_mapping || !fd_file(f)->f_mapping->a_ops || + (!S_ISREG(file_inode(fd_file(f))->i_mode) && + !S_ISBLK(file_inode(fd_file(f))->i_mode))) goto out; - ret = vfs_fadvise(f.file, offset, count, POSIX_FADV_WILLNEED); + ret = vfs_fadvise(fd_file(f), offset, count, POSIX_FADV_WILLNEED); out: fdput(f); return ret; diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 6a823ba906c6..18b7c8f31234 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -711,11 +711,11 @@ struct net *get_net_ns_by_fd(int fd) struct fd f = fdget(fd); struct net *net = ERR_PTR(-EINVAL); - if (!f.file) + if (!fd_file(f)) return ERR_PTR(-EBADF); - if (proc_ns_file(f.file)) { - struct ns_common *ns = get_proc_ns(file_inode(f.file)); + if (proc_ns_file(fd_file(f))) { + struct ns_common *ns = get_proc_ns(file_inode(fd_file(f))); if (ns->ops == &netns_operations) net = get_net(container_of(ns, struct net, ns)); } diff --git a/net/socket.c b/net/socket.c index fcbdd5bc47ac..f77a42a74510 100644 --- a/net/socket.c +++ b/net/socket.c @@ -556,8 +556,8 @@ static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed) struct socket *sock; *err = -EBADF; - if (f.file) { - sock = sock_from_file(f.file); + if (fd_file(f)) { + sock = sock_from_file(fd_file(f)); if (likely(sock)) { *fput_needed = f.flags & FDPUT_FPUT; return sock; @@ -2008,8 +2008,8 @@ int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, struct fd f; f = fdget(fd); - if (f.file) { - ret = __sys_accept4_file(f.file, upeer_sockaddr, + if (fd_file(f)) { + ret = __sys_accept4_file(fd_file(f), upeer_sockaddr, upeer_addrlen, flags); fdput(f); } @@ -2070,12 +2070,12 @@ int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen) struct fd f; f = fdget(fd); - if (f.file) { + if (fd_file(f)) { struct sockaddr_storage address; ret = move_addr_to_kernel(uservaddr, addrlen, &address); if (!ret) - ret = __sys_connect_file(f.file, &address, addrlen, 0); + ret = __sys_connect_file(fd_file(f), &address, addrlen, 0); fdput(f); } diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index f04f43af651c..e7c1d3ae33fe 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -1068,10 +1068,10 @@ void ima_kexec_cmdline(int kernel_fd, const void *buf, int size) return; f = fdget(kernel_fd); - if (!f.file) + if (!fd_file(f)) return; - process_buffer_measurement(file_mnt_idmap(f.file), file_inode(f.file), + process_buffer_measurement(file_mnt_idmap(fd_file(f)), file_inode(fd_file(f)), buf, size, "kexec-cmdline", KEXEC_CMDLINE, 0, NULL, false, NULL, 0); fdput(f); diff --git a/security/landlock/syscalls.c b/security/landlock/syscalls.c index ccc8bc6c1584..00b63971ab64 100644 --- a/security/landlock/syscalls.c +++ b/security/landlock/syscalls.c @@ -238,19 +238,19 @@ static struct landlock_ruleset *get_ruleset_from_fd(const int fd, struct landlock_ruleset *ruleset; ruleset_f = fdget(fd); - if (!ruleset_f.file) + if (!fd_file(ruleset_f)) return ERR_PTR(-EBADF); /* Checks FD type and access right. */ - if (ruleset_f.file->f_op != &ruleset_fops) { + if (fd_file(ruleset_f)->f_op != &ruleset_fops) { ruleset = ERR_PTR(-EBADFD); goto out_fdput; } - if (!(ruleset_f.file->f_mode & mode)) { + if (!(fd_file(ruleset_f)->f_mode & mode)) { ruleset = ERR_PTR(-EPERM); goto out_fdput; } - ruleset = ruleset_f.file->private_data; + ruleset = fd_file(ruleset_f)->private_data; if (WARN_ON_ONCE(ruleset->num_layers != 1)) { ruleset = ERR_PTR(-EINVAL); goto out_fdput; @@ -277,22 +277,22 @@ static int get_path_from_fd(const s32 fd, struct path *const path) /* Handles O_PATH. */ f = fdget_raw(fd); - if (!f.file) + if (!fd_file(f)) return -EBADF; /* * Forbids ruleset FDs, internal filesystems (e.g. nsfs), including * pseudo filesystems that will never be mountable (e.g. sockfs, * pipefs). */ - if ((f.file->f_op == &ruleset_fops) || - (f.file->f_path.mnt->mnt_flags & MNT_INTERNAL) || - (f.file->f_path.dentry->d_sb->s_flags & SB_NOUSER) || - d_is_negative(f.file->f_path.dentry) || - IS_PRIVATE(d_backing_inode(f.file->f_path.dentry))) { + if ((fd_file(f)->f_op == &ruleset_fops) || + (fd_file(f)->f_path.mnt->mnt_flags & MNT_INTERNAL) || + (fd_file(f)->f_path.dentry->d_sb->s_flags & SB_NOUSER) || + d_is_negative(fd_file(f)->f_path.dentry) || + IS_PRIVATE(d_backing_inode(fd_file(f)->f_path.dentry))) { err = -EBADFD; goto out_fdput; } - *path = f.file->f_path; + *path = fd_file(f)->f_path; path_get(path); out_fdput: diff --git a/security/loadpin/loadpin.c b/security/loadpin/loadpin.c index 93fd4d47b334..02144ec39f43 100644 --- a/security/loadpin/loadpin.c +++ b/security/loadpin/loadpin.c @@ -296,7 +296,7 @@ static int read_trusted_verity_root_digests(unsigned int fd) return -EPERM; f = fdget(fd); - if (!f.file) + if (!fd_file(f)) return -EINVAL; data = kzalloc(SZ_4K, GFP_KERNEL); @@ -305,7 +305,7 @@ static int read_trusted_verity_root_digests(unsigned int fd) goto err; } - rc = kernel_read_file(f.file, 0, (void **)&data, SZ_4K - 1, NULL, READING_POLICY); + rc = kernel_read_file(fd_file(f), 0, (void **)&data, SZ_4K - 1, NULL, READING_POLICY); if (rc < 0) goto err; diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 4057f9f10aee..cbb9c972cb93 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -2250,12 +2250,12 @@ static int snd_pcm_link(struct snd_pcm_substream *substream, int fd) bool nonatomic = substream->pcm->nonatomic; CLASS(fd, f)(fd); - if (!f.file) + if (!fd_file(f)) return -EBADFD; - if (!is_pcm_file(f.file)) + if (!is_pcm_file(fd_file(f))) return -EBADFD; - pcm_file = f.file->private_data; + pcm_file = fd_file(f)->private_data; substream1 = pcm_file->substream; if (substream == substream1) diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index 229570059a1b..65efb3735e79 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -327,12 +327,12 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) seqcount_spinlock_init(&irqfd->irq_entry_sc, &kvm->irqfds.lock); f = fdget(args->fd); - if (!f.file) { + if (!fd_file(f)) { ret = -EBADF; goto out; } - eventfd = eventfd_ctx_fileget(f.file); + eventfd = eventfd_ctx_fileget(fd_file(f)); if (IS_ERR(eventfd)) { ret = PTR_ERR(eventfd); goto fail; @@ -419,7 +419,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) * Check if there was an event already pending on the eventfd * before we registered, and trigger it as if we didn't miss it. */ - events = vfs_poll(f.file, &irqfd->pt); + events = vfs_poll(fd_file(f), &irqfd->pt); if (events & EPOLLIN) schedule_work(&irqfd->inject); diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c index 76b7f6085dcd..388ae471d258 100644 --- a/virt/kvm/vfio.c +++ b/virt/kvm/vfio.c @@ -194,7 +194,7 @@ static int kvm_vfio_file_del(struct kvm_device *dev, unsigned int fd) int ret; f = fdget(fd); - if (!f.file) + if (!fd_file(f)) return -EBADF; ret = -ENOENT; @@ -202,7 +202,7 @@ static int kvm_vfio_file_del(struct kvm_device *dev, unsigned int fd) mutex_lock(&kv->lock); list_for_each_entry(kvf, &kv->file_list, node) { - if (kvf->file != f.file) + if (kvf->file != fd_file(f)) continue; list_del(&kvf->node); @@ -240,7 +240,7 @@ static int kvm_vfio_file_set_spapr_tce(struct kvm_device *dev, return -EFAULT; f = fdget(param.groupfd); - if (!f.file) + if (!fd_file(f)) return -EBADF; ret = -ENOENT; @@ -248,7 +248,7 @@ static int kvm_vfio_file_set_spapr_tce(struct kvm_device *dev, mutex_lock(&kv->lock); list_for_each_entry(kvf, &kv->file_list, node) { - if (kvf->file != f.file) + if (kvf->file != fd_file(f)) continue; if (!kvf->iommu_group) { -- cgit v1.2.3 From 88a2f6468d013ca1163490dbddfc95135d1c27a1 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 31 May 2024 15:45:12 -0400 Subject: struct fd: representation change We want the compiler to see that fdput() on empty instance is a no-op. The emptiness check is that file reference is NULL, while fdput() is "fput() if FDPUT_FPUT is present in flags". The reason why fdput() on empty instance is a no-op is something compiler can't see - it's that we never generate instances with NULL file reference combined with non-zero flags. It's not that hard to deal with - the real primitives behind fdget() et.al. are returning an unsigned long value, unpacked by (inlined) __to_fd() into the current struct file * + int. The lower bits are used to store flags, while the rest encodes the pointer. Linus suggested that keeping this unsigned long around with the extractions done by inlined accessors should generate a sane code and that turns out to be the case. Namely, turning struct fd into a struct-wrapped unsinged long, with fd_empty(f) => unlikely(f.word == 0) fd_file(f) => (struct file *)(f.word & ~3) fdput(f) => if (f.word & 1) fput(fd_file(f)) ends up with compiler doing the right thing. The cost is the patch footprint, of course - we need to switch f.file to fd_file(f) all over the tree, and it's not doable with simple search and replace; there are false positives, etc. Note that the sole member of that structure is an opaque unsigned long - all accesses should be done via wrappers and I don't want to use a name that would invite manual casts to file pointers, etc. The value of that member is equal either to (unsigned long)p | flags, p being an address of some struct file instance, or to 0 for an empty fd. For now the new predicate (fd_empty(f)) has no users; all the existing checks have form (!fd_file(f)). We will convert to fd_empty() use later; here we only define it (and tell the compiler that it's unlikely to return true). This commit only deals with representation change; there will be followups. Reviewed-by: Christian Brauner Signed-off-by: Al Viro --- drivers/infiniband/core/uverbs_cmd.c | 2 +- fs/overlayfs/file.c | 28 +++++++++++++++------------- fs/xfs/xfs_handle.c | 2 +- include/linux/file.h | 22 ++++++++++++++++------ kernel/events/core.c | 2 +- net/socket.c | 2 +- 6 files changed, 35 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 3f85575cf971..a4cce360df21 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -572,7 +572,7 @@ static int ib_uverbs_open_xrcd(struct uverbs_attr_bundle *attrs) struct inode *inode = NULL; int new_xrcd = 0; struct ib_device *ib_dev; - struct fd f = {}; + struct fd f = EMPTY_FD; int ret; ret = uverbs_request(attrs, &cmd, sizeof(cmd)); diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index c4963d0c5549..2b7a5a3a7a2f 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -93,11 +93,11 @@ static int ovl_real_fdget_meta(const struct file *file, struct fd *real, bool allow_meta) { struct dentry *dentry = file_dentry(file); + struct file *realfile = file->private_data; struct path realpath; int err; - real->flags = 0; - real->file = file->private_data; + real->word = (unsigned long)realfile; if (allow_meta) { ovl_path_real(dentry, &realpath); @@ -113,16 +113,17 @@ static int ovl_real_fdget_meta(const struct file *file, struct fd *real, return -EIO; /* Has it been copied up since we'd opened it? */ - if (unlikely(file_inode(real->file) != d_inode(realpath.dentry))) { - real->flags = FDPUT_FPUT; - real->file = ovl_open_realfile(file, &realpath); - - return PTR_ERR_OR_ZERO(real->file); + if (unlikely(file_inode(realfile) != d_inode(realpath.dentry))) { + struct file *f = ovl_open_realfile(file, &realpath); + if (IS_ERR(f)) + return PTR_ERR(f); + real->word = (unsigned long)ovl_open_realfile(file, &realpath) | FDPUT_FPUT; + return 0; } /* Did the flags change since open? */ - if (unlikely((file->f_flags ^ real->file->f_flags) & ~OVL_OPEN_FLAGS)) - return ovl_change_flags(real->file, file->f_flags); + if (unlikely((file->f_flags ^ realfile->f_flags) & ~OVL_OPEN_FLAGS)) + return ovl_change_flags(realfile, file->f_flags); return 0; } @@ -130,10 +131,11 @@ static int ovl_real_fdget_meta(const struct file *file, struct fd *real, static int ovl_real_fdget(const struct file *file, struct fd *real) { if (d_is_dir(file_dentry(file))) { - real->flags = 0; - real->file = ovl_dir_real_file(file, false); - - return PTR_ERR_OR_ZERO(real->file); + struct file *f = ovl_dir_real_file(file, false); + if (IS_ERR(f)) + return PTR_ERR(f); + real->word = (unsigned long)f; + return 0; } return ovl_real_fdget_meta(file, real, false); diff --git a/fs/xfs/xfs_handle.c b/fs/xfs/xfs_handle.c index 7bcc4f519cb8..49e5e5f04e60 100644 --- a/fs/xfs/xfs_handle.c +++ b/fs/xfs/xfs_handle.c @@ -85,7 +85,7 @@ xfs_find_handle( int hsize; xfs_handle_t handle; struct inode *inode; - struct fd f = {NULL}; + struct fd f = EMPTY_FD; struct path path; int error; struct xfs_inode *ip; diff --git a/include/linux/file.h b/include/linux/file.h index 0f3f369f2450..eb28469b1c16 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -35,18 +35,28 @@ static inline void fput_light(struct file *file, int fput_needed) fput(file); } +/* either a reference to struct file + flags + * (cloned vs. borrowed, pos locked), with + * flags stored in lower bits of value, + * or empty (represented by 0). + */ struct fd { - struct file *file; - unsigned int flags; + unsigned long word; }; #define FDPUT_FPUT 1 #define FDPUT_POS_UNLOCK 2 -#define fd_file(f) ((f).file) +#define fd_file(f) ((struct file *)((f).word & ~(FDPUT_FPUT|FDPUT_POS_UNLOCK))) +static inline bool fd_empty(struct fd f) +{ + return unlikely(!f.word); +} + +#define EMPTY_FD (struct fd){0} static inline void fdput(struct fd fd) { - if (fd.flags & FDPUT_FPUT) + if (fd.word & FDPUT_FPUT) fput(fd_file(fd)); } @@ -60,7 +70,7 @@ extern void __f_unlock_pos(struct file *); static inline struct fd __to_fd(unsigned long v) { - return (struct fd){(struct file *)(v & ~3),v & 3}; + return (struct fd){v}; } static inline struct fd fdget(unsigned int fd) @@ -80,7 +90,7 @@ static inline struct fd fdget_pos(int fd) static inline void fdput_pos(struct fd f) { - if (f.flags & FDPUT_POS_UNLOCK) + if (f.word & FDPUT_POS_UNLOCK) __f_unlock_pos(fd_file(f)); fdput(f); } diff --git a/kernel/events/core.c b/kernel/events/core.c index 17b19d3e74ba..fd2ac9c7fd77 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -12474,7 +12474,7 @@ SYSCALL_DEFINE5(perf_event_open, struct perf_event_attr attr; struct perf_event_context *ctx; struct file *event_file = NULL; - struct fd group = {NULL, 0}; + struct fd group = EMPTY_FD; struct task_struct *task = NULL; struct pmu *pmu; int event_fd; diff --git a/net/socket.c b/net/socket.c index f77a42a74510..c0d4f5032374 100644 --- a/net/socket.c +++ b/net/socket.c @@ -559,7 +559,7 @@ static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed) if (fd_file(f)) { sock = sock_from_file(fd_file(f)); if (likely(sock)) { - *fput_needed = f.flags & FDPUT_FPUT; + *fput_needed = f.word & FDPUT_FPUT; return sock; } *err = -ENOTSOCK; -- cgit v1.2.3 From de12c3391bce10504c0e7bd767516c74110cfce1 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 31 May 2024 16:34:25 -0400 Subject: add struct fd constructors, get rid of __to_fd() Make __fdget() et.al. return struct fd directly. New helpers: BORROWED_FD(file) and CLONED_FD(file), for borrowed and cloned file references resp. NOTE: this might need tuning; in particular, inline on __fget_light() is there to keep the code generation same as before - we probably want to keep it inlined in fdget() et.al. (especially so in fdget_pos()), but that needs profiling. Reviewed-by: Christian Brauner Signed-off-by: Al Viro --- fs/file.c | 26 +++++++++++++------------- include/linux/file.h | 33 +++++++++++---------------------- 2 files changed, 24 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/fs/file.c b/fs/file.c index a3b72aa64f11..6f5ed4daafd2 100644 --- a/fs/file.c +++ b/fs/file.c @@ -1128,7 +1128,7 @@ EXPORT_SYMBOL(task_lookup_next_fdget_rcu); * The fput_needed flag returned by fget_light should be passed to the * corresponding fput_light. */ -static unsigned long __fget_light(unsigned int fd, fmode_t mask) +static inline struct fd __fget_light(unsigned int fd, fmode_t mask) { struct files_struct *files = current->files; struct file *file; @@ -1145,22 +1145,22 @@ static unsigned long __fget_light(unsigned int fd, fmode_t mask) if (likely(atomic_read_acquire(&files->count) == 1)) { file = files_lookup_fd_raw(files, fd); if (!file || unlikely(file->f_mode & mask)) - return 0; - return (unsigned long)file; + return EMPTY_FD; + return BORROWED_FD(file); } else { file = __fget_files(files, fd, mask); if (!file) - return 0; - return FDPUT_FPUT | (unsigned long)file; + return EMPTY_FD; + return CLONED_FD(file); } } -unsigned long __fdget(unsigned int fd) +struct fd fdget(unsigned int fd) { return __fget_light(fd, FMODE_PATH); } -EXPORT_SYMBOL(__fdget); +EXPORT_SYMBOL(fdget); -unsigned long __fdget_raw(unsigned int fd) +struct fd fdget_raw(unsigned int fd) { return __fget_light(fd, 0); } @@ -1181,16 +1181,16 @@ static inline bool file_needs_f_pos_lock(struct file *file) (file_count(file) > 1 || file->f_op->iterate_shared); } -unsigned long __fdget_pos(unsigned int fd) +struct fd fdget_pos(unsigned int fd) { - unsigned long v = __fdget(fd); - struct file *file = (struct file *)(v & ~3); + struct fd f = fdget(fd); + struct file *file = fd_file(f); if (file && file_needs_f_pos_lock(file)) { - v |= FDPUT_POS_UNLOCK; + f.word |= FDPUT_POS_UNLOCK; mutex_lock(&file->f_pos_lock); } - return v; + return f; } void __f_unlock_pos(struct file *f) diff --git a/include/linux/file.h b/include/linux/file.h index eb28469b1c16..aab1caff6713 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -53,6 +53,14 @@ static inline bool fd_empty(struct fd f) } #define EMPTY_FD (struct fd){0} +static inline struct fd BORROWED_FD(struct file *f) +{ + return (struct fd){(unsigned long)f}; +} +static inline struct fd CLONED_FD(struct file *f) +{ + return (struct fd){(unsigned long)f | FDPUT_FPUT}; +} static inline void fdput(struct fd fd) { @@ -63,30 +71,11 @@ static inline void fdput(struct fd fd) extern struct file *fget(unsigned int fd); extern struct file *fget_raw(unsigned int fd); extern struct file *fget_task(struct task_struct *task, unsigned int fd); -extern unsigned long __fdget(unsigned int fd); -extern unsigned long __fdget_raw(unsigned int fd); -extern unsigned long __fdget_pos(unsigned int fd); extern void __f_unlock_pos(struct file *); -static inline struct fd __to_fd(unsigned long v) -{ - return (struct fd){v}; -} - -static inline struct fd fdget(unsigned int fd) -{ - return __to_fd(__fdget(fd)); -} - -static inline struct fd fdget_raw(unsigned int fd) -{ - return __to_fd(__fdget_raw(fd)); -} - -static inline struct fd fdget_pos(int fd) -{ - return __to_fd(__fdget_pos(fd)); -} +struct fd fdget(unsigned int fd); +struct fd fdget_raw(unsigned int fd); +struct fd fdget_pos(unsigned int fd); static inline void fdput_pos(struct fd f) { -- cgit v1.2.3 From 12dbc67c3b0bcd7414b511fd8a42ba4e388705bc Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 7 Aug 2024 21:45:28 +0800 Subject: net: stmmac: Move the atds flag to the stmmac_dma_cfg structure ATDS (Alternate Descriptor Size) is a part of the DMA Bus Mode configs (together with PBL, ALL, EME, etc) of the DW GMAC controllers. Seeing it's not changed at runtime but is activated as long as the IP-core has it supported (at least due to the Type 2 Full Checksum Offload Engine feature), move the respective parameter from the stmmac_dma_ops::init() callback argument to the stmmac_dma_cfg structure, which already have the rest of the DMA-related configs defined. Besides the being added in the next commit DW GMAC multi-channels support will require to add the stmmac_dma_ops::init_chan() callback and have the ATDS flag set/cleared for each channel in there. Having the atds-flag in the stmmac_dma_cfg structure will make the parameter accessible from stmmac_dma_ops::init_chan() callback too. Signed-off-by: Feiyang Chen Signed-off-by: Yinggang Gu Reviewed-by: Serge Semin Acked-by: Huacai Chen Signed-off-by: Yanteng Si Tested-by: Serge Semin Signed-off-by: Paolo Abeni --- drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c | 4 ++-- drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c | 2 +- drivers/net/ethernet/stmicro/stmmac/hwif.h | 3 +-- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 5 ++--- include/linux/stmmac.h | 1 + 8 files changed, 10 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index e1b761dcfa1d..d87079016952 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -299,7 +299,7 @@ static int sun8i_dwmac_dma_reset(void __iomem *ioaddr) * Called from stmmac via stmmac_dma_ops->init */ static void sun8i_dwmac_dma_init(void __iomem *ioaddr, - struct stmmac_dma_cfg *dma_cfg, int atds) + struct stmmac_dma_cfg *dma_cfg) { writel(EMAC_RX_INT | EMAC_TX_INT, ioaddr + EMAC_INT_EN); writel(0x1FFFFFF, ioaddr + EMAC_INT_STA); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c index adccdd816ea9..984b809105af 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c @@ -71,7 +71,7 @@ static void dwmac1000_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi) } static void dwmac1000_dma_init(void __iomem *ioaddr, - struct stmmac_dma_cfg *dma_cfg, int atds) + struct stmmac_dma_cfg *dma_cfg) { u32 value = readl(ioaddr + DMA_BUS_MODE); int txpbl = dma_cfg->txpbl ?: dma_cfg->pbl; @@ -98,7 +98,7 @@ static void dwmac1000_dma_init(void __iomem *ioaddr, if (dma_cfg->mixed_burst) value |= DMA_BUS_MODE_MB; - if (atds) + if (dma_cfg->atds) value |= DMA_BUS_MODE_ATDS; if (dma_cfg->aal) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c index b402fb54f613..82957db47c99 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c @@ -19,7 +19,7 @@ #include "dwmac_dma.h" static void dwmac100_dma_init(void __iomem *ioaddr, - struct stmmac_dma_cfg *dma_cfg, int atds) + struct stmmac_dma_cfg *dma_cfg) { /* Enable Application Access by writing to DMA CSR0 */ writel(DMA_BUS_MODE_DEFAULT | (dma_cfg->pbl << DMA_BUS_MODE_PBL_SHIFT), diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c index 84d3a8551b03..e0165358c4ac 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c @@ -153,7 +153,7 @@ static void dwmac410_dma_init_channel(struct stmmac_priv *priv, } static void dwmac4_dma_init(void __iomem *ioaddr, - struct stmmac_dma_cfg *dma_cfg, int atds) + struct stmmac_dma_cfg *dma_cfg) { u32 value = readl(ioaddr + DMA_SYS_BUS_MODE); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c index dd2ab6185c40..7840bc403788 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c @@ -20,7 +20,7 @@ static int dwxgmac2_dma_reset(void __iomem *ioaddr) } static void dwxgmac2_dma_init(void __iomem *ioaddr, - struct stmmac_dma_cfg *dma_cfg, int atds) + struct stmmac_dma_cfg *dma_cfg) { u32 value = readl(ioaddr + XGMAC_DMA_SYSBUS_MODE); diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index e53c32362774..1c99c99f4627 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -175,8 +175,7 @@ struct dma_features; struct stmmac_dma_ops { /* DMA core initialization */ int (*reset)(void __iomem *ioaddr); - void (*init)(void __iomem *ioaddr, struct stmmac_dma_cfg *dma_cfg, - int atds); + void (*init)(void __iomem *ioaddr, struct stmmac_dma_cfg *dma_cfg); void (*init_chan)(struct stmmac_priv *priv, void __iomem *ioaddr, struct stmmac_dma_cfg *dma_cfg, u32 chan); void (*init_rx_chan)(struct stmmac_priv *priv, void __iomem *ioaddr, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index f3a1b179aaea..9f1286835550 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3003,7 +3003,6 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) struct stmmac_rx_queue *rx_q; struct stmmac_tx_queue *tx_q; u32 chan = 0; - int atds = 0; int ret = 0; if (!priv->plat->dma_cfg || !priv->plat->dma_cfg->pbl) { @@ -3012,7 +3011,7 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) } if (priv->extend_desc && (priv->mode == STMMAC_RING_MODE)) - atds = 1; + priv->plat->dma_cfg->atds = 1; ret = stmmac_reset(priv, priv->ioaddr); if (ret) { @@ -3021,7 +3020,7 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) } /* DMA Configuration */ - stmmac_dma_init(priv, priv->ioaddr, priv->plat->dma_cfg, atds); + stmmac_dma_init(priv, priv->ioaddr, priv->plat->dma_cfg); if (priv->plat->axi) stmmac_axi(priv, priv->ioaddr, priv->plat->axi); diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 84e13bd5df28..338991c08f00 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -100,6 +100,7 @@ struct stmmac_dma_cfg { bool eame; bool multi_msi_en; bool dche; + bool atds; }; #define AXI_BLEN 7 -- cgit v1.2.3 From c343e66ed009fdb6206787558130ccbd504ffc12 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 10 Aug 2024 22:52:17 +0200 Subject: usb: gadget: configfs: Make check_user_usb_string() static "linux/usb/gadget_configfs.h" is only included in "drivers/usb/gadget/configfs.c", so there is no need to declare a function in the header file. it is only used in this .c file. It's better to have it static. Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/958cb49dca1bff4254a3492c018efbf3b01918b4.1723323107.git.christophe.jaillet@wanadoo.fr Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/configfs.c | 2 +- include/linux/usb/gadget_configfs.h | 3 --- 2 files changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index 0e7c1e947c0a..e0bf2b2bfc01 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -12,7 +12,7 @@ #include "u_f.h" #include "u_os_desc.h" -int check_user_usb_string(const char *name, +static int check_user_usb_string(const char *name, struct usb_gadget_strings *stringtab_dev) { u16 num; diff --git a/include/linux/usb/gadget_configfs.h b/include/linux/usb/gadget_configfs.h index d61aebd68128..6a552dd4dec9 100644 --- a/include/linux/usb/gadget_configfs.h +++ b/include/linux/usb/gadget_configfs.h @@ -4,9 +4,6 @@ #include -int check_user_usb_string(const char *name, - struct usb_gadget_strings *stringtab_dev); - #define GS_STRINGS_W(__struct, __name) \ static ssize_t __struct##_##__name##_store(struct config_item *item, \ const char *page, size_t len) \ -- cgit v1.2.3 From d1e14e06810a96ef0cdabf572513594031d4dad6 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 10 Aug 2024 23:05:46 +0200 Subject: usb: gadget: configfs: Constify struct config_item_type 'struct config_item_type' is not modified in this file. Apparently, these structures are only used with config_group_init_type_name() which takes a const struct config_item_type* as a 3rd argument. Constifying this structure moves some data to a read-only section, so increase overall security, especially when the structure holds some function pointers. On a x86_64, with allmodconfig: Before: ====== text data bss dec hex filename 40834 5112 64 46010 b3ba drivers/usb/gadget/configfs.o After: ===== text data bss dec hex filename 41218 4728 64 46010 b3ba drivers/usb/gadget/configfs.o Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/513223e97082e1bb758e36d55c175ec9ea34a71c.1723323896.git.christophe.jaillet@wanadoo.fr Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/configfs.c | 8 ++++---- include/linux/usb/gadget_configfs.h | 4 ++-- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index e0bf2b2bfc01..5cba3e8d626c 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -902,7 +902,7 @@ static struct configfs_group_operations gadget_language_langid_group_ops = { .drop_item = gadget_language_string_drop, }; -static struct config_item_type gadget_language_type = { +static const struct config_item_type gadget_language_type = { .ct_item_ops = &gadget_language_langid_item_ops, .ct_group_ops = &gadget_language_langid_group_ops, .ct_attrs = gadget_language_langid_attrs, @@ -961,7 +961,7 @@ static struct configfs_group_operations gadget_language_group_ops = { .drop_item = &gadget_language_drop, }; -static struct config_item_type gadget_language_strings_type = { +static const struct config_item_type gadget_language_strings_type = { .ct_group_ops = &gadget_language_group_ops, .ct_owner = THIS_MODULE, }; @@ -1106,7 +1106,7 @@ static struct configfs_attribute *webusb_attrs[] = { NULL, }; -static struct config_item_type webusb_type = { +static const struct config_item_type webusb_type = { .ct_attrs = webusb_attrs, .ct_owner = THIS_MODULE, }; @@ -1263,7 +1263,7 @@ static struct configfs_item_operations os_desc_ops = { .drop_link = os_desc_unlink, }; -static struct config_item_type os_desc_type = { +static const struct config_item_type os_desc_type = { .ct_item_ops = &os_desc_ops, .ct_attrs = os_desc_attrs, .ct_owner = THIS_MODULE, diff --git a/include/linux/usb/gadget_configfs.h b/include/linux/usb/gadget_configfs.h index 6a552dd4dec9..6b5d6838f865 100644 --- a/include/linux/usb/gadget_configfs.h +++ b/include/linux/usb/gadget_configfs.h @@ -34,7 +34,7 @@ static struct configfs_item_operations struct_in##_langid_item_ops = { \ .release = struct_in##_attr_release, \ }; \ \ -static struct config_item_type struct_in##_langid_type = { \ +static const struct config_item_type struct_in##_langid_type = { \ .ct_item_ops = &struct_in##_langid_item_ops, \ .ct_attrs = struct_in##_langid_attrs, \ .ct_owner = THIS_MODULE, \ @@ -91,7 +91,7 @@ static struct configfs_group_operations struct_in##_strings_ops = { \ .drop_item = &struct_in##_strings_drop, \ }; \ \ -static struct config_item_type struct_in##_strings_type = { \ +static const struct config_item_type struct_in##_strings_type = { \ .ct_group_ops = &struct_in##_strings_ops, \ .ct_owner = THIS_MODULE, \ } -- cgit v1.2.3 From 92567a5f92bc947fb7aa4351979db1b7b71a554c Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Thu, 8 Aug 2024 22:06:19 +0800 Subject: iommu: Remove unused declaration iommu_sva_unbind_gpasid() Commit 0c9f17877891 ("iommu: Remove guest pasid related interfaces and definitions") removed the implementation but leave declaration. Signed-off-by: Yue Haibing Reviewed-by: Lu Baolu Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20240808140619.2498535-1-yuehaibing@huawei.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 4d47f2c33311..04cbdae0052e 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -795,8 +795,6 @@ extern int iommu_attach_device(struct iommu_domain *domain, struct device *dev); extern void iommu_detach_device(struct iommu_domain *domain, struct device *dev); -extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain, - struct device *dev, ioasid_t pasid); extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); extern struct iommu_domain *iommu_get_dma_domain(struct device *dev); extern int iommu_map(struct iommu_domain *domain, unsigned long iova, -- cgit v1.2.3 From 1ef33652d22c69a2a7519d003cd6c79b8e514f44 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 8 Aug 2024 05:25:07 -0700 Subject: net: netpoll: extract core of netpoll_cleanup Extract the core part of netpoll_cleanup(), so, it could be called from a caller that has the rtnl lock already. Netconsole uses this in a weird way right now: __netpoll_cleanup(&nt->np); spin_lock_irqsave(&target_list_lock, flags); netdev_put(nt->np.dev, &nt->np.dev_tracker); nt->np.dev = NULL; nt->enabled = false; This will be replaced by do_netpoll_cleanup() as the locking situation is overhauled. Signed-off-by: Breno Leitao Reviewed-by: Rik van Riel Signed-off-by: Paolo Abeni --- include/linux/netpoll.h | 1 + net/core/netpoll.c | 12 +++++++++--- 2 files changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index bd19c4b91e31..cd4e28db0cbd 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -64,6 +64,7 @@ int netpoll_setup(struct netpoll *np); void __netpoll_cleanup(struct netpoll *np); void __netpoll_free(struct netpoll *np); void netpoll_cleanup(struct netpoll *np); +void do_netpoll_cleanup(struct netpoll *np); netdev_tx_t netpoll_send_skb(struct netpoll *np, struct sk_buff *skb); #ifdef CONFIG_NETPOLL diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 55bcacf67df3..a58ea724790c 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -853,14 +853,20 @@ void __netpoll_free(struct netpoll *np) } EXPORT_SYMBOL_GPL(__netpoll_free); +void do_netpoll_cleanup(struct netpoll *np) +{ + __netpoll_cleanup(np); + netdev_put(np->dev, &np->dev_tracker); + np->dev = NULL; +} +EXPORT_SYMBOL(do_netpoll_cleanup); + void netpoll_cleanup(struct netpoll *np) { rtnl_lock(); if (!np->dev) goto out; - __netpoll_cleanup(np); - netdev_put(np->dev, &np->dev_tracker); - np->dev = NULL; + do_netpoll_cleanup(np); out: rtnl_unlock(); } -- cgit v1.2.3 From dde286ee57704226b500cb9eb59547fec07aad3d Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Thu, 8 Aug 2024 15:36:28 +0300 Subject: regmap: Allow setting IRQ domain name suffix When multiple IRQ domains are created from the same device-tree node they will get the same name based on the device-tree path. This will cause a naming collision in debugFS when IRQ domain specific entries are created. The regmap-IRQ creates per instance IRQ domains. This will lead to a domain name conflict when a device which provides more than one interrupt line uses the regmap-IRQ. Add support for specifying an IRQ domain name suffix when creating a regmap-IRQ controller. Signed-off-by: Matti Vaittinen Link: https://patch.msgid.link/776bc4996969e5081bcf61b9bdb5517e537147a3.1723120028.git.mazziesaccount@gmail.com Signed-off-by: Mark Brown --- drivers/base/regmap/regmap-irq.c | 37 ++++++++++++++++++++++++++----------- include/linux/regmap.h | 4 ++++ 2 files changed, 30 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c index d3ec1345b5b5..a750e48a26b8 100644 --- a/drivers/base/regmap/regmap-irq.c +++ b/drivers/base/regmap/regmap-irq.c @@ -608,6 +608,30 @@ int regmap_irq_set_type_config_simple(unsigned int **buf, unsigned int type, } EXPORT_SYMBOL_GPL(regmap_irq_set_type_config_simple); +static int regmap_irq_create_domain(struct fwnode_handle *fwnode, int irq_base, + const struct regmap_irq_chip *chip, + struct regmap_irq_chip_data *d) +{ + struct irq_domain_info info = { + .fwnode = fwnode, + .size = chip->num_irqs, + .hwirq_max = chip->num_irqs, + .virq_base = irq_base, + .ops = ®map_domain_ops, + .host_data = d, + .name_suffix = chip->domain_suffix, + }; + + d->domain = irq_domain_instantiate(&info); + if (IS_ERR(d->domain)) { + dev_err(d->map->dev, "Failed to create IRQ domain\n"); + return PTR_ERR(d->domain); + } + + return 0; +} + + /** * regmap_add_irq_chip_fwnode() - Use standard regmap IRQ controller handling * @@ -856,18 +880,9 @@ int regmap_add_irq_chip_fwnode(struct fwnode_handle *fwnode, } } - if (irq_base) - d->domain = irq_domain_create_legacy(fwnode, chip->num_irqs, - irq_base, 0, - ®map_domain_ops, d); - else - d->domain = irq_domain_create_linear(fwnode, chip->num_irqs, - ®map_domain_ops, d); - if (!d->domain) { - dev_err(map->dev, "Failed to create IRQ domain\n"); - ret = -ENOMEM; + ret = regmap_irq_create_domain(fwnode, irq_base, chip, d); + if (ret) goto err_alloc; - } ret = request_threaded_irq(irq, NULL, regmap_irq_thread, irq_flags | IRQF_ONESHOT, diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 122e38161acb..f9ccad32fc5c 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -1521,6 +1521,9 @@ struct regmap_irq_chip_data; * struct regmap_irq_chip - Description of a generic regmap irq_chip. * * @name: Descriptive name for IRQ controller. + * @domain_suffix: Name suffix to be appended to end of IRQ domain name. Needed + * when multiple regmap-IRQ controllers are created from same + * device. * * @main_status: Base main status register address. For chips which have * interrupts arranged in separate sub-irq blocks with own IRQ @@ -1606,6 +1609,7 @@ struct regmap_irq_chip_data; */ struct regmap_irq_chip { const char *name; + const char *domain_suffix; unsigned int main_status; unsigned int num_main_status_bits; -- cgit v1.2.3 From 2a0629834cd82f05d424bbc193374f9a43d1f87d Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Fri, 9 Aug 2024 11:16:28 +0800 Subject: vfs: Don't evict inode under the inode lru traversing context MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The inode reclaiming process(See function prune_icache_sb) collects all reclaimable inodes and mark them with I_FREEING flag at first, at that time, other processes will be stuck if they try getting these inodes (See function find_inode_fast), then the reclaiming process destroy the inodes by function dispose_list(). Some filesystems(eg. ext4 with ea_inode feature, ubifs with xattr) may do inode lookup in the inode evicting callback function, if the inode lookup is operated under the inode lru traversing context, deadlock problems may happen. Case 1: In function ext4_evict_inode(), the ea inode lookup could happen if ea_inode feature is enabled, the lookup process will be stuck under the evicting context like this: 1. File A has inode i_reg and an ea inode i_ea 2. getfattr(A, xattr_buf) // i_ea is added into lru // lru->i_ea 3. Then, following three processes running like this: PA PB echo 2 > /proc/sys/vm/drop_caches shrink_slab prune_dcache_sb // i_reg is added into lru, lru->i_ea->i_reg prune_icache_sb list_lru_walk_one inode_lru_isolate i_ea->i_state |= I_FREEING // set inode state inode_lru_isolate __iget(i_reg) spin_unlock(&i_reg->i_lock) spin_unlock(lru_lock) rm file A i_reg->nlink = 0 iput(i_reg) // i_reg->nlink is 0, do evict ext4_evict_inode ext4_xattr_delete_inode ext4_xattr_inode_dec_ref_all ext4_xattr_inode_iget ext4_iget(i_ea->i_ino) iget_locked find_inode_fast __wait_on_freeing_inode(i_ea) ----→ AA deadlock dispose_list // cannot be executed by prune_icache_sb wake_up_bit(&i_ea->i_state) Case 2: In deleted inode writing function ubifs_jnl_write_inode(), file deleting process holds BASEHD's wbuf->io_mutex while getting the xattr inode, which could race with inode reclaiming process(The reclaiming process could try locking BASEHD's wbuf->io_mutex in inode evicting function), then an ABBA deadlock problem would happen as following: 1. File A has inode ia and a xattr(with inode ixa), regular file B has inode ib and a xattr. 2. getfattr(A, xattr_buf) // ixa is added into lru // lru->ixa 3. Then, following three processes running like this: PA PB PC echo 2 > /proc/sys/vm/drop_caches shrink_slab prune_dcache_sb // ib and ia are added into lru, lru->ixa->ib->ia prune_icache_sb list_lru_walk_one inode_lru_isolate ixa->i_state |= I_FREEING // set inode state inode_lru_isolate __iget(ib) spin_unlock(&ib->i_lock) spin_unlock(lru_lock) rm file B ib->nlink = 0 rm file A iput(ia) ubifs_evict_inode(ia) ubifs_jnl_delete_inode(ia) ubifs_jnl_write_inode(ia) make_reservation(BASEHD) // Lock wbuf->io_mutex ubifs_iget(ixa->i_ino) iget_locked find_inode_fast __wait_on_freeing_inode(ixa) | iput(ib) // ib->nlink is 0, do evict | ubifs_evict_inode | ubifs_jnl_delete_inode(ib) ↓ ubifs_jnl_write_inode ABBA deadlock ←-----make_reservation(BASEHD) dispose_list // cannot be executed by prune_icache_sb wake_up_bit(&ixa->i_state) Fix the possible deadlock by using new inode state flag I_LRU_ISOLATING to pin the inode in memory while inode_lru_isolate() reclaims its pages instead of using ordinary inode reference. This way inode deletion cannot be triggered from inode_lru_isolate() thus avoiding the deadlock. evict() is made to wait for I_LRU_ISOLATING to be cleared before proceeding with inode cleanup. Link: https://lore.kernel.org/all/37c29c42-7685-d1f0-067d-63582ffac405@huaweicloud.com/ Link: https://bugzilla.kernel.org/show_bug.cgi?id=219022 Fixes: e50e5129f384 ("ext4: xattr-in-inode support") Fixes: 7959cf3a7506 ("ubifs: journal: Handle xattrs like files") Cc: stable@vger.kernel.org Signed-off-by: Zhihao Cheng Link: https://lore.kernel.org/r/20240809031628.1069873-1-chengzhihao@huaweicloud.com Reviewed-by: Jan Kara Suggested-by: Jan Kara Suggested-by: Mateusz Guzik Signed-off-by: Christian Brauner --- fs/inode.c | 39 +++++++++++++++++++++++++++++++++++++-- include/linux/fs.h | 5 +++++ 2 files changed, 42 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/inode.c b/fs/inode.c index 86670941884b..10c4619faeef 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -488,6 +488,39 @@ static void inode_lru_list_del(struct inode *inode) this_cpu_dec(nr_unused); } +static void inode_pin_lru_isolating(struct inode *inode) +{ + lockdep_assert_held(&inode->i_lock); + WARN_ON(inode->i_state & (I_LRU_ISOLATING | I_FREEING | I_WILL_FREE)); + inode->i_state |= I_LRU_ISOLATING; +} + +static void inode_unpin_lru_isolating(struct inode *inode) +{ + spin_lock(&inode->i_lock); + WARN_ON(!(inode->i_state & I_LRU_ISOLATING)); + inode->i_state &= ~I_LRU_ISOLATING; + smp_mb(); + wake_up_bit(&inode->i_state, __I_LRU_ISOLATING); + spin_unlock(&inode->i_lock); +} + +static void inode_wait_for_lru_isolating(struct inode *inode) +{ + spin_lock(&inode->i_lock); + if (inode->i_state & I_LRU_ISOLATING) { + DEFINE_WAIT_BIT(wq, &inode->i_state, __I_LRU_ISOLATING); + wait_queue_head_t *wqh; + + wqh = bit_waitqueue(&inode->i_state, __I_LRU_ISOLATING); + spin_unlock(&inode->i_lock); + __wait_on_bit(wqh, &wq, bit_wait, TASK_UNINTERRUPTIBLE); + spin_lock(&inode->i_lock); + WARN_ON(inode->i_state & I_LRU_ISOLATING); + } + spin_unlock(&inode->i_lock); +} + /** * inode_sb_list_add - add inode to the superblock list of inodes * @inode: inode to add @@ -657,6 +690,8 @@ static void evict(struct inode *inode) inode_sb_list_del(inode); + inode_wait_for_lru_isolating(inode); + /* * Wait for flusher thread to be done with the inode so that filesystem * does not start destroying it while writeback is still running. Since @@ -855,7 +890,7 @@ static enum lru_status inode_lru_isolate(struct list_head *item, * be under pressure before the cache inside the highmem zone. */ if (inode_has_buffers(inode) || !mapping_empty(&inode->i_data)) { - __iget(inode); + inode_pin_lru_isolating(inode); spin_unlock(&inode->i_lock); spin_unlock(lru_lock); if (remove_inode_buffers(inode)) { @@ -867,7 +902,7 @@ static enum lru_status inode_lru_isolate(struct list_head *item, __count_vm_events(PGINODESTEAL, reap); mm_account_reclaimed_pages(reap); } - iput(inode); + inode_unpin_lru_isolating(inode); spin_lock(lru_lock); return LRU_RETRY; } diff --git a/include/linux/fs.h b/include/linux/fs.h index fd34b5755c0b..fb0426f349fc 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2392,6 +2392,9 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, * * I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback. * + * I_LRU_ISOLATING Inode is pinned being isolated from LRU without holding + * i_count. + * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -2415,6 +2418,8 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, #define I_DONTCACHE (1 << 16) #define I_SYNC_QUEUED (1 << 17) #define I_PINNING_NETFS_WB (1 << 18) +#define __I_LRU_ISOLATING 19 +#define I_LRU_ISOLATING (1 << __I_LRU_ISOLATING) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) -- cgit v1.2.3 From bcc954c6caba01fca143162d5fbb90e46aa1ad80 Mon Sep 17 00:00:00 2001 From: Ryo Takakura Date: Mon, 12 Aug 2024 16:27:03 +0900 Subject: printk/panic: Allow cpu backtraces to be written into ringbuffer during panic commit 779dbc2e78d7 ("printk: Avoid non-panic CPUs writing to ringbuffer") disabled non-panic CPUs to further write messages to ringbuffer after panicked. Since the commit, non-panicked CPU's are not allowed to write to ring buffer after panicked and CPU backtrace which is triggered after panicked to sample non-panicked CPUs' backtrace no longer serves its function as it has nothing to print. Fix the issue by allowing non-panicked CPUs to write into ringbuffer while CPU backtrace is in flight. Fixes: 779dbc2e78d7 ("printk: Avoid non-panic CPUs writing to ringbuffer") Signed-off-by: Ryo Takakura Reviewed-by: Petr Mladek Link: https://lore.kernel.org/r/20240812072703.339690-1-takakura@valinux.co.jp Signed-off-by: Petr Mladek --- include/linux/panic.h | 1 + kernel/panic.c | 8 +++++++- kernel/printk/printk.c | 2 +- 3 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/panic.h b/include/linux/panic.h index 3130e0b5116b..54d90b6c5f47 100644 --- a/include/linux/panic.h +++ b/include/linux/panic.h @@ -16,6 +16,7 @@ extern void oops_enter(void); extern void oops_exit(void); extern bool oops_may_print(void); +extern bool panic_triggering_all_cpu_backtrace; extern int panic_timeout; extern unsigned long panic_print; extern int panic_on_oops; diff --git a/kernel/panic.c b/kernel/panic.c index f861bedc1925..2a0449144f82 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -64,6 +64,8 @@ unsigned long panic_on_taint; bool panic_on_taint_nousertaint = false; static unsigned int warn_limit __read_mostly; +bool panic_triggering_all_cpu_backtrace; + int panic_timeout = CONFIG_PANIC_TIMEOUT; EXPORT_SYMBOL_GPL(panic_timeout); @@ -253,8 +255,12 @@ void check_panic_on_warn(const char *origin) */ static void panic_other_cpus_shutdown(bool crash_kexec) { - if (panic_print & PANIC_PRINT_ALL_CPU_BT) + if (panic_print & PANIC_PRINT_ALL_CPU_BT) { + /* Temporary allow non-panic CPUs to write their backtraces. */ + panic_triggering_all_cpu_backtrace = true; trigger_all_cpu_backtrace(); + panic_triggering_all_cpu_backtrace = false; + } /* * Note that smp_send_stop() is the usual SMP shutdown function, diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 054c0e7784fd..c22b07049c38 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2316,7 +2316,7 @@ asmlinkage int vprintk_emit(int facility, int level, * non-panic CPUs are generating any messages, they will be * silently dropped. */ - if (other_cpu_in_panic()) + if (other_cpu_in_panic() && !panic_triggering_all_cpu_backtrace) return 0; if (level == LOGLEVEL_SCHED) { -- cgit v1.2.3 From ec0a7d44b358afaaf52856d03c72e20587bc888b Mon Sep 17 00:00:00 2001 From: Matthew Brost Date: Fri, 9 Aug 2024 15:28:25 -0700 Subject: workqueue: Add interface for user-defined workqueue lockdep map Add an interface for a user-defined workqueue lockdep map, which is helpful when multiple workqueues are created for the same purpose. This also helps avoid leaking lockdep maps on each workqueue creation. v2: - Add alloc_workqueue_lockdep_map (Tejun) v3: - Drop __WQ_USER_OWNED_LOCKDEP (Tejun) - static inline alloc_ordered_workqueue_lockdep_map (Tejun) Cc: Tejun Heo Cc: Lai Jiangshan Signed-off-by: Matthew Brost Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 52 +++++++++++++++++++++++++++++++++++++++++++++++ kernel/workqueue.c | 28 +++++++++++++++++++++++++ 2 files changed, 80 insertions(+) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 4eb8f9563136..8ccbf510880b 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -507,6 +507,58 @@ void workqueue_softirq_dead(unsigned int cpu); __printf(1, 4) struct workqueue_struct * alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...); +#ifdef CONFIG_LOCKDEP +/** + * alloc_workqueue_lockdep_map - allocate a workqueue with user-defined lockdep_map + * @fmt: printf format for the name of the workqueue + * @flags: WQ_* flags + * @max_active: max in-flight work items, 0 for default + * @lockdep_map: user-defined lockdep_map + * @...: args for @fmt + * + * Same as alloc_workqueue but with the a user-define lockdep_map. Useful for + * workqueues created with the same purpose and to avoid leaking a lockdep_map + * on each workqueue creation. + * + * RETURNS: + * Pointer to the allocated workqueue on success, %NULL on failure. + */ +__printf(1, 5) struct workqueue_struct * +alloc_workqueue_lockdep_map(const char *fmt, unsigned int flags, int max_active, + struct lockdep_map *lockdep_map, ...); + +/** + * alloc_ordered_workqueue_lockdep_map - allocate an ordered workqueue with + * user-defined lockdep_map + * + * @fmt: printf format for the name of the workqueue + * @flags: WQ_* flags (only WQ_FREEZABLE and WQ_MEM_RECLAIM are meaningful) + * @lockdep_map: user-defined lockdep_map + * @args: args for @fmt + * + * Same as alloc_ordered_workqueue but with the a user-define lockdep_map. + * Useful for workqueues created with the same purpose and to avoid leaking a + * lockdep_map on each workqueue creation. + * + * RETURNS: + * Pointer to the allocated workqueue on success, %NULL on failure. + */ +__printf(1, 4) static inline struct workqueue_struct * +alloc_ordered_workqueue_lockdep_map(const char *fmt, unsigned int flags, + struct lockdep_map *lockdep_map, ...) +{ + struct workqueue_struct *wq; + va_list args; + + va_start(args, lockdep_map); + wq = alloc_workqueue_lockdep_map(fmt, WQ_UNBOUND | __WQ_ORDERED | flags, + 1, lockdep_map, args); + va_end(args); + + return wq; +} +#endif + /** * alloc_ordered_workqueue - allocate an ordered workqueue * @fmt: printf format for the name of the workqueue diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 4c8ba5c4229f..7468ba5e2417 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -4775,11 +4775,17 @@ static void wq_init_lockdep(struct workqueue_struct *wq) static void wq_unregister_lockdep(struct workqueue_struct *wq) { + if (wq->lockdep_map != &wq->__lockdep_map) + return; + lockdep_unregister_key(&wq->key); } static void wq_free_lockdep(struct workqueue_struct *wq) { + if (wq->lockdep_map != &wq->__lockdep_map) + return; + if (wq->lock_name != wq->name) kfree(wq->lock_name); } @@ -5756,6 +5762,28 @@ struct workqueue_struct *alloc_workqueue(const char *fmt, } EXPORT_SYMBOL_GPL(alloc_workqueue); +#ifdef CONFIG_LOCKDEP +__printf(1, 5) +struct workqueue_struct * +alloc_workqueue_lockdep_map(const char *fmt, unsigned int flags, + int max_active, struct lockdep_map *lockdep_map, ...) +{ + struct workqueue_struct *wq; + va_list args; + + va_start(args, lockdep_map); + wq = __alloc_workqueue(fmt, flags, max_active, args); + va_end(args); + if (!wq) + return NULL; + + wq->lockdep_map = lockdep_map; + + return wq; +} +EXPORT_SYMBOL_GPL(alloc_workqueue_lockdep_map); +#endif + static bool pwq_busy(struct pool_workqueue *pwq) { int i; -- cgit v1.2.3 From fb4dae4ca315fe48f1a8a452172f29196b2a7f3d Mon Sep 17 00:00:00 2001 From: Junfeng Guo Date: Thu, 25 Jul 2024 16:08:05 -0600 Subject: virtchnl: support raw packet in protocol header The patch extends existing virtchnl_proto_hdrs structure to allow VF to pass a pair of buffers as packet data and mask that describe a match pattern of a filter rule. Then the kernel PF driver is requested to parse the pair of buffer and figure out low level hardware metadata (ptype, profile, field vector.. ) to program the expected FDIR or RSS rules. Reviewed-by: Simon Horman Reviewed-by: Marcin Szycik Signed-off-by: Qi Zhang Signed-off-by: Junfeng Guo Signed-off-by: Ahmed Zaki Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen --- include/linux/avf/virtchnl.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 8e177b67e82f..4f78a65e33dc 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -1121,6 +1121,7 @@ enum virtchnl_vfr_states { }; #define VIRTCHNL_MAX_NUM_PROTO_HDRS 32 +#define VIRTCHNL_MAX_SIZE_RAW_PACKET 1024 #define PROTO_HDR_SHIFT 5 #define PROTO_HDR_FIELD_START(proto_hdr_type) ((proto_hdr_type) << PROTO_HDR_SHIFT) #define PROTO_HDR_FIELD_MASK ((1UL << PROTO_HDR_SHIFT) - 1) @@ -1266,13 +1267,22 @@ struct virtchnl_proto_hdrs { u8 pad[3]; /** * specify where protocol header start from. + * must be 0 when sending a raw packet request. * 0 - from the outer layer * 1 - from the first inner layer * 2 - from the second inner layer * .... **/ int count; /* the proto layers must < VIRTCHNL_MAX_NUM_PROTO_HDRS */ - struct virtchnl_proto_hdr proto_hdr[VIRTCHNL_MAX_NUM_PROTO_HDRS]; + union { + struct virtchnl_proto_hdr + proto_hdr[VIRTCHNL_MAX_NUM_PROTO_HDRS]; + struct { + u16 pkt_len; + u8 spec[VIRTCHNL_MAX_SIZE_RAW_PACKET]; + u8 mask[VIRTCHNL_MAX_SIZE_RAW_PACKET]; + } raw; + }; }; VIRTCHNL_CHECK_STRUCT_LEN(2312, virtchnl_proto_hdrs); -- cgit v1.2.3 From 623122ac1c4074791ea319df4676fb2875817fe4 Mon Sep 17 00:00:00 2001 From: Ahmed Zaki Date: Thu, 25 Jul 2024 16:08:09 -0600 Subject: iavf: add support for offloading tc U32 cls filters Add support for offloading cls U32 filters. Only "skbedit queue_mapping" and "drop" actions are supported. Also, only "ip" and "802_3" tc protocols are allowed. The PF must advertise the VIRTCHNL_VF_OFFLOAD_TC_U32 capability flag. Since the filters will be enabled via the FD stage at the PF, a new type of FDIR filters is added and the existing list and state machine are used. The new filters can be used to configure flow directors based on raw (binary) pattern in the rx packet. Examples: 0. # tc qdisc add dev enp175s0v0 ingress 1. Redirect UDP from src IP 192.168.2.1 to queue 12: # tc filter add dev protocol ip ingress u32 \ match u32 0x45000000 0xff000000 at 0 \ match u32 0x00110000 0x00ff0000 at 8 \ match u32 0xC0A80201 0xffffffff at 12 \ match u32 0x00000000 0x00000000 at 24 \ action skbedit queue_mapping 12 skip_sw 2. Drop all ICMP: # tc filter add dev protocol ip ingress u32 \ match u32 0x45000000 0xff000000 at 0 \ match u32 0x00010000 0x00ff0000 at 8 \ match u32 0x00000000 0x00000000 at 24 \ action drop skip_sw 3. Redirect ICMP traffic from MAC 3c:fd:fe:a5:47:e0 to queue 7 (note proto: 802_3): # tc filter add dev protocol 802_3 ingress u32 \ match u32 0x00003CFD 0x0000ffff at 4 \ match u32 0xFEA547E0 0xffffffff at 8 \ match u32 0x08004500 0xffffff00 at 12 \ match u32 0x00000001 0x000000ff at 20 \ match u32 0x0000 0x0000 at 40 \ action skbedit queue_mapping 7 skip_sw Notes on matches: 1 - All intermediate fields that are needed to parse the correct PTYPE must be provided (in e.g. 3: Ethernet Type 0x0800 in MAC, IP version and IP length: 0x45 and protocol: 0x01 (ICMP)). 2 - The last match must provide an offset that guarantees all required headers are accounted for, even if the last header is not matched. For example, in #2, the last match is 4 bytes at offset 24 starting from IP header, so the total is 14 (MAC) + 24 + 4 = 42, which is the sum of MAC+IP+ICMP headers. Reviewed-by: Sridhar Samudrala Reviewed-by: Marcin Szycik Signed-off-by: Ahmed Zaki Tested-by: Rafal Romanowski Reviewed-by: Simon Horman Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/iavf/iavf.h | 27 +++- drivers/net/ethernet/intel/iavf/iavf_ethtool.c | 9 +- drivers/net/ethernet/intel/iavf/iavf_fdir.c | 29 +++-- drivers/net/ethernet/intel/iavf/iavf_fdir.h | 10 +- drivers/net/ethernet/intel/iavf/iavf_main.c | 160 +++++++++++++++++++++++- drivers/net/ethernet/intel/iavf/iavf_virtchnl.c | 25 ++-- drivers/net/ethernet/intel/ice/ice_virtchnl.c | 4 + include/linux/avf/virtchnl.h | 1 + 8 files changed, 238 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index dfed22baebf8..48cd1d06761c 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -33,6 +33,7 @@ #include #include #include +#include #include "iavf_type.h" #include @@ -393,6 +394,8 @@ struct iavf_adapter { VIRTCHNL_VF_OFFLOAD_VLAN_V2) #define CRC_OFFLOAD_ALLOWED(_a) ((_a)->vf_res->vf_cap_flags & \ VIRTCHNL_VF_OFFLOAD_CRC) +#define TC_U32_SUPPORT(_a) ((_a)->vf_res->vf_cap_flags & \ + VIRTCHNL_VF_OFFLOAD_TC_U32) #define VLAN_V2_FILTERING_ALLOWED(_a) \ (VLAN_V2_ALLOWED((_a)) && \ ((_a)->vlan_v2_caps.filtering.filtering_support.outer || \ @@ -437,6 +440,7 @@ struct iavf_adapter { #define IAVF_MAX_FDIR_FILTERS 128 /* max allowed Flow Director filters */ u16 fdir_active_fltr; + u16 raw_fdir_active_fltr; struct list_head fdir_list_head; spinlock_t fdir_fltr_lock; /* protect the Flow Director filter list */ @@ -447,7 +451,28 @@ struct iavf_adapter { /* Must be called with fdir_fltr_lock lock held */ static inline bool iavf_fdir_max_reached(struct iavf_adapter *adapter) { - return adapter->fdir_active_fltr >= IAVF_MAX_FDIR_FILTERS; + return adapter->fdir_active_fltr + adapter->raw_fdir_active_fltr >= + IAVF_MAX_FDIR_FILTERS; +} + +static inline void +iavf_inc_fdir_active_fltr(struct iavf_adapter *adapter, + struct iavf_fdir_fltr *fltr) +{ + if (iavf_is_raw_fdir(fltr)) + adapter->raw_fdir_active_fltr++; + else + adapter->fdir_active_fltr++; +} + +static inline void +iavf_dec_fdir_active_fltr(struct iavf_adapter *adapter, + struct iavf_fdir_fltr *fltr) +{ + if (iavf_is_raw_fdir(fltr)) + adapter->raw_fdir_active_fltr--; + else + adapter->fdir_active_fltr--; } /* Ethtool Private Flags */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 7ab445eeee18..74a1e9fe1821 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -927,7 +927,7 @@ iavf_get_ethtool_fdir_entry(struct iavf_adapter *adapter, spin_lock_bh(&adapter->fdir_fltr_lock); - rule = iavf_find_fdir_fltr(adapter, fsp->location); + rule = iavf_find_fdir_fltr(adapter, false, fsp->location); if (!rule) { ret = -EINVAL; goto release_lock; @@ -1072,6 +1072,9 @@ iavf_get_fdir_fltr_ids(struct iavf_adapter *adapter, struct ethtool_rxnfc *cmd, spin_lock_bh(&adapter->fdir_fltr_lock); list_for_each_entry(fltr, &adapter->fdir_list_head, list) { + if (iavf_is_raw_fdir(fltr)) + continue; + if (cnt == cmd->rule_cnt) { val = -EMSGSIZE; goto release_lock; @@ -1263,7 +1266,7 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx return -EINVAL; spin_lock_bh(&adapter->fdir_fltr_lock); - if (iavf_find_fdir_fltr(adapter, fsp->location)) { + if (iavf_find_fdir_fltr(adapter, false, fsp->location)) { dev_err(&adapter->pdev->dev, "Failed to add Flow Director filter, it already exists\n"); spin_unlock_bh(&adapter->fdir_fltr_lock); return -EEXIST; @@ -1307,7 +1310,7 @@ static int iavf_del_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED)) return -EOPNOTSUPP; - return iavf_fdir_del_fltr(adapter, fsp->location); + return iavf_fdir_del_fltr(adapter, false, fsp->location); } /** diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.c b/drivers/net/ethernet/intel/iavf/iavf_fdir.c index 1e1daf71dfa0..a1b3b44cc14a 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_fdir.c +++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.c @@ -796,6 +796,9 @@ bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr * spin_lock_bh(&adapter->fdir_fltr_lock); list_for_each_entry(tmp, &adapter->fdir_list_head, list) { + if (iavf_is_raw_fdir(fltr)) + continue; + if (tmp->flow_type != fltr->flow_type) continue; @@ -817,18 +820,21 @@ bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr * /** * iavf_find_fdir_fltr - find FDIR filter * @adapter: pointer to the VF adapter structure - * @loc: location to find. + * @is_raw: filter type, is raw (tc u32) or not (ethtool) + * @data: data to ID the filter, type dependent * * Returns: pointer to Flow Director filter if found or NULL. Lock must be held. */ struct iavf_fdir_fltr *iavf_find_fdir_fltr(struct iavf_adapter *adapter, - u32 loc) + bool is_raw, u32 data) { struct iavf_fdir_fltr *rule; - list_for_each_entry(rule, &adapter->fdir_list_head, list) - if (rule->loc == loc) + list_for_each_entry(rule, &adapter->fdir_list_head, list) { + if ((is_raw && rule->cls_u32_handle == data) || + (!is_raw && rule->loc == data)) return rule; + } return NULL; } @@ -855,6 +861,9 @@ int iavf_fdir_add_fltr(struct iavf_adapter *adapter, } list_for_each_entry(rule, &adapter->fdir_list_head, list) { + if (iavf_is_raw_fdir(fltr)) + break; + if (rule->loc >= fltr->loc) break; parent = rule; @@ -864,7 +873,8 @@ int iavf_fdir_add_fltr(struct iavf_adapter *adapter, list_add(&fltr->list, &parent->list); else list_add(&fltr->list, &adapter->fdir_list_head); - adapter->fdir_active_fltr++; + + iavf_inc_fdir_active_fltr(adapter, fltr); if (adapter->link_up) fltr->state = IAVF_FDIR_FLTR_ADD_REQUEST; @@ -881,25 +891,26 @@ int iavf_fdir_add_fltr(struct iavf_adapter *adapter, /** * iavf_fdir_del_fltr - delete a flow director filter from the list * @adapter: pointer to the VF adapter structure - * @loc: location to delete. + * @is_raw: filter type, is raw (tc u32) or not (ethtool) + * @data: data to ID the filter, type dependent * * Return: 0 on success or negative errno on failure. */ -int iavf_fdir_del_fltr(struct iavf_adapter *adapter, u32 loc) +int iavf_fdir_del_fltr(struct iavf_adapter *adapter, bool is_raw, u32 data) { struct iavf_fdir_fltr *fltr = NULL; int err = 0; spin_lock_bh(&adapter->fdir_fltr_lock); - fltr = iavf_find_fdir_fltr(adapter, loc); + fltr = iavf_find_fdir_fltr(adapter, is_raw, data); if (fltr) { if (fltr->state == IAVF_FDIR_FLTR_ACTIVE) { fltr->state = IAVF_FDIR_FLTR_DEL_REQUEST; } else if (fltr->state == IAVF_FDIR_FLTR_INACTIVE) { list_del(&fltr->list); + iavf_dec_fdir_active_fltr(adapter, fltr); kfree(fltr); - adapter->fdir_active_fltr--; fltr = NULL; } else { err = -EBUSY; diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.h b/drivers/net/ethernet/intel/iavf/iavf_fdir.h index 5c85eb25fa2a..e84a5351162f 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_fdir.h +++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.h @@ -117,12 +117,18 @@ struct iavf_fdir_fltr { u32 flow_id; + u32 cls_u32_handle; /* for FDIR added via tc u32 */ u32 loc; /* Rule location inside the flow table */ u32 q_index; struct virtchnl_fdir_add vc_add_msg; }; +static inline bool iavf_is_raw_fdir(struct iavf_fdir_fltr *fltr) +{ + return !fltr->vc_add_msg.rule_cfg.proto_hdrs.count; +} + int iavf_validate_fdir_fltr_masks(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); int iavf_fill_fdir_add_msg(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); @@ -130,7 +136,7 @@ void iavf_print_fdir_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *f bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); int iavf_fdir_add_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); -int iavf_fdir_del_fltr(struct iavf_adapter *adapter, u32 loc); +int iavf_fdir_del_fltr(struct iavf_adapter *adapter, bool is_raw, u32 data); struct iavf_fdir_fltr *iavf_find_fdir_fltr(struct iavf_adapter *adapter, - u32 loc); + bool is_raw, u32 data); #endif /* _IAVF_FDIR_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index ff11bafb3b4f..f782402cd789 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -4013,7 +4013,7 @@ static int iavf_delete_clsflower(struct iavf_adapter *adapter, /** * iavf_setup_tc_cls_flower - flower classifier offloads - * @adapter: board private structure + * @adapter: pointer to iavf adapter structure * @cls_flower: pointer to flow_cls_offload struct with flow info */ static int iavf_setup_tc_cls_flower(struct iavf_adapter *adapter, @@ -4031,6 +4031,154 @@ static int iavf_setup_tc_cls_flower(struct iavf_adapter *adapter, } } +/** + * iavf_add_cls_u32 - Add U32 classifier offloads + * @adapter: pointer to iavf adapter structure + * @cls_u32: pointer to tc_cls_u32_offload struct with flow info + * + * Return: 0 on success or negative errno on failure. + */ +static int iavf_add_cls_u32(struct iavf_adapter *adapter, + struct tc_cls_u32_offload *cls_u32) +{ + struct netlink_ext_ack *extack = cls_u32->common.extack; + struct virtchnl_fdir_rule *rule_cfg; + struct virtchnl_filter_action *vact; + struct virtchnl_proto_hdrs *hdrs; + struct ethhdr *spec_h, *mask_h; + const struct tc_action *act; + struct iavf_fdir_fltr *fltr; + struct tcf_exts *exts; + unsigned int q_index; + int i, status = 0; + int off_base = 0; + + if (cls_u32->knode.link_handle) { + NL_SET_ERR_MSG_MOD(extack, "Linking not supported"); + return -EOPNOTSUPP; + } + + fltr = kzalloc(sizeof(*fltr), GFP_KERNEL); + if (!fltr) + return -ENOMEM; + + rule_cfg = &fltr->vc_add_msg.rule_cfg; + hdrs = &rule_cfg->proto_hdrs; + hdrs->count = 0; + + /* The parser lib at the PF expects the packet starting with MAC hdr */ + switch (ntohs(cls_u32->common.protocol)) { + case ETH_P_802_3: + break; + case ETH_P_IP: + spec_h = (struct ethhdr *)hdrs->raw.spec; + mask_h = (struct ethhdr *)hdrs->raw.mask; + spec_h->h_proto = htons(ETH_P_IP); + mask_h->h_proto = htons(0xFFFF); + off_base += ETH_HLEN; + break; + default: + NL_SET_ERR_MSG_MOD(extack, "Only 802_3 and ip filter protocols are supported"); + status = -EOPNOTSUPP; + goto free_alloc; + } + + for (i = 0; i < cls_u32->knode.sel->nkeys; i++) { + __be32 val, mask; + int off; + + off = off_base + cls_u32->knode.sel->keys[i].off; + val = cls_u32->knode.sel->keys[i].val; + mask = cls_u32->knode.sel->keys[i].mask; + + if (off >= sizeof(hdrs->raw.spec)) { + NL_SET_ERR_MSG_MOD(extack, "Input exceeds maximum allowed."); + status = -EINVAL; + goto free_alloc; + } + + memcpy(&hdrs->raw.spec[off], &val, sizeof(val)); + memcpy(&hdrs->raw.mask[off], &mask, sizeof(mask)); + hdrs->raw.pkt_len = off + sizeof(val); + } + + /* Only one action is allowed */ + rule_cfg->action_set.count = 1; + vact = &rule_cfg->action_set.actions[0]; + exts = cls_u32->knode.exts; + + tcf_exts_for_each_action(i, act, exts) { + /* FDIR queue */ + if (is_tcf_skbedit_rx_queue_mapping(act)) { + q_index = tcf_skbedit_rx_queue_mapping(act); + if (q_index >= adapter->num_active_queues) { + status = -EINVAL; + goto free_alloc; + } + + vact->type = VIRTCHNL_ACTION_QUEUE; + vact->act_conf.queue.index = q_index; + break; + } + + /* Drop */ + if (is_tcf_gact_shot(act)) { + vact->type = VIRTCHNL_ACTION_DROP; + break; + } + + /* Unsupported action */ + NL_SET_ERR_MSG_MOD(extack, "Unsupported action."); + status = -EOPNOTSUPP; + goto free_alloc; + } + + fltr->vc_add_msg.vsi_id = adapter->vsi.id; + fltr->cls_u32_handle = cls_u32->knode.handle; + return iavf_fdir_add_fltr(adapter, fltr); + +free_alloc: + kfree(fltr); + return status; +} + +/** + * iavf_del_cls_u32 - Delete U32 classifier offloads + * @adapter: pointer to iavf adapter structure + * @cls_u32: pointer to tc_cls_u32_offload struct with flow info + * + * Return: 0 on success or negative errno on failure. + */ +static int iavf_del_cls_u32(struct iavf_adapter *adapter, + struct tc_cls_u32_offload *cls_u32) +{ + return iavf_fdir_del_fltr(adapter, true, cls_u32->knode.handle); +} + +/** + * iavf_setup_tc_cls_u32 - U32 filter offloads + * @adapter: pointer to iavf adapter structure + * @cls_u32: pointer to tc_cls_u32_offload struct with flow info + * + * Return: 0 on success or negative errno on failure. + */ +static int iavf_setup_tc_cls_u32(struct iavf_adapter *adapter, + struct tc_cls_u32_offload *cls_u32) +{ + if (!TC_U32_SUPPORT(adapter) || !FDIR_FLTR_SUPPORT(adapter)) + return -EOPNOTSUPP; + + switch (cls_u32->command) { + case TC_CLSU32_NEW_KNODE: + case TC_CLSU32_REPLACE_KNODE: + return iavf_add_cls_u32(adapter, cls_u32); + case TC_CLSU32_DELETE_KNODE: + return iavf_del_cls_u32(adapter, cls_u32); + default: + return -EOPNOTSUPP; + } +} + /** * iavf_setup_tc_block_cb - block callback for tc * @type: type of offload @@ -4050,6 +4198,8 @@ static int iavf_setup_tc_block_cb(enum tc_setup_type type, void *type_data, switch (type) { case TC_SETUP_CLSFLOWER: return iavf_setup_tc_cls_flower(cb_priv, type_data); + case TC_SETUP_CLSU32: + return iavf_setup_tc_cls_u32(cb_priv, type_data); default: return -EOPNOTSUPP; } @@ -4332,8 +4482,8 @@ static void iavf_disable_fdir(struct iavf_adapter *adapter) fdir->state == IAVF_FDIR_FLTR_INACTIVE) { /* Delete filters not registered in PF */ list_del(&fdir->list); + iavf_dec_fdir_active_fltr(adapter, fdir); kfree(fdir); - adapter->fdir_active_fltr--; } else if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING || fdir->state == IAVF_FDIR_FLTR_DIS_REQUEST || fdir->state == IAVF_FDIR_FLTR_ACTIVE) { @@ -4843,9 +4993,11 @@ int iavf_process_config(struct iavf_adapter *adapter) /* get HW VLAN features that can be toggled */ hw_vlan_features = iavf_get_netdev_vlan_hw_features(adapter); - /* Enable cloud filter if ADQ is supported */ - if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) + /* Enable HW TC offload if ADQ or tc U32 is supported */ + if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ || + TC_U32_SUPPORT(adapter)) hw_features |= NETIF_F_HW_TC; + if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_USO) hw_features |= NETIF_F_GSO_UDP_L4; diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 1e543f6a7c30..7e810b65380c 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -142,6 +142,7 @@ int iavf_send_vf_config_msg(struct iavf_adapter *adapter) VIRTCHNL_VF_OFFLOAD_WB_ON_ITR | VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 | VIRTCHNL_VF_OFFLOAD_ENCAP | + VIRTCHNL_VF_OFFLOAD_TC_U32 | VIRTCHNL_VF_OFFLOAD_VLAN_V2 | VIRTCHNL_VF_OFFLOAD_CRC | VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM | @@ -1961,8 +1962,8 @@ static void iavf_activate_fdir_filters(struct iavf_adapter *adapter) * list on PF is already cleared after a reset */ list_del(&f->list); + iavf_dec_fdir_active_fltr(adapter, f); kfree(f); - adapter->fdir_active_fltr--; } } spin_unlock_bh(&adapter->fdir_fltr_lock); @@ -2135,8 +2136,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, dev_err(&adapter->pdev->dev, "%s\n", msg); list_del(&fdir->list); + iavf_dec_fdir_active_fltr(adapter, fdir); kfree(fdir); - adapter->fdir_active_fltr--; } } spin_unlock_bh(&adapter->fdir_fltr_lock); @@ -2451,8 +2452,12 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, list) { if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING) { if (add_fltr->status == VIRTCHNL_FDIR_SUCCESS) { - dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is added\n", - fdir->loc); + if (!iavf_is_raw_fdir(fdir)) + dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is added\n", + fdir->loc); + else + dev_info(&adapter->pdev->dev, "Flow Director filter (raw) for TC handle %x is added\n", + TC_U32_USERHTID(fdir->cls_u32_handle)); fdir->state = IAVF_FDIR_FLTR_ACTIVE; fdir->flow_id = add_fltr->flow_id; } else { @@ -2460,8 +2465,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, add_fltr->status); iavf_print_fdir_fltr(adapter, fdir); list_del(&fdir->list); + iavf_dec_fdir_active_fltr(adapter, fdir); kfree(fdir); - adapter->fdir_active_fltr--; } } } @@ -2479,11 +2484,15 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, if (del_fltr->status == VIRTCHNL_FDIR_SUCCESS || del_fltr->status == VIRTCHNL_FDIR_FAILURE_RULE_NONEXIST) { - dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is deleted\n", - fdir->loc); + if (!iavf_is_raw_fdir(fdir)) + dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is deleted\n", + fdir->loc); + else + dev_info(&adapter->pdev->dev, "Flow Director filter (raw) for TC handle %x is deleted\n", + TC_U32_USERHTID(fdir->cls_u32_handle)); list_del(&fdir->list); + iavf_dec_fdir_active_fltr(adapter, fdir); kfree(fdir); - adapter->fdir_active_fltr--; } else { fdir->state = IAVF_FDIR_FLTR_ACTIVE; dev_info(&adapter->pdev->dev, "Failed to delete Flow Director filter with status: %d\n", diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index 1c6ce0c4ed4e..59f62306b9cb 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -461,6 +461,10 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_FDIR_PF) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_FDIR_PF; + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_TC_U32 && + vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_FDIR_PF) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_TC_U32; + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2; diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 4f78a65e33dc..f41395264dca 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -247,6 +247,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource); /* used to negotiate communicating link speeds in Mbps */ #define VIRTCHNL_VF_CAP_ADV_LINK_SPEED BIT(7) #define VIRTCHNL_VF_OFFLOAD_CRC BIT(10) +#define VIRTCHNL_VF_OFFLOAD_TC_U32 BIT(11) #define VIRTCHNL_VF_OFFLOAD_VLAN_V2 BIT(15) #define VIRTCHNL_VF_OFFLOAD_VLAN BIT(16) #define VIRTCHNL_VF_OFFLOAD_RX_POLLING BIT(17) -- cgit v1.2.3 From 55f325958ccc41eaea43eb4546d4dc77c1b5ef8a Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 30 Jul 2024 01:16:04 -0400 Subject: bpf: switch maps to CLASS(fd, ...) Calling conventions for __bpf_map_get() would be more convenient if it left fpdut() on failure to callers. Makes for simpler logics in the callers. Among other things, the proof of memory safety no longer has to rely upon file->private_data never being ERR_PTR(...) for bpffs files. Original calling conventions made it impossible for the caller to tell whether __bpf_map_get() has returned ERR_PTR(-EINVAL) because it has found the file not be a bpf map one (in which case it would've done fdput()) or because it found that ERR_PTR(-EINVAL) in file->private_data of a bpf map file (in which case fdput() would _not_ have been done). Signed-off-by: Al Viro Reviewed-by: Christian Brauner Signed-off-by: Andrii Nakryiko --- include/linux/bpf.h | 11 ++++- kernel/bpf/map_in_map.c | 38 +++++----------- kernel/bpf/syscall.c | 118 ++++++++++++------------------------------------ kernel/bpf/verifier.c | 7 +-- net/core/sock_map.c | 23 +++------- 5 files changed, 58 insertions(+), 139 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b9425e410bcb..9f35df07e86d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2241,7 +2241,16 @@ void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu); struct bpf_map *bpf_map_get(u32 ufd); struct bpf_map *bpf_map_get_with_uref(u32 ufd); -struct bpf_map *__bpf_map_get(struct fd f); + +static inline struct bpf_map *__bpf_map_get(struct fd f) +{ + if (fd_empty(f)) + return ERR_PTR(-EBADF); + if (unlikely(fd_file(f)->f_op != &bpf_map_fops)) + return ERR_PTR(-EINVAL); + return fd_file(f)->private_data; +} + void bpf_map_inc(struct bpf_map *map); void bpf_map_inc_with_uref(struct bpf_map *map); struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref); diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c index b4f18c85d7bc..645bd30bc9a9 100644 --- a/kernel/bpf/map_in_map.c +++ b/kernel/bpf/map_in_map.c @@ -11,24 +11,18 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) { struct bpf_map *inner_map, *inner_map_meta; u32 inner_map_meta_size; - struct fd f; - int ret; + CLASS(fd, f)(inner_map_ufd); - f = fdget(inner_map_ufd); inner_map = __bpf_map_get(f); if (IS_ERR(inner_map)) return inner_map; /* Does not support >1 level map-in-map */ - if (inner_map->inner_map_meta) { - ret = -EINVAL; - goto put; - } + if (inner_map->inner_map_meta) + return ERR_PTR(-EINVAL); - if (!inner_map->ops->map_meta_equal) { - ret = -ENOTSUPP; - goto put; - } + if (!inner_map->ops->map_meta_equal) + return ERR_PTR(-ENOTSUPP); inner_map_meta_size = sizeof(*inner_map_meta); /* In some cases verifier needs to access beyond just base map. */ @@ -36,10 +30,8 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) inner_map_meta_size = sizeof(struct bpf_array); inner_map_meta = kzalloc(inner_map_meta_size, GFP_USER); - if (!inner_map_meta) { - ret = -ENOMEM; - goto put; - } + if (!inner_map_meta) + return ERR_PTR(-ENOMEM); inner_map_meta->map_type = inner_map->map_type; inner_map_meta->key_size = inner_map->key_size; @@ -53,8 +45,9 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) * invalid/empty/valid, but ERR_PTR in case of errors. During * equality NULL or IS_ERR is equivalent. */ - ret = PTR_ERR(inner_map_meta->record); - goto free; + struct bpf_map *ret = ERR_CAST(inner_map_meta->record); + kfree(inner_map_meta); + return ret; } /* Note: We must use the same BTF, as we also used btf_record_dup above * which relies on BTF being same for both maps, as some members like @@ -77,14 +70,7 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) inner_array_meta->elem_size = inner_array->elem_size; inner_map_meta->bypass_spec_v1 = inner_map->bypass_spec_v1; } - - fdput(f); return inner_map_meta; -free: - kfree(inner_map_meta); -put: - fdput(f); - return ERR_PTR(ret); } void bpf_map_meta_free(struct bpf_map *map_meta) @@ -110,9 +96,8 @@ void *bpf_map_fd_get_ptr(struct bpf_map *map, int ufd) { struct bpf_map *inner_map, *inner_map_meta; - struct fd f; + CLASS(fd, f)(ufd); - f = fdget(ufd); inner_map = __bpf_map_get(f); if (IS_ERR(inner_map)) return inner_map; @@ -123,7 +108,6 @@ void *bpf_map_fd_get_ptr(struct bpf_map *map, else inner_map = ERR_PTR(-EINVAL); - fdput(f); return inner_map; } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 4909e3f23065..ab0d94f41c48 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1418,21 +1418,6 @@ put_token: return err; } -/* if error is returned, fd is released. - * On success caller should complete fd access with matching fdput() - */ -struct bpf_map *__bpf_map_get(struct fd f) -{ - if (!fd_file(f)) - return ERR_PTR(-EBADF); - if (fd_file(f)->f_op != &bpf_map_fops) { - fdput(f); - return ERR_PTR(-EINVAL); - } - - return fd_file(f)->private_data; -} - void bpf_map_inc(struct bpf_map *map) { atomic64_inc(&map->refcnt); @@ -1448,15 +1433,11 @@ EXPORT_SYMBOL_GPL(bpf_map_inc_with_uref); struct bpf_map *bpf_map_get(u32 ufd) { - struct fd f = fdget(ufd); - struct bpf_map *map; - - map = __bpf_map_get(f); - if (IS_ERR(map)) - return map; + CLASS(fd, f)(ufd); + struct bpf_map *map = __bpf_map_get(f); - bpf_map_inc(map); - fdput(f); + if (!IS_ERR(map)) + bpf_map_inc(map); return map; } @@ -1464,15 +1445,11 @@ EXPORT_SYMBOL(bpf_map_get); struct bpf_map *bpf_map_get_with_uref(u32 ufd) { - struct fd f = fdget(ufd); - struct bpf_map *map; - - map = __bpf_map_get(f); - if (IS_ERR(map)) - return map; + CLASS(fd, f)(ufd); + struct bpf_map *map = __bpf_map_get(f); - bpf_map_inc_with_uref(map); - fdput(f); + if (!IS_ERR(map)) + bpf_map_inc_with_uref(map); return map; } @@ -1537,11 +1514,9 @@ static int map_lookup_elem(union bpf_attr *attr) { void __user *ukey = u64_to_user_ptr(attr->key); void __user *uvalue = u64_to_user_ptr(attr->value); - int ufd = attr->map_fd; struct bpf_map *map; void *key, *value; u32 value_size; - struct fd f; int err; if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM)) @@ -1550,26 +1525,20 @@ static int map_lookup_elem(union bpf_attr *attr) if (attr->flags & ~BPF_F_LOCK) return -EINVAL; - f = fdget(ufd); + CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { - err = -EPERM; - goto err_put; - } + if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) + return -EPERM; if ((attr->flags & BPF_F_LOCK) && - !btf_record_has_field(map->record, BPF_SPIN_LOCK)) { - err = -EINVAL; - goto err_put; - } + !btf_record_has_field(map->record, BPF_SPIN_LOCK)) + return -EINVAL; key = __bpf_copy_key(ukey, map->key_size); - if (IS_ERR(key)) { - err = PTR_ERR(key); - goto err_put; - } + if (IS_ERR(key)) + return PTR_ERR(key); value_size = bpf_map_value_size(map); @@ -1600,8 +1569,6 @@ free_value: kvfree(value); free_key: kvfree(key); -err_put: - fdput(f); return err; } @@ -1612,17 +1579,15 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr) { bpfptr_t ukey = make_bpfptr(attr->key, uattr.is_kernel); bpfptr_t uvalue = make_bpfptr(attr->value, uattr.is_kernel); - int ufd = attr->map_fd; struct bpf_map *map; void *key, *value; u32 value_size; - struct fd f; int err; if (CHECK_ATTR(BPF_MAP_UPDATE_ELEM)) return -EINVAL; - f = fdget(ufd); + CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); @@ -1660,7 +1625,6 @@ free_key: kvfree(key); err_put: bpf_map_write_active_dec(map); - fdput(f); return err; } @@ -1669,16 +1633,14 @@ err_put: static int map_delete_elem(union bpf_attr *attr, bpfptr_t uattr) { bpfptr_t ukey = make_bpfptr(attr->key, uattr.is_kernel); - int ufd = attr->map_fd; struct bpf_map *map; - struct fd f; void *key; int err; if (CHECK_ATTR(BPF_MAP_DELETE_ELEM)) return -EINVAL; - f = fdget(ufd); + CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); @@ -1715,7 +1677,6 @@ out: kvfree(key); err_put: bpf_map_write_active_dec(map); - fdput(f); return err; } @@ -1726,30 +1687,24 @@ static int map_get_next_key(union bpf_attr *attr) { void __user *ukey = u64_to_user_ptr(attr->key); void __user *unext_key = u64_to_user_ptr(attr->next_key); - int ufd = attr->map_fd; struct bpf_map *map; void *key, *next_key; - struct fd f; int err; if (CHECK_ATTR(BPF_MAP_GET_NEXT_KEY)) return -EINVAL; - f = fdget(ufd); + CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { - err = -EPERM; - goto err_put; - } + if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) + return -EPERM; if (ukey) { key = __bpf_copy_key(ukey, map->key_size); - if (IS_ERR(key)) { - err = PTR_ERR(key); - goto err_put; - } + if (IS_ERR(key)) + return PTR_ERR(key); } else { key = NULL; } @@ -1781,8 +1736,6 @@ free_next_key: kvfree(next_key); free_key: kvfree(key); -err_put: - fdput(f); return err; } @@ -2011,11 +1964,9 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr) { void __user *ukey = u64_to_user_ptr(attr->key); void __user *uvalue = u64_to_user_ptr(attr->value); - int ufd = attr->map_fd; struct bpf_map *map; void *key, *value; u32 value_size; - struct fd f; int err; if (CHECK_ATTR(BPF_MAP_LOOKUP_AND_DELETE_ELEM)) @@ -2024,7 +1975,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr) if (attr->flags & ~BPF_F_LOCK) return -EINVAL; - f = fdget(ufd); + CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); @@ -2094,7 +2045,6 @@ free_key: kvfree(key); err_put: bpf_map_write_active_dec(map); - fdput(f); return err; } @@ -2102,27 +2052,22 @@ err_put: static int map_freeze(const union bpf_attr *attr) { - int err = 0, ufd = attr->map_fd; + int err = 0; struct bpf_map *map; - struct fd f; if (CHECK_ATTR(BPF_MAP_FREEZE)) return -EINVAL; - f = fdget(ufd); + CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS || !IS_ERR_OR_NULL(map->record)) { - fdput(f); + if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS || !IS_ERR_OR_NULL(map->record)) return -ENOTSUPP; - } - if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { - fdput(f); + if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) return -EPERM; - } mutex_lock(&map->freeze_mutex); if (bpf_map_write_active(map)) { @@ -2137,7 +2082,6 @@ static int map_freeze(const union bpf_attr *attr) WRITE_ONCE(map->frozen, true); err_put: mutex_unlock(&map->freeze_mutex); - fdput(f); return err; } @@ -5175,14 +5119,13 @@ static int bpf_map_do_batch(const union bpf_attr *attr, cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH; bool has_write = cmd != BPF_MAP_LOOKUP_BATCH; struct bpf_map *map; - int err, ufd; - struct fd f; + int err; if (CHECK_ATTR(BPF_MAP_BATCH)) return -EINVAL; - ufd = attr->batch.map_fd; - f = fdget(ufd); + CLASS(fd, f)(attr->batch.map_fd); + map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); @@ -5210,7 +5153,6 @@ err_put: maybe_wait_bpf_programs(map); bpf_map_write_active_dec(map); } - fdput(f); return err; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 14e4ef687a59..e3932f8ce10a 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -18872,7 +18872,7 @@ static bool bpf_map_is_cgroup_storage(struct bpf_map *map) */ static int add_used_map_from_fd(struct bpf_verifier_env *env, int fd, bool *reused) { - struct fd f = fdget(fd); + CLASS(fd, f)(fd); struct bpf_map *map; int i; @@ -18886,7 +18886,6 @@ static int add_used_map_from_fd(struct bpf_verifier_env *env, int fd, bool *reus for (i = 0; i < env->used_map_cnt; i++) { if (env->used_maps[i] == map) { *reused = true; - fdput(f); return i; } } @@ -18894,7 +18893,6 @@ static int add_used_map_from_fd(struct bpf_verifier_env *env, int fd, bool *reus if (env->used_map_cnt >= MAX_USED_MAPS) { verbose(env, "The total number of maps per program has reached the limit of %u\n", MAX_USED_MAPS); - fdput(f); return -E2BIG; } @@ -18911,10 +18909,7 @@ static int add_used_map_from_fd(struct bpf_verifier_env *env, int fd, bool *reus *reused = false; env->used_maps[env->used_map_cnt++] = map; - fdput(f); - return env->used_map_cnt - 1; - } /* find and rewrite pseudo imm in ld_imm64 instructions: diff --git a/net/core/sock_map.c b/net/core/sock_map.c index d3dbb92153f2..0f5f80f44d52 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -67,46 +67,39 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr) int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog) { - u32 ufd = attr->target_fd; struct bpf_map *map; - struct fd f; int ret; if (attr->attach_flags || attr->replace_bpf_fd) return -EINVAL; - f = fdget(ufd); + CLASS(fd, f)(attr->target_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); mutex_lock(&sockmap_mutex); ret = sock_map_prog_update(map, prog, NULL, NULL, attr->attach_type); mutex_unlock(&sockmap_mutex); - fdput(f); return ret; } int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) { - u32 ufd = attr->target_fd; struct bpf_prog *prog; struct bpf_map *map; - struct fd f; int ret; if (attr->attach_flags || attr->replace_bpf_fd) return -EINVAL; - f = fdget(ufd); + CLASS(fd, f)(attr->target_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); prog = bpf_prog_get(attr->attach_bpf_fd); - if (IS_ERR(prog)) { - ret = PTR_ERR(prog); - goto put_map; - } + if (IS_ERR(prog)) + return PTR_ERR(prog); if (prog->type != ptype) { ret = -EINVAL; @@ -118,8 +111,6 @@ int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) mutex_unlock(&sockmap_mutex); put_prog: bpf_prog_put(prog); -put_map: - fdput(f); return ret; } @@ -1550,18 +1541,17 @@ int sock_map_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); - u32 prog_cnt = 0, flags = 0, ufd = attr->target_fd; + u32 prog_cnt = 0, flags = 0; struct bpf_prog **pprog; struct bpf_prog *prog; struct bpf_map *map; - struct fd f; u32 id = 0; int ret; if (attr->query.query_flags) return -EINVAL; - f = fdget(ufd); + CLASS(fd, f)(attr->target_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); @@ -1593,7 +1583,6 @@ end: copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt))) ret = -EFAULT; - fdput(f); return ret; } -- cgit v1.2.3 From 7945b741d1fc071a621366c512a060ea08848955 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 3 Jul 2024 19:47:47 -0700 Subject: rcu-tasks: Remove RCU Tasks Rude asynchronous APIs The call_rcu_tasks_rude() and rcu_barrier_tasks_rude() APIs are currently unused. This commit therefore removes their definitions and boot-time self-tests. Signed-off-by: Paul E. McKenney Cc: Peter Zijlstra Signed-off-by: Neeraj Upadhyay --- include/linux/rcupdate.h | 2 -- kernel/rcu/tasks.h | 55 +++++++++++++++--------------------------------- 2 files changed, 17 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 13f6f00aecf9..31e679c7110e 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -37,7 +37,6 @@ /* Exported common interfaces */ void call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier_tasks(void); -void rcu_barrier_tasks_rude(void); void synchronize_rcu(void); struct rcu_gp_oldstate; @@ -202,7 +201,6 @@ do { \ } while (0) # ifdef CONFIG_TASKS_RUDE_RCU -void call_rcu_tasks_rude(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks_rude(void); # endif diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index ba3440a45b6d..4bc038bcc016 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -396,7 +396,7 @@ static void rcu_barrier_tasks_generic_cb(struct rcu_head *rhp) // Wait for all in-flight callbacks for the specified RCU Tasks flavor. // Operates in a manner similar to rcu_barrier(). -static void rcu_barrier_tasks_generic(struct rcu_tasks *rtp) +static void __maybe_unused rcu_barrier_tasks_generic(struct rcu_tasks *rtp) { int cpu; unsigned long flags; @@ -1244,13 +1244,12 @@ void exit_tasks_rcu_finish(void) { exit_tasks_rcu_finish_trace(current); } //////////////////////////////////////////////////////////////////////// // -// "Rude" variant of Tasks RCU, inspired by Steve Rostedt's trick of -// passing an empty function to schedule_on_each_cpu(). This approach -// provides an asynchronous call_rcu_tasks_rude() API and batching of -// concurrent calls to the synchronous synchronize_rcu_tasks_rude() API. -// This invokes schedule_on_each_cpu() in order to send IPIs far and wide -// and induces otherwise unnecessary context switches on all online CPUs, -// whether idle or not. +// "Rude" variant of Tasks RCU, inspired by Steve Rostedt's +// trick of passing an empty function to schedule_on_each_cpu(). +// This approach provides batching of concurrent calls to the synchronous +// synchronize_rcu_tasks_rude() API. This invokes schedule_on_each_cpu() +// in order to send IPIs far and wide and induces otherwise unnecessary +// context switches on all online CPUs, whether idle or not. // // Callback handling is provided by the rcu_tasks_kthread() function. // @@ -1268,11 +1267,11 @@ static void rcu_tasks_rude_wait_gp(struct rcu_tasks *rtp) schedule_on_each_cpu(rcu_tasks_be_rude); } -void call_rcu_tasks_rude(struct rcu_head *rhp, rcu_callback_t func); +static void call_rcu_tasks_rude(struct rcu_head *rhp, rcu_callback_t func); DEFINE_RCU_TASKS(rcu_tasks_rude, rcu_tasks_rude_wait_gp, call_rcu_tasks_rude, "RCU Tasks Rude"); -/** +/* * call_rcu_tasks_rude() - Queue a callback rude task-based grace period * @rhp: structure to be used for queueing the RCU updates. * @func: actual callback function to be invoked after the grace period @@ -1289,12 +1288,14 @@ DEFINE_RCU_TASKS(rcu_tasks_rude, rcu_tasks_rude_wait_gp, call_rcu_tasks_rude, * * See the description of call_rcu() for more detailed information on * memory ordering guarantees. + * + * This is no longer exported, and is instead reserved for use by + * synchronize_rcu_tasks_rude(). */ -void call_rcu_tasks_rude(struct rcu_head *rhp, rcu_callback_t func) +static void call_rcu_tasks_rude(struct rcu_head *rhp, rcu_callback_t func) { call_rcu_tasks_generic(rhp, func, &rcu_tasks_rude); } -EXPORT_SYMBOL_GPL(call_rcu_tasks_rude); /** * synchronize_rcu_tasks_rude - wait for a rude rcu-tasks grace period @@ -1320,26 +1321,9 @@ void synchronize_rcu_tasks_rude(void) } EXPORT_SYMBOL_GPL(synchronize_rcu_tasks_rude); -/** - * rcu_barrier_tasks_rude - Wait for in-flight call_rcu_tasks_rude() callbacks. - * - * Although the current implementation is guaranteed to wait, it is not - * obligated to, for example, if there are no pending callbacks. - */ -void rcu_barrier_tasks_rude(void) -{ - rcu_barrier_tasks_generic(&rcu_tasks_rude); -} -EXPORT_SYMBOL_GPL(rcu_barrier_tasks_rude); - -int rcu_tasks_rude_lazy_ms = -1; -module_param(rcu_tasks_rude_lazy_ms, int, 0444); - static int __init rcu_spawn_tasks_rude_kthread(void) { rcu_tasks_rude.gp_sleep = HZ / 10; - if (rcu_tasks_rude_lazy_ms >= 0) - rcu_tasks_rude.lazy_jiffies = msecs_to_jiffies(rcu_tasks_rude_lazy_ms); rcu_spawn_tasks_kthread_generic(&rcu_tasks_rude); return 0; } @@ -2069,11 +2053,6 @@ static struct rcu_tasks_test_desc tests[] = { /* If not defined, the test is skipped. */ .notrun = IS_ENABLED(CONFIG_TASKS_RCU), }, - { - .name = "call_rcu_tasks_rude()", - /* If not defined, the test is skipped. */ - .notrun = IS_ENABLED(CONFIG_TASKS_RUDE_RCU), - }, { .name = "call_rcu_tasks_trace()", /* If not defined, the test is skipped. */ @@ -2081,6 +2060,7 @@ static struct rcu_tasks_test_desc tests[] = { } }; +#if defined(CONFIG_TASKS_RCU) || defined(CONFIG_TASKS_TRACE_RCU) static void test_rcu_tasks_callback(struct rcu_head *rhp) { struct rcu_tasks_test_desc *rttd = @@ -2090,6 +2070,7 @@ static void test_rcu_tasks_callback(struct rcu_head *rhp) rttd->notrun = false; } +#endif // #if defined(CONFIG_TASKS_RCU) || defined(CONFIG_TASKS_TRACE_RCU) static void rcu_tasks_initiate_self_tests(void) { @@ -2102,16 +2083,14 @@ static void rcu_tasks_initiate_self_tests(void) #ifdef CONFIG_TASKS_RUDE_RCU pr_info("Running RCU Tasks Rude wait API self tests\n"); - tests[1].runstart = jiffies; synchronize_rcu_tasks_rude(); - call_rcu_tasks_rude(&tests[1].rh, test_rcu_tasks_callback); #endif #ifdef CONFIG_TASKS_TRACE_RCU pr_info("Running RCU Tasks Trace wait API self tests\n"); - tests[2].runstart = jiffies; + tests[1].runstart = jiffies; synchronize_rcu_tasks_trace(); - call_rcu_tasks_trace(&tests[2].rh, test_rcu_tasks_callback); + call_rcu_tasks_trace(&tests[1].rh, test_rcu_tasks_callback); #endif } -- cgit v1.2.3 From fe91cf39db0939ac8d523b5a1c31840f7cbe205c Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 1 Aug 2024 17:34:25 -0700 Subject: rcu/tasks: Add detailed grace-period and barrier diagnostics This commit adds rcu_tasks_torture_stats_print(), rcu_tasks_trace_torture_stats_print(), and rcu_tasks_rude_torture_stats_print() functions that provide detailed diagnostics on grace-period, callback, and barrier state. Signed-off-by: "Paul E. McKenney" Signed-off-by: Neeraj Upadhyay --- include/linux/rcupdate.h | 3 +++ kernel/rcu/tasks.h | 66 ++++++++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 67 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 31e679c7110e..17463e95b6ef 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -164,6 +164,7 @@ static inline void rcu_nocb_flush_deferred_wakeup(void) { } } while (0) void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks(void); +void rcu_tasks_torture_stats_print(char *tt, char *tf); # else # define rcu_tasks_classic_qs(t, preempt) do { } while (0) # define call_rcu_tasks call_rcu @@ -190,6 +191,7 @@ void rcu_tasks_trace_qs_blkd(struct task_struct *t); rcu_tasks_trace_qs_blkd(t); \ } \ } while (0) +void rcu_tasks_trace_torture_stats_print(char *tt, char *tf); # else # define rcu_tasks_trace_qs(t) do { } while (0) # endif @@ -202,6 +204,7 @@ do { \ # ifdef CONFIG_TASKS_RUDE_RCU void synchronize_rcu_tasks_rude(void); +void rcu_tasks_rude_torture_stats_print(char *tt, char *tf); # endif #define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t, false) diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index d44abcd656d6..5f6d80ce1e47 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -714,9 +714,7 @@ static void __init rcu_tasks_bootup_oddness(void) #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ } -#endif /* #ifndef CONFIG_TINY_RCU */ -#ifndef CONFIG_TINY_RCU /* Dump out rcutorture-relevant state common to all RCU-tasks flavors. */ static void show_rcu_tasks_generic_gp_kthread(struct rcu_tasks *rtp, char *s) { @@ -750,6 +748,52 @@ static void show_rcu_tasks_generic_gp_kthread(struct rcu_tasks *rtp, char *s) rtp->lazy_jiffies, s); } + +/* Dump out more rcutorture-relevant state common to all RCU-tasks flavors. */ +static void rcu_tasks_torture_stats_print_generic(struct rcu_tasks *rtp, char *tt, + char *tf, char *tst) +{ + cpumask_var_t cm; + int cpu; + bool gotcb = false; + unsigned long j = jiffies; + + pr_alert("%s%s Tasks%s RCU g%ld gp_start %lu gp_jiffies %lu gp_state %d (%s).\n", + tt, tf, tst, data_race(rtp->tasks_gp_seq), + j - data_race(rtp->gp_start), j - data_race(rtp->gp_jiffies), + data_race(rtp->gp_state), tasks_gp_state_getname(rtp)); + pr_alert("\tEnqueue shift %d limit %d Dequeue limit %d gpseq %lu.\n", + data_race(rtp->percpu_enqueue_shift), + data_race(rtp->percpu_enqueue_lim), + data_race(rtp->percpu_dequeue_lim), + data_race(rtp->percpu_dequeue_gpseq)); + (void)zalloc_cpumask_var(&cm, GFP_KERNEL); + pr_alert("\tCallback counts:"); + for_each_possible_cpu(cpu) { + long n; + struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, cpu); + + if (cpumask_available(cm) && !rcu_barrier_cb_is_done(&rtpcp->barrier_q_head)) + cpumask_set_cpu(cpu, cm); + n = rcu_segcblist_n_cbs(&rtpcp->cblist); + if (!n) + continue; + pr_cont(" %d:%ld", cpu, n); + gotcb = true; + } + if (gotcb) + pr_cont(".\n"); + else + pr_cont(" (none).\n"); + pr_alert("\tBarrier seq %lu count %d holdout CPUs ", + data_race(rtp->barrier_q_seq), atomic_read(&rtp->barrier_q_count)); + if (cpumask_available(cm) && !cpumask_empty(cm)) + pr_cont(" %*pbl.\n", cpumask_pr_args(cm)); + else + pr_cont("(none).\n"); + free_cpumask_var(cm); +} + #endif // #ifndef CONFIG_TINY_RCU static void exit_tasks_rcu_finish_trace(struct task_struct *t); @@ -1201,6 +1245,12 @@ void show_rcu_tasks_classic_gp_kthread(void) show_rcu_tasks_generic_gp_kthread(&rcu_tasks, ""); } EXPORT_SYMBOL_GPL(show_rcu_tasks_classic_gp_kthread); + +void rcu_tasks_torture_stats_print(char *tt, char *tf) +{ + rcu_tasks_torture_stats_print_generic(&rcu_tasks, tt, tf, ""); +} +EXPORT_SYMBOL_GPL(rcu_tasks_torture_stats_print); #endif // !defined(CONFIG_TINY_RCU) struct task_struct *get_rcu_tasks_gp_kthread(void) @@ -1361,6 +1411,12 @@ void show_rcu_tasks_rude_gp_kthread(void) show_rcu_tasks_generic_gp_kthread(&rcu_tasks_rude, ""); } EXPORT_SYMBOL_GPL(show_rcu_tasks_rude_gp_kthread); + +void rcu_tasks_rude_torture_stats_print(char *tt, char *tf) +{ + rcu_tasks_torture_stats_print_generic(&rcu_tasks_rude, tt, tf, ""); +} +EXPORT_SYMBOL_GPL(rcu_tasks_rude_torture_stats_print); #endif // !defined(CONFIG_TINY_RCU) struct task_struct *get_rcu_tasks_rude_gp_kthread(void) @@ -2038,6 +2094,12 @@ void show_rcu_tasks_trace_gp_kthread(void) show_rcu_tasks_generic_gp_kthread(&rcu_tasks_trace, buf); } EXPORT_SYMBOL_GPL(show_rcu_tasks_trace_gp_kthread); + +void rcu_tasks_trace_torture_stats_print(char *tt, char *tf) +{ + rcu_tasks_torture_stats_print_generic(&rcu_tasks_trace, tt, tf, ""); +} +EXPORT_SYMBOL_GPL(rcu_tasks_trace_torture_stats_print); #endif // !defined(CONFIG_TINY_RCU) struct task_struct *get_rcu_tasks_trace_gp_kthread(void) -- cgit v1.2.3 From 66155de93bcf4f2967e602a4b3bf7ebe58f34b11 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 9 Aug 2024 12:02:58 -0700 Subject: KVM: x86: Disallow read-only memslots for SEV-ES and SEV-SNP (and TDX) Disallow read-only memslots for SEV-{ES,SNP} VM types, as KVM can't directly emulate instructions for ES/SNP, and instead the guest must explicitly request emulation. Unless the guest explicitly requests emulation without accessing memory, ES/SNP relies on KVM creating an MMIO SPTE, with the subsequent #NPF being reflected into the guest as a #VC. But for read-only memslots, KVM deliberately doesn't create MMIO SPTEs, because except for ES/SNP, doing so requires setting reserved bits in the SPTE, i.e. the SPTE can't be readable while also generating a #VC on writes. Because KVM never creates MMIO SPTEs and jumps directly to emulation, the guest never gets a #VC. And since KVM simply resumes the guest if ES/SNP guests trigger emulation, KVM effectively puts the vCPU into an infinite #NPF loop if the vCPU attempts to write read-only memory. Disallow read-only memory for all VMs with protected state, i.e. for upcoming TDX VMs as well as ES/SNP VMs. For TDX, it's actually possible to support read-only memory, as TDX uses EPT Violation #VE to reflect the fault into the guest, e.g. KVM could configure read-only SPTEs with RX protections and SUPPRESS_VE=0. But there is no strong use case for supporting read-only memslots on TDX, e.g. the main historical usage is to emulate option ROMs, but TDX disallows executing from shared memory. And if someone comes along with a legitimate, strong use case, the restriction can always be lifted for TDX. Don't bother trying to retroactively apply the restriction to SEV-ES VMs that are created as type KVM_X86_DEFAULT_VM. Read-only memslots can't possibly work for SEV-ES, i.e. disallowing such memslots is really just means reporting an error to userspace instead of silently hanging vCPUs. Trying to deal with the ordering between KVM_SEV_INIT and memslot creation isn't worth the marginal benefit it would provide userspace. Fixes: 26c44aa9e076 ("KVM: SEV: define VM types for SEV and SEV-ES") Fixes: 1dfe571c12cf ("KVM: SEV: Add initial SEV-SNP support") Cc: Peter Gonda Cc: Michael Roth Cc: Vishal Annapurve Cc: Ackerly Tng Signed-off-by: Sean Christopherson Message-ID: <20240809190319.1710470-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 2 ++ include/linux/kvm_host.h | 7 +++++++ virt/kvm/kvm_main.c | 5 ++--- 3 files changed, 11 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 94e7b5a4fafe..4a68cb3eba78 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -2192,6 +2192,8 @@ void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level, #define kvm_arch_has_private_mem(kvm) false #endif +#define kvm_arch_has_readonly_mem(kvm) (!(kvm)->arch.has_protected_state) + static inline u16 kvm_read_ldt(void) { u16 ldt; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 79a6b1a63027..b23c6d48392f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -715,6 +715,13 @@ static inline bool kvm_arch_has_private_mem(struct kvm *kvm) } #endif +#ifndef kvm_arch_has_readonly_mem +static inline bool kvm_arch_has_readonly_mem(struct kvm *kvm) +{ + return IS_ENABLED(CONFIG_HAVE_KVM_READONLY_MEM); +} +#endif + struct kvm_memslots { u64 generation; atomic_long_t last_used_slot; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 92901656a0d4..cb2b78e92910 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1578,15 +1578,14 @@ static int check_memory_region_flags(struct kvm *kvm, if (mem->flags & KVM_MEM_GUEST_MEMFD) valid_flags &= ~KVM_MEM_LOG_DIRTY_PAGES; -#ifdef CONFIG_HAVE_KVM_READONLY_MEM /* * GUEST_MEMFD is incompatible with read-only memslots, as writes to * read-only memslots have emulated MMIO, not page fault, semantics, * and KVM doesn't allow emulated MMIO for private memory. */ - if (!(mem->flags & KVM_MEM_GUEST_MEMFD)) + if (kvm_arch_has_readonly_mem(kvm) && + !(mem->flags & KVM_MEM_GUEST_MEMFD)) valid_flags |= KVM_MEM_READONLY; -#endif if (mem->flags & ~valid_flags) return -EINVAL; -- cgit v1.2.3 From 44f65d900698278a8451988abe0d5ca37fd46882 Mon Sep 17 00:00:00 2001 From: Jeff Xu Date: Tue, 6 Aug 2024 21:49:27 +0000 Subject: binfmt_elf: mseal address zero MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In load_elf_binary as part of the execve(), when the current task’s personality has MMAP_PAGE_ZERO set, the kernel allocates one page at address 0. According to the comment: /* Why this, you ask??? Well SVr4 maps page 0 as read-only, and some applications "depend" upon this behavior. Since we do not have the power to recompile these, we emulate the SVr4 behavior. Sigh. */ At one point, Linus suggested removing this [1]. Code search in debian didn't see much use of MMAP_PAGE_ZERO [2], it exists in util and test (rr). Sealing this is probably safe, the comment doesn't say the app ever wanting to change the mapping to rwx. Sealing also ensures that never happens. If there is a complaint, we can make this configurable. Link: https://lore.kernel.org/lkml/CAHk-=whVa=nm_GW=NVfPHqcxDbWt4JjjK1YWb0cLjO4ZSGyiDA@mail.gmail.com/ [1] Link: https://codesearch.debian.net/search?q=MMAP_PAGE_ZERO&literal=1&perpkg=1&page=1 [2] Signed-off-by: Jeff Xu Link: https://lore.kernel.org/r/20240806214931.2198172-2-jeffxu@google.com Signed-off-by: Kees Cook --- fs/binfmt_elf.c | 5 +++++ include/linux/mm.h | 10 ++++++++++ mm/mseal.c | 2 +- 3 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index bf9bfd1a0007..c3aa700aeb3c 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1314,6 +1314,11 @@ out_free_interp: emulate the SVr4 behavior. Sigh. */ error = vm_mmap(NULL, 0, PAGE_SIZE, PROT_READ | PROT_EXEC, MAP_FIXED | MAP_PRIVATE, 0); + + retval = do_mseal(0, PAGE_SIZE, 0); + if (retval) + pr_warn_ratelimited("pid=%d, couldn't seal address 0, ret=%d.\n", + task_pid_nr(current), retval); } regs = current_pt_regs(); diff --git a/include/linux/mm.h b/include/linux/mm.h index c4b238a20b76..a178c15812eb 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -4201,4 +4201,14 @@ void vma_pgtable_walk_end(struct vm_area_struct *vma); int reserve_mem_find_by_name(const char *name, phys_addr_t *start, phys_addr_t *size); +#ifdef CONFIG_64BIT +int do_mseal(unsigned long start, size_t len_in, unsigned long flags); +#else +static inline int do_mseal(unsigned long start, size_t len_in, unsigned long flags) +{ + /* noop on 32 bit */ + return 0; +} +#endif + #endif /* _LINUX_MM_H */ diff --git a/mm/mseal.c b/mm/mseal.c index bf783bba8ed0..7a40a84569c8 100644 --- a/mm/mseal.c +++ b/mm/mseal.c @@ -248,7 +248,7 @@ static int apply_mm_seal(unsigned long start, unsigned long end) * * unseal() is not supported. */ -static int do_mseal(unsigned long start, size_t len_in, unsigned long flags) +int do_mseal(unsigned long start, size_t len_in, unsigned long flags) { size_t len; int ret = 0; -- cgit v1.2.3 From 71833e79a42178d8a50b5081c98c78ace9325628 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Wed, 14 Aug 2024 13:16:49 +0100 Subject: i2c: Use IS_REACHABLE() for substituting empty ACPI functions Replace IS_ENABLED() with IS_REACHABLE() to substitute empty stubs for: i2c_acpi_get_i2c_resource() i2c_acpi_client_count() i2c_acpi_find_bus_speed() i2c_acpi_new_device_by_fwnode() i2c_adapter *i2c_acpi_find_adapter_by_handle() i2c_acpi_waive_d0_probe() commit f17c06c6608a ("i2c: Fix conditional for substituting empty ACPI functions") partially fixed this conditional to depend on CONFIG_I2C, but used IS_ENABLED(), which is wrong since CONFIG_I2C is tristate. CONFIG_ACPI is boolean but let's also change it to use IS_REACHABLE() to future-proof it against becoming tristate. Somehow despite testing various combinations of CONFIG_I2C and CONFIG_ACPI we missed the combination CONFIG_I2C=m, CONFIG_ACPI=y. Signed-off-by: Richard Fitzgerald Fixes: f17c06c6608a ("i2c: Fix conditional for substituting empty ACPI functions") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202408141333.gYnaitcV-lkp@intel.com/ Reviewed-by: Takashi Iwai Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 7eedd0c662da..377def497298 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -1066,7 +1066,7 @@ static inline int of_i2c_get_board_info(struct device *dev, struct acpi_resource; struct acpi_resource_i2c_serialbus; -#if IS_ENABLED(CONFIG_ACPI) && IS_ENABLED(CONFIG_I2C) +#if IS_REACHABLE(CONFIG_ACPI) && IS_REACHABLE(CONFIG_I2C) bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares, struct acpi_resource_i2c_serialbus **i2c); int i2c_acpi_client_count(struct acpi_device *adev); -- cgit v1.2.3 From ac9d45544cd571decca395715d0b0a3b617d02f4 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 1 Jul 2024 13:33:58 -0700 Subject: locking/csd_lock: Provide an indication of ongoing CSD-lock stall If a CSD-lock stall goes on long enough, it will cause an RCU CPU stall warning. This additional warning provides much additional console-log traffic and little additional information. Therefore, provide a new csd_lock_is_stuck() function that returns true if there is an ongoing CSD-lock stall. This function will be used by the RCU CPU stall warnings to provide a one-line indication of the stall when this function returns true. [ neeraj.upadhyay: Apply Rik van Riel feedback. ] [ neeraj.upadhyay: Apply kernel test robot feedback. ] Signed-off-by: Paul E. McKenney Cc: Imran Khan Cc: Ingo Molnar Cc: Leonardo Bras Cc: "Peter Zijlstra (Intel)" Cc: Rik van Riel Signed-off-by: Neeraj Upadhyay --- include/linux/smp.h | 6 ++++++ kernel/smp.c | 16 ++++++++++++++++ lib/Kconfig.debug | 1 + 3 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/smp.h b/include/linux/smp.h index fcd61dfe2af3..3871bd32018f 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -294,4 +294,10 @@ int smpcfd_prepare_cpu(unsigned int cpu); int smpcfd_dead_cpu(unsigned int cpu); int smpcfd_dying_cpu(unsigned int cpu); +#ifdef CONFIG_CSD_LOCK_WAIT_DEBUG +bool csd_lock_is_stuck(void); +#else +static inline bool csd_lock_is_stuck(void) { return false; } +#endif + #endif /* __LINUX_SMP_H */ diff --git a/kernel/smp.c b/kernel/smp.c index e87953729230..202cda4d2a55 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -208,6 +208,19 @@ static int csd_lock_wait_getcpu(call_single_data_t *csd) return -1; } +static atomic_t n_csd_lock_stuck; + +/** + * csd_lock_is_stuck - Has a CSD-lock acquisition been stuck too long? + * + * Returns @true if a CSD-lock acquisition is stuck and has been stuck + * long enough for a "non-responsive CSD lock" message to be printed. + */ +bool csd_lock_is_stuck(void) +{ + return !!atomic_read(&n_csd_lock_stuck); +} + /* * Complain if too much time spent waiting. Note that only * the CSD_TYPE_SYNC/ASYNC types provide the destination CPU, @@ -229,6 +242,7 @@ static bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, in cpu = csd_lock_wait_getcpu(csd); pr_alert("csd: CSD lock (#%d) got unstuck on CPU#%02d, CPU#%02d released the lock.\n", *bug_id, raw_smp_processor_id(), cpu); + atomic_dec(&n_csd_lock_stuck); return true; } @@ -252,6 +266,8 @@ static bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, in pr_alert("csd: %s non-responsive CSD lock (#%d) on CPU#%d, waiting %lld ns for CPU#%02d %pS(%ps).\n", firsttime ? "Detected" : "Continued", *bug_id, raw_smp_processor_id(), (s64)ts_delta, cpu, csd->func, csd->info); + if (firsttime) + atomic_inc(&n_csd_lock_stuck); /* * If the CSD lock is still stuck after 5 minutes, it is unlikely * to become unstuck. Use a signed comparison to avoid triggering diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index a30c03a66172..4e5f61cba8e4 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1614,6 +1614,7 @@ config SCF_TORTURE_TEST config CSD_LOCK_WAIT_DEBUG bool "Debugging for csd_lock_wait(), called from smp_call_function*()" depends on DEBUG_KERNEL + depends on SMP depends on 64BIT default n help -- cgit v1.2.3 From 924fc22c282edbf93869b150d9e1b47e0b10485e Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Wed, 31 Jul 2024 09:44:57 +0200 Subject: firmware: qcom: qseecom: remove unused functions qseecom_scm_dev(), qseecom_dma_alloc() and qseecom_dma_free() are no longer used following the conversion to using tzmem. Remove them. Fixes: 6612103ec35a ("firmware: qcom: qseecom: convert to using the TZ allocator") Reviewed-by: Andrew Halaney Signed-off-by: Bartosz Golaszewski Link: https://lore.kernel.org/r/20240731-tzmem-efivars-fix-v2-2-f0e84071ec07@linaro.org Signed-off-by: Bjorn Andersson --- include/linux/firmware/qcom/qcom_qseecom.h | 45 ------------------------------ 1 file changed, 45 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firmware/qcom/qcom_qseecom.h b/include/linux/firmware/qcom/qcom_qseecom.h index 1dc5b3b50aa9..3387897bf368 100644 --- a/include/linux/firmware/qcom/qcom_qseecom.h +++ b/include/linux/firmware/qcom/qcom_qseecom.h @@ -25,51 +25,6 @@ struct qseecom_client { u32 app_id; }; -/** - * qseecom_scm_dev() - Get the SCM device associated with the QSEECOM client. - * @client: The QSEECOM client device. - * - * Returns the SCM device under which the provided QSEECOM client device - * operates. This function is intended to be used for DMA allocations. - */ -static inline struct device *qseecom_scm_dev(struct qseecom_client *client) -{ - return client->aux_dev.dev.parent->parent; -} - -/** - * qseecom_dma_alloc() - Allocate DMA memory for a QSEECOM client. - * @client: The QSEECOM client to allocate the memory for. - * @size: The number of bytes to allocate. - * @dma_handle: Pointer to where the DMA address should be stored. - * @gfp: Allocation flags. - * - * Wrapper function for dma_alloc_coherent(), allocating DMA memory usable for - * TZ/QSEECOM communication. Refer to dma_alloc_coherent() for details. - */ -static inline void *qseecom_dma_alloc(struct qseecom_client *client, size_t size, - dma_addr_t *dma_handle, gfp_t gfp) -{ - return dma_alloc_coherent(qseecom_scm_dev(client), size, dma_handle, gfp); -} - -/** - * dma_free_coherent() - Free QSEECOM DMA memory. - * @client: The QSEECOM client for which the memory has been allocated. - * @size: The number of bytes allocated. - * @cpu_addr: Virtual memory address to free. - * @dma_handle: DMA memory address to free. - * - * Wrapper function for dma_free_coherent(), freeing memory previously - * allocated with qseecom_dma_alloc(). Refer to dma_free_coherent() for - * details. - */ -static inline void qseecom_dma_free(struct qseecom_client *client, size_t size, - void *cpu_addr, dma_addr_t dma_handle) -{ - return dma_free_coherent(qseecom_scm_dev(client), size, cpu_addr, dma_handle); -} - /** * qcom_qseecom_app_send() - Send to and receive data from a given QSEE app. * @client: The QSEECOM client associated with the target app. -- cgit v1.2.3 From fda70207135b60dd1a7c8f16cc036bb1cc344490 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Tue, 16 Apr 2024 11:01:23 +0200 Subject: context_tracking, rcu: Rename rcu_dynticks_curr_cpu_in_eqs() into rcu_is_watching_curr_cpu() The context_tracking.state RCU_DYNTICKS subvariable has been renamed to RCU_WATCHING, reflect that change in the related helpers. Note that "watching" is the opposite of "in EQS", so the negation is lifted out of the helper and into the callsites. Signed-off-by: Valentin Schneider Reviewed-by: Frederic Weisbecker Signed-off-by: Neeraj Upadhyay --- include/linux/context_tracking.h | 12 ++++++++---- kernel/context_tracking.c | 6 +++--- kernel/rcu/tree.c | 6 +++--- 3 files changed, 14 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index a6c36780cc3b..d53092ffa9db 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -113,13 +113,17 @@ extern void ct_idle_enter(void); extern void ct_idle_exit(void); /* - * Is the current CPU in an extended quiescent state? + * Is RCU watching the current CPU (IOW, it is not in an extended quiescent state)? + * + * Note that this returns the actual boolean data (watching / not watching), + * whereas ct_rcu_watching() returns the RCU_WATCHING subvariable of + * context_tracking.state. * * No ordering, as we are sampling CPU-local information. */ -static __always_inline bool rcu_dynticks_curr_cpu_in_eqs(void) +static __always_inline bool rcu_is_watching_curr_cpu(void) { - return !(raw_atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_RCU_WATCHING); + return raw_atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_RCU_WATCHING; } /* @@ -140,7 +144,7 @@ static __always_inline bool warn_rcu_enter(void) * lots of the actual reporting also relies on RCU. */ preempt_disable_notrace(); - if (rcu_dynticks_curr_cpu_in_eqs()) { + if (!rcu_is_watching_curr_cpu()) { ret = true; ct_state_inc(CT_RCU_WATCHING); } diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 00c8f128885a..31c6d0c1b79d 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -212,7 +212,7 @@ void noinstr ct_nmi_exit(void) * to us!) */ WARN_ON_ONCE(ct_nmi_nesting() <= 0); - WARN_ON_ONCE(rcu_dynticks_curr_cpu_in_eqs()); + WARN_ON_ONCE(!rcu_is_watching_curr_cpu()); /* * If the nesting level is not 1, the CPU wasn't RCU-idle, so @@ -271,7 +271,7 @@ void noinstr ct_nmi_enter(void) * to be in the outermost NMI handler that interrupted an RCU-idle * period (observation due to Andy Lutomirski). */ - if (rcu_dynticks_curr_cpu_in_eqs()) { + if (!rcu_is_watching_curr_cpu()) { if (!in_nmi()) rcu_task_enter(); @@ -281,7 +281,7 @@ void noinstr ct_nmi_enter(void) // ... but is watching here. instrumentation_begin(); - // instrumentation for the noinstr rcu_dynticks_curr_cpu_in_eqs() + // instrumentation for the noinstr rcu_is_watching_curr_cpu() instrument_atomic_read(&ct->state, sizeof(ct->state)); // instrumentation for the noinstr ct_kernel_enter_state() instrument_atomic_write(&ct->state, sizeof(ct->state)); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 4778c873f4ac..68eca7d3fdd1 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -601,7 +601,7 @@ void rcu_irq_exit_check_preempt(void) RCU_LOCKDEP_WARN(ct_nmi_nesting() != CT_NESTING_IRQ_NONIDLE, "Bad RCU nmi_nesting counter\n"); - RCU_LOCKDEP_WARN(rcu_dynticks_curr_cpu_in_eqs(), + RCU_LOCKDEP_WARN(!rcu_is_watching_curr_cpu(), "RCU in extended quiescent state!"); } #endif /* #ifdef CONFIG_PROVE_RCU */ @@ -641,7 +641,7 @@ void __rcu_irq_enter_check_tick(void) if (in_nmi()) return; - RCU_LOCKDEP_WARN(rcu_dynticks_curr_cpu_in_eqs(), + RCU_LOCKDEP_WARN(!rcu_is_watching_curr_cpu(), "Illegal rcu_irq_enter_check_tick() from extended quiescent state"); if (!tick_nohz_full_cpu(rdp->cpu) || @@ -723,7 +723,7 @@ notrace bool rcu_is_watching(void) bool ret; preempt_disable_notrace(); - ret = !rcu_dynticks_curr_cpu_in_eqs(); + ret = rcu_is_watching_curr_cpu(); preempt_enable_notrace(); return ret; } -- cgit v1.2.3 From 32a9f26e5e266f0116cc8536e5e4544523ddd334 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Mon, 29 Apr 2024 16:43:36 +0200 Subject: rcu: Rename rcu_momentary_dyntick_idle() into rcu_momentary_eqs() The context_tracking.state RCU_DYNTICKS subvariable has been renamed to RCU_WATCHING, replace "dyntick_idle" into "eqs" to drop the dyntick reference. Signed-off-by: Valentin Schneider Reviewed-by: Frederic Weisbecker Signed-off-by: Neeraj Upadhyay --- include/linux/rcutiny.h | 2 +- include/linux/rcutree.h | 2 +- kernel/rcu/rcutorture.c | 4 ++-- kernel/rcu/tree.c | 4 ++-- kernel/rcu/tree_nocb.h | 2 +- kernel/rcu/tree_plugin.h | 6 +++--- kernel/stop_machine.c | 2 +- kernel/trace/trace_osnoise.c | 4 ++-- 8 files changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index d9ac7b136aea..cf2b5a188f78 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -158,7 +158,7 @@ void rcu_scheduler_starting(void); static inline void rcu_end_inkernel_boot(void) { } static inline bool rcu_inkernel_boot_has_ended(void) { return true; } static inline bool rcu_is_watching(void) { return true; } -static inline void rcu_momentary_dyntick_idle(void) { } +static inline void rcu_momentary_eqs(void) { } static inline void kfree_rcu_scheduler_running(void) { } static inline bool rcu_gp_might_be_stalled(void) { return false; } diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 254244202ea9..7dbde2b6f714 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -37,7 +37,7 @@ void synchronize_rcu_expedited(void); void kvfree_call_rcu(struct rcu_head *head, void *ptr); void rcu_barrier(void); -void rcu_momentary_dyntick_idle(void); +void rcu_momentary_eqs(void); void kfree_rcu_scheduler_running(void); bool rcu_gp_might_be_stalled(void); diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 08bf7c669dd3..ef757c3e84a2 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -2680,7 +2680,7 @@ static unsigned long rcu_torture_fwd_prog_cbfree(struct rcu_fwd *rfp) rcu_torture_fwd_prog_cond_resched(freed); if (tick_nohz_full_enabled()) { local_irq_save(flags); - rcu_momentary_dyntick_idle(); + rcu_momentary_eqs(); local_irq_restore(flags); } } @@ -2830,7 +2830,7 @@ static void rcu_torture_fwd_prog_cr(struct rcu_fwd *rfp) rcu_torture_fwd_prog_cond_resched(n_launders + n_max_cbs); if (tick_nohz_full_enabled()) { local_irq_save(flags); - rcu_momentary_dyntick_idle(); + rcu_momentary_eqs(); local_irq_restore(flags); } } diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index b53b354417ae..e0f6fc272906 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -367,7 +367,7 @@ bool rcu_watching_zero_in_eqs(int cpu, int *vp) * * The caller must have disabled interrupts and must not be idle. */ -notrace void rcu_momentary_dyntick_idle(void) +notrace void rcu_momentary_eqs(void) { int seq; @@ -377,7 +377,7 @@ notrace void rcu_momentary_dyntick_idle(void) WARN_ON_ONCE(!(seq & CT_RCU_WATCHING)); rcu_preempt_deferred_qs(current); } -EXPORT_SYMBOL_GPL(rcu_momentary_dyntick_idle); +EXPORT_SYMBOL_GPL(rcu_momentary_eqs); /** * rcu_is_cpu_rrupt_from_idle - see if 'interrupted' from idle diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h index 3ce30841119a..e629646ac6f5 100644 --- a/kernel/rcu/tree_nocb.h +++ b/kernel/rcu/tree_nocb.h @@ -917,7 +917,7 @@ static void nocb_cb_wait(struct rcu_data *rdp) WARN_ON_ONCE(!rcu_rdp_is_offloaded(rdp)); local_irq_save(flags); - rcu_momentary_dyntick_idle(); + rcu_momentary_eqs(); local_irq_restore(flags); /* * Disable BH to provide the expected environment. Also, when diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index c569da65b421..354fbf2e411c 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -869,7 +869,7 @@ static void rcu_qs(void) /* * Register an urgently needed quiescent state. If there is an - * emergency, invoke rcu_momentary_dyntick_idle() to do a heavy-weight + * emergency, invoke rcu_momentary_eqs() to do a heavy-weight * dyntick-idle quiescent state visible to other CPUs, which will in * some cases serve for expedited as well as normal grace periods. * Either way, register a lightweight quiescent state. @@ -889,7 +889,7 @@ void rcu_all_qs(void) this_cpu_write(rcu_data.rcu_urgent_qs, false); if (unlikely(raw_cpu_read(rcu_data.rcu_need_heavy_qs))) { local_irq_save(flags); - rcu_momentary_dyntick_idle(); + rcu_momentary_eqs(); local_irq_restore(flags); } rcu_qs(); @@ -909,7 +909,7 @@ void rcu_note_context_switch(bool preempt) goto out; this_cpu_write(rcu_data.rcu_urgent_qs, false); if (unlikely(raw_cpu_read(rcu_data.rcu_need_heavy_qs))) - rcu_momentary_dyntick_idle(); + rcu_momentary_eqs(); out: rcu_tasks_qs(current, preempt); trace_rcu_utilization(TPS("End context switch")); diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index cedb17ba158a..da821ce258ea 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -251,7 +251,7 @@ static int multi_cpu_stop(void *data) */ touch_nmi_watchdog(); } - rcu_momentary_dyntick_idle(); + rcu_momentary_eqs(); } while (curstate != MULTI_STOP_EXIT); local_irq_restore(flags); diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index 66a871553d4a..ad86b1ba2e43 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -1535,7 +1535,7 @@ static int run_osnoise(void) * This will eventually cause unwarranted noise as PREEMPT_RCU * will force preemption as the means of ending the current * grace period. We avoid this problem by calling - * rcu_momentary_dyntick_idle(), which performs a zero duration + * rcu_momentary_eqs(), which performs a zero duration * EQS allowing PREEMPT_RCU to end the current grace period. * This call shouldn't be wrapped inside an RCU critical * section. @@ -1547,7 +1547,7 @@ static int run_osnoise(void) if (!disable_irq) local_irq_disable(); - rcu_momentary_dyntick_idle(); + rcu_momentary_eqs(); if (!disable_irq) local_irq_enable(); -- cgit v1.2.3 From 4040b1139904b3f72b56862fc9a8d3e9abb69ffb Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Mon, 17 Jun 2024 08:51:14 -0700 Subject: context_tracking: Tag context_tracking_enabled_this_cpu() __always_inline Force context_tracking_enabled_this_cpu() to be inlined so that invoking it from guest_context_enter_irqoff(), which KVM uses in non-instrumentable code, doesn't unexpectedly leave a noinstr section. vmlinux.o: warning: objtool: vmx_vcpu_enter_exit+0x1c7: call to context_tracking_enabled_this_cpu() leaves .noinstr.text section vmlinux.o: warning: objtool: svm_vcpu_enter_exit+0x83: call to context_tracking_enabled_this_cpu() leaves .noinstr.text section Note, the CONFIG_CONTEXT_TRACKING_USER=n stub is already __always_inline. Signed-off-by: Sean Christopherson Signed-off-by: Paul E. McKenney Signed-off-by: Neeraj Upadhyay --- include/linux/context_tracking_state.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index 0dbda59c9f37..7b8433d5a8ef 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -113,7 +113,7 @@ static __always_inline bool context_tracking_enabled_cpu(int cpu) return context_tracking_enabled() && per_cpu(context_tracking.active, cpu); } -static inline bool context_tracking_enabled_this_cpu(void) +static __always_inline bool context_tracking_enabled_this_cpu(void) { return context_tracking_enabled() && __this_cpu_read(context_tracking.active); } -- cgit v1.2.3 From a98ae7f045b29de4f48b191d5aeb4e803183d759 Mon Sep 17 00:00:00 2001 From: Michal Wajdeczko Date: Thu, 25 Jul 2024 12:18:40 +0200 Subject: lib/string_choices: Add str_up_down() helper Add str_up_down() helper to return "up" or "down" string literal. Signed-off-by: Michal Wajdeczko Link: https://lore.kernel.org/r/20240725101841.574-1-michal.wajdeczko@intel.com Signed-off-by: Kees Cook --- include/linux/string_choices.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/string_choices.h b/include/linux/string_choices.h index d9ebe20229f8..bcde3c9cff81 100644 --- a/include/linux/string_choices.h +++ b/include/linux/string_choices.h @@ -42,6 +42,11 @@ static inline const char *str_yes_no(bool v) return v ? "yes" : "no"; } +static inline const char *str_up_down(bool v) +{ + return v ? "up" : "down"; +} + /** * str_plural - Return the simple pluralization based on English counts * @num: Number used for deciding pluralization -- cgit v1.2.3 From f5c1ca3a15fdb867d2b535003f74e0b975eff116 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 12 Aug 2024 11:29:40 -0700 Subject: string_choices: Add wrapper for str_down_up() The string choice functions which are not clearly true/false synonyms also have inverted wrappers. Add this for str_down_up() as well. Suggested-by: Andy Shevchenko Link: https://lore.kernel.org/r/20240812182939.work.424-kees@kernel.org Reviewed-by: Andy Shevchenko Signed-off-by: Kees Cook --- include/linux/string_choices.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/string_choices.h b/include/linux/string_choices.h index bcde3c9cff81..1320bcdcb89c 100644 --- a/include/linux/string_choices.h +++ b/include/linux/string_choices.h @@ -46,6 +46,7 @@ static inline const char *str_up_down(bool v) { return v ? "up" : "down"; } +#define str_down_up(v) str_up_down(!(v)) /** * str_plural - Return the simple pluralization based on English counts -- cgit v1.2.3 From 0cb70ee4a6ee6b0a4b0e0f70a64a094c6fe05944 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Wed, 14 Aug 2024 13:22:25 +0800 Subject: virtio: rename virtio_config_enabled to virtio_config_core_enabled Following patch will allow the config interrupt to be disabled by a specific driver via another boolean. So this patch renames virtio_config_enabled and relevant helpers to virtio_config_core_enabled. Cc: Venkat Venkatsubra Cc: Gia-Khanh Nguyen Acked-by: Michael S. Tsirkin Signed-off-by: Jason Wang Link: https://patch.msgid.link/20240814052228.4654-2-jasowang@redhat.com Signed-off-by: Jakub Kicinski --- drivers/virtio/virtio.c | 22 +++++++++++----------- include/linux/virtio.h | 4 ++-- 2 files changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index bc1f962e483b..6b692b0fa578 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -127,7 +127,7 @@ static void __virtio_config_changed(struct virtio_device *dev) { struct virtio_driver *drv = drv_to_virtio(dev->dev.driver); - if (!dev->config_enabled) + if (!dev->config_core_enabled) dev->config_change_pending = true; else if (drv && drv->config_changed) drv->config_changed(dev); @@ -143,17 +143,17 @@ void virtio_config_changed(struct virtio_device *dev) } EXPORT_SYMBOL_GPL(virtio_config_changed); -static void virtio_config_disable(struct virtio_device *dev) +static void virtio_config_core_disable(struct virtio_device *dev) { spin_lock_irq(&dev->config_lock); - dev->config_enabled = false; + dev->config_core_enabled = false; spin_unlock_irq(&dev->config_lock); } -static void virtio_config_enable(struct virtio_device *dev) +static void virtio_config_core_enable(struct virtio_device *dev) { spin_lock_irq(&dev->config_lock); - dev->config_enabled = true; + dev->config_core_enabled = true; if (dev->config_change_pending) __virtio_config_changed(dev); dev->config_change_pending = false; @@ -316,7 +316,7 @@ static int virtio_dev_probe(struct device *_d) if (drv->scan) drv->scan(dev); - virtio_config_enable(dev); + virtio_config_core_enable(dev); return 0; @@ -331,7 +331,7 @@ static void virtio_dev_remove(struct device *_d) struct virtio_device *dev = dev_to_virtio(_d); struct virtio_driver *drv = drv_to_virtio(dev->dev.driver); - virtio_config_disable(dev); + virtio_config_core_disable(dev); drv->remove(dev); @@ -443,7 +443,7 @@ int register_virtio_device(struct virtio_device *dev) goto out_ida_remove; spin_lock_init(&dev->config_lock); - dev->config_enabled = false; + dev->config_core_enabled = false; dev->config_change_pending = false; INIT_LIST_HEAD(&dev->vqs); @@ -500,14 +500,14 @@ int virtio_device_freeze(struct virtio_device *dev) struct virtio_driver *drv = drv_to_virtio(dev->dev.driver); int ret; - virtio_config_disable(dev); + virtio_config_core_disable(dev); dev->failed = dev->config->get_status(dev) & VIRTIO_CONFIG_S_FAILED; if (drv && drv->freeze) { ret = drv->freeze(dev); if (ret) { - virtio_config_enable(dev); + virtio_config_core_enable(dev); return ret; } } @@ -557,7 +557,7 @@ int virtio_device_restore(struct virtio_device *dev) if (!(dev->config->get_status(dev) & VIRTIO_CONFIG_S_DRIVER_OK)) virtio_device_ready(dev); - virtio_config_enable(dev); + virtio_config_core_enable(dev); return 0; diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 4b16844c6bc2..de6d3cc176d9 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -118,7 +118,7 @@ struct virtio_admin_cmd { * struct virtio_device - representation of a device using virtio * @index: unique position on the virtio bus * @failed: saved value for VIRTIO_CONFIG_S_FAILED bit (for restore) - * @config_enabled: configuration change reporting enabled + * @config_core_enabled: configuration change reporting enabled by core * @config_change_pending: configuration change reported while disabled * @config_lock: protects configuration change reporting * @vqs_list_lock: protects @vqs. @@ -135,7 +135,7 @@ struct virtio_admin_cmd { struct virtio_device { int index; bool failed; - bool config_enabled; + bool config_core_enabled; bool config_change_pending; spinlock_t config_lock; spinlock_t vqs_list_lock; -- cgit v1.2.3 From 224de6f886f8184fd448700a6d78f216694de948 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Wed, 14 Aug 2024 13:22:26 +0800 Subject: virtio: allow driver to disable the configure change notification Sometime, it would be useful to disable the configure change notification from the driver. So this patch allows this by introducing a variable config_change_driver_disabled and only allow the configure change notification callback to be triggered when it is allowed by both the virtio core and the driver. It is set to false by default to hold the current semantic so we don't need to change any drivers. The first user for this would be virtio-net. Cc: Venkat Venkatsubra Cc: Gia-Khanh Nguyen Acked-by: Michael S. Tsirkin Signed-off-by: Jason Wang Link: https://patch.msgid.link/20240814052228.4654-3-jasowang@redhat.com Signed-off-by: Jakub Kicinski --- drivers/virtio/virtio.c | 39 ++++++++++++++++++++++++++++++++++++--- include/linux/virtio.h | 7 +++++++ 2 files changed, 43 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 6b692b0fa578..b9095751e43b 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -127,10 +127,12 @@ static void __virtio_config_changed(struct virtio_device *dev) { struct virtio_driver *drv = drv_to_virtio(dev->dev.driver); - if (!dev->config_core_enabled) + if (!dev->config_core_enabled || dev->config_driver_disabled) dev->config_change_pending = true; - else if (drv && drv->config_changed) + else if (drv && drv->config_changed) { drv->config_changed(dev); + dev->config_change_pending = false; + } } void virtio_config_changed(struct virtio_device *dev) @@ -143,6 +145,38 @@ void virtio_config_changed(struct virtio_device *dev) } EXPORT_SYMBOL_GPL(virtio_config_changed); +/** + * virtio_config_driver_disable - disable config change reporting by drivers + * @dev: the device to reset + * + * This is only allowed to be called by a driver and disabling can't + * be nested. + */ +void virtio_config_driver_disable(struct virtio_device *dev) +{ + spin_lock_irq(&dev->config_lock); + dev->config_driver_disabled = true; + spin_unlock_irq(&dev->config_lock); +} +EXPORT_SYMBOL_GPL(virtio_config_driver_disable); + +/** + * virtio_config_driver_enable - enable config change reporting by drivers + * @dev: the device to reset + * + * This is only allowed to be called by a driver and enabling can't + * be nested. + */ +void virtio_config_driver_enable(struct virtio_device *dev) +{ + spin_lock_irq(&dev->config_lock); + dev->config_driver_disabled = false; + if (dev->config_change_pending) + __virtio_config_changed(dev); + spin_unlock_irq(&dev->config_lock); +} +EXPORT_SYMBOL_GPL(virtio_config_driver_enable); + static void virtio_config_core_disable(struct virtio_device *dev) { spin_lock_irq(&dev->config_lock); @@ -156,7 +190,6 @@ static void virtio_config_core_enable(struct virtio_device *dev) dev->config_core_enabled = true; if (dev->config_change_pending) __virtio_config_changed(dev); - dev->config_change_pending = false; spin_unlock_irq(&dev->config_lock); } diff --git a/include/linux/virtio.h b/include/linux/virtio.h index de6d3cc176d9..306137a15d07 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -119,6 +119,8 @@ struct virtio_admin_cmd { * @index: unique position on the virtio bus * @failed: saved value for VIRTIO_CONFIG_S_FAILED bit (for restore) * @config_core_enabled: configuration change reporting enabled by core + * @config_driver_disabled: configuration change reporting disabled by + * a driver * @config_change_pending: configuration change reported while disabled * @config_lock: protects configuration change reporting * @vqs_list_lock: protects @vqs. @@ -136,6 +138,7 @@ struct virtio_device { int index; bool failed; bool config_core_enabled; + bool config_driver_disabled; bool config_change_pending; spinlock_t config_lock; spinlock_t vqs_list_lock; @@ -166,6 +169,10 @@ void __virtqueue_break(struct virtqueue *_vq); void __virtqueue_unbreak(struct virtqueue *_vq); void virtio_config_changed(struct virtio_device *dev); + +void virtio_config_driver_disable(struct virtio_device *dev); +void virtio_config_driver_enable(struct virtio_device *dev); + #ifdef CONFIG_PM_SLEEP int virtio_device_freeze(struct virtio_device *dev); int virtio_device_restore(struct virtio_device *dev); -- cgit v1.2.3 From 5f75cfbd6bb02295ddaed48adf667b6c828ce07b Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 1 Aug 2024 22:47:48 +0200 Subject: mm/hugetlb: fix hugetlb vs. core-mm PT locking We recently made GUP's common page table walking code to also walk hugetlb VMAs without most hugetlb special-casing, preparing for the future of having less hugetlb-specific page table walking code in the codebase. Turns out that we missed one page table locking detail: page table locking for hugetlb folios that are not mapped using a single PMD/PUD. Assume we have hugetlb folio that spans multiple PTEs (e.g., 64 KiB hugetlb folios on arm64 with 4 KiB base page size). GUP, as it walks the page tables, will perform a pte_offset_map_lock() to grab the PTE table lock. However, hugetlb that concurrently modifies these page tables would actually grab the mm->page_table_lock: with USE_SPLIT_PTE_PTLOCKS, the locks would differ. Something similar can happen right now with hugetlb folios that span multiple PMDs when USE_SPLIT_PMD_PTLOCKS. This issue can be reproduced [1], for example triggering: [ 3105.936100] ------------[ cut here ]------------ [ 3105.939323] WARNING: CPU: 31 PID: 2732 at mm/gup.c:142 try_grab_folio+0x11c/0x188 [ 3105.944634] Modules linked in: [...] [ 3105.974841] CPU: 31 PID: 2732 Comm: reproducer Not tainted 6.10.0-64.eln141.aarch64 #1 [ 3105.980406] Hardware name: QEMU KVM Virtual Machine, BIOS edk2-20240524-4.fc40 05/24/2024 [ 3105.986185] pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 3105.991108] pc : try_grab_folio+0x11c/0x188 [ 3105.994013] lr : follow_page_pte+0xd8/0x430 [ 3105.996986] sp : ffff80008eafb8f0 [ 3105.999346] x29: ffff80008eafb900 x28: ffffffe8d481f380 x27: 00f80001207cff43 [ 3106.004414] x26: 0000000000000001 x25: 0000000000000000 x24: ffff80008eafba48 [ 3106.009520] x23: 0000ffff9372f000 x22: ffff7a54459e2000 x21: ffff7a546c1aa978 [ 3106.014529] x20: ffffffe8d481f3c0 x19: 0000000000610041 x18: 0000000000000001 [ 3106.019506] x17: 0000000000000001 x16: ffffffffffffffff x15: 0000000000000000 [ 3106.024494] x14: ffffb85477fdfe08 x13: 0000ffff9372ffff x12: 0000000000000000 [ 3106.029469] x11: 1fffef4a88a96be1 x10: ffff7a54454b5f0c x9 : ffffb854771b12f0 [ 3106.034324] x8 : 0008000000000000 x7 : ffff7a546c1aa980 x6 : 0008000000000080 [ 3106.038902] x5 : 00000000001207cf x4 : 0000ffff9372f000 x3 : ffffffe8d481f000 [ 3106.043420] x2 : 0000000000610041 x1 : 0000000000000001 x0 : 0000000000000000 [ 3106.047957] Call trace: [ 3106.049522] try_grab_folio+0x11c/0x188 [ 3106.051996] follow_pmd_mask.constprop.0.isra.0+0x150/0x2e0 [ 3106.055527] follow_page_mask+0x1a0/0x2b8 [ 3106.058118] __get_user_pages+0xf0/0x348 [ 3106.060647] faultin_page_range+0xb0/0x360 [ 3106.063651] do_madvise+0x340/0x598 Let's make huge_pte_lockptr() effectively use the same PT locks as any core-mm page table walker would. Add ptep_lockptr() to obtain the PTE page table lock using a pte pointer -- unfortunately we cannot convert pte_lockptr() because virt_to_page() doesn't work with kmap'ed page tables we can have with CONFIG_HIGHPTE. Handle CONFIG_PGTABLE_LEVELS correctly by checking in reverse order, such that when e.g., CONFIG_PGTABLE_LEVELS==2 with PGDIR_SIZE==P4D_SIZE==PUD_SIZE==PMD_SIZE will work as expected. Document why that works. There is one ugly case: powerpc 8xx, whereby we have an 8 MiB hugetlb folio being mapped using two PTE page tables. While hugetlb wants to take the PMD table lock, core-mm would grab the PTE table lock of one of both PTE page tables. In such corner cases, we have to make sure that both locks match, which is (fortunately!) currently guaranteed for 8xx as it does not support SMP and consequently doesn't use split PT locks. [1] https://lore.kernel.org/all/1bbfcc7f-f222-45a5-ac44-c5a1381c596d@redhat.com/ Link: https://lkml.kernel.org/r/20240801204748.99107-1-david@redhat.com Fixes: 9cb28da54643 ("mm/gup: handle hugetlb in the generic follow_page_mask code") Signed-off-by: David Hildenbrand Acked-by: Peter Xu Reviewed-by: Baolin Wang Tested-by: Baolin Wang Cc: Peter Xu Cc: Oscar Salvador Cc: Muchun Song Cc: Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 33 ++++++++++++++++++++++++++++++--- include/linux/mm.h | 11 +++++++++++ 2 files changed, 41 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index c9bf68c239a0..45bf05ad5c53 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -944,10 +944,37 @@ static inline bool htlb_allow_alloc_fallback(int reason) static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { - if (huge_page_size(h) == PMD_SIZE) + const unsigned long size = huge_page_size(h); + + VM_WARN_ON(size == PAGE_SIZE); + + /* + * hugetlb must use the exact same PT locks as core-mm page table + * walkers would. When modifying a PTE table, hugetlb must take the + * PTE PT lock, when modifying a PMD table, hugetlb must take the PMD + * PT lock etc. + * + * The expectation is that any hugetlb folio smaller than a PMD is + * always mapped into a single PTE table and that any hugetlb folio + * smaller than a PUD (but at least as big as a PMD) is always mapped + * into a single PMD table. + * + * If that does not hold for an architecture, then that architecture + * must disable split PT locks such that all *_lockptr() functions + * will give us the same result: the per-MM PT lock. + * + * Note that with e.g., CONFIG_PGTABLE_LEVELS=2 where + * PGDIR_SIZE==P4D_SIZE==PUD_SIZE==PMD_SIZE, we'd use pud_lockptr() + * and core-mm would use pmd_lockptr(). However, in such configurations + * split PMD locks are disabled -- they don't make sense on a single + * PGDIR page table -- and the end result is the same. + */ + if (size >= PUD_SIZE) + return pud_lockptr(mm, (pud_t *) pte); + else if (size >= PMD_SIZE || IS_ENABLED(CONFIG_HIGHPTE)) return pmd_lockptr(mm, (pmd_t *) pte); - VM_BUG_ON(huge_page_size(h) == PAGE_SIZE); - return &mm->page_table_lock; + /* pte_alloc_huge() only applies with !CONFIG_HIGHPTE */ + return ptep_lockptr(mm, pte); } #ifndef hugepages_supported diff --git a/include/linux/mm.h b/include/linux/mm.h index c4b238a20b76..6549d0979b28 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2920,6 +2920,13 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) return ptlock_ptr(page_ptdesc(pmd_page(*pmd))); } +static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte) +{ + BUILD_BUG_ON(IS_ENABLED(CONFIG_HIGHPTE)); + BUILD_BUG_ON(MAX_PTRS_PER_PTE * sizeof(pte_t) > PAGE_SIZE); + return ptlock_ptr(virt_to_ptdesc(pte)); +} + static inline bool ptlock_init(struct ptdesc *ptdesc) { /* @@ -2944,6 +2951,10 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) { return &mm->page_table_lock; } +static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte) +{ + return &mm->page_table_lock; +} static inline void ptlock_cache_init(void) {} static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; } static inline void ptlock_free(struct ptdesc *ptdesc) {} -- cgit v1.2.3 From f4cb78af91e3b2b7aa76dbf8213b898fa8811b12 Mon Sep 17 00:00:00 2001 From: Pasha Tatashin Date: Thu, 8 Aug 2024 21:34:35 +0000 Subject: mm: add system wide stats items category /proc/vmstat contains events and stats, events can only grow, but stats can grow and shrink. vmstat has the following: ------------------------- NR_VM_ZONE_STAT_ITEMS: per-zone stats NR_VM_NUMA_EVENT_ITEMS: per-numa events NR_VM_NODE_STAT_ITEMS: per-numa stats NR_VM_WRITEBACK_STAT_ITEMS: system-wide background-writeback and dirty-throttling tresholds. NR_VM_EVENT_ITEMS: system-wide events ------------------------- Rename NR_VM_WRITEBACK_STAT_ITEMS to NR_VM_STAT_ITEMS, to track the system-wide stats, we are going to add per-page metadata stats to this category in the next patch. Also delete unused writeback_stat_name(). Link: https://lkml.kernel.org/r/20240809191020.1142142-2-pasha.tatashin@soleen.com Link: https://lkml.kernel.org/r/20240808213437.682006-3-pasha.tatashin@soleen.com Fixes: 15995a352474 ("mm: report per-page metadata information") Signed-off-by: Pasha Tatashin Suggested-by: Yosry Ahmed Tested-by: Alison Schofield Acked-by: David Hildenbrand Acked-by: David Rientjes Cc: Dan Williams Cc: Domenico Cerasuolo Cc: Joel Granados Cc: Johannes Weiner Cc: Li Zhijian Cc: Matthew Wilcox (Oracle) Cc: Mike Rapoport Cc: Muchun Song Cc: Nhat Pham Cc: Sourav Panda Cc: Vlastimil Babka Cc: Yi Zhang Cc: Fan Ni Signed-off-by: Andrew Morton --- include/linux/vmstat.h | 15 ++++----------- mm/vmstat.c | 6 +++--- 2 files changed, 7 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 23cd17942036..9ab4fa5e09b5 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -34,10 +34,11 @@ struct reclaim_stat { unsigned nr_lazyfree_fail; }; -enum writeback_stat_item { +/* Stat data for system wide items */ +enum vm_stat_item { NR_DIRTY_THRESHOLD, NR_DIRTY_BG_THRESHOLD, - NR_VM_WRITEBACK_STAT_ITEMS, + NR_VM_STAT_ITEMS, }; #ifdef CONFIG_VM_EVENT_COUNTERS @@ -514,21 +515,13 @@ static inline const char *lru_list_name(enum lru_list lru) return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_" } -static inline const char *writeback_stat_name(enum writeback_stat_item item) -{ - return vmstat_text[NR_VM_ZONE_STAT_ITEMS + - NR_VM_NUMA_EVENT_ITEMS + - NR_VM_NODE_STAT_ITEMS + - item]; -} - #if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG) static inline const char *vm_event_name(enum vm_event_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + NR_VM_NUMA_EVENT_ITEMS + NR_VM_NODE_STAT_ITEMS + - NR_VM_WRITEBACK_STAT_ITEMS + + NR_VM_STAT_ITEMS + item]; } #endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */ diff --git a/mm/vmstat.c b/mm/vmstat.c index 04a1cb6cc636..6f8aa4766f16 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1257,7 +1257,7 @@ const char * const vmstat_text[] = { "pgdemote_khugepaged", "nr_memmap", "nr_memmap_boot", - /* enum writeback_stat_item counters */ + /* system-wide enum vm_stat_item counters */ "nr_dirty_threshold", "nr_dirty_background_threshold", @@ -1790,7 +1790,7 @@ static const struct seq_operations zoneinfo_op = { #define NR_VMSTAT_ITEMS (NR_VM_ZONE_STAT_ITEMS + \ NR_VM_NUMA_EVENT_ITEMS + \ NR_VM_NODE_STAT_ITEMS + \ - NR_VM_WRITEBACK_STAT_ITEMS + \ + NR_VM_STAT_ITEMS + \ (IS_ENABLED(CONFIG_VM_EVENT_COUNTERS) ? \ NR_VM_EVENT_ITEMS : 0)) @@ -1827,7 +1827,7 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos) global_dirty_limits(v + NR_DIRTY_BG_THRESHOLD, v + NR_DIRTY_THRESHOLD); - v += NR_VM_WRITEBACK_STAT_ITEMS; + v += NR_VM_STAT_ITEMS; #ifdef CONFIG_VM_EVENT_COUNTERS all_vm_events(v); -- cgit v1.2.3 From 9d85731110241fb8ca9445ea4177d816041a8825 Mon Sep 17 00:00:00 2001 From: Pasha Tatashin Date: Thu, 8 Aug 2024 21:34:36 +0000 Subject: mm: don't account memmap per-node Fix invalid access to pgdat during hot-remove operation: ndctl users reported a GPF when trying to destroy a namespace: $ ndctl destroy-namespace all -r all -f Segmentation fault dmesg: Oops: general protection fault, probably for non-canonical address 0xdffffc0000005650: 0000 [#1] PREEMPT SMP KASAN PTI KASAN: probably user-memory-access in range [0x000000000002b280-0x000000000002b287] CPU: 26 UID: 0 PID: 1868 Comm: ndctl Not tainted 6.11.0-rc1 #1 Hardware name: Dell Inc. PowerEdge R640/08HT8T, BIOS 2.20.1 09/13/2023 RIP: 0010:mod_node_page_state+0x2a/0x110 cxl-test users report a GPF when trying to unload the test module: $ modrpobe -r cxl-test dmesg BUG: unable to handle page fault for address: 0000000000004200 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: Oops: 0000 [#1] PREEMPT SMP PTI CPU: 0 UID: 0 PID: 1076 Comm: modprobe Tainted: G O N 6.11.0-rc1 #197 Tainted: [O]=OOT_MODULE, [N]=TEST Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/15 RIP: 0010:mod_node_page_state+0x6/0x90 Currently, when memory is hot-plugged or hot-removed the accounting is done based on the assumption that memmap is allocated from the same node as the hot-plugged/hot-removed memory, which is not always the case. In addition, there are challenges with keeping the node id of the memory that is being remove to the time when memmap accounting is actually performed: since this is done after remove_pfn_range_from_zone(), and also after remove_memory_block_devices(). Meaning that we cannot use pgdat nor walking though memblocks to get the nid. Given all of that, account the memmap overhead system wide instead. For this we are going to be using global atomic counters, but given that memmap size is rarely modified, and normally is only modified either during early boot when there is only one CPU, or under a hotplug global mutex lock, therefore there is no need for per-cpu optimizations. Also, while we are here rename nr_memmap to nr_memmap_pages, and nr_memmap_boot to nr_memmap_boot_pages to be self explanatory that the units are in page count. [pasha.tatashin@soleen.com: address a few nits from David Hildenbrand] Link: https://lkml.kernel.org/r/20240809191020.1142142-4-pasha.tatashin@soleen.com Link: https://lkml.kernel.org/r/20240809191020.1142142-4-pasha.tatashin@soleen.com Link: https://lkml.kernel.org/r/20240808213437.682006-4-pasha.tatashin@soleen.com Fixes: 15995a352474 ("mm: report per-page metadata information") Signed-off-by: Pasha Tatashin Reported-by: Yi Zhang Closes: https://lore.kernel.org/linux-cxl/CAHj4cs9Ax1=CoJkgBGP_+sNu6-6=6v=_L-ZBZY0bVLD3wUWZQg@mail.gmail.com Reported-by: Alison Schofield Closes: https://lore.kernel.org/linux-mm/Zq0tPd2h6alFz8XF@aschofie-mobl2/#t Tested-by: Dan Williams Tested-by: Alison Schofield Acked-by: David Hildenbrand Acked-by: David Rientjes Tested-by: Yi Zhang Cc: Domenico Cerasuolo Cc: Fan Ni Cc: Joel Granados Cc: Johannes Weiner Cc: Li Zhijian Cc: Matthew Wilcox (Oracle) Cc: Mike Rapoport Cc: Muchun Song Cc: Nhat Pham Cc: Sourav Panda Cc: Vlastimil Babka Cc: Yosry Ahmed Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 2 -- include/linux/vmstat.h | 7 ++++--- mm/hugetlb_vmemmap.c | 8 ++++---- mm/mm_init.c | 3 +-- mm/page_alloc.c | 1 - mm/page_ext.c | 18 ++++-------------- mm/sparse-vmemmap.c | 11 ++++------- mm/sparse.c | 5 ++--- mm/vmstat.c | 46 ++++++++++++++++++++++------------------------ 9 files changed, 41 insertions(+), 60 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 41458892bc8a..1dc6248feb83 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -220,8 +220,6 @@ enum node_stat_item { PGDEMOTE_KSWAPD, PGDEMOTE_DIRECT, PGDEMOTE_KHUGEPAGED, - NR_MEMMAP, /* page metadata allocated through buddy allocator */ - NR_MEMMAP_BOOT, /* page metadata allocated through boot allocator */ NR_VM_NODE_STAT_ITEMS }; diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 9ab4fa5e09b5..9eb77c9007e6 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -38,6 +38,8 @@ struct reclaim_stat { enum vm_stat_item { NR_DIRTY_THRESHOLD, NR_DIRTY_BG_THRESHOLD, + NR_MEMMAP_PAGES, /* page metadata allocated through buddy allocator */ + NR_MEMMAP_BOOT_PAGES, /* page metadata allocated through boot allocator */ NR_VM_STAT_ITEMS, }; @@ -618,7 +620,6 @@ static inline void lruvec_stat_sub_folio(struct folio *folio, lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio)); } -void __meminit mod_node_early_perpage_metadata(int nid, long delta); -void __meminit store_early_perpage_metadata(void); - +void memmap_boot_pages_add(long delta); +void memmap_pages_add(long delta); #endif /* _LINUX_VMSTAT_H */ diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c index 4f51e0596197..0c3f56b3578e 100644 --- a/mm/hugetlb_vmemmap.c +++ b/mm/hugetlb_vmemmap.c @@ -185,11 +185,11 @@ static int vmemmap_remap_range(unsigned long start, unsigned long end, static inline void free_vmemmap_page(struct page *page) { if (PageReserved(page)) { + memmap_boot_pages_add(-1); free_bootmem_page(page); - mod_node_page_state(page_pgdat(page), NR_MEMMAP_BOOT, -1); } else { + memmap_pages_add(-1); __free_page(page); - mod_node_page_state(page_pgdat(page), NR_MEMMAP, -1); } } @@ -341,7 +341,7 @@ static int vmemmap_remap_free(unsigned long start, unsigned long end, copy_page(page_to_virt(walk.reuse_page), (void *)walk.reuse_addr); list_add(&walk.reuse_page->lru, vmemmap_pages); - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP, 1); + memmap_pages_add(1); } /* @@ -396,7 +396,7 @@ static int alloc_vmemmap_page_list(unsigned long start, unsigned long end, goto out; list_add(&page->lru, list); } - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP, nr_pages); + memmap_pages_add(nr_pages); return 0; out: diff --git a/mm/mm_init.c b/mm/mm_init.c index 75c3bd42799b..f9a60ffc5532 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -1623,8 +1623,7 @@ static void __init alloc_node_mem_map(struct pglist_data *pgdat) panic("Failed to allocate %ld bytes for node %d memory map\n", size, pgdat->node_id); pgdat->node_mem_map = map + offset; - mod_node_early_perpage_metadata(pgdat->node_id, - DIV_ROUND_UP(size, PAGE_SIZE)); + memmap_boot_pages_add(DIV_ROUND_UP(size, PAGE_SIZE)); pr_debug("%s: node %d, pgdat %08lx, node_mem_map %08lx\n", __func__, pgdat->node_id, (unsigned long)pgdat, (unsigned long)pgdat->node_mem_map); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 28f80daf5c04..875d76e8684a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5755,7 +5755,6 @@ void __init setup_per_cpu_pageset(void) for_each_online_pgdat(pgdat) pgdat->per_cpu_nodestats = alloc_percpu(struct per_cpu_nodestat); - store_early_perpage_metadata(); } __meminit void zone_pcp_init(struct zone *zone) diff --git a/mm/page_ext.c b/mm/page_ext.c index c191e490c401..641d93f6af4c 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -214,8 +214,7 @@ static int __init alloc_node_page_ext(int nid) return -ENOMEM; NODE_DATA(nid)->node_page_ext = base; total_usage += table_size; - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP_BOOT, - DIV_ROUND_UP(table_size, PAGE_SIZE)); + memmap_boot_pages_add(DIV_ROUND_UP(table_size, PAGE_SIZE)); return 0; } @@ -275,10 +274,8 @@ static void *__meminit alloc_page_ext(size_t size, int nid) else addr = vzalloc_node(size, nid); - if (addr) { - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP, - DIV_ROUND_UP(size, PAGE_SIZE)); - } + if (addr) + memmap_pages_add(DIV_ROUND_UP(size, PAGE_SIZE)); return addr; } @@ -323,25 +320,18 @@ static void free_page_ext(void *addr) { size_t table_size; struct page *page; - struct pglist_data *pgdat; table_size = page_ext_size * PAGES_PER_SECTION; + memmap_pages_add(-1L * (DIV_ROUND_UP(table_size, PAGE_SIZE))); if (is_vmalloc_addr(addr)) { - page = vmalloc_to_page(addr); - pgdat = page_pgdat(page); vfree(addr); } else { page = virt_to_page(addr); - pgdat = page_pgdat(page); BUG_ON(PageReserved(page)); kmemleak_free(addr); free_pages_exact(addr, table_size); } - - mod_node_page_state(pgdat, NR_MEMMAP, - -1L * (DIV_ROUND_UP(table_size, PAGE_SIZE))); - } static void __free_page_ext(unsigned long pfn) diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 1dda6c53370b..edcc7a6b0f6f 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -469,13 +469,10 @@ struct page * __meminit __populate_section_memmap(unsigned long pfn, if (r < 0) return NULL; - if (system_state == SYSTEM_BOOTING) { - mod_node_early_perpage_metadata(nid, DIV_ROUND_UP(end - start, - PAGE_SIZE)); - } else { - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP, - DIV_ROUND_UP(end - start, PAGE_SIZE)); - } + if (system_state == SYSTEM_BOOTING) + memmap_boot_pages_add(DIV_ROUND_UP(end - start, PAGE_SIZE)); + else + memmap_pages_add(DIV_ROUND_UP(end - start, PAGE_SIZE)); return pfn_to_page(pfn); } diff --git a/mm/sparse.c b/mm/sparse.c index e4b830091d13..0f018c6f9ec5 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -463,7 +463,7 @@ static void __init sparse_buffer_init(unsigned long size, int nid) sparsemap_buf = memmap_alloc(size, section_map_size(), addr, nid, true); sparsemap_buf_end = sparsemap_buf + size; #ifndef CONFIG_SPARSEMEM_VMEMMAP - mod_node_early_perpage_metadata(nid, DIV_ROUND_UP(size, PAGE_SIZE)); + memmap_boot_pages_add(DIV_ROUND_UP(size, PAGE_SIZE)); #endif } @@ -643,8 +643,7 @@ static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages, unsigned long start = (unsigned long) pfn_to_page(pfn); unsigned long end = start + nr_pages * sizeof(struct page); - mod_node_page_state(page_pgdat(pfn_to_page(pfn)), NR_MEMMAP, - -1L * (DIV_ROUND_UP(end - start, PAGE_SIZE))); + memmap_pages_add(-1L * (DIV_ROUND_UP(end - start, PAGE_SIZE))); vmemmap_free(start, end, altmap); } static void free_map_bootmem(struct page *memmap) diff --git a/mm/vmstat.c b/mm/vmstat.c index 6f8aa4766f16..e875f2a4915f 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1033,6 +1033,24 @@ unsigned long node_page_state(struct pglist_data *pgdat, } #endif +/* + * Count number of pages "struct page" and "struct page_ext" consume. + * nr_memmap_boot_pages: # of pages allocated by boot allocator + * nr_memmap_pages: # of pages that were allocated by buddy allocator + */ +static atomic_long_t nr_memmap_boot_pages = ATOMIC_LONG_INIT(0); +static atomic_long_t nr_memmap_pages = ATOMIC_LONG_INIT(0); + +void memmap_boot_pages_add(long delta) +{ + atomic_long_add(delta, &nr_memmap_boot_pages); +} + +void memmap_pages_add(long delta) +{ + atomic_long_add(delta, &nr_memmap_pages); +} + #ifdef CONFIG_COMPACTION struct contig_page_info { @@ -1255,11 +1273,11 @@ const char * const vmstat_text[] = { "pgdemote_kswapd", "pgdemote_direct", "pgdemote_khugepaged", - "nr_memmap", - "nr_memmap_boot", /* system-wide enum vm_stat_item counters */ "nr_dirty_threshold", "nr_dirty_background_threshold", + "nr_memmap_pages", + "nr_memmap_boot_pages", #if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG) /* enum vm_event_item counters */ @@ -1827,6 +1845,8 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos) global_dirty_limits(v + NR_DIRTY_BG_THRESHOLD, v + NR_DIRTY_THRESHOLD); + v[NR_MEMMAP_PAGES] = atomic_long_read(&nr_memmap_pages); + v[NR_MEMMAP_BOOT_PAGES] = atomic_long_read(&nr_memmap_boot_pages); v += NR_VM_STAT_ITEMS; #ifdef CONFIG_VM_EVENT_COUNTERS @@ -2285,25 +2305,3 @@ static int __init extfrag_debug_init(void) module_init(extfrag_debug_init); #endif - -/* - * Page metadata size (struct page and page_ext) in pages - */ -static unsigned long early_perpage_metadata[MAX_NUMNODES] __meminitdata; - -void __meminit mod_node_early_perpage_metadata(int nid, long delta) -{ - early_perpage_metadata[nid] += delta; -} - -void __meminit store_early_perpage_metadata(void) -{ - int nid; - struct pglist_data *pgdat; - - for_each_online_pgdat(pgdat) { - nid = pgdat->node_id; - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP_BOOT, - early_perpage_metadata[nid]); - } -} -- cgit v1.2.3 From a8fc28dad6d574582cdf2f7e78c73c59c623df30 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Tue, 13 Aug 2024 08:07:56 -0700 Subject: alloc_tag: introduce clear_page_tag_ref() helper function In several cases we are freeing pages which were not allocated using common page allocators. For such cases, in order to keep allocation accounting correct, we should clear the page tag to indicate that the page being freed is expected to not have a valid allocation tag. Introduce clear_page_tag_ref() helper function to be used for this. Link: https://lkml.kernel.org/r/20240813150758.855881-1-surenb@google.com Fixes: d224eb0287fb ("codetag: debug: mark codetags for reserved pages as empty") Signed-off-by: Suren Baghdasaryan Suggested-by: David Hildenbrand Acked-by: David Hildenbrand Reviewed-by: Pasha Tatashin Cc: Kees Cook Cc: Kent Overstreet Cc: Sourav Panda Cc: Vlastimil Babka Cc: [6.10] Signed-off-by: Andrew Morton --- include/linux/pgalloc_tag.h | 13 +++++++++++++ mm/mm_init.c | 10 +--------- mm/page_alloc.c | 9 +-------- 3 files changed, 15 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pgalloc_tag.h b/include/linux/pgalloc_tag.h index 18cd0c0c73d9..207f0c83c8e9 100644 --- a/include/linux/pgalloc_tag.h +++ b/include/linux/pgalloc_tag.h @@ -43,6 +43,18 @@ static inline void put_page_tag_ref(union codetag_ref *ref) page_ext_put(page_ext_from_codetag_ref(ref)); } +static inline void clear_page_tag_ref(struct page *page) +{ + if (mem_alloc_profiling_enabled()) { + union codetag_ref *ref = get_page_tag_ref(page); + + if (ref) { + set_codetag_empty(ref); + put_page_tag_ref(ref); + } + } +} + static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, unsigned int nr) { @@ -126,6 +138,7 @@ static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) static inline union codetag_ref *get_page_tag_ref(struct page *page) { return NULL; } static inline void put_page_tag_ref(union codetag_ref *ref) {} +static inline void clear_page_tag_ref(struct page *page) {} static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, unsigned int nr) {} static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) {} diff --git a/mm/mm_init.c b/mm/mm_init.c index f9a60ffc5532..adc3127573cd 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -2459,15 +2459,7 @@ void __init memblock_free_pages(struct page *page, unsigned long pfn, } /* pages were reserved and not allocated */ - if (mem_alloc_profiling_enabled()) { - union codetag_ref *ref = get_page_tag_ref(page); - - if (ref) { - set_codetag_empty(ref); - put_page_tag_ref(ref); - } - } - + clear_page_tag_ref(page); __free_pages_core(page, order, MEMINIT_EARLY); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 8747087acee3..c565de8f48e9 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5815,14 +5815,7 @@ unsigned long free_reserved_area(void *start, void *end, int poison, const char void free_reserved_page(struct page *page) { - if (mem_alloc_profiling_enabled()) { - union codetag_ref *ref = get_page_tag_ref(page); - - if (ref) { - set_codetag_empty(ref); - put_page_tag_ref(ref); - } - } + clear_page_tag_ref(page); ClearPageReserved(page); init_page_count(page); __free_page(page); -- cgit v1.2.3 From 67c3ca2c5cfe6a50772514e3349b5e7b3b0fac03 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:07:02 +0300 Subject: net: mscc: ocelot: use ocelot_xmit_get_vlan_info() also for FDMA and register injection Problem description ------------------- On an NXP LS1028A (felix DSA driver) with the following configuration: - ocelot-8021q tagging protocol - VLAN-aware bridge (with STP) spanning at least swp0 and swp1 - 8021q VLAN upper interfaces on swp0 and swp1: swp0.700, swp1.700 - ptp4l on swp0.700 and swp1.700 we see that the ptp4l instances do not see each other's traffic, and they all go to the grand master state due to the ANNOUNCE_RECEIPT_TIMEOUT_EXPIRES condition. Jumping to the conclusion for the impatient ------------------------------------------- There is a zero-day bug in the ocelot switchdev driver in the way it handles VLAN-tagged packet injection. The correct logic already exists in the source code, in function ocelot_xmit_get_vlan_info() added by commit 5ca721c54d86 ("net: dsa: tag_ocelot: set the classified VLAN during xmit"). But it is used only for normal NPI-based injection with the DSA "ocelot" tagging protocol. The other injection code paths (register-based and FDMA-based) roll their own wrong logic. This affects and was noticed on the DSA "ocelot-8021q" protocol because it uses register-based injection. By moving ocelot_xmit_get_vlan_info() to a place that's common for both the DSA tagger and the ocelot switch library, it can also be called from ocelot_port_inject_frame() in ocelot.c. We need to touch the lines with ocelot_ifh_port_set()'s prototype anyway, so let's rename it to something clearer regarding what it does, and add a kernel-doc. ocelot_ifh_set_basic() should do. Investigation notes ------------------- Debugging reveals that PTP event (aka those carrying timestamps, like Sync) frames injected into swp0.700 (but also swp1.700) hit the wire with two VLAN tags: 00000000: 01 1b 19 00 00 00 00 01 02 03 04 05 81 00 02 bc ~~~~~~~~~~~ 00000010: 81 00 02 bc 88 f7 00 12 00 2c 00 00 02 00 00 00 ~~~~~~~~~~~ 00000020: 00 00 00 00 00 00 00 00 00 00 00 01 02 ff fe 03 00000030: 04 05 00 01 00 04 00 00 00 00 00 00 00 00 00 00 00000040: 00 00 The second (unexpected) VLAN tag makes felix_check_xtr_pkt() -> ptp_classify_raw() fail to see these as PTP packets at the link partner's receiving end, and return PTP_CLASS_NONE (because the BPF classifier is not written to expect 2 VLAN tags). The reason why packets have 2 VLAN tags is because the transmission code treats VLAN incorrectly. Neither ocelot switchdev, nor felix DSA, declare the NETIF_F_HW_VLAN_CTAG_TX feature. Therefore, at xmit time, all VLANs should be in the skb head, and none should be in the hwaccel area. This is done by: static struct sk_buff *validate_xmit_vlan(struct sk_buff *skb, netdev_features_t features) { if (skb_vlan_tag_present(skb) && !vlan_hw_offload_capable(features, skb->vlan_proto)) skb = __vlan_hwaccel_push_inside(skb); return skb; } But ocelot_port_inject_frame() handles things incorrectly: ocelot_ifh_port_set(ifh, port, rew_op, skb_vlan_tag_get(skb)); void ocelot_ifh_port_set(struct sk_buff *skb, void *ifh, int port, u32 rew_op) { (...) if (vlan_tag) ocelot_ifh_set_vlan_tci(ifh, vlan_tag); (...) } The way __vlan_hwaccel_push_inside() pushes the tag inside the skb head is by calling: static inline void __vlan_hwaccel_clear_tag(struct sk_buff *skb) { skb->vlan_present = 0; } which does _not_ zero out skb->vlan_tci as seen by skb_vlan_tag_get(). This means that ocelot, when it calls skb_vlan_tag_get(), sees (and uses) a residual skb->vlan_tci, while the same VLAN tag is _already_ in the skb head. The trivial fix for double VLAN headers is to replace the content of ocelot_ifh_port_set() with: if (skb_vlan_tag_present(skb)) ocelot_ifh_set_vlan_tci(ifh, skb_vlan_tag_get(skb)); but this would not be correct either, because, as mentioned, vlan_hw_offload_capable() is false for us, so we'd be inserting dead code and we'd always transmit packets with VID=0 in the injection frame header. I can't actually test the ocelot switchdev driver and rely exclusively on code inspection, but I don't think traffic from 8021q uppers has ever been injected properly, and not double-tagged. Thus I'm blaming the introduction of VLAN fields in the injection header - early driver code. As hinted at in the early conclusion, what we _want_ to happen for VLAN transmission was already described once in commit 5ca721c54d86 ("net: dsa: tag_ocelot: set the classified VLAN during xmit"). ocelot_xmit_get_vlan_info() intends to ensure that if the port through which we're transmitting is under a VLAN-aware bridge, the outer VLAN tag from the skb head is stripped from there and inserted into the injection frame header (so that the packet is processed in hardware through that actual VLAN). And in all other cases, the packet is sent with VID=0 in the injection frame header, since the port is VLAN-unaware and has logic to strip this VID on egress (making it invisible to the wire). Fixes: 08d02364b12f ("net: mscc: fix the injection header") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/mscc/ocelot.c | 29 +++++++++++++++----- drivers/net/ethernet/mscc/ocelot_fdma.c | 2 +- include/linux/dsa/ocelot.h | 47 +++++++++++++++++++++++++++++++++ include/soc/mscc/ocelot.h | 3 ++- net/dsa/tag_ocelot.c | 37 ++------------------------ 5 files changed, 75 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index ed2fb44500b0..69a4e5a90475 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1193,17 +1193,34 @@ bool ocelot_can_inject(struct ocelot *ocelot, int grp) } EXPORT_SYMBOL(ocelot_can_inject); -void ocelot_ifh_port_set(void *ifh, int port, u32 rew_op, u32 vlan_tag) +/** + * ocelot_ifh_set_basic - Set basic information in Injection Frame Header + * @ifh: Pointer to Injection Frame Header memory + * @ocelot: Switch private data structure + * @port: Egress port number + * @rew_op: Egress rewriter operation for PTP + * @skb: Pointer to socket buffer (packet) + * + * Populate the Injection Frame Header with basic information for this skb: the + * analyzer bypass bit, destination port, VLAN info, egress rewriter info. + */ +void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port, + u32 rew_op, struct sk_buff *skb) { + struct ocelot_port *ocelot_port = ocelot->ports[port]; + u64 vlan_tci, tag_type; + + ocelot_xmit_get_vlan_info(skb, ocelot_port->bridge, &vlan_tci, + &tag_type); + ocelot_ifh_set_bypass(ifh, 1); ocelot_ifh_set_dest(ifh, BIT_ULL(port)); - ocelot_ifh_set_tag_type(ifh, IFH_TAG_TYPE_C); - if (vlan_tag) - ocelot_ifh_set_vlan_tci(ifh, vlan_tag); + ocelot_ifh_set_tag_type(ifh, tag_type); + ocelot_ifh_set_vlan_tci(ifh, vlan_tci); if (rew_op) ocelot_ifh_set_rew_op(ifh, rew_op); } -EXPORT_SYMBOL(ocelot_ifh_port_set); +EXPORT_SYMBOL(ocelot_ifh_set_basic); void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, u32 rew_op, struct sk_buff *skb) @@ -1214,7 +1231,7 @@ void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, ocelot_write_rix(ocelot, QS_INJ_CTRL_GAP_SIZE(1) | QS_INJ_CTRL_SOF, QS_INJ_CTRL, grp); - ocelot_ifh_port_set(ifh, port, rew_op, skb_vlan_tag_get(skb)); + ocelot_ifh_set_basic(ifh, ocelot, port, rew_op, skb); for (i = 0; i < OCELOT_TAG_LEN / 4; i++) ocelot_write_rix(ocelot, ifh[i], QS_INJ_WR, grp); diff --git a/drivers/net/ethernet/mscc/ocelot_fdma.c b/drivers/net/ethernet/mscc/ocelot_fdma.c index 312a46832154..87b59cc5e441 100644 --- a/drivers/net/ethernet/mscc/ocelot_fdma.c +++ b/drivers/net/ethernet/mscc/ocelot_fdma.c @@ -666,7 +666,7 @@ static int ocelot_fdma_prepare_skb(struct ocelot *ocelot, int port, u32 rew_op, ifh = skb_push(skb, OCELOT_TAG_LEN); skb_put(skb, ETH_FCS_LEN); memset(ifh, 0, OCELOT_TAG_LEN); - ocelot_ifh_port_set(ifh, port, rew_op, skb_vlan_tag_get(skb)); + ocelot_ifh_set_basic(ifh, ocelot, port, rew_op, skb); return 0; } diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h index dca2969015d8..6fbfbde68a37 100644 --- a/include/linux/dsa/ocelot.h +++ b/include/linux/dsa/ocelot.h @@ -5,6 +5,8 @@ #ifndef _NET_DSA_TAG_OCELOT_H #define _NET_DSA_TAG_OCELOT_H +#include +#include #include #include #include @@ -273,4 +275,49 @@ static inline u32 ocelot_ptp_rew_op(struct sk_buff *skb) return rew_op; } +/** + * ocelot_xmit_get_vlan_info: Determine VLAN_TCI and TAG_TYPE for injected frame + * @skb: Pointer to socket buffer + * @br: Pointer to bridge device that the port is under, if any + * @vlan_tci: + * @tag_type: + * + * If the port is under a VLAN-aware bridge, remove the VLAN header from the + * payload and move it into the DSA tag, which will make the switch classify + * the packet to the bridge VLAN. Otherwise, leave the classified VLAN at zero, + * which is the pvid of standalone ports (OCELOT_STANDALONE_PVID), although not + * of VLAN-unaware bridge ports (that would be ocelot_vlan_unaware_pvid()). + * Anyway, VID 0 is fine because it is stripped on egress for these port modes, + * and source address learning is not performed for packets injected from the + * CPU anyway, so it doesn't matter that the VID is "wrong". + */ +static inline void ocelot_xmit_get_vlan_info(struct sk_buff *skb, + struct net_device *br, + u64 *vlan_tci, u64 *tag_type) +{ + struct vlan_ethhdr *hdr; + u16 proto, tci; + + if (!br || !br_vlan_enabled(br)) { + *vlan_tci = 0; + *tag_type = IFH_TAG_TYPE_C; + return; + } + + hdr = (struct vlan_ethhdr *)skb_mac_header(skb); + br_vlan_get_proto(br, &proto); + + if (ntohs(hdr->h_vlan_proto) == proto) { + vlan_remove_tag(skb, &tci); + *vlan_tci = tci; + } else { + rcu_read_lock(); + br_vlan_get_pvid_rcu(br, &tci); + rcu_read_unlock(); + *vlan_tci = tci; + } + + *tag_type = (proto != ETH_P_8021Q) ? IFH_TAG_TYPE_S : IFH_TAG_TYPE_C; +} + #endif diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 6a37b29f4b4c..ed18e6bafc8d 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -969,7 +969,8 @@ void __ocelot_target_write_ix(struct ocelot *ocelot, enum ocelot_target target, bool ocelot_can_inject(struct ocelot *ocelot, int grp); void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, u32 rew_op, struct sk_buff *skb); -void ocelot_ifh_port_set(void *ifh, int port, u32 rew_op, u32 vlan_tag); +void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port, + u32 rew_op, struct sk_buff *skb); int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **skb); void ocelot_drain_cpu_queue(struct ocelot *ocelot, int grp); void ocelot_ptp_rx_timestamp(struct ocelot *ocelot, struct sk_buff *skb, diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index e0e4300bfbd3..bf6608fc6be7 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -8,40 +8,6 @@ #define OCELOT_NAME "ocelot" #define SEVILLE_NAME "seville" -/* If the port is under a VLAN-aware bridge, remove the VLAN header from the - * payload and move it into the DSA tag, which will make the switch classify - * the packet to the bridge VLAN. Otherwise, leave the classified VLAN at zero, - * which is the pvid of standalone and VLAN-unaware bridge ports. - */ -static void ocelot_xmit_get_vlan_info(struct sk_buff *skb, struct dsa_port *dp, - u64 *vlan_tci, u64 *tag_type) -{ - struct net_device *br = dsa_port_bridge_dev_get(dp); - struct vlan_ethhdr *hdr; - u16 proto, tci; - - if (!br || !br_vlan_enabled(br)) { - *vlan_tci = 0; - *tag_type = IFH_TAG_TYPE_C; - return; - } - - hdr = skb_vlan_eth_hdr(skb); - br_vlan_get_proto(br, &proto); - - if (ntohs(hdr->h_vlan_proto) == proto) { - vlan_remove_tag(skb, &tci); - *vlan_tci = tci; - } else { - rcu_read_lock(); - br_vlan_get_pvid_rcu(br, &tci); - rcu_read_unlock(); - *vlan_tci = tci; - } - - *tag_type = (proto != ETH_P_8021Q) ? IFH_TAG_TYPE_S : IFH_TAG_TYPE_C; -} - static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev, __be32 ifh_prefix, void **ifh) { @@ -53,7 +19,8 @@ static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev, u32 rew_op = 0; u64 qos_class; - ocelot_xmit_get_vlan_info(skb, dp, &vlan_tci, &tag_type); + ocelot_xmit_get_vlan_info(skb, dsa_port_bridge_dev_get(dp), &vlan_tci, + &tag_type); qos_class = netdev_get_num_tc(netdev) ? netdev_get_prio_tc_map(netdev, skb->priority) : skb->priority; -- cgit v1.2.3 From 3942bb49728ad9e1f94d953a88af169a8f5d8099 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Wed, 14 Aug 2024 13:00:34 +0300 Subject: string: add mem_is_zero() helper to check if memory area is all zeros Almost two thirds of the memchr_inv() usages check if the memory area is all zeros, with no interest in where in the buffer the first non-zero byte is located. Checking for !memchr_inv(s, 0, n) is also not very intuitive or discoverable. Add an explicit mem_is_zero() helper for this use case. Reviewed-by: Kees Cook Reviewed-by: Andy Shevchenko Link: https://patchwork.freedesktop.org/patch/msgid/20240814100035.3100852-1-jani.nikula@intel.com Signed-off-by: Jani Nikula --- include/linux/string.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/string.h b/include/linux/string.h index 9edace076ddb..5855c5626b4b 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -279,6 +279,18 @@ static inline void memcpy_flushcache(void *dst, const void *src, size_t cnt) void *memchr_inv(const void *s, int c, size_t n); char *strreplace(char *str, char old, char new); +/** + * mem_is_zero - Check if an area of memory is all 0's. + * @s: The memory area + * @n: The size of the area + * + * Return: True if the area of memory is all 0's. + */ +static inline bool mem_is_zero(const void *s, size_t n) +{ + return !memchr_inv(s, 0, n); +} + extern void kfree_const(const void *x); extern char *kstrdup(const char *s, gfp_t gfp) __malloc; -- cgit v1.2.3 From 6e6f58a170ea98e44075b761f2da42a5aec47dfb Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 13 Aug 2024 16:29:11 +0200 Subject: thermal: gov_bang_bang: Use governor_data to reduce overhead MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit After running once, the for_each_trip_desc() loop in bang_bang_manage() is pure needless overhead because it is not going to make any changes unless a new cooling device has been bound to one of the trips in the thermal zone or the system is resuming from sleep. For this reason, make bang_bang_manage() set governor_data for the thermal zone and check it upfront to decide whether or not it needs to do anything. However, governor_data needs to be reset in some cases to let bang_bang_manage() know that it should walk the trips again, so add an .update_tz() callback to the governor and make the core additionally invoke it during system resume. To avoid affecting the other users of that callback unnecessarily, add a special notification reason for system resume, THERMAL_TZ_RESUME, and also pass it to __thermal_zone_device_update() called during system resume for consistency. Signed-off-by: Rafael J. Wysocki Acked-by: Peter Kästle Reviewed-by: Zhang Rui Cc: 6.10+ # 6.10+ Link: https://patch.msgid.link/2285575.iZASKD2KPV@rjwysocki.net --- drivers/thermal/gov_bang_bang.c | 18 ++++++++++++++++++ drivers/thermal/thermal_core.c | 3 ++- include/linux/thermal.h | 1 + 3 files changed, 21 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/thermal/gov_bang_bang.c b/drivers/thermal/gov_bang_bang.c index bc55e0698bfa..daed67d19efb 100644 --- a/drivers/thermal/gov_bang_bang.c +++ b/drivers/thermal/gov_bang_bang.c @@ -86,6 +86,10 @@ static void bang_bang_manage(struct thermal_zone_device *tz) const struct thermal_trip_desc *td; struct thermal_instance *instance; + /* If the code below has run already, nothing needs to be done. */ + if (tz->governor_data) + return; + for_each_trip_desc(tz, td) { const struct thermal_trip *trip = &td->trip; @@ -107,11 +111,25 @@ static void bang_bang_manage(struct thermal_zone_device *tz) bang_bang_set_instance_target(instance, 0); } } + + tz->governor_data = (void *)true; +} + +static void bang_bang_update_tz(struct thermal_zone_device *tz, + enum thermal_notify_event reason) +{ + /* + * Let bang_bang_manage() know that it needs to walk trips after binding + * a new cdev and after system resume. + */ + if (reason == THERMAL_TZ_BIND_CDEV || reason == THERMAL_TZ_RESUME) + tz->governor_data = NULL; } static struct thermal_governor thermal_gov_bang_bang = { .name = "bang_bang", .trip_crossed = bang_bang_control, .manage = bang_bang_manage, + .update_tz = bang_bang_update_tz, }; THERMAL_GOVERNOR_DECLARE(thermal_gov_bang_bang); diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 95c399f94744..e6669aeda1ff 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -1728,7 +1728,8 @@ static void thermal_zone_device_resume(struct work_struct *work) thermal_debug_tz_resume(tz); thermal_zone_device_init(tz); - __thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED); + thermal_governor_update_tz(tz, THERMAL_TZ_RESUME); + __thermal_zone_device_update(tz, THERMAL_TZ_RESUME); complete(&tz->resume); tz->resuming = false; diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 25fbf960b474..b86ddca46b9e 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -55,6 +55,7 @@ enum thermal_notify_event { THERMAL_TZ_BIND_CDEV, /* Cooling dev is bind to the thermal zone */ THERMAL_TZ_UNBIND_CDEV, /* Cooling dev is unbind from the thermal zone */ THERMAL_INSTANCE_WEIGHT_CHANGED, /* Thermal instance weight changed */ + THERMAL_TZ_RESUME, /* Thermal zone is resuming after system sleep */ }; /** -- cgit v1.2.3 From bf5ffc8c80e0cf5205849cd0c9c3cb261d2beee6 Mon Sep 17 00:00:00 2001 From: "Rob Herring (Arm)" Date: Wed, 31 Jul 2024 10:51:18 -0600 Subject: perf: arm_pmu: Remove event index to counter remapping Xscale and Armv6 PMUs defined the cycle counter at 0 and event counters starting at 1 and had 1:1 event index to counter numbering. On Armv7 and later, this changed the cycle counter to 31 and event counters start at 0. The drivers for Armv7 and PMUv3 kept the old event index numbering and introduced an event index to counter conversion. The conversion uses masking to convert from event index to a counter number. This operation relies on having at most 32 counters so that the cycle counter index 0 can be transformed to counter number 31. Armv9.4 adds support for an additional fixed function counter (instructions) which increases possible counters to more than 32, and the conversion won't work anymore as a simple subtract and mask. The primary reason for the translation (other than history) seems to be to have a contiguous mask of counters 0-N. Keeping that would result in more complicated index to counter conversions. Instead, store a mask of available counters rather than just number of events. That provides more information in addition to the number of events. No (intended) functional changes. Acked-by: Mark Rutland Signed-off-by: Rob Herring (Arm) Tested-by: James Clark Link: https://lore.kernel.org/r/20240731-arm-pmu-3-9-icntr-v3-1-280a8d7ff465@kernel.org Signed-off-by: Will Deacon --- arch/arm64/kvm/pmu-emul.c | 6 ++-- drivers/perf/apple_m1_cpu_pmu.c | 4 +-- drivers/perf/arm_pmu.c | 11 +++--- drivers/perf/arm_pmuv3.c | 62 +++++++++++---------------------- drivers/perf/arm_v6_pmu.c | 6 ++-- drivers/perf/arm_v7_pmu.c | 77 ++++++++++++++++------------------------- drivers/perf/arm_xscale_pmu.c | 12 ++++--- include/linux/perf/arm_pmu.h | 2 +- include/linux/perf/arm_pmuv3.h | 1 + 9 files changed, 75 insertions(+), 106 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 82a2a003259c..0e598f6c42c0 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -910,10 +910,10 @@ u8 kvm_arm_pmu_get_max_counters(struct kvm *kvm) struct arm_pmu *arm_pmu = kvm->arch.arm_pmu; /* - * The arm_pmu->num_events considers the cycle counter as well. - * Ignore that and return only the general-purpose counters. + * The arm_pmu->cntr_mask considers the fixed counter(s) as well. + * Ignore those and return only the general-purpose counters. */ - return arm_pmu->num_events - 1; + return bitmap_weight(arm_pmu->cntr_mask, ARMV8_PMU_MAX_GENERAL_COUNTERS); } static void kvm_arm_set_pmu(struct kvm *kvm, struct arm_pmu *arm_pmu) diff --git a/drivers/perf/apple_m1_cpu_pmu.c b/drivers/perf/apple_m1_cpu_pmu.c index f322e5ca1114..c8f607912567 100644 --- a/drivers/perf/apple_m1_cpu_pmu.c +++ b/drivers/perf/apple_m1_cpu_pmu.c @@ -400,7 +400,7 @@ static irqreturn_t m1_pmu_handle_irq(struct arm_pmu *cpu_pmu) regs = get_irq_regs(); - for (idx = 0; idx < cpu_pmu->num_events; idx++) { + for_each_set_bit(idx, cpu_pmu->cntr_mask, M1_PMU_NR_COUNTERS) { struct perf_event *event = cpuc->events[idx]; struct perf_sample_data data; @@ -560,7 +560,7 @@ static int m1_pmu_init(struct arm_pmu *cpu_pmu, u32 flags) cpu_pmu->reset = m1_pmu_reset; cpu_pmu->set_event_filter = m1_pmu_set_event_filter; - cpu_pmu->num_events = M1_PMU_NR_COUNTERS; + bitmap_set(cpu_pmu->cntr_mask, 0, M1_PMU_NR_COUNTERS); cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = &m1_pmu_events_attr_group; cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = &m1_pmu_format_attr_group; return 0; diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index 8458fe2cebb4..398cce3d76fc 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -522,7 +522,7 @@ static void armpmu_enable(struct pmu *pmu) { struct arm_pmu *armpmu = to_arm_pmu(pmu); struct pmu_hw_events *hw_events = this_cpu_ptr(armpmu->hw_events); - bool enabled = !bitmap_empty(hw_events->used_mask, armpmu->num_events); + bool enabled = !bitmap_empty(hw_events->used_mask, ARMPMU_MAX_HWEVENTS); /* For task-bound events we may be called on other CPUs */ if (!cpumask_test_cpu(smp_processor_id(), &armpmu->supported_cpus)) @@ -742,7 +742,7 @@ static void cpu_pm_pmu_setup(struct arm_pmu *armpmu, unsigned long cmd) struct perf_event *event; int idx; - for (idx = 0; idx < armpmu->num_events; idx++) { + for_each_set_bit(idx, armpmu->cntr_mask, ARMPMU_MAX_HWEVENTS) { event = hw_events->events[idx]; if (!event) continue; @@ -772,7 +772,7 @@ static int cpu_pm_pmu_notify(struct notifier_block *b, unsigned long cmd, { struct arm_pmu *armpmu = container_of(b, struct arm_pmu, cpu_pm_nb); struct pmu_hw_events *hw_events = this_cpu_ptr(armpmu->hw_events); - bool enabled = !bitmap_empty(hw_events->used_mask, armpmu->num_events); + bool enabled = !bitmap_empty(hw_events->used_mask, ARMPMU_MAX_HWEVENTS); if (!cpumask_test_cpu(smp_processor_id(), &armpmu->supported_cpus)) return NOTIFY_DONE; @@ -924,8 +924,9 @@ int armpmu_register(struct arm_pmu *pmu) if (ret) goto out_destroy; - pr_info("enabled with %s PMU driver, %d counters available%s\n", - pmu->name, pmu->num_events, + pr_info("enabled with %s PMU driver, %d (%*pb) counters available%s\n", + pmu->name, bitmap_weight(pmu->cntr_mask, ARMPMU_MAX_HWEVENTS), + ARMPMU_MAX_HWEVENTS, &pmu->cntr_mask, has_nmi ? ", using NMIs" : ""); kvm_host_pmu_init(pmu); diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c index d246840797b6..b48773ec892e 100644 --- a/drivers/perf/arm_pmuv3.c +++ b/drivers/perf/arm_pmuv3.c @@ -454,9 +454,7 @@ static const struct attribute_group armv8_pmuv3_caps_attr_group = { /* * Perf Events' indices */ -#define ARMV8_IDX_CYCLE_COUNTER 0 -#define ARMV8_IDX_COUNTER0 1 -#define ARMV8_IDX_CYCLE_COUNTER_USER 32 +#define ARMV8_IDX_CYCLE_COUNTER 31 /* * We unconditionally enable ARMv8.5-PMU long event counter support @@ -489,19 +487,12 @@ static bool armv8pmu_event_is_chained(struct perf_event *event) return !armv8pmu_event_has_user_read(event) && armv8pmu_event_is_64bit(event) && !armv8pmu_has_long_event(cpu_pmu) && - (idx != ARMV8_IDX_CYCLE_COUNTER); + (idx < ARMV8_PMU_MAX_GENERAL_COUNTERS); } /* * ARMv8 low level PMU access */ - -/* - * Perf Event to low level counters mapping - */ -#define ARMV8_IDX_TO_COUNTER(x) \ - (((x) - ARMV8_IDX_COUNTER0) & ARMV8_PMU_COUNTER_MASK) - static u64 armv8pmu_pmcr_read(void) { return read_pmcr(); @@ -521,14 +512,12 @@ static int armv8pmu_has_overflowed(u32 pmovsr) static int armv8pmu_counter_has_overflowed(u32 pmnc, int idx) { - return pmnc & BIT(ARMV8_IDX_TO_COUNTER(idx)); + return pmnc & BIT(idx); } static u64 armv8pmu_read_evcntr(int idx) { - u32 counter = ARMV8_IDX_TO_COUNTER(idx); - - return read_pmevcntrn(counter); + return read_pmevcntrn(idx); } static u64 armv8pmu_read_hw_counter(struct perf_event *event) @@ -557,7 +546,7 @@ static bool armv8pmu_event_needs_bias(struct perf_event *event) return false; if (armv8pmu_has_long_event(cpu_pmu) || - idx == ARMV8_IDX_CYCLE_COUNTER) + idx >= ARMV8_PMU_MAX_GENERAL_COUNTERS) return true; return false; @@ -595,9 +584,7 @@ static u64 armv8pmu_read_counter(struct perf_event *event) static void armv8pmu_write_evcntr(int idx, u64 value) { - u32 counter = ARMV8_IDX_TO_COUNTER(idx); - - write_pmevcntrn(counter, value); + write_pmevcntrn(idx, value); } static void armv8pmu_write_hw_counter(struct perf_event *event, @@ -628,7 +615,6 @@ static void armv8pmu_write_counter(struct perf_event *event, u64 value) static void armv8pmu_write_evtype(int idx, unsigned long val) { - u32 counter = ARMV8_IDX_TO_COUNTER(idx); unsigned long mask = ARMV8_PMU_EVTYPE_EVENT | ARMV8_PMU_INCLUDE_EL2 | ARMV8_PMU_EXCLUDE_EL0 | @@ -638,7 +624,7 @@ static void armv8pmu_write_evtype(int idx, unsigned long val) mask |= ARMV8_PMU_EVTYPE_TC | ARMV8_PMU_EVTYPE_TH; val &= mask; - write_pmevtypern(counter, val); + write_pmevtypern(idx, val); } static void armv8pmu_write_event_type(struct perf_event *event) @@ -667,7 +653,7 @@ static void armv8pmu_write_event_type(struct perf_event *event) static u32 armv8pmu_event_cnten_mask(struct perf_event *event) { - int counter = ARMV8_IDX_TO_COUNTER(event->hw.idx); + int counter = event->hw.idx; u32 mask = BIT(counter); if (armv8pmu_event_is_chained(event)) @@ -726,8 +712,7 @@ static void armv8pmu_enable_intens(u32 mask) static void armv8pmu_enable_event_irq(struct perf_event *event) { - u32 counter = ARMV8_IDX_TO_COUNTER(event->hw.idx); - armv8pmu_enable_intens(BIT(counter)); + armv8pmu_enable_intens(BIT(event->hw.idx)); } static void armv8pmu_disable_intens(u32 mask) @@ -741,8 +726,7 @@ static void armv8pmu_disable_intens(u32 mask) static void armv8pmu_disable_event_irq(struct perf_event *event) { - u32 counter = ARMV8_IDX_TO_COUNTER(event->hw.idx); - armv8pmu_disable_intens(BIT(counter)); + armv8pmu_disable_intens(BIT(event->hw.idx)); } static u32 armv8pmu_getreset_flags(void) @@ -786,7 +770,8 @@ static void armv8pmu_enable_user_access(struct arm_pmu *cpu_pmu) struct pmu_hw_events *cpuc = this_cpu_ptr(cpu_pmu->hw_events); /* Clear any unused counters to avoid leaking their contents */ - for_each_clear_bit(i, cpuc->used_mask, cpu_pmu->num_events) { + for_each_andnot_bit(i, cpu_pmu->cntr_mask, cpuc->used_mask, + ARMPMU_MAX_HWEVENTS) { if (i == ARMV8_IDX_CYCLE_COUNTER) write_pmccntr(0); else @@ -869,7 +854,7 @@ static irqreturn_t armv8pmu_handle_irq(struct arm_pmu *cpu_pmu) * to prevent skews in group events. */ armv8pmu_stop(cpu_pmu); - for (idx = 0; idx < cpu_pmu->num_events; ++idx) { + for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMPMU_MAX_HWEVENTS) { struct perf_event *event = cpuc->events[idx]; struct hw_perf_event *hwc; @@ -908,7 +893,7 @@ static int armv8pmu_get_single_idx(struct pmu_hw_events *cpuc, { int idx; - for (idx = ARMV8_IDX_COUNTER0; idx < cpu_pmu->num_events; idx++) { + for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMV8_PMU_MAX_GENERAL_COUNTERS) { if (!test_and_set_bit(idx, cpuc->used_mask)) return idx; } @@ -924,7 +909,9 @@ static int armv8pmu_get_chain_idx(struct pmu_hw_events *cpuc, * Chaining requires two consecutive event counters, where * the lower idx must be even. */ - for (idx = ARMV8_IDX_COUNTER0 + 1; idx < cpu_pmu->num_events; idx += 2) { + for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMV8_PMU_MAX_GENERAL_COUNTERS) { + if (!(idx & 0x1)) + continue; if (!test_and_set_bit(idx, cpuc->used_mask)) { /* Check if the preceding even counter is available */ if (!test_and_set_bit(idx - 1, cpuc->used_mask)) @@ -978,15 +965,7 @@ static int armv8pmu_user_event_idx(struct perf_event *event) if (!sysctl_perf_user_access || !armv8pmu_event_has_user_read(event)) return 0; - /* - * We remap the cycle counter index to 32 to - * match the offset applied to the rest of - * the counter indices. - */ - if (event->hw.idx == ARMV8_IDX_CYCLE_COUNTER) - return ARMV8_IDX_CYCLE_COUNTER_USER; - - return event->hw.idx; + return event->hw.idx + 1; } /* @@ -1211,10 +1190,11 @@ static void __armv8pmu_probe_pmu(void *info) probe->present = true; /* Read the nb of CNTx counters supported from PMNC */ - cpu_pmu->num_events = FIELD_GET(ARMV8_PMU_PMCR_N, armv8pmu_pmcr_read()); + bitmap_set(cpu_pmu->cntr_mask, + 0, FIELD_GET(ARMV8_PMU_PMCR_N, armv8pmu_pmcr_read())); /* Add the CPU cycles counter */ - cpu_pmu->num_events += 1; + set_bit(ARMV8_IDX_CYCLE_COUNTER, cpu_pmu->cntr_mask); pmceid[0] = pmceid_raw[0] = read_pmceid0(); pmceid[1] = pmceid_raw[1] = read_pmceid1(); diff --git a/drivers/perf/arm_v6_pmu.c b/drivers/perf/arm_v6_pmu.c index 0bb685b4bac5..b09615bb2bb2 100644 --- a/drivers/perf/arm_v6_pmu.c +++ b/drivers/perf/arm_v6_pmu.c @@ -64,6 +64,7 @@ enum armv6_counters { ARMV6_CYCLE_COUNTER = 0, ARMV6_COUNTER0, ARMV6_COUNTER1, + ARMV6_NUM_COUNTERS }; /* @@ -254,7 +255,7 @@ armv6pmu_handle_irq(struct arm_pmu *cpu_pmu) */ armv6_pmcr_write(pmcr); - for (idx = 0; idx < cpu_pmu->num_events; ++idx) { + for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMV6_NUM_COUNTERS) { struct perf_event *event = cpuc->events[idx]; struct hw_perf_event *hwc; @@ -391,7 +392,8 @@ static void armv6pmu_init(struct arm_pmu *cpu_pmu) cpu_pmu->start = armv6pmu_start; cpu_pmu->stop = armv6pmu_stop; cpu_pmu->map_event = armv6_map_event; - cpu_pmu->num_events = 3; + + bitmap_set(cpu_pmu->cntr_mask, 0, ARMV6_NUM_COUNTERS); } static int armv6_1136_pmu_init(struct arm_pmu *cpu_pmu) diff --git a/drivers/perf/arm_v7_pmu.c b/drivers/perf/arm_v7_pmu.c index 928ac3d626ed..420cadd108e7 100644 --- a/drivers/perf/arm_v7_pmu.c +++ b/drivers/perf/arm_v7_pmu.c @@ -649,24 +649,12 @@ static struct attribute_group armv7_pmuv2_events_attr_group = { /* * Perf Events' indices */ -#define ARMV7_IDX_CYCLE_COUNTER 0 -#define ARMV7_IDX_COUNTER0 1 -#define ARMV7_IDX_COUNTER_LAST(cpu_pmu) \ - (ARMV7_IDX_CYCLE_COUNTER + cpu_pmu->num_events - 1) - -#define ARMV7_MAX_COUNTERS 32 -#define ARMV7_COUNTER_MASK (ARMV7_MAX_COUNTERS - 1) - +#define ARMV7_IDX_CYCLE_COUNTER 31 +#define ARMV7_IDX_COUNTER_MAX 31 /* * ARMv7 low level PMNC access */ -/* - * Perf Event to low level counters mapping - */ -#define ARMV7_IDX_TO_COUNTER(x) \ - (((x) - ARMV7_IDX_COUNTER0) & ARMV7_COUNTER_MASK) - /* * Per-CPU PMNC: config reg */ @@ -725,19 +713,17 @@ static inline int armv7_pmnc_has_overflowed(u32 pmnc) static inline int armv7_pmnc_counter_valid(struct arm_pmu *cpu_pmu, int idx) { - return idx >= ARMV7_IDX_CYCLE_COUNTER && - idx <= ARMV7_IDX_COUNTER_LAST(cpu_pmu); + return test_bit(idx, cpu_pmu->cntr_mask); } static inline int armv7_pmnc_counter_has_overflowed(u32 pmnc, int idx) { - return pmnc & BIT(ARMV7_IDX_TO_COUNTER(idx)); + return pmnc & BIT(idx); } static inline void armv7_pmnc_select_counter(int idx) { - u32 counter = ARMV7_IDX_TO_COUNTER(idx); - asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (counter)); + asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (idx)); isb(); } @@ -787,29 +773,25 @@ static inline void armv7_pmnc_write_evtsel(int idx, u32 val) static inline void armv7_pmnc_enable_counter(int idx) { - u32 counter = ARMV7_IDX_TO_COUNTER(idx); - asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (BIT(counter))); + asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (BIT(idx))); } static inline void armv7_pmnc_disable_counter(int idx) { - u32 counter = ARMV7_IDX_TO_COUNTER(idx); - asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (BIT(counter))); + asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (BIT(idx))); } static inline void armv7_pmnc_enable_intens(int idx) { - u32 counter = ARMV7_IDX_TO_COUNTER(idx); - asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (BIT(counter))); + asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (BIT(idx))); } static inline void armv7_pmnc_disable_intens(int idx) { - u32 counter = ARMV7_IDX_TO_COUNTER(idx); - asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (BIT(counter))); + asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (BIT(idx))); isb(); /* Clear the overflow flag in case an interrupt is pending. */ - asm volatile("mcr p15, 0, %0, c9, c12, 3" : : "r" (BIT(counter))); + asm volatile("mcr p15, 0, %0, c9, c12, 3" : : "r" (BIT(idx))); isb(); } @@ -853,15 +835,12 @@ static void armv7_pmnc_dump_regs(struct arm_pmu *cpu_pmu) asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (val)); pr_info("CCNT =0x%08x\n", val); - for (cnt = ARMV7_IDX_COUNTER0; - cnt <= ARMV7_IDX_COUNTER_LAST(cpu_pmu); cnt++) { + for_each_set_bit(cnt, cpu_pmu->cntr_mask, ARMV7_IDX_COUNTER_MAX) { armv7_pmnc_select_counter(cnt); asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (val)); - pr_info("CNT[%d] count =0x%08x\n", - ARMV7_IDX_TO_COUNTER(cnt), val); + pr_info("CNT[%d] count =0x%08x\n", cnt, val); asm volatile("mrc p15, 0, %0, c9, c13, 1" : "=r" (val)); - pr_info("CNT[%d] evtsel=0x%08x\n", - ARMV7_IDX_TO_COUNTER(cnt), val); + pr_info("CNT[%d] evtsel=0x%08x\n", cnt, val); } } #endif @@ -958,7 +937,7 @@ static irqreturn_t armv7pmu_handle_irq(struct arm_pmu *cpu_pmu) */ regs = get_irq_regs(); - for (idx = 0; idx < cpu_pmu->num_events; ++idx) { + for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMPMU_MAX_HWEVENTS) { struct perf_event *event = cpuc->events[idx]; struct hw_perf_event *hwc; @@ -1027,7 +1006,7 @@ static int armv7pmu_get_event_idx(struct pmu_hw_events *cpuc, * For anything other than a cycle counter, try and use * the events counters */ - for (idx = ARMV7_IDX_COUNTER0; idx < cpu_pmu->num_events; ++idx) { + for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMV7_IDX_COUNTER_MAX) { if (!test_and_set_bit(idx, cpuc->used_mask)) return idx; } @@ -1073,7 +1052,7 @@ static int armv7pmu_set_event_filter(struct hw_perf_event *event, static void armv7pmu_reset(void *info) { struct arm_pmu *cpu_pmu = (struct arm_pmu *)info; - u32 idx, nb_cnt = cpu_pmu->num_events, val; + u32 idx, val; if (cpu_pmu->secure_access) { asm volatile("mrc p15, 0, %0, c1, c1, 1" : "=r" (val)); @@ -1082,7 +1061,7 @@ static void armv7pmu_reset(void *info) } /* The counter and interrupt enable registers are unknown at reset. */ - for (idx = ARMV7_IDX_CYCLE_COUNTER; idx < nb_cnt; ++idx) { + for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMPMU_MAX_HWEVENTS) { armv7_pmnc_disable_counter(idx); armv7_pmnc_disable_intens(idx); } @@ -1161,20 +1140,22 @@ static void armv7pmu_init(struct arm_pmu *cpu_pmu) static void armv7_read_num_pmnc_events(void *info) { - int *nb_cnt = info; + int nb_cnt; + struct arm_pmu *cpu_pmu = info; /* Read the nb of CNTx counters supported from PMNC */ - *nb_cnt = (armv7_pmnc_read() >> ARMV7_PMNC_N_SHIFT) & ARMV7_PMNC_N_MASK; + nb_cnt = (armv7_pmnc_read() >> ARMV7_PMNC_N_SHIFT) & ARMV7_PMNC_N_MASK; + bitmap_set(cpu_pmu->cntr_mask, 0, nb_cnt); /* Add the CPU cycles counter */ - *nb_cnt += 1; + set_bit(ARMV7_IDX_CYCLE_COUNTER, cpu_pmu->cntr_mask); } static int armv7_probe_num_events(struct arm_pmu *arm_pmu) { return smp_call_function_any(&arm_pmu->supported_cpus, armv7_read_num_pmnc_events, - &arm_pmu->num_events, 1); + arm_pmu, 1); } static int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu) @@ -1524,7 +1505,7 @@ static void krait_pmu_reset(void *info) { u32 vval, fval; struct arm_pmu *cpu_pmu = info; - u32 idx, nb_cnt = cpu_pmu->num_events; + u32 idx; armv7pmu_reset(info); @@ -1538,7 +1519,7 @@ static void krait_pmu_reset(void *info) venum_post_pmresr(vval, fval); /* Reset PMxEVNCTCR to sane default */ - for (idx = ARMV7_IDX_CYCLE_COUNTER; idx < nb_cnt; ++idx) { + for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMV7_IDX_COUNTER_MAX) { armv7_pmnc_select_counter(idx); asm volatile("mcr p15, 0, %0, c9, c15, 0" : : "r" (0)); } @@ -1562,7 +1543,7 @@ static int krait_event_to_bit(struct perf_event *event, unsigned int region, * Lower bits are reserved for use by the counters (see * armv7pmu_get_event_idx() for more info) */ - bit += ARMV7_IDX_COUNTER_LAST(cpu_pmu) + 1; + bit += bitmap_weight(cpu_pmu->cntr_mask, ARMV7_IDX_COUNTER_MAX); return bit; } @@ -1845,7 +1826,7 @@ static void scorpion_pmu_reset(void *info) { u32 vval, fval; struct arm_pmu *cpu_pmu = info; - u32 idx, nb_cnt = cpu_pmu->num_events; + u32 idx; armv7pmu_reset(info); @@ -1860,7 +1841,7 @@ static void scorpion_pmu_reset(void *info) venum_post_pmresr(vval, fval); /* Reset PMxEVNCTCR to sane default */ - for (idx = ARMV7_IDX_CYCLE_COUNTER; idx < nb_cnt; ++idx) { + for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMV7_IDX_COUNTER_MAX) { armv7_pmnc_select_counter(idx); asm volatile("mcr p15, 0, %0, c9, c15, 0" : : "r" (0)); } @@ -1883,7 +1864,7 @@ static int scorpion_event_to_bit(struct perf_event *event, unsigned int region, * Lower bits are reserved for use by the counters (see * armv7pmu_get_event_idx() for more info) */ - bit += ARMV7_IDX_COUNTER_LAST(cpu_pmu) + 1; + bit += bitmap_weight(cpu_pmu->cntr_mask, ARMV7_IDX_COUNTER_MAX); return bit; } diff --git a/drivers/perf/arm_xscale_pmu.c b/drivers/perf/arm_xscale_pmu.c index 3d8b72d6b37f..638fea9b1263 100644 --- a/drivers/perf/arm_xscale_pmu.c +++ b/drivers/perf/arm_xscale_pmu.c @@ -53,6 +53,8 @@ enum xscale_counters { XSCALE_COUNTER2, XSCALE_COUNTER3, }; +#define XSCALE1_NUM_COUNTERS 3 +#define XSCALE2_NUM_COUNTERS 5 static const unsigned xscale_perf_map[PERF_COUNT_HW_MAX] = { PERF_MAP_ALL_UNSUPPORTED, @@ -168,7 +170,7 @@ xscale1pmu_handle_irq(struct arm_pmu *cpu_pmu) regs = get_irq_regs(); - for (idx = 0; idx < cpu_pmu->num_events; ++idx) { + for_each_set_bit(idx, cpu_pmu->cntr_mask, XSCALE1_NUM_COUNTERS) { struct perf_event *event = cpuc->events[idx]; struct hw_perf_event *hwc; @@ -364,7 +366,8 @@ static int xscale1pmu_init(struct arm_pmu *cpu_pmu) cpu_pmu->start = xscale1pmu_start; cpu_pmu->stop = xscale1pmu_stop; cpu_pmu->map_event = xscale_map_event; - cpu_pmu->num_events = 3; + + bitmap_set(cpu_pmu->cntr_mask, 0, XSCALE1_NUM_COUNTERS); return 0; } @@ -500,7 +503,7 @@ xscale2pmu_handle_irq(struct arm_pmu *cpu_pmu) regs = get_irq_regs(); - for (idx = 0; idx < cpu_pmu->num_events; ++idx) { + for_each_set_bit(idx, cpu_pmu->cntr_mask, XSCALE2_NUM_COUNTERS) { struct perf_event *event = cpuc->events[idx]; struct hw_perf_event *hwc; @@ -719,7 +722,8 @@ static int xscale2pmu_init(struct arm_pmu *cpu_pmu) cpu_pmu->start = xscale2pmu_start; cpu_pmu->stop = xscale2pmu_stop; cpu_pmu->map_event = xscale_map_event; - cpu_pmu->num_events = 5; + + bitmap_set(cpu_pmu->cntr_mask, 0, XSCALE2_NUM_COUNTERS); return 0; } diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index b3b34f6670cf..e5d6d204beab 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -96,7 +96,7 @@ struct arm_pmu { void (*stop)(struct arm_pmu *); void (*reset)(void *); int (*map_event)(struct perf_event *event); - int num_events; + DECLARE_BITMAP(cntr_mask, ARMPMU_MAX_HWEVENTS); bool secure_access; /* 32-bit ARM only */ #define ARMV8_PMUV3_MAX_COMMON_EVENTS 0x40 DECLARE_BITMAP(pmceid_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS); diff --git a/include/linux/perf/arm_pmuv3.h b/include/linux/perf/arm_pmuv3.h index 7867db04ec98..eccbdd8eb98f 100644 --- a/include/linux/perf/arm_pmuv3.h +++ b/include/linux/perf/arm_pmuv3.h @@ -6,6 +6,7 @@ #ifndef __PERF_ARM_PMUV3_H #define __PERF_ARM_PMUV3_H +#define ARMV8_PMU_MAX_GENERAL_COUNTERS 31 #define ARMV8_PMU_MAX_COUNTERS 32 #define ARMV8_PMU_COUNTER_MASK (ARMV8_PMU_MAX_COUNTERS - 1) -- cgit v1.2.3 From f9b11aa00708d94a0cd78bfde34b68c0f95d8b50 Mon Sep 17 00:00:00 2001 From: "Rob Herring (Arm)" Date: Wed, 31 Jul 2024 10:51:21 -0600 Subject: KVM: arm64: pmu: Use generated define for PMSELR_EL0.SEL access ARMV8_PMU_COUNTER_MASK is really a mask for the PMSELR_EL0.SEL register field. Make that clear by adding a standard sysreg definition for the register, and using it instead. Reviewed-by: Mark Rutland Acked-by: Mark Rutland Reviewed-by: Marc Zyngier Signed-off-by: Rob Herring (Arm) Tested-by: James Clark Link: https://lore.kernel.org/r/20240731-arm-pmu-3-9-icntr-v3-4-280a8d7ff465@kernel.org Signed-off-by: Will Deacon --- arch/arm64/include/asm/sysreg.h | 1 - arch/arm64/kvm/sys_regs.c | 10 +++++----- arch/arm64/tools/sysreg | 5 +++++ include/linux/perf/arm_pmuv3.h | 1 - 4 files changed, 10 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 4a9ea103817e..00af1c331c1e 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -403,7 +403,6 @@ #define SYS_PMCNTENCLR_EL0 sys_reg(3, 3, 9, 12, 2) #define SYS_PMOVSCLR_EL0 sys_reg(3, 3, 9, 12, 3) #define SYS_PMSWINC_EL0 sys_reg(3, 3, 9, 12, 4) -#define SYS_PMSELR_EL0 sys_reg(3, 3, 9, 12, 5) #define SYS_PMCEID0_EL0 sys_reg(3, 3, 9, 12, 6) #define SYS_PMCEID1_EL0 sys_reg(3, 3, 9, 12, 7) #define SYS_PMCCNTR_EL0 sys_reg(3, 3, 9, 13, 0) diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index c90324060436..33497db257fb 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -887,7 +887,7 @@ static u64 reset_pmevtyper(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) static u64 reset_pmselr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { reset_unknown(vcpu, r); - __vcpu_sys_reg(vcpu, r->reg) &= ARMV8_PMU_COUNTER_MASK; + __vcpu_sys_reg(vcpu, r->reg) &= PMSELR_EL0_SEL_MASK; return __vcpu_sys_reg(vcpu, r->reg); } @@ -979,7 +979,7 @@ static bool access_pmselr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, else /* return PMSELR.SEL field */ p->regval = __vcpu_sys_reg(vcpu, PMSELR_EL0) - & ARMV8_PMU_COUNTER_MASK; + & PMSELR_EL0_SEL_MASK; return true; } @@ -1047,8 +1047,8 @@ static bool access_pmu_evcntr(struct kvm_vcpu *vcpu, if (pmu_access_event_counter_el0_disabled(vcpu)) return false; - idx = __vcpu_sys_reg(vcpu, PMSELR_EL0) - & ARMV8_PMU_COUNTER_MASK; + idx = SYS_FIELD_GET(PMSELR_EL0, SEL, + __vcpu_sys_reg(vcpu, PMSELR_EL0)); } else if (r->Op2 == 0) { /* PMCCNTR_EL0 */ if (pmu_access_cycle_counter_el0_disabled(vcpu)) @@ -1098,7 +1098,7 @@ static bool access_pmu_evtyper(struct kvm_vcpu *vcpu, struct sys_reg_params *p, if (r->CRn == 9 && r->CRm == 13 && r->Op2 == 1) { /* PMXEVTYPER_EL0 */ - idx = __vcpu_sys_reg(vcpu, PMSELR_EL0) & ARMV8_PMU_COUNTER_MASK; + idx = SYS_FIELD_GET(PMSELR_EL0, SEL, __vcpu_sys_reg(vcpu, PMSELR_EL0)); reg = PMEVTYPER0_EL0 + idx; } else if (r->CRn == 14 && (r->CRm & 12) == 12) { idx = ((r->CRm & 3) << 3) | (r->Op2 & 7); diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index 7ceaa1e0b4bc..37aa7eaad07b 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -2153,6 +2153,11 @@ Field 4 P Field 3:0 ALIGN EndSysreg +Sysreg PMSELR_EL0 3 3 9 12 5 +Res0 63:5 +Field 4:0 SEL +EndSysreg + SysregFields CONTEXTIDR_ELx Res0 63:32 Field 31:0 PROCID diff --git a/include/linux/perf/arm_pmuv3.h b/include/linux/perf/arm_pmuv3.h index eccbdd8eb98f..792b8e10b72a 100644 --- a/include/linux/perf/arm_pmuv3.h +++ b/include/linux/perf/arm_pmuv3.h @@ -8,7 +8,6 @@ #define ARMV8_PMU_MAX_GENERAL_COUNTERS 31 #define ARMV8_PMU_MAX_COUNTERS 32 -#define ARMV8_PMU_COUNTER_MASK (ARMV8_PMU_MAX_COUNTERS - 1) /* * Common architectural and microarchitectural event numbers. -- cgit v1.2.3 From 126d7d7cce5e048fb82477a9842d088d10ff0df6 Mon Sep 17 00:00:00 2001 From: "Rob Herring (Arm)" Date: Wed, 31 Jul 2024 10:51:22 -0600 Subject: arm64: perf/kvm: Use a common PMU cycle counter define The PMUv3 and KVM code each have a define for the PMU cycle counter index. Move KVM's define to a shared location and use it for PMUv3 driver. Reviewed-by: Marc Zyngier Acked-by: Mark Rutland Signed-off-by: Rob Herring (Arm) Tested-by: James Clark Link: https://lore.kernel.org/r/20240731-arm-pmu-3-9-icntr-v3-5-280a8d7ff465@kernel.org Signed-off-by: Will Deacon --- arch/arm64/kvm/sys_regs.c | 1 + drivers/perf/arm_pmuv3.c | 19 +++++++------------ include/kvm/arm_pmu.h | 1 - include/linux/perf/arm_pmuv3.h | 3 +++ 4 files changed, 11 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 33497db257fb..7db24de37ed6 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -18,6 +18,7 @@ #include #include +#include #include #include #include diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c index bd45fbcb9a5a..18046cf4b3a3 100644 --- a/drivers/perf/arm_pmuv3.c +++ b/drivers/perf/arm_pmuv3.c @@ -451,11 +451,6 @@ static const struct attribute_group armv8_pmuv3_caps_attr_group = { .attrs = armv8_pmuv3_caps_attrs, }; -/* - * Perf Events' indices - */ -#define ARMV8_IDX_CYCLE_COUNTER 31 - /* * We unconditionally enable ARMv8.5-PMU long event counter support * (64-bit events) where supported. Indicate if this arm_pmu has long @@ -574,7 +569,7 @@ static u64 armv8pmu_read_counter(struct perf_event *event) int idx = hwc->idx; u64 value; - if (idx == ARMV8_IDX_CYCLE_COUNTER) + if (idx == ARMV8_PMU_CYCLE_IDX) value = read_pmccntr(); else value = armv8pmu_read_hw_counter(event); @@ -607,7 +602,7 @@ static void armv8pmu_write_counter(struct perf_event *event, u64 value) value = armv8pmu_bias_long_counter(event, value); - if (idx == ARMV8_IDX_CYCLE_COUNTER) + if (idx == ARMV8_PMU_CYCLE_IDX) write_pmccntr(value); else armv8pmu_write_hw_counter(event, value); @@ -644,7 +639,7 @@ static void armv8pmu_write_event_type(struct perf_event *event) armv8pmu_write_evtype(idx - 1, hwc->config_base); armv8pmu_write_evtype(idx, chain_evt); } else { - if (idx == ARMV8_IDX_CYCLE_COUNTER) + if (idx == ARMV8_PMU_CYCLE_IDX) write_pmccfiltr(hwc->config_base); else armv8pmu_write_evtype(idx, hwc->config_base); @@ -772,7 +767,7 @@ static void armv8pmu_enable_user_access(struct arm_pmu *cpu_pmu) /* Clear any unused counters to avoid leaking their contents */ for_each_andnot_bit(i, cpu_pmu->cntr_mask, cpuc->used_mask, ARMPMU_MAX_HWEVENTS) { - if (i == ARMV8_IDX_CYCLE_COUNTER) + if (i == ARMV8_PMU_CYCLE_IDX) write_pmccntr(0); else armv8pmu_write_evcntr(i, 0); @@ -933,8 +928,8 @@ static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc, /* Always prefer to place a cycle counter into the cycle counter. */ if ((evtype == ARMV8_PMUV3_PERFCTR_CPU_CYCLES) && !armv8pmu_event_get_threshold(&event->attr)) { - if (!test_and_set_bit(ARMV8_IDX_CYCLE_COUNTER, cpuc->used_mask)) - return ARMV8_IDX_CYCLE_COUNTER; + if (!test_and_set_bit(ARMV8_PMU_CYCLE_IDX, cpuc->used_mask)) + return ARMV8_PMU_CYCLE_IDX; else if (armv8pmu_event_is_64bit(event) && armv8pmu_event_want_user_access(event) && !armv8pmu_has_long_event(cpu_pmu)) @@ -1196,7 +1191,7 @@ static void __armv8pmu_probe_pmu(void *info) 0, FIELD_GET(ARMV8_PMU_PMCR_N, armv8pmu_pmcr_read())); /* Add the CPU cycles counter */ - set_bit(ARMV8_IDX_CYCLE_COUNTER, cpu_pmu->cntr_mask); + set_bit(ARMV8_PMU_CYCLE_IDX, cpu_pmu->cntr_mask); pmceid[0] = pmceid_raw[0] = read_pmceid0(); pmceid[1] = pmceid_raw[1] = read_pmceid1(); diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index 334d7c5503cf..871067fb2616 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -10,7 +10,6 @@ #include #include -#define ARMV8_PMU_CYCLE_IDX (ARMV8_PMU_MAX_COUNTERS - 1) #if IS_ENABLED(CONFIG_HW_PERF_EVENTS) && IS_ENABLED(CONFIG_KVM) struct kvm_pmc { diff --git a/include/linux/perf/arm_pmuv3.h b/include/linux/perf/arm_pmuv3.h index 792b8e10b72a..f4ec76f725a3 100644 --- a/include/linux/perf/arm_pmuv3.h +++ b/include/linux/perf/arm_pmuv3.h @@ -9,6 +9,9 @@ #define ARMV8_PMU_MAX_GENERAL_COUNTERS 31 #define ARMV8_PMU_MAX_COUNTERS 32 +#define ARMV8_PMU_CYCLE_IDX 31 + + /* * Common architectural and microarchitectural event numbers. */ -- cgit v1.2.3 From 2f62701fa5b0ee94c68d2fcfc470d08aef195441 Mon Sep 17 00:00:00 2001 From: "Rob Herring (Arm)" Date: Wed, 31 Jul 2024 10:51:23 -0600 Subject: KVM: arm64: Refine PMU defines for number of counters There are 2 defines for the number of PMU counters: ARMV8_PMU_MAX_COUNTERS and ARMPMU_MAX_HWEVENTS. Both are the same currently, but Armv9.4/8.9 increases the number of possible counters from 32 to 33. With this change, the maximum number of counters will differ for KVM's PMU emulation which is PMUv3.4. Give KVM PMU emulation its own define to decouple it from the rest of the kernel's number PMU counters. The VHE PMU code needs to match the PMU driver, so switch it to use ARMPMU_MAX_HWEVENTS instead. Acked-by: Mark Rutland Reviewed-by: Marc Zyngier Signed-off-by: Rob Herring (Arm) Tested-by: James Clark Link: https://lore.kernel.org/r/20240731-arm-pmu-3-9-icntr-v3-6-280a8d7ff465@kernel.org Signed-off-by: Will Deacon --- arch/arm64/kvm/pmu-emul.c | 8 ++++---- arch/arm64/kvm/pmu.c | 5 +++-- include/kvm/arm_pmu.h | 3 ++- include/linux/perf/arm_pmuv3.h | 2 -- 4 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 0e598f6c42c0..ac36c438b8c1 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -233,7 +233,7 @@ void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu) int i; struct kvm_pmu *pmu = &vcpu->arch.pmu; - for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) + for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) pmu->pmc[i].idx = i; } @@ -260,7 +260,7 @@ void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu) { int i; - for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) + for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) kvm_pmu_release_perf_event(kvm_vcpu_idx_to_pmc(vcpu, i)); irq_work_sync(&vcpu->arch.pmu.overflow_work); } @@ -291,7 +291,7 @@ void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val) if (!(kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E) || !val) return; - for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) { + for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) { struct kvm_pmc *pmc; if (!(val & BIT(i))) @@ -323,7 +323,7 @@ void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val) if (!kvm_vcpu_has_pmu(vcpu) || !val) return; - for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) { + for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) { struct kvm_pmc *pmc; if (!(val & BIT(i))) diff --git a/arch/arm64/kvm/pmu.c b/arch/arm64/kvm/pmu.c index a47ae311d4a8..215b74875815 100644 --- a/arch/arm64/kvm/pmu.c +++ b/arch/arm64/kvm/pmu.c @@ -5,6 +5,7 @@ */ #include #include +#include #include static DEFINE_PER_CPU(struct kvm_pmu_events, kvm_pmu_events); @@ -95,7 +96,7 @@ static void kvm_vcpu_pmu_enable_el0(unsigned long events) u64 typer; u32 counter; - for_each_set_bit(counter, &events, 32) { + for_each_set_bit(counter, &events, ARMPMU_MAX_HWEVENTS) { typer = kvm_vcpu_pmu_read_evtype_direct(counter); typer &= ~ARMV8_PMU_EXCLUDE_EL0; kvm_vcpu_pmu_write_evtype_direct(counter, typer); @@ -110,7 +111,7 @@ static void kvm_vcpu_pmu_disable_el0(unsigned long events) u64 typer; u32 counter; - for_each_set_bit(counter, &events, 32) { + for_each_set_bit(counter, &events, ARMPMU_MAX_HWEVENTS) { typer = kvm_vcpu_pmu_read_evtype_direct(counter); typer |= ARMV8_PMU_EXCLUDE_EL0; kvm_vcpu_pmu_write_evtype_direct(counter, typer); diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index 871067fb2616..e08aeec5d936 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -10,6 +10,7 @@ #include #include +#define KVM_ARMV8_PMU_MAX_COUNTERS 32 #if IS_ENABLED(CONFIG_HW_PERF_EVENTS) && IS_ENABLED(CONFIG_KVM) struct kvm_pmc { @@ -25,7 +26,7 @@ struct kvm_pmu_events { struct kvm_pmu { struct irq_work overflow_work; struct kvm_pmu_events events; - struct kvm_pmc pmc[ARMV8_PMU_MAX_COUNTERS]; + struct kvm_pmc pmc[KVM_ARMV8_PMU_MAX_COUNTERS]; int irq_num; bool created; bool irq_level; diff --git a/include/linux/perf/arm_pmuv3.h b/include/linux/perf/arm_pmuv3.h index f4ec76f725a3..4f7a7f2222e5 100644 --- a/include/linux/perf/arm_pmuv3.h +++ b/include/linux/perf/arm_pmuv3.h @@ -7,8 +7,6 @@ #define __PERF_ARM_PMUV3_H #define ARMV8_PMU_MAX_GENERAL_COUNTERS 31 -#define ARMV8_PMU_MAX_COUNTERS 32 - #define ARMV8_PMU_CYCLE_IDX 31 -- cgit v1.2.3 From d8226d8cfbaf5eb9771af8ad8b4e58697e2ffb74 Mon Sep 17 00:00:00 2001 From: "Rob Herring (Arm)" Date: Wed, 31 Jul 2024 10:51:24 -0600 Subject: perf: arm_pmuv3: Add support for Armv9.4 PMU instruction counter Armv9.4/8.9 PMU adds optional support for a fixed instruction counter similar to the fixed cycle counter. Support for the feature is indicated in the ID_AA64DFR1_EL1 register PMICNTR field. The counter is not accessible in AArch32. Existing userspace using direct counter access won't know how to handle the fixed instruction counter, so we have to avoid using the counter when user access is requested. Acked-by: Mark Rutland Signed-off-by: Rob Herring (Arm) Tested-by: James Clark Link: https://lore.kernel.org/r/20240731-arm-pmu-3-9-icntr-v3-7-280a8d7ff465@kernel.org Signed-off-by: Will Deacon --- arch/arm/include/asm/arm_pmuv3.h | 20 ++++++++++++++++++++ arch/arm64/include/asm/arm_pmuv3.h | 28 ++++++++++++++++++++++++++++ arch/arm64/kvm/pmu.c | 8 ++++++-- arch/arm64/tools/sysreg | 25 +++++++++++++++++++++++++ drivers/perf/arm_pmuv3.c | 25 +++++++++++++++++++++++++ include/linux/perf/arm_pmu.h | 8 ++++++-- include/linux/perf/arm_pmuv3.h | 6 ++++-- 7 files changed, 114 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/include/asm/arm_pmuv3.h b/arch/arm/include/asm/arm_pmuv3.h index a41b503b7dcd..f63ba8986b24 100644 --- a/arch/arm/include/asm/arm_pmuv3.h +++ b/arch/arm/include/asm/arm_pmuv3.h @@ -127,6 +127,12 @@ static inline u32 read_pmuver(void) return (dfr0 >> 24) & 0xf; } +static inline bool pmuv3_has_icntr(void) +{ + /* FEAT_PMUv3_ICNTR not accessible for 32-bit */ + return false; +} + static inline void write_pmcr(u32 val) { write_sysreg(val, PMCR); @@ -152,6 +158,13 @@ static inline u64 read_pmccntr(void) return read_sysreg(PMCCNTR); } +static inline void write_pmicntr(u64 val) {} + +static inline u64 read_pmicntr(void) +{ + return 0; +} + static inline void write_pmcntenset(u32 val) { write_sysreg(val, PMCNTENSET); @@ -177,6 +190,13 @@ static inline void write_pmccfiltr(u32 val) write_sysreg(val, PMCCFILTR); } +static inline void write_pmicfiltr(u64 val) {} + +static inline u64 read_pmicfiltr(void) +{ + return 0; +} + static inline void write_pmovsclr(u32 val) { write_sysreg(val, PMOVSR); diff --git a/arch/arm64/include/asm/arm_pmuv3.h b/arch/arm64/include/asm/arm_pmuv3.h index 36c3e82b4eec..468a049bc63b 100644 --- a/arch/arm64/include/asm/arm_pmuv3.h +++ b/arch/arm64/include/asm/arm_pmuv3.h @@ -54,6 +54,14 @@ static inline u32 read_pmuver(void) ID_AA64DFR0_EL1_PMUVer_SHIFT); } +static inline bool pmuv3_has_icntr(void) +{ + u64 dfr1 = read_sysreg(id_aa64dfr1_el1); + + return !!cpuid_feature_extract_unsigned_field(dfr1, + ID_AA64DFR1_EL1_PMICNTR_SHIFT); +} + static inline void write_pmcr(u64 val) { write_sysreg(val, pmcr_el0); @@ -79,6 +87,16 @@ static inline u64 read_pmccntr(void) return read_sysreg(pmccntr_el0); } +static inline void write_pmicntr(u64 val) +{ + write_sysreg_s(val, SYS_PMICNTR_EL0); +} + +static inline u64 read_pmicntr(void) +{ + return read_sysreg_s(SYS_PMICNTR_EL0); +} + static inline void write_pmcntenset(u64 val) { write_sysreg(val, pmcntenset_el0); @@ -109,6 +127,16 @@ static inline u64 read_pmccfiltr(void) return read_sysreg(pmccfiltr_el0); } +static inline void write_pmicfiltr(u64 val) +{ + write_sysreg_s(val, SYS_PMICFILTR_EL0); +} + +static inline u64 read_pmicfiltr(void) +{ + return read_sysreg_s(SYS_PMICFILTR_EL0); +} + static inline void write_pmovsclr(u64 val) { write_sysreg(val, pmovsclr_el0); diff --git a/arch/arm64/kvm/pmu.c b/arch/arm64/kvm/pmu.c index 215b74875815..0b3adf3e17b4 100644 --- a/arch/arm64/kvm/pmu.c +++ b/arch/arm64/kvm/pmu.c @@ -66,24 +66,28 @@ void kvm_clr_pmu_events(u64 clr) /* * Read a value direct from PMEVTYPER where idx is 0-30 - * or PMCCFILTR_EL0 where idx is ARMV8_PMU_CYCLE_IDX (31). + * or PMxCFILTR_EL0 where idx is 31-32. */ static u64 kvm_vcpu_pmu_read_evtype_direct(int idx) { if (idx == ARMV8_PMU_CYCLE_IDX) return read_pmccfiltr(); + else if (idx == ARMV8_PMU_INSTR_IDX) + return read_pmicfiltr(); return read_pmevtypern(idx); } /* * Write a value direct to PMEVTYPER where idx is 0-30 - * or PMCCFILTR_EL0 where idx is ARMV8_PMU_CYCLE_IDX (31). + * or PMxCFILTR_EL0 where idx is 31-32. */ static void kvm_vcpu_pmu_write_evtype_direct(int idx, u32 val) { if (idx == ARMV8_PMU_CYCLE_IDX) write_pmccfiltr(val); + else if (idx == ARMV8_PMU_INSTR_IDX) + write_pmicfiltr(val); else write_pmevtypern(idx, val); } diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index 37aa7eaad07b..8d637ac4b7c6 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -2029,6 +2029,31 @@ Sysreg FAR_EL1 3 0 6 0 0 Field 63:0 ADDR EndSysreg +Sysreg PMICNTR_EL0 3 3 9 4 0 +Field 63:0 ICNT +EndSysreg + +Sysreg PMICFILTR_EL0 3 3 9 6 0 +Res0 63:59 +Field 58 SYNC +Field 57:56 VS +Res0 55:32 +Field 31 P +Field 30 U +Field 29 NSK +Field 28 NSU +Field 27 NSH +Field 26 M +Res0 25 +Field 24 SH +Field 23 T +Field 22 RLK +Field 21 RLU +Field 20 RLH +Res0 19:16 +Field 15:0 evtCount +EndSysreg + Sysreg PMSCR_EL1 3 0 9 9 0 Res0 63:8 Field 7:6 PCT diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c index 18046cf4b3a3..4d000532a07f 100644 --- a/drivers/perf/arm_pmuv3.c +++ b/drivers/perf/arm_pmuv3.c @@ -571,6 +571,8 @@ static u64 armv8pmu_read_counter(struct perf_event *event) if (idx == ARMV8_PMU_CYCLE_IDX) value = read_pmccntr(); + else if (idx == ARMV8_PMU_INSTR_IDX) + value = read_pmicntr(); else value = armv8pmu_read_hw_counter(event); @@ -604,6 +606,8 @@ static void armv8pmu_write_counter(struct perf_event *event, u64 value) if (idx == ARMV8_PMU_CYCLE_IDX) write_pmccntr(value); + else if (idx == ARMV8_PMU_INSTR_IDX) + write_pmicntr(value); else armv8pmu_write_hw_counter(event, value); } @@ -641,6 +645,8 @@ static void armv8pmu_write_event_type(struct perf_event *event) } else { if (idx == ARMV8_PMU_CYCLE_IDX) write_pmccfiltr(hwc->config_base); + else if (idx == ARMV8_PMU_INSTR_IDX) + write_pmicfiltr(hwc->config_base); else armv8pmu_write_evtype(idx, hwc->config_base); } @@ -769,6 +775,8 @@ static void armv8pmu_enable_user_access(struct arm_pmu *cpu_pmu) ARMPMU_MAX_HWEVENTS) { if (i == ARMV8_PMU_CYCLE_IDX) write_pmccntr(0); + else if (i == ARMV8_PMU_INSTR_IDX) + write_pmicntr(0); else armv8pmu_write_evcntr(i, 0); } @@ -936,6 +944,19 @@ static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc, return -EAGAIN; } + /* + * Always prefer to place a instruction counter into the instruction counter, + * but don't expose the instruction counter to userspace access as userspace + * may not know how to handle it. + */ + if ((evtype == ARMV8_PMUV3_PERFCTR_INST_RETIRED) && + !armv8pmu_event_get_threshold(&event->attr) && + test_bit(ARMV8_PMU_INSTR_IDX, cpu_pmu->cntr_mask) && + !armv8pmu_event_want_user_access(event)) { + if (!test_and_set_bit(ARMV8_PMU_INSTR_IDX, cpuc->used_mask)) + return ARMV8_PMU_INSTR_IDX; + } + /* * Otherwise use events counters */ @@ -1193,6 +1214,10 @@ static void __armv8pmu_probe_pmu(void *info) /* Add the CPU cycles counter */ set_bit(ARMV8_PMU_CYCLE_IDX, cpu_pmu->cntr_mask); + /* Add the CPU instructions counter */ + if (pmuv3_has_icntr()) + set_bit(ARMV8_PMU_INSTR_IDX, cpu_pmu->cntr_mask); + pmceid[0] = pmceid_raw[0] = read_pmceid0(); pmceid[1] = pmceid_raw[1] = read_pmceid1(); diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index e5d6d204beab..4b5b83677e3f 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -17,10 +17,14 @@ #ifdef CONFIG_ARM_PMU /* - * The ARMv7 CPU PMU supports up to 32 event counters. + * The Armv7 and Armv8.8 or less CPU PMU supports up to 32 event counters. + * The Armv8.9/9.4 CPU PMU supports up to 33 event counters. */ +#ifdef CONFIG_ARM #define ARMPMU_MAX_HWEVENTS 32 - +#else +#define ARMPMU_MAX_HWEVENTS 33 +#endif /* * ARM PMU hw_event flags */ diff --git a/include/linux/perf/arm_pmuv3.h b/include/linux/perf/arm_pmuv3.h index 4f7a7f2222e5..3372c1b56486 100644 --- a/include/linux/perf/arm_pmuv3.h +++ b/include/linux/perf/arm_pmuv3.h @@ -8,7 +8,7 @@ #define ARMV8_PMU_MAX_GENERAL_COUNTERS 31 #define ARMV8_PMU_CYCLE_IDX 31 - +#define ARMV8_PMU_INSTR_IDX 32 /* Not accessible from AArch32 */ /* * Common architectural and microarchitectural event numbers. @@ -228,8 +228,10 @@ */ #define ARMV8_PMU_OVSR_P GENMASK(30, 0) #define ARMV8_PMU_OVSR_C BIT(31) +#define ARMV8_PMU_OVSR_F BIT_ULL(32) /* arm64 only */ /* Mask for writable bits is both P and C fields */ -#define ARMV8_PMU_OVERFLOWED_MASK (ARMV8_PMU_OVSR_P | ARMV8_PMU_OVSR_C) +#define ARMV8_PMU_OVERFLOWED_MASK (ARMV8_PMU_OVSR_P | ARMV8_PMU_OVSR_C | \ + ARMV8_PMU_OVSR_F) /* * PMXEVTYPER: Event selection reg -- cgit v1.2.3 From fca5cb4dd2b4a9423cb6d112cc71c33899955a1f Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Sat, 10 Aug 2024 14:20:55 +0800 Subject: Revert "lib/mpi: Extend the MPI library" This partially reverts commit a8ea8bdd9df92a0e5db5b43900abb7a288b8a53e. Most of it is no longer needed since sm2 has been removed. However, the following functions have been kept as they have developed other uses: mpi_copy mpi_mod mpi_test_bit mpi_set_bit mpi_rshift mpi_add mpi_sub mpi_addm mpi_subm mpi_mul mpi_mulm mpi_tdiv_r mpi_fdiv_r Signed-off-by: Herbert Xu --- include/linux/mpi.h | 65 -------- lib/crypto/mpi/Makefile | 1 - lib/crypto/mpi/mpi-add.c | 51 ------- lib/crypto/mpi/mpi-bit.c | 143 ------------------ lib/crypto/mpi/mpi-cmp.c | 46 ++---- lib/crypto/mpi/mpi-div.c | 29 ---- lib/crypto/mpi/mpi-internal.h | 10 -- lib/crypto/mpi/mpi-inv.c | 143 ------------------ lib/crypto/mpi/mpi-mod.c | 144 ------------------ lib/crypto/mpi/mpicoder.c | 336 ------------------------------------------ lib/crypto/mpi/mpih-mul.c | 25 ---- lib/crypto/mpi/mpiutil.c | 182 ----------------------- 12 files changed, 10 insertions(+), 1165 deletions(-) delete mode 100644 lib/crypto/mpi/mpi-inv.c (limited to 'include/linux') diff --git a/include/linux/mpi.h b/include/linux/mpi.h index 89b720893e12..e081428b91ef 100644 --- a/include/linux/mpi.h +++ b/include/linux/mpi.h @@ -40,87 +40,33 @@ struct gcry_mpi { typedef struct gcry_mpi *MPI; #define mpi_get_nlimbs(a) ((a)->nlimbs) -#define mpi_has_sign(a) ((a)->sign) /*-- mpiutil.c --*/ MPI mpi_alloc(unsigned nlimbs); -void mpi_clear(MPI a); void mpi_free(MPI a); int mpi_resize(MPI a, unsigned nlimbs); -static inline MPI mpi_new(unsigned int nbits) -{ - return mpi_alloc((nbits + BITS_PER_MPI_LIMB - 1) / BITS_PER_MPI_LIMB); -} - MPI mpi_copy(MPI a); -MPI mpi_alloc_like(MPI a); -void mpi_snatch(MPI w, MPI u); -MPI mpi_set(MPI w, MPI u); -MPI mpi_set_ui(MPI w, unsigned long u); -MPI mpi_alloc_set_ui(unsigned long u); -void mpi_swap_cond(MPI a, MPI b, unsigned long swap); - -/* Constants used to return constant MPIs. See mpi_init if you - * want to add more constants. - */ -#define MPI_NUMBER_OF_CONSTANTS 6 -enum gcry_mpi_constants { - MPI_C_ZERO, - MPI_C_ONE, - MPI_C_TWO, - MPI_C_THREE, - MPI_C_FOUR, - MPI_C_EIGHT -}; - -MPI mpi_const(enum gcry_mpi_constants no); /*-- mpicoder.c --*/ - -/* Different formats of external big integer representation. */ -enum gcry_mpi_format { - GCRYMPI_FMT_NONE = 0, - GCRYMPI_FMT_STD = 1, /* Twos complement stored without length. */ - GCRYMPI_FMT_PGP = 2, /* As used by OpenPGP (unsigned only). */ - GCRYMPI_FMT_SSH = 3, /* As used by SSH (like STD but with length). */ - GCRYMPI_FMT_HEX = 4, /* Hex format. */ - GCRYMPI_FMT_USG = 5, /* Like STD but unsigned. */ - GCRYMPI_FMT_OPAQUE = 8 /* Opaque format (some functions only). */ -}; - MPI mpi_read_raw_data(const void *xbuffer, size_t nbytes); MPI mpi_read_from_buffer(const void *buffer, unsigned *ret_nread); -int mpi_fromstr(MPI val, const char *str); -MPI mpi_scanval(const char *string); MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int len); void *mpi_get_buffer(MPI a, unsigned *nbytes, int *sign); int mpi_read_buffer(MPI a, uint8_t *buf, unsigned buf_len, unsigned *nbytes, int *sign); int mpi_write_to_sgl(MPI a, struct scatterlist *sg, unsigned nbytes, int *sign); -int mpi_print(enum gcry_mpi_format format, unsigned char *buffer, - size_t buflen, size_t *nwritten, MPI a); /*-- mpi-mod.c --*/ void mpi_mod(MPI rem, MPI dividend, MPI divisor); -/* Context used with Barrett reduction. */ -struct barrett_ctx_s; -typedef struct barrett_ctx_s *mpi_barrett_t; - -mpi_barrett_t mpi_barrett_init(MPI m, int copy); -void mpi_barrett_free(mpi_barrett_t ctx); -void mpi_mod_barrett(MPI r, MPI x, mpi_barrett_t ctx); -void mpi_mul_barrett(MPI w, MPI u, MPI v, mpi_barrett_t ctx); - /*-- mpi-pow.c --*/ int mpi_powm(MPI res, MPI base, MPI exp, MPI mod); /*-- mpi-cmp.c --*/ int mpi_cmp_ui(MPI u, ulong v); int mpi_cmp(MPI u, MPI v); -int mpi_cmpabs(MPI u, MPI v); /*-- mpi-sub-ui.c --*/ int mpi_sub_ui(MPI w, MPI u, unsigned long vval); @@ -130,16 +76,9 @@ void mpi_normalize(MPI a); unsigned mpi_get_nbits(MPI a); int mpi_test_bit(MPI a, unsigned int n); void mpi_set_bit(MPI a, unsigned int n); -void mpi_set_highbit(MPI a, unsigned int n); -void mpi_clear_highbit(MPI a, unsigned int n); -void mpi_clear_bit(MPI a, unsigned int n); -void mpi_rshift_limbs(MPI a, unsigned int count); void mpi_rshift(MPI x, MPI a, unsigned int n); -void mpi_lshift_limbs(MPI a, unsigned int count); -void mpi_lshift(MPI x, MPI a, unsigned int n); /*-- mpi-add.c --*/ -void mpi_add_ui(MPI w, MPI u, unsigned long v); void mpi_add(MPI w, MPI u, MPI v); void mpi_sub(MPI w, MPI u, MPI v); void mpi_addm(MPI w, MPI u, MPI v, MPI m); @@ -152,10 +91,6 @@ void mpi_mulm(MPI w, MPI u, MPI v, MPI m); /*-- mpi-div.c --*/ void mpi_tdiv_r(MPI rem, MPI num, MPI den); void mpi_fdiv_r(MPI rem, MPI dividend, MPI divisor); -void mpi_fdiv_q(MPI quot, MPI dividend, MPI divisor); - -/*-- mpi-inv.c --*/ -int mpi_invm(MPI x, MPI a, MPI n); /* inline functions */ diff --git a/lib/crypto/mpi/Makefile b/lib/crypto/mpi/Makefile index 477debd7ed50..9ad84079025a 100644 --- a/lib/crypto/mpi/Makefile +++ b/lib/crypto/mpi/Makefile @@ -19,7 +19,6 @@ mpi-y = \ mpi-cmp.o \ mpi-sub-ui.o \ mpi-div.o \ - mpi-inv.o \ mpi-mod.o \ mpi-mul.o \ mpih-cmp.o \ diff --git a/lib/crypto/mpi/mpi-add.c b/lib/crypto/mpi/mpi-add.c index 9056fc5167fc..b47c8c35f5fe 100644 --- a/lib/crypto/mpi/mpi-add.c +++ b/lib/crypto/mpi/mpi-add.c @@ -13,57 +13,6 @@ #include "mpi-internal.h" -/**************** - * Add the unsigned integer V to the mpi-integer U and store the - * result in W. U and V may be the same. - */ -void mpi_add_ui(MPI w, MPI u, unsigned long v) -{ - mpi_ptr_t wp, up; - mpi_size_t usize, wsize; - int usign, wsign; - - usize = u->nlimbs; - usign = u->sign; - wsign = 0; - - /* If not space for W (and possible carry), increase space. */ - wsize = usize + 1; - if (w->alloced < wsize) - mpi_resize(w, wsize); - - /* These must be after realloc (U may be the same as W). */ - up = u->d; - wp = w->d; - - if (!usize) { /* simple */ - wp[0] = v; - wsize = v ? 1:0; - } else if (!usign) { /* mpi is not negative */ - mpi_limb_t cy; - cy = mpihelp_add_1(wp, up, usize, v); - wp[usize] = cy; - wsize = usize + cy; - } else { - /* The signs are different. Need exact comparison to determine - * which operand to subtract from which. - */ - if (usize == 1 && up[0] < v) { - wp[0] = v - up[0]; - wsize = 1; - } else { - mpihelp_sub_1(wp, up, usize, v); - /* Size can decrease with at most one limb. */ - wsize = usize - (wp[usize-1] == 0); - wsign = 1; - } - } - - w->nlimbs = wsize; - w->sign = wsign; -} - - void mpi_add(MPI w, MPI u, MPI v) { mpi_ptr_t wp, up, vp; diff --git a/lib/crypto/mpi/mpi-bit.c b/lib/crypto/mpi/mpi-bit.c index e08fc202ea5c..c29b85362664 100644 --- a/lib/crypto/mpi/mpi-bit.c +++ b/lib/crypto/mpi/mpi-bit.c @@ -32,7 +32,6 @@ void mpi_normalize(MPI a) for (; a->nlimbs && !a->d[a->nlimbs - 1]; a->nlimbs--) ; } -EXPORT_SYMBOL_GPL(mpi_normalize); /**************** * Return the number of bits in A. @@ -93,85 +92,6 @@ void mpi_set_bit(MPI a, unsigned int n) a->d[limbno] |= (A_LIMB_1<= a->nlimbs) { - for (i = a->nlimbs; i < a->alloced; i++) - a->d[i] = 0; - mpi_resize(a, limbno+1); - a->nlimbs = limbno+1; - } - a->d[limbno] |= (A_LIMB_1<d[limbno] &= ~(A_LIMB_1 << bitno); - a->nlimbs = limbno+1; -} -EXPORT_SYMBOL_GPL(mpi_set_highbit); - -/**************** - * clear bit N of A and all bits above - */ -void mpi_clear_highbit(MPI a, unsigned int n) -{ - unsigned int limbno, bitno; - - limbno = n / BITS_PER_MPI_LIMB; - bitno = n % BITS_PER_MPI_LIMB; - - if (limbno >= a->nlimbs) - return; /* not allocated, therefore no need to clear bits :-) */ - - for ( ; bitno < BITS_PER_MPI_LIMB; bitno++) - a->d[limbno] &= ~(A_LIMB_1 << bitno); - a->nlimbs = limbno+1; -} - -/**************** - * Clear bit N of A. - */ -void mpi_clear_bit(MPI a, unsigned int n) -{ - unsigned int limbno, bitno; - - limbno = n / BITS_PER_MPI_LIMB; - bitno = n % BITS_PER_MPI_LIMB; - - if (limbno >= a->nlimbs) - return; /* Don't need to clear this bit, it's far too left. */ - a->d[limbno] &= ~(A_LIMB_1 << bitno); -} -EXPORT_SYMBOL_GPL(mpi_clear_bit); - - -/**************** - * Shift A by COUNT limbs to the right - * This is used only within the MPI library - */ -void mpi_rshift_limbs(MPI a, unsigned int count) -{ - mpi_ptr_t ap = a->d; - mpi_size_t n = a->nlimbs; - unsigned int i; - - if (count >= n) { - a->nlimbs = 0; - return; - } - - for (i = 0; i < n - count; i++) - ap[i] = ap[i+count]; - ap[i] = 0; - a->nlimbs -= count; -} - /* * Shift A by N bits to the right. */ @@ -241,66 +161,3 @@ void mpi_rshift(MPI x, MPI a, unsigned int n) MPN_NORMALIZE(x->d, x->nlimbs); } EXPORT_SYMBOL_GPL(mpi_rshift); - -/**************** - * Shift A by COUNT limbs to the left - * This is used only within the MPI library - */ -void mpi_lshift_limbs(MPI a, unsigned int count) -{ - mpi_ptr_t ap; - int n = a->nlimbs; - int i; - - if (!count || !n) - return; - - RESIZE_IF_NEEDED(a, n+count); - - ap = a->d; - for (i = n-1; i >= 0; i--) - ap[i+count] = ap[i]; - for (i = 0; i < count; i++) - ap[i] = 0; - a->nlimbs += count; -} - -/* - * Shift A by N bits to the left. - */ -void mpi_lshift(MPI x, MPI a, unsigned int n) -{ - unsigned int nlimbs = (n/BITS_PER_MPI_LIMB); - unsigned int nbits = (n%BITS_PER_MPI_LIMB); - - if (x == a && !n) - return; /* In-place shift with an amount of zero. */ - - if (x != a) { - /* Copy A to X. */ - unsigned int alimbs = a->nlimbs; - int asign = a->sign; - mpi_ptr_t xp, ap; - - RESIZE_IF_NEEDED(x, alimbs+nlimbs+1); - xp = x->d; - ap = a->d; - MPN_COPY(xp, ap, alimbs); - x->nlimbs = alimbs; - x->flags = a->flags; - x->sign = asign; - } - - if (nlimbs && !nbits) { - /* Shift a full number of limbs. */ - mpi_lshift_limbs(x, nlimbs); - } else if (n) { - /* We use a very dump approach: Shift left by the number of - * limbs plus one and than fix it up by an rshift. - */ - mpi_lshift_limbs(x, nlimbs+1); - mpi_rshift(x, x, BITS_PER_MPI_LIMB - nbits); - } - - MPN_NORMALIZE(x->d, x->nlimbs); -} diff --git a/lib/crypto/mpi/mpi-cmp.c b/lib/crypto/mpi/mpi-cmp.c index 0835b6213235..ceaebe181cd7 100644 --- a/lib/crypto/mpi/mpi-cmp.c +++ b/lib/crypto/mpi/mpi-cmp.c @@ -45,54 +45,28 @@ int mpi_cmp_ui(MPI u, unsigned long v) } EXPORT_SYMBOL_GPL(mpi_cmp_ui); -static int do_mpi_cmp(MPI u, MPI v, int absmode) +int mpi_cmp(MPI u, MPI v) { - mpi_size_t usize; - mpi_size_t vsize; - int usign; - int vsign; + mpi_size_t usize, vsize; int cmp; mpi_normalize(u); mpi_normalize(v); - usize = u->nlimbs; vsize = v->nlimbs; - usign = absmode ? 0 : u->sign; - vsign = absmode ? 0 : v->sign; - - /* Compare sign bits. */ - - if (!usign && vsign) + if (!u->sign && v->sign) return 1; - if (usign && !vsign) + if (u->sign && !v->sign) return -1; - - /* U and V are either both positive or both negative. */ - - if (usize != vsize && !usign && !vsign) + if (usize != vsize && !u->sign && !v->sign) return usize - vsize; - if (usize != vsize && usign && vsign) - return vsize + usize; + if (usize != vsize && u->sign && v->sign) + return vsize - usize; if (!usize) return 0; cmp = mpihelp_cmp(u->d, v->d, usize); - if (!cmp) - return 0; - if ((cmp < 0?1:0) == (usign?1:0)) - return 1; - - return -1; -} - -int mpi_cmp(MPI u, MPI v) -{ - return do_mpi_cmp(u, v, 0); + if (u->sign) + return -cmp; + return cmp; } EXPORT_SYMBOL_GPL(mpi_cmp); - -int mpi_cmpabs(MPI u, MPI v) -{ - return do_mpi_cmp(u, v, 1); -} -EXPORT_SYMBOL_GPL(mpi_cmpabs); diff --git a/lib/crypto/mpi/mpi-div.c b/lib/crypto/mpi/mpi-div.c index 45beab8b9e9e..2ff0ebd74fd7 100644 --- a/lib/crypto/mpi/mpi-div.c +++ b/lib/crypto/mpi/mpi-div.c @@ -15,7 +15,6 @@ #include "longlong.h" void mpi_tdiv_qr(MPI quot, MPI rem, MPI num, MPI den); -void mpi_fdiv_qr(MPI quot, MPI rem, MPI dividend, MPI divisor); void mpi_fdiv_r(MPI rem, MPI dividend, MPI divisor) { @@ -40,34 +39,6 @@ void mpi_fdiv_r(MPI rem, MPI dividend, MPI divisor) mpi_free(temp_divisor); } -void mpi_fdiv_q(MPI quot, MPI dividend, MPI divisor) -{ - MPI tmp = mpi_alloc(mpi_get_nlimbs(quot)); - mpi_fdiv_qr(quot, tmp, dividend, divisor); - mpi_free(tmp); -} - -void mpi_fdiv_qr(MPI quot, MPI rem, MPI dividend, MPI divisor) -{ - int divisor_sign = divisor->sign; - MPI temp_divisor = NULL; - - if (quot == divisor || rem == divisor) { - temp_divisor = mpi_copy(divisor); - divisor = temp_divisor; - } - - mpi_tdiv_qr(quot, rem, dividend, divisor); - - if ((divisor_sign ^ dividend->sign) && rem->nlimbs) { - mpi_sub_ui(quot, quot, 1); - mpi_add(rem, rem, divisor); - } - - if (temp_divisor) - mpi_free(temp_divisor); -} - /* If den == quot, den needs temporary storage. * If den == rem, den needs temporary storage. * If num == quot, num needs temporary storage. diff --git a/lib/crypto/mpi/mpi-internal.h b/lib/crypto/mpi/mpi-internal.h index 554002182db1..b6fbb43afbc8 100644 --- a/lib/crypto/mpi/mpi-internal.h +++ b/lib/crypto/mpi/mpi-internal.h @@ -66,14 +66,6 @@ typedef int mpi_size_t; /* (must be a signed type) */ (d)[_i] = (s)[_i]; \ } while (0) -#define MPN_COPY_INCR(d, s, n) \ - do { \ - mpi_size_t _i; \ - for (_i = 0; _i < (n); _i++) \ - (d)[_i] = (s)[_i]; \ - } while (0) - - #define MPN_COPY_DECR(d, s, n) \ do { \ mpi_size_t _i; \ @@ -181,8 +173,6 @@ int mpihelp_mul(mpi_ptr_t prodp, mpi_ptr_t up, mpi_size_t usize, void mpih_sqr_n_basecase(mpi_ptr_t prodp, mpi_ptr_t up, mpi_size_t size); void mpih_sqr_n(mpi_ptr_t prodp, mpi_ptr_t up, mpi_size_t size, mpi_ptr_t tspace); -void mpihelp_mul_n(mpi_ptr_t prodp, - mpi_ptr_t up, mpi_ptr_t vp, mpi_size_t size); int mpihelp_mul_karatsuba_case(mpi_ptr_t prodp, mpi_ptr_t up, mpi_size_t usize, diff --git a/lib/crypto/mpi/mpi-inv.c b/lib/crypto/mpi/mpi-inv.c deleted file mode 100644 index 61e37d18f793..000000000000 --- a/lib/crypto/mpi/mpi-inv.c +++ /dev/null @@ -1,143 +0,0 @@ -/* mpi-inv.c - MPI functions - * Copyright (C) 1998, 2001, 2002, 2003 Free Software Foundation, Inc. - * - * This file is part of Libgcrypt. - * - * Libgcrypt is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as - * published by the Free Software Foundation; either version 2.1 of - * the License, or (at your option) any later version. - * - * Libgcrypt is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this program; if not, see . - */ - -#include "mpi-internal.h" - -/**************** - * Calculate the multiplicative inverse X of A mod N - * That is: Find the solution x for - * 1 = (a*x) mod n - */ -int mpi_invm(MPI x, MPI a, MPI n) -{ - /* Extended Euclid's algorithm (See TAOCP Vol II, 4.5.2, Alg X) - * modified according to Michael Penk's solution for Exercise 35 - * with further enhancement - */ - MPI u, v, u1, u2 = NULL, u3, v1, v2 = NULL, v3, t1, t2 = NULL, t3; - unsigned int k; - int sign; - int odd; - - if (!mpi_cmp_ui(a, 0)) - return 0; /* Inverse does not exists. */ - if (!mpi_cmp_ui(n, 1)) - return 0; /* Inverse does not exists. */ - - u = mpi_copy(a); - v = mpi_copy(n); - - for (k = 0; !mpi_test_bit(u, 0) && !mpi_test_bit(v, 0); k++) { - mpi_rshift(u, u, 1); - mpi_rshift(v, v, 1); - } - odd = mpi_test_bit(v, 0); - - u1 = mpi_alloc_set_ui(1); - if (!odd) - u2 = mpi_alloc_set_ui(0); - u3 = mpi_copy(u); - v1 = mpi_copy(v); - if (!odd) { - v2 = mpi_alloc(mpi_get_nlimbs(u)); - mpi_sub(v2, u1, u); /* U is used as const 1 */ - } - v3 = mpi_copy(v); - if (mpi_test_bit(u, 0)) { /* u is odd */ - t1 = mpi_alloc_set_ui(0); - if (!odd) { - t2 = mpi_alloc_set_ui(1); - t2->sign = 1; - } - t3 = mpi_copy(v); - t3->sign = !t3->sign; - goto Y4; - } else { - t1 = mpi_alloc_set_ui(1); - if (!odd) - t2 = mpi_alloc_set_ui(0); - t3 = mpi_copy(u); - } - - do { - do { - if (!odd) { - if (mpi_test_bit(t1, 0) || mpi_test_bit(t2, 0)) { - /* one is odd */ - mpi_add(t1, t1, v); - mpi_sub(t2, t2, u); - } - mpi_rshift(t1, t1, 1); - mpi_rshift(t2, t2, 1); - mpi_rshift(t3, t3, 1); - } else { - if (mpi_test_bit(t1, 0)) - mpi_add(t1, t1, v); - mpi_rshift(t1, t1, 1); - mpi_rshift(t3, t3, 1); - } -Y4: - ; - } while (!mpi_test_bit(t3, 0)); /* while t3 is even */ - - if (!t3->sign) { - mpi_set(u1, t1); - if (!odd) - mpi_set(u2, t2); - mpi_set(u3, t3); - } else { - mpi_sub(v1, v, t1); - sign = u->sign; u->sign = !u->sign; - if (!odd) - mpi_sub(v2, u, t2); - u->sign = sign; - sign = t3->sign; t3->sign = !t3->sign; - mpi_set(v3, t3); - t3->sign = sign; - } - mpi_sub(t1, u1, v1); - if (!odd) - mpi_sub(t2, u2, v2); - mpi_sub(t3, u3, v3); - if (t1->sign) { - mpi_add(t1, t1, v); - if (!odd) - mpi_sub(t2, t2, u); - } - } while (mpi_cmp_ui(t3, 0)); /* while t3 != 0 */ - /* mpi_lshift( u3, k ); */ - mpi_set(x, u1); - - mpi_free(u1); - mpi_free(v1); - mpi_free(t1); - if (!odd) { - mpi_free(u2); - mpi_free(v2); - mpi_free(t2); - } - mpi_free(u3); - mpi_free(v3); - mpi_free(t3); - - mpi_free(u); - mpi_free(v); - return 1; -} -EXPORT_SYMBOL_GPL(mpi_invm); diff --git a/lib/crypto/mpi/mpi-mod.c b/lib/crypto/mpi/mpi-mod.c index 54fcc01564d9..691bbdc52fc6 100644 --- a/lib/crypto/mpi/mpi-mod.c +++ b/lib/crypto/mpi/mpi-mod.c @@ -5,153 +5,9 @@ * This file is part of Libgcrypt. */ - #include "mpi-internal.h" -#include "longlong.h" - -/* Context used with Barrett reduction. */ -struct barrett_ctx_s { - MPI m; /* The modulus - may not be modified. */ - int m_copied; /* If true, M needs to be released. */ - int k; - MPI y; - MPI r1; /* Helper MPI. */ - MPI r2; /* Helper MPI. */ - MPI r3; /* Helper MPI allocated on demand. */ -}; - - void mpi_mod(MPI rem, MPI dividend, MPI divisor) { mpi_fdiv_r(rem, dividend, divisor); } - -/* This function returns a new context for Barrett based operations on - * the modulus M. This context needs to be released using - * _gcry_mpi_barrett_free. If COPY is true M will be transferred to - * the context and the user may change M. If COPY is false, M may not - * be changed until gcry_mpi_barrett_free has been called. - */ -mpi_barrett_t mpi_barrett_init(MPI m, int copy) -{ - mpi_barrett_t ctx; - MPI tmp; - - mpi_normalize(m); - ctx = kcalloc(1, sizeof(*ctx), GFP_KERNEL); - if (!ctx) - return NULL; - - if (copy) { - ctx->m = mpi_copy(m); - ctx->m_copied = 1; - } else - ctx->m = m; - - ctx->k = mpi_get_nlimbs(m); - tmp = mpi_alloc(ctx->k + 1); - - /* Barrett precalculation: y = floor(b^(2k) / m). */ - mpi_set_ui(tmp, 1); - mpi_lshift_limbs(tmp, 2 * ctx->k); - mpi_fdiv_q(tmp, tmp, m); - - ctx->y = tmp; - ctx->r1 = mpi_alloc(2 * ctx->k + 1); - ctx->r2 = mpi_alloc(2 * ctx->k + 1); - - return ctx; -} - -void mpi_barrett_free(mpi_barrett_t ctx) -{ - if (ctx) { - mpi_free(ctx->y); - mpi_free(ctx->r1); - mpi_free(ctx->r2); - if (ctx->r3) - mpi_free(ctx->r3); - if (ctx->m_copied) - mpi_free(ctx->m); - kfree(ctx); - } -} - - -/* R = X mod M - * - * Using Barrett reduction. Before using this function - * _gcry_mpi_barrett_init must have been called to do the - * precalculations. CTX is the context created by this precalculation - * and also conveys M. If the Barret reduction could no be done a - * straightforward reduction method is used. - * - * We assume that these conditions are met: - * Input: x =(x_2k-1 ...x_0)_b - * m =(m_k-1 ....m_0)_b with m_k-1 != 0 - * Output: r = x mod m - */ -void mpi_mod_barrett(MPI r, MPI x, mpi_barrett_t ctx) -{ - MPI m = ctx->m; - int k = ctx->k; - MPI y = ctx->y; - MPI r1 = ctx->r1; - MPI r2 = ctx->r2; - int sign; - - mpi_normalize(x); - if (mpi_get_nlimbs(x) > 2*k) { - mpi_mod(r, x, m); - return; - } - - sign = x->sign; - x->sign = 0; - - /* 1. q1 = floor( x / b^k-1) - * q2 = q1 * y - * q3 = floor( q2 / b^k+1 ) - * Actually, we don't need qx, we can work direct on r2 - */ - mpi_set(r2, x); - mpi_rshift_limbs(r2, k-1); - mpi_mul(r2, r2, y); - mpi_rshift_limbs(r2, k+1); - - /* 2. r1 = x mod b^k+1 - * r2 = q3 * m mod b^k+1 - * r = r1 - r2 - * 3. if r < 0 then r = r + b^k+1 - */ - mpi_set(r1, x); - if (r1->nlimbs > k+1) /* Quick modulo operation. */ - r1->nlimbs = k+1; - mpi_mul(r2, r2, m); - if (r2->nlimbs > k+1) /* Quick modulo operation. */ - r2->nlimbs = k+1; - mpi_sub(r, r1, r2); - - if (mpi_has_sign(r)) { - if (!ctx->r3) { - ctx->r3 = mpi_alloc(k + 2); - mpi_set_ui(ctx->r3, 1); - mpi_lshift_limbs(ctx->r3, k + 1); - } - mpi_add(r, r, ctx->r3); - } - - /* 4. while r >= m do r = r - m */ - while (mpi_cmp(r, m) >= 0) - mpi_sub(r, r, m); - - x->sign = sign; -} - - -void mpi_mul_barrett(MPI w, MPI u, MPI v, mpi_barrett_t ctx) -{ - mpi_mul(w, u, v); - mpi_mod_barrett(w, w, ctx); -} diff --git a/lib/crypto/mpi/mpicoder.c b/lib/crypto/mpi/mpicoder.c index 3cb6bd148fa9..dde01030807d 100644 --- a/lib/crypto/mpi/mpicoder.c +++ b/lib/crypto/mpi/mpicoder.c @@ -25,7 +25,6 @@ #include #include "mpi-internal.h" -#define MAX_EXTERN_SCAN_BYTES (16*1024*1024) #define MAX_EXTERN_MPI_BITS 16384 /** @@ -110,112 +109,6 @@ MPI mpi_read_from_buffer(const void *xbuffer, unsigned *ret_nread) } EXPORT_SYMBOL_GPL(mpi_read_from_buffer); -/**************** - * Fill the mpi VAL from the hex string in STR. - */ -int mpi_fromstr(MPI val, const char *str) -{ - int sign = 0; - int prepend_zero = 0; - int i, j, c, c1, c2; - unsigned int nbits, nbytes, nlimbs; - mpi_limb_t a; - - if (*str == '-') { - sign = 1; - str++; - } - - /* Skip optional hex prefix. */ - if (*str == '0' && str[1] == 'x') - str += 2; - - nbits = strlen(str); - if (nbits > MAX_EXTERN_SCAN_BYTES) { - mpi_clear(val); - return -EINVAL; - } - nbits *= 4; - if ((nbits % 8)) - prepend_zero = 1; - - nbytes = (nbits+7) / 8; - nlimbs = (nbytes+BYTES_PER_MPI_LIMB-1) / BYTES_PER_MPI_LIMB; - - if (val->alloced < nlimbs) - mpi_resize(val, nlimbs); - - i = BYTES_PER_MPI_LIMB - (nbytes % BYTES_PER_MPI_LIMB); - i %= BYTES_PER_MPI_LIMB; - j = val->nlimbs = nlimbs; - val->sign = sign; - for (; j > 0; j--) { - a = 0; - for (; i < BYTES_PER_MPI_LIMB; i++) { - if (prepend_zero) { - c1 = '0'; - prepend_zero = 0; - } else - c1 = *str++; - - if (!c1) { - mpi_clear(val); - return -EINVAL; - } - c2 = *str++; - if (!c2) { - mpi_clear(val); - return -EINVAL; - } - if (c1 >= '0' && c1 <= '9') - c = c1 - '0'; - else if (c1 >= 'a' && c1 <= 'f') - c = c1 - 'a' + 10; - else if (c1 >= 'A' && c1 <= 'F') - c = c1 - 'A' + 10; - else { - mpi_clear(val); - return -EINVAL; - } - c <<= 4; - if (c2 >= '0' && c2 <= '9') - c |= c2 - '0'; - else if (c2 >= 'a' && c2 <= 'f') - c |= c2 - 'a' + 10; - else if (c2 >= 'A' && c2 <= 'F') - c |= c2 - 'A' + 10; - else { - mpi_clear(val); - return -EINVAL; - } - a <<= 8; - a |= c; - } - i = 0; - val->d[j-1] = a; - } - - return 0; -} -EXPORT_SYMBOL_GPL(mpi_fromstr); - -MPI mpi_scanval(const char *string) -{ - MPI a; - - a = mpi_alloc(0); - if (!a) - return NULL; - - if (mpi_fromstr(a, string)) { - mpi_free(a); - return NULL; - } - mpi_normalize(a); - return a; -} -EXPORT_SYMBOL_GPL(mpi_scanval); - static int count_lzeros(MPI a) { mpi_limb_t alimb; @@ -521,232 +414,3 @@ MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int nbytes) return val; } EXPORT_SYMBOL_GPL(mpi_read_raw_from_sgl); - -/* Perform a two's complement operation on buffer P of size N bytes. */ -static void twocompl(unsigned char *p, unsigned int n) -{ - int i; - - for (i = n-1; i >= 0 && !p[i]; i--) - ; - if (i >= 0) { - if ((p[i] & 0x01)) - p[i] = (((p[i] ^ 0xfe) | 0x01) & 0xff); - else if ((p[i] & 0x02)) - p[i] = (((p[i] ^ 0xfc) | 0x02) & 0xfe); - else if ((p[i] & 0x04)) - p[i] = (((p[i] ^ 0xf8) | 0x04) & 0xfc); - else if ((p[i] & 0x08)) - p[i] = (((p[i] ^ 0xf0) | 0x08) & 0xf8); - else if ((p[i] & 0x10)) - p[i] = (((p[i] ^ 0xe0) | 0x10) & 0xf0); - else if ((p[i] & 0x20)) - p[i] = (((p[i] ^ 0xc0) | 0x20) & 0xe0); - else if ((p[i] & 0x40)) - p[i] = (((p[i] ^ 0x80) | 0x40) & 0xc0); - else - p[i] = 0x80; - - for (i--; i >= 0; i--) - p[i] ^= 0xff; - } -} - -int mpi_print(enum gcry_mpi_format format, unsigned char *buffer, - size_t buflen, size_t *nwritten, MPI a) -{ - unsigned int nbits = mpi_get_nbits(a); - size_t len; - size_t dummy_nwritten; - int negative; - - if (!nwritten) - nwritten = &dummy_nwritten; - - /* Libgcrypt does no always care to set clear the sign if the value - * is 0. For printing this is a bit of a surprise, in particular - * because if some of the formats don't support negative numbers but - * should be able to print a zero. Thus we need this extra test - * for a negative number. - */ - if (a->sign && mpi_cmp_ui(a, 0)) - negative = 1; - else - negative = 0; - - len = buflen; - *nwritten = 0; - if (format == GCRYMPI_FMT_STD) { - unsigned char *tmp; - int extra = 0; - unsigned int n; - - tmp = mpi_get_buffer(a, &n, NULL); - if (!tmp) - return -EINVAL; - - if (negative) { - twocompl(tmp, n); - if (!(*tmp & 0x80)) { - /* Need to extend the sign. */ - n++; - extra = 2; - } - } else if (n && (*tmp & 0x80)) { - /* Positive but the high bit of the returned buffer is set. - * Thus we need to print an extra leading 0x00 so that the - * output is interpreted as a positive number. - */ - n++; - extra = 1; - } - - if (buffer && n > len) { - /* The provided buffer is too short. */ - kfree(tmp); - return -E2BIG; - } - if (buffer) { - unsigned char *s = buffer; - - if (extra == 1) - *s++ = 0; - else if (extra) - *s++ = 0xff; - memcpy(s, tmp, n-!!extra); - } - kfree(tmp); - *nwritten = n; - return 0; - } else if (format == GCRYMPI_FMT_USG) { - unsigned int n = (nbits + 7)/8; - - /* Note: We ignore the sign for this format. */ - /* FIXME: for performance reasons we should put this into - * mpi_aprint because we can then use the buffer directly. - */ - - if (buffer && n > len) - return -E2BIG; - if (buffer) { - unsigned char *tmp; - - tmp = mpi_get_buffer(a, &n, NULL); - if (!tmp) - return -EINVAL; - memcpy(buffer, tmp, n); - kfree(tmp); - } - *nwritten = n; - return 0; - } else if (format == GCRYMPI_FMT_PGP) { - unsigned int n = (nbits + 7)/8; - - /* The PGP format can only handle unsigned integers. */ - if (negative) - return -EINVAL; - - if (buffer && n+2 > len) - return -E2BIG; - - if (buffer) { - unsigned char *tmp; - unsigned char *s = buffer; - - s[0] = nbits >> 8; - s[1] = nbits; - - tmp = mpi_get_buffer(a, &n, NULL); - if (!tmp) - return -EINVAL; - memcpy(s+2, tmp, n); - kfree(tmp); - } - *nwritten = n+2; - return 0; - } else if (format == GCRYMPI_FMT_SSH) { - unsigned char *tmp; - int extra = 0; - unsigned int n; - - tmp = mpi_get_buffer(a, &n, NULL); - if (!tmp) - return -EINVAL; - - if (negative) { - twocompl(tmp, n); - if (!(*tmp & 0x80)) { - /* Need to extend the sign. */ - n++; - extra = 2; - } - } else if (n && (*tmp & 0x80)) { - n++; - extra = 1; - } - - if (buffer && n+4 > len) { - kfree(tmp); - return -E2BIG; - } - - if (buffer) { - unsigned char *s = buffer; - - *s++ = n >> 24; - *s++ = n >> 16; - *s++ = n >> 8; - *s++ = n; - if (extra == 1) - *s++ = 0; - else if (extra) - *s++ = 0xff; - memcpy(s, tmp, n-!!extra); - } - kfree(tmp); - *nwritten = 4+n; - return 0; - } else if (format == GCRYMPI_FMT_HEX) { - unsigned char *tmp; - int i; - int extra = 0; - unsigned int n = 0; - - tmp = mpi_get_buffer(a, &n, NULL); - if (!tmp) - return -EINVAL; - if (!n || (*tmp & 0x80)) - extra = 2; - - if (buffer && 2*n + extra + negative + 1 > len) { - kfree(tmp); - return -E2BIG; - } - if (buffer) { - unsigned char *s = buffer; - - if (negative) - *s++ = '-'; - if (extra) { - *s++ = '0'; - *s++ = '0'; - } - - for (i = 0; i < n; i++) { - unsigned int c = tmp[i]; - - *s++ = (c >> 4) < 10 ? '0'+(c>>4) : 'A'+(c>>4)-10; - c &= 15; - *s++ = c < 10 ? '0'+c : 'A'+c-10; - } - *s++ = 0; - *nwritten = s - buffer; - } else { - *nwritten = 2*n + extra + negative + 1; - } - kfree(tmp); - return 0; - } else - return -EINVAL; -} -EXPORT_SYMBOL_GPL(mpi_print); diff --git a/lib/crypto/mpi/mpih-mul.c b/lib/crypto/mpi/mpih-mul.c index e5f1c84e3c48..a93647564054 100644 --- a/lib/crypto/mpi/mpih-mul.c +++ b/lib/crypto/mpi/mpih-mul.c @@ -317,31 +317,6 @@ mpih_sqr_n(mpi_ptr_t prodp, mpi_ptr_t up, mpi_size_t size, mpi_ptr_t tspace) } } - -void mpihelp_mul_n(mpi_ptr_t prodp, - mpi_ptr_t up, mpi_ptr_t vp, mpi_size_t size) -{ - if (up == vp) { - if (size < KARATSUBA_THRESHOLD) - mpih_sqr_n_basecase(prodp, up, size); - else { - mpi_ptr_t tspace; - tspace = mpi_alloc_limb_space(2 * size); - mpih_sqr_n(prodp, up, size, tspace); - mpi_free_limb_space(tspace); - } - } else { - if (size < KARATSUBA_THRESHOLD) - mul_n_basecase(prodp, up, vp, size); - else { - mpi_ptr_t tspace; - tspace = mpi_alloc_limb_space(2 * size); - mul_n(prodp, up, vp, size, tspace); - mpi_free_limb_space(tspace); - } - } -} - int mpihelp_mul_karatsuba_case(mpi_ptr_t prodp, mpi_ptr_t up, mpi_size_t usize, diff --git a/lib/crypto/mpi/mpiutil.c b/lib/crypto/mpi/mpiutil.c index aa8c46544af8..d57fd8afef64 100644 --- a/lib/crypto/mpi/mpiutil.c +++ b/lib/crypto/mpi/mpiutil.c @@ -20,63 +20,6 @@ #include "mpi-internal.h" -/* Constants allocated right away at startup. */ -static MPI constants[MPI_NUMBER_OF_CONSTANTS]; - -/* Initialize the MPI subsystem. This is called early and allows to - * do some initialization without taking care of threading issues. - */ -static int __init mpi_init(void) -{ - int idx; - unsigned long value; - - for (idx = 0; idx < MPI_NUMBER_OF_CONSTANTS; idx++) { - switch (idx) { - case MPI_C_ZERO: - value = 0; - break; - case MPI_C_ONE: - value = 1; - break; - case MPI_C_TWO: - value = 2; - break; - case MPI_C_THREE: - value = 3; - break; - case MPI_C_FOUR: - value = 4; - break; - case MPI_C_EIGHT: - value = 8; - break; - default: - pr_err("MPI: invalid mpi_const selector %d\n", idx); - return -EFAULT; - } - constants[idx] = mpi_alloc_set_ui(value); - constants[idx]->flags = (16|32); - } - - return 0; -} -postcore_initcall(mpi_init); - -/* Return a constant MPI descripbed by NO which is one of the - * MPI_C_xxx macros. There is no need to copy this returned value; it - * may be used directly. - */ -MPI mpi_const(enum gcry_mpi_constants no) -{ - if ((int)no < 0 || no > MPI_NUMBER_OF_CONSTANTS) - pr_err("MPI: invalid mpi_const selector %d\n", no); - if (!constants[no]) - pr_err("MPI: MPI subsystem not initialized\n"); - return constants[no]; -} -EXPORT_SYMBOL_GPL(mpi_const); - /**************** * Note: It was a bad idea to use the number of limbs to allocate * because on a alpha the limbs are large but we normally need @@ -163,15 +106,6 @@ int mpi_resize(MPI a, unsigned nlimbs) return 0; } -void mpi_clear(MPI a) -{ - if (!a) - return; - a->nlimbs = 0; - a->flags = 0; -} -EXPORT_SYMBOL_GPL(mpi_clear); - void mpi_free(MPI a) { if (!a) @@ -210,121 +144,5 @@ MPI mpi_copy(MPI a) return b; } -/**************** - * This function allocates an MPI which is optimized to hold - * a value as large as the one given in the argument and allocates it - * with the same flags as A. - */ -MPI mpi_alloc_like(MPI a) -{ - MPI b; - - if (a) { - b = mpi_alloc(a->nlimbs); - b->nlimbs = 0; - b->sign = 0; - b->flags = a->flags; - } else - b = NULL; - - return b; -} - - -/* Set U into W and release U. If W is NULL only U will be released. */ -void mpi_snatch(MPI w, MPI u) -{ - if (w) { - mpi_assign_limb_space(w, u->d, u->alloced); - w->nlimbs = u->nlimbs; - w->sign = u->sign; - w->flags = u->flags; - u->alloced = 0; - u->nlimbs = 0; - u->d = NULL; - } - mpi_free(u); -} - - -MPI mpi_set(MPI w, MPI u) -{ - mpi_ptr_t wp, up; - mpi_size_t usize = u->nlimbs; - int usign = u->sign; - - if (!w) - w = mpi_alloc(mpi_get_nlimbs(u)); - RESIZE_IF_NEEDED(w, usize); - wp = w->d; - up = u->d; - MPN_COPY(wp, up, usize); - w->nlimbs = usize; - w->flags = u->flags; - w->flags &= ~(16|32); /* Reset the immutable and constant flags. */ - w->sign = usign; - return w; -} -EXPORT_SYMBOL_GPL(mpi_set); - -MPI mpi_set_ui(MPI w, unsigned long u) -{ - if (!w) - w = mpi_alloc(1); - /* FIXME: If U is 0 we have no need to resize and thus possible - * allocating the limbs. - */ - RESIZE_IF_NEEDED(w, 1); - w->d[0] = u; - w->nlimbs = u ? 1 : 0; - w->sign = 0; - w->flags = 0; - return w; -} -EXPORT_SYMBOL_GPL(mpi_set_ui); - -MPI mpi_alloc_set_ui(unsigned long u) -{ - MPI w = mpi_alloc(1); - w->d[0] = u; - w->nlimbs = u ? 1 : 0; - w->sign = 0; - return w; -} - -/**************** - * Swap the value of A and B, when SWAP is 1. - * Leave the value when SWAP is 0. - * This implementation should be constant-time regardless of SWAP. - */ -void mpi_swap_cond(MPI a, MPI b, unsigned long swap) -{ - mpi_size_t i; - mpi_size_t nlimbs; - mpi_limb_t mask = ((mpi_limb_t)0) - swap; - mpi_limb_t x; - - if (a->alloced > b->alloced) - nlimbs = b->alloced; - else - nlimbs = a->alloced; - if (a->nlimbs > nlimbs || b->nlimbs > nlimbs) - return; - - for (i = 0; i < nlimbs; i++) { - x = mask & (a->d[i] ^ b->d[i]); - a->d[i] = a->d[i] ^ x; - b->d[i] = b->d[i] ^ x; - } - - x = mask & (a->nlimbs ^ b->nlimbs); - a->nlimbs = a->nlimbs ^ x; - b->nlimbs = b->nlimbs ^ x; - - x = mask & (a->sign ^ b->sign); - a->sign = a->sign ^ x; - b->sign = b->sign ^ x; -} - MODULE_DESCRIPTION("Multiprecision maths library"); MODULE_LICENSE("GPL"); -- cgit v1.2.3 From 8e3a67f2de87ee94ac11ea69beb4edc2993b17a0 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Sat, 10 Aug 2024 14:20:57 +0800 Subject: crypto: lib/mpi - Add error checks to extension The remaining functions added by commit a8ea8bdd9df92a0e5db5b43900abb7a288b8a53e did not check for memory allocation errors. Add the checks and change the API to allow errors to be returned. Fixes: a8ea8bdd9df9 ("lib/mpi: Extend the MPI library") Signed-off-by: Herbert Xu --- include/linux/mpi.h | 22 ++++++++--------- lib/crypto/mpi/mpi-add.c | 38 ++++++++++++++++++++---------- lib/crypto/mpi/mpi-bit.c | 25 ++++++++++++++------ lib/crypto/mpi/mpi-div.c | 55 +++++++++++++++++++++++++++++++------------ lib/crypto/mpi/mpi-internal.h | 11 +++++---- lib/crypto/mpi/mpi-mod.c | 4 ++-- lib/crypto/mpi/mpi-mul.c | 29 ++++++++++++++++++----- lib/crypto/mpi/mpiutil.c | 2 ++ 8 files changed, 128 insertions(+), 58 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mpi.h b/include/linux/mpi.h index e081428b91ef..47be46f36435 100644 --- a/include/linux/mpi.h +++ b/include/linux/mpi.h @@ -59,7 +59,7 @@ int mpi_write_to_sgl(MPI a, struct scatterlist *sg, unsigned nbytes, int *sign); /*-- mpi-mod.c --*/ -void mpi_mod(MPI rem, MPI dividend, MPI divisor); +int mpi_mod(MPI rem, MPI dividend, MPI divisor); /*-- mpi-pow.c --*/ int mpi_powm(MPI res, MPI base, MPI exp, MPI mod); @@ -75,22 +75,22 @@ int mpi_sub_ui(MPI w, MPI u, unsigned long vval); void mpi_normalize(MPI a); unsigned mpi_get_nbits(MPI a); int mpi_test_bit(MPI a, unsigned int n); -void mpi_set_bit(MPI a, unsigned int n); -void mpi_rshift(MPI x, MPI a, unsigned int n); +int mpi_set_bit(MPI a, unsigned int n); +int mpi_rshift(MPI x, MPI a, unsigned int n); /*-- mpi-add.c --*/ -void mpi_add(MPI w, MPI u, MPI v); -void mpi_sub(MPI w, MPI u, MPI v); -void mpi_addm(MPI w, MPI u, MPI v, MPI m); -void mpi_subm(MPI w, MPI u, MPI v, MPI m); +int mpi_add(MPI w, MPI u, MPI v); +int mpi_sub(MPI w, MPI u, MPI v); +int mpi_addm(MPI w, MPI u, MPI v, MPI m); +int mpi_subm(MPI w, MPI u, MPI v, MPI m); /*-- mpi-mul.c --*/ -void mpi_mul(MPI w, MPI u, MPI v); -void mpi_mulm(MPI w, MPI u, MPI v, MPI m); +int mpi_mul(MPI w, MPI u, MPI v); +int mpi_mulm(MPI w, MPI u, MPI v, MPI m); /*-- mpi-div.c --*/ -void mpi_tdiv_r(MPI rem, MPI num, MPI den); -void mpi_fdiv_r(MPI rem, MPI dividend, MPI divisor); +int mpi_tdiv_r(MPI rem, MPI num, MPI den); +int mpi_fdiv_r(MPI rem, MPI dividend, MPI divisor); /* inline functions */ diff --git a/lib/crypto/mpi/mpi-add.c b/lib/crypto/mpi/mpi-add.c index b47c8c35f5fe..3015140d4860 100644 --- a/lib/crypto/mpi/mpi-add.c +++ b/lib/crypto/mpi/mpi-add.c @@ -13,11 +13,12 @@ #include "mpi-internal.h" -void mpi_add(MPI w, MPI u, MPI v) +int mpi_add(MPI w, MPI u, MPI v) { mpi_ptr_t wp, up, vp; mpi_size_t usize, vsize, wsize; int usign, vsign, wsign; + int err; if (u->nlimbs < v->nlimbs) { /* Swap U and V. */ usize = v->nlimbs; @@ -25,7 +26,9 @@ void mpi_add(MPI w, MPI u, MPI v) vsize = u->nlimbs; vsign = u->sign; wsize = usize + 1; - RESIZE_IF_NEEDED(w, wsize); + err = RESIZE_IF_NEEDED(w, wsize); + if (err) + return err; /* These must be after realloc (u or v may be the same as w). */ up = v->d; vp = u->d; @@ -35,7 +38,9 @@ void mpi_add(MPI w, MPI u, MPI v) vsize = v->nlimbs; vsign = v->sign; wsize = usize + 1; - RESIZE_IF_NEEDED(w, wsize); + err = RESIZE_IF_NEEDED(w, wsize); + if (err) + return err; /* These must be after realloc (u or v may be the same as w). */ up = u->d; vp = v->d; @@ -77,28 +82,37 @@ void mpi_add(MPI w, MPI u, MPI v) w->nlimbs = wsize; w->sign = wsign; + return 0; } EXPORT_SYMBOL_GPL(mpi_add); -void mpi_sub(MPI w, MPI u, MPI v) +int mpi_sub(MPI w, MPI u, MPI v) { - MPI vv = mpi_copy(v); + int err; + MPI vv; + + vv = mpi_copy(v); + if (!vv) + return -ENOMEM; + vv->sign = !vv->sign; - mpi_add(w, u, vv); + err = mpi_add(w, u, vv); mpi_free(vv); + + return err; } EXPORT_SYMBOL_GPL(mpi_sub); -void mpi_addm(MPI w, MPI u, MPI v, MPI m) +int mpi_addm(MPI w, MPI u, MPI v, MPI m) { - mpi_add(w, u, v); - mpi_mod(w, w, m); + return mpi_add(w, u, v) ?: + mpi_mod(w, w, m); } EXPORT_SYMBOL_GPL(mpi_addm); -void mpi_subm(MPI w, MPI u, MPI v, MPI m) +int mpi_subm(MPI w, MPI u, MPI v, MPI m) { - mpi_sub(w, u, v); - mpi_mod(w, w, m); + return mpi_sub(w, u, v) ?: + mpi_mod(w, w, m); } EXPORT_SYMBOL_GPL(mpi_subm); diff --git a/lib/crypto/mpi/mpi-bit.c b/lib/crypto/mpi/mpi-bit.c index c29b85362664..835a2f0622a0 100644 --- a/lib/crypto/mpi/mpi-bit.c +++ b/lib/crypto/mpi/mpi-bit.c @@ -76,9 +76,10 @@ EXPORT_SYMBOL_GPL(mpi_test_bit); /**************** * Set bit N of A. */ -void mpi_set_bit(MPI a, unsigned int n) +int mpi_set_bit(MPI a, unsigned int n) { unsigned int i, limbno, bitno; + int err; limbno = n / BITS_PER_MPI_LIMB; bitno = n % BITS_PER_MPI_LIMB; @@ -86,27 +87,31 @@ void mpi_set_bit(MPI a, unsigned int n) if (limbno >= a->nlimbs) { for (i = a->nlimbs; i < a->alloced; i++) a->d[i] = 0; - mpi_resize(a, limbno+1); + err = mpi_resize(a, limbno+1); + if (err) + return err; a->nlimbs = limbno+1; } a->d[limbno] |= (A_LIMB_1<= x->nlimbs) { x->nlimbs = 0; - return; + return 0; } if (nlimbs) { @@ -121,7 +126,9 @@ void mpi_rshift(MPI x, MPI a, unsigned int n) /* Copy and shift by more or equal bits than in a limb. */ xsize = a->nlimbs; x->sign = a->sign; - RESIZE_IF_NEEDED(x, xsize); + err = RESIZE_IF_NEEDED(x, xsize); + if (err) + return err; x->nlimbs = xsize; for (i = 0; i < a->nlimbs; i++) x->d[i] = a->d[i]; @@ -129,7 +136,7 @@ void mpi_rshift(MPI x, MPI a, unsigned int n) if (nlimbs >= x->nlimbs) { x->nlimbs = 0; - return; + return 0; } for (i = 0; i < x->nlimbs - nlimbs; i++) @@ -143,7 +150,9 @@ void mpi_rshift(MPI x, MPI a, unsigned int n) /* Copy and shift by less than bits in a limb. */ xsize = a->nlimbs; x->sign = a->sign; - RESIZE_IF_NEEDED(x, xsize); + err = RESIZE_IF_NEEDED(x, xsize); + if (err) + return err; x->nlimbs = xsize; if (xsize) { @@ -159,5 +168,7 @@ void mpi_rshift(MPI x, MPI a, unsigned int n) } } MPN_NORMALIZE(x->d, x->nlimbs); + + return 0; } EXPORT_SYMBOL_GPL(mpi_rshift); diff --git a/lib/crypto/mpi/mpi-div.c b/lib/crypto/mpi/mpi-div.c index 2ff0ebd74fd7..6e5044e72595 100644 --- a/lib/crypto/mpi/mpi-div.c +++ b/lib/crypto/mpi/mpi-div.c @@ -14,12 +14,13 @@ #include "mpi-internal.h" #include "longlong.h" -void mpi_tdiv_qr(MPI quot, MPI rem, MPI num, MPI den); +int mpi_tdiv_qr(MPI quot, MPI rem, MPI num, MPI den); -void mpi_fdiv_r(MPI rem, MPI dividend, MPI divisor) +int mpi_fdiv_r(MPI rem, MPI dividend, MPI divisor) { int divisor_sign = divisor->sign; MPI temp_divisor = NULL; + int err; /* We need the original value of the divisor after the remainder has been * preliminary calculated. We have to copy it to temporary space if it's @@ -27,16 +28,22 @@ void mpi_fdiv_r(MPI rem, MPI dividend, MPI divisor) */ if (rem == divisor) { temp_divisor = mpi_copy(divisor); + if (!temp_divisor) + return -ENOMEM; divisor = temp_divisor; } - mpi_tdiv_r(rem, dividend, divisor); + err = mpi_tdiv_r(rem, dividend, divisor); + if (err) + goto free_temp_divisor; if (((divisor_sign?1:0) ^ (dividend->sign?1:0)) && rem->nlimbs) - mpi_add(rem, rem, divisor); + err = mpi_add(rem, rem, divisor); - if (temp_divisor) - mpi_free(temp_divisor); +free_temp_divisor: + mpi_free(temp_divisor); + + return err; } /* If den == quot, den needs temporary storage. @@ -46,12 +53,12 @@ void mpi_fdiv_r(MPI rem, MPI dividend, MPI divisor) * i.e no extra storage should be allocated. */ -void mpi_tdiv_r(MPI rem, MPI num, MPI den) +int mpi_tdiv_r(MPI rem, MPI num, MPI den) { - mpi_tdiv_qr(NULL, rem, num, den); + return mpi_tdiv_qr(NULL, rem, num, den); } -void mpi_tdiv_qr(MPI quot, MPI rem, MPI num, MPI den) +int mpi_tdiv_qr(MPI quot, MPI rem, MPI num, MPI den) { mpi_ptr_t np, dp; mpi_ptr_t qp, rp; @@ -64,13 +71,16 @@ void mpi_tdiv_qr(MPI quot, MPI rem, MPI num, MPI den) mpi_limb_t q_limb; mpi_ptr_t marker[5]; int markidx = 0; + int err; /* Ensure space is enough for quotient and remainder. * We need space for an extra limb in the remainder, because it's * up-shifted (normalized) below. */ rsize = nsize + 1; - mpi_resize(rem, rsize); + err = mpi_resize(rem, rsize); + if (err) + return err; qsize = rsize - dsize; /* qsize cannot be bigger than this. */ if (qsize <= 0) { @@ -86,11 +96,14 @@ void mpi_tdiv_qr(MPI quot, MPI rem, MPI num, MPI den) quot->nlimbs = 0; quot->sign = 0; } - return; + return 0; } - if (quot) - mpi_resize(quot, qsize); + if (quot) { + err = mpi_resize(quot, qsize); + if (err) + return err; + } /* Read pointers here, when reallocation is finished. */ np = num->d; @@ -112,10 +125,10 @@ void mpi_tdiv_qr(MPI quot, MPI rem, MPI num, MPI den) rsize = rlimb != 0?1:0; rem->nlimbs = rsize; rem->sign = sign_remainder; - return; + return 0; } - + err = -ENOMEM; if (quot) { qp = quot->d; /* Make sure QP and NP point to different objects. Otherwise the @@ -123,6 +136,8 @@ void mpi_tdiv_qr(MPI quot, MPI rem, MPI num, MPI den) */ if (qp == np) { /* Copy NP object to temporary space. */ np = marker[markidx++] = mpi_alloc_limb_space(nsize); + if (!np) + goto out_free_marker; MPN_COPY(np, qp, nsize); } } else /* Put quotient at top of remainder. */ @@ -143,6 +158,8 @@ void mpi_tdiv_qr(MPI quot, MPI rem, MPI num, MPI den) * the original contents of the denominator. */ tp = marker[markidx++] = mpi_alloc_limb_space(dsize); + if (!tp) + goto out_free_marker; mpihelp_lshift(tp, dp, dsize, normalization_steps); dp = tp; @@ -164,6 +181,8 @@ void mpi_tdiv_qr(MPI quot, MPI rem, MPI num, MPI den) mpi_ptr_t tp; tp = marker[markidx++] = mpi_alloc_limb_space(dsize); + if (!tp) + goto out_free_marker; MPN_COPY(tp, dp, dsize); dp = tp; } @@ -198,8 +217,14 @@ void mpi_tdiv_qr(MPI quot, MPI rem, MPI num, MPI den) rem->nlimbs = rsize; rem->sign = sign_remainder; + + err = 0; + +out_free_marker: while (markidx) { markidx--; mpi_free_limb_space(marker[markidx]); } + + return err; } diff --git a/lib/crypto/mpi/mpi-internal.h b/lib/crypto/mpi/mpi-internal.h index b6fbb43afbc8..8a4f49e3043c 100644 --- a/lib/crypto/mpi/mpi-internal.h +++ b/lib/crypto/mpi/mpi-internal.h @@ -52,11 +52,12 @@ typedef mpi_limb_t *mpi_ptr_t; /* pointer to a limb */ typedef int mpi_size_t; /* (must be a signed type) */ -#define RESIZE_IF_NEEDED(a, b) \ - do { \ - if ((a)->alloced < (b)) \ - mpi_resize((a), (b)); \ - } while (0) +static inline int RESIZE_IF_NEEDED(MPI a, unsigned b) +{ + if (a->alloced < b) + return mpi_resize(a, b); + return 0; +} /* Copy N limbs from S to D. */ #define MPN_COPY(d, s, n) \ diff --git a/lib/crypto/mpi/mpi-mod.c b/lib/crypto/mpi/mpi-mod.c index 691bbdc52fc6..d5fdaec3d0b6 100644 --- a/lib/crypto/mpi/mpi-mod.c +++ b/lib/crypto/mpi/mpi-mod.c @@ -7,7 +7,7 @@ #include "mpi-internal.h" -void mpi_mod(MPI rem, MPI dividend, MPI divisor) +int mpi_mod(MPI rem, MPI dividend, MPI divisor) { - mpi_fdiv_r(rem, dividend, divisor); + return mpi_fdiv_r(rem, dividend, divisor); } diff --git a/lib/crypto/mpi/mpi-mul.c b/lib/crypto/mpi/mpi-mul.c index 7f4eda8560dc..892a246216b9 100644 --- a/lib/crypto/mpi/mpi-mul.c +++ b/lib/crypto/mpi/mpi-mul.c @@ -13,7 +13,7 @@ #include "mpi-internal.h" -void mpi_mul(MPI w, MPI u, MPI v) +int mpi_mul(MPI w, MPI u, MPI v) { mpi_size_t usize, vsize, wsize; mpi_ptr_t up, vp, wp; @@ -21,6 +21,7 @@ void mpi_mul(MPI w, MPI u, MPI v) int usign, vsign, sign_product; int assign_wp = 0; mpi_ptr_t tmp_limb = NULL; + int err; if (u->nlimbs < v->nlimbs) { /* Swap U and V. */ @@ -46,15 +47,21 @@ void mpi_mul(MPI w, MPI u, MPI v) if (w->alloced < wsize) { if (wp == up || wp == vp) { wp = mpi_alloc_limb_space(wsize); + if (!wp) + return -ENOMEM; assign_wp = 1; } else { - mpi_resize(w, wsize); + err = mpi_resize(w, wsize); + if (err) + return err; wp = w->d; } } else { /* Make U and V not overlap with W. */ if (wp == up) { /* W and U are identical. Allocate temporary space for U. */ up = tmp_limb = mpi_alloc_limb_space(usize); + if (!up) + return -ENOMEM; /* Is V identical too? Keep it identical with U. */ if (wp == vp) vp = up; @@ -63,6 +70,8 @@ void mpi_mul(MPI w, MPI u, MPI v) } else if (wp == vp) { /* W and V are identical. Allocate temporary space for V. */ vp = tmp_limb = mpi_alloc_limb_space(vsize); + if (!vp) + return -ENOMEM; /* Copy to the temporary space. */ MPN_COPY(vp, wp, vsize); } @@ -71,7 +80,12 @@ void mpi_mul(MPI w, MPI u, MPI v) if (!vsize) wsize = 0; else { - mpihelp_mul(wp, up, usize, vp, vsize, &cy); + err = mpihelp_mul(wp, up, usize, vp, vsize, &cy); + if (err) { + if (assign_wp) + mpi_free_limb_space(wp); + goto free_tmp_limb; + } wsize -= cy ? 0:1; } @@ -79,14 +93,17 @@ void mpi_mul(MPI w, MPI u, MPI v) mpi_assign_limb_space(w, wp, wsize); w->nlimbs = wsize; w->sign = sign_product; + +free_tmp_limb: if (tmp_limb) mpi_free_limb_space(tmp_limb); + return err; } EXPORT_SYMBOL_GPL(mpi_mul); -void mpi_mulm(MPI w, MPI u, MPI v, MPI m) +int mpi_mulm(MPI w, MPI u, MPI v, MPI m) { - mpi_mul(w, u, v); - mpi_tdiv_r(w, w, m); + return mpi_mul(w, u, v) ?: + mpi_tdiv_r(w, w, m); } EXPORT_SYMBOL_GPL(mpi_mulm); diff --git a/lib/crypto/mpi/mpiutil.c b/lib/crypto/mpi/mpiutil.c index d57fd8afef64..979ece5a81d2 100644 --- a/lib/crypto/mpi/mpiutil.c +++ b/lib/crypto/mpi/mpiutil.c @@ -133,6 +133,8 @@ MPI mpi_copy(MPI a) if (a) { b = mpi_alloc(a->nlimbs); + if (!b) + return NULL; b->nlimbs = a->nlimbs; b->sign = a->sign; b->flags = a->flags; -- cgit v1.2.3 From abc158c82ae555078aa5dd2d8407c3df0f868904 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 23 May 2024 10:55:59 +0200 Subject: sched: Prepare generic code for delayed dequeue While most of the delayed dequeue code can be done inside the sched_class itself, there is one location where we do not have an appropriate hook, namely ttwu_runnable(). Add an ENQUEUE_DELAYED call to the on_rq path to deal with waking delayed dequeue tasks. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Valentin Schneider Tested-by: Valentin Schneider Link: https://lkml.kernel.org/r/20240727105029.200000445@infradead.org --- include/linux/sched.h | 1 + kernel/sched/core.c | 14 +++++++++++++- kernel/sched/sched.h | 2 ++ 3 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 2c1b4ee3234f..f4a648e739e1 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -544,6 +544,7 @@ struct sched_entity { struct list_head group_node; unsigned int on_rq; + unsigned int sched_delayed; u64 exec_start; u64 sum_exec_runtime; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 6c595485bcbc..7356464155a1 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2036,6 +2036,8 @@ void activate_task(struct rq *rq, struct task_struct *p, int flags) void deactivate_task(struct rq *rq, struct task_struct *p, int flags) { + SCHED_WARN_ON(flags & DEQUEUE_SLEEP); + WRITE_ONCE(p->on_rq, TASK_ON_RQ_MIGRATING); ASSERT_EXCLUSIVE_WRITER(p->on_rq); @@ -3689,12 +3691,14 @@ static int ttwu_runnable(struct task_struct *p, int wake_flags) rq = __task_rq_lock(p, &rf); if (task_on_rq_queued(p)) { + update_rq_clock(rq); + if (p->se.sched_delayed) + enqueue_task(rq, p, ENQUEUE_NOCLOCK | ENQUEUE_DELAYED); if (!task_on_cpu(rq, p)) { /* * When on_rq && !on_cpu the task is preempted, see if * it should preempt the task that is current now. */ - update_rq_clock(rq); wakeup_preempt(rq, p, wake_flags); } ttwu_do_wakeup(p); @@ -4074,11 +4078,16 @@ int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) * case the whole 'p->on_rq && ttwu_runnable()' case below * without taking any locks. * + * Specifically, given current runs ttwu() we must be before + * schedule()'s block_task(), as such this must not observe + * sched_delayed. + * * In particular: * - we rely on Program-Order guarantees for all the ordering, * - we're serialized against set_special_state() by virtue of * it disabling IRQs (this allows not taking ->pi_lock). */ + SCHED_WARN_ON(p->se.sched_delayed); if (!ttwu_state_match(p, state, &success)) goto out; @@ -4370,6 +4379,9 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) p->se.slice = sysctl_sched_base_slice; INIT_LIST_HEAD(&p->se.group_node); + /* A delayed task cannot be in clone(). */ + SCHED_WARN_ON(p->se.sched_delayed); + #ifdef CONFIG_FAIR_GROUP_SCHED p->se.cfs_rq = NULL; #endif diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 69ab3b0289c0..ffca9779519c 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -2253,6 +2253,7 @@ extern const u32 sched_prio_to_wmult[40]; #define DEQUEUE_MOVE 0x04 /* Matches ENQUEUE_MOVE */ #define DEQUEUE_NOCLOCK 0x08 /* Matches ENQUEUE_NOCLOCK */ #define DEQUEUE_MIGRATING 0x100 /* Matches ENQUEUE_MIGRATING */ +#define DEQUEUE_DELAYED 0x200 /* Matches ENQUEUE_DELAYED */ #define ENQUEUE_WAKEUP 0x01 #define ENQUEUE_RESTORE 0x02 @@ -2268,6 +2269,7 @@ extern const u32 sched_prio_to_wmult[40]; #endif #define ENQUEUE_INITIAL 0x80 #define ENQUEUE_MIGRATING 0x100 +#define ENQUEUE_DELAYED 0x200 #define RETRY_TASK ((void *)-1UL) -- cgit v1.2.3 From a1c446611e31ca5363d4db51e398271da1dce0af Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 1 Jul 2024 21:30:09 +0200 Subject: sched,freezer: Mark TASK_FROZEN special The special task states are those that do not suffer spurious wakeups, TASK_FROZEN is very much one of those, mark it as such. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Valentin Schneider Tested-by: Valentin Schneider Link: https://lkml.kernel.org/r/20240727105029.998329901@infradead.org --- include/linux/sched.h | 5 +++-- kernel/freezer.c | 2 +- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index f4a648e739e1..8a3a389bd623 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -149,8 +149,9 @@ struct user_event_mm; * Special states are those that do not use the normal wait-loop pattern. See * the comment with set_special_state(). */ -#define is_special_task_state(state) \ - ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | TASK_DEAD)) +#define is_special_task_state(state) \ + ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | \ + TASK_DEAD | TASK_FROZEN)) #ifdef CONFIG_DEBUG_ATOMIC_SLEEP # define debug_normal_state_change(state_value) \ diff --git a/kernel/freezer.c b/kernel/freezer.c index f57aaf96b829..44bbd7dbd2c8 100644 --- a/kernel/freezer.c +++ b/kernel/freezer.c @@ -72,7 +72,7 @@ bool __refrigerator(bool check_kthr_stop) bool freeze; raw_spin_lock_irq(¤t->pi_lock); - set_current_state(TASK_FROZEN); + WRITE_ONCE(current->__state, TASK_FROZEN); /* unstale saved_state so that __thaw_task() will wake us up */ current->saved_state = TASK_RUNNING; raw_spin_unlock_irq(¤t->pi_lock); -- cgit v1.2.3 From 82e9d0456e06cebe2c89f3c73cdbc9e3805e9437 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 31 May 2024 15:49:40 +0200 Subject: sched/fair: Avoid re-setting virtual deadline on 'migrations' During OSPM24 Youssef noted that migrations are re-setting the virtual deadline. Notably everything that does a dequeue-enqueue, like setting nice, changing preferred numa-node, and a myriad of other random crap, will cause this to happen. This shouldn't be. Preserve the relative virtual deadline across such dequeue/enqueue cycles. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Valentin Schneider Tested-by: Valentin Schneider Link: https://lkml.kernel.org/r/20240727105030.625119246@infradead.org --- include/linux/sched.h | 6 ++++-- kernel/sched/fair.c | 23 ++++++++++++++++++----- kernel/sched/features.h | 4 ++++ 3 files changed, 26 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 8a3a389bd623..d25e1cfd5766 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -544,8 +544,10 @@ struct sched_entity { u64 min_vruntime; struct list_head group_node; - unsigned int on_rq; - unsigned int sched_delayed; + unsigned char on_rq; + unsigned char sched_delayed; + unsigned char rel_deadline; + /* hole */ u64 exec_start; u64 sum_exec_runtime; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 0eb1bbf7f269..fef0e1f26cd8 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5270,6 +5270,12 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) se->vruntime = vruntime - lag; + if (sched_feat(PLACE_REL_DEADLINE) && se->rel_deadline) { + se->deadline += se->vruntime; + se->rel_deadline = 0; + return; + } + /* * When joining the competition; the existing tasks will be, * on average, halfway through their slice, as such start tasks @@ -5382,23 +5388,24 @@ static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq); static bool dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) { + bool sleep = flags & DEQUEUE_SLEEP; + update_curr(cfs_rq); if (flags & DEQUEUE_DELAYED) { SCHED_WARN_ON(!se->sched_delayed); } else { - bool sleep = flags & DEQUEUE_SLEEP; - + bool delay = sleep; /* * DELAY_DEQUEUE relies on spurious wakeups, special task * states must not suffer spurious wakeups, excempt them. */ if (flags & DEQUEUE_SPECIAL) - sleep = false; + delay = false; - SCHED_WARN_ON(sleep && se->sched_delayed); + SCHED_WARN_ON(delay && se->sched_delayed); - if (sched_feat(DELAY_DEQUEUE) && sleep && + if (sched_feat(DELAY_DEQUEUE) && delay && !entity_eligible(cfs_rq, se)) { if (cfs_rq->next == se) cfs_rq->next = NULL; @@ -5429,6 +5436,11 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) clear_buddies(cfs_rq, se); update_entity_lag(cfs_rq, se); + if (sched_feat(PLACE_REL_DEADLINE) && !sleep) { + se->deadline -= se->vruntime; + se->rel_deadline = 1; + } + if (se != cfs_rq->curr) __dequeue_entity(cfs_rq, se); se->on_rq = 0; @@ -12992,6 +13004,7 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p) if (p->se.sched_delayed) { dequeue_task(rq, p, DEQUEUE_NOCLOCK | DEQUEUE_SLEEP); p->se.sched_delayed = 0; + p->se.rel_deadline = 0; if (sched_feat(DELAY_ZERO) && p->se.vlag > 0) p->se.vlag = 0; } diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 7fdeb5576188..caa4d7221d52 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -9,6 +9,10 @@ SCHED_FEAT(PLACE_LAG, true) * Give new tasks half a slice to ease into the competition. */ SCHED_FEAT(PLACE_DEADLINE_INITIAL, true) +/* + * Preserve relative virtual deadline on 'migration'. + */ +SCHED_FEAT(PLACE_REL_DEADLINE, true) /* * Inhibit (wakeup) preemption until the current task has either matched the * 0-lag point or until is has exhausted it's slice. -- cgit v1.2.3 From 857b158dc5e81c6de795ef6be006eed146098fc6 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 22 May 2023 13:46:30 +0200 Subject: sched/eevdf: Use sched_attr::sched_runtime to set request/slice suggestion Allow applications to directly set a suggested request/slice length using sched_attr::sched_runtime. The implementation clamps the value to: 0.1[ms] <= slice <= 100[ms] which is 1/10 the size of HZ=1000 and 10 times the size of HZ=100. Applications should strive to use their periodic runtime at a high confidence interval (95%+) as the target slice. Using a smaller slice will introduce undue preemptions, while using a larger value will increase latency. For all the following examples assume a scheduling quantum of 8, and for consistency all examples have W=4: {A,B,C,D}(w=1,r=8): ABCD... +---+---+---+--- t=0, V=1.5 t=1, V=3.5 A |------< A |------< B |------< B |------< C |------< C |------< D |------< D |------< ---+*------+-------+--- ---+--*----+-------+--- t=2, V=5.5 t=3, V=7.5 A |------< A |------< B |------< B |------< C |------< C |------< D |------< D |------< ---+----*--+-------+--- ---+------*+-------+--- Note: 4 identical tasks in FIFO order ~~~ {A,B}(w=1,r=16) C(w=2,r=16) AACCBBCC... +---+---+---+--- t=0, V=1.25 t=2, V=5.25 A |--------------< A |--------------< B |--------------< B |--------------< C |------< C |------< ---+*------+-------+--- ---+----*--+-------+--- t=4, V=8.25 t=6, V=12.25 A |--------------< A |--------------< B |--------------< B |--------------< C |------< C |------< ---+-------*-------+--- ---+-------+---*---+--- Note: 1 heavy task -- because q=8, double r such that the deadline of the w=2 task doesn't go below q. Note: observe the full schedule becomes: W*max(r_i/w_i) = 4*2q = 8q in length. Note: the period of the heavy task is half the full period at: W*(r_i/w_i) = 4*(2q/2) = 4q ~~~ {A,C,D}(w=1,r=16) B(w=1,r=8): BAACCBDD... +---+---+---+--- t=0, V=1.5 t=1, V=3.5 A |--------------< A |---------------< B |------< B |------< C |--------------< C |--------------< D |--------------< D |--------------< ---+*------+-------+--- ---+--*----+-------+--- t=3, V=7.5 t=5, V=11.5 A |---------------< A |---------------< B |------< B |------< C |--------------< C |--------------< D |--------------< D |--------------< ---+------*+-------+--- ---+-------+--*----+--- t=6, V=13.5 A |---------------< B |------< C |--------------< D |--------------< ---+-------+----*--+--- Note: 1 short task -- again double r so that the deadline of the short task won't be below q. Made B short because its not the leftmost task, but is eligible with the 0,1,2,3 spread. Note: like with the heavy task, the period of the short task observes: W*(r_i/w_i) = 4*(1q/1) = 4q ~~~ A(w=1,r=16) B(w=1,r=8) C(w=2,r=16) BCCAABCC... +---+---+---+--- t=0, V=1.25 t=1, V=3.25 A |--------------< A |--------------< B |------< B |------< C |------< C |------< ---+*------+-------+--- ---+--*----+-------+--- t=3, V=7.25 t=5, V=11.25 A |--------------< A |--------------< B |------< B |------< C |------< C |------< ---+------*+-------+--- ---+-------+--*----+--- t=6, V=13.25 A |--------------< B |------< C |------< ---+-------+----*--+--- Note: 1 heavy and 1 short task -- combine them all. Note: both the short and heavy task end up with a period of 4q ~~~ A(w=1,r=16) B(w=2,r=16) C(w=1,r=8) BBCAABBC... +---+---+---+--- t=0, V=1 t=2, V=5 A |--------------< A |--------------< B |------< B |------< C |------< C |------< ---+*------+-------+--- ---+----*--+-------+--- t=3, V=7 t=5, V=11 A |--------------< A |--------------< B |------< B |------< C |------< C |------< ---+------*+-------+--- ---+-------+--*----+--- t=7, V=15 A |--------------< B |------< C |------< ---+-------+------*+--- Note: as before but permuted ~~~ From all this it can be deduced that, for the steady state: - the total period (P) of a schedule is: W*max(r_i/w_i) - the average period of a task is: W*(r_i/w_i) - each task obtains the fair share: w_i/W of each full period P Signed-off-by: Peter Zijlstra (Intel) Tested-by: Valentin Schneider Link: https://lkml.kernel.org/r/20240727105030.842834421@infradead.org --- include/linux/sched.h | 1 + kernel/sched/core.c | 4 +++- kernel/sched/debug.c | 3 ++- kernel/sched/fair.c | 6 ++++-- kernel/sched/syscalls.c | 29 +++++++++++++++++++++++------ 5 files changed, 33 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index d25e1cfd5766..89a3d8d94e96 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -547,6 +547,7 @@ struct sched_entity { unsigned char on_rq; unsigned char sched_delayed; unsigned char rel_deadline; + unsigned char custom_slice; /* hole */ u64 exec_start; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 868b71b9f2e4..016581168cb8 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4390,7 +4390,6 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) p->se.nr_migrations = 0; p->se.vruntime = 0; p->se.vlag = 0; - p->se.slice = sysctl_sched_base_slice; INIT_LIST_HEAD(&p->se.group_node); /* A delayed task cannot be in clone(). */ @@ -4643,6 +4642,8 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) p->prio = p->normal_prio = p->static_prio; set_load_weight(p, false); + p->se.custom_slice = 0; + p->se.slice = sysctl_sched_base_slice; /* * We don't need the reset flag anymore after the fork. It has @@ -8412,6 +8413,7 @@ void __init sched_init(void) } set_load_weight(&init_task, false); + init_task.se.slice = sysctl_sched_base_slice, /* * The boot idle thread does lazy MMU switching as well: diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 831a77ab8466..01ce9a76164c 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -739,11 +739,12 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) else SEQ_printf(m, " %c", task_state_to_char(p)); - SEQ_printf(m, "%15s %5d %9Ld.%06ld %c %9Ld.%06ld %9Ld.%06ld %9Ld.%06ld %9Ld %5d ", + SEQ_printf(m, "%15s %5d %9Ld.%06ld %c %9Ld.%06ld %c %9Ld.%06ld %9Ld.%06ld %9Ld %5d ", p->comm, task_pid_nr(p), SPLIT_NS(p->se.vruntime), entity_eligible(cfs_rq_of(&p->se), &p->se) ? 'E' : 'N', SPLIT_NS(p->se.deadline), + p->se.custom_slice ? 'S' : ' ', SPLIT_NS(p->se.slice), SPLIT_NS(p->se.sum_exec_runtime), (long long)(p->nvcsw + p->nivcsw), diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index cc30ea3a84e2..3284d3cb7147 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -983,7 +983,8 @@ static bool update_deadline(struct cfs_rq *cfs_rq, struct sched_entity *se) * nice) while the request time r_i is determined by * sysctl_sched_base_slice. */ - se->slice = sysctl_sched_base_slice; + if (!se->custom_slice) + se->slice = sysctl_sched_base_slice; /* * EEVDF: vd_i = ve_i + r_i / w_i @@ -5227,7 +5228,8 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) u64 vslice, vruntime = avg_vruntime(cfs_rq); s64 lag = 0; - se->slice = sysctl_sched_base_slice; + if (!se->custom_slice) + se->slice = sysctl_sched_base_slice; vslice = calc_delta_fair(se->slice, se); /* diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c index 60e70c889d91..4fae3cf25a3a 100644 --- a/kernel/sched/syscalls.c +++ b/kernel/sched/syscalls.c @@ -401,10 +401,20 @@ static void __setscheduler_params(struct task_struct *p, p->policy = policy; - if (dl_policy(policy)) + if (dl_policy(policy)) { __setparam_dl(p, attr); - else if (fair_policy(policy)) + } else if (fair_policy(policy)) { p->static_prio = NICE_TO_PRIO(attr->sched_nice); + if (attr->sched_runtime) { + p->se.custom_slice = 1; + p->se.slice = clamp_t(u64, attr->sched_runtime, + NSEC_PER_MSEC/10, /* HZ=1000 * 10 */ + NSEC_PER_MSEC*100); /* HZ=100 / 10 */ + } else { + p->se.custom_slice = 0; + p->se.slice = sysctl_sched_base_slice; + } + } /* * __sched_setscheduler() ensures attr->sched_priority == 0 when @@ -700,7 +710,9 @@ recheck: * but store a possible modification of reset_on_fork. */ if (unlikely(policy == p->policy)) { - if (fair_policy(policy) && attr->sched_nice != task_nice(p)) + if (fair_policy(policy) && + (attr->sched_nice != task_nice(p) || + (attr->sched_runtime != p->se.slice))) goto change; if (rt_policy(policy) && attr->sched_priority != p->rt_priority) goto change; @@ -846,6 +858,9 @@ static int _sched_setscheduler(struct task_struct *p, int policy, .sched_nice = PRIO_TO_NICE(p->static_prio), }; + if (p->se.custom_slice) + attr.sched_runtime = p->se.slice; + /* Fixup the legacy SCHED_RESET_ON_FORK hack. */ if ((policy != SETPARAM_POLICY) && (policy & SCHED_RESET_ON_FORK)) { attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK; @@ -1012,12 +1027,14 @@ err_size: static void get_params(struct task_struct *p, struct sched_attr *attr) { - if (task_has_dl_policy(p)) + if (task_has_dl_policy(p)) { __getparam_dl(p, attr); - else if (task_has_rt_policy(p)) + } else if (task_has_rt_policy(p)) { attr->sched_priority = p->rt_priority; - else + } else { attr->sched_nice = task_nice(p); + attr->sched_runtime = p->se.slice; + } } /** -- cgit v1.2.3 From aef6987d89544d63a47753cf3741cabff0b5574c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 20 Jun 2024 13:16:49 +0200 Subject: sched/eevdf: Propagate min_slice up the cgroup hierarchy In the absence of an explicit cgroup slice configureation, make mixed slice length work with cgroups by propagating the min_slice up the hierarchy. This ensures the cgroup entity gets timely service to service its entities that have this timing constraint set on them. Signed-off-by: Peter Zijlstra (Intel) Tested-by: Valentin Schneider Link: https://lkml.kernel.org/r/20240727105030.948188417@infradead.org --- include/linux/sched.h | 1 + kernel/sched/fair.c | 57 ++++++++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 57 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 89a3d8d94e96..3709dedbab59 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -542,6 +542,7 @@ struct sched_entity { struct rb_node run_node; u64 deadline; u64 min_vruntime; + u64 min_slice; struct list_head group_node; unsigned char on_rq; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 3284d3cb7147..fea057b311f6 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -782,6 +782,21 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq) cfs_rq->min_vruntime = __update_min_vruntime(cfs_rq, vruntime); } +static inline u64 cfs_rq_min_slice(struct cfs_rq *cfs_rq) +{ + struct sched_entity *root = __pick_root_entity(cfs_rq); + struct sched_entity *curr = cfs_rq->curr; + u64 min_slice = ~0ULL; + + if (curr && curr->on_rq) + min_slice = curr->slice; + + if (root) + min_slice = min(min_slice, root->min_slice); + + return min_slice; +} + static inline bool __entity_less(struct rb_node *a, const struct rb_node *b) { return entity_before(__node_2_se(a), __node_2_se(b)); @@ -798,19 +813,34 @@ static inline void __min_vruntime_update(struct sched_entity *se, struct rb_node } } +static inline void __min_slice_update(struct sched_entity *se, struct rb_node *node) +{ + if (node) { + struct sched_entity *rse = __node_2_se(node); + if (rse->min_slice < se->min_slice) + se->min_slice = rse->min_slice; + } +} + /* * se->min_vruntime = min(se->vruntime, {left,right}->min_vruntime) */ static inline bool min_vruntime_update(struct sched_entity *se, bool exit) { u64 old_min_vruntime = se->min_vruntime; + u64 old_min_slice = se->min_slice; struct rb_node *node = &se->run_node; se->min_vruntime = se->vruntime; __min_vruntime_update(se, node->rb_right); __min_vruntime_update(se, node->rb_left); - return se->min_vruntime == old_min_vruntime; + se->min_slice = se->slice; + __min_slice_update(se, node->rb_right); + __min_slice_update(se, node->rb_left); + + return se->min_vruntime == old_min_vruntime && + se->min_slice == old_min_slice; } RB_DECLARE_CALLBACKS(static, min_vruntime_cb, struct sched_entity, @@ -823,6 +853,7 @@ static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) { avg_vruntime_add(cfs_rq, se); se->min_vruntime = se->vruntime; + se->min_slice = se->slice; rb_add_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline, __entity_less, &min_vruntime_cb); } @@ -6911,6 +6942,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) int idle_h_nr_running = task_has_idle_policy(p); int task_new = !(flags & ENQUEUE_WAKEUP); int rq_h_nr_running = rq->cfs.h_nr_running; + u64 slice = 0; if (flags & ENQUEUE_DELAYED) { requeue_delayed_entity(se); @@ -6940,7 +6972,18 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) break; } cfs_rq = cfs_rq_of(se); + + /* + * Basically set the slice of group entries to the min_slice of + * their respective cfs_rq. This ensures the group can service + * its entities in the desired time-frame. + */ + if (slice) { + se->slice = slice; + se->custom_slice = 1; + } enqueue_entity(cfs_rq, se, flags); + slice = cfs_rq_min_slice(cfs_rq); cfs_rq->h_nr_running++; cfs_rq->idle_h_nr_running += idle_h_nr_running; @@ -6962,6 +7005,9 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) se_update_runnable(se); update_cfs_group(se); + se->slice = slice; + slice = cfs_rq_min_slice(cfs_rq); + cfs_rq->h_nr_running++; cfs_rq->idle_h_nr_running += idle_h_nr_running; @@ -7027,11 +7073,15 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags) int idle_h_nr_running = 0; int h_nr_running = 0; struct cfs_rq *cfs_rq; + u64 slice = 0; if (entity_is_task(se)) { p = task_of(se); h_nr_running = 1; idle_h_nr_running = task_has_idle_policy(p); + } else { + cfs_rq = group_cfs_rq(se); + slice = cfs_rq_min_slice(cfs_rq); } for_each_sched_entity(se) { @@ -7056,6 +7106,8 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags) /* Don't dequeue parent if it has other entities besides us */ if (cfs_rq->load.weight) { + slice = cfs_rq_min_slice(cfs_rq); + /* Avoid re-evaluating load for this entity: */ se = parent_entity(se); /* @@ -7077,6 +7129,9 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags) se_update_runnable(se); update_cfs_group(se); + se->slice = slice; + slice = cfs_rq_min_slice(cfs_rq); + cfs_rq->h_nr_running -= h_nr_running; cfs_rq->idle_h_nr_running -= idle_h_nr_running; -- cgit v1.2.3 From fda1dd3c54ef3c4200c2e77634a91610da973950 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Thu, 18 Jul 2024 17:50:37 -0700 Subject: find: Switch from inline to __always_inline 'inline' keyword is only a recommendation for compiler. If it decides to not inline find_bit nodemask functions, the whole small_const_nbits() machinery doesn't work. This is how a standard GCC 11.3.0 does for my x86_64 build now. This patch replaces 'inline' directive with unconditional '__always_inline' to make sure that there's always a chance for compile-time optimization. It doesn't change size of kernel image, according to bloat-o-meter. [[ Brian: split out from: Subject: [PATCH 1/3] bitmap: switch from inline to __always_inline https://lore.kernel.org/all/20221027043810.350460-2-yury.norov@gmail.com/ But rewritten, as there were too many conflicts. ]] Co-developed-by: Brian Norris Signed-off-by: Brian Norris Reviewed-by: Kees Cook Reviewed-by: Nathan Chancellor Signed-off-by: Yury Norov --- include/linux/find.h | 50 +++++++++++++++++++++++++------------------------- 1 file changed, 25 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/find.h b/include/linux/find.h index 5dfca4225fef..68685714bc18 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -52,7 +52,7 @@ unsigned long _find_next_bit_le(const unsigned long *addr, unsigned * Returns the bit number for the next set bit * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { @@ -81,7 +81,7 @@ unsigned long find_next_bit(const unsigned long *addr, unsigned long size, * Returns the bit number for the next set bit * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) @@ -112,7 +112,7 @@ unsigned long find_next_and_bit(const unsigned long *addr1, * Returns the bit number for the next set bit * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_next_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) @@ -142,7 +142,7 @@ unsigned long find_next_andnot_bit(const unsigned long *addr1, * Returns the bit number for the next set bit * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_next_or_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) @@ -171,7 +171,7 @@ unsigned long find_next_or_bit(const unsigned long *addr1, * Returns the bit number of the next zero bit * If no bits are zero, returns @size. */ -static inline +static __always_inline unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { @@ -198,7 +198,7 @@ unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, * Returns the bit number of the first set bit. * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_first_bit(const unsigned long *addr, unsigned long size) { if (small_const_nbits(size)) { @@ -224,7 +224,7 @@ unsigned long find_first_bit(const unsigned long *addr, unsigned long size) * Returns the bit number of the N'th set bit. * If no such, returns >= @size. */ -static inline +static __always_inline unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n) { if (n >= size) @@ -249,7 +249,7 @@ unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsign * Returns the bit number of the N'th set bit. * If no such, returns @size. */ -static inline +static __always_inline unsigned long find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long n) { @@ -276,7 +276,7 @@ unsigned long find_nth_and_bit(const unsigned long *addr1, const unsigned long * * Returns the bit number of the N'th set bit. * If no such, returns @size. */ -static inline +static __always_inline unsigned long find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long n) { @@ -332,7 +332,7 @@ unsigned long find_nth_and_andnot_bit(const unsigned long *addr1, * Returns the bit number for the next set bit * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size) @@ -357,7 +357,7 @@ unsigned long find_first_and_bit(const unsigned long *addr1, * Returns the bit number for the first set bit * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_first_and_and_bit(const unsigned long *addr1, const unsigned long *addr2, const unsigned long *addr3, @@ -381,7 +381,7 @@ unsigned long find_first_and_and_bit(const unsigned long *addr1, * Returns the bit number of the first cleared bit. * If no bits are zero, returns @size. */ -static inline +static __always_inline unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) { if (small_const_nbits(size)) { @@ -402,7 +402,7 @@ unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) * * Returns the bit number of the last set bit, or size. */ -static inline +static __always_inline unsigned long find_last_bit(const unsigned long *addr, unsigned long size) { if (small_const_nbits(size)) { @@ -425,7 +425,7 @@ unsigned long find_last_bit(const unsigned long *addr, unsigned long size) * Returns the bit number for the next set bit, or first set bit up to @offset * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_next_and_bit_wrap(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) @@ -448,7 +448,7 @@ unsigned long find_next_and_bit_wrap(const unsigned long *addr1, * Returns the bit number for the next set bit, or first set bit up to @offset * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_next_bit_wrap(const unsigned long *addr, unsigned long size, unsigned long offset) { @@ -465,7 +465,7 @@ unsigned long find_next_bit_wrap(const unsigned long *addr, * Helper for for_each_set_bit_wrap(). Make sure you're doing right thing * before using it alone. */ -static inline +static __always_inline unsigned long __for_each_wrap(const unsigned long *bitmap, unsigned long size, unsigned long start, unsigned long n) { @@ -506,20 +506,20 @@ extern unsigned long find_next_clump8(unsigned long *clump, #if defined(__LITTLE_ENDIAN) -static inline unsigned long find_next_zero_bit_le(const void *addr, - unsigned long size, unsigned long offset) +static __always_inline +unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset) { return find_next_zero_bit(addr, size, offset); } -static inline unsigned long find_next_bit_le(const void *addr, - unsigned long size, unsigned long offset) +static __always_inline +unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset) { return find_next_bit(addr, size, offset); } -static inline unsigned long find_first_zero_bit_le(const void *addr, - unsigned long size) +static __always_inline +unsigned long find_first_zero_bit_le(const void *addr, unsigned long size) { return find_first_zero_bit(addr, size); } @@ -527,7 +527,7 @@ static inline unsigned long find_first_zero_bit_le(const void *addr, #elif defined(__BIG_ENDIAN) #ifndef find_next_zero_bit_le -static inline +static __always_inline unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset) { @@ -546,7 +546,7 @@ unsigned long find_next_zero_bit_le(const void *addr, unsigned #endif #ifndef find_first_zero_bit_le -static inline +static __always_inline unsigned long find_first_zero_bit_le(const void *addr, unsigned long size) { if (small_const_nbits(size)) { @@ -560,7 +560,7 @@ unsigned long find_first_zero_bit_le(const void *addr, unsigned long size) #endif #ifndef find_next_bit_le -static inline +static __always_inline unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset) { -- cgit v1.2.3 From ed8cd2b3bd9f070120528fc5403a2d0b5afe07f8 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Thu, 18 Jul 2024 17:50:38 -0700 Subject: bitmap: Switch from inline to __always_inline 'inline' keyword is only a recommendation for compiler. If it decides to not inline bitmap functions, the whole small_const_nbits() machinery doesn't work. This is how a standard GCC 11.3.0 does for my x86_64 build now. This patch replaces 'inline' directive with unconditional '__always_inline' to make sure that there's always a chance for compile-time optimization. It doesn't change size of kernel image, according to bloat-o-meter. [[ Brian: split out from: Subject: [PATCH 1/3] bitmap: switch from inline to __always_inline https://lore.kernel.org/all/20221027043810.350460-2-yury.norov@gmail.com/ But rewritten, as there were too many conflicts. ]] Co-developed-by: Brian Norris Signed-off-by: Brian Norris Reviewed-by: Kees Cook Reviewed-by: Nathan Chancellor Signed-off-by: Yury Norov --- include/linux/bitmap.h | 140 +++++++++++++++++++++++++++---------------------- 1 file changed, 76 insertions(+), 64 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 8c4768c44a01..0406f48f0a6a 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -203,12 +203,12 @@ unsigned long bitmap_find_next_zero_area_off(unsigned long *map, * the bit offset of all zero areas this function finds is multiples of that * power of 2. A @align_mask of 0 means no alignment is required. */ -static inline unsigned long -bitmap_find_next_zero_area(unsigned long *map, - unsigned long size, - unsigned long start, - unsigned int nr, - unsigned long align_mask) +static __always_inline +unsigned long bitmap_find_next_zero_area(unsigned long *map, + unsigned long size, + unsigned long start, + unsigned int nr, + unsigned long align_mask) { return bitmap_find_next_zero_area_off(map, size, start, nr, align_mask, 0); @@ -228,7 +228,7 @@ void bitmap_fold(unsigned long *dst, const unsigned long *orig, #define bitmap_size(nbits) (ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE) -static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) +static __always_inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { unsigned int len = bitmap_size(nbits); @@ -238,7 +238,7 @@ static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) memset(dst, 0, len); } -static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) +static __always_inline void bitmap_fill(unsigned long *dst, unsigned int nbits) { unsigned int len = bitmap_size(nbits); @@ -248,8 +248,8 @@ static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) memset(dst, 0xff, len); } -static inline void bitmap_copy(unsigned long *dst, const unsigned long *src, - unsigned int nbits) +static __always_inline +void bitmap_copy(unsigned long *dst, const unsigned long *src, unsigned int nbits) { unsigned int len = bitmap_size(nbits); @@ -262,8 +262,8 @@ static inline void bitmap_copy(unsigned long *dst, const unsigned long *src, /* * Copy bitmap and clear tail bits in last word. */ -static inline void bitmap_copy_clear_tail(unsigned long *dst, - const unsigned long *src, unsigned int nbits) +static __always_inline +void bitmap_copy_clear_tail(unsigned long *dst, const unsigned long *src, unsigned int nbits) { bitmap_copy(dst, src, nbits); if (nbits % BITS_PER_LONG) @@ -306,16 +306,18 @@ void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits); bitmap_copy_clear_tail((unsigned long *)(buf), (const unsigned long *)(bitmap), (nbits)) #endif -static inline bool bitmap_and(unsigned long *dst, const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static __always_inline +bool bitmap_and(unsigned long *dst, const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return (*dst = *src1 & *src2 & BITMAP_LAST_WORD_MASK(nbits)) != 0; return __bitmap_and(dst, src1, src2, nbits); } -static inline void bitmap_or(unsigned long *dst, const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static __always_inline +void bitmap_or(unsigned long *dst, const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = *src1 | *src2; @@ -323,8 +325,9 @@ static inline void bitmap_or(unsigned long *dst, const unsigned long *src1, __bitmap_or(dst, src1, src2, nbits); } -static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static __always_inline +void bitmap_xor(unsigned long *dst, const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = *src1 ^ *src2; @@ -332,16 +335,17 @@ static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1, __bitmap_xor(dst, src1, src2, nbits); } -static inline bool bitmap_andnot(unsigned long *dst, const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static __always_inline +bool bitmap_andnot(unsigned long *dst, const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return (*dst = *src1 & ~(*src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0; return __bitmap_andnot(dst, src1, src2, nbits); } -static inline void bitmap_complement(unsigned long *dst, const unsigned long *src, - unsigned int nbits) +static __always_inline +void bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = ~(*src); @@ -356,8 +360,8 @@ static inline void bitmap_complement(unsigned long *dst, const unsigned long *sr #endif #define BITMAP_MEM_MASK (BITMAP_MEM_ALIGNMENT - 1) -static inline bool bitmap_equal(const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static __always_inline +bool bitmap_equal(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits)); @@ -376,10 +380,9 @@ static inline bool bitmap_equal(const unsigned long *src1, * * Returns: True if (*@src1 | *@src2) == *@src3, false otherwise */ -static inline bool bitmap_or_equal(const unsigned long *src1, - const unsigned long *src2, - const unsigned long *src3, - unsigned int nbits) +static __always_inline +bool bitmap_or_equal(const unsigned long *src1, const unsigned long *src2, + const unsigned long *src3, unsigned int nbits) { if (!small_const_nbits(nbits)) return __bitmap_or_equal(src1, src2, src3, nbits); @@ -387,9 +390,8 @@ static inline bool bitmap_or_equal(const unsigned long *src1, return !(((*src1 | *src2) ^ *src3) & BITMAP_LAST_WORD_MASK(nbits)); } -static inline bool bitmap_intersects(const unsigned long *src1, - const unsigned long *src2, - unsigned int nbits) +static __always_inline +bool bitmap_intersects(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return ((*src1 & *src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0; @@ -397,8 +399,8 @@ static inline bool bitmap_intersects(const unsigned long *src1, return __bitmap_intersects(src1, src2, nbits); } -static inline bool bitmap_subset(const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static __always_inline +bool bitmap_subset(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return ! ((*src1 & ~(*src2)) & BITMAP_LAST_WORD_MASK(nbits)); @@ -406,7 +408,8 @@ static inline bool bitmap_subset(const unsigned long *src1, return __bitmap_subset(src1, src2, nbits); } -static inline bool bitmap_empty(const unsigned long *src, unsigned nbits) +static __always_inline +bool bitmap_empty(const unsigned long *src, unsigned nbits) { if (small_const_nbits(nbits)) return ! (*src & BITMAP_LAST_WORD_MASK(nbits)); @@ -414,7 +417,8 @@ static inline bool bitmap_empty(const unsigned long *src, unsigned nbits) return find_first_bit(src, nbits) == nbits; } -static inline bool bitmap_full(const unsigned long *src, unsigned int nbits) +static __always_inline +bool bitmap_full(const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) return ! (~(*src) & BITMAP_LAST_WORD_MASK(nbits)); @@ -448,8 +452,8 @@ unsigned long bitmap_weight_andnot(const unsigned long *src1, return __bitmap_weight_andnot(src1, src2, nbits); } -static __always_inline void bitmap_set(unsigned long *map, unsigned int start, - unsigned int nbits) +static __always_inline +void bitmap_set(unsigned long *map, unsigned int start, unsigned int nbits) { if (__builtin_constant_p(nbits) && nbits == 1) __set_bit(start, map); @@ -464,8 +468,8 @@ static __always_inline void bitmap_set(unsigned long *map, unsigned int start, __bitmap_set(map, start, nbits); } -static __always_inline void bitmap_clear(unsigned long *map, unsigned int start, - unsigned int nbits) +static __always_inline +void bitmap_clear(unsigned long *map, unsigned int start, unsigned int nbits) { if (__builtin_constant_p(nbits) && nbits == 1) __clear_bit(start, map); @@ -480,8 +484,9 @@ static __always_inline void bitmap_clear(unsigned long *map, unsigned int start, __bitmap_clear(map, start, nbits); } -static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *src, - unsigned int shift, unsigned int nbits) +static __always_inline +void bitmap_shift_right(unsigned long *dst, const unsigned long *src, + unsigned int shift, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = (*src & BITMAP_LAST_WORD_MASK(nbits)) >> shift; @@ -489,8 +494,9 @@ static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *s __bitmap_shift_right(dst, src, shift, nbits); } -static inline void bitmap_shift_left(unsigned long *dst, const unsigned long *src, - unsigned int shift, unsigned int nbits) +static __always_inline +void bitmap_shift_left(unsigned long *dst, const unsigned long *src, + unsigned int shift, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = (*src << shift) & BITMAP_LAST_WORD_MASK(nbits); @@ -498,11 +504,12 @@ static inline void bitmap_shift_left(unsigned long *dst, const unsigned long *sr __bitmap_shift_left(dst, src, shift, nbits); } -static inline void bitmap_replace(unsigned long *dst, - const unsigned long *old, - const unsigned long *new, - const unsigned long *mask, - unsigned int nbits) +static __always_inline +void bitmap_replace(unsigned long *dst, + const unsigned long *old, + const unsigned long *new, + const unsigned long *mask, + unsigned int nbits) { if (small_const_nbits(nbits)) *dst = (*old & ~(*mask)) | (*new & *mask); @@ -545,8 +552,9 @@ static inline void bitmap_replace(unsigned long *dst, * bitmap_gather() can be seen as the 'reverse' bitmap_scatter() operation. * See bitmap_scatter() for details related to this relationship. */ -static inline void bitmap_scatter(unsigned long *dst, const unsigned long *src, - const unsigned long *mask, unsigned int nbits) +static __always_inline +void bitmap_scatter(unsigned long *dst, const unsigned long *src, + const unsigned long *mask, unsigned int nbits) { unsigned int n = 0; unsigned int bit; @@ -599,8 +607,9 @@ static inline void bitmap_scatter(unsigned long *dst, const unsigned long *src, * bitmap_scatter(res, src, mask, n) and a call to * bitmap_scatter(res, result, mask, n) will lead to the same res value. */ -static inline void bitmap_gather(unsigned long *dst, const unsigned long *src, - const unsigned long *mask, unsigned int nbits) +static __always_inline +void bitmap_gather(unsigned long *dst, const unsigned long *src, + const unsigned long *mask, unsigned int nbits) { unsigned int n = 0; unsigned int bit; @@ -611,9 +620,9 @@ static inline void bitmap_gather(unsigned long *dst, const unsigned long *src, __assign_bit(n++, dst, test_bit(bit, src)); } -static inline void bitmap_next_set_region(unsigned long *bitmap, - unsigned int *rs, unsigned int *re, - unsigned int end) +static __always_inline +void bitmap_next_set_region(unsigned long *bitmap, unsigned int *rs, + unsigned int *re, unsigned int end) { *rs = find_next_bit(bitmap, end, *rs); *re = find_next_zero_bit(bitmap, end, *rs + 1); @@ -628,7 +637,8 @@ static inline void bitmap_next_set_region(unsigned long *bitmap, * This is the complement to __bitmap_find_free_region() and releases * the found region (by clearing it in the bitmap). */ -static inline void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order) +static __always_inline +void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order) { bitmap_clear(bitmap, pos, BIT(order)); } @@ -644,7 +654,8 @@ static inline void bitmap_release_region(unsigned long *bitmap, unsigned int pos * Returns: 0 on success, or %-EBUSY if specified region wasn't * free (not all bits were zero). */ -static inline int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order) +static __always_inline +int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order) { unsigned int len = BIT(order); @@ -668,7 +679,8 @@ static inline int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos * Returns: the bit offset in bitmap of the allocated region, * or -errno on failure. */ -static inline int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order) +static __always_inline +int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order) { unsigned int pos, end; /* scans bitmap by regions of size order */ @@ -722,7 +734,7 @@ static inline int bitmap_find_free_region(unsigned long *bitmap, unsigned int bi * That is ``(u32 *)(&val)[0]`` gets the upper 32 bits, * but we expect the lower 32-bits of u64. */ -static inline void bitmap_from_u64(unsigned long *dst, u64 mask) +static __always_inline void bitmap_from_u64(unsigned long *dst, u64 mask) { bitmap_from_arr64(dst, &mask, 64); } @@ -737,9 +749,8 @@ static inline void bitmap_from_u64(unsigned long *dst, u64 mask) * @map memory region. For @nbits = 0 and @nbits > BITS_PER_LONG the return * value is undefined. */ -static inline unsigned long bitmap_read(const unsigned long *map, - unsigned long start, - unsigned long nbits) +static __always_inline +unsigned long bitmap_read(const unsigned long *map, unsigned long start, unsigned long nbits) { size_t index = BIT_WORD(start); unsigned long offset = start % BITS_PER_LONG; @@ -772,8 +783,9 @@ static inline unsigned long bitmap_read(const unsigned long *map, * * For @nbits == 0 and @nbits > BITS_PER_LONG no writes are performed. */ -static inline void bitmap_write(unsigned long *map, unsigned long value, - unsigned long start, unsigned long nbits) +static __always_inline +void bitmap_write(unsigned long *map, unsigned long value, + unsigned long start, unsigned long nbits) { size_t index; unsigned long offset; -- cgit v1.2.3 From ab6b1010dab68f6d4bf063517db4ce2d63554bc6 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Thu, 18 Jul 2024 17:50:39 -0700 Subject: cpumask: Switch from inline to __always_inline On recent (v6.6+) builds with Clang (based on Clang 18.0.0) and certain configurations [0], I'm finding that (lack of) inlining decisions may lead to section mismatch warnings like the following: WARNING: modpost: vmlinux.o: section mismatch in reference: cpumask_andnot (section: .text) -> cpuhp_bringup_cpus_parallel.tmp_mask (section: .init.data) ERROR: modpost: Section mismatches detected. or more confusingly: WARNING: modpost: vmlinux: section mismatch in reference: cpumask_andnot+0x5f (section: .text) -> efi_systab_phys (section: .init.data) The first warning makes a little sense, because cpuhp_bringup_cpus_parallel() (an __init function) calls cpumask_andnot() on tmp_mask (an __initdata symbol). If the compiler doesn't inline cpumask_andnot(), this may appear like a mismatch. The second warning makes less sense, but might be because efi_systab_phys and cpuhp_bringup_cpus_parallel.tmp_mask are laid out near each other, and the latter isn't a proper C symbol definition. In any case, it seems a reasonable solution to suggest more strongly to the compiler that these cpumask macros *must* be inlined, as 'inline' is just a recommendation. This change has been previously proposed in the past as: Subject: [PATCH 1/3] bitmap: switch from inline to __always_inline https://lore.kernel.org/all/20221027043810.350460-2-yury.norov@gmail.com/ But the change has been split up, to separately justify the cpumask changes (which drive my work) and the bitmap/const optimizations (that Yury separately proposed for other reasons). This ends up as somewhere between a "rebase" and "rewrite" -- I had to rewrite most of the patch. According to bloat-o-meter, vmlinux decreases minimally in size (-0.00% to -0.01%, depending on the version of GCC or Clang and .config in question) with this series of changes: gcc 13.2.0, x86_64_defconfig -3005 bytes, Before=21944501, After=21941496, chg -0.01% clang 16.0.6, x86_64_defconfig -105 bytes, Before=22571692, After=22571587, chg -0.00% gcc 9.5.0, x86_64_defconfig -1771 bytes, Before=21557598, After=21555827, chg -0.01% clang 18.0_pre516547 (ChromiumOS toolchain), x86_64_defconfig -191 bytes, Before=22615339, After=22615148, chg -0.00% clang 18.0_pre516547 (ChromiumOS toolchain), based on ChromiumOS config + gcov -979 bytes, Before=76294783, After=76293804, chg -0.00% [0] CONFIG_HOTPLUG_PARALLEL=y ('select'ed for x86 as of [1]) and CONFIG_GCOV_PROFILE_ALL. [1] commit 0c7ffa32dbd6 ("x86/smpboot/64: Implement arch_cpuhp_init_parallel_bringup() and enable it") Co-developed-by: Brian Norris Signed-off-by: Brian Norris Reviewed-by: Kees Cook Reviewed-by: Nathan Chancellor Signed-off-by: Yury Norov --- include/linux/cpumask.h | 212 +++++++++++++++++++++++++----------------------- 1 file changed, 112 insertions(+), 100 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 801a7e524113..9e3f3c96607d 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -30,7 +30,7 @@ extern unsigned int nr_cpu_ids; #endif -static inline void set_nr_cpu_ids(unsigned int nr) +static __always_inline void set_nr_cpu_ids(unsigned int nr) { #if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS) WARN_ON(nr != nr_cpu_ids); @@ -149,7 +149,7 @@ static __always_inline unsigned int cpumask_check(unsigned int cpu) * * Return: >= nr_cpu_ids if no cpus set. */ -static inline unsigned int cpumask_first(const struct cpumask *srcp) +static __always_inline unsigned int cpumask_first(const struct cpumask *srcp) { return find_first_bit(cpumask_bits(srcp), small_cpumask_bits); } @@ -160,7 +160,7 @@ static inline unsigned int cpumask_first(const struct cpumask *srcp) * * Return: >= nr_cpu_ids if all cpus are set. */ -static inline unsigned int cpumask_first_zero(const struct cpumask *srcp) +static __always_inline unsigned int cpumask_first_zero(const struct cpumask *srcp) { return find_first_zero_bit(cpumask_bits(srcp), small_cpumask_bits); } @@ -172,7 +172,7 @@ static inline unsigned int cpumask_first_zero(const struct cpumask *srcp) * * Return: >= nr_cpu_ids if no cpus set in both. See also cpumask_next_and(). */ -static inline +static __always_inline unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask *srcp2) { return find_first_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); @@ -186,7 +186,7 @@ unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask * * Return: >= nr_cpu_ids if no cpus set in all. */ -static inline +static __always_inline unsigned int cpumask_first_and_and(const struct cpumask *srcp1, const struct cpumask *srcp2, const struct cpumask *srcp3) @@ -201,7 +201,7 @@ unsigned int cpumask_first_and_and(const struct cpumask *srcp1, * * Return: >= nr_cpumask_bits if no CPUs set. */ -static inline unsigned int cpumask_last(const struct cpumask *srcp) +static __always_inline unsigned int cpumask_last(const struct cpumask *srcp) { return find_last_bit(cpumask_bits(srcp), small_cpumask_bits); } @@ -213,7 +213,7 @@ static inline unsigned int cpumask_last(const struct cpumask *srcp) * * Return: >= nr_cpu_ids if no further cpus set. */ -static inline +static __always_inline unsigned int cpumask_next(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ @@ -229,7 +229,8 @@ unsigned int cpumask_next(int n, const struct cpumask *srcp) * * Return: >= nr_cpu_ids if no further cpus unset. */ -static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) +static __always_inline +unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ if (n != -1) @@ -239,18 +240,21 @@ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) #if NR_CPUS == 1 /* Uniprocessor: there is only one valid CPU */ -static inline unsigned int cpumask_local_spread(unsigned int i, int node) +static __always_inline +unsigned int cpumask_local_spread(unsigned int i, int node) { return 0; } -static inline unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, + const struct cpumask *src2p) { return cpumask_first_and(src1p, src2p); } -static inline unsigned int cpumask_any_distribute(const struct cpumask *srcp) +static __always_inline +unsigned int cpumask_any_distribute(const struct cpumask *srcp) { return cpumask_first(srcp); } @@ -269,9 +273,9 @@ unsigned int cpumask_any_distribute(const struct cpumask *srcp); * * Return: >= nr_cpu_ids if no further cpus set in both. */ -static inline +static __always_inline unsigned int cpumask_next_and(int n, const struct cpumask *src1p, - const struct cpumask *src2p) + const struct cpumask *src2p) { /* -1 is a legal arg here. */ if (n != -1) @@ -291,7 +295,7 @@ unsigned int cpumask_next_and(int n, const struct cpumask *src1p, for_each_set_bit(cpu, cpumask_bits(mask), small_cpumask_bits) #if NR_CPUS == 1 -static inline +static __always_inline unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap) { cpumask_check(start); @@ -394,7 +398,7 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta * Often used to find any cpu but smp_processor_id() in a mask. * Return: >= nr_cpu_ids if no cpus set. */ -static inline +static __always_inline unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) { unsigned int i; @@ -414,7 +418,7 @@ unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) * * Returns >= nr_cpu_ids if no cpus set. */ -static inline +static __always_inline unsigned int cpumask_any_and_but(const struct cpumask *mask1, const struct cpumask *mask2, unsigned int cpu) @@ -436,7 +440,8 @@ unsigned int cpumask_any_and_but(const struct cpumask *mask1, * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ -static inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp) +static __always_inline +unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp) { return find_nth_bit(cpumask_bits(srcp), small_cpumask_bits, cpumask_check(cpu)); } @@ -449,7 +454,7 @@ static inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *s * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ -static inline +static __always_inline unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2) { @@ -465,7 +470,7 @@ unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1, * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ -static inline +static __always_inline unsigned int cpumask_nth_andnot(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2) { @@ -508,12 +513,14 @@ unsigned int cpumask_nth_and_andnot(unsigned int cpu, const struct cpumask *srcp * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer */ -static __always_inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) +static __always_inline +void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } -static __always_inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) +static __always_inline +void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { __set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } @@ -557,7 +564,8 @@ static __always_inline void __cpumask_assign_cpu(int cpu, struct cpumask *dstp, * * Return: true if @cpu is set in @cpumask, else returns false */ -static __always_inline bool cpumask_test_cpu(int cpu, const struct cpumask *cpumask) +static __always_inline +bool cpumask_test_cpu(int cpu, const struct cpumask *cpumask) { return test_bit(cpumask_check(cpu), cpumask_bits((cpumask))); } @@ -571,7 +579,8 @@ static __always_inline bool cpumask_test_cpu(int cpu, const struct cpumask *cpum * * Return: true if @cpu is set in old bitmap of @cpumask, else returns false */ -static __always_inline bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) +static __always_inline +bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) { return test_and_set_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } @@ -585,7 +594,8 @@ static __always_inline bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cp * * Return: true if @cpu is set in old bitmap of @cpumask, else returns false */ -static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask) +static __always_inline +bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask) { return test_and_clear_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } @@ -594,7 +604,7 @@ static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask * * cpumask_setall - set all cpus (< nr_cpu_ids) in a cpumask * @dstp: the cpumask pointer */ -static inline void cpumask_setall(struct cpumask *dstp) +static __always_inline void cpumask_setall(struct cpumask *dstp) { if (small_const_nbits(small_cpumask_bits)) { cpumask_bits(dstp)[0] = BITMAP_LAST_WORD_MASK(nr_cpumask_bits); @@ -607,7 +617,7 @@ static inline void cpumask_setall(struct cpumask *dstp) * cpumask_clear - clear all cpus (< nr_cpu_ids) in a cpumask * @dstp: the cpumask pointer */ -static inline void cpumask_clear(struct cpumask *dstp) +static __always_inline void cpumask_clear(struct cpumask *dstp) { bitmap_zero(cpumask_bits(dstp), large_cpumask_bits); } @@ -620,9 +630,9 @@ static inline void cpumask_clear(struct cpumask *dstp) * * Return: false if *@dstp is empty, else returns true */ -static inline bool cpumask_and(struct cpumask *dstp, - const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +bool cpumask_and(struct cpumask *dstp, const struct cpumask *src1p, + const struct cpumask *src2p) { return bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -634,8 +644,9 @@ static inline bool cpumask_and(struct cpumask *dstp, * @src1p: the first input * @src2p: the second input */ -static inline void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p, + const struct cpumask *src2p) { bitmap_or(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -647,9 +658,9 @@ static inline void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p, * @src1p: the first input * @src2p: the second input */ -static inline void cpumask_xor(struct cpumask *dstp, - const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +void cpumask_xor(struct cpumask *dstp, const struct cpumask *src1p, + const struct cpumask *src2p) { bitmap_xor(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -663,9 +674,9 @@ static inline void cpumask_xor(struct cpumask *dstp, * * Return: false if *@dstp is empty, else returns true */ -static inline bool cpumask_andnot(struct cpumask *dstp, - const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +bool cpumask_andnot(struct cpumask *dstp, const struct cpumask *src1p, + const struct cpumask *src2p) { return bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -678,8 +689,8 @@ static inline bool cpumask_andnot(struct cpumask *dstp, * * Return: true if the cpumasks are equal, false if not */ -static inline bool cpumask_equal(const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +bool cpumask_equal(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_equal(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -694,9 +705,9 @@ static inline bool cpumask_equal(const struct cpumask *src1p, * Return: true if first cpumask ORed with second cpumask == third cpumask, * otherwise false */ -static inline bool cpumask_or_equal(const struct cpumask *src1p, - const struct cpumask *src2p, - const struct cpumask *src3p) +static __always_inline +bool cpumask_or_equal(const struct cpumask *src1p, const struct cpumask *src2p, + const struct cpumask *src3p) { return bitmap_or_equal(cpumask_bits(src1p), cpumask_bits(src2p), cpumask_bits(src3p), small_cpumask_bits); @@ -710,8 +721,8 @@ static inline bool cpumask_or_equal(const struct cpumask *src1p, * Return: true if first cpumask ANDed with second cpumask is non-empty, * otherwise false */ -static inline bool cpumask_intersects(const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +bool cpumask_intersects(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_intersects(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -724,8 +735,8 @@ static inline bool cpumask_intersects(const struct cpumask *src1p, * * Return: true if *@src1p is a subset of *@src2p, else returns false */ -static inline bool cpumask_subset(const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +bool cpumask_subset(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_subset(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -737,7 +748,7 @@ static inline bool cpumask_subset(const struct cpumask *src1p, * * Return: true if srcp is empty (has no bits set), else false */ -static inline bool cpumask_empty(const struct cpumask *srcp) +static __always_inline bool cpumask_empty(const struct cpumask *srcp) { return bitmap_empty(cpumask_bits(srcp), small_cpumask_bits); } @@ -748,7 +759,7 @@ static inline bool cpumask_empty(const struct cpumask *srcp) * * Return: true if srcp is full (has all bits set), else false */ -static inline bool cpumask_full(const struct cpumask *srcp) +static __always_inline bool cpumask_full(const struct cpumask *srcp) { return bitmap_full(cpumask_bits(srcp), nr_cpumask_bits); } @@ -759,7 +770,7 @@ static inline bool cpumask_full(const struct cpumask *srcp) * * Return: count of bits set in *srcp */ -static inline unsigned int cpumask_weight(const struct cpumask *srcp) +static __always_inline unsigned int cpumask_weight(const struct cpumask *srcp) { return bitmap_weight(cpumask_bits(srcp), small_cpumask_bits); } @@ -771,8 +782,8 @@ static inline unsigned int cpumask_weight(const struct cpumask *srcp) * * Return: count of bits set in both *srcp1 and *srcp2 */ -static inline unsigned int cpumask_weight_and(const struct cpumask *srcp1, - const struct cpumask *srcp2) +static __always_inline +unsigned int cpumask_weight_and(const struct cpumask *srcp1, const struct cpumask *srcp2) { return bitmap_weight_and(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } @@ -784,8 +795,9 @@ static inline unsigned int cpumask_weight_and(const struct cpumask *srcp1, * * Return: count of bits set in both *srcp1 and *srcp2 */ -static inline unsigned int cpumask_weight_andnot(const struct cpumask *srcp1, - const struct cpumask *srcp2) +static __always_inline +unsigned int cpumask_weight_andnot(const struct cpumask *srcp1, + const struct cpumask *srcp2) { return bitmap_weight_andnot(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } @@ -796,8 +808,8 @@ static inline unsigned int cpumask_weight_andnot(const struct cpumask *srcp1, * @srcp: the input to shift * @n: the number of bits to shift by */ -static inline void cpumask_shift_right(struct cpumask *dstp, - const struct cpumask *srcp, int n) +static __always_inline +void cpumask_shift_right(struct cpumask *dstp, const struct cpumask *srcp, int n) { bitmap_shift_right(cpumask_bits(dstp), cpumask_bits(srcp), n, small_cpumask_bits); @@ -809,8 +821,8 @@ static inline void cpumask_shift_right(struct cpumask *dstp, * @srcp: the input to shift * @n: the number of bits to shift by */ -static inline void cpumask_shift_left(struct cpumask *dstp, - const struct cpumask *srcp, int n) +static __always_inline +void cpumask_shift_left(struct cpumask *dstp, const struct cpumask *srcp, int n) { bitmap_shift_left(cpumask_bits(dstp), cpumask_bits(srcp), n, nr_cpumask_bits); @@ -821,8 +833,8 @@ static inline void cpumask_shift_left(struct cpumask *dstp, * @dstp: the result * @srcp: the input cpumask */ -static inline void cpumask_copy(struct cpumask *dstp, - const struct cpumask *srcp) +static __always_inline +void cpumask_copy(struct cpumask *dstp, const struct cpumask *srcp) { bitmap_copy(cpumask_bits(dstp), cpumask_bits(srcp), large_cpumask_bits); } @@ -858,8 +870,8 @@ static inline void cpumask_copy(struct cpumask *dstp, * * Return: -errno, or 0 for success. */ -static inline int cpumask_parse_user(const char __user *buf, int len, - struct cpumask *dstp) +static __always_inline +int cpumask_parse_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); } @@ -872,8 +884,8 @@ static inline int cpumask_parse_user(const char __user *buf, int len, * * Return: -errno, or 0 for success. */ -static inline int cpumask_parselist_user(const char __user *buf, int len, - struct cpumask *dstp) +static __always_inline +int cpumask_parselist_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parselist_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); @@ -886,7 +898,7 @@ static inline int cpumask_parselist_user(const char __user *buf, int len, * * Return: -errno, or 0 for success. */ -static inline int cpumask_parse(const char *buf, struct cpumask *dstp) +static __always_inline int cpumask_parse(const char *buf, struct cpumask *dstp) { return bitmap_parse(buf, UINT_MAX, cpumask_bits(dstp), nr_cpumask_bits); } @@ -898,7 +910,7 @@ static inline int cpumask_parse(const char *buf, struct cpumask *dstp) * * Return: -errno, or 0 for success. */ -static inline int cpulist_parse(const char *buf, struct cpumask *dstp) +static __always_inline int cpulist_parse(const char *buf, struct cpumask *dstp) { return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpumask_bits); } @@ -908,7 +920,7 @@ static inline int cpulist_parse(const char *buf, struct cpumask *dstp) * * Return: size to allocate for a &struct cpumask in bytes */ -static inline unsigned int cpumask_size(void) +static __always_inline unsigned int cpumask_size(void) { return bitmap_size(large_cpumask_bits); } @@ -920,7 +932,7 @@ static inline unsigned int cpumask_size(void) bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node); -static inline +static __always_inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node); @@ -938,13 +950,13 @@ bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) * * Return: %true if allocation succeeded, %false if not */ -static inline +static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE); } -static inline +static __always_inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var(mask, flags | __GFP_ZERO); @@ -954,7 +966,7 @@ void alloc_bootmem_cpumask_var(cpumask_var_t *mask); void free_cpumask_var(cpumask_var_t mask); void free_bootmem_cpumask_var(cpumask_var_t mask); -static inline bool cpumask_available(cpumask_var_t mask) +static __always_inline bool cpumask_available(cpumask_var_t mask) { return mask != NULL; } @@ -964,43 +976,43 @@ static inline bool cpumask_available(cpumask_var_t mask) #define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x) #define __cpumask_var_read_mostly -static inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) +static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return true; } -static inline bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, +static __always_inline bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return true; } -static inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) +static __always_inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { cpumask_clear(*mask); return true; } -static inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, +static __always_inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { cpumask_clear(*mask); return true; } -static inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask) +static __always_inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask) { } -static inline void free_cpumask_var(cpumask_var_t mask) +static __always_inline void free_cpumask_var(cpumask_var_t mask) { } -static inline void free_bootmem_cpumask_var(cpumask_var_t mask) +static __always_inline void free_bootmem_cpumask_var(cpumask_var_t mask) { } -static inline bool cpumask_available(cpumask_var_t mask) +static __always_inline bool cpumask_available(cpumask_var_t mask) { return true; } @@ -1058,7 +1070,7 @@ void set_cpu_online(unsigned int cpu, bool online); ((struct cpumask *)(1 ? (bitmap) \ : (void *)sizeof(__check_is_bitmap(bitmap)))) -static inline int __check_is_bitmap(const unsigned long *bitmap) +static __always_inline int __check_is_bitmap(const unsigned long *bitmap) { return 1; } @@ -1073,7 +1085,7 @@ static inline int __check_is_bitmap(const unsigned long *bitmap) extern const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)]; -static inline const struct cpumask *get_cpu_mask(unsigned int cpu) +static __always_inline const struct cpumask *get_cpu_mask(unsigned int cpu) { const unsigned long *p = cpu_bit_bitmap[1 + cpu % BITS_PER_LONG]; p -= cpu / BITS_PER_LONG; @@ -1100,32 +1112,32 @@ static __always_inline unsigned int num_online_cpus(void) #define num_present_cpus() cpumask_weight(cpu_present_mask) #define num_active_cpus() cpumask_weight(cpu_active_mask) -static inline bool cpu_online(unsigned int cpu) +static __always_inline bool cpu_online(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_online_mask); } -static inline bool cpu_enabled(unsigned int cpu) +static __always_inline bool cpu_enabled(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_enabled_mask); } -static inline bool cpu_possible(unsigned int cpu) +static __always_inline bool cpu_possible(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_possible_mask); } -static inline bool cpu_present(unsigned int cpu) +static __always_inline bool cpu_present(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_present_mask); } -static inline bool cpu_active(unsigned int cpu) +static __always_inline bool cpu_active(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_active_mask); } -static inline bool cpu_dying(unsigned int cpu) +static __always_inline bool cpu_dying(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_dying_mask); } @@ -1138,32 +1150,32 @@ static inline bool cpu_dying(unsigned int cpu) #define num_present_cpus() 1U #define num_active_cpus() 1U -static inline bool cpu_online(unsigned int cpu) +static __always_inline bool cpu_online(unsigned int cpu) { return cpu == 0; } -static inline bool cpu_possible(unsigned int cpu) +static __always_inline bool cpu_possible(unsigned int cpu) { return cpu == 0; } -static inline bool cpu_enabled(unsigned int cpu) +static __always_inline bool cpu_enabled(unsigned int cpu) { return cpu == 0; } -static inline bool cpu_present(unsigned int cpu) +static __always_inline bool cpu_present(unsigned int cpu) { return cpu == 0; } -static inline bool cpu_active(unsigned int cpu) +static __always_inline bool cpu_active(unsigned int cpu) { return cpu == 0; } -static inline bool cpu_dying(unsigned int cpu) +static __always_inline bool cpu_dying(unsigned int cpu) { return false; } @@ -1197,7 +1209,7 @@ static inline bool cpu_dying(unsigned int cpu) * Return: the length of the (null-terminated) @buf string, zero if * nothing is copied. */ -static inline ssize_t +static __always_inline ssize_t cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask) { return bitmap_print_to_pagebuf(list, buf, cpumask_bits(mask), @@ -1220,9 +1232,9 @@ cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask) * Return: the length of how many bytes have been copied, excluding * terminating '\0'. */ -static inline ssize_t -cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask, - loff_t off, size_t count) +static __always_inline +ssize_t cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask, + loff_t off, size_t count) { return bitmap_print_bitmask_to_buf(buf, cpumask_bits(mask), nr_cpu_ids, off, count) - 1; @@ -1242,9 +1254,9 @@ cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask, * Return: the length of how many bytes have been copied, excluding * terminating '\0'. */ -static inline ssize_t -cpumap_print_list_to_buf(char *buf, const struct cpumask *mask, - loff_t off, size_t count) +static __always_inline +ssize_t cpumap_print_list_to_buf(char *buf, const struct cpumask *mask, + loff_t off, size_t count) { return bitmap_print_list_to_buf(buf, cpumask_bits(mask), nr_cpu_ids, off, count) - 1; -- cgit v1.2.3 From 54c9e0085bd1015e524d8f4d3c4e78a7bc77ffca Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Thu, 18 Jul 2024 17:50:40 -0700 Subject: nodemask: Switch from inline to __always_inline 'inline' keyword is only a recommendation for compiler. If it decides to not inline nodemask functions, the whole small_const_nbits() machinery doesn't work. This is how a standard GCC 11.3.0 does for my x86_64 build now. This patch replaces 'inline' directive with unconditional '__always_inline' to make sure that there's always a chance for compile-time optimization. It doesn't change size of kernel image, according to bloat-o-meter. [[ Brian: split out from: Subject: [PATCH 1/3] bitmap: switch from inline to __always_inline https://lore.kernel.org/all/20221027043810.350460-2-yury.norov@gmail.com/ But rewritten, as there were too many conflicts. ]] Co-developed-by: Brian Norris Signed-off-by: Brian Norris Reviewed-by: Kees Cook Reviewed-by: Nathan Chancellor Signed-off-by: Yury Norov --- include/linux/nodemask.h | 86 ++++++++++++++++++++++++------------------------ 1 file changed, 43 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index b61438313a73..9fd7a0ce9c1a 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -107,11 +107,11 @@ extern nodemask_t _unused_nodemask_arg_; */ #define nodemask_pr_args(maskp) __nodemask_pr_numnodes(maskp), \ __nodemask_pr_bits(maskp) -static inline unsigned int __nodemask_pr_numnodes(const nodemask_t *m) +static __always_inline unsigned int __nodemask_pr_numnodes(const nodemask_t *m) { return m ? MAX_NUMNODES : 0; } -static inline const unsigned long *__nodemask_pr_bits(const nodemask_t *m) +static __always_inline const unsigned long *__nodemask_pr_bits(const nodemask_t *m) { return m ? m->bits : NULL; } @@ -132,19 +132,19 @@ static __always_inline void __node_set(int node, volatile nodemask_t *dstp) } #define node_clear(node, dst) __node_clear((node), &(dst)) -static inline void __node_clear(int node, volatile nodemask_t *dstp) +static __always_inline void __node_clear(int node, volatile nodemask_t *dstp) { clear_bit(node, dstp->bits); } #define nodes_setall(dst) __nodes_setall(&(dst), MAX_NUMNODES) -static inline void __nodes_setall(nodemask_t *dstp, unsigned int nbits) +static __always_inline void __nodes_setall(nodemask_t *dstp, unsigned int nbits) { bitmap_fill(dstp->bits, nbits); } #define nodes_clear(dst) __nodes_clear(&(dst), MAX_NUMNODES) -static inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits) +static __always_inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits) { bitmap_zero(dstp->bits, nbits); } @@ -154,14 +154,14 @@ static inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits) #define node_test_and_set(node, nodemask) \ __node_test_and_set((node), &(nodemask)) -static inline bool __node_test_and_set(int node, nodemask_t *addr) +static __always_inline bool __node_test_and_set(int node, nodemask_t *addr) { return test_and_set_bit(node, addr->bits); } #define nodes_and(dst, src1, src2) \ __nodes_and(&(dst), &(src1), &(src2), MAX_NUMNODES) -static inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p, +static __always_inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits); @@ -169,7 +169,7 @@ static inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p, #define nodes_or(dst, src1, src2) \ __nodes_or(&(dst), &(src1), &(src2), MAX_NUMNODES) -static inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p, +static __always_inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_or(dstp->bits, src1p->bits, src2p->bits, nbits); @@ -177,7 +177,7 @@ static inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p, #define nodes_xor(dst, src1, src2) \ __nodes_xor(&(dst), &(src1), &(src2), MAX_NUMNODES) -static inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p, +static __always_inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_xor(dstp->bits, src1p->bits, src2p->bits, nbits); @@ -185,7 +185,7 @@ static inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p, #define nodes_andnot(dst, src1, src2) \ __nodes_andnot(&(dst), &(src1), &(src2), MAX_NUMNODES) -static inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p, +static __always_inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits); @@ -193,7 +193,7 @@ static inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p, #define nodes_complement(dst, src) \ __nodes_complement(&(dst), &(src), MAX_NUMNODES) -static inline void __nodes_complement(nodemask_t *dstp, +static __always_inline void __nodes_complement(nodemask_t *dstp, const nodemask_t *srcp, unsigned int nbits) { bitmap_complement(dstp->bits, srcp->bits, nbits); @@ -201,7 +201,7 @@ static inline void __nodes_complement(nodemask_t *dstp, #define nodes_equal(src1, src2) \ __nodes_equal(&(src1), &(src2), MAX_NUMNODES) -static inline bool __nodes_equal(const nodemask_t *src1p, +static __always_inline bool __nodes_equal(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_equal(src1p->bits, src2p->bits, nbits); @@ -209,7 +209,7 @@ static inline bool __nodes_equal(const nodemask_t *src1p, #define nodes_intersects(src1, src2) \ __nodes_intersects(&(src1), &(src2), MAX_NUMNODES) -static inline bool __nodes_intersects(const nodemask_t *src1p, +static __always_inline bool __nodes_intersects(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_intersects(src1p->bits, src2p->bits, nbits); @@ -217,33 +217,33 @@ static inline bool __nodes_intersects(const nodemask_t *src1p, #define nodes_subset(src1, src2) \ __nodes_subset(&(src1), &(src2), MAX_NUMNODES) -static inline bool __nodes_subset(const nodemask_t *src1p, +static __always_inline bool __nodes_subset(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_subset(src1p->bits, src2p->bits, nbits); } #define nodes_empty(src) __nodes_empty(&(src), MAX_NUMNODES) -static inline bool __nodes_empty(const nodemask_t *srcp, unsigned int nbits) +static __always_inline bool __nodes_empty(const nodemask_t *srcp, unsigned int nbits) { return bitmap_empty(srcp->bits, nbits); } #define nodes_full(nodemask) __nodes_full(&(nodemask), MAX_NUMNODES) -static inline bool __nodes_full(const nodemask_t *srcp, unsigned int nbits) +static __always_inline bool __nodes_full(const nodemask_t *srcp, unsigned int nbits) { return bitmap_full(srcp->bits, nbits); } #define nodes_weight(nodemask) __nodes_weight(&(nodemask), MAX_NUMNODES) -static inline int __nodes_weight(const nodemask_t *srcp, unsigned int nbits) +static __always_inline int __nodes_weight(const nodemask_t *srcp, unsigned int nbits) { return bitmap_weight(srcp->bits, nbits); } #define nodes_shift_right(dst, src, n) \ __nodes_shift_right(&(dst), &(src), (n), MAX_NUMNODES) -static inline void __nodes_shift_right(nodemask_t *dstp, +static __always_inline void __nodes_shift_right(nodemask_t *dstp, const nodemask_t *srcp, int n, int nbits) { bitmap_shift_right(dstp->bits, srcp->bits, n, nbits); @@ -251,7 +251,7 @@ static inline void __nodes_shift_right(nodemask_t *dstp, #define nodes_shift_left(dst, src, n) \ __nodes_shift_left(&(dst), &(src), (n), MAX_NUMNODES) -static inline void __nodes_shift_left(nodemask_t *dstp, +static __always_inline void __nodes_shift_left(nodemask_t *dstp, const nodemask_t *srcp, int n, int nbits) { bitmap_shift_left(dstp->bits, srcp->bits, n, nbits); @@ -261,13 +261,13 @@ static inline void __nodes_shift_left(nodemask_t *dstp, > MAX_NUMNODES, then the silly min_ts could be dropped. */ #define first_node(src) __first_node(&(src)) -static inline unsigned int __first_node(const nodemask_t *srcp) +static __always_inline unsigned int __first_node(const nodemask_t *srcp) { return min_t(unsigned int, MAX_NUMNODES, find_first_bit(srcp->bits, MAX_NUMNODES)); } #define next_node(n, src) __next_node((n), &(src)) -static inline unsigned int __next_node(int n, const nodemask_t *srcp) +static __always_inline unsigned int __next_node(int n, const nodemask_t *srcp) { return min_t(unsigned int, MAX_NUMNODES, find_next_bit(srcp->bits, MAX_NUMNODES, n+1)); } @@ -277,7 +277,7 @@ static inline unsigned int __next_node(int n, const nodemask_t *srcp) * the first node in src if needed. Returns MAX_NUMNODES if src is empty. */ #define next_node_in(n, src) __next_node_in((n), &(src)) -static inline unsigned int __next_node_in(int node, const nodemask_t *srcp) +static __always_inline unsigned int __next_node_in(int node, const nodemask_t *srcp) { unsigned int ret = __next_node(node, srcp); @@ -286,7 +286,7 @@ static inline unsigned int __next_node_in(int node, const nodemask_t *srcp) return ret; } -static inline void init_nodemask_of_node(nodemask_t *mask, int node) +static __always_inline void init_nodemask_of_node(nodemask_t *mask, int node) { nodes_clear(*mask); node_set(node, *mask); @@ -304,7 +304,7 @@ static inline void init_nodemask_of_node(nodemask_t *mask, int node) }) #define first_unset_node(mask) __first_unset_node(&(mask)) -static inline unsigned int __first_unset_node(const nodemask_t *maskp) +static __always_inline unsigned int __first_unset_node(const nodemask_t *maskp) { return min_t(unsigned int, MAX_NUMNODES, find_first_zero_bit(maskp->bits, MAX_NUMNODES)); @@ -338,21 +338,21 @@ static inline unsigned int __first_unset_node(const nodemask_t *maskp) #define nodemask_parse_user(ubuf, ulen, dst) \ __nodemask_parse_user((ubuf), (ulen), &(dst), MAX_NUMNODES) -static inline int __nodemask_parse_user(const char __user *buf, int len, +static __always_inline int __nodemask_parse_user(const char __user *buf, int len, nodemask_t *dstp, int nbits) { return bitmap_parse_user(buf, len, dstp->bits, nbits); } #define nodelist_parse(buf, dst) __nodelist_parse((buf), &(dst), MAX_NUMNODES) -static inline int __nodelist_parse(const char *buf, nodemask_t *dstp, int nbits) +static __always_inline int __nodelist_parse(const char *buf, nodemask_t *dstp, int nbits) { return bitmap_parselist(buf, dstp->bits, nbits); } #define node_remap(oldbit, old, new) \ __node_remap((oldbit), &(old), &(new), MAX_NUMNODES) -static inline int __node_remap(int oldbit, +static __always_inline int __node_remap(int oldbit, const nodemask_t *oldp, const nodemask_t *newp, int nbits) { return bitmap_bitremap(oldbit, oldp->bits, newp->bits, nbits); @@ -360,7 +360,7 @@ static inline int __node_remap(int oldbit, #define nodes_remap(dst, src, old, new) \ __nodes_remap(&(dst), &(src), &(old), &(new), MAX_NUMNODES) -static inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp, +static __always_inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp, const nodemask_t *oldp, const nodemask_t *newp, int nbits) { bitmap_remap(dstp->bits, srcp->bits, oldp->bits, newp->bits, nbits); @@ -368,7 +368,7 @@ static inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp, #define nodes_onto(dst, orig, relmap) \ __nodes_onto(&(dst), &(orig), &(relmap), MAX_NUMNODES) -static inline void __nodes_onto(nodemask_t *dstp, const nodemask_t *origp, +static __always_inline void __nodes_onto(nodemask_t *dstp, const nodemask_t *origp, const nodemask_t *relmapp, int nbits) { bitmap_onto(dstp->bits, origp->bits, relmapp->bits, nbits); @@ -376,7 +376,7 @@ static inline void __nodes_onto(nodemask_t *dstp, const nodemask_t *origp, #define nodes_fold(dst, orig, sz) \ __nodes_fold(&(dst), &(orig), sz, MAX_NUMNODES) -static inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp, +static __always_inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp, int sz, int nbits) { bitmap_fold(dstp->bits, origp->bits, sz, nbits); @@ -418,22 +418,22 @@ enum node_states { extern nodemask_t node_states[NR_NODE_STATES]; #if MAX_NUMNODES > 1 -static inline int node_state(int node, enum node_states state) +static __always_inline int node_state(int node, enum node_states state) { return node_isset(node, node_states[state]); } -static inline void node_set_state(int node, enum node_states state) +static __always_inline void node_set_state(int node, enum node_states state) { __node_set(node, &node_states[state]); } -static inline void node_clear_state(int node, enum node_states state) +static __always_inline void node_clear_state(int node, enum node_states state) { __node_clear(node, &node_states[state]); } -static inline int num_node_state(enum node_states state) +static __always_inline int num_node_state(enum node_states state) { return nodes_weight(node_states[state]); } @@ -443,11 +443,11 @@ static inline int num_node_state(enum node_states state) #define first_online_node first_node(node_states[N_ONLINE]) #define first_memory_node first_node(node_states[N_MEMORY]) -static inline unsigned int next_online_node(int nid) +static __always_inline unsigned int next_online_node(int nid) { return next_node(nid, node_states[N_ONLINE]); } -static inline unsigned int next_memory_node(int nid) +static __always_inline unsigned int next_memory_node(int nid) { return next_node(nid, node_states[N_MEMORY]); } @@ -455,13 +455,13 @@ static inline unsigned int next_memory_node(int nid) extern unsigned int nr_node_ids; extern unsigned int nr_online_nodes; -static inline void node_set_online(int nid) +static __always_inline void node_set_online(int nid) { node_set_state(nid, N_ONLINE); nr_online_nodes = num_node_state(N_ONLINE); } -static inline void node_set_offline(int nid) +static __always_inline void node_set_offline(int nid) { node_clear_state(nid, N_ONLINE); nr_online_nodes = num_node_state(N_ONLINE); @@ -469,20 +469,20 @@ static inline void node_set_offline(int nid) #else -static inline int node_state(int node, enum node_states state) +static __always_inline int node_state(int node, enum node_states state) { return node == 0; } -static inline void node_set_state(int node, enum node_states state) +static __always_inline void node_set_state(int node, enum node_states state) { } -static inline void node_clear_state(int node, enum node_states state) +static __always_inline void node_clear_state(int node, enum node_states state) { } -static inline int num_node_state(enum node_states state) +static __always_inline int num_node_state(enum node_states state) { return 1; } @@ -502,7 +502,7 @@ static inline int num_node_state(enum node_states state) #endif -static inline int node_random(const nodemask_t *maskp) +static __always_inline int node_random(const nodemask_t *maskp) { #if defined(CONFIG_NUMA) && (MAX_NUMNODES > 1) int w, bit; -- cgit v1.2.3 From b27404b2bbf951a11500525dea15681cc970226c Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Mon, 19 Aug 2024 08:55:46 +0800 Subject: ALSA/ASoC/SoundWire: Intel: use single definition for SDW_INTEL_MAX_LINKS MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The definitions are currently duplicated in intel-sdw-acpi.c and sof_sdw.c. Move the definition to the sdw_intel.h header, and change the prefix to make it Intel-specific. No functionality change in this patch. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Péter Ujfalusi Signed-off-by: Bard Liao Reviewed-by: Takashi Iwai Link: https://patch.msgid.link/20240819005548.5867-2-yung-chuan.liao@linux.intel.com Signed-off-by: Mark Brown --- include/linux/soundwire/sdw_intel.h | 5 +++++ sound/hda/intel-sdw-acpi.c | 5 ++--- sound/soc/intel/boards/sof_sdw.c | 4 +++- sound/soc/intel/boards/sof_sdw_common.h | 4 +--- sound/soc/intel/boards/sof_sdw_hdmi.c | 2 ++ 5 files changed, 13 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index d537587b4499..87d82ea9a13a 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -447,4 +447,9 @@ extern const struct sdw_intel_hw_ops sdw_intel_lnl_hw_ops; #define SDW_INTEL_DEV_NUM_IDA_MIN 6 +/* + * Max number of links supported in hardware + */ +#define SDW_INTEL_MAX_LINKS 4 + #endif diff --git a/sound/hda/intel-sdw-acpi.c b/sound/hda/intel-sdw-acpi.c index f3b2a610df23..04d6b6beabca 100644 --- a/sound/hda/intel-sdw-acpi.c +++ b/sound/hda/intel-sdw-acpi.c @@ -17,7 +17,6 @@ #include #define SDW_LINK_TYPE 4 /* from Intel ACPI documentation */ -#define SDW_MAX_LINKS 4 static int ctrl_link_mask; module_param_named(sdw_link_mask, ctrl_link_mask, int, 0444); @@ -87,9 +86,9 @@ sdw_intel_scan_controller(struct sdw_intel_acpi_info *info) } /* Check count is within bounds */ - if (count > SDW_MAX_LINKS) { + if (count > SDW_INTEL_MAX_LINKS) { dev_err(&adev->dev, "Link count %d exceeds max %d\n", - count, SDW_MAX_LINKS); + count, SDW_INTEL_MAX_LINKS); return -EINVAL; } diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index d258728d64cf..b1fb6fabd3b7 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -5,12 +5,14 @@ * sof_sdw - ASOC Machine driver for Intel SoundWire platforms */ +#include #include #include #include #include #include #include +#include #include #include "sof_sdw_common.h" #include "../../codecs/rt711.h" @@ -883,7 +885,7 @@ static int create_sdw_dailinks(struct snd_soc_card *card, struct intel_mc_ctx *intel_ctx = (struct intel_mc_ctx *)ctx->private; int ret, i; - for (i = 0; i < SDW_MAX_LINKS; i++) + for (i = 0; i < SDW_INTEL_MAX_LINKS; i++) intel_ctx->sdw_pin_index[i] = SOC_SDW_INTEL_BIDIR_PDI_BASE; /* generate DAI links by each sdw link */ diff --git a/sound/soc/intel/boards/sof_sdw_common.h b/sound/soc/intel/boards/sof_sdw_common.h index 02f3eebd019d..c10d2711b730 100644 --- a/sound/soc/intel/boards/sof_sdw_common.h +++ b/sound/soc/intel/boards/sof_sdw_common.h @@ -19,8 +19,6 @@ #define SOC_SDW_MAX_CPU_DAIS 16 #define SOC_SDW_INTEL_BIDIR_PDI_BASE 2 -#define SDW_MAX_LINKS 4 - /* 8 combinations with 4 links + unused group 0 */ #define SDW_MAX_GROUPS 9 @@ -57,7 +55,7 @@ enum { struct intel_mc_ctx { struct sof_hdmi_private hdmi; /* To store SDW Pin index for each SoundWire link */ - unsigned int sdw_pin_index[SDW_MAX_LINKS]; + unsigned int sdw_pin_index[SDW_INTEL_MAX_LINKS]; }; extern unsigned long sof_sdw_quirk; diff --git a/sound/soc/intel/boards/sof_sdw_hdmi.c b/sound/soc/intel/boards/sof_sdw_hdmi.c index 4084119a9a5f..f92867deb029 100644 --- a/sound/soc/intel/boards/sof_sdw_hdmi.c +++ b/sound/soc/intel/boards/sof_sdw_hdmi.c @@ -5,10 +5,12 @@ * sof_sdw_hdmi - Helpers to handle HDMI from generic machine driver */ +#include #include #include #include #include +#include #include #include #include -- cgit v1.2.3 From d2234596be2192d9c1ae34f8c7534531191bc433 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Mon, 19 Aug 2024 08:55:47 +0800 Subject: soundwire: intel: add probe-time check on link id MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In older platforms, the number of links was constant and hard-coded to 4. Newer platforms can have varying number of links, so we need to add a probe-time check to make sure the ACPI-reported information with _DSD properties is aligned with hardware capabilities reported in the SoundWire LCAP register. Acked-by: Vinod Koul Signed-off-by: Pierre-Louis Bossart Reviewed-by: Péter Ujfalusi Signed-off-by: Bard Liao Acked-by: Mark Brown Reviewed-by: Takashi Iwai Link: https://patch.msgid.link/20240819005548.5867-3-yung-chuan.liao@linux.intel.com Signed-off-by: Mark Brown --- drivers/soundwire/intel.h | 7 +++++++ drivers/soundwire/intel_ace2x.c | 20 ++++++++++++++++++++ drivers/soundwire/intel_auxdevice.c | 14 ++++++++++++++ include/linux/soundwire/sdw_intel.h | 3 +++ 4 files changed, 44 insertions(+) (limited to 'include/linux') diff --git a/drivers/soundwire/intel.h b/drivers/soundwire/intel.h index 68838e843b54..1db4d9d3a3ba 100644 --- a/drivers/soundwire/intel.h +++ b/drivers/soundwire/intel.h @@ -222,6 +222,13 @@ static inline bool sdw_intel_sync_check_cmdsync_unlocked(struct sdw_intel *sdw) return false; } +static inline int sdw_intel_get_link_count(struct sdw_intel *sdw) +{ + if (SDW_INTEL_CHECK_OPS(sdw, get_link_count)) + return SDW_INTEL_OPS(sdw, get_link_count)(sdw); + return 4; /* default on older generations */ +} + /* common bus management */ int intel_start_bus(struct sdw_intel *sdw); int intel_start_bus_after_reset(struct sdw_intel *sdw); diff --git a/drivers/soundwire/intel_ace2x.c b/drivers/soundwire/intel_ace2x.c index 781fe0aefa68..fff312c6968d 100644 --- a/drivers/soundwire/intel_ace2x.c +++ b/drivers/soundwire/intel_ace2x.c @@ -706,10 +706,30 @@ static void intel_program_sdi(struct sdw_intel *sdw, int dev_num) __func__, sdw->instance, dev_num); } +static int intel_get_link_count(struct sdw_intel *sdw) +{ + int ret; + + ret = hdac_bus_eml_get_count(sdw->link_res->hbus, true, AZX_REG_ML_LEPTR_ID_SDW); + if (!ret) { + dev_err(sdw->cdns.dev, "%s: could not retrieve link count\n", __func__); + return -ENODEV; + } + + if (ret > SDW_INTEL_MAX_LINKS) { + dev_err(sdw->cdns.dev, "%s: link count %d exceed max %d\n", __func__, ret, SDW_INTEL_MAX_LINKS); + return -EINVAL; + } + + return ret; +} + const struct sdw_intel_hw_ops sdw_intel_lnl_hw_ops = { .debugfs_init = intel_ace2x_debugfs_init, .debugfs_exit = intel_ace2x_debugfs_exit, + .get_link_count = intel_get_link_count, + .register_dai = intel_register_dai, .check_clock_stop = intel_check_clock_stop, diff --git a/drivers/soundwire/intel_auxdevice.c b/drivers/soundwire/intel_auxdevice.c index 8807e01cbf7c..d110f2b587d5 100644 --- a/drivers/soundwire/intel_auxdevice.c +++ b/drivers/soundwire/intel_auxdevice.c @@ -317,6 +317,20 @@ static int intel_link_probe(struct auxiliary_device *auxdev, bus->link_id = auxdev->id; bus->clk_stop_timeout = 1; + /* + * paranoia check: make sure ACPI-reported number of links is aligned with + * hardware capabilities. + */ + ret = sdw_intel_get_link_count(sdw); + if (ret < 0) { + dev_err(dev, "%s: sdw_intel_get_link_count failed: %d\n", __func__, ret); + return ret; + } + if (ret <= sdw->instance) { + dev_err(dev, "%s: invalid link id %d, link count %d\n", __func__, auxdev->id, ret); + return -EINVAL; + } + sdw_cdns_probe(cdns); /* Set ops */ diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 87d82ea9a13a..cb8e7396b4db 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -388,6 +388,7 @@ struct sdw_intel; /* struct intel_sdw_hw_ops - SoundWire ops for Intel platforms. * @debugfs_init: initialize all debugfs capabilities * @debugfs_exit: close and cleanup debugfs capabilities + * @get_link_count: fetch link count from hardware registers * @register_dai: read all PDI information and register DAIs * @check_clock_stop: throw error message if clock is not stopped. * @start_bus: normal start @@ -412,6 +413,8 @@ struct sdw_intel_hw_ops { void (*debugfs_init)(struct sdw_intel *sdw); void (*debugfs_exit)(struct sdw_intel *sdw); + int (*get_link_count)(struct sdw_intel *sdw); + int (*register_dai)(struct sdw_intel *sdw); void (*check_clock_stop)(struct sdw_intel *sdw); -- cgit v1.2.3 From 1f3662838a05f1ab6af89a417f6f252d91d0806b Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Mon, 19 Aug 2024 08:55:48 +0800 Subject: soundwire: intel: increase maximum number of links MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Intel platforms have enabled 4 links since the beginning, newer platforms now have 5 links. Update the definition accordingly. This patch will have no effect on older platforms where the number of links was hard-coded. A follow-up patch will add a dynamic check that the ACPI-reported information is aligned with hardware capabilities on newer platforms. Acked-by: Vinod Koul Signed-off-by: Pierre-Louis Bossart Reviewed-by: Péter Ujfalusi Signed-off-by: Bard Liao Acked-by: Mark Brown Reviewed-by: Takashi Iwai Link: https://patch.msgid.link/20240819005548.5867-4-yung-chuan.liao@linux.intel.com Signed-off-by: Mark Brown --- include/linux/soundwire/sdw_intel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index cb8e7396b4db..37ae69365fe2 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -453,6 +453,6 @@ extern const struct sdw_intel_hw_ops sdw_intel_lnl_hw_ops; /* * Max number of links supported in hardware */ -#define SDW_INTEL_MAX_LINKS 4 +#define SDW_INTEL_MAX_LINKS 5 #endif -- cgit v1.2.3 From c393eaa85349941badf3ce5f087400dbaf3bbe02 Mon Sep 17 00:00:00 2001 From: Haifeng Xu Date: Fri, 26 Jul 2024 11:05:25 +0800 Subject: fs: don't flush in-flight wb switches for superblocks without cgroup writeback When deactivating any type of superblock, it had to wait for the in-flight wb switches to be completed. wb switches are executed in inode_switch_wbs_work_fn() which needs to acquire the wb_switch_rwsem and races against sync_inodes_sb(). If there are too much dirty data in the superblock, the waiting time may increase significantly. For superblocks without cgroup writeback such as tmpfs, they have nothing to do with the wb swithes, so the flushing can be avoided. Signed-off-by: Haifeng Xu Link: https://lore.kernel.org/r/20240726030525.180330-1-haifeng.xu@shopee.com Reviewed-by: Jan Kara Suggested-by: Jan Kara Signed-off-by: Christian Brauner --- fs/fs-writeback.c | 7 ++++++- fs/super.c | 2 +- include/linux/writeback.h | 4 ++-- 3 files changed, 9 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index b865a3fa52f3..4451ecff37c4 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1132,6 +1132,7 @@ out_bdi_put: /** * cgroup_writeback_umount - flush inode wb switches for umount + * @sb: target super_block * * This function is called when a super_block is about to be destroyed and * flushes in-flight inode wb switches. An inode wb switch goes through @@ -1140,8 +1141,12 @@ out_bdi_put: * rare occurrences and synchronize_rcu() can take a while, perform * flushing iff wb switches are in flight. */ -void cgroup_writeback_umount(void) +void cgroup_writeback_umount(struct super_block *sb) { + + if (!(sb->s_bdi->capabilities & BDI_CAP_WRITEBACK)) + return; + /* * SB_ACTIVE should be reliably cleared before checking * isw_nr_in_flight, see generic_shutdown_super(). diff --git a/fs/super.c b/fs/super.c index 38d72a3cf6fc..28f42502bdf9 100644 --- a/fs/super.c +++ b/fs/super.c @@ -621,7 +621,7 @@ void generic_shutdown_super(struct super_block *sb) sync_filesystem(sb); sb->s_flags &= ~SB_ACTIVE; - cgroup_writeback_umount(); + cgroup_writeback_umount(sb); /* Evict all inodes with zero refcount. */ evict_inodes(sb); diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 1a54676d843a..56b85841ae4c 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -217,7 +217,7 @@ void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page, size_t bytes); int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, enum wb_reason reason, struct wb_completion *done); -void cgroup_writeback_umount(void); +void cgroup_writeback_umount(struct super_block *sb); bool cleanup_offline_cgwb(struct bdi_writeback *wb); /** @@ -324,7 +324,7 @@ static inline void wbc_account_cgroup_owner(struct writeback_control *wbc, { } -static inline void cgroup_writeback_umount(void) +static inline void cgroup_writeback_umount(struct super_block *sb) { } -- cgit v1.2.3 From c01a5d89e5c8abe638107be2a4ea9e4c7fcdd7f6 Mon Sep 17 00:00:00 2001 From: Wang Long Date: Fri, 2 Aug 2024 17:19:01 +0800 Subject: percpu-rwsem: remove the unused parameter 'read' In the function percpu_rwsem_release, the parameter `read` is unused, so remove it. Signed-off-by: Wang Long Link: https://lore.kernel.org/r/20240802091901.2546797-1-w@laoqinren.net Reviewed-by: Jan Kara Signed-off-by: Christian Brauner --- fs/super.c | 2 +- include/linux/fs.h | 2 +- include/linux/percpu-rwsem.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/fs/super.c b/fs/super.c index 28f42502bdf9..33f35abb1990 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1905,7 +1905,7 @@ static void lockdep_sb_freeze_release(struct super_block *sb) int level; for (level = SB_FREEZE_LEVELS - 1; level >= 0; level--) - percpu_rwsem_release(sb->s_writers.rw_sem + level, 0, _THIS_IP_); + percpu_rwsem_release(sb->s_writers.rw_sem + level, _THIS_IP_); } /* diff --git a/include/linux/fs.h b/include/linux/fs.h index fb0426f349fc..c0286d479c9d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1683,7 +1683,7 @@ static inline bool __sb_start_write_trylock(struct super_block *sb, int level) #define __sb_writers_acquired(sb, lev) \ percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) #define __sb_writers_release(sb, lev) \ - percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) + percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], _THIS_IP_) /** * __sb_write_started - check if sb freeze level is held diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h index 36b942b67b7d..c012df33a9f0 100644 --- a/include/linux/percpu-rwsem.h +++ b/include/linux/percpu-rwsem.h @@ -145,7 +145,7 @@ extern void percpu_free_rwsem(struct percpu_rw_semaphore *); #define percpu_rwsem_assert_held(sem) lockdep_assert_held(sem) static inline void percpu_rwsem_release(struct percpu_rw_semaphore *sem, - bool read, unsigned long ip) + unsigned long ip) { lock_release(&sem->dep_map, ip); } -- cgit v1.2.3 From 81475beb1b5996505a39cd1d9316ce1e668932a2 Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 15 Aug 2024 16:32:28 +0000 Subject: block: Drop NULL check in bdev_write_zeroes_sectors() Function bdev_get_queue() must not return NULL, so drop the check in bdev_write_zeroes_sectors(). Reviewed-by: Christoph Hellwig Signed-off-by: John Garry Reviewed-by: Martin K. Petersen Reviewed-by: Nitesh Shetty Link: https://lore.kernel.org/r/20240815163228.216051-3-john.g.garry@oracle.com Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e85ec73a07d5..b7664d593486 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1296,12 +1296,7 @@ bdev_max_secure_erase_sectors(struct block_device *bdev) static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) { - struct request_queue *q = bdev_get_queue(bdev); - - if (q) - return q->limits.max_write_zeroes_sectors; - - return 0; + return bdev_get_queue(bdev)->limits.max_write_zeroes_sectors; } static inline bool bdev_nonrot(struct block_device *bdev) -- cgit v1.2.3 From 2865baf54077aa98fcdb478cefe6a42c417b9374 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 8 Apr 2024 20:04:58 -0700 Subject: x86: support user address masking instead of non-speculative conditional The Spectre-v1 mitigations made "access_ok()" much more expensive, since it has to serialize execution with the test for a valid user address. All the normal user copy routines avoid this by just masking the user address with a data-dependent mask instead, but the fast "unsafe_user_read()" kind of patterms that were supposed to be a fast case got slowed down. This introduces a notion of using src = masked_user_access_begin(src); to do the user address sanity using a data-dependent mask instead of the more traditional conditional if (user_read_access_begin(src, len)) { model. This model only works for dense accesses that start at 'src' and on architectures that have a guard region that is guaranteed to fault in between the user space and the kernel space area. With this, the user access doesn't need to be manually checked, because a bad address is guaranteed to fault (by some architecture masking trick: on x86-64 this involves just turning an invalid user address into all ones, since we don't map the top of address space). This only converts a couple of examples for now. Example x86-64 code generation for loading two words from user space: stac mov %rax,%rcx sar $0x3f,%rcx or %rax,%rcx mov (%rcx),%r13 mov 0x8(%rcx),%r14 clac where all the error handling and -EFAULT is now purely handled out of line by the exception path. Of course, if the micro-architecture does badly at 'clac' and 'stac', the above is still pitifully slow. But at least we did as well as we could. Signed-off-by: Linus Torvalds --- arch/x86/include/asm/uaccess_64.h | 8 ++++++++ fs/select.c | 4 +++- include/linux/uaccess.h | 7 +++++++ lib/strncpy_from_user.c | 9 +++++++++ lib/strnlen_user.c | 9 +++++++++ 5 files changed, 36 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index 04789f45ab2b..a10149a96d9e 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -53,6 +53,14 @@ static inline unsigned long __untagged_addr_remote(struct mm_struct *mm, */ #define valid_user_address(x) ((__force long)(x) >= 0) +/* + * Masking the user address is an alternative to a conditional + * user_access_begin that can avoid the fencing. This only works + * for dense accesses starting at the address. + */ +#define mask_user_address(x) ((typeof(x))((long)(x)|((long)(x)>>63))) +#define masked_user_access_begin(x) ({ __uaccess_begin(); mask_user_address(x); }) + /* * User pointers can have tag bits on x86-64. This scheme tolerates * arbitrary values in those bits rather then masking them off. diff --git a/fs/select.c b/fs/select.c index 9515c3fa1a03..bc185d111436 100644 --- a/fs/select.c +++ b/fs/select.c @@ -780,7 +780,9 @@ static inline int get_sigset_argpack(struct sigset_argpack *to, { // the path is hot enough for overhead of copy_from_user() to matter if (from) { - if (!user_read_access_begin(from, sizeof(*from))) + if (can_do_masked_user_access()) + from = masked_user_access_begin(from); + else if (!user_read_access_begin(from, sizeof(*from))) return -EFAULT; unsafe_get_user(to->p, &from->p, Efault); unsafe_get_user(to->size, &from->size, Efault); diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 3064314f4832..f18371f6cf36 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -32,6 +32,13 @@ }) #endif +#ifdef masked_user_access_begin + #define can_do_masked_user_access() 1 +#else + #define can_do_masked_user_access() 0 + #define masked_user_access_begin(src) NULL +#endif + /* * Architectures should provide two primitives (raw_copy_{to,from}_user()) * and get rid of their private instances of copy_{to,from}_user() and diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c index 6432b8c3e431..989a12a67872 100644 --- a/lib/strncpy_from_user.c +++ b/lib/strncpy_from_user.c @@ -120,6 +120,15 @@ long strncpy_from_user(char *dst, const char __user *src, long count) if (unlikely(count <= 0)) return 0; + if (can_do_masked_user_access()) { + long retval; + + src = masked_user_access_begin(src); + retval = do_strncpy_from_user(dst, src, count, count); + user_read_access_end(); + return retval; + } + max_addr = TASK_SIZE_MAX; src_addr = (unsigned long)untagged_addr(src); if (likely(src_addr < max_addr)) { diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c index feeb935a2299..6e489f9e90f1 100644 --- a/lib/strnlen_user.c +++ b/lib/strnlen_user.c @@ -96,6 +96,15 @@ long strnlen_user(const char __user *str, long count) if (unlikely(count <= 0)) return 0; + if (can_do_masked_user_access()) { + long retval; + + str = masked_user_access_begin(str); + retval = do_strnlen_user(str, count, count); + user_read_access_end(); + return retval; + } + max_addr = TASK_SIZE_MAX; src_addr = (unsigned long)untagged_addr(str); if (likely(src_addr < max_addr)) { -- cgit v1.2.3 From 8dffaec34dd55473adcbc924a4c9b04aaa0d4278 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 19 Aug 2024 12:18:23 -1000 Subject: workqueue: Fix htmldocs build warning Fix htmldocs build warning introduced by ec0a7d44b358 ("workqueue: Add interface for user-defined workqueue lockdep map"). Signed-off-by: Tejun Heo Reported-by: Stephen Rothwell Cc: Matthew Brost --- include/linux/workqueue.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 8ccbf510880b..04dff07a9e2b 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -534,7 +534,7 @@ alloc_workqueue_lockdep_map(const char *fmt, unsigned int flags, int max_active, * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags (only WQ_FREEZABLE and WQ_MEM_RECLAIM are meaningful) * @lockdep_map: user-defined lockdep_map - * @args: args for @fmt + * @...: args for @fmt * * Same as alloc_ordered_workqueue but with the a user-define lockdep_map. * Useful for workqueues created with the same purpose and to avoid leaking a -- cgit v1.2.3 From 7f6287417baf57754f47687c6ea1a749a0686ab0 Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Mon, 19 Aug 2024 18:28:05 +0200 Subject: bpf: Allow bpf_current_task_under_cgroup() with BPF_CGROUP_* The helper bpf_current_task_under_cgroup() currently is only allowed for tracing programs, allow its usage also in the BPF_CGROUP_* program types. Move the code from kernel/trace/bpf_trace.c to kernel/bpf/helpers.c, so it compiles also without CONFIG_BPF_EVENTS. This will be used in systemd-networkd to monitor the sysctl writes, and filter it's own writes from others: https://github.com/systemd/systemd/pull/32212 Signed-off-by: Matteo Croce Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20240819162805.78235-3-technoboy85@gmail.com --- include/linux/bpf.h | 1 + kernel/bpf/cgroup.c | 2 ++ kernel/bpf/helpers.c | 23 +++++++++++++++++++++++ kernel/trace/bpf_trace.c | 27 ++------------------------- 4 files changed, 28 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b9425e410bcb..f0192c173ed8 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -3206,6 +3206,7 @@ extern const struct bpf_func_proto bpf_sock_hash_update_proto; extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto; extern const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto; extern const struct bpf_func_proto bpf_get_cgroup_classid_curr_proto; +extern const struct bpf_func_proto bpf_current_task_under_cgroup_proto; extern const struct bpf_func_proto bpf_msg_redirect_hash_proto; extern const struct bpf_func_proto bpf_msg_redirect_map_proto; extern const struct bpf_func_proto bpf_sk_redirect_hash_proto; diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 8ba73042a239..e7113d700b87 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -2581,6 +2581,8 @@ cgroup_current_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_get_cgroup_classid: return &bpf_get_cgroup_classid_curr_proto; #endif + case BPF_FUNC_current_task_under_cgroup: + return &bpf_current_task_under_cgroup_proto; default: return NULL; } diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 26b9649ab4ce..12e3aa40b180 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -2458,6 +2458,29 @@ __bpf_kfunc long bpf_task_under_cgroup(struct task_struct *task, return ret; } +BPF_CALL_2(bpf_current_task_under_cgroup, struct bpf_map *, map, u32, idx) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + struct cgroup *cgrp; + + if (unlikely(idx >= array->map.max_entries)) + return -E2BIG; + + cgrp = READ_ONCE(array->ptrs[idx]); + if (unlikely(!cgrp)) + return -EAGAIN; + + return task_under_cgroup_hierarchy(current, cgrp); +} + +const struct bpf_func_proto bpf_current_task_under_cgroup_proto = { + .func = bpf_current_task_under_cgroup, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_ANYTHING, +}; + /** * bpf_task_get_cgroup1 - Acquires the associated cgroup of a task within a * specific cgroup1 hierarchy. The cgroup1 hierarchy is identified by its diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index d557bb11e0ff..b69a39316c0c 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -797,29 +797,6 @@ const struct bpf_func_proto bpf_task_pt_regs_proto = { .ret_btf_id = &bpf_task_pt_regs_ids[0], }; -BPF_CALL_2(bpf_current_task_under_cgroup, struct bpf_map *, map, u32, idx) -{ - struct bpf_array *array = container_of(map, struct bpf_array, map); - struct cgroup *cgrp; - - if (unlikely(idx >= array->map.max_entries)) - return -E2BIG; - - cgrp = READ_ONCE(array->ptrs[idx]); - if (unlikely(!cgrp)) - return -EAGAIN; - - return task_under_cgroup_hierarchy(current, cgrp); -} - -static const struct bpf_func_proto bpf_current_task_under_cgroup_proto = { - .func = bpf_current_task_under_cgroup, - .gpl_only = false, - .ret_type = RET_INTEGER, - .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_ANYTHING, -}; - struct send_signal_irq_work { struct irq_work irq_work; struct task_struct *task; @@ -1480,8 +1457,6 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_numa_node_id_proto; case BPF_FUNC_perf_event_read: return &bpf_perf_event_read_proto; - case BPF_FUNC_current_task_under_cgroup: - return &bpf_current_task_under_cgroup_proto; case BPF_FUNC_get_prandom_u32: return &bpf_get_prandom_u32_proto; case BPF_FUNC_probe_write_user: @@ -1510,6 +1485,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_cgrp_storage_get_proto; case BPF_FUNC_cgrp_storage_delete: return &bpf_cgrp_storage_delete_proto; + case BPF_FUNC_current_task_under_cgroup: + return &bpf_current_task_under_cgroup_proto; #endif case BPF_FUNC_send_signal: return &bpf_send_signal_proto; -- cgit v1.2.3 From 6ad8bc92a47702f0b5d0b96b680199910b89f688 Mon Sep 17 00:00:00 2001 From: Christian Hopps Date: Thu, 15 Aug 2024 13:21:14 -0400 Subject: net: add copy from skb_seq_state to buffer function Add an skb helper function to copy a range of bytes from within an existing skb_seq_state. Signed-off-by: Christian Hopps Signed-off-by: Steffen Klassert --- include/linux/skbuff.h | 1 + net/core/skbuff.c | 35 +++++++++++++++++++++++++++++++++++ 2 files changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 29c3ea5b6e93..a871533b8568 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1433,6 +1433,7 @@ void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from, unsigned int skb_seq_read(unsigned int consumed, const u8 **data, struct skb_seq_state *st); void skb_abort_seq_read(struct skb_seq_state *st); +int skb_copy_seq_read(struct skb_seq_state *st, int offset, void *to, int len); unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, unsigned int to, struct ts_config *config); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 83f8cd8aa2d1..fe4b2dc5c19b 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4409,6 +4409,41 @@ void skb_abort_seq_read(struct skb_seq_state *st) } EXPORT_SYMBOL(skb_abort_seq_read); +/** + * skb_copy_seq_read() - copy from a skb_seq_state to a buffer + * @st: source skb_seq_state + * @offset: offset in source + * @to: destination buffer + * @len: number of bytes to copy + * + * Copy @len bytes from @offset bytes into the source @st to the destination + * buffer @to. `offset` should increase (or be unchanged) with each subsequent + * call to this function. If offset needs to decrease from the previous use `st` + * should be reset first. + * + * Return: 0 on success or -EINVAL if the copy ended early + */ +int skb_copy_seq_read(struct skb_seq_state *st, int offset, void *to, int len) +{ + const u8 *data; + u32 sqlen; + + for (;;) { + sqlen = skb_seq_read(offset, &data, st); + if (sqlen == 0) + return -EINVAL; + if (sqlen >= len) { + memcpy(to, data, len); + return 0; + } + memcpy(to, data, sqlen); + to += sqlen; + offset += sqlen; + len -= sqlen; + } +} +EXPORT_SYMBOL(skb_copy_seq_read); + #define TS_SKB_CB(state) ((struct skb_seq_state *) &((state)->cb)) static unsigned int skb_ts_get_next_block(unsigned int offset, const u8 **text, -- cgit v1.2.3 From b6cee6544d01b8ac01232d343b1b2b594d94d61c Mon Sep 17 00:00:00 2001 From: Dikshita Agarwal Date: Mon, 19 Aug 2024 15:59:09 +0530 Subject: PM: domains: add device managed version of dev_pm_domain_attach|detach_list() Add the devres-enabled version of dev_pm_domain_attach|detach_list. If client drivers use devm_pm_domain_attach_list() to attach the PM domains, devm_pm_domain_detach_list() will be invoked implicitly during remove phase. Signed-off-by: Dikshita Agarwal Link: https://lore.kernel.org/r/1724063350-11993-2-git-send-email-quic_dikshita@quicinc.com Signed-off-by: Ulf Hansson --- drivers/base/power/common.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/pm_domain.h | 11 +++++++++++ 2 files changed, 56 insertions(+) (limited to 'include/linux') diff --git a/drivers/base/power/common.c b/drivers/base/power/common.c index 327d168dd37a..8c34ae1cd8d5 100644 --- a/drivers/base/power/common.c +++ b/drivers/base/power/common.c @@ -276,6 +276,51 @@ err_attach: } EXPORT_SYMBOL_GPL(dev_pm_domain_attach_list); +/** + * devm_pm_domain_detach_list - devres-enabled version of dev_pm_domain_detach_list. + * @_list: The list of PM domains to detach. + * + * This function reverse the actions from devm_pm_domain_attach_list(). + * it will be invoked during the remove phase from drivers implicitly if driver + * uses devm_pm_domain_attach_list() to attach the PM domains. + */ +static void devm_pm_domain_detach_list(void *_list) +{ + struct dev_pm_domain_list *list = _list; + + dev_pm_domain_detach_list(list); +} + +/** + * devm_pm_domain_attach_list - devres-enabled version of dev_pm_domain_attach_list + * @dev: The device used to lookup the PM domains for. + * @data: The data used for attaching to the PM domains. + * @list: An out-parameter with an allocated list of attached PM domains. + * + * NOTE: this will also handle calling devm_pm_domain_detach_list() for + * you during remove phase. + * + * Returns the number of attached PM domains or a negative error code in case of + * a failure. + */ +int devm_pm_domain_attach_list(struct device *dev, + const struct dev_pm_domain_attach_data *data, + struct dev_pm_domain_list **list) +{ + int ret, num_pds; + + num_pds = dev_pm_domain_attach_list(dev, data, list); + if (num_pds <= 0) + return num_pds; + + ret = devm_add_action_or_reset(dev, devm_pm_domain_detach_list, *list); + if (ret) + return ret; + + return num_pds; +} +EXPORT_SYMBOL_GPL(devm_pm_domain_attach_list); + /** * dev_pm_domain_detach - Detach a device from its PM domain. * @dev: Device to detach. diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index b86bb52858ac..b637ec14025f 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -476,6 +476,9 @@ struct device *dev_pm_domain_attach_by_name(struct device *dev, int dev_pm_domain_attach_list(struct device *dev, const struct dev_pm_domain_attach_data *data, struct dev_pm_domain_list **list); +int devm_pm_domain_attach_list(struct device *dev, + const struct dev_pm_domain_attach_data *data, + struct dev_pm_domain_list **list); void dev_pm_domain_detach(struct device *dev, bool power_off); void dev_pm_domain_detach_list(struct dev_pm_domain_list *list); int dev_pm_domain_start(struct device *dev); @@ -502,6 +505,14 @@ static inline int dev_pm_domain_attach_list(struct device *dev, { return 0; } + +static inline int devm_pm_domain_attach_list(struct device *dev, + const struct dev_pm_domain_attach_data *data, + struct dev_pm_domain_list **list) +{ + return 0; +} + static inline void dev_pm_domain_detach(struct device *dev, bool power_off) {} static inline void dev_pm_domain_detach_list(struct dev_pm_domain_list *list) {} static inline int dev_pm_domain_start(struct device *dev) -- cgit v1.2.3 From ea72ce5da22806d5713f3ffb39a6d5ae73841f93 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 14 Aug 2024 00:29:36 +0200 Subject: x86/kaslr: Expose and use the end of the physical memory address space iounmap() on x86 occasionally fails to unmap because the provided valid ioremap address is not below high_memory. It turned out that this happens due to KASLR. KASLR uses the full address space between PAGE_OFFSET and vaddr_end to randomize the starting points of the direct map, vmalloc and vmemmap regions. It thereby limits the size of the direct map by using the installed memory size plus an extra configurable margin for hot-plug memory. This limitation is done to gain more randomization space because otherwise only the holes between the direct map, vmalloc, vmemmap and vaddr_end would be usable for randomizing. The limited direct map size is not exposed to the rest of the kernel, so the memory hot-plug and resource management related code paths still operate under the assumption that the available address space can be determined with MAX_PHYSMEM_BITS. request_free_mem_region() allocates from (1 << MAX_PHYSMEM_BITS) - 1 downwards. That means the first allocation happens past the end of the direct map and if unlucky this address is in the vmalloc space, which causes high_memory to become greater than VMALLOC_START and consequently causes iounmap() to fail for valid ioremap addresses. MAX_PHYSMEM_BITS cannot be changed for that because the randomization does not align with address bit boundaries and there are other places which actually require to know the maximum number of address bits. All remaining usage sites of MAX_PHYSMEM_BITS have been analyzed and found to be correct. Cure this by exposing the end of the direct map via PHYSMEM_END and use that for the memory hot-plug and resource management related places instead of relying on MAX_PHYSMEM_BITS. In the KASLR case PHYSMEM_END maps to a variable which is initialized by the KASLR initialization and otherwise it is based on MAX_PHYSMEM_BITS as before. To prevent future hickups add a check into add_pages() to catch callers trying to add memory above PHYSMEM_END. Fixes: 0483e1fa6e09 ("x86/mm: Implement ASLR for kernel memory regions") Reported-by: Max Ramanouski Reported-by: Alistair Popple Signed-off-by: Thomas Gleixner Tested-By: Max Ramanouski Tested-by: Alistair Popple Reviewed-by: Dan Williams Reviewed-by: Alistair Popple Reviewed-by: Kees Cook Cc: stable@vger.kernel.org Link: https://lore.kernel.org/all/87ed6soy3z.ffs@tglx --- arch/x86/include/asm/page_64.h | 1 + arch/x86/include/asm/pgtable_64_types.h | 4 ++++ arch/x86/mm/init_64.c | 4 ++++ arch/x86/mm/kaslr.c | 32 ++++++++++++++++++++++++++------ include/linux/mm.h | 4 ++++ kernel/resource.c | 6 ++---- mm/memory_hotplug.c | 2 +- mm/sparse.c | 2 +- 8 files changed, 43 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h index af4302d79b59..f3d257c45225 100644 --- a/arch/x86/include/asm/page_64.h +++ b/arch/x86/include/asm/page_64.h @@ -17,6 +17,7 @@ extern unsigned long phys_base; extern unsigned long page_offset_base; extern unsigned long vmalloc_base; extern unsigned long vmemmap_base; +extern unsigned long physmem_end; static __always_inline unsigned long __phys_addr_nodebug(unsigned long x) { diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 9053dfe9fa03..a98e53491a4e 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -140,6 +140,10 @@ extern unsigned int ptrs_per_p4d; # define VMEMMAP_START __VMEMMAP_BASE_L4 #endif /* CONFIG_DYNAMIC_MEMORY_LAYOUT */ +#ifdef CONFIG_RANDOMIZE_MEMORY +# define PHYSMEM_END physmem_end +#endif + /* * End of the region for which vmalloc page tables are pre-allocated. * For non-KMSAN builds, this is the same as VMALLOC_END. diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index d8dbeac8b206..ff253648706f 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -958,8 +958,12 @@ static void update_end_of_memory_vars(u64 start, u64 size) int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, struct mhp_params *params) { + unsigned long end = ((start_pfn + nr_pages) << PAGE_SHIFT) - 1; int ret; + if (WARN_ON_ONCE(end > PHYSMEM_END)) + return -ERANGE; + ret = __add_pages(nid, start_pfn, nr_pages, params); WARN_ON_ONCE(ret); diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index 37db264866b6..230f1dee4f09 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -47,13 +47,24 @@ static const unsigned long vaddr_end = CPU_ENTRY_AREA_BASE; */ static __initdata struct kaslr_memory_region { unsigned long *base; + unsigned long *end; unsigned long size_tb; } kaslr_regions[] = { - { &page_offset_base, 0 }, - { &vmalloc_base, 0 }, - { &vmemmap_base, 0 }, + { + .base = &page_offset_base, + .end = &physmem_end, + }, + { + .base = &vmalloc_base, + }, + { + .base = &vmemmap_base, + }, }; +/* The end of the possible address space for physical memory */ +unsigned long physmem_end __ro_after_init; + /* Get size in bytes used by the memory region */ static inline unsigned long get_padding(struct kaslr_memory_region *region) { @@ -82,6 +93,8 @@ void __init kernel_randomize_memory(void) BUILD_BUG_ON(vaddr_end != CPU_ENTRY_AREA_BASE); BUILD_BUG_ON(vaddr_end > __START_KERNEL_map); + /* Preset the end of the possible address space for physical memory */ + physmem_end = ((1ULL << MAX_PHYSMEM_BITS) - 1); if (!kaslr_memory_enabled()) return; @@ -128,11 +141,18 @@ void __init kernel_randomize_memory(void) vaddr += entropy; *kaslr_regions[i].base = vaddr; + /* Calculate the end of the region */ + vaddr += get_padding(&kaslr_regions[i]); /* - * Jump the region and add a minimum padding based on - * randomization alignment. + * KASLR trims the maximum possible size of the + * direct-map. Update the physmem_end boundary. + * No rounding required as the region starts + * PUD aligned and size is in units of TB. */ - vaddr += get_padding(&kaslr_regions[i]); + if (kaslr_regions[i].end) + *kaslr_regions[i].end = __pa_nodebug(vaddr - 1); + + /* Add a minimum padding based on randomization alignment. */ vaddr = round_up(vaddr + 1, PUD_SIZE); remain_entropy -= entropy; } diff --git a/include/linux/mm.h b/include/linux/mm.h index c4b238a20b76..b3864156eaa4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -97,6 +97,10 @@ extern const int mmap_rnd_compat_bits_max; extern int mmap_rnd_compat_bits __read_mostly; #endif +#ifndef PHYSMEM_END +# define PHYSMEM_END ((1ULL << MAX_PHYSMEM_BITS) - 1) +#endif + #include #include diff --git a/kernel/resource.c b/kernel/resource.c index 14777afb0a99..a83040fde236 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -1826,8 +1826,7 @@ static resource_size_t gfr_start(struct resource *base, resource_size_t size, if (flags & GFR_DESCENDING) { resource_size_t end; - end = min_t(resource_size_t, base->end, - (1ULL << MAX_PHYSMEM_BITS) - 1); + end = min_t(resource_size_t, base->end, PHYSMEM_END); return end - size + 1; } @@ -1844,8 +1843,7 @@ static bool gfr_continue(struct resource *base, resource_size_t addr, * @size did not wrap 0. */ return addr > addr - size && - addr <= min_t(resource_size_t, base->end, - (1ULL << MAX_PHYSMEM_BITS) - 1); + addr <= min_t(resource_size_t, base->end, PHYSMEM_END); } static resource_size_t gfr_next(resource_size_t addr, resource_size_t size, diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 66267c26ca1b..951878ab627a 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1681,7 +1681,7 @@ struct range __weak arch_get_mappable_range(void) struct range mhp_get_pluggable_range(bool need_mapping) { - const u64 max_phys = (1ULL << MAX_PHYSMEM_BITS) - 1; + const u64 max_phys = PHYSMEM_END; struct range mhp_range; if (need_mapping) { diff --git a/mm/sparse.c b/mm/sparse.c index e4b830091d13..0c3bff882033 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -129,7 +129,7 @@ static inline int sparse_early_nid(struct mem_section *section) static void __meminit mminit_validate_memmodel_limits(unsigned long *start_pfn, unsigned long *end_pfn) { - unsigned long max_sparsemem_pfn = 1UL << (MAX_PHYSMEM_BITS-PAGE_SHIFT); + unsigned long max_sparsemem_pfn = (PHYSMEM_END + 1) >> PAGE_SHIFT; /* * Sanity checks - do not allow an architecture to pass -- cgit v1.2.3 From acb0184fe9bca3bb7103dadc76ba9d38c969ca86 Mon Sep 17 00:00:00 2001 From: James Clark Date: Mon, 22 Jul 2024 11:11:53 +0100 Subject: coresight: Move struct coresight_trace_id_map to common header The trace ID maps will need to be created and stored by the core and Perf code so move the definition up to the common header. Reviewed-by: Anshuman Khandual Reviewed-by: Mike Leach Signed-off-by: James Clark Tested-by: Leo Yan Tested-by: Ganapatrao Kulkarni Signed-off-by: James Clark Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20240722101202.26915-12-james.clark@linaro.org --- drivers/hwtracing/coresight/coresight-trace-id.c | 1 + drivers/hwtracing/coresight/coresight-trace-id.h | 19 ------------------- include/linux/coresight.h | 18 ++++++++++++++++++ 3 files changed, 19 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/drivers/hwtracing/coresight/coresight-trace-id.c b/drivers/hwtracing/coresight/coresight-trace-id.c index af5b4ef59cea..19005b5b4dc4 100644 --- a/drivers/hwtracing/coresight/coresight-trace-id.c +++ b/drivers/hwtracing/coresight/coresight-trace-id.c @@ -3,6 +3,7 @@ * Copyright (c) 2022, Linaro Limited, All rights reserved. * Author: Mike Leach */ +#include #include #include #include diff --git a/drivers/hwtracing/coresight/coresight-trace-id.h b/drivers/hwtracing/coresight/coresight-trace-id.h index 3797777d367e..49438a96fcc6 100644 --- a/drivers/hwtracing/coresight/coresight-trace-id.h +++ b/drivers/hwtracing/coresight/coresight-trace-id.h @@ -32,10 +32,6 @@ #include #include - -/* architecturally we have 128 IDs some of which are reserved */ -#define CORESIGHT_TRACE_IDS_MAX 128 - /* ID 0 is reserved */ #define CORESIGHT_TRACE_ID_RES_0 0 @@ -46,21 +42,6 @@ #define IS_VALID_CS_TRACE_ID(id) \ ((id > CORESIGHT_TRACE_ID_RES_0) && (id < CORESIGHT_TRACE_ID_RES_TOP)) -/** - * Trace ID map. - * - * @used_ids: Bitmap to register available (bit = 0) and in use (bit = 1) IDs. - * Initialised so that the reserved IDs are permanently marked as - * in use. - * @pend_rel_ids: CPU IDs that have been released by the trace source but not - * yet marked as available, to allow re-allocation to the same - * CPU during a perf session. - */ -struct coresight_trace_id_map { - DECLARE_BITMAP(used_ids, CORESIGHT_TRACE_IDS_MAX); - DECLARE_BITMAP(pend_rel_ids, CORESIGHT_TRACE_IDS_MAX); -}; - /* Allocate and release IDs for a single default trace ID map */ /** diff --git a/include/linux/coresight.h b/include/linux/coresight.h index f09ace92176e..c16c61a8411d 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -218,6 +218,24 @@ struct coresight_sysfs_link { const char *target_name; }; +/* architecturally we have 128 IDs some of which are reserved */ +#define CORESIGHT_TRACE_IDS_MAX 128 + +/** + * Trace ID map. + * + * @used_ids: Bitmap to register available (bit = 0) and in use (bit = 1) IDs. + * Initialised so that the reserved IDs are permanently marked as + * in use. + * @pend_rel_ids: CPU IDs that have been released by the trace source but not + * yet marked as available, to allow re-allocation to the same + * CPU during a perf session. + */ +struct coresight_trace_id_map { + DECLARE_BITMAP(used_ids, CORESIGHT_TRACE_IDS_MAX); + DECLARE_BITMAP(pend_rel_ids, CORESIGHT_TRACE_IDS_MAX); +}; + /** * struct coresight_device - representation of a device as used by the framework * @pdata: Platform data with device connections associated to this device. -- cgit v1.2.3 From d53c8253c7822fbc524adcd950e7c6de6a229c99 Mon Sep 17 00:00:00 2001 From: James Clark Date: Mon, 22 Jul 2024 11:11:55 +0100 Subject: coresight: Make CPU id map a property of a trace ID map The global CPU ID mappings won't work for per-sink ID maps so move it to the ID map struct. coresight_trace_id_release_all_pending() is hard coded to operate on the default map, but once Perf sessions use their own maps the pending release mechanism will be deleted. So it doesn't need to be extended to accept a trace ID map argument at this point. Signed-off-by: James Clark Reviewed-by: Mike Leach Tested-by: Leo Yan Signed-off-by: James Clark Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20240722101202.26915-14-james.clark@linaro.org --- drivers/hwtracing/coresight/coresight-trace-id.c | 16 +++++++++------- include/linux/coresight.h | 1 + 2 files changed, 10 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/hwtracing/coresight/coresight-trace-id.c b/drivers/hwtracing/coresight/coresight-trace-id.c index 5561989a03fa..8a777c0af6ea 100644 --- a/drivers/hwtracing/coresight/coresight-trace-id.c +++ b/drivers/hwtracing/coresight/coresight-trace-id.c @@ -13,10 +13,12 @@ #include "coresight-trace-id.h" /* Default trace ID map. Used in sysfs mode and for system sources */ -static struct coresight_trace_id_map id_map_default; +static DEFINE_PER_CPU(atomic_t, id_map_default_cpu_ids) = ATOMIC_INIT(0); +static struct coresight_trace_id_map id_map_default = { + .cpu_map = &id_map_default_cpu_ids +}; -/* maintain a record of the mapping of IDs and pending releases per cpu */ -static DEFINE_PER_CPU(atomic_t, cpu_id) = ATOMIC_INIT(0); +/* maintain a record of the pending releases per cpu */ static cpumask_t cpu_id_release_pending; /* perf session active counter */ @@ -49,7 +51,7 @@ static void coresight_trace_id_dump_table(struct coresight_trace_id_map *id_map, /* unlocked read of current trace ID value for given CPU */ static int _coresight_trace_id_read_cpu_id(int cpu, struct coresight_trace_id_map *id_map) { - return atomic_read(&per_cpu(cpu_id, cpu)); + return atomic_read(per_cpu_ptr(id_map->cpu_map, cpu)); } /* look for next available odd ID, return 0 if none found */ @@ -145,7 +147,7 @@ static void coresight_trace_id_release_all_pending(void) clear_bit(bit, id_map->pend_rel_ids); } for_each_cpu(cpu, &cpu_id_release_pending) { - atomic_set(&per_cpu(cpu_id, cpu), 0); + atomic_set(per_cpu_ptr(id_map_default.cpu_map, cpu), 0); cpumask_clear_cpu(cpu, &cpu_id_release_pending); } spin_unlock_irqrestore(&id_map_lock, flags); @@ -181,7 +183,7 @@ static int _coresight_trace_id_get_cpu_id(int cpu, struct coresight_trace_id_map goto get_cpu_id_out_unlock; /* allocate the new id to the cpu */ - atomic_set(&per_cpu(cpu_id, cpu), id); + atomic_set(per_cpu_ptr(id_map->cpu_map, cpu), id); get_cpu_id_clr_pend: /* we are (re)using this ID - so ensure it is not marked for release */ @@ -215,7 +217,7 @@ static void _coresight_trace_id_put_cpu_id(int cpu, struct coresight_trace_id_ma } else { /* otherwise clear id */ coresight_trace_id_free(id, id_map); - atomic_set(&per_cpu(cpu_id, cpu), 0); + atomic_set(per_cpu_ptr(id_map->cpu_map, cpu), 0); } spin_unlock_irqrestore(&id_map_lock, flags); diff --git a/include/linux/coresight.h b/include/linux/coresight.h index c16c61a8411d..7d62b88bfb5c 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -234,6 +234,7 @@ struct coresight_sysfs_link { struct coresight_trace_id_map { DECLARE_BITMAP(used_ids, CORESIGHT_TRACE_IDS_MAX); DECLARE_BITMAP(pend_rel_ids, CORESIGHT_TRACE_IDS_MAX); + atomic_t __percpu *cpu_map; }; /** -- cgit v1.2.3 From 5ad628a7617607baac53745f8025638b967470a2 Mon Sep 17 00:00:00 2001 From: James Clark Date: Mon, 22 Jul 2024 11:11:56 +0100 Subject: coresight: Use per-sink trace ID maps for Perf sessions This will allow sessions with more than CORESIGHT_TRACE_IDS_MAX ETMs as long as there are fewer than that many ETMs connected to each sink. Each sink owns its own trace ID map, and any Perf session connecting to that sink will allocate from it, even if the sink is currently in use by other users. This is similar to the existing behavior where the dynamic trace IDs are constant as long as there is any concurrent Perf session active. It's not completely optimal because slightly more IDs will be used than necessary, but the optimal solution involves tracking the PIDs of each session and allocating ID maps based on the session owner. This is difficult to do with the combination of per-thread and per-cpu modes and some scheduling issues. The complexity of this isn't likely to worth it because even with multiple users they'd just see a difference in the ordering of ID allocations rather than hitting any limits (unless the hardware does have too many ETMs connected to one sink). Signed-off-by: James Clark Reviewed-by: Mike Leach Signed-off-by: James Clark Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20240722101202.26915-15-james.clark@linaro.org --- drivers/hwtracing/coresight/coresight-core.c | 10 ++++++++++ drivers/hwtracing/coresight/coresight-dummy.c | 3 ++- drivers/hwtracing/coresight/coresight-etm-perf.c | 15 ++++++++++----- drivers/hwtracing/coresight/coresight-etm3x-core.c | 9 +++++---- drivers/hwtracing/coresight/coresight-etm4x-core.c | 9 +++++---- drivers/hwtracing/coresight/coresight-stm.c | 3 ++- drivers/hwtracing/coresight/coresight-sysfs.c | 3 ++- drivers/hwtracing/coresight/coresight-tpdm.c | 3 ++- include/linux/coresight.h | 3 ++- 9 files changed, 40 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/drivers/hwtracing/coresight/coresight-core.c b/drivers/hwtracing/coresight/coresight-core.c index 9fc6f6b863e0..faf560ba8d64 100644 --- a/drivers/hwtracing/coresight/coresight-core.c +++ b/drivers/hwtracing/coresight/coresight-core.c @@ -902,6 +902,7 @@ static void coresight_device_release(struct device *dev) struct coresight_device *csdev = to_coresight_device(dev); fwnode_handle_put(csdev->dev.fwnode); + free_percpu(csdev->perf_sink_id_map.cpu_map); kfree(csdev); } @@ -1159,6 +1160,15 @@ struct coresight_device *coresight_register(struct coresight_desc *desc) csdev->dev.fwnode = fwnode_handle_get(dev_fwnode(desc->dev)); dev_set_name(&csdev->dev, "%s", desc->name); + if (csdev->type == CORESIGHT_DEV_TYPE_SINK || + csdev->type == CORESIGHT_DEV_TYPE_LINKSINK) { + csdev->perf_sink_id_map.cpu_map = alloc_percpu(atomic_t); + if (!csdev->perf_sink_id_map.cpu_map) { + kfree(csdev); + ret = -ENOMEM; + goto err_out; + } + } /* * Make sure the device registration and the connection fixup * are synchronised, so that we don't see uninitialised devices diff --git a/drivers/hwtracing/coresight/coresight-dummy.c b/drivers/hwtracing/coresight/coresight-dummy.c index dab389a5507c..bb85fa663ffc 100644 --- a/drivers/hwtracing/coresight/coresight-dummy.c +++ b/drivers/hwtracing/coresight/coresight-dummy.c @@ -21,7 +21,8 @@ DEFINE_CORESIGHT_DEVLIST(source_devs, "dummy_source"); DEFINE_CORESIGHT_DEVLIST(sink_devs, "dummy_sink"); static int dummy_source_enable(struct coresight_device *csdev, - struct perf_event *event, enum cs_mode mode) + struct perf_event *event, enum cs_mode mode, + __maybe_unused struct coresight_trace_id_map *id_map) { if (!coresight_take_mode(csdev, mode)) return -EBUSY; diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index c0c60e6a1703..7fb55dafb639 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -229,10 +229,13 @@ static void free_event_data(struct work_struct *work) struct list_head **ppath; ppath = etm_event_cpu_path_ptr(event_data, cpu); - if (!(IS_ERR_OR_NULL(*ppath))) + if (!(IS_ERR_OR_NULL(*ppath))) { + struct coresight_device *sink = coresight_get_sink(*ppath); + + coresight_trace_id_put_cpu_id_map(cpu, &sink->perf_sink_id_map); coresight_release_path(*ppath); + } *ppath = NULL; - coresight_trace_id_put_cpu_id(cpu); } /* mark perf event as done for trace id allocator */ @@ -401,7 +404,7 @@ static void *etm_setup_aux(struct perf_event *event, void **pages, } /* ensure we can allocate a trace ID for this CPU */ - trace_id = coresight_trace_id_get_cpu_id(cpu); + trace_id = coresight_trace_id_get_cpu_id_map(cpu, &sink->perf_sink_id_map); if (!IS_VALID_CS_TRACE_ID(trace_id)) { cpumask_clear_cpu(cpu, mask); coresight_release_path(path); @@ -495,7 +498,8 @@ static void etm_event_start(struct perf_event *event, int flags) goto fail_end_stop; /* Finally enable the tracer */ - if (source_ops(csdev)->enable(csdev, event, CS_MODE_PERF)) + if (source_ops(csdev)->enable(csdev, event, CS_MODE_PERF, + &sink->perf_sink_id_map)) goto fail_disable_path; /* @@ -507,7 +511,8 @@ static void etm_event_start(struct perf_event *event, int flags) hw_id = FIELD_PREP(CS_AUX_HW_ID_VERSION_MASK, CS_AUX_HW_ID_CURR_VERSION); hw_id |= FIELD_PREP(CS_AUX_HW_ID_TRACE_ID_MASK, - coresight_trace_id_read_cpu_id(cpu)); + coresight_trace_id_read_cpu_id_map(cpu, + &sink->perf_sink_id_map)); perf_report_aux_output_id(event, hw_id); } diff --git a/drivers/hwtracing/coresight/coresight-etm3x-core.c b/drivers/hwtracing/coresight/coresight-etm3x-core.c index 8b362605d242..c103f4c70f5d 100644 --- a/drivers/hwtracing/coresight/coresight-etm3x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm3x-core.c @@ -481,7 +481,8 @@ void etm_release_trace_id(struct etm_drvdata *drvdata) } static int etm_enable_perf(struct coresight_device *csdev, - struct perf_event *event) + struct perf_event *event, + struct coresight_trace_id_map *id_map) { struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); int trace_id; @@ -500,7 +501,7 @@ static int etm_enable_perf(struct coresight_device *csdev, * with perf locks - we know the ID cannot change until perf shuts down * the session */ - trace_id = coresight_trace_id_read_cpu_id(drvdata->cpu); + trace_id = coresight_trace_id_read_cpu_id_map(drvdata->cpu, id_map); if (!IS_VALID_CS_TRACE_ID(trace_id)) { dev_err(&drvdata->csdev->dev, "Failed to set trace ID for %s on CPU%d\n", dev_name(&drvdata->csdev->dev), drvdata->cpu); @@ -553,7 +554,7 @@ unlock_enable_sysfs: } static int etm_enable(struct coresight_device *csdev, struct perf_event *event, - enum cs_mode mode) + enum cs_mode mode, struct coresight_trace_id_map *id_map) { int ret; struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); @@ -568,7 +569,7 @@ static int etm_enable(struct coresight_device *csdev, struct perf_event *event, ret = etm_enable_sysfs(csdev); break; case CS_MODE_PERF: - ret = etm_enable_perf(csdev, event); + ret = etm_enable_perf(csdev, event, id_map); break; default: ret = -EINVAL; diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c index bf01f01964cf..66d44a404ad0 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c @@ -752,7 +752,8 @@ out: } static int etm4_enable_perf(struct coresight_device *csdev, - struct perf_event *event) + struct perf_event *event, + struct coresight_trace_id_map *id_map) { int ret = 0, trace_id; struct etmv4_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); @@ -775,7 +776,7 @@ static int etm4_enable_perf(struct coresight_device *csdev, * with perf locks - we know the ID cannot change until perf shuts down * the session */ - trace_id = coresight_trace_id_read_cpu_id(drvdata->cpu); + trace_id = coresight_trace_id_read_cpu_id_map(drvdata->cpu, id_map); if (!IS_VALID_CS_TRACE_ID(trace_id)) { dev_err(&drvdata->csdev->dev, "Failed to set trace ID for %s on CPU%d\n", dev_name(&drvdata->csdev->dev), drvdata->cpu); @@ -837,7 +838,7 @@ unlock_sysfs_enable: } static int etm4_enable(struct coresight_device *csdev, struct perf_event *event, - enum cs_mode mode) + enum cs_mode mode, struct coresight_trace_id_map *id_map) { int ret; @@ -851,7 +852,7 @@ static int etm4_enable(struct coresight_device *csdev, struct perf_event *event, ret = etm4_enable_sysfs(csdev); break; case CS_MODE_PERF: - ret = etm4_enable_perf(csdev, event); + ret = etm4_enable_perf(csdev, event, id_map); break; default: ret = -EINVAL; diff --git a/drivers/hwtracing/coresight/coresight-stm.c b/drivers/hwtracing/coresight/coresight-stm.c index 117dbb484543..cb3e04755c99 100644 --- a/drivers/hwtracing/coresight/coresight-stm.c +++ b/drivers/hwtracing/coresight/coresight-stm.c @@ -194,7 +194,8 @@ static void stm_enable_hw(struct stm_drvdata *drvdata) } static int stm_enable(struct coresight_device *csdev, struct perf_event *event, - enum cs_mode mode) + enum cs_mode mode, + __maybe_unused struct coresight_trace_id_map *trace_id) { struct stm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); diff --git a/drivers/hwtracing/coresight/coresight-sysfs.c b/drivers/hwtracing/coresight/coresight-sysfs.c index 1e67cc7758d7..a01c9e54e2ed 100644 --- a/drivers/hwtracing/coresight/coresight-sysfs.c +++ b/drivers/hwtracing/coresight/coresight-sysfs.c @@ -9,6 +9,7 @@ #include #include "coresight-priv.h" +#include "coresight-trace-id.h" /* * Use IDR to map the hash of the source's device name @@ -63,7 +64,7 @@ static int coresight_enable_source_sysfs(struct coresight_device *csdev, */ lockdep_assert_held(&coresight_mutex); if (coresight_get_mode(csdev) != CS_MODE_SYSFS) { - ret = source_ops(csdev)->enable(csdev, data, mode); + ret = source_ops(csdev)->enable(csdev, data, mode, NULL); if (ret) return ret; } diff --git a/drivers/hwtracing/coresight/coresight-tpdm.c b/drivers/hwtracing/coresight/coresight-tpdm.c index 5c5a4b3fe687..b7d99e91ab84 100644 --- a/drivers/hwtracing/coresight/coresight-tpdm.c +++ b/drivers/hwtracing/coresight/coresight-tpdm.c @@ -439,7 +439,8 @@ static void __tpdm_enable(struct tpdm_drvdata *drvdata) } static int tpdm_enable(struct coresight_device *csdev, struct perf_event *event, - enum cs_mode mode) + enum cs_mode mode, + __maybe_unused struct coresight_trace_id_map *id_map) { struct tpdm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 7d62b88bfb5c..9c3067e2e38b 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -290,6 +290,7 @@ struct coresight_device { bool sysfs_sink_activated; struct dev_ext_attribute *ea; struct coresight_device *def_sink; + struct coresight_trace_id_map perf_sink_id_map; /* sysfs links between components */ int nr_links; bool has_conns_grp; @@ -384,7 +385,7 @@ struct coresight_ops_link { struct coresight_ops_source { int (*cpu_id)(struct coresight_device *csdev); int (*enable)(struct coresight_device *csdev, struct perf_event *event, - enum cs_mode mode); + enum cs_mode mode, struct coresight_trace_id_map *id_map); void (*disable)(struct coresight_device *csdev, struct perf_event *event); }; -- cgit v1.2.3 From de0029fdde86092c75472c92e56a962f4edee0f6 Mon Sep 17 00:00:00 2001 From: James Clark Date: Mon, 22 Jul 2024 11:11:57 +0100 Subject: coresight: Remove pending trace ID release mechanism Pending the release of IDs was a way of managing concurrent sysfs and Perf sessions in a single global ID map. Perf may have finished while sysfs hadn't, and Perf shouldn't release the IDs in use by sysfs and vice versa. Now that Perf uses its own exclusive ID maps, pending release doesn't result in any different behavior than just releasing all IDs when the last Perf session finishes. As part of the per-sink trace ID change, we would have still had to make the pending mechanism work on a per-sink basis, due to the overlapping ID allocations, so instead of making that more complicated, just remove it. Signed-off-by: James Clark Reviewed-by: Mike Leach Signed-off-by: James Clark Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20240722101202.26915-16-james.clark@linaro.org --- drivers/hwtracing/coresight/coresight-etm-perf.c | 18 ++++--- drivers/hwtracing/coresight/coresight-trace-id.c | 67 ++++++------------------ drivers/hwtracing/coresight/coresight-trace-id.h | 31 +++++------ include/linux/coresight.h | 6 +-- 4 files changed, 43 insertions(+), 79 deletions(-) (limited to 'include/linux') diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index 7fb55dafb639..70c99f0409b2 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -232,15 +232,21 @@ static void free_event_data(struct work_struct *work) if (!(IS_ERR_OR_NULL(*ppath))) { struct coresight_device *sink = coresight_get_sink(*ppath); - coresight_trace_id_put_cpu_id_map(cpu, &sink->perf_sink_id_map); + /* + * Mark perf event as done for trace id allocator, but don't call + * coresight_trace_id_put_cpu_id_map() on individual IDs. Perf sessions + * never free trace IDs to ensure that the ID associated with a CPU + * cannot change during their and other's concurrent sessions. Instead, + * a refcount is used so that the last event to call + * coresight_trace_id_perf_stop() frees all IDs. + */ + coresight_trace_id_perf_stop(&sink->perf_sink_id_map); + coresight_release_path(*ppath); } *ppath = NULL; } - /* mark perf event as done for trace id allocator */ - coresight_trace_id_perf_stop(); - free_percpu(event_data->path); kfree(event_data); } @@ -328,9 +334,6 @@ static void *etm_setup_aux(struct perf_event *event, void **pages, sink = user_sink = coresight_get_sink_by_id(id); } - /* tell the trace ID allocator that a perf event is starting up */ - coresight_trace_id_perf_start(); - /* check if user wants a coresight configuration selected */ cfg_hash = (u32)((event->attr.config2 & GENMASK_ULL(63, 32)) >> 32); if (cfg_hash) { @@ -411,6 +414,7 @@ static void *etm_setup_aux(struct perf_event *event, void **pages, continue; } + coresight_trace_id_perf_start(&sink->perf_sink_id_map); *etm_event_cpu_path_ptr(event_data, cpu) = path; } diff --git a/drivers/hwtracing/coresight/coresight-trace-id.c b/drivers/hwtracing/coresight/coresight-trace-id.c index 8a777c0af6ea..bddaed3e5cf8 100644 --- a/drivers/hwtracing/coresight/coresight-trace-id.c +++ b/drivers/hwtracing/coresight/coresight-trace-id.c @@ -18,12 +18,6 @@ static struct coresight_trace_id_map id_map_default = { .cpu_map = &id_map_default_cpu_ids }; -/* maintain a record of the pending releases per cpu */ -static cpumask_t cpu_id_release_pending; - -/* perf session active counter */ -static atomic_t perf_cs_etm_session_active = ATOMIC_INIT(0); - /* lock to protect id_map and cpu data */ static DEFINE_SPINLOCK(id_map_lock); @@ -35,7 +29,6 @@ static void coresight_trace_id_dump_table(struct coresight_trace_id_map *id_map, { pr_debug("%s id_map::\n", func_name); pr_debug("Used = %*pb\n", CORESIGHT_TRACE_IDS_MAX, id_map->used_ids); - pr_debug("Pend = %*pb\n", CORESIGHT_TRACE_IDS_MAX, id_map->pend_rel_ids); } #define DUMP_ID_MAP(map) coresight_trace_id_dump_table(map, __func__) #define DUMP_ID_CPU(cpu, id) pr_debug("%s called; cpu=%d, id=%d\n", __func__, cpu, id) @@ -122,34 +115,18 @@ static void coresight_trace_id_free(int id, struct coresight_trace_id_map *id_ma clear_bit(id, id_map->used_ids); } -static void coresight_trace_id_set_pend_rel(int id, struct coresight_trace_id_map *id_map) -{ - if (WARN(!IS_VALID_CS_TRACE_ID(id), "Invalid Trace ID %d\n", id)) - return; - set_bit(id, id_map->pend_rel_ids); -} - /* - * release all pending IDs for all current maps & clear CPU associations - * - * This currently operates on the default id map, but may be extended to - * operate on all registered id maps if per sink id maps are used. + * Release all IDs and clear CPU associations. */ -static void coresight_trace_id_release_all_pending(void) +static void coresight_trace_id_release_all(struct coresight_trace_id_map *id_map) { - struct coresight_trace_id_map *id_map = &id_map_default; unsigned long flags; - int cpu, bit; + int cpu; spin_lock_irqsave(&id_map_lock, flags); - for_each_set_bit(bit, id_map->pend_rel_ids, CORESIGHT_TRACE_ID_RES_TOP) { - clear_bit(bit, id_map->used_ids); - clear_bit(bit, id_map->pend_rel_ids); - } - for_each_cpu(cpu, &cpu_id_release_pending) { - atomic_set(per_cpu_ptr(id_map_default.cpu_map, cpu), 0); - cpumask_clear_cpu(cpu, &cpu_id_release_pending); - } + bitmap_zero(id_map->used_ids, CORESIGHT_TRACE_IDS_MAX); + for_each_possible_cpu(cpu) + atomic_set(per_cpu_ptr(id_map->cpu_map, cpu), 0); spin_unlock_irqrestore(&id_map_lock, flags); DUMP_ID_MAP(id_map); } @@ -164,7 +141,7 @@ static int _coresight_trace_id_get_cpu_id(int cpu, struct coresight_trace_id_map /* check for existing allocation for this CPU */ id = _coresight_trace_id_read_cpu_id(cpu, id_map); if (id) - goto get_cpu_id_clr_pend; + goto get_cpu_id_out_unlock; /* * Find a new ID. @@ -185,11 +162,6 @@ static int _coresight_trace_id_get_cpu_id(int cpu, struct coresight_trace_id_map /* allocate the new id to the cpu */ atomic_set(per_cpu_ptr(id_map->cpu_map, cpu), id); -get_cpu_id_clr_pend: - /* we are (re)using this ID - so ensure it is not marked for release */ - cpumask_clear_cpu(cpu, &cpu_id_release_pending); - clear_bit(id, id_map->pend_rel_ids); - get_cpu_id_out_unlock: spin_unlock_irqrestore(&id_map_lock, flags); @@ -210,15 +182,8 @@ static void _coresight_trace_id_put_cpu_id(int cpu, struct coresight_trace_id_ma spin_lock_irqsave(&id_map_lock, flags); - if (atomic_read(&perf_cs_etm_session_active)) { - /* set release at pending if perf still active */ - coresight_trace_id_set_pend_rel(id, id_map); - cpumask_set_cpu(cpu, &cpu_id_release_pending); - } else { - /* otherwise clear id */ - coresight_trace_id_free(id, id_map); - atomic_set(per_cpu_ptr(id_map->cpu_map, cpu), 0); - } + coresight_trace_id_free(id, id_map); + atomic_set(per_cpu_ptr(id_map->cpu_map, cpu), 0); spin_unlock_irqrestore(&id_map_lock, flags); DUMP_ID_CPU(cpu, id); @@ -302,17 +267,17 @@ void coresight_trace_id_put_system_id(int id) } EXPORT_SYMBOL_GPL(coresight_trace_id_put_system_id); -void coresight_trace_id_perf_start(void) +void coresight_trace_id_perf_start(struct coresight_trace_id_map *id_map) { - atomic_inc(&perf_cs_etm_session_active); - PERF_SESSION(atomic_read(&perf_cs_etm_session_active)); + atomic_inc(&id_map->perf_cs_etm_session_active); + PERF_SESSION(atomic_read(&id_map->perf_cs_etm_session_active)); } EXPORT_SYMBOL_GPL(coresight_trace_id_perf_start); -void coresight_trace_id_perf_stop(void) +void coresight_trace_id_perf_stop(struct coresight_trace_id_map *id_map) { - if (!atomic_dec_return(&perf_cs_etm_session_active)) - coresight_trace_id_release_all_pending(); - PERF_SESSION(atomic_read(&perf_cs_etm_session_active)); + if (!atomic_dec_return(&id_map->perf_cs_etm_session_active)) + coresight_trace_id_release_all(id_map); + PERF_SESSION(atomic_read(&id_map->perf_cs_etm_session_active)); } EXPORT_SYMBOL_GPL(coresight_trace_id_perf_stop); diff --git a/drivers/hwtracing/coresight/coresight-trace-id.h b/drivers/hwtracing/coresight/coresight-trace-id.h index 840babdd0794..9aae50a553ca 100644 --- a/drivers/hwtracing/coresight/coresight-trace-id.h +++ b/drivers/hwtracing/coresight/coresight-trace-id.h @@ -17,9 +17,10 @@ * released when done. * * In order to ensure that a consistent cpu / ID matching is maintained - * throughout a perf cs_etm event session - a session in progress flag will - * be maintained, and released IDs not cleared until the perf session is - * complete. This allows the same CPU to be re-allocated its prior ID. + * throughout a perf cs_etm event session - a session in progress flag will be + * maintained for each sink, and IDs are cleared when all the perf sessions + * complete. This allows the same CPU to be re-allocated its prior ID when + * events are scheduled in and out. * * * Trace ID maps will be created and initialised to prevent architecturally @@ -66,11 +67,7 @@ int coresight_trace_id_get_cpu_id_map(int cpu, struct coresight_trace_id_map *id /** * Release an allocated trace ID associated with the CPU. * - * This will release the CoreSight trace ID associated with the CPU, - * unless a perf session is in operation. - * - * If a perf session is in operation then the ID will be marked as pending - * release. + * This will release the CoreSight trace ID associated with the CPU. * * @cpu: The CPU index to release the associated trace ID. */ @@ -133,21 +130,21 @@ void coresight_trace_id_put_system_id(int id); /** * Notify the Trace ID allocator that a perf session is starting. * - * Increase the perf session reference count - called by perf when setting up - * a trace event. + * Increase the perf session reference count - called by perf when setting up a + * trace event. * - * This reference count is used by the ID allocator to ensure that trace IDs - * associated with a CPU cannot change or be released during a perf session. + * Perf sessions never free trace IDs to ensure that the ID associated with a + * CPU cannot change during their and other's concurrent sessions. Instead, + * this refcount is used so that the last event to finish always frees all IDs. */ -void coresight_trace_id_perf_start(void); +void coresight_trace_id_perf_start(struct coresight_trace_id_map *id_map); /** * Notify the ID allocator that a perf session is stopping. * - * Decrease the perf session reference count. - * if this causes the count to go to zero, then all Trace IDs marked as pending - * release, will be released. + * Decrease the perf session reference count. If this causes the count to go to + * zero, then all Trace IDs will be released. */ -void coresight_trace_id_perf_stop(void); +void coresight_trace_id_perf_stop(struct coresight_trace_id_map *id_map); #endif /* _CORESIGHT_TRACE_ID_H */ diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 9c3067e2e38b..197949fd2c35 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -227,14 +227,12 @@ struct coresight_sysfs_link { * @used_ids: Bitmap to register available (bit = 0) and in use (bit = 1) IDs. * Initialised so that the reserved IDs are permanently marked as * in use. - * @pend_rel_ids: CPU IDs that have been released by the trace source but not - * yet marked as available, to allow re-allocation to the same - * CPU during a perf session. + * @perf_cs_etm_session_active: Number of Perf sessions using this ID map. */ struct coresight_trace_id_map { DECLARE_BITMAP(used_ids, CORESIGHT_TRACE_IDS_MAX); - DECLARE_BITMAP(pend_rel_ids, CORESIGHT_TRACE_IDS_MAX); atomic_t __percpu *cpu_map; + atomic_t perf_cs_etm_session_active; }; /** -- cgit v1.2.3 From 487eec8da80aef16229d30429f1b26090b1bf0eb Mon Sep 17 00:00:00 2001 From: James Clark Date: Mon, 22 Jul 2024 11:11:58 +0100 Subject: coresight: Emit sink ID in the HW_ID packets For Perf to be able to decode when per-sink trace IDs are used, emit the sink that's being written to for each ETM. Perf currently errors out if it sees a newer packet version so instead of bumping it, add a new minor version field. This can be used to signify new versions that have backwards compatible fields. Considering this change is only for high core count machines, it doesn't make sense to make a breaking change for everyone. Signed-off-by: James Clark Tested-by: Leo Yan Reviewed-by: Mike Leach Signed-off-by: James Clark Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20240722101202.26915-17-james.clark@linaro.org --- drivers/hwtracing/coresight/coresight-core.c | 26 +++++++++++++----------- drivers/hwtracing/coresight/coresight-etm-perf.c | 16 ++++++++++----- drivers/hwtracing/coresight/coresight-priv.h | 1 + include/linux/coresight-pmu.h | 17 ++++++++++++---- 4 files changed, 39 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/drivers/hwtracing/coresight/coresight-core.c b/drivers/hwtracing/coresight/coresight-core.c index faf560ba8d64..c427e9344a84 100644 --- a/drivers/hwtracing/coresight/coresight-core.c +++ b/drivers/hwtracing/coresight/coresight-core.c @@ -487,23 +487,25 @@ struct coresight_device *coresight_get_sink(struct list_head *path) return csdev; } +u32 coresight_get_sink_id(struct coresight_device *csdev) +{ + if (!csdev->ea) + return 0; + + /* + * See function etm_perf_add_symlink_sink() to know where + * this comes from. + */ + return (u32) (unsigned long) csdev->ea->var; +} + static int coresight_sink_by_id(struct device *dev, const void *data) { struct coresight_device *csdev = to_coresight_device(dev); - unsigned long hash; if (csdev->type == CORESIGHT_DEV_TYPE_SINK || - csdev->type == CORESIGHT_DEV_TYPE_LINKSINK) { - - if (!csdev->ea) - return 0; - /* - * See function etm_perf_add_symlink_sink() to know where - * this comes from. - */ - hash = (unsigned long)csdev->ea->var; - - if ((u32)hash == *(u32 *)data) + csdev->type == CORESIGHT_DEV_TYPE_LINKSINK) { + if (coresight_get_sink_id(csdev) == *(u32 *)data) return 1; } diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index 70c99f0409b2..ad6a8f4b70b6 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -460,6 +460,7 @@ static void etm_event_start(struct perf_event *event, int flags) struct coresight_device *sink, *csdev = per_cpu(csdev_src, cpu); struct list_head *path; u64 hw_id; + u8 trace_id; if (!csdev) goto fail; @@ -512,11 +513,16 @@ static void etm_event_start(struct perf_event *event, int flags) */ if (!cpumask_test_cpu(cpu, &event_data->aux_hwid_done)) { cpumask_set_cpu(cpu, &event_data->aux_hwid_done); - hw_id = FIELD_PREP(CS_AUX_HW_ID_VERSION_MASK, - CS_AUX_HW_ID_CURR_VERSION); - hw_id |= FIELD_PREP(CS_AUX_HW_ID_TRACE_ID_MASK, - coresight_trace_id_read_cpu_id_map(cpu, - &sink->perf_sink_id_map)); + + trace_id = coresight_trace_id_read_cpu_id_map(cpu, &sink->perf_sink_id_map); + + hw_id = FIELD_PREP(CS_AUX_HW_ID_MAJOR_VERSION_MASK, + CS_AUX_HW_ID_MAJOR_VERSION); + hw_id |= FIELD_PREP(CS_AUX_HW_ID_MINOR_VERSION_MASK, + CS_AUX_HW_ID_MINOR_VERSION); + hw_id |= FIELD_PREP(CS_AUX_HW_ID_TRACE_ID_MASK, trace_id); + hw_id |= FIELD_PREP(CS_AUX_HW_ID_SINK_ID_MASK, coresight_get_sink_id(sink)); + perf_report_aux_output_id(event, hw_id); } diff --git a/drivers/hwtracing/coresight/coresight-priv.h b/drivers/hwtracing/coresight/coresight-priv.h index 61a46d3bdcc8..05f891ca6b5c 100644 --- a/drivers/hwtracing/coresight/coresight-priv.h +++ b/drivers/hwtracing/coresight/coresight-priv.h @@ -148,6 +148,7 @@ int coresight_make_links(struct coresight_device *orig, struct coresight_device *target); void coresight_remove_links(struct coresight_device *orig, struct coresight_connection *conn); +u32 coresight_get_sink_id(struct coresight_device *csdev); #if IS_ENABLED(CONFIG_CORESIGHT_SOURCE_ETM3X) extern int etm_readl_cp14(u32 off, unsigned int *val); diff --git a/include/linux/coresight-pmu.h b/include/linux/coresight-pmu.h index 51ac441a37c3..89b0ac0014b0 100644 --- a/include/linux/coresight-pmu.h +++ b/include/linux/coresight-pmu.h @@ -49,12 +49,21 @@ * Interpretation of the PERF_RECORD_AUX_OUTPUT_HW_ID payload. * Used to associate a CPU with the CoreSight Trace ID. * [07:00] - Trace ID - uses 8 bits to make value easy to read in file. - * [59:08] - Unused (SBZ) - * [63:60] - Version + * [39:08] - Sink ID - as reported in /sys/bus/event_source/devices/cs_etm/sinks/ + * Added in minor version 1. + * [55:40] - Unused (SBZ) + * [59:56] - Minor Version - previously existing fields are compatible with + * all minor versions. + * [63:60] - Major Version - previously existing fields mean different things + * in new major versions. */ #define CS_AUX_HW_ID_TRACE_ID_MASK GENMASK_ULL(7, 0) -#define CS_AUX_HW_ID_VERSION_MASK GENMASK_ULL(63, 60) +#define CS_AUX_HW_ID_SINK_ID_MASK GENMASK_ULL(39, 8) -#define CS_AUX_HW_ID_CURR_VERSION 0 +#define CS_AUX_HW_ID_MINOR_VERSION_MASK GENMASK_ULL(59, 56) +#define CS_AUX_HW_ID_MAJOR_VERSION_MASK GENMASK_ULL(63, 60) + +#define CS_AUX_HW_ID_MAJOR_VERSION 0 +#define CS_AUX_HW_ID_MINOR_VERSION 1 #endif -- cgit v1.2.3 From 988d40a4d4e7d671305bea501562a5d1a1d479fa Mon Sep 17 00:00:00 2001 From: James Clark Date: Mon, 22 Jul 2024 11:11:59 +0100 Subject: coresight: Make trace ID map spinlock local to the map Reduce contention on the lock by replacing the global lock with one for each map. Signed-off-by: James Clark Reviewed-by: Mike Leach Signed-off-by: James Clark Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20240722101202.26915-18-james.clark@linaro.org --- drivers/hwtracing/coresight/coresight-core.c | 1 + drivers/hwtracing/coresight/coresight-trace-id.c | 26 +++++++++++------------- include/linux/coresight.h | 1 + 3 files changed, 14 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/hwtracing/coresight/coresight-core.c b/drivers/hwtracing/coresight/coresight-core.c index c427e9344a84..ea38ecf26fcb 100644 --- a/drivers/hwtracing/coresight/coresight-core.c +++ b/drivers/hwtracing/coresight/coresight-core.c @@ -1164,6 +1164,7 @@ struct coresight_device *coresight_register(struct coresight_desc *desc) if (csdev->type == CORESIGHT_DEV_TYPE_SINK || csdev->type == CORESIGHT_DEV_TYPE_LINKSINK) { + spin_lock_init(&csdev->perf_sink_id_map.lock); csdev->perf_sink_id_map.cpu_map = alloc_percpu(atomic_t); if (!csdev->perf_sink_id_map.cpu_map) { kfree(csdev); diff --git a/drivers/hwtracing/coresight/coresight-trace-id.c b/drivers/hwtracing/coresight/coresight-trace-id.c index bddaed3e5cf8..d98e12cb30ec 100644 --- a/drivers/hwtracing/coresight/coresight-trace-id.c +++ b/drivers/hwtracing/coresight/coresight-trace-id.c @@ -15,12 +15,10 @@ /* Default trace ID map. Used in sysfs mode and for system sources */ static DEFINE_PER_CPU(atomic_t, id_map_default_cpu_ids) = ATOMIC_INIT(0); static struct coresight_trace_id_map id_map_default = { - .cpu_map = &id_map_default_cpu_ids + .cpu_map = &id_map_default_cpu_ids, + .lock = __SPIN_LOCK_UNLOCKED(id_map_default.lock) }; -/* lock to protect id_map and cpu data */ -static DEFINE_SPINLOCK(id_map_lock); - /* #define TRACE_ID_DEBUG 1 */ #if defined(TRACE_ID_DEBUG) || defined(CONFIG_COMPILE_TEST) @@ -123,11 +121,11 @@ static void coresight_trace_id_release_all(struct coresight_trace_id_map *id_map unsigned long flags; int cpu; - spin_lock_irqsave(&id_map_lock, flags); + spin_lock_irqsave(&id_map->lock, flags); bitmap_zero(id_map->used_ids, CORESIGHT_TRACE_IDS_MAX); for_each_possible_cpu(cpu) atomic_set(per_cpu_ptr(id_map->cpu_map, cpu), 0); - spin_unlock_irqrestore(&id_map_lock, flags); + spin_unlock_irqrestore(&id_map->lock, flags); DUMP_ID_MAP(id_map); } @@ -136,7 +134,7 @@ static int _coresight_trace_id_get_cpu_id(int cpu, struct coresight_trace_id_map unsigned long flags; int id; - spin_lock_irqsave(&id_map_lock, flags); + spin_lock_irqsave(&id_map->lock, flags); /* check for existing allocation for this CPU */ id = _coresight_trace_id_read_cpu_id(cpu, id_map); @@ -163,7 +161,7 @@ static int _coresight_trace_id_get_cpu_id(int cpu, struct coresight_trace_id_map atomic_set(per_cpu_ptr(id_map->cpu_map, cpu), id); get_cpu_id_out_unlock: - spin_unlock_irqrestore(&id_map_lock, flags); + spin_unlock_irqrestore(&id_map->lock, flags); DUMP_ID_CPU(cpu, id); DUMP_ID_MAP(id_map); @@ -180,12 +178,12 @@ static void _coresight_trace_id_put_cpu_id(int cpu, struct coresight_trace_id_ma if (!id) return; - spin_lock_irqsave(&id_map_lock, flags); + spin_lock_irqsave(&id_map->lock, flags); coresight_trace_id_free(id, id_map); atomic_set(per_cpu_ptr(id_map->cpu_map, cpu), 0); - spin_unlock_irqrestore(&id_map_lock, flags); + spin_unlock_irqrestore(&id_map->lock, flags); DUMP_ID_CPU(cpu, id); DUMP_ID_MAP(id_map); } @@ -195,10 +193,10 @@ static int coresight_trace_id_map_get_system_id(struct coresight_trace_id_map *i unsigned long flags; int id; - spin_lock_irqsave(&id_map_lock, flags); + spin_lock_irqsave(&id_map->lock, flags); /* prefer odd IDs for system components to avoid legacy CPU IDS */ id = coresight_trace_id_alloc_new_id(id_map, 0, true); - spin_unlock_irqrestore(&id_map_lock, flags); + spin_unlock_irqrestore(&id_map->lock, flags); DUMP_ID(id); DUMP_ID_MAP(id_map); @@ -209,9 +207,9 @@ static void coresight_trace_id_map_put_system_id(struct coresight_trace_id_map * { unsigned long flags; - spin_lock_irqsave(&id_map_lock, flags); + spin_lock_irqsave(&id_map->lock, flags); coresight_trace_id_free(id, id_map); - spin_unlock_irqrestore(&id_map_lock, flags); + spin_unlock_irqrestore(&id_map->lock, flags); DUMP_ID(id); DUMP_ID_MAP(id_map); diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 197949fd2c35..c13342594278 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -233,6 +233,7 @@ struct coresight_trace_id_map { DECLARE_BITMAP(used_ids, CORESIGHT_TRACE_IDS_MAX); atomic_t __percpu *cpu_map; atomic_t perf_cs_etm_session_active; + spinlock_t lock; }; /** -- cgit v1.2.3 From 7c432a18ad216b4f7b08e93287586d60e12a3b7b Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 20 Aug 2024 15:27:55 +0100 Subject: firmware: arm_ffa: Update the FF-A command list with v1.2 additions Arm Firmware Framework for A-profile(FFA) v1.2 introduces register based discovery mechanism and direct messaging extensions that enables to target specific UUID within a partition. Let us add all the newly supported FF-A function IDs in the spec. Also update to the error values and associated handling. Message-Id: <20240820-ffa_v1-2-v2-2-18c0c5f3c65e@arm.com> Signed-off-by: Sudeep Holla --- drivers/firmware/arm_ffa/driver.c | 1 + include/linux/arm_ffa.h | 5 +++++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index b4b3ecc9824e..be77e03578cc 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -75,6 +75,7 @@ static const int ffa_linux_errmap[] = { -EAGAIN, /* FFA_RET_RETRY */ -ECANCELED, /* FFA_RET_ABORTED */ -ENODATA, /* FFA_RET_NO_DATA */ + -EAGAIN, /* FFA_RET_NOT_READY */ }; static inline int ffa_to_linux_errno(int errno) diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index 89683f31ae12..b34f0c0dc2c5 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -73,6 +73,11 @@ #define FFA_FN64_MEM_PERM_GET FFA_SMC_64(0x88) #define FFA_MEM_PERM_SET FFA_SMC_32(0x89) #define FFA_FN64_MEM_PERM_SET FFA_SMC_64(0x89) +#define FFA_CONSOLE_LOG FFA_SMC_32(0x8A) +#define FFA_PARTITION_INFO_GET_REGS FFA_SMC_64(0x8B) +#define FFA_EL3_INTR_HANDLE FFA_SMC_32(0x8C) +#define FFA_MSG_SEND_DIRECT_REQ2 FFA_SMC_64(0x8D) +#define FFA_MSG_SEND_DIRECT_RESP2 FFA_SMC_64(0x8E) /* * For some calls it is necessary to use SMC64 to pass or return 64-bit values. -- cgit v1.2.3 From aaef3bc98129c86078b336f16788dd733b0728a4 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 20 Aug 2024 15:27:58 +0100 Subject: firmware: arm_ffa: Add support for FFA_MSG_SEND_DIRECT_{REQ,RESP}2 FFA_MSG_SEND_DIRECT_{REQ,RESP} supported only x3-x7 to pass implementation defined values as part of the message. This may not be sufficient sometimes and also it would be good to use all the registers supported by SMCCC v1.2 (x0-x17) for such register based communication. Also another limitation with the FFA_MSG_SEND_DIRECT_{REQ,RESP} is the ability to target a specific service within the partition based on it's UUID. In order to address both of the above limitation, FF-A v1.2 introduced FFA_MSG_SEND_DIRECT_{REQ,RESP}2 which has the ability to target the message to a specific service based on its UUID within a partition as well as utilise all the available registers(x4-x17 specifically) for the communication. This change adds support for FFA_MSG_SEND_DIRECT_REQ2 and FFA_MSG_SEND_DIRECT_RESP2. Message-Id: <20240820-ffa_v1-2-v2-5-18c0c5f3c65e@arm.com> Signed-off-by: Sudeep Holla --- drivers/firmware/arm_ffa/driver.c | 49 +++++++++++++++++++++++++++++++++++++-- include/linux/arm_ffa.h | 7 ++++++ 2 files changed, 54 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index e28cbfe9a801..ec99fed5715d 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -99,6 +99,7 @@ struct ffa_drv_info { void *rx_buffer; void *tx_buffer; bool mem_ops_native; + bool msg_direct_req2_supp; bool bitmap_created; bool notif_enabled; unsigned int sched_recv_irq; @@ -468,6 +469,35 @@ static int ffa_msg_send2(u16 src_id, u16 dst_id, void *buf, size_t sz) return retval; } +static int ffa_msg_send_direct_req2(u16 src_id, u16 dst_id, const uuid_t *uuid, + struct ffa_send_direct_data2 *data) +{ + u32 src_dst_ids = PACK_TARGET_INFO(src_id, dst_id); + ffa_value_t ret, args = { + .a0 = FFA_MSG_SEND_DIRECT_REQ2, .a1 = src_dst_ids, + }; + + export_uuid((u8 *)&args.a2, uuid); + memcpy((void *)&args + offsetof(ffa_value_t, a4), data, sizeof(*data)); + + invoke_ffa_fn(args, &ret); + + while (ret.a0 == FFA_INTERRUPT) + invoke_ffa_fn((ffa_value_t){ + .a0 = FFA_RUN, .a1 = ret.a1, + }, &ret); + + if (ret.a0 == FFA_ERROR) + return ffa_to_linux_errno((int)ret.a2); + + if (ret.a0 == FFA_MSG_SEND_DIRECT_RESP2) { + memcpy(data, &ret.a4, sizeof(*data)); + return 0; + } + + return -EINVAL; +} + static int ffa_mem_first_frag(u32 func_id, phys_addr_t buf, u32 buf_sz, u32 frag_len, u32 len, u64 *handle) { @@ -923,11 +953,15 @@ static int ffa_run(struct ffa_device *dev, u16 vcpu) return 0; } -static void ffa_set_up_mem_ops_native_flag(void) +static void ffa_drvinfo_flags_init(void) { if (!ffa_features(FFA_FN_NATIVE(MEM_LEND), 0, NULL, NULL) || !ffa_features(FFA_FN_NATIVE(MEM_SHARE), 0, NULL, NULL)) drv_info->mem_ops_native = true; + + if (!ffa_features(FFA_MSG_SEND_DIRECT_REQ2, 0, NULL, NULL) || + !ffa_features(FFA_MSG_SEND_DIRECT_RESP2, 0, NULL, NULL)) + drv_info->msg_direct_req2_supp = true; } static u32 ffa_api_version_get(void) @@ -973,6 +1007,16 @@ static int ffa_indirect_msg_send(struct ffa_device *dev, void *buf, size_t sz) return ffa_msg_send2(drv_info->vm_id, dev->vm_id, buf, sz); } +static int ffa_sync_send_receive2(struct ffa_device *dev, const uuid_t *uuid, + struct ffa_send_direct_data2 *data) +{ + if (!drv_info->msg_direct_req2_supp) + return -EOPNOTSUPP; + + return ffa_msg_send_direct_req2(drv_info->vm_id, dev->vm_id, + uuid, data); +} + static int ffa_memory_share(struct ffa_mem_ops_args *args) { if (drv_info->mem_ops_native) @@ -1256,6 +1300,7 @@ static const struct ffa_msg_ops ffa_drv_msg_ops = { .mode_32bit_set = ffa_mode_32bit_set, .sync_send_receive = ffa_sync_send_receive, .indirect_send = ffa_indirect_msg_send, + .sync_send_receive2 = ffa_sync_send_receive2, }; static const struct ffa_mem_ops ffa_drv_mem_ops = { @@ -1708,7 +1753,7 @@ static int __init ffa_init(void) mutex_init(&drv_info->rx_lock); mutex_init(&drv_info->tx_lock); - ffa_set_up_mem_ops_native_flag(); + ffa_drvinfo_flags_init(); ffa_notifications_setup(); diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index b34f0c0dc2c5..a28e2a6a13d0 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -270,6 +270,11 @@ struct ffa_indirect_msg_hdr { u32 size; }; +/* For use with FFA_MSG_SEND_DIRECT_{REQ,RESP}2 which pass data via registers */ +struct ffa_send_direct_data2 { + unsigned long data[14]; /* x4-x17 */ +}; + struct ffa_mem_region_addr_range { /* The base IPA of the constituent memory region, aligned to 4 kiB */ u64 address; @@ -431,6 +436,8 @@ struct ffa_msg_ops { int (*sync_send_receive)(struct ffa_device *dev, struct ffa_send_direct_data *data); int (*indirect_send)(struct ffa_device *dev, void *buf, size_t sz); + int (*sync_send_receive2)(struct ffa_device *dev, const uuid_t *uuid, + struct ffa_send_direct_data2 *data); }; struct ffa_mem_ops { -- cgit v1.2.3 From e68ac2b488495fa4d127d6105ce633849859957a Mon Sep 17 00:00:00 2001 From: Caleb Sander Mateos Date: Thu, 15 Aug 2024 11:15:40 -0600 Subject: softirq: Remove unused 'action' parameter from action callback When soft interrupt actions are called, they are passed a pointer to the struct softirq action which contains the action's function pointer. This pointer isn't useful, as the action callback already knows what function it is. And since each callback handles a specific soft interrupt, the callback also knows which soft interrupt number is running. No soft interrupt action callback actually uses this parameter, so remove it from the function pointer signature. This clarifies that soft interrupt actions are global routines and makes it slightly cheaper to call them. Signed-off-by: Caleb Sander Mateos Signed-off-by: Thomas Gleixner Reviewed-by: Jens Axboe Link: https://lore.kernel.org/all/20240815171549.3260003-1-csander@purestorage.com --- block/blk-mq.c | 2 +- include/linux/interrupt.h | 4 ++-- kernel/rcu/tiny.c | 2 +- kernel/rcu/tree.c | 2 +- kernel/sched/fair.c | 2 +- kernel/softirq.c | 15 +++++++-------- kernel/time/hrtimer.c | 2 +- kernel/time/timer.c | 2 +- lib/irq_poll.c | 2 +- net/core/dev.c | 4 ++-- 10 files changed, 18 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index e3c3c0c21b55..aa28157b1aaf 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1128,7 +1128,7 @@ static void blk_complete_reqs(struct llist_head *list) rq->q->mq_ops->complete(rq); } -static __latent_entropy void blk_done_softirq(struct softirq_action *h) +static __latent_entropy void blk_done_softirq(void) { blk_complete_reqs(this_cpu_ptr(&blk_cpu_done)); } diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 3f30c88e0b4c..694de61e0b38 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -594,7 +594,7 @@ extern const char * const softirq_to_name[NR_SOFTIRQS]; struct softirq_action { - void (*action)(struct softirq_action *); + void (*action)(void); }; asmlinkage void do_softirq(void); @@ -609,7 +609,7 @@ static inline void do_softirq_post_smp_call_flush(unsigned int unused) } #endif -extern void open_softirq(int nr, void (*action)(struct softirq_action *)); +extern void open_softirq(int nr, void (*action)(void)); extern void softirq_init(void); extern void __raise_softirq_irqoff(unsigned int nr); diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index 4402d6f5f857..b3b3ce34df63 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -105,7 +105,7 @@ static inline bool rcu_reclaim_tiny(struct rcu_head *head) } /* Invoke the RCU callbacks whose grace period has elapsed. */ -static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused) +static __latent_entropy void rcu_process_callbacks(void) { struct rcu_head *next, *list; unsigned long flags; diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index e641cc681901..93bd665637c0 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -2855,7 +2855,7 @@ static __latent_entropy void rcu_core(void) queue_work_on(rdp->cpu, rcu_gp_wq, &rdp->strict_work); } -static void rcu_core_si(struct softirq_action *h) +static void rcu_core_si(void) { rcu_core(); } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 9057584ec06d..8dc9385f6da4 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -12483,7 +12483,7 @@ out: * - indirectly from a remote scheduler_tick() for NOHZ idle balancing * through the SMP cross-call nohz_csd_func() */ -static __latent_entropy void sched_balance_softirq(struct softirq_action *h) +static __latent_entropy void sched_balance_softirq(void) { struct rq *this_rq = this_rq(); enum cpu_idle_type idle = this_rq->idle_balance; diff --git a/kernel/softirq.c b/kernel/softirq.c index 02582017759a..d082e7840f88 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -551,7 +551,7 @@ restart: kstat_incr_softirqs_this_cpu(vec_nr); trace_softirq_entry(vec_nr); - h->action(h); + h->action(); trace_softirq_exit(vec_nr); if (unlikely(prev_count != preempt_count())) { pr_err("huh, entered softirq %u %s %p with preempt_count %08x, exited with %08x?\n", @@ -700,7 +700,7 @@ void __raise_softirq_irqoff(unsigned int nr) or_softirq_pending(1UL << nr); } -void open_softirq(int nr, void (*action)(struct softirq_action *)) +void open_softirq(int nr, void (*action)(void)) { softirq_vec[nr].action = action; } @@ -760,8 +760,7 @@ static bool tasklet_clear_sched(struct tasklet_struct *t) return false; } -static void tasklet_action_common(struct softirq_action *a, - struct tasklet_head *tl_head, +static void tasklet_action_common(struct tasklet_head *tl_head, unsigned int softirq_nr) { struct tasklet_struct *list; @@ -805,16 +804,16 @@ static void tasklet_action_common(struct softirq_action *a, } } -static __latent_entropy void tasklet_action(struct softirq_action *a) +static __latent_entropy void tasklet_action(void) { workqueue_softirq_action(false); - tasklet_action_common(a, this_cpu_ptr(&tasklet_vec), TASKLET_SOFTIRQ); + tasklet_action_common(this_cpu_ptr(&tasklet_vec), TASKLET_SOFTIRQ); } -static __latent_entropy void tasklet_hi_action(struct softirq_action *a) +static __latent_entropy void tasklet_hi_action(void) { workqueue_softirq_action(true); - tasklet_action_common(a, this_cpu_ptr(&tasklet_hi_vec), HI_SOFTIRQ); + tasklet_action_common(this_cpu_ptr(&tasklet_hi_vec), HI_SOFTIRQ); } void tasklet_setup(struct tasklet_struct *t, diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index b8ee320208d4..836157e09e25 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1757,7 +1757,7 @@ static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now, } } -static __latent_entropy void hrtimer_run_softirq(struct softirq_action *h) +static __latent_entropy void hrtimer_run_softirq(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); unsigned long flags; diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 64b0d8a0aa0f..760bbeb1f331 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -2440,7 +2440,7 @@ static void run_timer_base(int index) /* * This function runs timers and the timer-tq in bottom half context. */ -static __latent_entropy void run_timer_softirq(struct softirq_action *h) +static __latent_entropy void run_timer_softirq(void) { run_timer_base(BASE_LOCAL); if (IS_ENABLED(CONFIG_NO_HZ_COMMON)) { diff --git a/lib/irq_poll.c b/lib/irq_poll.c index 2d5329a42105..08b242bbdbdf 100644 --- a/lib/irq_poll.c +++ b/lib/irq_poll.c @@ -75,7 +75,7 @@ void irq_poll_complete(struct irq_poll *iop) } EXPORT_SYMBOL(irq_poll_complete); -static void __latent_entropy irq_poll_softirq(struct softirq_action *h) +static void __latent_entropy irq_poll_softirq(void) { struct list_head *list = this_cpu_ptr(&blk_cpu_iopoll); int rearm = 0, budget = irq_poll_budget; diff --git a/net/core/dev.c b/net/core/dev.c index 6ea1d20676fb..e24a3bcb496d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5247,7 +5247,7 @@ int netif_rx(struct sk_buff *skb) } EXPORT_SYMBOL(netif_rx); -static __latent_entropy void net_tx_action(struct softirq_action *h) +static __latent_entropy void net_tx_action(void) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); @@ -6920,7 +6920,7 @@ static int napi_threaded_poll(void *data) return 0; } -static __latent_entropy void net_rx_action(struct softirq_action *h) +static __latent_entropy void net_rx_action(void) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); unsigned long time_limit = jiffies + -- cgit v1.2.3 From 2fea0c26b82f304f43b3905e56d954cf98a6d0e9 Mon Sep 17 00:00:00 2001 From: Fan Wu Date: Fri, 2 Aug 2024 23:08:19 -0700 Subject: initramfs,lsm: add a security hook to do_populate_rootfs() This patch introduces a new hook to notify security system that the content of initramfs has been unpacked into the rootfs. Upon receiving this notification, the security system can activate a policy to allow only files that originated from the initramfs to execute or load into kernel during the early stages of booting. This approach is crucial for minimizing the attack surface by ensuring that only trusted files from the initramfs are operational in the critical boot phase. Signed-off-by: Fan Wu [PM: subject line tweak] Signed-off-by: Paul Moore --- include/linux/lsm_hook_defs.h | 2 ++ include/linux/security.h | 8 ++++++++ init/initramfs.c | 3 +++ security/security.c | 10 ++++++++++ 4 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 520730fe2d94..22a14fc794fe 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -449,3 +449,5 @@ LSM_HOOK(int, 0, uring_override_creds, const struct cred *new) LSM_HOOK(int, 0, uring_sqpoll, void) LSM_HOOK(int, 0, uring_cmd, struct io_uring_cmd *ioucmd) #endif /* CONFIG_IO_URING */ + +LSM_HOOK(void, LSM_RET_VOID, initramfs_populated, void) diff --git a/include/linux/security.h b/include/linux/security.h index 62233fec8ead..3298855abdbc 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -2256,4 +2256,12 @@ static inline int security_uring_cmd(struct io_uring_cmd *ioucmd) #endif /* CONFIG_SECURITY */ #endif /* CONFIG_IO_URING */ +#ifdef CONFIG_SECURITY +extern void security_initramfs_populated(void); +#else +static inline void security_initramfs_populated(void) +{ +} +#endif /* CONFIG_SECURITY */ + #endif /* ! __LINUX_SECURITY_H */ diff --git a/init/initramfs.c b/init/initramfs.c index 814241b64827..bc911e466d5b 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -17,6 +17,7 @@ #include #include #include +#include #include "do_mounts.h" @@ -712,6 +713,8 @@ static void __init do_populate_rootfs(void *unused, async_cookie_t cookie) } done: + security_initramfs_populated(); + /* * If the initrd region is overlapped with crashkernel reserved region, * free only memory that is not part of crashkernel region. diff --git a/security/security.c b/security/security.c index 645a660320cb..fafd2d43cba0 100644 --- a/security/security.c +++ b/security/security.c @@ -5778,3 +5778,13 @@ int security_uring_cmd(struct io_uring_cmd *ioucmd) return call_int_hook(uring_cmd, ioucmd); } #endif /* CONFIG_IO_URING */ + +/** + * security_initramfs_populated() - Notify LSMs that initramfs has been loaded + * + * Tells the LSMs the initramfs has been unpacked into the rootfs. + */ +void security_initramfs_populated(void) +{ + call_void_hook(initramfs_populated); +} -- cgit v1.2.3 From 7138679ff2a2b1674f16618558d6cabea6ab2c53 Mon Sep 17 00:00:00 2001 From: Fan Wu Date: Fri, 2 Aug 2024 23:08:21 -0700 Subject: lsm: add new securityfs delete function When deleting a directory in the security file system, the existing securityfs_remove requires the directory to be empty, otherwise it will do nothing. This leads to a potential risk that the security file system might be in an unclean state when the intended deletion did not happen. This commit introduces a new function securityfs_recursive_remove to recursively delete a directory without leaving an unclean state. Co-developed-by: Christian Brauner (Microsoft) Signed-off-by: Fan Wu [PM: subject line tweak] Signed-off-by: Paul Moore --- include/linux/security.h | 1 + security/inode.c | 25 +++++++++++++++++++++++++ 2 files changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 3298855abdbc..f6d2bc69cfa6 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -2090,6 +2090,7 @@ struct dentry *securityfs_create_symlink(const char *name, const char *target, const struct inode_operations *iops); extern void securityfs_remove(struct dentry *dentry); +extern void securityfs_recursive_remove(struct dentry *dentry); #else /* CONFIG_SECURITYFS */ diff --git a/security/inode.c b/security/inode.c index 9e7cde913667..f21847badb7d 100644 --- a/security/inode.c +++ b/security/inode.c @@ -313,6 +313,31 @@ void securityfs_remove(struct dentry *dentry) } EXPORT_SYMBOL_GPL(securityfs_remove); +static void remove_one(struct dentry *victim) +{ + simple_release_fs(&mount, &mount_count); +} + +/** + * securityfs_recursive_remove - recursively removes a file or directory + * + * @dentry: a pointer to a the dentry of the file or directory to be removed. + * + * This function recursively removes a file or directory in securityfs that was + * previously created with a call to another securityfs function (like + * securityfs_create_file() or variants thereof.) + */ +void securityfs_recursive_remove(struct dentry *dentry) +{ + if (IS_ERR_OR_NULL(dentry)) + return; + + simple_pin_fs(&fs_type, &mount, &mount_count); + simple_recursive_removal(dentry, remove_one); + simple_release_fs(&mount, &mount_count); +} +EXPORT_SYMBOL_GPL(securityfs_recursive_remove); + #ifdef CONFIG_SECURITY static struct dentry *lsm_dentry; static ssize_t lsm_read(struct file *filp, char __user *buf, size_t count, -- cgit v1.2.3 From b55d26bd1891423a3cdccf816b386aec8bbefc87 Mon Sep 17 00:00:00 2001 From: Deven Bowers Date: Fri, 2 Aug 2024 23:08:25 -0700 Subject: block,lsm: add LSM blob and new LSM hooks for block devices This patch introduces a new LSM blob to the block_device structure, enabling the security subsystem to store security-sensitive data related to block devices. Currently, for a device mapper's mapped device containing a dm-verity target, critical security information such as the roothash and its signing state are not readily accessible. Specifically, while the dm-verity volume creation process passes the dm-verity roothash and its signature from userspace to the kernel, the roothash is stored privately within the dm-verity target, and its signature is discarded post-verification. This makes it extremely hard for the security subsystem to utilize these data. With the addition of the LSM blob to the block_device structure, the security subsystem can now retain and manage important security metadata such as the roothash and the signing state of a dm-verity by storing them inside the blob. Access decisions can then be based on these stored data. The implementation follows the same approach used for security blobs in other structures like struct file, struct inode, and struct superblock. The initialization of the security blob occurs after the creation of the struct block_device, performed by the security subsystem. Similarly, the security blob is freed by the security subsystem before the struct block_device is deallocated or freed. This patch also introduces a new hook security_bdev_setintegrity() to save block device's integrity data to the new LSM blob. For example, for dm-verity, it can use this hook to expose its roothash and signing state to LSMs, then LSMs can save these data into the LSM blob. Please note that the new hook should be invoked every time the security information is updated to keep these data current. For example, in dm-verity, if the mapping table is reloaded and configured to use a different dm-verity target with a new roothash and signing information, the previously stored data in the LSM blob will become obsolete. It is crucial to re-invoke the hook to refresh these data and ensure they are up to date. This necessity arises from the design of device-mapper, where a device-mapper device is first created, and then targets are subsequently loaded into it. These targets can be modified multiple times during the device's lifetime. Therefore, while the LSM blob is allocated during the creation of the block device, its actual contents are not initialized at this stage and can change substantially over time. This includes alterations from data that the LSM 'trusts' to those it does not, making it essential to handle these changes correctly. Failure to address this dynamic aspect could potentially allow for bypassing LSM checks. Signed-off-by: Deven Bowers Signed-off-by: Fan Wu [PM: merge fuzz, subject line tweaks] Signed-off-by: Paul Moore --- block/bdev.c | 7 +++ include/linux/blk_types.h | 3 ++ include/linux/lsm_hook_defs.h | 5 ++ include/linux/lsm_hooks.h | 1 + include/linux/security.h | 26 +++++++++++ security/security.c | 103 ++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 145 insertions(+) (limited to 'include/linux') diff --git a/block/bdev.c b/block/bdev.c index c5507b6f63b8..33f9c4605e3a 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include @@ -324,6 +325,11 @@ static struct inode *bdev_alloc_inode(struct super_block *sb) if (!ei) return NULL; memset(&ei->bdev, 0, sizeof(ei->bdev)); + + if (security_bdev_alloc(&ei->bdev)) { + kmem_cache_free(bdev_cachep, ei); + return NULL; + } return &ei->vfs_inode; } @@ -333,6 +339,7 @@ static void bdev_free_inode(struct inode *inode) free_percpu(bdev->bd_stats); kfree(bdev->bd_meta_info); + security_bdev_free(bdev); if (!bdev_is_partition(bdev)) { if (bdev->bd_disk && bdev->bd_disk->bdi) diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 36ed96133217..413ebdff974b 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -71,6 +71,9 @@ struct block_device { struct partition_meta_info *bd_meta_info; int bd_writers; +#ifdef CONFIG_SECURITY + void *bd_security; +#endif /* * keep this out-of-line as it's both big and not needed in the fast * path diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 22a14fc794fe..860821f3bf6f 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -451,3 +451,8 @@ LSM_HOOK(int, 0, uring_cmd, struct io_uring_cmd *ioucmd) #endif /* CONFIG_IO_URING */ LSM_HOOK(void, LSM_RET_VOID, initramfs_populated, void) + +LSM_HOOK(int, 0, bdev_alloc_security, struct block_device *bdev) +LSM_HOOK(void, LSM_RET_VOID, bdev_free_security, struct block_device *bdev) +LSM_HOOK(int, 0, bdev_setintegrity, struct block_device *bdev, + enum lsm_integrity_type type, const void *value, size_t size) diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 11ea0063228f..4687985b9175 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -83,6 +83,7 @@ struct lsm_blob_sizes { int lbs_task; int lbs_xattr_count; /* number of xattr slots in new_xattrs array */ int lbs_tun_dev; + int lbs_bdev; }; /* diff --git a/include/linux/security.h b/include/linux/security.h index f6d2bc69cfa6..d7cab2d5002f 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -83,6 +83,10 @@ enum lsm_event { LSM_POLICY_CHANGE, }; +enum lsm_integrity_type { + __LSM_INT_MAX +}; + /* * These are reasons that can be passed to the security_locked_down() * LSM hook. Lockdown reasons that protect kernel integrity (ie, the @@ -509,6 +513,11 @@ int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen); int security_locked_down(enum lockdown_reason what); int lsm_fill_user_ctx(struct lsm_ctx __user *uctx, u32 *uctx_len, void *val, size_t val_len, u64 id, u64 flags); +int security_bdev_alloc(struct block_device *bdev); +void security_bdev_free(struct block_device *bdev); +int security_bdev_setintegrity(struct block_device *bdev, + enum lsm_integrity_type type, const void *value, + size_t size); #else /* CONFIG_SECURITY */ static inline int call_blocking_lsm_notifier(enum lsm_event event, void *data) @@ -1483,6 +1492,23 @@ static inline int lsm_fill_user_ctx(struct lsm_ctx __user *uctx, { return -EOPNOTSUPP; } + +static inline int security_bdev_alloc(struct block_device *bdev) +{ + return 0; +} + +static inline void security_bdev_free(struct block_device *bdev) +{ +} + +static inline int security_bdev_setintegrity(struct block_device *bdev, + enum lsm_integrity_type type, + const void *value, size_t size) +{ + return 0; +} + #endif /* CONFIG_SECURITY */ #if defined(CONFIG_SECURITY) && defined(CONFIG_WATCH_QUEUE) diff --git a/security/security.c b/security/security.c index fafd2d43cba0..c7feaa885a0e 100644 --- a/security/security.c +++ b/security/security.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include @@ -239,6 +240,7 @@ static void __init lsm_set_blob_sizes(struct lsm_blob_sizes *needed) lsm_set_blob_size(&needed->lbs_tun_dev, &blob_sizes.lbs_tun_dev); lsm_set_blob_size(&needed->lbs_xattr_count, &blob_sizes.lbs_xattr_count); + lsm_set_blob_size(&needed->lbs_bdev, &blob_sizes.lbs_bdev); } /* Prepare LSM for initialization. */ @@ -419,6 +421,7 @@ static void __init ordered_lsm_init(void) init_debug("task blob size = %d\n", blob_sizes.lbs_task); init_debug("tun device blob size = %d\n", blob_sizes.lbs_tun_dev); init_debug("xattr slots = %d\n", blob_sizes.lbs_xattr_count); + init_debug("bdev blob size = %d\n", blob_sizes.lbs_bdev); /* * Create any kmem_caches needed for blobs @@ -758,6 +761,28 @@ static int lsm_msg_msg_alloc(struct msg_msg *mp) GFP_KERNEL); } +/** + * lsm_bdev_alloc - allocate a composite block_device blob + * @bdev: the block_device that needs a blob + * + * Allocate the block_device blob for all the modules + * + * Returns 0, or -ENOMEM if memory can't be allocated. + */ +static int lsm_bdev_alloc(struct block_device *bdev) +{ + if (blob_sizes.lbs_bdev == 0) { + bdev->bd_security = NULL; + return 0; + } + + bdev->bd_security = kzalloc(blob_sizes.lbs_bdev, GFP_KERNEL); + if (!bdev->bd_security) + return -ENOMEM; + + return 0; +} + /** * lsm_early_task - during initialization allocate a composite task blob * @task: the task that needs a blob @@ -5658,6 +5683,84 @@ int security_locked_down(enum lockdown_reason what) } EXPORT_SYMBOL(security_locked_down); +/** + * security_bdev_alloc() - Allocate a block device LSM blob + * @bdev: block device + * + * Allocate and attach a security structure to @bdev->bd_security. The + * security field is initialized to NULL when the bdev structure is + * allocated. + * + * Return: Return 0 if operation was successful. + */ +int security_bdev_alloc(struct block_device *bdev) +{ + int rc = 0; + + rc = lsm_bdev_alloc(bdev); + if (unlikely(rc)) + return rc; + + rc = call_int_hook(bdev_alloc_security, bdev); + if (unlikely(rc)) + security_bdev_free(bdev); + + return rc; +} +EXPORT_SYMBOL(security_bdev_alloc); + +/** + * security_bdev_free() - Free a block device's LSM blob + * @bdev: block device + * + * Deallocate the bdev security structure and set @bdev->bd_security to NULL. + */ +void security_bdev_free(struct block_device *bdev) +{ + if (!bdev->bd_security) + return; + + call_void_hook(bdev_free_security, bdev); + + kfree(bdev->bd_security); + bdev->bd_security = NULL; +} +EXPORT_SYMBOL(security_bdev_free); + +/** + * security_bdev_setintegrity() - Set the device's integrity data + * @bdev: block device + * @type: type of integrity, e.g. hash digest, signature, etc + * @value: the integrity value + * @size: size of the integrity value + * + * Register a verified integrity measurement of a bdev with LSMs. + * LSMs should free the previously saved data if @value is NULL. + * Please note that the new hook should be invoked every time the security + * information is updated to keep these data current. For example, in dm-verity, + * if the mapping table is reloaded and configured to use a different dm-verity + * target with a new roothash and signing information, the previously stored data + * in the LSM blob will become obsolete. It is crucial to re-invoke the hook to + * refresh these data and ensure they are up to date. This necessity arises from + * the design of device-mapper, where a device-mapper device is first created, and + * then targets are subsequently loaded into it. These targets can be modified + * multiple times during the device's lifetime. Therefore, while the LSM blob is + * allocated during the creation of the block device, its actual contents are + * not initialized at this stage and can change substantially over time. This + * includes alterations from data that the LSMs 'trusts' to those they do not, + * making it essential to handle these changes correctly. Failure to address + * this dynamic aspect could potentially allow for bypassing LSM checks. + * + * Return: Returns 0 on success, negative values on failure. + */ +int security_bdev_setintegrity(struct block_device *bdev, + enum lsm_integrity_type type, const void *value, + size_t size) +{ + return call_int_hook(bdev_setintegrity, bdev, type, value, size); +} +EXPORT_SYMBOL(security_bdev_setintegrity); + #ifdef CONFIG_PERF_EVENTS /** * security_perf_event_open() - Check if a perf event open is allowed -- cgit v1.2.3 From a6af7bc3d72ff52c5526a392144347fcb3094149 Mon Sep 17 00:00:00 2001 From: Deven Bowers Date: Fri, 2 Aug 2024 23:08:26 -0700 Subject: dm-verity: expose root hash digest and signature data to LSMs dm-verity provides a strong guarantee of a block device's integrity. As a generic way to check the integrity of a block device, it provides those integrity guarantees to its higher layers, including the filesystem level. However, critical security metadata like the dm-verity roothash and its signing information are not easily accessible to the LSMs. To address this limitation, this patch introduces a mechanism to store and manage these essential security details within a newly added LSM blob in the block_device structure. This addition allows LSMs to make access control decisions on the integrity data stored within the block_device, enabling more flexible security policies. For instance, LSMs can now revoke access to dm-verity devices based on their roothashes, ensuring that only authorized and verified content is accessible. Additionally, LSMs can enforce policies to only allow files from dm-verity devices that have a valid digital signature to execute, effectively blocking any unsigned files from execution, thus enhancing security against unauthorized modifications. The patch includes new hook calls, `security_bdev_setintegrity()`, in dm-verity to expose the dm-verity roothash and the roothash signature to LSMs via preresume() callback. By using the preresume() callback, it ensures that the security metadata is consistently in sync with the metadata of the dm-verity target in the current active mapping table. The hook calls are depended on CONFIG_SECURITY. Signed-off-by: Deven Bowers Signed-off-by: Fan Wu Reviewed-by: Mikulas Patocka [PM: moved sig_size field as discussed] Signed-off-by: Paul Moore --- drivers/md/dm-verity-target.c | 118 ++++++++++++++++++++++++++++++++++++++++++ drivers/md/dm-verity.h | 4 ++ include/linux/security.h | 9 +++- 3 files changed, 130 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index cf659c8feb29..24ba9a10444c 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -22,6 +22,7 @@ #include #include #include +#include #define DM_MSG_PREFIX "verity" @@ -930,6 +931,41 @@ static void verity_io_hints(struct dm_target *ti, struct queue_limits *limits) limits->dma_alignment = limits->logical_block_size - 1; } +#ifdef CONFIG_SECURITY + +static int verity_init_sig(struct dm_verity *v, const void *sig, + size_t sig_size) +{ + v->sig_size = sig_size; + + if (sig) { + v->root_digest_sig = kmemdup(sig, v->sig_size, GFP_KERNEL); + if (!v->root_digest_sig) + return -ENOMEM; + } + + return 0; +} + +static void verity_free_sig(struct dm_verity *v) +{ + kfree(v->root_digest_sig); +} + +#else + +static inline int verity_init_sig(struct dm_verity *v, const void *sig, + size_t sig_size) +{ + return 0; +} + +static inline void verity_free_sig(struct dm_verity *v) +{ +} + +#endif /* CONFIG_SECURITY */ + static void verity_dtr(struct dm_target *ti) { struct dm_verity *v = ti->private; @@ -949,6 +985,7 @@ static void verity_dtr(struct dm_target *ti) kfree(v->initial_hashstate); kfree(v->root_digest); kfree(v->zero_digest); + verity_free_sig(v); if (v->ahash_tfm) { static_branch_dec(&ahash_enabled); @@ -1418,6 +1455,13 @@ static int verity_ctr(struct dm_target *ti, unsigned int argc, char **argv) ti->error = "Root hash verification failed"; goto bad; } + + r = verity_init_sig(v, verify_args.sig, verify_args.sig_size); + if (r < 0) { + ti->error = "Cannot allocate root digest signature"; + goto bad; + } + v->hash_per_block_bits = __fls((1 << v->hash_dev_block_bits) / v->digest_size); @@ -1559,8 +1603,79 @@ int dm_verity_get_root_digest(struct dm_target *ti, u8 **root_digest, unsigned i return 0; } +#ifdef CONFIG_SECURITY + +#ifdef CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG + +static int verity_security_set_signature(struct block_device *bdev, + struct dm_verity *v) +{ + /* + * if the dm-verity target is unsigned, v->root_digest_sig will + * be NULL, and the hook call is still required to let LSMs mark + * the device as unsigned. This information is crucial for LSMs to + * block operations such as execution on unsigned files + */ + return security_bdev_setintegrity(bdev, + LSM_INT_DMVERITY_SIG_VALID, + v->root_digest_sig, + v->sig_size); +} + +#else + +static inline int verity_security_set_signature(struct block_device *bdev, + struct dm_verity *v) +{ + return 0; +} + +#endif /* CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG */ + +/* + * Expose verity target's root hash and signature data to LSMs before resume. + * + * Returns 0 on success, or -ENOMEM if the system is out of memory. + */ +static int verity_preresume(struct dm_target *ti) +{ + struct block_device *bdev; + struct dm_verity_digest root_digest; + struct dm_verity *v; + int r; + + v = ti->private; + bdev = dm_disk(dm_table_get_md(ti->table))->part0; + root_digest.digest = v->root_digest; + root_digest.digest_len = v->digest_size; + if (static_branch_unlikely(&ahash_enabled) && !v->shash_tfm) + root_digest.alg = crypto_ahash_alg_name(v->ahash_tfm); + else + root_digest.alg = crypto_shash_alg_name(v->shash_tfm); + + r = security_bdev_setintegrity(bdev, LSM_INT_DMVERITY_ROOTHASH, &root_digest, + sizeof(root_digest)); + if (r) + return r; + + r = verity_security_set_signature(bdev, v); + if (r) + goto bad; + + return 0; + +bad: + + security_bdev_setintegrity(bdev, LSM_INT_DMVERITY_ROOTHASH, NULL, 0); + + return r; +} + +#endif /* CONFIG_SECURITY */ + static struct target_type verity_target = { .name = "verity", +/* Note: the LSMs depend on the singleton and immutable features */ .features = DM_TARGET_SINGLETON | DM_TARGET_IMMUTABLE, .version = {1, 10, 0}, .module = THIS_MODULE, @@ -1571,6 +1686,9 @@ static struct target_type verity_target = { .prepare_ioctl = verity_prepare_ioctl, .iterate_devices = verity_iterate_devices, .io_hints = verity_io_hints, +#ifdef CONFIG_SECURITY + .preresume = verity_preresume, +#endif /* CONFIG_SECURITY */ }; module_dm(verity); diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h index aac3a1b1d94a..754e70bb5fe0 100644 --- a/drivers/md/dm-verity.h +++ b/drivers/md/dm-verity.h @@ -45,6 +45,10 @@ struct dm_verity { u8 *salt; /* salt: its size is salt_size */ u8 *initial_hashstate; /* salted initial state, if shash_tfm is set */ u8 *zero_digest; /* digest for a zero block */ +#ifdef CONFIG_SECURITY + u8 *root_digest_sig; /* signature of the root digest */ + unsigned int sig_size; /* root digest signature size */ +#endif /* CONFIG_SECURITY */ unsigned int salt_size; sector_t data_start; /* data offset in 512-byte sectors */ sector_t hash_start; /* hash start in blocks */ diff --git a/include/linux/security.h b/include/linux/security.h index d7cab2d5002f..e383022467db 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -83,8 +83,15 @@ enum lsm_event { LSM_POLICY_CHANGE, }; +struct dm_verity_digest { + const char *alg; + const u8 *digest; + size_t digest_len; +}; + enum lsm_integrity_type { - __LSM_INT_MAX + LSM_INT_DMVERITY_SIG_VALID, + LSM_INT_DMVERITY_ROOTHASH, }; /* -- cgit v1.2.3 From fb55e177d5936fb80fb2586036d195c57e7f6892 Mon Sep 17 00:00:00 2001 From: Fan Wu Date: Fri, 2 Aug 2024 23:08:28 -0700 Subject: lsm: add security_inode_setintegrity() hook This patch introduces a new hook to save inode's integrity data. For example, for fsverity enabled files, LSMs can use this hook to save the existence of verified fsverity builtin signature into the inode's security blob, and LSMs can make access decisions based on this data. Signed-off-by: Fan Wu [PM: subject line tweak, removed changelog] Signed-off-by: Paul Moore --- include/linux/lsm_hook_defs.h | 2 ++ include/linux/security.h | 10 ++++++++++ security/security.c | 20 ++++++++++++++++++++ 3 files changed, 32 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 860821f3bf6f..1d59513bf230 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -180,6 +180,8 @@ LSM_HOOK(void, LSM_RET_VOID, inode_getsecid, struct inode *inode, u32 *secid) LSM_HOOK(int, 0, inode_copy_up, struct dentry *src, struct cred **new) LSM_HOOK(int, -EOPNOTSUPP, inode_copy_up_xattr, struct dentry *src, const char *name) +LSM_HOOK(int, 0, inode_setintegrity, const struct inode *inode, + enum lsm_integrity_type type, const void *value, size_t size) LSM_HOOK(int, 0, kernfs_init_security, struct kernfs_node *kn_dir, struct kernfs_node *kn) LSM_HOOK(int, 0, file_permission, struct file *file, int mask) diff --git a/include/linux/security.h b/include/linux/security.h index e383022467db..97b7c57e6560 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -410,6 +410,9 @@ int security_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer void security_inode_getsecid(struct inode *inode, u32 *secid); int security_inode_copy_up(struct dentry *src, struct cred **new); int security_inode_copy_up_xattr(struct dentry *src, const char *name); +int security_inode_setintegrity(const struct inode *inode, + enum lsm_integrity_type type, const void *value, + size_t size); int security_kernfs_init_security(struct kernfs_node *kn_dir, struct kernfs_node *kn); int security_file_permission(struct file *file, int mask); @@ -1026,6 +1029,13 @@ static inline int security_inode_copy_up(struct dentry *src, struct cred **new) return 0; } +static inline int security_inode_setintegrity(const struct inode *inode, + enum lsm_integrity_type type, + const void *value, size_t size) +{ + return 0; +} + static inline int security_kernfs_init_security(struct kernfs_node *kn_dir, struct kernfs_node *kn) { diff --git a/security/security.c b/security/security.c index 3160a0173581..bb43ad444f1f 100644 --- a/security/security.c +++ b/security/security.c @@ -2716,6 +2716,26 @@ int security_inode_copy_up_xattr(struct dentry *src, const char *name) } EXPORT_SYMBOL(security_inode_copy_up_xattr); +/** + * security_inode_setintegrity() - Set the inode's integrity data + * @inode: inode + * @type: type of integrity, e.g. hash digest, signature, etc + * @value: the integrity value + * @size: size of the integrity value + * + * Register a verified integrity measurement of a inode with LSMs. + * LSMs should free the previously saved data if @value is NULL. + * + * Return: Returns 0 on success, negative values on failure. + */ +int security_inode_setintegrity(const struct inode *inode, + enum lsm_integrity_type type, const void *value, + size_t size) +{ + return call_int_hook(inode_setintegrity, inode, type, value, size); +} +EXPORT_SYMBOL(security_inode_setintegrity); + /** * security_kernfs_init_security() - Init LSM context for a kernfs node * @kn_dir: parent kernfs node -- cgit v1.2.3 From 7c373e4f1445263728d3eeab7e33e932c8f4a288 Mon Sep 17 00:00:00 2001 From: Fan Wu Date: Fri, 2 Aug 2024 23:08:29 -0700 Subject: fsverity: expose verified fsverity built-in signatures to LSMs This patch enhances fsverity's capabilities to support both integrity and authenticity protection by introducing the exposure of built-in signatures through a new LSM hook. This functionality allows LSMs, e.g. IPE, to enforce policies based on the authenticity and integrity of files, specifically focusing on built-in fsverity signatures. It enables a policy enforcement layer within LSMs for fsverity, offering granular control over the usage of authenticity claims. For instance, a policy could be established to only permit the execution of all files with verified built-in fsverity signatures. The introduction of a security_inode_setintegrity() hook call within fsverity's workflow ensures that the verified built-in signature of a file is exposed to LSMs. This enables LSMs to recognize and label fsverity files that contain a verified built-in fsverity signature. This hook is invoked subsequent to the fsverity_verify_signature() process, guaranteeing the signature's verification against fsverity's keyring. This mechanism is crucial for maintaining system security, as it operates in kernel space, effectively thwarting attempts by malicious binaries to bypass user space stack interactions. The second to last commit in this patch set will add a link to the IPE documentation in fsverity.rst. Signed-off-by: Deven Bowers Signed-off-by: Fan Wu Acked-by: Eric Biggers Signed-off-by: Paul Moore --- Documentation/filesystems/fsverity.rst | 23 +++++++++++++++++++++-- fs/verity/signature.c | 18 +++++++++++++++++- include/linux/security.h | 1 + 3 files changed, 39 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/Documentation/filesystems/fsverity.rst b/Documentation/filesystems/fsverity.rst index 13e4b18e5dbb..362b7a5dc300 100644 --- a/Documentation/filesystems/fsverity.rst +++ b/Documentation/filesystems/fsverity.rst @@ -86,6 +86,14 @@ authenticating fs-verity file hashes include: signature in their "security.ima" extended attribute, as controlled by the IMA policy. For more information, see the IMA documentation. +- Integrity Policy Enforcement (IPE). IPE supports enforcing access + control decisions based on immutable security properties of files, + including those protected by fs-verity's built-in signatures. + "IPE policy" specifically allows for the authorization of fs-verity + files using properties ``fsverity_digest`` for identifying + files by their verity digest, and ``fsverity_signature`` to authorize + files with a verified fs-verity's built-in signature. + - Trusted userspace code in combination with `Built-in signature verification`_. This approach should be used only with great care. @@ -457,7 +465,11 @@ Enabling this option adds the following: On success, the ioctl persists the signature alongside the Merkle tree. Then, any time the file is opened, the kernel verifies the file's actual digest against this signature, using the certificates - in the ".fs-verity" keyring. + in the ".fs-verity" keyring. This verification happens as long as the + file's signature exists, regardless of the state of the sysctl variable + "fs.verity.require_signatures" described in the next item. The IPE LSM + relies on this behavior to recognize and label fsverity files + that contain a verified built-in fsverity signature. 3. A new sysctl "fs.verity.require_signatures" is made available. When set to 1, the kernel requires that all verity files have a @@ -481,7 +493,7 @@ be carefully considered before using them: - Builtin signature verification does *not* make the kernel enforce that any files actually have fs-verity enabled. Thus, it is not a - complete authentication policy. Currently, if it is used, the only + complete authentication policy. Currently, if it is used, one way to complete the authentication policy is for trusted userspace code to explicitly check whether files have fs-verity enabled with a signature before they are accessed. (With @@ -490,6 +502,13 @@ be carefully considered before using them: could just store the signature alongside the file and verify it itself using a cryptographic library, instead of using this feature. +- Another approach is to utilize fs-verity builtin signature + verification in conjunction with the IPE LSM, which supports defining + a kernel-enforced, system-wide authentication policy that allows only + files with a verified fs-verity builtin signature to perform certain + operations, such as execution. Note that IPE doesn't require + fs.verity.require_signatures=1. + - A file's builtin signature can only be set at the same time that fs-verity is being enabled on the file. Changing or deleting the builtin signature later requires re-creating the file. diff --git a/fs/verity/signature.c b/fs/verity/signature.c index 90c07573dd77..0302a4e506ec 100644 --- a/fs/verity/signature.c +++ b/fs/verity/signature.c @@ -17,6 +17,7 @@ #include #include +#include #include #include @@ -41,7 +42,11 @@ static struct key *fsverity_keyring; * @sig_size: size of signature in bytes, or 0 if no signature * * If the file includes a signature of its fs-verity file digest, verify it - * against the certificates in the fs-verity keyring. + * against the certificates in the fs-verity keyring. Note that signatures + * are verified regardless of the state of the 'fsverity_require_signatures' + * variable and the LSM subsystem relies on this behavior to help enforce + * file integrity policies. Please discuss changes with the LSM list + * (thank you!). * * Return: 0 on success (signature valid or not required); -errno on failure */ @@ -106,6 +111,17 @@ int fsverity_verify_signature(const struct fsverity_info *vi, return err; } + err = security_inode_setintegrity(inode, + LSM_INT_FSVERITY_BUILTINSIG_VALID, + signature, + sig_size); + + if (err) { + fsverity_err(inode, "Error %d exposing file signature to LSMs", + err); + return err; + } + return 0; } diff --git a/include/linux/security.h b/include/linux/security.h index 97b7c57e6560..c37c32ebbdcd 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -92,6 +92,7 @@ struct dm_verity_digest { enum lsm_integrity_type { LSM_INT_DMVERITY_SIG_VALID, LSM_INT_DMVERITY_ROOTHASH, + LSM_INT_FSVERITY_BUILTINSIG_VALID, }; /* -- cgit v1.2.3 From 7cff549daa67c7549c5a8688674cea2df8c2ec80 Mon Sep 17 00:00:00 2001 From: KP Singh Date: Fri, 16 Aug 2024 17:43:05 +0200 Subject: kernel: Add helper macros for loop unrolling This helps in easily initializing blocks of code (e.g. static calls and keys). UNROLL(N, MACRO, __VA_ARGS__) calls MACRO N times with the first argument as the index of the iteration. This allows string pasting to create unique tokens for variable names, function calls etc. As an example: #include #define MACRO(N, a, b) \ int add_##N(int a, int b) \ { \ return a + b + N; \ } UNROLL(2, MACRO, x, y) expands to: int add_0(int x, int y) { return x + y + 0; } int add_1(int x, int y) { return x + y + 1; } Tested-by: Guenter Roeck Reviewed-by: Kees Cook Reviewed-by: Casey Schaufler Reviewed-by: John Johansen Acked-by: Jiri Olsa Acked-by: Song Liu Acked-by: Andrii Nakryiko Acked-by: Casey Schaufler Nacked-by: Tetsuo Handa Signed-off-by: KP Singh Signed-off-by: Paul Moore --- include/linux/unroll.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) create mode 100644 include/linux/unroll.h (limited to 'include/linux') diff --git a/include/linux/unroll.h b/include/linux/unroll.h new file mode 100644 index 000000000000..d42fd6366373 --- /dev/null +++ b/include/linux/unroll.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Copyright (C) 2023 Google LLC. + */ + +#ifndef __UNROLL_H +#define __UNROLL_H + +#include + +#define UNROLL(N, MACRO, args...) CONCATENATE(__UNROLL_, N)(MACRO, args) + +#define __UNROLL_0(MACRO, args...) +#define __UNROLL_1(MACRO, args...) __UNROLL_0(MACRO, args) MACRO(0, args) +#define __UNROLL_2(MACRO, args...) __UNROLL_1(MACRO, args) MACRO(1, args) +#define __UNROLL_3(MACRO, args...) __UNROLL_2(MACRO, args) MACRO(2, args) +#define __UNROLL_4(MACRO, args...) __UNROLL_3(MACRO, args) MACRO(3, args) +#define __UNROLL_5(MACRO, args...) __UNROLL_4(MACRO, args) MACRO(4, args) +#define __UNROLL_6(MACRO, args...) __UNROLL_5(MACRO, args) MACRO(5, args) +#define __UNROLL_7(MACRO, args...) __UNROLL_6(MACRO, args) MACRO(6, args) +#define __UNROLL_8(MACRO, args...) __UNROLL_7(MACRO, args) MACRO(7, args) +#define __UNROLL_9(MACRO, args...) __UNROLL_8(MACRO, args) MACRO(8, args) +#define __UNROLL_10(MACRO, args...) __UNROLL_9(MACRO, args) MACRO(9, args) +#define __UNROLL_11(MACRO, args...) __UNROLL_10(MACRO, args) MACRO(10, args) +#define __UNROLL_12(MACRO, args...) __UNROLL_11(MACRO, args) MACRO(11, args) +#define __UNROLL_13(MACRO, args...) __UNROLL_12(MACRO, args) MACRO(12, args) +#define __UNROLL_14(MACRO, args...) __UNROLL_13(MACRO, args) MACRO(13, args) +#define __UNROLL_15(MACRO, args...) __UNROLL_14(MACRO, args) MACRO(14, args) +#define __UNROLL_16(MACRO, args...) __UNROLL_15(MACRO, args) MACRO(15, args) +#define __UNROLL_17(MACRO, args...) __UNROLL_16(MACRO, args) MACRO(16, args) +#define __UNROLL_18(MACRO, args...) __UNROLL_17(MACRO, args) MACRO(17, args) +#define __UNROLL_19(MACRO, args...) __UNROLL_18(MACRO, args) MACRO(18, args) +#define __UNROLL_20(MACRO, args...) __UNROLL_19(MACRO, args) MACRO(19, args) + +#endif /* __UNROLL_H */ -- cgit v1.2.3 From 9b59a85a84dc37ca4f2c54df5e06aff4c1eae5d3 Mon Sep 17 00:00:00 2001 From: Matthew Brost Date: Tue, 20 Aug 2024 12:38:08 -0700 Subject: workqueue: Don't call va_start / va_end twice Calling va_start / va_end multiple times is undefined and causes problems with certain compiler / platforms. Change alloc_ordered_workqueue_lockdep_map to a macro and updated __alloc_workqueue to take a va_list argument. Cc: Sergey Senozhatsky Cc: Tejun Heo Cc: Lai Jiangshan Signed-off-by: Matthew Brost Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 16 ++-------------- kernel/workqueue.c | 6 +----- 2 files changed, 3 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 04dff07a9e2b..f3cc15940b4d 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -543,20 +543,8 @@ alloc_workqueue_lockdep_map(const char *fmt, unsigned int flags, int max_active, * RETURNS: * Pointer to the allocated workqueue on success, %NULL on failure. */ -__printf(1, 4) static inline struct workqueue_struct * -alloc_ordered_workqueue_lockdep_map(const char *fmt, unsigned int flags, - struct lockdep_map *lockdep_map, ...) -{ - struct workqueue_struct *wq; - va_list args; - - va_start(args, lockdep_map); - wq = alloc_workqueue_lockdep_map(fmt, WQ_UNBOUND | __WQ_ORDERED | flags, - 1, lockdep_map, args); - va_end(args); - - return wq; -} +#define alloc_ordered_workqueue_lockdep_map(fmt, flags, lockdep_map, args...) \ + alloc_workqueue_lockdep_map(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, lockdep_map, ##args) #endif /** diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 7468ba5e2417..7cc77adb18bb 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -5619,12 +5619,10 @@ static void wq_adjust_max_active(struct workqueue_struct *wq) } while (activated); } -__printf(1, 4) static struct workqueue_struct *__alloc_workqueue(const char *fmt, unsigned int flags, - int max_active, ...) + int max_active, va_list args) { - va_list args; struct workqueue_struct *wq; size_t wq_size; int name_len; @@ -5656,9 +5654,7 @@ static struct workqueue_struct *__alloc_workqueue(const char *fmt, goto err_free_wq; } - va_start(args, max_active); name_len = vsnprintf(wq->name, sizeof(wq->name), fmt, args); - va_end(args); if (name_len >= WQ_NAME_LEN) pr_warn_once("workqueue: name exceeds WQ_NAME_LEN. Truncating to: %s\n", -- cgit v1.2.3 From 8fb9f31984bdc0aaa1b0f7c7e7a27bd3137f8744 Mon Sep 17 00:00:00 2001 From: Zhiguo Niu Date: Thu, 1 Aug 2024 09:33:51 +0800 Subject: f2fs: clean up val{>>,<<}F2FS_BLKSIZE_BITS Use F2FS_BYTES_TO_BLK(bytes) and F2FS_BLK_TO_BYTES(blk) for cleanup Signed-off-by: Zhiguo Niu Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/checkpoint.c | 2 +- fs/f2fs/debug.c | 2 +- fs/f2fs/file.c | 6 +++--- fs/f2fs/node.c | 4 ++-- fs/f2fs/super.c | 2 +- include/linux/f2fs_fs.h | 2 +- 6 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index bdd96329dddd..f3d22b8ef2ff 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -1551,7 +1551,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) blk = start_blk + BLKS_PER_SEG(sbi) - nm_i->nat_bits_blocks; for (i = 0; i < nm_i->nat_bits_blocks; i++) f2fs_update_meta_page(sbi, nm_i->nat_bits + - (i << F2FS_BLKSIZE_BITS), blk + i); + F2FS_BLK_TO_BYTES(i), blk + i); } /* write out checkpoint buffer at block 0 */ diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index 8b0e1e71b667..546b8ba91261 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -275,7 +275,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi) /* build nm */ si->base_mem += sizeof(struct f2fs_nm_info); si->base_mem += __bitmap_size(sbi, NAT_BITMAP); - si->base_mem += (NM_I(sbi)->nat_bits_blocks << F2FS_BLKSIZE_BITS); + si->base_mem += F2FS_BLK_TO_BYTES(NM_I(sbi)->nat_bits_blocks); si->base_mem += NM_I(sbi)->nat_blocks * f2fs_bitmap_size(NAT_ENTRY_PER_BLOCK); si->base_mem += NM_I(sbi)->nat_blocks / 8; diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index a2d466ca2579..bddcb2cd945a 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -2979,9 +2979,9 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, } f2fs_lock_op(sbi); - ret = __exchange_data_block(src, dst, pos_in >> F2FS_BLKSIZE_BITS, - pos_out >> F2FS_BLKSIZE_BITS, - len >> F2FS_BLKSIZE_BITS, false); + ret = __exchange_data_block(src, dst, F2FS_BYTES_TO_BLK(pos_in), + F2FS_BYTES_TO_BLK(pos_out), + F2FS_BYTES_TO_BLK(len), false); if (!ret) { if (dst_max_i_size) diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 2fe182f73599..9e7a6e21f30c 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -3166,7 +3166,7 @@ static int __get_nat_bitmaps(struct f2fs_sb_info *sbi) nm_i->nat_bits_blocks = F2FS_BLK_ALIGN((nat_bits_bytes << 1) + 8); nm_i->nat_bits = f2fs_kvzalloc(sbi, - nm_i->nat_bits_blocks << F2FS_BLKSIZE_BITS, GFP_KERNEL); + F2FS_BLK_TO_BYTES(nm_i->nat_bits_blocks), GFP_KERNEL); if (!nm_i->nat_bits) return -ENOMEM; @@ -3185,7 +3185,7 @@ static int __get_nat_bitmaps(struct f2fs_sb_info *sbi) if (IS_ERR(page)) return PTR_ERR(page); - memcpy(nm_i->nat_bits + (i << F2FS_BLKSIZE_BITS), + memcpy(nm_i->nat_bits + F2FS_BLK_TO_BYTES(i), page_address(page), F2FS_BLKSIZE); f2fs_put_page(page, 1); } diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 4d2f3bb8e418..977f038f3557 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -3317,7 +3317,7 @@ loff_t max_file_blocks(struct inode *inode) * fit within U32_MAX + 1 data units. */ - result = min(result, (((loff_t)U32_MAX + 1) * 4096) >> F2FS_BLKSIZE_BITS); + result = min(result, F2FS_BYTES_TO_BLK(((loff_t)U32_MAX + 1) * 4096)); return result; } diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 01bee2b289c2..f17f89a259e2 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -19,7 +19,6 @@ #define F2FS_BLKSIZE_BITS PAGE_SHIFT /* bits for F2FS_BLKSIZE */ #define F2FS_MAX_EXTENSION 64 /* # of extension entries */ #define F2FS_EXTENSION_LEN 8 /* max size of extension */ -#define F2FS_BLK_ALIGN(x) (((x) + F2FS_BLKSIZE - 1) >> F2FS_BLKSIZE_BITS) #define NULL_ADDR ((block_t)0) /* used as block_t addresses */ #define NEW_ADDR ((block_t)-1) /* used as block_t addresses */ @@ -28,6 +27,7 @@ #define F2FS_BYTES_TO_BLK(bytes) ((bytes) >> F2FS_BLKSIZE_BITS) #define F2FS_BLK_TO_BYTES(blk) ((blk) << F2FS_BLKSIZE_BITS) #define F2FS_BLK_END_BYTES(blk) (F2FS_BLK_TO_BYTES(blk + 1) - 1) +#define F2FS_BLK_ALIGN(x) (F2FS_BYTES_TO_BLK((x) + F2FS_BLKSIZE - 1)) /* 0, 1(node nid), 2(meta nid) are reserved node id */ #define F2FS_RESERVED_NODE_NUM 3 -- cgit v1.2.3 From 013f510d1fce563f37f420bf231b065885a16f21 Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Thu, 1 Aug 2024 21:31:21 +0800 Subject: dm: Remove unused declaration dm_get_rq_mapinfo() Commit ae6ad75e5c3c ("dm: remove unused dm_get_rq_mapinfo()") removed the implementation but leave declaration. Signed-off-by: Yue Haibing Reviewed-by: Damien Le Moal Signed-off-by: Mikulas Patocka --- include/linux/device-mapper.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 53ca3a913d06..8321f65897f3 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -524,7 +524,6 @@ int dm_post_suspending(struct dm_target *ti); int dm_noflush_suspending(struct dm_target *ti); void dm_accept_partial_bio(struct bio *bio, unsigned int n_sectors); void dm_submit_bio_remap(struct bio *clone, struct bio *tgt_clone); -union map_info *dm_get_rq_mapinfo(struct request *rq); #ifdef CONFIG_BLK_DEV_ZONED struct dm_report_zones_args { -- cgit v1.2.3 From 0e1d5731d3c1e2214249ef36dcd13ad51ad304cf Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 20 Aug 2024 08:35:30 +0206 Subject: printk: Check printk_deferred_enter()/_exit() usage Add validation that printk_deferred_enter()/_exit() are called in non-migration contexts. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: John Ogness Reviewed-by: Petr Mladek Link: https://lore.kernel.org/r/20240820063001.36405-5-john.ogness@linutronix.de Signed-off-by: Petr Mladek --- include/linux/printk.h | 9 +++++---- kernel/printk/internal.h | 3 +++ kernel/printk/printk_safe.c | 12 ++++++++++++ 3 files changed, 20 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index b937cefcb31c..eee8e97da681 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -161,15 +161,16 @@ int _printk(const char *fmt, ...); */ __printf(1, 2) __cold int _printk_deferred(const char *fmt, ...); -extern void __printk_safe_enter(void); -extern void __printk_safe_exit(void); +extern void __printk_deferred_enter(void); +extern void __printk_deferred_exit(void); + /* * The printk_deferred_enter/exit macros are available only as a hack for * some code paths that need to defer all printk console printing. Interrupts * must be disabled for the deferred duration. */ -#define printk_deferred_enter __printk_safe_enter -#define printk_deferred_exit __printk_safe_exit +#define printk_deferred_enter() __printk_deferred_enter() +#define printk_deferred_exit() __printk_deferred_exit() /* * Please don't use printk_ratelimit(), because it shares ratelimiting state diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h index 398ecb40d279..dc8bc0890fd2 100644 --- a/kernel/printk/internal.h +++ b/kernel/printk/internal.h @@ -53,6 +53,9 @@ int vprintk_store(int facility, int level, __printf(1, 0) int vprintk_default(const char *fmt, va_list args); __printf(1, 0) int vprintk_deferred(const char *fmt, va_list args); +void __printk_safe_enter(void); +void __printk_safe_exit(void); + bool printk_percpu_data_ready(void); #define printk_safe_enter_irqsave(flags) \ diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c index 6d10927a07d8..4421ccac3113 100644 --- a/kernel/printk/printk_safe.c +++ b/kernel/printk/printk_safe.c @@ -26,6 +26,18 @@ void __printk_safe_exit(void) this_cpu_dec(printk_context); } +void __printk_deferred_enter(void) +{ + cant_migrate(); + __printk_safe_enter(); +} + +void __printk_deferred_exit(void) +{ + cant_migrate(); + __printk_safe_exit(); +} + asmlinkage int vprintk(const char *fmt, va_list args) { #ifdef CONFIG_KGDB_KDB -- cgit v1.2.3 From b7049d88c1763d5f133b0e93e39da8e89a9f944b Mon Sep 17 00:00:00 2001 From: John Ogness Date: Tue, 20 Aug 2024 08:35:32 +0206 Subject: printk: nbcon: Remove return value for write_atomic() The return value of write_atomic() does not provide any useful information. On the contrary, it makes things more complicated for the caller to appropriately deal with the information. Change write_atomic() to not have a return value. If the message did not get printed due to loss of ownership, the caller will notice this on its own. If ownership was not lost, it will be assumed that the driver successfully printed the message and the sequence number for that console will be incremented. Signed-off-by: John Ogness Reviewed-by: Petr Mladek Link: https://lore.kernel.org/r/20240820063001.36405-7-john.ogness@linutronix.de Signed-off-by: Petr Mladek --- include/linux/console.h | 2 +- kernel/printk/nbcon.c | 15 +++++++-------- 2 files changed, 8 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index 31a8f5b85f5d..577b157fe4fb 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -345,7 +345,7 @@ struct console { struct hlist_node node; /* nbcon console specific members */ - bool (*write_atomic)(struct console *con, + void (*write_atomic)(struct console *con, struct nbcon_write_context *wctxt); atomic_t __private nbcon_state; atomic_long_t __private nbcon_seq; diff --git a/kernel/printk/nbcon.c b/kernel/printk/nbcon.c index 931b8f086902..f279f839741a 100644 --- a/kernel/printk/nbcon.c +++ b/kernel/printk/nbcon.c @@ -885,7 +885,6 @@ static bool nbcon_emit_next_record(struct nbcon_write_context *wctxt) unsigned long con_dropped; struct nbcon_state cur; unsigned long dropped; - bool done; /* * The printk buffers are filled within an unsafe section. This @@ -925,16 +924,16 @@ static bool nbcon_emit_next_record(struct nbcon_write_context *wctxt) wctxt->unsafe_takeover = cur.unsafe_takeover; if (con->write_atomic) { - done = con->write_atomic(con, wctxt); + con->write_atomic(con, wctxt); } else { - nbcon_context_release(ctxt); + /* + * This function should never be called for legacy consoles. + * Handle it as if ownership was lost and try to continue. + */ WARN_ON_ONCE(1); - done = false; - } - - /* If not done, the emit was aborted. */ - if (!done) + nbcon_context_release(ctxt); return false; + } /* * Since any dropped message was successfully output, reset the -- cgit v1.2.3 From 7d56936c1e5208b5eeea2a9a2f70e85248f6da49 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Tue, 20 Aug 2024 08:35:33 +0206 Subject: printk: nbcon: Add detailed doc for write_atomic() The write_atomic() callback has special requirements and is allowed to use special helper functions. Provide detailed documentation of the callback so that a developer has a chance of implementing it correctly. Signed-off-by: John Ogness Reviewed-by: Petr Mladek Link: https://lore.kernel.org/r/20240820063001.36405-8-john.ogness@linutronix.de Signed-off-by: Petr Mladek --- include/linux/console.h | 33 +++++++++++++++++++++++++++++---- 1 file changed, 29 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index 577b157fe4fb..35c64ee3827b 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -303,7 +303,7 @@ struct nbcon_write_context { /** * struct console - The console descriptor structure * @name: The name of the console driver - * @write: Write callback to output messages (Optional) + * @write: Legacy write callback to output messages (Optional) * @read: Read callback for console input (Optional) * @device: The underlying TTY device driver (Optional) * @unblank: Callback to unblank the console (Optional) @@ -320,7 +320,6 @@ struct nbcon_write_context { * @data: Driver private data * @node: hlist node for the console list * - * @write_atomic: Write callback for atomic context * @nbcon_state: State for nbcon consoles * @nbcon_seq: Sequence number of the next record for nbcon to print * @pbufs: Pointer to nbcon private buffer @@ -345,8 +344,34 @@ struct console { struct hlist_node node; /* nbcon console specific members */ - void (*write_atomic)(struct console *con, - struct nbcon_write_context *wctxt); + + /** + * @write_atomic: + * + * NBCON callback to write out text in any context. (Optional) + * + * This callback is called with the console already acquired. However, + * a higher priority context is allowed to take it over by default. + * + * The callback must call nbcon_enter_unsafe() and nbcon_exit_unsafe() + * around any code where the takeover is not safe, for example, when + * manipulating the serial port registers. + * + * nbcon_enter_unsafe() will fail if the context has lost the console + * ownership in the meantime. In this case, the callback is no longer + * allowed to go forward. It must back out immediately and carefully. + * The buffer content is also no longer trusted since it no longer + * belongs to the context. + * + * The callback should allow the takeover whenever it is safe. It + * increases the chance to see messages when the system is in trouble. + * + * The callback can be called from any context (including NMI). + * Therefore it must avoid usage of any locking and instead rely + * on the console ownership for synchronization. + */ + void (*write_atomic)(struct console *con, struct nbcon_write_context *wctxt); + atomic_t __private nbcon_state; atomic_long_t __private nbcon_seq; struct printk_buffers *pbufs; -- cgit v1.2.3 From 7a16a771890746b4060333d665ebe674945a3cfa Mon Sep 17 00:00:00 2001 From: John Ogness Date: Tue, 20 Aug 2024 08:35:34 +0206 Subject: printk: nbcon: Add callbacks to synchronize with driver Console drivers typically must deal with access to the hardware via user input/output (such as an interactive login shell) and output of kernel messages via printk() calls. To provide the necessary synchronization, usually some driver-specific locking mechanism is used (for example, the port spinlock for uart serial consoles). Until now, usage of this driver-specific locking has been hidden from the printk-subsystem and implemented within the various console callbacks. However, nbcon consoles would need to use it even in the generic code. Add device_lock() and device_unlock() callback which will need to get implemented by nbcon consoles. The callbacks will use whatever synchronization mechanism the driver is using for itself. The minimum requirement is to prevent CPU migration. It would allow a context friendly acquiring of nbcon console ownership in non-emergency and non-panic context. Signed-off-by: John Ogness Reviewed-by: Petr Mladek Link: https://lore.kernel.org/r/20240820063001.36405-9-john.ogness@linutronix.de Signed-off-by: Petr Mladek --- include/linux/console.h | 43 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index 35c64ee3827b..46b3c210b931 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -372,6 +372,49 @@ struct console { */ void (*write_atomic)(struct console *con, struct nbcon_write_context *wctxt); + /** + * @device_lock: + * + * NBCON callback to begin synchronization with driver code. + * + * Console drivers typically must deal with access to the hardware + * via user input/output (such as an interactive login shell) and + * output of kernel messages via printk() calls. This callback is + * called by the printk-subsystem whenever it needs to synchronize + * with hardware access by the driver. It should be implemented to + * use whatever synchronization mechanism the driver is using for + * itself (for example, the port lock for uart serial consoles). + * + * The callback is always called from task context. It may use any + * synchronization method required by the driver. + * + * IMPORTANT: The callback MUST disable migration. The console driver + * may be using a synchronization mechanism that already takes + * care of this (such as spinlocks). Otherwise this function must + * explicitly call migrate_disable(). + * + * The flags argument is provided as a convenience to the driver. It + * will be passed again to device_unlock(). It can be ignored if the + * driver does not need it. + */ + void (*device_lock)(struct console *con, unsigned long *flags); + + /** + * @device_unlock: + * + * NBCON callback to finish synchronization with driver code. + * + * It is the counterpart to device_lock(). + * + * This callback is always called from task context. It must + * appropriately re-enable migration (depending on how device_lock() + * disabled migration). + * + * The flags argument is the value of the same variable that was + * passed to device_lock(). + */ + void (*device_unlock)(struct console *con, unsigned long flags); + atomic_t __private nbcon_state; atomic_long_t __private nbcon_seq; struct printk_buffers *pbufs; -- cgit v1.2.3 From 77e73c0687f5bc884fa1b0cb97aca912bcc01957 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Tue, 20 Aug 2024 08:35:36 +0206 Subject: serial: core: Provide low-level functions to lock port It will be necessary at times for the uart nbcon console drivers to acquire the port lock directly (without the additional nbcon functionality of the port lock wrappers). These are special cases such as the implementation of the device_lock()/device_unlock() callbacks or for internal port lock wrapper synchronization. Provide low-level variants __uart_port_lock_irqsave() and __uart_port_unlock_irqrestore() for this purpose. Signed-off-by: John Ogness Reviewed-by: Petr Mladek Acked-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20240820063001.36405-11-john.ogness@linutronix.de Signed-off-by: Petr Mladek --- include/linux/serial_core.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index aea25eef9a1a..8872cd21e70a 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -590,6 +590,24 @@ struct uart_port { void *private_data; /* generic platform data pointer */ }; +/* + * Only for console->device_lock()/_unlock() callbacks and internal + * port lock wrapper synchronization. + */ +static inline void __uart_port_lock_irqsave(struct uart_port *up, unsigned long *flags) +{ + spin_lock_irqsave(&up->lock, *flags); +} + +/* + * Only for console->device_lock()/_unlock() callbacks and internal + * port lock wrapper synchronization. + */ +static inline void __uart_port_unlock_irqrestore(struct uart_port *up, unsigned long flags) +{ + spin_unlock_irqrestore(&up->lock, flags); +} + /** * uart_port_lock - Lock the UART port * @up: Pointer to UART port structure -- cgit v1.2.3 From eabd4600dafacf9895184259373f2445ff748654 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Tue, 20 Aug 2024 08:35:37 +0206 Subject: serial: core: Introduce wrapper to set @uart_port->cons MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce uart_port_set_cons() as a wrapper to set @cons of a uart_port. The wrapper sets @cons under the port lock in order to prevent @cons from disappearing while another context is holding the port lock. This is necessary for a follow-up commit relating to the port lock wrappers, which rely on @cons not changing between lock and unlock. Signed-off-by: John Ogness Tested-by: Théo Lebrun # EyeQ5, AMBA-PL011 Acked-by: Greg Kroah-Hartman Reviewed-by: Petr Mladek Reviewed-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20240820063001.36405-12-john.ogness@linutronix.de Signed-off-by: Petr Mladek --- drivers/tty/serial/8250/8250_core.c | 6 +++--- drivers/tty/serial/amba-pl011.c | 2 +- drivers/tty/serial/serial_core.c | 16 ++++++++-------- include/linux/serial_core.h | 17 +++++++++++++++++ 4 files changed, 29 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index 29e4b83e0376..5f9f06911795 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -423,11 +423,11 @@ static int univ8250_console_setup(struct console *co, char *options) port = &serial8250_ports[co->index].port; /* link port to console */ - port->cons = co; + uart_port_set_cons(port, co); retval = serial8250_console_setup(port, options, false); if (retval != 0) - port->cons = NULL; + uart_port_set_cons(port, NULL); return retval; } @@ -485,7 +485,7 @@ static int univ8250_console_match(struct console *co, char *name, int idx, continue; co->index = i; - port->cons = co; + uart_port_set_cons(port, co); return serial8250_console_setup(port, options, true); } diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index 8b1644f5411e..7d0134ecd82f 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -2480,7 +2480,7 @@ static int pl011_console_match(struct console *co, char *name, int idx, continue; co->index = i; - port->cons = co; + uart_port_set_cons(port, co); return pl011_console_setup(co, options); } diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 5bea3af46abc..1e3e28e364df 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -3176,8 +3176,15 @@ static int serial_core_add_one_port(struct uart_driver *drv, struct uart_port *u state->uart_port = uport; uport->state = state; + /* + * If this port is in use as a console then the spinlock is already + * initialised. + */ + if (!uart_console_registered(uport)) + uart_port_spin_lock_init(uport); + state->pm_state = UART_PM_STATE_UNDEFINED; - uport->cons = drv->cons; + uart_port_set_cons(uport, drv->cons); uport->minor = drv->tty_driver->minor_start + uport->line; uport->name = kasprintf(GFP_KERNEL, "%s%d", drv->dev_name, drv->tty_driver->name_base + uport->line); @@ -3186,13 +3193,6 @@ static int serial_core_add_one_port(struct uart_driver *drv, struct uart_port *u goto out; } - /* - * If this port is in use as a console then the spinlock is already - * initialised. - */ - if (!uart_console_registered(uport)) - uart_port_spin_lock_init(uport); - if (uport->cons && uport->dev) of_console_check(uport->dev->of_node, uport->cons->name, uport->line); diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 8872cd21e70a..2cf03ff2056a 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -608,6 +608,23 @@ static inline void __uart_port_unlock_irqrestore(struct uart_port *up, unsigned spin_unlock_irqrestore(&up->lock, flags); } +/** + * uart_port_set_cons - Safely set the @cons field for a uart + * @up: The uart port to set + * @con: The new console to set to + * + * This function must be used to set @up->cons. It uses the port lock to + * synchronize with the port lock wrappers in order to ensure that the console + * cannot change or disappear while another context is holding the port lock. + */ +static inline void uart_port_set_cons(struct uart_port *up, struct console *con) +{ + unsigned long flags; + + __uart_port_lock_irqsave(up, &flags); + up->cons = con; + __uart_port_unlock_irqrestore(up, flags); +} /** * uart_port_lock - Lock the UART port * @up: Pointer to UART port structure -- cgit v1.2.3 From dc219d8d858d95549543aa7a41b6e64a0da9e406 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Tue, 20 Aug 2024 08:35:38 +0206 Subject: console: Improve console_srcu_read_flags() comments It was not clear when exactly console_srcu_read_flags() must be used vs. directly reading @console->flags. Refactor and clarify that console_srcu_read_flags() is only needed if the console is registered or the caller is in a context where the registration status of the console may change (due to another context). The function requires the caller holds @console_srcu, which will ensure that the caller sees an appropriate @flags value for the registered console and that exit/cleanup routines will not run if the console is in the process of unregistration. Signed-off-by: John Ogness Reviewed-by: Petr Mladek Link: https://lore.kernel.org/r/20240820063001.36405-13-john.ogness@linutronix.de Signed-off-by: Petr Mladek --- include/linux/console.h | 28 +++++++++++++++++----------- 1 file changed, 17 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index 46b3c210b931..aafe3121b74e 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -446,28 +446,34 @@ extern void console_list_unlock(void) __releases(console_mutex); extern struct hlist_head console_list; /** - * console_srcu_read_flags - Locklessly read the console flags + * console_srcu_read_flags - Locklessly read flags of a possibly registered + * console * @con: struct console pointer of console to read flags from * - * This function provides the necessary READ_ONCE() and data_race() - * notation for locklessly reading the console flags. The READ_ONCE() - * in this function matches the WRITE_ONCE() when @flags are modified - * for registered consoles with console_srcu_write_flags(). + * Locklessly reading @con->flags provides a consistent read value because + * there is at most one CPU modifying @con->flags and that CPU is using only + * read-modify-write operations to do so. * - * Only use this function to read console flags when locklessly - * iterating the console list via srcu. + * Requires console_srcu_read_lock to be held, which implies that @con might + * be a registered console. The purpose of holding console_srcu_read_lock is + * to guarantee that the console state is valid (CON_SUSPENDED/CON_ENABLED) + * and that no exit/cleanup routines will run if the console is currently + * undergoing unregistration. + * + * If the caller is holding the console_list_lock or it is _certain_ that + * @con is not and will not become registered, the caller may read + * @con->flags directly instead. * * Context: Any context. + * Return: The current value of the @con->flags field. */ static inline short console_srcu_read_flags(const struct console *con) { WARN_ON_ONCE(!console_srcu_read_lock_is_held()); /* - * Locklessly reading console->flags provides a consistent - * read value because there is at most one CPU modifying - * console->flags and that CPU is using only read-modify-write - * operations to do so. + * The READ_ONCE() matches the WRITE_ONCE() when @flags are modified + * for registered consoles with console_srcu_write_flags(). */ return data_race(READ_ONCE(con->flags)); } -- cgit v1.2.3 From adf6f37d142e14896115929f3892bbc0a86e25bf Mon Sep 17 00:00:00 2001 From: John Ogness Date: Tue, 20 Aug 2024 08:35:39 +0206 Subject: nbcon: Add API to acquire context for non-printing operations Provide functions nbcon_device_try_acquire() and nbcon_device_release() which will try to acquire the nbcon console ownership with NBCON_PRIO_NORMAL and mark it unsafe for handover/takeover. These functions are to be used together with the device-specific locking when performing non-printing activities on the console device. They will allow synchronization against the atomic_write() callback which will be serialized, for higher priority contexts, only by acquiring the console context ownership. Pitfalls: The API requires to be called in a context with migration disabled because it uses per-CPU variables internally. The context is set unsafe for a takeover all the time. It guarantees full serialization against any atomic_write() caller except for the final flush in panic() which might try an unsafe takeover. Signed-off-by: John Ogness Reviewed-by: Petr Mladek Link: https://lore.kernel.org/r/20240820063001.36405-14-john.ogness@linutronix.de Signed-off-by: Petr Mladek --- include/linux/console.h | 2 ++ include/linux/printk.h | 14 ++++++++++++ kernel/printk/nbcon.c | 58 ++++++++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 73 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index aafe3121b74e..3706f944de46 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -322,6 +322,7 @@ struct nbcon_write_context { * * @nbcon_state: State for nbcon consoles * @nbcon_seq: Sequence number of the next record for nbcon to print + * @nbcon_device_ctxt: Context available for non-printing operations * @pbufs: Pointer to nbcon private buffer */ struct console { @@ -417,6 +418,7 @@ struct console { atomic_t __private nbcon_state; atomic_long_t __private nbcon_seq; + struct nbcon_context __private nbcon_device_ctxt; struct printk_buffers *pbufs; }; diff --git a/include/linux/printk.h b/include/linux/printk.h index eee8e97da681..9687089f5ace 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -9,6 +9,8 @@ #include #include +struct console; + extern const char linux_banner[]; extern const char linux_proc_banner[]; @@ -198,6 +200,8 @@ extern asmlinkage void dump_stack_lvl(const char *log_lvl) __cold; extern asmlinkage void dump_stack(void) __cold; void printk_trigger_flush(void); void console_try_replay_all(void); +extern bool nbcon_device_try_acquire(struct console *con); +extern void nbcon_device_release(struct console *con); #else static inline __printf(1, 0) int vprintk(const char *s, va_list args) @@ -280,6 +284,16 @@ static inline void printk_trigger_flush(void) static inline void console_try_replay_all(void) { } + +static inline bool nbcon_device_try_acquire(struct console *con) +{ + return false; +} + +static inline void nbcon_device_release(struct console *con) +{ +} + #endif bool this_cpu_in_panic(void); diff --git a/kernel/printk/nbcon.c b/kernel/printk/nbcon.c index f279f839741a..61f0ae6a4809 100644 --- a/kernel/printk/nbcon.c +++ b/kernel/printk/nbcon.c @@ -5,7 +5,9 @@ #include #include #include +#include #include +#include #include "internal.h" /* * Printk console printing implementation for consoles which does not depend @@ -546,6 +548,7 @@ static struct printk_buffers panic_nbcon_pbufs; * nbcon_context_try_acquire - Try to acquire nbcon console * @ctxt: The context of the caller * + * Context: Under @ctxt->con->device_lock() or local_irq_save(). * Return: True if the console was acquired. False otherwise. * * If the caller allowed an unsafe hostile takeover, on success the @@ -553,7 +556,6 @@ static struct printk_buffers panic_nbcon_pbufs; * in an unsafe state. Otherwise, on success the caller may assume * the console is not in an unsafe state. */ -__maybe_unused static bool nbcon_context_try_acquire(struct nbcon_context *ctxt) { unsigned int cpu = smp_processor_id(); @@ -1011,3 +1013,57 @@ void nbcon_free(struct console *con) con->pbufs = NULL; } + +/** + * nbcon_device_try_acquire - Try to acquire nbcon console and enter unsafe + * section + * @con: The nbcon console to acquire + * + * Context: Under the locking mechanism implemented in + * @con->device_lock() including disabling migration. + * Return: True if the console was acquired. False otherwise. + * + * Console drivers will usually use their own internal synchronization + * mechasism to synchronize between console printing and non-printing + * activities (such as setting baud rates). However, nbcon console drivers + * supporting atomic consoles may also want to mark unsafe sections when + * performing non-printing activities in order to synchronize against their + * atomic_write() callback. + * + * This function acquires the nbcon console using priority NBCON_PRIO_NORMAL + * and marks it unsafe for handover/takeover. + */ +bool nbcon_device_try_acquire(struct console *con) +{ + struct nbcon_context *ctxt = &ACCESS_PRIVATE(con, nbcon_device_ctxt); + + cant_migrate(); + + memset(ctxt, 0, sizeof(*ctxt)); + ctxt->console = con; + ctxt->prio = NBCON_PRIO_NORMAL; + + if (!nbcon_context_try_acquire(ctxt)) + return false; + + if (!nbcon_context_enter_unsafe(ctxt)) + return false; + + return true; +} +EXPORT_SYMBOL_GPL(nbcon_device_try_acquire); + +/** + * nbcon_device_release - Exit unsafe section and release the nbcon console + * @con: The nbcon console acquired in nbcon_device_try_acquire() + */ +void nbcon_device_release(struct console *con) +{ + struct nbcon_context *ctxt = &ACCESS_PRIVATE(con, nbcon_device_ctxt); + + if (!nbcon_context_exit_unsafe(ctxt)) + return; + + nbcon_context_release(ctxt); +} +EXPORT_SYMBOL_GPL(nbcon_device_release); -- cgit v1.2.3 From 4126f149c48b2ae757d11ea24675f7071ab22ebf Mon Sep 17 00:00:00 2001 From: John Ogness Date: Tue, 20 Aug 2024 08:35:40 +0206 Subject: serial: core: Acquire nbcon context in port->lock wrapper Currently the port->lock wrappers uart_port_lock(), uart_port_unlock() (and their variants) only lock/unlock the spin_lock. If the port is an nbcon console that has implemented the write_atomic() callback, the wrappers must also acquire/release the console context and mark the region as unsafe. This allows general port->lock synchronization to be synchronized against the nbcon write_atomic() callback. Note that __uart_port_using_nbcon() relies on the port->lock being held while a console is added and removed from the console list (i.e. all uart nbcon drivers *must* take the port->lock in their device_lock() callbacks). Signed-off-by: John Ogness Acked-by: Greg Kroah-Hartman Reviewed-by: Petr Mladek Link: https://lore.kernel.org/r/20240820063001.36405-15-john.ogness@linutronix.de Signed-off-by: Petr Mladek --- include/linux/serial_core.h | 82 +++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 80 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 2cf03ff2056a..4ab65874a850 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -11,6 +11,8 @@ #include #include #include +#include +#include #include #include #include @@ -625,6 +627,60 @@ static inline void uart_port_set_cons(struct uart_port *up, struct console *con) up->cons = con; __uart_port_unlock_irqrestore(up, flags); } + +/* Only for internal port lock wrapper usage. */ +static inline bool __uart_port_using_nbcon(struct uart_port *up) +{ + lockdep_assert_held_once(&up->lock); + + if (likely(!uart_console(up))) + return false; + + /* + * @up->cons is only modified under the port lock. Therefore it is + * certain that it cannot disappear here. + * + * @up->cons->node is added/removed from the console list under the + * port lock. Therefore it is certain that the registration status + * cannot change here, thus @up->cons->flags can be read directly. + */ + if (hlist_unhashed_lockless(&up->cons->node) || + !(up->cons->flags & CON_NBCON) || + !up->cons->write_atomic) { + return false; + } + + return true; +} + +/* Only for internal port lock wrapper usage. */ +static inline bool __uart_port_nbcon_try_acquire(struct uart_port *up) +{ + if (!__uart_port_using_nbcon(up)) + return true; + + return nbcon_device_try_acquire(up->cons); +} + +/* Only for internal port lock wrapper usage. */ +static inline void __uart_port_nbcon_acquire(struct uart_port *up) +{ + if (!__uart_port_using_nbcon(up)) + return; + + while (!nbcon_device_try_acquire(up->cons)) + cpu_relax(); +} + +/* Only for internal port lock wrapper usage. */ +static inline void __uart_port_nbcon_release(struct uart_port *up) +{ + if (!__uart_port_using_nbcon(up)) + return; + + nbcon_device_release(up->cons); +} + /** * uart_port_lock - Lock the UART port * @up: Pointer to UART port structure @@ -632,6 +688,7 @@ static inline void uart_port_set_cons(struct uart_port *up, struct console *con) static inline void uart_port_lock(struct uart_port *up) { spin_lock(&up->lock); + __uart_port_nbcon_acquire(up); } /** @@ -641,6 +698,7 @@ static inline void uart_port_lock(struct uart_port *up) static inline void uart_port_lock_irq(struct uart_port *up) { spin_lock_irq(&up->lock); + __uart_port_nbcon_acquire(up); } /** @@ -651,6 +709,7 @@ static inline void uart_port_lock_irq(struct uart_port *up) static inline void uart_port_lock_irqsave(struct uart_port *up, unsigned long *flags) { spin_lock_irqsave(&up->lock, *flags); + __uart_port_nbcon_acquire(up); } /** @@ -661,7 +720,15 @@ static inline void uart_port_lock_irqsave(struct uart_port *up, unsigned long *f */ static inline bool uart_port_trylock(struct uart_port *up) { - return spin_trylock(&up->lock); + if (!spin_trylock(&up->lock)) + return false; + + if (!__uart_port_nbcon_try_acquire(up)) { + spin_unlock(&up->lock); + return false; + } + + return true; } /** @@ -673,7 +740,15 @@ static inline bool uart_port_trylock(struct uart_port *up) */ static inline bool uart_port_trylock_irqsave(struct uart_port *up, unsigned long *flags) { - return spin_trylock_irqsave(&up->lock, *flags); + if (!spin_trylock_irqsave(&up->lock, *flags)) + return false; + + if (!__uart_port_nbcon_try_acquire(up)) { + spin_unlock_irqrestore(&up->lock, *flags); + return false; + } + + return true; } /** @@ -682,6 +757,7 @@ static inline bool uart_port_trylock_irqsave(struct uart_port *up, unsigned long */ static inline void uart_port_unlock(struct uart_port *up) { + __uart_port_nbcon_release(up); spin_unlock(&up->lock); } @@ -691,6 +767,7 @@ static inline void uart_port_unlock(struct uart_port *up) */ static inline void uart_port_unlock_irq(struct uart_port *up) { + __uart_port_nbcon_release(up); spin_unlock_irq(&up->lock); } @@ -701,6 +778,7 @@ static inline void uart_port_unlock_irq(struct uart_port *up) */ static inline void uart_port_unlock_irqrestore(struct uart_port *up, unsigned long flags) { + __uart_port_nbcon_release(up); spin_unlock_irqrestore(&up->lock, flags); } -- cgit v1.2.3 From 5dde3b7354133846079fa51e55e74ef90a836759 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Tue, 20 Aug 2024 08:35:52 +0206 Subject: printk: nbcon: Add unsafe flushing on panic Add nbcon_atomic_flush_unsafe() to flush all nbcon consoles using the write_atomic() callback and allowing unsafe hostile takeovers. Call this at the end of panic() as a final attempt to flush any pending messages. Note that legacy consoles use unsafe methods for flushing from the beginning of panic (see bust_spinlocks()). Therefore, systems using both legacy and nbcon consoles may still fail to see panic messages due to unsafe legacy console usage. Signed-off-by: John Ogness Reviewed-by: Petr Mladek Link: https://lore.kernel.org/r/20240820063001.36405-27-john.ogness@linutronix.de Signed-off-by: Petr Mladek --- include/linux/printk.h | 5 +++++ kernel/panic.c | 1 + kernel/printk/nbcon.c | 32 +++++++++++++++++++++++++------- 3 files changed, 31 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index 9687089f5ace..2e083f01f8a3 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -202,6 +202,7 @@ void printk_trigger_flush(void); void console_try_replay_all(void); extern bool nbcon_device_try_acquire(struct console *con); extern void nbcon_device_release(struct console *con); +void nbcon_atomic_flush_unsafe(void); #else static inline __printf(1, 0) int vprintk(const char *s, va_list args) @@ -294,6 +295,10 @@ static inline void nbcon_device_release(struct console *con) { } +static inline void nbcon_atomic_flush_unsafe(void) +{ +} + #endif bool this_cpu_in_panic(void); diff --git a/kernel/panic.c b/kernel/panic.c index 2a0449144f82..df37c913b010 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -463,6 +463,7 @@ void panic(const char *fmt, ...) * Explicitly flush the kernel log buffer one last time. */ console_flush_on_panic(CONSOLE_FLUSH_PENDING); + nbcon_atomic_flush_unsafe(); local_irq_enable(); for (i = 0; ; i += PANIC_TIMER_STEP) { diff --git a/kernel/printk/nbcon.c b/kernel/printk/nbcon.c index 269aeed18064..afdb16c1c733 100644 --- a/kernel/printk/nbcon.c +++ b/kernel/printk/nbcon.c @@ -1083,6 +1083,7 @@ bool nbcon_legacy_emit_next_record(struct console *con, bool *handover, * write_atomic() callback * @con: The nbcon console to flush * @stop_seq: Flush up until this record + * @allow_unsafe_takeover: True, to allow unsafe hostile takeovers * * Return: 0 if @con was flushed up to @stop_seq Otherwise, error code on * failure. @@ -1101,7 +1102,8 @@ bool nbcon_legacy_emit_next_record(struct console *con, bool *handover, * returned, it cannot be expected that the unfinalized record will become * available. */ -static int __nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq) +static int __nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq, + bool allow_unsafe_takeover) { struct nbcon_write_context wctxt = { }; struct nbcon_context *ctxt = &ACCESS_PRIVATE(&wctxt, ctxt); @@ -1110,6 +1112,7 @@ static int __nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq) ctxt->console = con; ctxt->spinwait_max_us = 2000; ctxt->prio = nbcon_get_default_prio(); + ctxt->allow_unsafe_takeover = allow_unsafe_takeover; if (!nbcon_context_try_acquire(ctxt)) return -EPERM; @@ -1140,13 +1143,15 @@ static int __nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq) * write_atomic() callback * @con: The nbcon console to flush * @stop_seq: Flush up until this record + * @allow_unsafe_takeover: True, to allow unsafe hostile takeovers * * This will stop flushing before @stop_seq if another context has ownership. * That context is then responsible for the flushing. Likewise, if new records * are added while this context was flushing and there is no other context * to handle the printing, this context must also flush those records. */ -static void nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq) +static void nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq, + bool allow_unsafe_takeover) { unsigned long flags; int err; @@ -1160,7 +1165,7 @@ again: */ local_irq_save(flags); - err = __nbcon_atomic_flush_pending_con(con, stop_seq); + err = __nbcon_atomic_flush_pending_con(con, stop_seq, allow_unsafe_takeover); local_irq_restore(flags); @@ -1190,8 +1195,9 @@ again: * __nbcon_atomic_flush_pending - Flush all nbcon consoles using their * write_atomic() callback * @stop_seq: Flush up until this record + * @allow_unsafe_takeover: True, to allow unsafe hostile takeovers */ -static void __nbcon_atomic_flush_pending(u64 stop_seq) +static void __nbcon_atomic_flush_pending(u64 stop_seq, bool allow_unsafe_takeover) { struct console *con; int cookie; @@ -1209,7 +1215,7 @@ static void __nbcon_atomic_flush_pending(u64 stop_seq) if (nbcon_seq_read(con) >= stop_seq) continue; - nbcon_atomic_flush_pending_con(con, stop_seq); + nbcon_atomic_flush_pending_con(con, stop_seq, allow_unsafe_takeover); } console_srcu_read_unlock(cookie); } @@ -1225,7 +1231,19 @@ static void __nbcon_atomic_flush_pending(u64 stop_seq) */ void nbcon_atomic_flush_pending(void) { - __nbcon_atomic_flush_pending(prb_next_reserve_seq(prb)); + __nbcon_atomic_flush_pending(prb_next_reserve_seq(prb), false); +} + +/** + * nbcon_atomic_flush_unsafe - Flush all nbcon consoles using their + * write_atomic() callback and allowing unsafe hostile takeovers + * + * Flush the backlog up through the currently newest record. Unsafe hostile + * takeovers will be performed, if necessary. + */ +void nbcon_atomic_flush_unsafe(void) +{ + __nbcon_atomic_flush_pending(prb_next_reserve_seq(prb), true); } /** @@ -1342,7 +1360,7 @@ void nbcon_device_release(struct console *con) if (console_is_usable(con, console_srcu_read_flags(con)) && prb_read_valid(prb, nbcon_seq_read(con), NULL)) { if (!have_boot_console) { - __nbcon_atomic_flush_pending_con(con, prb_next_reserve_seq(prb)); + __nbcon_atomic_flush_pending_con(con, prb_next_reserve_seq(prb), false); } else if (!is_printk_legacy_deferred()) { if (console_trylock()) console_unlock(); -- cgit v1.2.3 From e35a8884270bae11196eedf3b0a5bf22619f11f2 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Tue, 20 Aug 2024 08:35:55 +0206 Subject: printk: Coordinate direct printing in panic If legacy and nbcon consoles are registered and the nbcon consoles are allowed to flush (i.e. no boot consoles registered), the legacy consoles will no longer perform direct printing on the panic CPU until after the backtrace has been stored. This will give the safe nbcon consoles a chance to print the panic messages before allowing the unsafe legacy consoles to print. If no nbcon consoles are registered or they are not allowed to flush because boot consoles are registered, there is no change in behavior (i.e. legacy consoles will always attempt to print from the printk() caller context). Signed-off-by: John Ogness Reviewed-by: Petr Mladek Link: https://lore.kernel.org/r/20240820063001.36405-30-john.ogness@linutronix.de Signed-off-by: Petr Mladek --- include/linux/printk.h | 5 +++++ kernel/panic.c | 2 ++ kernel/printk/internal.h | 1 + kernel/printk/printk.c | 55 ++++++++++++++++++++++++++++++++++++++++++------ 4 files changed, 56 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index 2e083f01f8a3..eca9bb2ee637 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -200,6 +200,7 @@ extern asmlinkage void dump_stack_lvl(const char *log_lvl) __cold; extern asmlinkage void dump_stack(void) __cold; void printk_trigger_flush(void); void console_try_replay_all(void); +void printk_legacy_allow_panic_sync(void); extern bool nbcon_device_try_acquire(struct console *con); extern void nbcon_device_release(struct console *con); void nbcon_atomic_flush_unsafe(void); @@ -286,6 +287,10 @@ static inline void console_try_replay_all(void) { } +static inline void printk_legacy_allow_panic_sync(void) +{ +} + static inline bool nbcon_device_try_acquire(struct console *con) { return false; diff --git a/kernel/panic.c b/kernel/panic.c index df37c913b010..93096d5abcc7 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -374,6 +374,8 @@ void panic(const char *fmt, ...) panic_other_cpus_shutdown(_crash_kexec_post_notifiers); + printk_legacy_allow_panic_sync(); + /* * Run any panic handlers, including those that might need to * add information to the kmsg dump output. diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h index 7679e18f24b3..6b61350a3026 100644 --- a/kernel/printk/internal.h +++ b/kernel/printk/internal.h @@ -154,6 +154,7 @@ static inline bool console_is_usable(struct console *con, short flags) { return #endif /* CONFIG_PRINTK */ extern bool have_boot_console; +extern bool legacy_allow_panic_sync; extern struct printk_buffers printk_shared_pbufs; diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index e30107d216a5..fc3f8970eea2 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -471,7 +471,9 @@ static DEFINE_MUTEX(syslog_lock); static bool have_legacy_console; /* - * Specifies if an nbcon console is registered. + * Specifies if an nbcon console is registered. If nbcon consoles are present, + * synchronous printing of legacy consoles will not occur during panic until + * the backtrace has been stored to the ringbuffer. */ static bool have_nbcon_console; @@ -483,6 +485,9 @@ static bool have_nbcon_console; */ bool have_boot_console; +/* See printk_legacy_allow_panic_sync() for details. */ +bool legacy_allow_panic_sync; + /* * Specifies if the console lock/unlock dance is needed for console * printing. If @have_boot_console is true, the nbcon consoles will @@ -2330,12 +2335,28 @@ out: return ret; } +/* + * This acts as a one-way switch to allow legacy consoles to print from + * the printk() caller context on a panic CPU. It also attempts to flush + * the legacy consoles in this context. + */ +void printk_legacy_allow_panic_sync(void) +{ + legacy_allow_panic_sync = true; + + if (printing_via_unlock && !is_printk_legacy_deferred()) { + if (console_trylock()) + console_unlock(); + } +} + asmlinkage int vprintk_emit(int facility, int level, const struct dev_printk_info *dev_info, const char *fmt, va_list args) { + bool do_trylock_unlock = printing_via_unlock; + bool defer_legacy = false; int printed_len; - bool in_sched = false; /* Suppress unimportant messages after panic happens */ if (unlikely(suppress_printk)) @@ -2349,17 +2370,35 @@ asmlinkage int vprintk_emit(int facility, int level, if (other_cpu_in_panic() && !panic_triggering_all_cpu_backtrace) return 0; + /* If called from the scheduler, we can not call up(). */ if (level == LOGLEVEL_SCHED) { level = LOGLEVEL_DEFAULT; - in_sched = true; + defer_legacy = do_trylock_unlock; + do_trylock_unlock = false; } printk_delay(level); printed_len = vprintk_store(facility, level, dev_info, fmt, args); - /* If called from the scheduler, we can not call up(). */ - if (!in_sched && printing_via_unlock) { + if (have_nbcon_console && !have_boot_console) { + nbcon_atomic_flush_pending(); + + /* + * In panic, the legacy consoles are not allowed to print from + * the printk calling context unless explicitly allowed. This + * gives the safe nbcon consoles a chance to print out all the + * panic messages first. This restriction only applies if + * there are nbcon consoles registered and they are allowed to + * flush. + */ + if (this_cpu_in_panic() && !legacy_allow_panic_sync) { + do_trylock_unlock = false; + defer_legacy = false; + } + } + + if (do_trylock_unlock) { /* * The caller may be holding system-critical or * timing-sensitive locks. Disable preemption during @@ -2379,7 +2418,7 @@ asmlinkage int vprintk_emit(int facility, int level, preempt_enable(); } - if (in_sched && printing_via_unlock) + if (defer_legacy) defer_console_output(); else wake_up_klogd(); @@ -3292,7 +3331,9 @@ void console_flush_on_panic(enum con_flush_mode mode) if (!have_boot_console) nbcon_atomic_flush_pending(); - console_flush_all(false, &next_seq, &handover); + /* Flush legacy consoles once allowed, even when dangerous. */ + if (legacy_allow_panic_sync) + console_flush_all(false, &next_seq, &handover); } /* -- cgit v1.2.3 From ecb5e1aa82c86642ec1eaafefd4e317dfba3a238 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 20 Aug 2024 08:35:57 +0206 Subject: printk: nbcon: Implement emergency sections In emergency situations (something has gone wrong but the system continues to operate), usually important information (such as a backtrace) is generated via printk(). This information should be pushed out to the consoles ASAP. Add per-CPU emergency nesting tracking because an emergency can arise while in an emergency situation. Add functions to mark the beginning and end of emergency sections where the urgent messages are generated. Perform direct console flushing at the emergency priority if the current CPU is in an emergency state and it is safe to do so. Note that the emergency state is not system-wide. While one CPU is in an emergency state, another CPU may attempt to print console messages at normal priority. Also note that printk() already attempts to flush consoles in the caller context for normal priority. However, follow-up changes will introduce printing kthreads, in which case the normal priority printk() calls will offload to the kthreads. Co-developed-by: John Ogness Signed-off-by: John Ogness Signed-off-by: Thomas Gleixner (Intel) Reviewed-by: Petr Mladek Link: https://lore.kernel.org/r/20240820063001.36405-32-john.ogness@linutronix.de Signed-off-by: Petr Mladek --- include/linux/console.h | 4 +++ kernel/printk/internal.h | 1 + kernel/printk/nbcon.c | 75 +++++++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 79 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index 3706f944de46..9a13f91b0c43 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -553,10 +553,14 @@ static inline bool console_is_registered(const struct console *con) hlist_for_each_entry(con, &console_list, node) #ifdef CONFIG_PRINTK +extern void nbcon_cpu_emergency_enter(void); +extern void nbcon_cpu_emergency_exit(void); extern bool nbcon_can_proceed(struct nbcon_write_context *wctxt); extern bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt); extern bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt); #else +static inline void nbcon_cpu_emergency_enter(void) { } +static inline void nbcon_cpu_emergency_exit(void) { } static inline bool nbcon_can_proceed(struct nbcon_write_context *wctxt) { return false; } static inline bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt) { return false; } static inline bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt) { return false; } diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h index ba2e0f1940bd..8e36d8695f81 100644 --- a/kernel/printk/internal.h +++ b/kernel/printk/internal.h @@ -182,6 +182,7 @@ static inline void printk_get_console_flush_type(struct console_flush_type *ft) switch (nbcon_get_default_prio()) { case NBCON_PRIO_NORMAL: + case NBCON_PRIO_EMERGENCY: if (have_nbcon_console && !have_boot_console) ft->nbcon_atomic = true; diff --git a/kernel/printk/nbcon.c b/kernel/printk/nbcon.c index 18488d6c17c0..92ac5c590927 100644 --- a/kernel/printk/nbcon.c +++ b/kernel/printk/nbcon.c @@ -972,6 +972,36 @@ update_con: return nbcon_context_exit_unsafe(ctxt); } +/* Track the nbcon emergency nesting per CPU. */ +static DEFINE_PER_CPU(unsigned int, nbcon_pcpu_emergency_nesting); +static unsigned int early_nbcon_pcpu_emergency_nesting __initdata; + +/** + * nbcon_get_cpu_emergency_nesting - Get the per CPU emergency nesting pointer + * + * Context: For reading, any context. For writing, any context which could + * not be migrated to another CPU. + * Return: Either a pointer to the per CPU emergency nesting counter of + * the current CPU or to the init data during early boot. + * + * The function is safe for reading per-CPU variables in any context because + * preemption is disabled if the current CPU is in the emergency state. See + * also nbcon_cpu_emergency_enter(). + */ +static __ref unsigned int *nbcon_get_cpu_emergency_nesting(void) +{ + /* + * The value of __printk_percpu_data_ready gets set in normal + * context and before SMP initialization. As a result it could + * never change while inside an nbcon emergency section. + */ + if (!printk_percpu_data_ready()) + return &early_nbcon_pcpu_emergency_nesting; + + /* Open code this_cpu_ptr() without checking migration. */ + return per_cpu_ptr(&nbcon_pcpu_emergency_nesting, raw_smp_processor_id()); +} + /** * nbcon_get_default_prio - The appropriate nbcon priority to use for nbcon * printing on the current CPU @@ -981,13 +1011,20 @@ update_con: * context for printing. * * The function is safe for reading per-CPU data in any context because - * preemption is disabled if the current CPU is in the panic state. + * preemption is disabled if the current CPU is in the emergency or panic + * state. */ enum nbcon_prio nbcon_get_default_prio(void) { + unsigned int *cpu_emergency_nesting; + if (this_cpu_in_panic()) return NBCON_PRIO_PANIC; + cpu_emergency_nesting = nbcon_get_cpu_emergency_nesting(); + if (*cpu_emergency_nesting) + return NBCON_PRIO_EMERGENCY; + return NBCON_PRIO_NORMAL; } @@ -1246,6 +1283,42 @@ void nbcon_atomic_flush_unsafe(void) __nbcon_atomic_flush_pending(prb_next_reserve_seq(prb), true); } +/** + * nbcon_cpu_emergency_enter - Enter an emergency section where printk() + * messages for that CPU are flushed directly + * + * Context: Any context. Disables preemption. + * + * When within an emergency section, printk() calls will attempt to flush any + * pending messages in the ringbuffer. + */ +void nbcon_cpu_emergency_enter(void) +{ + unsigned int *cpu_emergency_nesting; + + preempt_disable(); + + cpu_emergency_nesting = nbcon_get_cpu_emergency_nesting(); + (*cpu_emergency_nesting)++; +} + +/** + * nbcon_cpu_emergency_exit - Exit an emergency section + * + * Context: Within an emergency section. Enables preemption. + */ +void nbcon_cpu_emergency_exit(void) +{ + unsigned int *cpu_emergency_nesting; + + cpu_emergency_nesting = nbcon_get_cpu_emergency_nesting(); + + if (!WARN_ON_ONCE(*cpu_emergency_nesting == 0)) + (*cpu_emergency_nesting)--; + + preempt_enable(); +} + /** * nbcon_alloc - Allocate and init the nbcon console specific data * @con: Console to initialize -- cgit v1.2.3 From 3568affcddd68743e25aa3ec1647d9b82797757b Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Tue, 20 Aug 2024 13:29:30 -0700 Subject: soc: qcom: pmic_glink: Fix race during initialization As pointed out by Stephen Boyd it is possible that during initialization of the pmic_glink child drivers, the protection-domain notifiers fires, and the associated work is scheduled, before the client registration returns and as a result the local "client" pointer has been initialized. The outcome of this is a NULL pointer dereference as the "client" pointer is blindly dereferenced. Timeline provided by Stephen: CPU0 CPU1 ---- ---- ucsi->client = NULL; devm_pmic_glink_register_client() client->pdr_notify(client->priv, pg->client_state) pmic_glink_ucsi_pdr_notify() schedule_work(&ucsi->register_work) pmic_glink_ucsi_register() ucsi_register() pmic_glink_ucsi_read_version() pmic_glink_ucsi_read() pmic_glink_ucsi_read() pmic_glink_send(ucsi->client) ucsi->client = client // Too late! This code is identical across the altmode, battery manager and usci child drivers. Resolve this by splitting the allocation of the "client" object and the registration thereof into two operations. This only happens if the protection domain registry is populated at the time of registration, which by the introduction of commit '1ebcde047c54 ("soc: qcom: add pd-mapper implementation")' became much more likely. Reported-by: Amit Pundir Closes: https://lore.kernel.org/all/CAMi1Hd2_a7TjA7J9ShrAbNOd_CoZ3D87twmO5t+nZxC9sX18tA@mail.gmail.com/ Reported-by: Johan Hovold Closes: https://lore.kernel.org/all/ZqiyLvP0gkBnuekL@hovoldconsulting.com/ Reported-by: Stephen Boyd Closes: https://lore.kernel.org/all/CAE-0n52JgfCBWiFQyQWPji8cq_rCsviBpW-m72YitgNfdaEhQg@mail.gmail.com/ Fixes: 58ef4ece1e41 ("soc: qcom: pmic_glink: Introduce base PMIC GLINK driver") Cc: stable@vger.kernel.org Reviewed-by: Heikki Krogerus Reviewed-by: Neil Armstrong Tested-by: Amit Pundir Reviewed-by: Johan Hovold Acked-by: Sebastian Reichel Tested-by: Johan Hovold Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20240820-pmic-glink-v6-11-races-v3-1-eec53c750a04@quicinc.com Signed-off-by: Bjorn Andersson --- drivers/power/supply/qcom_battmgr.c | 16 ++++++++++------ drivers/soc/qcom/pmic_glink.c | 28 ++++++++++++++++++---------- drivers/soc/qcom/pmic_glink_altmode.c | 17 +++++++++++------ drivers/usb/typec/ucsi/ucsi_glink.c | 16 ++++++++++------ include/linux/soc/qcom/pmic_glink.h | 11 ++++++----- 5 files changed, 55 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/drivers/power/supply/qcom_battmgr.c b/drivers/power/supply/qcom_battmgr.c index 46f36dcb185c..7cf19a39d986 100644 --- a/drivers/power/supply/qcom_battmgr.c +++ b/drivers/power/supply/qcom_battmgr.c @@ -1385,12 +1385,16 @@ static int qcom_battmgr_probe(struct auxiliary_device *adev, "failed to register wireless charing power supply\n"); } - battmgr->client = devm_pmic_glink_register_client(dev, - PMIC_GLINK_OWNER_BATTMGR, - qcom_battmgr_callback, - qcom_battmgr_pdr_notify, - battmgr); - return PTR_ERR_OR_ZERO(battmgr->client); + battmgr->client = devm_pmic_glink_client_alloc(dev, PMIC_GLINK_OWNER_BATTMGR, + qcom_battmgr_callback, + qcom_battmgr_pdr_notify, + battmgr); + if (IS_ERR(battmgr->client)) + return PTR_ERR(battmgr->client); + + pmic_glink_client_register(battmgr->client); + + return 0; } static const struct auxiliary_device_id qcom_battmgr_id_table[] = { diff --git a/drivers/soc/qcom/pmic_glink.c b/drivers/soc/qcom/pmic_glink.c index 9ebc0ba35947..53b176d04fbd 100644 --- a/drivers/soc/qcom/pmic_glink.c +++ b/drivers/soc/qcom/pmic_glink.c @@ -66,15 +66,14 @@ static void _devm_pmic_glink_release_client(struct device *dev, void *res) spin_unlock_irqrestore(&pg->client_lock, flags); } -struct pmic_glink_client *devm_pmic_glink_register_client(struct device *dev, - unsigned int id, - void (*cb)(const void *, size_t, void *), - void (*pdr)(void *, int), - void *priv) +struct pmic_glink_client *devm_pmic_glink_client_alloc(struct device *dev, + unsigned int id, + void (*cb)(const void *, size_t, void *), + void (*pdr)(void *, int), + void *priv) { struct pmic_glink_client *client; struct pmic_glink *pg = dev_get_drvdata(dev->parent); - unsigned long flags; client = devres_alloc(_devm_pmic_glink_release_client, sizeof(*client), GFP_KERNEL); if (!client) @@ -85,6 +84,18 @@ struct pmic_glink_client *devm_pmic_glink_register_client(struct device *dev, client->cb = cb; client->pdr_notify = pdr; client->priv = priv; + INIT_LIST_HEAD(&client->node); + + devres_add(dev, client); + + return client; +} +EXPORT_SYMBOL_GPL(devm_pmic_glink_client_alloc); + +void pmic_glink_client_register(struct pmic_glink_client *client) +{ + struct pmic_glink *pg = client->pg; + unsigned long flags; mutex_lock(&pg->state_lock); spin_lock_irqsave(&pg->client_lock, flags); @@ -95,11 +106,8 @@ struct pmic_glink_client *devm_pmic_glink_register_client(struct device *dev, spin_unlock_irqrestore(&pg->client_lock, flags); mutex_unlock(&pg->state_lock); - devres_add(dev, client); - - return client; } -EXPORT_SYMBOL_GPL(devm_pmic_glink_register_client); +EXPORT_SYMBOL_GPL(pmic_glink_client_register); int pmic_glink_send(struct pmic_glink_client *client, void *data, size_t len) { diff --git a/drivers/soc/qcom/pmic_glink_altmode.c b/drivers/soc/qcom/pmic_glink_altmode.c index 1e0808b3cb93..463b1c528831 100644 --- a/drivers/soc/qcom/pmic_glink_altmode.c +++ b/drivers/soc/qcom/pmic_glink_altmode.c @@ -520,12 +520,17 @@ static int pmic_glink_altmode_probe(struct auxiliary_device *adev, return ret; } - altmode->client = devm_pmic_glink_register_client(dev, - altmode->owner_id, - pmic_glink_altmode_callback, - pmic_glink_altmode_pdr_notify, - altmode); - return PTR_ERR_OR_ZERO(altmode->client); + altmode->client = devm_pmic_glink_client_alloc(dev, + altmode->owner_id, + pmic_glink_altmode_callback, + pmic_glink_altmode_pdr_notify, + altmode); + if (IS_ERR(altmode->client)) + return PTR_ERR(altmode->client); + + pmic_glink_client_register(altmode->client); + + return 0; } static const struct auxiliary_device_id pmic_glink_altmode_id_table[] = { diff --git a/drivers/usb/typec/ucsi/ucsi_glink.c b/drivers/usb/typec/ucsi/ucsi_glink.c index 16c328497e0b..f6f4fae40399 100644 --- a/drivers/usb/typec/ucsi/ucsi_glink.c +++ b/drivers/usb/typec/ucsi/ucsi_glink.c @@ -367,12 +367,16 @@ static int pmic_glink_ucsi_probe(struct auxiliary_device *adev, ucsi->port_orientation[port] = desc; } - ucsi->client = devm_pmic_glink_register_client(dev, - PMIC_GLINK_OWNER_USBC, - pmic_glink_ucsi_callback, - pmic_glink_ucsi_pdr_notify, - ucsi); - return PTR_ERR_OR_ZERO(ucsi->client); + ucsi->client = devm_pmic_glink_client_alloc(dev, PMIC_GLINK_OWNER_USBC, + pmic_glink_ucsi_callback, + pmic_glink_ucsi_pdr_notify, + ucsi); + if (IS_ERR(ucsi->client)) + return PTR_ERR(ucsi->client); + + pmic_glink_client_register(ucsi->client); + + return 0; } static void pmic_glink_ucsi_remove(struct auxiliary_device *adev) diff --git a/include/linux/soc/qcom/pmic_glink.h b/include/linux/soc/qcom/pmic_glink.h index fd124aa18c81..7cddf1027752 100644 --- a/include/linux/soc/qcom/pmic_glink.h +++ b/include/linux/soc/qcom/pmic_glink.h @@ -23,10 +23,11 @@ struct pmic_glink_hdr { int pmic_glink_send(struct pmic_glink_client *client, void *data, size_t len); -struct pmic_glink_client *devm_pmic_glink_register_client(struct device *dev, - unsigned int id, - void (*cb)(const void *, size_t, void *), - void (*pdr)(void *, int), - void *priv); +struct pmic_glink_client *devm_pmic_glink_client_alloc(struct device *dev, + unsigned int id, + void (*cb)(const void *, size_t, void *), + void (*pdr)(void *, int), + void *priv); +void pmic_glink_client_register(struct pmic_glink_client *client); #endif -- cgit v1.2.3 From d156263e247c334a8872578118e0709ed63c4806 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 21 Aug 2024 06:37:39 -1000 Subject: workqueue: Fix another htmldocs build warning Fix htmldocs build warning introduced by 9b59a85a84dc ("workqueue: Don't call va_start / va_end twice"). Signed-off-by: Tejun Heo Reported-by: Stephen Rothwell Cc: Matthew Brost --- include/linux/workqueue.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index f3cc15940b4d..59c2695e12e7 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -534,7 +534,7 @@ alloc_workqueue_lockdep_map(const char *fmt, unsigned int flags, int max_active, * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags (only WQ_FREEZABLE and WQ_MEM_RECLAIM are meaningful) * @lockdep_map: user-defined lockdep_map - * @...: args for @fmt + * @args: args for @fmt * * Same as alloc_ordered_workqueue but with the a user-define lockdep_map. * Useful for workqueues created with the same purpose and to avoid leaking a @@ -544,7 +544,8 @@ alloc_workqueue_lockdep_map(const char *fmt, unsigned int flags, int max_active, * Pointer to the allocated workqueue on success, %NULL on failure. */ #define alloc_ordered_workqueue_lockdep_map(fmt, flags, lockdep_map, args...) \ - alloc_workqueue_lockdep_map(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, lockdep_map, ##args) + alloc_workqueue_lockdep_map(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), \ + 1, lockdep_map, ##args) #endif /** -- cgit v1.2.3 From 496ddd19a0fad22f250fc7a7b7a8000155418934 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 8 Aug 2024 16:22:28 -0700 Subject: bpf: extract iterator argument type and name validation logic Verifier enforces that all iterator structs are named `bpf_iter_` and that whenever iterator is passed to a kfunc it's passed as a valid PTR -> STRUCT chain (with potentially const modifiers in between). We'll need this check for upcoming changes, so instead of duplicating the logic, extract it into a helper function. Signed-off-by: Andrii Nakryiko Acked-by: Eduard Zingerman Link: https://lore.kernel.org/r/20240808232230.2848712-2-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/btf.h | 5 +++++ kernel/bpf/btf.c | 50 ++++++++++++++++++++++++++++++++++++-------------- 2 files changed, 41 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index cffb43133c68..b8a583194c4a 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -580,6 +580,7 @@ bool btf_is_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, int get_kern_ctx_btf_id(struct bpf_verifier_log *log, enum bpf_prog_type prog_type); bool btf_types_are_same(const struct btf *btf1, u32 id1, const struct btf *btf2, u32 id2); +int btf_check_iter_arg(struct btf *btf, const struct btf_type *func, int arg_idx); #else static inline const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) @@ -654,6 +655,10 @@ static inline bool btf_types_are_same(const struct btf *btf1, u32 id1, { return false; } +static inline int btf_check_iter_arg(struct btf *btf, const struct btf_type *func, int arg_idx) +{ + return -EOPNOTSUPP; +} #endif static inline bool btf_type_is_struct_ptr(struct btf *btf, const struct btf_type *t) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index b12db397303e..c9338fb397fc 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -8047,15 +8047,44 @@ BTF_ID_LIST_GLOBAL(btf_tracing_ids, MAX_BTF_TRACING_TYPE) BTF_TRACING_TYPE_xxx #undef BTF_TRACING_TYPE +/* Validate well-formedness of iter argument type. + * On success, return positive BTF ID of iter state's STRUCT type. + * On error, negative error is returned. + */ +int btf_check_iter_arg(struct btf *btf, const struct btf_type *func, int arg_idx) +{ + const struct btf_param *arg; + const struct btf_type *t; + const char *name; + int btf_id; + + if (btf_type_vlen(func) <= arg_idx) + return -EINVAL; + + arg = &btf_params(func)[arg_idx]; + t = btf_type_skip_modifiers(btf, arg->type, NULL); + if (!t || !btf_type_is_ptr(t)) + return -EINVAL; + t = btf_type_skip_modifiers(btf, t->type, &btf_id); + if (!t || !__btf_type_is_struct(t)) + return -EINVAL; + + name = btf_name_by_offset(btf, t->name_off); + if (!name || strncmp(name, ITER_PREFIX, sizeof(ITER_PREFIX) - 1)) + return -EINVAL; + + return btf_id; +} + static int btf_check_iter_kfuncs(struct btf *btf, const char *func_name, const struct btf_type *func, u32 func_flags) { u32 flags = func_flags & (KF_ITER_NEW | KF_ITER_NEXT | KF_ITER_DESTROY); - const char *name, *sfx, *iter_name; - const struct btf_param *arg; + const char *sfx, *iter_name; const struct btf_type *t; char exp_name[128]; u32 nr_args; + int btf_id; /* exactly one of KF_ITER_{NEW,NEXT,DESTROY} can be set */ if (!flags || (flags & (flags - 1))) @@ -8066,28 +8095,21 @@ static int btf_check_iter_kfuncs(struct btf *btf, const char *func_name, if (nr_args < 1) return -EINVAL; - arg = &btf_params(func)[0]; - t = btf_type_skip_modifiers(btf, arg->type, NULL); - if (!t || !btf_type_is_ptr(t)) - return -EINVAL; - t = btf_type_skip_modifiers(btf, t->type, NULL); - if (!t || !__btf_type_is_struct(t)) - return -EINVAL; - - name = btf_name_by_offset(btf, t->name_off); - if (!name || strncmp(name, ITER_PREFIX, sizeof(ITER_PREFIX) - 1)) - return -EINVAL; + btf_id = btf_check_iter_arg(btf, func, 0); + if (btf_id < 0) + return btf_id; /* sizeof(struct bpf_iter_) should be a multiple of 8 to * fit nicely in stack slots */ + t = btf_type_by_id(btf, btf_id); if (t->size == 0 || (t->size % 8)) return -EINVAL; /* validate bpf_iter__{new,next,destroy}(struct bpf_iter_ *) * naming pattern */ - iter_name = name + sizeof(ITER_PREFIX) - 1; + iter_name = btf_name_by_offset(btf, t->name_off) + sizeof(ITER_PREFIX) - 1; if (flags & KF_ITER_NEW) sfx = "new"; else if (flags & KF_ITER_NEXT) -- cgit v1.2.3 From 74b1e94e94ea369923e5656eeb10b26b16591327 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 20 Aug 2024 13:51:19 -0700 Subject: net: repack struct netdev_queue Adding the NAPI pointer to struct netdev_queue made it grow into another cacheline, even though there was 44 bytes of padding available. The struct was historically grouped as follows: /* read-mostly stuff (align) */ /* ... random control path fields ... */ /* write-mostly stuff (align) */ /* ... 40 byte hole ... */ /* struct dql (align) */ It seems that people want to add control path fields after the read only fields. struct dql looks pretty innocent but it forces its own alignment and nothing indicates that there is a lot of empty space above it. Move dql above the xmit_lock. This shifts the empty space to the end of the struct rather than in the middle of it. Move two example fields there to set an example. Hopefully people will now add new fields at the end of the struct. A lot of the read-only stuff is also control path-only, but if we move it all we'll have another hole in the middle. Before: /* size: 384, cachelines: 6, members: 16 */ /* sum members: 284, holes: 3, sum holes: 100 */ After: /* size: 320, cachelines: 5, members: 16 */ /* sum members: 284, holes: 1, sum holes: 8 */ Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20240820205119.1321322-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 0ef3eaa23f4b..614ec5d3d75b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -644,9 +644,6 @@ struct netdev_queue { struct Qdisc __rcu *qdisc_sleeping; #ifdef CONFIG_SYSFS struct kobject kobj; -#endif -#if defined(CONFIG_XPS) && defined(CONFIG_NUMA) - int numa_node; #endif unsigned long tx_maxrate; /* @@ -660,13 +657,13 @@ struct netdev_queue { #ifdef CONFIG_XDP_SOCKETS struct xsk_buff_pool *pool; #endif - /* NAPI instance for the queue - * Readers and writers must hold RTNL - */ - struct napi_struct *napi; + /* * write-mostly part */ +#ifdef CONFIG_BQL + struct dql dql; +#endif spinlock_t _xmit_lock ____cacheline_aligned_in_smp; int xmit_lock_owner; /* @@ -676,8 +673,16 @@ struct netdev_queue { unsigned long state; -#ifdef CONFIG_BQL - struct dql dql; +/* + * slow- / control-path part + */ + /* NAPI instance for the queue + * Readers and writers must hold RTNL + */ + struct napi_struct *napi; + +#if defined(CONFIG_XPS) && defined(CONFIG_NUMA) + int numa_node; #endif } ____cacheline_aligned_in_smp; -- cgit v1.2.3 From ba0fb44aed47693cc2482427f63ba6cd19051327 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Sun, 11 Aug 2024 10:09:35 +0300 Subject: dma-mapping: replace zone_dma_bits by zone_dma_limit The hardware DMA limit might not be power of 2. When RAM range starts above 0, say 4GB, DMA limit of 30 bits should end at 5GB. A single high bit can not encode this limit. Use a plain address for the DMA zone limit instead. Since the DMA zone can now potentially span beyond 4GB physical limit of DMA32, make sure to use DMA zone for GFP_DMA32 allocations in that case. Signed-off-by: Catalin Marinas Co-developed-by: Baruch Siach Signed-off-by: Baruch Siach Reviewed-by: Catalin Marinas Reviewed-by: Petr Tesarik Signed-off-by: Christoph Hellwig --- arch/arm64/mm/init.c | 30 +++++++++++++++--------------- arch/powerpc/mm/mem.c | 5 ++++- arch/s390/mm/init.c | 2 +- include/linux/dma-direct.h | 2 +- kernel/dma/direct.c | 6 +++--- kernel/dma/pool.c | 4 ++-- kernel/dma/swiotlb.c | 6 +++--- 7 files changed, 29 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 9b5ab6818f7f..c45e2152ca9e 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -115,35 +115,35 @@ static void __init arch_reserve_crashkernel(void) } /* - * Return the maximum physical address for a zone accessible by the given bits - * limit. If DRAM starts above 32-bit, expand the zone to the maximum + * Return the maximum physical address for a zone given its limit. + * If DRAM starts above 32-bit, expand the zone to the maximum * available memory, otherwise cap it at 32-bit. */ -static phys_addr_t __init max_zone_phys(unsigned int zone_bits) +static phys_addr_t __init max_zone_phys(phys_addr_t zone_limit) { - phys_addr_t zone_mask = DMA_BIT_MASK(zone_bits); phys_addr_t phys_start = memblock_start_of_DRAM(); if (phys_start > U32_MAX) - zone_mask = PHYS_ADDR_MAX; - else if (phys_start > zone_mask) - zone_mask = U32_MAX; + zone_limit = PHYS_ADDR_MAX; + else if (phys_start > zone_limit) + zone_limit = U32_MAX; - return min(zone_mask, memblock_end_of_DRAM() - 1) + 1; + return min(zone_limit, memblock_end_of_DRAM() - 1) + 1; } static void __init zone_sizes_init(void) { unsigned long max_zone_pfns[MAX_NR_ZONES] = {0}; - unsigned int __maybe_unused acpi_zone_dma_bits; - unsigned int __maybe_unused dt_zone_dma_bits; - phys_addr_t __maybe_unused dma32_phys_limit = max_zone_phys(32); + phys_addr_t __maybe_unused acpi_zone_dma_limit; + phys_addr_t __maybe_unused dt_zone_dma_limit; + phys_addr_t __maybe_unused dma32_phys_limit = + max_zone_phys(DMA_BIT_MASK(32)); #ifdef CONFIG_ZONE_DMA - acpi_zone_dma_bits = fls64(acpi_iort_dma_get_max_cpu_address()); - dt_zone_dma_bits = fls64(of_dma_get_max_cpu_address(NULL)); - zone_dma_bits = min3(32U, dt_zone_dma_bits, acpi_zone_dma_bits); - arm64_dma_phys_limit = max_zone_phys(zone_dma_bits); + acpi_zone_dma_limit = acpi_iort_dma_get_max_cpu_address(); + dt_zone_dma_limit = of_dma_get_max_cpu_address(NULL); + zone_dma_limit = min(dt_zone_dma_limit, acpi_zone_dma_limit); + arm64_dma_phys_limit = max_zone_phys(zone_dma_limit); max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit); #endif #ifdef CONFIG_ZONE_DMA32 diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index da21cb018984..7e217aa4a274 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -216,7 +216,7 @@ static int __init mark_nonram_nosave(void) * everything else. GFP_DMA32 page allocations automatically fall back to * ZONE_DMA. * - * By using 31-bit unconditionally, we can exploit zone_dma_bits to inform the + * By using 31-bit unconditionally, we can exploit zone_dma_limit to inform the * generic DMA mapping code. 32-bit only devices (if not handled by an IOMMU * anyway) will take a first dip into ZONE_NORMAL and get otherwise served by * ZONE_DMA. @@ -230,6 +230,7 @@ void __init paging_init(void) { unsigned long long total_ram = memblock_phys_mem_size(); phys_addr_t top_of_ram = memblock_end_of_DRAM(); + int zone_dma_bits; #ifdef CONFIG_HIGHMEM unsigned long v = __fix_to_virt(FIX_KMAP_END); @@ -256,6 +257,8 @@ void __init paging_init(void) else zone_dma_bits = 31; + zone_dma_limit = DMA_BIT_MASK(zone_dma_bits); + #ifdef CONFIG_ZONE_DMA max_zone_pfns[ZONE_DMA] = min(max_low_pfn, 1UL << (zone_dma_bits - PAGE_SHIFT)); diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index e3d258f9e726..688abc65c79e 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -97,7 +97,7 @@ void __init paging_init(void) vmem_map_init(); sparse_init(); - zone_dma_bits = 31; + zone_dma_limit = DMA_BIT_MASK(31); memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); max_zone_pfns[ZONE_DMA] = virt_to_pfn(MAX_DMA_ADDRESS); max_zone_pfns[ZONE_NORMAL] = max_low_pfn; diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index edbe13d00776..d7e30d4f7503 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -12,7 +12,7 @@ #include #include -extern unsigned int zone_dma_bits; +extern u64 zone_dma_limit; /* * Record the mapping of CPU physical to DMA addresses for a given region. diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 4480a3cd92e0..f2ba074a6a54 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -20,7 +20,7 @@ * it for entirely different regions. In that case the arch code needs to * override the variable below for dma-direct to work properly. */ -unsigned int zone_dma_bits __ro_after_init = 24; +u64 zone_dma_limit __ro_after_init = DMA_BIT_MASK(24); static inline dma_addr_t phys_to_dma_direct(struct device *dev, phys_addr_t phys) @@ -59,7 +59,7 @@ static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 *phys_limit) * zones. */ *phys_limit = dma_to_phys(dev, dma_limit); - if (*phys_limit <= DMA_BIT_MASK(zone_dma_bits)) + if (*phys_limit <= zone_dma_limit) return GFP_DMA; if (*phys_limit <= DMA_BIT_MASK(32)) return GFP_DMA32; @@ -580,7 +580,7 @@ int dma_direct_supported(struct device *dev, u64 mask) * part of the check. */ if (IS_ENABLED(CONFIG_ZONE_DMA)) - min_mask = min_t(u64, min_mask, DMA_BIT_MASK(zone_dma_bits)); + min_mask = min_t(u64, min_mask, zone_dma_limit); return mask >= phys_to_dma_unencrypted(dev, min_mask); } diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c index d10613eb0f63..7b04f7575796 100644 --- a/kernel/dma/pool.c +++ b/kernel/dma/pool.c @@ -70,9 +70,9 @@ static bool cma_in_zone(gfp_t gfp) /* CMA can't cross zone boundaries, see cma_activate_area() */ end = cma_get_base(cma) + size - 1; if (IS_ENABLED(CONFIG_ZONE_DMA) && (gfp & GFP_DMA)) - return end <= DMA_BIT_MASK(zone_dma_bits); + return end <= zone_dma_limit; if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp & GFP_DMA32)) - return end <= DMA_BIT_MASK(32); + return end <= max(DMA_BIT_MASK(32), zone_dma_limit); return true; } diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index df68d29740a0..abcf3fa63a56 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -450,9 +450,9 @@ int swiotlb_init_late(size_t size, gfp_t gfp_mask, if (!remap) io_tlb_default_mem.can_grow = true; if (IS_ENABLED(CONFIG_ZONE_DMA) && (gfp_mask & __GFP_DMA)) - io_tlb_default_mem.phys_limit = DMA_BIT_MASK(zone_dma_bits); + io_tlb_default_mem.phys_limit = zone_dma_limit; else if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp_mask & __GFP_DMA32)) - io_tlb_default_mem.phys_limit = DMA_BIT_MASK(32); + io_tlb_default_mem.phys_limit = max(DMA_BIT_MASK(32), zone_dma_limit); else io_tlb_default_mem.phys_limit = virt_to_phys(high_memory - 1); #endif @@ -629,7 +629,7 @@ static struct page *swiotlb_alloc_tlb(struct device *dev, size_t bytes, } gfp &= ~GFP_ZONEMASK; - if (phys_limit <= DMA_BIT_MASK(zone_dma_bits)) + if (phys_limit <= zone_dma_limit) gfp |= __GFP_DMA; else if (phys_limit <= DMA_BIT_MASK(32)) gfp |= __GFP_DMA32; -- cgit v1.2.3 From b5c58b2fdc427e7958412ecb2de2804a1f7c1572 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 24 Jul 2024 21:04:49 +0300 Subject: dma-mapping: direct calls for dma-iommu Directly call into dma-iommu just like we have been doing for dma-direct for a while. This avoids the indirect call overhead for IOMMU ops and removes the need to have DMA ops entirely for many common configurations. Signed-off-by: Leon Romanovsky Signed-off-by: Leon Romanovsky Acked-by: Greg Kroah-Hartman Acked-by: Robin Murphy Signed-off-by: Christoph Hellwig --- MAINTAINERS | 1 + drivers/iommu/Kconfig | 2 +- drivers/iommu/dma-iommu.c | 104 +++++++++++-------------------- drivers/iommu/intel/Kconfig | 1 - include/linux/device.h | 5 ++ include/linux/dma-map-ops.h | 13 ---- include/linux/iommu-dma.h | 147 ++++++++++++++++++++++++++++++++++++++++++++ kernel/dma/Kconfig | 4 ++ kernel/dma/Makefile | 2 +- kernel/dma/mapping.c | 83 ++++++++++++++++++++++--- 10 files changed, 269 insertions(+), 93 deletions(-) create mode 100644 include/linux/iommu-dma.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index f328373463b0..6e653684efe9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11722,6 +11722,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/iommu/linux.git F: drivers/iommu/dma-iommu.c F: drivers/iommu/dma-iommu.h F: drivers/iommu/iova.c +F: include/linux/iommu-dma.h F: include/linux/iova.h IOMMU SUBSYSTEM diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index a82f10054aec..61a6889f4dee 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -151,7 +151,7 @@ config OF_IOMMU # IOMMU-agnostic DMA-mapping layer config IOMMU_DMA def_bool ARM64 || X86 || S390 - select DMA_OPS + select DMA_OPS_HELPERS select IOMMU_API select IOMMU_IOVA select IRQ_MSI_IOMMU diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 7b1dfa0665df..3672d619bcb6 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -1037,9 +1038,8 @@ out_unmap: return NULL; } -static struct sg_table *iommu_dma_alloc_noncontiguous(struct device *dev, - size_t size, enum dma_data_direction dir, gfp_t gfp, - unsigned long attrs) +struct sg_table *iommu_dma_alloc_noncontiguous(struct device *dev, size_t size, + enum dma_data_direction dir, gfp_t gfp, unsigned long attrs) { struct dma_sgt_handle *sh; @@ -1055,7 +1055,7 @@ static struct sg_table *iommu_dma_alloc_noncontiguous(struct device *dev, return &sh->sgt; } -static void iommu_dma_free_noncontiguous(struct device *dev, size_t size, +void iommu_dma_free_noncontiguous(struct device *dev, size_t size, struct sg_table *sgt, enum dma_data_direction dir) { struct dma_sgt_handle *sh = sgt_handle(sgt); @@ -1066,8 +1066,8 @@ static void iommu_dma_free_noncontiguous(struct device *dev, size_t size, kfree(sh); } -static void iommu_dma_sync_single_for_cpu(struct device *dev, - dma_addr_t dma_handle, size_t size, enum dma_data_direction dir) +void iommu_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, + size_t size, enum dma_data_direction dir) { phys_addr_t phys; @@ -1081,8 +1081,8 @@ static void iommu_dma_sync_single_for_cpu(struct device *dev, swiotlb_sync_single_for_cpu(dev, phys, size, dir); } -static void iommu_dma_sync_single_for_device(struct device *dev, - dma_addr_t dma_handle, size_t size, enum dma_data_direction dir) +void iommu_dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, + size_t size, enum dma_data_direction dir) { phys_addr_t phys; @@ -1096,9 +1096,8 @@ static void iommu_dma_sync_single_for_device(struct device *dev, arch_sync_dma_for_device(phys, size, dir); } -static void iommu_dma_sync_sg_for_cpu(struct device *dev, - struct scatterlist *sgl, int nelems, - enum dma_data_direction dir) +void iommu_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sgl, + int nelems, enum dma_data_direction dir) { struct scatterlist *sg; int i; @@ -1112,9 +1111,8 @@ static void iommu_dma_sync_sg_for_cpu(struct device *dev, arch_sync_dma_for_cpu(sg_phys(sg), sg->length, dir); } -static void iommu_dma_sync_sg_for_device(struct device *dev, - struct scatterlist *sgl, int nelems, - enum dma_data_direction dir) +void iommu_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sgl, + int nelems, enum dma_data_direction dir) { struct scatterlist *sg; int i; @@ -1129,9 +1127,9 @@ static void iommu_dma_sync_sg_for_device(struct device *dev, arch_sync_dma_for_device(sg_phys(sg), sg->length, dir); } -static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, enum dma_data_direction dir, - unsigned long attrs) +dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, enum dma_data_direction dir, + unsigned long attrs) { phys_addr_t phys = page_to_phys(page) + offset; bool coherent = dev_is_dma_coherent(dev); @@ -1189,7 +1187,7 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page, return iova; } -static void iommu_dma_unmap_page(struct device *dev, dma_addr_t dma_handle, +void iommu_dma_unmap_page(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction dir, unsigned long attrs) { struct iommu_domain *domain = iommu_get_dma_domain(dev); @@ -1342,8 +1340,8 @@ out_unmap: * impedance-matching, to be able to hand off a suitably-aligned list, * but still preserve the original offsets and sizes for the caller. */ -static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir, unsigned long attrs) +int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, unsigned long attrs) { struct iommu_domain *domain = iommu_get_dma_domain(dev); struct iommu_dma_cookie *cookie = domain->iova_cookie; @@ -1462,8 +1460,8 @@ out: return ret; } -static void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir, unsigned long attrs) +void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, unsigned long attrs) { dma_addr_t end = 0, start; struct scatterlist *tmp; @@ -1512,7 +1510,7 @@ static void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg, __iommu_dma_unmap(dev, start, end - start); } -static dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys, +dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys, size_t size, enum dma_data_direction dir, unsigned long attrs) { return __iommu_dma_map(dev, phys, size, @@ -1520,7 +1518,7 @@ static dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys, dma_get_mask(dev)); } -static void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle, +void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle, size_t size, enum dma_data_direction dir, unsigned long attrs) { __iommu_dma_unmap(dev, handle, size); @@ -1557,7 +1555,7 @@ static void __iommu_dma_free(struct device *dev, size_t size, void *cpu_addr) dma_free_contiguous(dev, page, alloc_size); } -static void iommu_dma_free(struct device *dev, size_t size, void *cpu_addr, +void iommu_dma_free(struct device *dev, size_t size, void *cpu_addr, dma_addr_t handle, unsigned long attrs) { __iommu_dma_unmap(dev, handle, size); @@ -1601,8 +1599,8 @@ out_free_pages: return NULL; } -static void *iommu_dma_alloc(struct device *dev, size_t size, - dma_addr_t *handle, gfp_t gfp, unsigned long attrs) +void *iommu_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, + gfp_t gfp, unsigned long attrs) { bool coherent = dev_is_dma_coherent(dev); int ioprot = dma_info_to_prot(DMA_BIDIRECTIONAL, coherent, attrs); @@ -1635,7 +1633,7 @@ static void *iommu_dma_alloc(struct device *dev, size_t size, return cpu_addr; } -static int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma, +int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs) { @@ -1666,7 +1664,7 @@ static int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma, vma->vm_page_prot); } -static int iommu_dma_get_sgtable(struct device *dev, struct sg_table *sgt, +int iommu_dma_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs) { @@ -1693,19 +1691,19 @@ static int iommu_dma_get_sgtable(struct device *dev, struct sg_table *sgt, return ret; } -static unsigned long iommu_dma_get_merge_boundary(struct device *dev) +unsigned long iommu_dma_get_merge_boundary(struct device *dev) { struct iommu_domain *domain = iommu_get_dma_domain(dev); return (1UL << __ffs(domain->pgsize_bitmap)) - 1; } -static size_t iommu_dma_opt_mapping_size(void) +size_t iommu_dma_opt_mapping_size(void) { return iova_rcache_range(); } -static size_t iommu_dma_max_mapping_size(struct device *dev) +size_t iommu_dma_max_mapping_size(struct device *dev) { if (dev_is_untrusted(dev)) return swiotlb_max_mapping_size(dev); @@ -1713,32 +1711,6 @@ static size_t iommu_dma_max_mapping_size(struct device *dev) return SIZE_MAX; } -static const struct dma_map_ops iommu_dma_ops = { - .flags = DMA_F_PCI_P2PDMA_SUPPORTED | - DMA_F_CAN_SKIP_SYNC, - .alloc = iommu_dma_alloc, - .free = iommu_dma_free, - .alloc_pages_op = dma_common_alloc_pages, - .free_pages = dma_common_free_pages, - .alloc_noncontiguous = iommu_dma_alloc_noncontiguous, - .free_noncontiguous = iommu_dma_free_noncontiguous, - .mmap = iommu_dma_mmap, - .get_sgtable = iommu_dma_get_sgtable, - .map_page = iommu_dma_map_page, - .unmap_page = iommu_dma_unmap_page, - .map_sg = iommu_dma_map_sg, - .unmap_sg = iommu_dma_unmap_sg, - .sync_single_for_cpu = iommu_dma_sync_single_for_cpu, - .sync_single_for_device = iommu_dma_sync_single_for_device, - .sync_sg_for_cpu = iommu_dma_sync_sg_for_cpu, - .sync_sg_for_device = iommu_dma_sync_sg_for_device, - .map_resource = iommu_dma_map_resource, - .unmap_resource = iommu_dma_unmap_resource, - .get_merge_boundary = iommu_dma_get_merge_boundary, - .opt_mapping_size = iommu_dma_opt_mapping_size, - .max_mapping_size = iommu_dma_max_mapping_size, -}; - void iommu_setup_dma_ops(struct device *dev) { struct iommu_domain *domain = iommu_get_domain_for_dev(dev); @@ -1746,19 +1718,15 @@ void iommu_setup_dma_ops(struct device *dev) if (dev_is_pci(dev)) dev->iommu->pci_32bit_workaround = !iommu_dma_forcedac; - if (iommu_is_dma_domain(domain)) { - if (iommu_dma_init_domain(domain, dev)) - goto out_err; - dev->dma_ops = &iommu_dma_ops; - } else if (dev->dma_ops == &iommu_dma_ops) { - /* Clean up if we've switched *from* a DMA domain */ - dev->dma_ops = NULL; - } + dev->dma_iommu = iommu_is_dma_domain(domain); + if (dev->dma_iommu && iommu_dma_init_domain(domain, dev)) + goto out_err; return; out_err: - pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n", - dev_name(dev)); + pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n", + dev_name(dev)); + dev->dma_iommu = false; } static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev, diff --git a/drivers/iommu/intel/Kconfig b/drivers/iommu/intel/Kconfig index f52fb39c968e..88fd32a9323c 100644 --- a/drivers/iommu/intel/Kconfig +++ b/drivers/iommu/intel/Kconfig @@ -12,7 +12,6 @@ config DMAR_DEBUG config INTEL_IOMMU bool "Support for Intel IOMMU using DMA Remapping Devices" depends on PCI_MSI && ACPI && X86 - select DMA_OPS select IOMMU_API select IOMMU_IOVA select IOMMUFD_DRIVER if IOMMUFD diff --git a/include/linux/device.h b/include/linux/device.h index 34eb20f5966f..1c5280d28bc3 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -707,6 +707,8 @@ struct device_physical_location { * for dma allocations. This flag is managed by the dma ops * instance from ->dma_supported. * @dma_skip_sync: DMA sync operations can be skipped for coherent buffers. + * @dma_iommu: Device is using default IOMMU implementation for DMA and + * doesn't rely on dma_ops structure. * * At the lowest level, every device in a Linux system is represented by an * instance of struct device. The device structure contains the information @@ -822,6 +824,9 @@ struct device { #ifdef CONFIG_DMA_NEED_SYNC bool dma_skip_sync:1; #endif +#ifdef CONFIG_IOMMU_DMA + bool dma_iommu:1; +#endif }; /** diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 02a1c825896b..077b15c93bb8 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -13,20 +13,7 @@ struct cma; struct iommu_ops; -/* - * Values for struct dma_map_ops.flags: - * - * DMA_F_PCI_P2PDMA_SUPPORTED: Indicates the dma_map_ops implementation can - * handle PCI P2PDMA pages in the map_sg/unmap_sg operation. - * DMA_F_CAN_SKIP_SYNC: DMA sync operations can be skipped if the device is - * coherent and it's not an SWIOTLB buffer. - */ -#define DMA_F_PCI_P2PDMA_SUPPORTED (1 << 0) -#define DMA_F_CAN_SKIP_SYNC (1 << 1) - struct dma_map_ops { - unsigned int flags; - void *(*alloc)(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); diff --git a/include/linux/iommu-dma.h b/include/linux/iommu-dma.h new file mode 100644 index 000000000000..d30a58bf00fd --- /dev/null +++ b/include/linux/iommu-dma.h @@ -0,0 +1,147 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved + * + * DMA operations that map physical memory through IOMMU. + */ +#ifndef _LINUX_IOMMU_DMA_H +#define _LINUX_IOMMU_DMA_H + +#include + +#ifdef CONFIG_IOMMU_DMA +dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, enum dma_data_direction dir, + unsigned long attrs); +void iommu_dma_unmap_page(struct device *dev, dma_addr_t dma_handle, + size_t size, enum dma_data_direction dir, unsigned long attrs); +int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, unsigned long attrs); +void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, unsigned long attrs); +void *iommu_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, + gfp_t gfp, unsigned long attrs); +int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs); +int iommu_dma_get_sgtable(struct device *dev, struct sg_table *sgt, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs); +unsigned long iommu_dma_get_merge_boundary(struct device *dev); +size_t iommu_dma_opt_mapping_size(void); +size_t iommu_dma_max_mapping_size(struct device *dev); +void iommu_dma_free(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t handle, unsigned long attrs); +dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys, + size_t size, enum dma_data_direction dir, unsigned long attrs); +void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle, + size_t size, enum dma_data_direction dir, unsigned long attrs); +struct sg_table *iommu_dma_alloc_noncontiguous(struct device *dev, size_t size, + enum dma_data_direction dir, gfp_t gfp, unsigned long attrs); +void iommu_dma_free_noncontiguous(struct device *dev, size_t size, + struct sg_table *sgt, enum dma_data_direction dir); +void iommu_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, + size_t size, enum dma_data_direction dir); +void iommu_dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, + size_t size, enum dma_data_direction dir); +void iommu_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sgl, + int nelems, enum dma_data_direction dir); +void iommu_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sgl, + int nelems, enum dma_data_direction dir); +#else +static inline dma_addr_t iommu_dma_map_page(struct device *dev, + struct page *page, unsigned long offset, size_t size, + enum dma_data_direction dir, unsigned long attrs) +{ + return DMA_MAPPING_ERROR; +} +static inline void iommu_dma_unmap_page(struct device *dev, + dma_addr_t dma_handle, size_t size, enum dma_data_direction dir, + unsigned long attrs) +{ +} +static inline int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir, unsigned long attrs) +{ + return -EINVAL; +} +static inline void iommu_dma_unmap_sg(struct device *dev, + struct scatterlist *sg, int nents, enum dma_data_direction dir, + unsigned long attrs) +{ +} +static inline void *iommu_dma_alloc(struct device *dev, size_t size, + dma_addr_t *handle, gfp_t gfp, unsigned long attrs) +{ + return NULL; +} +static inline int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs) +{ + return -EINVAL; +} +static inline int iommu_dma_get_sgtable(struct device *dev, + struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, + size_t size, unsigned long attrs) +{ + return -EINVAL; +} +static inline unsigned long iommu_dma_get_merge_boundary(struct device *dev) +{ + return 0; +} +static inline size_t iommu_dma_opt_mapping_size(void) +{ + return 0; +} +static inline size_t iommu_dma_max_mapping_size(struct device *dev) +{ + return 0; +} +static inline void iommu_dma_free(struct device *dev, size_t size, + void *cpu_addr, dma_addr_t handle, unsigned long attrs) +{ +} +static inline dma_addr_t iommu_dma_map_resource(struct device *dev, + phys_addr_t phys, size_t size, enum dma_data_direction dir, + unsigned long attrs) +{ + return DMA_MAPPING_ERROR; +} +static inline void iommu_dma_unmap_resource(struct device *dev, + dma_addr_t handle, size_t size, enum dma_data_direction dir, + unsigned long attrs) +{ +} +static inline struct sg_table * +iommu_dma_alloc_noncontiguous(struct device *dev, size_t size, + enum dma_data_direction dir, gfp_t gfp, unsigned long attrs) +{ + return NULL; +} +static inline void iommu_dma_free_noncontiguous(struct device *dev, size_t size, + struct sg_table *sgt, enum dma_data_direction dir) +{ +} +static inline void iommu_dma_sync_single_for_cpu(struct device *dev, + dma_addr_t dma_handle, size_t size, + enum dma_data_direction dir) +{ +} +static inline void iommu_dma_sync_single_for_device(struct device *dev, + dma_addr_t dma_handle, size_t size, enum dma_data_direction dir) +{ +} +static inline void iommu_dma_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sgl, int nelems, + enum dma_data_direction dir) +{ +} +static inline void iommu_dma_sync_sg_for_device(struct device *dev, + struct scatterlist *sgl, int nelems, + enum dma_data_direction dir) +{ +} +#endif /* CONFIG_IOMMU_DMA */ +#endif /* _LINUX_IOMMU_DMA_H */ diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig index c06e56be0ca1..21bae1700836 100644 --- a/kernel/dma/Kconfig +++ b/kernel/dma/Kconfig @@ -8,8 +8,12 @@ config HAS_DMA depends on !NO_DMA default y +config DMA_OPS_HELPERS + bool + config DMA_OPS depends on HAS_DMA + select DMA_OPS_HELPERS bool # diff --git a/kernel/dma/Makefile b/kernel/dma/Makefile index 21926e46ef4f..2e6e933cf7f3 100644 --- a/kernel/dma/Makefile +++ b/kernel/dma/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_HAS_DMA) += mapping.o direct.o -obj-$(CONFIG_DMA_OPS) += ops_helpers.o +obj-$(CONFIG_DMA_OPS_HELPERS) += ops_helpers.o obj-$(CONFIG_DMA_OPS) += dummy.o obj-$(CONFIG_DMA_CMA) += contiguous.o obj-$(CONFIG_DMA_DECLARE_COHERENT) += coherent.o diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 71416b156bb5..b50ae3d198a6 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -113,11 +114,27 @@ void *dmam_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, } EXPORT_SYMBOL(dmam_alloc_attrs); +#ifdef CONFIG_IOMMU_DMA +static bool use_dma_iommu(struct device *dev) +{ + return dev->dma_iommu; +} +#else +static bool use_dma_iommu(struct device *dev) +{ + return false; +} +#endif + static bool dma_go_direct(struct device *dev, dma_addr_t mask, const struct dma_map_ops *ops) { + if (use_dma_iommu(dev)) + return false; + if (likely(!ops)) return true; + #ifdef CONFIG_DMA_OPS_BYPASS if (dev->dma_ops_bypass) return min_not_zero(mask, dev->bus_dma_limit) >= @@ -159,6 +176,8 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page, if (dma_map_direct(dev, ops) || arch_dma_map_page_direct(dev, page_to_phys(page) + offset + size)) addr = dma_direct_map_page(dev, page, offset, size, dir, attrs); + else if (use_dma_iommu(dev)) + addr = iommu_dma_map_page(dev, page, offset, size, dir, attrs); else addr = ops->map_page(dev, page, offset, size, dir, attrs); kmsan_handle_dma(page, offset, size, dir); @@ -177,6 +196,8 @@ void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size, if (dma_map_direct(dev, ops) || arch_dma_unmap_page_direct(dev, addr + size)) dma_direct_unmap_page(dev, addr, size, dir, attrs); + else if (use_dma_iommu(dev)) + iommu_dma_unmap_page(dev, addr, size, dir, attrs); else ops->unmap_page(dev, addr, size, dir, attrs); debug_dma_unmap_page(dev, addr, size, dir); @@ -197,6 +218,8 @@ static int __dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, if (dma_map_direct(dev, ops) || arch_dma_map_sg_direct(dev, sg, nents)) ents = dma_direct_map_sg(dev, sg, nents, dir, attrs); + else if (use_dma_iommu(dev)) + ents = iommu_dma_map_sg(dev, sg, nents, dir, attrs); else ents = ops->map_sg(dev, sg, nents, dir, attrs); @@ -291,7 +314,9 @@ void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg, if (dma_map_direct(dev, ops) || arch_dma_unmap_sg_direct(dev, sg, nents)) dma_direct_unmap_sg(dev, sg, nents, dir, attrs); - else + else if (use_dma_iommu(dev)) + iommu_dma_unmap_sg(dev, sg, nents, dir, attrs); + else if (ops->unmap_sg) ops->unmap_sg(dev, sg, nents, dir, attrs); } EXPORT_SYMBOL(dma_unmap_sg_attrs); @@ -309,6 +334,8 @@ dma_addr_t dma_map_resource(struct device *dev, phys_addr_t phys_addr, if (dma_map_direct(dev, ops)) addr = dma_direct_map_resource(dev, phys_addr, size, dir, attrs); + else if (use_dma_iommu(dev)) + addr = iommu_dma_map_resource(dev, phys_addr, size, dir, attrs); else if (ops->map_resource) addr = ops->map_resource(dev, phys_addr, size, dir, attrs); @@ -323,7 +350,11 @@ void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size, const struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!valid_dma_direction(dir)); - if (!dma_map_direct(dev, ops) && ops->unmap_resource) + if (dma_map_direct(dev, ops)) + ; /* nothing to do: uncached and no swiotlb */ + else if (use_dma_iommu(dev)) + iommu_dma_unmap_resource(dev, addr, size, dir, attrs); + else if (ops->unmap_resource) ops->unmap_resource(dev, addr, size, dir, attrs); debug_dma_unmap_resource(dev, addr, size, dir); } @@ -338,6 +369,8 @@ void __dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, BUG_ON(!valid_dma_direction(dir)); if (dma_map_direct(dev, ops)) dma_direct_sync_single_for_cpu(dev, addr, size, dir); + else if (use_dma_iommu(dev)) + iommu_dma_sync_single_for_cpu(dev, addr, size, dir); else if (ops->sync_single_for_cpu) ops->sync_single_for_cpu(dev, addr, size, dir); debug_dma_sync_single_for_cpu(dev, addr, size, dir); @@ -352,6 +385,8 @@ void __dma_sync_single_for_device(struct device *dev, dma_addr_t addr, BUG_ON(!valid_dma_direction(dir)); if (dma_map_direct(dev, ops)) dma_direct_sync_single_for_device(dev, addr, size, dir); + else if (use_dma_iommu(dev)) + iommu_dma_sync_single_for_device(dev, addr, size, dir); else if (ops->sync_single_for_device) ops->sync_single_for_device(dev, addr, size, dir); debug_dma_sync_single_for_device(dev, addr, size, dir); @@ -366,6 +401,8 @@ void __dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, BUG_ON(!valid_dma_direction(dir)); if (dma_map_direct(dev, ops)) dma_direct_sync_sg_for_cpu(dev, sg, nelems, dir); + else if (use_dma_iommu(dev)) + iommu_dma_sync_sg_for_cpu(dev, sg, nelems, dir); else if (ops->sync_sg_for_cpu) ops->sync_sg_for_cpu(dev, sg, nelems, dir); debug_dma_sync_sg_for_cpu(dev, sg, nelems, dir); @@ -380,6 +417,8 @@ void __dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, BUG_ON(!valid_dma_direction(dir)); if (dma_map_direct(dev, ops)) dma_direct_sync_sg_for_device(dev, sg, nelems, dir); + else if (use_dma_iommu(dev)) + iommu_dma_sync_sg_for_device(dev, sg, nelems, dir); else if (ops->sync_sg_for_device) ops->sync_sg_for_device(dev, sg, nelems, dir); debug_dma_sync_sg_for_device(dev, sg, nelems, dir); @@ -405,7 +444,7 @@ static void dma_setup_need_sync(struct device *dev) { const struct dma_map_ops *ops = get_dma_ops(dev); - if (dma_map_direct(dev, ops) || (ops->flags & DMA_F_CAN_SKIP_SYNC)) + if (dma_map_direct(dev, ops) || use_dma_iommu(dev)) /* * dma_skip_sync will be reset to %false on first SWIOTLB buffer * mapping, if any. During the device initialization, it's @@ -446,6 +485,9 @@ int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, if (dma_alloc_direct(dev, ops)) return dma_direct_get_sgtable(dev, sgt, cpu_addr, dma_addr, size, attrs); + if (use_dma_iommu(dev)) + return iommu_dma_get_sgtable(dev, sgt, cpu_addr, dma_addr, + size, attrs); if (!ops->get_sgtable) return -ENXIO; return ops->get_sgtable(dev, sgt, cpu_addr, dma_addr, size, attrs); @@ -482,6 +524,8 @@ bool dma_can_mmap(struct device *dev) if (dma_alloc_direct(dev, ops)) return dma_direct_can_mmap(dev); + if (use_dma_iommu(dev)) + return true; return ops->mmap != NULL; } EXPORT_SYMBOL_GPL(dma_can_mmap); @@ -508,6 +552,9 @@ int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, if (dma_alloc_direct(dev, ops)) return dma_direct_mmap(dev, vma, cpu_addr, dma_addr, size, attrs); + if (use_dma_iommu(dev)) + return iommu_dma_mmap(dev, vma, cpu_addr, dma_addr, size, + attrs); if (!ops->mmap) return -ENXIO; return ops->mmap(dev, vma, cpu_addr, dma_addr, size, attrs); @@ -559,6 +606,8 @@ void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, if (dma_alloc_direct(dev, ops)) cpu_addr = dma_direct_alloc(dev, size, dma_handle, flag, attrs); + else if (use_dma_iommu(dev)) + cpu_addr = iommu_dma_alloc(dev, size, dma_handle, flag, attrs); else if (ops->alloc) cpu_addr = ops->alloc(dev, size, dma_handle, flag, attrs); else @@ -591,6 +640,8 @@ void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr, debug_dma_free_coherent(dev, size, cpu_addr, dma_handle); if (dma_alloc_direct(dev, ops)) dma_direct_free(dev, size, cpu_addr, dma_handle, attrs); + else if (use_dma_iommu(dev)) + iommu_dma_free(dev, size, cpu_addr, dma_handle, attrs); else if (ops->free) ops->free(dev, size, cpu_addr, dma_handle, attrs); } @@ -611,6 +662,8 @@ static struct page *__dma_alloc_pages(struct device *dev, size_t size, size = PAGE_ALIGN(size); if (dma_alloc_direct(dev, ops)) return dma_direct_alloc_pages(dev, size, dma_handle, dir, gfp); + if (use_dma_iommu(dev)) + return dma_common_alloc_pages(dev, size, dma_handle, dir, gfp); if (!ops->alloc_pages_op) return NULL; return ops->alloc_pages_op(dev, size, dma_handle, dir, gfp); @@ -635,6 +688,8 @@ static void __dma_free_pages(struct device *dev, size_t size, struct page *page, size = PAGE_ALIGN(size); if (dma_alloc_direct(dev, ops)) dma_direct_free_pages(dev, size, page, dma_handle, dir); + else if (use_dma_iommu(dev)) + dma_common_free_pages(dev, size, page, dma_handle, dir); else if (ops->free_pages) ops->free_pages(dev, size, page, dma_handle, dir); } @@ -697,6 +752,8 @@ struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size, if (ops && ops->alloc_noncontiguous) sgt = ops->alloc_noncontiguous(dev, size, dir, gfp, attrs); + else if (use_dma_iommu(dev)) + sgt = iommu_dma_alloc_noncontiguous(dev, size, dir, gfp, attrs); else sgt = alloc_single_sgt(dev, size, dir, gfp); @@ -725,6 +782,8 @@ void dma_free_noncontiguous(struct device *dev, size_t size, debug_dma_unmap_sg(dev, sgt->sgl, sgt->orig_nents, dir); if (ops && ops->free_noncontiguous) ops->free_noncontiguous(dev, size, sgt, dir); + else if (use_dma_iommu(dev)) + iommu_dma_free_noncontiguous(dev, size, sgt, dir); else free_single_sgt(dev, size, sgt, dir); } @@ -772,6 +831,8 @@ static int dma_supported(struct device *dev, u64 mask) { const struct dma_map_ops *ops = get_dma_ops(dev); + if (WARN_ON(ops && use_dma_iommu(dev))) + return false; /* * ->dma_supported sets the bypass flag, so we must always call * into the method here unless the device is truly direct mapped. @@ -787,17 +848,14 @@ bool dma_pci_p2pdma_supported(struct device *dev) { const struct dma_map_ops *ops = get_dma_ops(dev); - /* if ops is not set, dma direct will be used which supports P2PDMA */ - if (!ops) - return true; - /* * Note: dma_ops_bypass is not checked here because P2PDMA should * not be used with dma mapping ops that do not have support even * if the specific device is bypassing them. */ - return ops->flags & DMA_F_PCI_P2PDMA_SUPPORTED; + /* if ops is not set, dma direct and default IOMMU support P2PDMA */ + return !ops; } EXPORT_SYMBOL_GPL(dma_pci_p2pdma_supported); @@ -865,6 +923,8 @@ size_t dma_max_mapping_size(struct device *dev) if (dma_map_direct(dev, ops)) size = dma_direct_max_mapping_size(dev); + else if (use_dma_iommu(dev)) + size = iommu_dma_max_mapping_size(dev); else if (ops && ops->max_mapping_size) size = ops->max_mapping_size(dev); @@ -877,7 +937,9 @@ size_t dma_opt_mapping_size(struct device *dev) const struct dma_map_ops *ops = get_dma_ops(dev); size_t size = SIZE_MAX; - if (ops && ops->opt_mapping_size) + if (use_dma_iommu(dev)) + size = iommu_dma_opt_mapping_size(); + else if (ops && ops->opt_mapping_size) size = ops->opt_mapping_size(); return min(dma_max_mapping_size(dev), size); @@ -888,6 +950,9 @@ unsigned long dma_get_merge_boundary(struct device *dev) { const struct dma_map_ops *ops = get_dma_ops(dev); + if (use_dma_iommu(dev)) + return iommu_dma_get_merge_boundary(dev); + if (!ops || !ops->get_merge_boundary) return 0; /* can't merge */ -- cgit v1.2.3 From ae010757a55b57c8b82628e8ea9b7da2269131d9 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Thu, 22 Aug 2024 01:41:07 -0700 Subject: bpf: rename nocsr -> bpf_fastcall in verifier Attribute used by LLVM implementation of the feature had been changed from no_caller_saved_registers to bpf_fastcall (see [1]). This commit replaces references to nocsr by references to bpf_fastcall to keep LLVM and Kernel parts in sync. [1] https://github.com/llvm/llvm-project/pull/105417 Acked-by: Yonghong Song Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20240822084112.3257995-2-eddyz87@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 6 +- include/linux/bpf_verifier.h | 18 +++--- kernel/bpf/helpers.c | 2 +- kernel/bpf/verifier.c | 143 +++++++++++++++++++++---------------------- 4 files changed, 84 insertions(+), 85 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f0192c173ed8..00dc4dd28cbd 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -808,12 +808,12 @@ struct bpf_func_proto { bool gpl_only; bool pkt_access; bool might_sleep; - /* set to true if helper follows contract for gcc/llvm - * attribute no_caller_saved_registers: + /* set to true if helper follows contract for llvm + * attribute bpf_fastcall: * - void functions do not scratch r0 * - functions taking N arguments scratch only registers r1-rN */ - bool allow_nocsr; + bool allow_fastcall; enum bpf_return_type ret_type; union { struct { diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 5cea15c81b8a..634a302a39e3 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -577,13 +577,13 @@ struct bpf_insn_aux_data { bool call_with_percpu_alloc_ptr; /* {this,per}_cpu_ptr() with prog percpu alloc */ u8 alu_state; /* used in combination with alu_limit */ /* true if STX or LDX instruction is a part of a spill/fill - * pattern for a no_caller_saved_registers call. + * pattern for a bpf_fastcall call. */ - u8 nocsr_pattern:1; + u8 fastcall_pattern:1; /* for CALL instructions, a number of spill/fill pairs in the - * no_caller_saved_registers pattern. + * bpf_fastcall pattern. */ - u8 nocsr_spills_num:3; + u8 fastcall_spills_num:3; /* below fields are initialized once */ unsigned int orig_idx; /* original instruction index */ @@ -653,10 +653,10 @@ struct bpf_subprog_info { u32 linfo_idx; /* The idx to the main_prog->aux->linfo */ u16 stack_depth; /* max. stack depth used by this function */ u16 stack_extra; - /* offsets in range [stack_depth .. nocsr_stack_off) - * are used for no_caller_saved_registers spills and fills. + /* offsets in range [stack_depth .. fastcall_stack_off) + * are used for bpf_fastcall spills and fills. */ - s16 nocsr_stack_off; + s16 fastcall_stack_off; bool has_tail_call: 1; bool tail_call_reachable: 1; bool has_ld_abs: 1; @@ -664,8 +664,8 @@ struct bpf_subprog_info { bool is_async_cb: 1; bool is_exception_cb: 1; bool args_cached: 1; - /* true if nocsr stack region is used by functions that can't be inlined */ - bool keep_nocsr_stack: 1; + /* true if bpf_fastcall stack region is used by functions that can't be inlined */ + bool keep_fastcall_stack: 1; u8 arg_cnt; struct bpf_subprog_arg_info args[MAX_BPF_FUNC_REG_ARGS]; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index ccca6fe0367c..4105b4af6e03 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -158,7 +158,7 @@ const struct bpf_func_proto bpf_get_smp_processor_id_proto = { .func = bpf_get_smp_processor_id, .gpl_only = false, .ret_type = RET_INTEGER, - .allow_nocsr = true, + .allow_fastcall = true, }; BPF_CALL_0(bpf_get_numa_node_id) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 920d7c5fe944..0dfd91f36417 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4579,28 +4579,28 @@ static int get_reg_width(struct bpf_reg_state *reg) return fls64(reg->umax_value); } -/* See comment for mark_nocsr_pattern_for_call() */ -static void check_nocsr_stack_contract(struct bpf_verifier_env *env, struct bpf_func_state *state, - int insn_idx, int off) +/* See comment for mark_fastcall_pattern_for_call() */ +static void check_fastcall_stack_contract(struct bpf_verifier_env *env, + struct bpf_func_state *state, int insn_idx, int off) { struct bpf_subprog_info *subprog = &env->subprog_info[state->subprogno]; struct bpf_insn_aux_data *aux = env->insn_aux_data; int i; - if (subprog->nocsr_stack_off <= off || aux[insn_idx].nocsr_pattern) + if (subprog->fastcall_stack_off <= off || aux[insn_idx].fastcall_pattern) return; - /* access to the region [max_stack_depth .. nocsr_stack_off) - * from something that is not a part of the nocsr pattern, - * disable nocsr rewrites for current subprogram by setting - * nocsr_stack_off to a value smaller than any possible offset. + /* access to the region [max_stack_depth .. fastcall_stack_off) + * from something that is not a part of the fastcall pattern, + * disable fastcall rewrites for current subprogram by setting + * fastcall_stack_off to a value smaller than any possible offset. */ - subprog->nocsr_stack_off = S16_MIN; - /* reset nocsr aux flags within subprogram, + subprog->fastcall_stack_off = S16_MIN; + /* reset fastcall aux flags within subprogram, * happens at most once per subprogram */ for (i = subprog->start; i < (subprog + 1)->start; ++i) { - aux[i].nocsr_spills_num = 0; - aux[i].nocsr_pattern = 0; + aux[i].fastcall_spills_num = 0; + aux[i].fastcall_pattern = 0; } } @@ -4652,7 +4652,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, if (err) return err; - check_nocsr_stack_contract(env, state, insn_idx, off); + check_fastcall_stack_contract(env, state, insn_idx, off); mark_stack_slot_scratched(env, spi); if (reg && !(off % BPF_REG_SIZE) && reg->type == SCALAR_VALUE && env->bpf_capable) { bool reg_value_fits; @@ -4787,7 +4787,7 @@ static int check_stack_write_var_off(struct bpf_verifier_env *env, return err; } - check_nocsr_stack_contract(env, state, insn_idx, min_off); + check_fastcall_stack_contract(env, state, insn_idx, min_off); /* Variable offset writes destroy any spilled pointers in range. */ for (i = min_off; i < max_off; i++) { u8 new_type, *stype; @@ -4926,7 +4926,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, reg = ®_state->stack[spi].spilled_ptr; mark_stack_slot_scratched(env, spi); - check_nocsr_stack_contract(env, state, env->insn_idx, off); + check_fastcall_stack_contract(env, state, env->insn_idx, off); if (is_spilled_reg(®_state->stack[spi])) { u8 spill_size = 1; @@ -5087,7 +5087,7 @@ static int check_stack_read_var_off(struct bpf_verifier_env *env, min_off = reg->smin_value + off; max_off = reg->smax_value + off; mark_reg_stack_read(env, ptr_state, min_off, max_off + size, dst_regno); - check_nocsr_stack_contract(env, ptr_state, env->insn_idx, min_off); + check_fastcall_stack_contract(env, ptr_state, env->insn_idx, min_off); return 0; } @@ -6804,13 +6804,13 @@ static int check_stack_slot_within_bounds(struct bpf_verifier_env *env, struct bpf_insn_aux_data *aux = &env->insn_aux_data[env->insn_idx]; int min_valid_off, max_bpf_stack; - /* If accessing instruction is a spill/fill from nocsr pattern, + /* If accessing instruction is a spill/fill from bpf_fastcall pattern, * add room for all caller saved registers below MAX_BPF_STACK. - * In case if nocsr rewrite won't happen maximal stack depth + * In case if bpf_fastcall rewrite won't happen maximal stack depth * would be checked by check_max_stack_depth_subprog(). */ max_bpf_stack = MAX_BPF_STACK; - if (aux->nocsr_pattern) + if (aux->fastcall_pattern) max_bpf_stack += CALLER_SAVED_REGS * BPF_REG_SIZE; if (t == BPF_WRITE || env->allow_uninit_stack) @@ -16118,12 +16118,12 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns, /* Return a bitmask specifying which caller saved registers are * clobbered by a call to a helper *as if* this helper follows - * no_caller_saved_registers contract: + * bpf_fastcall contract: * - includes R0 if function is non-void; * - includes R1-R5 if corresponding parameter has is described * in the function prototype. */ -static u32 helper_nocsr_clobber_mask(const struct bpf_func_proto *fn) +static u32 helper_fastcall_clobber_mask(const struct bpf_func_proto *fn) { u8 mask; int i; @@ -16138,8 +16138,8 @@ static u32 helper_nocsr_clobber_mask(const struct bpf_func_proto *fn) } /* True if do_misc_fixups() replaces calls to helper number 'imm', - * replacement patch is presumed to follow no_caller_saved_registers contract - * (see mark_nocsr_pattern_for_call() below). + * replacement patch is presumed to follow bpf_fastcall contract + * (see mark_fastcall_pattern_for_call() below). */ static bool verifier_inlines_helper_call(struct bpf_verifier_env *env, s32 imm) { @@ -16153,7 +16153,7 @@ static bool verifier_inlines_helper_call(struct bpf_verifier_env *env, s32 imm) } } -/* GCC and LLVM define a no_caller_saved_registers function attribute. +/* LLVM define a bpf_fastcall function attribute. * This attribute means that function scratches only some of * the caller saved registers defined by ABI. * For BPF the set of such registers could be defined as follows: @@ -16163,13 +16163,12 @@ static bool verifier_inlines_helper_call(struct bpf_verifier_env *env, s32 imm) * * The contract between kernel and clang allows to simultaneously use * such functions and maintain backwards compatibility with old - * kernels that don't understand no_caller_saved_registers calls - * (nocsr for short): + * kernels that don't understand bpf_fastcall calls: * - * - for nocsr calls clang allocates registers as-if relevant r0-r5 + * - for bpf_fastcall calls clang allocates registers as-if relevant r0-r5 * registers are not scratched by the call; * - * - as a post-processing step, clang visits each nocsr call and adds + * - as a post-processing step, clang visits each bpf_fastcall call and adds * spill/fill for every live r0-r5; * * - stack offsets used for the spill/fill are allocated as lowest @@ -16177,11 +16176,11 @@ static bool verifier_inlines_helper_call(struct bpf_verifier_env *env, s32 imm) * purposes; * * - when kernel loads a program, it looks for such patterns - * (nocsr function surrounded by spills/fills) and checks if - * spill/fill stack offsets are used exclusively in nocsr patterns; + * (bpf_fastcall function surrounded by spills/fills) and checks if + * spill/fill stack offsets are used exclusively in fastcall patterns; * * - if so, and if verifier or current JIT inlines the call to the - * nocsr function (e.g. a helper call), kernel removes unnecessary + * bpf_fastcall function (e.g. a helper call), kernel removes unnecessary * spill/fill pairs; * * - when old kernel loads a program, presence of spill/fill pairs @@ -16200,22 +16199,22 @@ static bool verifier_inlines_helper_call(struct bpf_verifier_env *env, s32 imm) * r0 += r2; * exit; * - * The purpose of mark_nocsr_pattern_for_call is to: + * The purpose of mark_fastcall_pattern_for_call is to: * - look for such patterns; - * - mark spill and fill instructions in env->insn_aux_data[*].nocsr_pattern; - * - mark set env->insn_aux_data[*].nocsr_spills_num for call instruction; - * - update env->subprog_info[*]->nocsr_stack_off to find an offset - * at which nocsr spill/fill stack slots start; - * - update env->subprog_info[*]->keep_nocsr_stack. + * - mark spill and fill instructions in env->insn_aux_data[*].fastcall_pattern; + * - mark set env->insn_aux_data[*].fastcall_spills_num for call instruction; + * - update env->subprog_info[*]->fastcall_stack_off to find an offset + * at which bpf_fastcall spill/fill stack slots start; + * - update env->subprog_info[*]->keep_fastcall_stack. * - * The .nocsr_pattern and .nocsr_stack_off are used by - * check_nocsr_stack_contract() to check if every stack access to - * nocsr spill/fill stack slot originates from spill/fill - * instructions, members of nocsr patterns. + * The .fastcall_pattern and .fastcall_stack_off are used by + * check_fastcall_stack_contract() to check if every stack access to + * fastcall spill/fill stack slot originates from spill/fill + * instructions, members of fastcall patterns. * - * If such condition holds true for a subprogram, nocsr patterns could - * be rewritten by remove_nocsr_spills_fills(). - * Otherwise nocsr patterns are not changed in the subprogram + * If such condition holds true for a subprogram, fastcall patterns could + * be rewritten by remove_fastcall_spills_fills(). + * Otherwise bpf_fastcall patterns are not changed in the subprogram * (code, presumably, generated by an older clang version). * * For example, it is *not* safe to remove spill/fill below: @@ -16228,9 +16227,9 @@ static bool verifier_inlines_helper_call(struct bpf_verifier_env *env, s32 imm) * r0 += r1; exit; * exit; */ -static void mark_nocsr_pattern_for_call(struct bpf_verifier_env *env, - struct bpf_subprog_info *subprog, - int insn_idx, s16 lowest_off) +static void mark_fastcall_pattern_for_call(struct bpf_verifier_env *env, + struct bpf_subprog_info *subprog, + int insn_idx, s16 lowest_off) { struct bpf_insn *insns = env->prog->insnsi, *stx, *ldx; struct bpf_insn *call = &env->prog->insnsi[insn_idx]; @@ -16245,8 +16244,8 @@ static void mark_nocsr_pattern_for_call(struct bpf_verifier_env *env, if (get_helper_proto(env, call->imm, &fn) < 0) /* error would be reported later */ return; - clobbered_regs_mask = helper_nocsr_clobber_mask(fn); - can_be_inlined = fn->allow_nocsr && + clobbered_regs_mask = helper_fastcall_clobber_mask(fn); + can_be_inlined = fn->allow_fastcall && (verifier_inlines_helper_call(env, call->imm) || bpf_jit_inlines_helper_call(call->imm)); } @@ -16289,36 +16288,36 @@ static void mark_nocsr_pattern_for_call(struct bpf_verifier_env *env, if (stx->off != off || ldx->off != off) break; expected_regs_mask &= ~BIT(stx->src_reg); - env->insn_aux_data[insn_idx - i].nocsr_pattern = 1; - env->insn_aux_data[insn_idx + i].nocsr_pattern = 1; + env->insn_aux_data[insn_idx - i].fastcall_pattern = 1; + env->insn_aux_data[insn_idx + i].fastcall_pattern = 1; } if (i == 1) return; - /* Conditionally set 'nocsr_spills_num' to allow forward + /* Conditionally set 'fastcall_spills_num' to allow forward * compatibility when more helper functions are marked as - * nocsr at compile time than current kernel supports, e.g: + * bpf_fastcall at compile time than current kernel supports, e.g: * * 1: *(u64 *)(r10 - 8) = r1 - * 2: call A ;; assume A is nocsr for current kernel + * 2: call A ;; assume A is bpf_fastcall for current kernel * 3: r1 = *(u64 *)(r10 - 8) * 4: *(u64 *)(r10 - 8) = r1 - * 5: call B ;; assume B is not nocsr for current kernel + * 5: call B ;; assume B is not bpf_fastcall for current kernel * 6: r1 = *(u64 *)(r10 - 8) * - * There is no need to block nocsr rewrite for such program. - * Set 'nocsr_pattern' for both calls to keep check_nocsr_stack_contract() happy, - * don't set 'nocsr_spills_num' for call B so that remove_nocsr_spills_fills() + * There is no need to block bpf_fastcall rewrite for such program. + * Set 'fastcall_pattern' for both calls to keep check_fastcall_stack_contract() happy, + * don't set 'fastcall_spills_num' for call B so that remove_fastcall_spills_fills() * does not remove spill/fill pair {4,6}. */ if (can_be_inlined) - env->insn_aux_data[insn_idx].nocsr_spills_num = i - 1; + env->insn_aux_data[insn_idx].fastcall_spills_num = i - 1; else - subprog->keep_nocsr_stack = 1; - subprog->nocsr_stack_off = min(subprog->nocsr_stack_off, off); + subprog->keep_fastcall_stack = 1; + subprog->fastcall_stack_off = min(subprog->fastcall_stack_off, off); } -static int mark_nocsr_patterns(struct bpf_verifier_env *env) +static int mark_fastcall_patterns(struct bpf_verifier_env *env) { struct bpf_subprog_info *subprog = env->subprog_info; struct bpf_insn *insn; @@ -16335,12 +16334,12 @@ static int mark_nocsr_patterns(struct bpf_verifier_env *env) continue; lowest_off = min(lowest_off, insn->off); } - /* use this offset to find nocsr patterns */ + /* use this offset to find fastcall patterns */ for (i = subprog->start; i < (subprog + 1)->start; ++i) { insn = env->prog->insnsi + i; if (insn->code != (BPF_JMP | BPF_CALL)) continue; - mark_nocsr_pattern_for_call(env, subprog, i, lowest_off); + mark_fastcall_pattern_for_call(env, subprog, i, lowest_off); } } return 0; @@ -21244,10 +21243,10 @@ static int optimize_bpf_loop(struct bpf_verifier_env *env) return 0; } -/* Remove unnecessary spill/fill pairs, members of nocsr pattern, +/* Remove unnecessary spill/fill pairs, members of fastcall pattern, * adjust subprograms stack depth when possible. */ -static int remove_nocsr_spills_fills(struct bpf_verifier_env *env) +static int remove_fastcall_spills_fills(struct bpf_verifier_env *env) { struct bpf_subprog_info *subprog = env->subprog_info; struct bpf_insn_aux_data *aux = env->insn_aux_data; @@ -21258,8 +21257,8 @@ static int remove_nocsr_spills_fills(struct bpf_verifier_env *env) int i, j; for (i = 0; i < insn_cnt; i++, insn++) { - if (aux[i].nocsr_spills_num > 0) { - spills_num = aux[i].nocsr_spills_num; + if (aux[i].fastcall_spills_num > 0) { + spills_num = aux[i].fastcall_spills_num; /* NOPs would be removed by opt_remove_nops() */ for (j = 1; j <= spills_num; ++j) { *(insn - j) = NOP; @@ -21268,8 +21267,8 @@ static int remove_nocsr_spills_fills(struct bpf_verifier_env *env) modified = true; } if ((subprog + 1)->start == i + 1) { - if (modified && !subprog->keep_nocsr_stack) - subprog->stack_depth = -subprog->nocsr_stack_off; + if (modified && !subprog->keep_fastcall_stack) + subprog->stack_depth = -subprog->fastcall_stack_off; subprog++; modified = false; } @@ -22192,7 +22191,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 if (ret < 0) goto skip_full_check; - ret = mark_nocsr_patterns(env); + ret = mark_fastcall_patterns(env); if (ret < 0) goto skip_full_check; @@ -22209,7 +22208,7 @@ skip_full_check: * allocate additional slots. */ if (ret == 0) - ret = remove_nocsr_spills_fills(env); + ret = remove_fastcall_spills_fills(env); if (ret == 0) ret = check_max_stack_depth(env); -- cgit v1.2.3 From aa35e56a5217b86f9c05420c36c908baf3b2df5f Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 19 Aug 2024 18:00:19 +0200 Subject: thermal: core: Introduce .should_bind() thermal zone callback The current design of the code binding cooling devices to trip points in thermal zones is convoluted and hard to follow. Namely, a driver that registers a thermal zone can provide .bind() and .unbind() operations for it, which are required to call either thermal_bind_cdev_to_trip() and thermal_unbind_cdev_from_trip(), respectively, or thermal_zone_bind_cooling_device() and thermal_zone_unbind_cooling_device(), respectively, for every relevant trip point and the given cooling device. Moreover, if .bind() is provided and .unbind() is not, the cleanup necessary during the removal of a thermal zone or a cooling device may not be carried out. In other words, the core relies on the thermal zone owners to do the right thing, which is error prone and far from obvious, even though all of that is not really necessary. Specifically, if the core could ask the thermal zone owner, through a special thermal zone callback, whether or not a given cooling device should be bound to a given trip point in the given thermal zone, it might as well carry out all of the binding and unbinding by itself. In particular, the unbinding can be done automatically without involving the thermal zone owner at all because all of the thermal instances associated with a thermal zone or cooling device going away must be deleted regardless. Accordingly, introduce a new thermal zone operation, .should_bind(), that can be invoked by the thermal core for a given thermal zone, trip point and cooling device combination in order to check whether or not the cooling device should be bound to the trip point at hand. It takes an additional cooling_spec argument allowing the thermal zone owner to specify the highest and lowest cooling states of the cooling device and its weight for the given trip point binding. Make the thermal core use this operation, if present, in the absence of .bind() and .unbind(). Note that .should_bind() will be called under the thermal zone lock. No intentional functional impact. Signed-off-by: Rafael J. Wysocki Reviewed-by: Zhang Rui Acked-by: Huisong Li Reviewed-by: Daniel Lezcano Link: https://patch.msgid.link/9334403.CDJkKcVGEf@rjwysocki.net --- drivers/thermal/thermal_core.c | 106 +++++++++++++++++++++++++++++++---------- include/linux/thermal.h | 10 ++++ 2 files changed, 92 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 6980d750e926..2faa95083320 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -999,12 +999,61 @@ static struct class *thermal_class; static inline void print_bind_err_msg(struct thermal_zone_device *tz, + const struct thermal_trip *trip, struct thermal_cooling_device *cdev, int ret) { + if (trip) { + dev_err(&tz->device, "binding cdev %s to trip %d failed: %d\n", + cdev->type, thermal_zone_trip_id(tz, trip), ret); + return; + } + dev_err(&tz->device, "binding zone %s with cdev %s failed:%d\n", tz->type, cdev->type, ret); } +static void thermal_zone_cdev_binding(struct thermal_zone_device *tz, + struct thermal_cooling_device *cdev) +{ + struct thermal_trip_desc *td; + int ret; + + /* + * Old-style binding. The .bind() callback is expected to call + * thermal_bind_cdev_to_trip() under the thermal zone lock. + */ + if (tz->ops.bind) { + ret = tz->ops.bind(tz, cdev); + if (ret) + print_bind_err_msg(tz, NULL, cdev, ret); + + return; + } + + if (!tz->ops.should_bind) + return; + + mutex_lock(&tz->lock); + + for_each_trip_desc(tz, td) { + struct thermal_trip *trip = &td->trip; + struct cooling_spec c = { + .upper = THERMAL_NO_LIMIT, + .lower = THERMAL_NO_LIMIT, + .weight = THERMAL_WEIGHT_DEFAULT + }; + + if (tz->ops.should_bind(tz, trip, cdev, &c)) { + ret = thermal_bind_cdev_to_trip(tz, trip, cdev, c.upper, + c.lower, c.weight); + if (ret) + print_bind_err_msg(tz, trip, cdev, ret); + } + } + + mutex_unlock(&tz->lock); +} + /** * __thermal_cooling_device_register() - register a new thermal cooling device * @np: a pointer to a device tree node. @@ -1100,13 +1149,8 @@ __thermal_cooling_device_register(struct device_node *np, list_add(&cdev->node, &thermal_cdev_list); /* Update binding information for 'this' new cdev */ - list_for_each_entry(pos, &thermal_tz_list, node) { - if (pos->ops.bind) { - ret = pos->ops.bind(pos, cdev); - if (ret) - print_bind_err_msg(pos, cdev, ret); - } - } + list_for_each_entry(pos, &thermal_tz_list, node) + thermal_zone_cdev_binding(pos, cdev); list_for_each_entry(pos, &thermal_tz_list, node) if (atomic_cmpxchg(&pos->need_update, 1, 0)) @@ -1307,6 +1351,28 @@ unlock_list: } EXPORT_SYMBOL_GPL(thermal_cooling_device_update); +static void thermal_zone_cdev_unbinding(struct thermal_zone_device *tz, + struct thermal_cooling_device *cdev) +{ + struct thermal_trip_desc *td; + + /* + * Old-style unbinding. The .unbind callback is expected to call + * thermal_unbind_cdev_from_trip() under the thermal zone lock. + */ + if (tz->ops.unbind) { + tz->ops.unbind(tz, cdev); + return; + } + + mutex_lock(&tz->lock); + + for_each_trip_desc(tz, td) + thermal_unbind_cdev_from_trip(tz, &td->trip, cdev); + + mutex_unlock(&tz->lock); +} + /** * thermal_cooling_device_unregister - removes a thermal cooling device * @cdev: the thermal cooling device to remove. @@ -1333,10 +1399,8 @@ void thermal_cooling_device_unregister(struct thermal_cooling_device *cdev) list_del(&cdev->node); /* Unbind all thermal zones associated with 'this' cdev */ - list_for_each_entry(tz, &thermal_tz_list, node) { - if (tz->ops.unbind) - tz->ops.unbind(tz, cdev); - } + list_for_each_entry(tz, &thermal_tz_list, node) + thermal_zone_cdev_unbinding(tz, cdev); mutex_unlock(&thermal_list_lock); @@ -1411,6 +1475,7 @@ thermal_zone_device_register_with_trips(const char *type, unsigned int polling_delay) { const struct thermal_trip *trip = trips; + struct thermal_cooling_device *cdev; struct thermal_zone_device *tz; struct thermal_trip_desc *td; int id; @@ -1433,8 +1498,9 @@ thermal_zone_device_register_with_trips(const char *type, return ERR_PTR(-EINVAL); } - if (!ops || !ops->get_temp) { - pr_err("Thermal zone device ops not defined\n"); + if (!ops || !ops->get_temp || (ops->should_bind && ops->bind) || + (ops->should_bind && ops->unbind)) { + pr_err("Thermal zone device ops not defined or invalid\n"); return ERR_PTR(-EINVAL); } @@ -1547,15 +1613,8 @@ thermal_zone_device_register_with_trips(const char *type, mutex_unlock(&tz->lock); /* Bind cooling devices for this zone */ - if (tz->ops.bind) { - struct thermal_cooling_device *cdev; - - list_for_each_entry(cdev, &thermal_cdev_list, node) { - result = tz->ops.bind(tz, cdev); - if (result) - print_bind_err_msg(tz, cdev, result); - } - } + list_for_each_entry(cdev, &thermal_cdev_list, node) + thermal_zone_cdev_binding(tz, cdev); mutex_unlock(&thermal_list_lock); @@ -1649,8 +1708,7 @@ void thermal_zone_device_unregister(struct thermal_zone_device *tz) /* Unbind all cdevs associated with 'this' thermal zone */ list_for_each_entry(cdev, &thermal_cdev_list, node) - if (tz->ops.unbind) - tz->ops.unbind(tz, cdev); + thermal_zone_cdev_unbinding(tz, cdev); mutex_unlock(&thermal_list_lock); diff --git a/include/linux/thermal.h b/include/linux/thermal.h index ba6d74c11620..9c5d1f14224f 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -85,11 +85,21 @@ struct thermal_trip { struct thermal_zone_device; +struct cooling_spec { + unsigned long upper; /* Highest cooling state */ + unsigned long lower; /* Lowest cooling state */ + unsigned int weight; /* Cooling device weight */ +}; + struct thermal_zone_device_ops { int (*bind) (struct thermal_zone_device *, struct thermal_cooling_device *); int (*unbind) (struct thermal_zone_device *, struct thermal_cooling_device *); + bool (*should_bind) (struct thermal_zone_device *, + const struct thermal_trip *, + struct thermal_cooling_device *, + struct cooling_spec *); int (*get_temp) (struct thermal_zone_device *, int *); int (*set_trips) (struct thermal_zone_device *, int, int); int (*change_mode) (struct thermal_zone_device *, -- cgit v1.2.3 From 2fb85633641770d55b50c934db6b4fb02411a1fe Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 19 Aug 2024 18:05:00 +0200 Subject: thermal: core: Unexport thermal_bind_cdev_to_trip() and thermal_unbind_cdev_from_trip() Since thermal_bind_cdev_to_trip() and thermal_unbind_cdev_from_trip() are only called locally in the thermal core now, they can be static, so change their definitions accordingly and drop their headers from the global thermal header file. No intentional functional impact. Signed-off-by: Rafael J. Wysocki Reviewed-by: Zhang Rui Acked-by: Huisong Li Reviewed-by: Daniel Lezcano Link: https://patch.msgid.link/3512161.QJadu78ljV@rjwysocki.net --- drivers/thermal/thermal_core.c | 10 ++++------ include/linux/thermal.h | 8 -------- 2 files changed, 4 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 2faa95083320..68fb85c18afa 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -781,7 +781,7 @@ struct thermal_zone_device *thermal_zone_get_by_id(int id) * * Return: 0 on success, the proper error value otherwise. */ -int thermal_bind_cdev_to_trip(struct thermal_zone_device *tz, +static int thermal_bind_cdev_to_trip(struct thermal_zone_device *tz, const struct thermal_trip *trip, struct thermal_cooling_device *cdev, unsigned long upper, unsigned long lower, @@ -885,7 +885,6 @@ free_mem: kfree(dev); return result; } -EXPORT_SYMBOL_GPL(thermal_bind_cdev_to_trip); int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz, int trip_index, @@ -921,9 +920,9 @@ EXPORT_SYMBOL_GPL(thermal_zone_bind_cooling_device); * * Return: 0 on success, the proper error value otherwise. */ -int thermal_unbind_cdev_from_trip(struct thermal_zone_device *tz, - const struct thermal_trip *trip, - struct thermal_cooling_device *cdev) +static int thermal_unbind_cdev_from_trip(struct thermal_zone_device *tz, + const struct thermal_trip *trip, + struct thermal_cooling_device *cdev) { struct thermal_instance *pos, *next; @@ -953,7 +952,6 @@ unbind: kfree(pos); return 0; } -EXPORT_SYMBOL_GPL(thermal_unbind_cdev_from_trip); int thermal_zone_unbind_cooling_device(struct thermal_zone_device *tz, int trip_index, diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 9c5d1f14224f..6599a26847f7 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -247,18 +247,10 @@ const char *thermal_zone_device_type(struct thermal_zone_device *tzd); int thermal_zone_device_id(struct thermal_zone_device *tzd); struct device *thermal_zone_device(struct thermal_zone_device *tzd); -int thermal_bind_cdev_to_trip(struct thermal_zone_device *tz, - const struct thermal_trip *trip, - struct thermal_cooling_device *cdev, - unsigned long upper, unsigned long lower, - unsigned int weight); int thermal_zone_bind_cooling_device(struct thermal_zone_device *, int, struct thermal_cooling_device *, unsigned long, unsigned long, unsigned int); -int thermal_unbind_cdev_from_trip(struct thermal_zone_device *tz, - const struct thermal_trip *trip, - struct thermal_cooling_device *cdev); int thermal_zone_unbind_cooling_device(struct thermal_zone_device *, int, struct thermal_cooling_device *); void thermal_zone_device_update(struct thermal_zone_device *, -- cgit v1.2.3 From d51e783c17bab0c139bf78d6bd9d1f66673f7903 Mon Sep 17 00:00:00 2001 From: KP Singh Date: Fri, 16 Aug 2024 17:43:06 +0200 Subject: lsm: count the LSMs enabled at compile time These macros are a clever trick to determine a count of the number of LSMs that are enabled in the config to ascertain the maximum number of static calls that need to be configured per LSM hook. Without this one would need to generate static calls for the total number of LSMs in the kernel (even if they are not compiled) times the number of LSM hooks which ends up being quite wasteful. Tested-by: Guenter Roeck Suggested-by: Kui-Feng Lee Suggested-by: Andrii Nakryiko Reviewed-by: Kees Cook Reviewed-by: Casey Schaufler Reviewed-by: John Johansen Acked-by: Casey Schaufler Acked-by: Song Liu Acked-by: Andrii Nakryiko Nacked-by: Tetsuo Handa Signed-off-by: KP Singh [PM: added IPE to the count during merge] Signed-off-by: Paul Moore --- include/linux/args.h | 6 +-- include/linux/lsm_count.h | 135 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 138 insertions(+), 3 deletions(-) create mode 100644 include/linux/lsm_count.h (limited to 'include/linux') diff --git a/include/linux/args.h b/include/linux/args.h index 8ff60a54eb7d..2e8e65d975c7 100644 --- a/include/linux/args.h +++ b/include/linux/args.h @@ -17,9 +17,9 @@ * that as _n. */ -/* This counts to 12. Any more, it will return 13th argument. */ -#define __COUNT_ARGS(_0, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, _n, X...) _n -#define COUNT_ARGS(X...) __COUNT_ARGS(, ##X, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) +/* This counts to 15. Any more, it will return 16th argument. */ +#define __COUNT_ARGS(_0, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, _13, _14, _15, _n, X...) _n +#define COUNT_ARGS(X...) __COUNT_ARGS(, ##X, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) /* Concatenate two parameters, but allow them to be expanded beforehand. */ #define __CONCAT(a, b) a ## b diff --git a/include/linux/lsm_count.h b/include/linux/lsm_count.h new file mode 100644 index 000000000000..16eb49761b25 --- /dev/null +++ b/include/linux/lsm_count.h @@ -0,0 +1,135 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Copyright (C) 2023 Google LLC. + */ + +#ifndef __LINUX_LSM_COUNT_H +#define __LINUX_LSM_COUNT_H + +#include + +#ifdef CONFIG_SECURITY + +/* + * Macros to count the number of LSMs enabled in the kernel at compile time. + */ + +/* + * Capabilities is enabled when CONFIG_SECURITY is enabled. + */ +#if IS_ENABLED(CONFIG_SECURITY) +#define CAPABILITIES_ENABLED 1, +#else +#define CAPABILITIES_ENABLED +#endif + +#if IS_ENABLED(CONFIG_SECURITY_SELINUX) +#define SELINUX_ENABLED 1, +#else +#define SELINUX_ENABLED +#endif + +#if IS_ENABLED(CONFIG_SECURITY_SMACK) +#define SMACK_ENABLED 1, +#else +#define SMACK_ENABLED +#endif + +#if IS_ENABLED(CONFIG_SECURITY_APPARMOR) +#define APPARMOR_ENABLED 1, +#else +#define APPARMOR_ENABLED +#endif + +#if IS_ENABLED(CONFIG_SECURITY_TOMOYO) +#define TOMOYO_ENABLED 1, +#else +#define TOMOYO_ENABLED +#endif + +#if IS_ENABLED(CONFIG_SECURITY_YAMA) +#define YAMA_ENABLED 1, +#else +#define YAMA_ENABLED +#endif + +#if IS_ENABLED(CONFIG_SECURITY_LOADPIN) +#define LOADPIN_ENABLED 1, +#else +#define LOADPIN_ENABLED +#endif + +#if IS_ENABLED(CONFIG_SECURITY_LOCKDOWN_LSM) +#define LOCKDOWN_ENABLED 1, +#else +#define LOCKDOWN_ENABLED +#endif + +#if IS_ENABLED(CONFIG_SECURITY_SAFESETID) +#define SAFESETID_ENABLED 1, +#else +#define SAFESETID_ENABLED +#endif + +#if IS_ENABLED(CONFIG_BPF_LSM) +#define BPF_LSM_ENABLED 1, +#else +#define BPF_LSM_ENABLED +#endif + +#if IS_ENABLED(CONFIG_SECURITY_LANDLOCK) +#define LANDLOCK_ENABLED 1, +#else +#define LANDLOCK_ENABLED +#endif + +#if IS_ENABLED(CONFIG_IMA) +#define IMA_ENABLED 1, +#else +#define IMA_ENABLED +#endif + +#if IS_ENABLED(CONFIG_EVM) +#define EVM_ENABLED 1, +#else +#define EVM_ENABLED +#endif + +#if IS_ENABLED(CONFIG_SECURITY_IPE) +#define IPE_ENABLED 1, +#else +#define IPE_ENABLED +#endif + +/* + * There is a trailing comma that we need to be accounted for. This is done by + * using a skipped argument in __COUNT_LSMS + */ +#define __COUNT_LSMS(skipped_arg, args...) COUNT_ARGS(args...) +#define COUNT_LSMS(args...) __COUNT_LSMS(args) + +#define MAX_LSM_COUNT \ + COUNT_LSMS( \ + CAPABILITIES_ENABLED \ + SELINUX_ENABLED \ + SMACK_ENABLED \ + APPARMOR_ENABLED \ + TOMOYO_ENABLED \ + YAMA_ENABLED \ + LOADPIN_ENABLED \ + LOCKDOWN_ENABLED \ + SAFESETID_ENABLED \ + BPF_LSM_ENABLED \ + LANDLOCK_ENABLED \ + IMA_ENABLED \ + EVM_ENABLED \ + IPE_ENABLED) + +#else + +#define MAX_LSM_COUNT 0 + +#endif /* CONFIG_SECURITY */ + +#endif /* __LINUX_LSM_COUNT_H */ -- cgit v1.2.3 From 417c5643cd67a55f424b203b492082035d0236c3 Mon Sep 17 00:00:00 2001 From: KP Singh Date: Fri, 16 Aug 2024 17:43:07 +0200 Subject: lsm: replace indirect LSM hook calls with static calls LSM hooks are currently invoked from a linked list as indirect calls which are invoked using retpolines as a mitigation for speculative attacks (Branch History / Target injection) and add extra overhead which is especially bad in kernel hot paths: security_file_ioctl: 0xff...0320 <+0>: endbr64 0xff...0324 <+4>: push %rbp 0xff...0325 <+5>: push %r15 0xff...0327 <+7>: push %r14 0xff...0329 <+9>: push %rbx 0xff...032a <+10>: mov %rdx,%rbx 0xff...032d <+13>: mov %esi,%ebp 0xff...032f <+15>: mov %rdi,%r14 0xff...0332 <+18>: mov $0xff...7030,%r15 0xff...0339 <+25>: mov (%r15),%r15 0xff...033c <+28>: test %r15,%r15 0xff...033f <+31>: je 0xff...0358 0xff...0341 <+33>: mov 0x18(%r15),%r11 0xff...0345 <+37>: mov %r14,%rdi 0xff...0348 <+40>: mov %ebp,%esi 0xff...034a <+42>: mov %rbx,%rdx 0xff...034d <+45>: call 0xff...2e0 <__x86_indirect_thunk_array+352> ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Indirect calls that use retpolines leading to overhead, not just due to extra instruction but also branch misses. 0xff...0352 <+50>: test %eax,%eax 0xff...0354 <+52>: je 0xff...0339 0xff...0356 <+54>: jmp 0xff...035a 0xff...0358 <+56>: xor %eax,%eax 0xff...035a <+58>: pop %rbx 0xff...035b <+59>: pop %r14 0xff...035d <+61>: pop %r15 0xff...035f <+63>: pop %rbp 0xff...0360 <+64>: jmp 0xff...47c4 <__x86_return_thunk> The indirect calls are not really needed as one knows the addresses of enabled LSM callbacks at boot time and only the order can possibly change at boot time with the lsm= kernel command line parameter. An array of static calls is defined per LSM hook and the static calls are updated at boot time once the order has been determined. With the hook now exposed as a static call, one can see that the retpolines are no longer there and the LSM callbacks are invoked directly: security_file_ioctl: 0xff...0ca0 <+0>: endbr64 0xff...0ca4 <+4>: nopl 0x0(%rax,%rax,1) 0xff...0ca9 <+9>: push %rbp 0xff...0caa <+10>: push %r14 0xff...0cac <+12>: push %rbx 0xff...0cad <+13>: mov %rdx,%rbx 0xff...0cb0 <+16>: mov %esi,%ebp 0xff...0cb2 <+18>: mov %rdi,%r14 0xff...0cb5 <+21>: jmp 0xff...0cc7 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Static key enabled for SELinux 0xffffffff818f0cb7 <+23>: jmp 0xff...0cde ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Static key enabled for BPF LSM. This is something that is changed to default to false to avoid the existing side effect issues of BPF LSM [1] in a subsequent patch. 0xff...0cb9 <+25>: xor %eax,%eax 0xff...0cbb <+27>: xchg %ax,%ax 0xff...0cbd <+29>: pop %rbx 0xff...0cbe <+30>: pop %r14 0xff...0cc0 <+32>: pop %rbp 0xff...0cc1 <+33>: cs jmp 0xff...0000 <__x86_return_thunk> 0xff...0cc7 <+39>: endbr64 0xff...0ccb <+43>: mov %r14,%rdi 0xff...0cce <+46>: mov %ebp,%esi 0xff...0cd0 <+48>: mov %rbx,%rdx 0xff...0cd3 <+51>: call 0xff...3230 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Direct call to SELinux. 0xff...0cd8 <+56>: test %eax,%eax 0xff...0cda <+58>: jne 0xff...0cbd 0xff...0cdc <+60>: jmp 0xff...0cb7 0xff...0cde <+62>: endbr64 0xff...0ce2 <+66>: mov %r14,%rdi 0xff...0ce5 <+69>: mov %ebp,%esi 0xff...0ce7 <+71>: mov %rbx,%rdx 0xff...0cea <+74>: call 0xff...e220 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Direct call to BPF LSM. 0xff...0cef <+79>: test %eax,%eax 0xff...0cf1 <+81>: jne 0xff...0cbd 0xff...0cf3 <+83>: jmp 0xff...0cb9 0xff...0cf5 <+85>: endbr64 0xff...0cf9 <+89>: mov %r14,%rdi 0xff...0cfc <+92>: mov %ebp,%esi 0xff...0cfe <+94>: mov %rbx,%rdx 0xff...0d01 <+97>: pop %rbx 0xff...0d02 <+98>: pop %r14 0xff...0d04 <+100>: pop %rbp 0xff...0d05 <+101>: ret 0xff...0d06 <+102>: int3 0xff...0d07 <+103>: int3 0xff...0d08 <+104>: int3 0xff...0d09 <+105>: int3 While this patch uses static_branch_unlikely indicating that an LSM hook is likely to be not present. In most cases this is still a better choice as even when an LSM with one hook is added, empty slots are created for all LSM hooks (especially when many LSMs that do not initialize most hooks are present on the system). There are some hooks that don't use the call_int_hook or call_void_hook. These hooks are updated to use a new macro called lsm_for_each_hook where the lsm_callback is directly invoked as an indirect call. Below are results of the relevant Unixbench system benchmarks with BPF LSM and SELinux enabled with default policies enabled with and without these patches. Benchmark Delta(%): (+ is better) ========================================================================== Execl Throughput +1.9356 File Write 1024 bufsize 2000 maxblocks +6.5953 Pipe Throughput +9.5499 Pipe-based Context Switching +3.0209 Process Creation +2.3246 Shell Scripts (1 concurrent) +1.4975 System Call Overhead +2.7815 System Benchmarks Index Score (Partial Only): +3.4859 In the best case, some syscalls like eventfd_create benefitted to about ~10%. Tested-by: Guenter Roeck Reviewed-by: Casey Schaufler Reviewed-by: Kees Cook Acked-by: Song Liu Acked-by: Andrii Nakryiko Signed-off-by: KP Singh Signed-off-by: Paul Moore --- include/linux/lsm_hooks.h | 52 +++++++++-- security/security.c | 219 ++++++++++++++++++++++++++++++++-------------- 2 files changed, 198 insertions(+), 73 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 4687985b9175..090d1d3e19fe 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -30,19 +30,47 @@ #include #include #include +#include +#include +#include +#include union security_list_options { #define LSM_HOOK(RET, DEFAULT, NAME, ...) RET (*NAME)(__VA_ARGS__); #include "lsm_hook_defs.h" #undef LSM_HOOK + void *lsm_func_addr; }; -struct security_hook_heads { - #define LSM_HOOK(RET, DEFAULT, NAME, ...) struct hlist_head NAME; - #include "lsm_hook_defs.h" - #undef LSM_HOOK +/* + * @key: static call key as defined by STATIC_CALL_KEY + * @trampoline: static call trampoline as defined by STATIC_CALL_TRAMP + * @hl: The security_hook_list as initialized by the owning LSM. + * @active: Enabled when the static call has an LSM hook associated. + */ +struct lsm_static_call { + struct static_call_key *key; + void *trampoline; + struct security_hook_list *hl; + /* this needs to be true or false based on what the key defaults to */ + struct static_key_false *active; } __randomize_layout; +/* + * Table of the static calls for each LSM hook. + * Once the LSMs are initialized, their callbacks will be copied to these + * tables such that the calls are filled backwards (from last to first). + * This way, we can jump directly to the first used static call, and execute + * all of them after. This essentially makes the entry point + * dynamic to adapt the number of static calls to the number of callbacks. + */ +struct lsm_static_calls_table { + #define LSM_HOOK(RET, DEFAULT, NAME, ...) \ + struct lsm_static_call NAME[MAX_LSM_COUNT]; + #include + #undef LSM_HOOK +} __packed __randomize_layout; + /** * struct lsm_id - Identify a Linux Security Module. * @lsm: name of the LSM, must be approved by the LSM maintainers @@ -58,10 +86,14 @@ struct lsm_id { /* * Security module hook list structure. * For use with generic list macros for common operations. + * + * struct security_hook_list - Contents of a cacheable, mappable object. + * @scalls: The beginning of the array of static calls assigned to this hook. + * @hook: The callback for the hook. + * @lsm: The name of the lsm that owns this hook. */ struct security_hook_list { - struct hlist_node list; - struct hlist_head *head; + struct lsm_static_call *scalls; union security_list_options hook; const struct lsm_id *lsmid; } __randomize_layout; @@ -98,8 +130,11 @@ struct lsm_blob_sizes { * care of the common case and reduces the amount of * text involved. */ -#define LSM_HOOK_INIT(HEAD, HOOK) \ - { .head = &security_hook_heads.HEAD, .hook = { .HEAD = HOOK } } +#define LSM_HOOK_INIT(NAME, HOOK) \ + { \ + .scalls = static_calls_table.NAME, \ + .hook = { .NAME = HOOK } \ + } extern void security_add_hooks(struct security_hook_list *hooks, int count, const struct lsm_id *lsmid); @@ -134,7 +169,6 @@ struct lsm_info { /* DO NOT tamper with these variables outside of the LSM framework */ extern char *lsm_names; -extern struct security_hook_heads security_hook_heads; extern struct lsm_static_calls_table static_calls_table __ro_after_init; extern struct lsm_info __start_lsm_info[], __end_lsm_info[]; extern struct lsm_info __start_early_lsm_info[], __end_early_lsm_info[]; diff --git a/security/security.c b/security/security.c index bb43ad444f1f..3b888d5caf47 100644 --- a/security/security.c +++ b/security/security.c @@ -57,6 +57,25 @@ (IS_ENABLED(CONFIG_EVM) ? 1 : 0) + \ (IS_ENABLED(CONFIG_SECURITY_IPE) ? 1 : 0)) +#define SECURITY_HOOK_ACTIVE_KEY(HOOK, IDX) security_hook_active_##HOOK##_##IDX + +/* + * Identifier for the LSM static calls. + * HOOK is an LSM hook as defined in linux/lsm_hookdefs.h + * IDX is the index of the static call. 0 <= NUM < MAX_LSM_COUNT + */ +#define LSM_STATIC_CALL(HOOK, IDX) lsm_static_call_##HOOK##_##IDX + +/* + * Call the macro M for each LSM hook MAX_LSM_COUNT times. + */ +#define LSM_LOOP_UNROLL(M, ...) \ +do { \ + UNROLL(MAX_LSM_COUNT, M, __VA_ARGS__) \ +} while (0) + +#define LSM_DEFINE_UNROLL(M, ...) UNROLL(MAX_LSM_COUNT, M, __VA_ARGS__) + /* * These are descriptions of the reasons that can be passed to the * security_locked_down() LSM hook. Placing this array here allows @@ -96,7 +115,6 @@ const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX + 1] = { [LOCKDOWN_CONFIDENTIALITY_MAX] = "confidentiality", }; -struct security_hook_heads security_hook_heads __ro_after_init; static BLOCKING_NOTIFIER_HEAD(blocking_lsm_notifier_chain); static struct kmem_cache *lsm_file_cache; @@ -115,6 +133,55 @@ static __initconst const char *const builtin_lsm_order = CONFIG_LSM; static __initdata struct lsm_info **ordered_lsms; static __initdata struct lsm_info *exclusive; +#ifdef CONFIG_HAVE_STATIC_CALL +#define LSM_HOOK_TRAMP(NAME, NUM) \ + &STATIC_CALL_TRAMP(LSM_STATIC_CALL(NAME, NUM)) +#else +#define LSM_HOOK_TRAMP(NAME, NUM) NULL +#endif + +/* + * Define static calls and static keys for each LSM hook. + */ +#define DEFINE_LSM_STATIC_CALL(NUM, NAME, RET, ...) \ + DEFINE_STATIC_CALL_NULL(LSM_STATIC_CALL(NAME, NUM), \ + *((RET(*)(__VA_ARGS__))NULL)); \ + DEFINE_STATIC_KEY_FALSE(SECURITY_HOOK_ACTIVE_KEY(NAME, NUM)); + +#define LSM_HOOK(RET, DEFAULT, NAME, ...) \ + LSM_DEFINE_UNROLL(DEFINE_LSM_STATIC_CALL, NAME, RET, __VA_ARGS__) +#include +#undef LSM_HOOK +#undef DEFINE_LSM_STATIC_CALL + +/* + * Initialise a table of static calls for each LSM hook. + * DEFINE_STATIC_CALL_NULL invocation above generates a key (STATIC_CALL_KEY) + * and a trampoline (STATIC_CALL_TRAMP) which are used to call + * __static_call_update when updating the static call. + * + * The static calls table is used by early LSMs, some architectures can fault on + * unaligned accesses and the fault handling code may not be ready by then. + * Thus, the static calls table should be aligned to avoid any unhandled faults + * in early init. + */ +struct lsm_static_calls_table + static_calls_table __ro_after_init __aligned(sizeof(u64)) = { +#define INIT_LSM_STATIC_CALL(NUM, NAME) \ + (struct lsm_static_call) { \ + .key = &STATIC_CALL_KEY(LSM_STATIC_CALL(NAME, NUM)), \ + .trampoline = LSM_HOOK_TRAMP(NAME, NUM), \ + .active = &SECURITY_HOOK_ACTIVE_KEY(NAME, NUM), \ + }, +#define LSM_HOOK(RET, DEFAULT, NAME, ...) \ + .NAME = { \ + LSM_DEFINE_UNROLL(INIT_LSM_STATIC_CALL, NAME) \ + }, +#include +#undef LSM_HOOK +#undef INIT_LSM_STATIC_CALL + }; + static __initdata bool debug; #define init_debug(...) \ do { \ @@ -175,7 +242,7 @@ static void __init append_ordered_lsm(struct lsm_info *lsm, const char *from) if (exists_ordered_lsm(lsm)) return; - if (WARN(last_lsm == LSM_COUNT, "%s: out of LSM slots!?\n", from)) + if (WARN(last_lsm == LSM_COUNT, "%s: out of LSM static calls!?\n", from)) return; /* Enable this LSM, if it is not already set. */ @@ -360,6 +427,25 @@ static void __init ordered_lsm_parse(const char *order, const char *origin) kfree(sep); } +static void __init lsm_static_call_init(struct security_hook_list *hl) +{ + struct lsm_static_call *scall = hl->scalls; + int i; + + for (i = 0; i < MAX_LSM_COUNT; i++) { + /* Update the first static call that is not used yet */ + if (!scall->hl) { + __static_call_update(scall->key, scall->trampoline, + hl->hook.lsm_func_addr); + scall->hl = hl; + static_branch_enable(scall->active); + return; + } + scall++; + } + panic("%s - Ran out of static slots.\n", __func__); +} + static void __init lsm_early_cred(struct cred *cred); static void __init lsm_early_task(struct task_struct *task); @@ -447,11 +533,6 @@ int __init early_security_init(void) { struct lsm_info *lsm; -#define LSM_HOOK(RET, DEFAULT, NAME, ...) \ - INIT_HLIST_HEAD(&security_hook_heads.NAME); -#include "linux/lsm_hook_defs.h" -#undef LSM_HOOK - for (lsm = __start_early_lsm_info; lsm < __end_early_lsm_info; lsm++) { if (!lsm->enabled) lsm->enabled = &lsm_enabled_true; @@ -579,7 +660,7 @@ void __init security_add_hooks(struct security_hook_list *hooks, int count, for (i = 0; i < count; i++) { hooks[i].lsmid = lsmid; - hlist_add_tail_rcu(&hooks[i].list, hooks[i].head); + lsm_static_call_init(&hooks[i]); } /* @@ -893,29 +974,43 @@ out: * call_int_hook: * This is a hook that returns a value. */ +#define __CALL_STATIC_VOID(NUM, HOOK, ...) \ +do { \ + if (static_branch_unlikely(&SECURITY_HOOK_ACTIVE_KEY(HOOK, NUM))) { \ + static_call(LSM_STATIC_CALL(HOOK, NUM))(__VA_ARGS__); \ + } \ +} while (0); -#define call_void_hook(FUNC, ...) \ - do { \ - struct security_hook_list *P; \ - \ - hlist_for_each_entry(P, &security_hook_heads.FUNC, list) \ - P->hook.FUNC(__VA_ARGS__); \ +#define call_void_hook(HOOK, ...) \ + do { \ + LSM_LOOP_UNROLL(__CALL_STATIC_VOID, HOOK, __VA_ARGS__); \ } while (0) -#define call_int_hook(FUNC, ...) ({ \ - int RC = LSM_RET_DEFAULT(FUNC); \ - do { \ - struct security_hook_list *P; \ - \ - hlist_for_each_entry(P, &security_hook_heads.FUNC, list) { \ - RC = P->hook.FUNC(__VA_ARGS__); \ - if (RC != LSM_RET_DEFAULT(FUNC)) \ - break; \ - } \ - } while (0); \ - RC; \ + +#define __CALL_STATIC_INT(NUM, R, HOOK, LABEL, ...) \ +do { \ + if (static_branch_unlikely(&SECURITY_HOOK_ACTIVE_KEY(HOOK, NUM))) { \ + R = static_call(LSM_STATIC_CALL(HOOK, NUM))(__VA_ARGS__); \ + if (R != LSM_RET_DEFAULT(HOOK)) \ + goto LABEL; \ + } \ +} while (0); + +#define call_int_hook(HOOK, ...) \ +({ \ + __label__ OUT; \ + int RC = LSM_RET_DEFAULT(HOOK); \ + \ + LSM_LOOP_UNROLL(__CALL_STATIC_INT, RC, HOOK, OUT, __VA_ARGS__); \ +OUT: \ + RC; \ }) +#define lsm_for_each_hook(scall, NAME) \ + for (scall = static_calls_table.NAME; \ + scall - static_calls_table.NAME < MAX_LSM_COUNT; scall++) \ + if (static_key_enabled(&scall->active->key)) + /* Security operations */ /** @@ -1150,7 +1245,7 @@ int security_settime64(const struct timespec64 *ts, const struct timezone *tz) */ int security_vm_enough_memory_mm(struct mm_struct *mm, long pages) { - struct security_hook_list *hp; + struct lsm_static_call *scall; int cap_sys_admin = 1; int rc; @@ -1160,8 +1255,8 @@ int security_vm_enough_memory_mm(struct mm_struct *mm, long pages) * agree that it should be set it will. If any module thinks it should * not be set it won't. */ - hlist_for_each_entry(hp, &security_hook_heads.vm_enough_memory, list) { - rc = hp->hook.vm_enough_memory(mm, pages); + lsm_for_each_hook(scall, vm_enough_memory) { + rc = scall->hl->hook.vm_enough_memory(mm, pages); if (rc < 0) { cap_sys_admin = 0; break; @@ -1308,13 +1403,12 @@ int security_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc) int security_fs_context_parse_param(struct fs_context *fc, struct fs_parameter *param) { - struct security_hook_list *hp; + struct lsm_static_call *scall; int trc; int rc = -ENOPARAM; - hlist_for_each_entry(hp, &security_hook_heads.fs_context_parse_param, - list) { - trc = hp->hook.fs_context_parse_param(fc, param); + lsm_for_each_hook(scall, fs_context_parse_param) { + trc = scall->hl->hook.fs_context_parse_param(fc, param); if (trc == 0) rc = 0; else if (trc != -ENOPARAM) @@ -1544,12 +1638,11 @@ int security_sb_set_mnt_opts(struct super_block *sb, unsigned long kern_flags, unsigned long *set_kern_flags) { - struct security_hook_list *hp; + struct lsm_static_call *scall; int rc = mnt_opts ? -EOPNOTSUPP : LSM_RET_DEFAULT(sb_set_mnt_opts); - hlist_for_each_entry(hp, &security_hook_heads.sb_set_mnt_opts, - list) { - rc = hp->hook.sb_set_mnt_opts(sb, mnt_opts, kern_flags, + lsm_for_each_hook(scall, sb_set_mnt_opts) { + rc = scall->hl->hook.sb_set_mnt_opts(sb, mnt_opts, kern_flags, set_kern_flags); if (rc != LSM_RET_DEFAULT(sb_set_mnt_opts)) break; @@ -1744,7 +1837,7 @@ int security_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, const initxattrs initxattrs, void *fs_data) { - struct security_hook_list *hp; + struct lsm_static_call *scall; struct xattr *new_xattrs = NULL; int ret = -EOPNOTSUPP, xattr_count = 0; @@ -1762,9 +1855,8 @@ int security_inode_init_security(struct inode *inode, struct inode *dir, return -ENOMEM; } - hlist_for_each_entry(hp, &security_hook_heads.inode_init_security, - list) { - ret = hp->hook.inode_init_security(inode, dir, qstr, new_xattrs, + lsm_for_each_hook(scall, inode_init_security) { + ret = scall->hl->hook.inode_init_security(inode, dir, qstr, new_xattrs, &xattr_count); if (ret && ret != -EOPNOTSUPP) goto out; @@ -3611,10 +3703,10 @@ int security_task_prctl(int option, unsigned long arg2, unsigned long arg3, { int thisrc; int rc = LSM_RET_DEFAULT(task_prctl); - struct security_hook_list *hp; + struct lsm_static_call *scall; - hlist_for_each_entry(hp, &security_hook_heads.task_prctl, list) { - thisrc = hp->hook.task_prctl(option, arg2, arg3, arg4, arg5); + lsm_for_each_hook(scall, task_prctl) { + thisrc = scall->hl->hook.task_prctl(option, arg2, arg3, arg4, arg5); if (thisrc != LSM_RET_DEFAULT(task_prctl)) { rc = thisrc; if (thisrc != 0) @@ -4020,7 +4112,7 @@ EXPORT_SYMBOL(security_d_instantiate); int security_getselfattr(unsigned int attr, struct lsm_ctx __user *uctx, u32 __user *size, u32 flags) { - struct security_hook_list *hp; + struct lsm_static_call *scall; struct lsm_ctx lctx = { .id = LSM_ID_UNDEF, }; u8 __user *base = (u8 __user *)uctx; u32 entrysize; @@ -4058,13 +4150,13 @@ int security_getselfattr(unsigned int attr, struct lsm_ctx __user *uctx, * In the usual case gather all the data from the LSMs. * In the single case only get the data from the LSM specified. */ - hlist_for_each_entry(hp, &security_hook_heads.getselfattr, list) { - if (single && lctx.id != hp->lsmid->id) + lsm_for_each_hook(scall, getselfattr) { + if (single && lctx.id != scall->hl->lsmid->id) continue; entrysize = left; if (base) uctx = (struct lsm_ctx __user *)(base + total); - rc = hp->hook.getselfattr(attr, uctx, &entrysize, flags); + rc = scall->hl->hook.getselfattr(attr, uctx, &entrysize, flags); if (rc == -EOPNOTSUPP) { rc = 0; continue; @@ -4113,7 +4205,7 @@ int security_getselfattr(unsigned int attr, struct lsm_ctx __user *uctx, int security_setselfattr(unsigned int attr, struct lsm_ctx __user *uctx, u32 size, u32 flags) { - struct security_hook_list *hp; + struct lsm_static_call *scall; struct lsm_ctx *lctx; int rc = LSM_RET_DEFAULT(setselfattr); u64 required_len; @@ -4136,9 +4228,9 @@ int security_setselfattr(unsigned int attr, struct lsm_ctx __user *uctx, goto free_out; } - hlist_for_each_entry(hp, &security_hook_heads.setselfattr, list) - if ((hp->lsmid->id) == lctx->id) { - rc = hp->hook.setselfattr(attr, lctx, size, flags); + lsm_for_each_hook(scall, setselfattr) + if ((scall->hl->lsmid->id) == lctx->id) { + rc = scall->hl->hook.setselfattr(attr, lctx, size, flags); break; } @@ -4161,12 +4253,12 @@ free_out: int security_getprocattr(struct task_struct *p, int lsmid, const char *name, char **value) { - struct security_hook_list *hp; + struct lsm_static_call *scall; - hlist_for_each_entry(hp, &security_hook_heads.getprocattr, list) { - if (lsmid != 0 && lsmid != hp->lsmid->id) + lsm_for_each_hook(scall, getprocattr) { + if (lsmid != 0 && lsmid != scall->hl->lsmid->id) continue; - return hp->hook.getprocattr(p, name, value); + return scall->hl->hook.getprocattr(p, name, value); } return LSM_RET_DEFAULT(getprocattr); } @@ -4185,12 +4277,12 @@ int security_getprocattr(struct task_struct *p, int lsmid, const char *name, */ int security_setprocattr(int lsmid, const char *name, void *value, size_t size) { - struct security_hook_list *hp; + struct lsm_static_call *scall; - hlist_for_each_entry(hp, &security_hook_heads.setprocattr, list) { - if (lsmid != 0 && lsmid != hp->lsmid->id) + lsm_for_each_hook(scall, setprocattr) { + if (lsmid != 0 && lsmid != scall->hl->lsmid->id) continue; - return hp->hook.setprocattr(name, value, size); + return scall->hl->hook.setprocattr(name, value, size); } return LSM_RET_DEFAULT(setprocattr); } @@ -5322,7 +5414,7 @@ int security_xfrm_state_pol_flow_match(struct xfrm_state *x, struct xfrm_policy *xp, const struct flowi_common *flic) { - struct security_hook_list *hp; + struct lsm_static_call *scall; int rc = LSM_RET_DEFAULT(xfrm_state_pol_flow_match); /* @@ -5334,9 +5426,8 @@ int security_xfrm_state_pol_flow_match(struct xfrm_state *x, * For speed optimization, we explicitly break the loop rather than * using the macro */ - hlist_for_each_entry(hp, &security_hook_heads.xfrm_state_pol_flow_match, - list) { - rc = hp->hook.xfrm_state_pol_flow_match(x, xp, flic); + lsm_for_each_hook(scall, xfrm_state_pol_flow_match) { + rc = scall->hl->hook.xfrm_state_pol_flow_match(x, xp, flic); break; } return rc; -- cgit v1.2.3 From 6c65914a40d33e96ceedc757be0129139cdf7852 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Fri, 16 Aug 2024 11:54:23 -0700 Subject: Input: keypad-nomadik-ske - remove the driver The users of this driver were removed in 2013 in commit 28633c54bda6 ("ARM: ux500: Rip out keypad initialisation which is no longer used"). Remove the driver as well. Acked-by: Arnd Bergmann Link: https://lore.kernel.org/r/Zr-gX0dfN4te_8VG@google.com Signed-off-by: Dmitry Torokhov --- drivers/input/keyboard/Kconfig | 11 - drivers/input/keyboard/Makefile | 1 - drivers/input/keyboard/nomadik-ske-keypad.c | 378 ----------------------- include/linux/platform_data/keypad-nomadik-ske.h | 50 --- 4 files changed, 440 deletions(-) delete mode 100644 drivers/input/keyboard/nomadik-ske-keypad.c delete mode 100644 include/linux/platform_data/keypad-nomadik-ske.h (limited to 'include/linux') diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig index 72f9552cb571..a5015d6f8bed 100644 --- a/drivers/input/keyboard/Kconfig +++ b/drivers/input/keyboard/Kconfig @@ -473,17 +473,6 @@ config KEYBOARD_NEWTON To compile this driver as a module, choose M here: the module will be called newtonkbd. -config KEYBOARD_NOMADIK - tristate "ST-Ericsson Nomadik SKE keyboard" - depends on (ARCH_NOMADIK || ARCH_U8500 || COMPILE_TEST) - select INPUT_MATRIXKMAP - help - Say Y here if you want to use a keypad provided on the SKE controller - used on the Ux500 and Nomadik platforms - - To compile this driver as a module, choose M here: the - module will be called nmk-ske-keypad. - config KEYBOARD_NSPIRE tristate "TI-NSPIRE built-in keyboard" depends on ARCH_NSPIRE && OF diff --git a/drivers/input/keyboard/Makefile b/drivers/input/keyboard/Makefile index b8d12a0524e0..3631a9294c6f 100644 --- a/drivers/input/keyboard/Makefile +++ b/drivers/input/keyboard/Makefile @@ -45,7 +45,6 @@ obj-$(CONFIG_KEYBOARD_MPR121) += mpr121_touchkey.o obj-$(CONFIG_KEYBOARD_MT6779) += mt6779-keypad.o obj-$(CONFIG_KEYBOARD_MTK_PMIC) += mtk-pmic-keys.o obj-$(CONFIG_KEYBOARD_NEWTON) += newtonkbd.o -obj-$(CONFIG_KEYBOARD_NOMADIK) += nomadik-ske-keypad.o obj-$(CONFIG_KEYBOARD_NSPIRE) += nspire-keypad.o obj-$(CONFIG_KEYBOARD_OMAP) += omap-keypad.o obj-$(CONFIG_KEYBOARD_OMAP4) += omap4-keypad.o diff --git a/drivers/input/keyboard/nomadik-ske-keypad.c b/drivers/input/keyboard/nomadik-ske-keypad.c deleted file mode 100644 index b3ccc97f61e1..000000000000 --- a/drivers/input/keyboard/nomadik-ske-keypad.c +++ /dev/null @@ -1,378 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) ST-Ericsson SA 2010 - * - * Author: Naveen Kumar G for ST-Ericsson - * Author: Sundar Iyer for ST-Ericsson - * - * Keypad controller driver for the SKE (Scroll Key Encoder) module used in - * the Nomadik 8815 and Ux500 platforms. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include - -/* SKE_CR bits */ -#define SKE_KPMLT (0x1 << 6) -#define SKE_KPCN (0x7 << 3) -#define SKE_KPASEN (0x1 << 2) -#define SKE_KPASON (0x1 << 7) - -/* SKE_IMSC bits */ -#define SKE_KPIMA (0x1 << 2) - -/* SKE_ICR bits */ -#define SKE_KPICS (0x1 << 3) -#define SKE_KPICA (0x1 << 2) - -/* SKE_RIS bits */ -#define SKE_KPRISA (0x1 << 2) - -#define SKE_KEYPAD_ROW_SHIFT 3 -#define SKE_KPD_NUM_ROWS 8 -#define SKE_KPD_NUM_COLS 8 - -/* keypad auto scan registers */ -#define SKE_ASR0 0x20 -#define SKE_ASR1 0x24 -#define SKE_ASR2 0x28 -#define SKE_ASR3 0x2C - -#define SKE_NUM_ASRX_REGISTERS (4) -#define KEY_PRESSED_DELAY 10 - -/** - * struct ske_keypad - data structure used by keypad driver - * @irq: irq no - * @reg_base: ske registers base address - * @input: pointer to input device object - * @board: keypad platform device - * @keymap: matrix scan code table for keycodes - * @clk: clock structure pointer - * @pclk: clock structure pointer - * @ske_keypad_lock: spinlock protecting the keypad read/writes - */ -struct ske_keypad { - int irq; - void __iomem *reg_base; - struct input_dev *input; - const struct ske_keypad_platform_data *board; - unsigned short keymap[SKE_KPD_NUM_ROWS * SKE_KPD_NUM_COLS]; - struct clk *clk; - struct clk *pclk; - spinlock_t ske_keypad_lock; -}; - -static void ske_keypad_set_bits(struct ske_keypad *keypad, u16 addr, - u8 mask, u8 data) -{ - u32 ret; - - spin_lock(&keypad->ske_keypad_lock); - - ret = readl(keypad->reg_base + addr); - ret &= ~mask; - ret |= data; - writel(ret, keypad->reg_base + addr); - - spin_unlock(&keypad->ske_keypad_lock); -} - -/* - * ske_keypad_chip_init: init keypad controller configuration - * - * Enable Multi key press detection, auto scan mode - */ -static int __init ske_keypad_chip_init(struct ske_keypad *keypad) -{ - u32 value; - int timeout = keypad->board->debounce_ms; - - /* check SKE_RIS to be 0 */ - while ((readl(keypad->reg_base + SKE_RIS) != 0x00000000) && timeout--) - cpu_relax(); - - if (timeout == -1) - return -EINVAL; - - /* - * set debounce value - * keypad dbounce is configured in DBCR[15:8] - * dbounce value in steps of 32/32.768 ms - */ - spin_lock(&keypad->ske_keypad_lock); - value = readl(keypad->reg_base + SKE_DBCR); - value = value & 0xff; - value |= ((keypad->board->debounce_ms * 32000)/32768) << 8; - writel(value, keypad->reg_base + SKE_DBCR); - spin_unlock(&keypad->ske_keypad_lock); - - /* enable multi key detection */ - ske_keypad_set_bits(keypad, SKE_CR, 0x0, SKE_KPMLT); - - /* - * set up the number of columns - * KPCN[5:3] defines no. of keypad columns to be auto scanned - */ - value = (keypad->board->kcol - 1) << 3; - ske_keypad_set_bits(keypad, SKE_CR, SKE_KPCN, value); - - /* clear keypad interrupt for auto(and pending SW) scans */ - ske_keypad_set_bits(keypad, SKE_ICR, 0x0, SKE_KPICA | SKE_KPICS); - - /* un-mask keypad interrupts */ - ske_keypad_set_bits(keypad, SKE_IMSC, 0x0, SKE_KPIMA); - - /* enable automatic scan */ - ske_keypad_set_bits(keypad, SKE_CR, 0x0, SKE_KPASEN); - - return 0; -} - -static void ske_keypad_report(struct ske_keypad *keypad, u8 status, int col) -{ - int row = 0, code, pos; - struct input_dev *input = keypad->input; - u32 ske_ris; - int key_pressed; - int num_of_rows; - - /* find out the row */ - num_of_rows = hweight8(status); - do { - pos = __ffs(status); - row = pos; - status &= ~(1 << pos); - - code = MATRIX_SCAN_CODE(row, col, SKE_KEYPAD_ROW_SHIFT); - ske_ris = readl(keypad->reg_base + SKE_RIS); - key_pressed = ske_ris & SKE_KPRISA; - - input_event(input, EV_MSC, MSC_SCAN, code); - input_report_key(input, keypad->keymap[code], key_pressed); - input_sync(input); - num_of_rows--; - } while (num_of_rows); -} - -static void ske_keypad_read_data(struct ske_keypad *keypad) -{ - u8 status; - int col = 0; - int ske_asr, i; - - /* - * Read the auto scan registers - * - * Each SKE_ASRx (x=0 to x=3) contains two row values. - * lower byte contains row value for column 2*x, - * upper byte contains row value for column 2*x + 1 - */ - for (i = 0; i < SKE_NUM_ASRX_REGISTERS; i++) { - ske_asr = readl(keypad->reg_base + SKE_ASR0 + (4 * i)); - if (!ske_asr) - continue; - - /* now that ASRx is zero, find out the coloumn x and row y */ - status = ske_asr & 0xff; - if (status) { - col = i * 2; - ske_keypad_report(keypad, status, col); - } - status = (ske_asr & 0xff00) >> 8; - if (status) { - col = (i * 2) + 1; - ske_keypad_report(keypad, status, col); - } - } -} - -static irqreturn_t ske_keypad_irq(int irq, void *dev_id) -{ - struct ske_keypad *keypad = dev_id; - int timeout = keypad->board->debounce_ms; - - /* disable auto scan interrupt; mask the interrupt generated */ - ske_keypad_set_bits(keypad, SKE_IMSC, ~SKE_KPIMA, 0x0); - ske_keypad_set_bits(keypad, SKE_ICR, 0x0, SKE_KPICA); - - while ((readl(keypad->reg_base + SKE_CR) & SKE_KPASON) && --timeout) - cpu_relax(); - - /* SKEx registers are stable and can be read */ - ske_keypad_read_data(keypad); - - /* wait until raw interrupt is clear */ - while ((readl(keypad->reg_base + SKE_RIS)) && --timeout) - msleep(KEY_PRESSED_DELAY); - - /* enable auto scan interrupts */ - ske_keypad_set_bits(keypad, SKE_IMSC, 0x0, SKE_KPIMA); - - return IRQ_HANDLED; -} - -static void ske_keypad_board_exit(void *data) -{ - struct ske_keypad *keypad = data; - - keypad->board->exit(); -} - -static int __init ske_keypad_probe(struct platform_device *pdev) -{ - const struct ske_keypad_platform_data *plat = - dev_get_platdata(&pdev->dev); - struct device *dev = &pdev->dev; - struct ske_keypad *keypad; - struct input_dev *input; - int irq; - int error; - - if (!plat) { - dev_err(&pdev->dev, "invalid keypad platform data\n"); - return -EINVAL; - } - - irq = platform_get_irq(pdev, 0); - if (irq < 0) - return irq; - - keypad = devm_kzalloc(dev, sizeof(struct ske_keypad), - GFP_KERNEL); - input = devm_input_allocate_device(dev); - if (!keypad || !input) { - dev_err(&pdev->dev, "failed to allocate keypad memory\n"); - return -ENOMEM; - } - - keypad->irq = irq; - keypad->board = plat; - keypad->input = input; - spin_lock_init(&keypad->ske_keypad_lock); - - keypad->reg_base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(keypad->reg_base)) - return PTR_ERR(keypad->reg_base); - - keypad->pclk = devm_clk_get_enabled(dev, "apb_pclk"); - if (IS_ERR(keypad->pclk)) { - dev_err(&pdev->dev, "failed to get pclk\n"); - return PTR_ERR(keypad->pclk); - } - - keypad->clk = devm_clk_get_enabled(dev, NULL); - if (IS_ERR(keypad->clk)) { - dev_err(&pdev->dev, "failed to get clk\n"); - return PTR_ERR(keypad->clk); - } - - input->id.bustype = BUS_HOST; - input->name = "ux500-ske-keypad"; - input->dev.parent = &pdev->dev; - - error = matrix_keypad_build_keymap(plat->keymap_data, NULL, - SKE_KPD_NUM_ROWS, SKE_KPD_NUM_COLS, - keypad->keymap, input); - if (error) { - dev_err(&pdev->dev, "Failed to build keymap\n"); - return error; - } - - input_set_capability(input, EV_MSC, MSC_SCAN); - if (!plat->no_autorepeat) - __set_bit(EV_REP, input->evbit); - - /* go through board initialization helpers */ - if (keypad->board->init) - keypad->board->init(); - - if (keypad->board->exit) { - error = devm_add_action_or_reset(dev, ske_keypad_board_exit, - keypad); - if (error) - return error; - } - - error = ske_keypad_chip_init(keypad); - if (error) { - dev_err(&pdev->dev, "unable to init keypad hardware\n"); - return error; - } - - error = devm_request_threaded_irq(dev, keypad->irq, - NULL, ske_keypad_irq, - IRQF_ONESHOT, "ske-keypad", keypad); - if (error) { - dev_err(&pdev->dev, "allocate irq %d failed\n", keypad->irq); - return error; - } - - error = input_register_device(input); - if (error) { - dev_err(&pdev->dev, - "unable to register input device: %d\n", error); - return error; - } - - if (plat->wakeup_enable) - device_init_wakeup(&pdev->dev, true); - - platform_set_drvdata(pdev, keypad); - - return 0; -} - -static int ske_keypad_suspend(struct device *dev) -{ - struct platform_device *pdev = to_platform_device(dev); - struct ske_keypad *keypad = platform_get_drvdata(pdev); - int irq = platform_get_irq(pdev, 0); - - if (device_may_wakeup(dev)) - enable_irq_wake(irq); - else - ske_keypad_set_bits(keypad, SKE_IMSC, ~SKE_KPIMA, 0x0); - - return 0; -} - -static int ske_keypad_resume(struct device *dev) -{ - struct platform_device *pdev = to_platform_device(dev); - struct ske_keypad *keypad = platform_get_drvdata(pdev); - int irq = platform_get_irq(pdev, 0); - - if (device_may_wakeup(dev)) - disable_irq_wake(irq); - else - ske_keypad_set_bits(keypad, SKE_IMSC, 0x0, SKE_KPIMA); - - return 0; -} - -static DEFINE_SIMPLE_DEV_PM_OPS(ske_keypad_dev_pm_ops, - ske_keypad_suspend, ske_keypad_resume); - -static struct platform_driver ske_keypad_driver = { - .driver = { - .name = "nmk-ske-keypad", - .pm = pm_sleep_ptr(&ske_keypad_dev_pm_ops), - }, -}; - -module_platform_driver_probe(ske_keypad_driver, ske_keypad_probe); - -MODULE_LICENSE("GPL v2"); -MODULE_AUTHOR("Naveen Kumar / Sundar Iyer "); -MODULE_DESCRIPTION("Nomadik Scroll-Key-Encoder Keypad Driver"); -MODULE_ALIAS("platform:nomadik-ske-keypad"); diff --git a/include/linux/platform_data/keypad-nomadik-ske.h b/include/linux/platform_data/keypad-nomadik-ske.h deleted file mode 100644 index 7efabbca1dca..000000000000 --- a/include/linux/platform_data/keypad-nomadik-ske.h +++ /dev/null @@ -1,50 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) ST-Ericsson SA 2010 - * - * Author: Naveen Kumar Gaddipati - * - * ux500 Scroll key and Keypad Encoder (SKE) header - */ - -#ifndef __SKE_H -#define __SKE_H - -#include - -/* register definitions for SKE peripheral */ -#define SKE_CR 0x00 -#define SKE_VAL0 0x04 -#define SKE_VAL1 0x08 -#define SKE_DBCR 0x0C -#define SKE_IMSC 0x10 -#define SKE_RIS 0x14 -#define SKE_MIS 0x18 -#define SKE_ICR 0x1C - -/* - * Keypad module - */ - -/** - * struct keypad_platform_data - structure for platform specific data - * @init: pointer to keypad init function - * @exit: pointer to keypad deinitialisation function - * @keymap_data: matrix scan code table for keycodes - * @krow: maximum number of rows - * @kcol: maximum number of columns - * @debounce_ms: platform specific debounce time - * @no_autorepeat: flag for auto repetition - * @wakeup_enable: allow waking up the system - */ -struct ske_keypad_platform_data { - int (*init)(void); - int (*exit)(void); - const struct matrix_keymap_data *keymap_data; - u8 krow; - u8 kcol; - u8 debounce_ms; - bool no_autorepeat; - bool wakeup_enable; -}; -#endif /*__SKE_KPD_H*/ -- cgit v1.2.3 From 5bc46b49c828a6dfaab80b71ecb63fe76a1096d2 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Mon, 22 Jul 2024 14:02:20 +0200 Subject: nvme-tcp: check for invalidated or revoked key key_lookup() will always return a key, even if that key is revoked or invalidated. So check for invalid keys before continuing. Signed-off-by: Hannes Reinecke Reviewed-by: Sagi Grimberg Reviewed-by: Christoph Hellwig Signed-off-by: Keith Busch --- drivers/nvme/common/keyring.c | 22 ++++++++++++++++++++++ drivers/nvme/host/Kconfig | 1 + drivers/nvme/host/fabrics.c | 2 +- drivers/nvme/host/tcp.c | 2 +- include/linux/nvme-keyring.h | 6 +++++- 5 files changed, 30 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/nvme/common/keyring.c b/drivers/nvme/common/keyring.c index 05e89307c8aa..ed5167f942d8 100644 --- a/drivers/nvme/common/keyring.c +++ b/drivers/nvme/common/keyring.c @@ -20,6 +20,28 @@ key_serial_t nvme_keyring_id(void) } EXPORT_SYMBOL_GPL(nvme_keyring_id); +static bool nvme_tls_psk_revoked(struct key *psk) +{ + return test_bit(KEY_FLAG_REVOKED, &psk->flags) || + test_bit(KEY_FLAG_INVALIDATED, &psk->flags); +} + +struct key *nvme_tls_key_lookup(key_serial_t key_id) +{ + struct key *key = key_lookup(key_id); + + if (IS_ERR(key)) { + pr_err("key id %08x not found\n", key_id); + return key; + } + if (nvme_tls_psk_revoked(key)) { + pr_err("key id %08x revoked\n", key_id); + return ERR_PTR(-EKEYREVOKED); + } + return key; +} +EXPORT_SYMBOL_GPL(nvme_tls_key_lookup); + static void nvme_tls_psk_describe(const struct key *key, struct seq_file *m) { seq_puts(m, key->description); diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig index a3caef75aa0a..883aaab2d83e 100644 --- a/drivers/nvme/host/Kconfig +++ b/drivers/nvme/host/Kconfig @@ -109,6 +109,7 @@ config NVME_HOST_AUTH bool "NVMe over Fabrics In-Band Authentication in host side" depends on NVME_CORE select NVME_AUTH + select NVME_KEYRING if NVME_TCP_TLS help This provides support for NVMe over Fabrics In-Band Authentication in host side. diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index f5f545fa0103..432efcbf9e2f 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -665,7 +665,7 @@ static struct key *nvmf_parse_key(int key_id) return ERR_PTR(-EINVAL); } - key = key_lookup(key_id); + key = nvme_tls_key_lookup(key_id); if (IS_ERR(key)) pr_err("key id %08x not found\n", key_id); else diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index b40e95bee849..89c44413c593 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1596,7 +1596,7 @@ static void nvme_tcp_tls_done(void *data, int status, key_serial_t pskid) goto out_complete; } - tls_key = key_lookup(pskid); + tls_key = nvme_tls_key_lookup(pskid); if (IS_ERR(tls_key)) { dev_warn(ctrl->ctrl.device, "queue %d: Invalid key %x\n", qid, pskid); diff --git a/include/linux/nvme-keyring.h b/include/linux/nvme-keyring.h index e10333d78dbb..19d2b256180f 100644 --- a/include/linux/nvme-keyring.h +++ b/include/linux/nvme-keyring.h @@ -12,7 +12,7 @@ key_serial_t nvme_tls_psk_default(struct key *keyring, const char *hostnqn, const char *subnqn); key_serial_t nvme_keyring_id(void); - +struct key *nvme_tls_key_lookup(key_serial_t key_id); #else static inline key_serial_t nvme_tls_psk_default(struct key *keyring, @@ -24,5 +24,9 @@ static inline key_serial_t nvme_keyring_id(void) { return 0; } +static inline struct key *nvme_tls_key_lookup(key_serial_t key_id) +{ + return ERR_PTR(-ENOTSUPP); +} #endif /* !CONFIG_NVME_KEYRING */ #endif /* _NVME_KEYRING_H */ -- cgit v1.2.3 From 559048d156ff3391c4b793779a824c9193e20442 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 5 Aug 2024 14:43:44 -0700 Subject: string: Check for "nonstring" attribute on strscpy() arguments GCC already checks for arguments that are marked with the "nonstring"[1] attribute when used on standard C String API functions (e.g. strcpy). Gain this compile-time checking also for the kernel's primary string copying function, strscpy(). Note that Clang has neither "nonstring" nor __builtin_has_attribute(). Link: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-nonstring-variable-attribute [1] Reviewed-by: Miguel Ojeda Tested-by: Miguel Ojeda Link: https://lore.kernel.org/r/20240805214340.work.339-kees@kernel.org Signed-off-by: Kees Cook --- include/linux/compiler.h | 3 +++ include/linux/compiler_types.h | 7 +++++++ include/linux/string.h | 12 ++++++++---- 3 files changed, 18 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 2df665fa2964..ec55bcce4146 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -242,6 +242,9 @@ static inline void *offset_to_ptr(const int *off) /* &a[0] degrades to a pointer: a different type from an array */ #define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) +/* Require C Strings (i.e. NUL-terminated) lack the "nonstring" attribute. */ +#define __must_be_cstr(p) BUILD_BUG_ON_ZERO(__annotated(p, nonstring)) + /* * This returns a constant expression while determining if an argument is * a constant expression, most importantly without evaluating the argument. diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index f14c275950b5..1a957ea2f4fe 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -421,6 +421,13 @@ struct ftrace_likely_data { #define __member_size(p) __builtin_object_size(p, 1) #endif +/* Determine if an attribute has been applied to a variable. */ +#if __has_builtin(__builtin_has_attribute) +#define __annotated(var, attr) __builtin_has_attribute(var, attr) +#else +#define __annotated(var, attr) (false) +#endif + /* * Some versions of gcc do not mark 'asm goto' volatile: * diff --git a/include/linux/string.h b/include/linux/string.h index 9edace076ddb..95b3fc308f4f 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -76,12 +76,16 @@ ssize_t sized_strscpy(char *, const char *, size_t); * known size. */ #define __strscpy0(dst, src, ...) \ - sized_strscpy(dst, src, sizeof(dst) + __must_be_array(dst)) -#define __strscpy1(dst, src, size) sized_strscpy(dst, src, size) + sized_strscpy(dst, src, sizeof(dst) + __must_be_array(dst) + \ + __must_be_cstr(dst) + __must_be_cstr(src)) +#define __strscpy1(dst, src, size) \ + sized_strscpy(dst, src, size + __must_be_cstr(dst) + __must_be_cstr(src)) #define __strscpy_pad0(dst, src, ...) \ - sized_strscpy_pad(dst, src, sizeof(dst) + __must_be_array(dst)) -#define __strscpy_pad1(dst, src, size) sized_strscpy_pad(dst, src, size) + sized_strscpy_pad(dst, src, sizeof(dst) + __must_be_array(dst) + \ + __must_be_cstr(dst) + __must_be_cstr(src)) +#define __strscpy_pad1(dst, src, size) \ + sized_strscpy_pad(dst, src, size + __must_be_cstr(dst) + __must_be_cstr(src)) /** * strscpy - Copy a C-string into a sized buffer -- cgit v1.2.3 From b58b133e680b20d219940e0fdb6f6132c2b60f38 Mon Sep 17 00:00:00 2001 From: Pranjal Shrivastava Date: Fri, 16 Aug 2024 10:49:06 +0000 Subject: iommu: Handle iommu faults for a bad iopf setup The iommu_report_device_fault function was updated to return void while assuming that drivers only need to call iommu_report_device_fault() for reporting an iopf. This implementation causes following problems: 1. The drivers rely on the core code to call it's page_reponse, however, when a fault is received and no fault capable domain is attached / iopf_param is NULL, the ops->page_response is NOT called causing the device to stall in case the fault type was PAGE_REQ. 2. The arm_smmu_v3 driver relies on the returned value to log errors returning void from iommu_report_device_fault causes these events to be missed while logging. Modify the iommu_report_device_fault function to return -EINVAL for cases where no fault capable domain is attached or iopf_param was NULL and calls back to the driver (ops->page_response) in case the fault type was IOMMU_FAULT_PAGE_REQ. The returned value can be used by the drivers to log the fault/event as needed. Reported-by: Kunkun Jiang Closes: https://lore.kernel.org/all/6147caf0-b9a0-30ca-795e-a1aa502a5c51@huawei.com/ Fixes: 3dfa64aecbaf ("iommu: Make iommu_report_device_fault() return void") Signed-off-by: Jason Gunthorpe Signed-off-by: Pranjal Shrivastava Reviewed-by: Jason Gunthorpe Reviewed-by: Lu Baolu Link: https://lore.kernel.org/r/20240816104906.1010626-1-praan@google.com Signed-off-by: Joerg Roedel --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 2 +- drivers/iommu/io-pgfault.c | 121 +++++++++++++++++++--------- include/linux/iommu.h | 5 +- 3 files changed, 87 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index a31460f9f3d4..ed2b106e02dd 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -1777,7 +1777,7 @@ static int arm_smmu_handle_evt(struct arm_smmu_device *smmu, u64 *evt) goto out_unlock; } - iommu_report_device_fault(master->dev, &fault_evt); + ret = iommu_report_device_fault(master->dev, &fault_evt); out_unlock: mutex_unlock(&smmu->streams_mutex); return ret; diff --git a/drivers/iommu/io-pgfault.c b/drivers/iommu/io-pgfault.c index 81e9cc6e3164..4674e618797c 100644 --- a/drivers/iommu/io-pgfault.c +++ b/drivers/iommu/io-pgfault.c @@ -115,6 +115,59 @@ static struct iopf_group *iopf_group_alloc(struct iommu_fault_param *iopf_param, return group; } +static struct iommu_attach_handle *find_fault_handler(struct device *dev, + struct iopf_fault *evt) +{ + struct iommu_fault *fault = &evt->fault; + struct iommu_attach_handle *attach_handle; + + if (fault->prm.flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID) { + attach_handle = iommu_attach_handle_get(dev->iommu_group, + fault->prm.pasid, 0); + if (IS_ERR(attach_handle)) { + const struct iommu_ops *ops = dev_iommu_ops(dev); + + if (!ops->user_pasid_table) + return NULL; + /* + * The iommu driver for this device supports user- + * managed PASID table. Therefore page faults for + * any PASID should go through the NESTING domain + * attached to the device RID. + */ + attach_handle = iommu_attach_handle_get( + dev->iommu_group, IOMMU_NO_PASID, + IOMMU_DOMAIN_NESTED); + if (IS_ERR(attach_handle)) + return NULL; + } + } else { + attach_handle = iommu_attach_handle_get(dev->iommu_group, + IOMMU_NO_PASID, 0); + + if (IS_ERR(attach_handle)) + return NULL; + } + + if (!attach_handle->domain->iopf_handler) + return NULL; + + return attach_handle; +} + +static void iopf_error_response(struct device *dev, struct iopf_fault *evt) +{ + const struct iommu_ops *ops = dev_iommu_ops(dev); + struct iommu_fault *fault = &evt->fault; + struct iommu_page_response resp = { + .pasid = fault->prm.pasid, + .grpid = fault->prm.grpid, + .code = IOMMU_PAGE_RESP_INVALID + }; + + ops->page_response(dev, evt, &resp); +} + /** * iommu_report_device_fault() - Report fault event to device driver * @dev: the device @@ -153,24 +206,39 @@ static struct iopf_group *iopf_group_alloc(struct iommu_fault_param *iopf_param, * handling framework should guarantee that the iommu domain could only be * freed after the device has stopped generating page faults (or the iommu * hardware has been set to block the page faults) and the pending page faults - * have been flushed. + * have been flushed. In case no page fault handler is attached or no iopf params + * are setup, then the ops->page_response() is called to complete the evt. + * + * Returns 0 on success, or an error in case of a bad/failed iopf setup. */ -void iommu_report_device_fault(struct device *dev, struct iopf_fault *evt) +int iommu_report_device_fault(struct device *dev, struct iopf_fault *evt) { + struct iommu_attach_handle *attach_handle; struct iommu_fault *fault = &evt->fault; struct iommu_fault_param *iopf_param; struct iopf_group abort_group = {}; struct iopf_group *group; + attach_handle = find_fault_handler(dev, evt); + if (!attach_handle) + goto err_bad_iopf; + + /* + * Something has gone wrong if a fault capable domain is attached but no + * iopf_param is setup + */ iopf_param = iopf_get_dev_fault_param(dev); if (WARN_ON(!iopf_param)) - return; + goto err_bad_iopf; if (!(fault->prm.flags & IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE)) { - report_partial_fault(iopf_param, fault); + int ret; + + ret = report_partial_fault(iopf_param, fault); iopf_put_dev_fault_param(iopf_param); /* A request that is not the last does not need to be ack'd */ - return; + + return ret; } /* @@ -185,38 +253,7 @@ void iommu_report_device_fault(struct device *dev, struct iopf_fault *evt) if (group == &abort_group) goto err_abort; - if (fault->prm.flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID) { - group->attach_handle = iommu_attach_handle_get(dev->iommu_group, - fault->prm.pasid, - 0); - if (IS_ERR(group->attach_handle)) { - const struct iommu_ops *ops = dev_iommu_ops(dev); - - if (!ops->user_pasid_table) - goto err_abort; - - /* - * The iommu driver for this device supports user- - * managed PASID table. Therefore page faults for - * any PASID should go through the NESTING domain - * attached to the device RID. - */ - group->attach_handle = - iommu_attach_handle_get(dev->iommu_group, - IOMMU_NO_PASID, - IOMMU_DOMAIN_NESTED); - if (IS_ERR(group->attach_handle)) - goto err_abort; - } - } else { - group->attach_handle = - iommu_attach_handle_get(dev->iommu_group, IOMMU_NO_PASID, 0); - if (IS_ERR(group->attach_handle)) - goto err_abort; - } - - if (!group->attach_handle->domain->iopf_handler) - goto err_abort; + group->attach_handle = attach_handle; /* * On success iopf_handler must call iopf_group_response() and @@ -225,7 +262,7 @@ void iommu_report_device_fault(struct device *dev, struct iopf_fault *evt) if (group->attach_handle->domain->iopf_handler(group)) goto err_abort; - return; + return 0; err_abort: dev_warn_ratelimited(dev, "iopf with pasid %d aborted\n", @@ -235,6 +272,14 @@ err_abort: __iopf_free_group(group); else iopf_free_group(group); + + return 0; + +err_bad_iopf: + if (fault->type == IOMMU_FAULT_PAGE_REQ) + iopf_error_response(dev, evt); + + return -EINVAL; } EXPORT_SYMBOL_GPL(iommu_report_device_fault); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 04cbdae0052e..bd722f473635 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -1563,7 +1563,7 @@ struct iopf_queue *iopf_queue_alloc(const char *name); void iopf_queue_free(struct iopf_queue *queue); int iopf_queue_discard_partial(struct iopf_queue *queue); void iopf_free_group(struct iopf_group *group); -void iommu_report_device_fault(struct device *dev, struct iopf_fault *evt); +int iommu_report_device_fault(struct device *dev, struct iopf_fault *evt); void iopf_group_response(struct iopf_group *group, enum iommu_page_response_code status); #else @@ -1601,9 +1601,10 @@ static inline void iopf_free_group(struct iopf_group *group) { } -static inline void +static inline int iommu_report_device_fault(struct device *dev, struct iopf_fault *evt) { + return -ENODEV; } static inline void iopf_group_response(struct iopf_group *group, -- cgit v1.2.3 From 84429b675bcfd2a518ae167ee4661cdf7539aa7d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 22 Aug 2024 15:50:09 +0200 Subject: fs: Allow fine-grained control of folio sizes We need filesystems to be able to communicate acceptable folio sizes to the pagecache for a variety of uses (e.g. large block sizes). Support a range of folio sizes between order-0 and order-31. Signed-off-by: Matthew Wilcox (Oracle) Co-developed-by: Pankaj Raghav Signed-off-by: Pankaj Raghav Link: https://lore.kernel.org/r/20240822135018.1931258-2-kernel@pankajraghav.com Tested-by: David Howells Reviewed-by: Hannes Reinecke Reviewed-by: Darrick J. Wong Reviewed-by: Daniel Gomez Signed-off-by: Christian Brauner --- include/linux/pagemap.h | 90 +++++++++++++++++++++++++++++++++++++++++-------- mm/filemap.c | 6 ++-- mm/readahead.c | 4 +-- 3 files changed, 80 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index d9c7edb6422b..c60025bb584c 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -204,14 +204,21 @@ enum mapping_flags { AS_EXITING = 4, /* final truncate in progress */ /* writeback related tags are not used */ AS_NO_WRITEBACK_TAGS = 5, - AS_LARGE_FOLIO_SUPPORT = 6, - AS_RELEASE_ALWAYS, /* Call ->release_folio(), even if no private data */ - AS_STABLE_WRITES, /* must wait for writeback before modifying + AS_RELEASE_ALWAYS = 6, /* Call ->release_folio(), even if no private data */ + AS_STABLE_WRITES = 7, /* must wait for writeback before modifying folio contents */ - AS_INACCESSIBLE, /* Do not attempt direct R/W access to the mapping, - including to move the mapping */ + AS_INACCESSIBLE = 8, /* Do not attempt direct R/W access to the mapping */ + /* Bits 16-25 are used for FOLIO_ORDER */ + AS_FOLIO_ORDER_BITS = 5, + AS_FOLIO_ORDER_MIN = 16, + AS_FOLIO_ORDER_MAX = AS_FOLIO_ORDER_MIN + AS_FOLIO_ORDER_BITS, }; +#define AS_FOLIO_ORDER_BITS_MASK ((1u << AS_FOLIO_ORDER_BITS) - 1) +#define AS_FOLIO_ORDER_MIN_MASK (AS_FOLIO_ORDER_BITS_MASK << AS_FOLIO_ORDER_MIN) +#define AS_FOLIO_ORDER_MAX_MASK (AS_FOLIO_ORDER_BITS_MASK << AS_FOLIO_ORDER_MAX) +#define AS_FOLIO_ORDER_MASK (AS_FOLIO_ORDER_MIN_MASK | AS_FOLIO_ORDER_MAX_MASK) + /** * mapping_set_error - record a writeback error in the address_space * @mapping: the mapping in which an error should be set @@ -367,9 +374,51 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) #define MAX_XAS_ORDER (XA_CHUNK_SHIFT * 2 - 1) #define MAX_PAGECACHE_ORDER min(MAX_XAS_ORDER, PREFERRED_MAX_PAGECACHE_ORDER) +/* + * mapping_set_folio_order_range() - Set the orders supported by a file. + * @mapping: The address space of the file. + * @min: Minimum folio order (between 0-MAX_PAGECACHE_ORDER inclusive). + * @max: Maximum folio order (between @min-MAX_PAGECACHE_ORDER inclusive). + * + * The filesystem should call this function in its inode constructor to + * indicate which base size (min) and maximum size (max) of folio the VFS + * can use to cache the contents of the file. This should only be used + * if the filesystem needs special handling of folio sizes (ie there is + * something the core cannot know). + * Do not tune it based on, eg, i_size. + * + * Context: This should not be called while the inode is active as it + * is non-atomic. + */ +static inline void mapping_set_folio_order_range(struct address_space *mapping, + unsigned int min, + unsigned int max) +{ + if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) + return; + + if (min > MAX_PAGECACHE_ORDER) + min = MAX_PAGECACHE_ORDER; + + if (max > MAX_PAGECACHE_ORDER) + max = MAX_PAGECACHE_ORDER; + + if (max < min) + max = min; + + mapping->flags = (mapping->flags & ~AS_FOLIO_ORDER_MASK) | + (min << AS_FOLIO_ORDER_MIN) | (max << AS_FOLIO_ORDER_MAX); +} + +static inline void mapping_set_folio_min_order(struct address_space *mapping, + unsigned int min) +{ + mapping_set_folio_order_range(mapping, min, MAX_PAGECACHE_ORDER); +} + /** * mapping_set_large_folios() - Indicate the file supports large folios. - * @mapping: The file. + * @mapping: The address space of the file. * * The filesystem should call this function in its inode constructor to * indicate that the VFS can use large folios to cache the contents of @@ -380,7 +429,23 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) */ static inline void mapping_set_large_folios(struct address_space *mapping) { - __set_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); + mapping_set_folio_order_range(mapping, 0, MAX_PAGECACHE_ORDER); +} + +static inline unsigned int +mapping_max_folio_order(const struct address_space *mapping) +{ + if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) + return 0; + return (mapping->flags & AS_FOLIO_ORDER_MAX_MASK) >> AS_FOLIO_ORDER_MAX; +} + +static inline unsigned int +mapping_min_folio_order(const struct address_space *mapping) +{ + if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) + return 0; + return (mapping->flags & AS_FOLIO_ORDER_MIN_MASK) >> AS_FOLIO_ORDER_MIN; } /* @@ -389,20 +454,17 @@ static inline void mapping_set_large_folios(struct address_space *mapping) */ static inline bool mapping_large_folio_support(struct address_space *mapping) { - /* AS_LARGE_FOLIO_SUPPORT is only reasonable for pagecache folios */ + /* AS_FOLIO_ORDER is only reasonable for pagecache folios */ VM_WARN_ONCE((unsigned long)mapping & PAGE_MAPPING_ANON, "Anonymous mapping always supports large folio"); - return IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && - test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); + return mapping_max_folio_order(mapping) > 0; } /* Return the maximum folio size for this pagecache mapping, in bytes. */ -static inline size_t mapping_max_folio_size(struct address_space *mapping) +static inline size_t mapping_max_folio_size(const struct address_space *mapping) { - if (mapping_large_folio_support(mapping)) - return PAGE_SIZE << MAX_PAGECACHE_ORDER; - return PAGE_SIZE; + return PAGE_SIZE << mapping_max_folio_order(mapping); } static inline int filemap_nr_thps(struct address_space *mapping) diff --git a/mm/filemap.c b/mm/filemap.c index d62150418b91..ad5e4a848070 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1933,10 +1933,8 @@ no_page: if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP)))) fgp_flags |= FGP_LOCK; - if (!mapping_large_folio_support(mapping)) - order = 0; - if (order > MAX_PAGECACHE_ORDER) - order = MAX_PAGECACHE_ORDER; + if (order > mapping_max_folio_order(mapping)) + order = mapping_max_folio_order(mapping); /* If we're not aligned, allocate a smaller folio */ if (index & ((1UL << order) - 1)) order = __ffs(index); diff --git a/mm/readahead.c b/mm/readahead.c index 517c0be7ce66..3e5239e9e177 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -449,10 +449,10 @@ void page_cache_ra_order(struct readahead_control *ractl, limit = min(limit, index + ra->size - 1); - if (new_order < MAX_PAGECACHE_ORDER) + if (new_order < mapping_max_folio_order(mapping)) new_order += 2; - new_order = min_t(unsigned int, MAX_PAGECACHE_ORDER, new_order); + new_order = min(mapping_max_folio_order(mapping), new_order); new_order = min_t(unsigned int, new_order, ilog2(ra->size)); /* See comment in page_cache_ra_unbounded() */ -- cgit v1.2.3 From ab95d23bab220ef845c0d422f49452a475330eaf Mon Sep 17 00:00:00 2001 From: Pankaj Raghav Date: Thu, 22 Aug 2024 15:50:10 +0200 Subject: filemap: allocate mapping_min_order folios in the page cache filemap_create_folio() and do_read_cache_folio() were always allocating folio of order 0. __filemap_get_folio was trying to allocate higher order folios when fgp_flags had higher order hint set but it will default to order 0 folio if higher order memory allocation fails. Supporting mapping_min_order implies that we guarantee each folio in the page cache has at least an order of mapping_min_order. When adding new folios to the page cache we must also ensure the index used is aligned to the mapping_min_order as the page cache requires the index to be aligned to the order of the folio. Co-developed-by: Luis Chamberlain Signed-off-by: Luis Chamberlain Signed-off-by: Pankaj Raghav Link: https://lore.kernel.org/r/20240822135018.1931258-3-kernel@pankajraghav.com Tested-by: David Howells Reviewed-by: Hannes Reinecke Reviewed-by: Darrick J. Wong Reviewed-by: Matthew Wilcox (Oracle) Reviewed-by: Daniel Gomez Reviewed-by: Dave Chinner Signed-off-by: Christian Brauner --- include/linux/pagemap.h | 20 ++++++++++++++++++++ mm/filemap.c | 24 ++++++++++++++++-------- 2 files changed, 36 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index c60025bb584c..4cc170949e9c 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -448,6 +448,26 @@ mapping_min_folio_order(const struct address_space *mapping) return (mapping->flags & AS_FOLIO_ORDER_MIN_MASK) >> AS_FOLIO_ORDER_MIN; } +static inline unsigned long +mapping_min_folio_nrpages(struct address_space *mapping) +{ + return 1UL << mapping_min_folio_order(mapping); +} + +/** + * mapping_align_index() - Align index for this mapping. + * @mapping: The address_space. + * + * The index of a folio must be naturally aligned. If you are adding a + * new folio to the page cache and need to know what index to give it, + * call this function. + */ +static inline pgoff_t mapping_align_index(struct address_space *mapping, + pgoff_t index) +{ + return round_down(index, mapping_min_folio_nrpages(mapping)); +} + /* * Large folio support currently depends on THP. These dependencies are * being worked on but are not yet fixed. diff --git a/mm/filemap.c b/mm/filemap.c index ad5e4a848070..d27e9ac54309 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -859,6 +859,8 @@ noinline int __filemap_add_folio(struct address_space *mapping, VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(folio_test_swapbacked(folio), folio); + VM_BUG_ON_FOLIO(folio_order(folio) < mapping_min_folio_order(mapping), + folio); mapping_set_update(&xas, mapping); VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio); @@ -1919,8 +1921,10 @@ repeat: folio_wait_stable(folio); no_page: if (!folio && (fgp_flags & FGP_CREAT)) { - unsigned order = FGF_GET_ORDER(fgp_flags); + unsigned int min_order = mapping_min_folio_order(mapping); + unsigned int order = max(min_order, FGF_GET_ORDER(fgp_flags)); int err; + index = mapping_align_index(mapping, index); if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping)) gfp |= __GFP_WRITE; @@ -1943,7 +1947,7 @@ no_page: gfp_t alloc_gfp = gfp; err = -ENOMEM; - if (order > 0) + if (order > min_order) alloc_gfp |= __GFP_NORETRY | __GFP_NOWARN; folio = filemap_alloc_folio(alloc_gfp, order); if (!folio) @@ -1958,7 +1962,7 @@ no_page: break; folio_put(folio); folio = NULL; - } while (order-- > 0); + } while (order-- > min_order); if (err == -EEXIST) goto repeat; @@ -2447,13 +2451,15 @@ unlock_mapping: } static int filemap_create_folio(struct file *file, - struct address_space *mapping, pgoff_t index, + struct address_space *mapping, loff_t pos, struct folio_batch *fbatch) { struct folio *folio; int error; + unsigned int min_order = mapping_min_folio_order(mapping); + pgoff_t index; - folio = filemap_alloc_folio(mapping_gfp_mask(mapping), 0); + folio = filemap_alloc_folio(mapping_gfp_mask(mapping), min_order); if (!folio) return -ENOMEM; @@ -2471,6 +2477,7 @@ static int filemap_create_folio(struct file *file, * well to keep locking rules simple. */ filemap_invalidate_lock_shared(mapping); + index = (pos >> (PAGE_SHIFT + min_order)) << min_order; error = filemap_add_folio(mapping, folio, index, mapping_gfp_constraint(mapping, GFP_KERNEL)); if (error == -EEXIST) @@ -2531,8 +2538,7 @@ retry: if (!folio_batch_count(fbatch)) { if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ)) return -EAGAIN; - err = filemap_create_folio(filp, mapping, - iocb->ki_pos >> PAGE_SHIFT, fbatch); + err = filemap_create_folio(filp, mapping, iocb->ki_pos, fbatch); if (err == AOP_TRUNCATED_PAGE) goto retry; return err; @@ -3748,9 +3754,11 @@ static struct folio *do_read_cache_folio(struct address_space *mapping, repeat: folio = filemap_get_folio(mapping, index); if (IS_ERR(folio)) { - folio = filemap_alloc_folio(gfp, 0); + folio = filemap_alloc_folio(gfp, + mapping_min_folio_order(mapping)); if (!folio) return ERR_PTR(-ENOMEM); + index = mapping_align_index(mapping, index); err = filemap_add_folio(mapping, folio, index, gfp); if (unlikely(err)) { folio_put(folio); -- cgit v1.2.3 From 3849687869092094003ba009dc00e2e0237a3b8a Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Wed, 21 Aug 2024 17:09:55 +0200 Subject: net: phy: Introduce ethernet link topology representation Link topologies containing multiple network PHYs attached to the same net_device can be found when using a PHY as a media converter for use with an SFP connector, on which an SFP transceiver containing a PHY can be used. With the current model, the transceiver's PHY can't be used for operations such as cable testing, timestamping, macsec offload, etc. The reason being that most of the logic for these configuration, coming from either ethtool netlink or ioctls tend to use netdev->phydev, which in multi-phy systems will reference the PHY closest to the MAC. Introduce a numbering scheme allowing to enumerate PHY devices that belong to any netdev, which can in turn allow userspace to take more precise decisions with regard to each PHY's configuration. The numbering is maintained per-netdev, in a phy_device_list. The numbering works similarly to a netdevice's ifindex, with identifiers that are only recycled once INT_MAX has been reached. This prevents races that could occur between PHY listing and SFP transceiver removal/insertion. The identifiers are assigned at phy_attach time, as the numbering depends on the netdevice the phy is attached to. The PHY index can be re-used for PHYs that are persistent. Signed-off-by: Maxime Chevallier Reviewed-by: Christophe Leroy Tested-by: Christophe Leroy Signed-off-by: David S. Miller --- MAINTAINERS | 1 + drivers/net/phy/Makefile | 2 +- drivers/net/phy/phy_device.c | 6 +++ drivers/net/phy/phy_link_topology.c | 105 ++++++++++++++++++++++++++++++++++++ include/linux/netdevice.h | 4 +- include/linux/phy.h | 4 ++ include/linux/phy_link_topology.h | 82 ++++++++++++++++++++++++++++ include/uapi/linux/ethtool.h | 16 ++++++ net/core/dev.c | 15 ++++++ 9 files changed, 233 insertions(+), 2 deletions(-) create mode 100644 drivers/net/phy/phy_link_topology.c create mode 100644 include/linux/phy_link_topology.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 5f45b75eba96..e4fa9010fcb6 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8341,6 +8341,7 @@ F: include/linux/mii.h F: include/linux/of_net.h F: include/linux/phy.h F: include/linux/phy_fixed.h +F: include/linux/phy_link_topology.h F: include/linux/phylib_stubs.h F: include/linux/platform_data/mdio-bcm-unimac.h F: include/linux/platform_data/mdio-gpio.h diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index f086a606a87e..33adb3df5f64 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -2,7 +2,7 @@ # Makefile for Linux PHY drivers libphy-y := phy.o phy-c45.o phy-core.o phy_device.o \ - linkmode.o + linkmode.o phy_link_topology.o mdio-bus-y += mdio_bus.o mdio_device.o ifdef CONFIG_MDIO_DEVICE diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 159e71c1c972..d896c799f7c2 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include #include @@ -1526,6 +1527,10 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, if (phydev->sfp_bus_attached) dev->sfp_bus = phydev->sfp_bus; + + err = phy_link_topo_add_phy(dev, phydev, PHY_UPSTREAM_MAC, dev); + if (err) + goto error; } /* Some Ethernet drivers try to connect to a PHY device before @@ -1953,6 +1958,7 @@ void phy_detach(struct phy_device *phydev) if (dev) { phydev->attached_dev->phydev = NULL; phydev->attached_dev = NULL; + phy_link_topo_del_phy(dev, phydev); } phydev->phylink = NULL; diff --git a/drivers/net/phy/phy_link_topology.c b/drivers/net/phy/phy_link_topology.c new file mode 100644 index 000000000000..4a5d73002a1a --- /dev/null +++ b/drivers/net/phy/phy_link_topology.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Infrastructure to handle all PHY devices connected to a given netdev, + * either directly or indirectly attached. + * + * Copyright (c) 2023 Maxime Chevallier + */ + +#include +#include +#include +#include + +static int netdev_alloc_phy_link_topology(struct net_device *dev) +{ + struct phy_link_topology *topo; + + topo = kzalloc(sizeof(*topo), GFP_KERNEL); + if (!topo) + return -ENOMEM; + + xa_init_flags(&topo->phys, XA_FLAGS_ALLOC1); + topo->next_phy_index = 1; + + dev->link_topo = topo; + + return 0; +} + +int phy_link_topo_add_phy(struct net_device *dev, + struct phy_device *phy, + enum phy_upstream upt, void *upstream) +{ + struct phy_link_topology *topo = dev->link_topo; + struct phy_device_node *pdn; + int ret; + + if (!topo) { + ret = netdev_alloc_phy_link_topology(dev); + if (ret) + return ret; + + topo = dev->link_topo; + } + + pdn = kzalloc(sizeof(*pdn), GFP_KERNEL); + if (!pdn) + return -ENOMEM; + + pdn->phy = phy; + switch (upt) { + case PHY_UPSTREAM_MAC: + pdn->upstream.netdev = (struct net_device *)upstream; + if (phy_on_sfp(phy)) + pdn->parent_sfp_bus = pdn->upstream.netdev->sfp_bus; + break; + case PHY_UPSTREAM_PHY: + pdn->upstream.phydev = (struct phy_device *)upstream; + if (phy_on_sfp(phy)) + pdn->parent_sfp_bus = pdn->upstream.phydev->sfp_bus; + break; + default: + ret = -EINVAL; + goto err; + } + pdn->upstream_type = upt; + + /* Attempt to re-use a previously allocated phy_index */ + if (phy->phyindex) + ret = xa_insert(&topo->phys, phy->phyindex, pdn, GFP_KERNEL); + else + ret = xa_alloc_cyclic(&topo->phys, &phy->phyindex, pdn, + xa_limit_32b, &topo->next_phy_index, + GFP_KERNEL); + + if (ret) + goto err; + + return 0; + +err: + kfree(pdn); + return ret; +} +EXPORT_SYMBOL_GPL(phy_link_topo_add_phy); + +void phy_link_topo_del_phy(struct net_device *dev, + struct phy_device *phy) +{ + struct phy_link_topology *topo = dev->link_topo; + struct phy_device_node *pdn; + + if (!topo) + return; + + pdn = xa_erase(&topo->phys, phy->phyindex); + + /* We delete the PHY from the topology, however we don't re-set the + * phy->phyindex field. If the PHY isn't gone, we can re-assign it the + * same index next time it's added back to the topology + */ + + kfree(pdn); +} +EXPORT_SYMBOL_GPL(phy_link_topo_del_phy); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 614ec5d3d75b..289a6133769c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -40,7 +40,6 @@ #include #endif #include - #include #include #include @@ -81,6 +80,7 @@ struct xdp_frame; struct xdp_metadata_ops; struct xdp_md; struct ethtool_netdev_state; +struct phy_link_topology; typedef u32 xdp_features_t; @@ -1951,6 +1951,7 @@ enum netdev_reg_state { * @fcoe_ddp_xid: Max exchange id for FCoE LRO by ddp * * @priomap: XXX: need comments on this one + * @link_topo: Physical link topology tracking attached PHYs * @phydev: Physical device may attach itself * for hardware timestamping * @sfp_bus: attached &struct sfp_bus structure. @@ -2342,6 +2343,7 @@ struct net_device { #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) struct netprio_map __rcu *priomap; #endif + struct phy_link_topology *link_topo; struct phy_device *phydev; struct sfp_bus *sfp_bus; struct lock_class_key *qdisc_tx_busylock; diff --git a/include/linux/phy.h b/include/linux/phy.h index 6b7d40d49129..3b0f4bf80650 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -554,6 +554,9 @@ struct macsec_ops; * @drv: Pointer to the driver for this PHY instance * @devlink: Create a link between phy dev and mac dev, if the external phy * used by current mac interface is managed by another mac interface. + * @phyindex: Unique id across the phy's parent tree of phys to address the PHY + * from userspace, similar to ifindex. A zero index means the PHY + * wasn't assigned an id yet. * @phy_id: UID for this device found during discovery * @c45_ids: 802.3-c45 Device Identifiers if is_c45. * @is_c45: Set to true if this PHY uses clause 45 addressing. @@ -656,6 +659,7 @@ struct phy_device { struct device_link *devlink; + u32 phyindex; u32 phy_id; struct phy_c45_device_ids c45_ids; diff --git a/include/linux/phy_link_topology.h b/include/linux/phy_link_topology.h new file mode 100644 index 000000000000..68a59e25821c --- /dev/null +++ b/include/linux/phy_link_topology.h @@ -0,0 +1,82 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * PHY device list allow maintaining a list of PHY devices that are + * part of a netdevice's link topology. PHYs can for example be chained, + * as is the case when using a PHY that exposes an SFP module, on which an + * SFP transceiver that embeds a PHY is connected. + * + * This list can then be used by userspace to leverage individual PHY + * capabilities. + */ +#ifndef __PHY_LINK_TOPOLOGY_H +#define __PHY_LINK_TOPOLOGY_H + +#include +#include + +struct xarray; +struct phy_device; +struct sfp_bus; + +struct phy_link_topology { + struct xarray phys; + u32 next_phy_index; +}; + +struct phy_device_node { + enum phy_upstream upstream_type; + + union { + struct net_device *netdev; + struct phy_device *phydev; + } upstream; + + struct sfp_bus *parent_sfp_bus; + + struct phy_device *phy; +}; + +#if IS_ENABLED(CONFIG_PHYLIB) +int phy_link_topo_add_phy(struct net_device *dev, + struct phy_device *phy, + enum phy_upstream upt, void *upstream); + +void phy_link_topo_del_phy(struct net_device *dev, struct phy_device *phy); + +static inline struct phy_device * +phy_link_topo_get_phy(struct net_device *dev, u32 phyindex) +{ + struct phy_link_topology *topo = dev->link_topo; + struct phy_device_node *pdn; + + if (!topo) + return NULL; + + pdn = xa_load(&topo->phys, phyindex); + if (pdn) + return pdn->phy; + + return NULL; +} + +#else +static inline int phy_link_topo_add_phy(struct net_device *dev, + struct phy_device *phy, + enum phy_upstream upt, void *upstream) +{ + return 0; +} + +static inline void phy_link_topo_del_phy(struct net_device *dev, + struct phy_device *phy) +{ +} + +static inline struct phy_device * +phy_link_topo_get_phy(struct net_device *dev, u32 phyindex) +{ + return NULL; +} +#endif + +#endif /* __PHY_LINK_TOPOLOGY_H */ diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 4a0a6e703483..c405ed63acfa 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -2533,4 +2533,20 @@ struct ethtool_link_settings { * __u32 map_lp_advertising[link_mode_masks_nwords]; */ }; + +/** + * enum phy_upstream - Represents the upstream component a given PHY device + * is connected to, as in what is on the other end of the MII bus. Most PHYs + * will be attached to an Ethernet MAC controller, but in some cases, there's + * an intermediate PHY used as a media-converter, which will driver another + * MII interface as its output. + * @PHY_UPSTREAM_MAC: Upstream component is a MAC (a switch port, + * or ethernet controller) + * @PHY_UPSTREAM_PHY: Upstream component is a PHY (likely a media converter) + */ +enum phy_upstream { + PHY_UPSTREAM_MAC, + PHY_UPSTREAM_PHY, +}; + #endif /* _UAPI_LINUX_ETHTOOL_H */ diff --git a/net/core/dev.c b/net/core/dev.c index e7260889d4cb..d0e7483abdcd 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -158,6 +158,7 @@ #include #include #include +#include #include "dev.h" #include "net-sysfs.h" @@ -10321,6 +10322,17 @@ static void netdev_do_free_pcpu_stats(struct net_device *dev) } } +static void netdev_free_phy_link_topology(struct net_device *dev) +{ + struct phy_link_topology *topo = dev->link_topo; + + if (IS_ENABLED(CONFIG_PHYLIB) && topo) { + xa_destroy(&topo->phys); + kfree(topo); + dev->link_topo = NULL; + } +} + /** * register_netdevice() - register a network device * @dev: device to register @@ -11099,6 +11111,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, #ifdef CONFIG_NET_SCHED hash_init(dev->qdisc_hash); #endif + dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; setup(dev); @@ -11191,6 +11204,8 @@ void free_netdev(struct net_device *dev) free_percpu(dev->xdp_bulkq); dev->xdp_bulkq = NULL; + netdev_free_phy_link_topology(dev); + /* Compatibility with error handling in drivers */ if (dev->reg_state == NETREG_UNINITIALIZED || dev->reg_state == NETREG_DUMMY) { -- cgit v1.2.3 From 4d76f115ab9121f4458330da962ae9ef5430e60b Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Wed, 21 Aug 2024 17:09:56 +0200 Subject: net: sfp: pass the phy_device when disconnecting an sfp module's PHY Pass the phy_device as a parameter to the sfp upstream .disconnect_phy operation. This is preparatory work to help track phy devices across a net_device's link. Signed-off-by: Maxime Chevallier Reviewed-by: Andrew Lunn Reviewed-by: Christophe Leroy Tested-by: Christophe Leroy Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 3 ++- drivers/net/phy/sfp-bus.c | 4 ++-- include/linux/sfp.h | 2 +- 3 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 51c526d227fa..ab4e9fc03017 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -3423,7 +3423,8 @@ static int phylink_sfp_connect_phy(void *upstream, struct phy_device *phy) return ret; } -static void phylink_sfp_disconnect_phy(void *upstream) +static void phylink_sfp_disconnect_phy(void *upstream, + struct phy_device *phydev) { phylink_disconnect_phy(upstream); } diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index 2f44fc51848f..56953e66bb7b 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -487,7 +487,7 @@ static void sfp_unregister_bus(struct sfp_bus *bus) bus->socket_ops->stop(bus->sfp); bus->socket_ops->detach(bus->sfp); if (bus->phydev && ops && ops->disconnect_phy) - ops->disconnect_phy(bus->upstream); + ops->disconnect_phy(bus->upstream, bus->phydev); } bus->registered = false; } @@ -743,7 +743,7 @@ void sfp_remove_phy(struct sfp_bus *bus) const struct sfp_upstream_ops *ops = sfp_get_upstream_ops(bus); if (ops && ops->disconnect_phy) - ops->disconnect_phy(bus->upstream); + ops->disconnect_phy(bus->upstream, bus->phydev); bus->phydev = NULL; } EXPORT_SYMBOL_GPL(sfp_remove_phy); diff --git a/include/linux/sfp.h b/include/linux/sfp.h index b14be59550e3..54abb4d22b2e 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -550,7 +550,7 @@ struct sfp_upstream_ops { void (*link_down)(void *priv); void (*link_up)(void *priv); int (*connect_phy)(void *priv, struct phy_device *); - void (*disconnect_phy)(void *priv); + void (*disconnect_phy)(void *priv, struct phy_device *); }; #if IS_ENABLED(CONFIG_SFP) -- cgit v1.2.3 From b2db6f4ace72e71fa09b8d1354f8ac9854140d74 Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Wed, 21 Aug 2024 17:09:57 +0200 Subject: net: phy: add helpers to handle sfp phy connect/disconnect There are a few PHY drivers that can handle SFP modules through their sfp_upstream_ops. Introduce Phylib helpers to keep track of connected SFP PHYs in a netdevice's namespace, by adding the SFP PHY to the upstream PHY's netdev's namespace. By doing so, these SFP PHYs can be enumerated and exposed to users, which will be able to use their capabilities. Signed-off-by: Maxime Chevallier Reviewed-by: Andrew Lunn Reviewed-by: Christophe Leroy Tested-by: Christophe Leroy Signed-off-by: David S. Miller --- drivers/net/phy/marvell-88x2222.c | 2 ++ drivers/net/phy/marvell.c | 2 ++ drivers/net/phy/marvell10g.c | 2 ++ drivers/net/phy/phy_device.c | 42 +++++++++++++++++++++++++++++++++++++++ drivers/net/phy/qcom/at803x.c | 2 ++ drivers/net/phy/qcom/qca807x.c | 2 ++ include/linux/phy.h | 2 ++ 7 files changed, 54 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/marvell-88x2222.c b/drivers/net/phy/marvell-88x2222.c index b88398e6872b..0b777cdd7078 100644 --- a/drivers/net/phy/marvell-88x2222.c +++ b/drivers/net/phy/marvell-88x2222.c @@ -553,6 +553,8 @@ static const struct sfp_upstream_ops sfp_phy_ops = { .link_down = mv2222_sfp_link_down, .attach = phy_sfp_attach, .detach = phy_sfp_detach, + .connect_phy = phy_sfp_connect_phy, + .disconnect_phy = phy_sfp_disconnect_phy, }; static int mv2222_probe(struct phy_device *phydev) diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index b89fbffa6a93..9964bf3dea2f 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -3613,6 +3613,8 @@ static const struct sfp_upstream_ops m88e1510_sfp_ops = { .module_remove = m88e1510_sfp_remove, .attach = phy_sfp_attach, .detach = phy_sfp_detach, + .connect_phy = phy_sfp_connect_phy, + .disconnect_phy = phy_sfp_disconnect_phy, }; static int m88e1510_probe(struct phy_device *phydev) diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c index ad43e280930c..6642eb642d4b 100644 --- a/drivers/net/phy/marvell10g.c +++ b/drivers/net/phy/marvell10g.c @@ -503,6 +503,8 @@ static int mv3310_sfp_insert(void *upstream, const struct sfp_eeprom_id *id) static const struct sfp_upstream_ops mv3310_sfp_ops = { .attach = phy_sfp_attach, .detach = phy_sfp_detach, + .connect_phy = phy_sfp_connect_phy, + .disconnect_phy = phy_sfp_disconnect_phy, .module_insert = mv3310_sfp_insert, }; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index d896c799f7c2..8f5314c1fecc 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1385,6 +1385,48 @@ phy_standalone_show(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR_RO(phy_standalone); +/** + * phy_sfp_connect_phy - Connect the SFP module's PHY to the upstream PHY + * @upstream: pointer to the upstream phy device + * @phy: pointer to the SFP module's phy device + * + * This helper allows keeping track of PHY devices on the link. It adds the + * SFP module's phy to the phy namespace of the upstream phy + * + * Return: 0 on success, otherwise a negative error code. + */ +int phy_sfp_connect_phy(void *upstream, struct phy_device *phy) +{ + struct phy_device *phydev = upstream; + struct net_device *dev = phydev->attached_dev; + + if (dev) + return phy_link_topo_add_phy(dev, phy, PHY_UPSTREAM_PHY, phydev); + + return 0; +} +EXPORT_SYMBOL(phy_sfp_connect_phy); + +/** + * phy_sfp_disconnect_phy - Disconnect the SFP module's PHY from the upstream PHY + * @upstream: pointer to the upstream phy device + * @phy: pointer to the SFP module's phy device + * + * This helper allows keeping track of PHY devices on the link. It removes the + * SFP module's phy to the phy namespace of the upstream phy. As the module phy + * will be destroyed, re-inserting the same module will add a new phy with a + * new index. + */ +void phy_sfp_disconnect_phy(void *upstream, struct phy_device *phy) +{ + struct phy_device *phydev = upstream; + struct net_device *dev = phydev->attached_dev; + + if (dev) + phy_link_topo_del_phy(dev, phy); +} +EXPORT_SYMBOL(phy_sfp_disconnect_phy); + /** * phy_sfp_attach - attach the SFP bus to the PHY upstream network device * @upstream: pointer to the phy device diff --git a/drivers/net/phy/qcom/at803x.c b/drivers/net/phy/qcom/at803x.c index c8f83e5f78ab..105602581a03 100644 --- a/drivers/net/phy/qcom/at803x.c +++ b/drivers/net/phy/qcom/at803x.c @@ -770,6 +770,8 @@ static const struct sfp_upstream_ops at8031_sfp_ops = { .attach = phy_sfp_attach, .detach = phy_sfp_detach, .module_insert = at8031_sfp_insert, + .connect_phy = phy_sfp_connect_phy, + .disconnect_phy = phy_sfp_disconnect_phy, }; static int at8031_parse_dt(struct phy_device *phydev) diff --git a/drivers/net/phy/qcom/qca807x.c b/drivers/net/phy/qcom/qca807x.c index ba558486c72f..bd8a51ec0ecd 100644 --- a/drivers/net/phy/qcom/qca807x.c +++ b/drivers/net/phy/qcom/qca807x.c @@ -699,6 +699,8 @@ static const struct sfp_upstream_ops qca807x_sfp_ops = { .detach = phy_sfp_detach, .module_insert = qca807x_sfp_insert, .module_remove = qca807x_sfp_remove, + .connect_phy = phy_sfp_connect_phy, + .disconnect_phy = phy_sfp_disconnect_phy, }; static int qca807x_probe(struct phy_device *phydev) diff --git a/include/linux/phy.h b/include/linux/phy.h index 3b0f4bf80650..a98bc91a0cde 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1781,6 +1781,8 @@ int phy_suspend(struct phy_device *phydev); int phy_resume(struct phy_device *phydev); int __phy_resume(struct phy_device *phydev); int phy_loopback(struct phy_device *phydev, bool enable); +int phy_sfp_connect_phy(void *upstream, struct phy_device *phy); +void phy_sfp_disconnect_phy(void *upstream, struct phy_device *phy); void phy_sfp_attach(void *upstream, struct sfp_bus *bus); void phy_sfp_detach(void *upstream, struct sfp_bus *bus); int phy_sfp_probe(struct phy_device *phydev, -- cgit v1.2.3 From 0a2f7de0f3b96c4a30e56d2c79f8d812f89599a1 Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Wed, 21 Aug 2024 17:09:58 +0200 Subject: net: sfp: Add helper to return the SFP bus name Knowing the bus name is helpful when we want to expose the link topology to userspace, add a helper to return the SFP bus name. This call will always be made while holding the RTNL which ensures that the SFP driver won't unbind from the device. The returned pointer to the bus name will only be used while RTNL is held. Signed-off-by: Maxime Chevallier Suggested-by: "Russell King (Oracle)" Reviewed-by: Christophe Leroy Tested-by: Christophe Leroy Signed-off-by: David S. Miller --- drivers/net/phy/sfp-bus.c | 22 ++++++++++++++++++++++ include/linux/sfp.h | 6 ++++++ 2 files changed, 28 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index 56953e66bb7b..f13c00b5b449 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -722,6 +722,28 @@ void sfp_bus_del_upstream(struct sfp_bus *bus) } EXPORT_SYMBOL_GPL(sfp_bus_del_upstream); +/** + * sfp_get_name() - Get the SFP device name + * @bus: a pointer to the &struct sfp_bus structure for the sfp module + * + * Gets the SFP device's name, if @bus has a registered socket. Callers must + * hold RTNL, and the returned name is only valid until RTNL is released. + * + * Returns: + * - The name of the SFP device registered with sfp_register_socket() + * - %NULL if no device was registered on @bus + */ +const char *sfp_get_name(struct sfp_bus *bus) +{ + ASSERT_RTNL(); + + if (bus->sfp_dev) + return dev_name(bus->sfp_dev); + + return NULL; +} +EXPORT_SYMBOL_GPL(sfp_get_name); + /* Socket driver entry points */ int sfp_add_phy(struct sfp_bus *bus, struct phy_device *phydev) { diff --git a/include/linux/sfp.h b/include/linux/sfp.h index 54abb4d22b2e..60c65cea74f6 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -576,6 +576,7 @@ struct sfp_bus *sfp_bus_find_fwnode(const struct fwnode_handle *fwnode); int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream, const struct sfp_upstream_ops *ops); void sfp_bus_del_upstream(struct sfp_bus *bus); +const char *sfp_get_name(struct sfp_bus *bus); #else static inline int sfp_parse_port(struct sfp_bus *bus, const struct sfp_eeprom_id *id, @@ -654,6 +655,11 @@ static inline int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream, static inline void sfp_bus_del_upstream(struct sfp_bus *bus) { } + +static inline const char *sfp_get_name(struct sfp_bus *bus) +{ + return NULL; +} #endif #endif -- cgit v1.2.3 From c579286a514d88a3f0d3bdabfd4d88737b33cb17 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 19 Aug 2024 18:31:33 +0200 Subject: thermal: core: Drop unused bind/unbind functions and callbacks There are no more callers of thermal_zone_bind_cooling_device() and thermal_zone_unbind_cooling_device(), so drop them along with all of the corresponding headers, code and documentation. Moreover, because the .bind() and .unbind() thermal zone callbacks would only be used when the above functions, respectively, were called, drop them as well along with all of the code related to them. Signed-off-by: Rafael J. Wysocki Reviewed-by: Zhang Rui Acked-by: Huisong Li Reviewed-by: Daniel Lezcano Link: https://patch.msgid.link/4251116.1IzOArtZ34@rjwysocki.net --- Documentation/driver-api/thermal/sysfs-api.rst | 59 ++------------------ drivers/thermal/thermal_core.c | 75 ++------------------------ include/linux/thermal.h | 10 ---- 3 files changed, 6 insertions(+), 138 deletions(-) (limited to 'include/linux') diff --git a/Documentation/driver-api/thermal/sysfs-api.rst b/Documentation/driver-api/thermal/sysfs-api.rst index 15fb59a9365d..c803b89b7248 100644 --- a/Documentation/driver-api/thermal/sysfs-api.rst +++ b/Documentation/driver-api/thermal/sysfs-api.rst @@ -58,10 +58,9 @@ temperature) and throttle appropriate devices. ops: thermal zone device call-backs. - .bind: - bind the thermal zone device with a thermal cooling device. - .unbind: - unbind the thermal zone device with a thermal cooling device. + .should_bind: + check whether or not a given cooling device should be bound to + a given trip point in this thermal zone. .get_temp: get the current temperature of the thermal zone. .set_trips: @@ -246,56 +245,6 @@ temperature) and throttle appropriate devices. It deletes the corresponding entry from /sys/class/thermal folder and unbinds itself from all the thermal zone devices using it. -1.3 interface for binding a thermal zone device with a thermal cooling device ------------------------------------------------------------------------------ - - :: - - int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz, - int trip, struct thermal_cooling_device *cdev, - unsigned long upper, unsigned long lower, unsigned int weight); - - This interface function binds a thermal cooling device to a particular trip - point of a thermal zone device. - - This function is usually called in the thermal zone device .bind callback. - - tz: - the thermal zone device - cdev: - thermal cooling device - trip: - indicates which trip point in this thermal zone the cooling device - is associated with. - upper: - the Maximum cooling state for this trip point. - THERMAL_NO_LIMIT means no upper limit, - and the cooling device can be in max_state. - lower: - the Minimum cooling state can be used for this trip point. - THERMAL_NO_LIMIT means no lower limit, - and the cooling device can be in cooling state 0. - weight: - the influence of this cooling device in this thermal - zone. See 1.4.1 below for more information. - - :: - - int thermal_zone_unbind_cooling_device(struct thermal_zone_device *tz, - int trip, struct thermal_cooling_device *cdev); - - This interface function unbinds a thermal cooling device from a particular - trip point of a thermal zone device. This function is usually called in - the thermal zone device .unbind callback. - - tz: - the thermal zone device - cdev: - thermal cooling device - trip: - indicates which trip point in this thermal zone the cooling device - is associated with. - 1.4 Thermal Zone Parameters --------------------------- @@ -366,8 +315,6 @@ Thermal cooling device sys I/F, created once it's registered:: Then next two dynamic attributes are created/removed in pairs. They represent the relationship between a thermal zone and its associated cooling device. -They are created/removed for each successful execution of -thermal_zone_bind_cooling_device/thermal_zone_unbind_cooling_device. :: diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 68fb85c18afa..9ca9d741fa0f 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -886,28 +886,6 @@ free_mem: return result; } -int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz, - int trip_index, - struct thermal_cooling_device *cdev, - unsigned long upper, unsigned long lower, - unsigned int weight) -{ - int ret; - - if (trip_index < 0 || trip_index >= tz->num_trips) - return -EINVAL; - - mutex_lock(&tz->lock); - - ret = thermal_bind_cdev_to_trip(tz, &tz->trips[trip_index].trip, cdev, - upper, lower, weight); - - mutex_unlock(&tz->lock); - - return ret; -} -EXPORT_SYMBOL_GPL(thermal_zone_bind_cooling_device); - /** * thermal_unbind_cdev_from_trip - unbind a cooling device from a thermal zone. * @tz: pointer to a struct thermal_zone_device. @@ -953,25 +931,6 @@ unbind: return 0; } -int thermal_zone_unbind_cooling_device(struct thermal_zone_device *tz, - int trip_index, - struct thermal_cooling_device *cdev) -{ - int ret; - - if (trip_index < 0 || trip_index >= tz->num_trips) - return -EINVAL; - - mutex_lock(&tz->lock); - - ret = thermal_unbind_cdev_from_trip(tz, &tz->trips[trip_index].trip, cdev); - - mutex_unlock(&tz->lock); - - return ret; -} -EXPORT_SYMBOL_GPL(thermal_zone_unbind_cooling_device); - static void thermal_release(struct device *dev) { struct thermal_zone_device *tz; @@ -1000,14 +959,8 @@ void print_bind_err_msg(struct thermal_zone_device *tz, const struct thermal_trip *trip, struct thermal_cooling_device *cdev, int ret) { - if (trip) { - dev_err(&tz->device, "binding cdev %s to trip %d failed: %d\n", - cdev->type, thermal_zone_trip_id(tz, trip), ret); - return; - } - - dev_err(&tz->device, "binding zone %s with cdev %s failed:%d\n", - tz->type, cdev->type, ret); + dev_err(&tz->device, "binding cdev %s to trip %d failed: %d\n", + cdev->type, thermal_zone_trip_id(tz, trip), ret); } static void thermal_zone_cdev_binding(struct thermal_zone_device *tz, @@ -1016,18 +969,6 @@ static void thermal_zone_cdev_binding(struct thermal_zone_device *tz, struct thermal_trip_desc *td; int ret; - /* - * Old-style binding. The .bind() callback is expected to call - * thermal_bind_cdev_to_trip() under the thermal zone lock. - */ - if (tz->ops.bind) { - ret = tz->ops.bind(tz, cdev); - if (ret) - print_bind_err_msg(tz, NULL, cdev, ret); - - return; - } - if (!tz->ops.should_bind) return; @@ -1354,15 +1295,6 @@ static void thermal_zone_cdev_unbinding(struct thermal_zone_device *tz, { struct thermal_trip_desc *td; - /* - * Old-style unbinding. The .unbind callback is expected to call - * thermal_unbind_cdev_from_trip() under the thermal zone lock. - */ - if (tz->ops.unbind) { - tz->ops.unbind(tz, cdev); - return; - } - mutex_lock(&tz->lock); for_each_trip_desc(tz, td) @@ -1496,8 +1428,7 @@ thermal_zone_device_register_with_trips(const char *type, return ERR_PTR(-EINVAL); } - if (!ops || !ops->get_temp || (ops->should_bind && ops->bind) || - (ops->should_bind && ops->unbind)) { + if (!ops || !ops->get_temp) { pr_err("Thermal zone device ops not defined or invalid\n"); return ERR_PTR(-EINVAL); } diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 6599a26847f7..25ea8fe2313e 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -92,10 +92,6 @@ struct cooling_spec { }; struct thermal_zone_device_ops { - int (*bind) (struct thermal_zone_device *, - struct thermal_cooling_device *); - int (*unbind) (struct thermal_zone_device *, - struct thermal_cooling_device *); bool (*should_bind) (struct thermal_zone_device *, const struct thermal_trip *, struct thermal_cooling_device *, @@ -247,12 +243,6 @@ const char *thermal_zone_device_type(struct thermal_zone_device *tzd); int thermal_zone_device_id(struct thermal_zone_device *tzd); struct device *thermal_zone_device(struct thermal_zone_device *tzd); -int thermal_zone_bind_cooling_device(struct thermal_zone_device *, int, - struct thermal_cooling_device *, - unsigned long, unsigned long, - unsigned int); -int thermal_zone_unbind_cooling_device(struct thermal_zone_device *, int, - struct thermal_cooling_device *); void thermal_zone_device_update(struct thermal_zone_device *, enum thermal_notify_event); -- cgit v1.2.3 From ccce71013406a0a3c81850dab940f07b112349d3 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Wed, 14 Aug 2024 14:21:18 +0200 Subject: mtd: rawnand: davinci: make platform_data private There are no longer any users of the platform data for davinci rawnand in board files. We can remove the public pdata headers and move the structures that are still used into the driver compilation unit while removing the rest. Signed-off-by: Bartosz Golaszewski Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20240814122120.13975-1-brgl@bgdev.pl --- drivers/mtd/nand/raw/davinci_nand.c | 70 ++++++++++++++++++-- include/linux/platform_data/mtd-davinci-aemif.h | 36 ---------- include/linux/platform_data/mtd-davinci.h | 88 ------------------------- 3 files changed, 65 insertions(+), 129 deletions(-) delete mode 100644 include/linux/platform_data/mtd-davinci-aemif.h delete mode 100644 include/linux/platform_data/mtd-davinci.h (limited to 'include/linux') diff --git a/drivers/mtd/nand/raw/davinci_nand.c b/drivers/mtd/nand/raw/davinci_nand.c index 051deea768db..392678143a36 100644 --- a/drivers/mtd/nand/raw/davinci_nand.c +++ b/drivers/mtd/nand/raw/davinci_nand.c @@ -20,8 +20,71 @@ #include #include -#include -#include +#define NRCSR_OFFSET 0x00 +#define NANDFCR_OFFSET 0x60 +#define NANDFSR_OFFSET 0x64 +#define NANDF1ECC_OFFSET 0x70 + +/* 4-bit ECC syndrome registers */ +#define NAND_4BIT_ECC_LOAD_OFFSET 0xbc +#define NAND_4BIT_ECC1_OFFSET 0xc0 +#define NAND_4BIT_ECC2_OFFSET 0xc4 +#define NAND_4BIT_ECC3_OFFSET 0xc8 +#define NAND_4BIT_ECC4_OFFSET 0xcc +#define NAND_ERR_ADD1_OFFSET 0xd0 +#define NAND_ERR_ADD2_OFFSET 0xd4 +#define NAND_ERR_ERRVAL1_OFFSET 0xd8 +#define NAND_ERR_ERRVAL2_OFFSET 0xdc + +/* NOTE: boards don't need to use these address bits + * for ALE/CLE unless they support booting from NAND. + * They're used unless platform data overrides them. + */ +#define MASK_ALE 0x08 +#define MASK_CLE 0x10 + +struct davinci_nand_pdata { + uint32_t mask_ale; + uint32_t mask_cle; + + /* + * 0-indexed chip-select number of the asynchronous + * interface to which the NAND device has been connected. + * + * So, if you have NAND connected to CS3 of DA850, you + * will pass '1' here. Since the asynchronous interface + * on DA850 starts from CS2. + */ + uint32_t core_chipsel; + + /* for packages using two chipselects */ + uint32_t mask_chipsel; + + /* board's default static partition info */ + struct mtd_partition *parts; + unsigned int nr_parts; + + /* none == NAND_ECC_ENGINE_TYPE_NONE (strongly *not* advised!!) + * soft == NAND_ECC_ENGINE_TYPE_SOFT + * else == NAND_ECC_ENGINE_TYPE_ON_HOST, according to ecc_bits + * + * All DaVinci-family chips support 1-bit hardware ECC. + * Newer ones also support 4-bit ECC, but are awkward + * using it with large page chips. + */ + enum nand_ecc_engine_type engine_type; + enum nand_ecc_placement ecc_placement; + u8 ecc_bits; + + /* e.g. NAND_BUSWIDTH_16 */ + unsigned int options; + /* e.g. NAND_BBT_USE_FLASH */ + unsigned int bbt_options; + + /* Main and mirror bbt descriptor overrides */ + struct nand_bbt_descr *bbt_td; + struct nand_bbt_descr *bbt_md; +}; /* * This is a device driver for the NAND flash controller found on the @@ -54,8 +117,6 @@ struct davinci_nand_info { uint32_t mask_cle; uint32_t core_chipsel; - - struct davinci_aemif_timing *timing; }; static DEFINE_SPINLOCK(davinci_nand_lock); @@ -775,7 +836,6 @@ static int nand_davinci_probe(struct platform_device *pdev) info->chip.options = pdata->options; info->chip.bbt_td = pdata->bbt_td; info->chip.bbt_md = pdata->bbt_md; - info->timing = pdata->timing; info->current_cs = info->vaddr; info->core_chipsel = pdata->core_chipsel; diff --git a/include/linux/platform_data/mtd-davinci-aemif.h b/include/linux/platform_data/mtd-davinci-aemif.h deleted file mode 100644 index a49826214a39..000000000000 --- a/include/linux/platform_data/mtd-davinci-aemif.h +++ /dev/null @@ -1,36 +0,0 @@ -/* - * TI DaVinci AEMIF support - * - * Copyright 2010 (C) Texas Instruments, Inc. https://www.ti.com/ - * - * This file is licensed under the terms of the GNU General Public License - * version 2. This program is licensed "as is" without any warranty of any - * kind, whether express or implied. - */ -#ifndef _MACH_DAVINCI_AEMIF_H -#define _MACH_DAVINCI_AEMIF_H - -#include - -#define NRCSR_OFFSET 0x00 -#define AWCCR_OFFSET 0x04 -#define A1CR_OFFSET 0x10 - -#define ACR_ASIZE_MASK 0x3 -#define ACR_EW_MASK BIT(30) -#define ACR_SS_MASK BIT(31) - -/* All timings in nanoseconds */ -struct davinci_aemif_timing { - u8 wsetup; - u8 wstrobe; - u8 whold; - - u8 rsetup; - u8 rstrobe; - u8 rhold; - - u8 ta; -}; - -#endif diff --git a/include/linux/platform_data/mtd-davinci.h b/include/linux/platform_data/mtd-davinci.h deleted file mode 100644 index dd474dd44848..000000000000 --- a/include/linux/platform_data/mtd-davinci.h +++ /dev/null @@ -1,88 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * mach-davinci/nand.h - * - * Copyright © 2006 Texas Instruments. - * - * Ported to 2.6.23 Copyright © 2008 by - * Sander Huijsen - * Troy Kisky - * Dirk Behme - * - * -------------------------------------------------------------------------- - */ - -#ifndef __ARCH_ARM_DAVINCI_NAND_H -#define __ARCH_ARM_DAVINCI_NAND_H - -#include - -#define NANDFCR_OFFSET 0x60 -#define NANDFSR_OFFSET 0x64 -#define NANDF1ECC_OFFSET 0x70 - -/* 4-bit ECC syndrome registers */ -#define NAND_4BIT_ECC_LOAD_OFFSET 0xbc -#define NAND_4BIT_ECC1_OFFSET 0xc0 -#define NAND_4BIT_ECC2_OFFSET 0xc4 -#define NAND_4BIT_ECC3_OFFSET 0xc8 -#define NAND_4BIT_ECC4_OFFSET 0xcc -#define NAND_ERR_ADD1_OFFSET 0xd0 -#define NAND_ERR_ADD2_OFFSET 0xd4 -#define NAND_ERR_ERRVAL1_OFFSET 0xd8 -#define NAND_ERR_ERRVAL2_OFFSET 0xdc - -/* NOTE: boards don't need to use these address bits - * for ALE/CLE unless they support booting from NAND. - * They're used unless platform data overrides them. - */ -#define MASK_ALE 0x08 -#define MASK_CLE 0x10 - -struct davinci_nand_pdata { /* platform_data */ - uint32_t mask_ale; - uint32_t mask_cle; - - /* - * 0-indexed chip-select number of the asynchronous - * interface to which the NAND device has been connected. - * - * So, if you have NAND connected to CS3 of DA850, you - * will pass '1' here. Since the asynchronous interface - * on DA850 starts from CS2. - */ - uint32_t core_chipsel; - - /* for packages using two chipselects */ - uint32_t mask_chipsel; - - /* board's default static partition info */ - struct mtd_partition *parts; - unsigned nr_parts; - - /* none == NAND_ECC_ENGINE_TYPE_NONE (strongly *not* advised!!) - * soft == NAND_ECC_ENGINE_TYPE_SOFT - * else == NAND_ECC_ENGINE_TYPE_ON_HOST, according to ecc_bits - * - * All DaVinci-family chips support 1-bit hardware ECC. - * Newer ones also support 4-bit ECC, but are awkward - * using it with large page chips. - */ - enum nand_ecc_engine_type engine_type; - enum nand_ecc_placement ecc_placement; - u8 ecc_bits; - - /* e.g. NAND_BUSWIDTH_16 */ - unsigned options; - /* e.g. NAND_BBT_USE_FLASH */ - unsigned bbt_options; - - /* Main and mirror bbt descriptor overrides */ - struct nand_bbt_descr *bbt_td; - struct nand_bbt_descr *bbt_md; - - /* Access timings */ - struct davinci_aemif_timing *timing; -}; - -#endif /* __ARCH_ARM_DAVINCI_NAND_H */ -- cgit v1.2.3 From 8a48281cfa7f380707d42b649acda3ea36348697 Mon Sep 17 00:00:00 2001 From: Kunwu Chan Date: Fri, 23 Aug 2024 15:42:01 +0800 Subject: PCI: Make pci_bus_type constant Since commit d492cc2573a0 ("driver core: device.h: make struct bus_type a const *"), the driver core can properly handle constant struct bus_type, move the pci_bus_type variable to be a constant structure as well, placing it into read-only memory which can not be modified at runtime. Link: https://lore.kernel.org/r/20240823074202.139265-1-kunwu.chan@linux.dev Suggested-by: Greg Kroah-Hartman Signed-off-by: Kunwu Chan Signed-off-by: Bjorn Helgaas Cc: Greg Kroah-Hartman --- drivers/pci/pci-driver.c | 2 +- include/linux/pci.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index f412ef73a6e4..35270172c833 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -1670,7 +1670,7 @@ static void pci_dma_cleanup(struct device *dev) iommu_device_unuse_default_domain(dev); } -struct bus_type pci_bus_type = { +const struct bus_type pci_bus_type = { .name = "pci", .match = pci_bus_match, .uevent = pci_uevent, diff --git a/include/linux/pci.h b/include/linux/pci.h index 4cf89a4b4cbc..197292b336a5 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1098,7 +1098,7 @@ enum pcie_bus_config_types { extern enum pcie_bus_config_types pcie_bus_config; -extern struct bus_type pci_bus_type; +extern const struct bus_type pci_bus_type; /* Do NOT directly access these two variables, unless you are arch-specific PCI * code, or PCI core code. */ -- cgit v1.2.3 From 9246b487ab3c3b5993aae7552b7a4c541cc14a49 Mon Sep 17 00:00:00 2001 From: WangYuli Date: Fri, 23 Aug 2024 17:57:08 +0800 Subject: PCI: Add function 0 DMA alias quirk for Glenfly Arise chip Add DMA support for audio function of Glenfly Arise chip, which uses Requester ID of function 0. Link: https://lore.kernel.org/r/CA2BBD087345B6D1+20240823095708.3237375-1-wangyuli@uniontech.com Signed-off-by: SiyuLi Signed-off-by: WangYuli [bhelgaas: lower-case hex to match local code, drop unused Device IDs] Signed-off-by: Bjorn Helgaas Reviewed-by: Takashi Iwai --- drivers/pci/quirks.c | 4 ++++ include/linux/pci_ids.h | 2 ++ sound/pci/hda/hda_intel.c | 2 +- 3 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index a2ce4e08edf5..cc6c82c3bd3d 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -4246,6 +4246,10 @@ static void quirk_dma_func0_alias(struct pci_dev *dev) DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_RICOH, 0xe832, quirk_dma_func0_alias); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_RICOH, 0xe476, quirk_dma_func0_alias); +/* Some Glenfly chips use function 0 as the PCIe Requester ID for DMA */ +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_GLENFLY, 0x3d40, quirk_dma_func0_alias); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_GLENFLY, 0x3d41, quirk_dma_func0_alias); + static void quirk_dma_func1_alias(struct pci_dev *dev) { if (PCI_FUNC(dev->devfn) != 1) diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index e388c8b1cbc2..2c94d4004dd5 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2661,6 +2661,8 @@ #define PCI_DEVICE_ID_DCI_PCCOM8 0x0002 #define PCI_DEVICE_ID_DCI_PCCOM2 0x0004 +#define PCI_VENDOR_ID_GLENFLY 0x6766 + #define PCI_VENDOR_ID_INTEL 0x8086 #define PCI_DEVICE_ID_INTEL_EESSC 0x0008 #define PCI_DEVICE_ID_INTEL_HDA_CML_LP 0x02c8 diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index b33602e64d17..e8958a464647 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2671,7 +2671,7 @@ static const struct pci_device_id azx_ids[] = { .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS | AZX_DCAPS_PM_RUNTIME }, /* GLENFLY */ - { PCI_DEVICE(0x6766, PCI_ANY_ID), + { PCI_DEVICE(PCI_VENDOR_ID_GLENFLY, PCI_ANY_ID), .class = PCI_CLASS_MULTIMEDIA_HD_AUDIO << 8, .class_mask = 0xffffff, .driver_data = AZX_DRIVER_GFHDMI | AZX_DCAPS_POSFIX_LPIB | -- cgit v1.2.3 From d59232afb0344e33e9399f308d9b4a03876e7676 Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Tue, 13 Aug 2024 21:24:22 +0000 Subject: bpf: Rename ARG_PTR_TO_KPTR -> ARG_KPTR_XCHG_DEST ARG_PTR_TO_KPTR is currently only used by the bpf_kptr_xchg helper. Although it limits reg types for that helper's first arg to PTR_TO_MAP_VALUE, any arbitrary mapval won't do: further custom verification logic ensures that the mapval reg being xchgd-into is pointing to a kptr field. If this is not the case, it's not safe to xchg into that reg's pointee. Let's rename the bpf_arg_type to more accurately describe the fairly specific expectations that this arg type encodes. This is a nonfunctional change. Acked-by: Martin KaFai Lau Signed-off-by: Dave Marchevsky Signed-off-by: Amery Hung Link: https://lore.kernel.org/r/20240813212424.2871455-4-amery.hung@bytedance.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 +- kernel/bpf/helpers.c | 2 +- kernel/bpf/verifier.c | 6 +++--- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 00dc4dd28cbd..dc63083f76b7 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -744,7 +744,7 @@ enum bpf_arg_type { ARG_PTR_TO_STACK, /* pointer to stack */ ARG_PTR_TO_CONST_STR, /* pointer to a null terminated read-only string */ ARG_PTR_TO_TIMER, /* pointer to bpf_timer */ - ARG_PTR_TO_KPTR, /* pointer to referenced kptr */ + ARG_KPTR_XCHG_DEST, /* pointer to destination that kptrs are bpf_kptr_xchg'd into */ ARG_PTR_TO_DYNPTR, /* pointer to bpf_dynptr. See bpf_type_flag for dynptr type */ __BPF_ARG_TYPE_MAX, diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 4105b4af6e03..bf55b81b3e06 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1636,7 +1636,7 @@ static const struct bpf_func_proto bpf_kptr_xchg_proto = { .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .ret_btf_id = BPF_PTR_POISON, - .arg1_type = ARG_PTR_TO_KPTR, + .arg1_type = ARG_KPTR_XCHG_DEST, .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL | OBJ_RELEASE, .arg2_btf_id = BPF_PTR_POISON, }; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 148536446457..5fe2a8978bb8 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8412,7 +8412,7 @@ static const struct bpf_reg_types func_ptr_types = { .types = { PTR_TO_FUNC } }; static const struct bpf_reg_types stack_ptr_types = { .types = { PTR_TO_STACK } }; static const struct bpf_reg_types const_str_ptr_types = { .types = { PTR_TO_MAP_VALUE } }; static const struct bpf_reg_types timer_types = { .types = { PTR_TO_MAP_VALUE } }; -static const struct bpf_reg_types kptr_types = { .types = { PTR_TO_MAP_VALUE } }; +static const struct bpf_reg_types kptr_xchg_dest_types = { .types = { PTR_TO_MAP_VALUE } }; static const struct bpf_reg_types dynptr_types = { .types = { PTR_TO_STACK, @@ -8444,7 +8444,7 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = { [ARG_PTR_TO_STACK] = &stack_ptr_types, [ARG_PTR_TO_CONST_STR] = &const_str_ptr_types, [ARG_PTR_TO_TIMER] = &timer_types, - [ARG_PTR_TO_KPTR] = &kptr_types, + [ARG_KPTR_XCHG_DEST] = &kptr_xchg_dest_types, [ARG_PTR_TO_DYNPTR] = &dynptr_types, }; @@ -9044,7 +9044,7 @@ skip_type_check: return err; break; } - case ARG_PTR_TO_KPTR: + case ARG_KPTR_XCHG_DEST: err = process_kptr_func(env, regno, meta); if (err) return err; -- cgit v1.2.3 From 9e83dd3ebb14fadccb936308b7b101c75da76324 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Fri, 23 Aug 2024 18:39:34 +0800 Subject: irqchip/loongson-eiointc: Rename CPUHP_AP_IRQ_LOONGARCH_STARTING Rename CPUHP_AP_IRQ_LOONGARCH_STARTING to CPUHP_AP_IRQ_EIOINTC_STARTING because the upcoming AVECINTC irqchip driver will introduce a new state and so both are clearly identifiable. Signed-off-by: Huacai Chen Signed-off-by: Tianyang Zhang Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/all/20240823103936.25092-3-zhangtianyang@loongson.cn --- drivers/irqchip/irq-loongson-eiointc.c | 4 ++-- include/linux/cpuhotplug.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/irqchip/irq-loongson-eiointc.c b/drivers/irqchip/irq-loongson-eiointc.c index 34b5ca2f5e62..c756b7aa8055 100644 --- a/drivers/irqchip/irq-loongson-eiointc.c +++ b/drivers/irqchip/irq-loongson-eiointc.c @@ -398,8 +398,8 @@ static int __init eiointc_init(struct eiointc_priv *priv, int parent_irq, if (nr_pics == 1) { register_syscore_ops(&eiointc_syscore_ops); - cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_LOONGARCH_STARTING, - "irqchip/loongarch/intc:starting", + cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_EIOINTC_STARTING, + "irqchip/loongarch/eiointc:starting", eiointc_router_init, NULL); } diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 51ba681b915a..e49807f7805c 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -145,7 +145,7 @@ enum cpuhp_state { CPUHP_AP_IRQ_ARMADA_XP_STARTING, CPUHP_AP_IRQ_BCM2836_STARTING, CPUHP_AP_IRQ_MIPS_GIC_STARTING, - CPUHP_AP_IRQ_LOONGARCH_STARTING, + CPUHP_AP_IRQ_EIOINTC_STARTING, CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING, CPUHP_AP_IRQ_RISCV_IMSIC_STARTING, CPUHP_AP_ARM_MVEBU_COHERENCY, -- cgit v1.2.3 From ae16f05c928a1336d5d9d19fd805d7bf29c3f0c8 Mon Sep 17 00:00:00 2001 From: Tianyang Zhang Date: Fri, 23 Aug 2024 18:43:37 +0800 Subject: irqchip/loongarch-avec: Add AVEC irqchip support Introduce the advanced extended interrupt controllers (AVECINTC). This feature will allow each core to have 256 independent interrupt vectors and MSI interrupts can be independently routed to any vector on any CPU. The whole topology of irqchips in LoongArch machines looks like this if AVECINTC is supported: +-----+ +-----------------------+ +-------+ | IPI | --> | CPUINTC | <-- | Timer | +-----+ +-----------------------+ +-------+ ^ ^ ^ | | | +---------+ +----------+ +---------+ +-------+ | EIOINTC | | AVECINTC | | LIOINTC | <-- | UARTs | +---------+ +----------+ +---------+ +-------+ ^ ^ | | +---------+ +---------+ | PCH-PIC | | PCH-MSI | +---------+ +---------+ ^ ^ ^ | | | +---------+ +---------+ +---------+ | Devices | | PCH-LPC | | Devices | +---------+ +---------+ +---------+ ^ | +---------+ | Devices | +---------+ Co-developed-by: Jianmin Lv Signed-off-by: Jianmin Lv Co-developed-by: Liupu Wang Signed-off-by: Liupu Wang Co-developed-by: Huacai Chen Signed-off-by: Huacai Chen Signed-off-by: Tianyang Zhang Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/all/20240823104337.25577-2-zhangtianyang@loongson.cn --- arch/loongarch/Kconfig | 1 + arch/loongarch/include/asm/irq.h | 2 + arch/loongarch/kernel/paravirt.c | 5 + arch/loongarch/kernel/smp.c | 6 + drivers/irqchip/Makefile | 2 +- drivers/irqchip/irq-loongarch-avec.c | 425 +++++++++++++++++++++++++++++++++ drivers/irqchip/irq-loongarch-cpu.c | 5 +- drivers/irqchip/irq-loongson-eiointc.c | 3 + drivers/irqchip/irq-loongson-pch-msi.c | 14 ++ drivers/irqchip/irq-loongson.h | 2 + include/linux/cpuhotplug.h | 1 + 11 files changed, 464 insertions(+), 2 deletions(-) create mode 100644 drivers/irqchip/irq-loongarch-avec.c (limited to 'include/linux') diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index 70f169210b52..0e3abf7b0bd3 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -85,6 +85,7 @@ config LOONGARCH select GENERIC_ENTRY select GENERIC_GETTIMEOFDAY select GENERIC_IOREMAP if !ARCH_IOREMAP + select GENERIC_IRQ_MATRIX_ALLOCATOR select GENERIC_IRQ_MULTI_HANDLER select GENERIC_IRQ_PROBE select GENERIC_IRQ_SHOW diff --git a/arch/loongarch/include/asm/irq.h b/arch/loongarch/include/asm/irq.h index c4835800c8b9..9c2ca785faa9 100644 --- a/arch/loongarch/include/asm/irq.h +++ b/arch/loongarch/include/asm/irq.h @@ -99,6 +99,8 @@ struct acpi_madt_bio_pic; struct acpi_madt_msi_pic; struct acpi_madt_lpc_pic; +void complete_irq_moving(void); + struct fwnode_handle *get_pch_msi_handle(int pci_segment); extern struct acpi_madt_lio_pic *acpi_liointc; diff --git a/arch/loongarch/kernel/paravirt.c b/arch/loongarch/kernel/paravirt.c index 9c9b75b76f62..4d736a4e488d 100644 --- a/arch/loongarch/kernel/paravirt.c +++ b/arch/loongarch/kernel/paravirt.c @@ -134,6 +134,11 @@ static irqreturn_t pv_ipi_interrupt(int irq, void *dev) info->ipi_irqs[IPI_IRQ_WORK]++; } + if (action & SMP_CLEAR_VECTOR) { + complete_irq_moving(); + info->ipi_irqs[IPI_CLEAR_VECTOR]++; + } + return IRQ_HANDLED; } diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index ca405ab86aae..4adbbef3450a 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -72,6 +72,7 @@ static const char *ipi_types[NR_IPI] __tracepoint_string = { [IPI_RESCHEDULE] = "Rescheduling interrupts", [IPI_CALL_FUNCTION] = "Function call interrupts", [IPI_IRQ_WORK] = "IRQ work interrupts", + [IPI_CLEAR_VECTOR] = "Clear vector interrupts", }; void show_ipi_list(struct seq_file *p, int prec) @@ -248,6 +249,11 @@ static irqreturn_t loongson_ipi_interrupt(int irq, void *dev) per_cpu(irq_stat, cpu).ipi_irqs[IPI_IRQ_WORK]++; } + if (action & SMP_CLEAR_VECTOR) { + complete_irq_moving(); + per_cpu(irq_stat, cpu).ipi_irqs[IPI_CLEAR_VECTOR]++; + } + return IRQ_HANDLED; } diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile index 15635812b2d6..e3679ec2b9f7 100644 --- a/drivers/irqchip/Makefile +++ b/drivers/irqchip/Makefile @@ -110,7 +110,7 @@ obj-$(CONFIG_LS1X_IRQ) += irq-ls1x.o obj-$(CONFIG_TI_SCI_INTR_IRQCHIP) += irq-ti-sci-intr.o obj-$(CONFIG_TI_SCI_INTA_IRQCHIP) += irq-ti-sci-inta.o obj-$(CONFIG_TI_PRUSS_INTC) += irq-pruss-intc.o -obj-$(CONFIG_IRQ_LOONGARCH_CPU) += irq-loongarch-cpu.o +obj-$(CONFIG_IRQ_LOONGARCH_CPU) += irq-loongarch-cpu.o irq-loongarch-avec.o obj-$(CONFIG_LOONGSON_LIOINTC) += irq-loongson-liointc.o obj-$(CONFIG_LOONGSON_EIOINTC) += irq-loongson-eiointc.o obj-$(CONFIG_LOONGSON_HTPIC) += irq-loongson-htpic.o diff --git a/drivers/irqchip/irq-loongarch-avec.c b/drivers/irqchip/irq-loongarch-avec.c new file mode 100644 index 000000000000..0f6e465dd309 --- /dev/null +++ b/drivers/irqchip/irq-loongarch-avec.c @@ -0,0 +1,425 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2020-2024 Loongson Technologies, Inc. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#include "irq-msi-lib.h" +#include "irq-loongson.h" + +#define VECTORS_PER_REG 64 +#define IRR_VECTOR_MASK 0xffUL +#define IRR_INVALID_MASK 0x80000000UL +#define AVEC_MSG_OFFSET 0x100000 + +#ifdef CONFIG_SMP +struct pending_list { + struct list_head head; +}; + +static struct cpumask intersect_mask; +static DEFINE_PER_CPU(struct pending_list, pending_list); +#endif + +static DEFINE_PER_CPU(struct irq_desc * [NR_VECTORS], irq_map); + +struct avecintc_chip { + raw_spinlock_t lock; + struct fwnode_handle *fwnode; + struct irq_domain *domain; + struct irq_matrix *vector_matrix; + phys_addr_t msi_base_addr; +}; + +static struct avecintc_chip loongarch_avec; + +struct avecintc_data { + struct list_head entry; + unsigned int cpu; + unsigned int vec; + unsigned int prev_cpu; + unsigned int prev_vec; + unsigned int moving; +}; + +static inline void avecintc_ack_irq(struct irq_data *d) +{ +} + +static inline void avecintc_mask_irq(struct irq_data *d) +{ +} + +static inline void avecintc_unmask_irq(struct irq_data *d) +{ +} + +#ifdef CONFIG_SMP +static inline void pending_list_init(int cpu) +{ + struct pending_list *plist = per_cpu_ptr(&pending_list, cpu); + + INIT_LIST_HEAD(&plist->head); +} + +static void avecintc_sync(struct avecintc_data *adata) +{ + struct pending_list *plist; + + if (cpu_online(adata->prev_cpu)) { + plist = per_cpu_ptr(&pending_list, adata->prev_cpu); + list_add_tail(&adata->entry, &plist->head); + adata->moving = 1; + mp_ops.send_ipi_single(adata->prev_cpu, ACTION_CLEAR_VECTOR); + } +} + +static int avecintc_set_affinity(struct irq_data *data, const struct cpumask *dest, bool force) +{ + int cpu, ret, vector; + struct avecintc_data *adata; + + scoped_guard(raw_spinlock, &loongarch_avec.lock) { + adata = irq_data_get_irq_chip_data(data); + + if (adata->moving) + return -EBUSY; + + if (cpu_online(adata->cpu) && cpumask_test_cpu(adata->cpu, dest)) + return 0; + + cpumask_and(&intersect_mask, dest, cpu_online_mask); + + ret = irq_matrix_alloc(loongarch_avec.vector_matrix, &intersect_mask, false, &cpu); + if (ret < 0) + return ret; + + vector = ret; + adata->cpu = cpu; + adata->vec = vector; + per_cpu_ptr(irq_map, adata->cpu)[adata->vec] = irq_data_to_desc(data); + avecintc_sync(adata); + } + + irq_data_update_effective_affinity(data, cpumask_of(cpu)); + + return IRQ_SET_MASK_OK; +} + +static int avecintc_cpu_online(unsigned int cpu) +{ + if (!loongarch_avec.vector_matrix) + return 0; + + guard(raw_spinlock)(&loongarch_avec.lock); + + irq_matrix_online(loongarch_avec.vector_matrix); + + pending_list_init(cpu); + + return 0; +} + +static int avecintc_cpu_offline(unsigned int cpu) +{ + struct pending_list *plist = per_cpu_ptr(&pending_list, cpu); + + if (!loongarch_avec.vector_matrix) + return 0; + + guard(raw_spinlock)(&loongarch_avec.lock); + + if (!list_empty(&plist->head)) + pr_warn("CPU#%d vector is busy\n", cpu); + + irq_matrix_offline(loongarch_avec.vector_matrix); + + return 0; +} + +void complete_irq_moving(void) +{ + struct pending_list *plist = this_cpu_ptr(&pending_list); + struct avecintc_data *adata, *tdata; + int cpu, vector, bias; + uint64_t isr; + + guard(raw_spinlock)(&loongarch_avec.lock); + + list_for_each_entry_safe(adata, tdata, &plist->head, entry) { + cpu = adata->prev_cpu; + vector = adata->prev_vec; + bias = vector / VECTORS_PER_REG; + switch (bias) { + case 0: + isr = csr_read64(LOONGARCH_CSR_ISR0); + break; + case 1: + isr = csr_read64(LOONGARCH_CSR_ISR1); + break; + case 2: + isr = csr_read64(LOONGARCH_CSR_ISR2); + break; + case 3: + isr = csr_read64(LOONGARCH_CSR_ISR3); + break; + } + + if (isr & (1UL << (vector % VECTORS_PER_REG))) { + mp_ops.send_ipi_single(cpu, ACTION_CLEAR_VECTOR); + continue; + } + list_del(&adata->entry); + irq_matrix_free(loongarch_avec.vector_matrix, cpu, vector, false); + this_cpu_write(irq_map[vector], NULL); + adata->moving = 0; + adata->prev_cpu = adata->cpu; + adata->prev_vec = adata->vec; + } +} +#endif + +static void avecintc_compose_msi_msg(struct irq_data *d, struct msi_msg *msg) +{ + struct avecintc_data *adata = irq_data_get_irq_chip_data(d); + + msg->address_hi = 0x0; + msg->address_lo = (loongarch_avec.msi_base_addr | (adata->vec & 0xff) << 4) + | ((cpu_logical_map(adata->cpu & 0xffff)) << 12); + msg->data = 0x0; +} + +static struct irq_chip avec_irq_controller = { + .name = "AVECINTC", + .irq_ack = avecintc_ack_irq, + .irq_mask = avecintc_mask_irq, + .irq_unmask = avecintc_unmask_irq, +#ifdef CONFIG_SMP + .irq_set_affinity = avecintc_set_affinity, +#endif + .irq_compose_msi_msg = avecintc_compose_msi_msg, +}; + +static void avecintc_irq_dispatch(struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + struct irq_desc *d; + + chained_irq_enter(chip, desc); + + while (true) { + unsigned long vector = csr_read64(LOONGARCH_CSR_IRR); + if (vector & IRR_INVALID_MASK) + break; + + vector &= IRR_VECTOR_MASK; + + d = this_cpu_read(irq_map[vector]); + if (d) { + generic_handle_irq_desc(d); + } else { + spurious_interrupt(); + pr_warn("Unexpected IRQ occurs on CPU#%d [vector %ld]\n", smp_processor_id(), vector); + } + } + + chained_irq_exit(chip, desc); +} + +static int avecintc_alloc_vector(struct irq_data *irqd, struct avecintc_data *adata) +{ + int cpu, ret; + + guard(raw_spinlock_irqsave)(&loongarch_avec.lock); + + ret = irq_matrix_alloc(loongarch_avec.vector_matrix, cpu_online_mask, false, &cpu); + if (ret < 0) + return ret; + + adata->prev_cpu = adata->cpu = cpu; + adata->prev_vec = adata->vec = ret; + per_cpu_ptr(irq_map, adata->cpu)[adata->vec] = irq_data_to_desc(irqd); + + return 0; +} + +static int avecintc_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg) +{ + for (unsigned int i = 0; i < nr_irqs; i++) { + struct irq_data *irqd = irq_domain_get_irq_data(domain, virq + i); + struct avecintc_data *adata = kzalloc(sizeof(*adata), GFP_KERNEL); + int ret; + + if (!adata) + return -ENOMEM; + + ret = avecintc_alloc_vector(irqd, adata); + if (ret < 0) { + kfree(adata); + return ret; + } + + irq_domain_set_info(domain, virq + i, virq + i, &avec_irq_controller, + adata, handle_edge_irq, NULL, NULL); + irqd_set_single_target(irqd); + irqd_set_affinity_on_activate(irqd); + } + + return 0; +} + +static void avecintc_free_vector(struct irq_data *irqd, struct avecintc_data *adata) +{ + guard(raw_spinlock_irqsave)(&loongarch_avec.lock); + + per_cpu(irq_map, adata->cpu)[adata->vec] = NULL; + irq_matrix_free(loongarch_avec.vector_matrix, adata->cpu, adata->vec, false); + +#ifdef CONFIG_SMP + if (!adata->moving) + return; + + per_cpu(irq_map, adata->prev_cpu)[adata->prev_vec] = NULL; + irq_matrix_free(loongarch_avec.vector_matrix, adata->prev_cpu, adata->prev_vec, false); + list_del_init(&adata->entry); +#endif +} + +static void avecintc_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + for (unsigned int i = 0; i < nr_irqs; i++) { + struct irq_data *d = irq_domain_get_irq_data(domain, virq + i); + + if (d) { + struct avecintc_data *adata = irq_data_get_irq_chip_data(d); + + avecintc_free_vector(d, adata); + irq_domain_reset_irq_data(d); + kfree(adata); + } + } +} + +static const struct irq_domain_ops avecintc_domain_ops = { + .alloc = avecintc_domain_alloc, + .free = avecintc_domain_free, + .select = msi_lib_irq_domain_select, +}; + +static int __init irq_matrix_init(void) +{ + loongarch_avec.vector_matrix = irq_alloc_matrix(NR_VECTORS, 0, NR_VECTORS); + if (!loongarch_avec.vector_matrix) + return -ENOMEM; + + for (int i = 0; i < NR_LEGACY_VECTORS; i++) + irq_matrix_assign_system(loongarch_avec.vector_matrix, i, false); + + irq_matrix_online(loongarch_avec.vector_matrix); + + return 0; +} + +static int __init avecintc_init(struct irq_domain *parent) +{ + int ret, parent_irq; + unsigned long value; + + raw_spin_lock_init(&loongarch_avec.lock); + + loongarch_avec.fwnode = irq_domain_alloc_named_fwnode("AVECINTC"); + if (!loongarch_avec.fwnode) { + pr_err("Unable to allocate domain handle\n"); + ret = -ENOMEM; + goto out; + } + + loongarch_avec.domain = irq_domain_create_tree(loongarch_avec.fwnode, + &avecintc_domain_ops, NULL); + if (!loongarch_avec.domain) { + pr_err("Unable to create IRQ domain\n"); + ret = -ENOMEM; + goto out_free_handle; + } + + parent_irq = irq_create_mapping(parent, INT_AVEC); + if (!parent_irq) { + pr_err("Failed to mapping hwirq\n"); + ret = -EINVAL; + goto out_remove_domain; + } + + ret = irq_matrix_init(); + if (ret < 0) { + pr_err("Failed to init irq matrix\n"); + goto out_remove_domain; + } + irq_set_chained_handler_and_data(parent_irq, avecintc_irq_dispatch, NULL); + +#ifdef CONFIG_SMP + pending_list_init(0); + cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_AVECINTC_STARTING, + "irqchip/loongarch/avecintc:starting", + avecintc_cpu_online, avecintc_cpu_offline); +#endif + value = iocsr_read64(LOONGARCH_IOCSR_MISC_FUNC); + value |= IOCSR_MISC_FUNC_AVEC_EN; + iocsr_write64(value, LOONGARCH_IOCSR_MISC_FUNC); + + return ret; + +out_remove_domain: + irq_domain_remove(loongarch_avec.domain); +out_free_handle: + irq_domain_free_fwnode(loongarch_avec.fwnode); +out: + return ret; +} + +static int __init pch_msi_parse_madt(union acpi_subtable_headers *header, + const unsigned long end) +{ + struct acpi_madt_msi_pic *pchmsi_entry = (struct acpi_madt_msi_pic *)header; + + loongarch_avec.msi_base_addr = pchmsi_entry->msg_address - AVEC_MSG_OFFSET; + + return pch_msi_acpi_init_avec(loongarch_avec.domain); +} + +static inline int __init acpi_cascade_irqdomain_init(void) +{ + return acpi_table_parse_madt(ACPI_MADT_TYPE_MSI_PIC, pch_msi_parse_madt, 1); +} + +int __init avecintc_acpi_init(struct irq_domain *parent) +{ + int ret = avecintc_init(parent); + if (ret < 0) { + pr_err("Failed to init IRQ domain\n"); + return ret; + } + + ret = acpi_cascade_irqdomain_init(); + if (ret < 0) { + pr_err("Failed to init cascade IRQ domain\n"); + return ret; + } + + return ret; +} diff --git a/drivers/irqchip/irq-loongarch-cpu.c b/drivers/irqchip/irq-loongarch-cpu.c index 83f7492290a8..bcbd7fd33178 100644 --- a/drivers/irqchip/irq-loongarch-cpu.c +++ b/drivers/irqchip/irq-loongarch-cpu.c @@ -140,7 +140,10 @@ static int __init acpi_cascade_irqdomain_init(void) if (r < 0) return r; - return 0; + if (cpu_has_avecint) + r = avecintc_acpi_init(irq_domain); + + return r; } static int __init cpuintc_acpi_init(union acpi_subtable_headers *header, diff --git a/drivers/irqchip/irq-loongson-eiointc.c b/drivers/irqchip/irq-loongson-eiointc.c index c756b7aa8055..e24db71a8783 100644 --- a/drivers/irqchip/irq-loongson-eiointc.c +++ b/drivers/irqchip/irq-loongson-eiointc.c @@ -362,6 +362,9 @@ static int __init acpi_cascade_irqdomain_init(void) if (r < 0) return r; + if (cpu_has_avecint) + return 0; + r = acpi_table_parse_madt(ACPI_MADT_TYPE_MSI_PIC, pch_msi_parse_madt, 1); if (r < 0) return r; diff --git a/drivers/irqchip/irq-loongson-pch-msi.c b/drivers/irqchip/irq-loongson-pch-msi.c index 0dc14550791d..bd337ecddb40 100644 --- a/drivers/irqchip/irq-loongson-pch-msi.c +++ b/drivers/irqchip/irq-loongson-pch-msi.c @@ -278,4 +278,18 @@ int __init pch_msi_acpi_init(struct irq_domain *parent, struct acpi_madt_msi_pic return ret; } + +int __init pch_msi_acpi_init_avec(struct irq_domain *parent) +{ + if (pch_msi_handle[0]) + return 0; + + pch_msi_handle[0] = parent->fwnode; + irq_domain_update_bus_token(parent, DOMAIN_BUS_NEXUS); + + parent->flags |= IRQ_DOMAIN_FLAG_MSI_PARENT; + parent->msi_parent_ops = &pch_msi_parent_ops; + + return 0; +} #endif diff --git a/drivers/irqchip/irq-loongson.h b/drivers/irqchip/irq-loongson.h index b155f1258ed5..11fa138d1f44 100644 --- a/drivers/irqchip/irq-loongson.h +++ b/drivers/irqchip/irq-loongson.h @@ -12,6 +12,7 @@ int liointc_acpi_init(struct irq_domain *parent, struct acpi_madt_lio_pic *acpi_liointc); int eiointc_acpi_init(struct irq_domain *parent, struct acpi_madt_eio_pic *acpi_eiointc); +int avecintc_acpi_init(struct irq_domain *parent); int htvec_acpi_init(struct irq_domain *parent, struct acpi_madt_ht_pic *acpi_htvec); @@ -21,5 +22,6 @@ int pch_pic_acpi_init(struct irq_domain *parent, struct acpi_madt_bio_pic *acpi_pchpic); int pch_msi_acpi_init(struct irq_domain *parent, struct acpi_madt_msi_pic *acpi_pchmsi); +int pch_msi_acpi_init_avec(struct irq_domain *parent); #endif /* _DRIVERS_IRQCHIP_IRQ_LOONGSON_H */ diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index e49807f7805c..55a726d317d4 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -146,6 +146,7 @@ enum cpuhp_state { CPUHP_AP_IRQ_BCM2836_STARTING, CPUHP_AP_IRQ_MIPS_GIC_STARTING, CPUHP_AP_IRQ_EIOINTC_STARTING, + CPUHP_AP_IRQ_AVECINTC_STARTING, CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING, CPUHP_AP_IRQ_RISCV_IMSIC_STARTING, CPUHP_AP_ARM_MVEBU_COHERENCY, -- cgit v1.2.3 From 17e28a9aeae40d2de3c1ea3b94819ed94bfd6392 Mon Sep 17 00:00:00 2001 From: Costa Shulyupin Date: Thu, 22 Aug 2024 15:31:58 +0300 Subject: genirq: Fix typo in struct comment Remove redundant "e" in "assign(e)ments". Signed-off-by: Costa Shulyupin Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/all/20240822123205.2186221-1-costa.shul@redhat.com --- include/linux/interrupt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 694de61e0b38..457151f9f263 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -276,7 +276,7 @@ struct irq_affinity_notify { #define IRQ_AFFINITY_MAX_SETS 4 /** - * struct irq_affinity - Description for automatic irq affinity assignements + * struct irq_affinity - Description for automatic irq affinity assignments * @pre_vectors: Don't apply affinity to @pre_vectors at beginning of * the MSI(-X) vector space * @post_vectors: Don't apply affinity to @post_vectors at end of -- cgit v1.2.3 From 7d3aed652d090508990d245f9d80dcc481910d02 Mon Sep 17 00:00:00 2001 From: Mina Almasry Date: Thu, 22 Aug 2024 05:51:54 +0000 Subject: net: refactor ->ndo_bpf calls into dev_xdp_propagate When net devices propagate xdp configurations to slave devices, we will need to perform a memory provider check to ensure we're not binding xdp to a device using unreadable netmem. Currently the ->ndo_bpf calls in a few places. Adding checks to all these places would not be ideal. Refactor all the ->ndo_bpf calls into one place where we can add this check in the future. Suggested-by: Jakub Kicinski Signed-off-by: Mina Almasry Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 8 ++++---- drivers/net/hyperv/netvsc_bpf.c | 2 +- include/linux/netdevice.h | 1 + net/core/dev.c | 9 +++++++++ 4 files changed, 15 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 96f5470a5f55..a3b6e6c696b4 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2253,7 +2253,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, goto err_sysfs_del; } - res = slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp); + res = dev_xdp_propagate(slave_dev, &xdp); if (res < 0) { /* ndo_bpf() sets extack error message */ slave_dbg(bond_dev, slave_dev, "Error %d calling ndo_bpf\n", res); @@ -2389,7 +2389,7 @@ static int __bond_release_one(struct net_device *bond_dev, .prog = NULL, .extack = NULL, }; - if (slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp)) + if (dev_xdp_propagate(slave_dev, &xdp)) slave_warn(bond_dev, slave_dev, "failed to unload XDP program\n"); } @@ -5579,7 +5579,7 @@ static int bond_xdp_set(struct net_device *dev, struct bpf_prog *prog, goto err; } - err = slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp); + err = dev_xdp_propagate(slave_dev, &xdp); if (err < 0) { /* ndo_bpf() sets extack error message */ slave_err(dev, slave_dev, "Error %d calling ndo_bpf\n", err); @@ -5611,7 +5611,7 @@ err: if (slave == rollback_slave) break; - err_unwind = slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp); + err_unwind = dev_xdp_propagate(slave_dev, &xdp); if (err_unwind < 0) slave_err(dev, slave_dev, "Error %d when unwinding XDP program change\n", err_unwind); diff --git a/drivers/net/hyperv/netvsc_bpf.c b/drivers/net/hyperv/netvsc_bpf.c index 4a9522689fa4..e01c5997a551 100644 --- a/drivers/net/hyperv/netvsc_bpf.c +++ b/drivers/net/hyperv/netvsc_bpf.c @@ -183,7 +183,7 @@ int netvsc_vf_setxdp(struct net_device *vf_netdev, struct bpf_prog *prog) xdp.command = XDP_SETUP_PROG; xdp.prog = prog; - ret = vf_netdev->netdev_ops->ndo_bpf(vf_netdev, &xdp); + ret = dev_xdp_propagate(vf_netdev, &xdp); if (ret && prog) bpf_prog_put(prog); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 289a6133769c..7dfa836d9dbf 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3925,6 +3925,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); u8 dev_xdp_prog_count(struct net_device *dev); +int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf); u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); diff --git a/net/core/dev.c b/net/core/dev.c index d0e7483abdcd..271d6aa0cfb9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -9370,6 +9370,15 @@ u8 dev_xdp_prog_count(struct net_device *dev) } EXPORT_SYMBOL_GPL(dev_xdp_prog_count); +int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf) +{ + if (!dev->netdev_ops->ndo_bpf) + return -EOPNOTSUPP; + + return dev->netdev_ops->ndo_bpf(dev, bpf); +} +EXPORT_SYMBOL_GPL(dev_xdp_propagate); + u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode) { struct bpf_prog *prog = dev_xdp_prog(dev, mode); -- cgit v1.2.3 From 2b8e976b984278edbeab3251d370e76d237699f9 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 7 Aug 2024 15:18:14 +0100 Subject: io_uring: user registered clockid for wait timeouts Add a new registration opcode IORING_REGISTER_CLOCK, which allows the user to select which clock id it wants to use with CQ waiting timeouts. It only allows a subset of all posix clocks and currently supports CLOCK_MONOTONIC and CLOCK_BOOTTIME. Suggested-by: Lewis Baker Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/98f2bc8a3c36cdf8f0e6a275245e81e903459703.1723039801.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 3 +++ include/uapi/linux/io_uring.h | 7 +++++++ io_uring/io_uring.c | 8 ++++++-- io_uring/io_uring.h | 8 ++++++++ io_uring/napi.c | 2 +- io_uring/register.c | 31 +++++++++++++++++++++++++++++++ 6 files changed, 56 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 3315005df117..4b9ba523978d 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -239,6 +239,9 @@ struct io_ring_ctx { struct io_rings *rings; struct percpu_ref refs; + clockid_t clockid; + enum tk_offsets clock_offset; + enum task_work_notify_mode notify_method; unsigned sq_thread_idle; } ____cacheline_aligned_in_smp; diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 6a81f55fcd0d..7af716136df9 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -596,6 +596,8 @@ enum io_uring_register_op { IORING_REGISTER_NAPI = 27, IORING_UNREGISTER_NAPI = 28, + IORING_REGISTER_CLOCK = 29, + /* this goes last */ IORING_REGISTER_LAST, @@ -676,6 +678,11 @@ struct io_uring_restriction { __u32 resv2[3]; }; +struct io_uring_clock_register { + __u32 clockid; + __u32 __resv[3]; +}; + struct io_uring_buf { __u64 addr; __u32 len; diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 5282f9887440..20229e72b65c 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2377,7 +2377,8 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, ret = 0; if (iowq->timeout == KTIME_MAX) schedule(); - else if (!schedule_hrtimeout(&iowq->timeout, HRTIMER_MODE_ABS)) + else if (!schedule_hrtimeout_range_clock(&iowq->timeout, 0, + HRTIMER_MODE_ABS, ctx->clockid)) ret = -ETIME; current->in_iowait = 0; return ret; @@ -2422,7 +2423,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, u32 flags, iowq.timeout = timespec64_to_ktime(ts); if (!(flags & IORING_ENTER_ABS_TIMER)) - iowq.timeout = ktime_add(iowq.timeout, ktime_get()); + iowq.timeout = ktime_add(iowq.timeout, io_get_time(ctx)); } if (sig) { @@ -3424,6 +3425,9 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, if (!ctx) return -ENOMEM; + ctx->clockid = CLOCK_MONOTONIC; + ctx->clock_offset = 0; + if ((ctx->flags & IORING_SETUP_DEFER_TASKRUN) && !(ctx->flags & IORING_SETUP_IOPOLL) && !(ctx->flags & IORING_SETUP_SQPOLL)) diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index c2acf6180845..9935819f12b7 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -437,6 +437,14 @@ static inline bool io_file_can_poll(struct io_kiocb *req) return false; } +static inline ktime_t io_get_time(struct io_ring_ctx *ctx) +{ + if (ctx->clockid == CLOCK_MONOTONIC) + return ktime_get(); + + return ktime_get_with_offset(ctx->clock_offset); +} + enum { IO_CHECK_CQ_OVERFLOW_BIT, IO_CHECK_CQ_DROPPED_BIT, diff --git a/io_uring/napi.c b/io_uring/napi.c index d78fcbecdd27..d0cf694d0172 100644 --- a/io_uring/napi.c +++ b/io_uring/napi.c @@ -283,7 +283,7 @@ void __io_napi_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq) iowq->napi_busy_poll_dt = READ_ONCE(ctx->napi_busy_poll_dt); if (iowq->timeout != KTIME_MAX) { - ktime_t dt = ktime_sub(iowq->timeout, ktime_get()); + ktime_t dt = ktime_sub(iowq->timeout, io_get_time(ctx)); iowq->napi_busy_poll_dt = min_t(u64, iowq->napi_busy_poll_dt, dt); } diff --git a/io_uring/register.c b/io_uring/register.c index e3c20be5a198..57cb85c42526 100644 --- a/io_uring/register.c +++ b/io_uring/register.c @@ -335,6 +335,31 @@ err: return ret; } +static int io_register_clock(struct io_ring_ctx *ctx, + struct io_uring_clock_register __user *arg) +{ + struct io_uring_clock_register reg; + + if (copy_from_user(®, arg, sizeof(reg))) + return -EFAULT; + if (memchr_inv(®.__resv, 0, sizeof(reg.__resv))) + return -EINVAL; + + switch (reg.clockid) { + case CLOCK_MONOTONIC: + ctx->clock_offset = 0; + break; + case CLOCK_BOOTTIME: + ctx->clock_offset = TK_OFFS_BOOT; + break; + default: + return -EINVAL; + } + + ctx->clockid = reg.clockid; + return 0; +} + static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, void __user *arg, unsigned nr_args) __releases(ctx->uring_lock) @@ -511,6 +536,12 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, break; ret = io_unregister_napi(ctx, arg); break; + case IORING_REGISTER_CLOCK: + ret = -EINVAL; + if (!arg || nr_args) + break; + ret = io_register_clock(ctx, arg); + break; default: ret = -EINVAL; break; -- cgit v1.2.3 From 1e9046e3a154608f63ce79edcb01e6afd6b10c7c Mon Sep 17 00:00:00 2001 From: Jens Wiklander Date: Wed, 14 Aug 2024 17:35:55 +0200 Subject: rpmb: add Replay Protected Memory Block (RPMB) subsystem MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A number of storage technologies support a specialised hardware partition designed to be resistant to replay attacks. The underlying HW protocols differ but the operations are common. The RPMB partition cannot be accessed via standard block layer, but by a set of specific RPMB commands. Such a partition provides authenticated and replay protected access, hence suitable as a secure storage. The initial aim of this patch is to provide a simple RPMB driver interface which can be accessed by the optee driver to facilitate early RPMB access to OP-TEE OS (secure OS) during the boot time. A TEE device driver can claim the RPMB interface, for example, via rpmb_interface_register() or rpmb_dev_find_device(). The RPMB driver provides a callback to route RPMB frames to the RPMB device accessible via rpmb_route_frames(). The detailed operation of implementing the access is left to the TEE device driver itself. Signed-off-by: Tomas Winkler Signed-off-by: Alex Bennée Signed-off-by: Shyam Saini Signed-off-by: Jens Wiklander Reviewed-by: Linus Walleij Tested-by: Manuel Traut Reviewed-by: Ulf Hansson Reviewed-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20240814153558.708365-2-jens.wiklander@linaro.org Signed-off-by: Ulf Hansson --- MAINTAINERS | 7 ++ drivers/misc/Kconfig | 10 ++ drivers/misc/Makefile | 1 + drivers/misc/rpmb-core.c | 233 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/rpmb.h | 123 +++++++++++++++++++++++++ 5 files changed, 374 insertions(+) create mode 100644 drivers/misc/rpmb-core.c create mode 100644 include/linux/rpmb.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 878dcd23b331..ec8c7ccb0a92 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -19861,6 +19861,13 @@ T: git git://linuxtv.org/media_tree.git F: Documentation/devicetree/bindings/media/allwinner,sun8i-a83t-de2-rotate.yaml F: drivers/media/platform/sunxi/sun8i-rotate/ +RPMB SUBSYSTEM +M: Jens Wiklander +L: linux-kernel@vger.kernel.org +S: Supported +F: drivers/misc/rpmb-core.c +F: include/linux/rpmb.h + RPMSG TTY DRIVER M: Arnaud Pouliquen L: linux-remoteproc@vger.kernel.org diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig index 41c54051347a..3fe7e2a9bd29 100644 --- a/drivers/misc/Kconfig +++ b/drivers/misc/Kconfig @@ -104,6 +104,16 @@ config PHANTOM If you choose to build module, its name will be phantom. If unsure, say N here. +config RPMB + tristate "RPMB partition interface" + depends on MMC + help + Unified RPMB unit interface for RPMB capable devices such as eMMC and + UFS. Provides interface for in-kernel security controllers to access + RPMB unit. + + If unsure, select N. + config TIFM_CORE tristate "TI Flash Media interface support" depends on PCI diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile index c2f990862d2b..a9f94525e181 100644 --- a/drivers/misc/Makefile +++ b/drivers/misc/Makefile @@ -15,6 +15,7 @@ obj-$(CONFIG_LKDTM) += lkdtm/ obj-$(CONFIG_TIFM_CORE) += tifm_core.o obj-$(CONFIG_TIFM_7XX1) += tifm_7xx1.o obj-$(CONFIG_PHANTOM) += phantom.o +obj-$(CONFIG_RPMB) += rpmb-core.o obj-$(CONFIG_QCOM_COINCELL) += qcom-coincell.o obj-$(CONFIG_QCOM_FASTRPC) += fastrpc.o obj-$(CONFIG_SENSORS_BH1770) += bh1770glc.o diff --git a/drivers/misc/rpmb-core.c b/drivers/misc/rpmb-core.c new file mode 100644 index 000000000000..c8888267c222 --- /dev/null +++ b/drivers/misc/rpmb-core.c @@ -0,0 +1,233 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright(c) 2015 - 2019 Intel Corporation. All rights reserved. + * Copyright(c) 2021 - 2024 Linaro Ltd. + */ +#include +#include +#include +#include +#include +#include +#include +#include + +static DEFINE_IDA(rpmb_ida); +static DEFINE_MUTEX(rpmb_mutex); + +/** + * rpmb_dev_get() - increase rpmb device ref counter + * @rdev: rpmb device + */ +struct rpmb_dev *rpmb_dev_get(struct rpmb_dev *rdev) +{ + if (rdev) + get_device(&rdev->dev); + return rdev; +} +EXPORT_SYMBOL_GPL(rpmb_dev_get); + +/** + * rpmb_dev_put() - decrease rpmb device ref counter + * @rdev: rpmb device + */ +void rpmb_dev_put(struct rpmb_dev *rdev) +{ + if (rdev) + put_device(&rdev->dev); +} +EXPORT_SYMBOL_GPL(rpmb_dev_put); + +/** + * rpmb_route_frames() - route rpmb frames to rpmb device + * @rdev: rpmb device + * @req: rpmb request frames + * @req_len: length of rpmb request frames in bytes + * @rsp: rpmb response frames + * @rsp_len: length of rpmb response frames in bytes + * + * Returns: < 0 on failure + */ +int rpmb_route_frames(struct rpmb_dev *rdev, u8 *req, + unsigned int req_len, u8 *rsp, unsigned int rsp_len) +{ + if (!req || !req_len || !rsp || !rsp_len) + return -EINVAL; + + return rdev->descr.route_frames(rdev->dev.parent, req, req_len, + rsp, rsp_len); +} +EXPORT_SYMBOL_GPL(rpmb_route_frames); + +static void rpmb_dev_release(struct device *dev) +{ + struct rpmb_dev *rdev = to_rpmb_dev(dev); + + mutex_lock(&rpmb_mutex); + ida_simple_remove(&rpmb_ida, rdev->id); + mutex_unlock(&rpmb_mutex); + kfree(rdev->descr.dev_id); + kfree(rdev); +} + +static struct class rpmb_class = { + .name = "rpmb", + .dev_release = rpmb_dev_release, +}; + +/** + * rpmb_dev_find_device() - return first matching rpmb device + * @start: rpmb device to begin with + * @data: data for the match function + * @match: the matching function + * + * Iterate over registered RPMB devices, and call @match() for each passing + * it the RPMB device and @data. + * + * The return value of @match() is checked for each call. If it returns + * anything other 0, break and return the found RPMB device. + * + * It's the callers responsibility to call rpmb_dev_put() on the returned + * device, when it's done with it. + * + * Returns: a matching rpmb device or NULL on failure + */ +struct rpmb_dev *rpmb_dev_find_device(const void *data, + const struct rpmb_dev *start, + int (*match)(struct device *dev, + const void *data)) +{ + struct device *dev; + const struct device *start_dev = NULL; + + if (start) + start_dev = &start->dev; + dev = class_find_device(&rpmb_class, start_dev, data, match); + + return dev ? to_rpmb_dev(dev) : NULL; +} +EXPORT_SYMBOL_GPL(rpmb_dev_find_device); + +int rpmb_interface_register(struct class_interface *intf) +{ + intf->class = &rpmb_class; + + return class_interface_register(intf); +} +EXPORT_SYMBOL_GPL(rpmb_interface_register); + +void rpmb_interface_unregister(struct class_interface *intf) +{ + class_interface_unregister(intf); +} +EXPORT_SYMBOL_GPL(rpmb_interface_unregister); + +/** + * rpmb_dev_unregister() - unregister RPMB partition from the RPMB subsystem + * @rdev: the rpmb device to unregister + * + * This function should be called from the release function of the + * underlying device used when the RPMB device was registered. + * + * Returns: < 0 on failure + */ +int rpmb_dev_unregister(struct rpmb_dev *rdev) +{ + if (!rdev) + return -EINVAL; + + device_del(&rdev->dev); + + rpmb_dev_put(rdev); + + return 0; +} +EXPORT_SYMBOL_GPL(rpmb_dev_unregister); + +/** + * rpmb_dev_register - register RPMB partition with the RPMB subsystem + * @dev: storage device of the rpmb device + * @descr: RPMB device description + * + * While registering the RPMB partition extract needed device information + * while needed resources are available. + * + * Returns: a pointer to a 'struct rpmb_dev' or an ERR_PTR on failure + */ +struct rpmb_dev *rpmb_dev_register(struct device *dev, + struct rpmb_descr *descr) +{ + struct rpmb_dev *rdev; + int ret; + + if (!dev || !descr || !descr->route_frames || !descr->dev_id || + !descr->dev_id_len) + return ERR_PTR(-EINVAL); + + rdev = kzalloc(sizeof(*rdev), GFP_KERNEL); + if (!rdev) + return ERR_PTR(-ENOMEM); + rdev->descr = *descr; + rdev->descr.dev_id = kmemdup(descr->dev_id, descr->dev_id_len, + GFP_KERNEL); + if (!rdev->descr.dev_id) { + ret = -ENOMEM; + goto err_free_rdev; + } + + mutex_lock(&rpmb_mutex); + ret = ida_simple_get(&rpmb_ida, 0, 0, GFP_KERNEL); + mutex_unlock(&rpmb_mutex); + if (ret < 0) + goto err_free_dev_id; + rdev->id = ret; + + dev_set_name(&rdev->dev, "rpmb%d", rdev->id); + rdev->dev.class = &rpmb_class; + rdev->dev.parent = dev; + + ret = device_register(&rdev->dev); + if (ret) + goto err_id_remove; + + dev_dbg(&rdev->dev, "registered device\n"); + + return rdev; + +err_id_remove: + mutex_lock(&rpmb_mutex); + ida_simple_remove(&rpmb_ida, rdev->id); + mutex_unlock(&rpmb_mutex); +err_free_dev_id: + kfree(rdev->descr.dev_id); +err_free_rdev: + kfree(rdev); + return ERR_PTR(ret); +} +EXPORT_SYMBOL_GPL(rpmb_dev_register); + +static int __init rpmb_init(void) +{ + int ret; + + ret = class_register(&rpmb_class); + if (ret) { + pr_err("couldn't create class\n"); + return ret; + } + ida_init(&rpmb_ida); + return 0; +} + +static void __exit rpmb_exit(void) +{ + ida_destroy(&rpmb_ida); + class_unregister(&rpmb_class); +} + +subsys_initcall(rpmb_init); +module_exit(rpmb_exit); + +MODULE_AUTHOR("Jens Wiklander "); +MODULE_DESCRIPTION("RPMB class"); +MODULE_LICENSE("GPL"); diff --git a/include/linux/rpmb.h b/include/linux/rpmb.h new file mode 100644 index 000000000000..cccda73eea4d --- /dev/null +++ b/include/linux/rpmb.h @@ -0,0 +1,123 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2015-2019 Intel Corp. All rights reserved + * Copyright (C) 2021-2022 Linaro Ltd + */ +#ifndef __RPMB_H__ +#define __RPMB_H__ + +#include +#include + +/** + * enum rpmb_type - type of underlying storage technology + * + * @RPMB_TYPE_EMMC : emmc (JESD84-B50.1) + * @RPMB_TYPE_UFS : UFS (JESD220) + * @RPMB_TYPE_NVME : NVM Express + */ +enum rpmb_type { + RPMB_TYPE_EMMC, + RPMB_TYPE_UFS, + RPMB_TYPE_NVME, +}; + +/** + * struct rpmb_descr - RPMB description provided by the underlying block device + * + * @type : block device type + * @route_frames : routes frames to and from the RPMB device + * @dev_id : unique device identifier read from the hardware + * @dev_id_len : length of unique device identifier + * @reliable_wr_count: number of sectors that can be written in one access + * @capacity : capacity of the device in units of 128K + * + * @dev_id is intended to be used as input when deriving the authenticaion key. + */ +struct rpmb_descr { + enum rpmb_type type; + int (*route_frames)(struct device *dev, u8 *req, unsigned int req_len, + u8 *resp, unsigned int resp_len); + u8 *dev_id; + size_t dev_id_len; + u16 reliable_wr_count; + u16 capacity; +}; + +/** + * struct rpmb_dev - device which can support RPMB partition + * + * @dev : device + * @id : device_id + * @list_node : linked list node + * @descr : RPMB description + */ +struct rpmb_dev { + struct device dev; + int id; + struct list_head list_node; + struct rpmb_descr descr; +}; + +#define to_rpmb_dev(x) container_of((x), struct rpmb_dev, dev) + +#if IS_ENABLED(CONFIG_RPMB) +struct rpmb_dev *rpmb_dev_get(struct rpmb_dev *rdev); +void rpmb_dev_put(struct rpmb_dev *rdev); +struct rpmb_dev *rpmb_dev_find_device(const void *data, + const struct rpmb_dev *start, + int (*match)(struct device *dev, + const void *data)); +int rpmb_interface_register(struct class_interface *intf); +void rpmb_interface_unregister(struct class_interface *intf); +struct rpmb_dev *rpmb_dev_register(struct device *dev, + struct rpmb_descr *descr); +int rpmb_dev_unregister(struct rpmb_dev *rdev); + +int rpmb_route_frames(struct rpmb_dev *rdev, u8 *req, + unsigned int req_len, u8 *resp, unsigned int resp_len); + +#else +static inline struct rpmb_dev *rpmb_dev_get(struct rpmb_dev *rdev) +{ + return NULL; +} + +static inline void rpmb_dev_put(struct rpmb_dev *rdev) { } + +static inline struct rpmb_dev * +rpmb_dev_find_device(const void *data, const struct rpmb_dev *start, + int (*match)(struct device *dev, const void *data)) +{ + return NULL; +} + +static inline int rpmb_interface_register(struct class_interface *intf) +{ + return -EOPNOTSUPP; +} + +static inline void rpmb_interface_unregister(struct class_interface *intf) +{ +} + +static inline struct rpmb_dev * +rpmb_dev_register(struct device *dev, struct rpmb_descr *descr) +{ + return NULL; +} + +static inline int rpmb_dev_unregister(struct rpmb_dev *dev) +{ + return 0; +} + +static inline int rpmb_route_frames(struct rpmb_dev *rdev, u8 *req, + unsigned int req_len, u8 *resp, + unsigned int resp_len) +{ + return -EOPNOTSUPP; +} +#endif /* CONFIG_RPMB */ + +#endif /* __RPMB_H__ */ -- cgit v1.2.3 From c30b855e814d9094e369a19fbd86c9bb5badc154 Mon Sep 17 00:00:00 2001 From: Jens Wiklander Date: Wed, 14 Aug 2024 17:35:57 +0200 Subject: tee: add tee_device_set_dev_groups() Add tee_device_set_dev_groups() to TEE drivers to supply driver specific attribute groups. The class specific attributes are from now on added via the tee_class, which currently only consist of implementation_id. Signed-off-by: Jens Wiklander Reviewed-by: Sumit Garg Link: https://lore.kernel.org/r/20240814153558.708365-4-jens.wiklander@linaro.org Signed-off-by: Ulf Hansson --- drivers/tee/tee_core.c | 19 +++++++++++++------ include/linux/tee_core.h | 12 ++++++++++++ 2 files changed, 25 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/tee/tee_core.c b/drivers/tee/tee_core.c index d52e879b204e..d113679b1e2d 100644 --- a/drivers/tee/tee_core.c +++ b/drivers/tee/tee_core.c @@ -40,10 +40,7 @@ static const uuid_t tee_client_uuid_ns = UUID_INIT(0x58ac9ca0, 0x2086, 0x4683, static DECLARE_BITMAP(dev_mask, TEE_NUM_DEVICES); static DEFINE_SPINLOCK(driver_lock); -static const struct class tee_class = { - .name = "tee", -}; - +static const struct class tee_class; static dev_t tee_devt; struct tee_context *teedev_open(struct tee_device *teedev) @@ -965,6 +962,13 @@ err: } EXPORT_SYMBOL_GPL(tee_device_alloc); +void tee_device_set_dev_groups(struct tee_device *teedev, + const struct attribute_group **dev_groups) +{ + teedev->dev.groups = dev_groups; +} +EXPORT_SYMBOL_GPL(tee_device_set_dev_groups); + static ssize_t implementation_id_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -983,6 +987,11 @@ static struct attribute *tee_dev_attrs[] = { ATTRIBUTE_GROUPS(tee_dev); +static const struct class tee_class = { + .name = "tee", + .dev_groups = tee_dev_groups, +}; + /** * tee_device_register() - Registers a TEE device * @teedev: Device to register @@ -1001,8 +1010,6 @@ int tee_device_register(struct tee_device *teedev) return -EINVAL; } - teedev->dev.groups = tee_dev_groups; - rc = cdev_device_add(&teedev->cdev, &teedev->dev); if (rc) { dev_err(&teedev->dev, diff --git a/include/linux/tee_core.h b/include/linux/tee_core.h index efd16ed52315..a38494d6b5f4 100644 --- a/include/linux/tee_core.h +++ b/include/linux/tee_core.h @@ -154,6 +154,18 @@ int tee_device_register(struct tee_device *teedev); */ void tee_device_unregister(struct tee_device *teedev); +/** + * tee_device_set_dev_groups() - Set device attribute groups + * @teedev: Device to register + * @dev_groups: Attribute groups + * + * Assigns the provided @dev_groups to the @teedev to be registered later + * with tee_device_register(). Calling this function is optional, but if + * it's called it must be called before tee_device_register(). + */ +void tee_device_set_dev_groups(struct tee_device *teedev, + const struct attribute_group **dev_groups); + /** * tee_session_calc_client_uuid() - Calculates client UUID for session * @uuid: Resulting UUID -- cgit v1.2.3 From d3596c73011d1b0e9b43ae12f1e0f491d6bb96eb Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Wed, 21 Aug 2024 15:24:06 +0200 Subject: mmc: core: Remove struct mmc_context_info The 'mmc_context_info' structure is unused. It has been introduced in: - commit 2220eedfd7ae ("mmc: fix async request mechanism for sequential read scenarios") in 2013-02 and its usages have been removed in: - commit 126b62700386 ("mmc: core: Remove code no longer needed after the switch to blk-mq") - commit 0fbfd1251830 ("mmc: block: Remove code no longer needed after the switch to blk-mq") in 2017-12. Now remove this unused structure. Signed-off-by: Christophe JAILLET Reviewed-by: Vladimir Zapolskiy Link: https://lore.kernel.org/r/232106a8a6a374dee25feea9b94498361568c10b.1724246389.git.christophe.jaillet@wanadoo.fr Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 88c6a76042ee..f85df7d045ca 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -291,20 +291,6 @@ struct mmc_slot { void *handler_priv; }; -/** - * mmc_context_info - synchronization details for mmc context - * @is_done_rcv wake up reason was done request - * @is_new_req wake up reason was new request - * @is_waiting_last_req mmc context waiting for single running request - * @wait wait queue - */ -struct mmc_context_info { - bool is_done_rcv; - bool is_new_req; - bool is_waiting_last_req; - wait_queue_head_t wait; -}; - struct regulator; struct mmc_pwrseq; -- cgit v1.2.3 From f5e1638bf3c785600e2ab53e5532007af5296581 Mon Sep 17 00:00:00 2001 From: Vladimir Zapolskiy Date: Sat, 24 Aug 2024 01:59:17 +0300 Subject: mmc: core: remove left-over data structure declarations The last users of 'enum mmc_blk_status' and 'struct mmc_async_req' were removed by commit 126b62700386 ("mmc: core: Remove code no longer needed after the switch to blk-mq") in 2017, remove these two left-over data structures. Signed-off-by: Vladimir Zapolskiy Link: https://lore.kernel.org/r/20240823225917.2826156-1-vladimir.zapolskiy@linaro.org Signed-off-by: Ulf Hansson --- include/linux/mmc/core.h | 12 ------------ include/linux/mmc/host.h | 10 ---------- 2 files changed, 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index 2c7928a50907..f0ac2e469b32 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -11,18 +11,6 @@ struct mmc_data; struct mmc_request; -enum mmc_blk_status { - MMC_BLK_SUCCESS = 0, - MMC_BLK_PARTIAL, - MMC_BLK_CMD_ERR, - MMC_BLK_RETRY, - MMC_BLK_ABORT, - MMC_BLK_DATA_ERR, - MMC_BLK_ECC_ERR, - MMC_BLK_NOMEDIUM, - MMC_BLK_NEW_REQUEST, -}; - struct mmc_command { u32 opcode; u32 arg; diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index f85df7d045ca..ac01cd1622ef 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -264,16 +264,6 @@ struct mmc_cqe_ops { void (*cqe_recovery_finish)(struct mmc_host *host); }; -struct mmc_async_req { - /* active mmc request */ - struct mmc_request *mrq; - /* - * Check error status of completed mmc request. - * Returns 0 if success otherwise non zero. - */ - enum mmc_blk_status (*err_check)(struct mmc_card *, struct mmc_async_req *); -}; - /** * struct mmc_slot - MMC slot functions * -- cgit v1.2.3 From 8d3cefaf659265aa82b0373a563fdb9d16a2b947 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Thu, 15 Aug 2024 21:44:50 +0200 Subject: i2c: core: Lock address during client device instantiation Krzysztof reported an issue [0] which is caused by parallel attempts to instantiate the same I2C client device. This can happen if driver supports auto-detection, but certain devices are also instantiated explicitly. The original change isn't actually wrong, it just revealed that I2C core isn't prepared yet to handle this scenario. Calls to i2c_new_client_device() can be nested, therefore we can't use a simple mutex here. Parallel instantiation of devices at different addresses is ok, so we just have to prevent parallel instantiation at the same address. We can use a bitmap with one bit per 7-bit I2C client address, and atomic bit operations to set/check/clear bits. Now a parallel attempt to instantiate a device at the same address will result in -EBUSY being returned, avoiding the "sysfs: cannot create duplicate filename" splash. Note: This patch version includes small cosmetic changes to the Tested-by version, only functional change is that address locking is supported for slave addresses too. [0] https://lore.kernel.org/linux-i2c/9479fe4e-eb0c-407e-84c0-bd60c15baf74@ans.pl/T/#m12706546e8e2414d8f1a0dc61c53393f731685cc Fixes: caba40ec3531 ("eeprom: at24: Probe for DDR3 thermal sensor in the SPD case") Cc: stable@vger.kernel.org Tested-by: Krzysztof Piotr Oledzki Signed-off-by: Heiner Kallweit Signed-off-by: Wolfram Sang --- drivers/i2c/i2c-core-base.c | 28 ++++++++++++++++++++++++++++ include/linux/i2c.h | 3 +++ 2 files changed, 31 insertions(+) (limited to 'include/linux') diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index b63f75e44296..e39e8d792d03 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -915,6 +915,27 @@ int i2c_dev_irq_from_resources(const struct resource *resources, return 0; } +/* + * Serialize device instantiation in case it can be instantiated explicitly + * and by auto-detection + */ +static int i2c_lock_addr(struct i2c_adapter *adap, unsigned short addr, + unsigned short flags) +{ + if (!(flags & I2C_CLIENT_TEN) && + test_and_set_bit(addr, adap->addrs_in_instantiation)) + return -EBUSY; + + return 0; +} + +static void i2c_unlock_addr(struct i2c_adapter *adap, unsigned short addr, + unsigned short flags) +{ + if (!(flags & I2C_CLIENT_TEN)) + clear_bit(addr, adap->addrs_in_instantiation); +} + /** * i2c_new_client_device - instantiate an i2c device * @adap: the adapter managing the device @@ -962,6 +983,10 @@ i2c_new_client_device(struct i2c_adapter *adap, struct i2c_board_info const *inf goto out_err_silent; } + status = i2c_lock_addr(adap, client->addr, client->flags); + if (status) + goto out_err_silent; + /* Check for address business */ status = i2c_check_addr_busy(adap, i2c_encode_flags_to_addr(client)); if (status) @@ -993,6 +1018,8 @@ i2c_new_client_device(struct i2c_adapter *adap, struct i2c_board_info const *inf dev_dbg(&adap->dev, "client [%s] registered with bus id %s\n", client->name, dev_name(&client->dev)); + i2c_unlock_addr(adap, client->addr, client->flags); + return client; out_remove_swnode: @@ -1004,6 +1031,7 @@ out_err: dev_err(&adap->dev, "Failed to register i2c client %s at 0x%02x (%d)\n", client->name, client->addr, status); + i2c_unlock_addr(adap, client->addr, client->flags); out_err_silent: if (need_put) put_device(&client->dev); diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 7eedd0c662da..8d79440cd8ce 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -761,6 +761,9 @@ struct i2c_adapter { struct regulator *bus_regulator; struct dentry *debugfs; + + /* 7bit address space */ + DECLARE_BITMAP(addrs_in_instantiation, 1 << 7); }; #define to_i2c_adapter(d) container_of(d, struct i2c_adapter, dev) -- cgit v1.2.3 From af8a6e65f42c6c89414017cc4d78403e83056172 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 3 May 2024 12:10:52 +0200 Subject: USB: serial: set driver owner when registering drivers Modules registering drivers with usb_serial_register_drivers() might forget to set .owner field. The field is used by some of other kernel parts for reference counting (try_module_get()), so it is expected that drivers will set it. Solve the problem by moving this task away from the drivers to the core USB serial code, just like we did for platform_driver in commit 9447057eaff8 ("platform_device: use a macro instead of platform_driver_register"). Signed-off-by: Krzysztof Kozlowski [ johan: amend commit summary ] Signed-off-by: Johan Hovold --- drivers/usb/serial/usb-serial.c | 12 +++++++----- include/linux/usb/serial.h | 7 +++++-- 2 files changed, 12 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c index f1e91eb7f8a4..df6a2ae0bf42 100644 --- a/drivers/usb/serial/usb-serial.c +++ b/drivers/usb/serial/usb-serial.c @@ -1459,17 +1459,18 @@ static void usb_serial_deregister(struct usb_serial_driver *device) } /** - * usb_serial_register_drivers - register drivers for a usb-serial module + * __usb_serial_register_drivers - register drivers for a usb-serial module * @serial_drivers: NULL-terminated array of pointers to drivers to be registered + * @owner: owning module * @name: name of the usb_driver for this set of @serial_drivers * @id_table: list of all devices this @serial_drivers set binds to * * Registers all the drivers in the @serial_drivers array, and dynamically * creates a struct usb_driver with the name @name and id_table of @id_table. */ -int usb_serial_register_drivers(struct usb_serial_driver *const serial_drivers[], - const char *name, - const struct usb_device_id *id_table) +int __usb_serial_register_drivers(struct usb_serial_driver *const serial_drivers[], + struct module *owner, const char *name, + const struct usb_device_id *id_table) { int rc; struct usb_driver *udriver; @@ -1514,6 +1515,7 @@ int usb_serial_register_drivers(struct usb_serial_driver *const serial_drivers[] for (sd = serial_drivers; *sd; ++sd) { (*sd)->usb_driver = udriver; + (*sd)->driver.owner = owner; rc = usb_serial_register(*sd); if (rc) goto err_deregister_drivers; @@ -1532,7 +1534,7 @@ err_free_driver: kfree(udriver); return rc; } -EXPORT_SYMBOL_GPL(usb_serial_register_drivers); +EXPORT_SYMBOL_GPL(__usb_serial_register_drivers); /** * usb_serial_deregister_drivers - deregister drivers for a usb-serial module diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index 1a0a4dc87980..75b2b763f1ba 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -311,8 +311,11 @@ struct usb_serial_driver { #define to_usb_serial_driver(d) \ container_of(d, struct usb_serial_driver, driver) -int usb_serial_register_drivers(struct usb_serial_driver *const serial_drivers[], - const char *name, const struct usb_device_id *id_table); +#define usb_serial_register_drivers(serial_drivers, name, id_table) \ + __usb_serial_register_drivers(serial_drivers, THIS_MODULE, name, id_table) +int __usb_serial_register_drivers(struct usb_serial_driver *const serial_drivers[], + struct module *owner, const char *name, + const struct usb_device_id *id_table); void usb_serial_deregister_drivers(struct usb_serial_driver *const serial_drivers[]); void usb_serial_port_softint(struct usb_serial_port *port); -- cgit v1.2.3 From 1d4684fbe88dc28e2bf79f5e94a432f0469d2dac Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Fri, 2 Aug 2024 17:32:02 -0700 Subject: iommufd: Reorder include files Reorder include files to alphabetic order to simplify maintenance, and separate local headers and global headers with a blank line. No functional change intended. Link: https://patch.msgid.link/r/7524b037cc05afe19db3c18f863253e1d1554fa2.1722644866.git.nicolinc@nvidia.com Signed-off-by: Nicolin Chen Signed-off-by: Jason Gunthorpe --- drivers/iommu/iommufd/device.c | 4 ++-- drivers/iommu/iommufd/fault.c | 4 ++-- drivers/iommu/iommufd/io_pagetable.c | 8 ++++---- drivers/iommu/iommufd/io_pagetable.h | 2 +- drivers/iommu/iommufd/ioas.c | 2 +- drivers/iommu/iommufd/iommufd_private.h | 9 +++++---- drivers/iommu/iommufd/iommufd_test.h | 2 +- drivers/iommu/iommufd/iova_bitmap.c | 2 +- drivers/iommu/iommufd/main.c | 8 ++++---- drivers/iommu/iommufd/pages.c | 10 +++++----- drivers/iommu/iommufd/selftest.c | 9 +++++---- include/linux/iommufd.h | 4 ++-- include/uapi/linux/iommufd.h | 2 +- 13 files changed, 34 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c index 9a7ec5997c61..11573a84f68a 100644 --- a/drivers/iommu/iommufd/device.c +++ b/drivers/iommu/iommufd/device.c @@ -1,12 +1,12 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES */ +#include #include #include -#include #include -#include "../iommu-priv.h" +#include "../iommu-priv.h" #include "io_pagetable.h" #include "iommufd_private.h" diff --git a/drivers/iommu/iommufd/fault.c b/drivers/iommu/iommufd/fault.c index a643d5c7c535..df03411c8728 100644 --- a/drivers/iommu/iommufd/fault.c +++ b/drivers/iommu/iommufd/fault.c @@ -3,14 +3,14 @@ */ #define pr_fmt(fmt) "iommufd: " fmt +#include #include #include +#include #include #include -#include #include #include -#include #include #include "../iommu-priv.h" diff --git a/drivers/iommu/iommufd/io_pagetable.c b/drivers/iommu/iommufd/io_pagetable.c index 05fd9d3abf1b..bbbc8a044bcf 100644 --- a/drivers/iommu/iommufd/io_pagetable.c +++ b/drivers/iommu/iommufd/io_pagetable.c @@ -8,17 +8,17 @@ * The datastructure uses the iopt_pages to optimize the storage of the PFNs * between the domains and xarray. */ +#include +#include +#include #include #include -#include #include -#include #include -#include #include -#include "io_pagetable.h" #include "double_span.h" +#include "io_pagetable.h" struct iopt_pages_list { struct iopt_pages *pages; diff --git a/drivers/iommu/iommufd/io_pagetable.h b/drivers/iommu/iommufd/io_pagetable.h index 0ec3509b7e33..c61d74471684 100644 --- a/drivers/iommu/iommufd/io_pagetable.h +++ b/drivers/iommu/iommufd/io_pagetable.h @@ -6,8 +6,8 @@ #define __IO_PAGETABLE_H #include -#include #include +#include #include #include "iommufd_private.h" diff --git a/drivers/iommu/iommufd/ioas.c b/drivers/iommu/iommufd/ioas.c index 742248276548..82428e44a837 100644 --- a/drivers/iommu/iommufd/ioas.c +++ b/drivers/iommu/iommufd/ioas.c @@ -3,8 +3,8 @@ * Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES */ #include -#include #include +#include #include #include "io_pagetable.h" diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index 92efe30a8f0d..017e50574f3b 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -4,13 +4,14 @@ #ifndef __IOMMUFD_PRIVATE_H #define __IOMMUFD_PRIVATE_H -#include -#include -#include -#include #include #include +#include +#include +#include +#include #include + #include "../iommu-priv.h" struct iommu_domain; diff --git a/drivers/iommu/iommufd/iommufd_test.h b/drivers/iommu/iommufd/iommufd_test.h index acbbba1c6671..f4bc23a92f9a 100644 --- a/drivers/iommu/iommufd/iommufd_test.h +++ b/drivers/iommu/iommufd/iommufd_test.h @@ -4,8 +4,8 @@ #ifndef _UAPI_IOMMUFD_TEST_H #define _UAPI_IOMMUFD_TEST_H -#include #include +#include enum { IOMMU_TEST_OP_ADD_RESERVED = 1, diff --git a/drivers/iommu/iommufd/iova_bitmap.c b/drivers/iommu/iommufd/iova_bitmap.c index b9e964b1ad5c..d90b9e253412 100644 --- a/drivers/iommu/iommufd/iova_bitmap.c +++ b/drivers/iommu/iommufd/iova_bitmap.c @@ -3,10 +3,10 @@ * Copyright (c) 2022, Oracle and/or its affiliates. * Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved */ +#include #include #include #include -#include #define BITS_PER_PAGE (PAGE_SIZE * BITS_PER_BYTE) diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c index 83bbd7c5d160..b5f5d27ee963 100644 --- a/drivers/iommu/iommufd/main.c +++ b/drivers/iommu/iommufd/main.c @@ -8,15 +8,15 @@ */ #define pr_fmt(fmt) "iommufd: " fmt +#include #include #include -#include -#include +#include #include +#include #include -#include +#include #include -#include #include "io_pagetable.h" #include "iommufd_private.h" diff --git a/drivers/iommu/iommufd/pages.c b/drivers/iommu/iommufd/pages.c index 117f644a0c5b..93d806c9c073 100644 --- a/drivers/iommu/iommufd/pages.c +++ b/drivers/iommu/iommufd/pages.c @@ -45,16 +45,16 @@ * last_iova + 1 can overflow. An iopt_pages index will always be much less than * ULONG_MAX so last_index + 1 cannot overflow. */ +#include +#include +#include +#include #include #include -#include #include -#include -#include -#include -#include "io_pagetable.h" #include "double_span.h" +#include "io_pagetable.h" #ifndef CONFIG_IOMMUFD_TEST #define TEMP_MEMORY_LIMIT 65536 diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index f95e32e29133..04293b20e20c 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -3,13 +3,14 @@ * * Kernel side components to support tools/testing/selftests/iommu */ -#include -#include -#include -#include #include +#include #include +#include +#include #include +#include +#include #include #include "../iommu-priv.h" diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h index ffc3a949f837..c2f2f6b9148e 100644 --- a/include/linux/iommufd.h +++ b/include/linux/iommufd.h @@ -6,9 +6,9 @@ #ifndef __LINUX_IOMMUFD_H #define __LINUX_IOMMUFD_H -#include -#include #include +#include +#include struct device; struct iommufd_device; diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 4dde745cfb7e..72010f71c5e4 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -4,8 +4,8 @@ #ifndef _UAPI_IOMMUFD_H #define _UAPI_IOMMUFD_H -#include #include +#include #define IOMMUFD_TYPE (';') -- cgit v1.2.3 From 03c3d7c74371a46d967fbf41628874ec04ddda96 Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Thu, 15 Aug 2024 22:11:31 +0200 Subject: nvme-rdma: send cntlid in the RDMA_CM_REQUEST Private Data When sending a RDMA_CM_REQUEST, the NVMe RDMA Transport Specification allows you to populate the cntlid field in the RDMA_CM_REQUEST Private Data. The cntlid is returned by the target on completion of the first RDMA_CM_REQUEST command (which creates the admin queue). The cntlid field can then be populated by the host when the I/O queues are created (using additional RDMA_CM_REQUEST commands), such that the target can perform extra validation for additional RDMA_CM_REQUEST commands. This additional error code and error message is also added, such that nvme_rdma_cm_msg() will display the proper error message if the target fails the RDMA_CM_REQUEST command because of this extra validation. Signed-off-by: Niklas Cassel Reviewed-by: Sagi Grimberg Reviewed-by: Christoph Hellwig Signed-off-by: Keith Busch --- drivers/nvme/host/rdma.c | 2 ++ include/linux/nvme-rdma.h | 6 +++++- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 2eb33842f971..e3520a91147b 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1876,6 +1876,8 @@ static int nvme_rdma_route_resolved(struct nvme_rdma_queue *queue) */ priv.hrqsize = cpu_to_le16(queue->queue_size); priv.hsqsize = cpu_to_le16(queue->ctrl->ctrl.sqsize); + /* cntlid should only be set when creating an I/O queue */ + priv.cntlid = cpu_to_le16(ctrl->ctrl.cntlid); } ret = rdma_connect_locked(queue->cm_id, ¶m); diff --git a/include/linux/nvme-rdma.h b/include/linux/nvme-rdma.h index eb2f04d636c8..97c5f00b9aa3 100644 --- a/include/linux/nvme-rdma.h +++ b/include/linux/nvme-rdma.h @@ -25,6 +25,7 @@ enum nvme_rdma_cm_status { NVME_RDMA_CM_NO_RSC = 0x06, NVME_RDMA_CM_INVALID_IRD = 0x07, NVME_RDMA_CM_INVALID_ORD = 0x08, + NVME_RDMA_CM_INVALID_CNTLID = 0x09, }; static inline const char *nvme_rdma_cm_msg(enum nvme_rdma_cm_status status) @@ -46,6 +47,8 @@ static inline const char *nvme_rdma_cm_msg(enum nvme_rdma_cm_status status) return "invalid IRD"; case NVME_RDMA_CM_INVALID_ORD: return "Invalid ORD"; + case NVME_RDMA_CM_INVALID_CNTLID: + return "invalid controller ID"; default: return "unrecognized reason"; } @@ -64,7 +67,8 @@ struct nvme_rdma_cm_req { __le16 qid; __le16 hrqsize; __le16 hsqsize; - u8 rsvd[24]; + __le16 cntlid; + u8 rsvd[22]; }; /** -- cgit v1.2.3 From 4715d87e11ac805ab95a75adfbf93d67dfbdbe81 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Thu, 22 Aug 2024 14:07:02 +0200 Subject: ethtool: Add support for specifying information source in cable test results Enhance the ethtool cable test interface by introducing the ability to specify the source of the diagnostic information for cable test results. This is particularly useful for PHYs that offer multiple diagnostic methods, such as Time Domain Reflectometry (TDR) and Active Link Cable Diagnostic (ALCD). Key changes: - Added `ethnl_cable_test_result_with_src` and `ethnl_cable_test_fault_length_with_src` functions to allow specifying the information source when reporting cable test results. - Updated existing `ethnl_cable_test_result` and `ethnl_cable_test_fault_length` functions to use TDR as the default source, ensuring backward compatibility. - Modified the UAPI to support these new attributes, enabling drivers to provide more detailed diagnostic information. Signed-off-by: Oleksij Rempel Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/20240822120703.1393130-3-o.rempel@pengutronix.de Signed-off-by: Jakub Kicinski --- include/linux/ethtool_netlink.h | 29 +++++++++++++++++++++++------ net/ethtool/cabletest.c | 19 +++++++++++++++---- 2 files changed, 38 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool_netlink.h b/include/linux/ethtool_netlink.h index fae0dfb9a9c8..aba91335273a 100644 --- a/include/linux/ethtool_netlink.h +++ b/include/linux/ethtool_netlink.h @@ -23,8 +23,10 @@ struct phy_device; int ethnl_cable_test_alloc(struct phy_device *phydev, u8 cmd); void ethnl_cable_test_free(struct phy_device *phydev); void ethnl_cable_test_finished(struct phy_device *phydev); -int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, u8 result); -int ethnl_cable_test_fault_length(struct phy_device *phydev, u8 pair, u32 cm); +int ethnl_cable_test_result_with_src(struct phy_device *phydev, u8 pair, + u8 result, u32 src); +int ethnl_cable_test_fault_length_with_src(struct phy_device *phydev, u8 pair, + u32 cm, u32 src); int ethnl_cable_test_amplitude(struct phy_device *phydev, u8 pair, s16 mV); int ethnl_cable_test_pulse(struct phy_device *phydev, u16 mV); int ethnl_cable_test_step(struct phy_device *phydev, u32 first, u32 last, @@ -54,14 +56,14 @@ static inline void ethnl_cable_test_free(struct phy_device *phydev) static inline void ethnl_cable_test_finished(struct phy_device *phydev) { } -static inline int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, - u8 result) +static inline int ethnl_cable_test_result_with_src(struct phy_device *phydev, + u8 pair, u8 result, u32 src) { return -EOPNOTSUPP; } -static inline int ethnl_cable_test_fault_length(struct phy_device *phydev, - u8 pair, u32 cm) +static inline int ethnl_cable_test_fault_length_with_src(struct phy_device *phydev, + u8 pair, u32 cm, u32 src) { return -EOPNOTSUPP; } @@ -119,4 +121,19 @@ static inline bool ethtool_dev_mm_supported(struct net_device *dev) } #endif /* IS_ENABLED(CONFIG_ETHTOOL_NETLINK) */ + +static inline int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, + u8 result) +{ + return ethnl_cable_test_result_with_src(phydev, pair, result, + ETHTOOL_A_CABLE_INF_SRC_TDR); +} + +static inline int ethnl_cable_test_fault_length(struct phy_device *phydev, + u8 pair, u32 cm) +{ + return ethnl_cable_test_fault_length_with_src(phydev, pair, cm, + ETHTOOL_A_CABLE_INF_SRC_TDR); +} + #endif /* _LINUX_ETHTOOL_NETLINK_H_ */ diff --git a/net/ethtool/cabletest.c b/net/ethtool/cabletest.c index 01db8f394869..ff2fe3566ace 100644 --- a/net/ethtool/cabletest.c +++ b/net/ethtool/cabletest.c @@ -164,7 +164,8 @@ void ethnl_cable_test_finished(struct phy_device *phydev) } EXPORT_SYMBOL_GPL(ethnl_cable_test_finished); -int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, u8 result) +int ethnl_cable_test_result_with_src(struct phy_device *phydev, u8 pair, + u8 result, u32 src) { struct nlattr *nest; int ret = -EMSGSIZE; @@ -177,6 +178,10 @@ int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, u8 result) goto err; if (nla_put_u8(phydev->skb, ETHTOOL_A_CABLE_RESULT_CODE, result)) goto err; + if (src != ETHTOOL_A_CABLE_INF_SRC_UNSPEC) { + if (nla_put_u32(phydev->skb, ETHTOOL_A_CABLE_RESULT_SRC, src)) + goto err; + } nla_nest_end(phydev->skb, nest); return 0; @@ -185,9 +190,10 @@ err: nla_nest_cancel(phydev->skb, nest); return ret; } -EXPORT_SYMBOL_GPL(ethnl_cable_test_result); +EXPORT_SYMBOL_GPL(ethnl_cable_test_result_with_src); -int ethnl_cable_test_fault_length(struct phy_device *phydev, u8 pair, u32 cm) +int ethnl_cable_test_fault_length_with_src(struct phy_device *phydev, u8 pair, + u32 cm, u32 src) { struct nlattr *nest; int ret = -EMSGSIZE; @@ -201,6 +207,11 @@ int ethnl_cable_test_fault_length(struct phy_device *phydev, u8 pair, u32 cm) goto err; if (nla_put_u32(phydev->skb, ETHTOOL_A_CABLE_FAULT_LENGTH_CM, cm)) goto err; + if (src != ETHTOOL_A_CABLE_INF_SRC_UNSPEC) { + if (nla_put_u32(phydev->skb, ETHTOOL_A_CABLE_FAULT_LENGTH_SRC, + src)) + goto err; + } nla_nest_end(phydev->skb, nest); return 0; @@ -209,7 +220,7 @@ err: nla_nest_cancel(phydev->skb, nest); return ret; } -EXPORT_SYMBOL_GPL(ethnl_cable_test_fault_length); +EXPORT_SYMBOL_GPL(ethnl_cable_test_fault_length_with_src); static const struct nla_policy cable_test_tdr_act_cfg_policy[] = { [ETHTOOL_A_CABLE_TEST_TDR_CFG_FIRST] = { .type = NLA_U32 }, -- cgit v1.2.3 From 19f1f11c9a8e92a2211a3854bd2cfbd4bb6303f1 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Thu, 22 Aug 2024 13:57:27 +0100 Subject: net: qualcomm: rmnet: Correct spelling in if_rmnet.h Correct spelling in if_rmnet.h As reported by codespell. Cc: Sean Tranchetti Signed-off-by: Simon Horman Reviewed-by: Subash Abhinov Kasiviswanathan Link: https://patch.msgid.link/20240822-net-spell-v1-6-3a98971ce2d2@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/if_rmnet.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/if_rmnet.h b/include/linux/if_rmnet.h index 839d1e48b85e..c44bf6e80ecb 100644 --- a/include/linux/if_rmnet.h +++ b/include/linux/if_rmnet.h @@ -42,7 +42,7 @@ struct rmnet_map_ul_csum_header { /* csum_info field: * OFFSET: where (offset in bytes) to insert computed checksum - * UDP: 1 = UDP checksum (zero checkum means no checksum) + * UDP: 1 = UDP checksum (zero checksum means no checksum) * ENABLED: 1 = checksum computation requested */ #define MAP_CSUM_UL_OFFSET_MASK GENMASK(13, 0) -- cgit v1.2.3 From 70d0bb45fae87a3b08970a318e15f317446a1956 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Thu, 22 Aug 2024 13:57:33 +0100 Subject: net: Correct spelling in headers Correct spelling in Networking headers. As reported by codespell. Signed-off-by: Simon Horman Link: https://patch.msgid.link/20240822-net-spell-v1-12-3a98971ce2d2@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/etherdevice.h | 2 +- include/linux/netdevice.h | 8 ++++---- include/net/addrconf.h | 2 +- include/net/busy_poll.h | 2 +- include/net/caif/caif_layer.h | 4 ++-- include/net/caif/cfpkt.h | 2 +- include/net/dropreason-core.h | 6 +++--- include/net/dst.h | 2 +- include/net/dst_cache.h | 2 +- include/net/erspan.h | 4 ++-- include/net/hwbm.h | 4 ++-- include/net/llc_pdu.h | 2 +- include/net/netlink.h | 16 ++++++++-------- include/net/netns/sctp.h | 4 ++-- include/net/regulatory.h | 2 +- include/net/sock.h | 4 ++-- include/net/udp.h | 2 +- include/uapi/linux/in.h | 2 +- include/uapi/linux/inet_diag.h | 2 +- 19 files changed, 36 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 0ed47d00549b..30114c25ad12 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -645,7 +645,7 @@ static inline struct ethhdr *eth_skb_pull_mac(struct sk_buff *skb) } /** - * eth_skb_pad - Pad buffer to mininum number of octets for Ethernet frame + * eth_skb_pad - Pad buffer to minimum number of octets for Ethernet frame * @skb: Buffer to pad * * An Ethernet frame should have a minimum size of 60 bytes. This function diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7dfa836d9dbf..fce70990b209 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1237,7 +1237,7 @@ struct netdev_net_notifier { * int (*ndo_fdb_del)(struct ndmsg *ndm, struct nlattr *tb[], * struct net_device *dev, * const unsigned char *addr, u16 vid) - * Deletes the FDB entry from dev coresponding to addr. + * Deletes the FDB entry from dev corresponding to addr. * int (*ndo_fdb_del_bulk)(struct nlmsghdr *nlh, struct net_device *dev, * struct netlink_ext_ack *extack); * int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, @@ -3514,7 +3514,7 @@ static inline void netdev_tx_completed_queue(struct netdev_queue *dev_queue, dql_completed(&dev_queue->dql, bytes); /* - * Without the memory barrier there is a small possiblity that + * Without the memory barrier there is a small possibility that * netdev_tx_sent_queue will miss the update and cause the queue to * be stopped forever */ @@ -4583,7 +4583,7 @@ void dev_uc_flush(struct net_device *dev); void dev_uc_init(struct net_device *dev); /** - * __dev_uc_sync - Synchonize device's unicast list + * __dev_uc_sync - Synchronize device's unicast list * @dev: device to sync * @sync: function to call if address should be added * @unsync: function to call if address should be removed @@ -4627,7 +4627,7 @@ void dev_mc_flush(struct net_device *dev); void dev_mc_init(struct net_device *dev); /** - * __dev_mc_sync - Synchonize device's multicast list + * __dev_mc_sync - Synchronize device's multicast list * @dev: device to sync * @sync: function to call if address should be added * @unsync: function to call if address should be removed diff --git a/include/net/addrconf.h b/include/net/addrconf.h index c8ed31828db3..363dd63babe7 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -333,7 +333,7 @@ static inline struct inet6_dev *__in6_dev_get(const struct net_device *dev) /** * __in6_dev_stats_get - get inet6_dev pointer for stats * @dev: network device - * @skb: skb for original incoming interface if neeeded + * @skb: skb for original incoming interface if needed * * Caller must hold rcu_read_lock or RTNL, because this function * does not take a reference on the inet6_dev. diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index 9b09acac538e..5e3b5703e4ab 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -131,7 +131,7 @@ static inline void skb_mark_napi_id(struct sk_buff *skb, #endif } -/* used in the protocol hanlder to propagate the napi_id to the socket */ +/* used in the protocol handler to propagate the napi_id to the socket */ static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_NET_RX_BUSY_POLL diff --git a/include/net/caif/caif_layer.h b/include/net/caif/caif_layer.h index 0f45d875905f..053e7c6a6a66 100644 --- a/include/net/caif/caif_layer.h +++ b/include/net/caif/caif_layer.h @@ -20,7 +20,7 @@ struct caif_payload_info; * @assert: expression to evaluate. * * This function will print a error message and a do WARN_ON if the - * assertion failes. Normally this will do a stack up at the current location. + * assertion fails. Normally this will do a stack up at the current location. */ #define caif_assert(assert) \ do { \ @@ -116,7 +116,7 @@ enum caif_direction { * @dn: Pointer down to the layer below. * @node: List node used when layer participate in a list. * @receive: Packet receive function. - * @transmit: Packet transmit funciton. + * @transmit: Packet transmit function. * @ctrlcmd: Used for control signalling upwards in the stack. * @modemcmd: Used for control signaling downwards in the stack. * @id: The identity of this layer diff --git a/include/net/caif/cfpkt.h b/include/net/caif/cfpkt.h index 44d914a50369..acf664227d96 100644 --- a/include/net/caif/cfpkt.h +++ b/include/net/caif/cfpkt.h @@ -18,7 +18,7 @@ struct cfpkt *cfpkt_create(u16 len); /* * Destroy a CAIF Packet. - * pkt Packet to be destoyed. + * pkt Packet to be destroyed. */ void cfpkt_destroy(struct cfpkt *pkt); diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h index 9707ab54fdd5..4748680e8c88 100644 --- a/include/net/dropreason-core.h +++ b/include/net/dropreason-core.h @@ -155,8 +155,8 @@ enum skb_drop_reason { /** @SKB_DROP_REASON_SOCKET_RCVBUFF: socket receive buff is full */ SKB_DROP_REASON_SOCKET_RCVBUFF, /** - * @SKB_DROP_REASON_PROTO_MEM: proto memory limition, such as udp packet - * drop out of udp_memory_allocated. + * @SKB_DROP_REASON_PROTO_MEM: proto memory limitation, such as + * udp packet drop out of udp_memory_allocated. */ SKB_DROP_REASON_PROTO_MEM, /** @@ -217,7 +217,7 @@ enum skb_drop_reason { */ SKB_DROP_REASON_TCP_ZEROWINDOW, /** - * @SKB_DROP_REASON_TCP_OLD_DATA: the TCP data reveived is already + * @SKB_DROP_REASON_TCP_OLD_DATA: the TCP data received is already * received before (spurious retrans may happened), see * LINUX_MIB_DELAYEDACKLOST */ diff --git a/include/net/dst.h b/include/net/dst.h index 0aa331bd2fdb..0f303cc60252 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -341,7 +341,7 @@ static inline void __skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, skb->dev = dev; /* - * Clear hash so that we can recalulate the hash for the + * Clear hash so that we can recalculate the hash for the * encapsulated packet, unless we have already determine the hash * over the L4 4-tuple. */ diff --git a/include/net/dst_cache.h b/include/net/dst_cache.h index b4a55d2d5e71..1961699598e2 100644 --- a/include/net/dst_cache.h +++ b/include/net/dst_cache.h @@ -102,7 +102,7 @@ int dst_cache_init(struct dst_cache *dst_cache, gfp_t gfp); * @dst_cache: the cache * * No synchronization is enforced: it must be called only when the cache - * is unsed. + * is unused. */ void dst_cache_destroy(struct dst_cache *dst_cache); diff --git a/include/net/erspan.h b/include/net/erspan.h index 6cb4cbd6a48f..c6209e7b6c96 100644 --- a/include/net/erspan.h +++ b/include/net/erspan.h @@ -89,7 +89,7 @@ enum erspan_encap_type { ERSPAN_ENCAP_NOVLAN = 0x0, /* originally without VLAN tag */ ERSPAN_ENCAP_ISL = 0x1, /* originally ISL encapsulated */ ERSPAN_ENCAP_8021Q = 0x2, /* originally 802.1Q encapsulated */ - ERSPAN_ENCAP_INFRAME = 0x3, /* VLAN tag perserved in frame */ + ERSPAN_ENCAP_INFRAME = 0x3, /* VLAN tag preserved in frame */ }; #define ERSPAN_V1_MDSIZE 4 @@ -192,7 +192,7 @@ static inline void erspan_build_header(struct sk_buff *skb, enc_type = ERSPAN_ENCAP_NOVLAN; /* If mirrored packet has vlan tag, extract tci and - * perserve vlan header in the mirrored frame. + * preserve vlan header in the mirrored frame. */ if (eth->h_proto == htons(ETH_P_8021Q)) { qp = (struct qtag_prefix *)(skb->data + 2 * ETH_ALEN); diff --git a/include/net/hwbm.h b/include/net/hwbm.h index aa495decec35..bdbe91c609ff 100644 --- a/include/net/hwbm.h +++ b/include/net/hwbm.h @@ -11,9 +11,9 @@ struct hwbm_pool { int frag_size; /* Number of buffers currently used by this pool */ int buf_num; - /* constructor called during alocation */ + /* constructor called during allocation */ int (*construct)(struct hwbm_pool *bm_pool, void *buf); - /* protect acces to the buffer counter*/ + /* protect access to the buffer counter*/ struct mutex buf_lock; /* private data */ void *priv; diff --git a/include/net/llc_pdu.h b/include/net/llc_pdu.h index 1d55ba7c45be..86681f29bda7 100644 --- a/include/net/llc_pdu.h +++ b/include/net/llc_pdu.h @@ -254,7 +254,7 @@ static inline void llc_pdu_header_init(struct sk_buff *skb, u8 type, } /** - * llc_pdu_decode_sa - extracs source address (MAC) of input frame + * llc_pdu_decode_sa - extracts, source address (MAC) of input frame * @skb: input skb that source address must be extracted from it. * @sa: pointer to source address (6 byte array). * diff --git a/include/net/netlink.h b/include/net/netlink.h index e78ce008e07c..db6af207287c 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -827,7 +827,7 @@ nlmsg_parse_deprecated_strict(const struct nlmsghdr *nlh, int hdrlen, /** * nlmsg_find_attr - find a specific attribute in a netlink message * @nlh: netlink message header - * @hdrlen: length of familiy specific header + * @hdrlen: length of family specific header * @attrtype: type of attribute to look for * * Returns the first attribute which matches the specified type. @@ -849,7 +849,7 @@ static inline struct nlattr *nlmsg_find_attr(const struct nlmsghdr *nlh, * * Validates all attributes in the specified attribute stream against the * specified policy. Validation is done in liberal mode. - * See documenation of struct nla_policy for more details. + * See documentation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ @@ -872,7 +872,7 @@ static inline int nla_validate_deprecated(const struct nlattr *head, int len, * * Validates all attributes in the specified attribute stream against the * specified policy. Validation is done in strict mode. - * See documenation of struct nla_policy for more details. + * See documentation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ @@ -887,7 +887,7 @@ static inline int nla_validate(const struct nlattr *head, int len, int maxtype, /** * nlmsg_validate_deprecated - validate a netlink message including attributes * @nlh: netlinket message header - * @hdrlen: length of familiy specific header + * @hdrlen: length of family specific header * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct @@ -933,7 +933,7 @@ static inline u32 nlmsg_seq(const struct nlmsghdr *nlh) * nlmsg_for_each_attr - iterate over a stream of attributes * @pos: loop counter, set to current attribute * @nlh: netlink message header - * @hdrlen: length of familiy specific header + * @hdrlen: length of family specific header * @rem: initialized to len, holds bytes currently remaining in stream */ #define nlmsg_for_each_attr(pos, nlh, hdrlen, rem) \ @@ -1034,7 +1034,7 @@ static inline struct sk_buff *nlmsg_new_large(size_t payload) * @skb: socket buffer the message is stored in * @nlh: netlink message header * - * Corrects the netlink message header to include the appeneded + * Corrects the netlink message header to include the appended * attributes. Only necessary if attributes have been added to * the message. */ @@ -1954,7 +1954,7 @@ static inline struct nlattr *nla_nest_start(struct sk_buff *skb, int attrtype) * @start: container attribute * * Corrects the container attribute header to include the all - * appeneded attributes. + * appended attributes. * * Returns the total data length of the skb. */ @@ -1987,7 +1987,7 @@ static inline void nla_nest_cancel(struct sk_buff *skb, struct nlattr *start) * * Validates all attributes in the nested attribute stream against the * specified policy. Attributes with a type exceeding maxtype will be - * ignored. See documenation of struct nla_policy for more details. + * ignored. See documentation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ diff --git a/include/net/netns/sctp.h b/include/net/netns/sctp.h index 7eff3d981b89..d25cd7a9c5ff 100644 --- a/include/net/netns/sctp.h +++ b/include/net/netns/sctp.h @@ -125,14 +125,14 @@ struct netns_sctp { int pf_expose; /* - * Policy for preforming sctp/socket accounting + * Policy for performing sctp/socket accounting * 0 - do socket level accounting, all assocs share sk_sndbuf * 1 - do sctp accounting, each asoc may use sk_sndbuf bytes */ int sndbuf_policy; /* - * Policy for preforming sctp/socket accounting + * Policy for performing sctp/socket accounting * 0 - do socket level accounting, all assocs share sk_rcvbuf * 1 - do sctp accounting, each asoc may use sk_rcvbuf bytes */ diff --git a/include/net/regulatory.h b/include/net/regulatory.h index a103f4c8cf75..6633627f6e76 100644 --- a/include/net/regulatory.h +++ b/include/net/regulatory.h @@ -121,7 +121,7 @@ struct regulatory_request { * @REGULATORY_DISABLE_BEACON_HINTS: enable this if your driver needs to * ensure that passive scan flags and beaconing flags may not be lifted by * cfg80211 due to regulatory beacon hints. For more information on beacon - * hints read the documenation for regulatory_hint_found_beacon() + * hints read the documentation for regulatory_hint_found_beacon() * @REGULATORY_COUNTRY_IE_FOLLOW_POWER: for devices that have a preference * that even though they may have programmed their own custom power * setting prior to wiphy registration, they want to ensure their channel diff --git a/include/net/sock.h b/include/net/sock.h index cce23ac4d514..f51d61fab059 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1624,7 +1624,7 @@ bool __lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock); * lock_sock_fast - fast version of lock_sock * @sk: socket * - * This version should be used for very small section, where process wont block + * This version should be used for very small section, where process won't block * return false if fast path is taken: * * sk_lock.slock locked, owned = 0, BH disabled @@ -2546,7 +2546,7 @@ struct sock_skb_cb { /* Store sock_skb_cb at the end of skb->cb[] so protocol families * using skb->cb[] would keep using it directly and utilize its - * alignement guarantee. + * alignment guarantee. */ #define SOCK_SKB_CB_OFFSET ((sizeof_field(struct sk_buff, cb) - \ sizeof(struct sock_skb_cb))) diff --git a/include/net/udp.h b/include/net/udp.h index 5ca53b1cec67..61222545ab1c 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -232,7 +232,7 @@ static inline __be16 udp_flow_src_port(struct net *net, struct sk_buff *skb, } /* Since this is being sent on the wire obfuscate hash a bit - * to minimize possbility that any useful information to an + * to minimize possibility that any useful information to an * attacker is leaked. Only upper 16 bits are relevant in the * computation for 16 bit port value. */ diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index d358add1611c..5d32d53508d9 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -141,7 +141,7 @@ struct in_addr { */ #define IP_PMTUDISC_INTERFACE 4 /* weaker version of IP_PMTUDISC_INTERFACE, which allows packets to get - * fragmented if they exeed the interface mtu + * fragmented if they exceed the interface mtu */ #define IP_PMTUDISC_OMIT 5 diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h index 50655de04c9b..86bb2e8b17c9 100644 --- a/include/uapi/linux/inet_diag.h +++ b/include/uapi/linux/inet_diag.h @@ -143,7 +143,7 @@ enum { INET_DIAG_SHUTDOWN, /* - * Next extenstions cannot be requested in struct inet_diag_req_v2: + * Next extensions cannot be requested in struct inet_diag_req_v2: * its field idiag_ext has only 8 bits. */ -- cgit v1.2.3 From cead0b8991713bdeb5b947758dd62287fcf8da40 Mon Sep 17 00:00:00 2001 From: Anuj Gupta Date: Mon, 26 Aug 2024 16:09:43 +0530 Subject: nvme: rename apptag and appmask to lbat and lbatm Rename apptag and appmask to lbat and lbatm so that it matches the field names used in NVMe spec. Signed-off-by: Anuj Gupta Signed-off-by: Kanchan Joshi Suggested-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Signed-off-by: Keith Busch --- drivers/nvme/host/core.c | 4 ++-- drivers/nvme/host/ioctl.c | 4 ++-- drivers/nvme/host/rdma.c | 4 ++-- drivers/nvme/target/rdma.c | 4 ++-- include/linux/nvme.h | 8 ++++---- 5 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 93aa4c10adb7..75ab62cb4aa4 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -987,8 +987,8 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns, cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->head->lba_shift) - 1); cmnd->rw.reftag = 0; - cmnd->rw.apptag = 0; - cmnd->rw.appmask = 0; + cmnd->rw.lbat = 0; + cmnd->rw.lbatm = 0; if (ns->head->ms) { /* diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index f1d58e70933f..850f81e08e7d 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -260,8 +260,8 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) c.rw.control = cpu_to_le16(io.control); c.rw.dsmgmt = cpu_to_le32(io.dsmgmt); c.rw.reftag = cpu_to_le32(io.reftag); - c.rw.apptag = cpu_to_le16(io.apptag); - c.rw.appmask = cpu_to_le16(io.appmask); + c.rw.lbat = cpu_to_le16(io.apptag); + c.rw.lbatm = cpu_to_le16(io.appmask); return nvme_submit_user_cmd(ns->queue, &c, io.addr, length, metadata, meta_len, lower_32_bits(io.slba), NULL, 0, 0); diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index e3520a91147b..15b5e06039a5 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1363,8 +1363,8 @@ static void nvme_rdma_set_sig_domain(struct blk_integrity *bi, if (control & NVME_RW_PRINFO_PRCHK_REF) domain->sig.dif.ref_remap = true; - domain->sig.dif.app_tag = le16_to_cpu(cmd->rw.apptag); - domain->sig.dif.apptag_check_mask = le16_to_cpu(cmd->rw.appmask); + domain->sig.dif.app_tag = le16_to_cpu(cmd->rw.lbat); + domain->sig.dif.apptag_check_mask = le16_to_cpu(cmd->rw.lbatm); domain->sig.dif.app_escape = true; if (pi_type == NVME_NS_DPS_PI_TYPE3) domain->sig.dif.ref_escape = true; diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 1eff8ca6a5f1..1b6264fa5803 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -578,8 +578,8 @@ static void nvmet_rdma_set_sig_domain(struct blk_integrity *bi, if (control & NVME_RW_PRINFO_PRCHK_REF) domain->sig.dif.ref_remap = true; - domain->sig.dif.app_tag = le16_to_cpu(cmd->rw.apptag); - domain->sig.dif.apptag_check_mask = le16_to_cpu(cmd->rw.appmask); + domain->sig.dif.app_tag = le16_to_cpu(cmd->rw.lbat); + domain->sig.dif.apptag_check_mask = le16_to_cpu(cmd->rw.lbatm); domain->sig.dif.app_escape = true; if (pi_type == NVME_NS_DPS_PI_TYPE3) domain->sig.dif.ref_escape = true; diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 7b2ae2e43544..b58d9405d65e 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -987,8 +987,8 @@ struct nvme_rw_command { __le16 control; __le32 dsmgmt; __le32 reftag; - __le16 apptag; - __le16 appmask; + __le16 lbat; + __le16 lbatm; }; enum { @@ -1057,8 +1057,8 @@ struct nvme_write_zeroes_cmd { __le16 control; __le32 dsmgmt; __le32 reftag; - __le16 apptag; - __le16 appmask; + __le16 lbat; + __le16 lbatm; }; enum nvme_zone_mgmt_action { -- cgit v1.2.3 From 50c6dbdfd16e312382842198a7919341ad480e05 Mon Sep 17 00:00:00 2001 From: Max Ramanouski Date: Sun, 25 Aug 2024 01:01:11 +0300 Subject: x86/ioremap: Improve iounmap() address range checks Allowing iounmap() on memory that was not ioremap()'d in the first place is obviously a bad idea. There is currently a feeble attempt to avoid errant iounmap()s by checking to see if the address is below "high_memory". But that's imprecise at best because there are plenty of high addresses that are also invalid to call iounmap() on. Thankfully, there is a more precise helper: is_ioremap_addr(). x86 just does not use it in iounmap(). Restrict iounmap() to addresses in the ioremap region, by using is_ioremap_addr(). This aligns x86 closer to the generic iounmap() implementation. Additionally, add a warning in case there is an attempt to iounmap() invalid memory. This replaces an existing silent return and will help alert folks to any incorrect usage of iounmap(). Due to VMALLOC_START on i386 not being present in asm/pgtable.h, include for asm/vmalloc.h had to be added to include/linux/ioremap.h. [ dhansen: tweak subject and changelog ] Signed-off-by: Max Ramanouski Signed-off-by: Dave Hansen Reviewed-by: Christoph Hellwig Reviewed-by: Alistair Popple Link: https://lore.kernel.org/all/20240824220111.84441-1-max8rr8%40gmail.com --- arch/x86/mm/ioremap.c | 3 ++- include/linux/ioremap.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index aa7d279321ea..70b02fc61d93 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -457,7 +458,7 @@ void iounmap(volatile void __iomem *addr) { struct vm_struct *p, *o; - if ((void __force *)addr <= high_memory) + if (WARN_ON_ONCE(!is_ioremap_addr((void __force *)addr))) return; /* diff --git a/include/linux/ioremap.h b/include/linux/ioremap.h index f0e99fc7dd8b..2bd1661fe9ad 100644 --- a/include/linux/ioremap.h +++ b/include/linux/ioremap.h @@ -4,6 +4,7 @@ #include #include +#include #if defined(CONFIG_HAS_IOMEM) || defined(CONFIG_GENERIC_IOREMAP) /* -- cgit v1.2.3 From 1bf8012fc6997f2117f6919369cde16659db60e0 Mon Sep 17 00:00:00 2001 From: Wen Yang Date: Mon, 19 Aug 2024 22:59:45 +0800 Subject: pstore: replace spinlock_t by raw_spinlock_t pstore_dump() is called when both preemption and local IRQ are disabled, and a spinlock is obtained, which is problematic for the RT kernel because in this configuration, spinlocks are sleep locks. Replace the spinlock_t with raw_spinlock_t to avoid sleeping in atomic context. Signed-off-by: Wen Yang Cc: Kees Cook Cc: Tony Luck Cc: Guilherme G. Piccoli Cc: linux-hardening@vger.kernel.org Cc: linux-kernel@vger.kernel.org Link: https://lore.kernel.org/r/20240819145945.61274-1-wen.yang@linux.dev Signed-off-by: Kees Cook --- fs/pstore/platform.c | 8 ++++---- include/linux/pstore.h | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 3497ede88aa0..84719e2bcbc4 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -288,13 +288,13 @@ static void pstore_dump(struct kmsg_dumper *dumper, why = kmsg_dump_reason_str(reason); if (pstore_cannot_block_path(reason)) { - if (!spin_trylock_irqsave(&psinfo->buf_lock, flags)) { + if (!raw_spin_trylock_irqsave(&psinfo->buf_lock, flags)) { pr_err("dump skipped in %s path because of concurrent dump\n", in_nmi() ? "NMI" : why); return; } } else { - spin_lock_irqsave(&psinfo->buf_lock, flags); + raw_spin_lock_irqsave(&psinfo->buf_lock, flags); } kmsg_dump_rewind(&iter); @@ -364,7 +364,7 @@ static void pstore_dump(struct kmsg_dumper *dumper, total += record.size; part++; } - spin_unlock_irqrestore(&psinfo->buf_lock, flags); + raw_spin_unlock_irqrestore(&psinfo->buf_lock, flags); if (saved_ret) { pr_err_once("backend (%s) writing error (%d)\n", psinfo->name, @@ -503,7 +503,7 @@ int pstore_register(struct pstore_info *psi) psi->write_user = pstore_write_user_compat; psinfo = psi; mutex_init(&psinfo->read_mutex); - spin_lock_init(&psinfo->buf_lock); + raw_spin_lock_init(&psinfo->buf_lock); if (psi->flags & PSTORE_FLAGS_DMESG) allocate_buf_for_compression(); diff --git a/include/linux/pstore.h b/include/linux/pstore.h index 638507a3c8ff..fed601053c51 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -182,7 +182,7 @@ struct pstore_info { struct module *owner; const char *name; - spinlock_t buf_lock; + raw_spinlock_t buf_lock; char *buf; size_t bufsize; -- cgit v1.2.3 From 7e8ae8486e4471513e2111aba6ac29f2357bed2a Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 26 Aug 2024 10:32:34 -0400 Subject: fs/nfsd: fix update of inode attrs in CB_GETATTR Currently, we copy the mtime and ctime to the in-core inode and then mark the inode dirty. This is fine for certain types of filesystems, but not all. Some require a real setattr to properly change these values (e.g. ceph or reexported NFS). Fix this code to call notify_change() instead, which is the proper way to effect a setattr. There is one problem though: In this case, the client is holding a write delegation and has sent us attributes to update our cache. We don't want to break the delegation for this since that would defeat the purpose. Add a new ATTR_DELEG flag that makes notify_change bypass the try_break_deleg call. Fixes: c5967721e106 ("NFSD: handle GETATTR conflict with write delegation") Reviewed-by: Christian Brauner Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/attr.c | 14 +++++++++++--- fs/nfsd/nfs4state.c | 18 +++++++++++++----- fs/nfsd/nfs4xdr.c | 2 +- fs/nfsd/state.h | 2 +- include/linux/fs.h | 1 + 5 files changed, 27 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/fs/attr.c b/fs/attr.c index 960a310581eb..0dbf43b6555c 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -489,9 +489,17 @@ int notify_change(struct mnt_idmap *idmap, struct dentry *dentry, error = security_inode_setattr(idmap, dentry, attr); if (error) return error; - error = try_break_deleg(inode, delegated_inode); - if (error) - return error; + + /* + * If ATTR_DELEG is set, then these attributes are being set on + * behalf of the holder of a write delegation. We want to avoid + * breaking the delegation in this case. + */ + if (!(ia_valid & ATTR_DELEG)) { + error = try_break_deleg(inode, delegated_inode); + if (error) + return error; + } if (inode->i_op->setattr) error = inode->i_op->setattr(idmap, dentry, attr); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 02d43f95146e..07f2496850c4 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -8815,7 +8815,7 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate, /** * nfsd4_deleg_getattr_conflict - Recall if GETATTR causes conflict * @rqstp: RPC transaction context - * @inode: file to be checked for a conflict + * @dentry: dentry of inode to be checked for a conflict * @modified: return true if file was modified * @size: new size of file if modified is true * @@ -8830,7 +8830,7 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate, * code is returned. */ __be32 -nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode, +nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct dentry *dentry, bool *modified, u64 *size) { __be32 status; @@ -8839,6 +8839,7 @@ nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode, struct file_lease *fl; struct iattr attrs; struct nfs4_cb_fattr *ncf; + struct inode *inode = d_inode(dentry); *modified = false; ctx = locks_inode_context(inode); @@ -8890,15 +8891,22 @@ break_lease: ncf->ncf_cur_fsize != ncf->ncf_cb_fsize)) ncf->ncf_file_modified = true; if (ncf->ncf_file_modified) { + int err; + /* * Per section 10.4.3 of RFC 8881, the server would * not update the file's metadata with the client's * modified size */ attrs.ia_mtime = attrs.ia_ctime = current_time(inode); - attrs.ia_valid = ATTR_MTIME | ATTR_CTIME; - setattr_copy(&nop_mnt_idmap, inode, &attrs); - mark_inode_dirty(inode); + attrs.ia_valid = ATTR_MTIME | ATTR_CTIME | ATTR_DELEG; + inode_lock(inode); + err = notify_change(&nop_mnt_idmap, dentry, &attrs, NULL); + inode_unlock(inode); + if (err) { + nfs4_put_stid(&dp->dl_stid); + return nfserrno(err); + } ncf->ncf_cur_fsize = ncf->ncf_cb_fsize; *size = ncf->ncf_cur_fsize; *modified = true; diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 43ccf6119cf1..97f583777972 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -3565,7 +3565,7 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, } args.size = 0; if (attrmask[0] & (FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE)) { - status = nfsd4_deleg_getattr_conflict(rqstp, d_inode(dentry), + status = nfsd4_deleg_getattr_conflict(rqstp, dentry, &file_modified, &size); if (status) goto out; diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index ffc217099d19..ec4559ecd193 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -781,5 +781,5 @@ static inline bool try_to_expire_client(struct nfs4_client *clp) } extern __be32 nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, - struct inode *inode, bool *file_modified, u64 *size); + struct dentry *dentry, bool *file_modified, u64 *size); #endif /* NFSD4_STATE_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 0283cf366c2a..bafc1d134b94 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -208,6 +208,7 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define ATTR_OPEN (1 << 15) /* Truncating from open(O_TRUNC) */ #define ATTR_TIMES_SET (1 << 16) #define ATTR_TOUCH (1 << 17) +#define ATTR_DELEG (1 << 18) /* Delegated attrs. Don't break write delegations */ /* * Whiteout is represented by a char device. The following constants define the -- cgit v1.2.3 From 13acf2b74803a9a9ab3475c306d5814cf3cefbd8 Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Mon, 26 Aug 2024 14:32:42 +0800 Subject: ata: libata: Remove obsolete function declarations The function ata_schedule_scsi_eh() was removed with commit f8bbfc247efb ("[PATCH] SCSI: make scsi_implement_eh() generic API for SCSI transports"), and the function ata_sff_irq_clear() was removed with commit 37f65b8bc262("libata-sff: ata_sff_irq_clear() is BMDMA specific"). Remove the now useless declarations of these functions in drivers/ata/libata.h and include/linux/libata.h. Signed-off-by: Gaosheng Cui Signed-off-by: Damien Le Moal --- drivers/ata/libata.h | 1 - include/linux/libata.h | 1 - 2 files changed, 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h index 6abf265f626e..22e667394368 100644 --- a/drivers/ata/libata.h +++ b/drivers/ata/libata.h @@ -124,7 +124,6 @@ extern void ata_scsi_set_sense_information(struct ata_device *dev, const struct ata_taskfile *tf); extern void ata_scsi_media_change_notify(struct ata_device *dev); extern void ata_scsi_hotplug(struct work_struct *work); -extern void ata_schedule_scsi_eh(struct Scsi_Host *shost); extern void ata_scsi_dev_rescan(struct work_struct *work); extern int ata_scsi_user_scan(struct Scsi_Host *shost, unsigned int channel, unsigned int id, u64 lun); diff --git a/include/linux/libata.h b/include/linux/libata.h index 0279c0a6302f..6552e90753ae 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -2006,7 +2006,6 @@ extern unsigned int ata_sff_data_xfer(struct ata_queued_cmd *qc, extern unsigned int ata_sff_data_xfer32(struct ata_queued_cmd *qc, unsigned char *buf, unsigned int buflen, int rw); extern void ata_sff_irq_on(struct ata_port *ap); -extern void ata_sff_irq_clear(struct ata_port *ap); extern int ata_sff_hsm_move(struct ata_port *ap, struct ata_queued_cmd *qc, u8 status, int in_wq); extern void ata_sff_queue_work(struct work_struct *work); -- cgit v1.2.3 From cda1fba15cb2282b3c364805c9767698f11c3b0e Mon Sep 17 00:00:00 2001 From: Arkadiusz Kubalewski Date: Fri, 23 Aug 2024 00:25:12 +0200 Subject: dpll: add Embedded SYNC feature for a pin Implement and document new pin attributes for providing Embedded SYNC capabilities to the DPLL subsystem users through a netlink pin-get do/dump messages. Allow the user to set Embedded SYNC frequency with pin-set do netlink message. Reviewed-by: Aleksandr Loktionov Signed-off-by: Arkadiusz Kubalewski Reviewed-by: Jiri Pirko Link: https://patch.msgid.link/20240822222513.255179-2-arkadiusz.kubalewski@intel.com Signed-off-by: Jakub Kicinski --- Documentation/driver-api/dpll.rst | 21 ++++++ Documentation/netlink/specs/dpll.yaml | 24 +++++++ drivers/dpll/dpll_netlink.c | 130 ++++++++++++++++++++++++++++++++++ drivers/dpll/dpll_nl.c | 5 +- include/linux/dpll.h | 15 ++++ include/uapi/linux/dpll.h | 3 + 6 files changed, 196 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/Documentation/driver-api/dpll.rst b/Documentation/driver-api/dpll.rst index ea8d16600e16..e6855cd37e85 100644 --- a/Documentation/driver-api/dpll.rst +++ b/Documentation/driver-api/dpll.rst @@ -214,6 +214,27 @@ offset values are fractional with 3-digit decimal places and shell be divided with ``DPLL_PIN_PHASE_OFFSET_DIVIDER`` to get integer part and modulo divided to get fractional part. +Embedded SYNC +============= + +Device may provide ability to use Embedded SYNC feature. It allows +to embed additional SYNC signal into the base frequency of a pin - a one +special pulse of base frequency signal every time SYNC signal pulse +happens. The user can configure the frequency of Embedded SYNC. +The Embedded SYNC capability is always related to a given base frequency +and HW capabilities. The user is provided a range of Embedded SYNC +frequencies supported, depending on current base frequency configured for +the pin. + + ========================================= ================================= + ``DPLL_A_PIN_ESYNC_FREQUENCY`` current Embedded SYNC frequency + ``DPLL_A_PIN_ESYNC_FREQUENCY_SUPPORTED`` nest available Embedded SYNC + frequency ranges + ``DPLL_A_PIN_FREQUENCY_MIN`` attr minimum value of frequency + ``DPLL_A_PIN_FREQUENCY_MAX`` attr maximum value of frequency + ``DPLL_A_PIN_ESYNC_PULSE`` pulse type of Embedded SYNC + ========================================= ================================= + Configuration commands group ============================ diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml index 94132d30e0e0..f2894ca35de8 100644 --- a/Documentation/netlink/specs/dpll.yaml +++ b/Documentation/netlink/specs/dpll.yaml @@ -345,6 +345,26 @@ attribute-sets: Value is in PPM (parts per million). This may be implemented for example for pin of type PIN_TYPE_SYNCE_ETH_PORT. + - + name: esync-frequency + type: u64 + doc: | + Frequency of Embedded SYNC signal. If provided, the pin is configured + with a SYNC signal embedded into its base clock frequency. + - + name: esync-frequency-supported + type: nest + multi-attr: true + nested-attributes: frequency-range + doc: | + If provided a pin is capable of embedding a SYNC signal (within given + range) into its base frequency signal. + - + name: esync-pulse + type: u32 + doc: | + A ratio of high to low state of a SYNC signal pulse embedded + into base clock frequency. Value is in percents. - name: pin-parent-device subset-of: pin @@ -510,6 +530,9 @@ operations: - phase-adjust-max - phase-adjust - fractional-frequency-offset + - esync-frequency + - esync-frequency-supported + - esync-pulse dump: request: @@ -536,6 +559,7 @@ operations: - parent-device - parent-pin - phase-adjust + - esync-frequency - name: pin-create-ntf doc: Notification about pin appearing diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c index 98e6ad8528d3..fc0280dcddd1 100644 --- a/drivers/dpll/dpll_netlink.c +++ b/drivers/dpll/dpll_netlink.c @@ -342,6 +342,51 @@ dpll_msg_add_pin_freq(struct sk_buff *msg, struct dpll_pin *pin, return 0; } +static int +dpll_msg_add_pin_esync(struct sk_buff *msg, struct dpll_pin *pin, + struct dpll_pin_ref *ref, struct netlink_ext_ack *extack) +{ + const struct dpll_pin_ops *ops = dpll_pin_ops(ref); + struct dpll_device *dpll = ref->dpll; + struct dpll_pin_esync esync; + struct nlattr *nest; + int ret, i; + + if (!ops->esync_get) + return 0; + ret = ops->esync_get(pin, dpll_pin_on_dpll_priv(dpll, pin), dpll, + dpll_priv(dpll), &esync, extack); + if (ret == -EOPNOTSUPP) + return 0; + else if (ret) + return ret; + if (nla_put_64bit(msg, DPLL_A_PIN_ESYNC_FREQUENCY, sizeof(esync.freq), + &esync.freq, DPLL_A_PIN_PAD)) + return -EMSGSIZE; + if (nla_put_u32(msg, DPLL_A_PIN_ESYNC_PULSE, esync.pulse)) + return -EMSGSIZE; + for (i = 0; i < esync.range_num; i++) { + nest = nla_nest_start(msg, + DPLL_A_PIN_ESYNC_FREQUENCY_SUPPORTED); + if (!nest) + return -EMSGSIZE; + if (nla_put_64bit(msg, DPLL_A_PIN_FREQUENCY_MIN, + sizeof(esync.range[i].min), + &esync.range[i].min, DPLL_A_PIN_PAD)) + goto nest_cancel; + if (nla_put_64bit(msg, DPLL_A_PIN_FREQUENCY_MAX, + sizeof(esync.range[i].max), + &esync.range[i].max, DPLL_A_PIN_PAD)) + goto nest_cancel; + nla_nest_end(msg, nest); + } + return 0; + +nest_cancel: + nla_nest_cancel(msg, nest); + return -EMSGSIZE; +} + static bool dpll_pin_is_freq_supported(struct dpll_pin *pin, u32 freq) { int fs; @@ -481,6 +526,9 @@ dpll_cmd_pin_get_one(struct sk_buff *msg, struct dpll_pin *pin, if (ret) return ret; ret = dpll_msg_add_ffo(msg, pin, ref, extack); + if (ret) + return ret; + ret = dpll_msg_add_pin_esync(msg, pin, ref, extack); if (ret) return ret; if (xa_empty(&pin->parent_refs)) @@ -738,6 +786,83 @@ rollback: return ret; } +static int +dpll_pin_esync_set(struct dpll_pin *pin, struct nlattr *a, + struct netlink_ext_ack *extack) +{ + struct dpll_pin_ref *ref, *failed; + const struct dpll_pin_ops *ops; + struct dpll_pin_esync esync; + u64 freq = nla_get_u64(a); + struct dpll_device *dpll; + bool supported = false; + unsigned long i; + int ret; + + xa_for_each(&pin->dpll_refs, i, ref) { + ops = dpll_pin_ops(ref); + if (!ops->esync_set || !ops->esync_get) { + NL_SET_ERR_MSG(extack, + "embedded sync feature is not supported by this device"); + return -EOPNOTSUPP; + } + } + ref = dpll_xa_ref_dpll_first(&pin->dpll_refs); + ops = dpll_pin_ops(ref); + dpll = ref->dpll; + ret = ops->esync_get(pin, dpll_pin_on_dpll_priv(dpll, pin), dpll, + dpll_priv(dpll), &esync, extack); + if (ret) { + NL_SET_ERR_MSG(extack, "unable to get current embedded sync frequency value"); + return ret; + } + if (freq == esync.freq) + return 0; + for (i = 0; i < esync.range_num; i++) + if (freq <= esync.range[i].max && freq >= esync.range[i].min) + supported = true; + if (!supported) { + NL_SET_ERR_MSG_ATTR(extack, a, + "requested embedded sync frequency value is not supported by this device"); + return -EINVAL; + } + + xa_for_each(&pin->dpll_refs, i, ref) { + void *pin_dpll_priv; + + ops = dpll_pin_ops(ref); + dpll = ref->dpll; + pin_dpll_priv = dpll_pin_on_dpll_priv(dpll, pin); + ret = ops->esync_set(pin, pin_dpll_priv, dpll, dpll_priv(dpll), + freq, extack); + if (ret) { + failed = ref; + NL_SET_ERR_MSG_FMT(extack, + "embedded sync frequency set failed for dpll_id: %u", + dpll->id); + goto rollback; + } + } + __dpll_pin_change_ntf(pin); + + return 0; + +rollback: + xa_for_each(&pin->dpll_refs, i, ref) { + void *pin_dpll_priv; + + if (ref == failed) + break; + ops = dpll_pin_ops(ref); + dpll = ref->dpll; + pin_dpll_priv = dpll_pin_on_dpll_priv(dpll, pin); + if (ops->esync_set(pin, pin_dpll_priv, dpll, dpll_priv(dpll), + esync.freq, extack)) + NL_SET_ERR_MSG(extack, "set embedded sync frequency rollback failed"); + } + return ret; +} + static int dpll_pin_on_pin_state_set(struct dpll_pin *pin, u32 parent_idx, enum dpll_pin_state state, @@ -1039,6 +1164,11 @@ dpll_pin_set_from_nlattr(struct dpll_pin *pin, struct genl_info *info) if (ret) return ret; break; + case DPLL_A_PIN_ESYNC_FREQUENCY: + ret = dpll_pin_esync_set(pin, a, info->extack); + if (ret) + return ret; + break; } } diff --git a/drivers/dpll/dpll_nl.c b/drivers/dpll/dpll_nl.c index 1e95f5397cfc..fe9b6893d261 100644 --- a/drivers/dpll/dpll_nl.c +++ b/drivers/dpll/dpll_nl.c @@ -62,7 +62,7 @@ static const struct nla_policy dpll_pin_get_dump_nl_policy[DPLL_A_PIN_ID + 1] = }; /* DPLL_CMD_PIN_SET - do */ -static const struct nla_policy dpll_pin_set_nl_policy[DPLL_A_PIN_PHASE_ADJUST + 1] = { +static const struct nla_policy dpll_pin_set_nl_policy[DPLL_A_PIN_ESYNC_FREQUENCY + 1] = { [DPLL_A_PIN_ID] = { .type = NLA_U32, }, [DPLL_A_PIN_FREQUENCY] = { .type = NLA_U64, }, [DPLL_A_PIN_DIRECTION] = NLA_POLICY_RANGE(NLA_U32, 1, 2), @@ -71,6 +71,7 @@ static const struct nla_policy dpll_pin_set_nl_policy[DPLL_A_PIN_PHASE_ADJUST + [DPLL_A_PIN_PARENT_DEVICE] = NLA_POLICY_NESTED(dpll_pin_parent_device_nl_policy), [DPLL_A_PIN_PARENT_PIN] = NLA_POLICY_NESTED(dpll_pin_parent_pin_nl_policy), [DPLL_A_PIN_PHASE_ADJUST] = { .type = NLA_S32, }, + [DPLL_A_PIN_ESYNC_FREQUENCY] = { .type = NLA_U64, }, }; /* Ops table for dpll */ @@ -138,7 +139,7 @@ static const struct genl_split_ops dpll_nl_ops[] = { .doit = dpll_nl_pin_set_doit, .post_doit = dpll_pin_post_doit, .policy = dpll_pin_set_nl_policy, - .maxattr = DPLL_A_PIN_PHASE_ADJUST, + .maxattr = DPLL_A_PIN_ESYNC_FREQUENCY, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, }; diff --git a/include/linux/dpll.h b/include/linux/dpll.h index d275736230b3..81f7b623d0ba 100644 --- a/include/linux/dpll.h +++ b/include/linux/dpll.h @@ -15,6 +15,7 @@ struct dpll_device; struct dpll_pin; +struct dpll_pin_esync; struct dpll_device_ops { int (*mode_get)(const struct dpll_device *dpll, void *dpll_priv, @@ -83,6 +84,13 @@ struct dpll_pin_ops { int (*ffo_get)(const struct dpll_pin *pin, void *pin_priv, const struct dpll_device *dpll, void *dpll_priv, s64 *ffo, struct netlink_ext_ack *extack); + int (*esync_set)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + u64 freq, struct netlink_ext_ack *extack); + int (*esync_get)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + struct dpll_pin_esync *esync, + struct netlink_ext_ack *extack); }; struct dpll_pin_frequency { @@ -111,6 +119,13 @@ struct dpll_pin_phase_adjust_range { s32 max; }; +struct dpll_pin_esync { + u64 freq; + const struct dpll_pin_frequency *range; + u8 range_num; + u8 pulse; +}; + struct dpll_pin_properties { const char *board_label; const char *panel_label; diff --git a/include/uapi/linux/dpll.h b/include/uapi/linux/dpll.h index 0c13d7f1a1bc..b0654ade7b7e 100644 --- a/include/uapi/linux/dpll.h +++ b/include/uapi/linux/dpll.h @@ -210,6 +210,9 @@ enum dpll_a_pin { DPLL_A_PIN_PHASE_ADJUST, DPLL_A_PIN_PHASE_OFFSET, DPLL_A_PIN_FRACTIONAL_FREQUENCY_OFFSET, + DPLL_A_PIN_ESYNC_FREQUENCY, + DPLL_A_PIN_ESYNC_FREQUENCY_SUPPORTED, + DPLL_A_PIN_ESYNC_PULSE, __DPLL_A_PIN_MAX, DPLL_A_PIN_MAX = (__DPLL_A_PIN_MAX - 1) -- cgit v1.2.3 From 7e8fb2eda9885ea2d13179a4c0bbf810f900ef25 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 22 Jul 2024 22:16:47 -0700 Subject: jbd2: fix kernel-doc for j_transaction_overhead_buffers Use the correct struct member name in the kernel-doc notation to prevent a kernel-doc build warning. include/linux/jbd2.h:1303: warning: Function parameter or struct member 'j_transaction_overhead_buffers' not described in 'journal_s' include/linux/jbd2.h:1303: warning: Excess struct member 'j_transaction_overhead' description in 'journal_s' Fixes: e3a00a23781c ("jbd2: precompute number of transaction descriptor blocks") Reported-by: Stephen Rothwell Closes: https://lore.kernel.org/linux-next/20240710182252.4c281445@canb.auug.org.au/ Signed-off-by: Randy Dunlap Reviewed-by: Jan Kara Link: https://patch.msgid.link/20240723051647.3053491-1-rdunlap@infradead.org Signed-off-by: Theodore Ts'o --- include/linux/jbd2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 5157d92b6f23..17662eae408f 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1086,7 +1086,7 @@ struct journal_s int j_revoke_records_per_block; /** - * @j_transaction_overhead: + * @j_transaction_overhead_buffers: * * Number of blocks each transaction needs for its own bookkeeping */ -- cgit v1.2.3 From fa10db138d205362026daecc8ea65d4e339ade00 Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Thu, 1 Aug 2024 09:38:10 +0800 Subject: jbd2: remove unused return value of jbd2_fc_release_bufs Remove unused return value of jbd2_fc_release_bufs. Signed-off-by: Kemeng Shi Reviewed-by: Jan Kara Reviewed-by: Zhang Yi Link: https://patch.msgid.link/20240801013815.2393869-4-shikemeng@huaweicloud.com Signed-off-by: Theodore Ts'o --- fs/jbd2/journal.c | 4 +--- include/linux/jbd2.h | 2 +- 2 files changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 326373ab022a..51f184ba830c 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -903,7 +903,7 @@ int jbd2_fc_wait_bufs(journal_t *journal, int num_blks) } EXPORT_SYMBOL(jbd2_fc_wait_bufs); -int jbd2_fc_release_bufs(journal_t *journal) +void jbd2_fc_release_bufs(journal_t *journal) { struct buffer_head *bh; int i, j_fc_off; @@ -917,8 +917,6 @@ int jbd2_fc_release_bufs(journal_t *journal) put_bh(bh); journal->j_fc_wbuf[i] = NULL; } - - return 0; } EXPORT_SYMBOL(jbd2_fc_release_bufs); diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 17662eae408f..8aef9bb6ad57 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1675,7 +1675,7 @@ int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out); int jbd2_submit_inode_data(journal_t *journal, struct jbd2_inode *jinode); int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode); int jbd2_fc_wait_bufs(journal_t *journal, int num_blks); -int jbd2_fc_release_bufs(journal_t *journal); +void jbd2_fc_release_bufs(journal_t *journal); /* * is_journal_abort -- cgit v1.2.3 From 9a948c0c8e741776ee6d938b49d34d22034fbb7d Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Wed, 14 Aug 2024 11:34:15 +0800 Subject: ceph: Remove unused declarations These functions is never implemented and used. Signed-off-by: Yue Haibing Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/mds_client.h | 3 --- fs/ceph/super.h | 2 -- include/linux/ceph/osd_client.h | 2 -- 3 files changed, 7 deletions(-) (limited to 'include/linux') diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 9bcc7f181bfe..585ab5a6d87d 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -559,9 +559,6 @@ extern struct ceph_mds_session * ceph_get_mds_session(struct ceph_mds_session *s); extern void ceph_put_mds_session(struct ceph_mds_session *s); -extern int ceph_send_msg_mds(struct ceph_mds_client *mdsc, - struct ceph_msg *msg, int mds); - extern int ceph_mdsc_init(struct ceph_fs_client *fsc); extern void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc); extern void ceph_mdsc_force_umount(struct ceph_mds_client *mdsc); diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 6e817bf1337c..c88bf53f68e9 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -1056,8 +1056,6 @@ extern int ceph_fill_trace(struct super_block *sb, extern int ceph_readdir_prepopulate(struct ceph_mds_request *req, struct ceph_mds_session *session); -extern int ceph_inode_holds_cap(struct inode *inode, int mask); - extern bool ceph_inode_set_size(struct inode *inode, loff_t size); extern void __ceph_do_pending_vmtruncate(struct inode *inode); diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index f66f6aac74f6..d7941478158c 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -449,8 +449,6 @@ extern int ceph_osdc_init(struct ceph_osd_client *osdc, extern void ceph_osdc_stop(struct ceph_osd_client *osdc); extern void ceph_osdc_reopen_osds(struct ceph_osd_client *osdc); -extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc, - struct ceph_msg *msg); extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg); void ceph_osdc_update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb); -- cgit v1.2.3 From 373d3f8dcbb1c0d764123653ca4574be636b8d86 Mon Sep 17 00:00:00 2001 From: Zijun Hu Date: Sun, 11 Aug 2024 12:47:26 +0800 Subject: wifi: rfkill: Correct parameter type for rfkill_set_hw_state_reason() Change type of parameter @reason to enum rfkill_hard_block_reasons for API rfkill_set_hw_state_reason() according to its comments, and all kernel callers have invoked the API with enum type actually. Signed-off-by: Zijun Hu Link: https://patch.msgid.link/20240811-rfkill_fix-v2-1-9050760336f4@quicinc.com Signed-off-by: Johannes Berg --- include/linux/rfkill.h | 5 +++-- net/rfkill/core.c | 8 ++------ 2 files changed, 5 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rfkill.h b/include/linux/rfkill.h index 373003ace639..997b34197385 100644 --- a/include/linux/rfkill.h +++ b/include/linux/rfkill.h @@ -147,7 +147,8 @@ void rfkill_destroy(struct rfkill *rfkill); * Prefer to use rfkill_set_hw_state if you don't need any special reason. */ bool rfkill_set_hw_state_reason(struct rfkill *rfkill, - bool blocked, unsigned long reason); + bool blocked, + enum rfkill_hard_block_reasons reason); /** * rfkill_set_hw_state - Set the internal rfkill hardware block state * @rfkill: pointer to the rfkill class to modify. @@ -280,7 +281,7 @@ static inline void rfkill_destroy(struct rfkill *rfkill) static inline bool rfkill_set_hw_state_reason(struct rfkill *rfkill, bool blocked, - unsigned long reason) + enum rfkill_hard_block_reasons reason) { return blocked; } diff --git a/net/rfkill/core.c b/net/rfkill/core.c index 7a5367628c05..13a5126bc36e 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -539,18 +539,14 @@ bool rfkill_get_global_sw_state(const enum rfkill_type type) #endif bool rfkill_set_hw_state_reason(struct rfkill *rfkill, - bool blocked, unsigned long reason) + bool blocked, + enum rfkill_hard_block_reasons reason) { unsigned long flags; bool ret, prev; BUG_ON(!rfkill); - if (WARN(reason & ~(RFKILL_HARD_BLOCK_SIGNAL | - RFKILL_HARD_BLOCK_NOT_OWNER), - "hw_state reason not supported: 0x%lx", reason)) - return rfkill_blocked(rfkill); - spin_lock_irqsave(&rfkill->lock, flags); prev = !!(rfkill->hard_block_reasons & reason); if (blocked) { -- cgit v1.2.3 From 21b91d40575fb64f3f280f6c3af586e32a704a92 Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Thu, 8 Aug 2024 22:05:54 +0800 Subject: efi: Remove unused declaration efi_initialize_iomem_resources() Since commit cf8e8658100d ("arch: Remove Itanium (IA-64) architecture"), this is not used anymore. Signed-off-by: Yue Haibing Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 6bf3c4fe8511..e28d88066033 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -764,8 +764,6 @@ extern int efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md); extern int __efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md); extern void efi_mem_reserve(phys_addr_t addr, u64 size); extern int efi_mem_reserve_persistent(phys_addr_t addr, u64 size); -extern void efi_initialize_iomem_resources(struct resource *code_resource, - struct resource *data_resource, struct resource *bss_resource); extern u64 efi_get_fdt_params(struct efi_memory_map_data *data); extern struct kobject *efi_kobj; -- cgit v1.2.3 From 2b55d6a42d14c8675e38d6d9adca3014fdf01951 Mon Sep 17 00:00:00 2001 From: "Uladzislau Rezki (Sony)" Date: Tue, 20 Aug 2024 17:59:35 +0200 Subject: rcu/kvfree: Add kvfree_rcu_barrier() API Add a kvfree_rcu_barrier() function. It waits until all in-flight pointers are freed over RCU machinery. It does not wait any GP completion and it is within its right to return immediately if there are no outstanding pointers. This function is useful when there is a need to guarantee that a memory is fully freed before destroying memory caches. For example, during unloading a kernel module. Signed-off-by: Uladzislau Rezki (Sony) Signed-off-by: Vlastimil Babka --- include/linux/rcutiny.h | 5 +++ include/linux/rcutree.h | 1 + kernel/rcu/tree.c | 109 ++++++++++++++++++++++++++++++++++++++++++++---- 3 files changed, 107 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index d9ac7b136aea..522123050ff8 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -111,6 +111,11 @@ static inline void __kvfree_call_rcu(struct rcu_head *head, void *ptr) kvfree(ptr); } +static inline void kvfree_rcu_barrier(void) +{ + rcu_barrier(); +} + #ifdef CONFIG_KASAN_GENERIC void kvfree_call_rcu(struct rcu_head *head, void *ptr); #else diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 254244202ea9..58e7db80f3a8 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -35,6 +35,7 @@ static inline void rcu_virt_note_context_switch(void) void synchronize_rcu_expedited(void); void kvfree_call_rcu(struct rcu_head *head, void *ptr); +void kvfree_rcu_barrier(void); void rcu_barrier(void); void rcu_momentary_dyntick_idle(void); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index e641cc681901..be00aac5f4e7 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3584,18 +3584,15 @@ kvfree_rcu_drain_ready(struct kfree_rcu_cpu *krcp) } /* - * This function is invoked after the KFREE_DRAIN_JIFFIES timeout. + * Return: %true if a work is queued, %false otherwise. */ -static void kfree_rcu_monitor(struct work_struct *work) +static bool +kvfree_rcu_queue_batch(struct kfree_rcu_cpu *krcp) { - struct kfree_rcu_cpu *krcp = container_of(work, - struct kfree_rcu_cpu, monitor_work.work); unsigned long flags; + bool queued = false; int i, j; - // Drain ready for reclaim. - kvfree_rcu_drain_ready(krcp); - raw_spin_lock_irqsave(&krcp->lock, flags); // Attempt to start a new batch. @@ -3634,11 +3631,27 @@ static void kfree_rcu_monitor(struct work_struct *work) // be that the work is in the pending state when // channels have been detached following by each // other. - queue_rcu_work(system_wq, &krwp->rcu_work); + queued = queue_rcu_work(system_wq, &krwp->rcu_work); } } raw_spin_unlock_irqrestore(&krcp->lock, flags); + return queued; +} + +/* + * This function is invoked after the KFREE_DRAIN_JIFFIES timeout. + */ +static void kfree_rcu_monitor(struct work_struct *work) +{ + struct kfree_rcu_cpu *krcp = container_of(work, + struct kfree_rcu_cpu, monitor_work.work); + + // Drain ready for reclaim. + kvfree_rcu_drain_ready(krcp); + + // Queue a batch for a rest. + kvfree_rcu_queue_batch(krcp); // If there is nothing to detach, it means that our job is // successfully done here. In case of having at least one @@ -3859,6 +3872,86 @@ unlock_return: } EXPORT_SYMBOL_GPL(kvfree_call_rcu); +/** + * kvfree_rcu_barrier - Wait until all in-flight kvfree_rcu() complete. + * + * Note that a single argument of kvfree_rcu() call has a slow path that + * triggers synchronize_rcu() following by freeing a pointer. It is done + * before the return from the function. Therefore for any single-argument + * call that will result in a kfree() to a cache that is to be destroyed + * during module exit, it is developer's responsibility to ensure that all + * such calls have returned before the call to kmem_cache_destroy(). + */ +void kvfree_rcu_barrier(void) +{ + struct kfree_rcu_cpu_work *krwp; + struct kfree_rcu_cpu *krcp; + bool queued; + int i, cpu; + + /* + * Firstly we detach objects and queue them over an RCU-batch + * for all CPUs. Finally queued works are flushed for each CPU. + * + * Please note. If there are outstanding batches for a particular + * CPU, those have to be finished first following by queuing a new. + */ + for_each_possible_cpu(cpu) { + krcp = per_cpu_ptr(&krc, cpu); + + /* + * Check if this CPU has any objects which have been queued for a + * new GP completion. If not(means nothing to detach), we are done + * with it. If any batch is pending/running for this "krcp", below + * per-cpu flush_rcu_work() waits its completion(see last step). + */ + if (!need_offload_krc(krcp)) + continue; + + while (1) { + /* + * If we are not able to queue a new RCU work it means: + * - batches for this CPU are still in flight which should + * be flushed first and then repeat; + * - no objects to detach, because of concurrency. + */ + queued = kvfree_rcu_queue_batch(krcp); + + /* + * Bail out, if there is no need to offload this "krcp" + * anymore. As noted earlier it can run concurrently. + */ + if (queued || !need_offload_krc(krcp)) + break; + + /* There are ongoing batches. */ + for (i = 0; i < KFREE_N_BATCHES; i++) { + krwp = &(krcp->krw_arr[i]); + flush_rcu_work(&krwp->rcu_work); + } + } + } + + /* + * Now we guarantee that all objects are flushed. + */ + for_each_possible_cpu(cpu) { + krcp = per_cpu_ptr(&krc, cpu); + + /* + * A monitor work can drain ready to reclaim objects + * directly. Wait its completion if running or pending. + */ + cancel_delayed_work_sync(&krcp->monitor_work); + + for (i = 0; i < KFREE_N_BATCHES; i++) { + krwp = &(krcp->krw_arr[i]); + flush_rcu_work(&krwp->rcu_work); + } + } +} +EXPORT_SYMBOL_GPL(kvfree_rcu_barrier); + static unsigned long kfree_rcu_shrink_count(struct shrinker *shrink, struct shrink_control *sc) { -- cgit v1.2.3 From b3c34245756adada8a50bdaedbb3965b071c7b0a Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Fri, 9 Aug 2024 17:36:55 +0200 Subject: kasan: catch invalid free before SLUB reinitializes the object Currently, when KASAN is combined with init-on-free behavior, the initialization happens before KASAN's "invalid free" checks. More importantly, a subsequent commit will want to RCU-delay the actual SLUB freeing of an object, and we'd like KASAN to still validate synchronously that freeing the object is permitted. (Otherwise this change will make the existing testcase kmem_cache_invalid_free fail.) So add a new KASAN hook that allows KASAN to pre-validate a kmem_cache_free() operation before SLUB actually starts modifying the object or its metadata. Inside KASAN, this: - moves checks from poison_slab_object() into check_slab_allocation() - moves kasan_arch_is_ready() up into callers of poison_slab_object() - removes "ip" argument of poison_slab_object() and __kasan_slab_free() (since those functions no longer do any reporting) Acked-by: Vlastimil Babka #slub Reviewed-by: Andrey Konovalov Signed-off-by: Jann Horn Signed-off-by: Vlastimil Babka --- include/linux/kasan.h | 54 ++++++++++++++++++++++++++++++++++++++++++--- mm/kasan/common.c | 61 ++++++++++++++++++++++++++++++--------------------- mm/slub.c | 7 ++++++ 3 files changed, 94 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 70d6a8f6e25d..1570c7191176 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -175,13 +175,55 @@ static __always_inline void * __must_check kasan_init_slab_obj( return (void *)object; } -bool __kasan_slab_free(struct kmem_cache *s, void *object, - unsigned long ip, bool init); +bool __kasan_slab_pre_free(struct kmem_cache *s, void *object, + unsigned long ip); +/** + * kasan_slab_pre_free - Check whether freeing a slab object is safe. + * @object: Object to be freed. + * + * This function checks whether freeing the given object is safe. It may + * check for double-free and invalid-free bugs and report them. + * + * This function is intended only for use by the slab allocator. + * + * @Return true if freeing the object is unsafe; false otherwise. + */ +static __always_inline bool kasan_slab_pre_free(struct kmem_cache *s, + void *object) +{ + if (kasan_enabled()) + return __kasan_slab_pre_free(s, object, _RET_IP_); + return false; +} + +bool __kasan_slab_free(struct kmem_cache *s, void *object, bool init); +/** + * kasan_slab_free - Poison, initialize, and quarantine a slab object. + * @object: Object to be freed. + * @init: Whether to initialize the object. + * + * This function informs that a slab object has been freed and is not + * supposed to be accessed anymore, except for objects in + * SLAB_TYPESAFE_BY_RCU caches. + * + * For KASAN modes that have integrated memory initialization + * (kasan_has_integrated_init() == true), this function also initializes + * the object's memory. For other modes, the @init argument is ignored. + * + * This function might also take ownership of the object to quarantine it. + * When this happens, KASAN will defer freeing the object to a later + * stage and handle it internally until then. The return value indicates + * whether KASAN took ownership of the object. + * + * This function is intended only for use by the slab allocator. + * + * @Return true if KASAN took ownership of the object; false otherwise. + */ static __always_inline bool kasan_slab_free(struct kmem_cache *s, void *object, bool init) { if (kasan_enabled()) - return __kasan_slab_free(s, object, _RET_IP_, init); + return __kasan_slab_free(s, object, init); return false; } @@ -371,6 +413,12 @@ static inline void *kasan_init_slab_obj(struct kmem_cache *cache, { return (void *)object; } + +static inline bool kasan_slab_pre_free(struct kmem_cache *s, void *object) +{ + return false; +} + static inline bool kasan_slab_free(struct kmem_cache *s, void *object, bool init) { return false; diff --git a/mm/kasan/common.c b/mm/kasan/common.c index 85e7c6b4575c..f26bbc087b3b 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -208,15 +208,12 @@ void * __must_check __kasan_init_slab_obj(struct kmem_cache *cache, return (void *)object; } -static inline bool poison_slab_object(struct kmem_cache *cache, void *object, - unsigned long ip, bool init) +/* Returns true when freeing the object is not safe. */ +static bool check_slab_allocation(struct kmem_cache *cache, void *object, + unsigned long ip) { - void *tagged_object; - - if (!kasan_arch_is_ready()) - return false; + void *tagged_object = object; - tagged_object = object; object = kasan_reset_tag(object); if (unlikely(nearest_obj(cache, virt_to_slab(object), object) != object)) { @@ -224,37 +221,46 @@ static inline bool poison_slab_object(struct kmem_cache *cache, void *object, return true; } - /* RCU slabs could be legally used after free within the RCU period. */ - if (unlikely(cache->flags & SLAB_TYPESAFE_BY_RCU)) - return false; - if (!kasan_byte_accessible(tagged_object)) { kasan_report_invalid_free(tagged_object, ip, KASAN_REPORT_DOUBLE_FREE); return true; } + return false; +} + +static inline void poison_slab_object(struct kmem_cache *cache, void *object, + bool init) +{ + void *tagged_object = object; + + object = kasan_reset_tag(object); + + /* RCU slabs could be legally used after free within the RCU period. */ + if (unlikely(cache->flags & SLAB_TYPESAFE_BY_RCU)) + return; + kasan_poison(object, round_up(cache->object_size, KASAN_GRANULE_SIZE), KASAN_SLAB_FREE, init); if (kasan_stack_collection_enabled()) kasan_save_free_info(cache, tagged_object); +} - return false; +bool __kasan_slab_pre_free(struct kmem_cache *cache, void *object, + unsigned long ip) +{ + if (!kasan_arch_is_ready() || is_kfence_address(object)) + return false; + return check_slab_allocation(cache, object, ip); } -bool __kasan_slab_free(struct kmem_cache *cache, void *object, - unsigned long ip, bool init) +bool __kasan_slab_free(struct kmem_cache *cache, void *object, bool init) { - if (is_kfence_address(object)) + if (!kasan_arch_is_ready() || is_kfence_address(object)) return false; - /* - * If the object is buggy, do not let slab put the object onto the - * freelist. The object will thus never be allocated again and its - * metadata will never get released. - */ - if (poison_slab_object(cache, object, ip, init)) - return true; + poison_slab_object(cache, object, init); /* * If the object is put into quarantine, do not let slab put the object @@ -504,11 +510,16 @@ bool __kasan_mempool_poison_object(void *ptr, unsigned long ip) return true; } - if (is_kfence_address(ptr)) - return false; + if (is_kfence_address(ptr) || !kasan_arch_is_ready()) + return true; slab = folio_slab(folio); - return !poison_slab_object(slab->slab_cache, ptr, ip, false); + + if (check_slab_allocation(slab->slab_cache, ptr, ip)) + return false; + + poison_slab_object(slab->slab_cache, ptr, false); + return true; } void __kasan_mempool_unpoison_object(void *ptr, size_t size, unsigned long ip) diff --git a/mm/slub.c b/mm/slub.c index c9d8a2497fd6..4946488cb5a7 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2226,6 +2226,13 @@ bool slab_free_hook(struct kmem_cache *s, void *x, bool init) if (kfence_free(x)) return false; + /* + * Give KASAN a chance to notice an invalid free operation before we + * modify the object. + */ + if (kasan_slab_pre_free(s, x)) + return false; + /* * As memory initialization might be integrated into KASAN, * kasan_slab_free and initialization memset's must be -- cgit v1.2.3 From b8c8ba73c68bb3c3e9dad22f488b86c540c839f9 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Fri, 9 Aug 2024 17:36:56 +0200 Subject: slub: Introduce CONFIG_SLUB_RCU_DEBUG Currently, KASAN is unable to catch use-after-free in SLAB_TYPESAFE_BY_RCU slabs because use-after-free is allowed within the RCU grace period by design. Add a SLUB debugging feature which RCU-delays every individual kmem_cache_free() before either actually freeing the object or handing it off to KASAN, and change KASAN to poison freed objects as normal when this option is enabled. For now I've configured Kconfig.debug to default-enable this feature in the KASAN GENERIC and SW_TAGS modes; I'm not enabling it by default in HW_TAGS mode because I'm not sure if it might have unwanted performance degradation effects there. Note that this is mostly useful with KASAN in the quarantine-based GENERIC mode; SLAB_TYPESAFE_BY_RCU slabs are basically always also slabs with a ->ctor, and KASAN's assign_tag() currently has to assign fixed tags for those, reducing the effectiveness of SW_TAGS/HW_TAGS mode. (A possible future extension of this work would be to also let SLUB call the ->ctor() on every allocation instead of only when the slab page is allocated; then tag-based modes would be able to assign new tags on every reallocation.) Tested-by: syzbot+263726e59eab6b442723@syzkaller.appspotmail.com Reviewed-by: Andrey Konovalov Acked-by: Marco Elver Acked-by: Vlastimil Babka #slab Signed-off-by: Jann Horn Signed-off-by: Vlastimil Babka --- include/linux/kasan.h | 17 +++++++---- mm/Kconfig.debug | 32 +++++++++++++++++++++ mm/kasan/common.c | 11 +++---- mm/kasan/kasan_test.c | 46 ++++++++++++++++++++++++++++++ mm/slab_common.c | 16 +++++++++++ mm/slub.c | 79 +++++++++++++++++++++++++++++++++++++++++++++------ 6 files changed, 182 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 1570c7191176..00a3bf7c0d8f 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -196,15 +196,18 @@ static __always_inline bool kasan_slab_pre_free(struct kmem_cache *s, return false; } -bool __kasan_slab_free(struct kmem_cache *s, void *object, bool init); +bool __kasan_slab_free(struct kmem_cache *s, void *object, bool init, + bool still_accessible); /** * kasan_slab_free - Poison, initialize, and quarantine a slab object. * @object: Object to be freed. * @init: Whether to initialize the object. + * @still_accessible: Whether the object contents are still accessible. * * This function informs that a slab object has been freed and is not - * supposed to be accessed anymore, except for objects in - * SLAB_TYPESAFE_BY_RCU caches. + * supposed to be accessed anymore, except when @still_accessible is set + * (indicating that the object is in a SLAB_TYPESAFE_BY_RCU cache and an RCU + * grace period might not have passed yet). * * For KASAN modes that have integrated memory initialization * (kasan_has_integrated_init() == true), this function also initializes @@ -220,10 +223,11 @@ bool __kasan_slab_free(struct kmem_cache *s, void *object, bool init); * @Return true if KASAN took ownership of the object; false otherwise. */ static __always_inline bool kasan_slab_free(struct kmem_cache *s, - void *object, bool init) + void *object, bool init, + bool still_accessible) { if (kasan_enabled()) - return __kasan_slab_free(s, object, init); + return __kasan_slab_free(s, object, init, still_accessible); return false; } @@ -419,7 +423,8 @@ static inline bool kasan_slab_pre_free(struct kmem_cache *s, void *object) return false; } -static inline bool kasan_slab_free(struct kmem_cache *s, void *object, bool init) +static inline bool kasan_slab_free(struct kmem_cache *s, void *object, + bool init, bool still_accessible) { return false; } diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug index afc72fde0f03..41a58536531d 100644 --- a/mm/Kconfig.debug +++ b/mm/Kconfig.debug @@ -70,6 +70,38 @@ config SLUB_DEBUG_ON off in a kernel built with CONFIG_SLUB_DEBUG_ON by specifying "slab_debug=-". +config SLUB_RCU_DEBUG + bool "Enable UAF detection in TYPESAFE_BY_RCU caches (for KASAN)" + depends on SLUB_DEBUG + # SLUB_RCU_DEBUG should build fine without KASAN, but is currently useless + # without KASAN, so mark it as a dependency of KASAN for now. + depends on KASAN + default KASAN_GENERIC || KASAN_SW_TAGS + help + Make SLAB_TYPESAFE_BY_RCU caches behave approximately as if the cache + was not marked as SLAB_TYPESAFE_BY_RCU and every caller used + kfree_rcu() instead. + + This is intended for use in combination with KASAN, to enable KASAN to + detect use-after-free accesses in such caches. + (KFENCE is able to do that independent of this flag.) + + This might degrade performance. + Unfortunately this also prevents a very specific bug pattern from + triggering (insufficient checks against an object being recycled + within the RCU grace period); so this option can be turned off even on + KASAN builds, in case you want to test for such a bug. + + If you're using this for testing bugs / fuzzing and care about + catching all the bugs WAY more than performance, you might want to + also turn on CONFIG_RCU_STRICT_GRACE_PERIOD. + + WARNING: + This is designed as a debugging feature, not a security feature. + Objects are sometimes recycled without RCU delay under memory pressure. + + If unsure, say N. + config PAGE_OWNER bool "Track page owner" depends on DEBUG_KERNEL && STACKTRACE_SUPPORT diff --git a/mm/kasan/common.c b/mm/kasan/common.c index f26bbc087b3b..ed4873e18c75 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -230,14 +230,14 @@ static bool check_slab_allocation(struct kmem_cache *cache, void *object, } static inline void poison_slab_object(struct kmem_cache *cache, void *object, - bool init) + bool init, bool still_accessible) { void *tagged_object = object; object = kasan_reset_tag(object); /* RCU slabs could be legally used after free within the RCU period. */ - if (unlikely(cache->flags & SLAB_TYPESAFE_BY_RCU)) + if (unlikely(still_accessible)) return; kasan_poison(object, round_up(cache->object_size, KASAN_GRANULE_SIZE), @@ -255,12 +255,13 @@ bool __kasan_slab_pre_free(struct kmem_cache *cache, void *object, return check_slab_allocation(cache, object, ip); } -bool __kasan_slab_free(struct kmem_cache *cache, void *object, bool init) +bool __kasan_slab_free(struct kmem_cache *cache, void *object, bool init, + bool still_accessible) { if (!kasan_arch_is_ready() || is_kfence_address(object)) return false; - poison_slab_object(cache, object, init); + poison_slab_object(cache, object, init, still_accessible); /* * If the object is put into quarantine, do not let slab put the object @@ -518,7 +519,7 @@ bool __kasan_mempool_poison_object(void *ptr, unsigned long ip) if (check_slab_allocation(slab->slab_cache, ptr, ip)) return false; - poison_slab_object(slab->slab_cache, ptr, false); + poison_slab_object(slab->slab_cache, ptr, false, false); return true; } diff --git a/mm/kasan/kasan_test.c b/mm/kasan/kasan_test.c index 7b32be2a3cf0..567d33b493e2 100644 --- a/mm/kasan/kasan_test.c +++ b/mm/kasan/kasan_test.c @@ -996,6 +996,51 @@ static void kmem_cache_invalid_free(struct kunit *test) kmem_cache_destroy(cache); } +static void kmem_cache_rcu_uaf(struct kunit *test) +{ + char *p; + size_t size = 200; + struct kmem_cache *cache; + + KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_SLUB_RCU_DEBUG); + + cache = kmem_cache_create("test_cache", size, 0, SLAB_TYPESAFE_BY_RCU, + NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, cache); + + p = kmem_cache_alloc(cache, GFP_KERNEL); + if (!p) { + kunit_err(test, "Allocation failed: %s\n", __func__); + kmem_cache_destroy(cache); + return; + } + *p = 1; + + rcu_read_lock(); + + /* Free the object - this will internally schedule an RCU callback. */ + kmem_cache_free(cache, p); + + /* + * We should still be allowed to access the object at this point because + * the cache is SLAB_TYPESAFE_BY_RCU and we've been in an RCU read-side + * critical section since before the kmem_cache_free(). + */ + READ_ONCE(*p); + + rcu_read_unlock(); + + /* + * Wait for the RCU callback to execute; after this, the object should + * have actually been freed from KASAN's perspective. + */ + rcu_barrier(); + + KUNIT_EXPECT_KASAN_FAIL(test, READ_ONCE(*p)); + + kmem_cache_destroy(cache); +} + static void empty_cache_ctor(void *object) { } static void kmem_cache_double_destroy(struct kunit *test) @@ -1937,6 +1982,7 @@ static struct kunit_case kasan_kunit_test_cases[] = { KUNIT_CASE(kmem_cache_oob), KUNIT_CASE(kmem_cache_double_free), KUNIT_CASE(kmem_cache_invalid_free), + KUNIT_CASE(kmem_cache_rcu_uaf), KUNIT_CASE(kmem_cache_double_destroy), KUNIT_CASE(kmem_cache_accounted), KUNIT_CASE(kmem_cache_bulk), diff --git a/mm/slab_common.c b/mm/slab_common.c index 1a2873293f5d..884e8e70a56d 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -511,6 +511,22 @@ void kmem_cache_destroy(struct kmem_cache *s) /* in-flight kfree_rcu()'s may include objects from our cache */ kvfree_rcu_barrier(); + if (IS_ENABLED(CONFIG_SLUB_RCU_DEBUG) && + (s->flags & SLAB_TYPESAFE_BY_RCU)) { + /* + * Under CONFIG_SLUB_RCU_DEBUG, when objects in a + * SLAB_TYPESAFE_BY_RCU slab are freed, SLUB will internally + * defer their freeing with call_rcu(). + * Wait for such call_rcu() invocations here before actually + * destroying the cache. + * + * It doesn't matter that we haven't looked at the slab refcount + * yet - slabs with SLAB_TYPESAFE_BY_RCU can't be merged, so + * the refcount should be 1 here. + */ + rcu_barrier(); + } + cpus_read_lock(); mutex_lock(&slab_mutex); diff --git a/mm/slub.c b/mm/slub.c index 4946488cb5a7..95977f25a760 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2200,16 +2200,30 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab, } #endif /* CONFIG_MEMCG */ +#ifdef CONFIG_SLUB_RCU_DEBUG +static void slab_free_after_rcu_debug(struct rcu_head *rcu_head); + +struct rcu_delayed_free { + struct rcu_head head; + void *object; +}; +#endif + /* * Hooks for other subsystems that check memory allocations. In a typical * production configuration these hooks all should produce no code at all. * * Returns true if freeing of the object can proceed, false if its reuse - * was delayed by KASAN quarantine, or it was returned to KFENCE. + * was delayed by CONFIG_SLUB_RCU_DEBUG or KASAN quarantine, or it was returned + * to KFENCE. */ static __always_inline -bool slab_free_hook(struct kmem_cache *s, void *x, bool init) +bool slab_free_hook(struct kmem_cache *s, void *x, bool init, + bool after_rcu_delay) { + /* Are the object contents still accessible? */ + bool still_accessible = (s->flags & SLAB_TYPESAFE_BY_RCU) && !after_rcu_delay; + kmemleak_free_recursive(x, s->flags); kmsan_slab_free(s, x); @@ -2219,7 +2233,7 @@ bool slab_free_hook(struct kmem_cache *s, void *x, bool init) debug_check_no_obj_freed(x, s->object_size); /* Use KCSAN to help debug racy use-after-free. */ - if (!(s->flags & SLAB_TYPESAFE_BY_RCU)) + if (!still_accessible) __kcsan_check_access(x, s->object_size, KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ASSERT); @@ -2233,6 +2247,28 @@ bool slab_free_hook(struct kmem_cache *s, void *x, bool init) if (kasan_slab_pre_free(s, x)) return false; +#ifdef CONFIG_SLUB_RCU_DEBUG + if (still_accessible) { + struct rcu_delayed_free *delayed_free; + + delayed_free = kmalloc(sizeof(*delayed_free), GFP_NOWAIT); + if (delayed_free) { + /* + * Let KASAN track our call stack as a "related work + * creation", just like if the object had been freed + * normally via kfree_rcu(). + * We have to do this manually because the rcu_head is + * not located inside the object. + */ + kasan_record_aux_stack_noalloc(x); + + delayed_free->object = x; + call_rcu(&delayed_free->head, slab_free_after_rcu_debug); + return false; + } + } +#endif /* CONFIG_SLUB_RCU_DEBUG */ + /* * As memory initialization might be integrated into KASAN, * kasan_slab_free and initialization memset's must be @@ -2256,7 +2292,7 @@ bool slab_free_hook(struct kmem_cache *s, void *x, bool init) s->size - inuse - rsize); } /* KASAN might put x into memory quarantine, delaying its reuse. */ - return !kasan_slab_free(s, x, init); + return !kasan_slab_free(s, x, init, still_accessible); } static __fastpath_inline @@ -2270,7 +2306,7 @@ bool slab_free_freelist_hook(struct kmem_cache *s, void **head, void **tail, bool init; if (is_kfence_address(next)) { - slab_free_hook(s, next, false); + slab_free_hook(s, next, false, false); return false; } @@ -2285,7 +2321,7 @@ bool slab_free_freelist_hook(struct kmem_cache *s, void **head, void **tail, next = get_freepointer(s, object); /* If object's reuse doesn't have to be delayed */ - if (likely(slab_free_hook(s, object, init))) { + if (likely(slab_free_hook(s, object, init, false))) { /* Move object to the new freelist */ set_freepointer(s, object, *head); *head = object; @@ -4477,7 +4513,7 @@ void slab_free(struct kmem_cache *s, struct slab *slab, void *object, memcg_slab_free_hook(s, slab, &object, 1); alloc_tagging_slab_free_hook(s, slab, &object, 1); - if (likely(slab_free_hook(s, object, slab_want_init_on_free(s)))) + if (likely(slab_free_hook(s, object, slab_want_init_on_free(s), false))) do_slab_free(s, slab, object, object, 1, addr); } @@ -4486,7 +4522,7 @@ void slab_free(struct kmem_cache *s, struct slab *slab, void *object, static noinline void memcg_alloc_abort_single(struct kmem_cache *s, void *object) { - if (likely(slab_free_hook(s, object, slab_want_init_on_free(s)))) + if (likely(slab_free_hook(s, object, slab_want_init_on_free(s), false))) do_slab_free(s, virt_to_slab(object), object, object, 1, _RET_IP_); } #endif @@ -4505,6 +4541,33 @@ void slab_free_bulk(struct kmem_cache *s, struct slab *slab, void *head, do_slab_free(s, slab, head, tail, cnt, addr); } +#ifdef CONFIG_SLUB_RCU_DEBUG +static void slab_free_after_rcu_debug(struct rcu_head *rcu_head) +{ + struct rcu_delayed_free *delayed_free = + container_of(rcu_head, struct rcu_delayed_free, head); + void *object = delayed_free->object; + struct slab *slab = virt_to_slab(object); + struct kmem_cache *s; + + kfree(delayed_free); + + if (WARN_ON(is_kfence_address(object))) + return; + + /* find the object and the cache again */ + if (WARN_ON(!slab)) + return; + s = slab->slab_cache; + if (WARN_ON(!(s->flags & SLAB_TYPESAFE_BY_RCU))) + return; + + /* resume freeing */ + if (slab_free_hook(s, object, slab_want_init_on_free(s), true)) + do_slab_free(s, slab, object, object, 1, _THIS_IP_); +} +#endif /* CONFIG_SLUB_RCU_DEBUG */ + #ifdef CONFIG_KASAN_GENERIC void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr) { -- cgit v1.2.3 From a9b8f337ea4eb66e4980f90bb73e8786e56cacfd Mon Sep 17 00:00:00 2001 From: Sunil V L Date: Mon, 12 Aug 2024 06:29:14 +0530 Subject: ACPI: scan: Add a weak arch_sort_irqchip_probe() to order the IRQCHIP probe MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Unlike OF framework, the irqchip probe using IRQCHIP_ACPI_DECLARE has no order defined. Depending on the Makefile is not a good idea. So, usually it is worked around by mandating only root interrupt controller probed using IRQCHIP_ACPI_DECLARE and other interrupt controllers are probed via cascade mechanism. However, this is also not a clean solution because if there are multiple root controllers (ex: RINTC in RISC-V which is per CPU) which need to be probed first, then the cascade will happen for every root controller. So, introduce an architecture specific weak function arch_sort_irqchip_probe() to order the probing of the interrupt controllers which can be implemented by different architectures as per their interrupt controller hierarchy. Signed-off-by: Sunil V L Tested-by: Björn Töpel Link: https://patch.msgid.link/20240812005929.113499-3-sunilvl@ventanamicro.com Signed-off-by: Rafael J. Wysocki --- drivers/acpi/scan.c | 3 +++ include/linux/acpi.h | 2 ++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 22ae7829a915..607bbb8b90da 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -2757,6 +2757,8 @@ static int __init acpi_match_madt(union acpi_subtable_headers *header, return 0; } +void __weak arch_sort_irqchip_probe(struct acpi_probe_entry *ap_head, int nr) { } + int __init __acpi_probe_device_table(struct acpi_probe_entry *ap_head, int nr) { int count = 0; @@ -2765,6 +2767,7 @@ int __init __acpi_probe_device_table(struct acpi_probe_entry *ap_head, int nr) return 0; mutex_lock(&acpi_probe_mutex); + arch_sort_irqchip_probe(ap_head, nr); for (ape = ap_head; nr; ape++, nr--) { if (ACPI_COMPARE_NAMESEG(ACPI_SIG_MADT, ape->id)) { acpi_probe_count = 0; diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 0687a442fec7..3fff86f95c2f 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1343,6 +1343,8 @@ struct acpi_probe_entry { kernel_ulong_t driver_data; }; +void arch_sort_irqchip_probe(struct acpi_probe_entry *ap_head, int nr); + #define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, \ valid, data, fn) \ static const struct acpi_probe_entry __acpi_probe_##name \ -- cgit v1.2.3 From f7d7ccf92f2b9398781f791b4af1a74a9f65b5c3 Mon Sep 17 00:00:00 2001 From: Sunil V L Date: Mon, 12 Aug 2024 06:29:15 +0530 Subject: ACPI: bus: Add acpi_riscv_init() function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a new function for RISC-V to do architecture specific initialization similar to acpi_arm_init(). Some of the ACPI tables are architecture specific and there is no reason trying to find them on other architectures. So, add acpi_riscv_init() similar to acpi_arm_init(). Signed-off-by: Sunil V L Tested-by: Björn Töpel Link: https://patch.msgid.link/20240812005929.113499-4-sunilvl@ventanamicro.com Signed-off-by: Rafael J. Wysocki --- drivers/acpi/bus.c | 1 + drivers/acpi/riscv/Makefile | 2 +- drivers/acpi/riscv/init.c | 11 +++++++++++ include/linux/acpi.h | 6 ++++++ 4 files changed, 19 insertions(+), 1 deletion(-) create mode 100644 drivers/acpi/riscv/init.c (limited to 'include/linux') diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index 284bc2e03580..48d277657203 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -1459,6 +1459,7 @@ static int __init acpi_init(void) acpi_hest_init(); acpi_ghes_init(); acpi_arm_init(); + acpi_riscv_init(); acpi_scan_init(); acpi_ec_init(); acpi_debugfs_init(); diff --git a/drivers/acpi/riscv/Makefile b/drivers/acpi/riscv/Makefile index 86b0925f612d..877de00d1b50 100644 --- a/drivers/acpi/riscv/Makefile +++ b/drivers/acpi/riscv/Makefile @@ -1,4 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-y += rhct.o +obj-y += rhct.o init.o obj-$(CONFIG_ACPI_PROCESSOR_IDLE) += cpuidle.o obj-$(CONFIG_ACPI_CPPC_LIB) += cppc.o diff --git a/drivers/acpi/riscv/init.c b/drivers/acpi/riscv/init.c new file mode 100644 index 000000000000..a875a76aa44c --- /dev/null +++ b/drivers/acpi/riscv/init.c @@ -0,0 +1,11 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2023-2024, Ventana Micro Systems Inc + * Author: Sunil V L + */ + +#include + +void __init acpi_riscv_init(void) +{ +} diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 3fff86f95c2f..892025d873f0 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1531,6 +1531,12 @@ void acpi_arm_init(void); static inline void acpi_arm_init(void) { } #endif +#ifdef CONFIG_RISCV +void acpi_riscv_init(void); +#else +static inline void acpi_riscv_init(void) { } +#endif + #ifdef CONFIG_ACPI_PCC void acpi_init_pcc(void); #else -- cgit v1.2.3 From 21734d29f84ad610dbafdca5f4c1bf7ecceeb2fb Mon Sep 17 00:00:00 2001 From: Sunil V L Date: Mon, 12 Aug 2024 06:29:19 +0530 Subject: ACPI: bus: Add RINTC IRQ model for RISC-V MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add the IRQ model for RISC-V INTC so that acpi_set_irq_model can use this for RISC-V. Signed-off-by: Sunil V L Tested-by: Björn Töpel Link: https://patch.msgid.link/20240812005929.113499-8-sunilvl@ventanamicro.com Signed-off-by: Rafael J. Wysocki --- drivers/acpi/bus.c | 3 +++ include/linux/acpi.h | 1 + 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index 48d277657203..16917dc3ad60 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -1203,6 +1203,9 @@ static int __init acpi_bus_init_irq(void) case ACPI_IRQ_MODEL_LPIC: message = "LPIC"; break; + case ACPI_IRQ_MODEL_RINTC: + message = "RINTC"; + break; default: pr_info("Unknown interrupt routing model\n"); return -ENODEV; diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 892025d873f0..3a21f1cf126f 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -107,6 +107,7 @@ enum acpi_irq_model_id { ACPI_IRQ_MODEL_PLATFORM, ACPI_IRQ_MODEL_GIC, ACPI_IRQ_MODEL_LPIC, + ACPI_IRQ_MODEL_RINTC, ACPI_IRQ_MODEL_COUNT }; -- cgit v1.2.3 From fbe826b1c10699a70b81a441fe47b817d1019f37 Mon Sep 17 00:00:00 2001 From: Sunil V L Date: Mon, 12 Aug 2024 06:29:27 +0530 Subject: irqchip/riscv-imsic: Add ACPI support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit RISC-V IMSIC interrupt controller provides IPI and MSI support. Currently, DT based drivers setup the IPI feature early during boot but defer setting up the MSI functionality. However, in ACPI systems, PCI subsystem is probed early and assume MSI controller is already setup. Hence, both IPI and MSI features need to be initialized early itself. Signed-off-by: Sunil V L Reviewed-by: Anup Patel Tested-by: Björn Töpel Acked-by: Thomas Gleixner Link: https://patch.msgid.link/20240812005929.113499-16-sunilvl@ventanamicro.com Signed-off-by: Rafael J. Wysocki --- drivers/irqchip/irq-riscv-imsic-early.c | 64 +++++++++++++++++++++++++++++- drivers/irqchip/irq-riscv-imsic-platform.c | 32 ++++++++++++--- drivers/irqchip/irq-riscv-imsic-state.c | 57 ++++++++++++++++---------- drivers/irqchip/irq-riscv-imsic-state.h | 2 +- include/linux/irqchip/riscv-imsic.h | 9 +++++ 5 files changed, 134 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/drivers/irqchip/irq-riscv-imsic-early.c b/drivers/irqchip/irq-riscv-imsic-early.c index 4fbb37074d29..c5c2e6929a2f 100644 --- a/drivers/irqchip/irq-riscv-imsic-early.c +++ b/drivers/irqchip/irq-riscv-imsic-early.c @@ -5,13 +5,16 @@ */ #define pr_fmt(fmt) "riscv-imsic: " fmt +#include #include #include #include #include #include #include +#include #include +#include #include #include @@ -182,7 +185,7 @@ static int __init imsic_early_dt_init(struct device_node *node, struct device_no int rc; /* Setup IMSIC state */ - rc = imsic_setup_state(fwnode); + rc = imsic_setup_state(fwnode, NULL); if (rc) { pr_err("%pfwP: failed to setup state (error %d)\n", fwnode, rc); return rc; @@ -199,3 +202,62 @@ static int __init imsic_early_dt_init(struct device_node *node, struct device_no } IRQCHIP_DECLARE(riscv_imsic, "riscv,imsics", imsic_early_dt_init); + +#ifdef CONFIG_ACPI + +static struct fwnode_handle *imsic_acpi_fwnode; + +struct fwnode_handle *imsic_acpi_get_fwnode(struct device *dev) +{ + return imsic_acpi_fwnode; +} + +static int __init imsic_early_acpi_init(union acpi_subtable_headers *header, + const unsigned long end) +{ + struct acpi_madt_imsic *imsic = (struct acpi_madt_imsic *)header; + int rc; + + imsic_acpi_fwnode = irq_domain_alloc_named_fwnode("imsic"); + if (!imsic_acpi_fwnode) { + pr_err("unable to allocate IMSIC FW node\n"); + return -ENOMEM; + } + + /* Setup IMSIC state */ + rc = imsic_setup_state(imsic_acpi_fwnode, imsic); + if (rc) { + pr_err("%pfwP: failed to setup state (error %d)\n", imsic_acpi_fwnode, rc); + return rc; + } + + /* Do early setup of IMSIC state and IPIs */ + rc = imsic_early_probe(imsic_acpi_fwnode); + if (rc) { + irq_domain_free_fwnode(imsic_acpi_fwnode); + imsic_acpi_fwnode = NULL; + return rc; + } + + rc = imsic_platform_acpi_probe(imsic_acpi_fwnode); + +#ifdef CONFIG_PCI + if (!rc) + pci_msi_register_fwnode_provider(&imsic_acpi_get_fwnode); +#endif + + if (rc) + pr_err("%pfwP: failed to register IMSIC for MSI functionality (error %d)\n", + imsic_acpi_fwnode, rc); + + /* + * Even if imsic_platform_acpi_probe() fails, the IPI part of IMSIC can + * continue to work. So, no need to return failure. This is similar to + * DT where IPI works but MSI probe fails for some reason. + */ + return 0; +} + +IRQCHIP_ACPI_DECLARE(riscv_imsic, ACPI_MADT_TYPE_IMSIC, NULL, + 1, imsic_early_acpi_init); +#endif diff --git a/drivers/irqchip/irq-riscv-imsic-platform.c b/drivers/irqchip/irq-riscv-imsic-platform.c index 11723a763c10..64905e6f52d7 100644 --- a/drivers/irqchip/irq-riscv-imsic-platform.c +++ b/drivers/irqchip/irq-riscv-imsic-platform.c @@ -5,6 +5,7 @@ */ #define pr_fmt(fmt) "riscv-imsic: " fmt +#include #include #include #include @@ -348,18 +349,37 @@ int imsic_irqdomain_init(void) return 0; } -static int imsic_platform_probe(struct platform_device *pdev) +static int imsic_platform_probe_common(struct fwnode_handle *fwnode) { - struct device *dev = &pdev->dev; - - if (imsic && imsic->fwnode != dev->fwnode) { - dev_err(dev, "fwnode mismatch\n"); + if (imsic && imsic->fwnode != fwnode) { + pr_err("%pfwP: fwnode mismatch\n", fwnode); return -ENODEV; } return imsic_irqdomain_init(); } +static int imsic_platform_dt_probe(struct platform_device *pdev) +{ + return imsic_platform_probe_common(pdev->dev.fwnode); +} + +#ifdef CONFIG_ACPI + +/* + * On ACPI based systems, PCI enumeration happens early during boot in + * acpi_scan_init(). PCI enumeration expects MSI domain setup before + * it calls pci_set_msi_domain(). Hence, unlike in DT where + * imsic-platform drive probe happens late during boot, ACPI based + * systems need to setup the MSI domain early. + */ +int imsic_platform_acpi_probe(struct fwnode_handle *fwnode) +{ + return imsic_platform_probe_common(fwnode); +} + +#endif + static const struct of_device_id imsic_platform_match[] = { { .compatible = "riscv,imsics" }, {} @@ -370,6 +390,6 @@ static struct platform_driver imsic_platform_driver = { .name = "riscv-imsic", .of_match_table = imsic_platform_match, }, - .probe = imsic_platform_probe, + .probe = imsic_platform_dt_probe, }; builtin_platform_driver(imsic_platform_driver); diff --git a/drivers/irqchip/irq-riscv-imsic-state.c b/drivers/irqchip/irq-riscv-imsic-state.c index f9e70832863a..b97e6cd89ed7 100644 --- a/drivers/irqchip/irq-riscv-imsic-state.c +++ b/drivers/irqchip/irq-riscv-imsic-state.c @@ -5,6 +5,7 @@ */ #define pr_fmt(fmt) "riscv-imsic: " fmt +#include #include #include #include @@ -564,18 +565,36 @@ static int __init imsic_populate_global_dt(struct fwnode_handle *fwnode, return 0; } +static int __init imsic_populate_global_acpi(struct fwnode_handle *fwnode, + struct imsic_global_config *global, + u32 *nr_parent_irqs, void *opaque) +{ + struct acpi_madt_imsic *imsic = (struct acpi_madt_imsic *)opaque; + + global->guest_index_bits = imsic->guest_index_bits; + global->hart_index_bits = imsic->hart_index_bits; + global->group_index_bits = imsic->group_index_bits; + global->group_index_shift = imsic->group_index_shift; + global->nr_ids = imsic->num_ids; + global->nr_guest_ids = imsic->num_guest_ids; + return 0; +} + static int __init imsic_get_parent_hartid(struct fwnode_handle *fwnode, u32 index, unsigned long *hartid) { struct of_phandle_args parent; int rc; - /* - * Currently, only OF fwnode is supported so extend this - * function for ACPI support. - */ - if (!is_of_node(fwnode)) - return -EINVAL; + if (!is_of_node(fwnode)) { + if (hartid) + *hartid = acpi_rintc_index_to_hartid(index); + + if (!hartid || (*hartid == INVALID_HARTID)) + return -EINVAL; + + return 0; + } rc = of_irq_parse_one(to_of_node(fwnode), index, &parent); if (rc) @@ -594,12 +613,8 @@ static int __init imsic_get_parent_hartid(struct fwnode_handle *fwnode, static int __init imsic_get_mmio_resource(struct fwnode_handle *fwnode, u32 index, struct resource *res) { - /* - * Currently, only OF fwnode is supported so extend this - * function for ACPI support. - */ if (!is_of_node(fwnode)) - return -EINVAL; + return acpi_rintc_get_imsic_mmio_info(index, res); return of_address_to_resource(to_of_node(fwnode), index, res); } @@ -607,20 +622,14 @@ static int __init imsic_get_mmio_resource(struct fwnode_handle *fwnode, static int __init imsic_parse_fwnode(struct fwnode_handle *fwnode, struct imsic_global_config *global, u32 *nr_parent_irqs, - u32 *nr_mmios) + u32 *nr_mmios, + void *opaque) { unsigned long hartid; struct resource res; int rc; u32 i; - /* - * Currently, only OF fwnode is supported so extend this - * function for ACPI support. - */ - if (!is_of_node(fwnode)) - return -EINVAL; - *nr_parent_irqs = 0; *nr_mmios = 0; @@ -632,7 +641,11 @@ static int __init imsic_parse_fwnode(struct fwnode_handle *fwnode, return -EINVAL; } - rc = imsic_populate_global_dt(fwnode, global, nr_parent_irqs); + if (is_of_node(fwnode)) + rc = imsic_populate_global_dt(fwnode, global, nr_parent_irqs); + else + rc = imsic_populate_global_acpi(fwnode, global, nr_parent_irqs, opaque); + if (rc) return rc; @@ -701,7 +714,7 @@ static int __init imsic_parse_fwnode(struct fwnode_handle *fwnode, return 0; } -int __init imsic_setup_state(struct fwnode_handle *fwnode) +int __init imsic_setup_state(struct fwnode_handle *fwnode, void *opaque) { u32 i, j, index, nr_parent_irqs, nr_mmios, nr_handlers = 0; struct imsic_global_config *global; @@ -742,7 +755,7 @@ int __init imsic_setup_state(struct fwnode_handle *fwnode) } /* Parse IMSIC fwnode */ - rc = imsic_parse_fwnode(fwnode, global, &nr_parent_irqs, &nr_mmios); + rc = imsic_parse_fwnode(fwnode, global, &nr_parent_irqs, &nr_mmios, opaque); if (rc) goto out_free_local; diff --git a/drivers/irqchip/irq-riscv-imsic-state.h b/drivers/irqchip/irq-riscv-imsic-state.h index 5ae2f69b035b..391e44280827 100644 --- a/drivers/irqchip/irq-riscv-imsic-state.h +++ b/drivers/irqchip/irq-riscv-imsic-state.h @@ -102,7 +102,7 @@ void imsic_vector_debug_show_summary(struct seq_file *m, int ind); void imsic_state_online(void); void imsic_state_offline(void); -int imsic_setup_state(struct fwnode_handle *fwnode); +int imsic_setup_state(struct fwnode_handle *fwnode, void *opaque); int imsic_irqdomain_init(void); #endif diff --git a/include/linux/irqchip/riscv-imsic.h b/include/linux/irqchip/riscv-imsic.h index faf0b800b1b0..7494952c5518 100644 --- a/include/linux/irqchip/riscv-imsic.h +++ b/include/linux/irqchip/riscv-imsic.h @@ -8,6 +8,8 @@ #include #include +#include +#include #include #define IMSIC_MMIO_PAGE_SHIFT 12 @@ -84,4 +86,11 @@ static inline const struct imsic_global_config *imsic_get_global_config(void) #endif +#ifdef CONFIG_ACPI +int imsic_platform_acpi_probe(struct fwnode_handle *fwnode); +struct fwnode_handle *imsic_acpi_get_fwnode(struct device *dev); +#else +static inline struct fwnode_handle *imsic_acpi_get_fwnode(struct device *dev) { return NULL; } +#endif + #endif -- cgit v1.2.3 From a707f85d47cad3978bef8fe90c7a79e3998e9d36 Mon Sep 17 00:00:00 2001 From: Thomas Weißschuh Date: Sat, 3 Aug 2024 14:34:17 +0200 Subject: HID: bpf: constify parameter rdesc of call_hid_bpf_rdesc_fixup() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The parameter is never modified, so mark it as const. Also inline the return statement to avoid a type mismatch error. This is a prerequisite for constification changes in the HID core. Signed-off-by: Thomas Weißschuh Link: https://patch.msgid.link/20240803-hid-const-fixup-v2-1-f53d7a7b29d8@weissschuh.net Signed-off-by: Benjamin Tissoires --- drivers/hid/bpf/hid_bpf_dispatch.c | 6 ++---- include/linux/hid_bpf.h | 2 +- 2 files changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/hid/bpf/hid_bpf_dispatch.c b/drivers/hid/bpf/hid_bpf_dispatch.c index a272a086c950..8420c227e21b 100644 --- a/drivers/hid/bpf/hid_bpf_dispatch.c +++ b/drivers/hid/bpf/hid_bpf_dispatch.c @@ -148,7 +148,7 @@ out: } EXPORT_SYMBOL_GPL(dispatch_hid_bpf_output_report); -u8 *call_hid_bpf_rdesc_fixup(struct hid_device *hdev, u8 *rdesc, unsigned int *size) +u8 *call_hid_bpf_rdesc_fixup(struct hid_device *hdev, const u8 *rdesc, unsigned int *size) { int ret; struct hid_bpf_ctx_kern ctx_kern = { @@ -179,9 +179,7 @@ u8 *call_hid_bpf_rdesc_fixup(struct hid_device *hdev, u8 *rdesc, unsigned int *s *size = ret; } - rdesc = krealloc(ctx_kern.data, *size, GFP_KERNEL); - - return rdesc; + return krealloc(ctx_kern.data, *size, GFP_KERNEL); ignore_bpf: kfree(ctx_kern.data); diff --git a/include/linux/hid_bpf.h b/include/linux/hid_bpf.h index d4d063cf63b5..6a47223e6460 100644 --- a/include/linux/hid_bpf.h +++ b/include/linux/hid_bpf.h @@ -212,7 +212,7 @@ int hid_bpf_connect_device(struct hid_device *hdev); void hid_bpf_disconnect_device(struct hid_device *hdev); void hid_bpf_destroy_device(struct hid_device *hid); int hid_bpf_device_init(struct hid_device *hid); -u8 *call_hid_bpf_rdesc_fixup(struct hid_device *hdev, u8 *rdesc, unsigned int *size); +u8 *call_hid_bpf_rdesc_fixup(struct hid_device *hdev, const u8 *rdesc, unsigned int *size); #else /* CONFIG_HID_BPF */ static inline u8 *dispatch_hid_bpf_device_event(struct hid_device *hid, enum hid_report_type type, u8 *data, u32 *size, int interrupt, -- cgit v1.2.3 From 6737769ca0b6bfc82df53db5fd69068902d608db Mon Sep 17 00:00:00 2001 From: Thomas Weißschuh Date: Sat, 3 Aug 2024 14:34:18 +0200 Subject: HID: constify parameter rdesc of hid_parse_report() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The parameter is never modified, so mark it as const. This is a prerequisite for constification changes in the HID core. Signed-off-by: Thomas Weißschuh Link: https://patch.msgid.link/20240803-hid-const-fixup-v2-2-f53d7a7b29d8@weissschuh.net Signed-off-by: Benjamin Tissoires --- drivers/hid/hid-core.c | 2 +- include/linux/hid.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 988d0acbdf04..0d2cbe491708 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -946,7 +946,7 @@ static int hid_scan_report(struct hid_device *hid) * Allocate the device report as read by the bus driver. This function should * only be called from parse() in ll drivers. */ -int hid_parse_report(struct hid_device *hid, __u8 *start, unsigned size) +int hid_parse_report(struct hid_device *hid, const __u8 *start, unsigned size) { hid->dev_rdesc = kmemdup(start, size, GFP_KERNEL); if (!hid->dev_rdesc) diff --git a/include/linux/hid.h b/include/linux/hid.h index 1533c9dcd3a6..e7a5d6f2f2eb 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -953,7 +953,7 @@ struct hid_device *hid_allocate_device(void); struct hid_report *hid_register_report(struct hid_device *device, enum hid_report_type type, unsigned int id, unsigned int application); -int hid_parse_report(struct hid_device *hid, __u8 *start, unsigned size); +int hid_parse_report(struct hid_device *hid, const __u8 *start, unsigned size); struct hid_report *hid_validate_values(struct hid_device *hid, enum hid_report_type type, unsigned int id, unsigned int field_index, -- cgit v1.2.3 From 24ddd0d7de7aaf50f537fd727f31616cb5a65a9e Mon Sep 17 00:00:00 2001 From: Thomas Weißschuh Date: Sat, 3 Aug 2024 14:34:19 +0200 Subject: HID: constify hid_device::rdesc MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Once a report descriptor has been created by the HID core it is not supposed to be modified anymore. Enforce this invariant through the type system. Signed-off-by: Thomas Weißschuh Link: https://patch.msgid.link/20240803-hid-const-fixup-v2-3-f53d7a7b29d8@weissschuh.net Signed-off-by: Benjamin Tissoires --- include/linux/hid.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index e7a5d6f2f2eb..dda34d8cad19 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -602,7 +602,7 @@ struct hid_ll_driver; struct hid_device { /* device report descriptor */ __u8 *dev_rdesc; unsigned dev_rsize; - __u8 *rdesc; + const __u8 *rdesc; unsigned rsize; struct hid_collection *collection; /* List of HID collections */ unsigned collection_size; /* Number of allocated hid_collections */ -- cgit v1.2.3 From 80cfb508f3fe4c7c6a567fc4aa863c9a38709cd5 Mon Sep 17 00:00:00 2001 From: Thomas Weißschuh Date: Sat, 3 Aug 2024 14:34:20 +0200 Subject: HID: constify params and return value of fetch_item() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit fetch_item() does not modify the descriptor it operates on. As a prerequisite for the constification of hid_driver::dev_rdesc, mark the parameters and return value of fetch_item() as const. Also adapt the variable types in the callers to match this constification. Signed-off-by: Thomas Weißschuh Link: https://patch.msgid.link/20240803-hid-const-fixup-v2-4-f53d7a7b29d8@weissschuh.net Signed-off-by: Benjamin Tissoires --- drivers/hid/hid-core.c | 12 ++++++------ include/linux/hid.h | 2 +- 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 0d2cbe491708..311069588321 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -723,7 +723,7 @@ static void hid_device_release(struct device *dev) * items, though they are not used yet. */ -static u8 *fetch_item(__u8 *start, __u8 *end, struct hid_item *item) +static const u8 *fetch_item(const __u8 *start, const __u8 *end, struct hid_item *item) { u8 b; @@ -880,8 +880,8 @@ static int hid_scan_report(struct hid_device *hid) { struct hid_parser *parser; struct hid_item item; - __u8 *start = hid->dev_rdesc; - __u8 *end = start + hid->dev_rsize; + const __u8 *start = hid->dev_rdesc; + const __u8 *end = start + hid->dev_rsize; static int (*dispatch_type[])(struct hid_parser *parser, struct hid_item *item) = { hid_scan_main, @@ -1204,10 +1204,10 @@ int hid_open_report(struct hid_device *device) struct hid_parser *parser; struct hid_item item; unsigned int size; - __u8 *start; + const __u8 *start; __u8 *buf; - __u8 *end; - __u8 *next; + const __u8 *end; + const __u8 *next; int ret; int i; static int (*dispatch_type[])(struct hid_parser *parser, diff --git a/include/linux/hid.h b/include/linux/hid.h index dda34d8cad19..502bbc6f078c 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -46,7 +46,7 @@ struct hid_item { __s16 s16; __u32 u32; __s32 s32; - __u8 *longdata; + const __u8 *longdata; } data; }; -- cgit v1.2.3 From 3593630c89d7d3963c42262694f8aa8b4727a0ad Mon Sep 17 00:00:00 2001 From: Thomas Weißschuh Date: Sat, 3 Aug 2024 14:34:21 +0200 Subject: HID: constify hid_device::dev_rdesc MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Once a report descriptor has been created by the HID core it is not supposed to be modified anymore. Enforce this invariant through the type system. Signed-off-by: Thomas Weißschuh Link: https://patch.msgid.link/20240803-hid-const-fixup-v2-5-f53d7a7b29d8@weissschuh.net Signed-off-by: Benjamin Tissoires --- include/linux/hid.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 502bbc6f078c..c5fb43db0f2e 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -600,7 +600,7 @@ struct hid_driver; struct hid_ll_driver; struct hid_device { /* device report descriptor */ - __u8 *dev_rdesc; + const __u8 *dev_rdesc; unsigned dev_rsize; const __u8 *rdesc; unsigned rsize; -- cgit v1.2.3 From fe73965d078670406acee0218f118c0870d6a58b Mon Sep 17 00:00:00 2001 From: Thomas Weißschuh Date: Sat, 3 Aug 2024 14:34:22 +0200 Subject: HID: change return type of report_fixup() to const MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit By allowing the drivers to return a "const *" they can constify their static report arrays. This makes it clear to driver authors that the HID core will not modify those reports and they can be reused for multiple devices. Furthermore security is slightly improved as those reports are protected against accidental or malicious modifications. [bentiss: fixup hid-cougar.c and hid-multitouch.c for latest version of the master branch] Signed-off-by: Thomas Weißschuh Link: https://patch.msgid.link/20240803-hid-const-fixup-v2-6-f53d7a7b29d8@weissschuh.net Signed-off-by: Benjamin Tissoires --- drivers/hid/hid-apple.c | 2 +- drivers/hid/hid-asus.c | 2 +- drivers/hid/hid-aureal.c | 2 +- drivers/hid/hid-bigbenff.c | 2 +- drivers/hid/hid-cherry.c | 2 +- drivers/hid/hid-chicony.c | 4 ++-- drivers/hid/hid-cmedia.c | 2 +- drivers/hid/hid-corsair.c | 4 ++-- drivers/hid/hid-cougar.c | 4 ++-- drivers/hid/hid-cypress.c | 2 +- drivers/hid/hid-dr.c | 4 ++-- drivers/hid/hid-elecom.c | 2 +- drivers/hid/hid-gembird.c | 2 +- drivers/hid/hid-glorious.c | 2 +- drivers/hid/hid-holtek-kbd.c | 2 +- drivers/hid/hid-holtek-mouse.c | 4 ++-- drivers/hid/hid-ite.c | 2 +- drivers/hid/hid-keytouch.c | 2 +- drivers/hid/hid-kye.c | 2 +- drivers/hid/hid-lenovo.c | 2 +- drivers/hid/hid-lg.c | 2 +- drivers/hid/hid-logitech-hidpp.c | 4 ++-- drivers/hid/hid-macally.c | 4 ++-- drivers/hid/hid-magicmouse.c | 4 ++-- drivers/hid/hid-maltron.c | 4 ++-- drivers/hid/hid-microsoft.c | 2 +- drivers/hid/hid-monterey.c | 2 +- drivers/hid/hid-multitouch.c | 2 +- drivers/hid/hid-nti.c | 2 +- drivers/hid/hid-ortek.c | 2 +- drivers/hid/hid-petalynx.c | 2 +- drivers/hid/hid-prodikeys.c | 2 +- drivers/hid/hid-pxrc.c | 4 ++-- drivers/hid/hid-redragon.c | 2 +- drivers/hid/hid-saitek.c | 2 +- drivers/hid/hid-samsung.c | 2 +- drivers/hid/hid-semitek.c | 4 ++-- drivers/hid/hid-sensor-hub.c | 2 +- drivers/hid/hid-sigmamicro.c | 4 ++-- drivers/hid/hid-sony.c | 2 +- drivers/hid/hid-steelseries.c | 4 ++-- drivers/hid/hid-sunplus.c | 2 +- drivers/hid/hid-topre.c | 4 ++-- drivers/hid/hid-uclogic-core.c | 2 +- drivers/hid/hid-viewsonic.c | 4 ++-- drivers/hid/hid-vrc2.c | 4 ++-- drivers/hid/hid-waltop.c | 2 +- drivers/hid/hid-winwing.c | 2 +- drivers/hid/hid-xiaomi.c | 4 ++-- drivers/hid/hid-zydacron.c | 2 +- include/linux/hid.h | 2 +- 51 files changed, 68 insertions(+), 68 deletions(-) (limited to 'include/linux') diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c index af5cf94f9dea..7e1ae2a2bcc2 100644 --- a/drivers/hid/hid-apple.c +++ b/drivers/hid/hid-apple.c @@ -620,7 +620,7 @@ static void apple_battery_timer_tick(struct timer_list *t) * MacBook JIS keyboard has wrong logical maximum * Magic Keyboard JIS has wrong logical maximum */ -static __u8 *apple_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static const __u8 *apple_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { struct apple_sc *asc = hid_get_drvdata(hdev); diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index a282388b7aa5..28a958bc4723 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -1119,7 +1119,7 @@ static const __u8 asus_g752_fixed_rdesc[] = { 0x2A, 0xFF, 0x00, /* Usage Maximum (0xFF) */ }; -static __u8 *asus_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static const __u8 *asus_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { struct asus_drvdata *drvdata = hid_get_drvdata(hdev); diff --git a/drivers/hid/hid-aureal.c b/drivers/hid/hid-aureal.c index cf1a562d8523..896304148a87 100644 --- a/drivers/hid/hid-aureal.c +++ b/drivers/hid/hid-aureal.c @@ -18,7 +18,7 @@ #include "hid-ids.h" -static __u8 *aureal_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static const __u8 *aureal_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { if (*rsize >= 54 && rdesc[52] == 0x25 && rdesc[53] == 0x01) { diff --git a/drivers/hid/hid-bigbenff.c b/drivers/hid/hid-bigbenff.c index be17af3d9c0c..a2ff60dd834c 100644 --- a/drivers/hid/hid-bigbenff.c +++ b/drivers/hid/hid-bigbenff.c @@ -464,7 +464,7 @@ error_hw_stop: return error; } -static __u8 *bigben_report_fixup(struct hid_device *hid, __u8 *rdesc, +static const __u8 *bigben_report_fixup(struct hid_device *hid, __u8 *rdesc, unsigned int *rsize) { if (*rsize == PID0902_RDESC_ORIG_SIZE) { diff --git a/drivers/hid/hid-cherry.c b/drivers/hid/hid-cherry.c index 549c73b05b8d..a504632febfc 100644 --- a/drivers/hid/hid-cherry.c +++ b/drivers/hid/hid-cherry.c @@ -22,7 +22,7 @@ * Cherry Cymotion keyboard have an invalid HID report descriptor, * that needs fixing before we can parse it. */ -static __u8 *ch_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static const __u8 *ch_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { if (*rsize >= 18 && rdesc[11] == 0x3c && rdesc[12] == 0x02) { diff --git a/drivers/hid/hid-chicony.c b/drivers/hid/hid-chicony.c index 99954c6b3242..5776ec2e7159 100644 --- a/drivers/hid/hid-chicony.c +++ b/drivers/hid/hid-chicony.c @@ -88,8 +88,8 @@ static int ch_input_mapping(struct hid_device *hdev, struct hid_input *hi, return 1; } -static __u8 *ch_switch12_report_fixup(struct hid_device *hdev, __u8 *rdesc, - unsigned int *rsize) +static const __u8 *ch_switch12_report_fixup(struct hid_device *hdev, + __u8 *rdesc, unsigned int *rsize) { struct usb_interface *intf = to_usb_interface(hdev->dev.parent); diff --git a/drivers/hid/hid-cmedia.c b/drivers/hid/hid-cmedia.c index cab42047bc99..01009c95613c 100644 --- a/drivers/hid/hid-cmedia.c +++ b/drivers/hid/hid-cmedia.c @@ -199,7 +199,7 @@ static struct hid_driver cmhid_driver = { .input_mapping = cmhid_input_mapping, }; -static __u8 *cmhid_hs100b_report_fixup(struct hid_device *hid, __u8 *rdesc, +static const __u8 *cmhid_hs100b_report_fixup(struct hid_device *hid, __u8 *rdesc, unsigned int *rsize) { if (*rsize == HS100B_RDESC_ORIG_SIZE) { diff --git a/drivers/hid/hid-corsair.c b/drivers/hid/hid-corsair.c index 702f50e9841d..62b99f5c3cf8 100644 --- a/drivers/hid/hid-corsair.c +++ b/drivers/hid/hid-corsair.c @@ -690,8 +690,8 @@ static int corsair_input_mapping(struct hid_device *dev, * - USB ID 1b1c:1b3e, sold as Scimitar RGB Pro Gaming mouse */ -static __u8 *corsair_mouse_report_fixup(struct hid_device *hdev, __u8 *rdesc, - unsigned int *rsize) +static const __u8 *corsair_mouse_report_fixup(struct hid_device *hdev, + __u8 *rdesc, unsigned int *rsize) { struct usb_interface *intf = to_usb_interface(hdev->dev.parent); diff --git a/drivers/hid/hid-cougar.c b/drivers/hid/hid-cougar.c index 0fa785f52707..5596dd940322 100644 --- a/drivers/hid/hid-cougar.c +++ b/drivers/hid/hid-cougar.c @@ -103,8 +103,8 @@ static void cougar_fix_g6_mapping(void) /* * Constant-friendly rdesc fixup for mouse interface */ -static __u8 *cougar_report_fixup(struct hid_device *hdev, __u8 *rdesc, - unsigned int *rsize) +static const __u8 *cougar_report_fixup(struct hid_device *hdev, __u8 *rdesc, + unsigned int *rsize) { if (*rsize >= 117 && rdesc[2] == 0x09 && rdesc[3] == 0x02 && (rdesc[115] | rdesc[116] << 8) >= HID_MAX_USAGES) { diff --git a/drivers/hid/hid-cypress.c b/drivers/hid/hid-cypress.c index b952b235e70a..98548201feec 100644 --- a/drivers/hid/hid-cypress.c +++ b/drivers/hid/hid-cypress.c @@ -67,7 +67,7 @@ static __u8 *va_logical_boundary_fixup(struct hid_device *hdev, __u8 *rdesc, return rdesc; } -static __u8 *cp_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static const __u8 *cp_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { unsigned long quirks = (unsigned long)hid_get_drvdata(hdev); diff --git a/drivers/hid/hid-dr.c b/drivers/hid/hid-dr.c index c88224a96e9e..b24f9bc743e1 100644 --- a/drivers/hid/hid-dr.c +++ b/drivers/hid/hid-dr.c @@ -228,8 +228,8 @@ static __u8 pid0011_rdesc_fixed[] = { 0xC0 /* End Collection */ }; -static __u8 *dr_report_fixup(struct hid_device *hdev, __u8 *rdesc, - unsigned int *rsize) +static const __u8 *dr_report_fixup(struct hid_device *hdev, __u8 *rdesc, + unsigned int *rsize) { switch (hdev->product) { case 0x0011: diff --git a/drivers/hid/hid-elecom.c b/drivers/hid/hid-elecom.c index 5973a3bab29f..defcf91fdd14 100644 --- a/drivers/hid/hid-elecom.c +++ b/drivers/hid/hid-elecom.c @@ -53,7 +53,7 @@ static void mouse_button_fixup(struct hid_device *hdev, rdesc[padding_bit + 1] = MOUSE_BUTTONS_MAX - nbuttons; } -static __u8 *elecom_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static const __u8 *elecom_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { switch (hdev->product) { diff --git a/drivers/hid/hid-gembird.c b/drivers/hid/hid-gembird.c index c42593fe7116..20a8de766e56 100644 --- a/drivers/hid/hid-gembird.c +++ b/drivers/hid/hid-gembird.c @@ -57,7 +57,7 @@ static const __u8 gembird_jpd_fixed_rdesc[] = { 0x81, 0x02, /* Input (Data,Var,Abs) */ }; -static __u8 *gembird_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static const __u8 *gembird_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { __u8 *new_rdesc; diff --git a/drivers/hid/hid-glorious.c b/drivers/hid/hid-glorious.c index 281b3a7187ce..5bbd81248053 100644 --- a/drivers/hid/hid-glorious.c +++ b/drivers/hid/hid-glorious.c @@ -26,7 +26,7 @@ MODULE_DESCRIPTION("HID driver for Glorious PC Gaming Race mice"); * keyboard HID report, causing keycodes to be misinterpreted. * Fix this by setting Usage Minimum to 0 in that report. */ -static __u8 *glorious_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static const __u8 *glorious_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { if (*rsize == 213 && diff --git a/drivers/hid/hid-holtek-kbd.c b/drivers/hid/hid-holtek-kbd.c index 1f014ac54e14..794d609c2e31 100644 --- a/drivers/hid/hid-holtek-kbd.c +++ b/drivers/hid/hid-holtek-kbd.c @@ -102,7 +102,7 @@ static __u8 holtek_kbd_rdesc_fixed[] = { 0xC0, /* End Collection */ }; -static __u8 *holtek_kbd_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static const __u8 *holtek_kbd_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { struct usb_interface *intf = to_usb_interface(hdev->dev.parent); diff --git a/drivers/hid/hid-holtek-mouse.c b/drivers/hid/hid-holtek-mouse.c index 343730c28e2d..b618a1646c13 100644 --- a/drivers/hid/hid-holtek-mouse.c +++ b/drivers/hid/hid-holtek-mouse.c @@ -29,8 +29,8 @@ * - USB ID 04d9:a0c2, sold as ETEKCITY Scroll T-140 Gaming Mouse */ -static __u8 *holtek_mouse_report_fixup(struct hid_device *hdev, __u8 *rdesc, - unsigned int *rsize) +static const __u8 *holtek_mouse_report_fixup(struct hid_device *hdev, + __u8 *rdesc, unsigned int *rsize) { struct usb_interface *intf = to_usb_interface(hdev->dev.parent); diff --git a/drivers/hid/hid-ite.c b/drivers/hid/hid-ite.c index 6a7281bc27c9..8e42780a2663 100644 --- a/drivers/hid/hid-ite.c +++ b/drivers/hid/hid-ite.c @@ -13,7 +13,7 @@ #define QUIRK_TOUCHPAD_ON_OFF_REPORT BIT(0) -static __u8 *ite_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) +static const __u8 *ite_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { unsigned long quirks = (unsigned long)hid_get_drvdata(hdev); diff --git a/drivers/hid/hid-keytouch.c b/drivers/hid/hid-keytouch.c index a972943baaea..6e3033bb80dd 100644 --- a/drivers/hid/hid-keytouch.c +++ b/drivers/hid/hid-keytouch.c @@ -24,7 +24,7 @@ static __u8 keytouch_fixed_rdesc[] = { 0x26, 0xff, 0x00, 0x05, 0x07, 0x19, 0x00, 0x2a, 0xff, 0x00, 0x81, 0x00, 0xc0 }; -static __u8 *keytouch_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static const __u8 *keytouch_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { hid_info(hdev, "fixing up Keytouch IEC report descriptor\n"); diff --git a/drivers/hid/hid-kye.c b/drivers/hid/hid-kye.c index ca2ba3da2458..32344331282f 100644 --- a/drivers/hid/hid-kye.c +++ b/drivers/hid/hid-kye.c @@ -466,7 +466,7 @@ static __u8 *kye_tablet_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int return rdesc; } -static __u8 *kye_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static const __u8 *kye_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { switch (hdev->product) { diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c index e5e72aa5260a..3b0c779ce8f7 100644 --- a/drivers/hid/hid-lenovo.c +++ b/drivers/hid/hid-lenovo.c @@ -133,7 +133,7 @@ static const __u8 lenovo_tpIIbtkbd_need_fixup_collection[] = { 0x81, 0x01, /* Input (Const,Array,Abs,No Wrap,Linear,Preferred State,No Null Position) */ }; -static __u8 *lenovo_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static const __u8 *lenovo_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { switch (hdev->product) { diff --git a/drivers/hid/hid-lg.c b/drivers/hid/hid-lg.c index cfe2f4f6e93f..a9be918e2b5c 100644 --- a/drivers/hid/hid-lg.c +++ b/drivers/hid/hid-lg.c @@ -427,7 +427,7 @@ static __u8 fg_rdesc_fixed[] = { * above the logical maximum described in descriptor. This extends * the original value of 0x28c of logical maximum to 0x104d */ -static __u8 *lg_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static const __u8 *lg_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { struct lg_drv_data *drv_data = hid_get_drvdata(hdev); diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index 400d70e6dbe2..0e33fa0eb8db 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -3767,8 +3767,8 @@ static int hidpp_initialize_hires_scroll(struct hidpp_device *hidpp) /* Generic HID++ devices */ /* -------------------------------------------------------------------------- */ -static u8 *hidpp_report_fixup(struct hid_device *hdev, u8 *rdesc, - unsigned int *rsize) +static const u8 *hidpp_report_fixup(struct hid_device *hdev, u8 *rdesc, + unsigned int *rsize) { struct hidpp_device *hidpp = hid_get_drvdata(hdev); diff --git a/drivers/hid/hid-macally.c b/drivers/hid/hid-macally.c index aea46e522008..fe7576458afa 100644 --- a/drivers/hid/hid-macally.c +++ b/drivers/hid/hid-macally.c @@ -18,8 +18,8 @@ MODULE_LICENSE("GPL"); * The Macally ikey keyboard says that its logical and usage maximums are both * 101, but the power key is 102 and the equals key is 103 */ -static __u8 *macally_report_fixup(struct hid_device *hdev, __u8 *rdesc, - unsigned int *rsize) +static const __u8 *macally_report_fixup(struct hid_device *hdev, __u8 *rdesc, + unsigned int *rsize) { if (*rsize >= 60 && rdesc[53] == 0x65 && rdesc[59] == 0x65) { hid_info(hdev, diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c index 2eb285b97fc0..8a73b59e0827 100644 --- a/drivers/hid/hid-magicmouse.c +++ b/drivers/hid/hid-magicmouse.c @@ -907,8 +907,8 @@ static void magicmouse_remove(struct hid_device *hdev) hid_hw_stop(hdev); } -static __u8 *magicmouse_report_fixup(struct hid_device *hdev, __u8 *rdesc, - unsigned int *rsize) +static const __u8 *magicmouse_report_fixup(struct hid_device *hdev, __u8 *rdesc, + unsigned int *rsize) { /* * Change the usage from: diff --git a/drivers/hid/hid-maltron.c b/drivers/hid/hid-maltron.c index caba0def938c..374c64dd82c2 100644 --- a/drivers/hid/hid-maltron.c +++ b/drivers/hid/hid-maltron.c @@ -137,8 +137,8 @@ static u8 maltron_rdesc[] = { 0xC0 /* End Collection */ }; -static __u8 *maltron_report_fixup(struct hid_device *hdev, __u8 *rdesc, - unsigned int *rsize) +static const __u8 *maltron_report_fixup(struct hid_device *hdev, __u8 *rdesc, + unsigned int *rsize) { if (*rsize == sizeof(maltron_rdesc_o) && !memcmp(maltron_rdesc_o, rdesc, sizeof(maltron_rdesc_o))) { diff --git a/drivers/hid/hid-microsoft.c b/drivers/hid/hid-microsoft.c index 4cf0fcddb379..18ac21c0bcb2 100644 --- a/drivers/hid/hid-microsoft.c +++ b/drivers/hid/hid-microsoft.c @@ -56,7 +56,7 @@ struct xb1s_ff_report { __u8 loop_count; } __packed; -static __u8 *ms_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static const __u8 *ms_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { struct ms_data *ms = hid_get_drvdata(hdev); diff --git a/drivers/hid/hid-monterey.c b/drivers/hid/hid-monterey.c index 989681f73d77..3089be990afe 100644 --- a/drivers/hid/hid-monterey.c +++ b/drivers/hid/hid-monterey.c @@ -18,7 +18,7 @@ #include "hid-ids.h" -static __u8 *mr_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static const __u8 *mr_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { if (*rsize >= 31 && rdesc[29] == 0x05 && rdesc[30] == 0x09) { diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 99812c0f830b..5d4e916166c1 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -1441,7 +1441,7 @@ static int mt_event(struct hid_device *hid, struct hid_field *field, return 0; } -static __u8 *mt_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static const __u8 *mt_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *size) { if (hdev->vendor == I2C_VENDOR_ID_GOODIX && diff --git a/drivers/hid/hid-nti.c b/drivers/hid/hid-nti.c index 1952e9ca5f45..03f7dd491228 100644 --- a/drivers/hid/hid-nti.c +++ b/drivers/hid/hid-nti.c @@ -29,7 +29,7 @@ MODULE_DESCRIPTION("HID driver for Network Technologies USB-SUN keyboard adapter /* * NTI Sun keyboard adapter has wrong logical maximum in report descriptor */ -static __u8 *nti_usbsun_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static const __u8 *nti_usbsun_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { if (*rsize >= 60 && rdesc[53] == 0x65 && rdesc[59] == 0x65) { diff --git a/drivers/hid/hid-ortek.c b/drivers/hid/hid-ortek.c index 99e3b06a8331..f27297269a7f 100644 --- a/drivers/hid/hid-ortek.c +++ b/drivers/hid/hid-ortek.c @@ -22,7 +22,7 @@ #include "hid-ids.h" -static __u8 *ortek_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static const __u8 *ortek_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { if (*rsize >= 56 && rdesc[54] == 0x25 && rdesc[55] == 0x01) { diff --git a/drivers/hid/hid-petalynx.c b/drivers/hid/hid-petalynx.c index 5e47634bb07d..1a986f077ce1 100644 --- a/drivers/hid/hid-petalynx.c +++ b/drivers/hid/hid-petalynx.c @@ -19,7 +19,7 @@ #include "hid-ids.h" /* Petalynx Maxter Remote has maximum for consumer page set too low */ -static __u8 *pl_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static const __u8 *pl_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { if (*rsize >= 62 && rdesc[39] == 0x2a && rdesc[40] == 0xf5 && diff --git a/drivers/hid/hid-prodikeys.c b/drivers/hid/hid-prodikeys.c index 757361593e52..3d08c190a935 100644 --- a/drivers/hid/hid-prodikeys.c +++ b/drivers/hid/hid-prodikeys.c @@ -728,7 +728,7 @@ static int pcmidi_snd_terminate(struct pcmidi_snd *pm) /* * PC-MIDI report descriptor for report id is wrong. */ -static __u8 *pk_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static const __u8 *pk_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { if (*rsize == 178 && diff --git a/drivers/hid/hid-pxrc.c b/drivers/hid/hid-pxrc.c index b0e517f9cde7..ef38730e78ab 100644 --- a/drivers/hid/hid-pxrc.c +++ b/drivers/hid/hid-pxrc.c @@ -42,8 +42,8 @@ static __u8 pxrc_rdesc_fixed[] = { 0xC0, // End Collection }; -static __u8 *pxrc_report_fixup(struct hid_device *hdev, __u8 *rdesc, - unsigned int *rsize) +static const __u8 *pxrc_report_fixup(struct hid_device *hdev, __u8 *rdesc, + unsigned int *rsize) { hid_info(hdev, "fixing up PXRC report descriptor\n"); *rsize = sizeof(pxrc_rdesc_fixed); diff --git a/drivers/hid/hid-redragon.c b/drivers/hid/hid-redragon.c index 07d803513f27..20d28ed75c1e 100644 --- a/drivers/hid/hid-redragon.c +++ b/drivers/hid/hid-redragon.c @@ -33,7 +33,7 @@ * key codes are generated. */ -static __u8 *redragon_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static const __u8 *redragon_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { if (*rsize >= 102 && rdesc[100] == 0x81 && rdesc[101] == 0x00) { diff --git a/drivers/hid/hid-saitek.c b/drivers/hid/hid-saitek.c index 85ac8def368f..6fe7c087c594 100644 --- a/drivers/hid/hid-saitek.c +++ b/drivers/hid/hid-saitek.c @@ -66,7 +66,7 @@ static int saitek_probe(struct hid_device *hdev, return 0; } -static __u8 *saitek_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static const __u8 *saitek_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { struct saitek_sc *ssc = hid_get_drvdata(hdev); diff --git a/drivers/hid/hid-samsung.c b/drivers/hid/hid-samsung.c index d4e27142245c..f3908a9e04e6 100644 --- a/drivers/hid/hid-samsung.c +++ b/drivers/hid/hid-samsung.c @@ -469,7 +469,7 @@ static int samsung_universal_kbd_input_mapping(struct hid_device *hdev, return 1; } -static __u8 *samsung_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static const __u8 *samsung_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { if (hdev->product == USB_DEVICE_ID_SAMSUNG_IR_REMOTE && hid_is_usb(hdev)) diff --git a/drivers/hid/hid-semitek.c b/drivers/hid/hid-semitek.c index 710766f6839d..4fbec5fd87ce 100644 --- a/drivers/hid/hid-semitek.c +++ b/drivers/hid/hid-semitek.c @@ -11,8 +11,8 @@ #include "hid-ids.h" -static __u8 *semitek_report_fixup(struct hid_device *hdev, __u8 *rdesc, - unsigned int *rsize) +static const __u8 *semitek_report_fixup(struct hid_device *hdev, __u8 *rdesc, + unsigned int *rsize) { /* In the report descriptor for interface 2, fix the incorrect description of report ID 0x04 (the report contains a diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c index 26e93a331a51..7bd86eef6ec7 100644 --- a/drivers/hid/hid-sensor-hub.c +++ b/drivers/hid/hid-sensor-hub.c @@ -580,7 +580,7 @@ void sensor_hub_device_close(struct hid_sensor_hub_device *hsdev) } EXPORT_SYMBOL_GPL(sensor_hub_device_close); -static __u8 *sensor_hub_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static const __u8 *sensor_hub_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { /* diff --git a/drivers/hid/hid-sigmamicro.c b/drivers/hid/hid-sigmamicro.c index 2e7058ac0e9d..c87276d7ba0d 100644 --- a/drivers/hid/hid-sigmamicro.c +++ b/drivers/hid/hid-sigmamicro.c @@ -99,8 +99,8 @@ static const __u8 sm_0059_rdesc[] = { 0xc0, /* End Collection 166 */ }; -static __u8 *sm_report_fixup(struct hid_device *hdev, __u8 *rdesc, - unsigned int *rsize) +static const __u8 *sm_report_fixup(struct hid_device *hdev, __u8 *rdesc, + unsigned int *rsize) { if (*rsize == sizeof(sm_0059_rdesc) && !memcmp(sm_0059_rdesc, rdesc, *rsize)) { diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c index eac75f98f08a..8e2e914bd236 100644 --- a/drivers/hid/hid-sony.c +++ b/drivers/hid/hid-sony.c @@ -743,7 +743,7 @@ static int sixaxis_mapping(struct hid_device *hdev, struct hid_input *hi, return -1; } -static u8 *sony_report_fixup(struct hid_device *hdev, u8 *rdesc, +static const u8 *sony_report_fixup(struct hid_device *hdev, u8 *rdesc, unsigned int *rsize) { struct sony_sc *sc = hid_get_drvdata(hdev); diff --git a/drivers/hid/hid-steelseries.c b/drivers/hid/hid-steelseries.c index 2154e14f55f1..895da49e8ead 100644 --- a/drivers/hid/hid-steelseries.c +++ b/drivers/hid/hid-steelseries.c @@ -570,8 +570,8 @@ static void steelseries_remove(struct hid_device *hdev) hid_hw_stop(hdev); } -static __u8 *steelseries_srws1_report_fixup(struct hid_device *hdev, __u8 *rdesc, - unsigned int *rsize) +static const __u8 *steelseries_srws1_report_fixup(struct hid_device *hdev, + __u8 *rdesc, unsigned int *rsize) { if (hdev->vendor != USB_VENDOR_ID_STEELSERIES || hdev->product != USB_DEVICE_ID_STEELSERIES_SRWS1) diff --git a/drivers/hid/hid-sunplus.c b/drivers/hid/hid-sunplus.c index f32e60d4420f..64e4cff8ca1d 100644 --- a/drivers/hid/hid-sunplus.c +++ b/drivers/hid/hid-sunplus.c @@ -18,7 +18,7 @@ #include "hid-ids.h" -static __u8 *sp_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static const __u8 *sp_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { if (*rsize >= 112 && rdesc[104] == 0x26 && rdesc[105] == 0x80 && diff --git a/drivers/hid/hid-topre.c b/drivers/hid/hid-topre.c index d1d5ca310ead..848361f6225d 100644 --- a/drivers/hid/hid-topre.c +++ b/drivers/hid/hid-topre.c @@ -21,8 +21,8 @@ MODULE_LICENSE("GPL"); * events it's actually sending. It claims to send array events but is instead * sending variable events. */ -static __u8 *topre_report_fixup(struct hid_device *hdev, __u8 *rdesc, - unsigned int *rsize) +static const __u8 *topre_report_fixup(struct hid_device *hdev, __u8 *rdesc, + unsigned int *rsize) { if (*rsize >= 119 && rdesc[69] == 0x29 && rdesc[70] == 0xe7 && rdesc[71] == 0x81 && rdesc[72] == 0x00) { diff --git a/drivers/hid/hid-uclogic-core.c b/drivers/hid/hid-uclogic-core.c index b176f9c0dd52..f6a1572b3728 100644 --- a/drivers/hid/hid-uclogic-core.c +++ b/drivers/hid/hid-uclogic-core.c @@ -50,7 +50,7 @@ static void uclogic_inrange_timeout(struct timer_list *t) input_sync(input); } -static __u8 *uclogic_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static const __u8 *uclogic_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { struct uclogic_drvdata *drvdata = hid_get_drvdata(hdev); diff --git a/drivers/hid/hid-viewsonic.c b/drivers/hid/hid-viewsonic.c index 668c2adb77b6..86f41e3fcb95 100644 --- a/drivers/hid/hid-viewsonic.c +++ b/drivers/hid/hid-viewsonic.c @@ -70,8 +70,8 @@ static __u8 pd1011_rdesc_fixed[] = { 0xC0 /* End Collection */ }; -static __u8 *viewsonic_report_fixup(struct hid_device *hdev, __u8 *rdesc, - unsigned int *rsize) +static const __u8 *viewsonic_report_fixup(struct hid_device *hdev, __u8 *rdesc, + unsigned int *rsize) { switch (hdev->product) { case USB_DEVICE_ID_VIEWSONIC_PD1011: diff --git a/drivers/hid/hid-vrc2.c b/drivers/hid/hid-vrc2.c index 80a2b7ef5e66..9a4840b524ba 100644 --- a/drivers/hid/hid-vrc2.c +++ b/drivers/hid/hid-vrc2.c @@ -38,8 +38,8 @@ static __u8 vrc2_rdesc_fixed[] = { 0xC0, // End Collection }; -static __u8 *vrc2_report_fixup(struct hid_device *hdev, __u8 *rdesc, - unsigned int *rsize) +static const __u8 *vrc2_report_fixup(struct hid_device *hdev, __u8 *rdesc, + unsigned int *rsize) { hid_info(hdev, "fixing up VRC-2 report descriptor\n"); *rsize = sizeof(vrc2_rdesc_fixed); diff --git a/drivers/hid/hid-waltop.c b/drivers/hid/hid-waltop.c index 1e590c61eef5..137a682ef5fb 100644 --- a/drivers/hid/hid-waltop.c +++ b/drivers/hid/hid-waltop.c @@ -599,7 +599,7 @@ static __u8 sirius_battery_free_tablet_rdesc_fixed[] = { 0xC0 /* End Collection */ }; -static __u8 *waltop_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static const __u8 *waltop_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { switch (hdev->product) { diff --git a/drivers/hid/hid-winwing.c b/drivers/hid/hid-winwing.c index 10a5d87ccb96..86b64c0ced12 100644 --- a/drivers/hid/hid-winwing.c +++ b/drivers/hid/hid-winwing.c @@ -165,7 +165,7 @@ static __u8 original_rdesc_buttons[] = { * This module skips numbers 32-63, unused on some throttle grips. */ -static __u8 *winwing_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static const __u8 *winwing_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { int sig_length = sizeof(original_rdesc_buttons); diff --git a/drivers/hid/hid-xiaomi.c b/drivers/hid/hid-xiaomi.c index a97a90afad33..035733fce2e1 100644 --- a/drivers/hid/hid-xiaomi.c +++ b/drivers/hid/hid-xiaomi.c @@ -61,8 +61,8 @@ static __u8 mi_silent_mouse_rdesc_fixed[] = { 0xC0 /* End Collection */ }; -static __u8 *xiaomi_report_fixup(struct hid_device *hdev, __u8 *rdesc, - unsigned int *rsize) +static const __u8 *xiaomi_report_fixup(struct hid_device *hdev, __u8 *rdesc, + unsigned int *rsize) { switch (hdev->product) { case USB_DEVICE_ID_MI_SILENT_MOUSE: diff --git a/drivers/hid/hid-zydacron.c b/drivers/hid/hid-zydacron.c index 998a3db19c1f..3bdb26f45592 100644 --- a/drivers/hid/hid-zydacron.c +++ b/drivers/hid/hid-zydacron.c @@ -24,7 +24,7 @@ struct zc_device { * Zydacron remote control has an invalid HID report descriptor, * that needs fixing before we can parse it. */ -static __u8 *zc_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static const __u8 *zc_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { if (*rsize >= 253 && diff --git a/include/linux/hid.h b/include/linux/hid.h index c5fb43db0f2e..3a998fa3812d 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -822,7 +822,7 @@ struct hid_driver { struct hid_usage *usage, __s32 value); void (*report)(struct hid_device *hdev, struct hid_report *report); - __u8 *(*report_fixup)(struct hid_device *hdev, __u8 *buf, + const __u8 *(*report_fixup)(struct hid_device *hdev, __u8 *buf, unsigned int *size); int (*input_mapping)(struct hid_device *hdev, -- cgit v1.2.3 From ba7e053ec89f61be9d27bfb244de52849b5138aa Mon Sep 17 00:00:00 2001 From: Artur Weber Date: Fri, 16 Aug 2024 10:19:09 +0200 Subject: power: supply: max77693: Expose input current limit and CC current properties There are two charger current limit registers: - Fast charge current limit (which controls current going from the charger to the battery); - CHGIN input current limit (which controls current going into the charger through the cable). Add the necessary functions to retrieve the CHGIN input limit (from CHARGER regulator) and maximum fast charge current values, and expose them as power supply properties. Tested-by: Henrik Grimler Signed-off-by: Artur Weber Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20240816-max77693-charger-extcon-v4-3-050a0a9bfea0@gmail.com Signed-off-by: Sebastian Reichel --- drivers/power/supply/max77693_charger.c | 52 +++++++++++++++++++++++++++++++++ include/linux/mfd/max77693-private.h | 5 ++++ 2 files changed, 57 insertions(+) (limited to 'include/linux') diff --git a/drivers/power/supply/max77693_charger.c b/drivers/power/supply/max77693_charger.c index 2001e12c9f7d..4caac142c428 100644 --- a/drivers/power/supply/max77693_charger.c +++ b/drivers/power/supply/max77693_charger.c @@ -197,12 +197,58 @@ static int max77693_get_online(struct regmap *regmap, int *val) return 0; } +/* + * There are *two* current limit registers: + * - CHGIN limit, which limits the input current from the external charger; + * - Fast charge current limit, which limits the current going to the battery. + */ + +static int max77693_get_input_current_limit(struct regmap *regmap, int *val) +{ + unsigned int data; + int ret; + + ret = regmap_read(regmap, MAX77693_CHG_REG_CHG_CNFG_09, &data); + if (ret < 0) + return ret; + + data &= CHG_CNFG_09_CHGIN_ILIM_MASK; + data >>= CHG_CNFG_09_CHGIN_ILIM_SHIFT; + + if (data <= 0x03) + /* The first four values (0x00..0x03) are 60mA */ + *val = 60000; + else + *val = data * 20000; /* 20mA steps */ + + return 0; +} + +static int max77693_get_fast_charge_current(struct regmap *regmap, int *val) +{ + unsigned int data; + int ret; + + ret = regmap_read(regmap, MAX77693_CHG_REG_CHG_CNFG_02, &data); + if (ret < 0) + return ret; + + data &= CHG_CNFG_02_CC_MASK; + data >>= CHG_CNFG_02_CC_SHIFT; + + *val = data * 33300; /* 33.3mA steps */ + + return 0; +} + static enum power_supply_property max77693_charger_props[] = { POWER_SUPPLY_PROP_STATUS, POWER_SUPPLY_PROP_CHARGE_TYPE, POWER_SUPPLY_PROP_HEALTH, POWER_SUPPLY_PROP_PRESENT, POWER_SUPPLY_PROP_ONLINE, + POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT, + POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT_MAX, POWER_SUPPLY_PROP_MODEL_NAME, POWER_SUPPLY_PROP_MANUFACTURER, }; @@ -231,6 +277,12 @@ static int max77693_charger_get_property(struct power_supply *psy, case POWER_SUPPLY_PROP_ONLINE: ret = max77693_get_online(regmap, &val->intval); break; + case POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT: + ret = max77693_get_input_current_limit(regmap, &val->intval); + break; + case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT_MAX: + ret = max77693_get_fast_charge_current(regmap, &val->intval); + break; case POWER_SUPPLY_PROP_MODEL_NAME: val->strval = max77693_charger_model; break; diff --git a/include/linux/mfd/max77693-private.h b/include/linux/mfd/max77693-private.h index 54444ff2a5de..20c5e02ed9da 100644 --- a/include/linux/mfd/max77693-private.h +++ b/include/linux/mfd/max77693-private.h @@ -217,6 +217,10 @@ enum max77693_charger_battery_state { #define CHG_CNFG_01_CHGRSTRT_MASK (0x3 << CHG_CNFG_01_CHGRSTRT_SHIFT) #define CHG_CNFG_01_PQEN_MAKS BIT(CHG_CNFG_01_PQEN_SHIFT) +/* MAX77693_CHG_REG_CHG_CNFG_02 register */ +#define CHG_CNFG_02_CC_SHIFT 0 +#define CHG_CNFG_02_CC_MASK 0x3F + /* MAX77693_CHG_REG_CHG_CNFG_03 register */ #define CHG_CNFG_03_TOITH_SHIFT 0 #define CHG_CNFG_03_TOTIME_SHIFT 3 @@ -244,6 +248,7 @@ enum max77693_charger_battery_state { #define CHG_CNFG_12_VCHGINREG_MASK (0x3 << CHG_CNFG_12_VCHGINREG_SHIFT) /* MAX77693 CHG_CNFG_09 Register */ +#define CHG_CNFG_09_CHGIN_ILIM_SHIFT 0 #define CHG_CNFG_09_CHGIN_ILIM_MASK 0x7F /* MAX77693 CHG_CTRL Register */ -- cgit v1.2.3 From a96c5515d0d15df103598b2bc57245d66143b5dd Mon Sep 17 00:00:00 2001 From: Tristram Ha Date: Mon, 26 Aug 2024 21:43:08 +0000 Subject: net: dsa: microchip: Add KSZ8895/KSZ8864 switch support KSZ8895/KSZ8864 is a switch family between KSZ8863/73 and KSZ8795, so it shares some registers and functions in those switches already implemented in the KSZ DSA driver. Signed-off-by: Tristram Ha Tested-by: Pieter Van Trappen Reviewed-by: Oleksij Rempel Signed-off-by: Jakub Kicinski --- drivers/net/dsa/microchip/ksz8795.c | 16 ++-- drivers/net/dsa/microchip/ksz_common.c | 134 ++++++++++++++++++++++++++-- drivers/net/dsa/microchip/ksz_common.h | 25 +++++- drivers/net/dsa/microchip/ksz_dcb.c | 2 +- drivers/net/dsa/microchip/ksz_spi.c | 15 +++- include/linux/platform_data/microchip-ksz.h | 2 + 6 files changed, 178 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index a01079297a8c..aa09d89debf0 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -188,6 +188,8 @@ int ksz8_change_mtu(struct ksz_device *dev, int port, int mtu) case KSZ8765_CHIP_ID: return ksz8795_change_mtu(dev, frame_size); case KSZ8830_CHIP_ID: + case KSZ8864_CHIP_ID: + case KSZ8895_CHIP_ID: return ksz8863_change_mtu(dev, frame_size); } @@ -384,7 +386,7 @@ static void ksz8863_r_mib_pkt(struct ksz_device *dev, int port, u16 addr, void ksz8_r_mib_pkt(struct ksz_device *dev, int port, u16 addr, u64 *dropped, u64 *cnt) { - if (ksz_is_ksz88x3(dev)) + if (is_ksz88xx(dev)) ksz8863_r_mib_pkt(dev, port, addr, dropped, cnt); else ksz8795_r_mib_pkt(dev, port, addr, dropped, cnt); @@ -392,7 +394,7 @@ void ksz8_r_mib_pkt(struct ksz_device *dev, int port, u16 addr, void ksz8_freeze_mib(struct ksz_device *dev, int port, bool freeze) { - if (ksz_is_ksz88x3(dev)) + if (is_ksz88xx(dev)) return; /* enable the port for flush/freeze function */ @@ -410,7 +412,8 @@ void ksz8_port_init_cnt(struct ksz_device *dev, int port) struct ksz_port_mib *mib = &dev->ports[port].mib; u64 *dropped; - if (!ksz_is_ksz88x3(dev)) { + /* For KSZ8795 family. */ + if (ksz_is_ksz87xx(dev)) { /* flush all enabled port MIB counters */ ksz_cfg(dev, REG_SW_CTRL_6, BIT(port), true); ksz_cfg(dev, REG_SW_CTRL_6, SW_MIB_COUNTER_FLUSH, true); @@ -609,11 +612,11 @@ static int ksz8_r_sta_mac_table(struct ksz_device *dev, u16 addr, shifts[STATIC_MAC_FWD_PORTS]; alu->is_override = (data_hi & masks[STATIC_MAC_TABLE_OVERRIDE]) ? 1 : 0; - /* KSZ8795 family switches have STATIC_MAC_TABLE_USE_FID and + /* KSZ8795/KSZ8895 family switches have STATIC_MAC_TABLE_USE_FID and * STATIC_MAC_TABLE_FID definitions off by 1 when doing read on the * static MAC table compared to doing write. */ - if (ksz_is_ksz87xx(dev)) + if (ksz_is_ksz87xx(dev) || ksz_is_8895_family(dev)) data_hi >>= 1; alu->is_static = true; alu->is_use_fid = (data_hi & masks[STATIC_MAC_TABLE_USE_FID]) ? 1 : 0; @@ -1692,7 +1695,8 @@ void ksz8_config_cpu_port(struct dsa_switch *ds) for (i = 0; i < dev->phy_port_cnt; i++) { p = &dev->ports[i]; - if (!ksz_is_ksz88x3(dev)) { + /* For KSZ8795 family. */ + if (ksz_is_ksz87xx(dev)) { ksz_pread8(dev, i, regs[P_REMOTE_STATUS], &remote); if (remote & KSZ8_PORT_FIBER_MODE) p->fiber = 1; diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index cd3991792b69..6609bf271ad0 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -2,7 +2,7 @@ /* * Microchip switch driver main logic * - * Copyright (C) 2017-2019 Microchip Technology Inc. + * Copyright (C) 2017-2024 Microchip Technology Inc. */ #include @@ -277,7 +277,7 @@ static const struct phylink_mac_ops ksz8_phylink_mac_ops = { .mac_link_up = ksz8_phylink_mac_link_up, }; -static const struct ksz_dev_ops ksz88x3_dev_ops = { +static const struct ksz_dev_ops ksz88xx_dev_ops = { .setup = ksz8_setup, .get_port_addr = ksz8_get_port_addr, .cfg_port_member = ksz8_cfg_port_member, @@ -572,6 +572,61 @@ static u8 ksz8863_shifts[] = { [DYNAMIC_MAC_SRC_PORT] = 20, }; +static const u16 ksz8895_regs[] = { + [REG_SW_MAC_ADDR] = 0x68, + [REG_IND_CTRL_0] = 0x6E, + [REG_IND_DATA_8] = 0x70, + [REG_IND_DATA_CHECK] = 0x72, + [REG_IND_DATA_HI] = 0x71, + [REG_IND_DATA_LO] = 0x75, + [REG_IND_MIB_CHECK] = 0x75, + [P_FORCE_CTRL] = 0x0C, + [P_LINK_STATUS] = 0x0E, + [P_LOCAL_CTRL] = 0x0C, + [P_NEG_RESTART_CTRL] = 0x0D, + [P_REMOTE_STATUS] = 0x0E, + [P_SPEED_STATUS] = 0x09, + [S_TAIL_TAG_CTRL] = 0x0C, + [P_STP_CTRL] = 0x02, + [S_START_CTRL] = 0x01, + [S_BROADCAST_CTRL] = 0x06, + [S_MULTICAST_CTRL] = 0x04, +}; + +static const u32 ksz8895_masks[] = { + [PORT_802_1P_REMAPPING] = BIT(7), + [SW_TAIL_TAG_ENABLE] = BIT(1), + [MIB_COUNTER_OVERFLOW] = BIT(7), + [MIB_COUNTER_VALID] = BIT(6), + [VLAN_TABLE_FID] = GENMASK(6, 0), + [VLAN_TABLE_MEMBERSHIP] = GENMASK(11, 7), + [VLAN_TABLE_VALID] = BIT(12), + [STATIC_MAC_TABLE_VALID] = BIT(21), + [STATIC_MAC_TABLE_USE_FID] = BIT(23), + [STATIC_MAC_TABLE_FID] = GENMASK(30, 24), + [STATIC_MAC_TABLE_OVERRIDE] = BIT(22), + [STATIC_MAC_TABLE_FWD_PORTS] = GENMASK(20, 16), + [DYNAMIC_MAC_TABLE_ENTRIES_H] = GENMASK(6, 0), + [DYNAMIC_MAC_TABLE_MAC_EMPTY] = BIT(7), + [DYNAMIC_MAC_TABLE_NOT_READY] = BIT(7), + [DYNAMIC_MAC_TABLE_ENTRIES] = GENMASK(31, 29), + [DYNAMIC_MAC_TABLE_FID] = GENMASK(22, 16), + [DYNAMIC_MAC_TABLE_SRC_PORT] = GENMASK(26, 24), + [DYNAMIC_MAC_TABLE_TIMESTAMP] = GENMASK(28, 27), +}; + +static const u8 ksz8895_shifts[] = { + [VLAN_TABLE_MEMBERSHIP_S] = 7, + [VLAN_TABLE] = 13, + [STATIC_MAC_FWD_PORTS] = 16, + [STATIC_MAC_FID] = 24, + [DYNAMIC_MAC_ENTRIES_H] = 3, + [DYNAMIC_MAC_ENTRIES] = 29, + [DYNAMIC_MAC_FID] = 16, + [DYNAMIC_MAC_TIMESTAMP] = 27, + [DYNAMIC_MAC_SRC_PORT] = 24, +}; + static const u16 ksz9477_regs[] = { [REG_SW_MAC_ADDR] = 0x0302, [P_STP_CTRL] = 0x0B04, @@ -1397,7 +1452,7 @@ const struct ksz_chip_data ksz_switch_chips[] = { .port_cnt = 3, .num_tx_queues = 4, .num_ipms = 4, - .ops = &ksz88x3_dev_ops, + .ops = &ksz88xx_dev_ops, .phylink_mac_ops = &ksz8830_phylink_mac_ops, .mib_names = ksz88xx_mib_names, .mib_cnt = ARRAY_SIZE(ksz88xx_mib_names), @@ -1412,6 +1467,61 @@ const struct ksz_chip_data ksz_switch_chips[] = { .rd_table = &ksz8873_register_set, }, + [KSZ8864] = { + /* WARNING + * ======= + * KSZ8864 is similar to KSZ8895, except the first port + * does not exist. + * external cpu + * KSZ8864 1,2,3 4 + * KSZ8895 0,1,2,3 4 + * port_cnt is configured as 5, even though it is 4 + */ + .chip_id = KSZ8864_CHIP_ID, + .dev_name = "KSZ8864", + .num_vlans = 4096, + .num_alus = 0, + .num_statics = 32, + .cpu_ports = 0x10, /* can be configured as cpu port */ + .port_cnt = 5, /* total cpu and user ports */ + .num_tx_queues = 4, + .num_ipms = 4, + .ops = &ksz88xx_dev_ops, + .phylink_mac_ops = &ksz8830_phylink_mac_ops, + .mib_names = ksz88xx_mib_names, + .mib_cnt = ARRAY_SIZE(ksz88xx_mib_names), + .reg_mib_cnt = MIB_COUNTER_NUM, + .regs = ksz8895_regs, + .masks = ksz8895_masks, + .shifts = ksz8895_shifts, + .supports_mii = {false, false, false, false, true}, + .supports_rmii = {false, false, false, false, true}, + .internal_phy = {false, true, true, true, false}, + }, + + [KSZ8895] = { + .chip_id = KSZ8895_CHIP_ID, + .dev_name = "KSZ8895", + .num_vlans = 4096, + .num_alus = 0, + .num_statics = 32, + .cpu_ports = 0x10, /* can be configured as cpu port */ + .port_cnt = 5, /* total cpu and user ports */ + .num_tx_queues = 4, + .num_ipms = 4, + .ops = &ksz88xx_dev_ops, + .phylink_mac_ops = &ksz8830_phylink_mac_ops, + .mib_names = ksz88xx_mib_names, + .mib_cnt = ARRAY_SIZE(ksz88xx_mib_names), + .reg_mib_cnt = MIB_COUNTER_NUM, + .regs = ksz8895_regs, + .masks = ksz8895_masks, + .shifts = ksz8895_shifts, + .supports_mii = {false, false, false, false, true}, + .supports_rmii = {false, false, false, false, true}, + .internal_phy = {true, true, true, true, false}, + }, + [KSZ9477] = { .chip_id = KSZ9477_CHIP_ID, .dev_name = "KSZ9477", @@ -2937,9 +3047,7 @@ static enum dsa_tag_protocol ksz_get_tag_protocol(struct dsa_switch *ds, struct ksz_device *dev = ds->priv; enum dsa_tag_protocol proto = DSA_TAG_PROTO_NONE; - if (dev->chip_id == KSZ8795_CHIP_ID || - dev->chip_id == KSZ8794_CHIP_ID || - dev->chip_id == KSZ8765_CHIP_ID) + if (ksz_is_ksz87xx(dev) || ksz_is_8895_family(dev)) proto = DSA_TAG_PROTO_KSZ8795; if (dev->chip_id == KSZ8830_CHIP_ID || @@ -3055,6 +3163,8 @@ static int ksz_max_mtu(struct dsa_switch *ds, int port) case KSZ8765_CHIP_ID: return KSZ8795_HUGE_PACKET_SIZE - VLAN_ETH_HLEN - ETH_FCS_LEN; case KSZ8830_CHIP_ID: + case KSZ8864_CHIP_ID: + case KSZ8895_CHIP_ID: return KSZ8863_HUGE_PACKET_SIZE - VLAN_ETH_HLEN - ETH_FCS_LEN; case KSZ8563_CHIP_ID: case KSZ8567_CHIP_ID: @@ -3412,6 +3522,18 @@ static int ksz_switch_detect(struct ksz_device *dev) else return -ENODEV; break; + case KSZ8895_FAMILY_ID: + if (id2 == KSZ8895_CHIP_ID_95 || + id2 == KSZ8895_CHIP_ID_95R) + dev->chip_id = KSZ8895_CHIP_ID; + else + return -ENODEV; + ret = ksz_read8(dev, REG_KSZ8864_CHIP_ID, &id4); + if (ret) + return ret; + if (id4 & SW_KSZ8864) + dev->chip_id = KSZ8864_CHIP_ID; + break; default: ret = ksz_read32(dev, REG_CHIP_ID0, &id32); if (ret) diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index 8094d90d6ca4..e08d5a1339f4 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Microchip switch driver common header * - * Copyright (C) 2017-2019 Microchip Technology Inc. + * Copyright (C) 2017-2024 Microchip Technology Inc. */ #ifndef __KSZ_COMMON_H @@ -201,6 +201,8 @@ enum ksz_model { KSZ8794, KSZ8765, KSZ8830, + KSZ8864, + KSZ8895, KSZ9477, KSZ9896, KSZ9897, @@ -629,9 +631,21 @@ static inline bool ksz_is_ksz88x3(struct ksz_device *dev) return dev->chip_id == KSZ8830_CHIP_ID; } +static inline bool ksz_is_8895_family(struct ksz_device *dev) +{ + return dev->chip_id == KSZ8895_CHIP_ID || + dev->chip_id == KSZ8864_CHIP_ID; +} + static inline bool is_ksz8(struct ksz_device *dev) { - return ksz_is_ksz87xx(dev) || ksz_is_ksz88x3(dev); + return ksz_is_ksz87xx(dev) || ksz_is_ksz88x3(dev) || + ksz_is_8895_family(dev); +} + +static inline bool is_ksz88xx(struct ksz_device *dev) +{ + return ksz_is_ksz88x3(dev) || ksz_is_8895_family(dev); } static inline bool is_ksz9477(struct ksz_device *dev) @@ -665,6 +679,7 @@ static inline bool is_lan937x_tx_phy(struct ksz_device *dev, int port) #define SW_FAMILY_ID_M GENMASK(15, 8) #define KSZ87_FAMILY_ID 0x87 #define KSZ88_FAMILY_ID 0x88 +#define KSZ8895_FAMILY_ID 0x95 #define KSZ8_PORT_STATUS_0 0x08 #define KSZ8_PORT_FIBER_MODE BIT(7) @@ -673,6 +688,12 @@ static inline bool is_lan937x_tx_phy(struct ksz_device *dev, int port) #define KSZ87_CHIP_ID_94 0x6 #define KSZ87_CHIP_ID_95 0x9 #define KSZ88_CHIP_ID_63 0x3 +#define KSZ8895_CHIP_ID_95 0x4 +#define KSZ8895_CHIP_ID_95R 0x6 + +/* KSZ8895 specific register */ +#define REG_KSZ8864_CHIP_ID 0xFE +#define SW_KSZ8864 BIT(7) #define SW_REV_ID_M GENMASK(7, 4) diff --git a/drivers/net/dsa/microchip/ksz_dcb.c b/drivers/net/dsa/microchip/ksz_dcb.c index 086bc9b3cf53..30b4a6186e38 100644 --- a/drivers/net/dsa/microchip/ksz_dcb.c +++ b/drivers/net/dsa/microchip/ksz_dcb.c @@ -113,7 +113,7 @@ static void ksz_get_default_port_prio_reg(struct ksz_device *dev, int *reg, static void ksz_get_dscp_prio_reg(struct ksz_device *dev, int *reg, int *per_reg, u8 *mask) { - if (ksz_is_ksz87xx(dev)) { + if (ksz_is_ksz87xx(dev) || ksz_is_8895_family(dev)) { *reg = KSZ8765_REG_TOS_DSCP_CTRL; *per_reg = 4; *mask = GENMASK(1, 0); diff --git a/drivers/net/dsa/microchip/ksz_spi.c b/drivers/net/dsa/microchip/ksz_spi.c index 8e8d83213b04..f4287310e89f 100644 --- a/drivers/net/dsa/microchip/ksz_spi.c +++ b/drivers/net/dsa/microchip/ksz_spi.c @@ -2,7 +2,7 @@ /* * Microchip ksz series register access through SPI * - * Copyright (C) 2017 Microchip Technology Inc. + * Copyright (C) 2017-2024 Microchip Technology Inc. * Tristram Ha */ @@ -60,6 +60,9 @@ static int ksz_spi_probe(struct spi_device *spi) chip->chip_id == KSZ8794_CHIP_ID || chip->chip_id == KSZ8765_CHIP_ID) regmap_config = ksz8795_regmap_config; + else if (chip->chip_id == KSZ8895_CHIP_ID || + chip->chip_id == KSZ8864_CHIP_ID) + regmap_config = ksz8863_regmap_config; else regmap_config = ksz9477_regmap_config; @@ -136,10 +139,18 @@ static const struct of_device_id ksz_dt_ids[] = { .compatible = "microchip,ksz8863", .data = &ksz_switch_chips[KSZ8830] }, + { + .compatible = "microchip,ksz8864", + .data = &ksz_switch_chips[KSZ8864] + }, { .compatible = "microchip,ksz8873", .data = &ksz_switch_chips[KSZ8830] }, + { + .compatible = "microchip,ksz8895", + .data = &ksz_switch_chips[KSZ8895] + }, { .compatible = "microchip,ksz9477", .data = &ksz_switch_chips[KSZ9477] @@ -201,7 +212,9 @@ static const struct spi_device_id ksz_spi_ids[] = { { "ksz8794" }, { "ksz8795" }, { "ksz8863" }, + { "ksz8864" }, { "ksz8873" }, + { "ksz8895" }, { "ksz9477" }, { "ksz9896" }, { "ksz9897" }, diff --git a/include/linux/platform_data/microchip-ksz.h b/include/linux/platform_data/microchip-ksz.h index 8c659db4da6b..d074019474f5 100644 --- a/include/linux/platform_data/microchip-ksz.h +++ b/include/linux/platform_data/microchip-ksz.h @@ -28,6 +28,8 @@ enum ksz_chip_id { KSZ8794_CHIP_ID = 0x8794, KSZ8765_CHIP_ID = 0x8765, KSZ8830_CHIP_ID = 0x8830, + KSZ8864_CHIP_ID = 0x8864, + KSZ8895_CHIP_ID = 0x8895, KSZ9477_CHIP_ID = 0x00947700, KSZ9896_CHIP_ID = 0x00989600, KSZ9897_CHIP_ID = 0x00989700, -- cgit v1.2.3 From a547a5880cba6f287179135381f1b484b251be31 Mon Sep 17 00:00:00 2001 From: Peter Newman Date: Thu, 22 Aug 2024 12:02:11 -0700 Subject: x86/resctrl: Fix arch_mbm_* array overrun on SNC When using resctrl on systems with Sub-NUMA Clustering enabled, monitoring groups may be allocated RMID values which would overrun the arch_mbm_{local,total} arrays. This is due to inconsistencies in whether the SNC-adjusted num_rmid value or the unadjusted value in resctrl_arch_system_num_rmid_idx() is used. The num_rmid value for the L3 resource is currently: resctrl_arch_system_num_rmid_idx() / snc_nodes_per_l3_cache As a simple fix, make resctrl_arch_system_num_rmid_idx() return the SNC-adjusted, L3 num_rmid value on x86. Fixes: e13db55b5a0d ("x86/resctrl: Introduce snc_nodes_per_l3_cache") Signed-off-by: Peter Newman Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Reinette Chatre Link: https://lore.kernel.org/r/20240822190212.1848788-1-peternewman@google.com --- arch/x86/include/asm/resctrl.h | 6 ------ arch/x86/kernel/cpu/resctrl/core.c | 8 ++++++++ include/linux/resctrl.h | 1 + 3 files changed, 9 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h index 12dbd2588ca7..8b1b6ce1e51b 100644 --- a/arch/x86/include/asm/resctrl.h +++ b/arch/x86/include/asm/resctrl.h @@ -156,12 +156,6 @@ static inline void resctrl_sched_in(struct task_struct *tsk) __resctrl_sched_in(tsk); } -static inline u32 resctrl_arch_system_num_rmid_idx(void) -{ - /* RMID are independent numbers for x86. num_rmid_idx == num_rmid */ - return boot_cpu_data.x86_cache_max_rmid + 1; -} - static inline void resctrl_arch_rmid_idx_decode(u32 idx, u32 *closid, u32 *rmid) { *rmid = idx; diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 1930fce9dfe9..8591d53c144b 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -119,6 +119,14 @@ struct rdt_hw_resource rdt_resources_all[] = { }, }; +u32 resctrl_arch_system_num_rmid_idx(void) +{ + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; + + /* RMID are independent numbers for x86. num_rmid_idx == num_rmid */ + return r->num_rmid; +} + /* * cache_alloc_hsw_probe() - Have to probe for Intel haswell server CPUs * as they do not have CPUID enumeration support for Cache allocation. diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index b0875b99e811..d94abba1c716 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -248,6 +248,7 @@ struct resctrl_schema { /* The number of closid supported by this resource regardless of CDP */ u32 resctrl_arch_get_num_closid(struct rdt_resource *r); +u32 resctrl_arch_system_num_rmid_idx(void); int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid); /* -- cgit v1.2.3 From 1934b212615dc617ac84fc306333ab2b9fc3b04f Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 9 Aug 2024 18:00:01 +0200 Subject: file: reclaim 24 bytes from f_owner We do embedd struct fown_struct into struct file letting it take up 32 bytes in total. We could tweak struct fown_struct to be more compact but really it shouldn't even be embedded in struct file in the first place. Instead, actual users of struct fown_struct should allocate the struct on demand. This frees up 24 bytes in struct file. That will have some potentially user-visible changes for the ownership fcntl()s. Some of them can now fail due to allocation failures. Practically, that probably will almost never happen as the allocations are small and they only happen once per file. The fown_struct is used during kill_fasync() which is used by e.g., pipes to generate a SIGIO signal. Sending of such signals is conditional on userspace having set an owner for the file using one of the F_OWNER fcntl()s. Such users will be unaffected if struct fown_struct is allocated during the fcntl() call. There are a few subsystems that call __f_setown() expecting file->f_owner to be allocated: (1) tun devices file->f_op->fasync::tun_chr_fasync() -> __f_setown() There are no callers of tun_chr_fasync(). (2) tty devices file->f_op->fasync::tty_fasync() -> __tty_fasync() -> __f_setown() tty_fasync() has no additional callers but __tty_fasync() has. Note that __tty_fasync() only calls __f_setown() if the @on argument is true. It's called from: file->f_op->release::tty_release() -> tty_release() -> __tty_fasync() -> __f_setown() tty_release() calls __tty_fasync() with @on false => __f_setown() is never called from tty_release(). => All callers of tty_release() are safe as well. file->f_op->release::tty_open() -> tty_release() -> __tty_fasync() -> __f_setown() __tty_hangup() calls __tty_fasync() with @on false => __f_setown() is never called from tty_release(). => All callers of __tty_hangup() are safe as well. From the callchains it's obvious that (1) and (2) end up getting called via file->f_op->fasync(). That can happen either through the F_SETFL fcntl() with the FASYNC flag raised or via the FIOASYNC ioctl(). If FASYNC is requested and the file isn't already FASYNC then file->f_op->fasync() is called with @on true which ends up causing both (1) and (2) to call __f_setown(). (1) and (2) are the only subsystems that call __f_setown() from the file->f_op->fasync() handler. So both (1) and (2) have been updated to allocate a struct fown_struct prior to calling fasync_helper() to register with the fasync infrastructure. That's safe as they both call fasync_helper() which also does allocations if @on is true. The other interesting case are file leases: (3) file leases lease_manager_ops->lm_setup::lease_setup() -> __f_setown() Which in turn is called from: generic_add_lease() -> lease_manager_ops->lm_setup::lease_setup() -> __f_setown() So here again we can simply make generic_add_lease() allocate struct fown_struct prior to the lease_manager_ops->lm_setup::lease_setup() which happens under a spinlock. With that the two remaining subsystems that call __f_setown() are: (4) dnotify (5) sockets Both have their own custom ioctls to set struct fown_struct and both have been converted to allocate a struct fown_struct on demand from their respective ioctls. Interactions with O_PATH are fine as well e.g., when opening a /dev/tty as O_PATH then no file->f_op->open() happens thus no file->f_owner is allocated. That's fine as no file operation will be set for those and the device has never been opened. fcntl()s called on such things will just allocate a ->f_owner on demand. Although I have zero idea why'd you care about f_owner on an O_PATH fd. Link: https://lore.kernel.org/r/20240813-work-f_owner-v2-1-4e9343a79f9f@kernel.org Reviewed-by: Jeff Layton Signed-off-by: Christian Brauner --- drivers/net/tun.c | 6 ++ drivers/tty/tty_io.c | 6 ++ fs/fcntl.c | 166 +++++++++++++++++++++++++++++++++++--------- fs/file_table.c | 3 +- fs/internal.h | 1 + fs/locks.c | 6 +- fs/notify/dnotify/dnotify.c | 6 +- include/linux/fs.h | 11 ++- net/core/sock.c | 2 +- security/selinux/hooks.c | 2 +- security/smack/smack_lsm.c | 2 +- 11 files changed, 168 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 1d06c560c5e6..6fe5e8f7017c 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -3451,6 +3451,12 @@ static int tun_chr_fasync(int fd, struct file *file, int on) struct tun_file *tfile = file->private_data; int ret; + if (on) { + ret = file_f_owner_allocate(file); + if (ret) + goto out; + } + if ((ret = fasync_helper(fd, file, on, &tfile->fasync)) < 0) goto out; diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 407b0d87b7c1..7ae0c8934f42 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -2225,6 +2225,12 @@ static int __tty_fasync(int fd, struct file *filp, int on) if (tty_paranoia_check(tty, file_inode(filp), "tty_fasync")) goto out; + if (on) { + retval = file_f_owner_allocate(filp); + if (retval) + goto out; + } + retval = fasync_helper(fd, filp, on, &tty->fasync); if (retval <= 0) goto out; diff --git a/fs/fcntl.c b/fs/fcntl.c index 300e5d9ad913..0587a0e221a6 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -33,6 +33,8 @@ #include #include +#include "internal.h" + #define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME) static int setfl(int fd, struct file * filp, unsigned int arg) @@ -87,22 +89,64 @@ static int setfl(int fd, struct file * filp, unsigned int arg) return error; } +/* + * Allocate an file->f_owner struct if it doesn't exist, handling racing + * allocations correctly. + */ +int file_f_owner_allocate(struct file *file) +{ + struct fown_struct *f_owner; + + f_owner = file_f_owner(file); + if (f_owner) + return 0; + + f_owner = kzalloc(sizeof(struct fown_struct), GFP_KERNEL); + if (!f_owner) + return -ENOMEM; + + rwlock_init(&f_owner->lock); + f_owner->file = file; + /* If someone else raced us, drop our allocation. */ + if (unlikely(cmpxchg(&file->f_owner, NULL, f_owner))) + kfree(f_owner); + return 0; +} +EXPORT_SYMBOL(file_f_owner_allocate); + +void file_f_owner_release(struct file *file) +{ + struct fown_struct *f_owner; + + f_owner = file_f_owner(file); + if (f_owner) { + put_pid(f_owner->pid); + kfree(f_owner); + } +} + static void f_modown(struct file *filp, struct pid *pid, enum pid_type type, int force) { - write_lock_irq(&filp->f_owner.lock); - if (force || !filp->f_owner.pid) { - put_pid(filp->f_owner.pid); - filp->f_owner.pid = get_pid(pid); - filp->f_owner.pid_type = type; + struct fown_struct *f_owner; + + f_owner = file_f_owner(filp); + if (WARN_ON_ONCE(!f_owner)) + return; + + write_lock_irq(&f_owner->lock); + if (force || !f_owner->pid) { + put_pid(f_owner->pid); + f_owner->pid = get_pid(pid); + f_owner->pid_type = type; if (pid) { const struct cred *cred = current_cred(); - filp->f_owner.uid = cred->uid; - filp->f_owner.euid = cred->euid; + f_owner->uid = cred->uid; + f_owner->euid = cred->euid; } } - write_unlock_irq(&filp->f_owner.lock); + write_unlock_irq(&f_owner->lock); } void __f_setown(struct file *filp, struct pid *pid, enum pid_type type, @@ -119,6 +163,8 @@ int f_setown(struct file *filp, int who, int force) struct pid *pid = NULL; int ret = 0; + might_sleep(); + type = PIDTYPE_TGID; if (who < 0) { /* avoid overflow below */ @@ -129,6 +175,10 @@ int f_setown(struct file *filp, int who, int force) who = -who; } + ret = file_f_owner_allocate(filp); + if (ret) + return ret; + rcu_read_lock(); if (who) { pid = find_vpid(who); @@ -152,16 +202,21 @@ void f_delown(struct file *filp) pid_t f_getown(struct file *filp) { pid_t pid = 0; + struct fown_struct *f_owner; + + f_owner = file_f_owner(filp); + if (!f_owner) + return pid; - read_lock_irq(&filp->f_owner.lock); + read_lock_irq(&f_owner->lock); rcu_read_lock(); - if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) { - pid = pid_vnr(filp->f_owner.pid); - if (filp->f_owner.pid_type == PIDTYPE_PGID) + if (pid_task(f_owner->pid, f_owner->pid_type)) { + pid = pid_vnr(f_owner->pid); + if (f_owner->pid_type == PIDTYPE_PGID) pid = -pid; } rcu_read_unlock(); - read_unlock_irq(&filp->f_owner.lock); + read_unlock_irq(&f_owner->lock); return pid; } @@ -194,6 +249,10 @@ static int f_setown_ex(struct file *filp, unsigned long arg) return -EINVAL; } + ret = file_f_owner_allocate(filp); + if (ret) + return ret; + rcu_read_lock(); pid = find_vpid(owner.pid); if (owner.pid && !pid) @@ -210,13 +269,20 @@ static int f_getown_ex(struct file *filp, unsigned long arg) struct f_owner_ex __user *owner_p = (void __user *)arg; struct f_owner_ex owner = {}; int ret = 0; + struct fown_struct *f_owner; + enum pid_type pid_type = PIDTYPE_PID; - read_lock_irq(&filp->f_owner.lock); - rcu_read_lock(); - if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) - owner.pid = pid_vnr(filp->f_owner.pid); - rcu_read_unlock(); - switch (filp->f_owner.pid_type) { + f_owner = file_f_owner(filp); + if (f_owner) { + read_lock_irq(&f_owner->lock); + rcu_read_lock(); + if (pid_task(f_owner->pid, f_owner->pid_type)) + owner.pid = pid_vnr(f_owner->pid); + rcu_read_unlock(); + pid_type = f_owner->pid_type; + } + + switch (pid_type) { case PIDTYPE_PID: owner.type = F_OWNER_TID; break; @@ -234,7 +300,8 @@ static int f_getown_ex(struct file *filp, unsigned long arg) ret = -EINVAL; break; } - read_unlock_irq(&filp->f_owner.lock); + if (f_owner) + read_unlock_irq(&f_owner->lock); if (!ret) { ret = copy_to_user(owner_p, &owner, sizeof(owner)); @@ -248,14 +315,18 @@ static int f_getown_ex(struct file *filp, unsigned long arg) static int f_getowner_uids(struct file *filp, unsigned long arg) { struct user_namespace *user_ns = current_user_ns(); + struct fown_struct *f_owner; uid_t __user *dst = (void __user *)arg; - uid_t src[2]; + uid_t src[2] = {0, 0}; int err; - read_lock_irq(&filp->f_owner.lock); - src[0] = from_kuid(user_ns, filp->f_owner.uid); - src[1] = from_kuid(user_ns, filp->f_owner.euid); - read_unlock_irq(&filp->f_owner.lock); + f_owner = file_f_owner(filp); + if (f_owner) { + read_lock_irq(&f_owner->lock); + src[0] = from_kuid(user_ns, f_owner->uid); + src[1] = from_kuid(user_ns, f_owner->euid); + read_unlock_irq(&f_owner->lock); + } err = put_user(src[0], &dst[0]); err |= put_user(src[1], &dst[1]); @@ -343,6 +414,30 @@ static long f_dupfd_query(int fd, struct file *filp) return f.file == filp; } +static int f_owner_sig(struct file *filp, int signum, bool setsig) +{ + int ret = 0; + struct fown_struct *f_owner; + + might_sleep(); + + if (setsig) { + if (!valid_signal(signum)) + return -EINVAL; + + ret = file_f_owner_allocate(filp); + if (ret) + return ret; + } + + f_owner = file_f_owner(filp); + if (setsig) + f_owner->signum = signum; + else if (f_owner) + ret = f_owner->signum; + return ret; +} + static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, struct file *filp) { @@ -421,15 +516,10 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, err = f_getowner_uids(filp, arg); break; case F_GETSIG: - err = filp->f_owner.signum; + err = f_owner_sig(filp, 0, false); break; case F_SETSIG: - /* arg == 0 restores default behaviour. */ - if (!valid_signal(argi)) { - break; - } - err = 0; - filp->f_owner.signum = argi; + err = f_owner_sig(filp, argi, true); break; case F_GETLEASE: err = fcntl_getlease(filp); @@ -844,14 +934,19 @@ static void send_sigurg_to_task(struct task_struct *p, do_send_sig_info(SIGURG, SEND_SIG_PRIV, p, type); } -int send_sigurg(struct fown_struct *fown) +int send_sigurg(struct file *file) { + struct fown_struct *fown; struct task_struct *p; enum pid_type type; struct pid *pid; unsigned long flags; int ret = 0; + fown = file_f_owner(file); + if (!fown) + return 0; + read_lock_irqsave(&fown->lock, flags); type = fown->pid_type; @@ -1027,13 +1122,16 @@ static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band) } read_lock_irqsave(&fa->fa_lock, flags); if (fa->fa_file) { - fown = &fa->fa_file->f_owner; + fown = file_f_owner(fa->fa_file); + if (!fown) + goto next; /* Don't send SIGURG to processes which have not set a queued signum: SIGURG has its own default signalling mechanism. */ if (!(sig == SIGURG && fown->signum == 0)) send_sigio(fown, fa->fa_fd, band); } +next: read_unlock_irqrestore(&fa->fa_lock, flags); fa = rcu_dereference(fa->fa_next); } diff --git a/fs/file_table.c b/fs/file_table.c index ca7843dde56d..fdf98709dde2 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -155,7 +155,6 @@ static int init_file(struct file *f, int flags, const struct cred *cred) return error; } - rwlock_init(&f->f_owner.lock); spin_lock_init(&f->f_lock); mutex_init(&f->f_pos_lock); f->f_flags = flags; @@ -425,7 +424,7 @@ static void __fput(struct file *file) cdev_put(inode->i_cdev); } fops_put(file->f_op); - put_pid(file->f_owner.pid); + file_f_owner_release(file); put_file_access(file); dput(dentry); if (unlikely(mode & FMODE_NEED_UNMOUNT)) diff --git a/fs/internal.h b/fs/internal.h index cdd73209eecb..8c1b7acbbe8f 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -337,3 +337,4 @@ static inline bool path_mounted(const struct path *path) { return path->mnt->mnt_root == path->dentry; } +void file_f_owner_release(struct file *file); diff --git a/fs/locks.c b/fs/locks.c index e45cad40f8b6..b51b1c395ce6 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1451,7 +1451,7 @@ int lease_modify(struct file_lease *fl, int arg, struct list_head *dispose) struct file *filp = fl->c.flc_file; f_delown(filp); - filp->f_owner.signum = 0; + file_f_owner(filp)->signum = 0; fasync_helper(0, fl->c.flc_file, 0, &fl->fl_fasync); if (fl->fl_fasync != NULL) { printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync); @@ -1783,6 +1783,10 @@ generic_add_lease(struct file *filp, int arg, struct file_lease **flp, void **pr lease = *flp; trace_generic_add_lease(inode, lease); + error = file_f_owner_allocate(filp); + if (error) + return error; + /* Note that arg is never F_UNLCK here */ ctx = locks_get_lock_context(inode, arg); if (!ctx) diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c index f3669403fabf..46440fbb8662 100644 --- a/fs/notify/dnotify/dnotify.c +++ b/fs/notify/dnotify/dnotify.c @@ -110,7 +110,7 @@ static int dnotify_handle_event(struct fsnotify_mark *inode_mark, u32 mask, prev = &dn->dn_next; continue; } - fown = &dn->dn_filp->f_owner; + fown = file_f_owner(dn->dn_filp); send_sigio(fown, dn->dn_fd, POLL_MSG); if (dn->dn_mask & FS_DN_MULTISHOT) prev = &dn->dn_next; @@ -316,6 +316,10 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned int arg) goto out_err; } + error = file_f_owner_allocate(filp); + if (error) + goto out_err; + /* set up the new_fsn_mark and new_dn_mark */ new_fsn_mark = &new_dn_mark->fsn_mark; fsnotify_init_mark(new_fsn_mark, dnotify_group); diff --git a/include/linux/fs.h b/include/linux/fs.h index fb0426f349fc..7af239ca87e2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -947,6 +947,7 @@ static inline unsigned imajor(const struct inode *inode) } struct fown_struct { + struct file *file; /* backpointer for security modules */ rwlock_t lock; /* protects pid, uid, euid fields */ struct pid *pid; /* pid or -pgrp where SIGIO should be sent */ enum pid_type pid_type; /* Kind of process group SIGIO should be sent to */ @@ -1011,7 +1012,7 @@ struct file { struct mutex f_pos_lock; loff_t f_pos; unsigned int f_flags; - struct fown_struct f_owner; + struct fown_struct *f_owner; const struct cred *f_cred; struct file_ra_state f_ra; struct path f_path; @@ -1076,6 +1077,12 @@ struct file_lease; #define OFFT_OFFSET_MAX type_max(off_t) #endif +int file_f_owner_allocate(struct file *file); +static inline struct fown_struct *file_f_owner(const struct file *file) +{ + return READ_ONCE(file->f_owner); +} + extern void send_sigio(struct fown_struct *fown, int fd, int band); static inline struct inode *file_inode(const struct file *f) @@ -1124,7 +1131,7 @@ extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force extern int f_setown(struct file *filp, int who, int force); extern void f_delown(struct file *filp); extern pid_t f_getown(struct file *filp); -extern int send_sigurg(struct fown_struct *fown); +extern int send_sigurg(struct file *file); /* * sb->s_flags. Note that these mirror the equivalent MS_* flags where diff --git a/net/core/sock.c b/net/core/sock.c index 9abc4fe25953..bbe4c58470c3 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3429,7 +3429,7 @@ static void sock_def_destruct(struct sock *sk) void sk_send_sigurg(struct sock *sk) { if (sk->sk_socket && sk->sk_socket->file) - if (send_sigurg(&sk->sk_socket->file->f_owner)) + if (send_sigurg(sk->sk_socket->file)) sk_wake_async(sk, SOCK_WAKE_URG, POLL_PRI); } EXPORT_SYMBOL(sk_send_sigurg); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index bfa61e005aac..577e1fcbf6df 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3950,7 +3950,7 @@ static int selinux_file_send_sigiotask(struct task_struct *tsk, struct file_security_struct *fsec; /* struct fown_struct is never outside the context of a struct file */ - file = container_of(fown, struct file, f_owner); + file = fown->file; fsec = selinux_file(file); diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 4164699cd4f6..cb33920ab67c 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -1950,7 +1950,7 @@ static int smack_file_send_sigiotask(struct task_struct *tsk, /* * struct fown_struct is never outside the context of a struct file */ - file = container_of(fown, struct file, f_owner); + file = fown->file; /* we don't log here as rc can be overriden */ blob = smack_file(file); -- cgit v1.2.3 From a55d1cbd1720679cfe9837bce250e397ec513989 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 22 Aug 2024 16:14:46 +0200 Subject: fs: switch f_iocb_flags and f_ra Now that we shrank struct file by 24 bytes we still have a 4 byte hole. If we move struct file_ra_state into the union and f_iocb_flags out of the union we close that whole and bring down struct file to 192 bytes. Which means struct file is 3 cachelines and we managed to shrink it by 40 bytes this cycle. I've tried to audit all codepaths that use f_ra and none of them seem to rely on it in file->f_op->release() and never have since commit 1da177e4c3f4 ("Linux-2.6.12-rc2"). Link: https://lore.kernel.org/r/20240823-luftdicht-berappen-d69a2166a0db@brauner Reviewed-by: Jeff Layton Reviewed-by: Jens Axboe Signed-off-by: Christian Brauner --- include/linux/fs.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 7af239ca87e2..095a956aeb29 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -999,9 +999,9 @@ struct file { struct callback_head f_task_work; /* fput() must use workqueue (most kernel threads). */ struct llist_node f_llist; - unsigned int f_iocb_flags; + /* Invalid after last fput(). */ + struct file_ra_state f_ra; }; - /* * Protects f_ep, f_flags. * Must not be taken from IRQ context. @@ -1012,9 +1012,9 @@ struct file { struct mutex f_pos_lock; loff_t f_pos; unsigned int f_flags; + unsigned int f_iocb_flags; struct fown_struct *f_owner; const struct cred *f_cred; - struct file_ra_state f_ra; struct path f_path; struct inode *f_inode; /* cached value */ const struct file_operations *f_op; -- cgit v1.2.3 From 1da29f2c39b67b846b74205c81bf0ccd96d34727 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 22 Aug 2024 23:06:49 +0100 Subject: netfs, cifs: Fix handling of short DIO read Short DIO reads, particularly in relation to cifs, are not being handled correctly by cifs and netfslib. This can be tested by doing a DIO read of a file where the size of read is larger than the size of the file. When it crosses the EOF, it gets a short read and this gets retried, and in the case of cifs, the retry read fails, with the failure being translated to ENODATA. Fix this by the following means: (1) Add a flag, NETFS_SREQ_HIT_EOF, for the filesystem to set when it detects that the read did hit the EOF. (2) Make the netfslib read assessment stop processing subrequests when it encounters one with that flag set. (3) Return rreq->transferred, the accumulated contiguous amount read to that point, to userspace for a DIO read. (4) Make cifs set the flag and clear the error if the read RPC returned ENODATA. (5) Make cifs set the flag and clear the error if a short read occurred without error and the read-to file position is now at the remote inode size. Fixes: 69c3c023af25 ("cifs: Implement netfslib hooks") Signed-off-by: David Howells cc: Steve French cc: Paulo Alcantara cc: Jeff Layton cc: linux-cifs@vger.kernel.org cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Steve French --- fs/netfs/io.c | 17 +++++++++++------ fs/smb/client/smb2pdu.c | 13 +++++++++---- include/linux/netfs.h | 1 + 3 files changed, 21 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/fs/netfs/io.c b/fs/netfs/io.c index 3303b515b536..943128507af5 100644 --- a/fs/netfs/io.c +++ b/fs/netfs/io.c @@ -368,7 +368,8 @@ static void netfs_rreq_assess_dio(struct netfs_io_request *rreq) if (subreq->error || subreq->transferred == 0) break; transferred += subreq->transferred; - if (subreq->transferred < subreq->len) + if (subreq->transferred < subreq->len || + test_bit(NETFS_SREQ_HIT_EOF, &subreq->flags)) break; } @@ -503,7 +504,8 @@ void netfs_subreq_terminated(struct netfs_io_subrequest *subreq, subreq->error = 0; subreq->transferred += transferred_or_error; - if (subreq->transferred < subreq->len) + if (subreq->transferred < subreq->len && + !test_bit(NETFS_SREQ_HIT_EOF, &subreq->flags)) goto incomplete; complete: @@ -782,10 +784,13 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync) TASK_UNINTERRUPTIBLE); ret = rreq->error; - if (ret == 0 && rreq->submitted < rreq->len && - rreq->origin != NETFS_DIO_READ) { - trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read); - ret = -EIO; + if (ret == 0) { + if (rreq->origin == NETFS_DIO_READ) { + ret = rreq->transferred; + } else if (rreq->submitted < rreq->len) { + trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read); + ret = -EIO; + } } } else { /* If we decrement nr_outstanding to 0, the ref belongs to us. */ diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index be7a1a9c691d..88dc49d67037 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -4507,6 +4507,7 @@ static void smb2_readv_callback(struct mid_q_entry *mid) { struct cifs_io_subrequest *rdata = mid->callback_data; + struct netfs_inode *ictx = netfs_inode(rdata->rreq->inode); struct cifs_tcon *tcon = tlink_tcon(rdata->req->cfile->tlink); struct TCP_Server_Info *server = rdata->server; struct smb2_hdr *shdr = @@ -4599,11 +4600,15 @@ smb2_readv_callback(struct mid_q_entry *mid) rdata->got_bytes); if (rdata->result == -ENODATA) { - /* We may have got an EOF error because fallocate - * failed to enlarge the file. - */ - if (rdata->subreq.start < rdata->subreq.rreq->i_size) + __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); + rdata->result = 0; + } else { + if (rdata->got_bytes < rdata->actual_len && + rdata->subreq.start + rdata->subreq.transferred + rdata->got_bytes == + ictx->remote_i_size) { + __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); rdata->result = 0; + } } trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, rdata->credits.value, server->credits, server->in_flight, diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 983816608f15..c47443e7a97e 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -198,6 +198,7 @@ struct netfs_io_subrequest { #define NETFS_SREQ_NEED_RETRY 9 /* Set if the filesystem requests a retry */ #define NETFS_SREQ_RETRYING 10 /* Set if we're retrying */ #define NETFS_SREQ_FAILED 11 /* Set if the subreq failed unretryably */ +#define NETFS_SREQ_HIT_EOF 12 /* Set if we hit the EOF */ }; enum netfs_io_origin { -- cgit v1.2.3 From 947697c6f0f75f9866f2f891a102dece7a09a064 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Thu, 22 Aug 2024 10:18:52 +0530 Subject: uapi: Define GENMASK_U128 This adds GENMASK_U128() and __GENMASK_U128() macros using __BITS_PER_U128 and __int128 data types. These macros will be used in providing support for generating 128 bit masks. The macros wouldn't work in all assembler flavors for reasons described in the comments on top of declarations. Enforce it for more by adding !__ASSEMBLY__ guard. Cc: Yury Norov Cc: Rasmus Villemoes Cc: Arnd Bergmann > Cc: linux-kernel@vger.kernel.org Cc: linux-arch@vger.kernel.org Reviewed-by: Arnd Bergmann Signed-off-by: Anshuman Khandual Signed-off-by: Yury Norov --- include/linux/bits.h | 15 +++++++++++++++ include/uapi/linux/bits.h | 3 +++ include/uapi/linux/const.h | 17 +++++++++++++++++ 3 files changed, 35 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bits.h b/include/linux/bits.h index 0eb24d21aac2..60044b608817 100644 --- a/include/linux/bits.h +++ b/include/linux/bits.h @@ -36,4 +36,19 @@ #define GENMASK_ULL(h, l) \ (GENMASK_INPUT_CHECK(h, l) + __GENMASK_ULL(h, l)) +#if !defined(__ASSEMBLY__) +/* + * Missing asm support + * + * __GENMASK_U128() depends on _BIT128() which would not work + * in the asm code, as it shifts an 'unsigned __init128' data + * type instead of direct representation of 128 bit constants + * such as long and unsigned long. The fundamental problem is + * that a 128 bit constant will get silently truncated by the + * gcc compiler. + */ +#define GENMASK_U128(h, l) \ + (GENMASK_INPUT_CHECK(h, l) + __GENMASK_U128(h, l)) +#endif + #endif /* __LINUX_BITS_H */ diff --git a/include/uapi/linux/bits.h b/include/uapi/linux/bits.h index 3c2a101986a3..5ee30f882736 100644 --- a/include/uapi/linux/bits.h +++ b/include/uapi/linux/bits.h @@ -12,4 +12,7 @@ (((~_ULL(0)) - (_ULL(1) << (l)) + 1) & \ (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h)))) +#define __GENMASK_U128(h, l) \ + ((_BIT128((h)) << 1) - (_BIT128(l))) + #endif /* _UAPI_LINUX_BITS_H */ diff --git a/include/uapi/linux/const.h b/include/uapi/linux/const.h index a429381e7ca5..e16be0d37746 100644 --- a/include/uapi/linux/const.h +++ b/include/uapi/linux/const.h @@ -28,6 +28,23 @@ #define _BITUL(x) (_UL(1) << (x)) #define _BITULL(x) (_ULL(1) << (x)) +#if !defined(__ASSEMBLY__) +/* + * Missing asm support + * + * __BIT128() would not work in the asm code, as it shifts an + * 'unsigned __init128' data type as direct representation of + * 128 bit constants is not supported in the gcc compiler, as + * they get silently truncated. + * + * TODO: Please revisit this implementation when gcc compiler + * starts representing 128 bit constants directly like long + * and unsigned long etc. Subsequently drop the comment for + * GENMASK_U128() which would then start supporting asm code. + */ +#define _BIT128(x) ((unsigned __int128)(1) << (x)) +#endif + #define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1) #define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) -- cgit v1.2.3 From 57413d8e172c10c90fbd91f98d0f7d8eb27e824c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 27 Aug 2024 08:50:47 +0200 Subject: fs: sort out the fallocate mode vs flag mess The fallocate system call takes a mode argument, but that argument contains a wild mix of exclusive modes and an optional flags. Replace FALLOC_FL_SUPPORTED_MASK with FALLOC_FL_MODE_MASK, which excludes the optional flag bit, so that we can use switch statement on the value to easily enumerate the cases while getting the check for duplicate modes for free. To make this (and in the future the file system implementations) more readable also add a symbolic name for the 0 mode used to allocate blocks. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20240827065123.1762168-4-hch@lst.de Reviewed-by: Darrick J. Wong Reviewed-by: Jan Kara Signed-off-by: Christian Brauner --- fs/open.c | 51 ++++++++++++++++++++++----------------------- include/linux/falloc.h | 18 ++++++++++------ include/uapi/linux/falloc.h | 1 + 3 files changed, 38 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/fs/open.c b/fs/open.c index 22adbef7ecc2..daf1b55ca818 100644 --- a/fs/open.c +++ b/fs/open.c @@ -252,40 +252,39 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len) if (offset < 0 || len <= 0) return -EINVAL; - /* Return error if mode is not supported */ - if (mode & ~FALLOC_FL_SUPPORTED_MASK) + if (mode & ~(FALLOC_FL_MODE_MASK | FALLOC_FL_KEEP_SIZE)) return -EOPNOTSUPP; - /* Punch hole and zero range are mutually exclusive */ - if ((mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) == - (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) - return -EOPNOTSUPP; - - /* Punch hole must have keep size set */ - if ((mode & FALLOC_FL_PUNCH_HOLE) && - !(mode & FALLOC_FL_KEEP_SIZE)) + /* + * Modes are exclusive, even if that is not obvious from the encoding + * as bit masks and the mix with the flag in the same namespace. + * + * To make things even more complicated, FALLOC_FL_ALLOCATE_RANGE is + * encoded as no bit set. + */ + switch (mode & FALLOC_FL_MODE_MASK) { + case FALLOC_FL_ALLOCATE_RANGE: + case FALLOC_FL_UNSHARE_RANGE: + case FALLOC_FL_ZERO_RANGE: + break; + case FALLOC_FL_PUNCH_HOLE: + if (!(mode & FALLOC_FL_KEEP_SIZE)) + return -EOPNOTSUPP; + break; + case FALLOC_FL_COLLAPSE_RANGE: + case FALLOC_FL_INSERT_RANGE: + if (mode & FALLOC_FL_KEEP_SIZE) + return -EOPNOTSUPP; + break; + default: return -EOPNOTSUPP; - - /* Collapse range should only be used exclusively. */ - if ((mode & FALLOC_FL_COLLAPSE_RANGE) && - (mode & ~FALLOC_FL_COLLAPSE_RANGE)) - return -EINVAL; - - /* Insert range should only be used exclusively. */ - if ((mode & FALLOC_FL_INSERT_RANGE) && - (mode & ~FALLOC_FL_INSERT_RANGE)) - return -EINVAL; - - /* Unshare range should only be used with allocate mode. */ - if ((mode & FALLOC_FL_UNSHARE_RANGE) && - (mode & ~(FALLOC_FL_UNSHARE_RANGE | FALLOC_FL_KEEP_SIZE))) - return -EINVAL; + } if (!(file->f_mode & FMODE_WRITE)) return -EBADF; /* - * We can only allow pure fallocate on append only files + * On append-only files only space preallocation is supported. */ if ((mode & ~FALLOC_FL_KEEP_SIZE) && IS_APPEND(inode)) return -EPERM; diff --git a/include/linux/falloc.h b/include/linux/falloc.h index f3f0b97b1675..3f49f3df6af5 100644 --- a/include/linux/falloc.h +++ b/include/linux/falloc.h @@ -25,12 +25,18 @@ struct space_resv { #define FS_IOC_UNRESVSP64 _IOW('X', 43, struct space_resv) #define FS_IOC_ZERO_RANGE _IOW('X', 57, struct space_resv) -#define FALLOC_FL_SUPPORTED_MASK (FALLOC_FL_KEEP_SIZE | \ - FALLOC_FL_PUNCH_HOLE | \ - FALLOC_FL_COLLAPSE_RANGE | \ - FALLOC_FL_ZERO_RANGE | \ - FALLOC_FL_INSERT_RANGE | \ - FALLOC_FL_UNSHARE_RANGE) +/* + * Mask of all supported fallocate modes. Only one can be set at a time. + * + * In addition to the mode bit, the mode argument can also encode flags. + * FALLOC_FL_KEEP_SIZE is the only supported flag so far. + */ +#define FALLOC_FL_MODE_MASK (FALLOC_FL_ALLOCATE_RANGE | \ + FALLOC_FL_PUNCH_HOLE | \ + FALLOC_FL_COLLAPSE_RANGE | \ + FALLOC_FL_ZERO_RANGE | \ + FALLOC_FL_INSERT_RANGE | \ + FALLOC_FL_UNSHARE_RANGE) /* on ia32 l_start is on a 32-bit boundary */ #if defined(CONFIG_X86_64) diff --git a/include/uapi/linux/falloc.h b/include/uapi/linux/falloc.h index 51398fa57f6c..5810371ed72b 100644 --- a/include/uapi/linux/falloc.h +++ b/include/uapi/linux/falloc.h @@ -2,6 +2,7 @@ #ifndef _UAPI_FALLOC_H_ #define _UAPI_FALLOC_H_ +#define FALLOC_FL_ALLOCATE_RANGE 0x00 /* allocate range */ #define FALLOC_FL_KEEP_SIZE 0x01 /* default is extend size */ #define FALLOC_FL_PUNCH_HOLE 0x02 /* de-allocates range */ #define FALLOC_FL_NO_HIDE_STALE 0x04 /* reserved codepoint */ -- cgit v1.2.3 From 654beb75ca95240c00c78be0bbc2ea66a125a997 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Wed, 21 Aug 2024 18:46:33 +0200 Subject: dma: ipu: Remove include/linux/dma/ipu-dma.h When this file was renamed in commit b8a6d9980f75 ("dma: ipu: rename mach/ipu.h to include/linux/dma/ipu-dma.h"), 4 .c files have been modified accordingly: drivers/dma/ipu/ipu_idmac.c drivers/dma/ipu/ipu_irq.c --> removed in commit f1de55ff7c70 ("dmaengine: ipu: Remove the driver") in 2023-08 drivers/media/platform/soc_camera/mx3_camera.c --> removed in commit c93cc61475eb ("[media] staging/media: remove deprecated mx3 driver") in 2016-06 drivers/video/mx3fb.c --> removed in commit bfac19e239a7 ("fbdev: mx3fb: Remove the driver") in 2023-08 Now include/linux/dma/ipu-dma.h is unused and can be removed as-well. Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/532e7e2816ccf226f3ab1fa76ec7873bc09299d0.1724258714.git.christophe.jaillet@wanadoo.fr Signed-off-by: Vinod Koul --- include/linux/dma/ipu-dma.h | 174 -------------------------------------------- 1 file changed, 174 deletions(-) delete mode 100644 include/linux/dma/ipu-dma.h (limited to 'include/linux') diff --git a/include/linux/dma/ipu-dma.h b/include/linux/dma/ipu-dma.h deleted file mode 100644 index 6969391580d2..000000000000 --- a/include/linux/dma/ipu-dma.h +++ /dev/null @@ -1,174 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2008 - * Guennadi Liakhovetski, DENX Software Engineering, - * - * Copyright (C) 2005-2007 Freescale Semiconductor, Inc. - */ - -#ifndef __LINUX_DMA_IPU_DMA_H -#define __LINUX_DMA_IPU_DMA_H - -#include -#include - -/* IPU DMA Controller channel definitions. */ -enum ipu_channel { - IDMAC_IC_0 = 0, /* IC (encoding task) to memory */ - IDMAC_IC_1 = 1, /* IC (viewfinder task) to memory */ - IDMAC_ADC_0 = 1, - IDMAC_IC_2 = 2, - IDMAC_ADC_1 = 2, - IDMAC_IC_3 = 3, - IDMAC_IC_4 = 4, - IDMAC_IC_5 = 5, - IDMAC_IC_6 = 6, - IDMAC_IC_7 = 7, /* IC (sensor data) to memory */ - IDMAC_IC_8 = 8, - IDMAC_IC_9 = 9, - IDMAC_IC_10 = 10, - IDMAC_IC_11 = 11, - IDMAC_IC_12 = 12, - IDMAC_IC_13 = 13, - IDMAC_SDC_0 = 14, /* Background synchronous display data */ - IDMAC_SDC_1 = 15, /* Foreground data (overlay) */ - IDMAC_SDC_2 = 16, - IDMAC_SDC_3 = 17, - IDMAC_ADC_2 = 18, - IDMAC_ADC_3 = 19, - IDMAC_ADC_4 = 20, - IDMAC_ADC_5 = 21, - IDMAC_ADC_6 = 22, - IDMAC_ADC_7 = 23, - IDMAC_PF_0 = 24, - IDMAC_PF_1 = 25, - IDMAC_PF_2 = 26, - IDMAC_PF_3 = 27, - IDMAC_PF_4 = 28, - IDMAC_PF_5 = 29, - IDMAC_PF_6 = 30, - IDMAC_PF_7 = 31, -}; - -/* Order significant! */ -enum ipu_channel_status { - IPU_CHANNEL_FREE, - IPU_CHANNEL_INITIALIZED, - IPU_CHANNEL_READY, - IPU_CHANNEL_ENABLED, -}; - -#define IPU_CHANNELS_NUM 32 - -enum pixel_fmt { - /* 1 byte */ - IPU_PIX_FMT_GENERIC, - IPU_PIX_FMT_RGB332, - IPU_PIX_FMT_YUV420P, - IPU_PIX_FMT_YUV422P, - IPU_PIX_FMT_YUV420P2, - IPU_PIX_FMT_YVU422P, - /* 2 bytes */ - IPU_PIX_FMT_RGB565, - IPU_PIX_FMT_RGB666, - IPU_PIX_FMT_BGR666, - IPU_PIX_FMT_YUYV, - IPU_PIX_FMT_UYVY, - /* 3 bytes */ - IPU_PIX_FMT_RGB24, - IPU_PIX_FMT_BGR24, - /* 4 bytes */ - IPU_PIX_FMT_GENERIC_32, - IPU_PIX_FMT_RGB32, - IPU_PIX_FMT_BGR32, - IPU_PIX_FMT_ABGR32, - IPU_PIX_FMT_BGRA32, - IPU_PIX_FMT_RGBA32, -}; - -enum ipu_color_space { - IPU_COLORSPACE_RGB, - IPU_COLORSPACE_YCBCR, - IPU_COLORSPACE_YUV -}; - -/* - * Enumeration of IPU rotation modes - */ -enum ipu_rotate_mode { - /* Note the enum values correspond to BAM value */ - IPU_ROTATE_NONE = 0, - IPU_ROTATE_VERT_FLIP = 1, - IPU_ROTATE_HORIZ_FLIP = 2, - IPU_ROTATE_180 = 3, - IPU_ROTATE_90_RIGHT = 4, - IPU_ROTATE_90_RIGHT_VFLIP = 5, - IPU_ROTATE_90_RIGHT_HFLIP = 6, - IPU_ROTATE_90_LEFT = 7, -}; - -/* - * Enumeration of DI ports for ADC. - */ -enum display_port { - DISP0, - DISP1, - DISP2, - DISP3 -}; - -struct idmac_video_param { - unsigned short in_width; - unsigned short in_height; - uint32_t in_pixel_fmt; - unsigned short out_width; - unsigned short out_height; - uint32_t out_pixel_fmt; - unsigned short out_stride; - bool graphics_combine_en; - bool global_alpha_en; - bool key_color_en; - enum display_port disp; - unsigned short out_left; - unsigned short out_top; -}; - -/* - * Union of initialization parameters for a logical channel. So far only video - * parameters are used. - */ -union ipu_channel_param { - struct idmac_video_param video; -}; - -struct idmac_tx_desc { - struct dma_async_tx_descriptor txd; - struct scatterlist *sg; /* scatterlist for this */ - unsigned int sg_len; /* tx-descriptor. */ - struct list_head list; -}; - -struct idmac_channel { - struct dma_chan dma_chan; - dma_cookie_t completed; /* last completed cookie */ - union ipu_channel_param params; - enum ipu_channel link; /* input channel, linked to the output */ - enum ipu_channel_status status; - void *client; /* Only one client per channel */ - unsigned int n_tx_desc; - struct idmac_tx_desc *desc; /* allocated tx-descriptors */ - struct scatterlist *sg[2]; /* scatterlist elements in buffer-0 and -1 */ - struct list_head free_list; /* free tx-descriptors */ - struct list_head queue; /* queued tx-descriptors */ - spinlock_t lock; /* protects sg[0,1], queue */ - struct mutex chan_mutex; /* protects status, cookie, free_list */ - bool sec_chan_en; - int active_buffer; - unsigned int eof_irq; - char eof_name[16]; /* EOF IRQ name for request_irq() */ -}; - -#define to_tx_desc(tx) container_of(tx, struct idmac_tx_desc, txd) -#define to_idmac_chan(c) container_of(c, struct idmac_channel, dma_chan) - -#endif /* __LINUX_DMA_IPU_DMA_H */ -- cgit v1.2.3 From 73d5fc92a11cacb73a1aac0b5793c47e48c5b537 Mon Sep 17 00:00:00 2001 From: Nishad Saraf Date: Mon, 19 Aug 2024 14:19:48 -0700 Subject: dmaengine: amd: qdma: Add AMD QDMA driver Adds driver to enable PCIe board which uses AMD QDMA (the Queue-based Direct Memory Access) subsystem. For example, Xilinx Alveo V70 AI Accelerator devices. https://www.xilinx.com/applications/data-center/v70.html The QDMA subsystem is used in conjunction with the PCI Express IP block to provide high performance data transfer between host memory and the card's DMA subsystem. +-------+ +-------+ +-----------+ PCIe | | | | | | Tx/Rx | | | | AXI | | <=======> | PCIE | <===> | QDMA | <====>| User Logic| | | | | | | +-------+ +-------+ +-----------+ The primary mechanism to transfer data using the QDMA is for the QDMA engine to operate on instructions (descriptors) provided by the host operating system. Using the descriptors, the QDMA can move data in both the Host to Card (H2C) direction, or the Card to Host (C2H) direction. The QDMA provides a per-queue basis option whether DMA traffic goes to an AXI4 memory map (MM) interface or to an AXI4-Stream interface. The hardware detail is provided by https://docs.xilinx.com/r/en-US/pg302-qdma Implements dmaengine APIs to support MM DMA transfers. - probe the available DMA channels - use dma_slave_map for channel lookup - use virtual channel to manage dmaengine tx descriptors - implement device_prep_slave_sg callback to handle host scatter gather list Signed-off-by: Nishad Saraf Signed-off-by: Lizhi Hou Link: https://lore.kernel.org/r/20240819211948.688786-2-lizhi.hou@amd.com Signed-off-by: Vinod Koul --- MAINTAINERS | 8 + drivers/dma/Kconfig | 2 + drivers/dma/Makefile | 1 + drivers/dma/amd/Kconfig | 14 + drivers/dma/amd/Makefile | 3 + drivers/dma/amd/qdma/Makefile | 5 + drivers/dma/amd/qdma/qdma-comm-regs.c | 64 ++ drivers/dma/amd/qdma/qdma.c | 1143 ++++++++++++++++++++++++++++++++ drivers/dma/amd/qdma/qdma.h | 266 ++++++++ include/linux/platform_data/amd_qdma.h | 36 + 10 files changed, 1542 insertions(+) create mode 100644 drivers/dma/amd/Kconfig create mode 100644 drivers/dma/amd/Makefile create mode 100644 drivers/dma/amd/qdma/Makefile create mode 100644 drivers/dma/amd/qdma/qdma-comm-regs.c create mode 100644 drivers/dma/amd/qdma/qdma.c create mode 100644 drivers/dma/amd/qdma/qdma.h create mode 100644 include/linux/platform_data/amd_qdma.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 42decde38320..a9154c66795b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1128,6 +1128,14 @@ L: dmaengine@vger.kernel.org S: Maintained F: drivers/dma/ptdma/ +AMD QDMA DRIVER +M: Nishad Saraf +M: Lizhi Hou +L: dmaengine@vger.kernel.org +S: Supported +F: drivers/dma/amd/qdma/ +F: include/linux/platform_data/amd_qdma.h + AMD SEATTLE DEVICE TREE SUPPORT M: Suravee Suthikulpanit M: Tom Lendacky diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index cc0a62c34861..dbb75d35d767 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -716,6 +716,8 @@ config XILINX_ZYNQMP_DPDMA display driver. # driver files +source "drivers/dma/amd/Kconfig" + source "drivers/dma/bestcomm/Kconfig" source "drivers/dma/mediatek/Kconfig" diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile index 374ea98faf43..29c99bf9fd37 100644 --- a/drivers/dma/Makefile +++ b/drivers/dma/Makefile @@ -83,6 +83,7 @@ obj-$(CONFIG_ST_FDMA) += st_fdma.o obj-$(CONFIG_FSL_DPAA2_QDMA) += fsl-dpaa2-qdma/ obj-$(CONFIG_INTEL_LDMA) += lgm/ +obj-y += amd/ obj-y += mediatek/ obj-y += qcom/ obj-y += stm32/ diff --git a/drivers/dma/amd/Kconfig b/drivers/dma/amd/Kconfig new file mode 100644 index 000000000000..7d1f51d69675 --- /dev/null +++ b/drivers/dma/amd/Kconfig @@ -0,0 +1,14 @@ +# SPDX-License-Identifier: GPL-2.0-only + +config AMD_QDMA + tristate "AMD Queue-based DMA" + depends on HAS_IOMEM + select DMA_ENGINE + select DMA_VIRTUAL_CHANNELS + select REGMAP_MMIO + help + Enable support for the AMD Queue-based DMA subsystem. The primary + mechanism to transfer data using the QDMA is for the QDMA engine to + operate on instructions (descriptors) provided by the host operating + system. Using the descriptors, the QDMA can move data in either the + Host to Card (H2C) direction or the Card to Host (C2H) direction. diff --git a/drivers/dma/amd/Makefile b/drivers/dma/amd/Makefile new file mode 100644 index 000000000000..37212be9364f --- /dev/null +++ b/drivers/dma/amd/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_AMD_QDMA) += qdma/ diff --git a/drivers/dma/amd/qdma/Makefile b/drivers/dma/amd/qdma/Makefile new file mode 100644 index 000000000000..011268fef377 --- /dev/null +++ b/drivers/dma/amd/qdma/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_AMD_QDMA) += amd-qdma.o + +amd-qdma-$(CONFIG_AMD_QDMA) := qdma.o qdma-comm-regs.o diff --git a/drivers/dma/amd/qdma/qdma-comm-regs.c b/drivers/dma/amd/qdma/qdma-comm-regs.c new file mode 100644 index 000000000000..9162f9d367cc --- /dev/null +++ b/drivers/dma/amd/qdma/qdma-comm-regs.c @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2023-2024, Advanced Micro Devices, Inc. + */ + +#ifndef __QDMA_REGS_DEF_H +#define __QDMA_REGS_DEF_H + +#include "qdma.h" + +const struct qdma_reg qdma_regos_default[QDMA_REGO_MAX] = { + [QDMA_REGO_CTXT_DATA] = QDMA_REGO(0x804, 8), + [QDMA_REGO_CTXT_CMD] = QDMA_REGO(0x844, 1), + [QDMA_REGO_CTXT_MASK] = QDMA_REGO(0x824, 8), + [QDMA_REGO_MM_H2C_CTRL] = QDMA_REGO(0x1004, 1), + [QDMA_REGO_MM_C2H_CTRL] = QDMA_REGO(0x1204, 1), + [QDMA_REGO_QUEUE_COUNT] = QDMA_REGO(0x120, 1), + [QDMA_REGO_RING_SIZE] = QDMA_REGO(0x204, 1), + [QDMA_REGO_H2C_PIDX] = QDMA_REGO(0x18004, 1), + [QDMA_REGO_C2H_PIDX] = QDMA_REGO(0x18008, 1), + [QDMA_REGO_INTR_CIDX] = QDMA_REGO(0x18000, 1), + [QDMA_REGO_FUNC_ID] = QDMA_REGO(0x12c, 1), + [QDMA_REGO_ERR_INT] = QDMA_REGO(0xb04, 1), + [QDMA_REGO_ERR_STAT] = QDMA_REGO(0x248, 1), +}; + +const struct qdma_reg_field qdma_regfs_default[QDMA_REGF_MAX] = { + /* QDMA_REGO_CTXT_DATA fields */ + [QDMA_REGF_IRQ_ENABLE] = QDMA_REGF(53, 53), + [QDMA_REGF_WBK_ENABLE] = QDMA_REGF(52, 52), + [QDMA_REGF_WBI_CHECK] = QDMA_REGF(34, 34), + [QDMA_REGF_IRQ_ARM] = QDMA_REGF(16, 16), + [QDMA_REGF_IRQ_VEC] = QDMA_REGF(138, 128), + [QDMA_REGF_IRQ_AGG] = QDMA_REGF(139, 139), + [QDMA_REGF_WBI_INTVL_ENABLE] = QDMA_REGF(35, 35), + [QDMA_REGF_MRKR_DISABLE] = QDMA_REGF(62, 62), + [QDMA_REGF_QUEUE_ENABLE] = QDMA_REGF(32, 32), + [QDMA_REGF_QUEUE_MODE] = QDMA_REGF(63, 63), + [QDMA_REGF_DESC_BASE] = QDMA_REGF(127, 64), + [QDMA_REGF_DESC_SIZE] = QDMA_REGF(49, 48), + [QDMA_REGF_RING_ID] = QDMA_REGF(47, 44), + [QDMA_REGF_QUEUE_BASE] = QDMA_REGF(11, 0), + [QDMA_REGF_QUEUE_MAX] = QDMA_REGF(44, 32), + [QDMA_REGF_FUNCTION_ID] = QDMA_REGF(24, 17), + [QDMA_REGF_INTR_AGG_BASE] = QDMA_REGF(66, 15), + [QDMA_REGF_INTR_VECTOR] = QDMA_REGF(11, 1), + [QDMA_REGF_INTR_SIZE] = QDMA_REGF(69, 67), + [QDMA_REGF_INTR_VALID] = QDMA_REGF(0, 0), + [QDMA_REGF_INTR_COLOR] = QDMA_REGF(14, 14), + [QDMA_REGF_INTR_FUNCTION_ID] = QDMA_REGF(125, 114), + /* QDMA_REGO_CTXT_CMD fields */ + [QDMA_REGF_CMD_INDX] = QDMA_REGF(19, 7), + [QDMA_REGF_CMD_CMD] = QDMA_REGF(6, 5), + [QDMA_REGF_CMD_TYPE] = QDMA_REGF(4, 1), + [QDMA_REGF_CMD_BUSY] = QDMA_REGF(0, 0), + /* QDMA_REGO_QUEUE_COUNT fields */ + [QDMA_REGF_QUEUE_COUNT] = QDMA_REGF(11, 0), + /* QDMA_REGO_ERR_INT fields */ + [QDMA_REGF_ERR_INT_FUNC] = QDMA_REGF(11, 0), + [QDMA_REGF_ERR_INT_VEC] = QDMA_REGF(22, 12), + [QDMA_REGF_ERR_INT_ARM] = QDMA_REGF(24, 24), +}; + +#endif /* __QDMA_REGS_DEF_H */ diff --git a/drivers/dma/amd/qdma/qdma.c b/drivers/dma/amd/qdma/qdma.c new file mode 100644 index 000000000000..b0a1f3ad851b --- /dev/null +++ b/drivers/dma/amd/qdma/qdma.c @@ -0,0 +1,1143 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * DMA driver for AMD Queue-based DMA Subsystem + * + * Copyright (C) 2023-2024, Advanced Micro Devices, Inc. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "qdma.h" + +#define CHAN_STR(q) (((q)->dir == DMA_MEM_TO_DEV) ? "H2C" : "C2H") +#define QDMA_REG_OFF(d, r) ((d)->roffs[r].off) + +/* MMIO regmap config for all QDMA registers */ +static const struct regmap_config qdma_regmap_config = { + .reg_bits = 32, + .val_bits = 32, + .reg_stride = 4, +}; + +static inline struct qdma_queue *to_qdma_queue(struct dma_chan *chan) +{ + return container_of(chan, struct qdma_queue, vchan.chan); +} + +static inline struct qdma_mm_vdesc *to_qdma_vdesc(struct virt_dma_desc *vdesc) +{ + return container_of(vdesc, struct qdma_mm_vdesc, vdesc); +} + +static inline u32 qdma_get_intr_ring_idx(struct qdma_device *qdev) +{ + u32 idx; + + idx = qdev->qintr_rings[qdev->qintr_ring_idx++].ridx; + qdev->qintr_ring_idx %= qdev->qintr_ring_num; + + return idx; +} + +static u64 qdma_get_field(const struct qdma_device *qdev, const u32 *data, + enum qdma_reg_fields field) +{ + const struct qdma_reg_field *f = &qdev->rfields[field]; + u16 low_pos, hi_pos, low_bit, hi_bit; + u64 value = 0, mask; + + low_pos = f->lsb / BITS_PER_TYPE(*data); + hi_pos = f->msb / BITS_PER_TYPE(*data); + + if (low_pos == hi_pos) { + low_bit = f->lsb % BITS_PER_TYPE(*data); + hi_bit = f->msb % BITS_PER_TYPE(*data); + mask = GENMASK(hi_bit, low_bit); + value = (data[low_pos] & mask) >> low_bit; + } else if (hi_pos == low_pos + 1) { + low_bit = f->lsb % BITS_PER_TYPE(*data); + hi_bit = low_bit + (f->msb - f->lsb); + value = ((u64)data[hi_pos] << BITS_PER_TYPE(*data)) | + data[low_pos]; + mask = GENMASK_ULL(hi_bit, low_bit); + value = (value & mask) >> low_bit; + } else { + hi_bit = f->msb % BITS_PER_TYPE(*data); + mask = GENMASK(hi_bit, 0); + value = data[hi_pos] & mask; + low_bit = f->msb - f->lsb - hi_bit; + value <<= low_bit; + low_bit -= 32; + value |= (u64)data[hi_pos - 1] << low_bit; + mask = GENMASK(31, 32 - low_bit); + value |= (data[hi_pos - 2] & mask) >> low_bit; + } + + return value; +} + +static void qdma_set_field(const struct qdma_device *qdev, u32 *data, + enum qdma_reg_fields field, u64 value) +{ + const struct qdma_reg_field *f = &qdev->rfields[field]; + u16 low_pos, hi_pos, low_bit; + + low_pos = f->lsb / BITS_PER_TYPE(*data); + hi_pos = f->msb / BITS_PER_TYPE(*data); + low_bit = f->lsb % BITS_PER_TYPE(*data); + + data[low_pos++] |= value << low_bit; + if (low_pos <= hi_pos) + data[low_pos++] |= (u32)(value >> (32 - low_bit)); + if (low_pos <= hi_pos) + data[low_pos] |= (u32)(value >> (64 - low_bit)); +} + +static inline int qdma_reg_write(const struct qdma_device *qdev, + const u32 *data, enum qdma_regs reg) +{ + const struct qdma_reg *r = &qdev->roffs[reg]; + int ret; + + if (r->count > 1) + ret = regmap_bulk_write(qdev->regmap, r->off, data, r->count); + else + ret = regmap_write(qdev->regmap, r->off, *data); + + return ret; +} + +static inline int qdma_reg_read(const struct qdma_device *qdev, u32 *data, + enum qdma_regs reg) +{ + const struct qdma_reg *r = &qdev->roffs[reg]; + int ret; + + if (r->count > 1) + ret = regmap_bulk_read(qdev->regmap, r->off, data, r->count); + else + ret = regmap_read(qdev->regmap, r->off, data); + + return ret; +} + +static int qdma_context_cmd_execute(const struct qdma_device *qdev, + enum qdma_ctxt_type type, + enum qdma_ctxt_cmd cmd, u16 index) +{ + u32 value = 0; + int ret; + + qdma_set_field(qdev, &value, QDMA_REGF_CMD_INDX, index); + qdma_set_field(qdev, &value, QDMA_REGF_CMD_CMD, cmd); + qdma_set_field(qdev, &value, QDMA_REGF_CMD_TYPE, type); + + ret = qdma_reg_write(qdev, &value, QDMA_REGO_CTXT_CMD); + if (ret) + return ret; + + ret = regmap_read_poll_timeout(qdev->regmap, + QDMA_REG_OFF(qdev, QDMA_REGO_CTXT_CMD), + value, + !qdma_get_field(qdev, &value, + QDMA_REGF_CMD_BUSY), + QDMA_POLL_INTRVL_US, + QDMA_POLL_TIMEOUT_US); + if (ret) { + qdma_err(qdev, "Context command execution timed out"); + return ret; + } + + return 0; +} + +static int qdma_context_write_data(const struct qdma_device *qdev, + const u32 *data) +{ + u32 mask[QDMA_CTXT_REGMAP_LEN]; + int ret; + + memset(mask, ~0, sizeof(mask)); + + ret = qdma_reg_write(qdev, mask, QDMA_REGO_CTXT_MASK); + if (ret) + return ret; + + ret = qdma_reg_write(qdev, data, QDMA_REGO_CTXT_DATA); + if (ret) + return ret; + + return 0; +} + +static void qdma_prep_sw_desc_context(const struct qdma_device *qdev, + const struct qdma_ctxt_sw_desc *ctxt, + u32 *data) +{ + memset(data, 0, QDMA_CTXT_REGMAP_LEN * sizeof(*data)); + qdma_set_field(qdev, data, QDMA_REGF_DESC_BASE, ctxt->desc_base); + qdma_set_field(qdev, data, QDMA_REGF_IRQ_VEC, ctxt->vec); + qdma_set_field(qdev, data, QDMA_REGF_FUNCTION_ID, qdev->fid); + + qdma_set_field(qdev, data, QDMA_REGF_DESC_SIZE, QDMA_DESC_SIZE_32B); + qdma_set_field(qdev, data, QDMA_REGF_RING_ID, QDMA_DEFAULT_RING_ID); + qdma_set_field(qdev, data, QDMA_REGF_QUEUE_MODE, QDMA_QUEUE_OP_MM); + qdma_set_field(qdev, data, QDMA_REGF_IRQ_ENABLE, 1); + qdma_set_field(qdev, data, QDMA_REGF_WBK_ENABLE, 1); + qdma_set_field(qdev, data, QDMA_REGF_WBI_CHECK, 1); + qdma_set_field(qdev, data, QDMA_REGF_IRQ_ARM, 1); + qdma_set_field(qdev, data, QDMA_REGF_IRQ_AGG, 1); + qdma_set_field(qdev, data, QDMA_REGF_WBI_INTVL_ENABLE, 1); + qdma_set_field(qdev, data, QDMA_REGF_QUEUE_ENABLE, 1); + qdma_set_field(qdev, data, QDMA_REGF_MRKR_DISABLE, 1); +} + +static void qdma_prep_intr_context(const struct qdma_device *qdev, + const struct qdma_ctxt_intr *ctxt, + u32 *data) +{ + memset(data, 0, QDMA_CTXT_REGMAP_LEN * sizeof(*data)); + qdma_set_field(qdev, data, QDMA_REGF_INTR_AGG_BASE, ctxt->agg_base); + qdma_set_field(qdev, data, QDMA_REGF_INTR_VECTOR, ctxt->vec); + qdma_set_field(qdev, data, QDMA_REGF_INTR_SIZE, ctxt->size); + qdma_set_field(qdev, data, QDMA_REGF_INTR_VALID, ctxt->valid); + qdma_set_field(qdev, data, QDMA_REGF_INTR_COLOR, ctxt->color); + qdma_set_field(qdev, data, QDMA_REGF_INTR_FUNCTION_ID, qdev->fid); +} + +static void qdma_prep_fmap_context(const struct qdma_device *qdev, + const struct qdma_ctxt_fmap *ctxt, + u32 *data) +{ + memset(data, 0, QDMA_CTXT_REGMAP_LEN * sizeof(*data)); + qdma_set_field(qdev, data, QDMA_REGF_QUEUE_BASE, ctxt->qbase); + qdma_set_field(qdev, data, QDMA_REGF_QUEUE_MAX, ctxt->qmax); +} + +/* + * Program the indirect context register space + * + * Once the queue is enabled, context is dynamically updated by hardware. Any + * modification of the context through this API when the queue is enabled can + * result in unexpected behavior. Reading the context when the queue is enabled + * is not recommended as it can result in reduced performance. + */ +static int qdma_prog_context(struct qdma_device *qdev, enum qdma_ctxt_type type, + enum qdma_ctxt_cmd cmd, u16 index, u32 *ctxt) +{ + int ret; + + mutex_lock(&qdev->ctxt_lock); + if (cmd == QDMA_CTXT_WRITE) { + ret = qdma_context_write_data(qdev, ctxt); + if (ret) + goto failed; + } + + ret = qdma_context_cmd_execute(qdev, type, cmd, index); + if (ret) + goto failed; + + if (cmd == QDMA_CTXT_READ) { + ret = qdma_reg_read(qdev, ctxt, QDMA_REGO_CTXT_DATA); + if (ret) + goto failed; + } + +failed: + mutex_unlock(&qdev->ctxt_lock); + + return ret; +} + +static int qdma_check_queue_status(struct qdma_device *qdev, + enum dma_transfer_direction dir, u16 qid) +{ + u32 status, data[QDMA_CTXT_REGMAP_LEN] = {0}; + enum qdma_ctxt_type type; + int ret; + + if (dir == DMA_MEM_TO_DEV) + type = QDMA_CTXT_DESC_SW_H2C; + else + type = QDMA_CTXT_DESC_SW_C2H; + ret = qdma_prog_context(qdev, type, QDMA_CTXT_READ, qid, data); + if (ret) + return ret; + + status = qdma_get_field(qdev, data, QDMA_REGF_QUEUE_ENABLE); + if (status) { + qdma_err(qdev, "queue %d already in use", qid); + return -EBUSY; + } + + return 0; +} + +static int qdma_clear_queue_context(const struct qdma_queue *queue) +{ + enum qdma_ctxt_type h2c_types[] = { QDMA_CTXT_DESC_SW_H2C, + QDMA_CTXT_DESC_HW_H2C, + QDMA_CTXT_DESC_CR_H2C, + QDMA_CTXT_PFTCH, }; + enum qdma_ctxt_type c2h_types[] = { QDMA_CTXT_DESC_SW_C2H, + QDMA_CTXT_DESC_HW_C2H, + QDMA_CTXT_DESC_CR_C2H, + QDMA_CTXT_PFTCH, }; + struct qdma_device *qdev = queue->qdev; + enum qdma_ctxt_type *type; + int ret, num, i; + + if (queue->dir == DMA_MEM_TO_DEV) { + type = h2c_types; + num = ARRAY_SIZE(h2c_types); + } else { + type = c2h_types; + num = ARRAY_SIZE(c2h_types); + } + for (i = 0; i < num; i++) { + ret = qdma_prog_context(qdev, type[i], QDMA_CTXT_CLEAR, + queue->qid, NULL); + if (ret) { + qdma_err(qdev, "Failed to clear ctxt %d", type[i]); + return ret; + } + } + + return 0; +} + +static int qdma_setup_fmap_context(struct qdma_device *qdev) +{ + u32 ctxt[QDMA_CTXT_REGMAP_LEN]; + struct qdma_ctxt_fmap fmap; + int ret; + + ret = qdma_prog_context(qdev, QDMA_CTXT_FMAP, QDMA_CTXT_CLEAR, + qdev->fid, NULL); + if (ret) { + qdma_err(qdev, "Failed clearing context"); + return ret; + } + + fmap.qbase = 0; + fmap.qmax = qdev->chan_num * 2; + qdma_prep_fmap_context(qdev, &fmap, ctxt); + ret = qdma_prog_context(qdev, QDMA_CTXT_FMAP, QDMA_CTXT_WRITE, + qdev->fid, ctxt); + if (ret) + qdma_err(qdev, "Failed setup fmap, ret %d", ret); + + return ret; +} + +static int qdma_setup_queue_context(struct qdma_device *qdev, + const struct qdma_ctxt_sw_desc *sw_desc, + enum dma_transfer_direction dir, u16 qid) +{ + u32 ctxt[QDMA_CTXT_REGMAP_LEN]; + enum qdma_ctxt_type type; + int ret; + + if (dir == DMA_MEM_TO_DEV) + type = QDMA_CTXT_DESC_SW_H2C; + else + type = QDMA_CTXT_DESC_SW_C2H; + + qdma_prep_sw_desc_context(qdev, sw_desc, ctxt); + /* Setup SW descriptor context */ + ret = qdma_prog_context(qdev, type, QDMA_CTXT_WRITE, qid, ctxt); + if (ret) + qdma_err(qdev, "Failed setup SW desc ctxt for queue: %d", qid); + + return ret; +} + +/* + * Enable or disable memory-mapped DMA engines + * 1: enable, 0: disable + */ +static int qdma_sgdma_control(struct qdma_device *qdev, u32 ctrl) +{ + int ret; + + ret = qdma_reg_write(qdev, &ctrl, QDMA_REGO_MM_H2C_CTRL); + ret |= qdma_reg_write(qdev, &ctrl, QDMA_REGO_MM_C2H_CTRL); + + return ret; +} + +static int qdma_get_hw_info(struct qdma_device *qdev) +{ + struct qdma_platdata *pdata = dev_get_platdata(&qdev->pdev->dev); + u32 value = 0; + int ret; + + ret = qdma_reg_read(qdev, &value, QDMA_REGO_QUEUE_COUNT); + if (ret) + return ret; + + value = qdma_get_field(qdev, &value, QDMA_REGF_QUEUE_COUNT) + 1; + if (pdata->max_mm_channels * 2 > value) { + qdma_err(qdev, "not enough hw queues %d", value); + return -EINVAL; + } + qdev->chan_num = pdata->max_mm_channels; + + ret = qdma_reg_read(qdev, &qdev->fid, QDMA_REGO_FUNC_ID); + if (ret) + return ret; + + qdma_info(qdev, "max channel %d, function id %d", + qdev->chan_num, qdev->fid); + + return 0; +} + +static inline int qdma_update_pidx(const struct qdma_queue *queue, u16 pidx) +{ + struct qdma_device *qdev = queue->qdev; + + return regmap_write(qdev->regmap, queue->pidx_reg, + pidx | QDMA_QUEUE_ARM_BIT); +} + +static inline int qdma_update_cidx(const struct qdma_queue *queue, + u16 ridx, u16 cidx) +{ + struct qdma_device *qdev = queue->qdev; + + return regmap_write(qdev->regmap, queue->cidx_reg, + ((u32)ridx << 16) | cidx); +} + +/** + * qdma_free_vdesc - Free descriptor + * @vdesc: Virtual DMA descriptor + */ +static void qdma_free_vdesc(struct virt_dma_desc *vdesc) +{ + struct qdma_mm_vdesc *vd = to_qdma_vdesc(vdesc); + + kfree(vd); +} + +static int qdma_alloc_queues(struct qdma_device *qdev, + enum dma_transfer_direction dir) +{ + struct qdma_queue *q, **queues; + u32 i, pidx_base; + int ret; + + if (dir == DMA_MEM_TO_DEV) { + queues = &qdev->h2c_queues; + pidx_base = QDMA_REG_OFF(qdev, QDMA_REGO_H2C_PIDX); + } else { + queues = &qdev->c2h_queues; + pidx_base = QDMA_REG_OFF(qdev, QDMA_REGO_C2H_PIDX); + } + + *queues = devm_kcalloc(&qdev->pdev->dev, qdev->chan_num, sizeof(*q), + GFP_KERNEL); + if (!*queues) + return -ENOMEM; + + for (i = 0; i < qdev->chan_num; i++) { + ret = qdma_check_queue_status(qdev, dir, i); + if (ret) + return ret; + + q = &(*queues)[i]; + q->ring_size = QDMA_DEFAULT_RING_SIZE; + q->idx_mask = q->ring_size - 2; + q->qdev = qdev; + q->dir = dir; + q->qid = i; + q->pidx_reg = pidx_base + i * QDMA_DMAP_REG_STRIDE; + q->cidx_reg = QDMA_REG_OFF(qdev, QDMA_REGO_INTR_CIDX) + + i * QDMA_DMAP_REG_STRIDE; + q->vchan.desc_free = qdma_free_vdesc; + vchan_init(&q->vchan, &qdev->dma_dev); + } + + return 0; +} + +static int qdma_device_verify(struct qdma_device *qdev) +{ + u32 value; + int ret; + + ret = regmap_read(qdev->regmap, QDMA_IDENTIFIER_REGOFF, &value); + if (ret) + return ret; + + value = FIELD_GET(QDMA_IDENTIFIER_MASK, value); + if (value != QDMA_IDENTIFIER) { + qdma_err(qdev, "Invalid identifier"); + return -ENODEV; + } + qdev->rfields = qdma_regfs_default; + qdev->roffs = qdma_regos_default; + + return 0; +} + +static int qdma_device_setup(struct qdma_device *qdev) +{ + struct device *dev = &qdev->pdev->dev; + u32 ring_sz = QDMA_DEFAULT_RING_SIZE; + int ret = 0; + + while (dev && get_dma_ops(dev)) + dev = dev->parent; + if (!dev) { + qdma_err(qdev, "dma device not found"); + return -EINVAL; + } + set_dma_ops(&qdev->pdev->dev, get_dma_ops(dev)); + + ret = qdma_setup_fmap_context(qdev); + if (ret) { + qdma_err(qdev, "Failed setup fmap context"); + return ret; + } + + /* Setup global ring buffer size at QDMA_DEFAULT_RING_ID index */ + ret = qdma_reg_write(qdev, &ring_sz, QDMA_REGO_RING_SIZE); + if (ret) { + qdma_err(qdev, "Failed to setup ring %d of size %ld", + QDMA_DEFAULT_RING_ID, QDMA_DEFAULT_RING_SIZE); + return ret; + } + + /* Enable memory-mapped DMA engine in both directions */ + ret = qdma_sgdma_control(qdev, 1); + if (ret) { + qdma_err(qdev, "Failed to SGDMA with error %d", ret); + return ret; + } + + ret = qdma_alloc_queues(qdev, DMA_MEM_TO_DEV); + if (ret) { + qdma_err(qdev, "Failed to alloc H2C queues, ret %d", ret); + return ret; + } + + ret = qdma_alloc_queues(qdev, DMA_DEV_TO_MEM); + if (ret) { + qdma_err(qdev, "Failed to alloc C2H queues, ret %d", ret); + return ret; + } + + return 0; +} + +/** + * qdma_free_queue_resources() - Free queue resources + * @chan: DMA channel + */ +static void qdma_free_queue_resources(struct dma_chan *chan) +{ + struct qdma_queue *queue = to_qdma_queue(chan); + struct qdma_device *qdev = queue->qdev; + struct device *dev = qdev->dma_dev.dev; + + qdma_clear_queue_context(queue); + vchan_free_chan_resources(&queue->vchan); + dma_free_coherent(dev, queue->ring_size * QDMA_MM_DESC_SIZE, + queue->desc_base, queue->dma_desc_base); +} + +/** + * qdma_alloc_queue_resources() - Allocate queue resources + * @chan: DMA channel + */ +static int qdma_alloc_queue_resources(struct dma_chan *chan) +{ + struct qdma_queue *queue = to_qdma_queue(chan); + struct qdma_device *qdev = queue->qdev; + struct qdma_ctxt_sw_desc desc; + size_t size; + int ret; + + ret = qdma_clear_queue_context(queue); + if (ret) + return ret; + + size = queue->ring_size * QDMA_MM_DESC_SIZE; + queue->desc_base = dma_alloc_coherent(qdev->dma_dev.dev, size, + &queue->dma_desc_base, + GFP_KERNEL); + if (!queue->desc_base) { + qdma_err(qdev, "Failed to allocate descriptor ring"); + return -ENOMEM; + } + + /* Setup SW descriptor queue context for DMA memory map */ + desc.vec = qdma_get_intr_ring_idx(qdev); + desc.desc_base = queue->dma_desc_base; + ret = qdma_setup_queue_context(qdev, &desc, queue->dir, queue->qid); + if (ret) { + qdma_err(qdev, "Failed to setup SW desc ctxt for %s", + chan->name); + dma_free_coherent(qdev->dma_dev.dev, size, queue->desc_base, + queue->dma_desc_base); + return ret; + } + + queue->pidx = 0; + queue->cidx = 0; + + return 0; +} + +static bool qdma_filter_fn(struct dma_chan *chan, void *param) +{ + struct qdma_queue *queue = to_qdma_queue(chan); + struct qdma_queue_info *info = param; + + return info->dir == queue->dir; +} + +static int qdma_xfer_start(struct qdma_queue *queue) +{ + struct qdma_device *qdev = queue->qdev; + int ret; + + if (!vchan_next_desc(&queue->vchan)) + return 0; + + qdma_dbg(qdev, "Tnx kickoff with P: %d for %s%d", + queue->issued_vdesc->pidx, CHAN_STR(queue), queue->qid); + + ret = qdma_update_pidx(queue, queue->issued_vdesc->pidx); + if (ret) { + qdma_err(qdev, "Failed to update PIDX to %d for %s queue: %d", + queue->pidx, CHAN_STR(queue), queue->qid); + } + + return ret; +} + +static void qdma_issue_pending(struct dma_chan *chan) +{ + struct qdma_queue *queue = to_qdma_queue(chan); + unsigned long flags; + + spin_lock_irqsave(&queue->vchan.lock, flags); + if (vchan_issue_pending(&queue->vchan)) { + if (queue->submitted_vdesc) { + queue->issued_vdesc = queue->submitted_vdesc; + queue->submitted_vdesc = NULL; + } + qdma_xfer_start(queue); + } + + spin_unlock_irqrestore(&queue->vchan.lock, flags); +} + +static struct qdma_mm_desc *qdma_get_desc(struct qdma_queue *q) +{ + struct qdma_mm_desc *desc; + + if (((q->pidx + 1) & q->idx_mask) == q->cidx) + return NULL; + + desc = q->desc_base + q->pidx; + q->pidx = (q->pidx + 1) & q->idx_mask; + + return desc; +} + +static int qdma_hw_enqueue(struct qdma_queue *q, struct qdma_mm_vdesc *vdesc) +{ + struct qdma_mm_desc *desc; + struct scatterlist *sg; + u64 addr, *src, *dst; + u32 rest, len; + int ret = 0; + u32 i; + + if (!vdesc->sg_len) + return 0; + + if (q->dir == DMA_MEM_TO_DEV) { + dst = &vdesc->dev_addr; + src = &addr; + } else { + dst = &addr; + src = &vdesc->dev_addr; + } + + for_each_sg(vdesc->sgl, sg, vdesc->sg_len, i) { + addr = sg_dma_address(sg) + vdesc->sg_off; + rest = sg_dma_len(sg) - vdesc->sg_off; + while (rest) { + len = min_t(u32, rest, QDMA_MM_DESC_MAX_LEN); + desc = qdma_get_desc(q); + if (!desc) { + ret = -EBUSY; + goto out; + } + + desc->src_addr = cpu_to_le64(*src); + desc->dst_addr = cpu_to_le64(*dst); + desc->len = cpu_to_le32(len); + + vdesc->dev_addr += len; + vdesc->sg_off += len; + vdesc->pending_descs++; + addr += len; + rest -= len; + } + vdesc->sg_off = 0; + } +out: + vdesc->sg_len -= i; + vdesc->pidx = q->pidx; + return ret; +} + +static void qdma_fill_pending_vdesc(struct qdma_queue *q) +{ + struct virt_dma_chan *vc = &q->vchan; + struct qdma_mm_vdesc *vdesc = NULL; + struct virt_dma_desc *vd; + int ret; + + if (!list_empty(&vc->desc_issued)) { + vd = &q->issued_vdesc->vdesc; + list_for_each_entry_from(vd, &vc->desc_issued, node) { + vdesc = to_qdma_vdesc(vd); + ret = qdma_hw_enqueue(q, vdesc); + if (ret) { + q->issued_vdesc = vdesc; + return; + } + } + q->issued_vdesc = vdesc; + } + + if (list_empty(&vc->desc_submitted)) + return; + + if (q->submitted_vdesc) + vd = &q->submitted_vdesc->vdesc; + else + vd = list_first_entry(&vc->desc_submitted, typeof(*vd), node); + + list_for_each_entry_from(vd, &vc->desc_submitted, node) { + vdesc = to_qdma_vdesc(vd); + ret = qdma_hw_enqueue(q, vdesc); + if (ret) + break; + } + q->submitted_vdesc = vdesc; +} + +static dma_cookie_t qdma_tx_submit(struct dma_async_tx_descriptor *tx) +{ + struct virt_dma_chan *vc = to_virt_chan(tx->chan); + struct qdma_queue *q = to_qdma_queue(&vc->chan); + struct virt_dma_desc *vd; + unsigned long flags; + dma_cookie_t cookie; + + vd = container_of(tx, struct virt_dma_desc, tx); + spin_lock_irqsave(&vc->lock, flags); + cookie = dma_cookie_assign(tx); + + list_move_tail(&vd->node, &vc->desc_submitted); + qdma_fill_pending_vdesc(q); + spin_unlock_irqrestore(&vc->lock, flags); + + return cookie; +} + +static struct dma_async_tx_descriptor * +qdma_prep_device_sg(struct dma_chan *chan, struct scatterlist *sgl, + unsigned int sg_len, enum dma_transfer_direction dir, + unsigned long flags, void *context) +{ + struct qdma_queue *q = to_qdma_queue(chan); + struct dma_async_tx_descriptor *tx; + struct qdma_mm_vdesc *vdesc; + + vdesc = kzalloc(sizeof(*vdesc), GFP_NOWAIT); + if (!vdesc) + return NULL; + vdesc->sgl = sgl; + vdesc->sg_len = sg_len; + if (dir == DMA_MEM_TO_DEV) + vdesc->dev_addr = q->cfg.dst_addr; + else + vdesc->dev_addr = q->cfg.src_addr; + + tx = vchan_tx_prep(&q->vchan, &vdesc->vdesc, flags); + tx->tx_submit = qdma_tx_submit; + + return tx; +} + +static int qdma_device_config(struct dma_chan *chan, + struct dma_slave_config *cfg) +{ + struct qdma_queue *q = to_qdma_queue(chan); + + memcpy(&q->cfg, cfg, sizeof(*cfg)); + + return 0; +} + +static int qdma_arm_err_intr(const struct qdma_device *qdev) +{ + u32 value = 0; + + qdma_set_field(qdev, &value, QDMA_REGF_ERR_INT_FUNC, qdev->fid); + qdma_set_field(qdev, &value, QDMA_REGF_ERR_INT_VEC, qdev->err_irq_idx); + qdma_set_field(qdev, &value, QDMA_REGF_ERR_INT_ARM, 1); + + return qdma_reg_write(qdev, &value, QDMA_REGO_ERR_INT); +} + +static irqreturn_t qdma_error_isr(int irq, void *data) +{ + struct qdma_device *qdev = data; + u32 err_stat = 0; + int ret; + + ret = qdma_reg_read(qdev, &err_stat, QDMA_REGO_ERR_STAT); + if (ret) { + qdma_err(qdev, "read error state failed, ret %d", ret); + goto out; + } + + qdma_err(qdev, "global error %d", err_stat); + ret = qdma_reg_write(qdev, &err_stat, QDMA_REGO_ERR_STAT); + if (ret) + qdma_err(qdev, "clear error state failed, ret %d", ret); + +out: + qdma_arm_err_intr(qdev); + return IRQ_HANDLED; +} + +static irqreturn_t qdma_queue_isr(int irq, void *data) +{ + struct qdma_intr_ring *intr = data; + struct qdma_queue *q = NULL; + struct qdma_device *qdev; + u32 index, comp_desc; + u64 intr_ent; + u8 color; + int ret; + u16 qid; + + qdev = intr->qdev; + index = intr->cidx; + while (1) { + struct virt_dma_desc *vd; + struct qdma_mm_vdesc *vdesc; + unsigned long flags; + u32 cidx; + + intr_ent = le64_to_cpu(intr->base[index]); + color = FIELD_GET(QDMA_INTR_MASK_COLOR, intr_ent); + if (color != intr->color) + break; + + qid = FIELD_GET(QDMA_INTR_MASK_QID, intr_ent); + if (FIELD_GET(QDMA_INTR_MASK_TYPE, intr_ent)) + q = qdev->c2h_queues; + else + q = qdev->h2c_queues; + q += qid; + + cidx = FIELD_GET(QDMA_INTR_MASK_CIDX, intr_ent); + + spin_lock_irqsave(&q->vchan.lock, flags); + comp_desc = (cidx - q->cidx) & q->idx_mask; + + vd = vchan_next_desc(&q->vchan); + if (!vd) + goto skip; + + vdesc = to_qdma_vdesc(vd); + while (comp_desc > vdesc->pending_descs) { + list_del(&vd->node); + vchan_cookie_complete(vd); + comp_desc -= vdesc->pending_descs; + vd = vchan_next_desc(&q->vchan); + vdesc = to_qdma_vdesc(vd); + } + vdesc->pending_descs -= comp_desc; + if (!vdesc->pending_descs && QDMA_VDESC_QUEUED(vdesc)) { + list_del(&vd->node); + vchan_cookie_complete(vd); + } + q->cidx = cidx; + + qdma_fill_pending_vdesc(q); + qdma_xfer_start(q); + +skip: + spin_unlock_irqrestore(&q->vchan.lock, flags); + + /* + * Wrap the index value and flip the expected color value if + * interrupt aggregation PIDX has wrapped around. + */ + index++; + index &= QDMA_INTR_RING_IDX_MASK; + if (!index) + intr->color = !intr->color; + } + + /* + * Update the software interrupt aggregation ring CIDX if a valid entry + * was found. + */ + if (q) { + qdma_dbg(qdev, "update intr ring%d %d", intr->ridx, index); + + /* + * Record the last read index of status descriptor from the + * interrupt aggregation ring. + */ + intr->cidx = index; + + ret = qdma_update_cidx(q, intr->ridx, index); + if (ret) { + qdma_err(qdev, "Failed to update IRQ CIDX"); + return IRQ_NONE; + } + } + + return IRQ_HANDLED; +} + +static int qdma_init_error_irq(struct qdma_device *qdev) +{ + struct device *dev = &qdev->pdev->dev; + int ret; + u32 vec; + + vec = qdev->queue_irq_start - 1; + + ret = devm_request_threaded_irq(dev, vec, NULL, qdma_error_isr, + IRQF_ONESHOT, "amd-qdma-error", qdev); + if (ret) { + qdma_err(qdev, "Failed to request error IRQ vector: %d", vec); + return ret; + } + + ret = qdma_arm_err_intr(qdev); + if (ret) + qdma_err(qdev, "Failed to arm err interrupt, ret %d", ret); + + return ret; +} + +static int qdmam_alloc_qintr_rings(struct qdma_device *qdev) +{ + u32 ctxt[QDMA_CTXT_REGMAP_LEN]; + struct device *dev = &qdev->pdev->dev; + struct qdma_intr_ring *ring; + struct qdma_ctxt_intr intr_ctxt; + u32 vector; + int ret, i; + + qdev->qintr_ring_num = qdev->queue_irq_num; + qdev->qintr_rings = devm_kcalloc(dev, qdev->qintr_ring_num, + sizeof(*qdev->qintr_rings), + GFP_KERNEL); + if (!qdev->qintr_rings) + return -ENOMEM; + + vector = qdev->queue_irq_start; + for (i = 0; i < qdev->qintr_ring_num; i++, vector++) { + ring = &qdev->qintr_rings[i]; + ring->qdev = qdev; + ring->msix_id = qdev->err_irq_idx + i + 1; + ring->ridx = i; + ring->color = 1; + ring->base = dmam_alloc_coherent(dev, QDMA_INTR_RING_SIZE, + &ring->dev_base, GFP_KERNEL); + if (!ring->base) { + qdma_err(qdev, "Failed to alloc intr ring %d", i); + return -ENOMEM; + } + intr_ctxt.agg_base = QDMA_INTR_RING_BASE(ring->dev_base); + intr_ctxt.size = (QDMA_INTR_RING_SIZE - 1) / 4096; + intr_ctxt.vec = ring->msix_id; + intr_ctxt.valid = true; + intr_ctxt.color = true; + ret = qdma_prog_context(qdev, QDMA_CTXT_INTR_COAL, + QDMA_CTXT_CLEAR, ring->ridx, NULL); + if (ret) { + qdma_err(qdev, "Failed clear intr ctx, ret %d", ret); + return ret; + } + + qdma_prep_intr_context(qdev, &intr_ctxt, ctxt); + ret = qdma_prog_context(qdev, QDMA_CTXT_INTR_COAL, + QDMA_CTXT_WRITE, ring->ridx, ctxt); + if (ret) { + qdma_err(qdev, "Failed setup intr ctx, ret %d", ret); + return ret; + } + + ret = devm_request_threaded_irq(dev, vector, NULL, + qdma_queue_isr, IRQF_ONESHOT, + "amd-qdma-queue", ring); + if (ret) { + qdma_err(qdev, "Failed to request irq %d", vector); + return ret; + } + } + + return 0; +} + +static int qdma_intr_init(struct qdma_device *qdev) +{ + int ret; + + ret = qdma_init_error_irq(qdev); + if (ret) { + qdma_err(qdev, "Failed to init error IRQs, ret %d", ret); + return ret; + } + + ret = qdmam_alloc_qintr_rings(qdev); + if (ret) { + qdma_err(qdev, "Failed to init queue IRQs, ret %d", ret); + return ret; + } + + return 0; +} + +static void amd_qdma_remove(struct platform_device *pdev) +{ + struct qdma_device *qdev = platform_get_drvdata(pdev); + + qdma_sgdma_control(qdev, 0); + dma_async_device_unregister(&qdev->dma_dev); + + mutex_destroy(&qdev->ctxt_lock); +} + +static int amd_qdma_probe(struct platform_device *pdev) +{ + struct qdma_platdata *pdata = dev_get_platdata(&pdev->dev); + struct qdma_device *qdev; + struct resource *res; + void __iomem *regs; + int ret; + + qdev = devm_kzalloc(&pdev->dev, sizeof(*qdev), GFP_KERNEL); + if (!qdev) + return -ENOMEM; + + platform_set_drvdata(pdev, qdev); + qdev->pdev = pdev; + mutex_init(&qdev->ctxt_lock); + + res = platform_get_resource(pdev, IORESOURCE_IRQ, 0); + if (!res) { + qdma_err(qdev, "Failed to get IRQ resource"); + ret = -ENODEV; + goto failed; + } + qdev->err_irq_idx = pdata->irq_index; + qdev->queue_irq_start = res->start + 1; + qdev->queue_irq_num = resource_size(res) - 1; + + regs = devm_platform_get_and_ioremap_resource(pdev, 0, NULL); + if (IS_ERR(regs)) { + ret = PTR_ERR(regs); + qdma_err(qdev, "Failed to map IO resource, err %d", ret); + goto failed; + } + + qdev->regmap = devm_regmap_init_mmio(&pdev->dev, regs, + &qdma_regmap_config); + if (IS_ERR(qdev->regmap)) { + ret = PTR_ERR(qdev->regmap); + qdma_err(qdev, "Regmap init failed, err %d", ret); + goto failed; + } + + ret = qdma_device_verify(qdev); + if (ret) + goto failed; + + ret = qdma_get_hw_info(qdev); + if (ret) + goto failed; + + INIT_LIST_HEAD(&qdev->dma_dev.channels); + + ret = qdma_device_setup(qdev); + if (ret) + goto failed; + + ret = qdma_intr_init(qdev); + if (ret) { + qdma_err(qdev, "Failed to initialize IRQs %d", ret); + goto failed_disable_engine; + } + + dma_cap_set(DMA_SLAVE, qdev->dma_dev.cap_mask); + dma_cap_set(DMA_PRIVATE, qdev->dma_dev.cap_mask); + + qdev->dma_dev.dev = &pdev->dev; + qdev->dma_dev.filter.map = pdata->device_map; + qdev->dma_dev.filter.mapcnt = qdev->chan_num * 2; + qdev->dma_dev.filter.fn = qdma_filter_fn; + qdev->dma_dev.device_alloc_chan_resources = qdma_alloc_queue_resources; + qdev->dma_dev.device_free_chan_resources = qdma_free_queue_resources; + qdev->dma_dev.device_prep_slave_sg = qdma_prep_device_sg; + qdev->dma_dev.device_config = qdma_device_config; + qdev->dma_dev.device_issue_pending = qdma_issue_pending; + qdev->dma_dev.device_tx_status = dma_cookie_status; + qdev->dma_dev.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV); + + ret = dma_async_device_register(&qdev->dma_dev); + if (ret) { + qdma_err(qdev, "Failed to register AMD QDMA: %d", ret); + goto failed_disable_engine; + } + + return 0; + +failed_disable_engine: + qdma_sgdma_control(qdev, 0); +failed: + mutex_destroy(&qdev->ctxt_lock); + qdma_err(qdev, "Failed to probe AMD QDMA driver"); + return ret; +} + +static struct platform_driver amd_qdma_driver = { + .driver = { + .name = "amd-qdma", + }, + .probe = amd_qdma_probe, + .remove_new = amd_qdma_remove, +}; + +module_platform_driver(amd_qdma_driver); + +MODULE_DESCRIPTION("AMD QDMA driver"); +MODULE_AUTHOR("XRT Team "); +MODULE_LICENSE("GPL"); diff --git a/drivers/dma/amd/qdma/qdma.h b/drivers/dma/amd/qdma/qdma.h new file mode 100644 index 000000000000..94089f1f0c11 --- /dev/null +++ b/drivers/dma/amd/qdma/qdma.h @@ -0,0 +1,266 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * DMA header for AMD Queue-based DMA Subsystem + * + * Copyright (C) 2023-2024, Advanced Micro Devices, Inc. + */ + +#ifndef __QDMA_H +#define __QDMA_H + +#include +#include +#include +#include +#include + +#include "../../virt-dma.h" + +#define DISABLE 0 +#define ENABLE 1 + +#define QDMA_MIN_IRQ 3 +#define QDMA_INTR_NAME_MAX_LEN 30 +#define QDMA_INTR_PREFIX "amd-qdma" + +#define QDMA_IDENTIFIER 0x1FD3 +#define QDMA_DEFAULT_RING_SIZE (BIT(10) + 1) +#define QDMA_DEFAULT_RING_ID 0 +#define QDMA_POLL_INTRVL_US 10 /* 10us */ +#define QDMA_POLL_TIMEOUT_US (500 * 1000) /* 500ms */ +#define QDMA_DMAP_REG_STRIDE 16 +#define QDMA_CTXT_REGMAP_LEN 8 /* 8 regs */ +#define QDMA_MM_DESC_SIZE 32 /* Bytes */ +#define QDMA_MM_DESC_LEN_BITS 28 +#define QDMA_MM_DESC_MAX_LEN (BIT(QDMA_MM_DESC_LEN_BITS) - 1) +#define QDMA_MIN_DMA_ALLOC_SIZE 4096 +#define QDMA_INTR_RING_SIZE BIT(13) +#define QDMA_INTR_RING_IDX_MASK GENMASK(9, 0) +#define QDMA_INTR_RING_BASE(_addr) ((_addr) >> 12) + +#define QDMA_IDENTIFIER_REGOFF 0x0 +#define QDMA_IDENTIFIER_MASK GENMASK(31, 16) +#define QDMA_QUEUE_ARM_BIT BIT(16) + +#define qdma_err(qdev, fmt, args...) \ + dev_err(&(qdev)->pdev->dev, fmt, ##args) + +#define qdma_dbg(qdev, fmt, args...) \ + dev_dbg(&(qdev)->pdev->dev, fmt, ##args) + +#define qdma_info(qdev, fmt, args...) \ + dev_info(&(qdev)->pdev->dev, fmt, ##args) + +enum qdma_reg_fields { + QDMA_REGF_IRQ_ENABLE, + QDMA_REGF_WBK_ENABLE, + QDMA_REGF_WBI_CHECK, + QDMA_REGF_IRQ_ARM, + QDMA_REGF_IRQ_VEC, + QDMA_REGF_IRQ_AGG, + QDMA_REGF_WBI_INTVL_ENABLE, + QDMA_REGF_MRKR_DISABLE, + QDMA_REGF_QUEUE_ENABLE, + QDMA_REGF_QUEUE_MODE, + QDMA_REGF_DESC_BASE, + QDMA_REGF_DESC_SIZE, + QDMA_REGF_RING_ID, + QDMA_REGF_CMD_INDX, + QDMA_REGF_CMD_CMD, + QDMA_REGF_CMD_TYPE, + QDMA_REGF_CMD_BUSY, + QDMA_REGF_QUEUE_COUNT, + QDMA_REGF_QUEUE_MAX, + QDMA_REGF_QUEUE_BASE, + QDMA_REGF_FUNCTION_ID, + QDMA_REGF_INTR_AGG_BASE, + QDMA_REGF_INTR_VECTOR, + QDMA_REGF_INTR_SIZE, + QDMA_REGF_INTR_VALID, + QDMA_REGF_INTR_COLOR, + QDMA_REGF_INTR_FUNCTION_ID, + QDMA_REGF_ERR_INT_FUNC, + QDMA_REGF_ERR_INT_VEC, + QDMA_REGF_ERR_INT_ARM, + QDMA_REGF_MAX +}; + +enum qdma_regs { + QDMA_REGO_CTXT_DATA, + QDMA_REGO_CTXT_CMD, + QDMA_REGO_CTXT_MASK, + QDMA_REGO_MM_H2C_CTRL, + QDMA_REGO_MM_C2H_CTRL, + QDMA_REGO_QUEUE_COUNT, + QDMA_REGO_RING_SIZE, + QDMA_REGO_H2C_PIDX, + QDMA_REGO_C2H_PIDX, + QDMA_REGO_INTR_CIDX, + QDMA_REGO_FUNC_ID, + QDMA_REGO_ERR_INT, + QDMA_REGO_ERR_STAT, + QDMA_REGO_MAX +}; + +struct qdma_reg_field { + u16 lsb; /* Least significant bit of field */ + u16 msb; /* Most significant bit of field */ +}; + +struct qdma_reg { + u32 off; + u32 count; +}; + +#define QDMA_REGF(_msb, _lsb) { \ + .lsb = (_lsb), \ + .msb = (_msb), \ +} + +#define QDMA_REGO(_off, _count) { \ + .off = (_off), \ + .count = (_count), \ +} + +enum qdma_desc_size { + QDMA_DESC_SIZE_8B, + QDMA_DESC_SIZE_16B, + QDMA_DESC_SIZE_32B, + QDMA_DESC_SIZE_64B, +}; + +enum qdma_queue_op_mode { + QDMA_QUEUE_OP_STREAM, + QDMA_QUEUE_OP_MM, +}; + +enum qdma_ctxt_type { + QDMA_CTXT_DESC_SW_C2H, + QDMA_CTXT_DESC_SW_H2C, + QDMA_CTXT_DESC_HW_C2H, + QDMA_CTXT_DESC_HW_H2C, + QDMA_CTXT_DESC_CR_C2H, + QDMA_CTXT_DESC_CR_H2C, + QDMA_CTXT_WRB, + QDMA_CTXT_PFTCH, + QDMA_CTXT_INTR_COAL, + QDMA_CTXT_RSVD, + QDMA_CTXT_HOST_PROFILE, + QDMA_CTXT_TIMER, + QDMA_CTXT_FMAP, + QDMA_CTXT_FNC_STS, +}; + +enum qdma_ctxt_cmd { + QDMA_CTXT_CLEAR, + QDMA_CTXT_WRITE, + QDMA_CTXT_READ, + QDMA_CTXT_INVALIDATE, + QDMA_CTXT_MAX +}; + +struct qdma_ctxt_sw_desc { + u64 desc_base; + u16 vec; +}; + +struct qdma_ctxt_intr { + u64 agg_base; + u16 vec; + u32 size; + bool valid; + bool color; +}; + +struct qdma_ctxt_fmap { + u16 qbase; + u16 qmax; +}; + +struct qdma_device; + +struct qdma_mm_desc { + __le64 src_addr; + __le32 len; + __le32 reserved1; + __le64 dst_addr; + __le64 reserved2; +} __packed; + +struct qdma_mm_vdesc { + struct virt_dma_desc vdesc; + struct qdma_queue *queue; + struct scatterlist *sgl; + u64 sg_off; + u32 sg_len; + u64 dev_addr; + u32 pidx; + u32 pending_descs; + struct dma_slave_config cfg; +}; + +#define QDMA_VDESC_QUEUED(vdesc) (!(vdesc)->sg_len) + +struct qdma_queue { + struct qdma_device *qdev; + struct virt_dma_chan vchan; + enum dma_transfer_direction dir; + struct dma_slave_config cfg; + struct qdma_mm_desc *desc_base; + struct qdma_mm_vdesc *submitted_vdesc; + struct qdma_mm_vdesc *issued_vdesc; + dma_addr_t dma_desc_base; + u32 pidx_reg; + u32 cidx_reg; + u32 ring_size; + u32 idx_mask; + u16 qid; + u32 pidx; + u32 cidx; +}; + +struct qdma_intr_ring { + struct qdma_device *qdev; + __le64 *base; + dma_addr_t dev_base; + char msix_name[QDMA_INTR_NAME_MAX_LEN]; + u32 msix_vector; + u16 msix_id; + u32 ring_size; + u16 ridx; + u16 cidx; + u8 color; +}; + +#define QDMA_INTR_MASK_PIDX GENMASK_ULL(15, 0) +#define QDMA_INTR_MASK_CIDX GENMASK_ULL(31, 16) +#define QDMA_INTR_MASK_DESC_COLOR GENMASK_ULL(32, 32) +#define QDMA_INTR_MASK_STATE GENMASK_ULL(34, 33) +#define QDMA_INTR_MASK_ERROR GENMASK_ULL(36, 35) +#define QDMA_INTR_MASK_TYPE GENMASK_ULL(38, 38) +#define QDMA_INTR_MASK_QID GENMASK_ULL(62, 39) +#define QDMA_INTR_MASK_COLOR GENMASK_ULL(63, 63) + +struct qdma_device { + struct platform_device *pdev; + struct dma_device dma_dev; + struct regmap *regmap; + struct mutex ctxt_lock; /* protect ctxt registers */ + const struct qdma_reg_field *rfields; + const struct qdma_reg *roffs; + struct qdma_queue *h2c_queues; + struct qdma_queue *c2h_queues; + struct qdma_intr_ring *qintr_rings; + u32 qintr_ring_num; + u32 qintr_ring_idx; + u32 chan_num; + u32 queue_irq_start; + u32 queue_irq_num; + u32 err_irq_idx; + u32 fid; +}; + +extern const struct qdma_reg qdma_regos_default[QDMA_REGO_MAX]; +extern const struct qdma_reg_field qdma_regfs_default[QDMA_REGF_MAX]; + +#endif /* __QDMA_H */ diff --git a/include/linux/platform_data/amd_qdma.h b/include/linux/platform_data/amd_qdma.h new file mode 100644 index 000000000000..576d952f97ed --- /dev/null +++ b/include/linux/platform_data/amd_qdma.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2023-2024, Advanced Micro Devices, Inc. + */ + +#ifndef _PLATDATA_AMD_QDMA_H +#define _PLATDATA_AMD_QDMA_H + +#include + +/** + * struct qdma_queue_info - DMA queue information. This information is used to + * match queue when DMA channel is requested + * @dir: Channel transfer direction + */ +struct qdma_queue_info { + enum dma_transfer_direction dir; +}; + +#define QDMA_FILTER_PARAM(qinfo) ((void *)(qinfo)) + +struct dma_slave_map; + +/** + * struct qdma_platdata - Platform specific data for QDMA engine + * @max_mm_channels: Maximum number of MM DMA channels in each direction + * @device_map: DMA slave map + * @irq_index: The index of first IRQ + */ +struct qdma_platdata { + u32 max_mm_channels; + u32 irq_index; + struct dma_slave_map *device_map; +}; + +#endif /* _PLATDATA_AMD_QDMA_H */ -- cgit v1.2.3 From 4bb59323450db610b06c549fa4d5936e94fb9a36 Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Sat, 10 Aug 2024 17:45:40 +0800 Subject: dmaengine: ti: k3-udma: Remove unused declarations Commit d70241913413 ("dmaengine: ti: k3-udma: Add glue layer for non DMAengine users") declared but never implemented these. Signed-off-by: Yue Haibing Acked-by: Peter Ujfalusi Link: https://lore.kernel.org/r/20240810094540.2589310-1-yuehaibing@huawei.com Signed-off-by: Vinod Koul --- drivers/dma/ti/k3-udma.h | 1 - include/linux/dma/k3-udma-glue.h | 2 -- 2 files changed, 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma/ti/k3-udma.h b/drivers/dma/ti/k3-udma.h index d349c6d482ae..9062a237cd16 100644 --- a/drivers/dma/ti/k3-udma.h +++ b/drivers/dma/ti/k3-udma.h @@ -131,7 +131,6 @@ int xudma_navss_psil_unpair(struct udma_dev *ud, u32 src_thread, struct udma_dev *of_xudma_dev_get(struct device_node *np, const char *property); struct device *xudma_get_device(struct udma_dev *ud); struct k3_ringacc *xudma_get_ringacc(struct udma_dev *ud); -void xudma_dev_put(struct udma_dev *ud); u32 xudma_dev_get_psil_base(struct udma_dev *ud); struct udma_tisci_rm *xudma_dev_get_tisci_rm(struct udma_dev *ud); diff --git a/include/linux/dma/k3-udma-glue.h b/include/linux/dma/k3-udma-glue.h index 1e491c5dcac2..2dea217629d0 100644 --- a/include/linux/dma/k3-udma-glue.h +++ b/include/linux/dma/k3-udma-glue.h @@ -136,8 +136,6 @@ u32 k3_udma_glue_rx_flow_get_fdq_id(struct k3_udma_glue_rx_channel *rx_chn, u32 k3_udma_glue_rx_get_flow_id_base(struct k3_udma_glue_rx_channel *rx_chn); int k3_udma_glue_rx_get_irq(struct k3_udma_glue_rx_channel *rx_chn, u32 flow_num); -void k3_udma_glue_rx_put_irq(struct k3_udma_glue_rx_channel *rx_chn, - u32 flow_num); void k3_udma_glue_reset_rx_chn(struct k3_udma_glue_rx_channel *rx_chn, u32 flow_num, void *data, void (*cleanup)(void *data, dma_addr_t desc_dma), -- cgit v1.2.3 From 41845541adebc503b8574943c92670016d5e566b Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Fri, 23 Aug 2024 17:05:18 +0800 Subject: firmware: arm_scmi: Add initial support for i.MX BBM protocol i.MX95 has a battery-backed module(BBM), which has persistent storage (GPR), an RTC, and the ON/OFF button. The System Manager(SM) firmware use SCMI vendor protocol(SCMI BBM) to let agent be able to use GPR, RTC and ON/OFF button. Reviewed-by: Cristian Marussi Signed-off-by: Peng Fan Message-Id: <20240823-imx95-bbm-misc-v2-v8-2-e600ed9e9271@nxp.com> Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/Kconfig | 1 + drivers/firmware/arm_scmi/Makefile | 1 + drivers/firmware/arm_scmi/vendors/imx/Kconfig | 15 + drivers/firmware/arm_scmi/vendors/imx/Makefile | 2 + drivers/firmware/arm_scmi/vendors/imx/imx-sm-bbm.c | 383 +++++++++++++++++++++ include/linux/scmi_imx_protocol.h | 42 +++ 6 files changed, 444 insertions(+) create mode 100644 drivers/firmware/arm_scmi/vendors/imx/Kconfig create mode 100644 drivers/firmware/arm_scmi/vendors/imx/Makefile create mode 100644 drivers/firmware/arm_scmi/vendors/imx/imx-sm-bbm.c create mode 100644 include/linux/scmi_imx_protocol.h (limited to 'include/linux') diff --git a/drivers/firmware/arm_scmi/Kconfig b/drivers/firmware/arm_scmi/Kconfig index 67053c1862d1..dabd874641d0 100644 --- a/drivers/firmware/arm_scmi/Kconfig +++ b/drivers/firmware/arm_scmi/Kconfig @@ -70,6 +70,7 @@ config ARM_SCMI_DEBUG_COUNTERS SCMI monitoring. source "drivers/firmware/arm_scmi/transports/Kconfig" +source "drivers/firmware/arm_scmi/vendors/imx/Kconfig" endif #ARM_SCMI_PROTOCOL diff --git a/drivers/firmware/arm_scmi/Makefile b/drivers/firmware/arm_scmi/Makefile index 9659b7d1b963..9ac81adff567 100644 --- a/drivers/firmware/arm_scmi/Makefile +++ b/drivers/firmware/arm_scmi/Makefile @@ -11,6 +11,7 @@ scmi-protocols-y += pinctrl.o scmi-module-objs := $(scmi-driver-y) $(scmi-protocols-y) $(scmi-transport-y) obj-$(CONFIG_ARM_SCMI_PROTOCOL) += transports/ +obj-$(CONFIG_ARM_SCMI_PROTOCOL) += vendors/imx/ obj-$(CONFIG_ARM_SCMI_PROTOCOL) += scmi-core.o obj-$(CONFIG_ARM_SCMI_PROTOCOL) += scmi-module.o diff --git a/drivers/firmware/arm_scmi/vendors/imx/Kconfig b/drivers/firmware/arm_scmi/vendors/imx/Kconfig new file mode 100644 index 000000000000..95d0dec2ca94 --- /dev/null +++ b/drivers/firmware/arm_scmi/vendors/imx/Kconfig @@ -0,0 +1,15 @@ +# SPDX-License-Identifier: GPL-2.0-only +menu "ARM SCMI NXP i.MX Vendor Protocols" + +config IMX_SCMI_BBM_EXT + tristate "i.MX SCMI BBM EXTENSION" + depends on ARM_SCMI_PROTOCOL || (COMPILE_TEST && OF) + default y if ARCH_MXC + help + This enables i.MX System BBM control logic which supports RTC + and BUTTON. + + To compile this driver as a module, choose M here: the + module will be called imx-sm-bbm. + +endmenu diff --git a/drivers/firmware/arm_scmi/vendors/imx/Makefile b/drivers/firmware/arm_scmi/vendors/imx/Makefile new file mode 100644 index 000000000000..a7dbdd20dbb9 --- /dev/null +++ b/drivers/firmware/arm_scmi/vendors/imx/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +obj-$(CONFIG_IMX_SCMI_BBM_EXT) += imx-sm-bbm.o diff --git a/drivers/firmware/arm_scmi/vendors/imx/imx-sm-bbm.c b/drivers/firmware/arm_scmi/vendors/imx/imx-sm-bbm.c new file mode 100644 index 000000000000..17799eacf06c --- /dev/null +++ b/drivers/firmware/arm_scmi/vendors/imx/imx-sm-bbm.c @@ -0,0 +1,383 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * System Control and Management Interface (SCMI) NXP BBM Protocol + * + * Copyright 2024 NXP + */ + +#define pr_fmt(fmt) "SCMI Notifications BBM - " fmt + +#include +#include +#include +#include +#include +#include +#include + +#include "../../protocols.h" +#include "../../notify.h" + +#define SCMI_PROTOCOL_SUPPORTED_VERSION 0x10000 + +enum scmi_imx_bbm_protocol_cmd { + IMX_BBM_GPR_SET = 0x3, + IMX_BBM_GPR_GET = 0x4, + IMX_BBM_RTC_ATTRIBUTES = 0x5, + IMX_BBM_RTC_TIME_SET = 0x6, + IMX_BBM_RTC_TIME_GET = 0x7, + IMX_BBM_RTC_ALARM_SET = 0x8, + IMX_BBM_BUTTON_GET = 0x9, + IMX_BBM_RTC_NOTIFY = 0xA, + IMX_BBM_BUTTON_NOTIFY = 0xB, +}; + +#define GET_RTCS_NR(x) le32_get_bits((x), GENMASK(23, 16)) +#define GET_GPRS_NR(x) le32_get_bits((x), GENMASK(15, 0)) + +#define SCMI_IMX_BBM_NOTIFY_RTC_UPDATED BIT(2) +#define SCMI_IMX_BBM_NOTIFY_RTC_ROLLOVER BIT(1) +#define SCMI_IMX_BBM_NOTIFY_RTC_ALARM BIT(0) + +#define SCMI_IMX_BBM_RTC_ALARM_ENABLE_FLAG BIT(0) + +#define SCMI_IMX_BBM_NOTIFY_RTC_FLAG \ + (SCMI_IMX_BBM_NOTIFY_RTC_UPDATED | SCMI_IMX_BBM_NOTIFY_RTC_ROLLOVER | \ + SCMI_IMX_BBM_NOTIFY_RTC_ALARM) + +#define SCMI_IMX_BBM_EVENT_RTC_MASK GENMASK(31, 24) + +struct scmi_imx_bbm_info { + u32 version; + int nr_rtc; + int nr_gpr; +}; + +struct scmi_msg_imx_bbm_protocol_attributes { + __le32 attributes; +}; + +struct scmi_imx_bbm_set_time { + __le32 id; + __le32 flags; + __le32 value_low; + __le32 value_high; +}; + +struct scmi_imx_bbm_get_time { + __le32 id; + __le32 flags; +}; + +struct scmi_imx_bbm_alarm_time { + __le32 id; + __le32 flags; + __le32 value_low; + __le32 value_high; +}; + +struct scmi_msg_imx_bbm_rtc_notify { + __le32 rtc_id; + __le32 flags; +}; + +struct scmi_msg_imx_bbm_button_notify { + __le32 flags; +}; + +struct scmi_imx_bbm_notify_payld { + __le32 flags; +}; + +static int scmi_imx_bbm_attributes_get(const struct scmi_protocol_handle *ph, + struct scmi_imx_bbm_info *pi) +{ + int ret; + struct scmi_xfer *t; + struct scmi_msg_imx_bbm_protocol_attributes *attr; + + ret = ph->xops->xfer_get_init(ph, PROTOCOL_ATTRIBUTES, 0, sizeof(*attr), &t); + if (ret) + return ret; + + attr = t->rx.buf; + + ret = ph->xops->do_xfer(ph, t); + if (!ret) { + pi->nr_rtc = GET_RTCS_NR(attr->attributes); + pi->nr_gpr = GET_GPRS_NR(attr->attributes); + } + + ph->xops->xfer_put(ph, t); + + return ret; +} + +static int scmi_imx_bbm_notify(const struct scmi_protocol_handle *ph, + u32 src_id, int message_id, bool enable) +{ + int ret; + struct scmi_xfer *t; + + if (message_id == IMX_BBM_RTC_NOTIFY) { + struct scmi_msg_imx_bbm_rtc_notify *rtc_notify; + + ret = ph->xops->xfer_get_init(ph, message_id, + sizeof(*rtc_notify), 0, &t); + if (ret) + return ret; + + rtc_notify = t->tx.buf; + rtc_notify->rtc_id = cpu_to_le32(0); + rtc_notify->flags = + cpu_to_le32(enable ? SCMI_IMX_BBM_NOTIFY_RTC_FLAG : 0); + } else if (message_id == IMX_BBM_BUTTON_NOTIFY) { + struct scmi_msg_imx_bbm_button_notify *button_notify; + + ret = ph->xops->xfer_get_init(ph, message_id, + sizeof(*button_notify), 0, &t); + if (ret) + return ret; + + button_notify = t->tx.buf; + button_notify->flags = cpu_to_le32(enable ? 1 : 0); + } else { + return -EINVAL; + } + + ret = ph->xops->do_xfer(ph, t); + + ph->xops->xfer_put(ph, t); + return ret; +} + +static enum scmi_imx_bbm_protocol_cmd evt_2_cmd[] = { + IMX_BBM_RTC_NOTIFY, + IMX_BBM_BUTTON_NOTIFY +}; + +static int scmi_imx_bbm_set_notify_enabled(const struct scmi_protocol_handle *ph, + u8 evt_id, u32 src_id, bool enable) +{ + int ret, cmd_id; + + if (evt_id >= ARRAY_SIZE(evt_2_cmd)) + return -EINVAL; + + cmd_id = evt_2_cmd[evt_id]; + ret = scmi_imx_bbm_notify(ph, src_id, cmd_id, enable); + if (ret) + pr_debug("FAIL_ENABLED - evt[%X] dom[%d] - ret:%d\n", + evt_id, src_id, ret); + + return ret; +} + +static void *scmi_imx_bbm_fill_custom_report(const struct scmi_protocol_handle *ph, + u8 evt_id, ktime_t timestamp, + const void *payld, size_t payld_sz, + void *report, u32 *src_id) +{ + const struct scmi_imx_bbm_notify_payld *p = payld; + struct scmi_imx_bbm_notif_report *r = report; + + if (sizeof(*p) != payld_sz) + return NULL; + + if (evt_id == SCMI_EVENT_IMX_BBM_RTC) { + r->is_rtc = true; + r->is_button = false; + r->timestamp = timestamp; + r->rtc_id = le32_get_bits(p->flags, SCMI_IMX_BBM_EVENT_RTC_MASK); + r->rtc_evt = le32_get_bits(p->flags, SCMI_IMX_BBM_NOTIFY_RTC_FLAG); + dev_dbg(ph->dev, "RTC: %d evt: %x\n", r->rtc_id, r->rtc_evt); + *src_id = r->rtc_evt; + } else if (evt_id == SCMI_EVENT_IMX_BBM_BUTTON) { + r->is_rtc = false; + r->is_button = true; + r->timestamp = timestamp; + dev_dbg(ph->dev, "BBM Button\n"); + *src_id = 0; + } else { + WARN_ON_ONCE(1); + return NULL; + } + + return r; +} + +static const struct scmi_event scmi_imx_bbm_events[] = { + { + .id = SCMI_EVENT_IMX_BBM_RTC, + .max_payld_sz = sizeof(struct scmi_imx_bbm_notify_payld), + .max_report_sz = sizeof(struct scmi_imx_bbm_notif_report), + }, + { + .id = SCMI_EVENT_IMX_BBM_BUTTON, + .max_payld_sz = sizeof(struct scmi_imx_bbm_notify_payld), + .max_report_sz = sizeof(struct scmi_imx_bbm_notif_report), + }, +}; + +static const struct scmi_event_ops scmi_imx_bbm_event_ops = { + .set_notify_enabled = scmi_imx_bbm_set_notify_enabled, + .fill_custom_report = scmi_imx_bbm_fill_custom_report, +}; + +static const struct scmi_protocol_events scmi_imx_bbm_protocol_events = { + .queue_sz = SCMI_PROTO_QUEUE_SZ, + .ops = &scmi_imx_bbm_event_ops, + .evts = scmi_imx_bbm_events, + .num_events = ARRAY_SIZE(scmi_imx_bbm_events), + .num_sources = 1, +}; + +static int scmi_imx_bbm_rtc_time_set(const struct scmi_protocol_handle *ph, + u32 rtc_id, u64 sec) +{ + struct scmi_imx_bbm_info *pi = ph->get_priv(ph); + struct scmi_imx_bbm_set_time *cfg; + struct scmi_xfer *t; + int ret; + + if (rtc_id >= pi->nr_rtc) + return -EINVAL; + + ret = ph->xops->xfer_get_init(ph, IMX_BBM_RTC_TIME_SET, sizeof(*cfg), 0, &t); + if (ret) + return ret; + + cfg = t->tx.buf; + cfg->id = cpu_to_le32(rtc_id); + cfg->flags = 0; + cfg->value_low = cpu_to_le32(lower_32_bits(sec)); + cfg->value_high = cpu_to_le32(upper_32_bits(sec)); + + ret = ph->xops->do_xfer(ph, t); + + ph->xops->xfer_put(ph, t); + + return ret; +} + +static int scmi_imx_bbm_rtc_time_get(const struct scmi_protocol_handle *ph, + u32 rtc_id, u64 *value) +{ + struct scmi_imx_bbm_info *pi = ph->get_priv(ph); + struct scmi_imx_bbm_get_time *cfg; + struct scmi_xfer *t; + int ret; + + if (rtc_id >= pi->nr_rtc) + return -EINVAL; + + ret = ph->xops->xfer_get_init(ph, IMX_BBM_RTC_TIME_GET, sizeof(*cfg), + sizeof(u64), &t); + if (ret) + return ret; + + cfg = t->tx.buf; + cfg->id = cpu_to_le32(rtc_id); + cfg->flags = 0; + + ret = ph->xops->do_xfer(ph, t); + if (!ret) + *value = get_unaligned_le64(t->rx.buf); + + ph->xops->xfer_put(ph, t); + + return ret; +} + +static int scmi_imx_bbm_rtc_alarm_set(const struct scmi_protocol_handle *ph, + u32 rtc_id, bool enable, u64 sec) +{ + struct scmi_imx_bbm_info *pi = ph->get_priv(ph); + struct scmi_imx_bbm_alarm_time *cfg; + struct scmi_xfer *t; + int ret; + + if (rtc_id >= pi->nr_rtc) + return -EINVAL; + + ret = ph->xops->xfer_get_init(ph, IMX_BBM_RTC_ALARM_SET, sizeof(*cfg), 0, &t); + if (ret) + return ret; + + cfg = t->tx.buf; + cfg->id = cpu_to_le32(rtc_id); + cfg->flags = enable ? + cpu_to_le32(SCMI_IMX_BBM_RTC_ALARM_ENABLE_FLAG) : 0; + cfg->value_low = cpu_to_le32(lower_32_bits(sec)); + cfg->value_high = cpu_to_le32(upper_32_bits(sec)); + + ret = ph->xops->do_xfer(ph, t); + + ph->xops->xfer_put(ph, t); + + return ret; +} + +static int scmi_imx_bbm_button_get(const struct scmi_protocol_handle *ph, u32 *state) +{ + struct scmi_xfer *t; + int ret; + + ret = ph->xops->xfer_get_init(ph, IMX_BBM_BUTTON_GET, 0, sizeof(u32), &t); + if (ret) + return ret; + + ret = ph->xops->do_xfer(ph, t); + if (!ret) + *state = get_unaligned_le32(t->rx.buf); + + ph->xops->xfer_put(ph, t); + + return ret; +} + +static const struct scmi_imx_bbm_proto_ops scmi_imx_bbm_proto_ops = { + .rtc_time_get = scmi_imx_bbm_rtc_time_get, + .rtc_time_set = scmi_imx_bbm_rtc_time_set, + .rtc_alarm_set = scmi_imx_bbm_rtc_alarm_set, + .button_get = scmi_imx_bbm_button_get, +}; + +static int scmi_imx_bbm_protocol_init(const struct scmi_protocol_handle *ph) +{ + u32 version; + int ret; + struct scmi_imx_bbm_info *binfo; + + ret = ph->xops->version_get(ph, &version); + if (ret) + return ret; + + dev_info(ph->dev, "NXP SM BBM Version %d.%d\n", + PROTOCOL_REV_MAJOR(version), PROTOCOL_REV_MINOR(version)); + + binfo = devm_kzalloc(ph->dev, sizeof(*binfo), GFP_KERNEL); + if (!binfo) + return -ENOMEM; + + ret = scmi_imx_bbm_attributes_get(ph, binfo); + if (ret) + return ret; + + return ph->set_priv(ph, binfo, version); +} + +static const struct scmi_protocol scmi_imx_bbm = { + .id = SCMI_PROTOCOL_IMX_BBM, + .owner = THIS_MODULE, + .instance_init = &scmi_imx_bbm_protocol_init, + .ops = &scmi_imx_bbm_proto_ops, + .events = &scmi_imx_bbm_protocol_events, + .supported_version = SCMI_PROTOCOL_SUPPORTED_VERSION, + .vendor_id = "NXP", + .sub_vendor_id = "IMX", +}; +module_scmi_protocol(scmi_imx_bbm); + +MODULE_DESCRIPTION("i.MX SCMI BBM driver"); +MODULE_LICENSE("GPL"); diff --git a/include/linux/scmi_imx_protocol.h b/include/linux/scmi_imx_protocol.h new file mode 100644 index 000000000000..2df2ea0f1809 --- /dev/null +++ b/include/linux/scmi_imx_protocol.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * SCMI Message Protocol driver NXP extension header + * + * Copyright 2024 NXP. + */ + +#ifndef _LINUX_SCMI_NXP_PROTOCOL_H +#define _LINUX_SCMI_NXP_PROTOCOL_H + +#include +#include +#include +#include + +enum scmi_nxp_protocol { + SCMI_PROTOCOL_IMX_BBM = 0x81, +}; + +struct scmi_imx_bbm_proto_ops { + int (*rtc_time_set)(const struct scmi_protocol_handle *ph, u32 id, + uint64_t sec); + int (*rtc_time_get)(const struct scmi_protocol_handle *ph, u32 id, + u64 *val); + int (*rtc_alarm_set)(const struct scmi_protocol_handle *ph, u32 id, + bool enable, u64 sec); + int (*button_get)(const struct scmi_protocol_handle *ph, u32 *state); +}; + +enum scmi_nxp_notification_events { + SCMI_EVENT_IMX_BBM_RTC = 0x0, + SCMI_EVENT_IMX_BBM_BUTTON = 0x1, +}; + +struct scmi_imx_bbm_notif_report { + bool is_rtc; + bool is_button; + ktime_t timestamp; + unsigned int rtc_id; + unsigned int rtc_evt; +}; +#endif -- cgit v1.2.3 From 61c9f03e22fc57fe61726c513b1f92c0ed1ef00f Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Fri, 23 Aug 2024 17:05:19 +0800 Subject: firmware: arm_scmi: Add initial support for i.MX MISC protocol i.MX95 System Manager(SM) firmware includes a SCMI vendor protocol, SCMI MISC protocol which includes controls that are misc settings/actions that must be exposed from the SM to agents. They are device specific and are usually define to access bit fields in various mix block control modules, IOMUX_GPR, and other General Purpose registers, Control Status Registers owned by the SM. Reviewed-by: Cristian Marussi Signed-off-by: Peng Fan Message-Id: <20240823-imx95-bbm-misc-v2-v8-3-e600ed9e9271@nxp.com> Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/vendors/imx/Kconfig | 10 + drivers/firmware/arm_scmi/vendors/imx/Makefile | 1 + .../firmware/arm_scmi/vendors/imx/imx-sm-misc.c | 318 +++++++++++++++++++++ include/linux/scmi_imx_protocol.h | 17 ++ 4 files changed, 346 insertions(+) create mode 100644 drivers/firmware/arm_scmi/vendors/imx/imx-sm-misc.c (limited to 'include/linux') diff --git a/drivers/firmware/arm_scmi/vendors/imx/Kconfig b/drivers/firmware/arm_scmi/vendors/imx/Kconfig index 95d0dec2ca94..2883ed24a84d 100644 --- a/drivers/firmware/arm_scmi/vendors/imx/Kconfig +++ b/drivers/firmware/arm_scmi/vendors/imx/Kconfig @@ -12,4 +12,14 @@ config IMX_SCMI_BBM_EXT To compile this driver as a module, choose M here: the module will be called imx-sm-bbm. +config IMX_SCMI_MISC_EXT + tristate "i.MX SCMI MISC EXTENSION" + depends on ARM_SCMI_PROTOCOL || (COMPILE_TEST && OF) + default y if ARCH_MXC + help + This enables i.MX System MISC control logic such as gpio expander + wakeup + + To compile this driver as a module, choose M here: the + module will be called imx-sm-misc. endmenu diff --git a/drivers/firmware/arm_scmi/vendors/imx/Makefile b/drivers/firmware/arm_scmi/vendors/imx/Makefile index a7dbdd20dbb9..d3ee6d544924 100644 --- a/drivers/firmware/arm_scmi/vendors/imx/Makefile +++ b/drivers/firmware/arm_scmi/vendors/imx/Makefile @@ -1,2 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_IMX_SCMI_BBM_EXT) += imx-sm-bbm.o +obj-$(CONFIG_IMX_SCMI_MISC_EXT) += imx-sm-misc.o diff --git a/drivers/firmware/arm_scmi/vendors/imx/imx-sm-misc.c b/drivers/firmware/arm_scmi/vendors/imx/imx-sm-misc.c new file mode 100644 index 000000000000..a86ab9b35953 --- /dev/null +++ b/drivers/firmware/arm_scmi/vendors/imx/imx-sm-misc.c @@ -0,0 +1,318 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * System control and Management Interface (SCMI) NXP MISC Protocol + * + * Copyright 2024 NXP + */ + +#define pr_fmt(fmt) "SCMI Notifications MISC - " fmt + +#include +#include +#include +#include +#include +#include +#include + +#include "../../protocols.h" +#include "../../notify.h" + +#define SCMI_PROTOCOL_SUPPORTED_VERSION 0x10000 + +#define MAX_MISC_CTRL_SOURCES GENMASK(15, 0) + +enum scmi_imx_misc_protocol_cmd { + SCMI_IMX_MISC_CTRL_SET = 0x3, + SCMI_IMX_MISC_CTRL_GET = 0x4, + SCMI_IMX_MISC_CTRL_NOTIFY = 0x8, +}; + +struct scmi_imx_misc_info { + u32 version; + u32 nr_dev_ctrl; + u32 nr_brd_ctrl; + u32 nr_reason; +}; + +struct scmi_msg_imx_misc_protocol_attributes { + __le32 attributes; +}; + +#define GET_BRD_CTRLS_NR(x) le32_get_bits((x), GENMASK(31, 24)) +#define GET_REASONS_NR(x) le32_get_bits((x), GENMASK(23, 16)) +#define GET_DEV_CTRLS_NR(x) le32_get_bits((x), GENMASK(15, 0)) +#define BRD_CTRL_START_ID BIT(15) + +struct scmi_imx_misc_ctrl_set_in { + __le32 id; + __le32 num; + __le32 value[]; +}; + +struct scmi_imx_misc_ctrl_notify_in { + __le32 ctrl_id; + __le32 flags; +}; + +struct scmi_imx_misc_ctrl_notify_payld { + __le32 ctrl_id; + __le32 flags; +}; + +struct scmi_imx_misc_ctrl_get_out { + __le32 num; + __le32 val[]; +}; + +static int scmi_imx_misc_attributes_get(const struct scmi_protocol_handle *ph, + struct scmi_imx_misc_info *mi) +{ + int ret; + struct scmi_xfer *t; + struct scmi_msg_imx_misc_protocol_attributes *attr; + + ret = ph->xops->xfer_get_init(ph, PROTOCOL_ATTRIBUTES, 0, + sizeof(*attr), &t); + if (ret) + return ret; + + attr = t->rx.buf; + + ret = ph->xops->do_xfer(ph, t); + if (!ret) { + mi->nr_dev_ctrl = GET_DEV_CTRLS_NR(attr->attributes); + mi->nr_brd_ctrl = GET_BRD_CTRLS_NR(attr->attributes); + mi->nr_reason = GET_REASONS_NR(attr->attributes); + dev_info(ph->dev, "i.MX MISC NUM DEV CTRL: %d, NUM BRD CTRL: %d,NUM Reason: %d\n", + mi->nr_dev_ctrl, mi->nr_brd_ctrl, mi->nr_reason); + } + + ph->xops->xfer_put(ph, t); + + return ret; +} + +static int scmi_imx_misc_ctrl_validate_id(const struct scmi_protocol_handle *ph, + u32 ctrl_id) +{ + struct scmi_imx_misc_info *mi = ph->get_priv(ph); + + /* + * [0, BRD_CTRL_START_ID) is for Dev Ctrl which is SOC related + * [BRD_CTRL_START_ID, 0xffff) is for Board Ctrl which is board related + */ + if (ctrl_id < BRD_CTRL_START_ID && ctrl_id > mi->nr_dev_ctrl) + return -EINVAL; + if (ctrl_id >= BRD_CTRL_START_ID + mi->nr_brd_ctrl) + return -EINVAL; + + return 0; +} + +static int scmi_imx_misc_ctrl_notify(const struct scmi_protocol_handle *ph, + u32 ctrl_id, u32 evt_id, u32 flags) +{ + struct scmi_imx_misc_ctrl_notify_in *in; + struct scmi_xfer *t; + int ret; + + ret = scmi_imx_misc_ctrl_validate_id(ph, ctrl_id); + if (ret) + return ret; + + ret = ph->xops->xfer_get_init(ph, SCMI_IMX_MISC_CTRL_NOTIFY, + sizeof(*in), 0, &t); + if (ret) + return ret; + + in = t->tx.buf; + in->ctrl_id = cpu_to_le32(ctrl_id); + in->flags = cpu_to_le32(flags); + + ret = ph->xops->do_xfer(ph, t); + + ph->xops->xfer_put(ph, t); + + return ret; +} + +static int +scmi_imx_misc_ctrl_set_notify_enabled(const struct scmi_protocol_handle *ph, + u8 evt_id, u32 src_id, bool enable) +{ + int ret; + + /* misc_ctrl_req_notify is for enablement */ + if (enable) + return 0; + + ret = scmi_imx_misc_ctrl_notify(ph, src_id, evt_id, 0); + if (ret) + dev_err(ph->dev, "FAIL_ENABLED - evt[%X] src[%d] - ret:%d\n", + evt_id, src_id, ret); + + return ret; +} + +static void * +scmi_imx_misc_ctrl_fill_custom_report(const struct scmi_protocol_handle *ph, + u8 evt_id, ktime_t timestamp, + const void *payld, size_t payld_sz, + void *report, u32 *src_id) +{ + const struct scmi_imx_misc_ctrl_notify_payld *p = payld; + struct scmi_imx_misc_ctrl_notify_report *r = report; + + if (sizeof(*p) != payld_sz) + return NULL; + + r->timestamp = timestamp; + r->ctrl_id = le32_to_cpu(p->ctrl_id); + r->flags = le32_to_cpu(p->flags); + if (src_id) + *src_id = r->ctrl_id; + dev_dbg(ph->dev, "%s: ctrl_id: %d flags: %d\n", __func__, + r->ctrl_id, r->flags); + + return r; +} + +static const struct scmi_event_ops scmi_imx_misc_event_ops = { + .set_notify_enabled = scmi_imx_misc_ctrl_set_notify_enabled, + .fill_custom_report = scmi_imx_misc_ctrl_fill_custom_report, +}; + +static const struct scmi_event scmi_imx_misc_events[] = { + { + .id = SCMI_EVENT_IMX_MISC_CONTROL, + .max_payld_sz = sizeof(struct scmi_imx_misc_ctrl_notify_payld), + .max_report_sz = sizeof(struct scmi_imx_misc_ctrl_notify_report), + }, +}; + +static struct scmi_protocol_events scmi_imx_misc_protocol_events = { + .queue_sz = SCMI_PROTO_QUEUE_SZ, + .ops = &scmi_imx_misc_event_ops, + .evts = scmi_imx_misc_events, + .num_events = ARRAY_SIZE(scmi_imx_misc_events), + .num_sources = MAX_MISC_CTRL_SOURCES, +}; + +static int scmi_imx_misc_ctrl_get(const struct scmi_protocol_handle *ph, + u32 ctrl_id, u32 *num, u32 *val) +{ + struct scmi_imx_misc_ctrl_get_out *out; + struct scmi_xfer *t; + int ret, i; + int max_msg_size = ph->hops->get_max_msg_size(ph); + int max_num = (max_msg_size - sizeof(*out)) / sizeof(__le32); + + ret = scmi_imx_misc_ctrl_validate_id(ph, ctrl_id); + if (ret) + return ret; + + ret = ph->xops->xfer_get_init(ph, SCMI_IMX_MISC_CTRL_GET, sizeof(u32), + 0, &t); + if (ret) + return ret; + + put_unaligned_le32(ctrl_id, t->tx.buf); + ret = ph->xops->do_xfer(ph, t); + if (!ret) { + out = t->rx.buf; + *num = le32_to_cpu(out->num); + + if (*num >= max_num || + *num * sizeof(__le32) > t->rx.len - sizeof(__le32)) { + ph->xops->xfer_put(ph, t); + return -EINVAL; + } + + for (i = 0; i < *num; i++) + val[i] = le32_to_cpu(out->val[i]); + } + + ph->xops->xfer_put(ph, t); + + return ret; +} + +static int scmi_imx_misc_ctrl_set(const struct scmi_protocol_handle *ph, + u32 ctrl_id, u32 num, u32 *val) +{ + struct scmi_imx_misc_ctrl_set_in *in; + struct scmi_xfer *t; + int ret, i; + int max_msg_size = ph->hops->get_max_msg_size(ph); + int max_num = (max_msg_size - sizeof(*in)) / sizeof(__le32); + + ret = scmi_imx_misc_ctrl_validate_id(ph, ctrl_id); + if (ret) + return ret; + + if (num > max_num) + return -EINVAL; + + ret = ph->xops->xfer_get_init(ph, SCMI_IMX_MISC_CTRL_SET, sizeof(*in), + 0, &t); + if (ret) + return ret; + + in = t->tx.buf; + in->id = cpu_to_le32(ctrl_id); + in->num = cpu_to_le32(num); + for (i = 0; i < num; i++) + in->value[i] = cpu_to_le32(val[i]); + + ret = ph->xops->do_xfer(ph, t); + + ph->xops->xfer_put(ph, t); + + return ret; +} + +static const struct scmi_imx_misc_proto_ops scmi_imx_misc_proto_ops = { + .misc_ctrl_set = scmi_imx_misc_ctrl_set, + .misc_ctrl_get = scmi_imx_misc_ctrl_get, + .misc_ctrl_req_notify = scmi_imx_misc_ctrl_notify, +}; + +static int scmi_imx_misc_protocol_init(const struct scmi_protocol_handle *ph) +{ + struct scmi_imx_misc_info *minfo; + u32 version; + int ret; + + ret = ph->xops->version_get(ph, &version); + if (ret) + return ret; + + dev_info(ph->dev, "NXP SM MISC Version %d.%d\n", + PROTOCOL_REV_MAJOR(version), PROTOCOL_REV_MINOR(version)); + + minfo = devm_kzalloc(ph->dev, sizeof(*minfo), GFP_KERNEL); + if (!minfo) + return -ENOMEM; + + ret = scmi_imx_misc_attributes_get(ph, minfo); + if (ret) + return ret; + + return ph->set_priv(ph, minfo, version); +} + +static const struct scmi_protocol scmi_imx_misc = { + .id = SCMI_PROTOCOL_IMX_MISC, + .owner = THIS_MODULE, + .instance_init = &scmi_imx_misc_protocol_init, + .ops = &scmi_imx_misc_proto_ops, + .events = &scmi_imx_misc_protocol_events, + .supported_version = SCMI_PROTOCOL_SUPPORTED_VERSION, + .vendor_id = "NXP", + .sub_vendor_id = "IMX", +}; +module_scmi_protocol(scmi_imx_misc); + +MODULE_DESCRIPTION("i.MX SCMI MISC driver"); +MODULE_LICENSE("GPL"); diff --git a/include/linux/scmi_imx_protocol.h b/include/linux/scmi_imx_protocol.h index 2df2ea0f1809..066216f1357a 100644 --- a/include/linux/scmi_imx_protocol.h +++ b/include/linux/scmi_imx_protocol.h @@ -15,6 +15,7 @@ enum scmi_nxp_protocol { SCMI_PROTOCOL_IMX_BBM = 0x81, + SCMI_PROTOCOL_IMX_MISC = 0x84, }; struct scmi_imx_bbm_proto_ops { @@ -30,6 +31,7 @@ struct scmi_imx_bbm_proto_ops { enum scmi_nxp_notification_events { SCMI_EVENT_IMX_BBM_RTC = 0x0, SCMI_EVENT_IMX_BBM_BUTTON = 0x1, + SCMI_EVENT_IMX_MISC_CONTROL = 0x0, }; struct scmi_imx_bbm_notif_report { @@ -39,4 +41,19 @@ struct scmi_imx_bbm_notif_report { unsigned int rtc_id; unsigned int rtc_evt; }; + +struct scmi_imx_misc_ctrl_notify_report { + ktime_t timestamp; + unsigned int ctrl_id; + unsigned int flags; +}; + +struct scmi_imx_misc_proto_ops { + int (*misc_ctrl_set)(const struct scmi_protocol_handle *ph, u32 id, + u32 num, u32 *val); + int (*misc_ctrl_get)(const struct scmi_protocol_handle *ph, u32 id, + u32 *num, u32 *val); + int (*misc_ctrl_req_notify)(const struct scmi_protocol_handle *ph, + u32 ctrl_id, u32 evt_id, u32 flags); +}; #endif -- cgit v1.2.3 From 0b4f8a68b292e7ee82107b1ce15c3aad31c864b1 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Fri, 23 Aug 2024 17:05:21 +0800 Subject: firmware: imx: Add i.MX95 MISC driver The i.MX95 System manager exports SCMI MISC protocol for linux to do various settings, such as set board gpio expander as wakeup source. The driver is to add the support. Reviewed-by: Cristian Marussi Signed-off-by: Peng Fan Message-Id: <20240823-imx95-bbm-misc-v2-v8-5-e600ed9e9271@nxp.com> Signed-off-by: Sudeep Holla --- drivers/firmware/imx/Kconfig | 11 ++++ drivers/firmware/imx/Makefile | 1 + drivers/firmware/imx/sm-misc.c | 119 ++++++++++++++++++++++++++++++++++++++++ include/linux/firmware/imx/sm.h | 34 ++++++++++++ 4 files changed, 165 insertions(+) create mode 100644 drivers/firmware/imx/sm-misc.c create mode 100644 include/linux/firmware/imx/sm.h (limited to 'include/linux') diff --git a/drivers/firmware/imx/Kconfig b/drivers/firmware/imx/Kconfig index 183613f82a11..477d3f32d99a 100644 --- a/drivers/firmware/imx/Kconfig +++ b/drivers/firmware/imx/Kconfig @@ -22,3 +22,14 @@ config IMX_SCU This driver manages the IPC interface between host CPU and the SCU firmware running on M4. + +config IMX_SCMI_MISC_DRV + tristate "IMX SCMI MISC Protocol driver" + depends on IMX_SCMI_MISC_EXT || COMPILE_TEST + default y if ARCH_MXC + help + The System Controller Management Interface firmware (SCMI FW) is + a low-level system function which runs on a dedicated Cortex-M + core that could provide misc functions such as board control. + + This driver can also be built as a module. diff --git a/drivers/firmware/imx/Makefile b/drivers/firmware/imx/Makefile index 8f9f04a513a8..8d046c341be8 100644 --- a/drivers/firmware/imx/Makefile +++ b/drivers/firmware/imx/Makefile @@ -1,3 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_IMX_DSP) += imx-dsp.o obj-$(CONFIG_IMX_SCU) += imx-scu.o misc.o imx-scu-irq.o rm.o imx-scu-soc.o +obj-${CONFIG_IMX_SCMI_MISC_DRV} += sm-misc.o diff --git a/drivers/firmware/imx/sm-misc.c b/drivers/firmware/imx/sm-misc.c new file mode 100644 index 000000000000..fc3ee12c2be8 --- /dev/null +++ b/drivers/firmware/imx/sm-misc.c @@ -0,0 +1,119 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright 2024 NXP + */ + +#include +#include +#include +#include +#include +#include + +static const struct scmi_imx_misc_proto_ops *imx_misc_ctrl_ops; +static struct scmi_protocol_handle *ph; +struct notifier_block scmi_imx_misc_ctrl_nb; + +int scmi_imx_misc_ctrl_set(u32 id, u32 val) +{ + if (!ph) + return -EPROBE_DEFER; + + return imx_misc_ctrl_ops->misc_ctrl_set(ph, id, 1, &val); +}; +EXPORT_SYMBOL(scmi_imx_misc_ctrl_set); + +int scmi_imx_misc_ctrl_get(u32 id, u32 *num, u32 *val) +{ + if (!ph) + return -EPROBE_DEFER; + + return imx_misc_ctrl_ops->misc_ctrl_get(ph, id, num, val); +} +EXPORT_SYMBOL(scmi_imx_misc_ctrl_get); + +static int scmi_imx_misc_ctrl_notifier(struct notifier_block *nb, + unsigned long event, void *data) +{ + /* + * notifier_chain_register requires a valid notifier_block and + * valid notifier_call. SCMI_EVENT_IMX_MISC_CONTROL is needed + * to let SCMI firmware enable control events, but the hook here + * is just a dummy function to avoid kernel panic as of now. + */ + return 0; +} + +static int scmi_imx_misc_ctrl_probe(struct scmi_device *sdev) +{ + const struct scmi_handle *handle = sdev->handle; + struct device_node *np = sdev->dev.of_node; + u32 src_id, flags; + int ret, i, num; + + if (!handle) + return -ENODEV; + + if (imx_misc_ctrl_ops) { + dev_err(&sdev->dev, "misc ctrl already initialized\n"); + return -EEXIST; + } + + imx_misc_ctrl_ops = handle->devm_protocol_get(sdev, SCMI_PROTOCOL_IMX_MISC, &ph); + if (IS_ERR(imx_misc_ctrl_ops)) + return PTR_ERR(imx_misc_ctrl_ops); + + num = of_property_count_u32_elems(np, "nxp,ctrl-ids"); + if (num % 2) { + dev_err(&sdev->dev, "Invalid wakeup-sources\n"); + return -EINVAL; + } + + scmi_imx_misc_ctrl_nb.notifier_call = &scmi_imx_misc_ctrl_notifier; + for (i = 0; i < num; i += 2) { + ret = of_property_read_u32_index(np, "nxp,ctrl-ids", i, &src_id); + if (ret) { + dev_err(&sdev->dev, "Failed to read ctrl-id: %i\n", i); + continue; + } + + ret = of_property_read_u32_index(np, "nxp,ctrl-ids", i + 1, &flags); + if (ret) { + dev_err(&sdev->dev, "Failed to read ctrl-id value: %d\n", i + 1); + continue; + } + + ret = handle->notify_ops->devm_event_notifier_register(sdev, SCMI_PROTOCOL_IMX_MISC, + SCMI_EVENT_IMX_MISC_CONTROL, + &src_id, + &scmi_imx_misc_ctrl_nb); + if (ret) { + dev_err(&sdev->dev, "Failed to register scmi misc event: %d\n", src_id); + } else { + ret = imx_misc_ctrl_ops->misc_ctrl_req_notify(ph, src_id, + SCMI_EVENT_IMX_MISC_CONTROL, + flags); + if (ret) + dev_err(&sdev->dev, "Failed to req notify: %d\n", src_id); + } + } + + return 0; +} + +static const struct scmi_device_id scmi_id_table[] = { + { SCMI_PROTOCOL_IMX_MISC, "imx-misc-ctrl" }, + { }, +}; +MODULE_DEVICE_TABLE(scmi, scmi_id_table); + +static struct scmi_driver scmi_imx_misc_ctrl_driver = { + .name = "scmi-imx-misc-ctrl", + .probe = scmi_imx_misc_ctrl_probe, + .id_table = scmi_id_table, +}; +module_scmi_driver(scmi_imx_misc_ctrl_driver); + +MODULE_AUTHOR("Peng Fan "); +MODULE_DESCRIPTION("IMX SM MISC driver"); +MODULE_LICENSE("GPL"); diff --git a/include/linux/firmware/imx/sm.h b/include/linux/firmware/imx/sm.h new file mode 100644 index 000000000000..62a2690e2abd --- /dev/null +++ b/include/linux/firmware/imx/sm.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright 2024 NXP + */ + +#ifndef _SCMI_IMX_H +#define _SCMI_IMX_H + +#include +#include +#include + +#define SCMI_IMX_CTRL_PDM_CLK_SEL 0 /* AON PDM clock sel */ +#define SCMI_IMX_CTRL_MQS1_SETTINGS 1 /* AON MQS settings */ +#define SCMI_IMX_CTRL_SAI1_MCLK 2 /* AON SAI1 MCLK */ +#define SCMI_IMX_CTRL_SAI3_MCLK 3 /* WAKE SAI3 MCLK */ +#define SCMI_IMX_CTRL_SAI4_MCLK 4 /* WAKE SAI4 MCLK */ +#define SCMI_IMX_CTRL_SAI5_MCLK 5 /* WAKE SAI5 MCLK */ + +#if IS_ENABLED(CONFIG_IMX_SCMI_MISC_EXT) +int scmi_imx_misc_ctrl_get(u32 id, u32 *num, u32 *val); +int scmi_imx_misc_ctrl_set(u32 id, u32 val); +#else +static inline int scmi_imx_misc_ctrl_get(u32 id, u32 *num, u32 *val) +{ + return -EOPNOTSUPP; +} + +static inline int scmi_imx_misc_ctrl_set(u32 id, u32 val); +{ + return -EOPNOTSUPP; +} +#endif +#endif -- cgit v1.2.3 From c42a01264ba1497eb3193c08ff3c2656d98250a6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 19 Jul 2024 06:10:24 +0200 Subject: dma-mapping: don't return errors from dma_set_min_align_mask A NULL dev->dma_parms indicates either a bus that is not DMA capable or grave bug in the implementation of the bus code. There isn't much the driver can do in terms of error handling for either case, so just warn and continue as DMA operations will fail anyway. Signed-off-by: Christoph Hellwig Reviewed-by: Robin Murphy Reviewed-by: Martin K. Petersen --- include/linux/dma-mapping.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index f693aafe221f..cfd6bafec3f9 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -575,13 +575,12 @@ static inline unsigned int dma_get_min_align_mask(struct device *dev) return 0; } -static inline int dma_set_min_align_mask(struct device *dev, +static inline void dma_set_min_align_mask(struct device *dev, unsigned int min_align_mask) { if (WARN_ON_ONCE(!dev->dma_parms)) - return -EIO; + return; dev->dma_parms->min_align_mask = min_align_mask; - return 0; } #ifndef dma_get_cache_alignment -- cgit v1.2.3 From 560a861ab4174b42240157ab5cebe36b8c7bc418 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 19 Jul 2024 06:06:28 +0200 Subject: dma-mapping: don't return errors from dma_set_seg_boundary A NULL dev->dma_parms indicates either a bus that is not DMA capable or grave bug in the implementation of the bus code. There isn't much the driver can do in terms of error handling for either case, so just warn and continue as DMA operations will fail anyway. Signed-off-by: Christoph Hellwig Reviewed-by: Robin Murphy Reviewed-by: Martin K. Petersen --- include/linux/dma-mapping.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index cfd6bafec3f9..6bd1333dbacb 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -559,13 +559,11 @@ static inline unsigned long dma_get_seg_boundary_nr_pages(struct device *dev, return (dma_get_seg_boundary(dev) >> page_shift) + 1; } -static inline int dma_set_seg_boundary(struct device *dev, unsigned long mask) +static inline void dma_set_seg_boundary(struct device *dev, unsigned long mask) { - if (dev->dma_parms) { - dev->dma_parms->segment_boundary_mask = mask; - return 0; - } - return -EIO; + if (WARN_ON_ONCE(!dev->dma_parms)) + return; + dev->dma_parms->segment_boundary_mask = mask; } static inline unsigned int dma_get_min_align_mask(struct device *dev) -- cgit v1.2.3 From 334304ac2baca7f3e821c47cf5129d90e7a6b1e6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 19 Jul 2024 06:07:38 +0200 Subject: dma-mapping: don't return errors from dma_set_max_seg_size A NULL dev->dma_parms indicates either a bus that is not DMA capable or grave bug in the implementation of the bus code. There isn't much the driver can do in terms of error handling for either case, so just warn and continue as DMA operations will fail anyway. Signed-off-by: Christoph Hellwig Reviewed-by: Robin Murphy Reviewed-by: Martin K. Petersen Acked-by: Ulf Hansson # For MMC --- drivers/accel/qaic/qaic_drv.c | 4 +--- drivers/dma/idma64.c | 4 +--- drivers/dma/pl330.c | 5 +---- drivers/dma/qcom/bam_dma.c | 6 +----- drivers/dma/sh/rcar-dmac.c | 4 +--- drivers/dma/ste_dma40.c | 6 +----- drivers/gpu/drm/mediatek/mtk_drm_drv.c | 6 +----- drivers/media/common/videobuf2/videobuf2-dma-contig.c | 3 +-- drivers/media/pci/intel/ipu6/ipu6.c | 4 +--- drivers/mmc/host/mmci_stm32_sdmmc.c | 3 ++- drivers/net/ethernet/microsoft/mana/gdma_main.c | 6 +----- drivers/scsi/lpfc/lpfc_init.c | 7 +------ include/linux/dma-mapping.h | 10 ++++------ 13 files changed, 17 insertions(+), 51 deletions(-) (limited to 'include/linux') diff --git a/drivers/accel/qaic/qaic_drv.c b/drivers/accel/qaic/qaic_drv.c index 580b29ed1902..bf10156c334e 100644 --- a/drivers/accel/qaic/qaic_drv.c +++ b/drivers/accel/qaic/qaic_drv.c @@ -447,9 +447,7 @@ static int init_pci(struct qaic_device *qdev, struct pci_dev *pdev) ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (ret) return ret; - ret = dma_set_max_seg_size(&pdev->dev, UINT_MAX); - if (ret) - return ret; + dma_set_max_seg_size(&pdev->dev, UINT_MAX); qdev->bar_0 = devm_ioremap_resource(&pdev->dev, &pdev->resource[0]); if (IS_ERR(qdev->bar_0)) diff --git a/drivers/dma/idma64.c b/drivers/dma/idma64.c index e3505e56784b..1398814d8fbb 100644 --- a/drivers/dma/idma64.c +++ b/drivers/dma/idma64.c @@ -598,9 +598,7 @@ static int idma64_probe(struct idma64_chip *chip) idma64->dma.dev = chip->sysdev; - ret = dma_set_max_seg_size(idma64->dma.dev, IDMA64C_CTLH_BLOCK_TS_MASK); - if (ret) - return ret; + dma_set_max_seg_size(idma64->dma.dev, IDMA64C_CTLH_BLOCK_TS_MASK); ret = dma_async_device_register(&idma64->dma); if (ret) diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index 60c4de8dac1d..82a9fe88ad54 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -3163,10 +3163,7 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id) * This is the limit for transfers with a buswidth of 1, larger * buswidths will have larger limits. */ - ret = dma_set_max_seg_size(&adev->dev, 1900800); - if (ret) - dev_err(&adev->dev, "unable to set the seg size\n"); - + dma_set_max_seg_size(&adev->dev, 1900800); init_pl330_debugfs(pl330); dev_info(&adev->dev, diff --git a/drivers/dma/qcom/bam_dma.c b/drivers/dma/qcom/bam_dma.c index 5e7d332731e0..368ffaa40037 100644 --- a/drivers/dma/qcom/bam_dma.c +++ b/drivers/dma/qcom/bam_dma.c @@ -1325,11 +1325,7 @@ static int bam_dma_probe(struct platform_device *pdev) /* set max dma segment size */ bdev->common.dev = bdev->dev; - ret = dma_set_max_seg_size(bdev->common.dev, BAM_FIFO_SIZE); - if (ret) { - dev_err(bdev->dev, "cannot set maximum segment size\n"); - goto err_bam_channel_exit; - } + dma_set_max_seg_size(bdev->common.dev, BAM_FIFO_SIZE); platform_set_drvdata(pdev, bdev); diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c index 40482cb73d79..1094a2f82164 100644 --- a/drivers/dma/sh/rcar-dmac.c +++ b/drivers/dma/sh/rcar-dmac.c @@ -1868,9 +1868,7 @@ static int rcar_dmac_probe(struct platform_device *pdev) dmac->dev = &pdev->dev; platform_set_drvdata(pdev, dmac); - ret = dma_set_max_seg_size(dmac->dev, RCAR_DMATCR_MASK); - if (ret) - return ret; + dma_set_max_seg_size(dmac->dev, RCAR_DMATCR_MASK); ret = dma_set_mask_and_coherent(dmac->dev, DMA_BIT_MASK(40)); if (ret) diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c index 2c489299148e..d52e1685aed5 100644 --- a/drivers/dma/ste_dma40.c +++ b/drivers/dma/ste_dma40.c @@ -3632,11 +3632,7 @@ static int __init d40_probe(struct platform_device *pdev) if (ret) goto destroy_cache; - ret = dma_set_max_seg_size(base->dev, STEDMA40_MAX_SEG_SIZE); - if (ret) { - d40_err(dev, "Failed to set dma max seg size\n"); - goto destroy_cache; - } + dma_set_max_seg_size(base->dev, STEDMA40_MAX_SEG_SIZE); d40_hw_init(base); diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index 77b50c56c124..3e807195a0d0 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -559,11 +559,7 @@ static int mtk_drm_kms_init(struct drm_device *drm) * Configure the DMA segment size to make sure we get contiguous IOVA * when importing PRIME buffers. */ - ret = dma_set_max_seg_size(dma_dev, UINT_MAX); - if (ret) { - dev_err(dma_dev, "Failed to set DMA segment size\n"); - goto err_component_unbind; - } + dma_set_max_seg_size(dma_dev, UINT_MAX); ret = drm_vblank_init(drm, MAX_CRTC); if (ret < 0) diff --git a/drivers/media/common/videobuf2/videobuf2-dma-contig.c b/drivers/media/common/videobuf2/videobuf2-dma-contig.c index 3d4fd4ef5310..bb0b7fa67b53 100644 --- a/drivers/media/common/videobuf2/videobuf2-dma-contig.c +++ b/drivers/media/common/videobuf2/videobuf2-dma-contig.c @@ -854,8 +854,7 @@ int vb2_dma_contig_set_max_seg_size(struct device *dev, unsigned int size) return -ENODEV; } if (dma_get_max_seg_size(dev) < size) - return dma_set_max_seg_size(dev, size); - + dma_set_max_seg_size(dev, size); return 0; } EXPORT_SYMBOL_GPL(vb2_dma_contig_set_max_seg_size); diff --git a/drivers/media/pci/intel/ipu6/ipu6.c b/drivers/media/pci/intel/ipu6/ipu6.c index bbd646378ab3..83e70c692d95 100644 --- a/drivers/media/pci/intel/ipu6/ipu6.c +++ b/drivers/media/pci/intel/ipu6/ipu6.c @@ -576,9 +576,7 @@ static int ipu6_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (ret) return dev_err_probe(dev, ret, "Failed to set DMA mask\n"); - ret = dma_set_max_seg_size(dev, UINT_MAX); - if (ret) - return dev_err_probe(dev, ret, "Failed to set max_seg_size\n"); + dma_set_max_seg_size(dev, UINT_MAX); ret = ipu6_pci_config_setup(pdev, isp->hw_ver); if (ret) diff --git a/drivers/mmc/host/mmci_stm32_sdmmc.c b/drivers/mmc/host/mmci_stm32_sdmmc.c index f5da7f9baa52..9dc51859c2e5 100644 --- a/drivers/mmc/host/mmci_stm32_sdmmc.c +++ b/drivers/mmc/host/mmci_stm32_sdmmc.c @@ -213,7 +213,8 @@ static int sdmmc_idma_setup(struct mmci_host *host) host->mmc->max_seg_size = host->mmc->max_req_size; } - return dma_set_max_seg_size(dev, host->mmc->max_seg_size); + dma_set_max_seg_size(dev, host->mmc->max_seg_size); + return 0; } static int sdmmc_idma_start(struct mmci_host *host, unsigned int *datactrl) diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index ddb8f68d80a2..ca4ed58f1206 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -1496,11 +1496,7 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) goto release_region; - err = dma_set_max_seg_size(&pdev->dev, UINT_MAX); - if (err) { - dev_err(&pdev->dev, "Failed to set dma device segment size\n"); - goto release_region; - } + dma_set_max_seg_size(&pdev->dev, UINT_MAX); err = -ENOMEM; gc = vzalloc(sizeof(*gc)); diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index e1dfa96c2a55..50620918becd 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -13861,12 +13861,7 @@ fcponly: if (sli4_params->sge_supp_len > LPFC_MAX_SGE_SIZE) sli4_params->sge_supp_len = LPFC_MAX_SGE_SIZE; - rc = dma_set_max_seg_size(&phba->pcidev->dev, sli4_params->sge_supp_len); - if (unlikely(rc)) { - lpfc_printf_log(phba, KERN_INFO, LOG_INIT, - "6400 Can't set dma maximum segment size\n"); - return rc; - } + dma_set_max_seg_size(&phba->pcidev->dev, sli4_params->sge_supp_len); /* * Check whether the adapter supports an embedded copy of the diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 6bd1333dbacb..1524da363734 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -524,13 +524,11 @@ static inline unsigned int dma_get_max_seg_size(struct device *dev) return SZ_64K; } -static inline int dma_set_max_seg_size(struct device *dev, unsigned int size) +static inline void dma_set_max_seg_size(struct device *dev, unsigned int size) { - if (dev->dma_parms) { - dev->dma_parms->max_segment_size = size; - return 0; - } - return -EIO; + if (WARN_ON_ONCE(!dev->dma_parms)) + return; + dev->dma_parms->max_segment_size = size; } static inline unsigned long dma_get_seg_boundary(struct device *dev) -- cgit v1.2.3 From b31c9d9dc343146b9f4ce67b4eee748c49296e99 Mon Sep 17 00:00:00 2001 From: Peter Hutterer Date: Tue, 27 Aug 2024 17:19:29 +0900 Subject: HID: hidraw: add HIDIOCREVOKE ioctl There is a need for userspace applications to open HID devices directly. Use-cases include configuration of gaming mice or direct access to joystick devices. The latter is currently handled by the uaccess tag in systemd, other devices include more custom/local configurations or just sudo. A better approach is what we already have for evdev devices: give the application a file descriptor and revoke it when it may no longer access that device. This patch is the hidraw equivalent to the EVIOCREVOKE ioctl, see commit c7dc65737c9a ("Input: evdev - add EVIOCREVOKE ioctl") for full details. An MR for systemd-logind has been filed here: https://github.com/systemd/systemd/pull/33970 Signed-off-by: Peter Hutterer Link: https://patch.msgid.link/20240827-hidraw-revoke-v5-1-d004a7451aea@kernel.org Signed-off-by: Benjamin Tissoires --- drivers/hid/hidraw.c | 39 +++++++++++++++++++++++++++++++++++---- include/linux/hidraw.h | 1 + include/uapi/linux/hidraw.h | 1 + 3 files changed, 37 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c index 716294e40e8a..c887f48756f4 100644 --- a/drivers/hid/hidraw.c +++ b/drivers/hid/hidraw.c @@ -38,12 +38,20 @@ static const struct class hidraw_class = { static struct hidraw *hidraw_table[HIDRAW_MAX_DEVICES]; static DECLARE_RWSEM(minors_rwsem); +static inline bool hidraw_is_revoked(struct hidraw_list *list) +{ + return list->revoked; +} + static ssize_t hidraw_read(struct file *file, char __user *buffer, size_t count, loff_t *ppos) { struct hidraw_list *list = file->private_data; int ret = 0, len; DECLARE_WAITQUEUE(wait, current); + if (hidraw_is_revoked(list)) + return -ENODEV; + mutex_lock(&list->read_mutex); while (ret == 0) { @@ -161,9 +169,13 @@ out: static ssize_t hidraw_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { + struct hidraw_list *list = file->private_data; ssize_t ret; down_read(&minors_rwsem); - ret = hidraw_send_report(file, buffer, count, HID_OUTPUT_REPORT); + if (hidraw_is_revoked(list)) + ret = -ENODEV; + else + ret = hidraw_send_report(file, buffer, count, HID_OUTPUT_REPORT); up_read(&minors_rwsem); return ret; } @@ -256,7 +268,7 @@ static __poll_t hidraw_poll(struct file *file, poll_table *wait) poll_wait(file, &list->hidraw->wait, wait); if (list->head != list->tail) mask |= EPOLLIN | EPOLLRDNORM; - if (!list->hidraw->exist) + if (!list->hidraw->exist || hidraw_is_revoked(list)) mask |= EPOLLERR | EPOLLHUP; return mask; } @@ -320,6 +332,9 @@ static int hidraw_fasync(int fd, struct file *file, int on) { struct hidraw_list *list = file->private_data; + if (hidraw_is_revoked(list)) + return -ENODEV; + return fasync_helper(fd, file, on, &list->fasync); } @@ -372,6 +387,13 @@ static int hidraw_release(struct inode * inode, struct file * file) return 0; } +static int hidraw_revoke(struct hidraw_list *list) +{ + list->revoked = true; + + return 0; +} + static long hidraw_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -379,11 +401,12 @@ static long hidraw_ioctl(struct file *file, unsigned int cmd, unsigned int minor = iminor(inode); long ret = 0; struct hidraw *dev; + struct hidraw_list *list = file->private_data; void __user *user_arg = (void __user*) arg; down_read(&minors_rwsem); dev = hidraw_table[minor]; - if (!dev || !dev->exist) { + if (!dev || !dev->exist || hidraw_is_revoked(list)) { ret = -ENODEV; goto out; } @@ -421,6 +444,14 @@ static long hidraw_ioctl(struct file *file, unsigned int cmd, ret = -EFAULT; break; } + case HIDIOCREVOKE: + { + if (user_arg) + ret = -EINVAL; + else + ret = hidraw_revoke(list); + break; + } default: { struct hid_device *hid = dev->hid; @@ -527,7 +558,7 @@ int hidraw_report_event(struct hid_device *hid, u8 *data, int len) list_for_each_entry(list, &dev->list, node) { int new_head = (list->head + 1) & (HIDRAW_BUFFER_SIZE - 1); - if (new_head == list->tail) + if (hidraw_is_revoked(list) || new_head == list->tail) continue; if (!(list->buffer[list->head].value = kmemdup(data, len, GFP_ATOMIC))) { diff --git a/include/linux/hidraw.h b/include/linux/hidraw.h index cd67f4ca5599..18fd30a288de 100644 --- a/include/linux/hidraw.h +++ b/include/linux/hidraw.h @@ -32,6 +32,7 @@ struct hidraw_list { struct hidraw *hidraw; struct list_head node; struct mutex read_mutex; + bool revoked; }; #ifdef CONFIG_HIDRAW diff --git a/include/uapi/linux/hidraw.h b/include/uapi/linux/hidraw.h index 33ebad81720a..d5ee269864e0 100644 --- a/include/uapi/linux/hidraw.h +++ b/include/uapi/linux/hidraw.h @@ -46,6 +46,7 @@ struct hidraw_devinfo { /* The first byte of SOUTPUT and GOUTPUT is the report number */ #define HIDIOCSOUTPUT(len) _IOC(_IOC_WRITE|_IOC_READ, 'H', 0x0B, len) #define HIDIOCGOUTPUT(len) _IOC(_IOC_WRITE|_IOC_READ, 'H', 0x0C, len) +#define HIDIOCREVOKE _IOW('H', 0x0D, int) /* Revoke device access */ #define HIDRAW_FIRST_MINOR 0 #define HIDRAW_MAX_DEVICES 64 -- cgit v1.2.3 From b35243a447b9fe6457fa8e1352152b818436ba5a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 26 Aug 2024 19:37:54 +0200 Subject: block: rework bio splitting The current setup with bio_may_exceed_limit and __bio_split_to_limits is a bit of a mess. Change it so that __bio_split_to_limits does all the work and is just a variant of bio_split_to_limits that returns nr_segs. This is done by inlining it and instead have the various bio_split_* helpers directly submit the potentially split bios. To support btrfs, the rw version has a lower level helper split out that just returns the offset to split. This turns out to nicely clean up the btrfs flow as well. Signed-off-by: Christoph Hellwig Acked-by: David Sterba Reviewed-by: Damien Le Moal Tested-by: Hans Holmberg Reviewed-by: Hans Holmberg Link: https://lore.kernel.org/r/20240826173820.1690925-2-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-merge.c | 146 ++++++++++++++++++++-------------------------------- block/blk-mq.c | 11 ++-- block/blk.h | 63 ++++++++++++++++------- fs/btrfs/bio.c | 30 ++++++----- include/linux/bio.h | 4 +- 5 files changed, 125 insertions(+), 129 deletions(-) (limited to 'include/linux') diff --git a/block/blk-merge.c b/block/blk-merge.c index de5281bcadc5..c7222c4685e0 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -105,9 +105,33 @@ static unsigned int bio_allowed_max_sectors(const struct queue_limits *lim) return round_down(UINT_MAX, lim->logical_block_size) >> SECTOR_SHIFT; } -static struct bio *bio_split_discard(struct bio *bio, - const struct queue_limits *lim, - unsigned *nsegs, struct bio_set *bs) +static struct bio *bio_submit_split(struct bio *bio, int split_sectors) +{ + if (unlikely(split_sectors < 0)) { + bio->bi_status = errno_to_blk_status(split_sectors); + bio_endio(bio); + return NULL; + } + + if (split_sectors) { + struct bio *split; + + split = bio_split(bio, split_sectors, GFP_NOIO, + &bio->bi_bdev->bd_disk->bio_split); + split->bi_opf |= REQ_NOMERGE; + blkcg_bio_issue_init(split); + bio_chain(split, bio); + trace_block_split(split, bio->bi_iter.bi_sector); + WARN_ON_ONCE(bio_zone_write_plugging(bio)); + submit_bio_noacct(bio); + return split; + } + + return bio; +} + +struct bio *bio_split_discard(struct bio *bio, const struct queue_limits *lim, + unsigned *nsegs) { unsigned int max_discard_sectors, granularity; sector_t tmp; @@ -121,10 +145,10 @@ static struct bio *bio_split_discard(struct bio *bio, min(lim->max_discard_sectors, bio_allowed_max_sectors(lim)); max_discard_sectors -= max_discard_sectors % granularity; if (unlikely(!max_discard_sectors)) - return NULL; + return bio; if (bio_sectors(bio) <= max_discard_sectors) - return NULL; + return bio; split_sectors = max_discard_sectors; @@ -139,19 +163,18 @@ static struct bio *bio_split_discard(struct bio *bio, if (split_sectors > tmp) split_sectors -= tmp; - return bio_split(bio, split_sectors, GFP_NOIO, bs); + return bio_submit_split(bio, split_sectors); } -static struct bio *bio_split_write_zeroes(struct bio *bio, - const struct queue_limits *lim, - unsigned *nsegs, struct bio_set *bs) +struct bio *bio_split_write_zeroes(struct bio *bio, + const struct queue_limits *lim, unsigned *nsegs) { *nsegs = 0; if (!lim->max_write_zeroes_sectors) - return NULL; + return bio; if (bio_sectors(bio) <= lim->max_write_zeroes_sectors) - return NULL; - return bio_split(bio, lim->max_write_zeroes_sectors, GFP_NOIO, bs); + return bio; + return bio_submit_split(bio, lim->max_write_zeroes_sectors); } static inline unsigned int blk_boundary_sectors(const struct queue_limits *lim, @@ -274,27 +297,19 @@ static bool bvec_split_segs(const struct queue_limits *lim, } /** - * bio_split_rw - split a bio in two bios + * bio_split_rw_at - check if and where to split a read/write bio * @bio: [in] bio to be split * @lim: [in] queue limits to split based on * @segs: [out] number of segments in the bio with the first half of the sectors - * @bs: [in] bio set to allocate the clone from * @max_bytes: [in] maximum number of bytes per bio * - * Clone @bio, update the bi_iter of the clone to represent the first sectors - * of @bio and update @bio->bi_iter to represent the remaining sectors. The - * following is guaranteed for the cloned bio: - * - That it has at most @max_bytes worth of data - * - That it has at most queue_max_segments(@q) segments. - * - * Except for discard requests the cloned bio will point at the bi_io_vec of - * the original bio. It is the responsibility of the caller to ensure that the - * original bio is not freed before the cloned bio. The caller is also - * responsible for ensuring that @bs is only destroyed after processing of the - * split bio has finished. + * Find out if @bio needs to be split to fit the queue limits in @lim and a + * maximum size of @max_bytes. Returns a negative error number if @bio can't be + * split, 0 if the bio doesn't have to be split, or a positive sector offset if + * @bio needs to be split. */ -struct bio *bio_split_rw(struct bio *bio, const struct queue_limits *lim, - unsigned *segs, struct bio_set *bs, unsigned max_bytes) +int bio_split_rw_at(struct bio *bio, const struct queue_limits *lim, + unsigned *segs, unsigned max_bytes) { struct bio_vec bv, bvprv, *bvprvp = NULL; struct bvec_iter iter; @@ -324,22 +339,17 @@ struct bio *bio_split_rw(struct bio *bio, const struct queue_limits *lim, } *segs = nsegs; - return NULL; + return 0; split: - if (bio->bi_opf & REQ_ATOMIC) { - bio->bi_status = BLK_STS_INVAL; - bio_endio(bio); - return ERR_PTR(-EINVAL); - } + if (bio->bi_opf & REQ_ATOMIC) + return -EINVAL; + /* * We can't sanely support splitting for a REQ_NOWAIT bio. End it * with EAGAIN if splitting is required and return an error pointer. */ - if (bio->bi_opf & REQ_NOWAIT) { - bio->bi_status = BLK_STS_AGAIN; - bio_endio(bio); - return ERR_PTR(-EAGAIN); - } + if (bio->bi_opf & REQ_NOWAIT) + return -EAGAIN; *segs = nsegs; @@ -356,58 +366,16 @@ split: * big IO can be trival, disable iopoll when split needed. */ bio_clear_polled(bio); - return bio_split(bio, bytes >> SECTOR_SHIFT, GFP_NOIO, bs); + return bytes >> SECTOR_SHIFT; } -EXPORT_SYMBOL_GPL(bio_split_rw); +EXPORT_SYMBOL_GPL(bio_split_rw_at); -/** - * __bio_split_to_limits - split a bio to fit the queue limits - * @bio: bio to be split - * @lim: queue limits to split based on - * @nr_segs: returns the number of segments in the returned bio - * - * Check if @bio needs splitting based on the queue limits, and if so split off - * a bio fitting the limits from the beginning of @bio and return it. @bio is - * shortened to the remainder and re-submitted. - * - * The split bio is allocated from @q->bio_split, which is provided by the - * block layer. - */ -struct bio *__bio_split_to_limits(struct bio *bio, - const struct queue_limits *lim, - unsigned int *nr_segs) +struct bio *bio_split_rw(struct bio *bio, const struct queue_limits *lim, + unsigned *nr_segs) { - struct bio_set *bs = &bio->bi_bdev->bd_disk->bio_split; - struct bio *split; - - switch (bio_op(bio)) { - case REQ_OP_DISCARD: - case REQ_OP_SECURE_ERASE: - split = bio_split_discard(bio, lim, nr_segs, bs); - break; - case REQ_OP_WRITE_ZEROES: - split = bio_split_write_zeroes(bio, lim, nr_segs, bs); - break; - default: - split = bio_split_rw(bio, lim, nr_segs, bs, - get_max_io_size(bio, lim) << SECTOR_SHIFT); - if (IS_ERR(split)) - return NULL; - break; - } - - if (split) { - /* there isn't chance to merge the split bio */ - split->bi_opf |= REQ_NOMERGE; - - blkcg_bio_issue_init(split); - bio_chain(split, bio); - trace_block_split(split, bio->bi_iter.bi_sector); - WARN_ON_ONCE(bio_zone_write_plugging(bio)); - submit_bio_noacct(bio); - return split; - } - return bio; + return bio_submit_split(bio, + bio_split_rw_at(bio, lim, nr_segs, + get_max_io_size(bio, lim) << SECTOR_SHIFT)); } /** @@ -426,9 +394,7 @@ struct bio *bio_split_to_limits(struct bio *bio) const struct queue_limits *lim = &bdev_get_queue(bio->bi_bdev)->limits; unsigned int nr_segs; - if (bio_may_exceed_limits(bio, lim)) - return __bio_split_to_limits(bio, lim, &nr_segs); - return bio; + return __bio_split_to_limits(bio, lim, &nr_segs); } EXPORT_SYMBOL(bio_split_to_limits); diff --git a/block/blk-mq.c b/block/blk-mq.c index e3c3c0c21b55..36abbaefe387 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2939,7 +2939,7 @@ void blk_mq_submit_bio(struct bio *bio) struct blk_plug *plug = current->plug; const int is_sync = op_is_sync(bio->bi_opf); struct blk_mq_hw_ctx *hctx; - unsigned int nr_segs = 1; + unsigned int nr_segs; struct request *rq; blk_status_t ret; @@ -2981,11 +2981,10 @@ void blk_mq_submit_bio(struct bio *bio) goto queue_exit; } - if (unlikely(bio_may_exceed_limits(bio, &q->limits))) { - bio = __bio_split_to_limits(bio, &q->limits, &nr_segs); - if (!bio) - goto queue_exit; - } + bio = __bio_split_to_limits(bio, &q->limits, &nr_segs); + if (!bio) + goto queue_exit; + if (!bio_integrity_prep(bio)) goto queue_exit; diff --git a/block/blk.h b/block/blk.h index e180863f918b..0d8cd64c1260 100644 --- a/block/blk.h +++ b/block/blk.h @@ -331,33 +331,58 @@ ssize_t part_timeout_show(struct device *, struct device_attribute *, char *); ssize_t part_timeout_store(struct device *, struct device_attribute *, const char *, size_t); -static inline bool bio_may_exceed_limits(struct bio *bio, - const struct queue_limits *lim) +struct bio *bio_split_discard(struct bio *bio, const struct queue_limits *lim, + unsigned *nsegs); +struct bio *bio_split_write_zeroes(struct bio *bio, + const struct queue_limits *lim, unsigned *nsegs); +struct bio *bio_split_rw(struct bio *bio, const struct queue_limits *lim, + unsigned *nr_segs); + +/* + * All drivers must accept single-segments bios that are smaller than PAGE_SIZE. + * + * This is a quick and dirty check that relies on the fact that bi_io_vec[0] is + * always valid if a bio has data. The check might lead to occasional false + * positives when bios are cloned, but compared to the performance impact of + * cloned bios themselves the loop below doesn't matter anyway. + */ +static inline bool bio_may_need_split(struct bio *bio, + const struct queue_limits *lim) +{ + return lim->chunk_sectors || bio->bi_vcnt != 1 || + bio->bi_io_vec->bv_len + bio->bi_io_vec->bv_offset > PAGE_SIZE; +} + +/** + * __bio_split_to_limits - split a bio to fit the queue limits + * @bio: bio to be split + * @lim: queue limits to split based on + * @nr_segs: returns the number of segments in the returned bio + * + * Check if @bio needs splitting based on the queue limits, and if so split off + * a bio fitting the limits from the beginning of @bio and return it. @bio is + * shortened to the remainder and re-submitted. + * + * The split bio is allocated from @q->bio_split, which is provided by the + * block layer. + */ +static inline struct bio *__bio_split_to_limits(struct bio *bio, + const struct queue_limits *lim, unsigned int *nr_segs) { switch (bio_op(bio)) { + default: + if (bio_may_need_split(bio, lim)) + return bio_split_rw(bio, lim, nr_segs); + *nr_segs = 1; + return bio; case REQ_OP_DISCARD: case REQ_OP_SECURE_ERASE: + return bio_split_discard(bio, lim, nr_segs); case REQ_OP_WRITE_ZEROES: - return true; /* non-trivial splitting decisions */ - default: - break; + return bio_split_write_zeroes(bio, lim, nr_segs); } - - /* - * All drivers must accept single-segments bios that are <= PAGE_SIZE. - * This is a quick and dirty check that relies on the fact that - * bi_io_vec[0] is always valid if a bio has data. The check might - * lead to occasional false negatives when bios are cloned, but compared - * to the performance impact of cloned bios themselves the loop below - * doesn't matter anyway. - */ - return lim->chunk_sectors || bio->bi_vcnt != 1 || - bio->bi_io_vec->bv_len + bio->bi_io_vec->bv_offset > PAGE_SIZE; } -struct bio *__bio_split_to_limits(struct bio *bio, - const struct queue_limits *lim, - unsigned int *nr_segs); int ll_back_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs); bool blk_attempt_req_merge(struct request_queue *q, struct request *rq, diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c index f04d93109960..5ae769184907 100644 --- a/fs/btrfs/bio.c +++ b/fs/btrfs/bio.c @@ -73,20 +73,13 @@ struct btrfs_bio *btrfs_bio_alloc(unsigned int nr_vecs, blk_opf_t opf, static struct btrfs_bio *btrfs_split_bio(struct btrfs_fs_info *fs_info, struct btrfs_bio *orig_bbio, - u64 map_length, bool use_append) + u64 map_length) { struct btrfs_bio *bbio; struct bio *bio; - if (use_append) { - unsigned int nr_segs; - - bio = bio_split_rw(&orig_bbio->bio, &fs_info->limits, &nr_segs, - &btrfs_clone_bioset, map_length); - } else { - bio = bio_split(&orig_bbio->bio, map_length >> SECTOR_SHIFT, - GFP_NOFS, &btrfs_clone_bioset); - } + bio = bio_split(&orig_bbio->bio, map_length >> SECTOR_SHIFT, GFP_NOFS, + &btrfs_clone_bioset); bbio = btrfs_bio(bio); btrfs_bio_init(bbio, fs_info, NULL, orig_bbio); bbio->inode = orig_bbio->inode; @@ -664,6 +657,19 @@ static bool btrfs_wq_submit_bio(struct btrfs_bio *bbio, return true; } +static u64 btrfs_append_map_length(struct btrfs_bio *bbio, u64 map_length) +{ + unsigned int nr_segs; + int sector_offset; + + map_length = min(map_length, bbio->fs_info->max_zone_append_size); + sector_offset = bio_split_rw_at(&bbio->bio, &bbio->fs_info->limits, + &nr_segs, map_length); + if (sector_offset) + return sector_offset << SECTOR_SHIFT; + return map_length; +} + static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num) { struct btrfs_inode *inode = bbio->inode; @@ -691,10 +697,10 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num) map_length = min(map_length, length); if (use_append) - map_length = min(map_length, fs_info->max_zone_append_size); + map_length = btrfs_append_map_length(bbio, map_length); if (map_length < length) { - bbio = btrfs_split_bio(fs_info, bbio, map_length, use_append); + bbio = btrfs_split_bio(fs_info, bbio, map_length); bio = &bbio->bio; } diff --git a/include/linux/bio.h b/include/linux/bio.h index a46e2047bea4..faceadb040f9 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -324,8 +324,8 @@ static inline void bio_next_folio(struct folio_iter *fi, struct bio *bio) void bio_trim(struct bio *bio, sector_t offset, sector_t size); extern struct bio *bio_split(struct bio *bio, int sectors, gfp_t gfp, struct bio_set *bs); -struct bio *bio_split_rw(struct bio *bio, const struct queue_limits *lim, - unsigned *segs, struct bio_set *bs, unsigned max_bytes); +int bio_split_rw_at(struct bio *bio, const struct queue_limits *lim, + unsigned *segs, unsigned max_bytes); /** * bio_next_split - get next @sectors from a bio, splitting if necessary -- cgit v1.2.3 From 379b122a3ec8033aa43cb70e8ecb6fb7f98aa68f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 26 Aug 2024 19:37:55 +0200 Subject: block: constify the lim argument to queue_limits_max_zone_append_sectors queue_limits_max_zone_append_sectors doesn't change the lim argument, so mark it as const. Signed-off-by: Christoph Hellwig Reviewed-by: Damien Le Moal Tested-by: Hans Holmberg Reviewed-by: Hans Holmberg Link: https://lore.kernel.org/r/20240826173820.1690925-3-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e85ec73a07d5..ec3ea5d1f99d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1187,7 +1187,8 @@ static inline unsigned int queue_max_segment_size(const struct request_queue *q) return q->limits.max_segment_size; } -static inline unsigned int queue_limits_max_zone_append_sectors(struct queue_limits *l) +static inline unsigned int +queue_limits_max_zone_append_sectors(const struct queue_limits *l) { unsigned int max_sectors = min(l->chunk_sectors, l->max_hw_sectors); -- cgit v1.2.3 From 2e1a57d5b0adbb5bd1d85245ec29b6d3cc7edc69 Mon Sep 17 00:00:00 2001 From: Chris Morgan Date: Wed, 21 Aug 2024 16:54:52 -0500 Subject: mfd: axp20x: Add ADC, BAT, and USB cells for AXP717 Add support for the AXP717 PMIC to utilize the ADC (for reading voltage, current, and temperature information from the PMIC) as well as the USB charger and battery. Signed-off-by: Chris Morgan Link: https://lore.kernel.org/r/20240821215456.962564-12-macroalpha82@gmail.com Signed-off-by: Lee Jones --- drivers/mfd/axp20x.c | 25 ++++++++++++++++++++++++- include/linux/mfd/axp20x.h | 26 ++++++++++++++++++++++++++ 2 files changed, 50 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/mfd/axp20x.c b/drivers/mfd/axp20x.c index dacd3c96c9f5..4051551757f2 100644 --- a/drivers/mfd/axp20x.c +++ b/drivers/mfd/axp20x.c @@ -209,13 +209,23 @@ static const struct regmap_access_table axp313a_volatile_table = { }; static const struct regmap_range axp717_writeable_ranges[] = { + regmap_reg_range(AXP717_PMU_FAULT, AXP717_MODULE_EN_CONTROL_1), + regmap_reg_range(AXP717_MIN_SYS_V_CONTROL, AXP717_BOOST_CONTROL), + regmap_reg_range(AXP717_VSYS_V_POWEROFF, AXP717_VSYS_V_POWEROFF), regmap_reg_range(AXP717_IRQ0_EN, AXP717_IRQ4_EN), regmap_reg_range(AXP717_IRQ0_STATE, AXP717_IRQ4_STATE), + regmap_reg_range(AXP717_ICC_CHG_SET, AXP717_CV_CHG_SET), regmap_reg_range(AXP717_DCDC_OUTPUT_CONTROL, AXP717_CPUSLDO_CONTROL), + regmap_reg_range(AXP717_ADC_CH_EN_CONTROL, AXP717_ADC_CH_EN_CONTROL), + regmap_reg_range(AXP717_ADC_DATA_SEL, AXP717_ADC_DATA_SEL), }; static const struct regmap_range axp717_volatile_ranges[] = { + regmap_reg_range(AXP717_ON_INDICATE, AXP717_PMU_FAULT), regmap_reg_range(AXP717_IRQ0_STATE, AXP717_IRQ4_STATE), + regmap_reg_range(AXP717_BATT_PERCENT_DATA, AXP717_BATT_PERCENT_DATA), + regmap_reg_range(AXP717_BATT_V_H, AXP717_BATT_CHRG_I_L), + regmap_reg_range(AXP717_ADC_DATA_H, AXP717_ADC_DATA_L), }; static const struct regmap_access_table axp717_writeable_table = { @@ -308,6 +318,12 @@ static const struct resource axp22x_usb_power_supply_resources[] = { DEFINE_RES_IRQ_NAMED(AXP22X_IRQ_VBUS_REMOVAL, "VBUS_REMOVAL"), }; +static const struct resource axp717_usb_power_supply_resources[] = { + DEFINE_RES_IRQ_NAMED(AXP717_IRQ_VBUS_OVER_V, "VBUS_OVER_V"), + DEFINE_RES_IRQ_NAMED(AXP717_IRQ_VBUS_PLUGIN, "VBUS_PLUGIN"), + DEFINE_RES_IRQ_NAMED(AXP717_IRQ_VBUS_REMOVAL, "VBUS_REMOVAL"), +}; + /* AXP803 and AXP813/AXP818 share the same interrupts */ static const struct resource axp803_usb_power_supply_resources[] = { DEFINE_RES_IRQ_NAMED(AXP803_IRQ_VBUS_PLUGIN, "VBUS_PLUGIN"), @@ -422,7 +438,7 @@ static const struct regmap_config axp717_regmap_config = { .val_bits = 8, .wr_table = &axp717_writeable_table, .volatile_table = &axp717_volatile_table, - .max_register = AXP717_CPUSLDO_CONTROL, + .max_register = AXP717_ADC_DATA_L, .cache_type = REGCACHE_MAPLE, }; @@ -1024,6 +1040,13 @@ static struct mfd_cell axp313a_cells[] = { static struct mfd_cell axp717_cells[] = { MFD_CELL_NAME("axp20x-regulator"), MFD_CELL_RES("axp20x-pek", axp717_pek_resources), + MFD_CELL_OF("axp717-adc", + NULL, NULL, 0, 0, "x-powers,axp717-adc"), + MFD_CELL_OF("axp20x-usb-power-supply", + axp717_usb_power_supply_resources, NULL, 0, 0, + "x-powers,axp717-usb-power-supply"), + MFD_CELL_OF("axp20x-battery-power-supply", + NULL, NULL, 0, 0, "x-powers,axp717-battery-power-supply"), }; static const struct resource axp288_adc_resources[] = { diff --git a/include/linux/mfd/axp20x.h b/include/linux/mfd/axp20x.h index 8c0a33a2e9ce..9b7ef473adcb 100644 --- a/include/linux/mfd/axp20x.h +++ b/include/linux/mfd/axp20x.h @@ -115,6 +115,16 @@ enum axp20x_variants { #define AXP313A_IRQ_STATE 0x21 #define AXP717_ON_INDICATE 0x00 +#define AXP717_PMU_STATUS_2 0x01 +#define AXP717_BC_DETECT 0x05 +#define AXP717_PMU_FAULT 0x08 +#define AXP717_MODULE_EN_CONTROL_1 0x0b +#define AXP717_MIN_SYS_V_CONTROL 0x15 +#define AXP717_INPUT_VOL_LIMIT_CTRL 0x16 +#define AXP717_INPUT_CUR_LIMIT_CTRL 0x17 +#define AXP717_MODULE_EN_CONTROL_2 0x19 +#define AXP717_BOOST_CONTROL 0x1e +#define AXP717_VSYS_V_POWEROFF 0x24 #define AXP717_IRQ0_EN 0x40 #define AXP717_IRQ1_EN 0x41 #define AXP717_IRQ2_EN 0x42 @@ -125,6 +135,9 @@ enum axp20x_variants { #define AXP717_IRQ2_STATE 0x4a #define AXP717_IRQ3_STATE 0x4b #define AXP717_IRQ4_STATE 0x4c +#define AXP717_ICC_CHG_SET 0x62 +#define AXP717_ITERM_CHG_SET 0x63 +#define AXP717_CV_CHG_SET 0x64 #define AXP717_DCDC_OUTPUT_CONTROL 0x80 #define AXP717_DCDC1_CONTROL 0x83 #define AXP717_DCDC2_CONTROL 0x84 @@ -145,6 +158,19 @@ enum axp20x_variants { #define AXP717_CLDO3_CONTROL 0x9d #define AXP717_CLDO4_CONTROL 0x9e #define AXP717_CPUSLDO_CONTROL 0x9f +#define AXP717_BATT_PERCENT_DATA 0xa4 +#define AXP717_ADC_CH_EN_CONTROL 0xc0 +#define AXP717_BATT_V_H 0xc4 +#define AXP717_BATT_V_L 0xc5 +#define AXP717_VBUS_V_H 0xc6 +#define AXP717_VBUS_V_L 0xc7 +#define AXP717_VSYS_V_H 0xc8 +#define AXP717_VSYS_V_L 0xc9 +#define AXP717_BATT_CHRG_I_H 0xca +#define AXP717_BATT_CHRG_I_L 0xcb +#define AXP717_ADC_DATA_SEL 0xcd +#define AXP717_ADC_DATA_H 0xce +#define AXP717_ADC_DATA_L 0xcf #define AXP806_STARTUP_SRC 0x00 #define AXP806_CHIP_ID 0x03 -- cgit v1.2.3 From c0390d541128e8820af8177a572d9d87ff68a3bb Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 23 Aug 2024 21:06:58 +0200 Subject: fs: pack struct file Now that we shrunk struct file to 192 bytes aka 3 cachelines reorder struct file to not leave any holes or have members cross cachelines. Add a short comment to each of the fields and mark the cachelines. It's possible that we may have to tweak this based on profiling in the future. So far I had Jens test this comparing io_uring with non-fixed and fixed files and it improved performance. The layout is a combination of Jens' and my changes. Link: https: //lore.kernel.org/r/20240824-peinigen-hocken-7384b977c643@brauner Signed-off-by: Christian Brauner --- include/linux/fs.h | 91 ++++++++++++++++++++++++++++++------------------------ 1 file changed, 51 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 095a956aeb29..af8bbd4eeb3a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -987,52 +987,63 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) index < ra->start + ra->size); } -/* - * f_{lock,count,pos_lock} members can be highly contended and share - * the same cacheline. f_{lock,mode} are very frequently used together - * and so share the same cacheline as well. The read-mostly - * f_{path,inode,op} are kept on a separate cacheline. +/** + * struct file - Represents a file + * @f_count: reference count + * @f_lock: Protects f_ep, f_flags. Must not be taken from IRQ context. + * @f_mode: FMODE_* flags often used in hotpaths + * @f_op: file operations + * @f_mapping: Contents of a cacheable, mappable object. + * @private_data: filesystem or driver specific data + * @f_inode: cached inode + * @f_flags: file flags + * @f_iocb_flags: iocb flags + * @f_cred: stashed credentials of creator/opener + * @f_path: path of the file + * @f_pos_lock: lock protecting file position + * @f_pos: file position + * @f_version: file version + * @f_security: LSM security context of this file + * @f_owner: file owner + * @f_wb_err: writeback error + * @f_sb_err: per sb writeback errors + * @f_ep: link of all epoll hooks for this file + * @f_task_work: task work entry point + * @f_llist: work queue entrypoint + * @f_ra: file's readahead state */ struct file { - union { - /* fput() uses task work when closing and freeing file (default). */ - struct callback_head f_task_work; - /* fput() must use workqueue (most kernel threads). */ - struct llist_node f_llist; - /* Invalid after last fput(). */ - struct file_ra_state f_ra; - }; - /* - * Protects f_ep, f_flags. - * Must not be taken from IRQ context. - */ - spinlock_t f_lock; - fmode_t f_mode; - atomic_long_t f_count; - struct mutex f_pos_lock; - loff_t f_pos; - unsigned int f_flags; - unsigned int f_iocb_flags; - struct fown_struct *f_owner; - const struct cred *f_cred; - struct path f_path; - struct inode *f_inode; /* cached value */ + atomic_long_t f_count; + spinlock_t f_lock; + fmode_t f_mode; const struct file_operations *f_op; - - u64 f_version; + struct address_space *f_mapping; + void *private_data; + struct inode *f_inode; + unsigned int f_flags; + unsigned int f_iocb_flags; + const struct cred *f_cred; + /* --- cacheline 1 boundary (64 bytes) --- */ + struct path f_path; + struct mutex f_pos_lock; + loff_t f_pos; + u64 f_version; + /* --- cacheline 2 boundary (128 bytes) --- */ #ifdef CONFIG_SECURITY - void *f_security; + void *f_security; #endif - /* needed for tty driver, and maybe others */ - void *private_data; - + struct fown_struct *f_owner; + errseq_t f_wb_err; + errseq_t f_sb_err; #ifdef CONFIG_EPOLL - /* Used by fs/eventpoll.c to link all the hooks to this file */ - struct hlist_head *f_ep; -#endif /* #ifdef CONFIG_EPOLL */ - struct address_space *f_mapping; - errseq_t f_wb_err; - errseq_t f_sb_err; /* for syncfs */ + struct hlist_head *f_ep; +#endif + union { + struct callback_head f_task_work; + struct llist_node f_llist; + struct file_ra_state f_ra; + }; + /* --- cacheline 3 boundary (192 bytes) --- */ } __randomize_layout __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ -- cgit v1.2.3 From d345bd2e9834e2da505977e154a1c179c793b7b2 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 28 Aug 2024 12:56:24 +0200 Subject: mm: add kmem_cache_create_rcu() When a kmem cache is created with SLAB_TYPESAFE_BY_RCU the free pointer must be located outside of the object because we don't know what part of the memory can safely be overwritten as it may be needed to prevent object recycling. That has the consequence that SLAB_TYPESAFE_BY_RCU may end up adding a new cacheline. This is the case for e.g., struct file. After having it shrunk down by 40 bytes and having it fit in three cachelines we still have SLAB_TYPESAFE_BY_RCU adding a fourth cacheline because it needs to accommodate the free pointer. Add a new kmem_cache_create_rcu() function that allows the caller to specify an offset where the free pointer is supposed to be placed. Link: https://lore.kernel.org/r/20240828-work-kmem_cache-rcu-v3-2-5460bc1f09f6@kernel.org Acked-by: Mike Rapoport (Microsoft) Reviewed-by: Vlastimil Babka Signed-off-by: Christian Brauner --- include/linux/slab.h | 9 ++++ mm/slab.h | 2 + mm/slab_common.c | 136 ++++++++++++++++++++++++++++++++++++--------------- mm/slub.c | 20 +++++--- 4 files changed, 121 insertions(+), 46 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index eb2bf4629157..5b2da2cf31a8 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -212,6 +212,12 @@ enum _slab_flag_bits { #define SLAB_NO_OBJ_EXT __SLAB_FLAG_UNUSED #endif +/* + * freeptr_t represents a SLUB freelist pointer, which might be encoded + * and not dereferenceable if CONFIG_SLAB_FREELIST_HARDENED is enabled. + */ +typedef struct { unsigned long v; } freeptr_t; + /* * ZERO_SIZE_PTR will be returned for zero sized kmalloc requests. * @@ -242,6 +248,9 @@ struct kmem_cache *kmem_cache_create_usercopy(const char *name, slab_flags_t flags, unsigned int useroffset, unsigned int usersize, void (*ctor)(void *)); +struct kmem_cache *kmem_cache_create_rcu(const char *name, unsigned int size, + unsigned int freeptr_offset, + slab_flags_t flags); void kmem_cache_destroy(struct kmem_cache *s); int kmem_cache_shrink(struct kmem_cache *s); diff --git a/mm/slab.h b/mm/slab.h index dcdb56b8e7f5..a6051385186e 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -261,6 +261,8 @@ struct kmem_cache { unsigned int object_size; /* Object size without metadata */ struct reciprocal_value reciprocal_size; unsigned int offset; /* Free pointer offset */ + /* Specific free pointer requested (if not UINT_MAX) */ + unsigned int rcu_freeptr_offset; #ifdef CONFIG_SLUB_CPU_PARTIAL /* Number of per cpu partial objects to keep around */ unsigned int cpu_partial; diff --git a/mm/slab_common.c b/mm/slab_common.c index c8dd7e08c5f6..887f6b9855dd 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -202,9 +202,10 @@ struct kmem_cache *find_mergeable(unsigned int size, unsigned int align, } static struct kmem_cache *create_cache(const char *name, - unsigned int object_size, unsigned int align, - slab_flags_t flags, unsigned int useroffset, - unsigned int usersize, void (*ctor)(void *)) + unsigned int object_size, unsigned int freeptr_offset, + unsigned int align, slab_flags_t flags, + unsigned int useroffset, unsigned int usersize, + void (*ctor)(void *)) { struct kmem_cache *s; int err; @@ -212,6 +213,13 @@ static struct kmem_cache *create_cache(const char *name, if (WARN_ON(useroffset + usersize > object_size)) useroffset = usersize = 0; + /* If a custom freelist pointer is requested make sure it's sane. */ + err = -EINVAL; + if (freeptr_offset != UINT_MAX && + (freeptr_offset >= object_size || !(flags & SLAB_TYPESAFE_BY_RCU) || + !IS_ALIGNED(freeptr_offset, sizeof(freeptr_t)))) + goto out; + err = -ENOMEM; s = kmem_cache_zalloc(kmem_cache, GFP_KERNEL); if (!s) @@ -219,13 +227,13 @@ static struct kmem_cache *create_cache(const char *name, s->name = name; s->size = s->object_size = object_size; + s->rcu_freeptr_offset = freeptr_offset; s->align = align; s->ctor = ctor; #ifdef CONFIG_HARDENED_USERCOPY s->useroffset = useroffset; s->usersize = usersize; #endif - err = __kmem_cache_create(s, flags); if (err) goto out_free_cache; @@ -240,38 +248,10 @@ out: return ERR_PTR(err); } -/** - * kmem_cache_create_usercopy - Create a cache with a region suitable - * for copying to userspace - * @name: A string which is used in /proc/slabinfo to identify this cache. - * @size: The size of objects to be created in this cache. - * @align: The required alignment for the objects. - * @flags: SLAB flags - * @useroffset: Usercopy region offset - * @usersize: Usercopy region size - * @ctor: A constructor for the objects. - * - * Cannot be called within a interrupt, but can be interrupted. - * The @ctor is run when new pages are allocated by the cache. - * - * The flags are - * - * %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5) - * to catch references to uninitialised memory. - * - * %SLAB_RED_ZONE - Insert `Red` zones around the allocated memory to check - * for buffer overruns. - * - * %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware - * cacheline. This can be beneficial if you're counting cycles as closely - * as davem. - * - * Return: a pointer to the cache on success, NULL on failure. - */ -struct kmem_cache * -kmem_cache_create_usercopy(const char *name, - unsigned int size, unsigned int align, - slab_flags_t flags, +static struct kmem_cache * +do_kmem_cache_create_usercopy(const char *name, + unsigned int size, unsigned int freeptr_offset, + unsigned int align, slab_flags_t flags, unsigned int useroffset, unsigned int usersize, void (*ctor)(void *)) { @@ -331,7 +311,7 @@ kmem_cache_create_usercopy(const char *name, goto out_unlock; } - s = create_cache(cache_name, size, + s = create_cache(cache_name, size, freeptr_offset, calculate_alignment(flags, align, size), flags, useroffset, usersize, ctor); if (IS_ERR(s)) { @@ -355,6 +335,45 @@ out_unlock: } return s; } + +/** + * kmem_cache_create_usercopy - Create a cache with a region suitable + * for copying to userspace + * @name: A string which is used in /proc/slabinfo to identify this cache. + * @size: The size of objects to be created in this cache. + * @freeptr_offset: Custom offset for the free pointer in RCU caches + * @align: The required alignment for the objects. + * @flags: SLAB flags + * @useroffset: Usercopy region offset + * @usersize: Usercopy region size + * @ctor: A constructor for the objects. + * + * Cannot be called within a interrupt, but can be interrupted. + * The @ctor is run when new pages are allocated by the cache. + * + * The flags are + * + * %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5) + * to catch references to uninitialised memory. + * + * %SLAB_RED_ZONE - Insert `Red` zones around the allocated memory to check + * for buffer overruns. + * + * %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware + * cacheline. This can be beneficial if you're counting cycles as closely + * as davem. + * + * Return: a pointer to the cache on success, NULL on failure. + */ +struct kmem_cache * +kmem_cache_create_usercopy(const char *name, unsigned int size, + unsigned int align, slab_flags_t flags, + unsigned int useroffset, unsigned int usersize, + void (*ctor)(void *)) +{ + return do_kmem_cache_create_usercopy(name, size, UINT_MAX, align, flags, + useroffset, usersize, ctor); +} EXPORT_SYMBOL(kmem_cache_create_usercopy); /** @@ -386,11 +405,50 @@ struct kmem_cache * kmem_cache_create(const char *name, unsigned int size, unsigned int align, slab_flags_t flags, void (*ctor)(void *)) { - return kmem_cache_create_usercopy(name, size, align, flags, 0, 0, - ctor); + return do_kmem_cache_create_usercopy(name, size, UINT_MAX, align, flags, + 0, 0, ctor); } EXPORT_SYMBOL(kmem_cache_create); +/** + * kmem_cache_create_rcu - Create a SLAB_TYPESAFE_BY_RCU cache. + * @name: A string which is used in /proc/slabinfo to identify this cache. + * @size: The size of objects to be created in this cache. + * @freeptr_offset: The offset into the memory to the free pointer + * @flags: SLAB flags + * + * Cannot be called within an interrupt, but can be interrupted. + * + * See kmem_cache_create() for an explanation of possible @flags. + * + * By default SLAB_TYPESAFE_BY_RCU caches place the free pointer outside + * of the object. This might cause the object to grow in size. Callers + * that have a reason to avoid this can specify a custom free pointer + * offset in their struct where the free pointer will be placed. + * + * Note that placing the free pointer inside the object requires the + * caller to ensure that no fields are invalidated that are required to + * guard against object recycling (See SLAB_TYPESAFE_BY_RCU for + * details.). + * + * Using zero as a value for @freeptr_offset is valid. To request no + * offset UINT_MAX must be specified. + * + * Note that @ctor isn't supported with custom free pointers as a @ctor + * requires an external free pointer. + * + * Return: a pointer to the cache on success, NULL on failure. + */ +struct kmem_cache *kmem_cache_create_rcu(const char *name, unsigned int size, + unsigned int freeptr_offset, + slab_flags_t flags) +{ + return do_kmem_cache_create_usercopy(name, size, freeptr_offset, 0, + flags | SLAB_TYPESAFE_BY_RCU, 0, 0, + NULL); +} +EXPORT_SYMBOL(kmem_cache_create_rcu); + static struct kmem_cache *kmem_buckets_cache __ro_after_init; /** diff --git a/mm/slub.c b/mm/slub.c index c9d8a2497fd6..9aa5da1e8e27 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -465,12 +465,6 @@ static struct workqueue_struct *flushwq; * Core slab cache functions *******************************************************************/ -/* - * freeptr_t represents a SLUB freelist pointer, which might be encoded - * and not dereferenceable if CONFIG_SLAB_FREELIST_HARDENED is enabled. - */ -typedef struct { unsigned long v; } freeptr_t; - /* * Returns freelist pointer (ptr). With hardening, this is obfuscated * with an XOR of the address where the pointer is held and a per-cache @@ -3921,6 +3915,9 @@ static void *__slab_alloc_node(struct kmem_cache *s, /* * If the object has been wiped upon free, make sure it's fully initialized by * zeroing out freelist pointer. + * + * Note that we also wipe custom freelist pointers specified via + * s->rcu_freeptr_offset. */ static __always_inline void maybe_wipe_obj_freeptr(struct kmem_cache *s, void *obj) @@ -5144,6 +5141,12 @@ static void set_cpu_partial(struct kmem_cache *s) #endif } +/* Was a valid freeptr offset requested? */ +static inline bool has_freeptr_offset(const struct kmem_cache *s) +{ + return s->rcu_freeptr_offset != UINT_MAX; +} + /* * calculate_sizes() determines the order and the distribution of data within * a slab object. @@ -5189,7 +5192,8 @@ static int calculate_sizes(struct kmem_cache *s) */ s->inuse = size; - if ((flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)) || s->ctor || + if (((flags & SLAB_TYPESAFE_BY_RCU) && !has_freeptr_offset(s)) || + (flags & SLAB_POISON) || s->ctor || ((flags & SLAB_RED_ZONE) && (s->object_size < sizeof(void *) || slub_debug_orig_size(s)))) { /* @@ -5210,6 +5214,8 @@ static int calculate_sizes(struct kmem_cache *s) */ s->offset = size; size += sizeof(void *); + } else if ((flags & SLAB_TYPESAFE_BY_RCU) && has_freeptr_offset(s)) { + s->offset = s->rcu_freeptr_offset; } else { /* * Store freelist pointer near middle of object to keep -- cgit v1.2.3 From ea566e18b4deea6e998088de4f1a76d1f39c8d3f Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 28 Aug 2024 12:56:25 +0200 Subject: fs: use kmem_cache_create_rcu() Switch to the new kmem_cache_create_rcu() helper which allows us to use a custom free pointer offset avoiding the need to have an external free pointer which would grow struct file behind our backs. Link: https://lore.kernel.org/r/20240828-work-kmem_cache-rcu-v3-3-5460bc1f09f6@kernel.org Acked-by: Mike Rapoport (Microsoft) Reviewed-by: Vlastimil Babka Signed-off-by: Christian Brauner --- fs/file_table.c | 6 +++--- include/linux/fs.h | 2 ++ 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/fs/file_table.c b/fs/file_table.c index fdf98709dde2..3ef558f27a1c 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -511,9 +511,9 @@ EXPORT_SYMBOL(__fput_sync); void __init files_init(void) { - filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0, - SLAB_TYPESAFE_BY_RCU | SLAB_HWCACHE_ALIGN | - SLAB_PANIC | SLAB_ACCOUNT, NULL); + filp_cachep = kmem_cache_create_rcu("filp", sizeof(struct file), + offsetof(struct file, f_freeptr), + SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT); percpu_counter_init(&nr_files, 0, GFP_KERNEL); } diff --git a/include/linux/fs.h b/include/linux/fs.h index af8bbd4eeb3a..58c91a52cad1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1011,6 +1011,7 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) * @f_task_work: task work entry point * @f_llist: work queue entrypoint * @f_ra: file's readahead state + * @f_freeptr: Pointer used by SLAB_TYPESAFE_BY_RCU file cache (don't touch.) */ struct file { atomic_long_t f_count; @@ -1042,6 +1043,7 @@ struct file { struct callback_head f_task_work; struct llist_node f_llist; struct file_ra_state f_ra; + freeptr_t f_freeptr; }; /* --- cacheline 3 boundary (192 bytes) --- */ } __randomize_layout -- cgit v1.2.3 From f91f2a9879cc77db1f45f690f38f42698580416e Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Wed, 28 Aug 2024 16:34:00 -0700 Subject: dmaengine: idxd: Add a new DSA device ID for Granite Rapids-D platform A new DSA device ID, 0x11fb, is introduced for the Granite Rapids-D platform. Add the device ID to the IDXD driver. Since a potential security issue has been fixed on the new device, it's secure to assign the device to virtual machines, and therefore, the new device ID will not be added to the VFIO denylist. Additionally, the new device ID may be useful in identifying and addressing any other potential issues with this specific device in the future. The same is also applied to any other new DSA/IAA devices with new device IDs. Signed-off-by: Fenghua Yu Reviewed-by: Dave Jiang Link: https://lore.kernel.org/r/20240828233401.186007-2-fenghua.yu@intel.com Signed-off-by: Vinod Koul --- drivers/dma/idxd/init.c | 2 ++ include/linux/pci_ids.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 21f6905b554d..415b17b0acd0 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -69,6 +69,8 @@ static struct idxd_driver_data idxd_driver_data[] = { static struct pci_device_id idxd_pci_tbl[] = { /* DSA ver 1.0 platforms */ { PCI_DEVICE_DATA(INTEL, DSA_SPR0, &idxd_driver_data[IDXD_TYPE_DSA]) }, + /* DSA on GNR-D platforms */ + { PCI_DEVICE_DATA(INTEL, DSA_GNRD, &idxd_driver_data[IDXD_TYPE_DSA]) }, /* IAX ver 1.0 platforms */ { PCI_DEVICE_DATA(INTEL, IAX_SPR0, &idxd_driver_data[IDXD_TYPE_IAX]) }, diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index e388c8b1cbc2..ff99047dac44 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2706,6 +2706,7 @@ #define PCI_DEVICE_ID_INTEL_82815_MC 0x1130 #define PCI_DEVICE_ID_INTEL_82815_CGC 0x1132 #define PCI_DEVICE_ID_INTEL_SST_TNG 0x119a +#define PCI_DEVICE_ID_INTEL_DSA_GNRD 0x11fb #define PCI_DEVICE_ID_INTEL_82092AA_0 0x1221 #define PCI_DEVICE_ID_INTEL_82437 0x122d #define PCI_DEVICE_ID_INTEL_82371FB_0 0x122e -- cgit v1.2.3 From 4fecf944c051ea852e98c062636bf5b4c7f5f8a7 Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Wed, 28 Aug 2024 16:34:01 -0700 Subject: dmaengine: idxd: Add new DSA and IAA device IDs for Diamond Rapids platform A new DSA device ID, 0x1212, and a new IAA device ID, 0x1216, are introduced for Diamond Rapids platform. Add the device IDs to the IDXD driver. The name "IAA" is used in new code instead of the old name "IAX". However, the "IAX" naming (e.g., IDXD_TYPE_IAX) is retained for legacy code compatibility. Signed-off-by: Fenghua Yu Reviewed-by: Dave Jiang Link: https://lore.kernel.org/r/20240828233401.186007-3-fenghua.yu@intel.com Signed-off-by: Vinod Koul --- drivers/dma/idxd/init.c | 4 ++++ include/linux/pci_ids.h | 2 ++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 415b17b0acd0..0f693b27879c 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -71,9 +71,13 @@ static struct pci_device_id idxd_pci_tbl[] = { { PCI_DEVICE_DATA(INTEL, DSA_SPR0, &idxd_driver_data[IDXD_TYPE_DSA]) }, /* DSA on GNR-D platforms */ { PCI_DEVICE_DATA(INTEL, DSA_GNRD, &idxd_driver_data[IDXD_TYPE_DSA]) }, + /* DSA on DMR platforms */ + { PCI_DEVICE_DATA(INTEL, DSA_DMR, &idxd_driver_data[IDXD_TYPE_DSA]) }, /* IAX ver 1.0 platforms */ { PCI_DEVICE_DATA(INTEL, IAX_SPR0, &idxd_driver_data[IDXD_TYPE_IAX]) }, + /* IAA on DMR platforms */ + { PCI_DEVICE_DATA(INTEL, IAA_DMR, &idxd_driver_data[IDXD_TYPE_IAX]) }, { 0, } }; MODULE_DEVICE_TABLE(pci, idxd_pci_tbl); diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index ff99047dac44..8139231d0e86 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2707,6 +2707,8 @@ #define PCI_DEVICE_ID_INTEL_82815_CGC 0x1132 #define PCI_DEVICE_ID_INTEL_SST_TNG 0x119a #define PCI_DEVICE_ID_INTEL_DSA_GNRD 0x11fb +#define PCI_DEVICE_ID_INTEL_DSA_DMR 0x1212 +#define PCI_DEVICE_ID_INTEL_IAA_DMR 0x1216 #define PCI_DEVICE_ID_INTEL_82092AA_0 0x1221 #define PCI_DEVICE_ID_INTEL_82437 0x122d #define PCI_DEVICE_ID_INTEL_82371FB_0 0x122e -- cgit v1.2.3 From 6f606ffd6dd7583d8194ee3d858ba4da2eff26a3 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 29 Aug 2024 14:08:23 -0700 Subject: bpf: Move insn_buf[16] to bpf_verifier_env This patch moves the 'struct bpf_insn insn_buf[16]' stack usage to the bpf_verifier_env. A '#define INSN_BUF_SIZE 16' is also added to replace the ARRAY_SIZE(insn_buf) usages. Both convert_ctx_accesses() and do_misc_fixup() are changed to use the env->insn_buf. It is a refactoring work for adding the epilogue_buf[16] in a later patch. With this patch, the stack size usage decreased. Before: ./kernel/bpf/verifier.c:22133:5: warning: stack frame size (2584) After: ./kernel/bpf/verifier.c:22184:5: warning: stack frame size (2264) Reviewed-by: Eduard Zingerman Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20240829210833.388152-2-martin.lau@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 3 +++ kernel/bpf/verifier.c | 15 ++++++++------- 2 files changed, 11 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 279b4a640644..0ad2d189c546 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -23,6 +23,8 @@ * (in the "-8,-16,...,-512" form) */ #define TMP_STR_BUF_LEN 320 +/* Patch buffer size */ +#define INSN_BUF_SIZE 16 /* Liveness marks, used for registers and spilled-regs (in stack slots). * Read marks propagate upwards until they find a write mark; they record that @@ -780,6 +782,7 @@ struct bpf_verifier_env { * e.g., in reg_type_str() to generate reg_type string */ char tmp_str_buf[TMP_STR_BUF_LEN]; + struct bpf_insn insn_buf[INSN_BUF_SIZE]; }; static inline struct bpf_func_info_aux *subprog_aux(struct bpf_verifier_env *env, int subprog) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f32e3b9bb4e5..261849384ea8 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -19677,7 +19677,8 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) const struct bpf_verifier_ops *ops = env->ops; int i, cnt, size, ctx_field_size, delta = 0; const int insn_cnt = env->prog->len; - struct bpf_insn insn_buf[16], *insn; + struct bpf_insn *insn_buf = env->insn_buf; + struct bpf_insn *insn; u32 target_size, size_default, off; struct bpf_prog *new_prog; enum bpf_access_type type; @@ -19690,7 +19691,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) } cnt = ops->gen_prologue(insn_buf, env->seen_direct_write, env->prog); - if (cnt >= ARRAY_SIZE(insn_buf)) { + if (cnt >= INSN_BUF_SIZE) { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } else if (cnt) { @@ -19837,7 +19838,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) target_size = 0; cnt = convert_ctx_access(type, insn, insn_buf, env->prog, &target_size); - if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf) || + if (cnt == 0 || cnt >= INSN_BUF_SIZE || (ctx_field_size && !target_size)) { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; @@ -19846,7 +19847,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) if (is_narrower_load && size < target_size) { u8 shift = bpf_ctx_narrow_access_offset( off, size, size_default) * 8; - if (shift && cnt + 1 >= ARRAY_SIZE(insn_buf)) { + if (shift && cnt + 1 >= INSN_BUF_SIZE) { verbose(env, "bpf verifier narrow ctx load misconfigured\n"); return -EINVAL; } @@ -20391,7 +20392,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) const int insn_cnt = prog->len; const struct bpf_map_ops *ops; struct bpf_insn_aux_data *aux; - struct bpf_insn insn_buf[16]; + struct bpf_insn *insn_buf = env->insn_buf; struct bpf_prog *new_prog; struct bpf_map *map_ptr; int i, ret, cnt, delta = 0, cur_subprog = 0; @@ -20510,7 +20511,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) (BPF_MODE(insn->code) == BPF_ABS || BPF_MODE(insn->code) == BPF_IND)) { cnt = env->ops->gen_ld_abs(insn, insn_buf); - if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) { + if (cnt == 0 || cnt >= INSN_BUF_SIZE) { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } @@ -20803,7 +20804,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) cnt = ops->map_gen_lookup(map_ptr, insn_buf); if (cnt == -EOPNOTSUPP) goto patch_map_ops_generic; - if (cnt <= 0 || cnt >= ARRAY_SIZE(insn_buf)) { + if (cnt <= 0 || cnt >= INSN_BUF_SIZE) { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } -- cgit v1.2.3 From 169c31761c8d7f606f3ee628829c27998626c4f0 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 29 Aug 2024 14:08:25 -0700 Subject: bpf: Add gen_epilogue to bpf_verifier_ops This patch adds a .gen_epilogue to the bpf_verifier_ops. It is similar to the existing .gen_prologue. Instead of allowing a subsystem to run code at the beginning of a bpf prog, it allows the subsystem to run code just before the bpf prog exit. One of the use case is to allow the upcoming bpf qdisc to ensure that the skb->dev is the same as the qdisc->dev_queue->dev. The bpf qdisc struct_ops implementation could either fix it up or drop the skb. Another use case could be in bpf_tcp_ca.c to enforce snd_cwnd has sane value (e.g. non zero). The epilogue can do the useful thing (like checking skb->dev) if it can access the bpf prog's ctx. Unlike prologue, r1 may not hold the ctx pointer. This patch saves the r1 in the stack if the .gen_epilogue has returned some instructions in the "epilogue_buf". The existing .gen_prologue is done in convert_ctx_accesses(). The new .gen_epilogue is done in the convert_ctx_accesses() also. When it sees the (BPF_JMP | BPF_EXIT) instruction, it will be patched with the earlier generated "epilogue_buf". The epilogue patching is only done for the main prog. Only one epilogue will be patched to the main program. When the bpf prog has multiple BPF_EXIT instructions, a BPF_JA is used to goto the earlier patched epilogue. Majority of the archs support (BPF_JMP32 | BPF_JA): x86, arm, s390, risv64, loongarch, powerpc and arc. This patch keeps it simple and always use (BPF_JMP32 | BPF_JA). A new macro BPF_JMP32_A is added to generate the (BPF_JMP32 | BPF_JA) insn. Acked-by: Eduard Zingerman Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20240829210833.388152-4-martin.lau@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 ++ include/linux/bpf_verifier.h | 1 + include/linux/filter.h | 10 ++++++++++ kernel/bpf/verifier.c | 46 +++++++++++++++++++++++++++++++++++++++++++- 4 files changed, 58 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index dc63083f76b7..6f87fb014fba 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -974,6 +974,8 @@ struct bpf_verifier_ops { struct bpf_insn_access_aux *info); int (*gen_prologue)(struct bpf_insn *insn, bool direct_write, const struct bpf_prog *prog); + int (*gen_epilogue)(struct bpf_insn *insn, const struct bpf_prog *prog, + s16 ctx_stack_off); int (*gen_ld_abs)(const struct bpf_insn *orig, struct bpf_insn *insn_buf); u32 (*convert_ctx_access)(enum bpf_access_type type, diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 0ad2d189c546..2e20207315a9 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -783,6 +783,7 @@ struct bpf_verifier_env { */ char tmp_str_buf[TMP_STR_BUF_LEN]; struct bpf_insn insn_buf[INSN_BUF_SIZE]; + struct bpf_insn epilogue_buf[INSN_BUF_SIZE]; }; static inline struct bpf_func_info_aux *subprog_aux(struct bpf_verifier_env *env, int subprog) diff --git a/include/linux/filter.h b/include/linux/filter.h index b6672ff61407..99b6fc83825b 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -437,6 +437,16 @@ static inline bool insn_is_cast_user(const struct bpf_insn *insn) .off = OFF, \ .imm = 0 }) +/* Unconditional jumps, gotol pc + imm32 */ + +#define BPF_JMP32_A(IMM) \ + ((struct bpf_insn) { \ + .code = BPF_JMP32 | BPF_JA, \ + .dst_reg = 0, \ + .src_reg = 0, \ + .off = 0, \ + .imm = IMM }) + /* Relative call */ #define BPF_CALL_REL(TGT) \ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 03e974129c05..fdb1d39c8b58 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -19677,15 +19677,39 @@ apply_patch_buffer: */ static int convert_ctx_accesses(struct bpf_verifier_env *env) { + struct bpf_subprog_info *subprogs = env->subprog_info; const struct bpf_verifier_ops *ops = env->ops; - int i, cnt, size, ctx_field_size, delta = 0; + int i, cnt, size, ctx_field_size, delta = 0, epilogue_cnt = 0; const int insn_cnt = env->prog->len; + struct bpf_insn *epilogue_buf = env->epilogue_buf; struct bpf_insn *insn_buf = env->insn_buf; struct bpf_insn *insn; u32 target_size, size_default, off; struct bpf_prog *new_prog; enum bpf_access_type type; bool is_narrower_load; + int epilogue_idx = 0; + + if (ops->gen_epilogue) { + epilogue_cnt = ops->gen_epilogue(epilogue_buf, env->prog, + -(subprogs[0].stack_depth + 8)); + if (epilogue_cnt >= INSN_BUF_SIZE) { + verbose(env, "bpf verifier is misconfigured\n"); + return -EINVAL; + } else if (epilogue_cnt) { + /* Save the ARG_PTR_TO_CTX for the epilogue to use */ + cnt = 0; + subprogs[0].stack_depth += 8; + insn_buf[cnt++] = BPF_STX_MEM(BPF_DW, BPF_REG_FP, BPF_REG_1, + -subprogs[0].stack_depth); + insn_buf[cnt++] = env->prog->insnsi[0]; + new_prog = bpf_patch_insn_data(env, 0, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + env->prog = new_prog; + delta += cnt - 1; + } + } if (ops->gen_prologue || env->seen_direct_write) { if (!ops->gen_prologue) { @@ -19742,6 +19766,25 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) insn->code = BPF_STX | BPF_PROBE_ATOMIC | BPF_SIZE(insn->code); env->prog->aux->num_exentries++; continue; + } else if (insn->code == (BPF_JMP | BPF_EXIT) && + epilogue_cnt && + i + delta < subprogs[1].start) { + /* Generate epilogue for the main prog */ + if (epilogue_idx) { + /* jump back to the earlier generated epilogue */ + insn_buf[0] = BPF_JMP32_A(epilogue_idx - i - delta - 1); + cnt = 1; + } else { + memcpy(insn_buf, epilogue_buf, + epilogue_cnt * sizeof(*epilogue_buf)); + cnt = epilogue_cnt; + /* epilogue_idx cannot be 0. It must have at + * least one ctx ptr saving insn before the + * epilogue. + */ + epilogue_idx = i + delta; + } + goto patch_insn_buf; } else { continue; } @@ -19878,6 +19921,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) insn->dst_reg, insn->dst_reg, size * 8, 0); +patch_insn_buf: new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; -- cgit v1.2.3 From 087adb4f0f91ee330446a70af899e6a996e5cc13 Mon Sep 17 00:00:00 2001 From: Mateusz Guzik Date: Tue, 6 Aug 2024 19:28:46 +0200 Subject: vfs: dodge smp_mb in break_lease and break_deleg in the common case These inlines show up in the fast path (e.g., in do_dentry_open()) and induce said full barrier regarding i_flctx access when in most cases the pointer is NULL. The pointer can be safely checked before issuing the barrier, dodging it in most cases as a result. It is plausible the consume fence would be sufficient, but I don't want to go audit all callers regarding what they before calling here. Signed-off-by: Mateusz Guzik Link: https://lore.kernel.org/r/20240806172846.886570-1-mjguzik@gmail.com Reviewed-by: Jeff Layton Signed-off-by: Christian Brauner --- include/linux/filelock.h | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filelock.h b/include/linux/filelock.h index daee999d05f3..bb44224c6676 100644 --- a/include/linux/filelock.h +++ b/include/linux/filelock.h @@ -420,28 +420,38 @@ static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) #ifdef CONFIG_FILE_LOCKING static inline int break_lease(struct inode *inode, unsigned int mode) { + struct file_lock_context *flctx; + /* * Since this check is lockless, we must ensure that any refcounts * taken are done before checking i_flctx->flc_lease. Otherwise, we * could end up racing with tasks trying to set a new lease on this * file. */ + flctx = READ_ONCE(inode->i_flctx); + if (!flctx) + return 0; smp_mb(); - if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) + if (!list_empty_careful(&flctx->flc_lease)) return __break_lease(inode, mode, FL_LEASE); return 0; } static inline int break_deleg(struct inode *inode, unsigned int mode) { + struct file_lock_context *flctx; + /* * Since this check is lockless, we must ensure that any refcounts * taken are done before checking i_flctx->flc_lease. Otherwise, we * could end up racing with tasks trying to set a new lease on this * file. */ + flctx = READ_ONCE(inode->i_flctx); + if (!flctx) + return 0; smp_mb(); - if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) + if (!list_empty_careful(&flctx->flc_lease)) return __break_lease(inode, mode, FL_DELEG); return 0; } -- cgit v1.2.3 From 8447d848e1dc6d42d1dcd00f133d7715fc732c47 Mon Sep 17 00:00:00 2001 From: Mateusz Guzik Date: Sat, 10 Aug 2024 08:47:53 +0200 Subject: vfs: only read fops once in fops_get/put In do_dentry_open() the usage is: f->f_op = fops_get(inode->i_fop); In generated asm the compiler emits 2 reads from inode->i_fop instead of just one. This popped up due to false-sharing where loads from that offset end up bouncing a cacheline during parallel open. While this is going to be fixed, the spurious load does not need to be there. This makes do_dentry_open() go down from 1177 to 1154 bytes. fops_put() is patched to maintain some consistency. No functional changes. Reviewed-by: Josef Bacik Signed-off-by: Mateusz Guzik Link: https://lore.kernel.org/r/20240810064753.1211441-1-mjguzik@gmail.com Signed-off-by: Christian Brauner --- include/linux/fs.h | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index c0286d479c9d..696c620f90e0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2553,10 +2553,17 @@ struct super_block *sget(struct file_system_type *type, struct super_block *sget_dev(struct fs_context *fc, dev_t dev); /* Alas, no aliases. Too much hassle with bringing module.h everywhere */ -#define fops_get(fops) \ - (((fops) && try_module_get((fops)->owner) ? (fops) : NULL)) -#define fops_put(fops) \ - do { if (fops) module_put((fops)->owner); } while(0) +#define fops_get(fops) ({ \ + const struct file_operations *_fops = (fops); \ + (((_fops) && try_module_get((_fops)->owner) ? (_fops) : NULL)); \ +}) + +#define fops_put(fops) ({ \ + const struct file_operations *_fops = (fops); \ + if (_fops) \ + module_put((_fops)->owner); \ +}) + /* * This one is to be used *ONLY* from ->open() instances. * fops must be non-NULL, pinned down *and* module dependencies -- cgit v1.2.3 From 641bb4394f405cba498b100b44541ffc0aed5be1 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 9 Aug 2024 12:38:56 +0200 Subject: fs: move FMODE_UNSIGNED_OFFSET to fop_flags This is another flag that is statically set and doesn't need to use up an FMODE_* bit. Move it to ->fop_flags and free up another FMODE_* bit. (1) mem_open() used from proc_mem_operations (2) adi_open() used from adi_fops (3) drm_open_helper(): (3.1) accel_open() used from DRM_ACCEL_FOPS (3.2) drm_open() used from (3.2.1) amdgpu_driver_kms_fops (3.2.2) psb_gem_fops (3.2.3) i915_driver_fops (3.2.4) nouveau_driver_fops (3.2.5) panthor_drm_driver_fops (3.2.6) radeon_driver_kms_fops (3.2.7) tegra_drm_fops (3.2.8) vmwgfx_driver_fops (3.2.9) xe_driver_fops (3.2.10) DRM_GEM_FOPS (3.2.11) DEFINE_DRM_GEM_DMA_FOPS (4) struct memdev sets fmode flags based on type of device opened. For devices using struct mem_fops unsigned offset is used. Mark all these file operations as FOP_UNSIGNED_OFFSET and add asserts into the open helper to ensure that the flag is always set. Link: https://lore.kernel.org/r/20240809-work-fop_unsigned-v1-1-658e054d893e@kernel.org Reviewed-by: Jeff Layton Reviewed-by: Jan Kara Signed-off-by: Christian Brauner --- drivers/char/adi.c | 8 +------- drivers/char/mem.c | 3 ++- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 1 + drivers/gpu/drm/drm_file.c | 3 ++- drivers/gpu/drm/gma500/psb_drv.c | 1 + drivers/gpu/drm/i915/i915_driver.c | 1 + drivers/gpu/drm/nouveau/nouveau_drm.c | 1 + drivers/gpu/drm/radeon/radeon_drv.c | 1 + drivers/gpu/drm/tegra/drm.c | 1 + drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 1 + drivers/gpu/drm/xe/xe_device.c | 1 + fs/proc/base.c | 10 ++++------ fs/read_write.c | 2 +- include/drm/drm_accel.h | 3 ++- include/drm/drm_gem.h | 3 ++- include/drm/drm_gem_dma_helper.h | 1 + include/linux/fs.h | 5 +++-- mm/mmap.c | 2 +- 18 files changed, 27 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/drivers/char/adi.c b/drivers/char/adi.c index 751d7cc0da1b..1c76c8758f0f 100644 --- a/drivers/char/adi.c +++ b/drivers/char/adi.c @@ -14,12 +14,6 @@ #define MAX_BUF_SZ PAGE_SIZE -static int adi_open(struct inode *inode, struct file *file) -{ - file->f_mode |= FMODE_UNSIGNED_OFFSET; - return 0; -} - static int read_mcd_tag(unsigned long addr) { long err; @@ -206,9 +200,9 @@ static loff_t adi_llseek(struct file *file, loff_t offset, int whence) static const struct file_operations adi_fops = { .owner = THIS_MODULE, .llseek = adi_llseek, - .open = adi_open, .read = adi_read, .write = adi_write, + .fop_flags = FOP_UNSIGNED_OFFSET, }; static struct miscdevice adi_miscdev = { diff --git a/drivers/char/mem.c b/drivers/char/mem.c index 7c359cc406d5..169eed162a7f 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -643,6 +643,7 @@ static const struct file_operations __maybe_unused mem_fops = { .get_unmapped_area = get_unmapped_area_mem, .mmap_capabilities = memory_mmap_capabilities, #endif + .fop_flags = FOP_UNSIGNED_OFFSET, }; static const struct file_operations null_fops = { @@ -693,7 +694,7 @@ static const struct memdev { umode_t mode; } devlist[] = { #ifdef CONFIG_DEVMEM - [DEVMEM_MINOR] = { "mem", &mem_fops, FMODE_UNSIGNED_OFFSET, 0 }, + [DEVMEM_MINOR] = { "mem", &mem_fops, 0, 0 }, #endif [3] = { "null", &null_fops, FMODE_NOWAIT, 0666 }, #ifdef CONFIG_DEVPORT diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 094498a0964b..d7ef8cbecf6c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2908,6 +2908,7 @@ static const struct file_operations amdgpu_driver_kms_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = drm_show_fdinfo, #endif + .fop_flags = FOP_UNSIGNED_OFFSET, }; int amdgpu_file_to_fpriv(struct file *filp, struct amdgpu_fpriv **fpriv) diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c index 714e42b05108..f8de3cba1a08 100644 --- a/drivers/gpu/drm/drm_file.c +++ b/drivers/gpu/drm/drm_file.c @@ -318,6 +318,8 @@ int drm_open_helper(struct file *filp, struct drm_minor *minor) if (dev->switch_power_state != DRM_SWITCH_POWER_ON && dev->switch_power_state != DRM_SWITCH_POWER_DYNAMIC_OFF) return -EINVAL; + if (WARN_ON_ONCE(!(filp->f_op->fop_flags & FOP_UNSIGNED_OFFSET))) + return -EINVAL; drm_dbg_core(dev, "comm=\"%s\", pid=%d, minor=%d\n", current->comm, task_pid_nr(current), minor->index); @@ -335,7 +337,6 @@ int drm_open_helper(struct file *filp, struct drm_minor *minor) } filp->private_data = priv; - filp->f_mode |= FMODE_UNSIGNED_OFFSET; priv->filp = filp; mutex_lock(&dev->filelist_mutex); diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c index 8b64f61ffaf9..d67c2b3ad901 100644 --- a/drivers/gpu/drm/gma500/psb_drv.c +++ b/drivers/gpu/drm/gma500/psb_drv.c @@ -498,6 +498,7 @@ static const struct file_operations psb_gem_fops = { .mmap = drm_gem_mmap, .poll = drm_poll, .read = drm_read, + .fop_flags = FOP_UNSIGNED_OFFSET, }; static const struct drm_driver driver = { diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c index fb8e9c2fcea5..cf276299bccb 100644 --- a/drivers/gpu/drm/i915/i915_driver.c +++ b/drivers/gpu/drm/i915/i915_driver.c @@ -1671,6 +1671,7 @@ static const struct file_operations i915_driver_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = drm_show_fdinfo, #endif + .fop_flags = FOP_UNSIGNED_OFFSET, }; static int diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index a58c31089613..e243b42f8582 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -1274,6 +1274,7 @@ nouveau_driver_fops = { .compat_ioctl = nouveau_compat_ioctl, #endif .llseek = noop_llseek, + .fop_flags = FOP_UNSIGNED_OFFSET, }; static struct drm_driver diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c index 7bf08164140e..ac49779ed03d 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -520,6 +520,7 @@ static const struct file_operations radeon_driver_kms_fops = { #ifdef CONFIG_COMPAT .compat_ioctl = radeon_kms_compat_ioctl, #endif + .fop_flags = FOP_UNSIGNED_OFFSET, }; static const struct drm_ioctl_desc radeon_ioctls_kms[] = { diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index 03d1c76aec2d..108c26a33edb 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -801,6 +801,7 @@ static const struct file_operations tegra_drm_fops = { .read = drm_read, .compat_ioctl = drm_compat_ioctl, .llseek = noop_llseek, + .fop_flags = FOP_UNSIGNED_OFFSET, }; static int tegra_drm_context_cleanup(int id, void *p, void *data) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 50ad3105c16e..2825dd3149ed 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -1609,6 +1609,7 @@ static const struct file_operations vmwgfx_driver_fops = { .compat_ioctl = vmw_compat_ioctl, #endif .llseek = noop_llseek, + .fop_flags = FOP_UNSIGNED_OFFSET, }; static const struct drm_driver driver = { diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index f2f1d8ddb221..2e5537d6608d 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -238,6 +238,7 @@ static const struct file_operations xe_driver_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = drm_show_fdinfo, #endif + .fop_flags = FOP_UNSIGNED_OFFSET, }; static struct drm_driver driver = { diff --git a/fs/proc/base.c b/fs/proc/base.c index 72a1acd03675..1409d1003101 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -827,12 +827,9 @@ static int __mem_open(struct inode *inode, struct file *file, unsigned int mode) static int mem_open(struct inode *inode, struct file *file) { - int ret = __mem_open(inode, file, PTRACE_MODE_ATTACH); - - /* OK to pass negative loff_t, we can catch out-of-range */ - file->f_mode |= FMODE_UNSIGNED_OFFSET; - - return ret; + if (WARN_ON_ONCE(!(file->f_op->fop_flags & FOP_UNSIGNED_OFFSET))) + return -EINVAL; + return __mem_open(inode, file, PTRACE_MODE_ATTACH); } static ssize_t mem_rw(struct file *file, char __user *buf, @@ -932,6 +929,7 @@ static const struct file_operations proc_mem_operations = { .write = mem_write, .open = mem_open, .release = mem_release, + .fop_flags = FOP_UNSIGNED_OFFSET, }; static int environ_open(struct inode *inode, struct file *file) diff --git a/fs/read_write.c b/fs/read_write.c index 90e283b31ca1..89d4af0e3b93 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -36,7 +36,7 @@ EXPORT_SYMBOL(generic_ro_fops); static inline bool unsigned_offsets(struct file *file) { - return file->f_mode & FMODE_UNSIGNED_OFFSET; + return file->f_op->fop_flags & FOP_UNSIGNED_OFFSET; } /** diff --git a/include/drm/drm_accel.h b/include/drm/drm_accel.h index f4d3784b1dce..41c78b7d712c 100644 --- a/include/drm/drm_accel.h +++ b/include/drm/drm_accel.h @@ -28,7 +28,8 @@ .poll = drm_poll,\ .read = drm_read,\ .llseek = noop_llseek, \ - .mmap = drm_gem_mmap + .mmap = drm_gem_mmap, \ + .fop_flags = FOP_UNSIGNED_OFFSET /** * DEFINE_DRM_ACCEL_FOPS() - macro to generate file operations for accelerators drivers diff --git a/include/drm/drm_gem.h b/include/drm/drm_gem.h index bae4865b2101..d8b86df2ec0d 100644 --- a/include/drm/drm_gem.h +++ b/include/drm/drm_gem.h @@ -447,7 +447,8 @@ struct drm_gem_object { .poll = drm_poll,\ .read = drm_read,\ .llseek = noop_llseek,\ - .mmap = drm_gem_mmap + .mmap = drm_gem_mmap, \ + .fop_flags = FOP_UNSIGNED_OFFSET /** * DEFINE_DRM_GEM_FOPS() - macro to generate file operations for GEM drivers diff --git a/include/drm/drm_gem_dma_helper.h b/include/drm/drm_gem_dma_helper.h index a827bde494f6..f2678e7ecb98 100644 --- a/include/drm/drm_gem_dma_helper.h +++ b/include/drm/drm_gem_dma_helper.h @@ -267,6 +267,7 @@ unsigned long drm_gem_dma_get_unmapped_area(struct file *filp, .read = drm_read,\ .llseek = noop_llseek,\ .mmap = drm_gem_mmap,\ + .fop_flags = FOP_UNSIGNED_OFFSET, \ DRM_GEM_DMA_UNMAPPED_AREA_FOPS \ } diff --git a/include/linux/fs.h b/include/linux/fs.h index 696c620f90e0..0145bda465ff 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -146,8 +146,7 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* Expect random access pattern */ #define FMODE_RANDOM ((__force fmode_t)(1 << 12)) -/* File is huge (eg. /dev/mem): treat loff_t as unsigned */ -#define FMODE_UNSIGNED_OFFSET ((__force fmode_t)(1 << 13)) +/* FMODE_* bit 13 */ /* File is opened with O_PATH; almost nothing can be done with it */ #define FMODE_PATH ((__force fmode_t)(1 << 14)) @@ -2073,6 +2072,8 @@ struct file_operations { #define FOP_DIO_PARALLEL_WRITE ((__force fop_flags_t)(1 << 3)) /* Contains huge pages */ #define FOP_HUGE_PAGES ((__force fop_flags_t)(1 << 4)) +/* Treat loff_t as unsigned (e.g., /dev/mem) */ +#define FOP_UNSIGNED_OFFSET ((__force fop_flags_t)(1 << 5)) /* Wrap a directory iterator that needs exclusive inode access */ int wrap_directory_iterator(struct file *, struct dir_context *, diff --git a/mm/mmap.c b/mm/mmap.c index d0dfc85b209b..6ddb278a5ee8 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1229,7 +1229,7 @@ static inline u64 file_mmap_size_max(struct file *file, struct inode *inode) return MAX_LFS_FILESIZE; /* Special "we do even unsigned file positions" case */ - if (file->f_mode & FMODE_UNSIGNED_OFFSET) + if (file->f_op->fop_flags & FOP_UNSIGNED_OFFSET) return 0; /* Yes, random drivers might want more. But I'm tired of buggy drivers */ -- cgit v1.2.3 From 1c48d441468c425e878d81c5c3e7ff8a9a594cc0 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 16 Aug 2024 16:35:52 +0200 Subject: inode: remove __I_DIO_WAKEUP Afaict, we can just rely on inode->i_dio_count for waiting instead of this awkward indirection through __I_DIO_WAKEUP. This survives LTP dio and xfstests dio tests. Link: https://lore.kernel.org/r/20240816-vfs-misc-dio-v1-1-80fe21a2c710@kernel.org Reviewed-by: Josef Bacik Reviewed-by: Jeff Layton Signed-off-by: Christian Brauner --- fs/inode.c | 23 +++++++++++------------ fs/netfs/locking.c | 22 +++++----------------- include/linux/fs.h | 8 +++----- 3 files changed, 19 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/fs/inode.c b/fs/inode.c index de0969d6009c..248a131a02c3 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -2500,18 +2500,11 @@ EXPORT_SYMBOL(inode_owner_or_capable); /* * Direct i/o helper functions */ -static void __inode_dio_wait(struct inode *inode) +bool inode_dio_finished(const struct inode *inode) { - wait_queue_head_t *wq = bit_waitqueue(&inode->i_state, __I_DIO_WAKEUP); - DEFINE_WAIT_BIT(q, &inode->i_state, __I_DIO_WAKEUP); - - do { - prepare_to_wait(wq, &q.wq_entry, TASK_UNINTERRUPTIBLE); - if (atomic_read(&inode->i_dio_count)) - schedule(); - } while (atomic_read(&inode->i_dio_count)); - finish_wait(wq, &q.wq_entry); + return atomic_read(&inode->i_dio_count) == 0; } +EXPORT_SYMBOL(inode_dio_finished); /** * inode_dio_wait - wait for outstanding DIO requests to finish @@ -2525,11 +2518,17 @@ static void __inode_dio_wait(struct inode *inode) */ void inode_dio_wait(struct inode *inode) { - if (atomic_read(&inode->i_dio_count)) - __inode_dio_wait(inode); + wait_var_event(&inode->i_dio_count, inode_dio_finished(inode)); } EXPORT_SYMBOL(inode_dio_wait); +void inode_dio_wait_interruptible(struct inode *inode) +{ + wait_var_event_interruptible(&inode->i_dio_count, + inode_dio_finished(inode)); +} +EXPORT_SYMBOL(inode_dio_wait_interruptible); + /* * inode_set_flags - atomically set some inode flags * diff --git a/fs/netfs/locking.c b/fs/netfs/locking.c index 75dc52a49b3a..21eab56ee2f9 100644 --- a/fs/netfs/locking.c +++ b/fs/netfs/locking.c @@ -19,25 +19,13 @@ * Must be called under a lock that serializes taking new references * to i_dio_count, usually by inode->i_mutex. */ -static int inode_dio_wait_interruptible(struct inode *inode) +static int netfs_inode_dio_wait_interruptible(struct inode *inode) { - if (!atomic_read(&inode->i_dio_count)) + if (inode_dio_finished(inode)) return 0; - wait_queue_head_t *wq = bit_waitqueue(&inode->i_state, __I_DIO_WAKEUP); - DEFINE_WAIT_BIT(q, &inode->i_state, __I_DIO_WAKEUP); - - for (;;) { - prepare_to_wait(wq, &q.wq_entry, TASK_INTERRUPTIBLE); - if (!atomic_read(&inode->i_dio_count)) - break; - if (signal_pending(current)) - break; - schedule(); - } - finish_wait(wq, &q.wq_entry); - - return atomic_read(&inode->i_dio_count) ? -ERESTARTSYS : 0; + inode_dio_wait_interruptible(inode); + return !inode_dio_finished(inode) ? -ERESTARTSYS : 0; } /* Call with exclusively locked inode->i_rwsem */ @@ -46,7 +34,7 @@ static int netfs_block_o_direct(struct netfs_inode *ictx) if (!test_bit(NETFS_ICTX_ODIRECT, &ictx->flags)) return 0; clear_bit(NETFS_ICTX_ODIRECT, &ictx->flags); - return inode_dio_wait_interruptible(&ictx->inode); + return netfs_inode_dio_wait_interruptible(&ictx->inode); } /** diff --git a/include/linux/fs.h b/include/linux/fs.h index 0145bda465ff..8f8d274929d7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2373,8 +2373,6 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, * * I_REFERENCED Marks the inode as recently references on the LRU list. * - * I_DIO_WAKEUP Never set. Only used as a key for wait_on_bit(). - * * I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to * synchronize competing switching instances and to tell * wb stat updates to grab the i_pages lock. See @@ -2409,8 +2407,6 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, #define __I_SYNC 7 #define I_SYNC (1 << __I_SYNC) #define I_REFERENCED (1 << 8) -#define __I_DIO_WAKEUP 9 -#define I_DIO_WAKEUP (1 << __I_DIO_WAKEUP) #define I_LINKABLE (1 << 10) #define I_DIRTY_TIME (1 << 11) #define I_WB_SWITCH (1 << 13) @@ -3227,7 +3223,9 @@ static inline ssize_t blockdev_direct_IO(struct kiocb *iocb, } #endif +bool inode_dio_finished(const struct inode *inode); void inode_dio_wait(struct inode *inode); +void inode_dio_wait_interruptible(struct inode *inode); /** * inode_dio_begin - signal start of a direct I/O requests @@ -3251,7 +3249,7 @@ static inline void inode_dio_begin(struct inode *inode) static inline void inode_dio_end(struct inode *inode) { if (atomic_dec_and_test(&inode->i_dio_count)) - wake_up_bit(&inode->i_state, __I_DIO_WAKEUP); + wake_up_var(&inode->i_dio_count); } extern void inode_set_flags(struct inode *inode, unsigned int flags, -- cgit v1.2.3 From 029c3f27fe84c5fd29d49a99cc5176433bf12209 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 22 Aug 2024 11:28:38 +0200 Subject: fs: remove unused path_put_init() This helper has been unused for a while now. Link: https://lore.kernel.org/r/20240822-bewuchs-werktag-46672b3c0606@brauner Reviewed-by: Jan Kara Signed-off-by: Christian Brauner --- include/linux/path.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/path.h b/include/linux/path.h index ca073e70decd..7ea389dc764b 100644 --- a/include/linux/path.h +++ b/include/linux/path.h @@ -18,12 +18,6 @@ static inline int path_equal(const struct path *path1, const struct path *path2) return path1->mnt == path2->mnt && path1->dentry == path2->dentry; } -static inline void path_put_init(struct path *path) -{ - path_put(path); - *path = (struct path) { }; -} - /* * Cleanup macro for use with __free(path_put). Avoids dereference and * copying @path unlike DEFINE_FREE(). path_put() will handle the empty -- cgit v1.2.3 From 71ff58ce3428b2471efae5b00594e892b285c97c Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 22 Aug 2024 11:30:58 +0200 Subject: fs: s/__u32/u32/ for s_fsnotify_mask The underscore variants are for uapi whereas the non-underscore variants are for in-kernel consumers. Link: https://lore.kernel.org/r/20240822-anwerben-nutzung-1cd6c82a565f@brauner Reviewed-by: Jan Kara Signed-off-by: Christian Brauner --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 8f8d274929d7..cda1f2545ea0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1266,7 +1266,7 @@ struct super_block { time64_t s_time_min; time64_t s_time_max; #ifdef CONFIG_FSNOTIFY - __u32 s_fsnotify_mask; + u32 s_fsnotify_mask; struct fsnotify_sb_info *s_fsnotify_info; #endif -- cgit v1.2.3 From da18ecbf0fb6fb73e6f9273e7aa15610f148ce17 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 23 Aug 2024 14:47:35 +0200 Subject: fs: add i_state helpers The i_state member is an unsigned long so that it can be used with the wait bit infrastructure which expects unsigned long. This wastes 4 bytes which we're unlikely to ever use. Switch to using the var event wait mechanism using the address of the bit. Thanks to Linus for the address idea. Link: https://lore.kernel.org/r/20240823-work-i_state-v3-1-5cd5fd207a57@kernel.org Reviewed-by: Josef Bacik Reviewed-by: Jan Kara Signed-off-by: Christian Brauner --- fs/inode.c | 11 +++++++++++ include/linux/fs.h | 15 +++++++++++++++ 2 files changed, 26 insertions(+) (limited to 'include/linux') diff --git a/fs/inode.c b/fs/inode.c index ba1645a09603..1b0f52ebae27 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -472,6 +472,17 @@ static void __inode_add_lru(struct inode *inode, bool rotate) inode->i_state |= I_REFERENCED; } +struct wait_queue_head *inode_bit_waitqueue(struct wait_bit_queue_entry *wqe, + struct inode *inode, u32 bit) +{ + void *bit_address; + + bit_address = inode_state_wait_address(inode, bit); + init_wait_var_entry(wqe, bit_address, 0); + return __var_waitqueue(bit_address); +} +EXPORT_SYMBOL(inode_bit_waitqueue); + /* * Add inode to LRU if needed (inode is unused and clean). * diff --git a/include/linux/fs.h b/include/linux/fs.h index cda1f2545ea0..d35de348d2ec 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -744,6 +744,21 @@ struct inode { void *i_private; /* fs or device private pointer */ } __randomize_layout; +/* + * Get bit address from inode->i_state to use with wait_var_event() + * infrastructre. + */ +#define inode_state_wait_address(inode, bit) ((char *)&(inode)->i_state + (bit)) + +struct wait_queue_head *inode_bit_waitqueue(struct wait_bit_queue_entry *wqe, + struct inode *inode, u32 bit); + +static inline void inode_wake_up_bit(struct inode *inode, u32 bit) +{ + /* Caller is responsible for correct memory barriers. */ + wake_up_var(inode_state_wait_address(inode, bit)); +} + struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode); static inline unsigned int i_blocksize(const struct inode *node) -- cgit v1.2.3 From 2ed634c96ed1d6e4ee0497be176f9980866e81cb Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 23 Aug 2024 14:47:36 +0200 Subject: fs: reorder i_state bits so that we can use the first bits to derive unique addresses from i_state. Link: https://lore.kernel.org/r/20240823-work-i_state-v3-2-5cd5fd207a57@kernel.org Reviewed-by: Josef Bacik Reviewed-by: Jeff Layton Reviewed-by: Jan Kara Signed-off-by: Christian Brauner --- include/linux/fs.h | 38 +++++++++++++++++++++----------------- 1 file changed, 21 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index d35de348d2ec..a868c9823c10 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2410,28 +2410,32 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, * i_count. * * Q: What is the difference between I_WILL_FREE and I_FREEING? + * + * __I_{SYNC,NEW,LRU_ISOLATING} are used to derive unique addresses to wait + * upon. There's one free address left. */ -#define I_DIRTY_SYNC (1 << 0) -#define I_DIRTY_DATASYNC (1 << 1) -#define I_DIRTY_PAGES (1 << 2) -#define __I_NEW 3 +#define __I_NEW 0 #define I_NEW (1 << __I_NEW) -#define I_WILL_FREE (1 << 4) -#define I_FREEING (1 << 5) -#define I_CLEAR (1 << 6) -#define __I_SYNC 7 +#define __I_SYNC 1 #define I_SYNC (1 << __I_SYNC) -#define I_REFERENCED (1 << 8) +#define __I_LRU_ISOLATING 2 +#define I_LRU_ISOLATING (1 << __I_LRU_ISOLATING) + +#define I_DIRTY_SYNC (1 << 3) +#define I_DIRTY_DATASYNC (1 << 4) +#define I_DIRTY_PAGES (1 << 5) +#define I_WILL_FREE (1 << 6) +#define I_FREEING (1 << 7) +#define I_CLEAR (1 << 8) +#define I_REFERENCED (1 << 9) #define I_LINKABLE (1 << 10) #define I_DIRTY_TIME (1 << 11) -#define I_WB_SWITCH (1 << 13) -#define I_OVL_INUSE (1 << 14) -#define I_CREATING (1 << 15) -#define I_DONTCACHE (1 << 16) -#define I_SYNC_QUEUED (1 << 17) -#define I_PINNING_NETFS_WB (1 << 18) -#define __I_LRU_ISOLATING 19 -#define I_LRU_ISOLATING (1 << __I_LRU_ISOLATING) +#define I_WB_SWITCH (1 << 12) +#define I_OVL_INUSE (1 << 13) +#define I_CREATING (1 << 14) +#define I_DONTCACHE (1 << 15) +#define I_SYNC_QUEUED (1 << 16) +#define I_PINNING_NETFS_WB (1 << 17) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) -- cgit v1.2.3 From 0fe340a98b584a31b07c664dc5ff0c923730581e Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 23 Aug 2024 14:47:38 +0200 Subject: inode: port __I_NEW to var event Port the __I_NEW mechanism to use the new var event mechanism. Link: https://lore.kernel.org/r/20240823-work-i_state-v3-4-5cd5fd207a57@kernel.org Reviewed-by: Josef Bacik Reviewed-by: Jan Kara Signed-off-by: Christian Brauner --- fs/bcachefs/fs.c | 10 ++++++---- fs/dcache.c | 7 ++++++- fs/inode.c | 32 ++++++++++++++++++++++++-------- include/linux/writeback.h | 3 ++- 4 files changed, 38 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c index 94c392abef65..c0900c0c0f8a 100644 --- a/fs/bcachefs/fs.c +++ b/fs/bcachefs/fs.c @@ -1644,14 +1644,16 @@ again: break; } } else if (clean_pass && this_pass_clean) { - wait_queue_head_t *wq = bit_waitqueue(&inode->v.i_state, __I_NEW); - DEFINE_WAIT_BIT(wait, &inode->v.i_state, __I_NEW); + struct wait_bit_queue_entry wqe; + struct wait_queue_head *wq_head; - prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); + wq_head = inode_bit_waitqueue(&wqe, &inode->v, __I_NEW); + prepare_to_wait_event(wq_head, &wqe.wq_entry, + TASK_UNINTERRUPTIBLE); mutex_unlock(&c->vfs_inodes_lock); schedule(); - finish_wait(wq, &wait.wq_entry); + finish_wait(wq_head, &wqe.wq_entry); goto again; } } diff --git a/fs/dcache.c b/fs/dcache.c index 1af75fa68638..894e38cdf4d0 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1908,8 +1908,13 @@ void d_instantiate_new(struct dentry *entry, struct inode *inode) __d_instantiate(entry, inode); WARN_ON(!(inode->i_state & I_NEW)); inode->i_state &= ~I_NEW & ~I_CREATING; + /* + * Pairs with the barrier in prepare_to_wait_event() to make sure + * ___wait_var_event() either sees the bit cleared or + * waitqueue_active() check in wake_up_var() sees the waiter. + */ smp_mb(); - wake_up_bit(&inode->i_state, __I_NEW); + inode_wake_up_bit(inode, __I_NEW); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(d_instantiate_new); diff --git a/fs/inode.c b/fs/inode.c index 1b0f52ebae27..1aa785421f13 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -734,7 +734,13 @@ static void evict(struct inode *inode) * used as an indicator whether blocking on it is safe. */ spin_lock(&inode->i_lock); - wake_up_bit(&inode->i_state, __I_NEW); + /* + * Pairs with the barrier in prepare_to_wait_event() to make sure + * ___wait_var_event() either sees the bit cleared or + * waitqueue_active() check in wake_up_var() sees the waiter. + */ + smp_mb(); + inode_wake_up_bit(inode, __I_NEW); BUG_ON(inode->i_state != (I_FREEING | I_CLEAR)); spin_unlock(&inode->i_lock); @@ -1146,8 +1152,13 @@ void unlock_new_inode(struct inode *inode) spin_lock(&inode->i_lock); WARN_ON(!(inode->i_state & I_NEW)); inode->i_state &= ~I_NEW & ~I_CREATING; + /* + * Pairs with the barrier in prepare_to_wait_event() to make sure + * ___wait_var_event() either sees the bit cleared or + * waitqueue_active() check in wake_up_var() sees the waiter. + */ smp_mb(); - wake_up_bit(&inode->i_state, __I_NEW); + inode_wake_up_bit(inode, __I_NEW); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(unlock_new_inode); @@ -1158,8 +1169,13 @@ void discard_new_inode(struct inode *inode) spin_lock(&inode->i_lock); WARN_ON(!(inode->i_state & I_NEW)); inode->i_state &= ~I_NEW; + /* + * Pairs with the barrier in prepare_to_wait_event() to make sure + * ___wait_var_event() either sees the bit cleared or + * waitqueue_active() check in wake_up_var() sees the waiter. + */ smp_mb(); - wake_up_bit(&inode->i_state, __I_NEW); + inode_wake_up_bit(inode, __I_NEW); spin_unlock(&inode->i_lock); iput(inode); } @@ -2348,8 +2364,8 @@ EXPORT_SYMBOL(inode_needs_sync); */ static void __wait_on_freeing_inode(struct inode *inode, bool is_inode_hash_locked) { - wait_queue_head_t *wq; - DEFINE_WAIT_BIT(wait, &inode->i_state, __I_NEW); + struct wait_bit_queue_entry wqe; + struct wait_queue_head *wq_head; /* * Handle racing against evict(), see that routine for more details. @@ -2360,14 +2376,14 @@ static void __wait_on_freeing_inode(struct inode *inode, bool is_inode_hash_lock return; } - wq = bit_waitqueue(&inode->i_state, __I_NEW); - prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); + wq_head = inode_bit_waitqueue(&wqe, inode, __I_NEW); + prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE); spin_unlock(&inode->i_lock); rcu_read_unlock(); if (is_inode_hash_locked) spin_unlock(&inode_hash_lock); schedule(); - finish_wait(wq, &wait.wq_entry); + finish_wait(wq_head, &wqe.wq_entry); if (is_inode_hash_locked) spin_lock(&inode_hash_lock); rcu_read_lock(); diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 56b85841ae4c..8f651bb0a1a5 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -200,7 +200,8 @@ void inode_io_list_del(struct inode *inode); /* writeback.h requires fs.h; it, too, is not included from here. */ static inline void wait_on_inode(struct inode *inode) { - wait_on_bit(&inode->i_state, __I_NEW, TASK_UNINTERRUPTIBLE); + wait_var_event(inode_state_wait_address(inode, __I_NEW), + !(READ_ONCE(inode->i_state) & I_NEW)); } #ifdef CONFIG_CGROUP_WRITEBACK -- cgit v1.2.3 From 2b111edbe0a9c441605be5cfb73001dc98ec686f Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 23 Aug 2024 14:47:40 +0200 Subject: inode: make i_state a u32 Now that we use the wait var event mechanism make i_state a u32 and free up 4 bytes. This means we currently have two 4 byte holes in struct inode which we can pack. Link: https://lore.kernel.org/r/20240823-work-i_state-v3-6-5cd5fd207a57@kernel.org Reviewed-by: Josef Bacik Reviewed-by: Jan Kara Signed-off-by: Christian Brauner --- include/linux/fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index a868c9823c10..a1ef8c65d828 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -681,7 +681,8 @@ struct inode { #endif /* Misc */ - unsigned long i_state; + u32 i_state; + /* 32-bit hole */ struct rw_semaphore i_rwsem; unsigned long dirtied_when; /* jiffies of first dirtying */ -- cgit v1.2.3 From 2a9f8995f7139a759fe8cb31d9e8a433757228ec Mon Sep 17 00:00:00 2001 From: Javier Carrasco Date: Thu, 4 Jul 2024 19:23:18 +0200 Subject: mfd: 88pm80x: Constify read-only regmap structs `pm800_irq`, `pm805_irq` and `pm805_irq_chip` are not modified and can be declared as const to move their data to a read-only section. In order to keep the const modifier for the regmap_irq_chip structures, the pointer used to reference them must be converted to const as well. Signed-off-by: Javier Carrasco Link: https://lore.kernel.org/r/20240704-mfd-const-regmap_config-v2-8-0c8785b1331d@gmail.com Signed-off-by: Lee Jones --- drivers/mfd/88pm800.c | 2 +- drivers/mfd/88pm805.c | 4 ++-- include/linux/mfd/88pm80x.h | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/88pm800.c b/drivers/mfd/88pm800.c index 384ecf5301d2..e9941da58b18 100644 --- a/drivers/mfd/88pm800.c +++ b/drivers/mfd/88pm800.c @@ -391,7 +391,7 @@ static void device_irq_exit_800(struct pm80x_chip *chip) regmap_del_irq_chip(chip->irq, chip->irq_data); } -static struct regmap_irq_chip pm800_irq_chip = { +static const struct regmap_irq_chip pm800_irq_chip = { .name = "88pm800", .irqs = pm800_irqs, .num_irqs = ARRAY_SIZE(pm800_irqs), diff --git a/drivers/mfd/88pm805.c b/drivers/mfd/88pm805.c index 205f0762a928..f5d6663172ee 100644 --- a/drivers/mfd/88pm805.c +++ b/drivers/mfd/88pm805.c @@ -73,7 +73,7 @@ static const struct mfd_cell codec_devs[] = { }, }; -static struct regmap_irq pm805_irqs[] = { +static const struct regmap_irq pm805_irqs[] = { /* INT0 */ [PM805_IRQ_LDO_OFF] = { .mask = PM805_INT1_HP1_SHRT, @@ -163,7 +163,7 @@ static void device_irq_exit_805(struct pm80x_chip *chip) regmap_del_irq_chip(chip->irq, chip->irq_data); } -static struct regmap_irq_chip pm805_irq_chip = { +static const struct regmap_irq_chip pm805_irq_chip = { .name = "88pm805", .irqs = pm805_irqs, .num_irqs = ARRAY_SIZE(pm805_irqs), diff --git a/include/linux/mfd/88pm80x.h b/include/linux/mfd/88pm80x.h index def5df6e74bf..551ef1c367d6 100644 --- a/include/linux/mfd/88pm80x.h +++ b/include/linux/mfd/88pm80x.h @@ -294,7 +294,7 @@ struct pm80x_chip { struct i2c_client *client; struct i2c_client *companion; struct regmap *regmap; - struct regmap_irq_chip *regmap_irq_chip; + const struct regmap_irq_chip *regmap_irq_chip; struct regmap_irq_chip_data *irq_data; int type; int irq; -- cgit v1.2.3 From 87b9c9ea01f4fd9193f30cc19bd03b05541ff4cb Mon Sep 17 00:00:00 2001 From: Wilken Gottwalt Date: Mon, 15 Jul 2024 08:17:28 +0000 Subject: mfd: ds1wm: Remove remaining header file The driver was removed after kernel 6.2 rendering the header file unused. Signed-off-by: Wilken Gottwalt Link: https://lore.kernel.org/r/ZpTbGHb6EX2Oe7ok@monster.localdomain Signed-off-by: Lee Jones --- include/linux/mfd/ds1wm.h | 29 ----------------------------- 1 file changed, 29 deletions(-) delete mode 100644 include/linux/mfd/ds1wm.h (limited to 'include/linux') diff --git a/include/linux/mfd/ds1wm.h b/include/linux/mfd/ds1wm.h deleted file mode 100644 index 43dfca1c9702..000000000000 --- a/include/linux/mfd/ds1wm.h +++ /dev/null @@ -1,29 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* MFD cell driver data for the DS1WM driver - * - * to be defined in the MFD device that is - * using this driver for one of his sub devices - */ - -struct ds1wm_driver_data { - int active_high; - int clock_rate; - /* in milliseconds, the amount of time to - * sleep following a reset pulse. Zero - * should work if your bus devices recover - * time respects the 1-wire spec since the - * ds1wm implements the precise timings of - * a reset pulse/presence detect sequence. - */ - unsigned int reset_recover_delay; - - /* Say 1 here for big endian Hardware - * (only relevant with bus-shift > 0 - */ - bool is_hw_big_endian; - - /* left shift of register number to get register address offsett. - * Only 0,1,2 allowed for 8,16 or 32 bit bus width respectively - */ - unsigned int bus_shift; -}; -- cgit v1.2.3 From 5e9629d0ae977d6f6916d7e519724804e95f0b07 Mon Sep 17 00:00:00 2001 From: James Clark Date: Tue, 27 Aug 2024 15:51:12 +0100 Subject: drivers/perf: arm_spe: Use perf_allow_kernel() for permissions Use perf_allow_kernel() for 'pa_enable' (physical addresses), 'pct_enable' (physical timestamps) and context IDs. This means that perf_event_paranoid is now taken into account and LSM hooks can be used, which is more consistent with other perf_event_open calls. For example PERF_SAMPLE_PHYS_ADDR uses perf_allow_kernel() rather than just perfmon_capable(). This also indirectly fixes the following error message which is misleading because perf_event_paranoid is not taken into account by perfmon_capable(): $ perf record -e arm_spe/pa_enable/ Error: Access to performance monitoring and observability operations is limited. Consider adjusting /proc/sys/kernel/perf_event_paranoid setting ... Suggested-by: Al Grant Signed-off-by: James Clark Link: https://lore.kernel.org/r/20240827145113.1224604-1-james.clark@linaro.org Link: https://lore.kernel.org/all/20240807120039.GD37996@noisy.programming.kicks-ass.net/ Signed-off-by: Will Deacon --- drivers/perf/arm_spe_pmu.c | 9 ++++----- include/linux/perf_event.h | 8 +------- kernel/events/core.c | 9 +++++++++ 3 files changed, 14 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c index 9100d82bfabc..3569050f9cf3 100644 --- a/drivers/perf/arm_spe_pmu.c +++ b/drivers/perf/arm_spe_pmu.c @@ -41,7 +41,7 @@ /* * Cache if the event is allowed to trace Context information. - * This allows us to perform the check, i.e, perfmon_capable(), + * This allows us to perform the check, i.e, perf_allow_kernel(), * in the context of the event owner, once, during the event_init(). */ #define SPE_PMU_HW_FLAGS_CX 0x00001 @@ -50,7 +50,7 @@ static_assert((PERF_EVENT_FLAG_ARCH & SPE_PMU_HW_FLAGS_CX) == SPE_PMU_HW_FLAGS_C static void set_spe_event_has_cx(struct perf_event *event) { - if (IS_ENABLED(CONFIG_PID_IN_CONTEXTIDR) && perfmon_capable()) + if (IS_ENABLED(CONFIG_PID_IN_CONTEXTIDR) && !perf_allow_kernel(&event->attr)) event->hw.flags |= SPE_PMU_HW_FLAGS_CX; } @@ -745,9 +745,8 @@ static int arm_spe_pmu_event_init(struct perf_event *event) set_spe_event_has_cx(event); reg = arm_spe_event_to_pmscr(event); - if (!perfmon_capable() && - (reg & (PMSCR_EL1_PA | PMSCR_EL1_PCT))) - return -EACCES; + if (reg & (PMSCR_EL1_PA | PMSCR_EL1_PCT)) + return perf_allow_kernel(&event->attr); return 0; } diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 1a8942277dda..e336306b8c08 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1602,13 +1602,7 @@ static inline int perf_is_paranoid(void) return sysctl_perf_event_paranoid > -1; } -static inline int perf_allow_kernel(struct perf_event_attr *attr) -{ - if (sysctl_perf_event_paranoid > 1 && !perfmon_capable()) - return -EACCES; - - return security_perf_event_open(attr, PERF_SECURITY_KERNEL); -} +int perf_allow_kernel(struct perf_event_attr *attr); static inline int perf_allow_cpu(struct perf_event_attr *attr) { diff --git a/kernel/events/core.c b/kernel/events/core.c index aa3450bdc227..ae7d63c0c593 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -13351,6 +13351,15 @@ const struct perf_event_attr *perf_event_attrs(struct perf_event *event) return &event->attr; } +int perf_allow_kernel(struct perf_event_attr *attr) +{ + if (sysctl_perf_event_paranoid > 1 && !perfmon_capable()) + return -EACCES; + + return security_perf_event_open(attr, PERF_SECURITY_KERNEL); +} +EXPORT_SYMBOL_GPL(perf_allow_kernel); + /* * Inherit an event from parent task to child task. * -- cgit v1.2.3 From 6c17c7d5936e6af6a5bda9f9de98a5e2ee6e8a6f Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 7 Aug 2024 15:19:20 -0300 Subject: iommu: Allow ATS to work on VFs when the PF uses IDENTITY PCI ATS has a global Smallest Translation Unit field that is located in the PF but shared by all of the VFs. The expectation is that the STU will be set to the root port's global STU capability which is driven by the IO page table configuration of the iommu HW. Today it becomes set when the iommu driver first enables ATS. Thus, to enable ATS on the VF, the PF must have already had the correct STU programmed, even if ATS is off on the PF. Unfortunately the PF only programs the STU when the PF enables ATS. The iommu drivers tend to leave ATS disabled when IDENTITY translation is being used. Thus we can get into a state where the PF is setup to use IDENTITY with the DMA API while the VF would like to use VFIO with a PAGING domain and have ATS turned on. This fails because the PF never loaded a PAGING domain and so it never setup the STU, and the VF can't do it. The simplest solution is to have the iommu driver set the ATS STU when it probes the device. This way the ATS STU is loaded immediately at boot time to all PFs and there is no issue when a VF comes to use it. Add a new call pci_prepare_ats() which should be called by iommu drivers in their probe_device() op for every PCI device if the iommu driver supports ATS. This will setup the STU based on whatever page size capability the iommu HW has. Signed-off-by: Jason Gunthorpe Acked-by: Bjorn Helgaas Reviewed-by: Kevin Tian Reviewed-by: Lu Baolu Link: https://lore.kernel.org/r/0-v1-0fb4d2ab6770+7e706-ats_vf_jgg@nvidia.com Signed-off-by: Joerg Roedel --- drivers/iommu/amd/iommu.c | 3 +++ drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 6 ++++++ drivers/iommu/intel/iommu.c | 1 + drivers/pci/ats.c | 33 +++++++++++++++++++++++++++++ include/linux/pci-ats.h | 3 +++ 5 files changed, 46 insertions(+) (limited to 'include/linux') diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index b19e8c0f48fa..98054497d343 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -2203,6 +2203,9 @@ static struct iommu_device *amd_iommu_probe_device(struct device *dev) iommu_completion_wait(iommu); + if (dev_is_pci(dev)) + pci_prepare_ats(to_pci_dev(dev), PAGE_SHIFT); + return iommu_dev; } diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index a31460f9f3d4..9bc50bded5af 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -3295,6 +3295,12 @@ static struct iommu_device *arm_smmu_probe_device(struct device *dev) smmu->features & ARM_SMMU_FEAT_STALL_FORCE) master->stall_enabled = true; + if (dev_is_pci(dev)) { + unsigned int stu = __ffs(smmu->pgsize_bitmap); + + pci_prepare_ats(to_pci_dev(dev), stu); + } + return &smmu->iommu; err_free_master: diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 9ff8b83c19a3..ad81db026ab2 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -4091,6 +4091,7 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev) dev_iommu_priv_set(dev, info); if (pdev && pci_ats_supported(pdev)) { + pci_prepare_ats(pdev, VTD_PAGE_SHIFT); ret = device_rbtree_insert(iommu, info); if (ret) goto free; diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c index c570892b2090..87fa03540b8a 100644 --- a/drivers/pci/ats.c +++ b/drivers/pci/ats.c @@ -47,6 +47,39 @@ bool pci_ats_supported(struct pci_dev *dev) } EXPORT_SYMBOL_GPL(pci_ats_supported); +/** + * pci_prepare_ats - Setup the PS for ATS + * @dev: the PCI device + * @ps: the IOMMU page shift + * + * This must be done by the IOMMU driver on the PF before any VFs are created to + * ensure that the VF can have ATS enabled. + * + * Returns 0 on success, or negative on failure. + */ +int pci_prepare_ats(struct pci_dev *dev, int ps) +{ + u16 ctrl; + + if (!pci_ats_supported(dev)) + return -EINVAL; + + if (WARN_ON(dev->ats_enabled)) + return -EBUSY; + + if (ps < PCI_ATS_MIN_STU) + return -EINVAL; + + if (dev->is_virtfn) + return 0; + + dev->ats_stu = ps; + ctrl = PCI_ATS_CTRL_STU(dev->ats_stu - PCI_ATS_MIN_STU); + pci_write_config_word(dev, dev->ats_cap + PCI_ATS_CTRL, ctrl); + return 0; +} +EXPORT_SYMBOL_GPL(pci_prepare_ats); + /** * pci_enable_ats - enable the ATS capability * @dev: the PCI device diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h index df54cd5b15db..0e8b74e63767 100644 --- a/include/linux/pci-ats.h +++ b/include/linux/pci-ats.h @@ -8,6 +8,7 @@ /* Address Translation Service */ bool pci_ats_supported(struct pci_dev *dev); int pci_enable_ats(struct pci_dev *dev, int ps); +int pci_prepare_ats(struct pci_dev *dev, int ps); void pci_disable_ats(struct pci_dev *dev); int pci_ats_queue_depth(struct pci_dev *dev); int pci_ats_page_aligned(struct pci_dev *dev); @@ -16,6 +17,8 @@ static inline bool pci_ats_supported(struct pci_dev *d) { return false; } static inline int pci_enable_ats(struct pci_dev *d, int ps) { return -ENODEV; } +static inline int pci_prepare_ats(struct pci_dev *dev, int ps) +{ return -ENODEV; } static inline void pci_disable_ats(struct pci_dev *d) { } static inline int pci_ats_queue_depth(struct pci_dev *d) { return -ENODEV; } -- cgit v1.2.3 From 5c40e050e6ac0218af7c520095729d440cc87e6b Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Thu, 29 Aug 2024 15:06:40 +0200 Subject: fs: drop GFP_NOFAIL mode from alloc_page_buffers There is only one called of alloc_page_buffers and it doesn't require __GFP_NOFAIL so drop this allocation mode. Signed-off-by: Michal Hocko Link: https://lore.kernel.org/r/20240829130640.1397970-1-mhocko@kernel.org Acked-by: Song Liu Reviewed-by: Jan Kara Signed-off-by: Christian Brauner --- drivers/md/md-bitmap.c | 2 +- fs/buffer.c | 5 +---- include/linux/buffer_head.h | 3 +-- 3 files changed, 3 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 08232d8dc815..db5330d97348 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -360,7 +360,7 @@ static int read_file_page(struct file *file, unsigned long index, pr_debug("read bitmap file (%dB @ %llu)\n", (int)PAGE_SIZE, (unsigned long long)index << PAGE_SHIFT); - bh = alloc_page_buffers(page, blocksize, false); + bh = alloc_page_buffers(page, blocksize); if (!bh) { ret = -ENOMEM; goto out; diff --git a/fs/buffer.c b/fs/buffer.c index 31a9062cad7e..74f4eb5c7087 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -957,12 +957,9 @@ no_grow: } EXPORT_SYMBOL_GPL(folio_alloc_buffers); -struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, - bool retry) +struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size) { gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT; - if (retry) - gfp |= __GFP_NOFAIL; return folio_alloc_buffers(page_folio(page), size, gfp); } diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 14acf1bbe0ce..7e903457967a 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -199,8 +199,7 @@ void folio_set_bh(struct buffer_head *bh, struct folio *folio, unsigned long offset); struct buffer_head *folio_alloc_buffers(struct folio *folio, unsigned long size, gfp_t gfp); -struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, - bool retry); +struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size); struct buffer_head *create_empty_buffers(struct folio *folio, unsigned long blocksize, unsigned long b_state); void end_buffer_read_sync(struct buffer_head *bh, int uptodate); -- cgit v1.2.3 From 1a5caec7f80ca2e659c03f45378ee26915f4eda2 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Fri, 30 Aug 2024 07:35:12 -0700 Subject: regulator: core: Stub devm_regulator_bulk_get_const() if !CONFIG_REGULATOR When adding devm_regulator_bulk_get_const() I missed adding a stub for when CONFIG_REGULATOR is not enabled. Under certain conditions (like randconfig testing) this can cause the compiler to reports errors like: error: implicit declaration of function 'devm_regulator_bulk_get_const'; did you mean 'devm_regulator_bulk_get_enable'? Add the stub. Fixes: 1de452a0edda ("regulator: core: Allow drivers to define their init data as const") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202408301813.TesFuSbh-lkp@intel.com/ Cc: Neil Armstrong Signed-off-by: Douglas Anderson Link: https://patch.msgid.link/20240830073511.1.Ib733229a8a19fad8179213c05e1af01b51e42328@changeid Signed-off-by: Mark Brown --- include/linux/regulator/consumer.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index d986ec13092e..b9ce521910a0 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -452,6 +452,14 @@ static inline int of_regulator_bulk_get_all(struct device *dev, struct device_no return 0; } +static inline int devm_regulator_bulk_get_const( + struct device *dev, int num_consumers, + const struct regulator_bulk_data *in_consumers, + struct regulator_bulk_data **out_consumers) +{ + return 0; +} + static inline int regulator_bulk_enable(int num_consumers, struct regulator_bulk_data *consumers) { -- cgit v1.2.3 From a06c3fad49a50d5d5eb078f93e70f4d3eca5d5a5 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 30 Aug 2024 14:01:45 +0100 Subject: drivers/virt: pkvm: Add initial support for running as a protected guest Implement a pKVM protected guest driver to probe the presence of pKVM and determine the memory protection granule using the HYP_MEMINFO hypercall. Acked-by: Marc Zyngier Link: https://lore.kernel.org/r/20240830130150.8568-3-will@kernel.org Signed-off-by: Will Deacon --- Documentation/virt/kvm/arm/hypercalls.rst | 22 ++++++++++++++++ arch/arm64/include/asm/hypervisor.h | 7 +++++ drivers/virt/coco/Kconfig | 2 ++ drivers/virt/coco/Makefile | 1 + drivers/virt/coco/pkvm-guest/Kconfig | 10 ++++++++ drivers/virt/coco/pkvm-guest/Makefile | 2 ++ drivers/virt/coco/pkvm-guest/arm-pkvm-guest.c | 37 +++++++++++++++++++++++++++ include/linux/arm-smccc.h | 7 +++++ 8 files changed, 88 insertions(+) create mode 100644 drivers/virt/coco/pkvm-guest/Kconfig create mode 100644 drivers/virt/coco/pkvm-guest/Makefile create mode 100644 drivers/virt/coco/pkvm-guest/arm-pkvm-guest.c (limited to 'include/linux') diff --git a/Documentation/virt/kvm/arm/hypercalls.rst b/Documentation/virt/kvm/arm/hypercalls.rst index 17be111f493f..16515eb42149 100644 --- a/Documentation/virt/kvm/arm/hypercalls.rst +++ b/Documentation/virt/kvm/arm/hypercalls.rst @@ -44,3 +44,25 @@ Provides a discovery mechanism for other KVM/arm64 hypercalls. ---------------------------------------- See ptp_kvm.rst + +``ARM_SMCCC_KVM_FUNC_HYP_MEMINFO`` +---------------------------------- + +Query the memory protection parameters for a pKVM protected virtual machine. + ++---------------------+-------------------------------------------------------------+ +| Presence: | Optional; pKVM protected guests only. | ++---------------------+-------------------------------------------------------------+ +| Calling convention: | HVC64 | ++---------------------+----------+--------------------------------------------------+ +| Function ID: | (uint32) | 0xC6000002 | ++---------------------+----------+----+---------------------------------------------+ +| Arguments: | (uint64) | R1 | Reserved / Must be zero | +| +----------+----+---------------------------------------------+ +| | (uint64) | R2 | Reserved / Must be zero | +| +----------+----+---------------------------------------------+ +| | (uint64) | R3 | Reserved / Must be zero | ++---------------------+----------+----+---------------------------------------------+ +| Return Values: | (int64) | R0 | ``INVALID_PARAMETER (-3)`` on error, else | +| | | | memory protection granule in bytes | ++---------------------+----------+----+---------------------------------------------+ diff --git a/arch/arm64/include/asm/hypervisor.h b/arch/arm64/include/asm/hypervisor.h index 8cab2ab535b7..409e239834d1 100644 --- a/arch/arm64/include/asm/hypervisor.h +++ b/arch/arm64/include/asm/hypervisor.h @@ -7,8 +7,15 @@ void kvm_init_hyp_services(void); bool kvm_arm_hyp_service_available(u32 func_id); +#ifdef CONFIG_ARM_PKVM_GUEST +void pkvm_init_hyp_services(void); +#else +static inline void pkvm_init_hyp_services(void) { }; +#endif + static inline void kvm_arch_init_hyp_services(void) { + pkvm_init_hyp_services(); }; #endif diff --git a/drivers/virt/coco/Kconfig b/drivers/virt/coco/Kconfig index 87d142c1f932..d9ff676bf48d 100644 --- a/drivers/virt/coco/Kconfig +++ b/drivers/virt/coco/Kconfig @@ -9,6 +9,8 @@ config TSM_REPORTS source "drivers/virt/coco/efi_secret/Kconfig" +source "drivers/virt/coco/pkvm-guest/Kconfig" + source "drivers/virt/coco/sev-guest/Kconfig" source "drivers/virt/coco/tdx-guest/Kconfig" diff --git a/drivers/virt/coco/Makefile b/drivers/virt/coco/Makefile index 18c1aba5edb7..b69c30c1c720 100644 --- a/drivers/virt/coco/Makefile +++ b/drivers/virt/coco/Makefile @@ -4,5 +4,6 @@ # obj-$(CONFIG_TSM_REPORTS) += tsm.o obj-$(CONFIG_EFI_SECRET) += efi_secret/ +obj-$(CONFIG_ARM_PKVM_GUEST) += pkvm-guest/ obj-$(CONFIG_SEV_GUEST) += sev-guest/ obj-$(CONFIG_INTEL_TDX_GUEST) += tdx-guest/ diff --git a/drivers/virt/coco/pkvm-guest/Kconfig b/drivers/virt/coco/pkvm-guest/Kconfig new file mode 100644 index 000000000000..d2f344f1f98f --- /dev/null +++ b/drivers/virt/coco/pkvm-guest/Kconfig @@ -0,0 +1,10 @@ +config ARM_PKVM_GUEST + bool "Arm pKVM protected guest driver" + depends on ARM64 + help + Protected guests running under the pKVM hypervisor on arm64 + are isolated from the host and must issue hypercalls to enable + interaction with virtual devices. This driver implements + support for probing and issuing these hypercalls. + + If unsure, say 'N'. diff --git a/drivers/virt/coco/pkvm-guest/Makefile b/drivers/virt/coco/pkvm-guest/Makefile new file mode 100644 index 000000000000..4bee24579423 --- /dev/null +++ b/drivers/virt/coco/pkvm-guest/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +obj-$(CONFIG_ARM_PKVM_GUEST) += arm-pkvm-guest.o diff --git a/drivers/virt/coco/pkvm-guest/arm-pkvm-guest.c b/drivers/virt/coco/pkvm-guest/arm-pkvm-guest.c new file mode 100644 index 000000000000..a5148701d2f1 --- /dev/null +++ b/drivers/virt/coco/pkvm-guest/arm-pkvm-guest.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Support for the hypercall interface exposed to protected guests by + * pKVM. + * + * Author: Will Deacon + * Copyright (C) 2024 Google LLC + */ + +#include +#include +#include + +#include + +static size_t pkvm_granule; + +void pkvm_init_hyp_services(void) +{ + int i; + struct arm_smccc_res res; + const u32 funcs[] = { + ARM_SMCCC_KVM_FUNC_HYP_MEMINFO, + }; + + for (i = 0; i < ARRAY_SIZE(funcs); ++i) { + if (!kvm_arm_hyp_service_available(funcs[i])) + return; + } + + arm_smccc_1_1_invoke(ARM_SMCCC_VENDOR_HYP_KVM_HYP_MEMINFO_FUNC_ID, + 0, 0, 0, &res); + if (res.a0 > PAGE_SIZE) /* Includes error codes */ + return; + + pkvm_granule = res.a0; +} diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 083f85653716..16b6dcc54e02 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -115,6 +115,7 @@ /* KVM "vendor specific" services */ #define ARM_SMCCC_KVM_FUNC_FEATURES 0 #define ARM_SMCCC_KVM_FUNC_PTP 1 +#define ARM_SMCCC_KVM_FUNC_HYP_MEMINFO 2 #define ARM_SMCCC_KVM_FUNC_FEATURES_2 127 #define ARM_SMCCC_KVM_NUM_FUNCS 128 @@ -137,6 +138,12 @@ ARM_SMCCC_OWNER_VENDOR_HYP, \ ARM_SMCCC_KVM_FUNC_PTP) +#define ARM_SMCCC_VENDOR_HYP_KVM_HYP_MEMINFO_FUNC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_64, \ + ARM_SMCCC_OWNER_VENDOR_HYP, \ + ARM_SMCCC_KVM_FUNC_HYP_MEMINFO) + /* ptp_kvm counter type ID */ #define KVM_PTP_VIRT_COUNTER 0 #define KVM_PTP_PHYS_COUNTER 1 -- cgit v1.2.3 From ebc59b120c588156feb7ce194a9636584ced18ba Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 30 Aug 2024 14:01:47 +0100 Subject: drivers/virt: pkvm: Hook up mem_encrypt API using pKVM hypercalls If we detect the presence of pKVM's SHARE and UNSHARE hypercalls, then register a backend implementation of the mem_encrypt API so that things like DMA buffers can be shared appropriately with the host. Acked-by: Marc Zyngier Link: https://lore.kernel.org/r/20240830130150.8568-5-will@kernel.org Signed-off-by: Will Deacon --- Documentation/virt/kvm/arm/hypercalls.rst | 50 ++++++++++++++++++++++++ drivers/virt/coco/pkvm-guest/arm-pkvm-guest.c | 55 +++++++++++++++++++++++++++ include/linux/arm-smccc.h | 14 +++++++ 3 files changed, 119 insertions(+) (limited to 'include/linux') diff --git a/Documentation/virt/kvm/arm/hypercalls.rst b/Documentation/virt/kvm/arm/hypercalls.rst index 16515eb42149..c42580e71bf8 100644 --- a/Documentation/virt/kvm/arm/hypercalls.rst +++ b/Documentation/virt/kvm/arm/hypercalls.rst @@ -66,3 +66,53 @@ Query the memory protection parameters for a pKVM protected virtual machine. | Return Values: | (int64) | R0 | ``INVALID_PARAMETER (-3)`` on error, else | | | | | memory protection granule in bytes | +---------------------+----------+----+---------------------------------------------+ + +``ARM_SMCCC_KVM_FUNC_MEM_SHARE`` +-------------------------------- + +Share a region of memory with the KVM host, granting it read, write and execute +permissions. The size of the region is equal to the memory protection granule +advertised by ``ARM_SMCCC_KVM_FUNC_HYP_MEMINFO``. + ++---------------------+-------------------------------------------------------------+ +| Presence: | Optional; pKVM protected guests only. | ++---------------------+-------------------------------------------------------------+ +| Calling convention: | HVC64 | ++---------------------+----------+--------------------------------------------------+ +| Function ID: | (uint32) | 0xC6000003 | ++---------------------+----------+----+---------------------------------------------+ +| Arguments: | (uint64) | R1 | Base IPA of memory region to share | +| +----------+----+---------------------------------------------+ +| | (uint64) | R2 | Reserved / Must be zero | +| +----------+----+---------------------------------------------+ +| | (uint64) | R3 | Reserved / Must be zero | ++---------------------+----------+----+---------------------------------------------+ +| Return Values: | (int64) | R0 | ``SUCCESS (0)`` | +| | | +---------------------------------------------+ +| | | | ``INVALID_PARAMETER (-3)`` | ++---------------------+----------+----+---------------------------------------------+ + +``ARM_SMCCC_KVM_FUNC_MEM_UNSHARE`` +---------------------------------- + +Revoke access permission from the KVM host to a memory region previously shared +with ``ARM_SMCCC_KVM_FUNC_MEM_SHARE``. The size of the region is equal to the +memory protection granule advertised by ``ARM_SMCCC_KVM_FUNC_HYP_MEMINFO``. + ++---------------------+-------------------------------------------------------------+ +| Presence: | Optional; pKVM protected guests only. | ++---------------------+-------------------------------------------------------------+ +| Calling convention: | HVC64 | ++---------------------+----------+--------------------------------------------------+ +| Function ID: | (uint32) | 0xC6000004 | ++---------------------+----------+----+---------------------------------------------+ +| Arguments: | (uint64) | R1 | Base IPA of memory region to unshare | +| +----------+----+---------------------------------------------+ +| | (uint64) | R2 | Reserved / Must be zero | +| +----------+----+---------------------------------------------+ +| | (uint64) | R3 | Reserved / Must be zero | ++---------------------+----------+----+---------------------------------------------+ +| Return Values: | (int64) | R0 | ``SUCCESS (0)`` | +| | | +---------------------------------------------+ +| | | | ``INVALID_PARAMETER (-3)`` | ++---------------------+----------+----+---------------------------------------------+ diff --git a/drivers/virt/coco/pkvm-guest/arm-pkvm-guest.c b/drivers/virt/coco/pkvm-guest/arm-pkvm-guest.c index a5148701d2f1..8256cf68fd76 100644 --- a/drivers/virt/coco/pkvm-guest/arm-pkvm-guest.c +++ b/drivers/virt/coco/pkvm-guest/arm-pkvm-guest.c @@ -9,18 +9,72 @@ #include #include +#include #include #include static size_t pkvm_granule; +static int arm_smccc_do_one_page(u32 func_id, phys_addr_t phys) +{ + phys_addr_t end = phys + PAGE_SIZE; + + while (phys < end) { + struct arm_smccc_res res; + + arm_smccc_1_1_invoke(func_id, phys, 0, 0, &res); + if (res.a0 != SMCCC_RET_SUCCESS) + return -EPERM; + + phys += pkvm_granule; + } + + return 0; +} + +static int __set_memory_range(u32 func_id, unsigned long start, int numpages) +{ + void *addr = (void *)start, *end = addr + numpages * PAGE_SIZE; + + while (addr < end) { + int err; + + err = arm_smccc_do_one_page(func_id, virt_to_phys(addr)); + if (err) + return err; + + addr += PAGE_SIZE; + } + + return 0; +} + +static int pkvm_set_memory_encrypted(unsigned long addr, int numpages) +{ + return __set_memory_range(ARM_SMCCC_VENDOR_HYP_KVM_MEM_UNSHARE_FUNC_ID, + addr, numpages); +} + +static int pkvm_set_memory_decrypted(unsigned long addr, int numpages) +{ + return __set_memory_range(ARM_SMCCC_VENDOR_HYP_KVM_MEM_SHARE_FUNC_ID, + addr, numpages); +} + +static const struct arm64_mem_crypt_ops pkvm_crypt_ops = { + .encrypt = pkvm_set_memory_encrypted, + .decrypt = pkvm_set_memory_decrypted, +}; + void pkvm_init_hyp_services(void) { int i; struct arm_smccc_res res; const u32 funcs[] = { ARM_SMCCC_KVM_FUNC_HYP_MEMINFO, + ARM_SMCCC_KVM_FUNC_MEM_SHARE, + ARM_SMCCC_KVM_FUNC_MEM_UNSHARE, }; for (i = 0; i < ARRAY_SIZE(funcs); ++i) { @@ -34,4 +88,5 @@ void pkvm_init_hyp_services(void) return; pkvm_granule = res.a0; + arm64_mem_crypt_ops_register(&pkvm_crypt_ops); } diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 16b6dcc54e02..9cb7c95920b0 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -116,6 +116,8 @@ #define ARM_SMCCC_KVM_FUNC_FEATURES 0 #define ARM_SMCCC_KVM_FUNC_PTP 1 #define ARM_SMCCC_KVM_FUNC_HYP_MEMINFO 2 +#define ARM_SMCCC_KVM_FUNC_MEM_SHARE 3 +#define ARM_SMCCC_KVM_FUNC_MEM_UNSHARE 4 #define ARM_SMCCC_KVM_FUNC_FEATURES_2 127 #define ARM_SMCCC_KVM_NUM_FUNCS 128 @@ -144,6 +146,18 @@ ARM_SMCCC_OWNER_VENDOR_HYP, \ ARM_SMCCC_KVM_FUNC_HYP_MEMINFO) +#define ARM_SMCCC_VENDOR_HYP_KVM_MEM_SHARE_FUNC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_64, \ + ARM_SMCCC_OWNER_VENDOR_HYP, \ + ARM_SMCCC_KVM_FUNC_MEM_SHARE) + +#define ARM_SMCCC_VENDOR_HYP_KVM_MEM_UNSHARE_FUNC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_64, \ + ARM_SMCCC_OWNER_VENDOR_HYP, \ + ARM_SMCCC_KVM_FUNC_MEM_UNSHARE) + /* ptp_kvm counter type ID */ #define KVM_PTP_VIRT_COUNTER 0 #define KVM_PTP_PHYS_COUNTER 1 -- cgit v1.2.3 From 0f12694958001c96bda811473fdb23f333c6d3ca Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 30 Aug 2024 14:01:49 +0100 Subject: drivers/virt: pkvm: Intercept ioremap using pKVM MMIO_GUARD hypercall Hook up pKVM's MMIO_GUARD hypercall so that ioremap() and friends will register the target physical address as MMIO with the hypervisor, allowing guest exits to that page to be emulated by the host with full syndrome information. Acked-by: Marc Zyngier Link: https://lore.kernel.org/r/20240830130150.8568-7-will@kernel.org Signed-off-by: Will Deacon --- Documentation/virt/kvm/arm/hypercalls.rst | 26 ++++++++++++++++++++ drivers/virt/coco/pkvm-guest/arm-pkvm-guest.c | 35 +++++++++++++++++++++++++++ include/linux/arm-smccc.h | 7 ++++++ 3 files changed, 68 insertions(+) (limited to 'include/linux') diff --git a/Documentation/virt/kvm/arm/hypercalls.rst b/Documentation/virt/kvm/arm/hypercalls.rst index c42580e71bf8..af7bc2c2e0cb 100644 --- a/Documentation/virt/kvm/arm/hypercalls.rst +++ b/Documentation/virt/kvm/arm/hypercalls.rst @@ -116,3 +116,29 @@ memory protection granule advertised by ``ARM_SMCCC_KVM_FUNC_HYP_MEMINFO``. | | | +---------------------------------------------+ | | | | ``INVALID_PARAMETER (-3)`` | +---------------------+----------+----+---------------------------------------------+ + +``ARM_SMCCC_KVM_FUNC_MMIO_GUARD`` +---------------------------------- + +Request that a given memory region is handled as MMIO by the hypervisor, +allowing accesses to this region to be emulated by the KVM host. The size of the +region is equal to the memory protection granule advertised by +``ARM_SMCCC_KVM_FUNC_HYP_MEMINFO``. + ++---------------------+-------------------------------------------------------------+ +| Presence: | Optional; pKVM protected guests only. | ++---------------------+-------------------------------------------------------------+ +| Calling convention: | HVC64 | ++---------------------+----------+--------------------------------------------------+ +| Function ID: | (uint32) | 0xC6000007 | ++---------------------+----------+----+---------------------------------------------+ +| Arguments: | (uint64) | R1 | Base IPA of MMIO memory region | +| +----------+----+---------------------------------------------+ +| | (uint64) | R2 | Reserved / Must be zero | +| +----------+----+---------------------------------------------+ +| | (uint64) | R3 | Reserved / Must be zero | ++---------------------+----------+----+---------------------------------------------+ +| Return Values: | (int64) | R0 | ``SUCCESS (0)`` | +| | | +---------------------------------------------+ +| | | | ``INVALID_PARAMETER (-3)`` | ++---------------------+----------+----+---------------------------------------------+ diff --git a/drivers/virt/coco/pkvm-guest/arm-pkvm-guest.c b/drivers/virt/coco/pkvm-guest/arm-pkvm-guest.c index 8256cf68fd76..56a3859dda8a 100644 --- a/drivers/virt/coco/pkvm-guest/arm-pkvm-guest.c +++ b/drivers/virt/coco/pkvm-guest/arm-pkvm-guest.c @@ -9,8 +9,10 @@ #include #include +#include #include #include +#include #include @@ -67,6 +69,36 @@ static const struct arm64_mem_crypt_ops pkvm_crypt_ops = { .decrypt = pkvm_set_memory_decrypted, }; +static int mmio_guard_ioremap_hook(phys_addr_t phys, size_t size, + pgprot_t *prot) +{ + phys_addr_t end; + pteval_t protval = pgprot_val(*prot); + + /* + * We only expect MMIO emulation for regions mapped with device + * attributes. + */ + if (protval != PROT_DEVICE_nGnRE && protval != PROT_DEVICE_nGnRnE) + return 0; + + phys = PAGE_ALIGN_DOWN(phys); + end = phys + PAGE_ALIGN(size); + + while (phys < end) { + const int func_id = ARM_SMCCC_VENDOR_HYP_KVM_MMIO_GUARD_FUNC_ID; + int err; + + err = arm_smccc_do_one_page(func_id, phys); + if (err) + return err; + + phys += PAGE_SIZE; + } + + return 0; +} + void pkvm_init_hyp_services(void) { int i; @@ -89,4 +121,7 @@ void pkvm_init_hyp_services(void) pkvm_granule = res.a0; arm64_mem_crypt_ops_register(&pkvm_crypt_ops); + + if (kvm_arm_hyp_service_available(ARM_SMCCC_KVM_FUNC_MMIO_GUARD)) + arm64_ioremap_prot_hook_register(&mmio_guard_ioremap_hook); } diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 9cb7c95920b0..e93c1f7cea70 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -118,6 +118,7 @@ #define ARM_SMCCC_KVM_FUNC_HYP_MEMINFO 2 #define ARM_SMCCC_KVM_FUNC_MEM_SHARE 3 #define ARM_SMCCC_KVM_FUNC_MEM_UNSHARE 4 +#define ARM_SMCCC_KVM_FUNC_MMIO_GUARD 7 #define ARM_SMCCC_KVM_FUNC_FEATURES_2 127 #define ARM_SMCCC_KVM_NUM_FUNCS 128 @@ -158,6 +159,12 @@ ARM_SMCCC_OWNER_VENDOR_HYP, \ ARM_SMCCC_KVM_FUNC_MEM_UNSHARE) +#define ARM_SMCCC_VENDOR_HYP_KVM_MMIO_GUARD_FUNC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_64, \ + ARM_SMCCC_OWNER_VENDOR_HYP, \ + ARM_SMCCC_KVM_FUNC_MMIO_GUARD) + /* ptp_kvm counter type ID */ #define KVM_PTP_VIRT_COUNTER 0 #define KVM_PTP_PHYS_COUNTER 1 -- cgit v1.2.3 From 21be9f7110d4c044c2b49bafbd7246335f236221 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 30 Aug 2024 14:01:50 +0100 Subject: arm64: smccc: Reserve block of KVM "vendor" services for pKVM hypercalls pKVM relies on hypercalls to expose services such as memory sharing to protected guests. Tentatively allocate a block of 58 hypercalls (i.e. fill the remaining space in the first 64 function IDs) for pKVM usage, as future extensions such as pvIOMMU support, range-based memory sharing and validation of assigned devices will require additional services. Suggested-by: Marc Zyngier Link: https://lore.kernel.org/r/86a5h5yg5y.wl-maz@kernel.org Acked-by: Marc Zyngier Link: https://lore.kernel.org/r/20240830130150.8568-8-will@kernel.org Signed-off-by: Will Deacon --- include/linux/arm-smccc.h | 60 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 60 insertions(+) (limited to 'include/linux') diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index e93c1f7cea70..f59099a213d0 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -115,10 +115,70 @@ /* KVM "vendor specific" services */ #define ARM_SMCCC_KVM_FUNC_FEATURES 0 #define ARM_SMCCC_KVM_FUNC_PTP 1 +/* Start of pKVM hypercall range */ #define ARM_SMCCC_KVM_FUNC_HYP_MEMINFO 2 #define ARM_SMCCC_KVM_FUNC_MEM_SHARE 3 #define ARM_SMCCC_KVM_FUNC_MEM_UNSHARE 4 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_5 5 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_6 6 #define ARM_SMCCC_KVM_FUNC_MMIO_GUARD 7 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_8 8 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_9 9 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_10 10 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_11 11 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_12 12 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_13 13 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_14 14 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_15 15 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_16 16 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_17 17 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_18 18 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_19 19 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_20 20 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_21 21 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_22 22 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_23 23 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_24 24 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_25 25 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_26 26 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_27 27 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_28 28 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_29 29 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_30 30 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_31 31 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_32 32 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_33 33 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_34 34 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_35 35 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_36 36 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_37 37 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_38 38 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_39 39 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_40 40 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_41 41 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_42 42 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_43 43 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_44 44 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_45 45 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_46 46 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_47 47 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_48 48 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_49 49 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_50 50 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_51 51 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_52 52 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_53 53 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_54 54 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_55 55 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_56 56 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_57 57 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_58 58 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_59 59 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_60 60 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_61 61 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_62 62 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_63 63 +/* End of pKVM hypercall range */ #define ARM_SMCCC_KVM_FUNC_FEATURES_2 127 #define ARM_SMCCC_KVM_NUM_FUNCS 128 -- cgit v1.2.3 From 929c81ade6355b87097a2a4886c10750e68626cf Mon Sep 17 00:00:00 2001 From: Thomas Weißschuh Date: Fri, 30 Aug 2024 11:45:57 +0200 Subject: fbdev: Introduce devm_register_framebuffer() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce a device-managed variant of register_framebuffer() which automatically unregisters the framebuffer on device destruction. This can simplify the error handling and resource management in drivers. Signed-off-by: Thomas Weißschuh Signed-off-by: Helge Deller --- drivers/video/fbdev/core/fbmem.c | 30 ++++++++++++++++++++++++++++++ include/linux/fb.h | 1 + 2 files changed, 31 insertions(+) (limited to 'include/linux') diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index 4c4ad0a86a50..3c568cff2913 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -544,6 +544,36 @@ unregister_framebuffer(struct fb_info *fb_info) } EXPORT_SYMBOL(unregister_framebuffer); +static void devm_unregister_framebuffer(void *data) +{ + struct fb_info *info = data; + + unregister_framebuffer(info); +} + +/** + * devm_register_framebuffer - resource-managed frame buffer device registration + * @dev: device the framebuffer belongs to + * @fb_info: frame buffer info structure + * + * Registers a frame buffer device @fb_info to device @dev. + * + * Returns negative errno on error, or zero for success. + * + */ +int +devm_register_framebuffer(struct device *dev, struct fb_info *fb_info) +{ + int ret; + + ret = register_framebuffer(fb_info); + if (ret) + return ret; + + return devm_add_action_or_reset(dev, devm_unregister_framebuffer, fb_info); +} +EXPORT_SYMBOL(devm_register_framebuffer); + /** * fb_set_suspend - low level driver signals suspend * @info: framebuffer affected diff --git a/include/linux/fb.h b/include/linux/fb.h index db7d97b10964..abf6643ebcaf 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -601,6 +601,7 @@ extern ssize_t fb_sys_write(struct fb_info *info, const char __user *buf, /* fbmem.c */ extern int register_framebuffer(struct fb_info *fb_info); extern void unregister_framebuffer(struct fb_info *fb_info); +extern int devm_register_framebuffer(struct device *dev, struct fb_info *fb_info); extern char* fb_get_buffer_offset(struct fb_info *info, struct fb_pixmap *buf, u32 size); extern void fb_pad_unaligned_buffer(u8 *dst, u32 d_pitch, u8 *src, u32 idx, u32 height, u32 shift_high, u32 shift_low, u32 mod); -- cgit v1.2.3 From 9aee8262445d185960431e972e2d997e6aba3de0 Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Mon, 26 Aug 2024 11:58:23 +0800 Subject: ARM: OMAP2+: Remove obsoleted declaration for gpmc_onenand_init The gpmc_onenand_init() have been removed since commit 2514830b8b8c ("ARM: OMAP2+: Remove gpmc-onenand"), and now it is useless, so remove it. Signed-off-by: Gaosheng Cui Link: https://lore.kernel.org/r/20240826035823.4043171-1-cuigaosheng1@huawei.com Signed-off-by: Kevin Hilman --- include/linux/omap-gpmc.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/omap-gpmc.h b/include/linux/omap-gpmc.h index 082841908fe7..c9e3843d2dd5 100644 --- a/include/linux/omap-gpmc.h +++ b/include/linux/omap-gpmc.h @@ -84,13 +84,3 @@ extern void gpmc_read_settings_dt(struct device_node *np, struct gpmc_timings; struct omap_nand_platform_data; struct omap_onenand_platform_data; - -#if IS_ENABLED(CONFIG_MTD_ONENAND_OMAP2) -extern int gpmc_onenand_init(struct omap_onenand_platform_data *d); -#else -#define board_onenand_data NULL -static inline int gpmc_onenand_init(struct omap_onenand_platform_data *d) -{ - return 0; -} -#endif -- cgit v1.2.3 From ddc94d0b17e8ea8179ecbbefacac3fba0fb77265 Mon Sep 17 00:00:00 2001 From: Matthew Brost Date: Mon, 26 Aug 2024 10:01:43 -0700 Subject: dma-buf: Split out dma fence array create into alloc and arm functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Useful to preallocate dma fence array and then arm in path of reclaim or a dma fence. v2: - s/arm/init (Christian) - Drop !array warn (Christian) v3: - Fix kernel doc typos (dim) Cc: Sumit Semwal Cc: Christian König Signed-off-by: Matthew Brost Reviewed-by: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/20240826170144.2492062-2-matthew.brost@intel.com --- drivers/dma-buf/dma-fence-array.c | 78 ++++++++++++++++++++++++++++----------- include/linux/dma-fence-array.h | 6 +++ 2 files changed, 63 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma-buf/dma-fence-array.c b/drivers/dma-buf/dma-fence-array.c index c74ac197d5fe..8a08ffde31e7 100644 --- a/drivers/dma-buf/dma-fence-array.c +++ b/drivers/dma-buf/dma-fence-array.c @@ -144,37 +144,38 @@ const struct dma_fence_ops dma_fence_array_ops = { EXPORT_SYMBOL(dma_fence_array_ops); /** - * dma_fence_array_create - Create a custom fence array + * dma_fence_array_alloc - Allocate a custom fence array + * @num_fences: [in] number of fences to add in the array + * + * Return dma fence array on success, NULL on failure + */ +struct dma_fence_array *dma_fence_array_alloc(int num_fences) +{ + struct dma_fence_array *array; + + return kzalloc(struct_size(array, callbacks, num_fences), GFP_KERNEL); +} +EXPORT_SYMBOL(dma_fence_array_alloc); + +/** + * dma_fence_array_init - Init a custom fence array + * @array: [in] dma fence array to arm * @num_fences: [in] number of fences to add in the array * @fences: [in] array containing the fences * @context: [in] fence context to use * @seqno: [in] sequence number to use * @signal_on_any: [in] signal on any fence in the array * - * Allocate a dma_fence_array object and initialize the base fence with - * dma_fence_init(). - * In case of error it returns NULL. - * - * The caller should allocate the fences array with num_fences size - * and fill it with the fences it wants to add to the object. Ownership of this - * array is taken and dma_fence_put() is used on each fence on release. - * - * If @signal_on_any is true the fence array signals if any fence in the array - * signals, otherwise it signals when all fences in the array signal. + * Implementation of @dma_fence_array_create without allocation. Useful to init + * a preallocated dma fence array in the path of reclaim or dma fence signaling. */ -struct dma_fence_array *dma_fence_array_create(int num_fences, - struct dma_fence **fences, - u64 context, unsigned seqno, - bool signal_on_any) +void dma_fence_array_init(struct dma_fence_array *array, + int num_fences, struct dma_fence **fences, + u64 context, unsigned seqno, + bool signal_on_any) { - struct dma_fence_array *array; - WARN_ON(!num_fences || !fences); - array = kzalloc(struct_size(array, callbacks, num_fences), GFP_KERNEL); - if (!array) - return NULL; - array->num_fences = num_fences; spin_lock_init(&array->lock); @@ -200,6 +201,41 @@ struct dma_fence_array *dma_fence_array_create(int num_fences, */ while (num_fences--) WARN_ON(dma_fence_is_container(fences[num_fences])); +} +EXPORT_SYMBOL(dma_fence_array_init); + +/** + * dma_fence_array_create - Create a custom fence array + * @num_fences: [in] number of fences to add in the array + * @fences: [in] array containing the fences + * @context: [in] fence context to use + * @seqno: [in] sequence number to use + * @signal_on_any: [in] signal on any fence in the array + * + * Allocate a dma_fence_array object and initialize the base fence with + * dma_fence_init(). + * In case of error it returns NULL. + * + * The caller should allocate the fences array with num_fences size + * and fill it with the fences it wants to add to the object. Ownership of this + * array is taken and dma_fence_put() is used on each fence on release. + * + * If @signal_on_any is true the fence array signals if any fence in the array + * signals, otherwise it signals when all fences in the array signal. + */ +struct dma_fence_array *dma_fence_array_create(int num_fences, + struct dma_fence **fences, + u64 context, unsigned seqno, + bool signal_on_any) +{ + struct dma_fence_array *array; + + array = dma_fence_array_alloc(num_fences); + if (!array) + return NULL; + + dma_fence_array_init(array, num_fences, fences, + context, seqno, signal_on_any); return array; } diff --git a/include/linux/dma-fence-array.h b/include/linux/dma-fence-array.h index 29c5650c1038..079b3dec0a16 100644 --- a/include/linux/dma-fence-array.h +++ b/include/linux/dma-fence-array.h @@ -79,6 +79,12 @@ to_dma_fence_array(struct dma_fence *fence) for (index = 0, fence = dma_fence_array_first(head); fence; \ ++(index), fence = dma_fence_array_next(head, index)) +struct dma_fence_array *dma_fence_array_alloc(int num_fences); +void dma_fence_array_init(struct dma_fence_array *array, + int num_fences, struct dma_fence **fences, + u64 context, unsigned seqno, + bool signal_on_any); + struct dma_fence_array *dma_fence_array_create(int num_fences, struct dma_fence **fences, u64 context, unsigned seqno, -- cgit v1.2.3 From 1abab1ba0775036bb67c6c57945c637be644c04f Mon Sep 17 00:00:00 2001 From: Chen Ridong Date: Fri, 30 Aug 2024 10:02:28 +0000 Subject: cgroup/cpuset: guard cpuset-v1 code under CONFIG_CPUSETS_V1 This patch introduces CONFIG_CPUSETS_V1 and guard cpuset-v1 code under CONFIG_CPUSETS_V1. The default value of CONFIG_CPUSETS_V1 is N, so that user who adopted v2 don't have 'pay' for cpuset v1. Signed-off-by: Chen Ridong Acked-by: Waiman Long Signed-off-by: Tejun Heo --- include/linux/cpuset.h | 4 ++++ init/Kconfig | 13 +++++++++++++ kernel/cgroup/Makefile | 3 ++- kernel/cgroup/cpuset-internal.h | 12 ++++++++++++ kernel/cgroup/cpuset.c | 2 ++ 5 files changed, 33 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 2a6981eeebf8..835e7b793f6a 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -99,6 +99,7 @@ static inline bool cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) extern int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, const struct task_struct *tsk2); +#ifdef CONFIG_CPUSETS_V1 #define cpuset_memory_pressure_bump() \ do { \ if (cpuset_memory_pressure_enabled) \ @@ -106,6 +107,9 @@ extern int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, } while (0) extern int cpuset_memory_pressure_enabled; extern void __cpuset_memory_pressure_bump(void); +#else +static inline void cpuset_memory_pressure_bump(void) { } +#endif extern void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task); diff --git a/init/Kconfig b/init/Kconfig index a465ea9525bd..8bf091354bea 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1143,6 +1143,19 @@ config CPUSETS Say N if unsure. +config CPUSETS_V1 + bool "Legacy cgroup v1 cpusets controller" + depends on CPUSETS + default n + help + Legacy cgroup v1 cpusets controller which has been deprecated by + cgroup v2 implementation. The v1 is there for legacy applications + which haven't migrated to the new cgroup v2 interface yet. If you + do not have any such application then you are completely fine leaving + this option disabled. + + Say N if unsure. + config PROC_PID_CPUSET bool "Include legacy /proc//cpuset file" depends on CPUSETS diff --git a/kernel/cgroup/Makefile b/kernel/cgroup/Makefile index 005ac4c675cb..a5c9359d516f 100644 --- a/kernel/cgroup/Makefile +++ b/kernel/cgroup/Makefile @@ -4,6 +4,7 @@ obj-y := cgroup.o rstat.o namespace.o cgroup-v1.o freezer.o obj-$(CONFIG_CGROUP_FREEZER) += legacy_freezer.o obj-$(CONFIG_CGROUP_PIDS) += pids.o obj-$(CONFIG_CGROUP_RDMA) += rdma.o -obj-$(CONFIG_CPUSETS) += cpuset.o cpuset-v1.o +obj-$(CONFIG_CPUSETS) += cpuset.o +obj-$(CONFIG_CPUSETS_V1) += cpuset-v1.o obj-$(CONFIG_CGROUP_MISC) += misc.o obj-$(CONFIG_CGROUP_DEBUG) += debug.o diff --git a/kernel/cgroup/cpuset-internal.h b/kernel/cgroup/cpuset-internal.h index f36419d688bd..8c113d46ddd3 100644 --- a/kernel/cgroup/cpuset-internal.h +++ b/kernel/cgroup/cpuset-internal.h @@ -279,6 +279,7 @@ int cpuset_common_seq_show(struct seq_file *sf, void *v); /* * cpuset-v1.c */ +#ifdef CONFIG_CPUSETS_V1 extern struct cftype cpuset1_files[]; void fmeter_init(struct fmeter *fmp); void cpuset1_update_task_spread_flags(struct cpuset *cs, @@ -288,5 +289,16 @@ void cpuset1_hotplug_update_tasks(struct cpuset *cs, struct cpumask *new_cpus, nodemask_t *new_mems, bool cpus_updated, bool mems_updated); int cpuset1_validate_change(struct cpuset *cur, struct cpuset *trial); +#else +static inline void fmeter_init(struct fmeter *fmp) {} +static inline void cpuset1_update_task_spread_flags(struct cpuset *cs, + struct task_struct *tsk) {} +static inline void cpuset1_update_tasks_flags(struct cpuset *cs) {} +static inline void cpuset1_hotplug_update_tasks(struct cpuset *cs, + struct cpumask *new_cpus, nodemask_t *new_mems, + bool cpus_updated, bool mems_updated) {} +static inline int cpuset1_validate_change(struct cpuset *cur, + struct cpuset *trial) { return 0; } +#endif /* CONFIG_CPUSETS_V1 */ #endif /* __CPUSET_INTERNAL_H */ diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index c14fe8283a73..13016ad284a1 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -3623,7 +3623,9 @@ struct cgroup_subsys cpuset_cgrp_subsys = { .can_fork = cpuset_can_fork, .cancel_fork = cpuset_cancel_fork, .fork = cpuset_fork, +#ifdef CONFIG_CPUSETS_V1 .legacy_cftypes = cpuset1_files, +#endif .dfl_cftypes = dfl_files, .early_init = true, .threaded = true, -- cgit v1.2.3 From 0328947c50324cf4b2d8b181bf948edb8101f59f Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Wed, 28 Aug 2024 21:16:15 +0530 Subject: PCI: endpoint: Assign PCI domain number for endpoint controllers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Right now, PCI endpoint subsystem doesn't assign PCI domain number for the PCI endpoint controllers. But this domain number could be useful to the EPC drivers to uniquely identify each controller based on the hardware instance when there are multiple ones present in an SoC (even multiple RC/EP). So let's make use of the existing pci_bus_find_domain_nr() API to allocate domain numbers based on either devicetree (linux,pci-domain) property or dynamic domain number allocation scheme. It should be noted that the domain number allocated by this API will be based on both RC and EP controllers in a SoC. If the 'linux,pci-domain' DT property is present, then the domain number represents the actual hardware instance of the PCI endpoint controller. If not, then the domain number will be allocated based on the PCI EP/RC controller probe order. If the architecture doesn't support CONFIG_PCI_DOMAINS_GENERIC (rare), then currently a warning is thrown to indicate that the architecture specific implementation is needed. Link: https://lore.kernel.org/linux-pci/20240828-pci-qcom-hotplug-v4-5-263a385fbbcb@linaro.org Signed-off-by: Manivannan Sadhasivam Signed-off-by: Krzysztof Wilczyński Reviewed-by: Frank Li --- drivers/pci/endpoint/pci-epc-core.c | 14 ++++++++++++++ include/linux/pci-epc.h | 2 ++ 2 files changed, 16 insertions(+) (limited to 'include/linux') diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c index 84309dfe0c68..085a2de8b923 100644 --- a/drivers/pci/endpoint/pci-epc-core.c +++ b/drivers/pci/endpoint/pci-epc-core.c @@ -838,6 +838,10 @@ void pci_epc_destroy(struct pci_epc *epc) { pci_ep_cfs_remove_epc_group(epc->group); device_unregister(&epc->dev); + +#ifdef CONFIG_PCI_DOMAINS_GENERIC + pci_bus_release_domain_nr(NULL, &epc->dev); +#endif } EXPORT_SYMBOL_GPL(pci_epc_destroy); @@ -900,6 +904,16 @@ __pci_epc_create(struct device *dev, const struct pci_epc_ops *ops, epc->dev.release = pci_epc_release; epc->ops = ops; +#ifdef CONFIG_PCI_DOMAINS_GENERIC + epc->domain_nr = pci_bus_find_domain_nr(NULL, dev); +#else + /* + * TODO: If the architecture doesn't support generic PCI + * domains, then a custom implementation has to be used. + */ + WARN_ONCE(1, "This architecture doesn't support generic PCI domains\n"); +#endif + ret = dev_set_name(&epc->dev, "%s", dev_name(dev)); if (ret) goto put_dev; diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index 85bdf2adb760..8e3dcac55dcd 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -128,6 +128,7 @@ struct pci_epc_mem { * @group: configfs group representing the PCI EPC device * @lock: mutex to protect pci_epc ops * @function_num_map: bitmap to manage physical function number + * @domain_nr: PCI domain number of the endpoint controller * @init_complete: flag to indicate whether the EPC initialization is complete * or not */ @@ -145,6 +146,7 @@ struct pci_epc { /* mutex to protect against concurrent access of EP controller */ struct mutex lock; unsigned long function_num_map; + int domain_nr; bool init_complete; }; -- cgit v1.2.3 From 4ed9ef32606386efc562bada891d7baa16fc46b4 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 15 Jul 2024 17:14:14 +1000 Subject: lockd: discard nlmsvc_timeout nlmsvc_timeout always has the same value as (nlm_timeout * HZ), so use that in the one place that nlmsvc_timeout is used. In truth it *might* not always be the same as nlmsvc_timeout is only set when lockd is started while nlm_timeout can be set at anytime via sysctl. I think this difference it not helpful so removing it is good. Also remove the test for nlm_timout being 0. This is not possible - unless a module parameter is used to set the minimum timeout to 0, and if that happens then it probably should be honoured. Signed-off-by: NeilBrown Signed-off-by: Chuck Lever --- fs/lockd/host.c | 2 +- fs/lockd/svc.c | 7 +------ include/linux/lockd/lockd.h | 2 +- 3 files changed, 3 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/fs/lockd/host.c b/fs/lockd/host.c index c11516801784..5e6877c37f73 100644 --- a/fs/lockd/host.c +++ b/fs/lockd/host.c @@ -440,7 +440,7 @@ nlm_bind_host(struct nlm_host *host) if ((clnt = host->h_rpcclnt) != NULL) { nlm_rebind_host(host); } else { - unsigned long increment = nlmsvc_timeout; + unsigned long increment = nlm_timeout * HZ; struct rpc_timeout timeparms = { .to_initval = increment, .to_increment = increment, diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index ab8042a5b895..71713309967d 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -53,7 +53,6 @@ EXPORT_SYMBOL_GPL(nlmsvc_ops); static DEFINE_MUTEX(nlmsvc_mutex); static unsigned int nlmsvc_users; static struct svc_serv *nlmsvc_serv; -unsigned long nlmsvc_timeout; static void nlmsvc_request_retry(struct timer_list *tl) { @@ -68,7 +67,7 @@ unsigned int lockd_net_id; * and also changed through the sysctl interface. -- Jamie Lokier, Aug 2003 */ static unsigned long nlm_grace_period; -static unsigned long nlm_timeout = LOCKD_DFLT_TIMEO; +unsigned long nlm_timeout = LOCKD_DFLT_TIMEO; static int nlm_udpport, nlm_tcpport; /* RLIM_NOFILE defaults to 1024. That seems like a reasonable default here. */ @@ -333,10 +332,6 @@ static int lockd_get(void) printk(KERN_WARNING "lockd_up: no pid, %d users??\n", nlmsvc_users); - if (!nlm_timeout) - nlm_timeout = LOCKD_DFLT_TIMEO; - nlmsvc_timeout = nlm_timeout * HZ; - serv = svc_create(&nlmsvc_program, LOCKD_BUFSIZE, lockd); if (!serv) { printk(KERN_WARNING "lockd_up: create service failed\n"); diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 1b95fe31051f..61c4b9c41904 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -200,7 +200,7 @@ extern const struct svc_procedure nlmsvc_procedures[24]; extern const struct svc_procedure nlmsvc_procedures4[24]; #endif extern int nlmsvc_grace_period; -extern unsigned long nlmsvc_timeout; +extern unsigned long nlm_timeout; extern bool nsm_use_hostnames; extern u32 nsm_local_state; -- cgit v1.2.3 From f2b27e1d72527f94f030b6356b3187576e60885b Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 15 Jul 2024 17:14:15 +1000 Subject: SUNRPC: make various functions static, or not exported. Various functions are only used within the sunrpc module, and several are only use in the one file. So clean up: These are marked static, and any EXPORT is removed. svc_rcpb_setup() svc_rqst_alloc() svc_rqst_free() - also moved before first use svc_rpcbind_set_version() svc_drop() - also moved to svc.c These are now not EXPORTed, but are not static. svc_authenticate() svc_sock_update_bufs() Signed-off-by: NeilBrown Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc.h | 9 -------- include/linux/sunrpc/svcauth.h | 1 - include/linux/sunrpc/svcsock.h | 2 -- net/sunrpc/sunrpc.h | 4 ++++ net/sunrpc/svc.c | 48 ++++++++++++++++++++++-------------------- net/sunrpc/svc_xprt.c | 9 -------- net/sunrpc/svcauth.c | 1 - net/sunrpc/svcsock.c | 1 - 8 files changed, 29 insertions(+), 46 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index a7d0406b9ef5..e4fa25fafa97 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -401,17 +401,13 @@ struct svc_procedure { */ int sunrpc_set_pool_mode(const char *val); int sunrpc_get_pool_mode(char *val, size_t size); -int svc_rpcb_setup(struct svc_serv *serv, struct net *net); void svc_rpcb_cleanup(struct svc_serv *serv, struct net *net); int svc_bind(struct svc_serv *serv, struct net *net); struct svc_serv *svc_create(struct svc_program *, unsigned int, int (*threadfn)(void *data)); -struct svc_rqst *svc_rqst_alloc(struct svc_serv *serv, - struct svc_pool *pool, int node); bool svc_rqst_replace_page(struct svc_rqst *rqstp, struct page *page); void svc_rqst_release_pages(struct svc_rqst *rqstp); -void svc_rqst_free(struct svc_rqst *); void svc_exit_thread(struct svc_rqst *); struct svc_serv * svc_create_pooled(struct svc_program *prog, struct svc_stat *stats, @@ -446,11 +442,6 @@ int svc_generic_rpcbind_set(struct net *net, u32 version, int family, unsigned short proto, unsigned short port); -int svc_rpcbind_set_version(struct net *net, - const struct svc_program *progp, - u32 version, int family, - unsigned short proto, - unsigned short port); #define RPC_MAX_ADDRBUFLEN (63U) diff --git a/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h index 61c455f1e1f5..63cf6fb26dcc 100644 --- a/include/linux/sunrpc/svcauth.h +++ b/include/linux/sunrpc/svcauth.h @@ -151,7 +151,6 @@ struct auth_ops { struct svc_xprt; -extern enum svc_auth_status svc_authenticate(struct svc_rqst *rqstp); extern rpc_authflavor_t svc_auth_flavor(struct svc_rqst *rqstp); extern int svc_authorise(struct svc_rqst *rqstp); extern enum svc_auth_status svc_set_client(struct svc_rqst *rqstp); diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index 7c78ec6356b9..bf45d9e8492a 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -58,8 +58,6 @@ static inline u32 svc_sock_final_rec(struct svc_sock *svsk) */ void svc_recv(struct svc_rqst *rqstp); void svc_send(struct svc_rqst *rqstp); -void svc_drop(struct svc_rqst *); -void svc_sock_update_bufs(struct svc_serv *serv); int svc_addsock(struct svc_serv *serv, struct net *net, const int fd, char *name_return, const size_t len, const struct cred *cred); diff --git a/net/sunrpc/sunrpc.h b/net/sunrpc/sunrpc.h index d4a362c9e4b3..e3c6e3b63f0b 100644 --- a/net/sunrpc/sunrpc.h +++ b/net/sunrpc/sunrpc.h @@ -36,7 +36,11 @@ static inline int sock_is_loopback(struct sock *sk) return loopback; } +struct svc_serv; +struct svc_rqst; int rpc_clients_notifier_register(void); void rpc_clients_notifier_unregister(void); void auth_domain_cleanup(void); +void svc_sock_update_bufs(struct svc_serv *serv); +enum svc_auth_status svc_authenticate(struct svc_rqst *rqstp); #endif /* _NET_SUNRPC_SUNRPC_H */ diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 88a59cfa5583..561d20a5316e 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -32,6 +32,7 @@ #include #include "fail.h" +#include "sunrpc.h" #define RPCDBG_FACILITY RPCDBG_SVCDSP @@ -417,7 +418,7 @@ struct svc_pool *svc_pool_for_cpu(struct svc_serv *serv) return &serv->sv_pools[pidx % serv->sv_nrpools]; } -int svc_rpcb_setup(struct svc_serv *serv, struct net *net) +static int svc_rpcb_setup(struct svc_serv *serv, struct net *net) { int err; @@ -429,7 +430,6 @@ int svc_rpcb_setup(struct svc_serv *serv, struct net *net) svc_unregister(serv, net); return 0; } -EXPORT_SYMBOL_GPL(svc_rpcb_setup); void svc_rpcb_cleanup(struct svc_serv *serv, struct net *net) { @@ -664,7 +664,20 @@ svc_release_buffer(struct svc_rqst *rqstp) put_page(rqstp->rq_pages[i]); } -struct svc_rqst * +static void +svc_rqst_free(struct svc_rqst *rqstp) +{ + folio_batch_release(&rqstp->rq_fbatch); + svc_release_buffer(rqstp); + if (rqstp->rq_scratch_page) + put_page(rqstp->rq_scratch_page); + kfree(rqstp->rq_resp); + kfree(rqstp->rq_argp); + kfree(rqstp->rq_auth_data); + kfree_rcu(rqstp, rq_rcu_head); +} + +static struct svc_rqst * svc_rqst_alloc(struct svc_serv *serv, struct svc_pool *pool, int node) { struct svc_rqst *rqstp; @@ -698,7 +711,6 @@ out_enomem: svc_rqst_free(rqstp); return NULL; } -EXPORT_SYMBOL_GPL(svc_rqst_alloc); static struct svc_rqst * svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node) @@ -933,24 +945,6 @@ void svc_rqst_release_pages(struct svc_rqst *rqstp) } } -/* - * Called from a server thread as it's exiting. Caller must hold the "service - * mutex" for the service. - */ -void -svc_rqst_free(struct svc_rqst *rqstp) -{ - folio_batch_release(&rqstp->rq_fbatch); - svc_release_buffer(rqstp); - if (rqstp->rq_scratch_page) - put_page(rqstp->rq_scratch_page); - kfree(rqstp->rq_resp); - kfree(rqstp->rq_argp); - kfree(rqstp->rq_auth_data); - kfree_rcu(rqstp, rq_rcu_head); -} -EXPORT_SYMBOL_GPL(svc_rqst_free); - void svc_exit_thread(struct svc_rqst *rqstp) { @@ -1098,6 +1092,7 @@ static int __svc_register(struct net *net, const char *progname, return error; } +static int svc_rpcbind_set_version(struct net *net, const struct svc_program *progp, u32 version, int family, @@ -1108,7 +1103,6 @@ int svc_rpcbind_set_version(struct net *net, version, family, proto, port); } -EXPORT_SYMBOL_GPL(svc_rpcbind_set_version); int svc_generic_rpcbind_set(struct net *net, const struct svc_program *progp, @@ -1526,6 +1520,14 @@ err_system_err: goto sendit; } +/* + * Drop request + */ +static void svc_drop(struct svc_rqst *rqstp) +{ + trace_svc_drop(rqstp); +} + /** * svc_process - Execute one RPC transaction * @rqstp: RPC transaction context diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index d3735ab3e6d1..53ebc719ff5a 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -905,15 +905,6 @@ void svc_recv(struct svc_rqst *rqstp) } EXPORT_SYMBOL_GPL(svc_recv); -/* - * Drop request - */ -void svc_drop(struct svc_rqst *rqstp) -{ - trace_svc_drop(rqstp); -} -EXPORT_SYMBOL_GPL(svc_drop); - /** * svc_send - Return reply to client * @rqstp: RPC transaction context diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c index 1619211f0960..93d9e949e265 100644 --- a/net/sunrpc/svcauth.c +++ b/net/sunrpc/svcauth.c @@ -98,7 +98,6 @@ enum svc_auth_status svc_authenticate(struct svc_rqst *rqstp) rqstp->rq_authop = aops; return aops->accept(rqstp); } -EXPORT_SYMBOL_GPL(svc_authenticate); /** * svc_set_client - Assign an appropriate 'auth_domain' as the client diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 6b3f01beb294..825ec5357691 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1378,7 +1378,6 @@ void svc_sock_update_bufs(struct svc_serv *serv) set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags); spin_unlock_bh(&serv->sv_lock); } -EXPORT_SYMBOL_GPL(svc_sock_update_bufs); /* * Initialize socket for RPC use and create svc_sock struct -- cgit v1.2.3 From 5fe690a5946442f7f2d08448341dd621367f80bc Mon Sep 17 00:00:00 2001 From: Matthew Cassell Date: Mon, 22 Jul 2024 17:13:16 +0000 Subject: mm: add node_reclaim successes to VM event counters /proc/vmstat currently shows the number of node_reclaim() failures when vm.zone_reclaim_mode is set appropriately. It would be convenient to have the number of successes right next to zone_reclaim_failed (similar to compaction and migration). While just a trivially addition to the vmstat file. It was helpful during benchmarking to not have to probe node_reclaim() to observe the success/failure ratio. Link: https://lkml.kernel.org/r/20240722171316.7517-1-mcassell411@gmail.com Signed-off-by: Matthew Cassell Cc: Domenico Cerasuolo Cc: "Huang, Ying" Cc: Li Zhijian Cc: Yosry Ahmed Signed-off-by: Andrew Morton --- include/linux/vm_event_item.h | 1 + mm/vmscan.c | 4 +++- mm/vmstat.c | 1 + 3 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 747943bc8cc2..6fff8ed3b1fd 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -50,6 +50,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, PGSTEAL_ANON, PGSTEAL_FILE, #ifdef CONFIG_NUMA + PGSCAN_ZONE_RECLAIM_SUCCESS, PGSCAN_ZONE_RECLAIM_FAILED, #endif PGINODESTEAL, SLABS_SCANNED, KSWAPD_INODESTEAL, diff --git a/mm/vmscan.c b/mm/vmscan.c index cfa839284b92..c9682c8a1d75 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -7539,7 +7539,9 @@ int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) ret = __node_reclaim(pgdat, gfp_mask, order); clear_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags); - if (!ret) + if (ret) + count_vm_event(PGSCAN_ZONE_RECLAIM_SUCCESS); + else count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED); return ret; diff --git a/mm/vmstat.c b/mm/vmstat.c index e875f2a4915f..1ac2a569b6cf 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1314,6 +1314,7 @@ const char * const vmstat_text[] = { "pgsteal_file", #ifdef CONFIG_NUMA + "zone_reclaim_success", "zone_reclaim_failed", #endif "pginodesteal", -- cgit v1.2.3 From 3ddc2fefe6f34ec870fcb22f4cd656e53db079f2 Mon Sep 17 00:00:00 2001 From: Danilo Krummrich Date: Mon, 22 Jul 2024 18:29:23 +0200 Subject: mm: vmalloc: implement vrealloc() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "Align kvrealloc() with krealloc()", v2. Besides the obvious (and desired) difference between krealloc() and kvrealloc(), there is some inconsistency in their function signatures and behavior: - krealloc() frees the memory when the requested size is zero, whereas kvrealloc() simply returns a pointer to the existing allocation. - krealloc() behaves like kmalloc() if a NULL pointer is passed, whereas kvrealloc() does not accept a NULL pointer at all and, if passed, would fault instead. - krealloc() is self-contained, whereas kvrealloc() relies on the caller to provide the size of the previous allocation. Inconsistent behavior throughout allocation APIs is error prone, hence make kvrealloc() behave like krealloc(), which seems superior in all mentioned aspects. In order to be able to get rid of kvrealloc()'s oldsize parameter, introduce vrealloc() and make use of it in kvrealloc(). Making use of vrealloc() in kvrealloc() also provides oppertunities to grow (and shrink) allocations more efficiently. For instance, vrealloc() can be optimized to allocate and map additional pages to grow the allocation or unmap and free unused pages to shrink the allocation. Besides the above, those functions are required by Rust's allocator abstractons [1] (rework based on this series in [2]). With `Vec` or `KVec` respectively, potentially growing (and shrinking) data structures are rather common. [1] https://lore.kernel.org/lkml/20240704170738.3621-1-dakr@redhat.com/ [2] https://git.kernel.org/pub/scm/linux/kernel/git/dakr/linux.git/log/?h=rust/mm This patch (of 2): Implement vrealloc() analogous to krealloc(). Currently, krealloc() requires the caller to pass the size of the previous memory allocation, which, instead, should be self-contained. We attempt to fix this in a subsequent patch which, in order to do so, requires vrealloc(). Besides that, we need realloc() functions for kernel allocators in Rust too. With `Vec` or `KVec` respectively, potentially growing (and shrinking) data structures are rather common. [dakr@kernel.org: fix missing nommu implementation] Link: https://lkml.kernel.org/r/20240725141227.13954-1-dakr@kernel.org [dakr@kernel.org: document concurrency restrictions] Link: https://lkml.kernel.org/r/20240725125442.4957-1-dakr@kernel.org [dakr@kernel.org: consider spare memory for __GFP_ZERO] Link: https://lkml.kernel.org/r/20240730185049.6244-3-dakr@kernel.org [dakr@kernel.org: properly document __GFP_ZERO behavior] Link: https://lkml.kernel.org/r/20240730185049.6244-4-dakr@kernel.org Link: https://lkml.kernel.org/r/20240722163111.4766-1-dakr@kernel.org Link: https://lkml.kernel.org/r/20240722163111.4766-2-dakr@kernel.org Signed-off-by: Danilo Krummrich Acked-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Chandan Babu R Cc: Christian König Cc: Christoph Hellwig Cc: Christoph Lameter Cc: David Rientjes Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com> Cc: Joonsoo Kim Cc: Kees Cook Cc: Marc Zyngier Cc: Michael Ellerman Cc: Miguel Ojeda Cc: Oliver Upton Cc: Pekka Enberg Cc: Roman Gushchin Cc: Uladzislau Rezki Cc: Wedson Almeida Filho Signed-off-by: Andrew Morton --- include/linux/vmalloc.h | 4 +++ mm/nommu.c | 5 ++++ mm/vmalloc.c | 70 +++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 79 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index e4a631ec430b..ad2ce7a6ab7a 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -189,6 +189,10 @@ extern void *__vcalloc_noprof(size_t n, size_t size, gfp_t flags) __alloc_size(1 extern void *vcalloc_noprof(size_t n, size_t size) __alloc_size(1, 2); #define vcalloc(...) alloc_hooks(vcalloc_noprof(__VA_ARGS__)) +void * __must_check vrealloc_noprof(const void *p, size_t size, gfp_t flags) + __realloc_size(2); +#define vrealloc(...) alloc_hooks(vrealloc_noprof(__VA_ARGS__)) + extern void vfree(const void *addr); extern void vfree_atomic(const void *addr); diff --git a/mm/nommu.c b/mm/nommu.c index 7296e775e04e..40cac1348b40 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -126,6 +126,11 @@ void *__vmalloc_noprof(unsigned long size, gfp_t gfp_mask) } EXPORT_SYMBOL(__vmalloc_noprof); +void *vrealloc_noprof(const void *p, size_t size, gfp_t flags) +{ + return krealloc_noprof(p, size, (flags | __GFP_COMP) & ~__GFP_HIGHMEM); +} + void *__vmalloc_node_range_noprof(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, diff --git a/mm/vmalloc.c b/mm/vmalloc.c index af2de36549d6..884e21fed28f 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -4030,6 +4030,76 @@ void *vzalloc_node_noprof(unsigned long size, int node) } EXPORT_SYMBOL(vzalloc_node_noprof); +/** + * vrealloc - reallocate virtually contiguous memory; contents remain unchanged + * @p: object to reallocate memory for + * @size: the size to reallocate + * @flags: the flags for the page level allocator + * + * If @p is %NULL, vrealloc() behaves exactly like vmalloc(). If @size is 0 and + * @p is not a %NULL pointer, the object pointed to is freed. + * + * If __GFP_ZERO logic is requested, callers must ensure that, starting with the + * initial memory allocation, every subsequent call to this API for the same + * memory allocation is flagged with __GFP_ZERO. Otherwise, it is possible that + * __GFP_ZERO is not fully honored by this API. + * + * In any case, the contents of the object pointed to are preserved up to the + * lesser of the new and old sizes. + * + * This function must not be called concurrently with itself or vfree() for the + * same memory allocation. + * + * Return: pointer to the allocated memory; %NULL if @size is zero or in case of + * failure + */ +void *vrealloc_noprof(const void *p, size_t size, gfp_t flags) +{ + size_t old_size = 0; + void *n; + + if (!size) { + vfree(p); + return NULL; + } + + if (p) { + struct vm_struct *vm; + + vm = find_vm_area(p); + if (unlikely(!vm)) { + WARN(1, "Trying to vrealloc() nonexistent vm area (%p)\n", p); + return NULL; + } + + old_size = get_vm_area_size(vm); + } + + /* + * TODO: Shrink the vm_area, i.e. unmap and free unused pages. What + * would be a good heuristic for when to shrink the vm_area? + */ + if (size <= old_size) { + /* Zero out spare memory. */ + if (want_init_on_alloc(flags)) + memset((void *)p + size, 0, old_size - size); + + return (void *)p; + } + + /* TODO: Grow the vm_area, i.e. allocate and map additional pages. */ + n = __vmalloc_noprof(size, flags); + if (!n) + return NULL; + + if (p) { + memcpy(n, p, old_size); + vfree(p); + } + + return n; +} + #if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32) #define GFP_VMALLOC32 (GFP_DMA32 | GFP_KERNEL) #elif defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA) -- cgit v1.2.3 From 590b9d576caec6b4c46bba49ed36223a399c3fc5 Mon Sep 17 00:00:00 2001 From: Danilo Krummrich Date: Mon, 22 Jul 2024 18:29:24 +0200 Subject: mm: kvmalloc: align kvrealloc() with krealloc() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Besides the obvious (and desired) difference between krealloc() and kvrealloc(), there is some inconsistency in their function signatures and behavior: - krealloc() frees the memory when the requested size is zero, whereas kvrealloc() simply returns a pointer to the existing allocation. - krealloc() behaves like kmalloc() if a NULL pointer is passed, whereas kvrealloc() does not accept a NULL pointer at all and, if passed, would fault instead. - krealloc() is self-contained, whereas kvrealloc() relies on the caller to provide the size of the previous allocation. Inconsistent behavior throughout allocation APIs is error prone, hence make kvrealloc() behave like krealloc(), which seems superior in all mentioned aspects. Besides that, implementing kvrealloc() by making use of krealloc() and vrealloc() provides oppertunities to grow (and shrink) allocations more efficiently. For instance, vrealloc() can be optimized to allocate and map additional pages to grow the allocation or unmap and free unused pages to shrink the allocation. [dakr@kernel.org: document concurrency restrictions] Link: https://lkml.kernel.org/r/20240725125442.4957-1-dakr@kernel.org [dakr@kernel.org: disable KASAN when switching to vmalloc] Link: https://lkml.kernel.org/r/20240730185049.6244-2-dakr@kernel.org [dakr@kernel.org: properly document __GFP_ZERO behavior] Link: https://lkml.kernel.org/r/20240730185049.6244-5-dakr@kernel.org Link: https://lkml.kernel.org/r/20240722163111.4766-3-dakr@kernel.org Signed-off-by: Danilo Krummrich Acked-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Chandan Babu R Cc: Christian König Cc: Christoph Hellwig Cc: Christoph Lameter Cc: David Rientjes Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com> Cc: Joonsoo Kim Cc: Kees Cook Cc: Marc Zyngier Cc: Michael Ellerman Cc: Miguel Ojeda Cc: Oliver Upton Cc: Pekka Enberg Cc: Roman Gushchin Cc: Uladzislau Rezki Cc: Wedson Almeida Filho Signed-off-by: Andrew Morton --- arch/arm64/kvm/nested.c | 1 - arch/powerpc/platforms/pseries/papr-vpd.c | 5 +- drivers/gpu/drm/drm_exec.c | 3 +- fs/xfs/xfs_log_recover.c | 2 +- include/linux/slab.h | 4 +- kernel/resource.c | 3 +- lib/fortify_kunit.c | 3 +- mm/util.c | 100 +++++++++++++++++++++--------- 8 files changed, 77 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c index bab27f9d8cc6..8632c05e7997 100644 --- a/arch/arm64/kvm/nested.c +++ b/arch/arm64/kvm/nested.c @@ -62,7 +62,6 @@ int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu) */ num_mmus = atomic_read(&kvm->online_vcpus) * S2_MMU_PER_VCPU; tmp = kvrealloc(kvm->arch.nested_mmus, - size_mul(sizeof(*kvm->arch.nested_mmus), kvm->arch.nested_mmus_size), size_mul(sizeof(*kvm->arch.nested_mmus), num_mmus), GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!tmp) diff --git a/arch/powerpc/platforms/pseries/papr-vpd.c b/arch/powerpc/platforms/pseries/papr-vpd.c index c29e85db5f35..1574176e3ffc 100644 --- a/arch/powerpc/platforms/pseries/papr-vpd.c +++ b/arch/powerpc/platforms/pseries/papr-vpd.c @@ -156,10 +156,7 @@ static int vpd_blob_extend(struct vpd_blob *blob, const char *data, size_t len) const char *old_ptr = blob->data; char *new_ptr; - new_ptr = old_ptr ? - kvrealloc(old_ptr, old_len, new_len, GFP_KERNEL_ACCOUNT) : - kvmalloc(len, GFP_KERNEL_ACCOUNT); - + new_ptr = kvrealloc(old_ptr, new_len, GFP_KERNEL_ACCOUNT); if (!new_ptr) return -ENOMEM; diff --git a/drivers/gpu/drm/drm_exec.c b/drivers/gpu/drm/drm_exec.c index 2da094bdf8a4..18e366cc4993 100644 --- a/drivers/gpu/drm/drm_exec.c +++ b/drivers/gpu/drm/drm_exec.c @@ -145,8 +145,7 @@ static int drm_exec_obj_locked(struct drm_exec *exec, size_t size = exec->max_objects * sizeof(void *); void *tmp; - tmp = kvrealloc(exec->objects, size, size + PAGE_SIZE, - GFP_KERNEL); + tmp = kvrealloc(exec->objects, size + PAGE_SIZE, GFP_KERNEL); if (!tmp) return -ENOMEM; diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 4423dd344239..1997981827fb 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -2128,7 +2128,7 @@ xlog_recover_add_to_cont_trans( old_ptr = item->ri_buf[item->ri_cnt-1].i_addr; old_len = item->ri_buf[item->ri_cnt-1].i_len; - ptr = kvrealloc(old_ptr, old_len, len + old_len, GFP_KERNEL); + ptr = kvrealloc(old_ptr, len + old_len, GFP_KERNEL); if (!ptr) return -ENOMEM; memcpy(&ptr[old_len], dp, len); diff --git a/include/linux/slab.h b/include/linux/slab.h index eb2bf4629157..c9cb42203183 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -841,8 +841,8 @@ kvmalloc_array_node_noprof(size_t n, size_t size, gfp_t flags, int node) #define kvcalloc_node(...) alloc_hooks(kvcalloc_node_noprof(__VA_ARGS__)) #define kvcalloc(...) alloc_hooks(kvcalloc_noprof(__VA_ARGS__)) -extern void *kvrealloc_noprof(const void *p, size_t oldsize, size_t newsize, gfp_t flags) - __realloc_size(3); +void *kvrealloc_noprof(const void *p, size_t size, gfp_t flags) + __realloc_size(2); #define kvrealloc(...) alloc_hooks(kvrealloc_noprof(__VA_ARGS__)) extern void kvfree(const void *addr); diff --git a/kernel/resource.c b/kernel/resource.c index 14777afb0a99..9f747bb7cd03 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -450,8 +450,7 @@ int walk_system_ram_res_rev(u64 start, u64 end, void *arg, /* re-alloc */ struct resource *rams_new; - rams_new = kvrealloc(rams, rams_size * sizeof(struct resource), - (rams_size + 16) * sizeof(struct resource), + rams_new = kvrealloc(rams, (rams_size + 16) * sizeof(struct resource), GFP_KERNEL); if (!rams_new) goto out; diff --git a/lib/fortify_kunit.c b/lib/fortify_kunit.c index f9ad60a9c7bd..ecb638d4cde1 100644 --- a/lib/fortify_kunit.c +++ b/lib/fortify_kunit.c @@ -306,8 +306,7 @@ DEFINE_ALLOC_SIZE_TEST_PAIR(vmalloc) orig = kvmalloc(prev_size, gfp); \ KUNIT_EXPECT_TRUE(test, orig != NULL); \ checker(((expected_pages) * PAGE_SIZE) * 2, \ - kvrealloc(orig, prev_size, \ - ((alloc_pages) * PAGE_SIZE) * 2, gfp), \ + kvrealloc(orig, ((alloc_pages) * PAGE_SIZE) * 2, gfp), \ kvfree(p)); \ } while (0) DEFINE_ALLOC_SIZE_TEST_PAIR(kvmalloc) diff --git a/mm/util.c b/mm/util.c index bd283e2132e0..ac01925a4179 100644 --- a/mm/util.c +++ b/mm/util.c @@ -608,6 +608,28 @@ unsigned long vm_mmap(struct file *file, unsigned long addr, } EXPORT_SYMBOL(vm_mmap); +static gfp_t kmalloc_gfp_adjust(gfp_t flags, size_t size) +{ + /* + * We want to attempt a large physically contiguous block first because + * it is less likely to fragment multiple larger blocks and therefore + * contribute to a long term fragmentation less than vmalloc fallback. + * However make sure that larger requests are not too disruptive - no + * OOM killer and no allocation failure warnings as we have a fallback. + */ + if (size > PAGE_SIZE) { + flags |= __GFP_NOWARN; + + if (!(flags & __GFP_RETRY_MAYFAIL)) + flags |= __GFP_NORETRY; + + /* nofail semantic is implemented by the vmalloc fallback */ + flags &= ~__GFP_NOFAIL; + } + + return flags; +} + /** * __kvmalloc_node - attempt to allocate physically contiguous memory, but upon * failure, fall back to non-contiguous (vmalloc) allocation. @@ -627,32 +649,15 @@ EXPORT_SYMBOL(vm_mmap); */ void *__kvmalloc_node_noprof(DECL_BUCKET_PARAMS(size, b), gfp_t flags, int node) { - gfp_t kmalloc_flags = flags; void *ret; - /* - * We want to attempt a large physically contiguous block first because - * it is less likely to fragment multiple larger blocks and therefore - * contribute to a long term fragmentation less than vmalloc fallback. - * However make sure that larger requests are not too disruptive - no - * OOM killer and no allocation failure warnings as we have a fallback. - */ - if (size > PAGE_SIZE) { - kmalloc_flags |= __GFP_NOWARN; - - if (!(kmalloc_flags & __GFP_RETRY_MAYFAIL)) - kmalloc_flags |= __GFP_NORETRY; - - /* nofail semantic is implemented by the vmalloc fallback */ - kmalloc_flags &= ~__GFP_NOFAIL; - } - - ret = __kmalloc_node_noprof(PASS_BUCKET_PARAMS(size, b), kmalloc_flags, node); - /* * It doesn't really make sense to fallback to vmalloc for sub page * requests */ + ret = __kmalloc_node_noprof(PASS_BUCKET_PARAMS(size, b), + kmalloc_gfp_adjust(flags, size), + node); if (ret || size <= PAGE_SIZE) return ret; @@ -715,18 +720,53 @@ void kvfree_sensitive(const void *addr, size_t len) } EXPORT_SYMBOL(kvfree_sensitive); -void *kvrealloc_noprof(const void *p, size_t oldsize, size_t newsize, gfp_t flags) +/** + * kvrealloc - reallocate memory; contents remain unchanged + * @p: object to reallocate memory for + * @size: the size to reallocate + * @flags: the flags for the page level allocator + * + * If @p is %NULL, kvrealloc() behaves exactly like kvmalloc(). If @size is 0 + * and @p is not a %NULL pointer, the object pointed to is freed. + * + * If __GFP_ZERO logic is requested, callers must ensure that, starting with the + * initial memory allocation, every subsequent call to this API for the same + * memory allocation is flagged with __GFP_ZERO. Otherwise, it is possible that + * __GFP_ZERO is not fully honored by this API. + * + * In any case, the contents of the object pointed to are preserved up to the + * lesser of the new and old sizes. + * + * This function must not be called concurrently with itself or kvfree() for the + * same memory allocation. + * + * Return: pointer to the allocated memory or %NULL in case of error + */ +void *kvrealloc_noprof(const void *p, size_t size, gfp_t flags) { - void *newp; + void *n; - if (oldsize >= newsize) - return (void *)p; - newp = kvmalloc_noprof(newsize, flags); - if (!newp) - return NULL; - memcpy(newp, p, oldsize); - kvfree(p); - return newp; + if (is_vmalloc_addr(p)) + return vrealloc_noprof(p, size, flags); + + n = krealloc_noprof(p, size, kmalloc_gfp_adjust(flags, size)); + if (!n) { + /* We failed to krealloc(), fall back to kvmalloc(). */ + n = kvmalloc_noprof(size, flags); + if (!n) + return NULL; + + if (p) { + /* We already know that `p` is not a vmalloc address. */ + kasan_disable_current(); + memcpy(n, kasan_reset_tag(p), ksize(p)); + kasan_enable_current(); + + kfree(p); + } + } + + return n; } EXPORT_SYMBOL(kvrealloc_noprof); -- cgit v1.2.3 From d58a2a581f132529eefac5377676011562b631b8 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Mon, 22 Jul 2024 13:43:18 +0800 Subject: mm: shmem: rename shmem_is_huge() to shmem_huge_global_enabled() shmem_is_huge() is now used to check if the top-level huge page is enabled, thus rename it to reflect its usage. Link: https://lkml.kernel.org/r/da53296e0ab6359aa083561d9dc01e4223d60fbe.1721626645.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Reviewed-by: Ryan Roberts Acked-by: David Hildenbrand Cc: Barry Song <21cnbao@gmail.com> Cc: Hugh Dickins Cc: Lance Yang Cc: Matthew Wilcox (Oracle) Cc: Zi Yan Signed-off-by: Andrew Morton --- include/linux/shmem_fs.h | 9 +++++---- mm/huge_memory.c | 5 +++-- mm/shmem.c | 15 ++++++++------- 3 files changed, 16 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 1d06b1e5408a..405ee8d3589a 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -111,14 +111,15 @@ extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); int shmem_unuse(unsigned int type); #ifdef CONFIG_TRANSPARENT_HUGEPAGE -extern bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, - struct mm_struct *mm, unsigned long vm_flags); +extern bool shmem_huge_global_enabled(struct inode *inode, pgoff_t index, bool shmem_huge_force, + struct mm_struct *mm, unsigned long vm_flags); unsigned long shmem_allowable_huge_orders(struct inode *inode, struct vm_area_struct *vma, pgoff_t index, bool global_huge); #else -static __always_inline bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, - struct mm_struct *mm, unsigned long vm_flags) +static __always_inline bool shmem_huge_global_enabled(struct inode *inode, pgoff_t index, + bool shmem_huge_force, struct mm_struct *mm, + unsigned long vm_flags) { return false; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 67c86a5d64a6..3af9366b1c4c 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -160,8 +160,9 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, * own flags. */ if (!in_pf && shmem_file(vma->vm_file)) { - bool global_huge = shmem_is_huge(file_inode(vma->vm_file), vma->vm_pgoff, - !enforce_sysfs, vma->vm_mm, vm_flags); + bool global_huge = shmem_huge_global_enabled(file_inode(vma->vm_file), + vma->vm_pgoff, !enforce_sysfs, + vma->vm_mm, vm_flags); if (!vma_is_anon_shmem(vma)) return global_huge ? orders : 0; diff --git a/mm/shmem.c b/mm/shmem.c index 7889b499d33f..2a86b0d9f516 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -548,9 +548,9 @@ static bool shmem_confirm_swap(struct address_space *mapping, static int shmem_huge __read_mostly = SHMEM_HUGE_NEVER; -static bool __shmem_is_huge(struct inode *inode, pgoff_t index, - bool shmem_huge_force, struct mm_struct *mm, - unsigned long vm_flags) +static bool __shmem_huge_global_enabled(struct inode *inode, pgoff_t index, + bool shmem_huge_force, struct mm_struct *mm, + unsigned long vm_flags) { loff_t i_size; @@ -581,14 +581,15 @@ static bool __shmem_is_huge(struct inode *inode, pgoff_t index, } } -bool shmem_is_huge(struct inode *inode, pgoff_t index, +bool shmem_huge_global_enabled(struct inode *inode, pgoff_t index, bool shmem_huge_force, struct mm_struct *mm, unsigned long vm_flags) { if (HPAGE_PMD_ORDER > MAX_PAGECACHE_ORDER) return false; - return __shmem_is_huge(inode, index, shmem_huge_force, mm, vm_flags); + return __shmem_huge_global_enabled(inode, index, shmem_huge_force, + mm, vm_flags); } #if defined(CONFIG_SYSFS) @@ -1156,7 +1157,7 @@ static int shmem_getattr(struct mnt_idmap *idmap, STATX_ATTR_NODUMP); generic_fillattr(idmap, request_mask, inode, stat); - if (shmem_is_huge(inode, 0, false, NULL, 0)) + if (shmem_huge_global_enabled(inode, 0, false, NULL, 0)) stat->blksize = HPAGE_PMD_SIZE; if (request_mask & STATX_BTIME) { @@ -2149,7 +2150,7 @@ repeat: return 0; } - huge = shmem_is_huge(inode, index, false, fault_mm, + huge = shmem_huge_global_enabled(inode, index, false, fault_mm, vma ? vma->vm_flags : 0); /* Find hugepage orders that are allowed for anonymous shmem. */ if (vma && vma_is_anon_shmem(vma)) -- cgit v1.2.3 From 6beeab870e70b2d4f49baf6c6be9da1b61c169f8 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Mon, 22 Jul 2024 13:43:19 +0800 Subject: mm: shmem: move shmem_huge_global_enabled() into shmem_allowable_huge_orders() Move shmem_huge_global_enabled() into shmem_allowable_huge_orders(), so that shmem_allowable_huge_orders() can also help to find the allowable huge orders for tmpfs. Moreover the shmem_huge_global_enabled() can become static. While we are at it, passing the vma instead of mm for shmem_huge_global_enabled() makes code cleaner. No functional changes. Link: https://lkml.kernel.org/r/8e825146bb29ee1a1c7bd64d2968ff3e19be7815.1721626645.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Reviewed-by: Ryan Roberts Acked-by: David Hildenbrand Cc: Barry Song <21cnbao@gmail.com> Cc: Hugh Dickins Cc: Lance Yang Cc: Matthew Wilcox (Oracle) Cc: Zi Yan Signed-off-by: Andrew Morton --- include/linux/shmem_fs.h | 12 ++---------- mm/huge_memory.c | 12 +++--------- mm/shmem.c | 47 ++++++++++++++++++++++++++++++----------------- 3 files changed, 35 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 405ee8d3589a..1564d7d3ca61 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -111,21 +111,13 @@ extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); int shmem_unuse(unsigned int type); #ifdef CONFIG_TRANSPARENT_HUGEPAGE -extern bool shmem_huge_global_enabled(struct inode *inode, pgoff_t index, bool shmem_huge_force, - struct mm_struct *mm, unsigned long vm_flags); unsigned long shmem_allowable_huge_orders(struct inode *inode, struct vm_area_struct *vma, pgoff_t index, - bool global_huge); + bool shmem_huge_force); #else -static __always_inline bool shmem_huge_global_enabled(struct inode *inode, pgoff_t index, - bool shmem_huge_force, struct mm_struct *mm, - unsigned long vm_flags) -{ - return false; -} static inline unsigned long shmem_allowable_huge_orders(struct inode *inode, struct vm_area_struct *vma, pgoff_t index, - bool global_huge) + bool shmem_huge_force) { return 0; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 3af9366b1c4c..1ec32c02b19c 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -159,16 +159,10 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, * Must be done before hugepage flags check since shmem has its * own flags. */ - if (!in_pf && shmem_file(vma->vm_file)) { - bool global_huge = shmem_huge_global_enabled(file_inode(vma->vm_file), - vma->vm_pgoff, !enforce_sysfs, - vma->vm_mm, vm_flags); - - if (!vma_is_anon_shmem(vma)) - return global_huge ? orders : 0; + if (!in_pf && shmem_file(vma->vm_file)) return shmem_allowable_huge_orders(file_inode(vma->vm_file), - vma, vma->vm_pgoff, global_huge); - } + vma, vma->vm_pgoff, + !enforce_sysfs); if (!vma_is_anonymous(vma)) { /* diff --git a/mm/shmem.c b/mm/shmem.c index 2a86b0d9f516..4a5254bfd610 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -549,9 +549,10 @@ static bool shmem_confirm_swap(struct address_space *mapping, static int shmem_huge __read_mostly = SHMEM_HUGE_NEVER; static bool __shmem_huge_global_enabled(struct inode *inode, pgoff_t index, - bool shmem_huge_force, struct mm_struct *mm, + bool shmem_huge_force, struct vm_area_struct *vma, unsigned long vm_flags) { + struct mm_struct *mm = vma ? vma->vm_mm : NULL; loff_t i_size; if (!S_ISREG(inode->i_mode)) @@ -581,15 +582,15 @@ static bool __shmem_huge_global_enabled(struct inode *inode, pgoff_t index, } } -bool shmem_huge_global_enabled(struct inode *inode, pgoff_t index, - bool shmem_huge_force, struct mm_struct *mm, +static bool shmem_huge_global_enabled(struct inode *inode, pgoff_t index, + bool shmem_huge_force, struct vm_area_struct *vma, unsigned long vm_flags) { if (HPAGE_PMD_ORDER > MAX_PAGECACHE_ORDER) return false; return __shmem_huge_global_enabled(inode, index, shmem_huge_force, - mm, vm_flags); + vma, vm_flags); } #if defined(CONFIG_SYSFS) @@ -772,6 +773,13 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, { return 0; } + +static bool shmem_huge_global_enabled(struct inode *inode, pgoff_t index, + bool shmem_huge_force, struct vm_area_struct *vma, + unsigned long vm_flags) +{ + return false; +} #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ /* @@ -1625,22 +1633,33 @@ static gfp_t limit_gfp_mask(gfp_t huge_gfp, gfp_t limit_gfp) #ifdef CONFIG_TRANSPARENT_HUGEPAGE unsigned long shmem_allowable_huge_orders(struct inode *inode, struct vm_area_struct *vma, pgoff_t index, - bool global_huge) + bool shmem_huge_force) { unsigned long mask = READ_ONCE(huge_shmem_orders_always); unsigned long within_size_orders = READ_ONCE(huge_shmem_orders_within_size); - unsigned long vm_flags = vma->vm_flags; + unsigned long vm_flags = vma ? vma->vm_flags : 0; + bool global_huge; loff_t i_size; int order; - if ((vm_flags & VM_NOHUGEPAGE) || - test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) + if (vma && ((vm_flags & VM_NOHUGEPAGE) || + test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))) return 0; /* If the hardware/firmware marked hugepage support disabled. */ if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED)) return 0; + global_huge = shmem_huge_global_enabled(inode, index, shmem_huge_force, + vma, vm_flags); + if (!vma || !vma_is_anon_shmem(vma)) { + /* + * For tmpfs, we now only support PMD sized THP if huge page + * is enabled, otherwise fallback to order 0. + */ + return global_huge ? BIT(HPAGE_PMD_ORDER) : 0; + } + /* * Following the 'deny' semantics of the top level, force the huge * option off from all mounts. @@ -2077,7 +2096,7 @@ static int shmem_get_folio_gfp(struct inode *inode, pgoff_t index, struct mm_struct *fault_mm; struct folio *folio; int error; - bool alloced, huge; + bool alloced; unsigned long orders = 0; if (WARN_ON_ONCE(!shmem_mapping(inode->i_mapping))) @@ -2150,14 +2169,8 @@ repeat: return 0; } - huge = shmem_huge_global_enabled(inode, index, false, fault_mm, - vma ? vma->vm_flags : 0); - /* Find hugepage orders that are allowed for anonymous shmem. */ - if (vma && vma_is_anon_shmem(vma)) - orders = shmem_allowable_huge_orders(inode, vma, index, huge); - else if (huge) - orders = BIT(HPAGE_PMD_ORDER); - + /* Find hugepage orders that are allowed for anonymous shmem and tmpfs. */ + orders = shmem_allowable_huge_orders(inode, vma, index, false); if (orders > 0) { gfp_t huge_gfp; -- cgit v1.2.3 From 4fd568faf6e7e21f206cd66dd4fca9a72e7d922c Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Thu, 18 Jul 2024 17:18:21 +0800 Subject: mm: kmem: remove mem_cgroup_from_obj() There is no user of mem_cgroup_from_obj(), remove it. Link: https://lkml.kernel.org/r/20240718091821.44740-1-songmuchun@bytedance.com Signed-off-by: Muchun Song Acked-by: Shakeel Butt Acked-by: Roman Gushchin Cc: Johannes Weiner Cc: Michal Hocko Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 6 ------ mm/memcontrol.c | 32 +------------------------------- 2 files changed, 1 insertion(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 0e5bf25d324f..af7da7bd00af 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1717,7 +1717,6 @@ static inline int memcg_kmem_id(struct mem_cgroup *memcg) return memcg ? memcg->kmemcg_id : -1; } -struct mem_cgroup *mem_cgroup_from_obj(void *p); struct mem_cgroup *mem_cgroup_from_slab_obj(void *p); static inline void count_objcg_event(struct obj_cgroup *objcg, @@ -1780,11 +1779,6 @@ static inline int memcg_kmem_id(struct mem_cgroup *memcg) return -1; } -static inline struct mem_cgroup *mem_cgroup_from_obj(void *p) -{ - return NULL; -} - static inline struct mem_cgroup *mem_cgroup_from_slab_obj(void *p) { return NULL; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index f29157288b7d..f0297e7c3d12 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2446,37 +2446,7 @@ struct mem_cgroup *mem_cgroup_from_obj_folio(struct folio *folio, void *p) /* * Returns a pointer to the memory cgroup to which the kernel object is charged. - * - * A passed kernel object can be a slab object, vmalloc object or a generic - * kernel page, so different mechanisms for getting the memory cgroup pointer - * should be used. - * - * In certain cases (e.g. kernel stacks or large kmallocs with SLUB) the caller - * can not know for sure how the kernel object is implemented. - * mem_cgroup_from_obj() can be safely used in such cases. - * - * The caller must ensure the memcg lifetime, e.g. by taking rcu_read_lock(), - * cgroup_mutex, etc. - */ -struct mem_cgroup *mem_cgroup_from_obj(void *p) -{ - struct folio *folio; - - if (mem_cgroup_disabled()) - return NULL; - - if (unlikely(is_vmalloc_addr(p))) - folio = page_folio(vmalloc_to_page(p)); - else - folio = virt_to_folio(p); - - return mem_cgroup_from_obj_folio(folio, p); -} - -/* - * Returns a pointer to the memory cgroup to which the kernel object is charged. - * Similar to mem_cgroup_from_obj(), but faster and not suitable for objects, - * allocated using vmalloc(). + * It is not suitable for objects allocated using vmalloc(). * * A passed kernel object must be a slab object or a generic kernel page. * -- cgit v1.2.3 From 2a28713a67fd28eedc13b32300df6b9c5a2381f5 Mon Sep 17 00:00:00 2001 From: Zi Yan Date: Wed, 24 Jul 2024 09:01:14 -0400 Subject: memory tiering: introduce folio_use_access_time() check If memory tiering mode is on and a folio is not in the top tier memory, folio's cpupid field is repurposed to store page access time. Instead of an open coded check, use a function to encapsulate the check. Link: https://lkml.kernel.org/r/20240724130115.793641-3-ziy@nvidia.com Signed-off-by: Zi Yan Reviewed-by: "Huang, Ying" Acked-by: David Hildenbrand Reviewed-by: Kefeng Wang Cc: Baolin Wang Cc: Lorenzo Stoakes Signed-off-by: Andrew Morton --- include/linux/mm.h | 6 ++++++ kernel/sched/fair.c | 3 +-- mm/huge_memory.c | 6 ++---- mm/memory-tiers.c | 19 +++++++++++++++++++ mm/memory.c | 3 +-- mm/mprotect.c | 3 +-- 6 files changed, 30 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 6549d0979b28..6c2078ca3391 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1745,6 +1745,8 @@ static inline void vma_set_access_pid_bit(struct vm_area_struct *vma) __set_bit(pid_bit, &vma->numab_state->pids_active[1]); } } + +bool folio_use_access_time(struct folio *folio); #else /* !CONFIG_NUMA_BALANCING */ static inline int folio_xchg_last_cpupid(struct folio *folio, int cpupid) { @@ -1798,6 +1800,10 @@ static inline bool cpupid_match_pid(struct task_struct *task, int cpupid) static inline void vma_set_access_pid_bit(struct vm_area_struct *vma) { } +static inline bool folio_use_access_time(struct folio *folio) +{ + return false; +} #endif /* CONFIG_NUMA_BALANCING */ #if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 9057584ec06d..416e29b56cc4 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1840,8 +1840,7 @@ bool should_numa_migrate_memory(struct task_struct *p, struct folio *folio, * The pages in slow memory node should be migrated according * to hot/cold instead of private/shared. */ - if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING && - !node_is_toptier(src_nid)) { + if (folio_use_access_time(folio)) { struct pglist_data *pgdat; unsigned long rate_limit; unsigned int latency, th, def_th; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 632a92edec4e..29e76d285e4b 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1707,8 +1707,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) * For memory tiering mode, cpupid of slow memory page is used * to record page access time. So use default value. */ - if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) || - node_is_toptier(nid)) + if (!folio_use_access_time(folio)) last_cpupid = folio_last_cpupid(folio); target_nid = numa_migrate_prep(folio, vmf, haddr, nid, &flags); if (target_nid == NUMA_NO_NODE) @@ -2058,8 +2057,7 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, toptier) goto unlock; - if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING && - !toptier) + if (folio_use_access_time(folio)) folio_xchg_access_time(folio, jiffies_to_msecs(jiffies)); } diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c index 4775b3a3dabe..2a642ea86cb2 100644 --- a/mm/memory-tiers.c +++ b/mm/memory-tiers.c @@ -6,6 +6,7 @@ #include #include #include +#include #include "internal.h" @@ -50,6 +51,24 @@ static const struct bus_type memory_tier_subsys = { .dev_name = "memory_tier", }; +#ifdef CONFIG_NUMA_BALANCING +/** + * folio_use_access_time - check if a folio reuses cpupid for page access time + * @folio: folio to check + * + * folio's _last_cpupid field is repurposed by memory tiering. In memory + * tiering mode, cpupid of slow memory folio (not toptier memory) is used to + * record page access time. + * + * Return: the folio _last_cpupid is used to record page access time + */ +bool folio_use_access_time(struct folio *folio) +{ + return (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) && + !node_is_toptier(folio_nid(folio)); +} +#endif + #ifdef CONFIG_MIGRATION static int top_tier_adistance; /* diff --git a/mm/memory.c b/mm/memory.c index 3c01d68065be..a3d955098a19 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -5337,8 +5337,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) * For memory tiering mode, cpupid of slow memory page is used * to record page access time. So use default value. */ - if ((sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) && - !node_is_toptier(nid)) + if (folio_use_access_time(folio)) last_cpupid = (-1 & LAST_CPUPID_MASK); else last_cpupid = folio_last_cpupid(folio); diff --git a/mm/mprotect.c b/mm/mprotect.c index 222ab434da54..37cf8d249405 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -161,8 +161,7 @@ static long change_pte_range(struct mmu_gather *tlb, if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_NORMAL) && toptier) continue; - if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING && - !toptier) + if (folio_use_access_time(folio)) folio_xchg_access_time(folio, jiffies_to_msecs(jiffies)); } -- cgit v1.2.3 From c4a6fce85640beb4f79e8217272d1ef79839cc17 Mon Sep 17 00:00:00 2001 From: Pasha Tatashin Date: Wed, 24 Jul 2024 20:33:21 +0000 Subject: vmstat: kernel stack usage histogram As part of the dynamic kernel stack project, we need to know the amount of data that can be saved by reducing the default kernel stack size [1]. Provide a kernel stack usage histogram to aid in optimizing kernel stack sizes and minimizing memory waste in large-scale environments. The histogram divides stack usage into power-of-two buckets and reports the results in /proc/vmstat. This information is especially valuable in environments with millions of machines, where even small optimizations can have a significant impact. The histogram data is presented in /proc/vmstat with entries like "kstack_1k", "kstack_2k", and so on, indicating the number of threads that exited with stack usage falling within each respective bucket. Example outputs: Intel: $ grep kstack /proc/vmstat kstack_1k 3 kstack_2k 188 kstack_4k 11391 kstack_8k 243 kstack_16k 0 ARM with 64K page_size: $ grep kstack /proc/vmstat kstack_1k 1 kstack_2k 340 kstack_4k 25212 kstack_8k 1659 kstack_16k 0 kstack_32k 0 kstack_64k 0 Note: once the dynamic kernel stack is implemented it will depend on the implementation the usability of this feature: On hardware that supports faults on kernel stacks, we will have other metrics that show the total number of pages allocated for stacks. On hardware where faults are not supported, we will most likely have some optimization where only some threads are extended, and for those, these metrics will still be very useful. [1] https://lwn.net/Articles/974367 Link: https://lkml.kernel.org/r/20240730150158.832783-3-pasha.tatashin@soleen.com Link: https://lkml.kernel.org/r/20240724203322.2765486-3-pasha.tatashin@soleen.com Signed-off-by: Pasha Tatashin Reviewed-by: Kent Overstreet Acked-by: Shakeel Butt Cc: Domenico Cerasuolo Cc: Li Zhijian Cc: Matthew Wilcox Cc: Nhat Pham Cc: Peter Zijlstra Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Zi Yan Signed-off-by: Andrew Morton --- include/linux/vm_event_item.h | 24 ++++++++++++++++++++++++ kernel/exit.c | 38 ++++++++++++++++++++++++++++++++++++++ mm/vmstat.c | 24 ++++++++++++++++++++++++ 3 files changed, 86 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 6fff8ed3b1fd..aae5c7c5cfb4 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -155,6 +155,30 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, VMA_LOCK_RETRY, VMA_LOCK_MISS, #endif +#ifdef CONFIG_DEBUG_STACK_USAGE + KSTACK_1K, +#if THREAD_SIZE > 1024 + KSTACK_2K, +#endif +#if THREAD_SIZE > 2048 + KSTACK_4K, +#endif +#if THREAD_SIZE > 4096 + KSTACK_8K, +#endif +#if THREAD_SIZE > 8192 + KSTACK_16K, +#endif +#if THREAD_SIZE > 16384 + KSTACK_32K, +#endif +#if THREAD_SIZE > 32768 + KSTACK_64K, +#endif +#if THREAD_SIZE > 65536 + KSTACK_REST, +#endif +#endif /* CONFIG_DEBUG_STACK_USAGE */ NR_VM_EVENT_ITEMS }; diff --git a/kernel/exit.c b/kernel/exit.c index 7430852a8571..64bfc2bae55b 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -778,6 +778,43 @@ static void exit_notify(struct task_struct *tsk, int group_dead) } #ifdef CONFIG_DEBUG_STACK_USAGE +/* Count the maximum pages reached in kernel stacks */ +static inline void kstack_histogram(unsigned long used_stack) +{ +#ifdef CONFIG_VM_EVENT_COUNTERS + if (used_stack <= 1024) + count_vm_event(KSTACK_1K); +#if THREAD_SIZE > 1024 + else if (used_stack <= 2048) + count_vm_event(KSTACK_2K); +#endif +#if THREAD_SIZE > 2048 + else if (used_stack <= 4096) + count_vm_event(KSTACK_4K); +#endif +#if THREAD_SIZE > 4096 + else if (used_stack <= 8192) + count_vm_event(KSTACK_8K); +#endif +#if THREAD_SIZE > 8192 + else if (used_stack <= 16384) + count_vm_event(KSTACK_16K); +#endif +#if THREAD_SIZE > 16384 + else if (used_stack <= 32768) + count_vm_event(KSTACK_32K); +#endif +#if THREAD_SIZE > 32768 + else if (used_stack <= 65536) + count_vm_event(KSTACK_64K); +#endif +#if THREAD_SIZE > 65536 + else + count_vm_event(KSTACK_REST); +#endif +#endif /* CONFIG_VM_EVENT_COUNTERS */ +} + static void check_stack_usage(void) { static DEFINE_SPINLOCK(low_water_lock); @@ -785,6 +822,7 @@ static void check_stack_usage(void) unsigned long free; free = stack_not_used(current); + kstack_histogram(THREAD_SIZE - free); if (free >= lowest_to_date) return; diff --git a/mm/vmstat.c b/mm/vmstat.c index 1ac2a569b6cf..2dc97baf7d62 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1436,6 +1436,30 @@ const char * const vmstat_text[] = { "vma_lock_retry", "vma_lock_miss", #endif +#ifdef CONFIG_DEBUG_STACK_USAGE + "kstack_1k", +#if THREAD_SIZE > 1024 + "kstack_2k", +#endif +#if THREAD_SIZE > 2048 + "kstack_4k", +#endif +#if THREAD_SIZE > 4096 + "kstack_8k", +#endif +#if THREAD_SIZE > 8192 + "kstack_16k", +#endif +#if THREAD_SIZE > 16384 + "kstack_32k", +#endif +#if THREAD_SIZE > 32768 + "kstack_64k", +#endif +#if THREAD_SIZE > 65536 + "kstack_rest", +#endif +#endif #endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */ }; #endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA || CONFIG_MEMCG */ -- cgit v1.2.3 From fbe76a6557a83af5ef3819fd7b7ffd0a5d3b4e51 Mon Sep 17 00:00:00 2001 From: Pasha Tatashin Date: Wed, 24 Jul 2024 20:33:22 +0000 Subject: task_stack: uninline stack_not_used Given that stack_not_used() is not performance critical function uninline it. Link: https://lkml.kernel.org/r/20240730150158.832783-4-pasha.tatashin@soleen.com Link: https://lkml.kernel.org/r/20240724203322.2765486-4-pasha.tatashin@soleen.com Signed-off-by: Pasha Tatashin Acked-by: Shakeel Butt Cc: Domenico Cerasuolo Cc: Kent Overstreet Cc: Li Zhijian Cc: Matthew Wilcox Cc: Nhat Pham Cc: Peter Zijlstra Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Zi Yan Signed-off-by: Andrew Morton --- include/linux/sched/task_stack.h | 18 +++--------------- kernel/exit.c | 19 +++++++++++++++++++ kernel/sched/core.c | 4 +--- 3 files changed, 23 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h index ccd72b978e1f..bf10bdb487dd 100644 --- a/include/linux/sched/task_stack.h +++ b/include/linux/sched/task_stack.h @@ -95,23 +95,11 @@ static inline int object_is_on_stack(const void *obj) extern void thread_stack_cache_init(void); #ifdef CONFIG_DEBUG_STACK_USAGE +unsigned long stack_not_used(struct task_struct *p); +#else static inline unsigned long stack_not_used(struct task_struct *p) { - unsigned long *n = end_of_stack(p); - - do { /* Skip over canary */ -# ifdef CONFIG_STACK_GROWSUP - n--; -# else - n++; -# endif - } while (!*n); - -# ifdef CONFIG_STACK_GROWSUP - return (unsigned long)end_of_stack(p) - (unsigned long)n; -# else - return (unsigned long)n - (unsigned long)end_of_stack(p); -# endif + return 0; } #endif extern void set_task_stack_end_magic(struct task_struct *tsk); diff --git a/kernel/exit.c b/kernel/exit.c index 64bfc2bae55b..45085a0e7c16 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -778,6 +778,25 @@ static void exit_notify(struct task_struct *tsk, int group_dead) } #ifdef CONFIG_DEBUG_STACK_USAGE +unsigned long stack_not_used(struct task_struct *p) +{ + unsigned long *n = end_of_stack(p); + + do { /* Skip over canary */ +# ifdef CONFIG_STACK_GROWSUP + n--; +# else + n++; +# endif + } while (!*n); + +# ifdef CONFIG_STACK_GROWSUP + return (unsigned long)end_of_stack(p) - (unsigned long)n; +# else + return (unsigned long)n - (unsigned long)end_of_stack(p); +# endif +} + /* Count the maximum pages reached in kernel stacks */ static inline void kstack_histogram(unsigned long used_stack) { diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f3951e4a55e5..43e701f54013 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7405,7 +7405,7 @@ EXPORT_SYMBOL(io_schedule); void sched_show_task(struct task_struct *p) { - unsigned long free = 0; + unsigned long free; int ppid; if (!try_get_task_stack(p)) @@ -7415,9 +7415,7 @@ void sched_show_task(struct task_struct *p) if (task_is_running(p)) pr_cont(" running task "); -#ifdef CONFIG_DEBUG_STACK_USAGE free = stack_not_used(p); -#endif ppid = 0; rcu_read_lock(); if (pid_alive(p)) -- cgit v1.2.3 From f77bd4b14ccfd38dfcfe67eecad517b8ec1b7f37 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 26 Jul 2024 20:31:08 +0000 Subject: mm: memcg: don't call propagate_protected_usage() needlessly Patch series "mm: memcg: page counters optimizations", v3. This patchset contains 3 independent small optimizations of page counters. This patch (of 3): Memory protection (min/low) requires a constant tracking of protected memory usage. propagate_protected_usage() is called on each page counters update and does a number of operations even in cases when the actual memory protection functionality is not supported (e.g. hugetlb cgroups or memcg swap counters). It's obviously inefficient and leads to a waste of CPU cycles. It can be addressed by calling propagate_protected_usage() only for the counters which do support memory guarantees. As of now it's only memcg->memory - the unified memory memcg counter. Link: https://lkml.kernel.org/r/20240726203110.1577216-2-roman.gushchin@linux.dev Signed-off-by: Roman Gushchin Acked-by: Shakeel Butt Acked-by: Johannes Weiner Cc: Michal Hocko Cc: Muchun Song Signed-off-by: Andrew Morton --- include/linux/page_counter.h | 8 +++++++- mm/hugetlb_cgroup.c | 4 ++-- mm/memcontrol.c | 16 ++++++++-------- mm/page_counter.c | 17 ++++++++++++++--- 4 files changed, 31 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h index 904c52f97284..0b8e993f9163 100644 --- a/include/linux/page_counter.h +++ b/include/linux/page_counter.h @@ -31,6 +31,7 @@ struct page_counter { /* Keep all the read most fields in a separete cacheline. */ CACHELINE_PADDING(_pad2_); + bool protection_support; unsigned long min; unsigned long low; unsigned long high; @@ -44,12 +45,17 @@ struct page_counter { #define PAGE_COUNTER_MAX (LONG_MAX / PAGE_SIZE) #endif +/* + * Protection is supported only for the first counter (with id 0). + */ static inline void page_counter_init(struct page_counter *counter, - struct page_counter *parent) + struct page_counter *parent, + bool protection_support) { atomic_long_set(&counter->usage, 0); counter->max = PAGE_COUNTER_MAX; counter->parent = parent; + counter->protection_support = protection_support; } static inline unsigned long page_counter_read(struct page_counter *counter) diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index 4ff238ba1250..e716c4671a15 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -114,10 +114,10 @@ static void hugetlb_cgroup_init(struct hugetlb_cgroup *h_cgroup, } page_counter_init(hugetlb_cgroup_counter_from_cgroup(h_cgroup, idx), - fault_parent); + fault_parent, false); page_counter_init( hugetlb_cgroup_counter_from_cgroup_rsvd(h_cgroup, idx), - rsvd_parent); + rsvd_parent, false); limit = round_down(PAGE_COUNTER_MAX, pages_per_huge_page(&hstates[idx])); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index c0ee0f2f8176..f92578f13b2e 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3596,21 +3596,21 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) if (parent) { WRITE_ONCE(memcg->swappiness, mem_cgroup_swappiness(parent)); - page_counter_init(&memcg->memory, &parent->memory); - page_counter_init(&memcg->swap, &parent->swap); + page_counter_init(&memcg->memory, &parent->memory, true); + page_counter_init(&memcg->swap, &parent->swap, false); #ifdef CONFIG_MEMCG_V1 WRITE_ONCE(memcg->oom_kill_disable, READ_ONCE(parent->oom_kill_disable)); - page_counter_init(&memcg->kmem, &parent->kmem); - page_counter_init(&memcg->tcpmem, &parent->tcpmem); + page_counter_init(&memcg->kmem, &parent->kmem, false); + page_counter_init(&memcg->tcpmem, &parent->tcpmem, false); #endif } else { init_memcg_stats(); init_memcg_events(); - page_counter_init(&memcg->memory, NULL); - page_counter_init(&memcg->swap, NULL); + page_counter_init(&memcg->memory, NULL, true); + page_counter_init(&memcg->swap, NULL, false); #ifdef CONFIG_MEMCG_V1 - page_counter_init(&memcg->kmem, NULL); - page_counter_init(&memcg->tcpmem, NULL); + page_counter_init(&memcg->kmem, NULL, false); + page_counter_init(&memcg->tcpmem, NULL, false); #endif root_mem_cgroup = memcg; return &memcg->css; diff --git a/mm/page_counter.c b/mm/page_counter.c index 0153f5bb3161..dd242245bee2 100644 --- a/mm/page_counter.c +++ b/mm/page_counter.c @@ -13,6 +13,11 @@ #include #include +static bool track_protection(struct page_counter *c) +{ + return c->protection_support; +} + static void propagate_protected_usage(struct page_counter *c, unsigned long usage) { @@ -57,7 +62,8 @@ void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages) new = 0; atomic_long_set(&counter->usage, new); } - propagate_protected_usage(counter, new); + if (track_protection(counter)) + propagate_protected_usage(counter, new); } /** @@ -70,12 +76,14 @@ void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages) void page_counter_charge(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; + bool protection = track_protection(counter); for (c = counter; c; c = c->parent) { long new; new = atomic_long_add_return(nr_pages, &c->usage); - propagate_protected_usage(c, new); + if (protection) + propagate_protected_usage(c, new); /* * This is indeed racy, but we can live with some * inaccuracy in the watermark. @@ -99,6 +107,7 @@ bool page_counter_try_charge(struct page_counter *counter, struct page_counter **fail) { struct page_counter *c; + bool protection = track_protection(counter); for (c = counter; c; c = c->parent) { long new; @@ -128,7 +137,9 @@ bool page_counter_try_charge(struct page_counter *counter, *fail = c; goto failed; } - propagate_protected_usage(c, new); + if (protection) + propagate_protected_usage(c, new); + /* * Just like with failcnt, we can live with some * inaccuracy in the watermark. -- cgit v1.2.3 From 941ce635234162c420c9185816c59f7d5dd1ad07 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 26 Jul 2024 20:31:09 +0000 Subject: mm: page_counters: put page_counter_calculate_protection() under CONFIG_MEMCG Put page_counter_calculate_protection() under CONFIG_MEMCG. The protection functionality (min/low limits) is not supported by any other cgroup subsystem, so page_counter_calculate_protection() and related static effective_protection() can be compiled out if CONFIG_MEMCG is not enabled. Link: https://lkml.kernel.org/r/20240726203110.1577216-3-roman.gushchin@linux.dev Signed-off-by: Roman Gushchin Acked-by: Shakeel Butt Acked-by: Johannes Weiner Cc: Michal Hocko Cc: Muchun Song Signed-off-by: Andrew Morton --- include/linux/page_counter.h | 6 ++++++ mm/page_counter.c | 2 ++ 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h index 0b8e993f9163..1b3e92c09b80 100644 --- a/include/linux/page_counter.h +++ b/include/linux/page_counter.h @@ -87,8 +87,14 @@ static inline void page_counter_reset_watermark(struct page_counter *counter) counter->watermark = page_counter_read(counter); } +#ifdef CONFIG_MEMCG void page_counter_calculate_protection(struct page_counter *root, struct page_counter *counter, bool recursive_protection); +#else +static inline void page_counter_calculate_protection(struct page_counter *root, + struct page_counter *counter, + bool recursive_protection) {} +#endif #endif /* _LINUX_PAGE_COUNTER_H */ diff --git a/mm/page_counter.c b/mm/page_counter.c index dd242245bee2..3887bd152b75 100644 --- a/mm/page_counter.c +++ b/mm/page_counter.c @@ -275,6 +275,7 @@ int page_counter_memparse(const char *buf, const char *max, } +#ifdef CONFIG_MEMCG /* * This function calculates an individual page counter's effective * protection which is derived from its own memory.min/low, its @@ -446,3 +447,4 @@ void page_counter_calculate_protection(struct page_counter *root, atomic_long_read(&parent->children_low_usage), recursive_protection)); } +#endif /* CONFIG_MEMCG */ -- cgit v1.2.3 From 57979fabff554bf4d1edeeee69251b22ca9bf55e Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 26 Jul 2024 20:31:10 +0000 Subject: mm: page_counters: initialize usage using ATOMIC_LONG_INIT() macro When a page_counter structure is initialized, there is no need to use an atomic set operation to initialize the usage counter because at this point the structure is not visible to anybody else. ATOMIC_LONG_INIT() is what should be used in such cases. Link: https://lkml.kernel.org/r/20240726203110.1577216-4-roman.gushchin@linux.dev Signed-off-by: Roman Gushchin Acked-by: Shakeel Butt Acked-by: Johannes Weiner Cc: Michal Hocko Cc: Muchun Song Signed-off-by: Andrew Morton --- include/linux/page_counter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h index 1b3e92c09b80..66ebf9a73158 100644 --- a/include/linux/page_counter.h +++ b/include/linux/page_counter.h @@ -52,7 +52,7 @@ static inline void page_counter_init(struct page_counter *counter, struct page_counter *parent, bool protection_support) { - atomic_long_set(&counter->usage, 0); + counter->usage = (atomic_long_t)ATOMIC_LONG_INIT(0); counter->max = PAGE_COUNTER_MAX; counter->parent = parent; counter->protection_support = protection_support; -- cgit v1.2.3 From 394290cba9664ed3ab80d0e247402102a9b7287a Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 26 Jul 2024 17:07:26 +0200 Subject: mm: turn USE_SPLIT_PTE_PTLOCKS / USE_SPLIT_PTE_PTLOCKS into Kconfig options Patch series "mm: split PTE/PMD PT table Kconfig cleanups+clarifications". This series is a follow up to the fixes: "[PATCH v1 0/2] mm/hugetlb: fix hugetlb vs. core-mm PT locking" When working on the fixes, I wondered why 8xx is fine (-> never uses split PT locks) and how PT locking even works properly with PMD page table sharing (-> always requires split PMD PT locks). Let's improve the split PT lock detection, make hugetlb properly depend on it and make 8xx bail out if it would ever get enabled by accident. As an alternative to patch #3 we could extend the Kconfig SPLIT_PTE_PTLOCKS option from patch #2 -- but enforcing it closer to the code that actually implements it feels a bit nicer for documentation purposes, and there is no need to actually disable it because it should always be disabled (!SMP). Did a bunch of cross-compilations to make sure that split PTE/PMD PT locks are still getting used where we would expect them. [1] https://lkml.kernel.org/r/20240725183955.2268884-1-david@redhat.com This patch (of 3): Let's clean that up a bit and prepare for depending on CONFIG_SPLIT_PMD_PTLOCKS in other Kconfig options. More cleanups would be reasonable (like the arch-specific "depends on" for CONFIG_SPLIT_PTE_PTLOCKS), but we'll leave that for another day. Link: https://lkml.kernel.org/r/20240726150728.3159964-1-david@redhat.com Link: https://lkml.kernel.org/r/20240726150728.3159964-2-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Mike Rapoport (Microsoft) Reviewed-by: Russell King (Oracle) Reviewed-by: Qi Zheng Cc: Alexander Viro Cc: Borislav Petkov Cc: Boris Ostrovsky Cc: Christian Brauner Cc: Christophe Leroy Cc: Dave Hansen Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Juergen Gross Cc: Michael Ellerman Cc: Muchun Song Cc: "Naveen N. Rao" Cc: Nicholas Piggin Cc: Oscar Salvador Cc: Peter Xu Cc: Thomas Gleixner Signed-off-by: Andrew Morton --- arch/arm/mm/fault-armv.c | 6 +++--- arch/x86/xen/mmu_pv.c | 7 ++++--- include/linux/mm.h | 8 ++++---- include/linux/mm_types.h | 2 +- include/linux/mm_types_task.h | 3 --- kernel/fork.c | 4 ++-- mm/Kconfig | 18 +++++++++++------- mm/memory.c | 2 +- 8 files changed, 26 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c index 2286c2ea60ec..831793cd6ff9 100644 --- a/arch/arm/mm/fault-armv.c +++ b/arch/arm/mm/fault-armv.c @@ -61,7 +61,7 @@ static int do_adjust_pte(struct vm_area_struct *vma, unsigned long address, return ret; } -#if USE_SPLIT_PTE_PTLOCKS +#if defined(CONFIG_SPLIT_PTE_PTLOCKS) /* * If we are using split PTE locks, then we need to take the page * lock here. Otherwise we are using shared mm->page_table_lock @@ -80,10 +80,10 @@ static inline void do_pte_unlock(spinlock_t *ptl) { spin_unlock(ptl); } -#else /* !USE_SPLIT_PTE_PTLOCKS */ +#else /* !defined(CONFIG_SPLIT_PTE_PTLOCKS) */ static inline void do_pte_lock(spinlock_t *ptl) {} static inline void do_pte_unlock(spinlock_t *ptl) {} -#endif /* USE_SPLIT_PTE_PTLOCKS */ +#endif /* defined(CONFIG_SPLIT_PTE_PTLOCKS) */ static int adjust_pte(struct vm_area_struct *vma, unsigned long address, unsigned long pfn) diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index f1ce39d6d32c..f4a316894bbb 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -665,7 +665,7 @@ static spinlock_t *xen_pte_lock(struct page *page, struct mm_struct *mm) { spinlock_t *ptl = NULL; -#if USE_SPLIT_PTE_PTLOCKS +#if defined(CONFIG_SPLIT_PTE_PTLOCKS) ptl = ptlock_ptr(page_ptdesc(page)); spin_lock_nest_lock(ptl, &mm->page_table_lock); #endif @@ -1553,7 +1553,8 @@ static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn, __set_pfn_prot(pfn, PAGE_KERNEL_RO); - if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS && !pinned) + if (level == PT_PTE && IS_ENABLED(CONFIG_SPLIT_PTE_PTLOCKS) && + !pinned) __pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn); xen_mc_issue(XEN_LAZY_MMU); @@ -1581,7 +1582,7 @@ static inline void xen_release_ptpage(unsigned long pfn, unsigned level) if (pinned) { xen_mc_batch(); - if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS) + if (level == PT_PTE && IS_ENABLED(CONFIG_SPLIT_PTE_PTLOCKS)) __pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn); __set_pfn_prot(pfn, PAGE_KERNEL); diff --git a/include/linux/mm.h b/include/linux/mm.h index 6c2078ca3391..b7000fa300f3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2891,7 +2891,7 @@ static inline void pagetable_free(struct ptdesc *pt) __free_pages(page, compound_order(page)); } -#if USE_SPLIT_PTE_PTLOCKS +#if defined(CONFIG_SPLIT_PTE_PTLOCKS) #if ALLOC_SPLIT_PTLOCKS void __init ptlock_cache_init(void); bool ptlock_alloc(struct ptdesc *ptdesc); @@ -2949,7 +2949,7 @@ static inline bool ptlock_init(struct ptdesc *ptdesc) return true; } -#else /* !USE_SPLIT_PTE_PTLOCKS */ +#else /* !defined(CONFIG_SPLIT_PTE_PTLOCKS) */ /* * We use mm->page_table_lock to guard all pagetable pages of the mm. */ @@ -2964,7 +2964,7 @@ static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte) static inline void ptlock_cache_init(void) {} static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; } static inline void ptlock_free(struct ptdesc *ptdesc) {} -#endif /* USE_SPLIT_PTE_PTLOCKS */ +#endif /* defined(CONFIG_SPLIT_PTE_PTLOCKS) */ static inline bool pagetable_pte_ctor(struct ptdesc *ptdesc) { @@ -3024,7 +3024,7 @@ pte_t *pte_offset_map_nolock(struct mm_struct *mm, pmd_t *pmd, ((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd))? \ NULL: pte_offset_kernel(pmd, address)) -#if USE_SPLIT_PMD_PTLOCKS +#if defined(CONFIG_SPLIT_PMD_PTLOCKS) static inline struct page *pmd_pgtable_page(pmd_t *pmd) { diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 485424979254..165c58b12ccc 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -947,7 +947,7 @@ struct mm_struct { #ifdef CONFIG_MMU_NOTIFIER struct mmu_notifier_subscriptions *notifier_subscriptions; #endif -#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !defined(CONFIG_SPLIT_PMD_PTLOCKS) pgtable_t pmd_huge_pte; /* protected by page_table_lock */ #endif #ifdef CONFIG_NUMA_BALANCING diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h index a2f6179b672b..bff5706b76e1 100644 --- a/include/linux/mm_types_task.h +++ b/include/linux/mm_types_task.h @@ -16,9 +16,6 @@ #include #endif -#define USE_SPLIT_PTE_PTLOCKS (NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS) -#define USE_SPLIT_PMD_PTLOCKS (USE_SPLIT_PTE_PTLOCKS && \ - IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK)) #define ALLOC_SPLIT_PTLOCKS (SPINLOCK_SIZE > BITS_PER_LONG/8) /* diff --git a/kernel/fork.c b/kernel/fork.c index cc760491f201..3d590e51ce84 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -832,7 +832,7 @@ static void check_mm(struct mm_struct *mm) pr_alert("BUG: non-zero pgtables_bytes on freeing mm: %ld\n", mm_pgtables_bytes(mm)); -#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !defined(CONFIG_SPLIT_PMD_PTLOCKS) VM_BUG_ON_MM(mm->pmd_huge_pte, mm); #endif } @@ -1276,7 +1276,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, RCU_INIT_POINTER(mm->exe_file, NULL); mmu_notifier_subscriptions_init(mm); init_tlb_flush_pending(mm); -#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !defined(CONFIG_SPLIT_PMD_PTLOCKS) mm->pmd_huge_pte = NULL; #endif mm_init_uprobes_state(mm); diff --git a/mm/Kconfig b/mm/Kconfig index b72e7d040f78..7b716ac80272 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -585,17 +585,21 @@ config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE # at the same time (e.g. copy_page_range()). # DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC spinlock_t also enlarge struct page. # -config SPLIT_PTLOCK_CPUS - int - default "999999" if !MMU - default "999999" if ARM && !CPU_CACHE_VIPT - default "999999" if PARISC && !PA20 - default "999999" if SPARC32 - default "4" +config SPLIT_PTE_PTLOCKS + def_bool y + depends on MMU + depends on NR_CPUS >= 4 + depends on !ARM || CPU_CACHE_VIPT + depends on !PARISC || PA20 + depends on !SPARC32 config ARCH_ENABLE_SPLIT_PMD_PTLOCK bool +config SPLIT_PMD_PTLOCKS + def_bool y + depends on SPLIT_PTE_PTLOCKS && ARCH_ENABLE_SPLIT_PMD_PTLOCK + # # support for memory balloon config MEMORY_BALLOON diff --git a/mm/memory.c b/mm/memory.c index a3d955098a19..71236ae6fd14 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -6571,7 +6571,7 @@ long copy_folio_from_user(struct folio *dst_folio, } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ -#if USE_SPLIT_PTE_PTLOCKS && ALLOC_SPLIT_PTLOCKS +#if defined(CONFIG_SPLIT_PTE_PTLOCKS) && ALLOC_SPLIT_PTLOCKS static struct kmem_cache *page_ptl_cachep; -- cgit v1.2.3 From 188cac58a8bcdf82c7f63275b68f7a46871e45d6 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 26 Jul 2024 17:07:27 +0200 Subject: mm/hugetlb: enforce that PMD PT sharing has split PMD PT locks Sharing page tables between processes but falling back to per-MM page table locks cannot possibly work. So, let's make sure that we do have split PMD locks by adding a new Kconfig option and letting that depend on CONFIG_SPLIT_PMD_PTLOCKS. Link: https://lkml.kernel.org/r/20240726150728.3159964-3-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Mike Rapoport (Microsoft) Cc: Alexander Viro Cc: Borislav Petkov Cc: Boris Ostrovsky Cc: Christian Brauner Cc: Christophe Leroy Cc: Dave Hansen Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Juergen Gross Cc: Michael Ellerman Cc: Muchun Song Cc: "Naveen N. Rao" Cc: Nicholas Piggin Cc: Oscar Salvador Cc: Peter Xu Cc: Russell King Cc: Thomas Gleixner Signed-off-by: Andrew Morton --- fs/Kconfig | 4 ++++ include/linux/hugetlb.h | 5 ++--- mm/hugetlb.c | 8 ++++---- 3 files changed, 10 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/fs/Kconfig b/fs/Kconfig index a46b0cbc4d8f..0e4efec1d92e 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -288,6 +288,10 @@ config HUGETLB_PAGE_OPTIMIZE_VMEMMAP depends on ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP depends on SPARSEMEM_VMEMMAP +config HUGETLB_PMD_PAGE_TABLE_SHARING + def_bool HUGETLB_PAGE + depends on ARCH_WANT_HUGE_PMD_SHARE && SPLIT_PMD_PTLOCKS + config ARCH_HAS_GIGANTIC_PAGE bool diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 45bf05ad5c53..9b7bcfce6920 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -1251,7 +1251,7 @@ static inline __init void hugetlb_cma_reserve(int order) } #endif -#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING static inline bool hugetlb_pmd_shared(pte_t *pte) { return page_count(virt_to_page(pte)) > 1; @@ -1287,8 +1287,7 @@ bool __vma_private_lock(struct vm_area_struct *vma); static inline pte_t * hugetlb_walk(struct vm_area_struct *vma, unsigned long addr, unsigned long sz) { -#if defined(CONFIG_HUGETLB_PAGE) && \ - defined(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) && defined(CONFIG_LOCKDEP) +#if defined(CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING) && defined(CONFIG_LOCKDEP) struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; /* diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 5a32157ca309..1fdd9eab240c 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -7211,7 +7211,7 @@ long hugetlb_unreserve_pages(struct inode *inode, long start, long end, return 0; } -#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING static unsigned long page_table_shareable(struct vm_area_struct *svma, struct vm_area_struct *vma, unsigned long addr, pgoff_t idx) @@ -7373,7 +7373,7 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, return 1; } -#else /* !CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ +#else /* !CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pud_t *pud) @@ -7396,7 +7396,7 @@ bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr) { return false; } -#endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ +#endif /* CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */ #ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, @@ -7494,7 +7494,7 @@ unsigned long hugetlb_mask_last_page(struct hstate *h) /* See description above. Architectures can provide their own version. */ __weak unsigned long hugetlb_mask_last_page(struct hstate *h) { -#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING if (huge_page_size(h) == PMD_SIZE) return PUD_SIZE - PMD_SIZE; #endif -- cgit v1.2.3 From e5a41fc77771c7c7f6b9bef85a02b38b802b7371 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 29 Jul 2024 20:38:42 +0200 Subject: mm: simplify arch_make_folio_accessible() Patch series "mm: remove arch_make_page_accessible()". Now that s390x implements arch_make_folio_accessible(), let's convert remaining users to use arch_make_folio_accessible() instead so we can remove arch_make_page_accessible(). This patch (of 3): Now that s390x implements HAVE_ARCH_MAKE_FOLIO_ACCESSIBLE, let's turn generic arch_make_folio_accessible() into a NOP: there are no other targets that implement HAVE_ARCH_MAKE_PAGE_ACCESSIBLE but not HAVE_ARCH_MAKE_FOLIO_ACCESSIBLE. Link: https://lkml.kernel.org/r/20240729183844.388481-1-david@redhat.com Link: https://lkml.kernel.org/r/20240729183844.388481-2-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Matthew Wilcox (Oracle) Reviewed-by: Vishal Moola (Oracle) Reviewed-by: Claudio Imbrenda Cc: Alexander Gordeev Cc: Christian Borntraeger Cc: David Hildenbrand Cc: Heiko Carstens Cc: Janosch Frank Cc: Sven Schnelle Cc: Vasily Gorbik Signed-off-by: Andrew Morton --- include/linux/mm.h | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index b7000fa300f3..fc7bd3864bcd 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2215,16 +2215,7 @@ static inline int arch_make_page_accessible(struct page *page) #ifndef HAVE_ARCH_MAKE_FOLIO_ACCESSIBLE static inline int arch_make_folio_accessible(struct folio *folio) { - int ret; - long i, nr = folio_nr_pages(folio); - - for (i = 0; i < nr; i++) { - ret = arch_make_page_accessible(folio_page(folio, i)); - if (ret) - break; - } - - return ret; + return 0; } #endif -- cgit v1.2.3 From 3290ef3c7f2a8171fc534e02fb95a512eeae689a Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 29 Jul 2024 20:38:44 +0200 Subject: s390/uv: drop arch_make_page_accessible() All code was converted to using arch_make_folio_accessible(), let's drop arch_make_page_accessible(). Link: https://lkml.kernel.org/r/20240729183844.388481-4-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Matthew Wilcox (Oracle) Reviewed-by: Vishal Moola (Oracle) Reviewed-by: Claudio Imbrenda Cc: Alexander Gordeev Cc: Christian Borntraeger Cc: Heiko Carstens Cc: Janosch Frank Cc: Sven Schnelle Cc: Vasily Gorbik Signed-off-by: Andrew Morton --- arch/s390/include/asm/page.h | 2 -- arch/s390/kernel/uv.c | 5 ----- include/linux/mm.h | 7 ------- 3 files changed, 14 deletions(-) (limited to 'include/linux') diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index 16e4caa931f1..73e1e03317b4 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -176,8 +176,6 @@ static inline int devmem_is_allowed(unsigned long pfn) int arch_make_folio_accessible(struct folio *folio); #define HAVE_ARCH_MAKE_FOLIO_ACCESSIBLE -int arch_make_page_accessible(struct page *page); -#define HAVE_ARCH_MAKE_PAGE_ACCESSIBLE struct vm_layout { unsigned long kaslr_offset; diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c index 36db065c7cf7..35ed2aea8891 100644 --- a/arch/s390/kernel/uv.c +++ b/arch/s390/kernel/uv.c @@ -548,11 +548,6 @@ int arch_make_folio_accessible(struct folio *folio) } EXPORT_SYMBOL_GPL(arch_make_folio_accessible); -int arch_make_page_accessible(struct page *page) -{ - return arch_make_folio_accessible(page_folio(page)); -} -EXPORT_SYMBOL_GPL(arch_make_page_accessible); static ssize_t uv_query_facilities(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { diff --git a/include/linux/mm.h b/include/linux/mm.h index fc7bd3864bcd..153a4662a0cd 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2205,13 +2205,6 @@ static inline bool folio_likely_mapped_shared(struct folio *folio) return atomic_read(&folio->_mapcount) > 0; } -#ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE -static inline int arch_make_page_accessible(struct page *page) -{ - return 0; -} -#endif - #ifndef HAVE_ARCH_MAKE_FOLIO_ACCESSIBLE static inline int arch_make_folio_accessible(struct folio *folio) { -- cgit v1.2.3 From c6f53ed8f213a66ae8bc40aa9112c32412c35a21 Mon Sep 17 00:00:00 2001 From: David Finkel Date: Mon, 29 Jul 2024 10:37:42 -0400 Subject: mm, memcg: cg2 memory{.swap,}.peak write handlers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "mm, memcg: cg2 memory{.swap,}.peak write handlers", v7. This patch (of 2): Other mechanisms for querying the peak memory usage of either a process or v1 memory cgroup allow for resetting the high watermark. Restore parity with those mechanisms, but with a less racy API. For example: - Any write to memory.max_usage_in_bytes in a cgroup v1 mount resets the high watermark. - writing "5" to the clear_refs pseudo-file in a processes's proc directory resets the peak RSS. This change is an evolution of a previous patch, which mostly copied the cgroup v1 behavior, however, there were concerns about races/ownership issues with a global reset, so instead this change makes the reset filedescriptor-local. Writing any non-empty string to the memory.peak and memory.swap.peak pseudo-files reset the high watermark to the current usage for subsequent reads through that same FD. Notably, following Johannes's suggestion, this implementation moves the O(FDs that have written) behavior onto the FD write(2) path. Instead, on the page-allocation path, we simply add one additional watermark to conditionally bump per-hierarchy level in the page-counter. Additionally, this takes Longman's suggestion of nesting the page-charging-path checks for the two watermarks to reduce the number of common-case comparisons. This behavior is particularly useful for work scheduling systems that need to track memory usage of worker processes/cgroups per-work-item. Since memory can't be squeezed like CPU can (the OOM-killer has opinions), these systems need to track the peak memory usage to compute system/container fullness when binpacking workitems. Most notably, Vimeo's use-case involves a system that's doing global binpacking across many Kubernetes pods/containers, and while we can use PSI for some local decisions about overload, we strive to avoid packing workloads too tightly in the first place. To facilitate this, we track the peak memory usage. However, since we run with long-lived workers (to amortize startup costs) we need a way to track the high watermark while a work-item is executing. Polling runs the risk of missing short spikes that last for timescales below the polling interval, and peak memory tracking at the cgroup level is otherwise perfect for this use-case. As this data is used to ensure that binpacked work ends up with sufficient headroom, this use-case mostly avoids the inaccuracies surrounding reclaimable memory. Link: https://lkml.kernel.org/r/20240730231304.761942-1-davidf@vimeo.com Link: https://lkml.kernel.org/r/20240729143743.34236-1-davidf@vimeo.com Link: https://lkml.kernel.org/r/20240729143743.34236-2-davidf@vimeo.com Signed-off-by: David Finkel Suggested-by: Johannes Weiner Suggested-by: Waiman Long Acked-by: Johannes Weiner Reviewed-by: Michal Koutný Acked-by: Tejun Heo Reviewed-by: Roman Gushchin Cc: Jonathan Corbet Cc: Michal Hocko Cc: Muchun Song Cc: Shakeel Butt Cc: Shuah Khan Cc: Zefan Li Signed-off-by: Andrew Morton --- Documentation/admin-guide/cgroup-v2.rst | 22 +++--- include/linux/cgroup-defs.h | 5 ++ include/linux/cgroup.h | 3 + include/linux/memcontrol.h | 5 ++ include/linux/page_counter.h | 11 ++- kernel/cgroup/cgroup-internal.h | 2 + kernel/cgroup/cgroup.c | 7 ++ mm/memcontrol.c | 116 +++++++++++++++++++++++++++++--- mm/page_counter.c | 29 +++++--- 9 files changed, 173 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 86311c2907cd..f0499884124d 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1333,11 +1333,14 @@ The following nested keys are defined. all the existing limitations and potential future extensions. memory.peak - A read-only single value file which exists on non-root - cgroups. + A read-write single value file which exists on non-root cgroups. + + The max memory usage recorded for the cgroup and its descendants since + either the creation of the cgroup or the most recent reset for that FD. - The max memory usage recorded for the cgroup and its - descendants since the creation of the cgroup. + A write of any non-empty string to this file resets it to the + current memory usage for subsequent reads through the same + file descriptor. memory.oom.group A read-write single value file which exists on non-root @@ -1663,11 +1666,14 @@ The following nested keys are defined. Healthy workloads are not expected to reach this limit. memory.swap.peak - A read-only single value file which exists on non-root - cgroups. + A read-write single value file which exists on non-root cgroups. + + The max swap usage recorded for the cgroup and its descendants since + the creation of the cgroup or the most recent reset for that FD. - The max swap usage recorded for the cgroup and its - descendants since the creation of the cgroup. + A write of any non-empty string to this file resets it to the + current memory usage for subsequent reads through the same + file descriptor. memory.swap.max A read-write single value file which exists on non-root diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index ae04035b6cbe..7fc2d0195f56 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -775,6 +775,11 @@ struct cgroup_subsys { extern struct percpu_rw_semaphore cgroup_threadgroup_rwsem; +struct cgroup_of_peak { + unsigned long value; + struct list_head list; +}; + /** * cgroup_threadgroup_change_begin - threadgroup exclusion for cgroups * @tsk: target task diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index c60ba0ab1462..3e0563753cc3 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -11,6 +11,7 @@ #include #include +#include #include #include #include @@ -854,4 +855,6 @@ static inline void cgroup_bpf_put(struct cgroup *cgrp) {} struct cgroup *task_get_cgroup1(struct task_struct *tsk, int hierarchy_id); +struct cgroup_of_peak *of_peak(struct kernfs_open_file *of); + #endif /* _LINUX_CGROUP_H */ diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index af7da7bd00af..1b79760af685 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -193,6 +193,11 @@ struct mem_cgroup { struct page_counter memsw; /* v1 only */ }; + /* registered local peak watchers */ + struct list_head memory_peaks; + struct list_head swap_peaks; + spinlock_t peaks_lock; + /* Range enforcement for interrupt charges */ struct work_struct high_work; diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h index 66ebf9a73158..79dbd8bc35a7 100644 --- a/include/linux/page_counter.h +++ b/include/linux/page_counter.h @@ -26,6 +26,8 @@ struct page_counter { atomic_long_t children_low_usage; unsigned long watermark; + /* Latest cg2 reset watermark */ + unsigned long local_watermark; unsigned long failcnt; /* Keep all the read most fields in a separete cacheline. */ @@ -84,7 +86,14 @@ int page_counter_memparse(const char *buf, const char *max, static inline void page_counter_reset_watermark(struct page_counter *counter) { - counter->watermark = page_counter_read(counter); + unsigned long usage = page_counter_read(counter); + + /* + * Update local_watermark first, so it's always <= watermark + * (modulo CPU/compiler re-ordering) + */ + counter->local_watermark = usage; + counter->watermark = usage; } #ifdef CONFIG_MEMCG diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h index 520b90dd97ec..c964dd7ff967 100644 --- a/kernel/cgroup/cgroup-internal.h +++ b/kernel/cgroup/cgroup-internal.h @@ -81,6 +81,8 @@ struct cgroup_file_ctx { struct { struct cgroup_pidlist *pidlist; } procs1; + + struct cgroup_of_peak peak; }; /* diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index c8e4b62b436a..0a97cb2ef124 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1972,6 +1972,13 @@ static int cgroup2_parse_param(struct fs_context *fc, struct fs_parameter *param return -EINVAL; } +struct cgroup_of_peak *of_peak(struct kernfs_open_file *of) +{ + struct cgroup_file_ctx *ctx = of->priv; + + return &ctx->peak; +} + static void apply_cgroup_root_flags(unsigned int root_flags) { if (current->nsproxy->cgroup_ns == &init_cgroup_ns) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index f92578f13b2e..8971d3473a7b 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -25,6 +25,7 @@ * Copyright (C) 2020 Alibaba, Inc, Alex Shi */ +#include #include #include #include @@ -41,6 +42,7 @@ #include #include #include +#include #include #include #include @@ -3550,6 +3552,9 @@ static struct mem_cgroup *mem_cgroup_alloc(struct mem_cgroup *parent) INIT_WORK(&memcg->high_work, high_work_func); vmpressure_init(&memcg->vmpressure); + INIT_LIST_HEAD(&memcg->memory_peaks); + INIT_LIST_HEAD(&memcg->swap_peaks); + spin_lock_init(&memcg->peaks_lock); memcg->socket_pressure = jiffies; memcg1_memcg_init(memcg); memcg->kmemcg_id = -1; @@ -3944,14 +3949,91 @@ static u64 memory_current_read(struct cgroup_subsys_state *css, return (u64)page_counter_read(&memcg->memory) * PAGE_SIZE; } -static u64 memory_peak_read(struct cgroup_subsys_state *css, - struct cftype *cft) +#define OFP_PEAK_UNSET (((-1UL))) + +static int peak_show(struct seq_file *sf, void *v, struct page_counter *pc) { - struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct cgroup_of_peak *ofp = of_peak(sf->private); + u64 fd_peak = READ_ONCE(ofp->value), peak; + + /* User wants global or local peak? */ + if (fd_peak == OFP_PEAK_UNSET) + peak = pc->watermark; + else + peak = max(fd_peak, READ_ONCE(pc->local_watermark)); + + seq_printf(sf, "%llu\n", peak * PAGE_SIZE); + return 0; +} + +static int memory_peak_show(struct seq_file *sf, void *v) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(sf)); + + return peak_show(sf, v, &memcg->memory); +} + +static int peak_open(struct kernfs_open_file *of) +{ + struct cgroup_of_peak *ofp = of_peak(of); + + ofp->value = OFP_PEAK_UNSET; + return 0; +} + +static void peak_release(struct kernfs_open_file *of) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + struct cgroup_of_peak *ofp = of_peak(of); + + if (ofp->value == OFP_PEAK_UNSET) { + /* fast path (no writes on this fd) */ + return; + } + spin_lock(&memcg->peaks_lock); + list_del(&ofp->list); + spin_unlock(&memcg->peaks_lock); +} + +static ssize_t peak_write(struct kernfs_open_file *of, char *buf, size_t nbytes, + loff_t off, struct page_counter *pc, + struct list_head *watchers) +{ + unsigned long usage; + struct cgroup_of_peak *peer_ctx; + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + struct cgroup_of_peak *ofp = of_peak(of); + + spin_lock(&memcg->peaks_lock); + + usage = page_counter_read(pc); + WRITE_ONCE(pc->local_watermark, usage); + + list_for_each_entry(peer_ctx, watchers, list) + if (usage > peer_ctx->value) + WRITE_ONCE(peer_ctx->value, usage); + + /* initial write, register watcher */ + if (ofp->value == -1) + list_add(&ofp->list, watchers); + + WRITE_ONCE(ofp->value, usage); + spin_unlock(&memcg->peaks_lock); + + return nbytes; +} + +static ssize_t memory_peak_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); - return (u64)memcg->memory.watermark * PAGE_SIZE; + return peak_write(of, buf, nbytes, off, &memcg->memory, + &memcg->memory_peaks); } +#undef OFP_PEAK_UNSET + static int memory_min_show(struct seq_file *m, void *v) { return seq_puts_memcg_tunable(m, @@ -4301,7 +4383,10 @@ static struct cftype memory_files[] = { { .name = "peak", .flags = CFTYPE_NOT_ON_ROOT, - .read_u64 = memory_peak_read, + .open = peak_open, + .release = peak_release, + .seq_show = memory_peak_show, + .write = memory_peak_write, }, { .name = "min", @@ -5093,12 +5178,20 @@ static u64 swap_current_read(struct cgroup_subsys_state *css, return (u64)page_counter_read(&memcg->swap) * PAGE_SIZE; } -static u64 swap_peak_read(struct cgroup_subsys_state *css, - struct cftype *cft) +static int swap_peak_show(struct seq_file *sf, void *v) { - struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(sf)); + + return peak_show(sf, v, &memcg->swap); +} + +static ssize_t swap_peak_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); - return (u64)memcg->swap.watermark * PAGE_SIZE; + return peak_write(of, buf, nbytes, off, &memcg->swap, + &memcg->swap_peaks); } static int swap_high_show(struct seq_file *m, void *v) @@ -5182,7 +5275,10 @@ static struct cftype swap_files[] = { { .name = "swap.peak", .flags = CFTYPE_NOT_ON_ROOT, - .read_u64 = swap_peak_read, + .open = peak_open, + .release = peak_release, + .seq_show = swap_peak_show, + .write = swap_peak_write, }, { .name = "swap.events", diff --git a/mm/page_counter.c b/mm/page_counter.c index 3887bd152b75..b249d15af9dd 100644 --- a/mm/page_counter.c +++ b/mm/page_counter.c @@ -87,9 +87,22 @@ void page_counter_charge(struct page_counter *counter, unsigned long nr_pages) /* * This is indeed racy, but we can live with some * inaccuracy in the watermark. + * + * Notably, we have two watermarks to allow for both a globally + * visible peak and one that can be reset at a smaller scope. + * + * Since we reset both watermarks when the global reset occurs, + * we can guarantee that watermark >= local_watermark, so we + * don't need to do both comparisons every time. + * + * On systems with branch predictors, the inner condition should + * be almost free. */ - if (new > READ_ONCE(c->watermark)) - WRITE_ONCE(c->watermark, new); + if (new > READ_ONCE(c->local_watermark)) { + WRITE_ONCE(c->local_watermark, new); + if (new > READ_ONCE(c->watermark)) + WRITE_ONCE(c->watermark, new); + } } } @@ -140,12 +153,12 @@ bool page_counter_try_charge(struct page_counter *counter, if (protection) propagate_protected_usage(c, new); - /* - * Just like with failcnt, we can live with some - * inaccuracy in the watermark. - */ - if (new > READ_ONCE(c->watermark)) - WRITE_ONCE(c->watermark, new); + /* see comment on page_counter_charge */ + if (new > READ_ONCE(c->local_watermark)) { + WRITE_ONCE(c->local_watermark, new); + if (new > READ_ONCE(c->watermark)) + WRITE_ONCE(c->watermark, new); + } } return true; -- cgit v1.2.3 From a17c7d8fd2b097a422fc892b660e879e19c20214 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Mon, 29 Jul 2024 12:50:35 +0100 Subject: userfaultfd: move core VMA manipulation logic to mm/userfaultfd.c Patch series "Make core VMA operations internal and testable", v4. There are a number of "core" VMA manipulation functions implemented in mm/mmap.c, notably those concerning VMA merging, splitting, modifying, expanding and shrinking, which logically don't belong there. More importantly this functionality represents an internal implementation detail of memory management and should not be exposed outside of mm/ itself. This patch series isolates core VMA manipulation functionality into its own file, mm/vma.c, and provides an API to the rest of the mm code in mm/vma.h. Importantly, it also carefully implements mm/vma_internal.h, which specifies which headers need to be imported by vma.c, leading to the very useful property that vma.c depends only on mm/vma.h and mm/vma_internal.h. This means we can then re-implement vma_internal.h in userland, adding shims for kernel mechanisms as required, allowing us to unit test internal VMA functionality. This testing is useful as opposed to an e.g. kunit implementation as this way we can avoid all external kernel side-effects while testing, run tests VERY quickly, and iterate on and debug problems quickly. Excitingly this opens the door to, in the future, recreating precise problems observed in production in userland and very quickly debugging problems that might otherwise be very difficult to reproduce. This patch series takes advantage of existing shim logic and full userland maple tree support contained in tools/testing/radix-tree/ and tools/include/linux/, separating out shared components of the radix tree implementation to provide this testing. Kernel functionality is stubbed and shimmed as needed in tools/testing/vma/ which contains a fully functional userland vma_internal.h file and which imports mm/vma.c and mm/vma.h to be directly tested from userland. A simple, skeleton testing implementation is provided in tools/testing/vma/vma.c as a proof-of-concept, asserting that simple VMA merge, modify (testing split), expand and shrink functionality work correctly. This patch (of 4): This patch forms part of a patch series intending to separate out VMA logic and render it testable from userspace, which requires that core manipulation functions be exposed in an mm/-internal header file. In order to do this, we must abstract APIs we wish to test, in this instance functions which ultimately invoke vma_modify(). This patch therefore moves all logic which ultimately invokes vma_modify() to mm/userfaultfd.c, trying to transfer code at a functional granularity where possible. [lorenzo.stoakes@oracle.com: fix user-after-free in userfaultfd_clear_vma()] Link: https://lkml.kernel.org/r/3c947ddc-b804-49b7-8fe9-3ea3ca13def5@lucifer.local Link: https://lkml.kernel.org/r/cover.1722251717.git.lorenzo.stoakes@oracle.com Link: https://lkml.kernel.org/r/50c3ed995fd81c45876c86304c8a00bf3e396cfd.1722251717.git.lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes Reviewed-by: Vlastimil Babka Reviewed-by: Liam R. Howlett Cc: Alexander Viro Cc: Brendan Higgins Cc: Christian Brauner Cc: David Gow Cc: Eric W. Biederman Cc: Jan Kara Cc: Kees Cook Cc: Matthew Wilcox (Oracle) Cc: Rae Moar Cc: SeongJae Park Cc: Shuah Khan Cc: Suren Baghdasaryan Cc: Pengfei Xu Signed-off-by: Andrew Morton --- fs/userfaultfd.c | 160 +++------------------------------------- include/linux/userfaultfd_k.h | 19 +++++ mm/userfaultfd.c | 168 ++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 198 insertions(+), 149 deletions(-) (limited to 'include/linux') diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 27a3e9285fbf..b3ed7207df7e 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -104,21 +104,6 @@ bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma) return ctx->features & UFFD_FEATURE_WP_UNPOPULATED; } -static void userfaultfd_set_vm_flags(struct vm_area_struct *vma, - vm_flags_t flags) -{ - const bool uffd_wp_changed = (vma->vm_flags ^ flags) & VM_UFFD_WP; - - vm_flags_reset(vma, flags); - /* - * For shared mappings, we want to enable writenotify while - * userfaultfd-wp is enabled (see vma_wants_writenotify()). We'll simply - * recalculate vma->vm_page_prot whenever userfaultfd-wp changes. - */ - if ((vma->vm_flags & VM_SHARED) && uffd_wp_changed) - vma_set_page_prot(vma); -} - static int userfaultfd_wake_function(wait_queue_entry_t *wq, unsigned mode, int wake_flags, void *key) { @@ -615,22 +600,7 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, spin_unlock_irq(&ctx->event_wqh.lock); if (release_new_ctx) { - struct vm_area_struct *vma; - struct mm_struct *mm = release_new_ctx->mm; - VMA_ITERATOR(vmi, mm, 0); - - /* the various vma->vm_userfaultfd_ctx still points to it */ - mmap_write_lock(mm); - for_each_vma(vmi, vma) { - if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) { - vma_start_write(vma); - vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; - userfaultfd_set_vm_flags(vma, - vma->vm_flags & ~__VM_UFFD_FLAGS); - } - } - mmap_write_unlock(mm); - + userfaultfd_release_new(release_new_ctx); userfaultfd_ctx_put(release_new_ctx); } @@ -662,9 +632,7 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs) return 0; if (!(octx->features & UFFD_FEATURE_EVENT_FORK)) { - vma_start_write(vma); - vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; - userfaultfd_set_vm_flags(vma, vma->vm_flags & ~__VM_UFFD_FLAGS); + userfaultfd_reset_ctx(vma); return 0; } @@ -749,9 +717,7 @@ void mremap_userfaultfd_prep(struct vm_area_struct *vma, up_write(&ctx->map_changing_lock); } else { /* Drop uffd context if remap feature not enabled */ - vma_start_write(vma); - vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; - userfaultfd_set_vm_flags(vma, vma->vm_flags & ~__VM_UFFD_FLAGS); + userfaultfd_reset_ctx(vma); } } @@ -870,53 +836,13 @@ static int userfaultfd_release(struct inode *inode, struct file *file) { struct userfaultfd_ctx *ctx = file->private_data; struct mm_struct *mm = ctx->mm; - struct vm_area_struct *vma, *prev; /* len == 0 means wake all */ struct userfaultfd_wake_range range = { .len = 0, }; - unsigned long new_flags; - VMA_ITERATOR(vmi, mm, 0); WRITE_ONCE(ctx->released, true); - if (!mmget_not_zero(mm)) - goto wakeup; - - /* - * Flush page faults out of all CPUs. NOTE: all page faults - * must be retried without returning VM_FAULT_SIGBUS if - * userfaultfd_ctx_get() succeeds but vma->vma_userfault_ctx - * changes while handle_userfault released the mmap_lock. So - * it's critical that released is set to true (above), before - * taking the mmap_lock for writing. - */ - mmap_write_lock(mm); - prev = NULL; - for_each_vma(vmi, vma) { - cond_resched(); - BUG_ON(!!vma->vm_userfaultfd_ctx.ctx ^ - !!(vma->vm_flags & __VM_UFFD_FLAGS)); - if (vma->vm_userfaultfd_ctx.ctx != ctx) { - prev = vma; - continue; - } - /* Reset ptes for the whole vma range if wr-protected */ - if (userfaultfd_wp(vma)) - uffd_wp_range(vma, vma->vm_start, - vma->vm_end - vma->vm_start, false); - new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS; - vma = vma_modify_flags_uffd(&vmi, prev, vma, vma->vm_start, - vma->vm_end, new_flags, - NULL_VM_UFFD_CTX); - - vma_start_write(vma); - userfaultfd_set_vm_flags(vma, new_flags); - vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; + userfaultfd_release_all(mm, ctx); - prev = vma; - } - mmap_write_unlock(mm); - mmput(mm); -wakeup: /* * After no new page faults can wait on this fault_*wqh, flush * the last page faults that may have been already waiting on @@ -1293,14 +1219,14 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, unsigned long arg) { struct mm_struct *mm = ctx->mm; - struct vm_area_struct *vma, *prev, *cur; + struct vm_area_struct *vma, *cur; int ret; struct uffdio_register uffdio_register; struct uffdio_register __user *user_uffdio_register; - unsigned long vm_flags, new_flags; + unsigned long vm_flags; bool found; bool basic_ioctls; - unsigned long start, end, vma_end; + unsigned long start, end; struct vma_iterator vmi; bool wp_async = userfaultfd_wp_async_ctx(ctx); @@ -1428,57 +1354,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, } for_each_vma_range(vmi, cur, end); BUG_ON(!found); - vma_iter_set(&vmi, start); - prev = vma_prev(&vmi); - if (vma->vm_start < start) - prev = vma; - - ret = 0; - for_each_vma_range(vmi, vma, end) { - cond_resched(); - - BUG_ON(!vma_can_userfault(vma, vm_flags, wp_async)); - BUG_ON(vma->vm_userfaultfd_ctx.ctx && - vma->vm_userfaultfd_ctx.ctx != ctx); - WARN_ON(!(vma->vm_flags & VM_MAYWRITE)); - - /* - * Nothing to do: this vma is already registered into this - * userfaultfd and with the right tracking mode too. - */ - if (vma->vm_userfaultfd_ctx.ctx == ctx && - (vma->vm_flags & vm_flags) == vm_flags) - goto skip; - - if (vma->vm_start > start) - start = vma->vm_start; - vma_end = min(end, vma->vm_end); - - new_flags = (vma->vm_flags & ~__VM_UFFD_FLAGS) | vm_flags; - vma = vma_modify_flags_uffd(&vmi, prev, vma, start, vma_end, - new_flags, - (struct vm_userfaultfd_ctx){ctx}); - if (IS_ERR(vma)) { - ret = PTR_ERR(vma); - break; - } - - /* - * In the vma_merge() successful mprotect-like case 8: - * the next vma was merged into the current one and - * the current one has not been updated yet. - */ - vma_start_write(vma); - userfaultfd_set_vm_flags(vma, new_flags); - vma->vm_userfaultfd_ctx.ctx = ctx; - - if (is_vm_hugetlb_page(vma) && uffd_disable_huge_pmd_share(vma)) - hugetlb_unshare_all_pmds(vma); - - skip: - prev = vma; - start = vma->vm_end; - } + ret = userfaultfd_register_range(ctx, vma, vm_flags, start, end, + wp_async); out_unlock: mmap_write_unlock(mm); @@ -1519,7 +1396,6 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, struct vm_area_struct *vma, *prev, *cur; int ret; struct uffdio_range uffdio_unregister; - unsigned long new_flags; bool found; unsigned long start, end, vma_end; const void __user *buf = (void __user *)arg; @@ -1622,27 +1498,13 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, wake_userfault(vma->vm_userfaultfd_ctx.ctx, &range); } - /* Reset ptes for the whole vma range if wr-protected */ - if (userfaultfd_wp(vma)) - uffd_wp_range(vma, start, vma_end - start, false); - - new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS; - vma = vma_modify_flags_uffd(&vmi, prev, vma, start, vma_end, - new_flags, NULL_VM_UFFD_CTX); + vma = userfaultfd_clear_vma(&vmi, prev, vma, + start, vma_end); if (IS_ERR(vma)) { ret = PTR_ERR(vma); break; } - /* - * In the vma_merge() successful mprotect-like case 8: - * the next vma was merged into the current one and - * the current one has not been updated yet. - */ - vma_start_write(vma); - userfaultfd_set_vm_flags(vma, new_flags); - vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; - skip: prev = vma; start = vma->vm_end; diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index a12bcf042551..9fc6ce15c499 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -267,6 +267,25 @@ extern void userfaultfd_unmap_complete(struct mm_struct *mm, extern bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma); extern bool userfaultfd_wp_async(struct vm_area_struct *vma); +void userfaultfd_reset_ctx(struct vm_area_struct *vma); + +struct vm_area_struct *userfaultfd_clear_vma(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, + unsigned long end); + +int userfaultfd_register_range(struct userfaultfd_ctx *ctx, + struct vm_area_struct *vma, + unsigned long vm_flags, + unsigned long start, unsigned long end, + bool wp_async); + +void userfaultfd_release_new(struct userfaultfd_ctx *ctx); + +void userfaultfd_release_all(struct mm_struct *mm, + struct userfaultfd_ctx *ctx); + #else /* CONFIG_USERFAULTFD */ /* mm helpers */ diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index e54e5c8907fa..966e6c81a685 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -1760,3 +1760,171 @@ out: VM_WARN_ON(!moved && !err); return moved ? moved : err; } + +static void userfaultfd_set_vm_flags(struct vm_area_struct *vma, + vm_flags_t flags) +{ + const bool uffd_wp_changed = (vma->vm_flags ^ flags) & VM_UFFD_WP; + + vm_flags_reset(vma, flags); + /* + * For shared mappings, we want to enable writenotify while + * userfaultfd-wp is enabled (see vma_wants_writenotify()). We'll simply + * recalculate vma->vm_page_prot whenever userfaultfd-wp changes. + */ + if ((vma->vm_flags & VM_SHARED) && uffd_wp_changed) + vma_set_page_prot(vma); +} + +static void userfaultfd_set_ctx(struct vm_area_struct *vma, + struct userfaultfd_ctx *ctx, + unsigned long flags) +{ + vma_start_write(vma); + vma->vm_userfaultfd_ctx = (struct vm_userfaultfd_ctx){ctx}; + userfaultfd_set_vm_flags(vma, + (vma->vm_flags & ~__VM_UFFD_FLAGS) | flags); +} + +void userfaultfd_reset_ctx(struct vm_area_struct *vma) +{ + userfaultfd_set_ctx(vma, NULL, 0); +} + +struct vm_area_struct *userfaultfd_clear_vma(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, + unsigned long end) +{ + struct vm_area_struct *ret; + + /* Reset ptes for the whole vma range if wr-protected */ + if (userfaultfd_wp(vma)) + uffd_wp_range(vma, start, end - start, false); + + ret = vma_modify_flags_uffd(vmi, prev, vma, start, end, + vma->vm_flags & ~__VM_UFFD_FLAGS, + NULL_VM_UFFD_CTX); + + /* + * In the vma_merge() successful mprotect-like case 8: + * the next vma was merged into the current one and + * the current one has not been updated yet. + */ + if (!IS_ERR(ret)) + userfaultfd_reset_ctx(ret); + + return ret; +} + +/* Assumes mmap write lock taken, and mm_struct pinned. */ +int userfaultfd_register_range(struct userfaultfd_ctx *ctx, + struct vm_area_struct *vma, + unsigned long vm_flags, + unsigned long start, unsigned long end, + bool wp_async) +{ + VMA_ITERATOR(vmi, ctx->mm, start); + struct vm_area_struct *prev = vma_prev(&vmi); + unsigned long vma_end; + unsigned long new_flags; + + if (vma->vm_start < start) + prev = vma; + + for_each_vma_range(vmi, vma, end) { + cond_resched(); + + BUG_ON(!vma_can_userfault(vma, vm_flags, wp_async)); + BUG_ON(vma->vm_userfaultfd_ctx.ctx && + vma->vm_userfaultfd_ctx.ctx != ctx); + WARN_ON(!(vma->vm_flags & VM_MAYWRITE)); + + /* + * Nothing to do: this vma is already registered into this + * userfaultfd and with the right tracking mode too. + */ + if (vma->vm_userfaultfd_ctx.ctx == ctx && + (vma->vm_flags & vm_flags) == vm_flags) + goto skip; + + if (vma->vm_start > start) + start = vma->vm_start; + vma_end = min(end, vma->vm_end); + + new_flags = (vma->vm_flags & ~__VM_UFFD_FLAGS) | vm_flags; + vma = vma_modify_flags_uffd(&vmi, prev, vma, start, vma_end, + new_flags, + (struct vm_userfaultfd_ctx){ctx}); + if (IS_ERR(vma)) + return PTR_ERR(vma); + + /* + * In the vma_merge() successful mprotect-like case 8: + * the next vma was merged into the current one and + * the current one has not been updated yet. + */ + userfaultfd_set_ctx(vma, ctx, vm_flags); + + if (is_vm_hugetlb_page(vma) && uffd_disable_huge_pmd_share(vma)) + hugetlb_unshare_all_pmds(vma); + +skip: + prev = vma; + start = vma->vm_end; + } + + return 0; +} + +void userfaultfd_release_new(struct userfaultfd_ctx *ctx) +{ + struct mm_struct *mm = ctx->mm; + struct vm_area_struct *vma; + VMA_ITERATOR(vmi, mm, 0); + + /* the various vma->vm_userfaultfd_ctx still points to it */ + mmap_write_lock(mm); + for_each_vma(vmi, vma) { + if (vma->vm_userfaultfd_ctx.ctx == ctx) + userfaultfd_reset_ctx(vma); + } + mmap_write_unlock(mm); +} + +void userfaultfd_release_all(struct mm_struct *mm, + struct userfaultfd_ctx *ctx) +{ + struct vm_area_struct *vma, *prev; + VMA_ITERATOR(vmi, mm, 0); + + if (!mmget_not_zero(mm)) + return; + + /* + * Flush page faults out of all CPUs. NOTE: all page faults + * must be retried without returning VM_FAULT_SIGBUS if + * userfaultfd_ctx_get() succeeds but vma->vma_userfault_ctx + * changes while handle_userfault released the mmap_lock. So + * it's critical that released is set to true (above), before + * taking the mmap_lock for writing. + */ + mmap_write_lock(mm); + prev = NULL; + for_each_vma(vmi, vma) { + cond_resched(); + BUG_ON(!!vma->vm_userfaultfd_ctx.ctx ^ + !!(vma->vm_flags & __VM_UFFD_FLAGS)); + if (vma->vm_userfaultfd_ctx.ctx != ctx) { + prev = vma; + continue; + } + + vma = userfaultfd_clear_vma(&vmi, prev, vma, + vma->vm_start, vma->vm_end); + prev = vma; + } + mmap_write_unlock(mm); + mmput(mm); +} -- cgit v1.2.3 From fa04c08f3ce649b47781c7663e92398197f5b551 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Mon, 29 Jul 2024 12:50:36 +0100 Subject: mm: move vma_modify() and helpers to internal header These are core VMA manipulation functions which invoke VMA splitting and merging and should not be directly accessed from outside of mm/. Link: https://lkml.kernel.org/r/5efde0c6342a8860d5ffc90b415f3989fd8ed0b2.1722251717.git.lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes Reviewed-by: Vlastimil Babka Reviewed-by: Liam R. Howlett Cc: Alexander Viro Cc: Brendan Higgins Cc: Christian Brauner Cc: David Gow Cc: Eric W. Biederman Cc: Jan Kara Cc: Kees Cook Cc: Matthew Wilcox (Oracle) Cc: Rae Moar Cc: SeongJae Park Cc: Shuah Khan Cc: Suren Baghdasaryan Cc: Pengfei Xu Signed-off-by: Andrew Morton --- include/linux/mm.h | 60 ----------------------------------------------------- mm/internal.h | 61 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 61 insertions(+), 60 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 153a4662a0cd..c4054e68dc09 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3279,66 +3279,6 @@ extern struct vm_area_struct *copy_vma(struct vm_area_struct **, unsigned long addr, unsigned long len, pgoff_t pgoff, bool *need_rmap_locks); extern void exit_mmap(struct mm_struct *); -struct vm_area_struct *vma_modify(struct vma_iterator *vmi, - struct vm_area_struct *prev, - struct vm_area_struct *vma, - unsigned long start, unsigned long end, - unsigned long vm_flags, - struct mempolicy *policy, - struct vm_userfaultfd_ctx uffd_ctx, - struct anon_vma_name *anon_name); - -/* We are about to modify the VMA's flags. */ -static inline struct vm_area_struct -*vma_modify_flags(struct vma_iterator *vmi, - struct vm_area_struct *prev, - struct vm_area_struct *vma, - unsigned long start, unsigned long end, - unsigned long new_flags) -{ - return vma_modify(vmi, prev, vma, start, end, new_flags, - vma_policy(vma), vma->vm_userfaultfd_ctx, - anon_vma_name(vma)); -} - -/* We are about to modify the VMA's flags and/or anon_name. */ -static inline struct vm_area_struct -*vma_modify_flags_name(struct vma_iterator *vmi, - struct vm_area_struct *prev, - struct vm_area_struct *vma, - unsigned long start, - unsigned long end, - unsigned long new_flags, - struct anon_vma_name *new_name) -{ - return vma_modify(vmi, prev, vma, start, end, new_flags, - vma_policy(vma), vma->vm_userfaultfd_ctx, new_name); -} - -/* We are about to modify the VMA's memory policy. */ -static inline struct vm_area_struct -*vma_modify_policy(struct vma_iterator *vmi, - struct vm_area_struct *prev, - struct vm_area_struct *vma, - unsigned long start, unsigned long end, - struct mempolicy *new_pol) -{ - return vma_modify(vmi, prev, vma, start, end, vma->vm_flags, - new_pol, vma->vm_userfaultfd_ctx, anon_vma_name(vma)); -} - -/* We are about to modify the VMA's flags and/or uffd context. */ -static inline struct vm_area_struct -*vma_modify_flags_uffd(struct vma_iterator *vmi, - struct vm_area_struct *prev, - struct vm_area_struct *vma, - unsigned long start, unsigned long end, - unsigned long new_flags, - struct vm_userfaultfd_ctx new_ctx) -{ - return vma_modify(vmi, prev, vma, start, end, new_flags, - vma_policy(vma), new_ctx, anon_vma_name(vma)); -} static inline int check_data_rlimit(unsigned long rlim, unsigned long new, diff --git a/mm/internal.h b/mm/internal.h index b4d86436565b..81564ce0f9e2 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -1244,6 +1244,67 @@ struct vm_area_struct *vma_merge_extend(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long delta); +struct vm_area_struct *vma_modify(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, unsigned long end, + unsigned long vm_flags, + struct mempolicy *policy, + struct vm_userfaultfd_ctx uffd_ctx, + struct anon_vma_name *anon_name); + +/* We are about to modify the VMA's flags. */ +static inline struct vm_area_struct +*vma_modify_flags(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, unsigned long end, + unsigned long new_flags) +{ + return vma_modify(vmi, prev, vma, start, end, new_flags, + vma_policy(vma), vma->vm_userfaultfd_ctx, + anon_vma_name(vma)); +} + +/* We are about to modify the VMA's flags and/or anon_name. */ +static inline struct vm_area_struct +*vma_modify_flags_name(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, + unsigned long end, + unsigned long new_flags, + struct anon_vma_name *new_name) +{ + return vma_modify(vmi, prev, vma, start, end, new_flags, + vma_policy(vma), vma->vm_userfaultfd_ctx, new_name); +} + +/* We are about to modify the VMA's memory policy. */ +static inline struct vm_area_struct +*vma_modify_policy(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, unsigned long end, + struct mempolicy *new_pol) +{ + return vma_modify(vmi, prev, vma, start, end, vma->vm_flags, + new_pol, vma->vm_userfaultfd_ctx, anon_vma_name(vma)); +} + +/* We are about to modify the VMA's flags and/or uffd context. */ +static inline struct vm_area_struct +*vma_modify_flags_uffd(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, unsigned long end, + unsigned long new_flags, + struct vm_userfaultfd_ctx new_ctx) +{ + return vma_modify(vmi, prev, vma, start, end, new_flags, + vma_policy(vma), new_ctx, anon_vma_name(vma)); +} + enum { /* mark page accessed */ FOLL_TOUCH = 1 << 16, -- cgit v1.2.3 From d61f0d59683d9c899211c300254d4140c482a6c0 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Mon, 29 Jul 2024 12:50:37 +0100 Subject: mm: move vma_shrink(), vma_expand() to internal header The vma_shrink() and vma_expand() functions are internal VMA manipulation functions which we ought to abstract for use outside of memory management code. To achieve this, we replace shift_arg_pages() in fs/exec.c with an invocation of a new relocate_vma_down() function implemented in mm/mmap.c, which enables us to also move move_page_tables() and vma_iter_prev_range() to internal.h. The purpose of doing this is to isolate key VMA manipulation functions in order that we can both abstract them and later render them easily testable. Link: https://lkml.kernel.org/r/3cfcd9ec433e032a85f636fdc0d7d98fafbd19c5.1722251717.git.lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes Reviewed-by: Vlastimil Babka Reviewed-by: Liam R. Howlett Cc: Alexander Viro Cc: Brendan Higgins Cc: Christian Brauner Cc: David Gow Cc: Eric W. Biederman Cc: Jan Kara Cc: Kees Cook Cc: Matthew Wilcox (Oracle) Cc: Rae Moar Cc: SeongJae Park Cc: Shuah Khan Cc: Suren Baghdasaryan Cc: Pengfei Xu Signed-off-by: Andrew Morton --- fs/exec.c | 81 ++++-------------------------------------------------- include/linux/mm.h | 17 +----------- mm/internal.h | 18 ++++++++++++ mm/mmap.c | 81 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 106 insertions(+), 91 deletions(-) (limited to 'include/linux') diff --git a/fs/exec.c b/fs/exec.c index 50e76cc633c4..9009e2b2805e 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -711,80 +711,6 @@ static int copy_strings_kernel(int argc, const char *const *argv, #ifdef CONFIG_MMU -/* - * During bprm_mm_init(), we create a temporary stack at STACK_TOP_MAX. Once - * the binfmt code determines where the new stack should reside, we shift it to - * its final location. The process proceeds as follows: - * - * 1) Use shift to calculate the new vma endpoints. - * 2) Extend vma to cover both the old and new ranges. This ensures the - * arguments passed to subsequent functions are consistent. - * 3) Move vma's page tables to the new range. - * 4) Free up any cleared pgd range. - * 5) Shrink the vma to cover only the new range. - */ -static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) -{ - struct mm_struct *mm = vma->vm_mm; - unsigned long old_start = vma->vm_start; - unsigned long old_end = vma->vm_end; - unsigned long length = old_end - old_start; - unsigned long new_start = old_start - shift; - unsigned long new_end = old_end - shift; - VMA_ITERATOR(vmi, mm, new_start); - struct vm_area_struct *next; - struct mmu_gather tlb; - - BUG_ON(new_start > new_end); - - /* - * ensure there are no vmas between where we want to go - * and where we are - */ - if (vma != vma_next(&vmi)) - return -EFAULT; - - vma_iter_prev_range(&vmi); - /* - * cover the whole range: [new_start, old_end) - */ - if (vma_expand(&vmi, vma, new_start, old_end, vma->vm_pgoff, NULL)) - return -ENOMEM; - - /* - * move the page tables downwards, on failure we rely on - * process cleanup to remove whatever mess we made. - */ - if (length != move_page_tables(vma, old_start, - vma, new_start, length, false, true)) - return -ENOMEM; - - lru_add_drain(); - tlb_gather_mmu(&tlb, mm); - next = vma_next(&vmi); - if (new_end > old_start) { - /* - * when the old and new regions overlap clear from new_end. - */ - free_pgd_range(&tlb, new_end, old_end, new_end, - next ? next->vm_start : USER_PGTABLES_CEILING); - } else { - /* - * otherwise, clean from old_start; this is done to not touch - * the address space in [new_end, old_start) some architectures - * have constraints on va-space that make this illegal (IA64) - - * for the others its just a little faster. - */ - free_pgd_range(&tlb, old_start, old_end, new_end, - next ? next->vm_start : USER_PGTABLES_CEILING); - } - tlb_finish_mmu(&tlb); - - vma_prev(&vmi); - /* Shrink the vma to just the new range */ - return vma_shrink(&vmi, vma, new_start, new_end, vma->vm_pgoff); -} - /* * Finalizes the stack vm_area_struct. The flags and permissions are updated, * the stack is optionally relocated, and some extra space is added. @@ -877,7 +803,12 @@ int setup_arg_pages(struct linux_binprm *bprm, /* Move stack pages down in memory. */ if (stack_shift) { - ret = shift_arg_pages(vma, stack_shift); + /* + * During bprm_mm_init(), we create a temporary stack at STACK_TOP_MAX. Once + * the binfmt code determines where the new stack should reside, we shift it to + * its final location. + */ + ret = relocate_vma_down(vma, stack_shift); if (ret) goto out_unlock; } diff --git a/include/linux/mm.h b/include/linux/mm.h index c4054e68dc09..1c0d88446eb8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1005,12 +1005,6 @@ static inline struct vm_area_struct *vma_prev(struct vma_iterator *vmi) return mas_prev(&vmi->mas, 0); } -static inline -struct vm_area_struct *vma_iter_prev_range(struct vma_iterator *vmi) -{ - return mas_prev_range(&vmi->mas, 0); -} - static inline unsigned long vma_iter_addr(struct vma_iterator *vmi) { return vmi->mas.index; @@ -2520,11 +2514,6 @@ int set_page_dirty_lock(struct page *page); int get_cmdline(struct task_struct *task, char *buffer, int buflen); -extern unsigned long move_page_tables(struct vm_area_struct *vma, - unsigned long old_addr, struct vm_area_struct *new_vma, - unsigned long new_addr, unsigned long len, - bool need_rmap_locks, bool for_stack); - /* * Flags used by change_protection(). For now we make it a bitmap so * that we can pass in multiple flags just like parameters. However @@ -3267,11 +3256,6 @@ void anon_vma_interval_tree_verify(struct anon_vma_chain *node); /* mmap.c */ extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin); -extern int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma, - unsigned long start, unsigned long end, pgoff_t pgoff, - struct vm_area_struct *next); -extern int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma, - unsigned long start, unsigned long end, pgoff_t pgoff); extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *); extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *); extern void unlink_file_vma(struct vm_area_struct *); @@ -3279,6 +3263,7 @@ extern struct vm_area_struct *copy_vma(struct vm_area_struct **, unsigned long addr, unsigned long len, pgoff_t pgoff, bool *need_rmap_locks); extern void exit_mmap(struct mm_struct *); +int relocate_vma_down(struct vm_area_struct *vma, unsigned long shift); static inline int check_data_rlimit(unsigned long rlim, unsigned long new, diff --git a/mm/internal.h b/mm/internal.h index 81564ce0f9e2..a4d0e98ccb97 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -1305,6 +1305,12 @@ static inline struct vm_area_struct vma_policy(vma), new_ctx, anon_vma_name(vma)); } +int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma, + unsigned long start, unsigned long end, pgoff_t pgoff, + struct vm_area_struct *next); +int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma, + unsigned long start, unsigned long end, pgoff_t pgoff); + enum { /* mark page accessed */ FOLL_TOUCH = 1 << 16, @@ -1528,6 +1534,12 @@ static inline int vma_iter_store_gfp(struct vma_iterator *vmi, return 0; } +static inline +struct vm_area_struct *vma_iter_prev_range(struct vma_iterator *vmi) +{ + return mas_prev_range(&vmi->mas, 0); +} + /* * VMA lock generalization */ @@ -1639,4 +1651,10 @@ void unlink_file_vma_batch_init(struct unlink_vma_file_batch *); void unlink_file_vma_batch_add(struct unlink_vma_file_batch *, struct vm_area_struct *); void unlink_file_vma_batch_final(struct unlink_vma_file_batch *); +/* mremap.c */ +unsigned long move_page_tables(struct vm_area_struct *vma, + unsigned long old_addr, struct vm_area_struct *new_vma, + unsigned long new_addr, unsigned long len, + bool need_rmap_locks, bool for_stack); + #endif /* __MM_INTERNAL_H */ diff --git a/mm/mmap.c b/mm/mmap.c index d0dfc85b209b..211148ba2831 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -4088,3 +4088,84 @@ static int __meminit init_reserve_notifier(void) return 0; } subsys_initcall(init_reserve_notifier); + +/* + * Relocate a VMA downwards by shift bytes. There cannot be any VMAs between + * this VMA and its relocated range, which will now reside at [vma->vm_start - + * shift, vma->vm_end - shift). + * + * This function is almost certainly NOT what you want for anything other than + * early executable temporary stack relocation. + */ +int relocate_vma_down(struct vm_area_struct *vma, unsigned long shift) +{ + /* + * The process proceeds as follows: + * + * 1) Use shift to calculate the new vma endpoints. + * 2) Extend vma to cover both the old and new ranges. This ensures the + * arguments passed to subsequent functions are consistent. + * 3) Move vma's page tables to the new range. + * 4) Free up any cleared pgd range. + * 5) Shrink the vma to cover only the new range. + */ + + struct mm_struct *mm = vma->vm_mm; + unsigned long old_start = vma->vm_start; + unsigned long old_end = vma->vm_end; + unsigned long length = old_end - old_start; + unsigned long new_start = old_start - shift; + unsigned long new_end = old_end - shift; + VMA_ITERATOR(vmi, mm, new_start); + struct vm_area_struct *next; + struct mmu_gather tlb; + + BUG_ON(new_start > new_end); + + /* + * ensure there are no vmas between where we want to go + * and where we are + */ + if (vma != vma_next(&vmi)) + return -EFAULT; + + vma_iter_prev_range(&vmi); + /* + * cover the whole range: [new_start, old_end) + */ + if (vma_expand(&vmi, vma, new_start, old_end, vma->vm_pgoff, NULL)) + return -ENOMEM; + + /* + * move the page tables downwards, on failure we rely on + * process cleanup to remove whatever mess we made. + */ + if (length != move_page_tables(vma, old_start, + vma, new_start, length, false, true)) + return -ENOMEM; + + lru_add_drain(); + tlb_gather_mmu(&tlb, mm); + next = vma_next(&vmi); + if (new_end > old_start) { + /* + * when the old and new regions overlap clear from new_end. + */ + free_pgd_range(&tlb, new_end, old_end, new_end, + next ? next->vm_start : USER_PGTABLES_CEILING); + } else { + /* + * otherwise, clean from old_start; this is done to not touch + * the address space in [new_end, old_start) some architectures + * have constraints on va-space that make this illegal (IA64) - + * for the others its just a little faster. + */ + free_pgd_range(&tlb, old_start, old_end, new_end, + next ? next->vm_start : USER_PGTABLES_CEILING); + } + tlb_finish_mmu(&tlb); + + vma_prev(&vmi); + /* Shrink the vma to just the new range */ + return vma_shrink(&vmi, vma, new_start, new_end, vma->vm_pgoff); +} -- cgit v1.2.3 From 49b1b8d6f6831026cb105b0eafa18f13db612d86 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Mon, 29 Jul 2024 12:50:38 +0100 Subject: mm: move internal core VMA manipulation functions to own file This patch introduces vma.c and moves internal core VMA manipulation functions to this file from mmap.c. This allows us to isolate VMA functionality in a single place such that we can create userspace testing code that invokes this functionality in an environment where we can implement simple unit tests of core functionality. This patch ensures that core VMA functionality is explicitly marked as such by its presence in mm/vma.h. It also places the header includes required by vma.c in vma_internal.h, which is simply imported by vma.c. This makes the VMA functionality testable, as userland testing code can simply stub out functionality as required. Link: https://lkml.kernel.org/r/c77a6aafb4c42aaadb8e7271a853658cbdca2e22.1722251717.git.lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes Reviewed-by: Vlastimil Babka Reviewed-by: Liam R. Howlett Cc: Alexander Viro Cc: Brendan Higgins Cc: Christian Brauner Cc: David Gow Cc: Eric W. Biederman Cc: Jan Kara Cc: Kees Cook Cc: Matthew Wilcox (Oracle) Cc: Rae Moar Cc: SeongJae Park Cc: Shuah Khan Cc: Suren Baghdasaryan Cc: Pengfei Xu Signed-off-by: Andrew Morton --- include/linux/mm.h | 35 - mm/Makefile | 2 +- mm/internal.h | 236 +------ mm/mmap.c | 1980 +++------------------------------------------------- mm/mmu_notifier.c | 2 + mm/vma.c | 1766 ++++++++++++++++++++++++++++++++++++++++++++++ mm/vma.h | 364 ++++++++++ mm/vma_internal.h | 50 ++ 8 files changed, 2292 insertions(+), 2143 deletions(-) create mode 100644 mm/vma.c create mode 100644 mm/vma.h create mode 100644 mm/vma_internal.h (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1c0d88446eb8..bd219ac9c026 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1005,21 +1005,6 @@ static inline struct vm_area_struct *vma_prev(struct vma_iterator *vmi) return mas_prev(&vmi->mas, 0); } -static inline unsigned long vma_iter_addr(struct vma_iterator *vmi) -{ - return vmi->mas.index; -} - -static inline unsigned long vma_iter_end(struct vma_iterator *vmi) -{ - return vmi->mas.last + 1; -} -static inline int vma_iter_bulk_alloc(struct vma_iterator *vmi, - unsigned long count) -{ - return mas_expected_entries(&vmi->mas, count); -} - static inline int vma_iter_clear_gfp(struct vma_iterator *vmi, unsigned long start, unsigned long end, gfp_t gfp) { @@ -2534,21 +2519,6 @@ int get_cmdline(struct task_struct *task, char *buffer, int buflen); #define MM_CP_UFFD_WP_ALL (MM_CP_UFFD_WP | \ MM_CP_UFFD_WP_RESOLVE) -bool vma_needs_dirty_tracking(struct vm_area_struct *vma); -bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot); -static inline bool vma_wants_manual_pte_write_upgrade(struct vm_area_struct *vma) -{ - /* - * We want to check manually if we can change individual PTEs writable - * if we can't do that automatically for all PTEs in a mapping. For - * private mappings, that's always the case when we have write - * permissions as we properly have to handle COW. - */ - if (vma->vm_flags & VM_SHARED) - return vma_wants_writenotify(vma, vma->vm_page_prot); - return !!(vma->vm_flags & VM_WRITE); - -} bool can_change_pte_writable(struct vm_area_struct *vma, unsigned long addr, pte_t pte); extern long change_protection(struct mmu_gather *tlb, @@ -3256,12 +3226,7 @@ void anon_vma_interval_tree_verify(struct anon_vma_chain *node); /* mmap.c */ extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin); -extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *); extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *); -extern void unlink_file_vma(struct vm_area_struct *); -extern struct vm_area_struct *copy_vma(struct vm_area_struct **, - unsigned long addr, unsigned long len, pgoff_t pgoff, - bool *need_rmap_locks); extern void exit_mmap(struct mm_struct *); int relocate_vma_down(struct vm_area_struct *vma, unsigned long shift); diff --git a/mm/Makefile b/mm/Makefile index b11fefbc13bc..24b918260c7f 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -37,7 +37,7 @@ mmu-y := nommu.o mmu-$(CONFIG_MMU) := highmem.o memory.o mincore.o \ mlock.o mmap.o mmu_gather.o mprotect.o mremap.o \ msync.o page_vma_mapped.o pagewalk.o \ - pgtable-generic.o rmap.o vmalloc.o + pgtable-generic.o rmap.o vmalloc.o vma.o ifdef CONFIG_CROSS_MEMORY_ATTACH diff --git a/mm/internal.h b/mm/internal.h index a4d0e98ccb97..1159b04e76a3 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -8,13 +8,18 @@ #define __MM_INTERNAL_H #include +#include #include +#include #include #include #include #include #include +/* Internal core VMA manipulation functions. */ +#include "vma.h" + struct folio_batch; /* @@ -778,37 +783,6 @@ static inline bool free_area_empty(struct free_area *area, int migratetype) return list_empty(&area->free_list[migratetype]); } -/* - * These three helpers classifies VMAs for virtual memory accounting. - */ - -/* - * Executable code area - executable, not writable, not stack - */ -static inline bool is_exec_mapping(vm_flags_t flags) -{ - return (flags & (VM_EXEC | VM_WRITE | VM_STACK)) == VM_EXEC; -} - -/* - * Stack area (including shadow stacks) - * - * VM_GROWSUP / VM_GROWSDOWN VMAs are always private anonymous: - * do_mmap() forbids all other combinations. - */ -static inline bool is_stack_mapping(vm_flags_t flags) -{ - return ((flags & VM_STACK) == VM_STACK) || (flags & VM_SHADOW_STACK); -} - -/* - * Data area - private, writable, not stack - */ -static inline bool is_data_mapping(vm_flags_t flags) -{ - return (flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE; -} - /* mm/util.c */ struct anon_vma *folio_anon_vma(struct folio *folio); @@ -1237,80 +1211,6 @@ void touch_pud(struct vm_area_struct *vma, unsigned long addr, void touch_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, bool write); -/* - * mm/mmap.c - */ -struct vm_area_struct *vma_merge_extend(struct vma_iterator *vmi, - struct vm_area_struct *vma, - unsigned long delta); - -struct vm_area_struct *vma_modify(struct vma_iterator *vmi, - struct vm_area_struct *prev, - struct vm_area_struct *vma, - unsigned long start, unsigned long end, - unsigned long vm_flags, - struct mempolicy *policy, - struct vm_userfaultfd_ctx uffd_ctx, - struct anon_vma_name *anon_name); - -/* We are about to modify the VMA's flags. */ -static inline struct vm_area_struct -*vma_modify_flags(struct vma_iterator *vmi, - struct vm_area_struct *prev, - struct vm_area_struct *vma, - unsigned long start, unsigned long end, - unsigned long new_flags) -{ - return vma_modify(vmi, prev, vma, start, end, new_flags, - vma_policy(vma), vma->vm_userfaultfd_ctx, - anon_vma_name(vma)); -} - -/* We are about to modify the VMA's flags and/or anon_name. */ -static inline struct vm_area_struct -*vma_modify_flags_name(struct vma_iterator *vmi, - struct vm_area_struct *prev, - struct vm_area_struct *vma, - unsigned long start, - unsigned long end, - unsigned long new_flags, - struct anon_vma_name *new_name) -{ - return vma_modify(vmi, prev, vma, start, end, new_flags, - vma_policy(vma), vma->vm_userfaultfd_ctx, new_name); -} - -/* We are about to modify the VMA's memory policy. */ -static inline struct vm_area_struct -*vma_modify_policy(struct vma_iterator *vmi, - struct vm_area_struct *prev, - struct vm_area_struct *vma, - unsigned long start, unsigned long end, - struct mempolicy *new_pol) -{ - return vma_modify(vmi, prev, vma, start, end, vma->vm_flags, - new_pol, vma->vm_userfaultfd_ctx, anon_vma_name(vma)); -} - -/* We are about to modify the VMA's flags and/or uffd context. */ -static inline struct vm_area_struct -*vma_modify_flags_uffd(struct vma_iterator *vmi, - struct vm_area_struct *prev, - struct vm_area_struct *vma, - unsigned long start, unsigned long end, - unsigned long new_flags, - struct vm_userfaultfd_ctx new_ctx) -{ - return vma_modify(vmi, prev, vma, start, end, new_flags, - vma_policy(vma), new_ctx, anon_vma_name(vma)); -} - -int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma, - unsigned long start, unsigned long end, pgoff_t pgoff, - struct vm_area_struct *next); -int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma, - unsigned long start, unsigned long end, pgoff_t pgoff); - enum { /* mark page accessed */ FOLL_TOUCH = 1 << 16, @@ -1437,123 +1337,6 @@ static inline bool pte_needs_soft_dirty_wp(struct vm_area_struct *vma, pte_t pte return vma_soft_dirty_enabled(vma) && !pte_soft_dirty(pte); } -static inline void vma_iter_config(struct vma_iterator *vmi, - unsigned long index, unsigned long last) -{ - __mas_set_range(&vmi->mas, index, last - 1); -} - -static inline void vma_iter_reset(struct vma_iterator *vmi) -{ - mas_reset(&vmi->mas); -} - -static inline -struct vm_area_struct *vma_iter_prev_range_limit(struct vma_iterator *vmi, unsigned long min) -{ - return mas_prev_range(&vmi->mas, min); -} - -static inline -struct vm_area_struct *vma_iter_next_range_limit(struct vma_iterator *vmi, unsigned long max) -{ - return mas_next_range(&vmi->mas, max); -} - -static inline int vma_iter_area_lowest(struct vma_iterator *vmi, unsigned long min, - unsigned long max, unsigned long size) -{ - return mas_empty_area(&vmi->mas, min, max - 1, size); -} - -static inline int vma_iter_area_highest(struct vma_iterator *vmi, unsigned long min, - unsigned long max, unsigned long size) -{ - return mas_empty_area_rev(&vmi->mas, min, max - 1, size); -} - -/* - * VMA Iterator functions shared between nommu and mmap - */ -static inline int vma_iter_prealloc(struct vma_iterator *vmi, - struct vm_area_struct *vma) -{ - return mas_preallocate(&vmi->mas, vma, GFP_KERNEL); -} - -static inline void vma_iter_clear(struct vma_iterator *vmi) -{ - mas_store_prealloc(&vmi->mas, NULL); -} - -static inline struct vm_area_struct *vma_iter_load(struct vma_iterator *vmi) -{ - return mas_walk(&vmi->mas); -} - -/* Store a VMA with preallocated memory */ -static inline void vma_iter_store(struct vma_iterator *vmi, - struct vm_area_struct *vma) -{ - -#if defined(CONFIG_DEBUG_VM_MAPLE_TREE) - if (MAS_WARN_ON(&vmi->mas, vmi->mas.status != ma_start && - vmi->mas.index > vma->vm_start)) { - pr_warn("%lx > %lx\n store vma %lx-%lx\n into slot %lx-%lx\n", - vmi->mas.index, vma->vm_start, vma->vm_start, - vma->vm_end, vmi->mas.index, vmi->mas.last); - } - if (MAS_WARN_ON(&vmi->mas, vmi->mas.status != ma_start && - vmi->mas.last < vma->vm_start)) { - pr_warn("%lx < %lx\nstore vma %lx-%lx\ninto slot %lx-%lx\n", - vmi->mas.last, vma->vm_start, vma->vm_start, vma->vm_end, - vmi->mas.index, vmi->mas.last); - } -#endif - - if (vmi->mas.status != ma_start && - ((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start))) - vma_iter_invalidate(vmi); - - __mas_set_range(&vmi->mas, vma->vm_start, vma->vm_end - 1); - mas_store_prealloc(&vmi->mas, vma); -} - -static inline int vma_iter_store_gfp(struct vma_iterator *vmi, - struct vm_area_struct *vma, gfp_t gfp) -{ - if (vmi->mas.status != ma_start && - ((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start))) - vma_iter_invalidate(vmi); - - __mas_set_range(&vmi->mas, vma->vm_start, vma->vm_end - 1); - mas_store_gfp(&vmi->mas, vma, gfp); - if (unlikely(mas_is_err(&vmi->mas))) - return -ENOMEM; - - return 0; -} - -static inline -struct vm_area_struct *vma_iter_prev_range(struct vma_iterator *vmi) -{ - return mas_prev_range(&vmi->mas, 0); -} - -/* - * VMA lock generalization - */ -struct vma_prepare { - struct vm_area_struct *vma; - struct vm_area_struct *adj_next; - struct file *file; - struct address_space *mapping; - struct anon_vma *anon_vma; - struct vm_area_struct *insert; - struct vm_area_struct *remove; - struct vm_area_struct *remove2; -}; - void __meminit __init_single_page(struct page *page, unsigned long pfn, unsigned long zone, int nid); @@ -1642,15 +1425,6 @@ static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry, void workingset_update_node(struct xa_node *node); extern struct list_lru shadow_nodes; -struct unlink_vma_file_batch { - int count; - struct vm_area_struct *vmas[8]; -}; - -void unlink_file_vma_batch_init(struct unlink_vma_file_batch *); -void unlink_file_vma_batch_add(struct unlink_vma_file_batch *, struct vm_area_struct *); -void unlink_file_vma_batch_final(struct unlink_vma_file_batch *); - /* mremap.c */ unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, diff --git a/mm/mmap.c b/mm/mmap.c index 211148ba2831..4a9c2329b09a 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -76,16 +76,6 @@ int mmap_rnd_compat_bits __read_mostly = CONFIG_ARCH_MMAP_RND_COMPAT_BITS; static bool ignore_rlimit_data; core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644); -static void unmap_region(struct mm_struct *mm, struct ma_state *mas, - struct vm_area_struct *vma, struct vm_area_struct *prev, - struct vm_area_struct *next, unsigned long start, - unsigned long end, unsigned long tree_end, bool mm_wr_locked); - -static pgprot_t vm_pgprot_modify(pgprot_t oldprot, unsigned long vm_flags) -{ - return pgprot_modify(oldprot, vm_get_page_prot(vm_flags)); -} - /* Update vma->vm_page_prot to reflect vma->vm_flags. */ void vma_set_page_prot(struct vm_area_struct *vma) { @@ -101,100 +91,6 @@ void vma_set_page_prot(struct vm_area_struct *vma) WRITE_ONCE(vma->vm_page_prot, vm_page_prot); } -/* - * Requires inode->i_mapping->i_mmap_rwsem - */ -static void __remove_shared_vm_struct(struct vm_area_struct *vma, - struct address_space *mapping) -{ - if (vma_is_shared_maywrite(vma)) - mapping_unmap_writable(mapping); - - flush_dcache_mmap_lock(mapping); - vma_interval_tree_remove(vma, &mapping->i_mmap); - flush_dcache_mmap_unlock(mapping); -} - -/* - * Unlink a file-based vm structure from its interval tree, to hide - * vma from rmap and vmtruncate before freeing its page tables. - */ -void unlink_file_vma(struct vm_area_struct *vma) -{ - struct file *file = vma->vm_file; - - if (file) { - struct address_space *mapping = file->f_mapping; - i_mmap_lock_write(mapping); - __remove_shared_vm_struct(vma, mapping); - i_mmap_unlock_write(mapping); - } -} - -void unlink_file_vma_batch_init(struct unlink_vma_file_batch *vb) -{ - vb->count = 0; -} - -static void unlink_file_vma_batch_process(struct unlink_vma_file_batch *vb) -{ - struct address_space *mapping; - int i; - - mapping = vb->vmas[0]->vm_file->f_mapping; - i_mmap_lock_write(mapping); - for (i = 0; i < vb->count; i++) { - VM_WARN_ON_ONCE(vb->vmas[i]->vm_file->f_mapping != mapping); - __remove_shared_vm_struct(vb->vmas[i], mapping); - } - i_mmap_unlock_write(mapping); - - unlink_file_vma_batch_init(vb); -} - -void unlink_file_vma_batch_add(struct unlink_vma_file_batch *vb, - struct vm_area_struct *vma) -{ - if (vma->vm_file == NULL) - return; - - if ((vb->count > 0 && vb->vmas[0]->vm_file != vma->vm_file) || - vb->count == ARRAY_SIZE(vb->vmas)) - unlink_file_vma_batch_process(vb); - - vb->vmas[vb->count] = vma; - vb->count++; -} - -void unlink_file_vma_batch_final(struct unlink_vma_file_batch *vb) -{ - if (vb->count > 0) - unlink_file_vma_batch_process(vb); -} - -/* - * Close a vm structure and free it. - */ -static void remove_vma(struct vm_area_struct *vma, bool unreachable) -{ - might_sleep(); - if (vma->vm_ops && vma->vm_ops->close) - vma->vm_ops->close(vma); - if (vma->vm_file) - fput(vma->vm_file); - mpol_put(vma_policy(vma)); - if (unreachable) - __vm_area_free(vma); - else - vm_area_free(vma); -} - -static inline struct vm_area_struct *vma_prev_limit(struct vma_iterator *vmi, - unsigned long min) -{ - return mas_prev(&vmi->mas, min); -} - /* * check_brk_limits() - Use platform specific check of range & verify mlock * limits. @@ -300,891 +196,22 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) if (do_brk_flags(&vmi, brkvma, oldbrk, newbrk - oldbrk, 0) < 0) goto out; - mm->brk = brk; - if (mm->def_flags & VM_LOCKED) - populate = true; - -success: - mmap_write_unlock(mm); -success_unlocked: - userfaultfd_unmap_complete(mm, &uf); - if (populate) - mm_populate(oldbrk, newbrk - oldbrk); - return brk; - -out: - mm->brk = origbrk; - mmap_write_unlock(mm); - return origbrk; -} - -#if defined(CONFIG_DEBUG_VM_MAPLE_TREE) -static void validate_mm(struct mm_struct *mm) -{ - int bug = 0; - int i = 0; - struct vm_area_struct *vma; - VMA_ITERATOR(vmi, mm, 0); - - mt_validate(&mm->mm_mt); - for_each_vma(vmi, vma) { -#ifdef CONFIG_DEBUG_VM_RB - struct anon_vma *anon_vma = vma->anon_vma; - struct anon_vma_chain *avc; -#endif - unsigned long vmi_start, vmi_end; - bool warn = 0; - - vmi_start = vma_iter_addr(&vmi); - vmi_end = vma_iter_end(&vmi); - if (VM_WARN_ON_ONCE_MM(vma->vm_end != vmi_end, mm)) - warn = 1; - - if (VM_WARN_ON_ONCE_MM(vma->vm_start != vmi_start, mm)) - warn = 1; - - if (warn) { - pr_emerg("issue in %s\n", current->comm); - dump_stack(); - dump_vma(vma); - pr_emerg("tree range: %px start %lx end %lx\n", vma, - vmi_start, vmi_end - 1); - vma_iter_dump_tree(&vmi); - } - -#ifdef CONFIG_DEBUG_VM_RB - if (anon_vma) { - anon_vma_lock_read(anon_vma); - list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) - anon_vma_interval_tree_verify(avc); - anon_vma_unlock_read(anon_vma); - } -#endif - i++; - } - if (i != mm->map_count) { - pr_emerg("map_count %d vma iterator %d\n", mm->map_count, i); - bug = 1; - } - VM_BUG_ON_MM(bug, mm); -} - -#else /* !CONFIG_DEBUG_VM_MAPLE_TREE */ -#define validate_mm(mm) do { } while (0) -#endif /* CONFIG_DEBUG_VM_MAPLE_TREE */ - -/* - * vma has some anon_vma assigned, and is already inserted on that - * anon_vma's interval trees. - * - * Before updating the vma's vm_start / vm_end / vm_pgoff fields, the - * vma must be removed from the anon_vma's interval trees using - * anon_vma_interval_tree_pre_update_vma(). - * - * After the update, the vma will be reinserted using - * anon_vma_interval_tree_post_update_vma(). - * - * The entire update must be protected by exclusive mmap_lock and by - * the root anon_vma's mutex. - */ -static inline void -anon_vma_interval_tree_pre_update_vma(struct vm_area_struct *vma) -{ - struct anon_vma_chain *avc; - - list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) - anon_vma_interval_tree_remove(avc, &avc->anon_vma->rb_root); -} - -static inline void -anon_vma_interval_tree_post_update_vma(struct vm_area_struct *vma) -{ - struct anon_vma_chain *avc; - - list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) - anon_vma_interval_tree_insert(avc, &avc->anon_vma->rb_root); -} - -static unsigned long count_vma_pages_range(struct mm_struct *mm, - unsigned long addr, unsigned long end) -{ - VMA_ITERATOR(vmi, mm, addr); - struct vm_area_struct *vma; - unsigned long nr_pages = 0; - - for_each_vma_range(vmi, vma, end) { - unsigned long vm_start = max(addr, vma->vm_start); - unsigned long vm_end = min(end, vma->vm_end); - - nr_pages += PHYS_PFN(vm_end - vm_start); - } - - return nr_pages; -} - -static void __vma_link_file(struct vm_area_struct *vma, - struct address_space *mapping) -{ - if (vma_is_shared_maywrite(vma)) - mapping_allow_writable(mapping); - - flush_dcache_mmap_lock(mapping); - vma_interval_tree_insert(vma, &mapping->i_mmap); - flush_dcache_mmap_unlock(mapping); -} - -static void vma_link_file(struct vm_area_struct *vma) -{ - struct file *file = vma->vm_file; - struct address_space *mapping; - - if (file) { - mapping = file->f_mapping; - i_mmap_lock_write(mapping); - __vma_link_file(vma, mapping); - i_mmap_unlock_write(mapping); - } -} - -static int vma_link(struct mm_struct *mm, struct vm_area_struct *vma) -{ - VMA_ITERATOR(vmi, mm, 0); - - vma_iter_config(&vmi, vma->vm_start, vma->vm_end); - if (vma_iter_prealloc(&vmi, vma)) - return -ENOMEM; - - vma_start_write(vma); - vma_iter_store(&vmi, vma); - vma_link_file(vma); - mm->map_count++; - validate_mm(mm); - return 0; -} - -/* - * init_multi_vma_prep() - Initializer for struct vma_prepare - * @vp: The vma_prepare struct - * @vma: The vma that will be altered once locked - * @next: The next vma if it is to be adjusted - * @remove: The first vma to be removed - * @remove2: The second vma to be removed - */ -static inline void init_multi_vma_prep(struct vma_prepare *vp, - struct vm_area_struct *vma, struct vm_area_struct *next, - struct vm_area_struct *remove, struct vm_area_struct *remove2) -{ - memset(vp, 0, sizeof(struct vma_prepare)); - vp->vma = vma; - vp->anon_vma = vma->anon_vma; - vp->remove = remove; - vp->remove2 = remove2; - vp->adj_next = next; - if (!vp->anon_vma && next) - vp->anon_vma = next->anon_vma; - - vp->file = vma->vm_file; - if (vp->file) - vp->mapping = vma->vm_file->f_mapping; - -} - -/* - * init_vma_prep() - Initializer wrapper for vma_prepare struct - * @vp: The vma_prepare struct - * @vma: The vma that will be altered once locked - */ -static inline void init_vma_prep(struct vma_prepare *vp, - struct vm_area_struct *vma) -{ - init_multi_vma_prep(vp, vma, NULL, NULL, NULL); -} - - -/* - * vma_prepare() - Helper function for handling locking VMAs prior to altering - * @vp: The initialized vma_prepare struct - */ -static inline void vma_prepare(struct vma_prepare *vp) -{ - if (vp->file) { - uprobe_munmap(vp->vma, vp->vma->vm_start, vp->vma->vm_end); - - if (vp->adj_next) - uprobe_munmap(vp->adj_next, vp->adj_next->vm_start, - vp->adj_next->vm_end); - - i_mmap_lock_write(vp->mapping); - if (vp->insert && vp->insert->vm_file) { - /* - * Put into interval tree now, so instantiated pages - * are visible to arm/parisc __flush_dcache_page - * throughout; but we cannot insert into address - * space until vma start or end is updated. - */ - __vma_link_file(vp->insert, - vp->insert->vm_file->f_mapping); - } - } - - if (vp->anon_vma) { - anon_vma_lock_write(vp->anon_vma); - anon_vma_interval_tree_pre_update_vma(vp->vma); - if (vp->adj_next) - anon_vma_interval_tree_pre_update_vma(vp->adj_next); - } - - if (vp->file) { - flush_dcache_mmap_lock(vp->mapping); - vma_interval_tree_remove(vp->vma, &vp->mapping->i_mmap); - if (vp->adj_next) - vma_interval_tree_remove(vp->adj_next, - &vp->mapping->i_mmap); - } - -} - -/* - * vma_complete- Helper function for handling the unlocking after altering VMAs, - * or for inserting a VMA. - * - * @vp: The vma_prepare struct - * @vmi: The vma iterator - * @mm: The mm_struct - */ -static inline void vma_complete(struct vma_prepare *vp, - struct vma_iterator *vmi, struct mm_struct *mm) -{ - if (vp->file) { - if (vp->adj_next) - vma_interval_tree_insert(vp->adj_next, - &vp->mapping->i_mmap); - vma_interval_tree_insert(vp->vma, &vp->mapping->i_mmap); - flush_dcache_mmap_unlock(vp->mapping); - } - - if (vp->remove && vp->file) { - __remove_shared_vm_struct(vp->remove, vp->mapping); - if (vp->remove2) - __remove_shared_vm_struct(vp->remove2, vp->mapping); - } else if (vp->insert) { - /* - * split_vma has split insert from vma, and needs - * us to insert it before dropping the locks - * (it may either follow vma or precede it). - */ - vma_iter_store(vmi, vp->insert); - mm->map_count++; - } - - if (vp->anon_vma) { - anon_vma_interval_tree_post_update_vma(vp->vma); - if (vp->adj_next) - anon_vma_interval_tree_post_update_vma(vp->adj_next); - anon_vma_unlock_write(vp->anon_vma); - } - - if (vp->file) { - i_mmap_unlock_write(vp->mapping); - uprobe_mmap(vp->vma); - - if (vp->adj_next) - uprobe_mmap(vp->adj_next); - } - - if (vp->remove) { -again: - vma_mark_detached(vp->remove, true); - if (vp->file) { - uprobe_munmap(vp->remove, vp->remove->vm_start, - vp->remove->vm_end); - fput(vp->file); - } - if (vp->remove->anon_vma) - anon_vma_merge(vp->vma, vp->remove); - mm->map_count--; - mpol_put(vma_policy(vp->remove)); - if (!vp->remove2) - WARN_ON_ONCE(vp->vma->vm_end < vp->remove->vm_end); - vm_area_free(vp->remove); - - /* - * In mprotect's case 6 (see comments on vma_merge), - * we are removing both mid and next vmas - */ - if (vp->remove2) { - vp->remove = vp->remove2; - vp->remove2 = NULL; - goto again; - } - } - if (vp->insert && vp->file) - uprobe_mmap(vp->insert); - validate_mm(mm); -} - -/* - * dup_anon_vma() - Helper function to duplicate anon_vma - * @dst: The destination VMA - * @src: The source VMA - * @dup: Pointer to the destination VMA when successful. - * - * Returns: 0 on success. - */ -static inline int dup_anon_vma(struct vm_area_struct *dst, - struct vm_area_struct *src, struct vm_area_struct **dup) -{ - /* - * Easily overlooked: when mprotect shifts the boundary, make sure the - * expanding vma has anon_vma set if the shrinking vma had, to cover any - * anon pages imported. - */ - if (src->anon_vma && !dst->anon_vma) { - int ret; - - vma_assert_write_locked(dst); - dst->anon_vma = src->anon_vma; - ret = anon_vma_clone(dst, src); - if (ret) - return ret; - - *dup = dst; - } - - return 0; -} - -/* - * vma_expand - Expand an existing VMA - * - * @vmi: The vma iterator - * @vma: The vma to expand - * @start: The start of the vma - * @end: The exclusive end of the vma - * @pgoff: The page offset of vma - * @next: The current of next vma. - * - * Expand @vma to @start and @end. Can expand off the start and end. Will - * expand over @next if it's different from @vma and @end == @next->vm_end. - * Checking if the @vma can expand and merge with @next needs to be handled by - * the caller. - * - * Returns: 0 on success - */ -int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma, - unsigned long start, unsigned long end, pgoff_t pgoff, - struct vm_area_struct *next) -{ - struct vm_area_struct *anon_dup = NULL; - bool remove_next = false; - struct vma_prepare vp; - - vma_start_write(vma); - if (next && (vma != next) && (end == next->vm_end)) { - int ret; - - remove_next = true; - vma_start_write(next); - ret = dup_anon_vma(vma, next, &anon_dup); - if (ret) - return ret; - } - - init_multi_vma_prep(&vp, vma, NULL, remove_next ? next : NULL, NULL); - /* Not merging but overwriting any part of next is not handled. */ - VM_WARN_ON(next && !vp.remove && - next != vma && end > next->vm_start); - /* Only handles expanding */ - VM_WARN_ON(vma->vm_start < start || vma->vm_end > end); - - /* Note: vma iterator must be pointing to 'start' */ - vma_iter_config(vmi, start, end); - if (vma_iter_prealloc(vmi, vma)) - goto nomem; - - vma_prepare(&vp); - vma_adjust_trans_huge(vma, start, end, 0); - vma_set_range(vma, start, end, pgoff); - vma_iter_store(vmi, vma); - - vma_complete(&vp, vmi, vma->vm_mm); - return 0; - -nomem: - if (anon_dup) - unlink_anon_vmas(anon_dup); - return -ENOMEM; -} - -/* - * vma_shrink() - Reduce an existing VMAs memory area - * @vmi: The vma iterator - * @vma: The VMA to modify - * @start: The new start - * @end: The new end - * - * Returns: 0 on success, -ENOMEM otherwise - */ -int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma, - unsigned long start, unsigned long end, pgoff_t pgoff) -{ - struct vma_prepare vp; - - WARN_ON((vma->vm_start != start) && (vma->vm_end != end)); - - if (vma->vm_start < start) - vma_iter_config(vmi, vma->vm_start, start); - else - vma_iter_config(vmi, end, vma->vm_end); - - if (vma_iter_prealloc(vmi, NULL)) - return -ENOMEM; - - vma_start_write(vma); - - init_vma_prep(&vp, vma); - vma_prepare(&vp); - vma_adjust_trans_huge(vma, start, end, 0); - - vma_iter_clear(vmi); - vma_set_range(vma, start, end, pgoff); - vma_complete(&vp, vmi, vma->vm_mm); - return 0; -} - -/* - * If the vma has a ->close operation then the driver probably needs to release - * per-vma resources, so we don't attempt to merge those if the caller indicates - * the current vma may be removed as part of the merge. - */ -static inline bool is_mergeable_vma(struct vm_area_struct *vma, - struct file *file, unsigned long vm_flags, - struct vm_userfaultfd_ctx vm_userfaultfd_ctx, - struct anon_vma_name *anon_name, bool may_remove_vma) -{ - /* - * VM_SOFTDIRTY should not prevent from VMA merging, if we - * match the flags but dirty bit -- the caller should mark - * merged VMA as dirty. If dirty bit won't be excluded from - * comparison, we increase pressure on the memory system forcing - * the kernel to generate new VMAs when old one could be - * extended instead. - */ - if ((vma->vm_flags ^ vm_flags) & ~VM_SOFTDIRTY) - return false; - if (vma->vm_file != file) - return false; - if (may_remove_vma && vma->vm_ops && vma->vm_ops->close) - return false; - if (!is_mergeable_vm_userfaultfd_ctx(vma, vm_userfaultfd_ctx)) - return false; - if (!anon_vma_name_eq(anon_vma_name(vma), anon_name)) - return false; - return true; -} - -static inline bool is_mergeable_anon_vma(struct anon_vma *anon_vma1, - struct anon_vma *anon_vma2, struct vm_area_struct *vma) -{ - /* - * The list_is_singular() test is to avoid merging VMA cloned from - * parents. This can improve scalability caused by anon_vma lock. - */ - if ((!anon_vma1 || !anon_vma2) && (!vma || - list_is_singular(&vma->anon_vma_chain))) - return true; - return anon_vma1 == anon_vma2; -} - -/* - * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff) - * in front of (at a lower virtual address and file offset than) the vma. - * - * We cannot merge two vmas if they have differently assigned (non-NULL) - * anon_vmas, nor if same anon_vma is assigned but offsets incompatible. - * - * We don't check here for the merged mmap wrapping around the end of pagecache - * indices (16TB on ia32) because do_mmap() does not permit mmap's which - * wrap, nor mmaps which cover the final page at index -1UL. - * - * We assume the vma may be removed as part of the merge. - */ -static bool -can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags, - struct anon_vma *anon_vma, struct file *file, - pgoff_t vm_pgoff, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, - struct anon_vma_name *anon_name) -{ - if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name, true) && - is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { - if (vma->vm_pgoff == vm_pgoff) - return true; - } - return false; -} - -/* - * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff) - * beyond (at a higher virtual address and file offset than) the vma. - * - * We cannot merge two vmas if they have differently assigned (non-NULL) - * anon_vmas, nor if same anon_vma is assigned but offsets incompatible. - * - * We assume that vma is not removed as part of the merge. - */ -static bool -can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, - struct anon_vma *anon_vma, struct file *file, - pgoff_t vm_pgoff, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, - struct anon_vma_name *anon_name) -{ - if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name, false) && - is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { - pgoff_t vm_pglen; - vm_pglen = vma_pages(vma); - if (vma->vm_pgoff + vm_pglen == vm_pgoff) - return true; - } - return false; -} - -/* - * Given a mapping request (addr,end,vm_flags,file,pgoff,anon_name), - * figure out whether that can be merged with its predecessor or its - * successor. Or both (it neatly fills a hole). - * - * In most cases - when called for mmap, brk or mremap - [addr,end) is - * certain not to be mapped by the time vma_merge is called; but when - * called for mprotect, it is certain to be already mapped (either at - * an offset within prev, or at the start of next), and the flags of - * this area are about to be changed to vm_flags - and the no-change - * case has already been eliminated. - * - * The following mprotect cases have to be considered, where **** is - * the area passed down from mprotect_fixup, never extending beyond one - * vma, PPPP is the previous vma, CCCC is a concurrent vma that starts - * at the same address as **** and is of the same or larger span, and - * NNNN the next vma after ****: - * - * **** **** **** - * PPPPPPNNNNNN PPPPPPNNNNNN PPPPPPCCCCCC - * cannot merge might become might become - * PPNNNNNNNNNN PPPPPPPPPPCC - * mmap, brk or case 4 below case 5 below - * mremap move: - * **** **** - * PPPP NNNN PPPPCCCCNNNN - * might become might become - * PPPPPPPPPPPP 1 or PPPPPPPPPPPP 6 or - * PPPPPPPPNNNN 2 or PPPPPPPPNNNN 7 or - * PPPPNNNNNNNN 3 PPPPNNNNNNNN 8 - * - * It is important for case 8 that the vma CCCC overlapping the - * region **** is never going to extended over NNNN. Instead NNNN must - * be extended in region **** and CCCC must be removed. This way in - * all cases where vma_merge succeeds, the moment vma_merge drops the - * rmap_locks, the properties of the merged vma will be already - * correct for the whole merged range. Some of those properties like - * vm_page_prot/vm_flags may be accessed by rmap_walks and they must - * be correct for the whole merged range immediately after the - * rmap_locks are released. Otherwise if NNNN would be removed and - * CCCC would be extended over the NNNN range, remove_migration_ptes - * or other rmap walkers (if working on addresses beyond the "end" - * parameter) may establish ptes with the wrong permissions of CCCC - * instead of the right permissions of NNNN. - * - * In the code below: - * PPPP is represented by *prev - * CCCC is represented by *curr or not represented at all (NULL) - * NNNN is represented by *next or not represented at all (NULL) - * **** is not represented - it will be merged and the vma containing the - * area is returned, or the function will return NULL - */ -static struct vm_area_struct -*vma_merge(struct vma_iterator *vmi, struct vm_area_struct *prev, - struct vm_area_struct *src, unsigned long addr, unsigned long end, - unsigned long vm_flags, pgoff_t pgoff, struct mempolicy *policy, - struct vm_userfaultfd_ctx vm_userfaultfd_ctx, - struct anon_vma_name *anon_name) -{ - struct mm_struct *mm = src->vm_mm; - struct anon_vma *anon_vma = src->anon_vma; - struct file *file = src->vm_file; - struct vm_area_struct *curr, *next, *res; - struct vm_area_struct *vma, *adjust, *remove, *remove2; - struct vm_area_struct *anon_dup = NULL; - struct vma_prepare vp; - pgoff_t vma_pgoff; - int err = 0; - bool merge_prev = false; - bool merge_next = false; - bool vma_expanded = false; - unsigned long vma_start = addr; - unsigned long vma_end = end; - pgoff_t pglen = (end - addr) >> PAGE_SHIFT; - long adj_start = 0; - - /* - * We later require that vma->vm_flags == vm_flags, - * so this tests vma->vm_flags & VM_SPECIAL, too. - */ - if (vm_flags & VM_SPECIAL) - return NULL; - - /* Does the input range span an existing VMA? (cases 5 - 8) */ - curr = find_vma_intersection(mm, prev ? prev->vm_end : 0, end); - - if (!curr || /* cases 1 - 4 */ - end == curr->vm_end) /* cases 6 - 8, adjacent VMA */ - next = vma_lookup(mm, end); - else - next = NULL; /* case 5 */ - - if (prev) { - vma_start = prev->vm_start; - vma_pgoff = prev->vm_pgoff; - - /* Can we merge the predecessor? */ - if (addr == prev->vm_end && mpol_equal(vma_policy(prev), policy) - && can_vma_merge_after(prev, vm_flags, anon_vma, file, - pgoff, vm_userfaultfd_ctx, anon_name)) { - merge_prev = true; - vma_prev(vmi); - } - } - - /* Can we merge the successor? */ - if (next && mpol_equal(policy, vma_policy(next)) && - can_vma_merge_before(next, vm_flags, anon_vma, file, pgoff+pglen, - vm_userfaultfd_ctx, anon_name)) { - merge_next = true; - } - - /* Verify some invariant that must be enforced by the caller. */ - VM_WARN_ON(prev && addr <= prev->vm_start); - VM_WARN_ON(curr && (addr != curr->vm_start || end > curr->vm_end)); - VM_WARN_ON(addr >= end); - - if (!merge_prev && !merge_next) - return NULL; /* Not mergeable. */ - - if (merge_prev) - vma_start_write(prev); - - res = vma = prev; - remove = remove2 = adjust = NULL; - - /* Can we merge both the predecessor and the successor? */ - if (merge_prev && merge_next && - is_mergeable_anon_vma(prev->anon_vma, next->anon_vma, NULL)) { - vma_start_write(next); - remove = next; /* case 1 */ - vma_end = next->vm_end; - err = dup_anon_vma(prev, next, &anon_dup); - if (curr) { /* case 6 */ - vma_start_write(curr); - remove = curr; - remove2 = next; - /* - * Note that the dup_anon_vma below cannot overwrite err - * since the first caller would do nothing unless next - * has an anon_vma. - */ - if (!next->anon_vma) - err = dup_anon_vma(prev, curr, &anon_dup); - } - } else if (merge_prev) { /* case 2 */ - if (curr) { - vma_start_write(curr); - if (end == curr->vm_end) { /* case 7 */ - /* - * can_vma_merge_after() assumed we would not be - * removing prev vma, so it skipped the check - * for vm_ops->close, but we are removing curr - */ - if (curr->vm_ops && curr->vm_ops->close) - err = -EINVAL; - remove = curr; - } else { /* case 5 */ - adjust = curr; - adj_start = (end - curr->vm_start); - } - if (!err) - err = dup_anon_vma(prev, curr, &anon_dup); - } - } else { /* merge_next */ - vma_start_write(next); - res = next; - if (prev && addr < prev->vm_end) { /* case 4 */ - vma_start_write(prev); - vma_end = addr; - adjust = next; - adj_start = -(prev->vm_end - addr); - err = dup_anon_vma(next, prev, &anon_dup); - } else { - /* - * Note that cases 3 and 8 are the ONLY ones where prev - * is permitted to be (but is not necessarily) NULL. - */ - vma = next; /* case 3 */ - vma_start = addr; - vma_end = next->vm_end; - vma_pgoff = next->vm_pgoff - pglen; - if (curr) { /* case 8 */ - vma_pgoff = curr->vm_pgoff; - vma_start_write(curr); - remove = curr; - err = dup_anon_vma(next, curr, &anon_dup); - } - } - } - - /* Error in anon_vma clone. */ - if (err) - goto anon_vma_fail; - - if (vma_start < vma->vm_start || vma_end > vma->vm_end) - vma_expanded = true; - - if (vma_expanded) { - vma_iter_config(vmi, vma_start, vma_end); - } else { - vma_iter_config(vmi, adjust->vm_start + adj_start, - adjust->vm_end); - } - - if (vma_iter_prealloc(vmi, vma)) - goto prealloc_fail; - - init_multi_vma_prep(&vp, vma, adjust, remove, remove2); - VM_WARN_ON(vp.anon_vma && adjust && adjust->anon_vma && - vp.anon_vma != adjust->anon_vma); - - vma_prepare(&vp); - vma_adjust_trans_huge(vma, vma_start, vma_end, adj_start); - vma_set_range(vma, vma_start, vma_end, vma_pgoff); - - if (vma_expanded) - vma_iter_store(vmi, vma); - - if (adj_start) { - adjust->vm_start += adj_start; - adjust->vm_pgoff += adj_start >> PAGE_SHIFT; - if (adj_start < 0) { - WARN_ON(vma_expanded); - vma_iter_store(vmi, next); - } - } - - vma_complete(&vp, vmi, mm); - khugepaged_enter_vma(res, vm_flags); - return res; - -prealloc_fail: - if (anon_dup) - unlink_anon_vmas(anon_dup); - -anon_vma_fail: - vma_iter_set(vmi, addr); - vma_iter_load(vmi); - return NULL; -} - -/* - * Rough compatibility check to quickly see if it's even worth looking - * at sharing an anon_vma. - * - * They need to have the same vm_file, and the flags can only differ - * in things that mprotect may change. - * - * NOTE! The fact that we share an anon_vma doesn't _have_ to mean that - * we can merge the two vma's. For example, we refuse to merge a vma if - * there is a vm_ops->close() function, because that indicates that the - * driver is doing some kind of reference counting. But that doesn't - * really matter for the anon_vma sharing case. - */ -static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct *b) -{ - return a->vm_end == b->vm_start && - mpol_equal(vma_policy(a), vma_policy(b)) && - a->vm_file == b->vm_file && - !((a->vm_flags ^ b->vm_flags) & ~(VM_ACCESS_FLAGS | VM_SOFTDIRTY)) && - b->vm_pgoff == a->vm_pgoff + ((b->vm_start - a->vm_start) >> PAGE_SHIFT); -} - -/* - * Do some basic sanity checking to see if we can re-use the anon_vma - * from 'old'. The 'a'/'b' vma's are in VM order - one of them will be - * the same as 'old', the other will be the new one that is trying - * to share the anon_vma. - * - * NOTE! This runs with mmap_lock held for reading, so it is possible that - * the anon_vma of 'old' is concurrently in the process of being set up - * by another page fault trying to merge _that_. But that's ok: if it - * is being set up, that automatically means that it will be a singleton - * acceptable for merging, so we can do all of this optimistically. But - * we do that READ_ONCE() to make sure that we never re-load the pointer. - * - * IOW: that the "list_is_singular()" test on the anon_vma_chain only - * matters for the 'stable anon_vma' case (ie the thing we want to avoid - * is to return an anon_vma that is "complex" due to having gone through - * a fork). - * - * We also make sure that the two vma's are compatible (adjacent, - * and with the same memory policies). That's all stable, even with just - * a read lock on the mmap_lock. - */ -static struct anon_vma *reusable_anon_vma(struct vm_area_struct *old, struct vm_area_struct *a, struct vm_area_struct *b) -{ - if (anon_vma_compatible(a, b)) { - struct anon_vma *anon_vma = READ_ONCE(old->anon_vma); - - if (anon_vma && list_is_singular(&old->anon_vma_chain)) - return anon_vma; - } - return NULL; -} - -/* - * find_mergeable_anon_vma is used by anon_vma_prepare, to check - * neighbouring vmas for a suitable anon_vma, before it goes off - * to allocate a new anon_vma. It checks because a repetitive - * sequence of mprotects and faults may otherwise lead to distinct - * anon_vmas being allocated, preventing vma merge in subsequent - * mprotect. - */ -struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma) -{ - struct anon_vma *anon_vma = NULL; - struct vm_area_struct *prev, *next; - VMA_ITERATOR(vmi, vma->vm_mm, vma->vm_end); - - /* Try next first. */ - next = vma_iter_load(&vmi); - if (next) { - anon_vma = reusable_anon_vma(next, vma, next); - if (anon_vma) - return anon_vma; - } + mm->brk = brk; + if (mm->def_flags & VM_LOCKED) + populate = true; - prev = vma_prev(&vmi); - VM_BUG_ON_VMA(prev != vma, vma); - prev = vma_prev(&vmi); - /* Try prev next. */ - if (prev) - anon_vma = reusable_anon_vma(prev, prev, vma); +success: + mmap_write_unlock(mm); +success_unlocked: + userfaultfd_unmap_complete(mm, &uf); + if (populate) + mm_populate(oldbrk, newbrk - oldbrk); + return brk; - /* - * We might reach here with anon_vma == NULL if we can't find - * any reusable anon_vma. - * There's no absolute need to look only at touching neighbours: - * we could search further afield for "compatible" anon_vmas. - * But it would probably just be a waste of time searching, - * or lead to too many vmas hanging off the same anon_vma. - * We're trying to allow mprotect remerging later on, - * not trying to minimize memory used for anon_vmas. - */ - return anon_vma; +out: + mm->brk = origbrk; + mmap_write_unlock(mm); + return origbrk; } /* @@ -1549,85 +576,6 @@ SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg) } #endif /* __ARCH_WANT_SYS_OLD_MMAP */ -static bool vm_ops_needs_writenotify(const struct vm_operations_struct *vm_ops) -{ - return vm_ops && (vm_ops->page_mkwrite || vm_ops->pfn_mkwrite); -} - -static bool vma_is_shared_writable(struct vm_area_struct *vma) -{ - return (vma->vm_flags & (VM_WRITE | VM_SHARED)) == - (VM_WRITE | VM_SHARED); -} - -static bool vma_fs_can_writeback(struct vm_area_struct *vma) -{ - /* No managed pages to writeback. */ - if (vma->vm_flags & VM_PFNMAP) - return false; - - return vma->vm_file && vma->vm_file->f_mapping && - mapping_can_writeback(vma->vm_file->f_mapping); -} - -/* - * Does this VMA require the underlying folios to have their dirty state - * tracked? - */ -bool vma_needs_dirty_tracking(struct vm_area_struct *vma) -{ - /* Only shared, writable VMAs require dirty tracking. */ - if (!vma_is_shared_writable(vma)) - return false; - - /* Does the filesystem need to be notified? */ - if (vm_ops_needs_writenotify(vma->vm_ops)) - return true; - - /* - * Even if the filesystem doesn't indicate a need for writenotify, if it - * can writeback, dirty tracking is still required. - */ - return vma_fs_can_writeback(vma); -} - -/* - * Some shared mappings will want the pages marked read-only - * to track write events. If so, we'll downgrade vm_page_prot - * to the private version (using protection_map[] without the - * VM_SHARED bit). - */ -bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot) -{ - /* If it was private or non-writable, the write bit is already clear */ - if (!vma_is_shared_writable(vma)) - return false; - - /* The backer wishes to know when pages are first written to? */ - if (vm_ops_needs_writenotify(vma->vm_ops)) - return true; - - /* The open routine did something to the protections that pgprot_modify - * won't preserve? */ - if (pgprot_val(vm_page_prot) != - pgprot_val(vm_pgprot_modify(vm_page_prot, vma->vm_flags))) - return false; - - /* - * Do we need to track softdirty? hugetlb does not support softdirty - * tracking yet. - */ - if (vma_soft_dirty_enabled(vma) && !is_vm_hugetlb_page(vma)) - return true; - - /* Do we need write faults for uffd-wp tracking? */ - if (userfaultfd_wp(vma)) - return true; - - /* Can the mapping track the dirty pages? */ - return vma_fs_can_writeback(vma); -} - /* * We account for memory if it's a private writeable mapping, * not hugepages and VM_NORESERVE wasn't set. @@ -2268,566 +1216,129 @@ int expand_downwards(struct vm_area_struct *vma, unsigned long address) anon_vma_interval_tree_post_update_vma(vma); spin_unlock(&mm->page_table_lock); - perf_event_mmap(vma); - } - } - } - anon_vma_unlock_write(vma->anon_vma); - vma_iter_free(&vmi); - validate_mm(mm); - return error; -} - -/* enforced gap between the expanding stack and other mappings. */ -unsigned long stack_guard_gap = 256UL<close operation then the driver probably needs to release + * per-vma resources, so we don't attempt to merge those if the caller indicates + * the current vma may be removed as part of the merge. + */ +static inline bool is_mergeable_vma(struct vm_area_struct *vma, + struct file *file, unsigned long vm_flags, + struct vm_userfaultfd_ctx vm_userfaultfd_ctx, + struct anon_vma_name *anon_name, bool may_remove_vma) +{ + /* + * VM_SOFTDIRTY should not prevent from VMA merging, if we + * match the flags but dirty bit -- the caller should mark + * merged VMA as dirty. If dirty bit won't be excluded from + * comparison, we increase pressure on the memory system forcing + * the kernel to generate new VMAs when old one could be + * extended instead. + */ + if ((vma->vm_flags ^ vm_flags) & ~VM_SOFTDIRTY) + return false; + if (vma->vm_file != file) + return false; + if (may_remove_vma && vma->vm_ops && vma->vm_ops->close) + return false; + if (!is_mergeable_vm_userfaultfd_ctx(vma, vm_userfaultfd_ctx)) + return false; + if (!anon_vma_name_eq(anon_vma_name(vma), anon_name)) + return false; + return true; +} + +static inline bool is_mergeable_anon_vma(struct anon_vma *anon_vma1, + struct anon_vma *anon_vma2, struct vm_area_struct *vma) +{ + /* + * The list_is_singular() test is to avoid merging VMA cloned from + * parents. This can improve scalability caused by anon_vma lock. + */ + if ((!anon_vma1 || !anon_vma2) && (!vma || + list_is_singular(&vma->anon_vma_chain))) + return true; + return anon_vma1 == anon_vma2; +} + +/* + * init_multi_vma_prep() - Initializer for struct vma_prepare + * @vp: The vma_prepare struct + * @vma: The vma that will be altered once locked + * @next: The next vma if it is to be adjusted + * @remove: The first vma to be removed + * @remove2: The second vma to be removed + */ +static void init_multi_vma_prep(struct vma_prepare *vp, + struct vm_area_struct *vma, + struct vm_area_struct *next, + struct vm_area_struct *remove, + struct vm_area_struct *remove2) +{ + memset(vp, 0, sizeof(struct vma_prepare)); + vp->vma = vma; + vp->anon_vma = vma->anon_vma; + vp->remove = remove; + vp->remove2 = remove2; + vp->adj_next = next; + if (!vp->anon_vma && next) + vp->anon_vma = next->anon_vma; + + vp->file = vma->vm_file; + if (vp->file) + vp->mapping = vma->vm_file->f_mapping; + +} + +/* + * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff) + * in front of (at a lower virtual address and file offset than) the vma. + * + * We cannot merge two vmas if they have differently assigned (non-NULL) + * anon_vmas, nor if same anon_vma is assigned but offsets incompatible. + * + * We don't check here for the merged mmap wrapping around the end of pagecache + * indices (16TB on ia32) because do_mmap() does not permit mmap's which + * wrap, nor mmaps which cover the final page at index -1UL. + * + * We assume the vma may be removed as part of the merge. + */ +bool +can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags, + struct anon_vma *anon_vma, struct file *file, + pgoff_t vm_pgoff, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, + struct anon_vma_name *anon_name) +{ + if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name, true) && + is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { + if (vma->vm_pgoff == vm_pgoff) + return true; + } + return false; +} + +/* + * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff) + * beyond (at a higher virtual address and file offset than) the vma. + * + * We cannot merge two vmas if they have differently assigned (non-NULL) + * anon_vmas, nor if same anon_vma is assigned but offsets incompatible. + * + * We assume that vma is not removed as part of the merge. + */ +bool +can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, + struct anon_vma *anon_vma, struct file *file, + pgoff_t vm_pgoff, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, + struct anon_vma_name *anon_name) +{ + if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name, false) && + is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { + pgoff_t vm_pglen; + + vm_pglen = vma_pages(vma); + if (vma->vm_pgoff + vm_pglen == vm_pgoff) + return true; + } + return false; +} + +/* + * Close a vm structure and free it. + */ +void remove_vma(struct vm_area_struct *vma, bool unreachable) +{ + might_sleep(); + if (vma->vm_ops && vma->vm_ops->close) + vma->vm_ops->close(vma); + if (vma->vm_file) + fput(vma->vm_file); + mpol_put(vma_policy(vma)); + if (unreachable) + __vm_area_free(vma); + else + vm_area_free(vma); +} + +/* + * Get rid of page table information in the indicated region. + * + * Called with the mm semaphore held. + */ +void unmap_region(struct mm_struct *mm, struct ma_state *mas, + struct vm_area_struct *vma, struct vm_area_struct *prev, + struct vm_area_struct *next, unsigned long start, + unsigned long end, unsigned long tree_end, bool mm_wr_locked) +{ + struct mmu_gather tlb; + unsigned long mt_start = mas->index; + + lru_add_drain(); + tlb_gather_mmu(&tlb, mm); + update_hiwater_rss(mm); + unmap_vmas(&tlb, mas, vma, start, end, tree_end, mm_wr_locked); + mas_set(mas, mt_start); + free_pgtables(&tlb, mas, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS, + next ? next->vm_start : USER_PGTABLES_CEILING, + mm_wr_locked); + tlb_finish_mmu(&tlb); +} + +/* + * __split_vma() bypasses sysctl_max_map_count checking. We use this where it + * has already been checked or doesn't make sense to fail. + * VMA Iterator will point to the end VMA. + */ +static int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, + unsigned long addr, int new_below) +{ + struct vma_prepare vp; + struct vm_area_struct *new; + int err; + + WARN_ON(vma->vm_start >= addr); + WARN_ON(vma->vm_end <= addr); + + if (vma->vm_ops && vma->vm_ops->may_split) { + err = vma->vm_ops->may_split(vma, addr); + if (err) + return err; + } + + new = vm_area_dup(vma); + if (!new) + return -ENOMEM; + + if (new_below) { + new->vm_end = addr; + } else { + new->vm_start = addr; + new->vm_pgoff += ((addr - vma->vm_start) >> PAGE_SHIFT); + } + + err = -ENOMEM; + vma_iter_config(vmi, new->vm_start, new->vm_end); + if (vma_iter_prealloc(vmi, new)) + goto out_free_vma; + + err = vma_dup_policy(vma, new); + if (err) + goto out_free_vmi; + + err = anon_vma_clone(new, vma); + if (err) + goto out_free_mpol; + + if (new->vm_file) + get_file(new->vm_file); + + if (new->vm_ops && new->vm_ops->open) + new->vm_ops->open(new); + + vma_start_write(vma); + vma_start_write(new); + + init_vma_prep(&vp, vma); + vp.insert = new; + vma_prepare(&vp); + vma_adjust_trans_huge(vma, vma->vm_start, addr, 0); + + if (new_below) { + vma->vm_start = addr; + vma->vm_pgoff += (addr - new->vm_start) >> PAGE_SHIFT; + } else { + vma->vm_end = addr; + } + + /* vma_complete stores the new vma */ + vma_complete(&vp, vmi, vma->vm_mm); + + /* Success. */ + if (new_below) + vma_next(vmi); + return 0; + +out_free_mpol: + mpol_put(vma_policy(new)); +out_free_vmi: + vma_iter_free(vmi); +out_free_vma: + vm_area_free(new); + return err; +} + +/* + * Split a vma into two pieces at address 'addr', a new vma is allocated + * either for the first part or the tail. + */ +static int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, + unsigned long addr, int new_below) +{ + if (vma->vm_mm->map_count >= sysctl_max_map_count) + return -ENOMEM; + + return __split_vma(vmi, vma, addr, new_below); +} + +/* + * Ok - we have the memory areas we should free on a maple tree so release them, + * and do the vma updates. + * + * Called with the mm semaphore held. + */ +static inline void remove_mt(struct mm_struct *mm, struct ma_state *mas) +{ + unsigned long nr_accounted = 0; + struct vm_area_struct *vma; + + /* Update high watermark before we lower total_vm */ + update_hiwater_vm(mm); + mas_for_each(mas, vma, ULONG_MAX) { + long nrpages = vma_pages(vma); + + if (vma->vm_flags & VM_ACCOUNT) + nr_accounted += nrpages; + vm_stat_account(mm, vma->vm_flags, -nrpages); + remove_vma(vma, false); + } + vm_unacct_memory(nr_accounted); +} + +/* + * init_vma_prep() - Initializer wrapper for vma_prepare struct + * @vp: The vma_prepare struct + * @vma: The vma that will be altered once locked + */ +void init_vma_prep(struct vma_prepare *vp, + struct vm_area_struct *vma) +{ + init_multi_vma_prep(vp, vma, NULL, NULL, NULL); +} + +/* + * Requires inode->i_mapping->i_mmap_rwsem + */ +static void __remove_shared_vm_struct(struct vm_area_struct *vma, + struct address_space *mapping) +{ + if (vma_is_shared_maywrite(vma)) + mapping_unmap_writable(mapping); + + flush_dcache_mmap_lock(mapping); + vma_interval_tree_remove(vma, &mapping->i_mmap); + flush_dcache_mmap_unlock(mapping); +} + +/* + * vma has some anon_vma assigned, and is already inserted on that + * anon_vma's interval trees. + * + * Before updating the vma's vm_start / vm_end / vm_pgoff fields, the + * vma must be removed from the anon_vma's interval trees using + * anon_vma_interval_tree_pre_update_vma(). + * + * After the update, the vma will be reinserted using + * anon_vma_interval_tree_post_update_vma(). + * + * The entire update must be protected by exclusive mmap_lock and by + * the root anon_vma's mutex. + */ +void +anon_vma_interval_tree_pre_update_vma(struct vm_area_struct *vma) +{ + struct anon_vma_chain *avc; + + list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) + anon_vma_interval_tree_remove(avc, &avc->anon_vma->rb_root); +} + +void +anon_vma_interval_tree_post_update_vma(struct vm_area_struct *vma) +{ + struct anon_vma_chain *avc; + + list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) + anon_vma_interval_tree_insert(avc, &avc->anon_vma->rb_root); +} + +static void __vma_link_file(struct vm_area_struct *vma, + struct address_space *mapping) +{ + if (vma_is_shared_maywrite(vma)) + mapping_allow_writable(mapping); + + flush_dcache_mmap_lock(mapping); + vma_interval_tree_insert(vma, &mapping->i_mmap); + flush_dcache_mmap_unlock(mapping); +} + +/* + * vma_prepare() - Helper function for handling locking VMAs prior to altering + * @vp: The initialized vma_prepare struct + */ +void vma_prepare(struct vma_prepare *vp) +{ + if (vp->file) { + uprobe_munmap(vp->vma, vp->vma->vm_start, vp->vma->vm_end); + + if (vp->adj_next) + uprobe_munmap(vp->adj_next, vp->adj_next->vm_start, + vp->adj_next->vm_end); + + i_mmap_lock_write(vp->mapping); + if (vp->insert && vp->insert->vm_file) { + /* + * Put into interval tree now, so instantiated pages + * are visible to arm/parisc __flush_dcache_page + * throughout; but we cannot insert into address + * space until vma start or end is updated. + */ + __vma_link_file(vp->insert, + vp->insert->vm_file->f_mapping); + } + } + + if (vp->anon_vma) { + anon_vma_lock_write(vp->anon_vma); + anon_vma_interval_tree_pre_update_vma(vp->vma); + if (vp->adj_next) + anon_vma_interval_tree_pre_update_vma(vp->adj_next); + } + + if (vp->file) { + flush_dcache_mmap_lock(vp->mapping); + vma_interval_tree_remove(vp->vma, &vp->mapping->i_mmap); + if (vp->adj_next) + vma_interval_tree_remove(vp->adj_next, + &vp->mapping->i_mmap); + } + +} + +/* + * dup_anon_vma() - Helper function to duplicate anon_vma + * @dst: The destination VMA + * @src: The source VMA + * @dup: Pointer to the destination VMA when successful. + * + * Returns: 0 on success. + */ +static int dup_anon_vma(struct vm_area_struct *dst, + struct vm_area_struct *src, struct vm_area_struct **dup) +{ + /* + * Easily overlooked: when mprotect shifts the boundary, make sure the + * expanding vma has anon_vma set if the shrinking vma had, to cover any + * anon pages imported. + */ + if (src->anon_vma && !dst->anon_vma) { + int ret; + + vma_assert_write_locked(dst); + dst->anon_vma = src->anon_vma; + ret = anon_vma_clone(dst, src); + if (ret) + return ret; + + *dup = dst; + } + + return 0; +} + +#ifdef CONFIG_DEBUG_VM_MAPLE_TREE +void validate_mm(struct mm_struct *mm) +{ + int bug = 0; + int i = 0; + struct vm_area_struct *vma; + VMA_ITERATOR(vmi, mm, 0); + + mt_validate(&mm->mm_mt); + for_each_vma(vmi, vma) { +#ifdef CONFIG_DEBUG_VM_RB + struct anon_vma *anon_vma = vma->anon_vma; + struct anon_vma_chain *avc; +#endif + unsigned long vmi_start, vmi_end; + bool warn = 0; + + vmi_start = vma_iter_addr(&vmi); + vmi_end = vma_iter_end(&vmi); + if (VM_WARN_ON_ONCE_MM(vma->vm_end != vmi_end, mm)) + warn = 1; + + if (VM_WARN_ON_ONCE_MM(vma->vm_start != vmi_start, mm)) + warn = 1; + + if (warn) { + pr_emerg("issue in %s\n", current->comm); + dump_stack(); + dump_vma(vma); + pr_emerg("tree range: %px start %lx end %lx\n", vma, + vmi_start, vmi_end - 1); + vma_iter_dump_tree(&vmi); + } + +#ifdef CONFIG_DEBUG_VM_RB + if (anon_vma) { + anon_vma_lock_read(anon_vma); + list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) + anon_vma_interval_tree_verify(avc); + anon_vma_unlock_read(anon_vma); + } +#endif + i++; + } + if (i != mm->map_count) { + pr_emerg("map_count %d vma iterator %d\n", mm->map_count, i); + bug = 1; + } + VM_BUG_ON_MM(bug, mm); +} +#endif /* CONFIG_DEBUG_VM_MAPLE_TREE */ + +/* + * vma_expand - Expand an existing VMA + * + * @vmi: The vma iterator + * @vma: The vma to expand + * @start: The start of the vma + * @end: The exclusive end of the vma + * @pgoff: The page offset of vma + * @next: The current of next vma. + * + * Expand @vma to @start and @end. Can expand off the start and end. Will + * expand over @next if it's different from @vma and @end == @next->vm_end. + * Checking if the @vma can expand and merge with @next needs to be handled by + * the caller. + * + * Returns: 0 on success + */ +int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma, + unsigned long start, unsigned long end, pgoff_t pgoff, + struct vm_area_struct *next) +{ + struct vm_area_struct *anon_dup = NULL; + bool remove_next = false; + struct vma_prepare vp; + + vma_start_write(vma); + if (next && (vma != next) && (end == next->vm_end)) { + int ret; + + remove_next = true; + vma_start_write(next); + ret = dup_anon_vma(vma, next, &anon_dup); + if (ret) + return ret; + } + + init_multi_vma_prep(&vp, vma, NULL, remove_next ? next : NULL, NULL); + /* Not merging but overwriting any part of next is not handled. */ + VM_WARN_ON(next && !vp.remove && + next != vma && end > next->vm_start); + /* Only handles expanding */ + VM_WARN_ON(vma->vm_start < start || vma->vm_end > end); + + /* Note: vma iterator must be pointing to 'start' */ + vma_iter_config(vmi, start, end); + if (vma_iter_prealloc(vmi, vma)) + goto nomem; + + vma_prepare(&vp); + vma_adjust_trans_huge(vma, start, end, 0); + vma_set_range(vma, start, end, pgoff); + vma_iter_store(vmi, vma); + + vma_complete(&vp, vmi, vma->vm_mm); + return 0; + +nomem: + if (anon_dup) + unlink_anon_vmas(anon_dup); + return -ENOMEM; +} + +/* + * vma_shrink() - Reduce an existing VMAs memory area + * @vmi: The vma iterator + * @vma: The VMA to modify + * @start: The new start + * @end: The new end + * + * Returns: 0 on success, -ENOMEM otherwise + */ +int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma, + unsigned long start, unsigned long end, pgoff_t pgoff) +{ + struct vma_prepare vp; + + WARN_ON((vma->vm_start != start) && (vma->vm_end != end)); + + if (vma->vm_start < start) + vma_iter_config(vmi, vma->vm_start, start); + else + vma_iter_config(vmi, end, vma->vm_end); + + if (vma_iter_prealloc(vmi, NULL)) + return -ENOMEM; + + vma_start_write(vma); + + init_vma_prep(&vp, vma); + vma_prepare(&vp); + vma_adjust_trans_huge(vma, start, end, 0); + + vma_iter_clear(vmi); + vma_set_range(vma, start, end, pgoff); + vma_complete(&vp, vmi, vma->vm_mm); + return 0; +} + +/* + * vma_complete- Helper function for handling the unlocking after altering VMAs, + * or for inserting a VMA. + * + * @vp: The vma_prepare struct + * @vmi: The vma iterator + * @mm: The mm_struct + */ +void vma_complete(struct vma_prepare *vp, + struct vma_iterator *vmi, struct mm_struct *mm) +{ + if (vp->file) { + if (vp->adj_next) + vma_interval_tree_insert(vp->adj_next, + &vp->mapping->i_mmap); + vma_interval_tree_insert(vp->vma, &vp->mapping->i_mmap); + flush_dcache_mmap_unlock(vp->mapping); + } + + if (vp->remove && vp->file) { + __remove_shared_vm_struct(vp->remove, vp->mapping); + if (vp->remove2) + __remove_shared_vm_struct(vp->remove2, vp->mapping); + } else if (vp->insert) { + /* + * split_vma has split insert from vma, and needs + * us to insert it before dropping the locks + * (it may either follow vma or precede it). + */ + vma_iter_store(vmi, vp->insert); + mm->map_count++; + } + + if (vp->anon_vma) { + anon_vma_interval_tree_post_update_vma(vp->vma); + if (vp->adj_next) + anon_vma_interval_tree_post_update_vma(vp->adj_next); + anon_vma_unlock_write(vp->anon_vma); + } + + if (vp->file) { + i_mmap_unlock_write(vp->mapping); + uprobe_mmap(vp->vma); + + if (vp->adj_next) + uprobe_mmap(vp->adj_next); + } + + if (vp->remove) { +again: + vma_mark_detached(vp->remove, true); + if (vp->file) { + uprobe_munmap(vp->remove, vp->remove->vm_start, + vp->remove->vm_end); + fput(vp->file); + } + if (vp->remove->anon_vma) + anon_vma_merge(vp->vma, vp->remove); + mm->map_count--; + mpol_put(vma_policy(vp->remove)); + if (!vp->remove2) + WARN_ON_ONCE(vp->vma->vm_end < vp->remove->vm_end); + vm_area_free(vp->remove); + + /* + * In mprotect's case 6 (see comments on vma_merge), + * we are removing both mid and next vmas + */ + if (vp->remove2) { + vp->remove = vp->remove2; + vp->remove2 = NULL; + goto again; + } + } + if (vp->insert && vp->file) + uprobe_mmap(vp->insert); + validate_mm(mm); +} + +/* + * do_vmi_align_munmap() - munmap the aligned region from @start to @end. + * @vmi: The vma iterator + * @vma: The starting vm_area_struct + * @mm: The mm_struct + * @start: The aligned start address to munmap. + * @end: The aligned end address to munmap. + * @uf: The userfaultfd list_head + * @unlock: Set to true to drop the mmap_lock. unlocking only happens on + * success. + * + * Return: 0 on success and drops the lock if so directed, error and leaves the + * lock held otherwise. + */ +int +do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, + struct mm_struct *mm, unsigned long start, + unsigned long end, struct list_head *uf, bool unlock) +{ + struct vm_area_struct *prev, *next = NULL; + struct maple_tree mt_detach; + int count = 0; + int error = -ENOMEM; + unsigned long locked_vm = 0; + MA_STATE(mas_detach, &mt_detach, 0, 0); + mt_init_flags(&mt_detach, vmi->mas.tree->ma_flags & MT_FLAGS_LOCK_MASK); + mt_on_stack(mt_detach); + + /* + * If we need to split any vma, do it now to save pain later. + * + * Note: mremap's move_vma VM_ACCOUNT handling assumes a partially + * unmapped vm_area_struct will remain in use: so lower split_vma + * places tmp vma above, and higher split_vma places tmp vma below. + */ + + /* Does it split the first one? */ + if (start > vma->vm_start) { + + /* + * Make sure that map_count on return from munmap() will + * not exceed its limit; but let map_count go just above + * its limit temporarily, to help free resources as expected. + */ + if (end < vma->vm_end && mm->map_count >= sysctl_max_map_count) + goto map_count_exceeded; + + error = __split_vma(vmi, vma, start, 1); + if (error) + goto start_split_failed; + } + + /* + * Detach a range of VMAs from the mm. Using next as a temp variable as + * it is always overwritten. + */ + next = vma; + do { + /* Does it split the end? */ + if (next->vm_end > end) { + error = __split_vma(vmi, next, end, 0); + if (error) + goto end_split_failed; + } + vma_start_write(next); + mas_set(&mas_detach, count); + error = mas_store_gfp(&mas_detach, next, GFP_KERNEL); + if (error) + goto munmap_gather_failed; + vma_mark_detached(next, true); + if (next->vm_flags & VM_LOCKED) + locked_vm += vma_pages(next); + + count++; + if (unlikely(uf)) { + /* + * If userfaultfd_unmap_prep returns an error the vmas + * will remain split, but userland will get a + * highly unexpected error anyway. This is no + * different than the case where the first of the two + * __split_vma fails, but we don't undo the first + * split, despite we could. This is unlikely enough + * failure that it's not worth optimizing it for. + */ + error = userfaultfd_unmap_prep(next, start, end, uf); + + if (error) + goto userfaultfd_error; + } +#ifdef CONFIG_DEBUG_VM_MAPLE_TREE + BUG_ON(next->vm_start < start); + BUG_ON(next->vm_start > end); +#endif + } for_each_vma_range(*vmi, next, end); + +#if defined(CONFIG_DEBUG_VM_MAPLE_TREE) + /* Make sure no VMAs are about to be lost. */ + { + MA_STATE(test, &mt_detach, 0, 0); + struct vm_area_struct *vma_mas, *vma_test; + int test_count = 0; + + vma_iter_set(vmi, start); + rcu_read_lock(); + vma_test = mas_find(&test, count - 1); + for_each_vma_range(*vmi, vma_mas, end) { + BUG_ON(vma_mas != vma_test); + test_count++; + vma_test = mas_next(&test, count - 1); + } + rcu_read_unlock(); + BUG_ON(count != test_count); + } +#endif + + while (vma_iter_addr(vmi) > start) + vma_iter_prev_range(vmi); + + error = vma_iter_clear_gfp(vmi, start, end, GFP_KERNEL); + if (error) + goto clear_tree_failed; + + /* Point of no return */ + mm->locked_vm -= locked_vm; + mm->map_count -= count; + if (unlock) + mmap_write_downgrade(mm); + + prev = vma_iter_prev_range(vmi); + next = vma_next(vmi); + if (next) + vma_iter_prev_range(vmi); + + /* + * We can free page tables without write-locking mmap_lock because VMAs + * were isolated before we downgraded mmap_lock. + */ + mas_set(&mas_detach, 1); + unmap_region(mm, &mas_detach, vma, prev, next, start, end, count, + !unlock); + /* Statistics and freeing VMAs */ + mas_set(&mas_detach, 0); + remove_mt(mm, &mas_detach); + validate_mm(mm); + if (unlock) + mmap_read_unlock(mm); + + __mt_destroy(&mt_detach); + return 0; + +clear_tree_failed: +userfaultfd_error: +munmap_gather_failed: +end_split_failed: + mas_set(&mas_detach, 0); + mas_for_each(&mas_detach, next, end) + vma_mark_detached(next, false); + + __mt_destroy(&mt_detach); +start_split_failed: +map_count_exceeded: + validate_mm(mm); + return error; +} + +/* + * do_vmi_munmap() - munmap a given range. + * @vmi: The vma iterator + * @mm: The mm_struct + * @start: The start address to munmap + * @len: The length of the range to munmap + * @uf: The userfaultfd list_head + * @unlock: set to true if the user wants to drop the mmap_lock on success + * + * This function takes a @mas that is either pointing to the previous VMA or set + * to MA_START and sets it up to remove the mapping(s). The @len will be + * aligned and any arch_unmap work will be preformed. + * + * Return: 0 on success and drops the lock if so directed, error and leaves the + * lock held otherwise. + */ +int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm, + unsigned long start, size_t len, struct list_head *uf, + bool unlock) +{ + unsigned long end; + struct vm_area_struct *vma; + + if ((offset_in_page(start)) || start > TASK_SIZE || len > TASK_SIZE-start) + return -EINVAL; + + end = start + PAGE_ALIGN(len); + if (end == start) + return -EINVAL; + + /* + * Check if memory is sealed before arch_unmap. + * Prevent unmapping a sealed VMA. + * can_modify_mm assumes we have acquired the lock on MM. + */ + if (unlikely(!can_modify_mm(mm, start, end))) + return -EPERM; + + /* arch_unmap() might do unmaps itself. */ + arch_unmap(mm, start, end); + + /* Find the first overlapping VMA */ + vma = vma_find(vmi, end); + if (!vma) { + if (unlock) + mmap_write_unlock(mm); + return 0; + } + + return do_vmi_align_munmap(vmi, vma, mm, start, end, uf, unlock); +} + +/* + * Given a mapping request (addr,end,vm_flags,file,pgoff,anon_name), + * figure out whether that can be merged with its predecessor or its + * successor. Or both (it neatly fills a hole). + * + * In most cases - when called for mmap, brk or mremap - [addr,end) is + * certain not to be mapped by the time vma_merge is called; but when + * called for mprotect, it is certain to be already mapped (either at + * an offset within prev, or at the start of next), and the flags of + * this area are about to be changed to vm_flags - and the no-change + * case has already been eliminated. + * + * The following mprotect cases have to be considered, where **** is + * the area passed down from mprotect_fixup, never extending beyond one + * vma, PPPP is the previous vma, CCCC is a concurrent vma that starts + * at the same address as **** and is of the same or larger span, and + * NNNN the next vma after ****: + * + * **** **** **** + * PPPPPPNNNNNN PPPPPPNNNNNN PPPPPPCCCCCC + * cannot merge might become might become + * PPNNNNNNNNNN PPPPPPPPPPCC + * mmap, brk or case 4 below case 5 below + * mremap move: + * **** **** + * PPPP NNNN PPPPCCCCNNNN + * might become might become + * PPPPPPPPPPPP 1 or PPPPPPPPPPPP 6 or + * PPPPPPPPNNNN 2 or PPPPPPPPNNNN 7 or + * PPPPNNNNNNNN 3 PPPPNNNNNNNN 8 + * + * It is important for case 8 that the vma CCCC overlapping the + * region **** is never going to extended over NNNN. Instead NNNN must + * be extended in region **** and CCCC must be removed. This way in + * all cases where vma_merge succeeds, the moment vma_merge drops the + * rmap_locks, the properties of the merged vma will be already + * correct for the whole merged range. Some of those properties like + * vm_page_prot/vm_flags may be accessed by rmap_walks and they must + * be correct for the whole merged range immediately after the + * rmap_locks are released. Otherwise if NNNN would be removed and + * CCCC would be extended over the NNNN range, remove_migration_ptes + * or other rmap walkers (if working on addresses beyond the "end" + * parameter) may establish ptes with the wrong permissions of CCCC + * instead of the right permissions of NNNN. + * + * In the code below: + * PPPP is represented by *prev + * CCCC is represented by *curr or not represented at all (NULL) + * NNNN is represented by *next or not represented at all (NULL) + * **** is not represented - it will be merged and the vma containing the + * area is returned, or the function will return NULL + */ +static struct vm_area_struct +*vma_merge(struct vma_iterator *vmi, struct vm_area_struct *prev, + struct vm_area_struct *src, unsigned long addr, unsigned long end, + unsigned long vm_flags, pgoff_t pgoff, struct mempolicy *policy, + struct vm_userfaultfd_ctx vm_userfaultfd_ctx, + struct anon_vma_name *anon_name) +{ + struct mm_struct *mm = src->vm_mm; + struct anon_vma *anon_vma = src->anon_vma; + struct file *file = src->vm_file; + struct vm_area_struct *curr, *next, *res; + struct vm_area_struct *vma, *adjust, *remove, *remove2; + struct vm_area_struct *anon_dup = NULL; + struct vma_prepare vp; + pgoff_t vma_pgoff; + int err = 0; + bool merge_prev = false; + bool merge_next = false; + bool vma_expanded = false; + unsigned long vma_start = addr; + unsigned long vma_end = end; + pgoff_t pglen = (end - addr) >> PAGE_SHIFT; + long adj_start = 0; + + /* + * We later require that vma->vm_flags == vm_flags, + * so this tests vma->vm_flags & VM_SPECIAL, too. + */ + if (vm_flags & VM_SPECIAL) + return NULL; + + /* Does the input range span an existing VMA? (cases 5 - 8) */ + curr = find_vma_intersection(mm, prev ? prev->vm_end : 0, end); + + if (!curr || /* cases 1 - 4 */ + end == curr->vm_end) /* cases 6 - 8, adjacent VMA */ + next = vma_lookup(mm, end); + else + next = NULL; /* case 5 */ + + if (prev) { + vma_start = prev->vm_start; + vma_pgoff = prev->vm_pgoff; + + /* Can we merge the predecessor? */ + if (addr == prev->vm_end && mpol_equal(vma_policy(prev), policy) + && can_vma_merge_after(prev, vm_flags, anon_vma, file, + pgoff, vm_userfaultfd_ctx, anon_name)) { + merge_prev = true; + vma_prev(vmi); + } + } + + /* Can we merge the successor? */ + if (next && mpol_equal(policy, vma_policy(next)) && + can_vma_merge_before(next, vm_flags, anon_vma, file, pgoff+pglen, + vm_userfaultfd_ctx, anon_name)) { + merge_next = true; + } + + /* Verify some invariant that must be enforced by the caller. */ + VM_WARN_ON(prev && addr <= prev->vm_start); + VM_WARN_ON(curr && (addr != curr->vm_start || end > curr->vm_end)); + VM_WARN_ON(addr >= end); + + if (!merge_prev && !merge_next) + return NULL; /* Not mergeable. */ + + if (merge_prev) + vma_start_write(prev); + + res = vma = prev; + remove = remove2 = adjust = NULL; + + /* Can we merge both the predecessor and the successor? */ + if (merge_prev && merge_next && + is_mergeable_anon_vma(prev->anon_vma, next->anon_vma, NULL)) { + vma_start_write(next); + remove = next; /* case 1 */ + vma_end = next->vm_end; + err = dup_anon_vma(prev, next, &anon_dup); + if (curr) { /* case 6 */ + vma_start_write(curr); + remove = curr; + remove2 = next; + /* + * Note that the dup_anon_vma below cannot overwrite err + * since the first caller would do nothing unless next + * has an anon_vma. + */ + if (!next->anon_vma) + err = dup_anon_vma(prev, curr, &anon_dup); + } + } else if (merge_prev) { /* case 2 */ + if (curr) { + vma_start_write(curr); + if (end == curr->vm_end) { /* case 7 */ + /* + * can_vma_merge_after() assumed we would not be + * removing prev vma, so it skipped the check + * for vm_ops->close, but we are removing curr + */ + if (curr->vm_ops && curr->vm_ops->close) + err = -EINVAL; + remove = curr; + } else { /* case 5 */ + adjust = curr; + adj_start = (end - curr->vm_start); + } + if (!err) + err = dup_anon_vma(prev, curr, &anon_dup); + } + } else { /* merge_next */ + vma_start_write(next); + res = next; + if (prev && addr < prev->vm_end) { /* case 4 */ + vma_start_write(prev); + vma_end = addr; + adjust = next; + adj_start = -(prev->vm_end - addr); + err = dup_anon_vma(next, prev, &anon_dup); + } else { + /* + * Note that cases 3 and 8 are the ONLY ones where prev + * is permitted to be (but is not necessarily) NULL. + */ + vma = next; /* case 3 */ + vma_start = addr; + vma_end = next->vm_end; + vma_pgoff = next->vm_pgoff - pglen; + if (curr) { /* case 8 */ + vma_pgoff = curr->vm_pgoff; + vma_start_write(curr); + remove = curr; + err = dup_anon_vma(next, curr, &anon_dup); + } + } + } + + /* Error in anon_vma clone. */ + if (err) + goto anon_vma_fail; + + if (vma_start < vma->vm_start || vma_end > vma->vm_end) + vma_expanded = true; + + if (vma_expanded) { + vma_iter_config(vmi, vma_start, vma_end); + } else { + vma_iter_config(vmi, adjust->vm_start + adj_start, + adjust->vm_end); + } + + if (vma_iter_prealloc(vmi, vma)) + goto prealloc_fail; + + init_multi_vma_prep(&vp, vma, adjust, remove, remove2); + VM_WARN_ON(vp.anon_vma && adjust && adjust->anon_vma && + vp.anon_vma != adjust->anon_vma); + + vma_prepare(&vp); + vma_adjust_trans_huge(vma, vma_start, vma_end, adj_start); + vma_set_range(vma, vma_start, vma_end, vma_pgoff); + + if (vma_expanded) + vma_iter_store(vmi, vma); + + if (adj_start) { + adjust->vm_start += adj_start; + adjust->vm_pgoff += adj_start >> PAGE_SHIFT; + if (adj_start < 0) { + WARN_ON(vma_expanded); + vma_iter_store(vmi, next); + } + } + + vma_complete(&vp, vmi, mm); + khugepaged_enter_vma(res, vm_flags); + return res; + +prealloc_fail: + if (anon_dup) + unlink_anon_vmas(anon_dup); + +anon_vma_fail: + vma_iter_set(vmi, addr); + vma_iter_load(vmi); + return NULL; +} + +/* + * We are about to modify one or multiple of a VMA's flags, policy, userfaultfd + * context and anonymous VMA name within the range [start, end). + * + * As a result, we might be able to merge the newly modified VMA range with an + * adjacent VMA with identical properties. + * + * If no merge is possible and the range does not span the entirety of the VMA, + * we then need to split the VMA to accommodate the change. + * + * The function returns either the merged VMA, the original VMA if a split was + * required instead, or an error if the split failed. + */ +struct vm_area_struct *vma_modify(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, unsigned long end, + unsigned long vm_flags, + struct mempolicy *policy, + struct vm_userfaultfd_ctx uffd_ctx, + struct anon_vma_name *anon_name) +{ + pgoff_t pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); + struct vm_area_struct *merged; + + merged = vma_merge(vmi, prev, vma, start, end, vm_flags, + pgoff, policy, uffd_ctx, anon_name); + if (merged) + return merged; + + if (vma->vm_start < start) { + int err = split_vma(vmi, vma, start, 1); + + if (err) + return ERR_PTR(err); + } + + if (vma->vm_end > end) { + int err = split_vma(vmi, vma, end, 0); + + if (err) + return ERR_PTR(err); + } + + return vma; +} + +/* + * Attempt to merge a newly mapped VMA with those adjacent to it. The caller + * must ensure that [start, end) does not overlap any existing VMA. + */ +struct vm_area_struct +*vma_merge_new_vma(struct vma_iterator *vmi, struct vm_area_struct *prev, + struct vm_area_struct *vma, unsigned long start, + unsigned long end, pgoff_t pgoff) +{ + return vma_merge(vmi, prev, vma, start, end, vma->vm_flags, pgoff, + vma_policy(vma), vma->vm_userfaultfd_ctx, anon_vma_name(vma)); +} + +/* + * Expand vma by delta bytes, potentially merging with an immediately adjacent + * VMA with identical properties. + */ +struct vm_area_struct *vma_merge_extend(struct vma_iterator *vmi, + struct vm_area_struct *vma, + unsigned long delta) +{ + pgoff_t pgoff = vma->vm_pgoff + vma_pages(vma); + + /* vma is specified as prev, so case 1 or 2 will apply. */ + return vma_merge(vmi, vma, vma, vma->vm_end, vma->vm_end + delta, + vma->vm_flags, pgoff, vma_policy(vma), + vma->vm_userfaultfd_ctx, anon_vma_name(vma)); +} + +void unlink_file_vma_batch_init(struct unlink_vma_file_batch *vb) +{ + vb->count = 0; +} + +static void unlink_file_vma_batch_process(struct unlink_vma_file_batch *vb) +{ + struct address_space *mapping; + int i; + + mapping = vb->vmas[0]->vm_file->f_mapping; + i_mmap_lock_write(mapping); + for (i = 0; i < vb->count; i++) { + VM_WARN_ON_ONCE(vb->vmas[i]->vm_file->f_mapping != mapping); + __remove_shared_vm_struct(vb->vmas[i], mapping); + } + i_mmap_unlock_write(mapping); + + unlink_file_vma_batch_init(vb); +} + +void unlink_file_vma_batch_add(struct unlink_vma_file_batch *vb, + struct vm_area_struct *vma) +{ + if (vma->vm_file == NULL) + return; + + if ((vb->count > 0 && vb->vmas[0]->vm_file != vma->vm_file) || + vb->count == ARRAY_SIZE(vb->vmas)) + unlink_file_vma_batch_process(vb); + + vb->vmas[vb->count] = vma; + vb->count++; +} + +void unlink_file_vma_batch_final(struct unlink_vma_file_batch *vb) +{ + if (vb->count > 0) + unlink_file_vma_batch_process(vb); +} + +/* + * Unlink a file-based vm structure from its interval tree, to hide + * vma from rmap and vmtruncate before freeing its page tables. + */ +void unlink_file_vma(struct vm_area_struct *vma) +{ + struct file *file = vma->vm_file; + + if (file) { + struct address_space *mapping = file->f_mapping; + + i_mmap_lock_write(mapping); + __remove_shared_vm_struct(vma, mapping); + i_mmap_unlock_write(mapping); + } +} + +void vma_link_file(struct vm_area_struct *vma) +{ + struct file *file = vma->vm_file; + struct address_space *mapping; + + if (file) { + mapping = file->f_mapping; + i_mmap_lock_write(mapping); + __vma_link_file(vma, mapping); + i_mmap_unlock_write(mapping); + } +} + +int vma_link(struct mm_struct *mm, struct vm_area_struct *vma) +{ + VMA_ITERATOR(vmi, mm, 0); + + vma_iter_config(&vmi, vma->vm_start, vma->vm_end); + if (vma_iter_prealloc(&vmi, vma)) + return -ENOMEM; + + vma_start_write(vma); + vma_iter_store(&vmi, vma); + vma_link_file(vma); + mm->map_count++; + validate_mm(mm); + return 0; +} + +/* + * Copy the vma structure to a new location in the same mm, + * prior to moving page table entries, to effect an mremap move. + */ +struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, + unsigned long addr, unsigned long len, pgoff_t pgoff, + bool *need_rmap_locks) +{ + struct vm_area_struct *vma = *vmap; + unsigned long vma_start = vma->vm_start; + struct mm_struct *mm = vma->vm_mm; + struct vm_area_struct *new_vma, *prev; + bool faulted_in_anon_vma = true; + VMA_ITERATOR(vmi, mm, addr); + + /* + * If anonymous vma has not yet been faulted, update new pgoff + * to match new location, to increase its chance of merging. + */ + if (unlikely(vma_is_anonymous(vma) && !vma->anon_vma)) { + pgoff = addr >> PAGE_SHIFT; + faulted_in_anon_vma = false; + } + + new_vma = find_vma_prev(mm, addr, &prev); + if (new_vma && new_vma->vm_start < addr + len) + return NULL; /* should never get here */ + + new_vma = vma_merge_new_vma(&vmi, prev, vma, addr, addr + len, pgoff); + if (new_vma) { + /* + * Source vma may have been merged into new_vma + */ + if (unlikely(vma_start >= new_vma->vm_start && + vma_start < new_vma->vm_end)) { + /* + * The only way we can get a vma_merge with + * self during an mremap is if the vma hasn't + * been faulted in yet and we were allowed to + * reset the dst vma->vm_pgoff to the + * destination address of the mremap to allow + * the merge to happen. mremap must change the + * vm_pgoff linearity between src and dst vmas + * (in turn preventing a vma_merge) to be + * safe. It is only safe to keep the vm_pgoff + * linear if there are no pages mapped yet. + */ + VM_BUG_ON_VMA(faulted_in_anon_vma, new_vma); + *vmap = vma = new_vma; + } + *need_rmap_locks = (new_vma->vm_pgoff <= vma->vm_pgoff); + } else { + new_vma = vm_area_dup(vma); + if (!new_vma) + goto out; + vma_set_range(new_vma, addr, addr + len, pgoff); + if (vma_dup_policy(vma, new_vma)) + goto out_free_vma; + if (anon_vma_clone(new_vma, vma)) + goto out_free_mempol; + if (new_vma->vm_file) + get_file(new_vma->vm_file); + if (new_vma->vm_ops && new_vma->vm_ops->open) + new_vma->vm_ops->open(new_vma); + if (vma_link(mm, new_vma)) + goto out_vma_link; + *need_rmap_locks = false; + } + return new_vma; + +out_vma_link: + if (new_vma->vm_ops && new_vma->vm_ops->close) + new_vma->vm_ops->close(new_vma); + + if (new_vma->vm_file) + fput(new_vma->vm_file); + + unlink_anon_vmas(new_vma); +out_free_mempol: + mpol_put(vma_policy(new_vma)); +out_free_vma: + vm_area_free(new_vma); +out: + return NULL; +} + +/* + * Rough compatibility check to quickly see if it's even worth looking + * at sharing an anon_vma. + * + * They need to have the same vm_file, and the flags can only differ + * in things that mprotect may change. + * + * NOTE! The fact that we share an anon_vma doesn't _have_ to mean that + * we can merge the two vma's. For example, we refuse to merge a vma if + * there is a vm_ops->close() function, because that indicates that the + * driver is doing some kind of reference counting. But that doesn't + * really matter for the anon_vma sharing case. + */ +static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct *b) +{ + return a->vm_end == b->vm_start && + mpol_equal(vma_policy(a), vma_policy(b)) && + a->vm_file == b->vm_file && + !((a->vm_flags ^ b->vm_flags) & ~(VM_ACCESS_FLAGS | VM_SOFTDIRTY)) && + b->vm_pgoff == a->vm_pgoff + ((b->vm_start - a->vm_start) >> PAGE_SHIFT); +} + +/* + * Do some basic sanity checking to see if we can re-use the anon_vma + * from 'old'. The 'a'/'b' vma's are in VM order - one of them will be + * the same as 'old', the other will be the new one that is trying + * to share the anon_vma. + * + * NOTE! This runs with mmap_lock held for reading, so it is possible that + * the anon_vma of 'old' is concurrently in the process of being set up + * by another page fault trying to merge _that_. But that's ok: if it + * is being set up, that automatically means that it will be a singleton + * acceptable for merging, so we can do all of this optimistically. But + * we do that READ_ONCE() to make sure that we never re-load the pointer. + * + * IOW: that the "list_is_singular()" test on the anon_vma_chain only + * matters for the 'stable anon_vma' case (ie the thing we want to avoid + * is to return an anon_vma that is "complex" due to having gone through + * a fork). + * + * We also make sure that the two vma's are compatible (adjacent, + * and with the same memory policies). That's all stable, even with just + * a read lock on the mmap_lock. + */ +static struct anon_vma *reusable_anon_vma(struct vm_area_struct *old, + struct vm_area_struct *a, + struct vm_area_struct *b) +{ + if (anon_vma_compatible(a, b)) { + struct anon_vma *anon_vma = READ_ONCE(old->anon_vma); + + if (anon_vma && list_is_singular(&old->anon_vma_chain)) + return anon_vma; + } + return NULL; +} + +/* + * find_mergeable_anon_vma is used by anon_vma_prepare, to check + * neighbouring vmas for a suitable anon_vma, before it goes off + * to allocate a new anon_vma. It checks because a repetitive + * sequence of mprotects and faults may otherwise lead to distinct + * anon_vmas being allocated, preventing vma merge in subsequent + * mprotect. + */ +struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma) +{ + struct anon_vma *anon_vma = NULL; + struct vm_area_struct *prev, *next; + VMA_ITERATOR(vmi, vma->vm_mm, vma->vm_end); + + /* Try next first. */ + next = vma_iter_load(&vmi); + if (next) { + anon_vma = reusable_anon_vma(next, vma, next); + if (anon_vma) + return anon_vma; + } + + prev = vma_prev(&vmi); + VM_BUG_ON_VMA(prev != vma, vma); + prev = vma_prev(&vmi); + /* Try prev next. */ + if (prev) + anon_vma = reusable_anon_vma(prev, prev, vma); + + /* + * We might reach here with anon_vma == NULL if we can't find + * any reusable anon_vma. + * There's no absolute need to look only at touching neighbours: + * we could search further afield for "compatible" anon_vmas. + * But it would probably just be a waste of time searching, + * or lead to too many vmas hanging off the same anon_vma. + * We're trying to allow mprotect remerging later on, + * not trying to minimize memory used for anon_vmas. + */ + return anon_vma; +} + +static bool vm_ops_needs_writenotify(const struct vm_operations_struct *vm_ops) +{ + return vm_ops && (vm_ops->page_mkwrite || vm_ops->pfn_mkwrite); +} + +static bool vma_is_shared_writable(struct vm_area_struct *vma) +{ + return (vma->vm_flags & (VM_WRITE | VM_SHARED)) == + (VM_WRITE | VM_SHARED); +} + +static bool vma_fs_can_writeback(struct vm_area_struct *vma) +{ + /* No managed pages to writeback. */ + if (vma->vm_flags & VM_PFNMAP) + return false; + + return vma->vm_file && vma->vm_file->f_mapping && + mapping_can_writeback(vma->vm_file->f_mapping); +} + +/* + * Does this VMA require the underlying folios to have their dirty state + * tracked? + */ +bool vma_needs_dirty_tracking(struct vm_area_struct *vma) +{ + /* Only shared, writable VMAs require dirty tracking. */ + if (!vma_is_shared_writable(vma)) + return false; + + /* Does the filesystem need to be notified? */ + if (vm_ops_needs_writenotify(vma->vm_ops)) + return true; + + /* + * Even if the filesystem doesn't indicate a need for writenotify, if it + * can writeback, dirty tracking is still required. + */ + return vma_fs_can_writeback(vma); +} + +/* + * Some shared mappings will want the pages marked read-only + * to track write events. If so, we'll downgrade vm_page_prot + * to the private version (using protection_map[] without the + * VM_SHARED bit). + */ +bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot) +{ + /* If it was private or non-writable, the write bit is already clear */ + if (!vma_is_shared_writable(vma)) + return false; + + /* The backer wishes to know when pages are first written to? */ + if (vm_ops_needs_writenotify(vma->vm_ops)) + return true; + + /* The open routine did something to the protections that pgprot_modify + * won't preserve? */ + if (pgprot_val(vm_page_prot) != + pgprot_val(vm_pgprot_modify(vm_page_prot, vma->vm_flags))) + return false; + + /* + * Do we need to track softdirty? hugetlb does not support softdirty + * tracking yet. + */ + if (vma_soft_dirty_enabled(vma) && !is_vm_hugetlb_page(vma)) + return true; + + /* Do we need write faults for uffd-wp tracking? */ + if (userfaultfd_wp(vma)) + return true; + + /* Can the mapping track the dirty pages? */ + return vma_fs_can_writeback(vma); +} + +unsigned long count_vma_pages_range(struct mm_struct *mm, + unsigned long addr, unsigned long end) +{ + VMA_ITERATOR(vmi, mm, addr); + struct vm_area_struct *vma; + unsigned long nr_pages = 0; + + for_each_vma_range(vmi, vma, end) { + unsigned long vm_start = max(addr, vma->vm_start); + unsigned long vm_end = min(end, vma->vm_end); + + nr_pages += PHYS_PFN(vm_end - vm_start); + } + + return nr_pages; +} + +static DEFINE_MUTEX(mm_all_locks_mutex); + +static void vm_lock_anon_vma(struct mm_struct *mm, struct anon_vma *anon_vma) +{ + if (!test_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) { + /* + * The LSB of head.next can't change from under us + * because we hold the mm_all_locks_mutex. + */ + down_write_nest_lock(&anon_vma->root->rwsem, &mm->mmap_lock); + /* + * We can safely modify head.next after taking the + * anon_vma->root->rwsem. If some other vma in this mm shares + * the same anon_vma we won't take it again. + * + * No need of atomic instructions here, head.next + * can't change from under us thanks to the + * anon_vma->root->rwsem. + */ + if (__test_and_set_bit(0, (unsigned long *) + &anon_vma->root->rb_root.rb_root.rb_node)) + BUG(); + } +} + +static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping) +{ + if (!test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) { + /* + * AS_MM_ALL_LOCKS can't change from under us because + * we hold the mm_all_locks_mutex. + * + * Operations on ->flags have to be atomic because + * even if AS_MM_ALL_LOCKS is stable thanks to the + * mm_all_locks_mutex, there may be other cpus + * changing other bitflags in parallel to us. + */ + if (test_and_set_bit(AS_MM_ALL_LOCKS, &mapping->flags)) + BUG(); + down_write_nest_lock(&mapping->i_mmap_rwsem, &mm->mmap_lock); + } +} + +/* + * This operation locks against the VM for all pte/vma/mm related + * operations that could ever happen on a certain mm. This includes + * vmtruncate, try_to_unmap, and all page faults. + * + * The caller must take the mmap_lock in write mode before calling + * mm_take_all_locks(). The caller isn't allowed to release the + * mmap_lock until mm_drop_all_locks() returns. + * + * mmap_lock in write mode is required in order to block all operations + * that could modify pagetables and free pages without need of + * altering the vma layout. It's also needed in write mode to avoid new + * anon_vmas to be associated with existing vmas. + * + * A single task can't take more than one mm_take_all_locks() in a row + * or it would deadlock. + * + * The LSB in anon_vma->rb_root.rb_node and the AS_MM_ALL_LOCKS bitflag in + * mapping->flags avoid to take the same lock twice, if more than one + * vma in this mm is backed by the same anon_vma or address_space. + * + * We take locks in following order, accordingly to comment at beginning + * of mm/rmap.c: + * - all hugetlbfs_i_mmap_rwsem_key locks (aka mapping->i_mmap_rwsem for + * hugetlb mapping); + * - all vmas marked locked + * - all i_mmap_rwsem locks; + * - all anon_vma->rwseml + * + * We can take all locks within these types randomly because the VM code + * doesn't nest them and we protected from parallel mm_take_all_locks() by + * mm_all_locks_mutex. + * + * mm_take_all_locks() and mm_drop_all_locks are expensive operations + * that may have to take thousand of locks. + * + * mm_take_all_locks() can fail if it's interrupted by signals. + */ +int mm_take_all_locks(struct mm_struct *mm) +{ + struct vm_area_struct *vma; + struct anon_vma_chain *avc; + VMA_ITERATOR(vmi, mm, 0); + + mmap_assert_write_locked(mm); + + mutex_lock(&mm_all_locks_mutex); + + /* + * vma_start_write() does not have a complement in mm_drop_all_locks() + * because vma_start_write() is always asymmetrical; it marks a VMA as + * being written to until mmap_write_unlock() or mmap_write_downgrade() + * is reached. + */ + for_each_vma(vmi, vma) { + if (signal_pending(current)) + goto out_unlock; + vma_start_write(vma); + } + + vma_iter_init(&vmi, mm, 0); + for_each_vma(vmi, vma) { + if (signal_pending(current)) + goto out_unlock; + if (vma->vm_file && vma->vm_file->f_mapping && + is_vm_hugetlb_page(vma)) + vm_lock_mapping(mm, vma->vm_file->f_mapping); + } + + vma_iter_init(&vmi, mm, 0); + for_each_vma(vmi, vma) { + if (signal_pending(current)) + goto out_unlock; + if (vma->vm_file && vma->vm_file->f_mapping && + !is_vm_hugetlb_page(vma)) + vm_lock_mapping(mm, vma->vm_file->f_mapping); + } + + vma_iter_init(&vmi, mm, 0); + for_each_vma(vmi, vma) { + if (signal_pending(current)) + goto out_unlock; + if (vma->anon_vma) + list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) + vm_lock_anon_vma(mm, avc->anon_vma); + } + + return 0; + +out_unlock: + mm_drop_all_locks(mm); + return -EINTR; +} + +static void vm_unlock_anon_vma(struct anon_vma *anon_vma) +{ + if (test_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) { + /* + * The LSB of head.next can't change to 0 from under + * us because we hold the mm_all_locks_mutex. + * + * We must however clear the bitflag before unlocking + * the vma so the users using the anon_vma->rb_root will + * never see our bitflag. + * + * No need of atomic instructions here, head.next + * can't change from under us until we release the + * anon_vma->root->rwsem. + */ + if (!__test_and_clear_bit(0, (unsigned long *) + &anon_vma->root->rb_root.rb_root.rb_node)) + BUG(); + anon_vma_unlock_write(anon_vma); + } +} + +static void vm_unlock_mapping(struct address_space *mapping) +{ + if (test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) { + /* + * AS_MM_ALL_LOCKS can't change to 0 from under us + * because we hold the mm_all_locks_mutex. + */ + i_mmap_unlock_write(mapping); + if (!test_and_clear_bit(AS_MM_ALL_LOCKS, + &mapping->flags)) + BUG(); + } +} + +/* + * The mmap_lock cannot be released by the caller until + * mm_drop_all_locks() returns. + */ +void mm_drop_all_locks(struct mm_struct *mm) +{ + struct vm_area_struct *vma; + struct anon_vma_chain *avc; + VMA_ITERATOR(vmi, mm, 0); + + mmap_assert_write_locked(mm); + BUG_ON(!mutex_is_locked(&mm_all_locks_mutex)); + + for_each_vma(vmi, vma) { + if (vma->anon_vma) + list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) + vm_unlock_anon_vma(avc->anon_vma); + if (vma->vm_file && vma->vm_file->f_mapping) + vm_unlock_mapping(vma->vm_file->f_mapping); + } + + mutex_unlock(&mm_all_locks_mutex); +} diff --git a/mm/vma.h b/mm/vma.h new file mode 100644 index 000000000000..6efdf1768a0a --- /dev/null +++ b/mm/vma.h @@ -0,0 +1,364 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * vma.h + * + * Core VMA manipulation API implemented in vma.c. + */ +#ifndef __MM_VMA_H +#define __MM_VMA_H + +/* + * VMA lock generalization + */ +struct vma_prepare { + struct vm_area_struct *vma; + struct vm_area_struct *adj_next; + struct file *file; + struct address_space *mapping; + struct anon_vma *anon_vma; + struct vm_area_struct *insert; + struct vm_area_struct *remove; + struct vm_area_struct *remove2; +}; + +struct unlink_vma_file_batch { + int count; + struct vm_area_struct *vmas[8]; +}; + +#ifdef CONFIG_DEBUG_VM_MAPLE_TREE +void validate_mm(struct mm_struct *mm); +#else +#define validate_mm(mm) do { } while (0) +#endif + +/* Required for expand_downwards(). */ +void anon_vma_interval_tree_pre_update_vma(struct vm_area_struct *vma); + +/* Required for expand_downwards(). */ +void anon_vma_interval_tree_post_update_vma(struct vm_area_struct *vma); + +/* Required for do_brk_flags(). */ +void vma_prepare(struct vma_prepare *vp); + +/* Required for do_brk_flags(). */ +void init_vma_prep(struct vma_prepare *vp, + struct vm_area_struct *vma); + +/* Required for do_brk_flags(). */ +void vma_complete(struct vma_prepare *vp, + struct vma_iterator *vmi, struct mm_struct *mm); + +int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma, + unsigned long start, unsigned long end, pgoff_t pgoff, + struct vm_area_struct *next); + +int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma, + unsigned long start, unsigned long end, pgoff_t pgoff); + +int +do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, + struct mm_struct *mm, unsigned long start, + unsigned long end, struct list_head *uf, bool unlock); + +int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm, + unsigned long start, size_t len, struct list_head *uf, + bool unlock); + +void remove_vma(struct vm_area_struct *vma, bool unreachable); + +void unmap_region(struct mm_struct *mm, struct ma_state *mas, + struct vm_area_struct *vma, struct vm_area_struct *prev, + struct vm_area_struct *next, unsigned long start, + unsigned long end, unsigned long tree_end, bool mm_wr_locked); + +/* Required by mmap_region(). */ +bool +can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags, + struct anon_vma *anon_vma, struct file *file, + pgoff_t vm_pgoff, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, + struct anon_vma_name *anon_name); + +/* Required by mmap_region() and do_brk_flags(). */ +bool +can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, + struct anon_vma *anon_vma, struct file *file, + pgoff_t vm_pgoff, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, + struct anon_vma_name *anon_name); + +struct vm_area_struct *vma_modify(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, unsigned long end, + unsigned long vm_flags, + struct mempolicy *policy, + struct vm_userfaultfd_ctx uffd_ctx, + struct anon_vma_name *anon_name); + +/* We are about to modify the VMA's flags. */ +static inline struct vm_area_struct +*vma_modify_flags(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, unsigned long end, + unsigned long new_flags) +{ + return vma_modify(vmi, prev, vma, start, end, new_flags, + vma_policy(vma), vma->vm_userfaultfd_ctx, + anon_vma_name(vma)); +} + +/* We are about to modify the VMA's flags and/or anon_name. */ +static inline struct vm_area_struct +*vma_modify_flags_name(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, + unsigned long end, + unsigned long new_flags, + struct anon_vma_name *new_name) +{ + return vma_modify(vmi, prev, vma, start, end, new_flags, + vma_policy(vma), vma->vm_userfaultfd_ctx, new_name); +} + +/* We are about to modify the VMA's memory policy. */ +static inline struct vm_area_struct +*vma_modify_policy(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, unsigned long end, + struct mempolicy *new_pol) +{ + return vma_modify(vmi, prev, vma, start, end, vma->vm_flags, + new_pol, vma->vm_userfaultfd_ctx, anon_vma_name(vma)); +} + +/* We are about to modify the VMA's flags and/or uffd context. */ +static inline struct vm_area_struct +*vma_modify_flags_uffd(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, unsigned long end, + unsigned long new_flags, + struct vm_userfaultfd_ctx new_ctx) +{ + return vma_modify(vmi, prev, vma, start, end, new_flags, + vma_policy(vma), new_ctx, anon_vma_name(vma)); +} + +struct vm_area_struct +*vma_merge_new_vma(struct vma_iterator *vmi, struct vm_area_struct *prev, + struct vm_area_struct *vma, unsigned long start, + unsigned long end, pgoff_t pgoff); + +struct vm_area_struct *vma_merge_extend(struct vma_iterator *vmi, + struct vm_area_struct *vma, + unsigned long delta); + +void unlink_file_vma_batch_init(struct unlink_vma_file_batch *vb); + +void unlink_file_vma_batch_final(struct unlink_vma_file_batch *vb); + +void unlink_file_vma_batch_add(struct unlink_vma_file_batch *vb, + struct vm_area_struct *vma); + +void unlink_file_vma(struct vm_area_struct *vma); + +void vma_link_file(struct vm_area_struct *vma); + +int vma_link(struct mm_struct *mm, struct vm_area_struct *vma); + +struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, + unsigned long addr, unsigned long len, pgoff_t pgoff, + bool *need_rmap_locks); + +struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma); + +bool vma_needs_dirty_tracking(struct vm_area_struct *vma); +bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot); + +int mm_take_all_locks(struct mm_struct *mm); +void mm_drop_all_locks(struct mm_struct *mm); +unsigned long count_vma_pages_range(struct mm_struct *mm, + unsigned long addr, unsigned long end); + +static inline bool vma_wants_manual_pte_write_upgrade(struct vm_area_struct *vma) +{ + /* + * We want to check manually if we can change individual PTEs writable + * if we can't do that automatically for all PTEs in a mapping. For + * private mappings, that's always the case when we have write + * permissions as we properly have to handle COW. + */ + if (vma->vm_flags & VM_SHARED) + return vma_wants_writenotify(vma, vma->vm_page_prot); + return !!(vma->vm_flags & VM_WRITE); +} + +#ifdef CONFIG_MMU +static inline pgprot_t vm_pgprot_modify(pgprot_t oldprot, unsigned long vm_flags) +{ + return pgprot_modify(oldprot, vm_get_page_prot(vm_flags)); +} +#endif + +static inline struct vm_area_struct *vma_prev_limit(struct vma_iterator *vmi, + unsigned long min) +{ + return mas_prev(&vmi->mas, min); +} + +static inline int vma_iter_store_gfp(struct vma_iterator *vmi, + struct vm_area_struct *vma, gfp_t gfp) +{ + if (vmi->mas.status != ma_start && + ((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start))) + vma_iter_invalidate(vmi); + + __mas_set_range(&vmi->mas, vma->vm_start, vma->vm_end - 1); + mas_store_gfp(&vmi->mas, vma, gfp); + if (unlikely(mas_is_err(&vmi->mas))) + return -ENOMEM; + + return 0; +} + + +/* + * These three helpers classifies VMAs for virtual memory accounting. + */ + +/* + * Executable code area - executable, not writable, not stack + */ +static inline bool is_exec_mapping(vm_flags_t flags) +{ + return (flags & (VM_EXEC | VM_WRITE | VM_STACK)) == VM_EXEC; +} + +/* + * Stack area (including shadow stacks) + * + * VM_GROWSUP / VM_GROWSDOWN VMAs are always private anonymous: + * do_mmap() forbids all other combinations. + */ +static inline bool is_stack_mapping(vm_flags_t flags) +{ + return ((flags & VM_STACK) == VM_STACK) || (flags & VM_SHADOW_STACK); +} + +/* + * Data area - private, writable, not stack + */ +static inline bool is_data_mapping(vm_flags_t flags) +{ + return (flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE; +} + + +static inline void vma_iter_config(struct vma_iterator *vmi, + unsigned long index, unsigned long last) +{ + __mas_set_range(&vmi->mas, index, last - 1); +} + +static inline void vma_iter_reset(struct vma_iterator *vmi) +{ + mas_reset(&vmi->mas); +} + +static inline +struct vm_area_struct *vma_iter_prev_range_limit(struct vma_iterator *vmi, unsigned long min) +{ + return mas_prev_range(&vmi->mas, min); +} + +static inline +struct vm_area_struct *vma_iter_next_range_limit(struct vma_iterator *vmi, unsigned long max) +{ + return mas_next_range(&vmi->mas, max); +} + +static inline int vma_iter_area_lowest(struct vma_iterator *vmi, unsigned long min, + unsigned long max, unsigned long size) +{ + return mas_empty_area(&vmi->mas, min, max - 1, size); +} + +static inline int vma_iter_area_highest(struct vma_iterator *vmi, unsigned long min, + unsigned long max, unsigned long size) +{ + return mas_empty_area_rev(&vmi->mas, min, max - 1, size); +} + +/* + * VMA Iterator functions shared between nommu and mmap + */ +static inline int vma_iter_prealloc(struct vma_iterator *vmi, + struct vm_area_struct *vma) +{ + return mas_preallocate(&vmi->mas, vma, GFP_KERNEL); +} + +static inline void vma_iter_clear(struct vma_iterator *vmi) +{ + mas_store_prealloc(&vmi->mas, NULL); +} + +static inline struct vm_area_struct *vma_iter_load(struct vma_iterator *vmi) +{ + return mas_walk(&vmi->mas); +} + +/* Store a VMA with preallocated memory */ +static inline void vma_iter_store(struct vma_iterator *vmi, + struct vm_area_struct *vma) +{ + +#if defined(CONFIG_DEBUG_VM_MAPLE_TREE) + if (MAS_WARN_ON(&vmi->mas, vmi->mas.status != ma_start && + vmi->mas.index > vma->vm_start)) { + pr_warn("%lx > %lx\n store vma %lx-%lx\n into slot %lx-%lx\n", + vmi->mas.index, vma->vm_start, vma->vm_start, + vma->vm_end, vmi->mas.index, vmi->mas.last); + } + if (MAS_WARN_ON(&vmi->mas, vmi->mas.status != ma_start && + vmi->mas.last < vma->vm_start)) { + pr_warn("%lx < %lx\nstore vma %lx-%lx\ninto slot %lx-%lx\n", + vmi->mas.last, vma->vm_start, vma->vm_start, vma->vm_end, + vmi->mas.index, vmi->mas.last); + } +#endif + + if (vmi->mas.status != ma_start && + ((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start))) + vma_iter_invalidate(vmi); + + __mas_set_range(&vmi->mas, vma->vm_start, vma->vm_end - 1); + mas_store_prealloc(&vmi->mas, vma); +} + +static inline unsigned long vma_iter_addr(struct vma_iterator *vmi) +{ + return vmi->mas.index; +} + +static inline unsigned long vma_iter_end(struct vma_iterator *vmi) +{ + return vmi->mas.last + 1; +} + +static inline int vma_iter_bulk_alloc(struct vma_iterator *vmi, + unsigned long count) +{ + return mas_expected_entries(&vmi->mas, count); +} + +static inline +struct vm_area_struct *vma_iter_prev_range(struct vma_iterator *vmi) +{ + return mas_prev_range(&vmi->mas, 0); +} + +#endif /* __MM_VMA_H */ diff --git a/mm/vma_internal.h b/mm/vma_internal.h new file mode 100644 index 000000000000..14c24d5cb582 --- /dev/null +++ b/mm/vma_internal.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * vma_internal.h + * + * Headers required by vma.c, which can be substituted accordingly when testing + * VMA functionality. + */ + +#ifndef __MM_VMA_INTERNAL_H +#define __MM_VMA_INTERNAL_H + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#include "internal.h" + +#endif /* __MM_VMA_INTERNAL_H */ -- cgit v1.2.3 From 29943248af0a8ac3edb808564baa417b40e35521 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Mon, 29 Jul 2024 14:47:17 +0530 Subject: mm: improve code consistency with zonelist_* helper functions Replace direct access to zoneref->zone, zoneref->zone_idx, or zone_to_nid(zoneref->zone) with the corresponding zonelist_* helper functions for consistency. No functional change. Link: https://lkml.kernel.org/r/20240729091717.464-1-shivankg@amd.com Co-developed-by: Shivank Garg Signed-off-by: Shivank Garg Signed-off-by: Wei Yang Acked-by: David Hildenbrand Cc: Mike Rapoport (IBM) Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 4 ++-- include/trace/events/oom.h | 4 ++-- mm/mempolicy.c | 4 ++-- mm/mmzone.c | 2 +- mm/page_alloc.c | 22 +++++++++++----------- 5 files changed, 18 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 1dc6248feb83..dbb69f96a152 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1688,7 +1688,7 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, zone = zonelist_zone(z)) #define for_next_zone_zonelist_nodemask(zone, z, highidx, nodemask) \ - for (zone = z->zone; \ + for (zone = zonelist_zone(z); \ zone; \ z = next_zones_zonelist(++z, highidx, nodemask), \ zone = zonelist_zone(z)) @@ -1724,7 +1724,7 @@ static inline bool movable_only_nodes(nodemask_t *nodes) nid = first_node(*nodes); zonelist = &NODE_DATA(nid)->node_zonelists[ZONELIST_FALLBACK]; z = first_zones_zonelist(zonelist, ZONE_NORMAL, nodes); - return (!z->zone) ? true : false; + return (!zonelist_zone(z)) ? true : false; } diff --git a/include/trace/events/oom.h b/include/trace/events/oom.h index a42be4c8563b..9f0a5d1482c4 100644 --- a/include/trace/events/oom.h +++ b/include/trace/events/oom.h @@ -55,8 +55,8 @@ TRACE_EVENT(reclaim_retry_zone, ), TP_fast_assign( - __entry->node = zone_to_nid(zoneref->zone); - __entry->zone_idx = zoneref->zone_idx; + __entry->node = zonelist_node_idx(zoneref); + __entry->zone_idx = zonelist_zone_idx(zoneref); __entry->order = order; __entry->reclaimable = reclaimable; __entry->available = available; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index b858e22b259d..b3b5f376471f 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1951,7 +1951,7 @@ unsigned int mempolicy_slab_node(void) zonelist = &NODE_DATA(node)->node_zonelists[ZONELIST_FALLBACK]; z = first_zones_zonelist(zonelist, highest_zoneidx, &policy->nodes); - return z->zone ? zone_to_nid(z->zone) : node; + return zonelist_zone(z) ? zonelist_node_idx(z) : node; } case MPOL_LOCAL: return node; @@ -2809,7 +2809,7 @@ int mpol_misplaced(struct folio *folio, struct vm_fault *vmf, node_zonelist(thisnid, GFP_HIGHUSER), gfp_zone(GFP_HIGHUSER), &pol->nodes); - polnid = zone_to_nid(z->zone); + polnid = zonelist_node_idx(z); break; default: diff --git a/mm/mmzone.c b/mm/mmzone.c index c01896eca736..f9baa8882fbf 100644 --- a/mm/mmzone.c +++ b/mm/mmzone.c @@ -66,7 +66,7 @@ struct zoneref *__next_zones_zonelist(struct zoneref *z, z++; else while (zonelist_zone_idx(z) > highest_zoneidx || - (z->zone && !zref_in_nodemask(z, nodes))) + (zonelist_zone(z) && !zref_in_nodemask(z, nodes))) z++; return z; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c565de8f48e9..60742d057b05 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3350,7 +3350,7 @@ retry: } if (no_fallback && nr_online_nodes > 1 && - zone != ac->preferred_zoneref->zone) { + zone != zonelist_zone(ac->preferred_zoneref)) { int local_nid; /* @@ -3358,7 +3358,7 @@ retry: * fragmenting fallbacks. Locality is more important * than fragmentation avoidance. */ - local_nid = zone_to_nid(ac->preferred_zoneref->zone); + local_nid = zonelist_node_idx(ac->preferred_zoneref); if (zone_to_nid(zone) != local_nid) { alloc_flags &= ~ALLOC_NOFRAGMENT; goto retry; @@ -3411,7 +3411,7 @@ check_alloc_wmark: goto try_this_zone; if (!node_reclaim_enabled() || - !zone_allows_reclaim(ac->preferred_zoneref->zone, zone)) + !zone_allows_reclaim(zonelist_zone(ac->preferred_zoneref), zone)) continue; ret = node_reclaim(zone->zone_pgdat, gfp_mask, order); @@ -3433,7 +3433,7 @@ check_alloc_wmark: } try_this_zone: - page = rmqueue(ac->preferred_zoneref->zone, zone, order, + page = rmqueue(zonelist_zone(ac->preferred_zoneref), zone, order, gfp_mask, alloc_flags, ac->migratetype); if (page) { prep_new_page(page, order, gfp_mask, alloc_flags); @@ -4202,7 +4202,7 @@ restart: */ ac->preferred_zoneref = first_zones_zonelist(ac->zonelist, ac->highest_zoneidx, ac->nodemask); - if (!ac->preferred_zoneref->zone) + if (!zonelist_zone(ac->preferred_zoneref)) goto nopage; /* @@ -4214,7 +4214,7 @@ restart: struct zoneref *z = first_zones_zonelist(ac->zonelist, ac->highest_zoneidx, &cpuset_current_mems_allowed); - if (!z->zone) + if (!zonelist_zone(z)) goto nopage; } @@ -4571,8 +4571,8 @@ unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid, continue; } - if (nr_online_nodes > 1 && zone != ac.preferred_zoneref->zone && - zone_to_nid(zone) != zone_to_nid(ac.preferred_zoneref->zone)) { + if (nr_online_nodes > 1 && zone != zonelist_zone(ac.preferred_zoneref) && + zone_to_nid(zone) != zonelist_node_idx(ac.preferred_zoneref)) { goto failed; } @@ -4631,7 +4631,7 @@ unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid, pcp_trylock_finish(UP_flags); __count_zid_vm_events(PGALLOC, zone_idx(zone), nr_account); - zone_statistics(ac.preferred_zoneref->zone, zone, nr_account); + zone_statistics(zonelist_zone(ac.preferred_zoneref), zone, nr_account); out: return nr_populated; @@ -4689,7 +4689,7 @@ struct page *__alloc_pages_noprof(gfp_t gfp, unsigned int order, * Forbid the first pass from falling back to types that fragment * memory until all local zones are considered. */ - alloc_flags |= alloc_flags_nofragment(ac.preferred_zoneref->zone, gfp); + alloc_flags |= alloc_flags_nofragment(zonelist_zone(ac.preferred_zoneref), gfp); /* First allocation attempt */ page = get_page_from_freelist(alloc_gfp, order, alloc_flags, &ac); @@ -5294,7 +5294,7 @@ int local_memory_node(int node) z = first_zones_zonelist(node_zonelist(node, GFP_KERNEL), gfp_zone(GFP_KERNEL), NULL); - return zone_to_nid(z->zone); + return zonelist_node_idx(z); } #endif -- cgit v1.2.3 From 9f101bef408a3f70c44b6e4de44d3d4e2655ed10 Mon Sep 17 00:00:00 2001 From: Barry Song Date: Tue, 30 Jul 2024 19:13:39 +1200 Subject: mm: swap: add nr argument in swapcache_prepare and swapcache_clear to support large folios Right now, swapcache_prepare() and swapcache_clear() supports one entry only, to support large folios, we need to handle multiple swap entries. To optimize stack usage, we iterate twice in __swap_duplicate(): the first time to verify that all entries are valid, and the second time to apply the modifications to the entries. Currently, we're using nr=1 for the existing users. [v-songbaohua@oppo.com: clarify swap_count_continued and improve readability for __swap_duplicate] Link: https://lkml.kernel.org/r/20240802071817.47081-1-21cnbao@gmail.com Link: https://lkml.kernel.org/r/20240730071339.107447-2-21cnbao@gmail.com Signed-off-by: Barry Song Reviewed-by: Baolin Wang Acked-by: David Hildenbrand Tested-by: Baolin Wang Cc: Chris Li Cc: Gao Xiang Cc: "Huang, Ying" Cc: Hugh Dickins Cc: Johannes Weiner Cc: Kairui Song Cc: Kalesh Singh Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Minchan Kim Cc: Nhat Pham Cc: Ryan Roberts Cc: Sergey Senozhatsky Cc: Shakeel Butt Cc: Suren Baghdasaryan Cc: Yang Shi Cc: Yosry Ahmed Signed-off-by: Andrew Morton --- include/linux/swap.h | 4 +-- mm/memory.c | 6 ++-- mm/swap.h | 5 +-- mm/swap_state.c | 2 +- mm/swapfile.c | 95 +++++++++++++++++++++++++++++----------------------- 5 files changed, 63 insertions(+), 49 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index ba7ea95d1c57..5b920fa2315b 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -480,7 +480,7 @@ extern int get_swap_pages(int n, swp_entry_t swp_entries[], int order); extern int add_swap_count_continuation(swp_entry_t, gfp_t); extern void swap_shmem_alloc(swp_entry_t); extern int swap_duplicate(swp_entry_t); -extern int swapcache_prepare(swp_entry_t); +extern int swapcache_prepare(swp_entry_t entry, int nr); extern void swap_free_nr(swp_entry_t entry, int nr_pages); extern void swapcache_free_entries(swp_entry_t *entries, int n); extern void free_swap_and_cache_nr(swp_entry_t entry, int nr); @@ -554,7 +554,7 @@ static inline int swap_duplicate(swp_entry_t swp) return 0; } -static inline int swapcache_prepare(swp_entry_t swp) +static inline int swapcache_prepare(swp_entry_t swp, int nr) { return 0; } diff --git a/mm/memory.c b/mm/memory.c index 71236ae6fd14..cacf03bbdd7a 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4081,7 +4081,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) * reusing the same entry. It's undetectable as * pte_same() returns true due to entry reuse. */ - if (swapcache_prepare(entry)) { + if (swapcache_prepare(entry, 1)) { /* Relax a bit to prevent rapid repeated page faults */ schedule_timeout_uninterruptible(1); goto out; @@ -4387,7 +4387,7 @@ unlock: out: /* Clear the swap cache pin for direct swapin after PTL unlock */ if (need_clear_cache) - swapcache_clear(si, entry); + swapcache_clear(si, entry, 1); if (si) put_swap_device(si); return ret; @@ -4403,7 +4403,7 @@ out_release: folio_put(swapcache); } if (need_clear_cache) - swapcache_clear(si, entry); + swapcache_clear(si, entry, 1); if (si) put_swap_device(si); return ret; diff --git a/mm/swap.h b/mm/swap.h index baa1fa946b34..7c6330561d84 100644 --- a/mm/swap.h +++ b/mm/swap.h @@ -59,7 +59,7 @@ void __delete_from_swap_cache(struct folio *folio, void delete_from_swap_cache(struct folio *folio); void clear_shadow_from_swap_cache(int type, unsigned long begin, unsigned long end); -void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry); +void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry, int nr); struct folio *swap_cache_get_folio(swp_entry_t entry, struct vm_area_struct *vma, unsigned long addr); struct folio *filemap_get_incore_folio(struct address_space *mapping, @@ -120,7 +120,7 @@ static inline int swap_writepage(struct page *p, struct writeback_control *wbc) return 0; } -static inline void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry) +static inline void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry, int nr) { } @@ -172,4 +172,5 @@ static inline unsigned int folio_swap_flags(struct folio *folio) return 0; } #endif /* CONFIG_SWAP */ + #endif /* _MM_SWAP_H */ diff --git a/mm/swap_state.c b/mm/swap_state.c index a1726e49a5eb..b06f2a054f5a 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -477,7 +477,7 @@ struct folio *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, /* * Swap entry may have been freed since our caller observed it. */ - err = swapcache_prepare(entry); + err = swapcache_prepare(entry, 1); if (!err) break; diff --git a/mm/swapfile.c b/mm/swapfile.c index 5f73a8553371..0259f36de715 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -3363,7 +3363,7 @@ void si_swapinfo(struct sysinfo *val) } /* - * Verify that a swap entry is valid and increment its swap map count. + * Verify that nr swap entries are valid and increment their swap map counts. * * Returns error code in following case. * - success -> 0 @@ -3373,60 +3373,73 @@ void si_swapinfo(struct sysinfo *val) * - swap-cache reference is requested but the entry is not used. -> ENOENT * - swap-mapped reference requested but needs continued swap count. -> ENOMEM */ -static int __swap_duplicate(swp_entry_t entry, unsigned char usage) +static int __swap_duplicate(swp_entry_t entry, unsigned char usage, int nr) { struct swap_info_struct *p; struct swap_cluster_info *ci; unsigned long offset; unsigned char count; unsigned char has_cache; - int err; + int err, i; p = swp_swap_info(entry); offset = swp_offset(entry); + VM_WARN_ON(nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER); + VM_WARN_ON(usage == 1 && nr > 1); ci = lock_cluster_or_swap_info(p, offset); - count = p->swap_map[offset]; - - /* - * swapin_readahead() doesn't check if a swap entry is valid, so the - * swap entry could be SWAP_MAP_BAD. Check here with lock held. - */ - if (unlikely(swap_count(count) == SWAP_MAP_BAD)) { - err = -ENOENT; - goto unlock_out; - } - - has_cache = count & SWAP_HAS_CACHE; - count &= ~SWAP_HAS_CACHE; err = 0; + for (i = 0; i < nr; i++) { + count = p->swap_map[offset + i]; - if (usage == SWAP_HAS_CACHE) { + /* + * swapin_readahead() doesn't check if a swap entry is valid, so the + * swap entry could be SWAP_MAP_BAD. Check here with lock held. + */ + if (unlikely(swap_count(count) == SWAP_MAP_BAD)) { + err = -ENOENT; + goto unlock_out; + } - /* set SWAP_HAS_CACHE if there is no cache and entry is used */ - if (!has_cache && count) - has_cache = SWAP_HAS_CACHE; - else if (has_cache) /* someone else added cache */ - err = -EEXIST; - else /* no users remaining */ + has_cache = count & SWAP_HAS_CACHE; + count &= ~SWAP_HAS_CACHE; + + if (!count && !has_cache) { err = -ENOENT; + } else if (usage == SWAP_HAS_CACHE) { + if (has_cache) + err = -EEXIST; + } else if ((count & ~COUNT_CONTINUED) > SWAP_MAP_MAX) { + err = -EINVAL; + } + + if (err) + goto unlock_out; + } - } else if (count || has_cache) { + for (i = 0; i < nr; i++) { + count = p->swap_map[offset + i]; + has_cache = count & SWAP_HAS_CACHE; + count &= ~SWAP_HAS_CACHE; - if ((count & ~COUNT_CONTINUED) < SWAP_MAP_MAX) + if (usage == SWAP_HAS_CACHE) + has_cache = SWAP_HAS_CACHE; + else if ((count & ~COUNT_CONTINUED) < SWAP_MAP_MAX) count += usage; - else if ((count & ~COUNT_CONTINUED) > SWAP_MAP_MAX) - err = -EINVAL; - else if (swap_count_continued(p, offset, count)) + else if (swap_count_continued(p, offset + i, count)) count = COUNT_CONTINUED; - else + else { + /* + * Don't need to rollback changes, because if + * usage == 1, there must be nr == 1. + */ err = -ENOMEM; - } else - err = -ENOENT; /* unused swap entry */ + goto unlock_out; + } - if (!err) - WRITE_ONCE(p->swap_map[offset], count | has_cache); + WRITE_ONCE(p->swap_map[offset + i], count | has_cache); + } unlock_out: unlock_cluster_or_swap_info(p, ci); @@ -3439,7 +3452,7 @@ unlock_out: */ void swap_shmem_alloc(swp_entry_t entry) { - __swap_duplicate(entry, SWAP_MAP_SHMEM); + __swap_duplicate(entry, SWAP_MAP_SHMEM, 1); } /* @@ -3453,29 +3466,29 @@ int swap_duplicate(swp_entry_t entry) { int err = 0; - while (!err && __swap_duplicate(entry, 1) == -ENOMEM) + while (!err && __swap_duplicate(entry, 1, 1) == -ENOMEM) err = add_swap_count_continuation(entry, GFP_ATOMIC); return err; } /* - * @entry: swap entry for which we allocate swap cache. + * @entry: first swap entry from which we allocate nr swap cache. * - * Called when allocating swap cache for existing swap entry, + * Called when allocating swap cache for existing swap entries, * This can return error codes. Returns 0 at success. * -EEXIST means there is a swap cache. * Note: return code is different from swap_duplicate(). */ -int swapcache_prepare(swp_entry_t entry) +int swapcache_prepare(swp_entry_t entry, int nr) { - return __swap_duplicate(entry, SWAP_HAS_CACHE); + return __swap_duplicate(entry, SWAP_HAS_CACHE, nr); } -void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry) +void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry, int nr) { unsigned long offset = swp_offset(entry); - cluster_swap_free_nr(si, offset, 1, SWAP_HAS_CACHE); + cluster_swap_free_nr(si, offset, nr, SWAP_HAS_CACHE); } struct swap_info_struct *swp_swap_info(swp_entry_t entry) -- cgit v1.2.3 From 94ccd21e9a5f41585bd16cc84dab2afa6cc21149 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Wed, 31 Jul 2024 16:20:00 +0200 Subject: mm/hugetlb: remove hugetlb_follow_page_mask() leftover We removed hugetlb_follow_page_mask() in commit 9cb28da54643 ("mm/gup: handle hugetlb in the generic follow_page_mask code") but forgot to cleanup some leftovers. While at it, simplify the hugetlb comment, it's overly detailed and rather confusing. Stating that we may end up in there during coredumping is sufficient to explain the PF_DUMPCORE usage. Link: https://lkml.kernel.org/r/20240731142000.625044-1-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Peter Xu Cc: Muchun Song Cc: Alexander Viro Cc: Christian Brauner Cc: Jan Kara Signed-off-by: Andrew Morton --- fs/userfaultfd.c | 11 ++--------- include/linux/hugetlb.h | 3 --- 2 files changed, 2 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index b3ed7207df7e..68cdd89c97a3 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -371,15 +371,8 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) unsigned int blocking_state; /* - * We don't do userfault handling for the final child pid update. - * - * We also don't do userfault handling during - * coredumping. hugetlbfs has the special - * hugetlb_follow_page_mask() to skip missing pages in the - * FOLL_DUMP case, anon memory also checks for FOLL_DUMP with - * the no_page_table() helper in follow_page_mask(), but the - * shmem_vm_ops->fault method is invoked even during - * coredumping and it ends up here. + * We don't do userfault handling for the final child pid update + * and when coredumping (faults triggered by get_dump_page()). */ if (current->flags & (PF_EXITING|PF_DUMPCORE)) goto out; diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 9b7bcfce6920..3100a52ceb73 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -127,9 +127,6 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, unsigned long len); int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *, struct vm_area_struct *); -struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma, - unsigned long address, unsigned int flags, - unsigned int *page_mask); void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long, struct page *, zap_flags_t); -- cgit v1.2.3 From 17d5f38b33b66210c5a46af639c47fddfe1c5b4d Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Wed, 31 Jul 2024 18:07:58 +0200 Subject: mm: clarify folio_likely_mapped_shared() documentation for KSM folios For KSM folios, the function actually does what it is supposed to do: even having multiple mappings inside the same MM is considered "sharing", as there is no real relationship between these KSM page mappings -- in contrast to mapping the same file range twice and having the same pagecache page mapped twice. Link: https://lkml.kernel.org/r/20240731160758.808925-1-david@redhat.com Signed-off-by: David Hildenbrand Signed-off-by: Andrew Morton --- include/linux/mm.h | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index bd219ac9c026..2f6c08b53e4f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2132,14 +2132,19 @@ static inline size_t folio_size(const struct folio *folio) * MM ("mapped shared"), or if the folio is only mapped into a single MM * ("mapped exclusively"). * + * For KSM folios, this function also returns "mapped shared" when a folio is + * mapped multiple times into the same MM, because the individual page mappings + * are independent. + * * As precise information is not easily available for all folios, this function * estimates the number of MMs ("sharers") that are currently mapping a folio * using the number of times the first page of the folio is currently mapped * into page tables. * - * For small anonymous folios (except KSM folios) and anonymous hugetlb folios, - * the return value will be exactly correct, because they can only be mapped - * at most once into an MM, and they cannot be partially mapped. + * For small anonymous folios and anonymous hugetlb folios, the return + * value will be exactly correct: non-KSM folios can only be mapped at most once + * into an MM, and they cannot be partially mapped. KSM folios are + * considered shared even if mapped multiple times into the same MM. * * For other folios, the result can be fuzzy: * #. For partially-mappable large folios (THP), the return value can wrongly @@ -2148,9 +2153,6 @@ static inline size_t folio_size(const struct folio *folio) * #. For pagecache folios (including hugetlb), the return value can wrongly * indicate "mapped shared" (false positive) when two VMAs in the same MM * cover the same file range. - * #. For (small) KSM folios, the return value can wrongly indicate "mapped - * shared" (false positive), when the folio is mapped multiple times into - * the same MM. * * Further, this function only considers current page table mappings that * are tracked using the folio mapcount(s). -- cgit v1.2.3 From 03790c51a475c46647079e67e2460a149938bfd6 Mon Sep 17 00:00:00 2001 From: Kaiyang Zhao Date: Thu, 1 Aug 2024 23:25:47 +0000 Subject: mm: create promo_wmark_pages and clean up open-coded sites Patch series "mm: print the promo watermark in zoneinfo", v2. This patch (of 2): Define promo_wmark_pages and convert current call sites of wmark_pages with fixed WMARK_PROMO to using it instead. Link: https://lkml.kernel.org/r/20240801232548.36604-1-kaiyang2@cs.cmu.edu Link: https://lkml.kernel.org/r/20240801232548.36604-2-kaiyang2@cs.cmu.edu Signed-off-by: Kaiyang Zhao Cc: Johannes Weiner Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 1 + kernel/sched/fair.c | 2 +- mm/vmscan.c | 2 +- 3 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index dbb69f96a152..9f3589f7f05c 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -669,6 +669,7 @@ enum zone_watermarks { #define min_wmark_pages(z) (z->_watermark[WMARK_MIN] + z->watermark_boost) #define low_wmark_pages(z) (z->_watermark[WMARK_LOW] + z->watermark_boost) #define high_wmark_pages(z) (z->_watermark[WMARK_HIGH] + z->watermark_boost) +#define promo_wmark_pages(z) (z->_watermark[WMARK_PROMO] + z->watermark_boost) #define wmark_pages(z, i) (z->_watermark[i] + z->watermark_boost) /* diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 416e29b56cc4..20ea6d085305 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1742,7 +1742,7 @@ static bool pgdat_free_space_enough(struct pglist_data *pgdat) continue; if (zone_watermark_ok(zone, 0, - wmark_pages(zone, WMARK_PROMO) + enough_wmark, + promo_wmark_pages(zone) + enough_wmark, ZONE_MOVABLE, 0)) return true; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 852d97c134df..6b70e80ca0ee 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -6669,7 +6669,7 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx) continue; if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) - mark = wmark_pages(zone, WMARK_PROMO); + mark = promo_wmark_pages(zone); else mark = high_wmark_pages(zone); if (zone_watermark_ok_safe(zone, order, mark, highest_zoneidx)) -- cgit v1.2.3 From 620943d7ee69070df8844235d58843af48ac70e2 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 1 Aug 2024 16:50:05 -0700 Subject: include/linux/mmzone.h: clean up watermark accessors - we have a helper wmark_pages(). Teach min_wmark_pages(), low_wmark_pages(), high_wmark_pages() and promo_wmark_pages() to use it instead of open-coding its implementation. - there's no reason to implement all these things as macros. Redo them in C. Acked-by: Johannes Weiner Cc: Kaiyang Zhao Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 32 ++++++++++++++++++++++++++------ 1 file changed, 26 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 9f3589f7f05c..17506e4a2835 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -666,12 +666,6 @@ enum zone_watermarks { #define NR_LOWORDER_PCP_LISTS (MIGRATE_PCPTYPES * (PAGE_ALLOC_COSTLY_ORDER + 1)) #define NR_PCP_LISTS (NR_LOWORDER_PCP_LISTS + NR_PCP_THP) -#define min_wmark_pages(z) (z->_watermark[WMARK_MIN] + z->watermark_boost) -#define low_wmark_pages(z) (z->_watermark[WMARK_LOW] + z->watermark_boost) -#define high_wmark_pages(z) (z->_watermark[WMARK_HIGH] + z->watermark_boost) -#define promo_wmark_pages(z) (z->_watermark[WMARK_PROMO] + z->watermark_boost) -#define wmark_pages(z, i) (z->_watermark[i] + z->watermark_boost) - /* * Flags used in pcp->flags field. * @@ -1017,6 +1011,32 @@ enum zone_flags { ZONE_BELOW_HIGH, /* zone is below high watermark. */ }; +static inline unsigned long wmark_pages(const struct zone *z, + enum zone_watermarks w) +{ + return z->_watermark[w] + z->watermark_boost; +} + +static inline unsigned long min_wmark_pages(const struct zone *z) +{ + return wmark_pages(z, WMARK_MIN); +} + +static inline unsigned long low_wmark_pages(const struct zone *z) +{ + return wmark_pages(z, WMARK_LOW); +} + +static inline unsigned long high_wmark_pages(const struct zone *z) +{ + return wmark_pages(z, WMARK_HIGH); +} + +static inline unsigned long promo_wmark_pages(const struct zone *z) +{ + return wmark_pages(z, WMARK_PROMO); +} + static inline unsigned long zone_managed_pages(struct zone *zone) { return (unsigned long)atomic_long_read(&zone->managed_pages); -- cgit v1.2.3 From aa39ca6940f1a0540f2984051b3089972f42959b Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 2 Aug 2024 17:55:15 +0200 Subject: mm/pagewalk: introduce folio_walk_start() + folio_walk_end() We want to get rid of follow_page(), and have a more reasonable way to just lookup a folio mapped at a certain address, perform some checks while still under PTL, and then only conditionally grab a folio reference if really required. Further, we might want to get rid of some walk_page_range*() users that really only want to temporarily lookup a single folio at a single address. So let's add a new page table walker that does exactly that, similarly to GUP also being able to walk hugetlb VMAs. Add folio_walk_end() as a macro for now: the compiler is not easy to please with the pte_unmap()->kunmap_local(). Note that one difference between follow_page() and get_user_pages(1) is that follow_page() will not trigger faults to get something mapped. So folio_walk is at least currently not a replacement for get_user_pages(1), but could likely be extended/reused to achieve something similar in the future. Link: https://lkml.kernel.org/r/20240802155524.517137-3-david@redhat.com Signed-off-by: David Hildenbrand Cc: Alexander Gordeev Cc: Christian Borntraeger Cc: Claudio Imbrenda Cc: Gerald Schaefer Cc: Heiko Carstens Cc: Janosch Frank Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Sven Schnelle Cc: Vasily Gorbik Cc: Ryan Roberts Cc: Zi Yan Signed-off-by: Andrew Morton --- include/linux/pagewalk.h | 58 ++++++++++++++ mm/pagewalk.c | 202 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 260 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h index 27cd1e59ccf7..f5eb5a32aeed 100644 --- a/include/linux/pagewalk.h +++ b/include/linux/pagewalk.h @@ -130,4 +130,62 @@ int walk_page_mapping(struct address_space *mapping, pgoff_t first_index, pgoff_t nr, const struct mm_walk_ops *ops, void *private); +typedef int __bitwise folio_walk_flags_t; + +/* + * Walk migration entries as well. Careful: a large folio might get split + * concurrently. + */ +#define FW_MIGRATION ((__force folio_walk_flags_t)BIT(0)) + +/* Walk shared zeropages (small + huge) as well. */ +#define FW_ZEROPAGE ((__force folio_walk_flags_t)BIT(1)) + +enum folio_walk_level { + FW_LEVEL_PTE, + FW_LEVEL_PMD, + FW_LEVEL_PUD, +}; + +/** + * struct folio_walk - folio_walk_start() / folio_walk_end() data + * @page: exact folio page referenced (if applicable) + * @level: page table level identifying the entry type + * @pte: pointer to the page table entry (FW_LEVEL_PTE). + * @pmd: pointer to the page table entry (FW_LEVEL_PMD). + * @pud: pointer to the page table entry (FW_LEVEL_PUD). + * @ptl: pointer to the page table lock. + * + * (see folio_walk_start() documentation for more details) + */ +struct folio_walk { + /* public */ + struct page *page; + enum folio_walk_level level; + union { + pte_t *ptep; + pud_t *pudp; + pmd_t *pmdp; + }; + union { + pte_t pte; + pud_t pud; + pmd_t pmd; + }; + /* private */ + struct vm_area_struct *vma; + spinlock_t *ptl; +}; + +struct folio *folio_walk_start(struct folio_walk *fw, + struct vm_area_struct *vma, unsigned long addr, + folio_walk_flags_t flags); + +#define folio_walk_end(__fw, __vma) do { \ + spin_unlock((__fw)->ptl); \ + if (likely((__fw)->level == FW_LEVEL_PTE)) \ + pte_unmap((__fw)->ptep); \ + vma_pgtable_walk_end(__vma); \ +} while (0) + #endif /* _LINUX_PAGEWALK_H */ diff --git a/mm/pagewalk.c b/mm/pagewalk.c index ae2f08ce991b..cd79fb3b89e5 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -3,6 +3,8 @@ #include #include #include +#include +#include /* * We want to know the real level where a entry is located ignoring any @@ -654,3 +656,203 @@ int walk_page_mapping(struct address_space *mapping, pgoff_t first_index, return err; } + +/** + * folio_walk_start - walk the page tables to a folio + * @fw: filled with information on success. + * @vma: the VMA. + * @addr: the virtual address to use for the page table walk. + * @flags: flags modifying which folios to walk to. + * + * Walk the page tables using @addr in a given @vma to a mapped folio and + * return the folio, making sure that the page table entry referenced by + * @addr cannot change until folio_walk_end() was called. + * + * As default, this function returns only folios that are not special (e.g., not + * the zeropage) and never returns folios that are supposed to be ignored by the + * VM as documented by vm_normal_page(). If requested, zeropages will be + * returned as well. + * + * As default, this function only considers present page table entries. + * If requested, it will also consider migration entries. + * + * If this function returns NULL it might either indicate "there is nothing" or + * "there is nothing suitable". + * + * On success, @fw is filled and the function returns the folio while the PTL + * is still held and folio_walk_end() must be called to clean up, + * releasing any held locks. The returned folio must *not* be used after the + * call to folio_walk_end(), unless a short-term folio reference is taken before + * that call. + * + * @fw->page will correspond to the page that is effectively referenced by + * @addr. However, for migration entries and shared zeropages @fw->page is + * set to NULL. Note that large folios might be mapped by multiple page table + * entries, and this function will always only lookup a single entry as + * specified by @addr, which might or might not cover more than a single page of + * the returned folio. + * + * This function must *not* be used as a naive replacement for + * get_user_pages() / pin_user_pages(), especially not to perform DMA or + * to carelessly modify page content. This function may *only* be used to grab + * short-term folio references, never to grab long-term folio references. + * + * Using the page table entry pointers in @fw for reading or modifying the + * entry should be avoided where possible: however, there might be valid + * use cases. + * + * WARNING: Modifying page table entries in hugetlb VMAs requires a lot of care. + * For example, PMD page table sharing might require prior unsharing. Also, + * logical hugetlb entries might span multiple physical page table entries, + * which *must* be modified in a single operation (set_huge_pte_at(), + * huge_ptep_set_*, ...). Note that the page table entry stored in @fw might + * not correspond to the first physical entry of a logical hugetlb entry. + * + * The mmap lock must be held in read mode. + * + * Return: folio pointer on success, otherwise NULL. + */ +struct folio *folio_walk_start(struct folio_walk *fw, + struct vm_area_struct *vma, unsigned long addr, + folio_walk_flags_t flags) +{ + unsigned long entry_size; + bool expose_page = true; + struct page *page; + pud_t *pudp, pud; + pmd_t *pmdp, pmd; + pte_t *ptep, pte; + spinlock_t *ptl; + pgd_t *pgdp; + p4d_t *p4dp; + + mmap_assert_locked(vma->vm_mm); + vma_pgtable_walk_begin(vma); + + if (WARN_ON_ONCE(addr < vma->vm_start || addr >= vma->vm_end)) + goto not_found; + + pgdp = pgd_offset(vma->vm_mm, addr); + if (pgd_none_or_clear_bad(pgdp)) + goto not_found; + + p4dp = p4d_offset(pgdp, addr); + if (p4d_none_or_clear_bad(p4dp)) + goto not_found; + + pudp = pud_offset(p4dp, addr); + pud = pudp_get(pudp); + if (pud_none(pud)) + goto not_found; + if (IS_ENABLED(CONFIG_PGTABLE_HAS_HUGE_LEAVES) && pud_leaf(pud)) { + ptl = pud_lock(vma->vm_mm, pudp); + pud = pudp_get(pudp); + + entry_size = PUD_SIZE; + fw->level = FW_LEVEL_PUD; + fw->pudp = pudp; + fw->pud = pud; + + if (!pud_present(pud) || pud_devmap(pud)) { + spin_unlock(ptl); + goto not_found; + } else if (!pud_leaf(pud)) { + spin_unlock(ptl); + goto pmd_table; + } + /* + * TODO: vm_normal_page_pud() will be handy once we want to + * support PUD mappings in VM_PFNMAP|VM_MIXEDMAP VMAs. + */ + page = pud_page(pud); + goto found; + } + +pmd_table: + VM_WARN_ON_ONCE(pud_leaf(*pudp)); + pmdp = pmd_offset(pudp, addr); + pmd = pmdp_get_lockless(pmdp); + if (pmd_none(pmd)) + goto not_found; + if (IS_ENABLED(CONFIG_PGTABLE_HAS_HUGE_LEAVES) && pmd_leaf(pmd)) { + ptl = pmd_lock(vma->vm_mm, pmdp); + pmd = pmdp_get(pmdp); + + entry_size = PMD_SIZE; + fw->level = FW_LEVEL_PMD; + fw->pmdp = pmdp; + fw->pmd = pmd; + + if (pmd_none(pmd)) { + spin_unlock(ptl); + goto not_found; + } else if (!pmd_leaf(pmd)) { + spin_unlock(ptl); + goto pte_table; + } else if (pmd_present(pmd)) { + page = vm_normal_page_pmd(vma, addr, pmd); + if (page) { + goto found; + } else if ((flags & FW_ZEROPAGE) && + is_huge_zero_pmd(pmd)) { + page = pfn_to_page(pmd_pfn(pmd)); + expose_page = false; + goto found; + } + } else if ((flags & FW_MIGRATION) && + is_pmd_migration_entry(pmd)) { + swp_entry_t entry = pmd_to_swp_entry(pmd); + + page = pfn_swap_entry_to_page(entry); + expose_page = false; + goto found; + } + spin_unlock(ptl); + goto not_found; + } + +pte_table: + VM_WARN_ON_ONCE(pmd_leaf(pmdp_get_lockless(pmdp))); + ptep = pte_offset_map_lock(vma->vm_mm, pmdp, addr, &ptl); + if (!ptep) + goto not_found; + pte = ptep_get(ptep); + + entry_size = PAGE_SIZE; + fw->level = FW_LEVEL_PTE; + fw->ptep = ptep; + fw->pte = pte; + + if (pte_present(pte)) { + page = vm_normal_page(vma, addr, pte); + if (page) + goto found; + if ((flags & FW_ZEROPAGE) && + is_zero_pfn(pte_pfn(pte))) { + page = pfn_to_page(pte_pfn(pte)); + expose_page = false; + goto found; + } + } else if (!pte_none(pte)) { + swp_entry_t entry = pte_to_swp_entry(pte); + + if ((flags & FW_MIGRATION) && + is_migration_entry(entry)) { + page = pfn_swap_entry_to_page(entry); + expose_page = false; + goto found; + } + } + pte_unmap_unlock(ptep, ptl); +not_found: + vma_pgtable_walk_end(vma); + return NULL; +found: + if (expose_page) + /* Note: Offset from the mapped page, not the folio start. */ + fw->page = nth_page(page, (addr & (entry_size - 1)) >> PAGE_SHIFT); + else + fw->page = NULL; + fw->ptl = ptl; + return page_folio(page); +} -- cgit v1.2.3 From 8710f6ed34e7bcf98971d65acfb5eaed5fc469b0 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 2 Aug 2024 17:55:20 +0200 Subject: mm/huge_memory: convert split_huge_pages_pid() from follow_page() to folio_walk Let's remove yet another follow_page() user. Note that we have to do the split without holding the PTL, after folio_walk_end(). We don't care about losing the secretmem check in follow_page(). [david@redhat.com: teach can_split_folio() that we are not holding an additional reference] Link: https://lkml.kernel.org/r/c75d1c6c-8ea6-424f-853c-1ccda6c77ba2@redhat.com Link: https://lkml.kernel.org/r/20240802155524.517137-8-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Zi Yan Cc: Alexander Gordeev Cc: Christian Borntraeger Cc: Claudio Imbrenda Cc: Gerald Schaefer Cc: Heiko Carstens Cc: Janosch Frank Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Sven Schnelle Cc: Vasily Gorbik Cc: Ryan Roberts Signed-off-by: Andrew Morton --- include/linux/huge_mm.h | 4 ++-- mm/huge_memory.c | 27 ++++++++++++++++----------- mm/vmscan.c | 2 +- 3 files changed, 19 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index e25d9ebfdf89..ce44caa40eed 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -314,7 +314,7 @@ unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long add unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags); -bool can_split_folio(struct folio *folio, int *pextra_pins); +bool can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins); int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, unsigned int new_order); static inline int split_huge_page(struct page *page) @@ -470,7 +470,7 @@ thp_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, } static inline bool -can_split_folio(struct folio *folio, int *pextra_pins) +can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins) { return false; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 29e76d285e4b..666fa675e5b6 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -40,6 +40,7 @@ #include #include #include +#include #include #include @@ -3017,7 +3018,7 @@ static void __split_huge_page(struct page *page, struct list_head *list, } /* Racy check whether the huge page can be split */ -bool can_split_folio(struct folio *folio, int *pextra_pins) +bool can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins) { int extra_pins; @@ -3029,7 +3030,8 @@ bool can_split_folio(struct folio *folio, int *pextra_pins) extra_pins = folio_nr_pages(folio); if (pextra_pins) *pextra_pins = extra_pins; - return folio_mapcount(folio) == folio_ref_count(folio) - extra_pins - 1; + return folio_mapcount(folio) == folio_ref_count(folio) - extra_pins - + caller_pins; } /* @@ -3197,7 +3199,7 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, * Racy check if we can split the page, before unmap_folio() will * split PMDs */ - if (!can_split_folio(folio, &extra_pins)) { + if (!can_split_folio(folio, 1, &extra_pins)) { ret = -EAGAIN; goto out_unlock; } @@ -3504,7 +3506,7 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start, */ for (addr = vaddr_start; addr < vaddr_end; addr += PAGE_SIZE) { struct vm_area_struct *vma = vma_lookup(mm, addr); - struct page *page; + struct folio_walk fw; struct folio *folio; if (!vma) @@ -3516,13 +3518,10 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start, continue; } - /* FOLL_DUMP to ignore special (like zero) pages */ - page = follow_page(vma, addr, FOLL_GET | FOLL_DUMP); - - if (IS_ERR_OR_NULL(page)) + folio = folio_walk_start(&fw, vma, addr, 0); + if (!folio) continue; - folio = page_folio(page); if (!is_transparent_hugepage(folio)) goto next; @@ -3536,18 +3535,24 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start, * can be split or not. So skip the check here. */ if (!folio_test_private(folio) && - !can_split_folio(folio, NULL)) + !can_split_folio(folio, 0, NULL)) goto next; if (!folio_trylock(folio)) goto next; + folio_get(folio); + folio_walk_end(&fw, vma); if (!split_folio_to_order(folio, new_order)) split++; folio_unlock(folio); -next: folio_put(folio); + + cond_resched(); + continue; +next: + folio_walk_end(&fw, vma); cond_resched(); } mmap_read_unlock(mm); diff --git a/mm/vmscan.c b/mm/vmscan.c index 6b70e80ca0ee..96ce889ea3d0 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1227,7 +1227,7 @@ retry: goto keep_locked; if (folio_test_large(folio)) { /* cannot split folio, skip it */ - if (!can_split_folio(folio, NULL)) + if (!can_split_folio(folio, 1, NULL)) goto activate_locked; /* * Split partially mapped folios right away. -- cgit v1.2.3 From 7290840de65e04c1fc59dab692468fc9600c6038 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 2 Aug 2024 17:55:23 +0200 Subject: mm: remove follow_page() All users are gone, let's remove it and any leftovers in comments. We'll leave any FOLL/follow_page_() naming cleanups as future work. Link: https://lkml.kernel.org/r/20240802155524.517137-11-david@redhat.com Signed-off-by: David Hildenbrand Cc: Alexander Gordeev Cc: Christian Borntraeger Cc: Claudio Imbrenda Cc: Gerald Schaefer Cc: Heiko Carstens Cc: Janosch Frank Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Sven Schnelle Cc: Vasily Gorbik Cc: Ryan Roberts Cc: Zi Yan Signed-off-by: Andrew Morton --- Documentation/mm/transhuge.rst | 6 +++--- include/linux/mm.h | 3 --- mm/filemap.c | 2 +- mm/gup.c | 24 +----------------------- mm/nommu.c | 6 ------ 5 files changed, 5 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/Documentation/mm/transhuge.rst b/Documentation/mm/transhuge.rst index 1ba0ad63246c..a2cd8800d527 100644 --- a/Documentation/mm/transhuge.rst +++ b/Documentation/mm/transhuge.rst @@ -31,10 +31,10 @@ Design principles feature that applies to all dynamic high order allocations in the kernel) -get_user_pages and follow_page -============================== +get_user_pages and pin_user_pages +================================= -get_user_pages and follow_page if run on a hugepage, will return the +get_user_pages and pin_user_pages if run on a hugepage, will return the head or tail pages as usual (exactly as they would do on hugetlbfs). Most GUP users will only care about the actual physical address of the page and its temporary pinning to release after the I/O diff --git a/include/linux/mm.h b/include/linux/mm.h index 2f6c08b53e4f..ee8cea73d415 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3527,9 +3527,6 @@ static inline vm_fault_t vmf_fs_error(int err) return VM_FAULT_SIGBUS; } -struct page *follow_page(struct vm_area_struct *vma, unsigned long address, - unsigned int foll_flags); - static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) { if (vm_fault & VM_FAULT_OOM) diff --git a/mm/filemap.c b/mm/filemap.c index d62150418b91..4130be74f6fd 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -112,7 +112,7 @@ * ->swap_lock (try_to_unmap_one) * ->private_lock (try_to_unmap_one) * ->i_pages lock (try_to_unmap_one) - * ->lruvec->lru_lock (follow_page->mark_page_accessed) + * ->lruvec->lru_lock (follow_page_mask->mark_page_accessed) * ->lruvec->lru_lock (check_pte_range->isolate_lru_page) * ->private_lock (folio_remove_rmap_pte->set_page_dirty) * ->i_pages lock (folio_remove_rmap_pte->set_page_dirty) diff --git a/mm/gup.c b/mm/gup.c index 3e8484c893aa..d19884e097fd 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1072,28 +1072,6 @@ static struct page *follow_page_mask(struct vm_area_struct *vma, return page; } -struct page *follow_page(struct vm_area_struct *vma, unsigned long address, - unsigned int foll_flags) -{ - struct follow_page_context ctx = { NULL }; - struct page *page; - - if (vma_is_secretmem(vma)) - return NULL; - - if (WARN_ON_ONCE(foll_flags & FOLL_PIN)) - return NULL; - - /* - * We never set FOLL_HONOR_NUMA_FAULT because callers don't expect - * to fail on PROT_NONE-mapped pages. - */ - page = follow_page_mask(vma, address, foll_flags, &ctx); - if (ctx.pgmap) - put_dev_pagemap(ctx.pgmap); - return page; -} - static int get_gate_page(struct mm_struct *mm, unsigned long address, unsigned int gup_flags, struct vm_area_struct **vma, struct page **page) @@ -2519,7 +2497,7 @@ static bool is_valid_gup_args(struct page **pages, int *locked, * These flags not allowed to be specified externally to the gup * interfaces: * - FOLL_TOUCH/FOLL_PIN/FOLL_TRIED/FOLL_FAST_ONLY are internal only - * - FOLL_REMOTE is internal only and used on follow_page() + * - FOLL_REMOTE is internal only, set in (get|pin)_user_pages_remote() * - FOLL_UNLOCKABLE is internal only and used if locked is !NULL */ if (WARN_ON_ONCE(gup_flags & INTERNAL_GUP_FLAGS)) diff --git a/mm/nommu.c b/mm/nommu.c index 40cac1348b40..385b0c15add8 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1578,12 +1578,6 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, return ret; } -struct page *follow_page(struct vm_area_struct *vma, unsigned long address, - unsigned int foll_flags) -{ - return NULL; -} - int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { -- cgit v1.2.3 From e31c38e037621c445bb4393fd77e0a76e6e0899a Mon Sep 17 00:00:00 2001 From: Nhat Pham Date: Mon, 5 Aug 2024 16:22:42 -0700 Subject: zswap: implement a second chance algorithm for dynamic zswap shrinker Patch series "improving dynamic zswap shrinker protection scheme", v3. When experimenting with the memory-pressure based (i.e "dynamic") zswap shrinker in production, we observed a sharp increase in the number of swapins, which led to performance regression. We were able to trace this regression to the following problems with the shrinker's warm pages protection scheme: 1. The protection decays way too rapidly, and the decaying is coupled with zswap stores, leading to anomalous patterns, in which a small batch of zswap stores effectively erase all the protection in place for the warmer pages in the zswap LRU. This observation has also been corroborated upstream by Takero Funaki (in [1]). 2. We inaccurately track the number of swapped in pages, missing the non-pivot pages that are part of the readahead window, while counting the pages that are found in the zswap pool. To alleviate these two issues, this patch series improve the dynamic zswap shrinker in the following manner: 1. Replace the protection size tracking scheme with a second chance algorithm. This new scheme removes the need for haphazard stats decaying, and automatically adjusts the pace of pages aging with memory pressure, and writeback rate with pool activities: slowing down when the pool is dominated with zswpouts, and speeding up when the pool is dominated with stale entries. 2. Fix the tracking of the number of swapins to take into account non-pivot pages in the readahead window. With these two changes in place, in a kernel-building benchmark without any cold data added, the number of swapins is reduced by 64.12%. This translate to a 10.32% reduction in build time. We also observe a 3% reduction in kernel CPU time. In another benchmark, with cold data added (to gauge the new algorithm's ability to offload cold data), the new second chance scheme outperforms the old protection scheme by around 0.7%, and actually written back around 21% more pages to backing swap device. So the new scheme is just as good, if not even better than the old scheme on this front as well. [1]: https://lore.kernel.org/linux-mm/CAPpodddcGsK=0Xczfuk8usgZ47xeyf4ZjiofdT+ujiyz6V2pFQ@mail.gmail.com/ This patch (of 2): Current zswap shrinker's heuristics to prevent overshrinking is brittle and inaccurate, specifically in the way we decay the protection size (i.e making pages in the zswap LRU eligible for reclaim). We currently decay protection aggressively in zswap_lru_add() calls. This leads to the following unfortunate effect: when a new batch of pages enter zswap, the protection size rapidly decays to below 25% of the zswap LRU size, which is way too low. We have observed this effect in production, when experimenting with the zswap shrinker: the rate of shrinking shoots up massively right after a new batch of zswap stores. This is somewhat the opposite of what we want originally - when new pages enter zswap, we want to protect both these new pages AND the pages that are already protected in the zswap LRU. Replace existing heuristics with a second chance algorithm 1. When a new zswap entry is stored in the zswap pool, its referenced bit is set. 2. When the zswap shrinker encounters a zswap entry with the referenced bit set, give it a second chance - only flips the referenced bit and rotate it in the LRU. 3. If the shrinker encounters the entry again, this time with its referenced bit unset, then it can reclaim the entry. In this manner, the aging of the pages in the zswap LRUs are decoupled from zswap stores, and picks up the pace with increasing memory pressure (which is what we want). The second chance scheme allows us to modulate the writeback rate based on recent pool activities. Entries that recently entered the pool will be protected, so if the pool is dominated by such entries the writeback rate will reduce proportionally, protecting the workload's workingset.On the other hand, stale entries will be written back quickly, which increases the effective writeback rate. The referenced bit is added at the hole after the `length` field of struct zswap_entry, so there is no extra space overhead for this algorithm. We will still maintain the count of swapins, which is consumed and subtracted from the lru size in zswap_shrinker_count(), to further penalize past overshrinking that led to disk swapins. The idea is that had we considered this many more pages in the LRU active/protected, they would not have been written back and we would not have had to swapped them in. To test this new heuristics, I built the kernel under a cgroup with memory.max set to 2G, on a host with 36 cores: With the old shrinker: real: 263.89s user: 4318.11s sys: 673.29s swapins: 227300.5 With the second chance algorithm: real: 244.85s user: 4327.22s sys: 664.39s swapins: 94663 (average over 5 runs) We observe an 1.3% reduction in kernel CPU usage, and around 7.2% reduction in real time. Note that the number of swapped in pages dropped by 58%. [nphamcs@gmail.com: fix a small mistake in the referenced bit documentation] Link: https://lkml.kernel.org/r/20240806003403.3142387-1-nphamcs@gmail.com Link: https://lkml.kernel.org/r/20240805232243.2896283-1-nphamcs@gmail.com Link: https://lkml.kernel.org/r/20240805232243.2896283-2-nphamcs@gmail.com Signed-off-by: Nhat Pham Suggested-by: Johannes Weiner Acked-by: Yosry Ahmed Cc: Chengming Zhou Cc: Shakeel Butt Cc: Takero Funaki Signed-off-by: Andrew Morton --- include/linux/zswap.h | 16 ++++---- mm/zswap.c | 108 +++++++++++++++++++++++++++++--------------------- 2 files changed, 70 insertions(+), 54 deletions(-) (limited to 'include/linux') diff --git a/include/linux/zswap.h b/include/linux/zswap.h index 6cecb4a4f68b..9cd1beef0654 100644 --- a/include/linux/zswap.h +++ b/include/linux/zswap.h @@ -13,17 +13,15 @@ extern atomic_t zswap_stored_pages; struct zswap_lruvec_state { /* - * Number of pages in zswap that should be protected from the shrinker. - * This number is an estimate of the following counts: + * Number of swapped in pages from disk, i.e not found in the zswap pool. * - * a) Recent page faults. - * b) Recent insertion to the zswap LRU. This includes new zswap stores, - * as well as recent zswap LRU rotations. - * - * These pages are likely to be warm, and might incur IO if the are written - * to swap. + * This is consumed and subtracted from the lru size in + * zswap_shrinker_count() to penalize past overshrinking that led to disk + * swapins. The idea is that had we considered this many more pages in the + * LRU active/protected and not written them back, we would not have had to + * swapped them in. */ - atomic_long_t nr_zswap_protected; + atomic_long_t nr_disk_swapins; }; unsigned long zswap_total_pages(void); diff --git a/mm/zswap.c b/mm/zswap.c index 71b75ff1f3fb..df66ab102d27 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -187,6 +187,10 @@ static struct shrinker *zswap_shrinker; * length - the length in bytes of the compressed page data. Needed during * decompression. For a same value filled page length is 0, and both * pool and lru are invalid and must be ignored. + * referenced - true if the entry recently entered the zswap pool. Unset by the + * writeback logic. The entry is only reclaimed by the writeback + * logic if referenced is unset. See comments in the shrinker + * section for context. * pool - the zswap_pool the entry's data is in * handle - zpool allocation handle that stores the compressed page data * value - value of the same-value filled pages which have same content @@ -196,6 +200,7 @@ static struct shrinker *zswap_shrinker; struct zswap_entry { swp_entry_t swpentry; unsigned int length; + bool referenced; struct zswap_pool *pool; union { unsigned long handle; @@ -700,11 +705,8 @@ static inline int entry_to_nid(struct zswap_entry *entry) static void zswap_lru_add(struct list_lru *list_lru, struct zswap_entry *entry) { - atomic_long_t *nr_zswap_protected; - unsigned long lru_size, old, new; int nid = entry_to_nid(entry); struct mem_cgroup *memcg; - struct lruvec *lruvec; /* * Note that it is safe to use rcu_read_lock() here, even in the face of @@ -722,19 +724,6 @@ static void zswap_lru_add(struct list_lru *list_lru, struct zswap_entry *entry) memcg = mem_cgroup_from_entry(entry); /* will always succeed */ list_lru_add(list_lru, &entry->lru, nid, memcg); - - /* Update the protection area */ - lru_size = list_lru_count_one(list_lru, nid, memcg); - lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(nid)); - nr_zswap_protected = &lruvec->zswap_lruvec_state.nr_zswap_protected; - old = atomic_long_inc_return(nr_zswap_protected); - /* - * Decay to avoid overflow and adapt to changing workloads. - * This is based on LRU reclaim cost decaying heuristics. - */ - do { - new = old > lru_size / 4 ? old / 2 : old; - } while (!atomic_long_try_cmpxchg(nr_zswap_protected, &old, new)); rcu_read_unlock(); } @@ -752,7 +741,7 @@ static void zswap_lru_del(struct list_lru *list_lru, struct zswap_entry *entry) void zswap_lruvec_state_init(struct lruvec *lruvec) { - atomic_long_set(&lruvec->zswap_lruvec_state.nr_zswap_protected, 0); + atomic_long_set(&lruvec->zswap_lruvec_state.nr_disk_swapins, 0); } void zswap_folio_swapin(struct folio *folio) @@ -761,7 +750,7 @@ void zswap_folio_swapin(struct folio *folio) if (folio) { lruvec = folio_lruvec(folio); - atomic_long_inc(&lruvec->zswap_lruvec_state.nr_zswap_protected); + atomic_long_inc(&lruvec->zswap_lruvec_state.nr_disk_swapins); } } @@ -1095,6 +1084,28 @@ static int zswap_writeback_entry(struct zswap_entry *entry, /********************************* * shrinker functions **********************************/ +/* + * The dynamic shrinker is modulated by the following factors: + * + * 1. Each zswap entry has a referenced bit, which the shrinker unsets (giving + * the entry a second chance) before rotating it in the LRU list. If the + * entry is considered again by the shrinker, with its referenced bit unset, + * it is written back. The writeback rate as a result is dynamically + * adjusted by the pool activities - if the pool is dominated by new entries + * (i.e lots of recent zswapouts), these entries will be protected and + * the writeback rate will slow down. On the other hand, if the pool has a + * lot of stagnant entries, these entries will be reclaimed immediately, + * effectively increasing the writeback rate. + * + * 2. Swapins counter: If we observe swapins, it is a sign that we are + * overshrinking and should slow down. We maintain a swapins counter, which + * is consumed and subtract from the number of eligible objects on the LRU + * in zswap_shrinker_count(). + * + * 3. Compression ratio. The better the workload compresses, the less gains we + * can expect from writeback. We scale down the number of objects available + * for reclaim by this ratio. + */ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_one *l, spinlock_t *lock, void *arg) { @@ -1104,6 +1115,16 @@ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_o enum lru_status ret = LRU_REMOVED_RETRY; int writeback_result; + /* + * Second chance algorithm: if the entry has its referenced bit set, give it + * a second chance. Only clear the referenced bit and rotate it in the + * zswap's LRU list. + */ + if (entry->referenced) { + entry->referenced = false; + return LRU_ROTATE; + } + /* * As soon as we drop the LRU lock, the entry can be freed by * a concurrent invalidation. This means the following: @@ -1170,8 +1191,7 @@ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_o static unsigned long zswap_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) { - struct lruvec *lruvec = mem_cgroup_lruvec(sc->memcg, NODE_DATA(sc->nid)); - unsigned long shrink_ret, nr_protected, lru_size; + unsigned long shrink_ret; bool encountered_page_in_swapcache = false; if (!zswap_shrinker_enabled || @@ -1180,25 +1200,6 @@ static unsigned long zswap_shrinker_scan(struct shrinker *shrinker, return SHRINK_STOP; } - nr_protected = - atomic_long_read(&lruvec->zswap_lruvec_state.nr_zswap_protected); - lru_size = list_lru_shrink_count(&zswap_list_lru, sc); - - /* - * Abort if we are shrinking into the protected region. - * - * This short-circuiting is necessary because if we have too many multiple - * concurrent reclaimers getting the freeable zswap object counts at the - * same time (before any of them made reasonable progress), the total - * number of reclaimed objects might be more than the number of unprotected - * objects (i.e the reclaimers will reclaim into the protected area of the - * zswap LRU). - */ - if (nr_protected >= lru_size - sc->nr_to_scan) { - sc->nr_scanned = 0; - return SHRINK_STOP; - } - shrink_ret = list_lru_shrink_walk(&zswap_list_lru, sc, &shrink_memcg_cb, &encountered_page_in_swapcache); @@ -1213,7 +1214,10 @@ static unsigned long zswap_shrinker_count(struct shrinker *shrinker, { struct mem_cgroup *memcg = sc->memcg; struct lruvec *lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(sc->nid)); - unsigned long nr_backing, nr_stored, nr_freeable, nr_protected; + atomic_long_t *nr_disk_swapins = + &lruvec->zswap_lruvec_state.nr_disk_swapins; + unsigned long nr_backing, nr_stored, nr_freeable, nr_disk_swapins_cur, + nr_remain; if (!zswap_shrinker_enabled || !mem_cgroup_zswap_writeback_enabled(memcg)) return 0; @@ -1246,14 +1250,27 @@ static unsigned long zswap_shrinker_count(struct shrinker *shrinker, if (!nr_stored) return 0; - nr_protected = - atomic_long_read(&lruvec->zswap_lruvec_state.nr_zswap_protected); nr_freeable = list_lru_shrink_count(&zswap_list_lru, sc); + if (!nr_freeable) + return 0; + /* - * Subtract the lru size by an estimate of the number of pages - * that should be protected. + * Subtract from the lru size the number of pages that are recently swapped + * in from disk. The idea is that had we protect the zswap's LRU by this + * amount of pages, these disk swapins would not have happened. */ - nr_freeable = nr_freeable > nr_protected ? nr_freeable - nr_protected : 0; + nr_disk_swapins_cur = atomic_long_read(nr_disk_swapins); + do { + if (nr_freeable >= nr_disk_swapins_cur) + nr_remain = 0; + else + nr_remain = nr_disk_swapins_cur - nr_freeable; + } while (!atomic_long_try_cmpxchg( + nr_disk_swapins, &nr_disk_swapins_cur, nr_remain)); + + nr_freeable -= nr_disk_swapins_cur - nr_remain; + if (!nr_freeable) + return 0; /* * Scale the number of freeable pages by the memory saving factor. @@ -1506,6 +1523,7 @@ bool zswap_store(struct folio *folio) store_entry: entry->swpentry = swp; entry->objcg = objcg; + entry->referenced = true; old = xa_store(tree, offset, entry, GFP_KERNEL); if (xa_is_err(old)) { -- cgit v1.2.3 From 17fe833b0de08a78bfb51388e0615969d73ea8ad Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Mon, 5 Aug 2024 14:52:03 +0200 Subject: mm: fix (harmless) type confusion in lock_vma_under_rcu() There is a (harmless) type confusion in lock_vma_under_rcu(): After vma_start_read(), we have taken the VMA lock but don't know yet whether the VMA has already been detached and scheduled for RCU freeing. At this point, ->vm_start and ->vm_end are accessed. vm_area_struct contains a union such that ->vm_rcu uses the same memory as ->vm_start and ->vm_end; so accessing ->vm_start and ->vm_end of a detached VMA is illegal and leads to type confusion between union members. Fix it by reordering the vma->detached check above the address checks, and document the rules for RCU readers accessing VMAs. This will probably change the number of observed VMA_LOCK_MISS events (since previously, trying to access a detached VMA whose ->vm_rcu has been scheduled would bail out when checking the fault address against the rcu_head members reinterpreted as VMA bounds). Link: https://lkml.kernel.org/r/20240805-fix-vma-lock-type-confusion-v1-1-9f25443a9a71@google.com Fixes: 50ee32537206 ("mm: introduce lock_vma_under_rcu to be used from arch-specific code") Signed-off-by: Jann Horn Acked-by: Suren Baghdasaryan Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- include/linux/mm_types.h | 15 +++++++++++++-- mm/memory.c | 14 ++++++++++---- 2 files changed, 23 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 165c58b12ccc..003619fab20e 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -660,6 +660,9 @@ struct vma_numab_state { * per VM-area/task. A VM area is any part of the process virtual memory * space that has a special rule for the page-fault handlers (ie a shared * library, the executable area etc). + * + * Only explicitly marked struct members may be accessed by RCU readers before + * getting a stable reference. */ struct vm_area_struct { /* The first cache line has the info for VMA tree walking. */ @@ -675,7 +678,11 @@ struct vm_area_struct { #endif }; - struct mm_struct *vm_mm; /* The address space we belong to. */ + /* + * The address space we belong to. + * Unstable RCU readers are allowed to read this. + */ + struct mm_struct *vm_mm; pgprot_t vm_page_prot; /* Access permissions of this VMA. */ /* @@ -688,7 +695,10 @@ struct vm_area_struct { }; #ifdef CONFIG_PER_VMA_LOCK - /* Flag to indicate areas detached from the mm->mm_mt tree */ + /* + * Flag to indicate areas detached from the mm->mm_mt tree. + * Unstable RCU readers are allowed to read this. + */ bool detached; /* @@ -706,6 +716,7 @@ struct vm_area_struct { * slowpath. */ int vm_lock_seq; + /* Unstable RCU readers are allowed to read this. */ struct vma_lock *vm_lock; #endif diff --git a/mm/memory.c b/mm/memory.c index 661168a46b43..46a44dc702fa 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -5997,10 +5997,6 @@ retry: if (!vma_start_read(vma)) goto inval; - /* Check since vm_start/vm_end might change before we lock the VMA */ - if (unlikely(address < vma->vm_start || address >= vma->vm_end)) - goto inval_end_read; - /* Check if the VMA got isolated after we found it */ if (vma->detached) { vma_end_read(vma); @@ -6008,6 +6004,16 @@ retry: /* The area was replaced with another one */ goto retry; } + /* + * At this point, we have a stable reference to a VMA: The VMA is + * locked and we know it hasn't already been isolated. + * From here on, we can access the VMA without worrying about which + * fields are accessible for RCU readers. + */ + + /* Check since vm_start/vm_end might change before we lock the VMA */ + if (unlikely(address < vma->vm_start || address >= vma->vm_end)) + goto inval_end_read; rcu_read_unlock(); return vma; -- cgit v1.2.3 From cc0a0f98553528791ae33ba5ee8c118b52ae2028 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Mon, 5 Aug 2024 14:39:39 +0200 Subject: kfence: introduce burst mode Introduce burst mode, which can be configured with kfence.burst=$count, where the burst count denotes the additional successive slab allocations to be allocated through KFENCE for each sample interval. The idea is that this can give developers an additional knob to make KFENCE more aggressive when debugging specific issues of systems where either rebooting or recompiling the kernel with KASAN is not possible. Experiment: To assess the effectiveness of the new option, we randomly picked a recent out-of-bounds [1] and use-after-free bug [2], each with a reproducer provided by syzbot, that initially detected these bugs with KASAN. We then tried to reproduce the bugs with KFENCE below. [1] Fixed by: 7c55b78818cf ("jfs: xattr: fix buffer overflow for invalid xattr") https://syzkaller.appspot.com/bug?id=9d1b59d4718239da6f6069d3891863c25f9f24a2 [2] Fixed by: f8ad00f3fb2a ("l2tp: fix possible UAF when cleaning up tunnels") https://syzkaller.appspot.com/bug?id=4f34adc84f4a3b080187c390eeef60611fd450e1 The following KFENCE configs were compared. A pool size of 1023 objects was used for all configurations. Baseline kfence.sample_interval=100 kfence.skip_covered_thresh=75 kfence.burst=0 Aggressive kfence.sample_interval=1 kfence.skip_covered_thresh=10 kfence.burst=0 AggressiveBurst kfence.sample_interval=1 kfence.skip_covered_thresh=10 kfence.burst=1000 Each reproducer was run 10 times (after a fresh reboot), with the following detection counts for each KFENCE config: | Detection Count out of 10 | | OOB [1] | UAF [2] | ------------------+-------------+-------------+ Default | 0/10 | 0/10 | Aggressive | 0/10 | 0/10 | AggressiveBurst | 8/10 | 8/10 | With the Default and even the Aggressive configs the results are unsurprising, given KFENCE has not been designed for deterministic bug detection of small test cases. However, when enabling burst mode with relatively large burst count, KFENCE can start to detect heap memory-safety bugs even in simpler test cases with high probability (in the above cases with ~80% probability). Link: https://lkml.kernel.org/r/20240805124203.2692278-1-elver@google.com Signed-off-by: Marco Elver Reviewed-by: Alexander Potapenko Cc: Andrey Konovalov Cc: Dmitry Vyukov Cc: Jann Horn Signed-off-by: Andrew Morton --- Documentation/dev-tools/kfence.rst | 7 +++++++ include/linux/kfence.h | 2 +- mm/kfence/core.c | 14 ++++++++++---- 3 files changed, 18 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/Documentation/dev-tools/kfence.rst b/Documentation/dev-tools/kfence.rst index 936f6aaa75c8..541899353865 100644 --- a/Documentation/dev-tools/kfence.rst +++ b/Documentation/dev-tools/kfence.rst @@ -53,6 +53,13 @@ configurable via the Kconfig option ``CONFIG_KFENCE_DEFERRABLE``. The KUnit test suite is very likely to fail when using a deferrable timer since it currently causes very unpredictable sample intervals. +By default KFENCE will only sample 1 heap allocation within each sample +interval. *Burst mode* allows to sample successive heap allocations, where the +kernel boot parameter ``kfence.burst`` can be set to a non-zero value which +denotes the *additional* successive allocations within a sample interval; +setting ``kfence.burst=N`` means that ``1 + N`` successive allocations are +attempted through KFENCE for each sample interval. + The KFENCE memory pool is of fixed size, and if the pool is exhausted, no further KFENCE allocations occur. With ``CONFIG_KFENCE_NUM_OBJECTS`` (default 255), the number of available guarded objects can be controlled. Each object diff --git a/include/linux/kfence.h b/include/linux/kfence.h index 88100cc9caba..0ad1ddbb8b99 100644 --- a/include/linux/kfence.h +++ b/include/linux/kfence.h @@ -124,7 +124,7 @@ static __always_inline void *kfence_alloc(struct kmem_cache *s, size_t size, gfp if (!static_branch_likely(&kfence_allocation_key)) return NULL; #endif - if (likely(atomic_read(&kfence_allocation_gate))) + if (likely(atomic_read(&kfence_allocation_gate) > 0)) return NULL; return __kfence_alloc(s, size, flags); } diff --git a/mm/kfence/core.c b/mm/kfence/core.c index c5cb54fc696d..c3ef7eb8d4dc 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -99,6 +99,10 @@ module_param_cb(sample_interval, &sample_interval_param_ops, &kfence_sample_inte static unsigned long kfence_skip_covered_thresh __read_mostly = 75; module_param_named(skip_covered_thresh, kfence_skip_covered_thresh, ulong, 0644); +/* Allocation burst count: number of excess KFENCE allocations per sample. */ +static unsigned int kfence_burst __read_mostly; +module_param_named(burst, kfence_burst, uint, 0644); + /* If true, use a deferrable timer. */ static bool kfence_deferrable __read_mostly = IS_ENABLED(CONFIG_KFENCE_DEFERRABLE); module_param_named(deferrable, kfence_deferrable, bool, 0444); @@ -827,12 +831,12 @@ static void toggle_allocation_gate(struct work_struct *work) if (!READ_ONCE(kfence_enabled)) return; - atomic_set(&kfence_allocation_gate, 0); + atomic_set(&kfence_allocation_gate, -kfence_burst); #ifdef CONFIG_KFENCE_STATIC_KEYS /* Enable static key, and await allocation to happen. */ static_branch_enable(&kfence_allocation_key); - wait_event_idle(allocation_wait, atomic_read(&kfence_allocation_gate)); + wait_event_idle(allocation_wait, atomic_read(&kfence_allocation_gate) > 0); /* Disable static key and reset timer. */ static_branch_disable(&kfence_allocation_key); @@ -1052,6 +1056,7 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) unsigned long stack_entries[KFENCE_STACK_DEPTH]; size_t num_stack_entries; u32 alloc_stack_hash; + int allocation_gate; /* * Perform size check before switching kfence_allocation_gate, so that @@ -1080,14 +1085,15 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) if (s->flags & SLAB_SKIP_KFENCE) return NULL; - if (atomic_inc_return(&kfence_allocation_gate) > 1) + allocation_gate = atomic_inc_return(&kfence_allocation_gate); + if (allocation_gate > 1) return NULL; #ifdef CONFIG_KFENCE_STATIC_KEYS /* * waitqueue_active() is fully ordered after the update of * kfence_allocation_gate per atomic_inc_return(). */ - if (waitqueue_active(&allocation_wait)) { + if (allocation_gate == 1 && waitqueue_active(&allocation_wait)) { /* * Calling wake_up() here may deadlock when allocations happen * from within timer code. Use an irq_work to defer it. -- cgit v1.2.3 From 47baed6a132f611228113851a70c73f6e6478d87 Mon Sep 17 00:00:00 2001 From: Jianhui Zhou <912460177@qq.com> Date: Wed, 7 Aug 2024 15:44:48 +0800 Subject: percpu: remove pcpu_alloc_size() pcpu_alloc_size() was added in 7ac5c53e0073 "mm/percpu.c: introduce pcpu_alloc_size()", which is used to get the allocated memory size in bpf. However, pcpu_alloc_size() is no longer used in "bpf: Use c->unit_size to select target cache during free" because its actuall allocated memory size may change at runtime due to its slab merging mechanism. Therefore, pcpu_alloc_size() can be removed. Link: https://lkml.kernel.org/r/tencent_AD5C50E8D78C07A3CE539BD5F6BF39706507@qq.com Signed-off-by: Jianhui Zhou <912460177@qq.com> Cc: Christoph Lameter Cc: Dennis Zhou Cc: JonasZhou Cc: Tejun Heo Signed-off-by: Andrew Morton --- include/linux/percpu.h | 1 - mm/percpu.c | 31 ------------------------------- 2 files changed, 32 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 4b2047b78b67..b6321fc49159 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -135,7 +135,6 @@ extern void __init setup_per_cpu_areas(void); extern void __percpu *pcpu_alloc_noprof(size_t size, size_t align, bool reserved, gfp_t gfp) __alloc_size(1); -extern size_t pcpu_alloc_size(void __percpu *__pdata); #define __alloc_percpu_gfp(_size, _align, _gfp) \ alloc_hooks(pcpu_alloc_noprof(_size, _align, false, _gfp)) diff --git a/mm/percpu.c b/mm/percpu.c index 20d91af8c033..da21680ff294 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -2216,37 +2216,6 @@ static void pcpu_balance_workfn(struct work_struct *work) mutex_unlock(&pcpu_alloc_mutex); } -/** - * pcpu_alloc_size - the size of the dynamic percpu area - * @ptr: pointer to the dynamic percpu area - * - * Returns the size of the @ptr allocation. This is undefined for statically - * defined percpu variables as there is no corresponding chunk->bound_map. - * - * RETURNS: - * The size of the dynamic percpu area. - * - * CONTEXT: - * Can be called from atomic context. - */ -size_t pcpu_alloc_size(void __percpu *ptr) -{ - struct pcpu_chunk *chunk; - unsigned long bit_off, end; - void *addr; - - if (!ptr) - return 0; - - addr = __pcpu_ptr_to_addr(ptr); - /* No pcpu_lock here: ptr has not been freed, so chunk is still alive */ - chunk = pcpu_chunk_addr_search(addr); - bit_off = (addr - chunk->base_addr) / PCPU_MIN_ALLOC_SIZE; - end = find_next_bit(chunk->bound_map, pcpu_chunk_map_bits(chunk), - bit_off + 1); - return (end - bit_off) * PCPU_MIN_ALLOC_SIZE; -} - /** * free_percpu - free percpu area * @ptr: pointer to area to free -- cgit v1.2.3 From 09022bc196d23484a7a5d48cf373f8583e3fcf23 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 7 Aug 2024 20:35:26 +0100 Subject: mm: remove PG_error The PG_error bit is now unused; delete it and free up a bit in page->flags. Link: https://lkml.kernel.org/r/20240807193528.1865100-2-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- fs/proc/page.c | 1 - include/linux/page-flags.h | 6 +----- include/trace/events/mmflags.h | 1 - include/uapi/linux/kernel-page-flags.h | 2 +- 4 files changed, 2 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/page.c b/fs/proc/page.c index b7a5c84b5819..73a0f872d97f 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -182,7 +182,6 @@ u64 stable_page_flags(const struct page *page) #endif u |= kpf_copy_bit(k, KPF_LOCKED, PG_locked); - u |= kpf_copy_bit(k, KPF_ERROR, PG_error); u |= kpf_copy_bit(k, KPF_DIRTY, PG_dirty); u |= kpf_copy_bit(k, KPF_UPTODATE, PG_uptodate); u |= kpf_copy_bit(k, KPF_WRITEBACK, PG_writeback); diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 5769fe6e4950..a0a29bd092f8 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -66,8 +66,6 @@ * PG_referenced, PG_reclaim are used for page reclaim for anonymous and * file-backed pagecache (see mm/vmscan.c). * - * PG_error is set to indicate that an I/O error occurred on this page. - * * PG_arch_1 is an architecture specific page state bit. The generic code * guarantees that this bit is cleared for a page when it first is entered into * the page cache. @@ -103,7 +101,6 @@ enum pageflags { PG_waiters, /* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */ PG_active, PG_workingset, - PG_error, PG_owner_priv_1, /* Owner use. If pagecache, fs may use*/ PG_arch_1, PG_reserved, @@ -183,7 +180,7 @@ enum pageflags { */ /* At least one page in this folio has the hwpoison flag set */ - PG_has_hwpoisoned = PG_error, + PG_has_hwpoisoned = PG_active, PG_large_rmappable = PG_workingset, /* anon or file-backed */ }; @@ -506,7 +503,6 @@ static inline int TestClearPage##uname(struct page *page) { return 0; } __PAGEFLAG(Locked, locked, PF_NO_TAIL) FOLIO_FLAG(waiters, FOLIO_HEAD_PAGE) -PAGEFLAG(Error, error, PF_NO_TAIL) TESTCLEARFLAG(Error, error, PF_NO_TAIL) FOLIO_FLAG(referenced, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(referenced, FOLIO_HEAD_PAGE) __FOLIO_SET_FLAG(referenced, FOLIO_HEAD_PAGE) diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index b63d211bd141..b5c4da370a50 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -100,7 +100,6 @@ #define __def_pageflag_names \ DEF_PAGEFLAG_NAME(locked), \ DEF_PAGEFLAG_NAME(waiters), \ - DEF_PAGEFLAG_NAME(error), \ DEF_PAGEFLAG_NAME(referenced), \ DEF_PAGEFLAG_NAME(uptodate), \ DEF_PAGEFLAG_NAME(dirty), \ diff --git a/include/uapi/linux/kernel-page-flags.h b/include/uapi/linux/kernel-page-flags.h index 6f2f2720f3ac..ff8032227876 100644 --- a/include/uapi/linux/kernel-page-flags.h +++ b/include/uapi/linux/kernel-page-flags.h @@ -7,7 +7,7 @@ */ #define KPF_LOCKED 0 -#define KPF_ERROR 1 +#define KPF_ERROR 1 /* Now unused */ #define KPF_REFERENCED 2 #define KPF_UPTODATE 3 #define KPF_DIRTY 4 -- cgit v1.2.3 From 310183de7bb2ed114a80d057690ddb23d0cfe814 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 9 Aug 2024 14:48:50 +0300 Subject: mm: introduce PageUnaccepted() page type The new page type allows physical memory scanners to detect unaccepted memory and handle it accordingly. The page type is serialized with zone lock. Link: https://lkml.kernel.org/r/20240809114854.3745464-5-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Acked-by: David Hildenbrand Cc: Borislav Petkov Cc: Johannes Weiner Cc: Matthew Wilcox Cc: Mel Gorman Cc: Mike Rapoport (Microsoft) Cc: Tom Lendacky Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/page-flags.h | 8 ++++++++ mm/page_alloc.c | 2 ++ 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index a0a29bd092f8..17175a328e6b 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -939,6 +939,7 @@ enum pagetype { PG_hugetlb = 0x04000000, PG_slab = 0x02000000, PG_zsmalloc = 0x01000000, + PG_unaccepted = 0x00800000, PAGE_TYPE_BASE = 0x80000000, @@ -1072,6 +1073,13 @@ FOLIO_TEST_FLAG_FALSE(hugetlb) PAGE_TYPE_OPS(Zsmalloc, zsmalloc, zsmalloc) +/* + * Mark pages that has to be accepted before touched for the first time. + * + * Serialized with zone lock. + */ +PAGE_TYPE_OPS(Unaccepted, unaccepted, unaccepted) + /** * PageHuge - Determine if the page belongs to hugetlbfs * @page: The page to test. diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 9dde1b04a04e..fec7ed5a04f2 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6963,6 +6963,7 @@ static bool try_to_accept_memory_one(struct zone *zone) account_freepages(zone, -MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE); __mod_zone_page_state(zone, NR_UNACCEPTED, -MAX_ORDER_NR_PAGES); + __ClearPageUnaccepted(page); spin_unlock_irqrestore(&zone->lock, flags); accept_page(page, MAX_PAGE_ORDER); @@ -7021,6 +7022,7 @@ static bool __free_unaccepted(struct page *page) list_add_tail(&page->lru, &zone->unaccepted_pages); account_freepages(zone, MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE); __mod_zone_page_state(zone, NR_UNACCEPTED, MAX_ORDER_NR_PAGES); + __SetPageUnaccepted(page); spin_unlock_irqrestore(&zone->lock, flags); if (first) -- cgit v1.2.3 From 5adfeaecc487e7023f1c7bbdc081707d7a93110f Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 9 Aug 2024 14:48:51 +0300 Subject: mm: rework accept memory helpers Make accept_memory() and range_contains_unaccepted_memory() take 'start' and 'size' arguments instead of 'start' and 'end'. Remove accept_page(), replacing it with direct calls to accept_memory(). The accept_page() name is going to be used for a different function. Link: https://lkml.kernel.org/r/20240809114854.3745464-6-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Suggested-by: David Hildenbrand Cc: Borislav Petkov Cc: Johannes Weiner Cc: Matthew Wilcox Cc: Mel Gorman Cc: Mike Rapoport (Microsoft) Cc: Tom Lendacky Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- arch/x86/boot/compressed/misc.c | 2 +- arch/x86/boot/compressed/misc.h | 2 +- drivers/firmware/efi/libstub/efistub.h | 2 +- drivers/firmware/efi/libstub/unaccepted_memory.c | 3 ++- drivers/firmware/efi/unaccepted_memory.c | 18 ++++++++++-------- include/linux/mm.h | 12 +++++------- mm/memblock.c | 2 +- mm/mm_init.c | 2 +- mm/page_alloc.c | 19 +++---------------- tools/testing/memblock/internal.h | 2 +- 10 files changed, 26 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 944454306ef4..04a35b2c26e9 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -511,7 +511,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output) if (init_unaccepted_memory()) { debug_putstr("Accepting memory... "); - accept_memory(__pa(output), __pa(output) + needed_size); + accept_memory(__pa(output), needed_size); } entry_offset = decompress_kernel(output, virt_addr, error); diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index b353a7be380c..dd8d1a85f671 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -256,6 +256,6 @@ static inline bool init_unaccepted_memory(void) { return false; } /* Defined in EFI stub */ extern struct efi_unaccepted_memory *unaccepted_table; -void accept_memory(phys_addr_t start, phys_addr_t end); +void accept_memory(phys_addr_t start, unsigned long size); #endif /* BOOT_COMPRESSED_MISC_H */ diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h index d33ccbc4a2c6..685098f9626f 100644 --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -1229,7 +1229,7 @@ efi_zboot_entry(efi_handle_t handle, efi_system_table_t *systab); efi_status_t allocate_unaccepted_bitmap(__u32 nr_desc, struct efi_boot_memmap *map); void process_unaccepted_memory(u64 start, u64 end); -void accept_memory(phys_addr_t start, phys_addr_t end); +void accept_memory(phys_addr_t start, unsigned long size); void arch_accept_memory(phys_addr_t start, phys_addr_t end); #endif diff --git a/drivers/firmware/efi/libstub/unaccepted_memory.c b/drivers/firmware/efi/libstub/unaccepted_memory.c index c295ea3a6efc..757dbe734a47 100644 --- a/drivers/firmware/efi/libstub/unaccepted_memory.c +++ b/drivers/firmware/efi/libstub/unaccepted_memory.c @@ -177,9 +177,10 @@ void process_unaccepted_memory(u64 start, u64 end) start / unit_size, (end - start) / unit_size); } -void accept_memory(phys_addr_t start, phys_addr_t end) +void accept_memory(phys_addr_t start, unsigned long size) { unsigned long range_start, range_end; + phys_addr_t end = start + size; unsigned long bitmap_size; u64 unit_size; diff --git a/drivers/firmware/efi/unaccepted_memory.c b/drivers/firmware/efi/unaccepted_memory.c index 50f6503fe49f..c2c067eff634 100644 --- a/drivers/firmware/efi/unaccepted_memory.c +++ b/drivers/firmware/efi/unaccepted_memory.c @@ -30,11 +30,12 @@ static LIST_HEAD(accepting_list); * - memory that is below phys_base; * - memory that is above the memory that addressable by the bitmap; */ -void accept_memory(phys_addr_t start, phys_addr_t end) +void accept_memory(phys_addr_t start, unsigned long size) { struct efi_unaccepted_memory *unaccepted; unsigned long range_start, range_end; struct accept_range range, *entry; + phys_addr_t end = start + size; unsigned long flags; u64 unit_size; @@ -74,13 +75,13 @@ void accept_memory(phys_addr_t start, phys_addr_t end) * "guard" page is accepted in addition to the memory that needs to be * used: * - * 1. Implicitly extend the range_contains_unaccepted_memory(start, end) - * checks up to end+unit_size if 'end' is aligned on a unit_size - * boundary. + * 1. Implicitly extend the range_contains_unaccepted_memory(start, size) + * checks up to the next unit_size if 'start+size' is aligned on a + * unit_size boundary. * - * 2. Implicitly extend accept_memory(start, end) to end+unit_size if - * 'end' is aligned on a unit_size boundary. (immediately following - * this comment) + * 2. Implicitly extend accept_memory(start, size) to the next unit_size + * if 'size+end' is aligned on a unit_size boundary. (immediately + * following this comment) */ if (!(end % unit_size)) end += unit_size; @@ -156,9 +157,10 @@ retry: spin_unlock_irqrestore(&unaccepted_memory_lock, flags); } -bool range_contains_unaccepted_memory(phys_addr_t start, phys_addr_t end) +bool range_contains_unaccepted_memory(phys_addr_t start, unsigned long size) { struct efi_unaccepted_memory *unaccepted; + phys_addr_t end = start + size; unsigned long flags; bool ret = false; u64 unit_size; diff --git a/include/linux/mm.h b/include/linux/mm.h index ee8cea73d415..b1eed30fdc06 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -4062,18 +4062,18 @@ madvise_set_anon_name(struct mm_struct *mm, unsigned long start, #ifdef CONFIG_UNACCEPTED_MEMORY -bool range_contains_unaccepted_memory(phys_addr_t start, phys_addr_t end); -void accept_memory(phys_addr_t start, phys_addr_t end); +bool range_contains_unaccepted_memory(phys_addr_t start, unsigned long size); +void accept_memory(phys_addr_t start, unsigned long size); #else static inline bool range_contains_unaccepted_memory(phys_addr_t start, - phys_addr_t end) + unsigned long size) { return false; } -static inline void accept_memory(phys_addr_t start, phys_addr_t end) +static inline void accept_memory(phys_addr_t start, unsigned long size) { } @@ -4081,9 +4081,7 @@ static inline void accept_memory(phys_addr_t start, phys_addr_t end) static inline bool pfn_is_unaccepted_memory(unsigned long pfn) { - phys_addr_t paddr = pfn << PAGE_SHIFT; - - return range_contains_unaccepted_memory(paddr, paddr + PAGE_SIZE); + return range_contains_unaccepted_memory(pfn << PAGE_SHIFT, PAGE_SIZE); } void vma_pgtable_walk_begin(struct vm_area_struct *vma); diff --git a/mm/memblock.c b/mm/memblock.c index 3b9dc2d89b8a..0a77a748a8eb 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1500,7 +1500,7 @@ done: * * Accept the memory of the allocated buffer. */ - accept_memory(found, found + size); + accept_memory(found, size); return found; } diff --git a/mm/mm_init.c b/mm/mm_init.c index 51960079875b..f3106b6299d3 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -1939,7 +1939,7 @@ static void __init deferred_free_pages(unsigned long pfn, } /* Accept chunks smaller than MAX_PAGE_ORDER upfront */ - accept_memory(PFN_PHYS(pfn), PFN_PHYS(pfn + nr_pages)); + accept_memory(PFN_PHYS(pfn), nr_pages * PAGE_SIZE); for (i = 0; i < nr_pages; i++, page++, pfn++) { if (pageblock_aligned(pfn)) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index fec7ed5a04f2..6ba88929c1e3 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -286,7 +286,6 @@ EXPORT_SYMBOL(nr_online_nodes); #endif static bool page_contains_unaccepted(struct page *page, unsigned int order); -static void accept_page(struct page *page, unsigned int order); static bool cond_accept_memory(struct zone *zone, unsigned int order); static inline bool has_unaccepted_memory(void); static bool __free_unaccepted(struct page *page); @@ -1268,7 +1267,7 @@ void __meminit __free_pages_core(struct page *page, unsigned int order, if (order == MAX_PAGE_ORDER && __free_unaccepted(page)) return; - accept_page(page, order); + accept_memory(page_to_phys(page), PAGE_SIZE << order); } /* @@ -6932,16 +6931,8 @@ early_param("accept_memory", accept_memory_parse); static bool page_contains_unaccepted(struct page *page, unsigned int order) { phys_addr_t start = page_to_phys(page); - phys_addr_t end = start + (PAGE_SIZE << order); - return range_contains_unaccepted_memory(start, end); -} - -static void accept_page(struct page *page, unsigned int order) -{ - phys_addr_t start = page_to_phys(page); - - accept_memory(start, start + (PAGE_SIZE << order)); + return range_contains_unaccepted_memory(start, PAGE_SIZE << order); } static bool try_to_accept_memory_one(struct zone *zone) @@ -6966,7 +6957,7 @@ static bool try_to_accept_memory_one(struct zone *zone) __ClearPageUnaccepted(page); spin_unlock_irqrestore(&zone->lock, flags); - accept_page(page, MAX_PAGE_ORDER); + accept_memory(page_to_phys(page), PAGE_SIZE << MAX_PAGE_ORDER); __free_pages_ok(page, MAX_PAGE_ORDER, FPI_TO_TAIL); @@ -7038,10 +7029,6 @@ static bool page_contains_unaccepted(struct page *page, unsigned int order) return false; } -static void accept_page(struct page *page, unsigned int order) -{ -} - static bool cond_accept_memory(struct zone *zone, unsigned int order) { return false; diff --git a/tools/testing/memblock/internal.h b/tools/testing/memblock/internal.h index f6c6e5474c3a..1cf82acb2a3e 100644 --- a/tools/testing/memblock/internal.h +++ b/tools/testing/memblock/internal.h @@ -20,7 +20,7 @@ void memblock_free_pages(struct page *page, unsigned long pfn, { } -static inline void accept_memory(phys_addr_t start, phys_addr_t end) +static inline void accept_memory(phys_addr_t start, unsigned long size) { } -- cgit v1.2.3 From 1c399e74a97ca733d0780cc51819aa81fb292c22 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Mon, 12 Aug 2024 14:12:23 -0400 Subject: mm/x86: implement arch_check_zapped_pud() Introduce arch_check_zapped_pud() to sanity check shadow stack on PUD zaps. It has the same logic as the PMD helper. One thing to mention is, it might be a good idea to use page_table_check in the future for trapping wrong setups of shadow stack pgtable entries [1]. That is left for the future as a separate effort. [1] https://lore.kernel.org/all/59d518698f664e07c036a5098833d7b56b953305.camel@intel.com Link: https://lkml.kernel.org/r/20240812181225.1360970-6-peterx@redhat.com Signed-off-by: Peter Xu Acked-by: David Hildenbrand Cc: "Edgecombe, Rick P" Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: Aneesh Kumar K.V Cc: Christophe Leroy Cc: Dan Williams Cc: Dave Jiang Cc: David Rientjes Cc: Hugh Dickins Cc: Kirill A. Shutemov Cc: Matthew Wilcox Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Oscar Salvador Cc: Paolo Bonzini Cc: Rik van Riel Cc: Sean Christopherson Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- arch/x86/include/asm/pgtable.h | 10 ++++++++++ arch/x86/mm/pgtable.c | 6 ++++++ include/linux/pgtable.h | 6 ++++++ mm/huge_memory.c | 4 +++- 4 files changed, 25 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index a2a3bd4c1bda..fdb8ac9e7030 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -174,6 +174,13 @@ static inline int pud_young(pud_t pud) return pud_flags(pud) & _PAGE_ACCESSED; } +static inline bool pud_shstk(pud_t pud) +{ + return cpu_feature_enabled(X86_FEATURE_SHSTK) && + (pud_flags(pud) & (_PAGE_RW | _PAGE_DIRTY | _PAGE_PSE)) == + (_PAGE_DIRTY | _PAGE_PSE); +} + static inline int pte_write(pte_t pte) { /* @@ -1667,6 +1674,9 @@ void arch_check_zapped_pte(struct vm_area_struct *vma, pte_t pte); #define arch_check_zapped_pmd arch_check_zapped_pmd void arch_check_zapped_pmd(struct vm_area_struct *vma, pmd_t pmd); +#define arch_check_zapped_pud arch_check_zapped_pud +void arch_check_zapped_pud(struct vm_area_struct *vma, pud_t pud); + #ifdef CONFIG_XEN_PV #define arch_has_hw_nonleaf_pmd_young arch_has_hw_nonleaf_pmd_young static inline bool arch_has_hw_nonleaf_pmd_young(void) diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index f5931499c2d6..36e7139a61d9 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -926,3 +926,9 @@ void arch_check_zapped_pmd(struct vm_area_struct *vma, pmd_t pmd) VM_WARN_ON_ONCE(!(vma->vm_flags & VM_SHADOW_STACK) && pmd_shstk(pmd)); } + +void arch_check_zapped_pud(struct vm_area_struct *vma, pud_t pud) +{ + /* See note in arch_check_zapped_pte() */ + VM_WARN_ON_ONCE(!(vma->vm_flags & VM_SHADOW_STACK) && pud_shstk(pud)); +} diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 2a6a3cccfc36..780f3b439d98 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -447,6 +447,12 @@ static inline void arch_check_zapped_pmd(struct vm_area_struct *vma, } #endif +#ifndef arch_check_zapped_pud +static inline void arch_check_zapped_pud(struct vm_area_struct *vma, pud_t pud) +{ +} +#endif + #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long address, diff --git a/mm/huge_memory.c b/mm/huge_memory.c index f2fd3aabb67b..608ea551da16 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2283,12 +2283,14 @@ int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, unsigned long addr) { spinlock_t *ptl; + pud_t orig_pud; ptl = __pud_trans_huge_lock(pud, vma); if (!ptl) return 0; - pudp_huge_get_and_clear_full(vma, addr, pud, tlb->fullmm); + orig_pud = pudp_huge_get_and_clear_full(vma, addr, pud, tlb->fullmm); + arch_check_zapped_pud(vma, orig_pud); tlb_remove_pud_tlb_entry(tlb, pud, addr); if (vma_is_special_huge(vma)) { spin_unlock(ptl); -- cgit v1.2.3 From cb0f01beb16669e91510fcdb2cea213931aee017 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Mon, 12 Aug 2024 14:12:25 -0400 Subject: mm/mprotect: fix dax pud handlings This is only relevant to the two archs that support PUD dax, aka, x86_64 and ppc64. PUD THPs do not yet exist elsewhere, and hugetlb PUDs do not count in this case. DAX have had PUD mappings for years, but change protection path never worked. When the path is triggered in any form (a simple test program would be: call mprotect() on a 1G dev_dax mapping), the kernel will report "bad pud". This patch should fix that. The new change_huge_pud() tries to keep everything simple. For example, it doesn't optimize write bit as that will need even more PUD helpers. It's not too bad anyway to have one more write fault in the worst case once for 1G range; may be a bigger thing for each PAGE_SIZE, though. Neither does it support userfault-wp bits, as there isn't such PUD mappings that is supported; file mappings always need a split there. The same to TLB shootdown: the pmd path (which was for x86 only) has the trick of using _ad() version of pmdp_invalidate*() which can avoid one redundant TLB, but let's also leave that for later. Again, the larger the mapping, the smaller of such effect. There's some difference on handling "retry" for change_huge_pud() (where it can return 0): it isn't like change_huge_pmd(), as the pmd version is safe with all conditions handled in change_pte_range() later, thanks to Hugh's new pte_offset_map_lock(). In short, change_pte_range() is simply smarter. For that, change_pud_range() will need proper retry if it races with something else when a huge PUD changed from under us. The last thing to mention is currently the PUD path ignores the huge pte numa counter (NUMA_HUGE_PTE_UPDATES), not only because DAX is not applicable to NUMA, but also that it's ambiguous on its own to decide how to account pud in this case. In one earlier version of this patchset I proposed to remove the counter as it doesn't even look right to do the accounting as of now [1], but then a further discussion suggests we can leave that for later, as that doesn't block this series if we choose to ignore that counter. That's what this patch does, by ignoring it. When at it, touch up the comment in pgtable_split_needed() to make it generic to either pmd or pud file THPs. [1] https://lore.kernel.org/all/20240715192142.3241557-3-peterx@redhat.com/ [2] https://lore.kernel.org/r/added2d0-b8be-4108-82ca-1367a388d0b1@redhat.com Link: https://lkml.kernel.org/r/20240812181225.1360970-8-peterx@redhat.com Fixes: a00cc7d9dd93 ("mm, x86: add support for PUD-sized transparent hugepages") Fixes: 27af67f35631 ("powerpc/book3s64/mm: enable transparent pud hugepage") Signed-off-by: Peter Xu Cc: Dan Williams Cc: Matthew Wilcox Cc: Dave Jiang Cc: Hugh Dickins Cc: Kirill A. Shutemov Cc: Vlastimil Babka Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: Michael Ellerman Cc: Aneesh Kumar K.V Cc: Oscar Salvador Cc: Christophe Leroy Cc: David Hildenbrand Cc: David Rientjes Cc: "Edgecombe, Rick P" Cc: Nicholas Piggin Cc: Paolo Bonzini Cc: Rik van Riel Cc: Sean Christopherson Signed-off-by: Andrew Morton --- include/linux/huge_mm.h | 24 +++++++++++++++++++++++ mm/huge_memory.c | 52 +++++++++++++++++++++++++++++++++++++++++++++++++ mm/mprotect.c | 39 +++++++++++++++++++++++++++++-------- 3 files changed, 107 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index ce44caa40eed..6370026689e0 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -342,6 +342,17 @@ void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, unsigned long address); +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +int change_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, + pud_t *pudp, unsigned long addr, pgprot_t newprot, + unsigned long cp_flags); +#else +static inline int +change_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, + pud_t *pudp, unsigned long addr, pgprot_t newprot, + unsigned long cp_flags) { return 0; } +#endif + #define split_huge_pud(__vma, __pud, __address) \ do { \ pud_t *____pud = (__pud); \ @@ -585,6 +596,19 @@ static inline int next_order(unsigned long *orders, int prev) { return 0; } + +static inline void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, + unsigned long address) +{ +} + +static inline int change_huge_pud(struct mmu_gather *tlb, + struct vm_area_struct *vma, pud_t *pudp, + unsigned long addr, pgprot_t newprot, + unsigned long cp_flags) +{ + return 0; +} #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline int split_folio_to_list_to_order(struct folio *folio, diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 608ea551da16..ac9e8a77059d 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2104,6 +2104,53 @@ unlock: return ret; } +/* + * Returns: + * + * - 0: if pud leaf changed from under us + * - 1: if pud can be skipped + * - HPAGE_PUD_NR: if pud was successfully processed + */ +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +int change_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, + pud_t *pudp, unsigned long addr, pgprot_t newprot, + unsigned long cp_flags) +{ + struct mm_struct *mm = vma->vm_mm; + pud_t oldpud, entry; + spinlock_t *ptl; + + tlb_change_page_size(tlb, HPAGE_PUD_SIZE); + + /* NUMA balancing doesn't apply to dax */ + if (cp_flags & MM_CP_PROT_NUMA) + return 1; + + /* + * Huge entries on userfault-wp only works with anonymous, while we + * don't have anonymous PUDs yet. + */ + if (WARN_ON_ONCE(cp_flags & MM_CP_UFFD_WP_ALL)) + return 1; + + ptl = __pud_trans_huge_lock(pudp, vma); + if (!ptl) + return 0; + + /* + * Can't clear PUD or it can race with concurrent zapping. See + * change_huge_pmd(). + */ + oldpud = pudp_invalidate(vma, addr, pudp); + entry = pud_modify(oldpud, newprot); + set_pud_at(mm, addr, pudp, entry); + tlb_flush_pud_range(tlb, addr, HPAGE_PUD_SIZE); + + spin_unlock(ptl); + return HPAGE_PUD_NR; +} +#endif + #ifdef CONFIG_USERFAULTFD /* * The PT lock for src_pmd and dst_vma/src_vma (for reading) are locked by @@ -2334,6 +2381,11 @@ out: spin_unlock(ptl); mmu_notifier_invalidate_range_end(&range); } +#else +void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, + unsigned long address) +{ +} #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, diff --git a/mm/mprotect.c b/mm/mprotect.c index d423080e6509..446f8e5f10d9 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -302,8 +302,9 @@ pgtable_split_needed(struct vm_area_struct *vma, unsigned long cp_flags) { /* * pte markers only resides in pte level, if we need pte markers, - * we need to split. We cannot wr-protect shmem thp because file - * thp is handled differently when split by erasing the pmd so far. + * we need to split. For example, we cannot wr-protect a file thp + * (e.g. 2M shmem) because file thp is handled differently when + * split by erasing the pmd so far. */ return (cp_flags & MM_CP_UFFD_WP) && !vma_is_anonymous(vma); } @@ -430,31 +431,53 @@ static inline long change_pud_range(struct mmu_gather *tlb, unsigned long end, pgprot_t newprot, unsigned long cp_flags) { struct mmu_notifier_range range; - pud_t *pud; + pud_t *pudp, pud; unsigned long next; long pages = 0, ret; range.start = 0; - pud = pud_offset(p4d, addr); + pudp = pud_offset(p4d, addr); do { +again: next = pud_addr_end(addr, end); - ret = change_prepare(vma, pud, pmd, addr, cp_flags); + ret = change_prepare(vma, pudp, pmd, addr, cp_flags); if (ret) { pages = ret; break; } - if (pud_none_or_clear_bad(pud)) + + pud = READ_ONCE(*pudp); + if (pud_none(pud)) continue; + if (!range.start) { mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_VMA, 0, vma->vm_mm, addr, end); mmu_notifier_invalidate_range_start(&range); } - pages += change_pmd_range(tlb, vma, pud, addr, next, newprot, + + if (pud_leaf(pud)) { + if ((next - addr != PUD_SIZE) || + pgtable_split_needed(vma, cp_flags)) { + __split_huge_pud(vma, pudp, addr); + goto again; + } else { + ret = change_huge_pud(tlb, vma, pudp, + addr, newprot, cp_flags); + if (ret == 0) + goto again; + /* huge pud was handled */ + if (ret == HPAGE_PUD_NR) + pages += HPAGE_PUD_NR; + continue; + } + } + + pages += change_pmd_range(tlb, vma, pudp, addr, next, newprot, cp_flags); - } while (pud++, addr = next, addr != end); + } while (pudp++, addr = next, addr != end); if (range.start) mmu_notifier_invalidate_range_end(&range); -- cgit v1.2.3 From 223febc6e5573cda5e94e6b38fcdaded068db777 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Mon, 12 Aug 2024 18:26:02 +1000 Subject: mm: add optional close() to struct vm_special_mapping Add an optional close() callback to struct vm_special_mapping. It will be used, by powerpc at least, to handle unmapping of the VDSO. Although support for unmapping the VDSO was initially added for CRIU[1], it is not desirable to guard that support behind CONFIG_CHECKPOINT_RESTORE. There are other known users of unmapping the VDSO which are not related to CRIU, eg. Valgrind [2] and void-ship [3]. The powerpc arch_unmap() hook has been in place for ~9 years, with no ifdef, so there may be other unknown users that have come to rely on unmapping the VDSO. Even if the code was behind an ifdef, major distros enable CHECKPOINT_RESTORE so users may not realise unmapping the VDSO depends on that configuration option. It's also undesirable to have such core mm behaviour behind a relatively obscure CONFIG option. Longer term the unmap behaviour should be standardised across architectures, however that is complicated by the fact the VDSO pointer is stored differently across architectures. There was a previous attempt to unify that handling [4], which could be revived. See [5] for further discussion. [1]: commit 83d3f0e90c6c ("powerpc/mm: tracking vDSO remap") [2]: https://sourceware.org/git/?p=valgrind.git;a=commit;h=3a004915a2cbdcdebafc1612427576bf3321eef5 [3]: https://github.com/insanitybit/void-ship [4]: https://lore.kernel.org/lkml/20210611180242.711399-17-dima@arista.com/ [5]: https://lore.kernel.org/linuxppc-dev/shiq5v3jrmyi6ncwke7wgl76ojysgbhrchsk32q4lbx2hadqqc@kzyy2igem256 Link: https://lkml.kernel.org/r/20240812082605.743814-1-mpe@ellerman.id.au Signed-off-by: Michael Ellerman Suggested-by: Linus Torvalds Reviewed-by: David Hildenbrand Reviewed-by: Liam R. Howlett Cc: Christophe Leroy Cc: Jeff Xu Cc: Nicholas Piggin Cc: Pedro Falcato Cc: Thomas Gleixner Signed-off-by: Andrew Morton --- include/linux/mm_types.h | 3 +++ mm/mmap.c | 6 ++++++ 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 003619fab20e..2419e60c9a7f 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -1324,6 +1324,9 @@ struct vm_special_mapping { int (*mremap)(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma); + + void (*close)(const struct vm_special_mapping *sm, + struct vm_area_struct *vma); }; enum tlb_flush_reason { diff --git a/mm/mmap.c b/mm/mmap.c index 4a9c2329b09a..933fdc1491a7 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2045,10 +2045,16 @@ void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, long npages) static vm_fault_t special_mapping_fault(struct vm_fault *vmf); /* + * Close hook, called for unmap() and on the old vma for mremap(). + * * Having a close hook prevents vma merging regardless of flags. */ static void special_mapping_close(struct vm_area_struct *vma) { + const struct vm_special_mapping *sm = vma->vm_private_data; + + if (sm->close) + sm->close(sm, vma); } static const char *special_mapping_name(struct vm_area_struct *vma) -- cgit v1.2.3 From 497258dfafcc6b88e7c4c46a38a479721d44cf41 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 20 Aug 2024 15:14:47 -0700 Subject: mm: remove legacy install_special_mapping() code All relevant architectures had already been converted to the new interface (which just has an underscore in front of the name - not very imaginative naming), this just force-converts the stragglers. The modern interface is almost identical to the old one, except instead of the page pointer it takes a "struct vm_special_mapping" that describes the mapping (and contains the page pointer as one member), and it returns the resulting 'vma' instead of just the error code. Getting rid of the old interface also gets rid of some special casing, which had caused problems with the mremap extensions to "struct vm_special_mapping". [akpm@linux-foundation.org: coding-style cleanups] Link: https://lkml.kernel.org/r/CAHk-=whvR+z=0=0gzgdfUiK70JTa-=+9vxD-4T=3BagXR6dciA@mail.gmail.comTested-by: Rob Landley # arch/sh/ Link: https://lore.kernel.org/all/20240819195120.GA1113263@thelio-3990X/ Signed-off-by: Linus Torvalds Cc: Nathan Chancellor Cc: Michael Ellerman Cc: Anton Ivanov Cc: Brian Cain Cc: Christophe Leroy Cc: Dinh Nguyen Cc: Guo Ren Cc: Jeff Xu Cc: Johannes Berg Cc: John Paul Adrian Glaubitz Cc: Liam R. Howlett Cc: Nicholas Piggin Cc: Pedro Falcato Cc: Richard Weinberger Cc: Rich Felker Cc: Rob Landley Cc: Yoshinori Sato Signed-off-by: Andrew Morton --- arch/csky/kernel/vdso.c | 28 +++++++++++++++++++++------- arch/hexagon/kernel/vdso.c | 14 ++++++++++---- arch/nios2/mm/init.c | 12 ++++++++---- arch/sh/kernel/vsyscall/vsyscall.c | 14 +++++++++++--- arch/x86/um/vdso/vma.c | 12 ++++++++---- include/linux/mm.h | 4 ---- mm/mmap.c | 32 +++++--------------------------- 7 files changed, 63 insertions(+), 53 deletions(-) (limited to 'include/linux') diff --git a/arch/csky/kernel/vdso.c b/arch/csky/kernel/vdso.c index 2ca886e4a458..5c9ef63c29f1 100644 --- a/arch/csky/kernel/vdso.c +++ b/arch/csky/kernel/vdso.c @@ -45,9 +45,16 @@ arch_initcall(vdso_init); int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { + struct vm_area_struct *vma; struct mm_struct *mm = current->mm; unsigned long vdso_base, vdso_len; int ret; + static struct vm_special_mapping vdso_mapping = { + .name = "[vdso]", + }; + static struct vm_special_mapping vvar_mapping = { + .name = "[vvar]", + }; vdso_len = (vdso_pages + 1) << PAGE_SHIFT; @@ -65,22 +72,29 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, */ mm->context.vdso = (void *)vdso_base; - ret = - install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT, + vdso_mapping.pages = vdso_pagelist; + vma = + _install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT, (VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC), - vdso_pagelist); + &vdso_mapping); - if (unlikely(ret)) { + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); mm->context.vdso = NULL; goto end; } vdso_base += (vdso_pages << PAGE_SHIFT); - ret = install_special_mapping(mm, vdso_base, PAGE_SIZE, - (VM_READ | VM_MAYREAD), &vdso_pagelist[vdso_pages]); + vvar_mapping.pages = &vdso_pagelist[vdso_pages]; + vma = _install_special_mapping(mm, vdso_base, PAGE_SIZE, + (VM_READ | VM_MAYREAD), &vvar_mapping); - if (unlikely(ret)) + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); mm->context.vdso = NULL; + goto end; + } + ret = 0; end: mmap_write_unlock(mm); return ret; diff --git a/arch/hexagon/kernel/vdso.c b/arch/hexagon/kernel/vdso.c index 2e4872d62124..6fd27ff1df73 100644 --- a/arch/hexagon/kernel/vdso.c +++ b/arch/hexagon/kernel/vdso.c @@ -51,7 +51,11 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { int ret; unsigned long vdso_base; + struct vm_area_struct *vma; struct mm_struct *mm = current->mm; + static struct vm_special_mapping vdso_mapping = { + name = "[vdso]", + }; if (mmap_write_lock_killable(mm)) return -EINTR; @@ -66,16 +70,18 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) } /* MAYWRITE to allow gdb to COW and set breakpoints. */ - ret = install_special_mapping(mm, vdso_base, PAGE_SIZE, + vdso_mapping.pages = &vdso_page; + vma = _install_special_mapping(mm, vdso_base, PAGE_SIZE, VM_READ|VM_EXEC| VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, - &vdso_page); + &vdso_mapping); - if (ret) + ret = PTR_ERR(vma); + if (IS_ERR(vma)) goto up_fail; mm->context.vdso = (void *)vdso_base; - + ret = 0; up_fail: mmap_write_unlock(mm); return ret; diff --git a/arch/nios2/mm/init.c b/arch/nios2/mm/init.c index 3459df28afee..a2278485de19 100644 --- a/arch/nios2/mm/init.c +++ b/arch/nios2/mm/init.c @@ -82,6 +82,10 @@ void __init mmu_init(void) pgd_t swapper_pg_dir[PTRS_PER_PGD] __aligned(PAGE_SIZE); pte_t invalid_pte_table[PTRS_PER_PTE] __aligned(PAGE_SIZE); static struct page *kuser_page[1]; +static struct vm_special_mapping vdso_mapping = { + .name = "[vdso]", + .pages = kuser_page, +}; static int alloc_kuser_page(void) { @@ -106,18 +110,18 @@ arch_initcall(alloc_kuser_page); int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { struct mm_struct *mm = current->mm; - int ret; + struct vm_area_struct *vma; mmap_write_lock(mm); /* Map kuser helpers to user space address */ - ret = install_special_mapping(mm, KUSER_BASE, KUSER_SIZE, + vma = _install_special_mapping(mm, KUSER_BASE, KUSER_SIZE, VM_READ | VM_EXEC | VM_MAYREAD | - VM_MAYEXEC, kuser_page); + VM_MAYEXEC, &vdso_mapping); mmap_write_unlock(mm); - return ret; + return IS_ERR(vma) ? PTR_ERR(vma) : 0; } const char *arch_vma_name(struct vm_area_struct *vma) diff --git a/arch/sh/kernel/vsyscall/vsyscall.c b/arch/sh/kernel/vsyscall/vsyscall.c index 1bd85a6949c4..add35c51e017 100644 --- a/arch/sh/kernel/vsyscall/vsyscall.c +++ b/arch/sh/kernel/vsyscall/vsyscall.c @@ -36,6 +36,10 @@ __setup("vdso=", vdso_setup); */ extern const char vsyscall_trapa_start, vsyscall_trapa_end; static struct page *syscall_pages[1]; +static struct vm_special_mapping vdso_mapping = { + .name = "[vdso]", + .pages = syscall_pages, +}; int __init vsyscall_init(void) { @@ -58,6 +62,7 @@ int __init vsyscall_init(void) int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; unsigned long addr; int ret; @@ -70,14 +75,17 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) goto up_fail; } - ret = install_special_mapping(mm, addr, PAGE_SIZE, + vdso_mapping.pages = syscall_pages; + vma = _install_special_mapping(mm, addr, PAGE_SIZE, VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC, - syscall_pages); - if (unlikely(ret)) + &vdso_mapping); + ret = PTR_ERR(vma); + if (IS_ERR(vma)) goto up_fail; current->mm->context.vdso = (void *)addr; + ret = 0; up_fail: mmap_write_unlock(mm); diff --git a/arch/x86/um/vdso/vma.c b/arch/x86/um/vdso/vma.c index 76d9f6ce7a3d..f238f7b33cdd 100644 --- a/arch/x86/um/vdso/vma.c +++ b/arch/x86/um/vdso/vma.c @@ -52,8 +52,11 @@ subsys_initcall(init_vdso); int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { - int err; + struct vm_area_struct *vma; struct mm_struct *mm = current->mm; + static struct vm_special_mapping vdso_mapping = { + .name = "[vdso]", + }; if (!vdso_enabled) return 0; @@ -61,12 +64,13 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) if (mmap_write_lock_killable(mm)) return -EINTR; - err = install_special_mapping(mm, um_vdso_addr, PAGE_SIZE, + vdso_mapping.pages = vdsop; + vma = _install_special_mapping(mm, um_vdso_addr, PAGE_SIZE, VM_READ|VM_EXEC| VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, - vdsop); + &vdso_mapping); mmap_write_unlock(mm); - return err; + return IS_ERR(vma) ? PTR_ERR(vma) : 0; } diff --git a/include/linux/mm.h b/include/linux/mm.h index b1eed30fdc06..0fde51c0532f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3263,10 +3263,6 @@ extern struct vm_area_struct *_install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long flags, const struct vm_special_mapping *spec); -/* This is an obsolete alternative to _install_special_mapping. */ -extern int install_special_mapping(struct mm_struct *mm, - unsigned long addr, unsigned long len, - unsigned long flags, struct page **pages); unsigned long randomize_stack_top(unsigned long stack_top); unsigned long randomize_page(unsigned long start, unsigned long range); diff --git a/mm/mmap.c b/mm/mmap.c index 3af256bacef3..7cba84f8e3a5 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2094,27 +2094,17 @@ static const struct vm_operations_struct special_mapping_vmops = { .may_split = special_mapping_split, }; -static const struct vm_operations_struct legacy_special_mapping_vmops = { - .close = special_mapping_close, - .fault = special_mapping_fault, -}; - static vm_fault_t special_mapping_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; pgoff_t pgoff; struct page **pages; + struct vm_special_mapping *sm = vma->vm_private_data; - if (vma->vm_ops == &legacy_special_mapping_vmops) { - pages = vma->vm_private_data; - } else { - struct vm_special_mapping *sm = vma->vm_private_data; + if (sm->fault) + return sm->fault(sm, vmf->vma, vmf); - if (sm->fault) - return sm->fault(sm, vmf->vma, vmf); - - pages = sm->pages; - } + pages = sm->pages; for (pgoff = vmf->pgoff; pgoff && *pages; ++pages) pgoff--; @@ -2169,8 +2159,7 @@ bool vma_is_special_mapping(const struct vm_area_struct *vma, const struct vm_special_mapping *sm) { return vma->vm_private_data == sm && - (vma->vm_ops == &special_mapping_vmops || - vma->vm_ops == &legacy_special_mapping_vmops); + vma->vm_ops == &special_mapping_vmops; } /* @@ -2191,17 +2180,6 @@ struct vm_area_struct *_install_special_mapping( &special_mapping_vmops); } -int install_special_mapping(struct mm_struct *mm, - unsigned long addr, unsigned long len, - unsigned long vm_flags, struct page **pages) -{ - struct vm_area_struct *vma = __install_special_mapping( - mm, addr, len, vm_flags, (void *)pages, - &legacy_special_mapping_vmops); - - return PTR_ERR_OR_ZERO(vma); -} - /* * initialise the percpu counter for VM */ -- cgit v1.2.3 From 02f4bbefcada38cab86b365e5c795e0f858356bc Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Wed, 14 Aug 2024 17:34:15 +0800 Subject: mm: kmem: add lockdep assertion to obj_cgroup_memcg obj_cgroup_memcg() is supposed to safe to prevent the returned memory cgroup from being freed only when the caller is holding the rcu read lock or objcg_lock or cgroup_mutex. It is very easy to ignore thoes conditions when users call some upper APIs which call obj_cgroup_memcg() internally like mem_cgroup_from_slab_obj() (See the link below). So it is better to add lockdep assertion to obj_cgroup_memcg() to find those issues ASAP. Because there is no user of obj_cgroup_memcg() holding objcg_lock to make the returned memory cgroup safe, do not add objcg_lock assertion (We should export objcg_lock if we really want to do). Additionally, this is some internal implementation detail of memcg and should not be accessible outside memcg code. Some users like __mem_cgroup_uncharge() do not care the lifetime of the returned memory cgroup, which just want to know if the folio is charged to a memory cgroup, therefore, they do not need to hold the needed locks. In which case, introduce a new helper folio_memcg_charged() to do this. Compare it to folio_memcg(), it could eliminate a memory access of objcg->memcg for kmem, actually, a really small gain. [songmuchun@bytedance.com: fix split_page_memcg()] Link: https://lkml.kernel.org/r/20240819080415.44964-1-songmuchun@bytedance.com Link: https://lore.kernel.org/all/20240718083607.42068-1-songmuchun@bytedance.com/ Link: https://lkml.kernel.org/r/20240814093415.17634-1-songmuchun@bytedance.com Signed-off-by: Muchun Song Acked-by: Shakeel Butt Acked-by: Roman Gushchin Acked-by: Vlastimil Babka Cc: Johannes Weiner Cc: Michal Hocko Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 20 +++++++++++++++++--- mm/memcontrol.c | 11 +++++------ 2 files changed, 22 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 1b79760af685..07eadf7ecbba 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -366,11 +366,11 @@ static inline bool folio_memcg_kmem(struct folio *folio); * After the initialization objcg->memcg is always pointing at * a valid memcg, but can be atomically swapped to the parent memcg. * - * The caller must ensure that the returned memcg won't be released: - * e.g. acquire the rcu_read_lock or css_set_lock. + * The caller must ensure that the returned memcg won't be released. */ static inline struct mem_cgroup *obj_cgroup_memcg(struct obj_cgroup *objcg) { + lockdep_assert_once(rcu_read_lock_held() || lockdep_is_held(&cgroup_mutex)); return READ_ONCE(objcg->memcg); } @@ -444,6 +444,19 @@ static inline struct mem_cgroup *folio_memcg(struct folio *folio) return __folio_memcg(folio); } +/* + * folio_memcg_charged - If a folio is charged to a memory cgroup. + * @folio: Pointer to the folio. + * + * Returns true if folio is charged to a memory cgroup, otherwise returns false. + */ +static inline bool folio_memcg_charged(struct folio *folio) +{ + if (folio_memcg_kmem(folio)) + return __folio_objcg(folio) != NULL; + return __folio_memcg(folio) != NULL; +} + /** * folio_memcg_rcu - Locklessly get the memory cgroup associated with a folio. * @folio: Pointer to the folio. @@ -460,7 +473,6 @@ static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) unsigned long memcg_data = READ_ONCE(folio->memcg_data); VM_BUG_ON_FOLIO(folio_test_slab(folio), folio); - WARN_ON_ONCE(!rcu_read_lock_held()); if (memcg_data & MEMCG_DATA_KMEM) { struct obj_cgroup *objcg; @@ -469,6 +481,8 @@ static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) return obj_cgroup_memcg(objcg); } + WARN_ON_ONCE(!rcu_read_lock_held()); + return (struct mem_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index cb2996d5d3f4..96f85fd0e5b3 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2374,7 +2374,7 @@ void mem_cgroup_cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) static void commit_charge(struct folio *folio, struct mem_cgroup *memcg) { - VM_BUG_ON_FOLIO(folio_memcg(folio), folio); + VM_BUG_ON_FOLIO(folio_memcg_charged(folio), folio); /* * Any of the following ensures page's memcg stability: * @@ -3035,12 +3035,11 @@ void __memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab, void split_page_memcg(struct page *head, int old_order, int new_order) { struct folio *folio = page_folio(head); - struct mem_cgroup *memcg = folio_memcg(folio); int i; unsigned int old_nr = 1 << old_order; unsigned int new_nr = 1 << new_order; - if (mem_cgroup_disabled() || !memcg) + if (mem_cgroup_disabled() || !folio_memcg_charged(folio)) return; for (i = new_nr; i < old_nr; i += new_nr) @@ -3049,7 +3048,7 @@ void split_page_memcg(struct page *head, int old_order, int new_order) if (folio_memcg_kmem(folio)) obj_cgroup_get_many(__folio_objcg(folio), old_nr / new_nr - 1); else - css_get_many(&memcg->css, old_nr / new_nr - 1); + css_get_many(&folio_memcg(folio)->css, old_nr / new_nr - 1); } unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) @@ -4707,7 +4706,7 @@ void __mem_cgroup_uncharge(struct folio *folio) struct uncharge_gather ug; /* Don't touch folio->lru of any random page, pre-check: */ - if (!folio_memcg(folio)) + if (!folio_memcg_charged(folio)) return; uncharge_gather_clear(&ug); @@ -4752,7 +4751,7 @@ void mem_cgroup_replace_folio(struct folio *old, struct folio *new) return; /* Page cache replacement: new folio already charged? */ - if (folio_memcg(new)) + if (folio_memcg_charged(new)) return; memcg = folio_memcg(old); -- cgit v1.2.3 From bd164d81a767f33c30d5c5b50b775631699ee976 Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Wed, 14 Aug 2024 12:19:28 -0400 Subject: maple_tree: introduce store_type enum Patch series "Introduce a store type enum for the Maple tree", v4. ================================ OVERVIEW ================================ This series implements two work items[3]: "aligning mas_store_gfp() with mas_preallocate()" and "enum for store type". mas_store_gfp() is modified to preallocate nodes. This simplies many of the write helper functions by allowing them to use mas_store_gfp() rather than open coding node allocation and error handling. The enum defines the following store types: enum store_type { wr_invalid, wr_new_root, wr_store_root, wr_exact_fit, wr_spanning_store, wr_split_store, wr_rebalance, wr_append, wr_node_store, wr_slot_store, }; In the current maple tree code, a walk down the tree is done in mas_preallocate() to determine the number of nodes needed for this write. After node allocation, mas_wr_store_entry() will perform another walk to determine which write helper function to use to complete the write. Rather than performing the second walk, we can store the type of write in the maple write state during node allocation and read this field to complete the write. Patches 1-16 implement this store type feature. Patch 17 is a cleanup patch to change functions that have unused return types to be void. ================================ RESULTS ================================= Phoronix t-test-1 (Seconds < Lower Is Better) v6.10-rc6 Threads: 1 33.15 Threads: 2 10.81 v6.10-rc6 + this series Threads: 1 32.69 Threads: 2 10.45 Stress-ng mmap 6.10_base store_type_v4 Duration User 2744.65 2769.40 Duration System 10862.69 10817.59 Duration Elapsed 1477.58 1478.35 ================================ TESTING ================================= Testing was done with the maple tree test suite. A new test case is also added to validate the order in which we test for and assign the store type. [1]: https://lore.kernel.org/linux-mm/80926b22-a8d2-9992-eb5e-27e2c99cf460@google.com/T/#m81044feb66765265f8ca7f21e4b4b3725b18780a [2]: https://lore.kernel.org/linux-mm/80926b22-a8d2-9992-eb5e-27e2c99cf460@google.com/T/#mb36c6526486638e82518c0f37a428fb279c84d8a [3]: https://lists.infradead.org/pipermail/maple-tree/2023-December/003098.html This patch (of 17): Add a store_type enum that is stored in ma_state. This will be used to keep track of partial walks of the tree so that subsequent walks can pick up where a previous walk left off. Link: https://lkml.kernel.org/r/20240814161944.55347-1-sidhartha.kumar@oracle.com Link: https://lkml.kernel.org/r/20240814161944.55347-2-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar Cc: Liam R. Howlett Cc: Matthew Wilcox (Oracle) Cc: Suren Baghdasaryan Signed-off-by: Andrew Morton --- include/linux/maple_tree.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h index a53ad4dabd7e..8e1504a81cd2 100644 --- a/include/linux/maple_tree.h +++ b/include/linux/maple_tree.h @@ -148,6 +148,18 @@ enum maple_type { maple_arange_64, }; +enum store_type { + wr_invalid, + wr_new_root, + wr_store_root, + wr_exact_fit, + wr_spanning_store, + wr_split_store, + wr_rebalance, + wr_append, + wr_node_store, + wr_slot_store, +}; /** * DOC: Maple tree flags @@ -436,6 +448,7 @@ struct ma_state { unsigned char offset; unsigned char mas_flags; unsigned char end; /* The end of the node */ + enum store_type store_type; /* The type of store needed for this operation */ }; struct ma_wr_state { @@ -477,6 +490,7 @@ struct ma_wr_state { .max = ULONG_MAX, \ .alloc = NULL, \ .mas_flags = 0, \ + .store_type = wr_invalid, \ } #define MA_WR_STATE(name, ma_state, wr_entry) \ -- cgit v1.2.3 From 5d383b69a04e2eb2e0ae06e91821fd82cb9acf73 Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Wed, 14 Aug 2024 22:04:47 -0700 Subject: memcg: move v1 only percpu stats in separate struct Patch series "memcg: further decouple v1 code from v2". Some of the v1 code is still in v2 code base due to v1 fields in the struct memcg_vmstats_percpu. This field decouples those fileds from v2 struct and move all the related code into v1 only code base. This patch (of 7): At the moment struct memcg_vmstats_percpu contains two v1 only fields which consumes memory even when CONFIG_MEMCG_V1 is not enabled. In addition there are v1 only functions accessing them and are in the main memcontrol source file and can not be moved to v1 only source file due to these fields. Let's move these fields into their own struct. Later patches will move the functions accessing them to v1 source file and only allocate these fields when CONFIG_MEMCG_V1 is enabled. Link: https://lkml.kernel.org/r/20240815050453.1298138-1-shakeel.butt@linux.dev Link: https://lkml.kernel.org/r/20240815050453.1298138-2-shakeel.butt@linux.dev Signed-off-by: Shakeel Butt Acked-by: Roman Gushchin Cc: Johannes Weiner Cc: Michal Hocko Cc: Muchun Song Cc: T.J. Mercier Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 2 ++ mm/memcontrol-v1.h | 19 +++++++++++++++++++ mm/memcontrol.c | 18 +++++++++--------- 3 files changed, 30 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 07eadf7ecbba..08b7121cf43a 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -70,6 +70,7 @@ struct mem_cgroup_id { }; struct memcg_vmstats_percpu; +struct memcg1_events_percpu; struct memcg_vmstats; struct lruvec_stats_percpu; struct lruvec_stats; @@ -254,6 +255,7 @@ struct mem_cgroup { struct list_head objcg_list; struct memcg_vmstats_percpu __percpu *vmstats_percpu; + struct memcg1_events_percpu __percpu *events_percpu; #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; diff --git a/mm/memcontrol-v1.h b/mm/memcontrol-v1.h index 56d7eaa98274..8feccecf8e2a 100644 --- a/mm/memcontrol-v1.h +++ b/mm/memcontrol-v1.h @@ -56,6 +56,12 @@ enum mem_cgroup_events_target { MEM_CGROUP_NTARGETS, }; +/* Cgroup1: threshold notifications & softlimit tree updates */ +struct memcg1_events_percpu { + unsigned long nr_page_events; + unsigned long targets[MEM_CGROUP_NTARGETS]; +}; + bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg, enum mem_cgroup_events_target target); unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap); @@ -69,6 +75,19 @@ unsigned long memcg_page_state_output(struct mem_cgroup *memcg, int item); unsigned long memcg_page_state_local_output(struct mem_cgroup *memcg, int item); int memory_stat_show(struct seq_file *m, void *v); +static inline bool memcg1_alloc_events(struct mem_cgroup *memcg) +{ + memcg->events_percpu = alloc_percpu_gfp(struct memcg1_events_percpu, + GFP_KERNEL_ACCOUNT); + return !!memcg->events_percpu; +} + +static inline void memcg1_free_events(struct mem_cgroup *memcg) +{ + if (memcg->events_percpu) + free_percpu(memcg->events_percpu); +} + /* Cgroup v1-specific declarations */ #ifdef CONFIG_MEMCG_V1 void memcg1_memcg_init(struct mem_cgroup *memcg); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 96f85fd0e5b3..36ec28d3d25e 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -477,10 +477,6 @@ struct memcg_vmstats_percpu { /* Delta calculation for lockless upward propagation */ long state_prev[MEMCG_VMSTAT_SIZE]; unsigned long events_prev[NR_MEMCG_EVENTS]; - - /* Cgroup1: threshold notifications & softlimit tree updates */ - unsigned long nr_page_events; - unsigned long targets[MEM_CGROUP_NTARGETS]; } ____cacheline_aligned; struct memcg_vmstats { @@ -857,7 +853,7 @@ void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, int nr_pages) nr_pages = -nr_pages; /* for event */ } - __this_cpu_add(memcg->vmstats_percpu->nr_page_events, nr_pages); + __this_cpu_add(memcg->events_percpu->nr_page_events, nr_pages); } bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg, @@ -865,8 +861,8 @@ bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg, { unsigned long val, next; - val = __this_cpu_read(memcg->vmstats_percpu->nr_page_events); - next = __this_cpu_read(memcg->vmstats_percpu->targets[target]); + val = __this_cpu_read(memcg->events_percpu->nr_page_events); + next = __this_cpu_read(memcg->events_percpu->targets[target]); /* from time_after() in jiffies.h */ if ((long)(next - val) < 0) { switch (target) { @@ -879,7 +875,7 @@ bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg, default: break; } - __this_cpu_write(memcg->vmstats_percpu->targets[target], next); + __this_cpu_write(memcg->events_percpu->targets[target], next); return true; } return false; @@ -3477,6 +3473,7 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) for_each_node(node) free_mem_cgroup_per_node_info(memcg, node); + memcg1_free_events(memcg); kfree(memcg->vmstats); free_percpu(memcg->vmstats_percpu); kfree(memcg); @@ -3517,6 +3514,9 @@ static struct mem_cgroup *mem_cgroup_alloc(struct mem_cgroup *parent) if (!memcg->vmstats_percpu) goto fail; + if (!memcg1_alloc_events(memcg)) + goto fail; + for_each_possible_cpu(cpu) { if (parent) pstatc = per_cpu_ptr(parent->vmstats_percpu, cpu); @@ -4631,7 +4631,7 @@ static void uncharge_batch(const struct uncharge_gather *ug) local_irq_save(flags); __count_memcg_events(ug->memcg, PGPGOUT, ug->pgpgout); - __this_cpu_add(ug->memcg->vmstats_percpu->nr_page_events, ug->nr_memory); + __this_cpu_add(ug->memcg->events_percpu->nr_page_events, ug->nr_memory); memcg1_check_events(ug->memcg, ug->nid); local_irq_restore(flags); -- cgit v1.2.3 From 0ccaf421d6592bb99bb9b424e4ccca3c6367d799 Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Wed, 14 Aug 2024 22:04:52 -0700 Subject: memcg: allocate v1 event percpu only on v1 deployment Currently memcg->events_percpu gets allocated on v2 deployments. Let's move the allocation to v1 only codebase. This is not needed in v2. Link: https://lkml.kernel.org/r/20240815050453.1298138-7-shakeel.butt@linux.dev Signed-off-by: Shakeel Butt Cc: Johannes Weiner Cc: Michal Hocko Cc: Muchun Song Cc: Roman Gushchin Cc: T.J. Mercier Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 3 ++- mm/memcontrol-v1.c | 19 +++++++++++++++++++ mm/memcontrol-v1.h | 26 +++++++------------------- 3 files changed, 28 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 08b7121cf43a..ed170399179a 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -255,7 +255,6 @@ struct mem_cgroup { struct list_head objcg_list; struct memcg_vmstats_percpu __percpu *vmstats_percpu; - struct memcg1_events_percpu __percpu *events_percpu; #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; @@ -277,6 +276,8 @@ struct mem_cgroup { struct page_counter kmem; /* v1 only */ struct page_counter tcpmem; /* v1 only */ + struct memcg1_events_percpu __percpu *events_percpu; + unsigned long soft_limit; /* protected by memcg_oom_lock */ diff --git a/mm/memcontrol-v1.c b/mm/memcontrol-v1.c index 8168a0c965b7..ff972a35ecc5 100644 --- a/mm/memcontrol-v1.c +++ b/mm/memcontrol-v1.c @@ -1442,6 +1442,12 @@ static void mem_cgroup_threshold(struct mem_cgroup *memcg) } } +/* Cgroup1: threshold notifications & softlimit tree updates */ +struct memcg1_events_percpu { + unsigned long nr_page_events; + unsigned long targets[MEM_CGROUP_NTARGETS]; +}; + static void memcg1_charge_statistics(struct mem_cgroup *memcg, int nr_pages) { /* pagein of a big page is an event. So, ignore page size */ @@ -3033,6 +3039,19 @@ bool memcg1_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages, return false; } +bool memcg1_alloc_events(struct mem_cgroup *memcg) +{ + memcg->events_percpu = alloc_percpu_gfp(struct memcg1_events_percpu, + GFP_KERNEL_ACCOUNT); + return !!memcg->events_percpu; +} + +void memcg1_free_events(struct mem_cgroup *memcg) +{ + if (memcg->events_percpu) + free_percpu(memcg->events_percpu); +} + static int __init memcg1_init(void) { int node; diff --git a/mm/memcontrol-v1.h b/mm/memcontrol-v1.h index 0a9f3f9c2362..3bb8b3030e61 100644 --- a/mm/memcontrol-v1.h +++ b/mm/memcontrol-v1.h @@ -55,12 +55,6 @@ enum mem_cgroup_events_target { MEM_CGROUP_NTARGETS, }; -/* Cgroup1: threshold notifications & softlimit tree updates */ -struct memcg1_events_percpu { - unsigned long nr_page_events; - unsigned long targets[MEM_CGROUP_NTARGETS]; -}; - unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap); void drain_all_stock(struct mem_cgroup *root_memcg); @@ -72,21 +66,12 @@ unsigned long memcg_page_state_output(struct mem_cgroup *memcg, int item); unsigned long memcg_page_state_local_output(struct mem_cgroup *memcg, int item); int memory_stat_show(struct seq_file *m, void *v); -static inline bool memcg1_alloc_events(struct mem_cgroup *memcg) -{ - memcg->events_percpu = alloc_percpu_gfp(struct memcg1_events_percpu, - GFP_KERNEL_ACCOUNT); - return !!memcg->events_percpu; -} - -static inline void memcg1_free_events(struct mem_cgroup *memcg) -{ - if (memcg->events_percpu) - free_percpu(memcg->events_percpu); -} - /* Cgroup v1-specific declarations */ #ifdef CONFIG_MEMCG_V1 + +bool memcg1_alloc_events(struct mem_cgroup *memcg); +void memcg1_free_events(struct mem_cgroup *memcg); + void memcg1_memcg_init(struct mem_cgroup *memcg); void memcg1_remove_from_trees(struct mem_cgroup *memcg); @@ -139,6 +124,9 @@ extern struct cftype mem_cgroup_legacy_files[]; #else /* CONFIG_MEMCG_V1 */ +static inline bool memcg1_alloc_events(struct mem_cgroup *memcg) { return true; } +static inline void memcg1_free_events(struct mem_cgroup *memcg) {} + static inline void memcg1_memcg_init(struct mem_cgroup *memcg) {} static inline void memcg1_remove_from_trees(struct mem_cgroup *memcg) {} static inline void memcg1_soft_limit_reset(struct mem_cgroup *memcg) {} -- cgit v1.2.3 From 836d13a6ef8a2eb0eab2bd2de06f2deabc62b060 Mon Sep 17 00:00:00 2001 From: Lasse Collin Date: Sun, 21 Jul 2024 16:36:18 +0300 Subject: xz: switch from public domain to BSD Zero Clause License (0BSD) Remove the public domain notices and add SPDX license identifiers. Change MODULE_LICENSE from "GPL" to "Dual BSD/GPL" because 0BSD should count as a BSD license variant here. The switch to 0BSD was done in the upstream XZ Embedded project because public domain has (real or perceived) legal issues in some jurisdictions. Link: https://lkml.kernel.org/r/20240721133633.47721-4-lasse.collin@tukaani.org Signed-off-by: Lasse Collin Reviewed-by: Sam James Cc: Thomas Gleixner Cc: Greg Kroah-Hartman Cc: Albert Ou Cc: Catalin Marinas Cc: Emil Renner Berthing Cc: Herbert Xu Cc: Joel Stanley Cc: Jonathan Corbet Cc: Jubin Zhong Cc: Jules Maselbas Cc: Krzysztof Kozlowski Cc: Michael Ellerman Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Randy Dunlap Cc: Rui Li Cc: Simon Glass Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/decompress/unxz.h | 5 ++--- include/linux/xz.h | 5 ++--- lib/decompress_unxz.c | 5 ++--- lib/xz/xz_crc32.c | 5 ++--- lib/xz/xz_dec_bcj.c | 5 ++--- lib/xz/xz_dec_lzma2.c | 5 ++--- lib/xz/xz_dec_stream.c | 5 ++--- lib/xz/xz_dec_syms.c | 12 +++--------- lib/xz/xz_dec_test.c | 12 +++--------- lib/xz/xz_lzma2.h | 5 ++--- lib/xz/xz_private.h | 5 ++--- lib/xz/xz_stream.h | 5 ++--- scripts/xz_wrap.sh | 5 +---- 13 files changed, 27 insertions(+), 52 deletions(-) (limited to 'include/linux') diff --git a/include/linux/decompress/unxz.h b/include/linux/decompress/unxz.h index f764e2a7201e..3dd2658a9dab 100644 --- a/include/linux/decompress/unxz.h +++ b/include/linux/decompress/unxz.h @@ -1,10 +1,9 @@ +/* SPDX-License-Identifier: 0BSD */ + /* * Wrapper for decompressing XZ-compressed kernel, initramfs, and initrd * * Author: Lasse Collin - * - * This file has been put into the public domain. - * You can do whatever you want with this file. */ #ifndef DECOMPRESS_UNXZ_H diff --git a/include/linux/xz.h b/include/linux/xz.h index 7285ca5d56e9..5728d57aecc0 100644 --- a/include/linux/xz.h +++ b/include/linux/xz.h @@ -1,11 +1,10 @@ +/* SPDX-License-Identifier: 0BSD */ + /* * XZ decompressor * * Authors: Lasse Collin * Igor Pavlov - * - * This file has been put into the public domain. - * You can do whatever you want with this file. */ #ifndef XZ_H diff --git a/lib/decompress_unxz.c b/lib/decompress_unxz.c index 842894158944..34bb7efc0412 100644 --- a/lib/decompress_unxz.c +++ b/lib/decompress_unxz.c @@ -1,10 +1,9 @@ +// SPDX-License-Identifier: 0BSD + /* * Wrapper for decompressing XZ-compressed kernel, initramfs, and initrd * * Author: Lasse Collin - * - * This file has been put into the public domain. - * You can do whatever you want with this file. */ /* diff --git a/lib/xz/xz_crc32.c b/lib/xz/xz_crc32.c index 88a2c35e1b59..30b8a27110b1 100644 --- a/lib/xz/xz_crc32.c +++ b/lib/xz/xz_crc32.c @@ -1,11 +1,10 @@ +// SPDX-License-Identifier: 0BSD + /* * CRC32 using the polynomial from IEEE-802.3 * * Authors: Lasse Collin * Igor Pavlov - * - * This file has been put into the public domain. - * You can do whatever you want with this file. */ /* diff --git a/lib/xz/xz_dec_bcj.c b/lib/xz/xz_dec_bcj.c index ef449e97d1a1..ab9237ed6db8 100644 --- a/lib/xz/xz_dec_bcj.c +++ b/lib/xz/xz_dec_bcj.c @@ -1,11 +1,10 @@ +// SPDX-License-Identifier: 0BSD + /* * Branch/Call/Jump (BCJ) filter decoders * * Authors: Lasse Collin * Igor Pavlov - * - * This file has been put into the public domain. - * You can do whatever you want with this file. */ #include "xz_private.h" diff --git a/lib/xz/xz_dec_lzma2.c b/lib/xz/xz_dec_lzma2.c index 27ce34520e78..613939f5dd6c 100644 --- a/lib/xz/xz_dec_lzma2.c +++ b/lib/xz/xz_dec_lzma2.c @@ -1,11 +1,10 @@ +// SPDX-License-Identifier: 0BSD + /* * LZMA2 decoder * * Authors: Lasse Collin * Igor Pavlov - * - * This file has been put into the public domain. - * You can do whatever you want with this file. */ #include "xz_private.h" diff --git a/lib/xz/xz_dec_stream.c b/lib/xz/xz_dec_stream.c index 683570b93a8c..0058406ccd17 100644 --- a/lib/xz/xz_dec_stream.c +++ b/lib/xz/xz_dec_stream.c @@ -1,10 +1,9 @@ +// SPDX-License-Identifier: 0BSD + /* * .xz Stream decoder * * Author: Lasse Collin - * - * This file has been put into the public domain. - * You can do whatever you want with this file. */ #include "xz_private.h" diff --git a/lib/xz/xz_dec_syms.c b/lib/xz/xz_dec_syms.c index 61098c67a413..495d2cc2e6e8 100644 --- a/lib/xz/xz_dec_syms.c +++ b/lib/xz/xz_dec_syms.c @@ -1,10 +1,9 @@ +// SPDX-License-Identifier: 0BSD + /* * XZ decoder module information * * Author: Lasse Collin - * - * This file has been put into the public domain. - * You can do whatever you want with this file. */ #include @@ -25,9 +24,4 @@ EXPORT_SYMBOL(xz_dec_microlzma_end); MODULE_DESCRIPTION("XZ decompressor"); MODULE_VERSION("1.1"); MODULE_AUTHOR("Lasse Collin and Igor Pavlov"); - -/* - * This code is in the public domain, but in Linux it's simplest to just - * say it's GPL and consider the authors as the copyright holders. - */ -MODULE_LICENSE("GPL"); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/lib/xz/xz_dec_test.c b/lib/xz/xz_dec_test.c index da28a19d6c98..53d3600f2ddb 100644 --- a/lib/xz/xz_dec_test.c +++ b/lib/xz/xz_dec_test.c @@ -1,10 +1,9 @@ +// SPDX-License-Identifier: 0BSD + /* * XZ decoder tester * * Author: Lasse Collin - * - * This file has been put into the public domain. - * You can do whatever you want with this file. */ #include @@ -212,9 +211,4 @@ module_exit(xz_dec_test_exit); MODULE_DESCRIPTION("XZ decompressor tester"); MODULE_VERSION("1.0"); MODULE_AUTHOR("Lasse Collin "); - -/* - * This code is in the public domain, but in Linux it's simplest to just - * say it's GPL and consider the authors as the copyright holders. - */ -MODULE_LICENSE("GPL"); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/lib/xz/xz_lzma2.h b/lib/xz/xz_lzma2.h index 92d852d4f87a..d2632b7dfb9c 100644 --- a/lib/xz/xz_lzma2.h +++ b/lib/xz/xz_lzma2.h @@ -1,11 +1,10 @@ +/* SPDX-License-Identifier: 0BSD */ + /* * LZMA2 definitions * * Authors: Lasse Collin * Igor Pavlov - * - * This file has been put into the public domain. - * You can do whatever you want with this file. */ #ifndef XZ_LZMA2_H diff --git a/lib/xz/xz_private.h b/lib/xz/xz_private.h index bf1e94ec7873..2412a5d54801 100644 --- a/lib/xz/xz_private.h +++ b/lib/xz/xz_private.h @@ -1,10 +1,9 @@ +/* SPDX-License-Identifier: 0BSD */ + /* * Private includes and definitions * * Author: Lasse Collin - * - * This file has been put into the public domain. - * You can do whatever you want with this file. */ #ifndef XZ_PRIVATE_H diff --git a/lib/xz/xz_stream.h b/lib/xz/xz_stream.h index 430bb3a0d195..55f9f6f94b78 100644 --- a/lib/xz/xz_stream.h +++ b/lib/xz/xz_stream.h @@ -1,10 +1,9 @@ +/* SPDX-License-Identifier: 0BSD */ + /* * Definitions for handling the .xz file format * * Author: Lasse Collin - * - * This file has been put into the public domain. - * You can do whatever you want with this file. */ #ifndef XZ_STREAM_H diff --git a/scripts/xz_wrap.sh b/scripts/xz_wrap.sh index d06baf626abe..bb760b721b2c 100755 --- a/scripts/xz_wrap.sh +++ b/scripts/xz_wrap.sh @@ -1,13 +1,10 @@ #!/bin/sh +# SPDX-License-Identifier: 0BSD # # This is a wrapper for xz to compress the kernel image using appropriate # compression options depending on the architecture. # # Author: Lasse Collin -# -# This file has been put into the public domain. -# You can do whatever you want with this file. -# BCJ= LZMA2OPTS= -- cgit v1.2.3 From ad8c67b870d108aa1286f4fc76d0c29a736fd75e Mon Sep 17 00:00:00 2001 From: Lasse Collin Date: Sun, 21 Jul 2024 16:36:20 +0300 Subject: xz: fix kernel-doc formatting errors in xz.h The opaque structs xz_dec and xz_dec_microlzma are declared in xz.h but their definitions are in xz_dec_lzma2.c without kernel-doc comments. Use regular comments for these structs in xz.h to avoid errors when building the docs. Add a few missing colons. Link: https://lkml.kernel.org/r/20240721133633.47721-6-lasse.collin@tukaani.org Signed-off-by: Lasse Collin Reviewed-by: Sam James Cc: Albert Ou Cc: Catalin Marinas Cc: Emil Renner Berthing Cc: Greg Kroah-Hartman Cc: Herbert Xu Cc: Joel Stanley Cc: Jonathan Corbet Cc: Jubin Zhong Cc: Jules Maselbas Cc: Krzysztof Kozlowski Cc: Michael Ellerman Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Randy Dunlap Cc: Rui Li Cc: Simon Glass Cc: Thomas Gleixner Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/xz.h | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xz.h b/include/linux/xz.h index 5728d57aecc0..af1e075d9add 100644 --- a/include/linux/xz.h +++ b/include/linux/xz.h @@ -142,7 +142,7 @@ struct xz_buf { size_t out_size; }; -/** +/* * struct xz_dec - Opaque type to hold the XZ decoder state */ struct xz_dec; @@ -240,15 +240,16 @@ XZ_EXTERN void xz_dec_end(struct xz_dec *s); * marked with XZ_EXTERN. This avoids warnings about static functions that * are never defined. */ -/** + +/* * struct xz_dec_microlzma - Opaque type to hold the MicroLZMA decoder state */ struct xz_dec_microlzma; /** * xz_dec_microlzma_alloc() - Allocate memory for the MicroLZMA decoder - * @mode XZ_SINGLE or XZ_PREALLOC - * @dict_size LZMA dictionary size. This must be at least 4 KiB and + * @mode: XZ_SINGLE or XZ_PREALLOC + * @dict_size: LZMA dictionary size. This must be at least 4 KiB and * at most 3 GiB. * * In contrast to xz_dec_init(), this function only allocates the memory @@ -276,15 +277,15 @@ extern struct xz_dec_microlzma *xz_dec_microlzma_alloc(enum xz_mode mode, /** * xz_dec_microlzma_reset() - Reset the MicroLZMA decoder state - * @s Decoder state allocated using xz_dec_microlzma_alloc() - * @comp_size Compressed size of the input stream - * @uncomp_size Uncompressed size of the input stream. A value smaller + * @s: Decoder state allocated using xz_dec_microlzma_alloc() + * @comp_size: Compressed size of the input stream + * @uncomp_size: Uncompressed size of the input stream. A value smaller * than the real uncompressed size of the input stream can * be specified if uncomp_size_is_exact is set to false. * uncomp_size can never be set to a value larger than the * expected real uncompressed size because it would eventually * result in XZ_DATA_ERROR. - * @uncomp_size_is_exact This is an int instead of bool to avoid + * @uncomp_size_is_exact: This is an int instead of bool to avoid * requiring stdbool.h. This should normally be set to true. * When this is set to false, error detection is weaker. */ @@ -294,7 +295,7 @@ extern void xz_dec_microlzma_reset(struct xz_dec_microlzma *s, /** * xz_dec_microlzma_run() - Run the MicroLZMA decoder - * @s Decoder state initialized using xz_dec_microlzma_reset() + * @s: Decoder state initialized using xz_dec_microlzma_reset() * @b: Input and output buffers * * This works similarly to xz_dec_run() with a few important differences. -- cgit v1.2.3 From 0f2c5996340b69d167d3f6ca38d3012204787ac1 Mon Sep 17 00:00:00 2001 From: Lasse Collin Date: Sun, 21 Jul 2024 16:36:21 +0300 Subject: xz: improve the MicroLZMA kernel-doc in xz.h Move the description of the format into a "DOC:" comment. Emphasize that MicroLZMA functions aren't usually needed. Link: https://lkml.kernel.org/r/20240721133633.47721-7-lasse.collin@tukaani.org Signed-off-by: Lasse Collin Reviewed-by: Sam James Cc: Albert Ou Cc: Catalin Marinas Cc: Emil Renner Berthing Cc: Greg Kroah-Hartman Cc: Herbert Xu Cc: Joel Stanley Cc: Jonathan Corbet Cc: Jubin Zhong Cc: Jules Maselbas Cc: Krzysztof Kozlowski Cc: Michael Ellerman Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Randy Dunlap Cc: Rui Li Cc: Simon Glass Cc: Thomas Gleixner Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/xz.h | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xz.h b/include/linux/xz.h index af1e075d9add..701d62c02b9a 100644 --- a/include/linux/xz.h +++ b/include/linux/xz.h @@ -232,9 +232,18 @@ XZ_EXTERN void xz_dec_reset(struct xz_dec *s); */ XZ_EXTERN void xz_dec_end(struct xz_dec *s); -/* - * Decompressor for MicroLZMA, an LZMA variant with a very minimal header. - * See xz_dec_microlzma_alloc() below for details. +/** + * DOC: MicroLZMA decompressor + * + * This MicroLZMA header format was created for use in EROFS but may be used + * by others too. **In most cases one needs the XZ APIs above instead.** + * + * The compressed format supported by this decoder is a raw LZMA stream + * whose first byte (always 0x00) has been replaced with bitwise-negation + * of the LZMA properties (lc/lp/pb) byte. For example, if lc/lp/pb is + * 3/0/2, the first byte is 0xA2. This way the first byte can never be 0x00. + * Just like with LZMA2, lc + lp <= 4 must be true. The LZMA end-of-stream + * marker must not be used. The unused values are reserved for future use. * * These functions aren't used or available in preboot code and thus aren't * marked with XZ_EXTERN. This avoids warnings about static functions that @@ -262,15 +271,6 @@ struct xz_dec_microlzma; * On success, xz_dec_microlzma_alloc() returns a pointer to * struct xz_dec_microlzma. If memory allocation fails or * dict_size is invalid, NULL is returned. - * - * The compressed format supported by this decoder is a raw LZMA stream - * whose first byte (always 0x00) has been replaced with bitwise-negation - * of the LZMA properties (lc/lp/pb) byte. For example, if lc/lp/pb is - * 3/0/2, the first byte is 0xA2. This way the first byte can never be 0x00. - * Just like with LZMA2, lc + lp <= 4 must be true. The LZMA end-of-stream - * marker must not be used. The unused values are reserved for future use. - * This MicroLZMA header format was created for use in EROFS but may be used - * by others too. */ extern struct xz_dec_microlzma *xz_dec_microlzma_alloc(enum xz_mode mode, uint32_t dict_size); -- cgit v1.2.3 From c6f371bab25edccd39caa5dd452b50d9dfdf4ff0 Mon Sep 17 00:00:00 2001 From: Lasse Collin Date: Wed, 24 Jul 2024 14:05:41 +0300 Subject: xz: remove XZ_EXTERN and extern from functions XZ_EXTERN was used to make internal functions static in the preboot code. However, in other decompressors this hasn't been done. On x86-64, this makes no difference to the kernel image size. Omit XZ_EXTERN and let some of the internal functions be extern in the preboot code. Omitting XZ_EXTERN from include/linux/xz.h fixes warnings in "make htmldocs" and makes the intradocument links to xz_dec functions work in Documentation/staging/xz.rst. The alternative would have been to add "XZ_EXTERN" to c_id_attributes in Documentation/conf.py but omitting XZ_EXTERN seemed cleaner. Link: https://lore.kernel.org/lkml/20240723205437.3c0664b0@kaneli/ Link: https://lkml.kernel.org/r/20240724110544.16430-1-lasse.collin@tukaani.org Signed-off-by: Lasse Collin Tested-by: Michael Ellerman (powerpc) Cc: Jonathan Corbet Cc: Sam James Cc: Albert Ou Cc: Catalin Marinas Cc: Emil Renner Berthing Cc: Greg Kroah-Hartman Cc: Herbert Xu Cc: Joel Stanley Cc: Jubin Zhong Cc: Jules Maselbas Cc: Krzysztof Kozlowski Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Randy Dunlap Cc: Rui Li Cc: Simon Glass Cc: Thomas Gleixner Cc: Will Deacon Signed-off-by: Andrew Morton --- Documentation/staging/xz.rst | 3 --- arch/powerpc/boot/xz_config.h | 3 --- include/linux/xz.h | 35 ++++++++++++----------------------- lib/decompress_unxz.c | 1 - lib/xz/xz_crc32.c | 4 ++-- lib/xz/xz_dec_bcj.c | 9 ++++----- lib/xz/xz_dec_lzma2.c | 10 ++++------ lib/xz/xz_dec_stream.c | 8 ++++---- lib/xz/xz_private.h | 20 ++++++++------------ 9 files changed, 34 insertions(+), 59 deletions(-) (limited to 'include/linux') diff --git a/Documentation/staging/xz.rst b/Documentation/staging/xz.rst index e1054e9a8e65..6953a189e5f2 100644 --- a/Documentation/staging/xz.rst +++ b/Documentation/staging/xz.rst @@ -95,7 +95,4 @@ xz_dec API This is available with ``#include ``. -``XZ_EXTERN`` is a macro used in the preboot code. Ignore it when -reading this documentation. - .. kernel-doc:: include/linux/xz.h diff --git a/arch/powerpc/boot/xz_config.h b/arch/powerpc/boot/xz_config.h index ebfadd39e192..9506a96ebbcc 100644 --- a/arch/powerpc/boot/xz_config.h +++ b/arch/powerpc/boot/xz_config.h @@ -50,11 +50,8 @@ static inline void put_unaligned_be32(u32 val, void *p) /* prevent the inclusion of the xz-preboot MM headers */ #define DECOMPR_MM_H #define memmove memmove -#define XZ_EXTERN static /* xz.h needs to be included directly since we need enum xz_mode */ #include "../../../include/linux/xz.h" -#undef XZ_EXTERN - #endif diff --git a/include/linux/xz.h b/include/linux/xz.h index 701d62c02b9a..58ae1d746c6f 100644 --- a/include/linux/xz.h +++ b/include/linux/xz.h @@ -18,11 +18,6 @@ # include #endif -/* In Linux, this is used to make extern functions static when needed. */ -#ifndef XZ_EXTERN -# define XZ_EXTERN extern -#endif - /** * enum xz_mode - Operation mode * @@ -190,7 +185,7 @@ struct xz_dec; * ready to be used with xz_dec_run(). If memory allocation fails, * xz_dec_init() returns NULL. */ -XZ_EXTERN struct xz_dec *xz_dec_init(enum xz_mode mode, uint32_t dict_max); +struct xz_dec *xz_dec_init(enum xz_mode mode, uint32_t dict_max); /** * xz_dec_run() - Run the XZ decoder @@ -210,7 +205,7 @@ XZ_EXTERN struct xz_dec *xz_dec_init(enum xz_mode mode, uint32_t dict_max); * get that amount valid data from the beginning of the stream. You must use * the multi-call decoder if you don't want to uncompress the whole stream. */ -XZ_EXTERN enum xz_ret xz_dec_run(struct xz_dec *s, struct xz_buf *b); +enum xz_ret xz_dec_run(struct xz_dec *s, struct xz_buf *b); /** * xz_dec_reset() - Reset an already allocated decoder state @@ -223,14 +218,14 @@ XZ_EXTERN enum xz_ret xz_dec_run(struct xz_dec *s, struct xz_buf *b); * xz_dec_run(). Thus, explicit call to xz_dec_reset() is useful only in * multi-call mode. */ -XZ_EXTERN void xz_dec_reset(struct xz_dec *s); +void xz_dec_reset(struct xz_dec *s); /** * xz_dec_end() - Free the memory allocated for the decoder state * @s: Decoder state allocated using xz_dec_init(). If s is NULL, * this function does nothing. */ -XZ_EXTERN void xz_dec_end(struct xz_dec *s); +void xz_dec_end(struct xz_dec *s); /** * DOC: MicroLZMA decompressor @@ -244,10 +239,6 @@ XZ_EXTERN void xz_dec_end(struct xz_dec *s); * 3/0/2, the first byte is 0xA2. This way the first byte can never be 0x00. * Just like with LZMA2, lc + lp <= 4 must be true. The LZMA end-of-stream * marker must not be used. The unused values are reserved for future use. - * - * These functions aren't used or available in preboot code and thus aren't - * marked with XZ_EXTERN. This avoids warnings about static functions that - * are never defined. */ /* @@ -272,8 +263,8 @@ struct xz_dec_microlzma; * struct xz_dec_microlzma. If memory allocation fails or * dict_size is invalid, NULL is returned. */ -extern struct xz_dec_microlzma *xz_dec_microlzma_alloc(enum xz_mode mode, - uint32_t dict_size); +struct xz_dec_microlzma *xz_dec_microlzma_alloc(enum xz_mode mode, + uint32_t dict_size); /** * xz_dec_microlzma_reset() - Reset the MicroLZMA decoder state @@ -289,9 +280,8 @@ extern struct xz_dec_microlzma *xz_dec_microlzma_alloc(enum xz_mode mode, * requiring stdbool.h. This should normally be set to true. * When this is set to false, error detection is weaker. */ -extern void xz_dec_microlzma_reset(struct xz_dec_microlzma *s, - uint32_t comp_size, uint32_t uncomp_size, - int uncomp_size_is_exact); +void xz_dec_microlzma_reset(struct xz_dec_microlzma *s, uint32_t comp_size, + uint32_t uncomp_size, int uncomp_size_is_exact); /** * xz_dec_microlzma_run() - Run the MicroLZMA decoder @@ -329,15 +319,14 @@ extern void xz_dec_microlzma_reset(struct xz_dec_microlzma *s, * may be changed normally like with XZ_PREALLOC. This way input data can be * provided from non-contiguous memory. */ -extern enum xz_ret xz_dec_microlzma_run(struct xz_dec_microlzma *s, - struct xz_buf *b); +enum xz_ret xz_dec_microlzma_run(struct xz_dec_microlzma *s, struct xz_buf *b); /** * xz_dec_microlzma_end() - Free the memory allocated for the decoder state * @s: Decoder state allocated using xz_dec_microlzma_alloc(). * If s is NULL, this function does nothing. */ -extern void xz_dec_microlzma_end(struct xz_dec_microlzma *s); +void xz_dec_microlzma_end(struct xz_dec_microlzma *s); /* * Standalone build (userspace build or in-kernel build for boot time use) @@ -358,13 +347,13 @@ extern void xz_dec_microlzma_end(struct xz_dec_microlzma *s); * This must be called before any other xz_* function to initialize * the CRC32 lookup table. */ -XZ_EXTERN void xz_crc32_init(void); +void xz_crc32_init(void); /* * Update CRC32 value using the polynomial from IEEE-802.3. To start a new * calculation, the third argument must be zero. To continue the calculation, * the previously returned value is passed as the third argument. */ -XZ_EXTERN uint32_t xz_crc32(const uint8_t *buf, size_t size, uint32_t crc); +uint32_t xz_crc32(const uint8_t *buf, size_t size, uint32_t crc); #endif #endif diff --git a/lib/decompress_unxz.c b/lib/decompress_unxz.c index cae00395d7a6..32138bb8ef77 100644 --- a/lib/decompress_unxz.c +++ b/lib/decompress_unxz.c @@ -107,7 +107,6 @@ #ifdef __KERNEL__ # include #endif -#define XZ_EXTERN STATIC #ifndef XZ_PREBOOT # include diff --git a/lib/xz/xz_crc32.c b/lib/xz/xz_crc32.c index effdf34ec48d..6a7906a328ba 100644 --- a/lib/xz/xz_crc32.c +++ b/lib/xz/xz_crc32.c @@ -26,7 +26,7 @@ STATIC_RW_DATA uint32_t xz_crc32_table[256]; -XZ_EXTERN void xz_crc32_init(void) +void xz_crc32_init(void) { const uint32_t poly = 0xEDB88320; @@ -45,7 +45,7 @@ XZ_EXTERN void xz_crc32_init(void) return; } -XZ_EXTERN uint32_t xz_crc32(const uint8_t *buf, size_t size, uint32_t crc) +uint32_t xz_crc32(const uint8_t *buf, size_t size, uint32_t crc) { crc = ~crc; diff --git a/lib/xz/xz_dec_bcj.c b/lib/xz/xz_dec_bcj.c index 42d7f268726f..8237db17eee3 100644 --- a/lib/xz/xz_dec_bcj.c +++ b/lib/xz/xz_dec_bcj.c @@ -572,9 +572,8 @@ static void bcj_flush(struct xz_dec_bcj *s, struct xz_buf *b) * data in chunks of 1-16 bytes. To hide this issue, this function does * some buffering. */ -XZ_EXTERN enum xz_ret xz_dec_bcj_run(struct xz_dec_bcj *s, - struct xz_dec_lzma2 *lzma2, - struct xz_buf *b) +enum xz_ret xz_dec_bcj_run(struct xz_dec_bcj *s, struct xz_dec_lzma2 *lzma2, + struct xz_buf *b) { size_t out_start; @@ -682,7 +681,7 @@ XZ_EXTERN enum xz_ret xz_dec_bcj_run(struct xz_dec_bcj *s, return s->ret; } -XZ_EXTERN struct xz_dec_bcj *xz_dec_bcj_create(bool single_call) +struct xz_dec_bcj *xz_dec_bcj_create(bool single_call) { struct xz_dec_bcj *s = kmalloc(sizeof(*s), GFP_KERNEL); if (s != NULL) @@ -691,7 +690,7 @@ XZ_EXTERN struct xz_dec_bcj *xz_dec_bcj_create(bool single_call) return s; } -XZ_EXTERN enum xz_ret xz_dec_bcj_reset(struct xz_dec_bcj *s, uint8_t id) +enum xz_ret xz_dec_bcj_reset(struct xz_dec_bcj *s, uint8_t id) { switch (id) { #ifdef XZ_DEC_X86 diff --git a/lib/xz/xz_dec_lzma2.c b/lib/xz/xz_dec_lzma2.c index 613939f5dd6c..83bb66b6016d 100644 --- a/lib/xz/xz_dec_lzma2.c +++ b/lib/xz/xz_dec_lzma2.c @@ -960,8 +960,7 @@ static bool lzma2_lzma(struct xz_dec_lzma2 *s, struct xz_buf *b) * Take care of the LZMA2 control layer, and forward the job of actual LZMA * decoding or copying of uncompressed chunks to other functions. */ -XZ_EXTERN enum xz_ret xz_dec_lzma2_run(struct xz_dec_lzma2 *s, - struct xz_buf *b) +enum xz_ret xz_dec_lzma2_run(struct xz_dec_lzma2 *s, struct xz_buf *b) { uint32_t tmp; @@ -1137,8 +1136,7 @@ XZ_EXTERN enum xz_ret xz_dec_lzma2_run(struct xz_dec_lzma2 *s, return XZ_OK; } -XZ_EXTERN struct xz_dec_lzma2 *xz_dec_lzma2_create(enum xz_mode mode, - uint32_t dict_max) +struct xz_dec_lzma2 *xz_dec_lzma2_create(enum xz_mode mode, uint32_t dict_max) { struct xz_dec_lzma2 *s = kmalloc(sizeof(*s), GFP_KERNEL); if (s == NULL) @@ -1161,7 +1159,7 @@ XZ_EXTERN struct xz_dec_lzma2 *xz_dec_lzma2_create(enum xz_mode mode, return s; } -XZ_EXTERN enum xz_ret xz_dec_lzma2_reset(struct xz_dec_lzma2 *s, uint8_t props) +enum xz_ret xz_dec_lzma2_reset(struct xz_dec_lzma2 *s, uint8_t props) { /* This limits dictionary size to 3 GiB to keep parsing simpler. */ if (props > 39) @@ -1197,7 +1195,7 @@ XZ_EXTERN enum xz_ret xz_dec_lzma2_reset(struct xz_dec_lzma2 *s, uint8_t props) return XZ_OK; } -XZ_EXTERN void xz_dec_lzma2_end(struct xz_dec_lzma2 *s) +void xz_dec_lzma2_end(struct xz_dec_lzma2 *s) { if (DEC_IS_MULTI(s->dict.mode)) vfree(s->dict.buf); diff --git a/lib/xz/xz_dec_stream.c b/lib/xz/xz_dec_stream.c index 0058406ccd17..f9d003684d56 100644 --- a/lib/xz/xz_dec_stream.c +++ b/lib/xz/xz_dec_stream.c @@ -746,7 +746,7 @@ static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b) * actually succeeds (that's the price to pay of using the output buffer as * the workspace). */ -XZ_EXTERN enum xz_ret xz_dec_run(struct xz_dec *s, struct xz_buf *b) +enum xz_ret xz_dec_run(struct xz_dec *s, struct xz_buf *b) { size_t in_start; size_t out_start; @@ -782,7 +782,7 @@ XZ_EXTERN enum xz_ret xz_dec_run(struct xz_dec *s, struct xz_buf *b) return ret; } -XZ_EXTERN struct xz_dec *xz_dec_init(enum xz_mode mode, uint32_t dict_max) +struct xz_dec *xz_dec_init(enum xz_mode mode, uint32_t dict_max) { struct xz_dec *s = kmalloc(sizeof(*s), GFP_KERNEL); if (s == NULL) @@ -812,7 +812,7 @@ error_bcj: return NULL; } -XZ_EXTERN void xz_dec_reset(struct xz_dec *s) +void xz_dec_reset(struct xz_dec *s) { s->sequence = SEQ_STREAM_HEADER; s->allow_buf_error = false; @@ -824,7 +824,7 @@ XZ_EXTERN void xz_dec_reset(struct xz_dec *s) s->temp.size = STREAM_HEADER_SIZE; } -XZ_EXTERN void xz_dec_end(struct xz_dec *s) +void xz_dec_end(struct xz_dec *s) { if (s != NULL) { xz_dec_lzma2_end(s->lzma2); diff --git a/lib/xz/xz_private.h b/lib/xz/xz_private.h index a8b1cbe8d21d..5f1294a1408c 100644 --- a/lib/xz/xz_private.h +++ b/lib/xz/xz_private.h @@ -115,8 +115,7 @@ * Allocate memory for LZMA2 decoder. xz_dec_lzma2_reset() must be used * before calling xz_dec_lzma2_run(). */ -XZ_EXTERN struct xz_dec_lzma2 *xz_dec_lzma2_create(enum xz_mode mode, - uint32_t dict_max); +struct xz_dec_lzma2 *xz_dec_lzma2_create(enum xz_mode mode, uint32_t dict_max); /* * Decode the LZMA2 properties (one byte) and reset the decoder. Return @@ -124,22 +123,20 @@ XZ_EXTERN struct xz_dec_lzma2 *xz_dec_lzma2_create(enum xz_mode mode, * big enough, and XZ_OPTIONS_ERROR if props indicates something that this * decoder doesn't support. */ -XZ_EXTERN enum xz_ret xz_dec_lzma2_reset(struct xz_dec_lzma2 *s, - uint8_t props); +enum xz_ret xz_dec_lzma2_reset(struct xz_dec_lzma2 *s, uint8_t props); /* Decode raw LZMA2 stream from b->in to b->out. */ -XZ_EXTERN enum xz_ret xz_dec_lzma2_run(struct xz_dec_lzma2 *s, - struct xz_buf *b); +enum xz_ret xz_dec_lzma2_run(struct xz_dec_lzma2 *s, struct xz_buf *b); /* Free the memory allocated for the LZMA2 decoder. */ -XZ_EXTERN void xz_dec_lzma2_end(struct xz_dec_lzma2 *s); +void xz_dec_lzma2_end(struct xz_dec_lzma2 *s); #ifdef XZ_DEC_BCJ /* * Allocate memory for BCJ decoders. xz_dec_bcj_reset() must be used before * calling xz_dec_bcj_run(). */ -XZ_EXTERN struct xz_dec_bcj *xz_dec_bcj_create(bool single_call); +struct xz_dec_bcj *xz_dec_bcj_create(bool single_call); /* * Decode the Filter ID of a BCJ filter. This implementation doesn't @@ -147,16 +144,15 @@ XZ_EXTERN struct xz_dec_bcj *xz_dec_bcj_create(bool single_call); * is needed. Returns XZ_OK if the given Filter ID is supported. * Otherwise XZ_OPTIONS_ERROR is returned. */ -XZ_EXTERN enum xz_ret xz_dec_bcj_reset(struct xz_dec_bcj *s, uint8_t id); +enum xz_ret xz_dec_bcj_reset(struct xz_dec_bcj *s, uint8_t id); /* * Decode raw BCJ + LZMA2 stream. This must be used only if there actually is * a BCJ filter in the chain. If the chain has only LZMA2, xz_dec_lzma2_run() * must be called directly. */ -XZ_EXTERN enum xz_ret xz_dec_bcj_run(struct xz_dec_bcj *s, - struct xz_dec_lzma2 *lzma2, - struct xz_buf *b); +enum xz_ret xz_dec_bcj_run(struct xz_dec_bcj *s, struct xz_dec_lzma2 *lzma2, + struct xz_buf *b); /* Free the memory allocated for the BCJ filters. */ #define xz_dec_bcj_end(s) kfree(s) -- cgit v1.2.3 From 9a42bfd255b288dad2d1a9df0a1fe58394d5da12 Mon Sep 17 00:00:00 2001 From: Deshan Zhang Date: Thu, 25 Jul 2024 17:30:45 +0800 Subject: lib/lru_cache: fix spelling mistake "colision"->"collision" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a spelling mistake in a literal string and in cariable names. Fix these. Link: https://lkml.kernel.org/r/20240725093044.1742842-1-deshan@nfschina.com Signed-off-by: Deshan Zhang Cc: Christoph Böhmwalder Cc: Lars Ellenberg Cc: Philipp Reisner Signed-off-by: Andrew Morton --- include/linux/lru_cache.h | 4 ++-- lib/lru_cache.c | 10 +++++----- 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lru_cache.h b/include/linux/lru_cache.h index c9afcdd9324c..ff82ef85a084 100644 --- a/include/linux/lru_cache.h +++ b/include/linux/lru_cache.h @@ -119,7 +119,7 @@ write intent log information, three of which are mentioned here. */ /* this defines an element in a tracked set - * .colision is for hash table lookup. + * .collision is for hash table lookup. * When we process a new IO request, we know its sector, thus can deduce the * region number (label) easily. To do the label -> object lookup without a * full list walk, we use a simple hash table. @@ -145,7 +145,7 @@ write intent log information, three of which are mentioned here. * But it avoids high order page allocations in kmalloc. */ struct lc_element { - struct hlist_node colision; + struct hlist_node collision; struct list_head list; /* LRU list or free list */ unsigned refcnt; /* back "pointer" into lc_cache->element[index], diff --git a/lib/lru_cache.c b/lib/lru_cache.c index b3d9187611de..9e0d469c7658 100644 --- a/lib/lru_cache.c +++ b/lib/lru_cache.c @@ -243,7 +243,7 @@ static struct lc_element *__lc_find(struct lru_cache *lc, unsigned int enr, BUG_ON(!lc); BUG_ON(!lc->nr_elements); - hlist_for_each_entry(e, lc_hash_slot(lc, enr), colision) { + hlist_for_each_entry(e, lc_hash_slot(lc, enr), collision) { /* "about to be changed" elements, pending transaction commit, * are hashed by their "new number". "Normal" elements have * lc_number == lc_new_number. */ @@ -303,7 +303,7 @@ void lc_del(struct lru_cache *lc, struct lc_element *e) BUG_ON(e->refcnt); e->lc_number = e->lc_new_number = LC_FREE; - hlist_del_init(&e->colision); + hlist_del_init(&e->collision); list_move(&e->list, &lc->free); RETURN(); } @@ -324,9 +324,9 @@ static struct lc_element *lc_prepare_for_change(struct lru_cache *lc, unsigned n PARANOIA_LC_ELEMENT(lc, e); e->lc_new_number = new_number; - if (!hlist_unhashed(&e->colision)) - __hlist_del(&e->colision); - hlist_add_head(&e->colision, lc_hash_slot(lc, new_number)); + if (!hlist_unhashed(&e->collision)) + __hlist_del(&e->collision); + hlist_add_head(&e->collision, lc_hash_slot(lc, new_number)); list_move(&e->list, &lc->to_be_changed); return e; -- cgit v1.2.3 From 6ce2082fd3a25d5a8c756120959237cace0379f1 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Tue, 13 Aug 2024 15:12:35 +0300 Subject: fault-inject: improve build for CONFIG_FAULT_INJECTION=n MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The fault-inject.h users across the kernel need to add a lot of #ifdef CONFIG_FAULT_INJECTION to cater for shortcomings in the header. Make fault-inject.h self-contained for CONFIG_FAULT_INJECTION=n, and add stubs for DECLARE_FAULT_ATTR(), setup_fault_attr(), should_fail_ex(), and should_fail() to allow removal of conditional compilation. [akpm@linux-foundation.org: repair fallout from no longer including debugfs.h into fault-inject.h] [akpm@linux-foundation.org: fix drivers/misc/xilinx_tmr_inject.c] [akpm@linux-foundation.org: Add debugfs.h inclusion to more files, per Stephen] Link: https://lkml.kernel.org/r/20240813121237.2382534-1-jani.nikula@intel.com Fixes: 6ff1cb355e62 ("[PATCH] fault-injection capabilities infrastructure") Signed-off-by: Jani Nikula Cc: Akinobu Mita Cc: Abhinav Kumar Cc: Dmitry Baryshkov Cc: Himal Prasad Ghimiray Cc: Lucas De Marchi Cc: Rob Clark Cc: Rodrigo Vivi Cc: Thomas Hellström Cc: Stephen Rothwell Signed-off-by: Andrew Morton --- drivers/gpu/drm/msm/msm_drv.c | 1 + drivers/iommu/iommufd/selftest.c | 1 + drivers/misc/xilinx_tmr_inject.c | 1 + drivers/nvme/host/fault_inject.c | 1 + drivers/ufs/core/ufs-fault-injection.c | 1 + include/linux/fault-inject.h | 36 +++++++++++++++++++++++++++------- include/linux/mmc/host.h | 1 + include/ufs/ufshcd.h | 1 + kernel/futex/core.c | 1 + lib/fault-inject.c | 1 + mm/fail_page_alloc.c | 1 + mm/failslab.c | 1 + 12 files changed, 40 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 9c33f4e3f822..e018bc79e188 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -7,6 +7,7 @@ #include #include +#include #include #include diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index 222cfc11ebfd..db4032feccee 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/misc/xilinx_tmr_inject.c b/drivers/misc/xilinx_tmr_inject.c index 73c6da7d0963..734fdfac19ef 100644 --- a/drivers/misc/xilinx_tmr_inject.c +++ b/drivers/misc/xilinx_tmr_inject.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include diff --git a/drivers/nvme/host/fault_inject.c b/drivers/nvme/host/fault_inject.c index 1d1b6441a339..105d6cb41c72 100644 --- a/drivers/nvme/host/fault_inject.c +++ b/drivers/nvme/host/fault_inject.c @@ -6,6 +6,7 @@ */ #include +#include #include "nvme.h" static DECLARE_FAULT_ATTR(fail_default_attr); diff --git a/drivers/ufs/core/ufs-fault-injection.c b/drivers/ufs/core/ufs-fault-injection.c index 169540417079..55db38e75cc4 100644 --- a/drivers/ufs/core/ufs-fault-injection.c +++ b/drivers/ufs/core/ufs-fault-injection.c @@ -3,6 +3,7 @@ #include #include #include +#include #include #include #include "ufs-fault-injection.h" diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h index 354413950d34..8c829d28dcf3 100644 --- a/include/linux/fault-inject.h +++ b/include/linux/fault-inject.h @@ -2,13 +2,17 @@ #ifndef _LINUX_FAULT_INJECT_H #define _LINUX_FAULT_INJECT_H +#include +#include + +struct dentry; +struct kmem_cache; + #ifdef CONFIG_FAULT_INJECTION -#include -#include +#include #include #include -#include /* * For explanation of the elements of this struct, see @@ -51,6 +55,28 @@ int setup_fault_attr(struct fault_attr *attr, char *str); bool should_fail_ex(struct fault_attr *attr, ssize_t size, int flags); bool should_fail(struct fault_attr *attr, ssize_t size); +#else /* CONFIG_FAULT_INJECTION */ + +struct fault_attr { +}; + +#define DECLARE_FAULT_ATTR(name) struct fault_attr name = {} + +static inline int setup_fault_attr(struct fault_attr *attr, char *str) +{ + return 0; /* Note: 0 means error for __setup() handlers! */ +} +static inline bool should_fail_ex(struct fault_attr *attr, ssize_t size, int flags) +{ + return false; +} +static inline bool should_fail(struct fault_attr *attr, ssize_t size) +{ + return false; +} + +#endif /* CONFIG_FAULT_INJECTION */ + #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS struct dentry *fault_create_debugfs_attr(const char *name, @@ -87,10 +113,6 @@ static inline void fault_config_init(struct fault_config *config, #endif /* CONFIG_FAULT_INJECTION_CONFIGFS */ -#endif /* CONFIG_FAULT_INJECTION */ - -struct kmem_cache; - #ifdef CONFIG_FAIL_PAGE_ALLOC bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order); #else diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 88c6a76042ee..49470188fca7 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -10,6 +10,7 @@ #include #include #include +#include #include #include diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h index 0fd2aebac728..3f68ae3e4330 100644 --- a/include/ufs/ufshcd.h +++ b/include/ufs/ufshcd.h @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include diff --git a/kernel/futex/core.c b/kernel/futex/core.c index 06a1f091be81..136768ae2637 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -34,6 +34,7 @@ #include #include #include +#include #include #include #include diff --git a/lib/fault-inject.c b/lib/fault-inject.c index d608f9b48c10..52eb6ba29698 100644 --- a/lib/fault-inject.c +++ b/lib/fault-inject.c @@ -2,6 +2,7 @@ #include #include #include +#include #include #include #include diff --git a/mm/fail_page_alloc.c b/mm/fail_page_alloc.c index 532851ce5132..7647096170e9 100644 --- a/mm/fail_page_alloc.c +++ b/mm/fail_page_alloc.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include +#include #include #include diff --git a/mm/failslab.c b/mm/failslab.c index af16c2ed578f..c3901b136498 100644 --- a/mm/failslab.c +++ b/mm/failslab.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include #include +#include #include #include #include "slab.h" -- cgit v1.2.3 From d994c238347d7ba4de15da00985e1bea75e91dc7 Mon Sep 17 00:00:00 2001 From: Mateusz Guzik Date: Sat, 17 Aug 2024 14:37:54 +0200 Subject: ratelimit: convert flags to int to save 8 bytes in size Only bit 1 is used, making an unsigned long a total overkill. This brings it from 40 to 32 bytes, which in turn shrinks user_struct from 136 to 128 bytes. Since the latter is allocated with hwalign, this means the total usage goes down from 192 to 128 bytes per object. No functional changes. Link: https://lkml.kernel.org/r/20240817123754.240924-1-mjguzik@gmail.com Signed-off-by: Mateusz Guzik Signed-off-by: Andrew Morton --- include/linux/ratelimit_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ratelimit_types.h b/include/linux/ratelimit_types.h index 002266693e50..765232ce0b5e 100644 --- a/include/linux/ratelimit_types.h +++ b/include/linux/ratelimit_types.h @@ -19,8 +19,8 @@ struct ratelimit_state { int burst; int printed; int missed; + unsigned int flags; unsigned long begin; - unsigned long flags; }; #define RATELIMIT_STATE_INIT_FLAGS(name, interval_init, burst_init, flags_init) { \ -- cgit v1.2.3 From 32cebfe1cc21a84e4a907575bb9fd1c3f6b091fd Mon Sep 17 00:00:00 2001 From: Hongbo Li Date: Tue, 27 Aug 2024 10:45:15 +0800 Subject: lib/string_choices: add str_true_false()/str_false_true() helper Add str_true_false()/str_false_true() helper to retur a "true" or "false" string literal. We found more than 10 cases currently exist in the tree. So these helpers can be used for these cases. This patch (of 3): Add str_true_false()/str_false_true() helper to return "true" or "false" string literal. Link: https://lkml.kernel.org/r/20240827024517.914100-1-lihongbo22@huawei.com Link: https://lkml.kernel.org/r/20240827024517.914100-2-lihongbo22@huawei.com Signed-off-by: Hongbo Li Cc: Andy Shevchenko Cc: Anna Schumaker Cc: Greg Kroah-Hartman Cc: Kees Cook Cc: Matthew Wilcox Cc: Trond Myklebust Signed-off-by: Andrew Morton --- include/linux/string_choices.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/string_choices.h b/include/linux/string_choices.h index d9ebe20229f8..4a2432313b8e 100644 --- a/include/linux/string_choices.h +++ b/include/linux/string_choices.h @@ -42,6 +42,12 @@ static inline const char *str_yes_no(bool v) return v ? "yes" : "no"; } +static inline const char *str_true_false(bool v) +{ + return v ? "true" : "false"; +} +#define str_false_true(v) str_true_false(!(v)) + /** * str_plural - Return the simple pluralization based on English counts * @num: Number used for deciding pluralization -- cgit v1.2.3 From c4a315eaf8eff0d3234600e13db7e7c71c0b3405 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Wed, 21 Aug 2024 14:14:56 +0200 Subject: gpio: ath79: remove support for platform data There are no more board files defining platform data for this driver so remove the header and support from the driver. Reviewed-by: Linus Walleij Link: https://lore.kernel.org/r/20240821121456.19553-4-brgl@bgdev.pl Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-ath79.c | 22 ++++++---------------- include/linux/platform_data/gpio-ath79.h | 16 ---------------- 2 files changed, 6 insertions(+), 32 deletions(-) delete mode 100644 include/linux/platform_data/gpio-ath79.h (limited to 'include/linux') diff --git a/drivers/gpio/gpio-ath79.c b/drivers/gpio/gpio-ath79.c index 211faffbef32..de4cc12e5e03 100644 --- a/drivers/gpio/gpio-ath79.c +++ b/drivers/gpio/gpio-ath79.c @@ -14,7 +14,6 @@ #include #include #include -#include #include #define AR71XX_GPIO_REG_OE 0x00 @@ -225,9 +224,7 @@ MODULE_DEVICE_TABLE(of, ath79_gpio_of_match); static int ath79_gpio_probe(struct platform_device *pdev) { - struct ath79_gpio_platform_data *pdata = dev_get_platdata(&pdev->dev); struct device *dev = &pdev->dev; - struct device_node *np = dev->of_node; struct ath79_gpio_ctrl *ctrl; struct gpio_irq_chip *girq; u32 ath79_gpio_count; @@ -238,21 +235,14 @@ static int ath79_gpio_probe(struct platform_device *pdev) if (!ctrl) return -ENOMEM; - if (np) { - err = device_property_read_u32(dev, "ngpios", &ath79_gpio_count); - if (err) { - dev_err(dev, "ngpios property is not valid\n"); - return err; - } - oe_inverted = device_is_compatible(dev, "qca,ar9340-gpio"); - } else if (pdata) { - ath79_gpio_count = pdata->ngpios; - oe_inverted = pdata->oe_inverted; - } else { - dev_err(dev, "No DT node or platform data found\n"); - return -EINVAL; + err = device_property_read_u32(dev, "ngpios", &ath79_gpio_count); + if (err) { + dev_err(dev, "ngpios property is not valid\n"); + return err; } + oe_inverted = device_is_compatible(dev, "qca,ar9340-gpio"); + if (ath79_gpio_count >= 32) { dev_err(dev, "ngpios must be less than 32\n"); return -EINVAL; diff --git a/include/linux/platform_data/gpio-ath79.h b/include/linux/platform_data/gpio-ath79.h deleted file mode 100644 index 3ea6dd942c27..000000000000 --- a/include/linux/platform_data/gpio-ath79.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Atheros AR7XXX/AR9XXX GPIO controller platform data - * - * Copyright (C) 2015 Alban Bedel - */ - -#ifndef __LINUX_PLATFORM_DATA_GPIO_ATH79_H -#define __LINUX_PLATFORM_DATA_GPIO_ATH79_H - -struct ath79_gpio_platform_data { - unsigned ngpios; - bool oe_inverted; -}; - -#endif -- cgit v1.2.3 From 4b2b0a2ce8153d65d0829e45e73bf6acdc291344 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 28 Aug 2024 17:23:57 +0300 Subject: gpiolib: legacy: Kill GPIOF_INIT_* definitions Besides the fact that (old) drivers use wrong definitions, e.g., GPIOF_INIT_HIGH instead of GPIOF_OUT_INIT_HIGH, shrink the legacy definitions by killing those GPIOF_INIT_* completely. Signed-off-by: Andy Shevchenko Reviewed-by: Linus Walleij Acked-by: Alexander Sverdlin Reviewed-by: Alexander Sverdlin Link: https://lore.kernel.org/r/20240828142554.2424189-2-andriy.shevchenko@linux.intel.com Signed-off-by: Bartosz Golaszewski --- arch/arm/mach-ep93xx/vision_ep9307.c | 3 +-- arch/mips/bcm63xx/boards/board_bcm963xx.c | 2 +- drivers/gpio/gpiolib-legacy.c | 3 +-- include/linux/gpio.h | 7 ++----- 4 files changed, 5 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/mach-ep93xx/vision_ep9307.c b/arch/arm/mach-ep93xx/vision_ep9307.c index 9471938df64c..02c5a4724192 100644 --- a/arch/arm/mach-ep93xx/vision_ep9307.c +++ b/arch/arm/mach-ep93xx/vision_ep9307.c @@ -76,8 +76,7 @@ static int vision_lcd_setup(struct platform_device *pdev) { int err; - err = gpio_request_one(VISION_LCD_ENABLE, GPIOF_INIT_HIGH, - dev_name(&pdev->dev)); + err = gpio_request_one(VISION_LCD_ENABLE, GPIOF_OUT_INIT_HIGH, dev_name(&pdev->dev)); if (err) return err; diff --git a/arch/mips/bcm63xx/boards/board_bcm963xx.c b/arch/mips/bcm63xx/boards/board_bcm963xx.c index 99f321b6e417..9cc8fbf218a5 100644 --- a/arch/mips/bcm63xx/boards/board_bcm963xx.c +++ b/arch/mips/bcm63xx/boards/board_bcm963xx.c @@ -42,7 +42,7 @@ static struct board_info __initdata board_cvg834g = { .expected_cpu_id = 0x3368, .ephy_reset_gpio = 36, - .ephy_reset_gpio_flags = GPIOF_INIT_HIGH, + .ephy_reset_gpio_flags = GPIOF_OUT_INIT_HIGH, .has_pci = 1, .has_uart0 = 1, .has_uart1 = 1, diff --git a/drivers/gpio/gpiolib-legacy.c b/drivers/gpio/gpiolib-legacy.c index 5a9911ae9125..354dd0cc8f2f 100644 --- a/drivers/gpio/gpiolib-legacy.c +++ b/drivers/gpio/gpiolib-legacy.c @@ -43,8 +43,7 @@ int gpio_request_one(unsigned gpio, unsigned long flags, const char *label) if (flags & GPIOF_DIR_IN) err = gpiod_direction_input(desc); else - err = gpiod_direction_output_raw(desc, - (flags & GPIOF_INIT_HIGH) ? 1 : 0); + err = gpiod_direction_output_raw(desc, !!(flags & GPIOF_OUT_INIT_HIGH)); if (err) goto free_gpio; diff --git a/include/linux/gpio.h b/include/linux/gpio.h index 063f71b18a7c..4af8ad114557 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -20,12 +20,9 @@ struct device; #define GPIOF_DIR_OUT (0 << 0) #define GPIOF_DIR_IN (1 << 0) -#define GPIOF_INIT_LOW (0 << 1) -#define GPIOF_INIT_HIGH (1 << 1) - #define GPIOF_IN (GPIOF_DIR_IN) -#define GPIOF_OUT_INIT_LOW (GPIOF_DIR_OUT | GPIOF_INIT_LOW) -#define GPIOF_OUT_INIT_HIGH (GPIOF_DIR_OUT | GPIOF_INIT_HIGH) +#define GPIOF_OUT_INIT_LOW (GPIOF_DIR_OUT | (0 << 1)) +#define GPIOF_OUT_INIT_HIGH (GPIOF_DIR_OUT | (1 << 1)) /* Gpio pin is active-low */ #define GPIOF_ACTIVE_LOW (1 << 2) -- cgit v1.2.3 From 8c045ca534d03bab1ce4b4de49d29a36276a1e35 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 28 Aug 2024 17:23:58 +0300 Subject: gpiolib: legacy: Kill GPIOF_DIR_* definitions Besides the fact that (old) drivers use wrong definitions, e.g., GPIOF_DIR_IN instead of GPIOF_IN, shrink the legacy definitions by killing those GPIOF_DIR_* completely. Signed-off-by: Andy Shevchenko Reviewed-by: Linus Walleij Acked-by: Alexander Sverdlin Reviewed-by: Alexander Sverdlin Link: https://lore.kernel.org/r/20240828142554.2424189-3-andriy.shevchenko@linux.intel.com Signed-off-by: Bartosz Golaszewski --- arch/arm/mach-ep93xx/vision_ep9307.c | 3 +-- drivers/gpio/gpiolib-legacy.c | 2 +- include/linux/gpio.h | 9 +++------ 3 files changed, 5 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/mach-ep93xx/vision_ep9307.c b/arch/arm/mach-ep93xx/vision_ep9307.c index 02c5a4724192..85f0dd7255a9 100644 --- a/arch/arm/mach-ep93xx/vision_ep9307.c +++ b/arch/arm/mach-ep93xx/vision_ep9307.c @@ -292,8 +292,7 @@ static void __init vision_init_machine(void) * Request the gpio expander's interrupt gpio line now to prevent * the kernel from doing a WARN in gpiolib:gpio_ensure_requested(). */ - if (gpio_request_one(EP93XX_GPIO_LINE_F(7), GPIOF_DIR_IN, - "pca9539:74")) + if (gpio_request_one(EP93XX_GPIO_LINE_F(7), GPIOF_IN, "pca9539:74")) pr_warn("cannot request interrupt gpio for pca9539:74\n"); vision_i2c_info[1].irq = gpio_to_irq(EP93XX_GPIO_LINE_F(7)); diff --git a/drivers/gpio/gpiolib-legacy.c b/drivers/gpio/gpiolib-legacy.c index 354dd0cc8f2f..f421208ddbdd 100644 --- a/drivers/gpio/gpiolib-legacy.c +++ b/drivers/gpio/gpiolib-legacy.c @@ -40,7 +40,7 @@ int gpio_request_one(unsigned gpio, unsigned long flags, const char *label) if (flags & GPIOF_ACTIVE_LOW) set_bit(FLAG_ACTIVE_LOW, &desc->flags); - if (flags & GPIOF_DIR_IN) + if (flags & GPIOF_IN) err = gpiod_direction_input(desc); else err = gpiod_direction_output_raw(desc, !!(flags & GPIOF_OUT_INIT_HIGH)); diff --git a/include/linux/gpio.h b/include/linux/gpio.h index 4af8ad114557..2d105be7bbc3 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -17,12 +17,9 @@ struct device; /* make these flag values available regardless of GPIO kconfig options */ -#define GPIOF_DIR_OUT (0 << 0) -#define GPIOF_DIR_IN (1 << 0) - -#define GPIOF_IN (GPIOF_DIR_IN) -#define GPIOF_OUT_INIT_LOW (GPIOF_DIR_OUT | (0 << 1)) -#define GPIOF_OUT_INIT_HIGH (GPIOF_DIR_OUT | (1 << 1)) +#define GPIOF_IN ((1 << 0)) +#define GPIOF_OUT_INIT_LOW ((0 << 0) | (0 << 1)) +#define GPIOF_OUT_INIT_HIGH ((0 << 0) | (1 << 1)) /* Gpio pin is active-low */ #define GPIOF_ACTIVE_LOW (1 << 2) -- cgit v1.2.3 From e220917fa50774fedb27c075df2261fd664e8ca3 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Thu, 22 Aug 2024 15:50:12 +0200 Subject: mm: split a folio in minimum folio order chunks split_folio() and split_folio_to_list() assume order 0, to support minorder for non-anonymous folios, we must expand these to check the folio mapping order and use that. Set new_order to be at least minimum folio order if it is set in split_huge_page_to_list() so that we can maintain minimum folio order requirement in the page cache. Update the debugfs write files used for testing to ensure the order is respected as well. We simply enforce the min order when a file mapping is used. Signed-off-by: Luis Chamberlain Signed-off-by: Pankaj Raghav Link: https://lore.kernel.org/r/20240902124931.506061-2-kernel@pankajraghav.com # folded fix Link: https://lore.kernel.org/r/20240822135018.1931258-5-kernel@pankajraghav.com Tested-by: David Howells Reviewed-by: Hannes Reinecke Reviewed-by: Zi Yan Signed-off-by: Christian Brauner --- include/linux/huge_mm.h | 28 ++++++++++++++++++--- mm/huge_memory.c | 65 ++++++++++++++++++++++++++++++++++++++++++++++--- 2 files changed, 85 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index e25d9ebfdf89..7a570e0437c9 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -96,6 +96,8 @@ extern struct kobj_attribute thpsize_shmem_enabled_attr; #define thp_vma_allowable_order(vma, vm_flags, tva_flags, order) \ (!!thp_vma_allowable_orders(vma, vm_flags, tva_flags, BIT(order))) +#define split_folio(f) split_folio_to_list(f, NULL) + #ifdef CONFIG_PGTABLE_HAS_HUGE_LEAVES #define HPAGE_PMD_SHIFT PMD_SHIFT #define HPAGE_PUD_SHIFT PUD_SHIFT @@ -317,9 +319,24 @@ unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long add bool can_split_folio(struct folio *folio, int *pextra_pins); int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, unsigned int new_order); +int min_order_for_split(struct folio *folio); +int split_folio_to_list(struct folio *folio, struct list_head *list); static inline int split_huge_page(struct page *page) { - return split_huge_page_to_list_to_order(page, NULL, 0); + struct folio *folio = page_folio(page); + int ret = min_order_for_split(folio); + + if (ret < 0) + return ret; + + /* + * split_huge_page() locks the page before splitting and + * expects the same page that has been split to be locked when + * returned. split_folio(page_folio(page)) cannot be used here + * because it converts the page to folio and passes the head + * page to be split. + */ + return split_huge_page_to_list_to_order(page, NULL, ret); } void deferred_split_folio(struct folio *folio); @@ -484,6 +501,12 @@ static inline int split_huge_page(struct page *page) { return 0; } + +static inline int split_folio_to_list(struct folio *folio, struct list_head *list) +{ + return 0; +} + static inline void deferred_split_folio(struct folio *folio) {} #define split_huge_pmd(__vma, __pmd, __address) \ do { } while (0) @@ -598,7 +621,4 @@ static inline int split_folio_to_order(struct folio *folio, int new_order) return split_folio_to_list_to_order(folio, NULL, new_order); } -#define split_folio_to_list(f, l) split_folio_to_list_to_order(f, l, 0) -#define split_folio(f) split_folio_to_order(f, 0) - #endif /* _LINUX_HUGE_MM_H */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index f4be468e06a4..9931ff1d9a9d 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3082,6 +3082,9 @@ bool can_split_folio(struct folio *folio, int *pextra_pins) * released, or if some unexpected race happened (e.g., anon VMA disappeared, * truncation). * + * Callers should ensure that the order respects the address space mapping + * min-order if one is set for non-anonymous folios. + * * Returns -EINVAL when trying to split to an order that is incompatible * with the folio. Splitting to order 0 is compatible with all folios. */ @@ -3163,6 +3166,7 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, mapping = NULL; anon_vma_lock_write(anon_vma); } else { + unsigned int min_order; gfp_t gfp; mapping = folio->mapping; @@ -3173,6 +3177,14 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, goto out; } + min_order = mapping_min_folio_order(folio->mapping); + if (new_order < min_order) { + VM_WARN_ONCE(1, "Cannot split mapped folio below min-order: %u", + min_order); + ret = -EINVAL; + goto out; + } + gfp = current_gfp_context(mapping_gfp_mask(mapping) & GFP_RECLAIM_MASK); @@ -3285,6 +3297,30 @@ out: return ret; } +int min_order_for_split(struct folio *folio) +{ + if (folio_test_anon(folio)) + return 0; + + if (!folio->mapping) { + if (folio_test_pmd_mappable(folio)) + count_vm_event(THP_SPLIT_PAGE_FAILED); + return -EBUSY; + } + + return mapping_min_folio_order(folio->mapping); +} + +int split_folio_to_list(struct folio *folio, struct list_head *list) +{ + int ret = min_order_for_split(folio); + + if (ret < 0) + return ret; + + return split_huge_page_to_list_to_order(&folio->page, list, ret); +} + void __folio_undo_large_rmappable(struct folio *folio) { struct deferred_split *ds_queue; @@ -3515,6 +3551,8 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start, struct vm_area_struct *vma = vma_lookup(mm, addr); struct page *page; struct folio *folio; + struct address_space *mapping; + unsigned int target_order = new_order; if (!vma) break; @@ -3535,7 +3573,13 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start, if (!is_transparent_hugepage(folio)) goto next; - if (new_order >= folio_order(folio)) + if (!folio_test_anon(folio)) { + mapping = folio->mapping; + target_order = max(new_order, + mapping_min_folio_order(mapping)); + } + + if (target_order >= folio_order(folio)) goto next; total++; @@ -3551,9 +3595,14 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start, if (!folio_trylock(folio)) goto next; - if (!split_folio_to_order(folio, new_order)) + if (!folio_test_anon(folio) && folio->mapping != mapping) + goto unlock; + + if (!split_folio_to_order(folio, target_order)) split++; +unlock: + folio_unlock(folio); next: folio_put(folio); @@ -3578,6 +3627,8 @@ static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start, pgoff_t index; int nr_pages = 1; unsigned long total = 0, split = 0; + unsigned int min_order; + unsigned int target_order; file = getname_kernel(file_path); if (IS_ERR(file)) @@ -3591,6 +3642,8 @@ static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start, file_path, off_start, off_end); mapping = candidate->f_mapping; + min_order = mapping_min_folio_order(mapping); + target_order = max(new_order, min_order); for (index = off_start; index < off_end; index += nr_pages) { struct folio *folio = filemap_get_folio(mapping, index); @@ -3605,15 +3658,19 @@ static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start, total++; nr_pages = folio_nr_pages(folio); - if (new_order >= folio_order(folio)) + if (target_order >= folio_order(folio)) goto next; if (!folio_trylock(folio)) goto next; - if (!split_folio_to_order(folio, new_order)) + if (folio->mapping != mapping) + goto unlock; + + if (!split_folio_to_order(folio, target_order)) split++; +unlock: folio_unlock(folio); next: folio_put(folio); -- cgit v1.2.3 From f46a6e16519712651e2304da03ec144cc0bb084c Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Fri, 30 Aug 2024 18:26:28 +0300 Subject: usb: Add tunnel_mode parameter to usb device structure Add 'tunnel_mode' enum to usb device structure to describe if a USB3 link is tunneled over USB4, or connected directly using native USB2/USB3 protocols. Tunneled devices depend on USB4 NHI host to maintain the tunnel. Knowledge about tunneled devices is important to ensure correct suspend and resume order between USB4 hosts and tunneled devices. i.e. make sure tunnel is up before the USB device using it resumes. USB hosts such as xHCI may have vendor specific ways to detect tunneled connections. This 'tunnel_mode' parameter can be set by USB3 host driver during hcd->driver->update_device(hcd, udev) callback. tunnel_mode can be set to: USB_LINK_UNKNOWN = 0 USB_LINK_NATIVE USB_LINK_TUNNELED USB_LINK_UNKNOWN is used in case host is not capable of detecting tunneled links. Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20240830152630.3943215-3-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-hub.c | 13 +++++++++---- drivers/usb/host/xhci.c | 7 +++++-- drivers/usb/host/xhci.h | 4 ++-- include/linux/usb.h | 8 ++++++++ 4 files changed, 24 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index 4ba910eadd3f..d27c30ac17fd 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -763,9 +763,12 @@ static int xhci_exit_test_mode(struct xhci_hcd *xhci) * * A USB3 device must be connected to the port to detect the tunnel. * - * Return: true if USB3 connection is tunneled over USB4 + * Return: link tunnel mode enum, USB_LINK_UNKNOWN if host is incapable of + * detecting USB3 over USB4 tunnels. USB_LINK_NATIVE or USB_LINK_TUNNELED + * otherwise. */ -bool xhci_port_is_tunneled(struct xhci_hcd *xhci, struct xhci_port *port) +enum usb_link_tunnel_mode xhci_port_is_tunneled(struct xhci_hcd *xhci, + struct xhci_port *port) { void __iomem *base; u32 offset; @@ -777,10 +780,12 @@ bool xhci_port_is_tunneled(struct xhci_hcd *xhci, struct xhci_port *port) offset = XHCI_INTEL_SPR_ESS_PORT_OFFSET + port->hcd_portnum * 0x20; if (readl(base + offset) & XHCI_INTEL_SPR_TUNEN) - return true; + return USB_LINK_TUNNELED; + else + return USB_LINK_NATIVE; } - return false; + return USB_LINK_UNKNOWN; } void xhci_set_link_state(struct xhci_hcd *xhci, struct xhci_port *port, diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 1ea2c91106b7..a69245074395 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -4529,9 +4529,12 @@ static int xhci_update_device(struct usb_hcd *hcd, struct usb_device *udev) if (hcd->speed >= HCD_USB3 && !udev->parent->parent) { port = xhci->usb3_rhub.ports[udev->portnum - 1]; - if (xhci_port_is_tunneled(xhci, port)) + udev->tunnel_mode = xhci_port_is_tunneled(xhci, port); + if (udev->tunnel_mode == USB_LINK_UNKNOWN) + dev_dbg(&udev->dev, "link tunnel state unknown\n"); + else if (udev->tunnel_mode == USB_LINK_TUNNELED) dev_dbg(&udev->dev, "tunneled over USB4 link\n"); - else + else if (udev->tunnel_mode == USB_LINK_NATIVE) dev_dbg(&udev->dev, "native USB 3.x link\n"); return 0; } diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index e87a6b2f139d..40aebdfb37c9 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1929,8 +1929,8 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, u16 wIndex, int xhci_hub_status_data(struct usb_hcd *hcd, char *buf); int xhci_find_raw_port_number(struct usb_hcd *hcd, int port1); struct xhci_hub *xhci_get_rhub(struct usb_hcd *hcd); -bool xhci_port_is_tunneled(struct xhci_hcd *xhci, struct xhci_port *port); - +enum usb_link_tunnel_mode xhci_port_is_tunneled(struct xhci_hcd *xhci, + struct xhci_port *port); void xhci_hc_died(struct xhci_hcd *xhci); #ifdef CONFIG_PM diff --git a/include/linux/usb.h b/include/linux/usb.h index 832997a9da0a..672d8fc2abdb 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -495,6 +495,12 @@ struct usb_dev_state; struct usb_tt; +enum usb_link_tunnel_mode { + USB_LINK_UNKNOWN = 0, + USB_LINK_NATIVE, + USB_LINK_TUNNELED, +}; + enum usb_port_connect_type { USB_PORT_CONNECT_TYPE_UNKNOWN = 0, USB_PORT_CONNECT_TYPE_HOT_PLUG, @@ -605,6 +611,7 @@ struct usb3_lpm_parameters { * WUSB devices are not, until we authorize them from user space. * FIXME -- complete doc * @authenticated: Crypto authentication passed + * @tunnel_mode: Connection native or tunneled over USB4 * @lpm_capable: device supports LPM * @lpm_devinit_allow: Allow USB3 device initiated LPM, exit latency is in range * @usb2_hw_lpm_capable: device can perform USB2 hardware LPM @@ -714,6 +721,7 @@ struct usb_device { unsigned do_remote_wakeup:1; unsigned reset_resume:1; unsigned port_is_suspended:1; + enum usb_link_tunnel_mode tunnel_mode; int slot_id; struct usb2_lpm_parameters l1_params; -- cgit v1.2.3 From d9c61bb33fbbcbc2d5f69efa10db116dab4b56cc Mon Sep 17 00:00:00 2001 From: Michael Grzeschik Date: Sun, 1 Sep 2024 21:11:16 +0200 Subject: usb: gadget: function: move u_f.h to include/linux/usb/func_utils.h We move the func_utils.h header to include/linux/usb to be able to compile function drivers outside of the drivers/usb/gadget/function directory. Signed-off-by: Michael Grzeschik Link: https://lore.kernel.org/r/20240116-ml-topic-u9p-v12-1-9a27de5160e0@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/configfs.c | 2 +- drivers/usb/gadget/function/f_fs.c | 2 +- drivers/usb/gadget/function/f_hid.c | 2 +- drivers/usb/gadget/function/f_loopback.c | 2 +- drivers/usb/gadget/function/f_midi.c | 2 +- drivers/usb/gadget/function/f_midi2.c | 2 +- drivers/usb/gadget/function/f_sourcesink.c | 2 +- drivers/usb/gadget/u_f.c | 2 +- drivers/usb/gadget/u_f.h | 86 ------------------------------ include/linux/usb/func_utils.h | 86 ++++++++++++++++++++++++++++++ 10 files changed, 94 insertions(+), 94 deletions(-) delete mode 100644 drivers/usb/gadget/u_f.h create mode 100644 include/linux/usb/func_utils.h (limited to 'include/linux') diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index 5cba3e8d626c..c82a6a0fba93 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -6,10 +6,10 @@ #include #include #include +#include #include #include #include "configfs.h" -#include "u_f.h" #include "u_os_desc.h" static int check_user_usb_string(const char *name, diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index e35177fc6c55..05b52e61a66f 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include @@ -40,7 +41,6 @@ #include #include "u_fs.h" -#include "u_f.h" #include "u_os_desc.h" #include "configfs.h" diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c index 82c7dff6de5c..740311c4fa24 100644 --- a/drivers/usb/gadget/function/f_hid.c +++ b/drivers/usb/gadget/function/f_hid.c @@ -16,10 +16,10 @@ #include #include #include +#include #include #include -#include "u_f.h" #include "u_hid.h" #define HIDG_MINORS 4 diff --git a/drivers/usb/gadget/function/f_loopback.c b/drivers/usb/gadget/function/f_loopback.c index 979b028edb99..49b009a7d5d7 100644 --- a/drivers/usb/gadget/function/f_loopback.c +++ b/drivers/usb/gadget/function/f_loopback.c @@ -14,9 +14,9 @@ #include #include #include +#include #include "g_zero.h" -#include "u_f.h" /* * LOOPBACK FUNCTION ... a testing vehicle for USB peripherals, diff --git a/drivers/usb/gadget/function/f_midi.c b/drivers/usb/gadget/function/f_midi.c index 67052a664e74..1067847cc079 100644 --- a/drivers/usb/gadget/function/f_midi.c +++ b/drivers/usb/gadget/function/f_midi.c @@ -30,11 +30,11 @@ #include #include +#include #include #include #include -#include "u_f.h" #include "u_midi.h" MODULE_AUTHOR("Ben Williamson"); diff --git a/drivers/usb/gadget/function/f_midi2.c b/drivers/usb/gadget/function/f_midi2.c index 3f63253ad3e0..8285df9ed6fd 100644 --- a/drivers/usb/gadget/function/f_midi2.c +++ b/drivers/usb/gadget/function/f_midi2.c @@ -15,11 +15,11 @@ #include #include +#include #include #include #include -#include "u_f.h" #include "u_midi2.h" struct f_midi2; diff --git a/drivers/usb/gadget/function/f_sourcesink.c b/drivers/usb/gadget/function/f_sourcesink.c index 6f3702210450..ec5fd25020fd 100644 --- a/drivers/usb/gadget/function/f_sourcesink.c +++ b/drivers/usb/gadget/function/f_sourcesink.c @@ -13,10 +13,10 @@ #include #include #include +#include #include #include "g_zero.h" -#include "u_f.h" /* * SOURCE/SINK FUNCTION ... a primary testing vehicle for USB peripheral diff --git a/drivers/usb/gadget/u_f.c b/drivers/usb/gadget/u_f.c index 6aea1ecb3999..115d219c9c00 100644 --- a/drivers/usb/gadget/u_f.c +++ b/drivers/usb/gadget/u_f.c @@ -8,8 +8,8 @@ * Author: Andrzej Pietrasiewicz */ -#include "u_f.h" #include +#include struct usb_request *alloc_ep_req(struct usb_ep *ep, size_t len) { diff --git a/drivers/usb/gadget/u_f.h b/drivers/usb/gadget/u_f.h deleted file mode 100644 index e313c3b8dcb1..000000000000 --- a/drivers/usb/gadget/u_f.h +++ /dev/null @@ -1,86 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * u_f.h - * - * Utility definitions for USB functions - * - * Copyright (c) 2013 Samsung Electronics Co., Ltd. - * http://www.samsung.com - * - * Author: Andrzej Pietrasiewicz - */ - -#ifndef __U_F_H__ -#define __U_F_H__ - -#include -#include - -/* Variable Length Array Macros **********************************************/ -#define vla_group(groupname) size_t groupname##__next = 0 -#define vla_group_size(groupname) groupname##__next - -#define vla_item(groupname, type, name, n) \ - size_t groupname##_##name##__offset = ({ \ - size_t offset = 0; \ - if (groupname##__next != SIZE_MAX) { \ - size_t align_mask = __alignof__(type) - 1; \ - size_t size = array_size(n, sizeof(type)); \ - offset = (groupname##__next + align_mask) & \ - ~align_mask; \ - if (check_add_overflow(offset, size, \ - &groupname##__next)) { \ - groupname##__next = SIZE_MAX; \ - offset = 0; \ - } \ - } \ - offset; \ - }) - -#define vla_item_with_sz(groupname, type, name, n) \ - size_t groupname##_##name##__sz = array_size(n, sizeof(type)); \ - size_t groupname##_##name##__offset = ({ \ - size_t offset = 0; \ - if (groupname##__next != SIZE_MAX) { \ - size_t align_mask = __alignof__(type) - 1; \ - offset = (groupname##__next + align_mask) & \ - ~align_mask; \ - if (check_add_overflow(offset, groupname##_##name##__sz,\ - &groupname##__next)) { \ - groupname##__next = SIZE_MAX; \ - offset = 0; \ - } \ - } \ - offset; \ - }) - -#define vla_ptr(ptr, groupname, name) \ - ((void *) ((char *)ptr + groupname##_##name##__offset)) - -struct usb_ep; -struct usb_request; - -/** - * alloc_ep_req - returns a usb_request allocated by the gadget driver and - * allocates the request's buffer. - * - * @ep: the endpoint to allocate a usb_request - * @len: usb_requests's buffer suggested size - * - * In case @ep direction is OUT, the @len will be aligned to ep's - * wMaxPacketSize. In order to avoid memory leaks or drops, *always* use - * usb_requests's length (req->length) to refer to the allocated buffer size. - * Requests allocated via alloc_ep_req() *must* be freed by free_ep_req(). - */ -struct usb_request *alloc_ep_req(struct usb_ep *ep, size_t len); - -/* Frees a usb_request previously allocated by alloc_ep_req() */ -static inline void free_ep_req(struct usb_ep *ep, struct usb_request *req) -{ - WARN_ON(req->buf == NULL); - kfree(req->buf); - req->buf = NULL; - usb_ep_free_request(ep, req); -} - -#endif /* __U_F_H__ */ diff --git a/include/linux/usb/func_utils.h b/include/linux/usb/func_utils.h new file mode 100644 index 000000000000..c8795c965109 --- /dev/null +++ b/include/linux/usb/func_utils.h @@ -0,0 +1,86 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * func_utils.h + * + * Utility definitions for USB functions + * + * Copyright (c) 2013 Samsung Electronics Co., Ltd. + * http://www.samsung.com + * + * Author: Andrzej Pietrasiewicz + */ + +#ifndef _FUNC_UTILS_H_ +#define _FUNC_UTILS_H_ + +#include +#include + +/* Variable Length Array Macros **********************************************/ +#define vla_group(groupname) size_t groupname##__next = 0 +#define vla_group_size(groupname) groupname##__next + +#define vla_item(groupname, type, name, n) \ + size_t groupname##_##name##__offset = ({ \ + size_t offset = 0; \ + if (groupname##__next != SIZE_MAX) { \ + size_t align_mask = __alignof__(type) - 1; \ + size_t size = array_size(n, sizeof(type)); \ + offset = (groupname##__next + align_mask) & \ + ~align_mask; \ + if (check_add_overflow(offset, size, \ + &groupname##__next)) { \ + groupname##__next = SIZE_MAX; \ + offset = 0; \ + } \ + } \ + offset; \ + }) + +#define vla_item_with_sz(groupname, type, name, n) \ + size_t groupname##_##name##__sz = array_size(n, sizeof(type)); \ + size_t groupname##_##name##__offset = ({ \ + size_t offset = 0; \ + if (groupname##__next != SIZE_MAX) { \ + size_t align_mask = __alignof__(type) - 1; \ + offset = (groupname##__next + align_mask) & \ + ~align_mask; \ + if (check_add_overflow(offset, groupname##_##name##__sz,\ + &groupname##__next)) { \ + groupname##__next = SIZE_MAX; \ + offset = 0; \ + } \ + } \ + offset; \ + }) + +#define vla_ptr(ptr, groupname, name) \ + ((void *) ((char *)ptr + groupname##_##name##__offset)) + +struct usb_ep; +struct usb_request; + +/** + * alloc_ep_req - returns a usb_request allocated by the gadget driver and + * allocates the request's buffer. + * + * @ep: the endpoint to allocate a usb_request + * @len: usb_requests's buffer suggested size + * + * In case @ep direction is OUT, the @len will be aligned to ep's + * wMaxPacketSize. In order to avoid memory leaks or drops, *always* use + * usb_requests's length (req->length) to refer to the allocated buffer size. + * Requests allocated via alloc_ep_req() *must* be freed by free_ep_req(). + */ +struct usb_request *alloc_ep_req(struct usb_ep *ep, size_t len); + +/* Frees a usb_request previously allocated by alloc_ep_req() */ +static inline void free_ep_req(struct usb_ep *ep, struct usb_request *req) +{ + WARN_ON(req->buf == NULL); + kfree(req->buf); + req->buf = NULL; + usb_ep_free_request(ep, req); +} + +#endif /* _FUNC_UTILS_H_ */ -- cgit v1.2.3 From beb5a9bea8239cdf4adf6b62672e30db3e9fa5ce Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Thu, 29 Aug 2024 14:33:36 +0200 Subject: netdevice: convert private flags > BIT(31) to bitfields Make dev->priv_flags `u32` back and define bits higher than 31 as bitfield booleans as per Jakub's suggestion. This simplifies code which accesses these bits with no optimization loss (testb both before/after), allows to not extend &netdev_priv_flags each time, but also scales better as bits > 63 in the future would only add a new u64 to the structure with no complications, comparing to that extending ::priv_flags would require converting it to a bitmap. Note that I picked `unsigned long :1` to not lose any potential optimizations comparing to `bool :1` etc. Suggested-by: Jakub Kicinski Signed-off-by: Alexander Lobakin Signed-off-by: Paolo Abeni --- .../networking/net_cachelines/net_device.rst | 4 +++- .../net/ethernet/microchip/lan966x/lan966x_main.c | 2 +- drivers/net/macvlan.c | 3 ++- drivers/net/vxlan/vxlan_core.c | 3 ++- include/linux/netdevice.h | 28 ++++++++++++++-------- net/8021q/vlanproc.c | 4 ++-- net/core/dev.c | 4 ++-- net/core/dev_ioctl.c | 9 ++++--- net/core/rtnetlink.c | 2 +- 9 files changed, 35 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst index a0e0fab8161a..1fe3cdfe3582 100644 --- a/Documentation/networking/net_cachelines/net_device.rst +++ b/Documentation/networking/net_cachelines/net_device.rst @@ -7,6 +7,7 @@ net_device struct fast path usage breakdown Type Name fastpath_tx_access fastpath_rx_access Comments ..struct ..net_device +unsigned_long:32 priv_flags read_mostly - __dev_queue_xmit(tx) char name[16] - - struct_netdev_name_node* name_node struct_dev_ifalias* ifalias @@ -23,7 +24,6 @@ struct_list_head ptype_specific struct adj_list unsigned_int flags read_mostly read_mostly __dev_queue_xmit,__dev_xmit_skb,ip6_output,__ip6_finish_output(tx);ip6_rcv_core(rx) xdp_features_t xdp_features -unsigned_long_long priv_flags read_mostly - __dev_queue_xmit(tx) struct_net_device_ops* netdev_ops read_mostly - netdev_core_pick_tx,netdev_start_xmit(tx) struct_xdp_metadata_ops* xdp_metadata_ops int ifindex - read_mostly ip6_rcv_core @@ -163,6 +163,8 @@ struct_lock_class_key* qdisc_tx_busylock bool proto_down unsigned:1 wol_enabled unsigned:1 threaded - - napi_poll(napi_enable,dev_set_threaded) +unsigned_long:1 see_all_hwtstamp_requests +unsigned_long:1 change_proto_down struct_list_head net_notifier_list struct_macsec_ops* macsec_ops struct_udp_tunnel_nic_info* udp_tunnel_nic_info diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c index ec672af12e25..534d4716d5f7 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c @@ -816,7 +816,7 @@ static int lan966x_probe_port(struct lan966x *lan966x, u32 p, NETIF_F_HW_VLAN_STAG_TX | NETIF_F_HW_TC; dev->hw_features |= NETIF_F_HW_TC; - dev->priv_flags |= IFF_SEE_ALL_HWTSTAMP_REQUESTS; + dev->see_all_hwtstamp_requests = true; dev->needed_headroom = IFH_LEN_BYTES; eth_hw_addr_gen(dev, lan966x->base_mac, p + 1); diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 24298a33e0e9..b45f137f365e 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1213,7 +1213,8 @@ void macvlan_common_setup(struct net_device *dev) dev->max_mtu = ETH_MAX_MTU; dev->priv_flags &= ~IFF_TX_SKB_SHARING; netif_keep_dst(dev); - dev->priv_flags |= IFF_UNICAST_FLT | IFF_CHANGE_PROTO_DOWN; + dev->priv_flags |= IFF_UNICAST_FLT; + dev->change_proto_down = true; dev->netdev_ops = &macvlan_netdev_ops; dev->needs_free_netdev = true; dev->priv_destructor = macvlan_dev_free; diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 34391c18bba7..4a54dd1950c1 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -3331,7 +3331,8 @@ static void vxlan_setup(struct net_device *dev) dev->hw_features |= NETIF_F_RXCSUM; dev->hw_features |= NETIF_F_GSO_SOFTWARE; netif_keep_dst(dev); - dev->priv_flags |= IFF_NO_QUEUE | IFF_CHANGE_PROTO_DOWN; + dev->priv_flags |= IFF_NO_QUEUE; + dev->change_proto_down = true; /* MTU range: 68 - 65535 */ dev->min_mtu = ETH_MIN_MTU; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index fce70990b209..d6f35c9d8580 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1613,7 +1613,8 @@ struct net_device_ops { * userspace; this means that the order of these flags can change * during any kernel release. * - * You should have a pretty good reason to be extending these flags. + * You should add bitfield booleans after either net_device::priv_flags + * (hotpath) or ::threaded (slowpath) instead of extending these flags. * * @IFF_802_1Q_VLAN: 802.1Q VLAN device * @IFF_EBRIDGE: Ethernet bridging device @@ -1652,10 +1653,6 @@ struct net_device_ops { * @IFF_NO_ADDRCONF: prevent ipv6 addrconf * @IFF_TX_SKB_NO_LINEAR: device/driver is capable of xmitting frames with * skb_headlen(skb) == 0 (data starts from frag0) - * @IFF_CHANGE_PROTO_DOWN: device supports setting carrier via IFLA_PROTO_DOWN - * @IFF_SEE_ALL_HWTSTAMP_REQUESTS: device wants to see calls to - * ndo_hwtstamp_set() for all timestamp requests regardless of source, - * even if those aren't HWTSTAMP_SOURCE_NETDEV. */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1690,8 +1687,6 @@ enum netdev_priv_flags { IFF_L3MDEV_RX_HANDLER = 1<<29, IFF_NO_ADDRCONF = BIT_ULL(30), IFF_TX_SKB_NO_LINEAR = BIT_ULL(31), - IFF_CHANGE_PROTO_DOWN = BIT_ULL(32), - IFF_SEE_ALL_HWTSTAMP_REQUESTS = BIT_ULL(33), }; /* Specifies the type of the struct net_device::ml_priv pointer */ @@ -1723,6 +1718,9 @@ enum netdev_reg_state { * data with strictly "high-level" data, and it has to know about * almost every data structure used in the INET module. * + * @priv_flags: flags invisible to userspace defined as bits, see + * enum netdev_priv_flags for the definitions + * * @name: This is the first field of the "visible" part of this structure * (i.e. as seen by users in the "Space.c" file). It is the name * of the interface. @@ -1789,8 +1787,6 @@ enum netdev_reg_state { * * @flags: Interface flags (a la BSD) * @xdp_features: XDP capability supported by the device - * @priv_flags: Like 'flags' but invisible to userspace, - * see if.h for the definitions * @gflags: Global flags ( kept as legacy ) * @priv_len: Size of the ->priv flexible array * @priv: Flexible array containing private data @@ -1964,6 +1960,12 @@ enum netdev_reg_state { * * @threaded: napi threaded mode is enabled * + * @see_all_hwtstamp_requests: device wants to see calls to + * ndo_hwtstamp_set() for all timestamp requests + * regardless of source, even if those aren't + * HWTSTAMP_SOURCE_NETDEV + * @change_proto_down: device supports setting carrier via IFLA_PROTO_DOWN + * * @net_notifier_list: List of per-net netdev notifier block * that follow this device when it is moved * to another network namespace. @@ -2014,7 +2016,9 @@ struct net_device { /* TX read-mostly hotpath */ __cacheline_group_begin(net_device_read_tx); - unsigned long long priv_flags; + struct_group(priv_flags_fast, + unsigned long priv_flags:32; + ); const struct net_device_ops *netdev_ops; const struct header_ops *header_ops; struct netdev_queue *_tx; @@ -2350,6 +2354,10 @@ struct net_device { bool proto_down; bool threaded; + /* priv_flags_slow, ungrouped to save space */ + unsigned long see_all_hwtstamp_requests:1; + unsigned long change_proto_down:1; + struct list_head net_notifier_list; #if IS_ENABLED(CONFIG_MACSEC) diff --git a/net/8021q/vlanproc.c b/net/8021q/vlanproc.c index 87b959da00cd..fa67374bda49 100644 --- a/net/8021q/vlanproc.c +++ b/net/8021q/vlanproc.c @@ -238,9 +238,9 @@ static int vlandev_seq_show(struct seq_file *seq, void *offset) stats = dev_get_stats(vlandev, &temp); seq_printf(seq, - "%s VID: %d REORDER_HDR: %i dev->priv_flags: %llx\n", + "%s VID: %d REORDER_HDR: %i dev->priv_flags: %x\n", vlandev->name, vlan->vlan_id, - (int)(vlan->flags & 1), vlandev->priv_flags); + (int)(vlan->flags & 1), (u32)vlandev->priv_flags); seq_printf(seq, fmt64, "total frames received", stats->rx_packets); seq_printf(seq, fmt64, "total bytes received", stats->rx_bytes); diff --git a/net/core/dev.c b/net/core/dev.c index 932d67b975f5..56aed88ceadf 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -9274,7 +9274,7 @@ EXPORT_SYMBOL(netdev_port_same_parent_id); */ int dev_change_proto_down(struct net_device *dev, bool proto_down) { - if (!(dev->priv_flags & IFF_CHANGE_PROTO_DOWN)) + if (!dev->change_proto_down) return -EOPNOTSUPP; if (!netif_device_present(dev)) return -ENODEV; @@ -11930,7 +11930,7 @@ static struct pernet_operations __net_initdata default_device_ops = { static void __init net_dev_struct_check(void) { /* TX read-mostly hotpath */ - CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, priv_flags); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, priv_flags_fast); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, netdev_ops); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, header_ops); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, _tx); diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 8592c052c0f4..473c437b6b53 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -317,8 +317,7 @@ static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr) * should take precedence in front of hardware timestamping provided by the * netdev. If the netdev driver needs to perform specific actions even for PHY * timestamping to work properly (a switch port must trap the timestamped - * frames and not forward them), it must set IFF_SEE_ALL_HWTSTAMP_REQUESTS in - * dev->priv_flags. + * frames and not forward them), it must set dev->see_all_hwtstamp_requests. */ int dev_set_hwtstamp_phylib(struct net_device *dev, struct kernel_hwtstamp_config *cfg, @@ -332,13 +331,13 @@ int dev_set_hwtstamp_phylib(struct net_device *dev, cfg->source = phy_ts ? HWTSTAMP_SOURCE_PHYLIB : HWTSTAMP_SOURCE_NETDEV; - if (phy_ts && (dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS)) { + if (phy_ts && dev->see_all_hwtstamp_requests) { err = ops->ndo_hwtstamp_get(dev, &old_cfg); if (err) return err; } - if (!phy_ts || (dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS)) { + if (!phy_ts || dev->see_all_hwtstamp_requests) { err = ops->ndo_hwtstamp_set(dev, cfg, extack); if (err) { if (extack->_msg) @@ -347,7 +346,7 @@ int dev_set_hwtstamp_phylib(struct net_device *dev, } } - if (phy_ts && (dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS)) + if (phy_ts && dev->see_all_hwtstamp_requests) changed = kernel_hwtstamp_config_changed(&old_cfg, cfg); if (phy_ts) { diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index cd9487a12d1a..f0a520987085 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2724,7 +2724,7 @@ static int do_set_proto_down(struct net_device *dev, bool proto_down; int err; - if (!(dev->priv_flags & IFF_CHANGE_PROTO_DOWN)) { + if (!dev->change_proto_down) { NL_SET_ERR_MSG(extack, "Protodown not supported by device"); return -EOPNOTSUPP; } -- cgit v1.2.3 From 00d066a4d4edbe559ba6c35153da71d4b2b8a383 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Thu, 29 Aug 2024 14:33:37 +0200 Subject: netdev_features: convert NETIF_F_LLTX to dev->lltx NETIF_F_LLTX can't be changed via Ethtool and is not a feature, rather an attribute, very similar to IFF_NO_QUEUE (and hot). Free one netdev_features_t bit and make it a "hot" private flag. Signed-off-by: Alexander Lobakin Signed-off-by: Paolo Abeni --- Documentation/networking/net_cachelines/net_device.rst | 1 + Documentation/networking/netdev-features.rst | 8 -------- Documentation/networking/netdevices.rst | 4 ++-- drivers/net/amt.c | 2 +- drivers/net/bareudp.c | 2 +- drivers/net/bonding/bond_main.c | 2 +- drivers/net/dummy.c | 3 ++- drivers/net/ethernet/chelsio/cxgb/cxgb2.c | 3 ++- drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 3 ++- drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 3 ++- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 3 ++- drivers/net/ethernet/netronome/nfp/nfp_net_repr.c | 3 +-- drivers/net/ethernet/pasemi/pasemi_mac.c | 5 +++-- drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c | 2 +- drivers/net/ethernet/sfc/ef100_rep.c | 4 ++-- drivers/net/ethernet/tehuti/tehuti.c | 4 ++-- drivers/net/ethernet/tehuti/tehuti.h | 2 +- drivers/net/ethernet/toshiba/spider_net.c | 3 ++- drivers/net/geneve.c | 2 +- drivers/net/gtp.c | 2 +- drivers/net/hamradio/bpqether.c | 2 +- drivers/net/ipvlan/ipvlan_main.c | 3 ++- drivers/net/loopback.c | 2 +- drivers/net/macsec.c | 4 ++-- drivers/net/macvlan.c | 3 ++- drivers/net/net_failover.c | 2 +- drivers/net/netkit.c | 3 ++- drivers/net/nlmon.c | 4 ++-- drivers/net/ppp/ppp_generic.c | 2 +- drivers/net/rionet.c | 2 +- drivers/net/team/team_core.c | 2 +- drivers/net/tun.c | 5 +++-- drivers/net/veth.c | 2 +- drivers/net/vrf.c | 2 +- drivers/net/vsockmon.c | 4 ++-- drivers/net/vxlan/vxlan_core.c | 2 +- drivers/net/wireguard/device.c | 2 +- drivers/staging/octeon/ethernet.c | 2 +- include/linux/netdev_features.h | 6 ++---- include/linux/netdevice.h | 10 +++++++--- lib/test_bpf.c | 3 +-- net/8021q/vlan_dev.c | 4 ++-- net/batman-adv/soft-interface.c | 2 +- net/bridge/br_device.c | 3 ++- net/core/net-sysfs.c | 3 +-- net/dsa/user.c | 3 ++- net/ethtool/common.c | 1 - net/hsr/hsr_device.c | 4 ++-- net/ipv4/ip_gre.c | 4 +++- net/ipv4/ip_vti.c | 2 +- net/ipv4/ipip.c | 2 +- net/ipv6/ip6_gre.c | 4 +++- net/ipv6/ip6_tunnel.c | 2 +- net/ipv6/sit.c | 2 +- net/l2tp/l2tp_eth.c | 2 +- net/openvswitch/vport-internal_dev.c | 9 +++++---- net/xfrm/xfrm_interface_core.c | 2 +- 57 files changed, 93 insertions(+), 84 deletions(-) (limited to 'include/linux') diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst index 1fe3cdfe3582..e55319277074 100644 --- a/Documentation/networking/net_cachelines/net_device.rst +++ b/Documentation/networking/net_cachelines/net_device.rst @@ -8,6 +8,7 @@ net_device struct fast path usage breakdown Type Name fastpath_tx_access fastpath_rx_access Comments ..struct ..net_device unsigned_long:32 priv_flags read_mostly - __dev_queue_xmit(tx) +unsigned_long:1 lltx read_mostly - HARD_TX_LOCK,HARD_TX_TRYLOCK,HARD_TX_UNLOCK(tx) char name[16] - - struct_netdev_name_node* name_node struct_dev_ifalias* ifalias diff --git a/Documentation/networking/netdev-features.rst b/Documentation/networking/netdev-features.rst index d7b15bb64deb..f29d982ebf5d 100644 --- a/Documentation/networking/netdev-features.rst +++ b/Documentation/networking/netdev-features.rst @@ -139,14 +139,6 @@ chained skbs (skb->next/prev list). Features contained in NETIF_F_SOFT_FEATURES are features of networking stack. Driver should not change behaviour based on them. - * LLTX driver (deprecated for hardware drivers) - -NETIF_F_LLTX is meant to be used by drivers that don't need locking at all, -e.g. software tunnels. - -This is also used in a few legacy drivers that implement their -own locking, don't use it for new (hardware) drivers. - * netns-local device NETIF_F_NETNS_LOCAL is set for devices that are not allowed to move between diff --git a/Documentation/networking/netdevices.rst b/Documentation/networking/netdevices.rst index c2476917a6c3..857c9784f87e 100644 --- a/Documentation/networking/netdevices.rst +++ b/Documentation/networking/netdevices.rst @@ -258,11 +258,11 @@ ndo_get_stats: ndo_start_xmit: Synchronization: __netif_tx_lock spinlock. - When the driver sets NETIF_F_LLTX in dev->features this will be + When the driver sets dev->lltx this will be called without holding netif_tx_lock. In this case the driver has to lock by itself when needed. The locking there should also properly protect against - set_rx_mode. WARNING: use of NETIF_F_LLTX is deprecated. + set_rx_mode. WARNING: use of dev->lltx is deprecated. Don't use it for new drivers. Context: Process with BHs disabled or BH (timer), diff --git a/drivers/net/amt.c b/drivers/net/amt.c index 6d15ab3bfbbc..921bbfd72a38 100644 --- a/drivers/net/amt.c +++ b/drivers/net/amt.c @@ -3098,7 +3098,7 @@ static void amt_link_setup(struct net_device *dev) dev->hard_header_len = 0; dev->addr_len = 0; dev->priv_flags |= IFF_NO_QUEUE; - dev->features |= NETIF_F_LLTX; + dev->lltx = true; dev->features |= NETIF_F_GSO_SOFTWARE; dev->features |= NETIF_F_NETNS_LOCAL; dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM; diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c index d5c56ca91b77..6f4de883e872 100644 --- a/drivers/net/bareudp.c +++ b/drivers/net/bareudp.c @@ -553,7 +553,6 @@ static void bareudp_setup(struct net_device *dev) SET_NETDEV_DEVTYPE(dev, &bareudp_type); dev->features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST; dev->features |= NETIF_F_RXCSUM; - dev->features |= NETIF_F_LLTX; dev->features |= NETIF_F_GSO_SOFTWARE; dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST; dev->hw_features |= NETIF_F_RXCSUM; @@ -566,6 +565,7 @@ static void bareudp_setup(struct net_device *dev) dev->type = ARPHRD_NONE; netif_keep_dst(dev); dev->priv_flags |= IFF_NO_QUEUE; + dev->lltx = true; dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index cb6a694313d5..8ae887cdc231 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -5928,7 +5928,7 @@ void bond_setup(struct net_device *bond_dev) #endif /* CONFIG_XFRM_OFFLOAD */ /* don't acquire bond device's netif_tx_lock when transmitting */ - bond_dev->features |= NETIF_F_LLTX; + bond_dev->lltx = true; /* By default, we declare the bond to be fully * VLAN hardware accelerated capable. Special diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c index d29b5d7af0d7..e9c5e1e11fa0 100644 --- a/drivers/net/dummy.c +++ b/drivers/net/dummy.c @@ -109,9 +109,10 @@ static void dummy_setup(struct net_device *dev) dev->flags |= IFF_NOARP; dev->flags &= ~IFF_MULTICAST; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE; + dev->lltx = true; dev->features |= NETIF_F_SG | NETIF_F_FRAGLIST; dev->features |= NETIF_F_GSO_SOFTWARE; - dev->features |= NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_LLTX; + dev->features |= NETIF_F_HW_CSUM | NETIF_F_HIGHDMA; dev->features |= NETIF_F_GSO_ENCAP_ALL; dev->hw_features |= dev->features; dev->hw_enc_features |= dev->features; diff --git a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c index 7d7d3e0098df..3b7068832f95 100644 --- a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c +++ b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c @@ -1034,7 +1034,8 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->hw_features |= NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_RXCSUM; netdev->features |= NETIF_F_SG | NETIF_F_IP_CSUM | - NETIF_F_RXCSUM | NETIF_F_LLTX | NETIF_F_HIGHDMA; + NETIF_F_RXCSUM | NETIF_F_HIGHDMA; + netdev->lltx = true; if (vlan_tso_capable(adapter)) { netdev->features |= diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 5d99cfb4e994..1d0208b5db7d 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -229,7 +229,7 @@ static int dpaa_netdev_init(struct net_device *net_dev, net_dev->max_mtu = dpaa_get_max_mtu(); net_dev->hw_features |= (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | - NETIF_F_LLTX | NETIF_F_RXHASH); + NETIF_F_RXHASH); net_dev->hw_features |= NETIF_F_SG | NETIF_F_HIGHDMA; /* The kernels enables GSO automatically, if we declare NETIF_F_SG. @@ -239,6 +239,7 @@ static int dpaa_netdev_init(struct net_device *net_dev, net_dev->features |= NETIF_F_RXCSUM; net_dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + net_dev->lltx = true; /* we do not want shared skbs on TX */ net_dev->priv_flags &= ~IFF_TX_SKB_SHARING; diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 6866807973da..29886a8ba73f 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -4594,12 +4594,13 @@ static int dpaa2_eth_netdev_init(struct net_device *net_dev) net_dev->priv_flags |= supported; net_dev->priv_flags &= ~not_supported; + net_dev->lltx = true; /* Features */ net_dev->features = NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_SG | NETIF_F_HIGHDMA | - NETIF_F_LLTX | NETIF_F_HW_TC | NETIF_F_TSO; + NETIF_F_HW_TC | NETIF_F_TSO; net_dev->gso_max_segs = DPAA2_ETH_ENQUEUE_MAX_FDS; net_dev->hw_features = net_dev->features; net_dev->xdp_features = NETDEV_XDP_ACT_BASIC | diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index f064789f3240..44d6e125bd6f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -1676,9 +1676,10 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u16 local_port, netif_carrier_off(dev); - dev->features |= NETIF_F_NETNS_LOCAL | NETIF_F_LLTX | NETIF_F_SG | + dev->features |= NETIF_F_NETNS_LOCAL | NETIF_F_SG | NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_TC; dev->hw_features |= NETIF_F_HW_TC | NETIF_F_LOOPBACK; + dev->lltx = true; dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = MLXSW_PORT_MAX_MTU - MLXSW_PORT_ETH_FRAME_HDR; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c index eee0bfc41074..227e7a5d712e 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c @@ -248,7 +248,6 @@ nfp_repr_fix_features(struct net_device *netdev, netdev_features_t features) features = netdev_intersect_features(features, lower_features); features |= old_features & (NETIF_F_SOFT_FEATURES | NETIF_F_HW_TC); - features |= NETIF_F_LLTX; return features; } @@ -386,7 +385,7 @@ int nfp_repr_init(struct nfp_app *app, struct net_device *netdev, netif_set_tso_max_segs(netdev, NFP_NET_LSO_MAX_SEGS); netdev->priv_flags |= IFF_NO_QUEUE | IFF_DISABLE_NETPOLL; - netdev->features |= NETIF_F_LLTX; + netdev->lltx = true; if (nfp_app_has_tc(app)) { netdev->features |= NETIF_F_HW_TC; diff --git a/drivers/net/ethernet/pasemi/pasemi_mac.c b/drivers/net/ethernet/pasemi/pasemi_mac.c index 62ba269da902..cb4e12df7719 100644 --- a/drivers/net/ethernet/pasemi/pasemi_mac.c +++ b/drivers/net/ethernet/pasemi/pasemi_mac.c @@ -1699,8 +1699,9 @@ pasemi_mac_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netif_napi_add(dev, &mac->napi, pasemi_mac_poll); - dev->features = NETIF_F_IP_CSUM | NETIF_F_LLTX | NETIF_F_SG | - NETIF_F_HIGHDMA | NETIF_F_GSO; + dev->features = NETIF_F_IP_CSUM | NETIF_F_SG | NETIF_F_HIGHDMA | + NETIF_F_GSO; + dev->lltx = true; mac->dma_pdev = pci_get_device(PCI_VENDOR_ID_PASEMI, 0xa007, NULL); if (!mac->dma_pdev) { diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c index f1e40aade127..4f0ddcedfa97 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c @@ -286,7 +286,7 @@ void rmnet_vnd_setup(struct net_device *rmnet_dev) rmnet_dev->needs_free_netdev = true; rmnet_dev->ethtool_ops = &rmnet_ethtool_ops; - rmnet_dev->features |= NETIF_F_LLTX; + rmnet_dev->lltx = true; /* This perm addr will be used as interface identifier by IPv6 */ rmnet_dev->addr_assign_type = NET_ADDR_RANDOM; diff --git a/drivers/net/ethernet/sfc/ef100_rep.c b/drivers/net/ethernet/sfc/ef100_rep.c index 0b3083ef0ead..e923e1796369 100644 --- a/drivers/net/ethernet/sfc/ef100_rep.c +++ b/drivers/net/ethernet/sfc/ef100_rep.c @@ -233,8 +233,8 @@ static struct efx_rep *efx_ef100_rep_create_netdev(struct efx_nic *efx, net_dev->ethtool_ops = &efx_ef100_rep_ethtool_ops; net_dev->min_mtu = EFX_MIN_MTU; net_dev->max_mtu = EFX_MAX_MTU; - net_dev->features |= NETIF_F_LLTX; - net_dev->hw_features |= NETIF_F_LLTX; + net_dev->lltx = true; + return efv; fail1: free_netdev(net_dev); diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c index ede5f7890fb4..fc77f424f90b 100644 --- a/drivers/net/ethernet/tehuti/tehuti.c +++ b/drivers/net/ethernet/tehuti/tehuti.c @@ -1671,7 +1671,7 @@ static netdev_tx_t bdx_tx_transmit(struct sk_buff *skb, #endif #ifdef BDX_LLTX - netif_trans_update(ndev); /* NETIF_F_LLTX driver :( */ + netif_trans_update(ndev); /* dev->lltx driver :( */ #endif ndev->stats.tx_packets++; ndev->stats.tx_bytes += skb->len; @@ -2019,7 +2019,7 @@ bdx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * set multicast list callback has to use priv->tx_lock. */ #ifdef BDX_LLTX - ndev->features |= NETIF_F_LLTX; + ndev->lltx = true; #endif /* MTU range: 60 - 16384 */ ndev->min_mtu = ETH_ZLEN; diff --git a/drivers/net/ethernet/tehuti/tehuti.h b/drivers/net/ethernet/tehuti/tehuti.h index 909e7296cecf..47a2d3e5f8ed 100644 --- a/drivers/net/ethernet/tehuti/tehuti.h +++ b/drivers/net/ethernet/tehuti/tehuti.h @@ -260,7 +260,7 @@ struct bdx_priv { int tx_update_mark; int tx_noupd; #endif - spinlock_t tx_lock; /* NETIF_F_LLTX mode */ + spinlock_t tx_lock; /* dev->lltx mode */ /* rarely used */ u8 port; diff --git a/drivers/net/ethernet/toshiba/spider_net.c b/drivers/net/ethernet/toshiba/spider_net.c index 87e67121477c..a4937c18d7cb 100644 --- a/drivers/net/ethernet/toshiba/spider_net.c +++ b/drivers/net/ethernet/toshiba/spider_net.c @@ -2277,10 +2277,11 @@ spider_net_setup_netdev(struct spider_net_card *card) netdev->hw_features = NETIF_F_RXCSUM | NETIF_F_IP_CSUM; if (SPIDER_NET_RX_CSUM_DEFAULT) netdev->features |= NETIF_F_RXCSUM; - netdev->features |= NETIF_F_IP_CSUM | NETIF_F_LLTX; + netdev->features |= NETIF_F_IP_CSUM; /* some time: NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | * NETIF_F_HW_VLAN_CTAG_FILTER */ + netdev->lltx = true; /* MTU range: 64 - 2294 */ netdev->min_mtu = SPIDER_NET_MIN_MTU; diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 838e85ddec67..7f611c74eb62 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1194,7 +1194,6 @@ static void geneve_setup(struct net_device *dev) SET_NETDEV_DEVTYPE(dev, &geneve_type); - dev->features |= NETIF_F_LLTX; dev->features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST; dev->features |= NETIF_F_RXCSUM; dev->features |= NETIF_F_GSO_SOFTWARE; @@ -1215,6 +1214,7 @@ static void geneve_setup(struct net_device *dev) netif_keep_dst(dev); dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE; + dev->lltx = true; eth_hw_addr_random(dev); } diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 2e94d10348cc..a60bfb1abb7f 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -1356,7 +1356,7 @@ static void gtp_link_setup(struct net_device *dev) dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; dev->priv_flags |= IFF_NO_QUEUE; - dev->features |= NETIF_F_LLTX; + dev->lltx = true; netif_keep_dst(dev); dev->needed_headroom = LL_MAX_HEADER + GTP_IPV4_MAXLEN; diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c index 83a16d10eedb..bac1bb69d63a 100644 --- a/drivers/net/hamradio/bpqether.c +++ b/drivers/net/hamradio/bpqether.c @@ -458,7 +458,7 @@ static void bpq_setup(struct net_device *dev) dev->needs_free_netdev = true; dev->flags = 0; - dev->features = NETIF_F_LLTX; /* Allow recursion */ + dev->lltx = true; /* Allow recursion */ #if IS_ENABLED(CONFIG_AX25) dev->header_ops = &ax25_header_ops; diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 094f44dac5c8..ee2c3cf4df36 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -114,7 +114,7 @@ static void ipvlan_port_destroy(struct net_device *dev) NETIF_F_GSO_ROBUST | NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL) #define IPVLAN_ALWAYS_ON \ - (IPVLAN_ALWAYS_ON_OFLOADS | NETIF_F_LLTX | NETIF_F_VLAN_CHALLENGED) + (IPVLAN_ALWAYS_ON_OFLOADS | NETIF_F_VLAN_CHALLENGED) #define IPVLAN_FEATURES \ (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \ @@ -141,6 +141,7 @@ static int ipvlan_init(struct net_device *dev) dev->vlan_features = phy_dev->vlan_features & IPVLAN_FEATURES; dev->vlan_features |= IPVLAN_ALWAYS_ON_OFLOADS; dev->hw_enc_features |= dev->features; + dev->lltx = true; netif_inherit_tso_max(dev, phy_dev); dev->hard_header_len = phy_dev->hard_header_len; diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index 2b486e7c749c..bf857782be0f 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -171,6 +171,7 @@ static void gen_lo_setup(struct net_device *dev, dev->type = ARPHRD_LOOPBACK; /* 0x0001*/ dev->flags = IFF_LOOPBACK; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE; + dev->lltx = true; netif_keep_dst(dev); dev->hw_features = NETIF_F_GSO_SOFTWARE; dev->features = NETIF_F_SG | NETIF_F_FRAGLIST @@ -179,7 +180,6 @@ static void gen_lo_setup(struct net_device *dev, | NETIF_F_RXCSUM | NETIF_F_SCTP_CRC | NETIF_F_HIGHDMA - | NETIF_F_LLTX | NETIF_F_NETNS_LOCAL | NETIF_F_VLAN_CHALLENGED | NETIF_F_LOOPBACK; diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 2da70bc3dd86..12d1b205f6d1 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -3550,7 +3550,8 @@ static int macsec_dev_init(struct net_device *dev) return err; dev->features = real_dev->features & MACSEC_FEATURES; - dev->features |= NETIF_F_LLTX | NETIF_F_GSO_SOFTWARE; + dev->features |= NETIF_F_GSO_SOFTWARE; + dev->lltx = true; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; macsec_set_head_tail_room(dev); @@ -3581,7 +3582,6 @@ static netdev_features_t macsec_fix_features(struct net_device *dev, features &= (real_dev->features & MACSEC_FEATURES) | NETIF_F_GSO_SOFTWARE | NETIF_F_SOFT_FEATURES; - features |= NETIF_F_LLTX; return features; } diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index b45f137f365e..cf18e66de142 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -900,7 +900,7 @@ static struct lock_class_key macvlan_netdev_addr_lock_key; (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE | \ NETIF_F_GSO_ROBUST | NETIF_F_GSO_ENCAP_ALL) -#define ALWAYS_ON_FEATURES (ALWAYS_ON_OFFLOADS | NETIF_F_LLTX) +#define ALWAYS_ON_FEATURES ALWAYS_ON_OFFLOADS #define MACVLAN_FEATURES \ (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \ @@ -932,6 +932,7 @@ static int macvlan_init(struct net_device *dev) dev->vlan_features = lowerdev->vlan_features & MACVLAN_FEATURES; dev->vlan_features |= ALWAYS_ON_OFFLOADS; dev->hw_enc_features |= dev->features; + dev->lltx = true; netif_inherit_tso_max(dev, lowerdev); dev->hard_header_len = lowerdev->hard_header_len; macvlan_set_lockdep_class(dev); diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c index 963d8b4af28d..06728385a35f 100644 --- a/drivers/net/net_failover.c +++ b/drivers/net/net_failover.c @@ -731,7 +731,7 @@ struct failover *net_failover_create(struct net_device *standby_dev) IFF_TX_SKB_SHARING); /* don't acquire failover netdev's netif_tx_lock when transmitting */ - failover_dev->features |= NETIF_F_LLTX; + failover_dev->lltx = true; /* Don't allow failover devices to change network namespaces. */ failover_dev->features |= NETIF_F_NETNS_LOCAL; diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c index 16789cd446e9..79232f5cc088 100644 --- a/drivers/net/netkit.c +++ b/drivers/net/netkit.c @@ -255,11 +255,12 @@ static void netkit_setup(struct net_device *dev) dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; dev->priv_flags |= IFF_PHONY_HEADROOM; dev->priv_flags |= IFF_NO_QUEUE; + dev->lltx = true; dev->ethtool_ops = &netkit_ethtool_ops; dev->netdev_ops = &netkit_netdev_ops; - dev->features |= netkit_features | NETIF_F_LLTX; + dev->features |= netkit_features; dev->hw_features = netkit_features; dev->hw_enc_features = netkit_features; dev->mpls_features = NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE; diff --git a/drivers/net/nlmon.c b/drivers/net/nlmon.c index e5a0987a263e..8bfd4ee5a8c4 100644 --- a/drivers/net/nlmon.c +++ b/drivers/net/nlmon.c @@ -63,13 +63,13 @@ static void nlmon_setup(struct net_device *dev) { dev->type = ARPHRD_NETLINK; dev->priv_flags |= IFF_NO_QUEUE; + dev->lltx = true; dev->netdev_ops = &nlmon_ops; dev->ethtool_ops = &nlmon_ethtool_ops; dev->needs_free_netdev = true; - dev->features = NETIF_F_SG | NETIF_F_FRAGLIST | - NETIF_F_HIGHDMA | NETIF_F_LLTX; + dev->features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA; dev->flags = IFF_NOARP; dev->pcpu_stat_type = NETDEV_PCPU_STAT_LSTATS; diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index eb9acfcaeb09..4b2971e2bf48 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -1631,7 +1631,7 @@ static void ppp_setup(struct net_device *dev) dev->netdev_ops = &ppp_netdev_ops; SET_NETDEV_DEVTYPE(dev, &ppp_type); - dev->features |= NETIF_F_LLTX; + dev->lltx = true; dev->hard_header_len = PPP_HDRLEN; dev->mtu = PPP_MRU; diff --git a/drivers/net/rionet.c b/drivers/net/rionet.c index 4eececc94513..318a0ef1af50 100644 --- a/drivers/net/rionet.c +++ b/drivers/net/rionet.c @@ -515,7 +515,7 @@ static int rionet_setup_netdev(struct rio_mport *mport, struct net_device *ndev) /* MTU range: 68 - 4082 */ ndev->min_mtu = ETH_MIN_MTU; ndev->max_mtu = RIONET_MAX_MTU; - ndev->features = NETIF_F_LLTX; + ndev->lltx = true; SET_NETDEV_DEV(ndev, &mport->dev); ndev->ethtool_ops = &rionet_ethtool_ops; diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c index ab1935a4aa2c..1d1bad3cedc2 100644 --- a/drivers/net/team/team_core.c +++ b/drivers/net/team/team_core.c @@ -2189,8 +2189,8 @@ static void team_setup(struct net_device *dev) * Let this up to underlay drivers. */ dev->priv_flags |= IFF_UNICAST_FLT | IFF_LIVE_ADDR_CHANGE; + dev->lltx = true; - dev->features |= NETIF_F_LLTX; dev->features |= NETIF_F_GRO; /* Don't allow team devices to change network namespaces. */ diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 1d06c560c5e6..a645c36f2cee 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -990,10 +990,11 @@ static int tun_net_init(struct net_device *dev) dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | TUN_USER_FEATURES | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; - dev->features = dev->hw_features | NETIF_F_LLTX; + dev->features = dev->hw_features; dev->vlan_features = dev->features & ~(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX); + dev->lltx = true; tun->flags = (tun->flags & ~TUN_FEATURES) | (ifr->ifr_flags & TUN_FEATURES); @@ -1129,7 +1130,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) goto drop; } - /* NETIF_F_LLTX requires to do our own update of trans_start */ + /* dev->lltx requires to do our own update of trans_start */ queue = netdev_get_tx_queue(dev, txq); txq_trans_cond_update(queue); diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 34499b91a8bd..18148e068aa0 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -1697,11 +1697,11 @@ static void veth_setup(struct net_device *dev) dev->priv_flags |= IFF_NO_QUEUE; dev->priv_flags |= IFF_PHONY_HEADROOM; dev->priv_flags |= IFF_DISABLE_NETPOLL; + dev->lltx = true; dev->netdev_ops = &veth_netdev_ops; dev->xdp_metadata_ops = &veth_xdp_metadata_ops; dev->ethtool_ops = &veth_ethtool_ops; - dev->features |= NETIF_F_LLTX; dev->features |= VETH_FEATURES; dev->vlan_features = dev->features & ~(NETIF_F_HW_VLAN_CTAG_TX | diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index a900908eb24a..b1d4ef538995 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -1635,7 +1635,7 @@ static void vrf_setup(struct net_device *dev) eth_hw_addr_random(dev); /* don't acquire vrf device's netif_tx_lock when transmitting */ - dev->features |= NETIF_F_LLTX; + dev->lltx = true; /* don't allow vrf devices to change network namespaces. */ dev->features |= NETIF_F_NETNS_LOCAL; diff --git a/drivers/net/vsockmon.c b/drivers/net/vsockmon.c index 4c260074c091..53fb76d574c6 100644 --- a/drivers/net/vsockmon.c +++ b/drivers/net/vsockmon.c @@ -83,13 +83,13 @@ static void vsockmon_setup(struct net_device *dev) { dev->type = ARPHRD_VSOCKMON; dev->priv_flags |= IFF_NO_QUEUE; + dev->lltx = true; dev->netdev_ops = &vsockmon_ops; dev->ethtool_ops = &vsockmon_ethtool_ops; dev->needs_free_netdev = true; - dev->features = NETIF_F_SG | NETIF_F_FRAGLIST | - NETIF_F_HIGHDMA | NETIF_F_LLTX; + dev->features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA; dev->flags = IFF_NOARP; diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 4a54dd1950c1..53dcb9fffc04 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -3321,7 +3321,6 @@ static void vxlan_setup(struct net_device *dev) dev->needs_free_netdev = true; SET_NETDEV_DEVTYPE(dev, &vxlan_type); - dev->features |= NETIF_F_LLTX; dev->features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST; dev->features |= NETIF_F_RXCSUM; dev->features |= NETIF_F_GSO_SOFTWARE; @@ -3333,6 +3332,7 @@ static void vxlan_setup(struct net_device *dev) netif_keep_dst(dev); dev->priv_flags |= IFF_NO_QUEUE; dev->change_proto_down = true; + dev->lltx = true; /* MTU range: 68 - 65535 */ dev->min_mtu = ETH_MIN_MTU; diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c index 3feb36ee5bfb..45e9b908dbfb 100644 --- a/drivers/net/wireguard/device.c +++ b/drivers/net/wireguard/device.c @@ -289,7 +289,7 @@ static void wg_setup(struct net_device *dev) dev->type = ARPHRD_NONE; dev->flags = IFF_POINTOPOINT | IFF_NOARP; dev->priv_flags |= IFF_NO_QUEUE; - dev->features |= NETIF_F_LLTX; + dev->lltx = true; dev->features |= WG_NETDEV_FEATURES; dev->hw_features |= WG_NETDEV_FEATURES; dev->hw_enc_features |= WG_NETDEV_FEATURES; diff --git a/drivers/staging/octeon/ethernet.c b/drivers/staging/octeon/ethernet.c index 9eee28f2940c..a5e99cc78a45 100644 --- a/drivers/staging/octeon/ethernet.c +++ b/drivers/staging/octeon/ethernet.c @@ -425,7 +425,7 @@ int cvm_oct_common_init(struct net_device *dev) dev->features |= NETIF_F_SG | NETIF_F_IP_CSUM; /* We do our own locking, Linux doesn't need to */ - dev->features |= NETIF_F_LLTX; + dev->lltx = true; dev->ethtool_ops = &cvm_oct_ethtool_ops; cvm_oct_set_mac_filter(dev); diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 7c2d77d75a88..a2e20b517584 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -24,8 +24,7 @@ enum { NETIF_F_HW_VLAN_CTAG_FILTER_BIT,/* Receive filtering on VLAN CTAGs */ NETIF_F_VLAN_CHALLENGED_BIT, /* Device cannot handle VLAN packets */ NETIF_F_GSO_BIT, /* Enable software GSO. */ - NETIF_F_LLTX_BIT, /* LockLess TX - deprecated. Please */ - /* do not use LLTX in new drivers */ + __UNUSED_NETIF_F_12, NETIF_F_NETNS_LOCAL_BIT, /* Does not change network namespaces */ NETIF_F_GRO_BIT, /* Generic receive offload */ NETIF_F_LRO_BIT, /* large receive offload */ @@ -120,7 +119,6 @@ enum { #define NETIF_F_HW_VLAN_CTAG_TX __NETIF_F(HW_VLAN_CTAG_TX) #define NETIF_F_IP_CSUM __NETIF_F(IP_CSUM) #define NETIF_F_IPV6_CSUM __NETIF_F(IPV6_CSUM) -#define NETIF_F_LLTX __NETIF_F(LLTX) #define NETIF_F_LOOPBACK __NETIF_F(LOOPBACK) #define NETIF_F_LRO __NETIF_F(LRO) #define NETIF_F_NETNS_LOCAL __NETIF_F(NETNS_LOCAL) @@ -193,7 +191,7 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start) /* Features valid for ethtool to change */ /* = all defined minus driver/device-class-related */ #define NETIF_F_NEVER_CHANGE (NETIF_F_VLAN_CHALLENGED | \ - NETIF_F_LLTX | NETIF_F_NETNS_LOCAL) + NETIF_F_NETNS_LOCAL) /* remember that ((t)1 << t_BITS) is undefined in C99 */ #define NETIF_F_ETHTOOL_BITS ((__NETIF_F_BIT(NETDEV_FEATURE_COUNT - 1) | \ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d6f35c9d8580..e22ca5e07490 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1720,6 +1720,9 @@ enum netdev_reg_state { * * @priv_flags: flags invisible to userspace defined as bits, see * enum netdev_priv_flags for the definitions + * @lltx: device supports lockless Tx. Deprecated for real HW + * drivers. Mainly used by logical interfaces, such as + * bonding and tunnels * * @name: This is the first field of the "visible" part of this structure * (i.e. as seen by users in the "Space.c" file). It is the name @@ -2018,6 +2021,7 @@ struct net_device { __cacheline_group_begin(net_device_read_tx); struct_group(priv_flags_fast, unsigned long priv_flags:32; + unsigned long lltx:1; ); const struct net_device_ops *netdev_ops; const struct header_ops *header_ops; @@ -4433,7 +4437,7 @@ static inline void netif_tx_unlock_bh(struct net_device *dev) } #define HARD_TX_LOCK(dev, txq, cpu) { \ - if ((dev->features & NETIF_F_LLTX) == 0) { \ + if (!(dev)->lltx) { \ __netif_tx_lock(txq, cpu); \ } else { \ __netif_tx_acquire(txq); \ @@ -4441,12 +4445,12 @@ static inline void netif_tx_unlock_bh(struct net_device *dev) } #define HARD_TX_TRYLOCK(dev, txq) \ - (((dev->features & NETIF_F_LLTX) == 0) ? \ + (!(dev)->lltx ? \ __netif_tx_trylock(txq) : \ __netif_tx_acquire(txq)) #define HARD_TX_UNLOCK(dev, txq) { \ - if ((dev->features & NETIF_F_LLTX) == 0) { \ + if (!(dev)->lltx) { \ __netif_tx_unlock(txq); \ } else { \ __netif_tx_release(txq); \ diff --git a/lib/test_bpf.c b/lib/test_bpf.c index ca4b0eea81a2..fa5edd6ef7f7 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -15077,8 +15077,7 @@ static struct skb_segment_test skb_segment_tests[] __initconst = { .build_skb = build_test_skb_linear_no_head_frag, .features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_GSO | - NETIF_F_LLTX | NETIF_F_GRO | - NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM | + NETIF_F_GRO | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM | NETIF_F_HW_VLAN_STAG_TX } }; diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 217be32426b5..3ca485537d77 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -569,7 +569,8 @@ static int vlan_dev_init(struct net_device *dev) if (real_dev->vlan_features & NETIF_F_HW_MACSEC) dev->hw_features |= NETIF_F_HW_MACSEC; - dev->features |= dev->hw_features | NETIF_F_LLTX; + dev->features |= dev->hw_features; + dev->lltx = true; netif_inherit_tso_max(dev, real_dev); if (dev->features & NETIF_F_VLAN_FEATURES) netdev_warn(real_dev, "VLAN features are set incorrectly. Q-in-Q configurations may not work correctly.\n"); @@ -655,7 +656,6 @@ static netdev_features_t vlan_dev_fix_features(struct net_device *dev, lower_features |= NETIF_F_HW_CSUM; features = netdev_intersect_features(features, lower_features); features |= old_features & (NETIF_F_SOFT_FEATURES | NETIF_F_GSO_SOFTWARE); - features |= NETIF_F_LLTX; return features; } diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 30ecbc2ef1fd..e791a73ef901 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -1021,8 +1021,8 @@ static void batadv_softif_init_early(struct net_device *dev) dev->needs_free_netdev = true; dev->priv_destructor = batadv_softif_free; dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_NETNS_LOCAL; - dev->features |= NETIF_F_LLTX; dev->priv_flags |= IFF_NO_QUEUE; + dev->lltx = true; /* can't call min_mtu, because the needed variables * have not been initialized yet diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index fb1115857e49..a6d25113dfb1 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -487,8 +487,9 @@ void br_dev_setup(struct net_device *dev) dev->ethtool_ops = &br_ethtool_ops; SET_NETDEV_DEVTYPE(dev, &br_type); dev->priv_flags = IFF_EBRIDGE | IFF_NO_QUEUE; + dev->lltx = true; - dev->features = COMMON_FEATURES | NETIF_F_LLTX | NETIF_F_NETNS_LOCAL | + dev->features = COMMON_FEATURES | NETIF_F_NETNS_LOCAL | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; dev->hw_features = COMMON_FEATURES | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 444f23e74f8e..01a9fb54ef42 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1764,8 +1764,7 @@ static const struct kobj_type netdev_queue_ktype = { static bool netdev_uses_bql(const struct net_device *dev) { - if (dev->features & NETIF_F_LLTX || - dev->priv_flags & IFF_NO_QUEUE) + if (dev->lltx || (dev->priv_flags & IFF_NO_QUEUE)) return false; return IS_ENABLED(CONFIG_BQL); diff --git a/net/dsa/user.c b/net/dsa/user.c index f5adfa1d978a..74eda9b30608 100644 --- a/net/dsa/user.c +++ b/net/dsa/user.c @@ -2642,11 +2642,12 @@ void dsa_user_setup_tagger(struct net_device *user) user->features = conduit->vlan_features | NETIF_F_HW_TC; user->hw_features |= NETIF_F_HW_TC; - user->features |= NETIF_F_LLTX; if (user->needed_tailroom) user->features &= ~(NETIF_F_SG | NETIF_F_FRAGLIST); if (ds->needs_standalone_vlan_filtering) user->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + + user->lltx = true; } int dsa_user_suspend(struct net_device *user_dev) diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 7257ae272296..447fc80e1b00 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -25,7 +25,6 @@ const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = { [NETIF_F_HW_VLAN_STAG_FILTER_BIT] = "rx-vlan-stag-filter", [NETIF_F_VLAN_CHALLENGED_BIT] = "vlan-challenged", [NETIF_F_GSO_BIT] = "tx-generic-segmentation", - [NETIF_F_LLTX_BIT] = "tx-lockless", [NETIF_F_NETNS_LOCAL_BIT] = "netns-local", [NETIF_F_GRO_BIT] = "rx-gro", [NETIF_F_GRO_HW_BIT] = "rx-gro-hw", diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index e4cc6b78dcfc..d4c783076662 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -554,6 +554,8 @@ void hsr_dev_setup(struct net_device *dev) dev->netdev_ops = &hsr_device_ops; SET_NETDEV_DEVTYPE(dev, &hsr_type); dev->priv_flags |= IFF_NO_QUEUE | IFF_DISABLE_NETPOLL; + /* Prevent recursive tx locking */ + dev->lltx = true; dev->needs_free_netdev = true; @@ -563,8 +565,6 @@ void hsr_dev_setup(struct net_device *dev) dev->features = dev->hw_features; - /* Prevent recursive tx locking */ - dev->features |= NETIF_F_LLTX; /* VLAN on top of HSR needs testing and probably some work on * hsr_header_create() etc. */ diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index ba205473522e..b54c41f3ae3c 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -996,7 +996,7 @@ static void __gre_tunnel_init(struct net_device *dev) tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen; dev->needed_headroom = tunnel->hlen + sizeof(tunnel->parms.iph); - dev->features |= GRE_FEATURES | NETIF_F_LLTX; + dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; /* TCP offload with GRE SEQ is not supported, nor can we support 2 @@ -1010,6 +1010,8 @@ static void __gre_tunnel_init(struct net_device *dev) dev->features |= NETIF_F_GSO_SOFTWARE; dev->hw_features |= NETIF_F_GSO_SOFTWARE; + + dev->lltx = true; } static int ipgre_tunnel_init(struct net_device *dev) diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 14536da9f5dc..f0b4419cef34 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -443,7 +443,7 @@ static int vti_tunnel_init(struct net_device *dev) dev->flags = IFF_NOARP; dev->addr_len = 4; - dev->features |= NETIF_F_LLTX; + dev->lltx = true; netif_keep_dst(dev); return ip_tunnel_init(dev); diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 923a2ef68c2f..dc0db5895e0e 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -378,7 +378,7 @@ static void ipip_tunnel_setup(struct net_device *dev) dev->type = ARPHRD_TUNNEL; dev->flags = IFF_NOARP; dev->addr_len = 4; - dev->features |= NETIF_F_LLTX; + dev->lltx = true; netif_keep_dst(dev); dev->features |= IPIP_FEATURES; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 3942bd2ade78..08beab638bda 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1471,7 +1471,7 @@ static void ip6gre_tnl_init_features(struct net_device *dev) { struct ip6_tnl *nt = netdev_priv(dev); - dev->features |= GRE6_FEATURES | NETIF_F_LLTX; + dev->features |= GRE6_FEATURES; dev->hw_features |= GRE6_FEATURES; /* TCP offload with GRE SEQ is not supported, nor can we support 2 @@ -1485,6 +1485,8 @@ static void ip6gre_tnl_init_features(struct net_device *dev) dev->features |= NETIF_F_GSO_SOFTWARE; dev->hw_features |= NETIF_F_GSO_SOFTWARE; + + dev->lltx = true; } static int ip6gre_tunnel_init_common(struct net_device *dev) diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 87dfb565a9f8..cbef0fcece71 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1849,7 +1849,7 @@ static void ip6_tnl_dev_setup(struct net_device *dev) dev->type = ARPHRD_TUNNEL6; dev->flags |= IFF_NOARP; dev->addr_len = sizeof(struct in6_addr); - dev->features |= NETIF_F_LLTX; + dev->lltx = true; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; netif_keep_dst(dev); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 3b2eed7fc765..58306522fb1e 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1436,7 +1436,7 @@ static void ipip6_tunnel_setup(struct net_device *dev) dev->flags = IFF_NOARP; netif_keep_dst(dev); dev->addr_len = 4; - dev->features |= NETIF_F_LLTX; + dev->lltx = true; dev->features |= SIT_FEATURES; dev->hw_features |= SIT_FEATURES; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 15a862f33f76..d692b902e120 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -97,7 +97,7 @@ static void l2tp_eth_dev_setup(struct net_device *dev) SET_NETDEV_DEVTYPE(dev, &l2tpeth_type); ether_setup(dev); dev->priv_flags &= ~IFF_TX_SKB_SHARING; - dev->features |= NETIF_F_LLTX; + dev->lltx = true; dev->netdev_ops = &l2tp_eth_netdev_ops; dev->needs_free_netdev = true; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c index 4b33133cbdff..3a369a31c5cc 100644 --- a/net/openvswitch/vport-internal_dev.c +++ b/net/openvswitch/vport-internal_dev.c @@ -102,19 +102,20 @@ static void do_setup(struct net_device *netdev) netdev->priv_flags &= ~IFF_TX_SKB_SHARING; netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_OPENVSWITCH | IFF_NO_QUEUE; + netdev->lltx = true; netdev->needs_free_netdev = true; netdev->priv_destructor = NULL; netdev->ethtool_ops = &internal_dev_ethtool_ops; netdev->rtnl_link_ops = &internal_dev_link_ops; - netdev->features = NETIF_F_LLTX | NETIF_F_SG | NETIF_F_FRAGLIST | - NETIF_F_HIGHDMA | NETIF_F_HW_CSUM | - NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL; + netdev->features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | + NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE | + NETIF_F_GSO_ENCAP_ALL; netdev->vlan_features = netdev->features; netdev->hw_enc_features = netdev->features; netdev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; - netdev->hw_features = netdev->features & ~NETIF_F_LLTX; + netdev->hw_features = netdev->features; eth_hw_addr_random(netdev); } diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index e50e4bf993fa..98f1e2b67c76 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -769,7 +769,7 @@ static int xfrmi_dev_init(struct net_device *dev) if (err) return err; - dev->features |= NETIF_F_LLTX; + dev->lltx = true; dev->features |= XFRMI_FEATURES; dev->hw_features |= XFRMI_FEATURES; -- cgit v1.2.3 From 05c1280a2bcfca187fe7fa90bb240602cf54af0a Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Thu, 29 Aug 2024 14:33:38 +0200 Subject: netdev_features: convert NETIF_F_NETNS_LOCAL to dev->netns_local "Interface can't change network namespaces" is rather an attribute, not a feature, and it can't be changed via Ethtool. Make it a "cold" private flag instead of a netdev_feature and free one more bit. Signed-off-by: Alexander Lobakin Signed-off-by: Paolo Abeni --- Documentation/networking/net_cachelines/net_device.rst | 1 + Documentation/networking/netdev-features.rst | 7 ------- Documentation/networking/switchdev.rst | 4 ++-- drivers/net/amt.c | 2 +- drivers/net/bonding/bond_main.c | 6 +++--- drivers/net/ethernet/adi/adin1110.c | 2 +- drivers/net/ethernet/marvell/prestera/prestera_main.c | 3 ++- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 3 ++- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 5 +++-- drivers/net/ethernet/rocker/rocker_main.c | 3 ++- drivers/net/ethernet/ti/cpsw_new.c | 3 ++- drivers/net/loopback.c | 2 +- drivers/net/net_failover.c | 2 +- drivers/net/team/team_core.c | 6 +++--- drivers/net/vrf.c | 2 +- include/linux/netdev_features.h | 6 ++---- include/linux/netdevice.h | 2 ++ net/batman-adv/soft-interface.c | 3 ++- net/bridge/br_device.c | 5 +++-- net/core/dev.c | 4 ++-- net/ethtool/common.c | 1 - net/hsr/hsr_device.c | 8 ++++---- net/ieee802154/6lowpan/core.c | 2 +- net/ieee802154/core.c | 10 +++++----- net/ipv4/ip_tunnel.c | 2 +- net/ipv4/ipmr.c | 2 +- net/ipv6/ip6_gre.c | 3 +-- net/ipv6/ip6_tunnel.c | 2 +- net/ipv6/ip6mr.c | 2 +- net/ipv6/sit.c | 2 +- net/openvswitch/vport-internal_dev.c | 2 +- net/wireless/core.c | 10 +++++----- tools/testing/selftests/net/forwarding/README | 2 +- 34 files changed, 61 insertions(+), 62 deletions(-) (limited to 'include/linux') diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst index e55319277074..e649d8e9556f 100644 --- a/Documentation/networking/net_cachelines/net_device.rst +++ b/Documentation/networking/net_cachelines/net_device.rst @@ -166,6 +166,7 @@ unsigned:1 wol_enabled unsigned:1 threaded - - napi_poll(napi_enable,dev_set_threaded) unsigned_long:1 see_all_hwtstamp_requests unsigned_long:1 change_proto_down +unsigned_long:1 netns_local struct_list_head net_notifier_list struct_macsec_ops* macsec_ops struct_udp_tunnel_nic_info* udp_tunnel_nic_info diff --git a/Documentation/networking/netdev-features.rst b/Documentation/networking/netdev-features.rst index f29d982ebf5d..5014f7cc1398 100644 --- a/Documentation/networking/netdev-features.rst +++ b/Documentation/networking/netdev-features.rst @@ -139,13 +139,6 @@ chained skbs (skb->next/prev list). Features contained in NETIF_F_SOFT_FEATURES are features of networking stack. Driver should not change behaviour based on them. - * netns-local device - -NETIF_F_NETNS_LOCAL is set for devices that are not allowed to move between -network namespaces (e.g. loopback). - -Don't use it in drivers. - * VLAN challenged NETIF_F_VLAN_CHALLENGED should be set for devices which can't cope with VLAN diff --git a/Documentation/networking/switchdev.rst b/Documentation/networking/switchdev.rst index 758f1dae3fce..f355f0166f1b 100644 --- a/Documentation/networking/switchdev.rst +++ b/Documentation/networking/switchdev.rst @@ -137,10 +137,10 @@ would be sub-port 0 on port 1 on switch 1. Port Features ^^^^^^^^^^^^^ -NETIF_F_NETNS_LOCAL +dev->netns_local If the switchdev driver (and device) only supports offloading of the default -network namespace (netns), the driver should set this feature flag to prevent +network namespace (netns), the driver should set this private flag to prevent the port netdev from being moved out of the default netns. A netns-aware driver/device would not set this flag and be responsible for partitioning hardware to preserve netns containment. This means hardware cannot forward diff --git a/drivers/net/amt.c b/drivers/net/amt.c index 921bbfd72a38..0433a0f36d1b 100644 --- a/drivers/net/amt.c +++ b/drivers/net/amt.c @@ -3099,8 +3099,8 @@ static void amt_link_setup(struct net_device *dev) dev->addr_len = 0; dev->priv_flags |= IFF_NO_QUEUE; dev->lltx = true; + dev->netns_local = true; dev->features |= NETIF_F_GSO_SOFTWARE; - dev->features |= NETIF_F_NETNS_LOCAL; dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM; dev->hw_features |= NETIF_F_FRAGLIST | NETIF_F_RXCSUM; dev->hw_features |= NETIF_F_GSO_SOFTWARE; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 8ae887cdc231..f13d413ad26c 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -5930,6 +5930,9 @@ void bond_setup(struct net_device *bond_dev) /* don't acquire bond device's netif_tx_lock when transmitting */ bond_dev->lltx = true; + /* Don't allow bond devices to change network namespaces. */ + bond_dev->netns_local = true; + /* By default, we declare the bond to be fully * VLAN hardware accelerated capable. Special * care is taken in the various xmit functions @@ -5937,9 +5940,6 @@ void bond_setup(struct net_device *bond_dev) * capable */ - /* Don't allow bond devices to change network namespaces. */ - bond_dev->features |= NETIF_F_NETNS_LOCAL; - bond_dev->hw_features = BOND_VLAN_FEATURES | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER | diff --git a/drivers/net/ethernet/adi/adin1110.c b/drivers/net/ethernet/adi/adin1110.c index 0713f1e2c7f3..3431a7e62b0d 100644 --- a/drivers/net/ethernet/adi/adin1110.c +++ b/drivers/net/ethernet/adi/adin1110.c @@ -1599,7 +1599,7 @@ static int adin1110_probe_netdevs(struct adin1110_priv *priv) netdev->netdev_ops = &adin1110_netdev_ops; netdev->ethtool_ops = &adin1110_ethtool_ops; netdev->priv_flags |= IFF_UNICAST_FLT; - netdev->features |= NETIF_F_NETNS_LOCAL; + netdev->netns_local = true; port_priv->phydev = get_phy_device(priv->mii_bus, i + 1, false); if (IS_ERR(port_priv->phydev)) { diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c index 63ae01954dfc..22ca6ee9665e 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_main.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c @@ -633,7 +633,8 @@ static int prestera_port_create(struct prestera_switch *sw, u32 id) if (err) goto err_dl_port_register; - dev->features |= NETIF_F_NETNS_LOCAL | NETIF_F_HW_TC; + dev->features |= NETIF_F_HW_TC; + dev->netns_local = true; dev->netdev_ops = &prestera_netdev_ops; dev->ethtool_ops = &prestera_ethtool_ops; SET_NETDEV_DEV(dev, sw->dev->dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 16b67c457b60..47e7a80d221b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4414,9 +4414,9 @@ static netdev_features_t mlx5e_fix_features(struct net_device *netdev, if (mlx5e_is_uplink_rep(priv)) { features = mlx5e_fix_uplink_rep_features(netdev, features); - features |= NETIF_F_NETNS_LOCAL; + netdev->netns_local = true; } else { - features &= ~NETIF_F_NETNS_LOCAL; + netdev->netns_local = false; } mutex_unlock(&priv->state_lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index b885042eef14..92094bf60d59 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -898,7 +898,8 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev, netdev->hw_features |= NETIF_F_RXCSUM; netdev->features |= netdev->hw_features; - netdev->features |= NETIF_F_NETNS_LOCAL; + + netdev->netns_local = true; } static int mlx5e_init_rep(struct mlx5_core_dev *mdev, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 44d6e125bd6f..b9ffd7236aff 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -1676,10 +1676,11 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u16 local_port, netif_carrier_off(dev); - dev->features |= NETIF_F_NETNS_LOCAL | NETIF_F_SG | - NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_TC; + dev->features |= NETIF_F_SG | NETIF_F_HW_VLAN_CTAG_FILTER | + NETIF_F_HW_TC; dev->hw_features |= NETIF_F_HW_TC | NETIF_F_LOOPBACK; dev->lltx = true; + dev->netns_local = true; dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = MLXSW_PORT_MAX_MTU - MLXSW_PORT_ETH_FRAME_HDR; diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index e097ce3e69ea..84fa911c78db 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -2575,7 +2575,8 @@ static int rocker_probe_port(struct rocker *rocker, unsigned int port_number) netif_napi_add(dev, &rocker_port->napi_rx, rocker_port_poll_rx); rocker_carrier_init(rocker_port); - dev->features |= NETIF_F_NETNS_LOCAL | NETIF_F_SG; + dev->features |= NETIF_F_SG; + dev->netns_local = true; /* MTU range: 68 - 9000 */ dev->min_mtu = ROCKER_PORT_MIN_MTU; diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index 2baa198ebfa0..557cc71b9dd2 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -1407,7 +1407,8 @@ static int cpsw_create_ports(struct cpsw_common *cpsw) cpsw->slaves[i].ndev = ndev; ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | - NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_NETNS_LOCAL | NETIF_F_HW_TC; + NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_TC; + ndev->netns_local = true; ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index bf857782be0f..1993b90b1a5f 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -172,6 +172,7 @@ static void gen_lo_setup(struct net_device *dev, dev->flags = IFF_LOOPBACK; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE; dev->lltx = true; + dev->netns_local = true; netif_keep_dst(dev); dev->hw_features = NETIF_F_GSO_SOFTWARE; dev->features = NETIF_F_SG | NETIF_F_FRAGLIST @@ -180,7 +181,6 @@ static void gen_lo_setup(struct net_device *dev, | NETIF_F_RXCSUM | NETIF_F_SCTP_CRC | NETIF_F_HIGHDMA - | NETIF_F_NETNS_LOCAL | NETIF_F_VLAN_CHALLENGED | NETIF_F_LOOPBACK; dev->ethtool_ops = eth_ops; diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c index 06728385a35f..54c8b9d5b5fc 100644 --- a/drivers/net/net_failover.c +++ b/drivers/net/net_failover.c @@ -734,7 +734,7 @@ struct failover *net_failover_create(struct net_device *standby_dev) failover_dev->lltx = true; /* Don't allow failover devices to change network namespaces. */ - failover_dev->features |= NETIF_F_NETNS_LOCAL; + failover_dev->netns_local = true; failover_dev->hw_features = FAILOVER_VLAN_FEATURES | NETIF_F_HW_VLAN_CTAG_TX | diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c index 1d1bad3cedc2..18191d5a8bd4 100644 --- a/drivers/net/team/team_core.c +++ b/drivers/net/team/team_core.c @@ -2191,10 +2191,10 @@ static void team_setup(struct net_device *dev) dev->priv_flags |= IFF_UNICAST_FLT | IFF_LIVE_ADDR_CHANGE; dev->lltx = true; - dev->features |= NETIF_F_GRO; - /* Don't allow team devices to change network namespaces. */ - dev->features |= NETIF_F_NETNS_LOCAL; + dev->netns_local = true; + + dev->features |= NETIF_F_GRO; dev->hw_features = TEAM_VLAN_FEATURES | NETIF_F_HW_VLAN_CTAG_RX | diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index b1d4ef538995..4d8ccaf9a2b4 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -1638,7 +1638,7 @@ static void vrf_setup(struct net_device *dev) dev->lltx = true; /* don't allow vrf devices to change network namespaces. */ - dev->features |= NETIF_F_NETNS_LOCAL; + dev->netns_local = true; /* does not make sense for a VLAN to be added to a vrf device */ dev->features |= NETIF_F_VLAN_CHALLENGED; diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index a2e20b517584..d5a3836f4793 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -25,7 +25,7 @@ enum { NETIF_F_VLAN_CHALLENGED_BIT, /* Device cannot handle VLAN packets */ NETIF_F_GSO_BIT, /* Enable software GSO. */ __UNUSED_NETIF_F_12, - NETIF_F_NETNS_LOCAL_BIT, /* Does not change network namespaces */ + __UNUSED_NETIF_F_13, NETIF_F_GRO_BIT, /* Generic receive offload */ NETIF_F_LRO_BIT, /* large receive offload */ @@ -121,7 +121,6 @@ enum { #define NETIF_F_IPV6_CSUM __NETIF_F(IPV6_CSUM) #define NETIF_F_LOOPBACK __NETIF_F(LOOPBACK) #define NETIF_F_LRO __NETIF_F(LRO) -#define NETIF_F_NETNS_LOCAL __NETIF_F(NETNS_LOCAL) #define NETIF_F_NOCACHE_COPY __NETIF_F(NOCACHE_COPY) #define NETIF_F_NTUPLE __NETIF_F(NTUPLE) #define NETIF_F_RXCSUM __NETIF_F(RXCSUM) @@ -190,8 +189,7 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start) /* Features valid for ethtool to change */ /* = all defined minus driver/device-class-related */ -#define NETIF_F_NEVER_CHANGE (NETIF_F_VLAN_CHALLENGED | \ - NETIF_F_NETNS_LOCAL) +#define NETIF_F_NEVER_CHANGE NETIF_F_VLAN_CHALLENGED /* remember that ((t)1 << t_BITS) is undefined in C99 */ #define NETIF_F_ETHTOOL_BITS ((__NETIF_F_BIT(NETDEV_FEATURE_COUNT - 1) | \ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e22ca5e07490..a698e2402420 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1968,6 +1968,7 @@ enum netdev_reg_state { * regardless of source, even if those aren't * HWTSTAMP_SOURCE_NETDEV * @change_proto_down: device supports setting carrier via IFLA_PROTO_DOWN + * @netns_local: interface can't change network namespaces * * @net_notifier_list: List of per-net netdev notifier block * that follow this device when it is moved @@ -2361,6 +2362,7 @@ struct net_device { /* priv_flags_slow, ungrouped to save space */ unsigned long see_all_hwtstamp_requests:1; unsigned long change_proto_down:1; + unsigned long netns_local:1; struct list_head net_notifier_list; diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index e791a73ef901..2758aba47a2f 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -1020,9 +1020,10 @@ static void batadv_softif_init_early(struct net_device *dev) dev->netdev_ops = &batadv_netdev_ops; dev->needs_free_netdev = true; dev->priv_destructor = batadv_softif_free; - dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_NETNS_LOCAL; + dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; dev->priv_flags |= IFF_NO_QUEUE; dev->lltx = true; + dev->netns_local = true; /* can't call min_mtu, because the needed variables * have not been initialized yet diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index a6d25113dfb1..26b79feb385d 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -488,9 +488,10 @@ void br_dev_setup(struct net_device *dev) SET_NETDEV_DEVTYPE(dev, &br_type); dev->priv_flags = IFF_EBRIDGE | IFF_NO_QUEUE; dev->lltx = true; + dev->netns_local = true; - dev->features = COMMON_FEATURES | NETIF_F_NETNS_LOCAL | - NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; + dev->features = COMMON_FEATURES | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX; dev->hw_features = COMMON_FEATURES | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; dev->vlan_features = COMMON_FEATURES; diff --git a/net/core/dev.c b/net/core/dev.c index 56aed88ceadf..98bb5f890b88 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -11487,7 +11487,7 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, /* Don't allow namespace local devices to be moved. */ err = -EINVAL; - if (dev->features & NETIF_F_NETNS_LOCAL) + if (dev->netns_local) goto out; /* Ensure the device has been registered */ @@ -11869,7 +11869,7 @@ static void __net_exit default_device_exit_net(struct net *net) char fb_name[IFNAMSIZ]; /* Ignore unmoveable devices (i.e. loopback) */ - if (dev->features & NETIF_F_NETNS_LOCAL) + if (dev->netns_local) continue; /* Leave virtual devices for the generic cleanup */ diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 447fc80e1b00..ca8e64162104 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -25,7 +25,6 @@ const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = { [NETIF_F_HW_VLAN_STAG_FILTER_BIT] = "rx-vlan-stag-filter", [NETIF_F_VLAN_CHALLENGED_BIT] = "vlan-challenged", [NETIF_F_GSO_BIT] = "tx-generic-segmentation", - [NETIF_F_NETNS_LOCAL_BIT] = "netns-local", [NETIF_F_GRO_BIT] = "rx-gro", [NETIF_F_GRO_HW_BIT] = "rx-gro-hw", [NETIF_F_LRO_BIT] = "rx-lro", diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index d4c783076662..a06e790042e2 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -556,6 +556,10 @@ void hsr_dev_setup(struct net_device *dev) dev->priv_flags |= IFF_NO_QUEUE | IFF_DISABLE_NETPOLL; /* Prevent recursive tx locking */ dev->lltx = true; + /* Not sure about this. Taken from bridge code. netdevice.h says + * it means "Does not change network namespaces". + */ + dev->netns_local = true; dev->needs_free_netdev = true; @@ -569,10 +573,6 @@ void hsr_dev_setup(struct net_device *dev) * hsr_header_create() etc. */ dev->features |= NETIF_F_VLAN_CHALLENGED; - /* Not sure about this. Taken from bridge code. netdev_features.h says - * it means "Does not change network namespaces". - */ - dev->features |= NETIF_F_NETNS_LOCAL; } /* Return true if dev is a HSR master; return false otherwise. diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index 77b4e92027c5..175efd860f7b 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -116,7 +116,7 @@ static void lowpan_setup(struct net_device *ldev) ldev->netdev_ops = &lowpan_netdev_ops; ldev->header_ops = &lowpan_header_ops; ldev->needs_free_netdev = true; - ldev->features |= NETIF_F_NETNS_LOCAL; + ldev->netns_local = true; } static int lowpan_validate(struct nlattr *tb[], struct nlattr *data[], diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c index 60e8fff1347e..88adb04e4072 100644 --- a/net/ieee802154/core.c +++ b/net/ieee802154/core.c @@ -226,11 +226,11 @@ int cfg802154_switch_netns(struct cfg802154_registered_device *rdev, list_for_each_entry(wpan_dev, &rdev->wpan_dev_list, list) { if (!wpan_dev->netdev) continue; - wpan_dev->netdev->features &= ~NETIF_F_NETNS_LOCAL; + wpan_dev->netdev->netns_local = false; err = dev_change_net_namespace(wpan_dev->netdev, net, "wpan%d"); if (err) break; - wpan_dev->netdev->features |= NETIF_F_NETNS_LOCAL; + wpan_dev->netdev->netns_local = true; } if (err) { @@ -242,11 +242,11 @@ int cfg802154_switch_netns(struct cfg802154_registered_device *rdev, list) { if (!wpan_dev->netdev) continue; - wpan_dev->netdev->features &= ~NETIF_F_NETNS_LOCAL; + wpan_dev->netdev->netns_local = false; err = dev_change_net_namespace(wpan_dev->netdev, net, "wpan%d"); WARN_ON(err); - wpan_dev->netdev->features |= NETIF_F_NETNS_LOCAL; + wpan_dev->netdev->netns_local = true; } return err; @@ -291,7 +291,7 @@ static int cfg802154_netdev_notifier_call(struct notifier_block *nb, switch (state) { /* TODO NETDEV_DEVTYPE */ case NETDEV_REGISTER: - dev->features |= NETIF_F_NETNS_LOCAL; + dev->netns_local = true; wpan_dev->identifier = ++rdev->wpan_dev_id; list_add_rcu(&wpan_dev->list, &rdev->wpan_dev_list); rdev->devlist_generation++; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 0cd2f3de100c..18964394d6bd 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -1161,7 +1161,7 @@ int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id, * Allowing to move it to another netns is clearly unsafe. */ if (!IS_ERR(itn->fb_tunnel_dev)) { - itn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL; + itn->fb_tunnel_dev->netns_local = true; itn->fb_tunnel_dev->mtu = ip_tunnel_bind_dev(itn->fb_tunnel_dev); ip_tunnel_add(itn, netdev_priv(itn->fb_tunnel_dev)); itn->type = itn->fb_tunnel_dev->type; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index b0eda745e3bc..f1a43199551b 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -537,7 +537,7 @@ static void reg_vif_setup(struct net_device *dev) dev->flags = IFF_NOARP; dev->netdev_ops = ®_vif_netdev_ops; dev->needs_free_netdev = true; - dev->features |= NETIF_F_NETNS_LOCAL; + dev->netns_local = true; } static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt) diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 08beab638bda..235808cfec70 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1621,8 +1621,7 @@ static int __net_init ip6gre_init_net(struct net *net) /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. */ - ign->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL; - + ign->fb_tunnel_dev->netns_local = true; ip6gre_fb_tunnel_init(ign->fb_tunnel_dev); ign->fb_tunnel_dev->rtnl_link_ops = &ip6gre_link_ops; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index cbef0fcece71..ec51ab5063e8 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -2258,7 +2258,7 @@ static int __net_init ip6_tnl_init_net(struct net *net) /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. */ - ip6n->fb_tnl_dev->features |= NETIF_F_NETNS_LOCAL; + ip6n->fb_tnl_dev->netns_local = true; err = ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev); if (err < 0) diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index e3ee93c562c3..2ce4ae0d8dc3 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -640,7 +640,7 @@ static void reg_vif_setup(struct net_device *dev) dev->flags = IFF_NOARP; dev->netdev_ops = ®_vif_netdev_ops; dev->needs_free_netdev = true; - dev->features |= NETIF_F_NETNS_LOCAL; + dev->netns_local = true; } static struct net_device *ip6mr_reg_vif(struct net *net, struct mr_table *mrt) diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 58306522fb1e..16b90a24c9ba 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1856,7 +1856,7 @@ static int __net_init sit_init_net(struct net *net) /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. */ - sitn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL; + sitn->fb_tunnel_dev->netns_local = true; err = register_netdev(sitn->fb_tunnel_dev); if (err) diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c index 3a369a31c5cc..5858d65ea1a9 100644 --- a/net/openvswitch/vport-internal_dev.c +++ b/net/openvswitch/vport-internal_dev.c @@ -149,7 +149,7 @@ static struct vport *internal_dev_create(const struct vport_parms *parms) /* Restrict bridge port to current netns. */ if (vport->port_no == OVSP_LOCAL) - vport->dev->features |= NETIF_F_NETNS_LOCAL; + vport->dev->netns_local = true; rtnl_lock(); err = register_netdevice(vport->dev); diff --git a/net/wireless/core.c b/net/wireless/core.c index 4d5d351bd0b5..661adfc77644 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -165,11 +165,11 @@ int cfg80211_switch_netns(struct cfg80211_registered_device *rdev, list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { if (!wdev->netdev) continue; - wdev->netdev->features &= ~NETIF_F_NETNS_LOCAL; + wdev->netdev->netns_local = false; err = dev_change_net_namespace(wdev->netdev, net, "wlan%d"); if (err) break; - wdev->netdev->features |= NETIF_F_NETNS_LOCAL; + wdev->netdev->netns_local = true; } if (err) { @@ -181,11 +181,11 @@ int cfg80211_switch_netns(struct cfg80211_registered_device *rdev, list) { if (!wdev->netdev) continue; - wdev->netdev->features &= ~NETIF_F_NETNS_LOCAL; + wdev->netdev->netns_local = false; err = dev_change_net_namespace(wdev->netdev, net, "wlan%d"); WARN_ON(err); - wdev->netdev->features |= NETIF_F_NETNS_LOCAL; + wdev->netdev->netns_local = true; } return err; @@ -1473,7 +1473,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, SET_NETDEV_DEVTYPE(dev, &wiphy_type); wdev->netdev = dev; /* can only change netns with wiphy */ - dev->features |= NETIF_F_NETNS_LOCAL; + dev->netns_local = true; cfg80211_init_wdev(wdev); break; diff --git a/tools/testing/selftests/net/forwarding/README b/tools/testing/selftests/net/forwarding/README index 7fdb6a9ca543..a652429bfd53 100644 --- a/tools/testing/selftests/net/forwarding/README +++ b/tools/testing/selftests/net/forwarding/README @@ -6,7 +6,7 @@ to easily create and test complex environments. Unfortunately, these namespaces can not be used with actual switching ASICs, as their ports can not be migrated to other network namespaces -(NETIF_F_NETNS_LOCAL) and most of them probably do not support the +(dev->netns_local) and most of them probably do not support the L1-separation provided by namespaces. However, a similar kind of flexibility can be achieved by using VRFs and -- cgit v1.2.3 From 782dbbf589cd9082effaec522e3f1b4ce1594803 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Thu, 29 Aug 2024 14:33:39 +0200 Subject: netdev_features: convert NETIF_F_FCOE_MTU to dev->fcoe_mtu Ability to handle maximum FCoE frames of 2158 bytes can never be changed and thus more of an attribute, not a toggleable feature. Move it from netdev_features_t to "cold" priv flags (bitfield bool) and free yet another feature bit. Signed-off-by: Alexander Lobakin Signed-off-by: Paolo Abeni --- Documentation/networking/net_cachelines/net_device.rst | 1 + drivers/net/ethernet/chelsio/cxgb4/cxgb4_fcoe.c | 6 ++---- drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c | 4 ++-- drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 11 ++++------- drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c | 4 ++-- drivers/scsi/fcoe/fcoe.c | 4 ++-- include/linux/netdev_features.h | 6 ++---- include/linux/netdevice.h | 2 ++ net/8021q/vlan_dev.c | 1 + net/ethtool/common.c | 1 - 12 files changed, 20 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst index e649d8e9556f..56d4bbaf8a2c 100644 --- a/Documentation/networking/net_cachelines/net_device.rst +++ b/Documentation/networking/net_cachelines/net_device.rst @@ -167,6 +167,7 @@ unsigned:1 threaded - unsigned_long:1 see_all_hwtstamp_requests unsigned_long:1 change_proto_down unsigned_long:1 netns_local +unsigned_long:1 fcoe_mtu struct_list_head net_notifier_list struct_macsec_ops* macsec_ops struct_udp_tunnel_nic_info* udp_tunnel_nic_info diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_fcoe.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_fcoe.c index 33b2c0c45509..f6f745f5c022 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_fcoe.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_fcoe.c @@ -81,8 +81,7 @@ int cxgb_fcoe_enable(struct net_device *netdev) netdev->features |= NETIF_F_FCOE_CRC; netdev->vlan_features |= NETIF_F_FCOE_CRC; - netdev->features |= NETIF_F_FCOE_MTU; - netdev->vlan_features |= NETIF_F_FCOE_MTU; + netdev->fcoe_mtu = true; netdev_features_change(netdev); @@ -112,8 +111,7 @@ int cxgb_fcoe_disable(struct net_device *netdev) netdev->features &= ~NETIF_F_FCOE_CRC; netdev->vlan_features &= ~NETIF_F_FCOE_CRC; - netdev->features &= ~NETIF_F_FCOE_MTU; - netdev->vlan_features &= ~NETIF_F_FCOE_MTU; + netdev->fcoe_mtu = false; netdev_features_change(netdev); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c index e85f7d2e8810..f2709b10c2e5 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c @@ -317,7 +317,7 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev) int max_frame = adapter->netdev->mtu + ETH_HLEN + ETH_FCS_LEN; #ifdef IXGBE_FCOE - if (adapter->netdev->features & NETIF_F_FCOE_MTU) + if (adapter->netdev->fcoe_mtu) max_frame = max(max_frame, IXGBE_FCOE_JUMBO_FRAME_SIZE); #endif diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c index 18d63c8c2ff4..955dced844a9 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c @@ -858,7 +858,7 @@ int ixgbe_fcoe_enable(struct net_device *netdev) /* enable FCoE and notify stack */ adapter->flags |= IXGBE_FLAG_FCOE_ENABLED; - netdev->features |= NETIF_F_FCOE_MTU; + netdev->fcoe_mtu = true; netdev_features_change(netdev); /* release existing queues and reallocate them */ @@ -898,7 +898,7 @@ int ixgbe_fcoe_disable(struct net_device *netdev) /* disable FCoE and notify stack */ adapter->flags &= ~IXGBE_FLAG_FCOE_ENABLED; - netdev->features &= ~NETIF_F_FCOE_MTU; + netdev->fcoe_mtu = false; netdev_features_change(netdev); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c index 0ee943db3dc9..16fa621ce0ff 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c @@ -981,7 +981,7 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter, set_bit(__IXGBE_RX_CSUM_UDP_ZERO_ERR, &ring->state); #ifdef IXGBE_FCOE - if (adapter->netdev->features & NETIF_F_FCOE_MTU) { + if (adapter->netdev->fcoe_mtu) { struct ixgbe_ring_feature *f; f = &adapter->ring_feature[RING_F_FCOE]; if ((rxr_idx >= f->offset) && diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 8057cef61f39..8b8404d8c946 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -5079,7 +5079,7 @@ static void ixgbe_configure_dcb(struct ixgbe_adapter *adapter) netif_set_tso_max_size(adapter->netdev, 32768); #ifdef IXGBE_FCOE - if (adapter->netdev->features & NETIF_F_FCOE_MTU) + if (adapter->netdev->fcoe_mtu) max_frame = max(max_frame, IXGBE_FCOE_JUMBO_FRAME_SIZE); #endif @@ -5136,8 +5136,7 @@ static int ixgbe_hpbthresh(struct ixgbe_adapter *adapter, int pb) #ifdef IXGBE_FCOE /* FCoE traffic class uses FCOE jumbo frames */ - if ((dev->features & NETIF_F_FCOE_MTU) && - (tc < IXGBE_FCOE_JUMBO_FRAME_SIZE) && + if (dev->fcoe_mtu && tc < IXGBE_FCOE_JUMBO_FRAME_SIZE && (pb == ixgbe_fcoe_get_tc(adapter))) tc = IXGBE_FCOE_JUMBO_FRAME_SIZE; #endif @@ -5197,8 +5196,7 @@ static int ixgbe_lpbthresh(struct ixgbe_adapter *adapter, int pb) #ifdef IXGBE_FCOE /* FCoE traffic class uses FCOE jumbo frames */ - if ((dev->features & NETIF_F_FCOE_MTU) && - (tc < IXGBE_FCOE_JUMBO_FRAME_SIZE) && + if (dev->fcoe_mtu && tc < IXGBE_FCOE_JUMBO_FRAME_SIZE && (pb == netdev_get_prio_tc_map(dev, adapter->fcoe.up))) tc = IXGBE_FCOE_JUMBO_FRAME_SIZE; #endif @@ -11096,8 +11094,7 @@ skip_sriov: NETIF_F_FCOE_CRC; netdev->vlan_features |= NETIF_F_FSO | - NETIF_F_FCOE_CRC | - NETIF_F_FCOE_MTU; + NETIF_F_FCOE_CRC; } #endif /* IXGBE_FCOE */ if (adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index fcfd0a075eee..e71715f5da22 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -495,7 +495,7 @@ static int ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 max_frame, u32 vf int err = 0; #ifdef CONFIG_FCOE - if (dev->features & NETIF_F_FCOE_MTU) + if (dev->fcoe_mtu) pf_max_frame = max_t(int, pf_max_frame, IXGBE_FCOE_JUMBO_FRAME_SIZE); @@ -857,7 +857,7 @@ static void ixgbe_set_vf_rx_tx(struct ixgbe_adapter *adapter, int vf) int pf_max_frame = dev->mtu + ETH_HLEN; #if IS_ENABLED(CONFIG_FCOE) - if (dev->features & NETIF_F_FCOE_MTU) + if (dev->fcoe_mtu) pf_max_frame = max_t(int, pf_max_frame, IXGBE_FCOE_JUMBO_FRAME_SIZE); #endif /* CONFIG_FCOE */ diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c index f1429f270170..39aec710660c 100644 --- a/drivers/scsi/fcoe/fcoe.c +++ b/drivers/scsi/fcoe/fcoe.c @@ -722,7 +722,7 @@ static int fcoe_netdev_config(struct fc_lport *lport, struct net_device *netdev) * will return 0, so do this first. */ mfs = netdev->mtu; - if (netdev->features & NETIF_F_FCOE_MTU) { + if (netdev->fcoe_mtu) { mfs = FCOE_MTU; FCOE_NETDEV_DBG(netdev, "Supports FCOE_MTU of %d bytes\n", mfs); } @@ -1863,7 +1863,7 @@ static int fcoe_device_notification(struct notifier_block *notifier, case NETDEV_CHANGE: break; case NETDEV_CHANGEMTU: - if (netdev->features & NETIF_F_FCOE_MTU) + if (netdev->fcoe_mtu) break; mfs = netdev->mtu - (sizeof(struct fcoe_hdr) + sizeof(struct fcoe_crc_eof)); diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index d5a3836f4793..37af2c6e7caf 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -58,7 +58,7 @@ enum { NETIF_F_FCOE_CRC_BIT, /* FCoE CRC32 */ NETIF_F_SCTP_CRC_BIT, /* SCTP checksum offload */ - NETIF_F_FCOE_MTU_BIT, /* Supports max FCoE MTU, 2158 bytes*/ + __UNUSED_NETIF_F_37, NETIF_F_NTUPLE_BIT, /* N-tuple filters supported */ NETIF_F_RXHASH_BIT, /* Receive hashing offload */ NETIF_F_RXCSUM_BIT, /* Receive checksumming offload */ @@ -105,7 +105,6 @@ enum { #define __NETIF_F(name) __NETIF_F_BIT(NETIF_F_##name##_BIT) #define NETIF_F_FCOE_CRC __NETIF_F(FCOE_CRC) -#define NETIF_F_FCOE_MTU __NETIF_F(FCOE_MTU) #define NETIF_F_FRAGLIST __NETIF_F(FRAGLIST) #define NETIF_F_FSO __NETIF_F(FSO) #define NETIF_F_GRO __NETIF_F(GRO) @@ -210,8 +209,7 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start) #define NETIF_F_ALL_TSO (NETIF_F_TSO | NETIF_F_TSO6 | \ NETIF_F_TSO_ECN | NETIF_F_TSO_MANGLEID) -#define NETIF_F_ALL_FCOE (NETIF_F_FCOE_CRC | NETIF_F_FCOE_MTU | \ - NETIF_F_FSO) +#define NETIF_F_ALL_FCOE (NETIF_F_FCOE_CRC | NETIF_F_FSO) /* List of features with software fallbacks. */ #define NETIF_F_GSO_SOFTWARE (NETIF_F_ALL_TSO | NETIF_F_GSO_SCTP | \ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a698e2402420..ca5f0dda733b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1969,6 +1969,7 @@ enum netdev_reg_state { * HWTSTAMP_SOURCE_NETDEV * @change_proto_down: device supports setting carrier via IFLA_PROTO_DOWN * @netns_local: interface can't change network namespaces + * @fcoe_mtu: device supports maximum FCoE MTU, 2158 bytes * * @net_notifier_list: List of per-net netdev notifier block * that follow this device when it is moved @@ -2363,6 +2364,7 @@ struct net_device { unsigned long see_all_hwtstamp_requests:1; unsigned long change_proto_down:1; unsigned long netns_local:1; + unsigned long fcoe_mtu:1; struct list_head net_notifier_list; diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 3ca485537d77..09b46b057ab2 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -571,6 +571,7 @@ static int vlan_dev_init(struct net_device *dev) dev->features |= dev->hw_features; dev->lltx = true; + dev->fcoe_mtu = true; netif_inherit_tso_max(dev, real_dev); if (dev->features & NETIF_F_VLAN_FEATURES) netdev_warn(real_dev, "VLAN features are set incorrectly. Q-in-Q configurations may not work correctly.\n"); diff --git a/net/ethtool/common.c b/net/ethtool/common.c index ca8e64162104..00f93c58b319 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -50,7 +50,6 @@ const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = { [NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc", [NETIF_F_SCTP_CRC_BIT] = "tx-checksum-sctp", - [NETIF_F_FCOE_MTU_BIT] = "fcoe-mtu", [NETIF_F_NTUPLE_BIT] = "rx-ntuple-filter", [NETIF_F_RXHASH_BIT] = "rx-hashing", [NETIF_F_RXCSUM_BIT] = "rx-checksum", -- cgit v1.2.3 From a61fec1c87be682b5c0fdba6074649c469c675a3 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Thu, 29 Aug 2024 14:33:40 +0200 Subject: netdev_features: remove NETIF_F_ALL_FCOE NETIF_F_ALL_FCOE is used only in vlan_dev.c, 2 times. Now that it's only 2 bits, open-code it and remove the definition from netdev_features.h. Suggested-by: Jakub Kicinski Signed-off-by: Alexander Lobakin Signed-off-by: Paolo Abeni --- include/linux/netdev_features.h | 2 -- net/8021q/vlan_dev.c | 5 +++-- 2 files changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 37af2c6e7caf..66e7d26b70a4 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -209,8 +209,6 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start) #define NETIF_F_ALL_TSO (NETIF_F_TSO | NETIF_F_TSO6 | \ NETIF_F_TSO_ECN | NETIF_F_TSO_MANGLEID) -#define NETIF_F_ALL_FCOE (NETIF_F_FCOE_CRC | NETIF_F_FSO) - /* List of features with software fallbacks. */ #define NETIF_F_GSO_SOFTWARE (NETIF_F_ALL_TSO | NETIF_F_GSO_SCTP | \ NETIF_F_GSO_UDP_L4 | NETIF_F_GSO_FRAGLIST) diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 09b46b057ab2..458040e8a0e0 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -564,7 +564,7 @@ static int vlan_dev_init(struct net_device *dev) NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL | NETIF_F_HIGHDMA | NETIF_F_SCTP_CRC | - NETIF_F_ALL_FCOE; + NETIF_F_FCOE_CRC | NETIF_F_FSO; if (real_dev->vlan_features & NETIF_F_HW_MACSEC) dev->hw_features |= NETIF_F_HW_MACSEC; @@ -576,7 +576,8 @@ static int vlan_dev_init(struct net_device *dev) if (dev->features & NETIF_F_VLAN_FEATURES) netdev_warn(real_dev, "VLAN features are set incorrectly. Q-in-Q configurations may not work correctly.\n"); - dev->vlan_features = real_dev->vlan_features & ~NETIF_F_ALL_FCOE; + dev->vlan_features = real_dev->vlan_features & + ~(NETIF_F_FCOE_CRC | NETIF_F_FSO); dev->hw_enc_features = vlan_tnl_features(real_dev); dev->mpls_features = real_dev->mpls_features; -- cgit v1.2.3 From b45ed06f46737f8c2ee65698f4305409f2386674 Mon Sep 17 00:00:00 2001 From: Zijun Hu Date: Tue, 13 Aug 2024 22:19:32 +0800 Subject: drivers/base: Introduce device_match_t for device finding APIs There are several drivers/base APIs for finding a specific device, and they currently use the following good type for the @match parameter: int (*match)(struct device *dev, const void *data) Since these operations do not modify the caller-provided @*data, this type is worthy of a dedicated typedef: typedef int (*device_match_t)(struct device *dev, const void *data) Advantages of using device_match_t: - Shorter API declarations and definitions - Prevent further APIs from using a bad type for @match So introduce device_match_t and apply it to the existing (bus|class|driver|auxiliary)_find_device() APIs. Signed-off-by: Zijun Hu Link: https://lore.kernel.org/r/20240813-dev_match_api-v3-1-6c6878a99b9f@quicinc.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/auxiliary.c | 2 +- drivers/base/bus.c | 2 +- drivers/base/class.c | 3 +-- drivers/base/driver.c | 2 +- include/linux/auxiliary_bus.h | 2 +- include/linux/device/bus.h | 6 ++++-- include/linux/device/class.h | 2 +- include/linux/device/driver.h | 2 +- 8 files changed, 11 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/auxiliary.c b/drivers/base/auxiliary.c index 54b92839e05c..7823888af4f6 100644 --- a/drivers/base/auxiliary.c +++ b/drivers/base/auxiliary.c @@ -352,7 +352,7 @@ EXPORT_SYMBOL_GPL(__auxiliary_device_add); */ struct auxiliary_device *auxiliary_find_device(struct device *start, const void *data, - int (*match)(struct device *dev, const void *data)) + device_match_t match) { struct device *dev; diff --git a/drivers/base/bus.c b/drivers/base/bus.c index abf090ace833..657c93c38b0d 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -391,7 +391,7 @@ EXPORT_SYMBOL_GPL(bus_for_each_dev); */ struct device *bus_find_device(const struct bus_type *bus, struct device *start, const void *data, - int (*match)(struct device *dev, const void *data)) + device_match_t match) { struct subsys_private *sp = bus_to_subsys(bus); struct klist_iter i; diff --git a/drivers/base/class.c b/drivers/base/class.c index 7b38fdf8e1d7..ae22fa992c04 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -433,8 +433,7 @@ EXPORT_SYMBOL_GPL(class_for_each_device); * code. There's no locking restriction. */ struct device *class_find_device(const struct class *class, const struct device *start, - const void *data, - int (*match)(struct device *, const void *)) + const void *data, device_match_t match) { struct subsys_private *sp = class_to_subsys(class); struct class_dev_iter iter; diff --git a/drivers/base/driver.c b/drivers/base/driver.c index 88c6fd1f1992..b4eb5b89c4ee 100644 --- a/drivers/base/driver.c +++ b/drivers/base/driver.c @@ -150,7 +150,7 @@ EXPORT_SYMBOL_GPL(driver_for_each_device); */ struct device *driver_find_device(const struct device_driver *drv, struct device *start, const void *data, - int (*match)(struct device *dev, const void *data)) + device_match_t match) { struct klist_iter i; struct device *dev; diff --git a/include/linux/auxiliary_bus.h b/include/linux/auxiliary_bus.h index 662b8ae54b6a..31762324bcc9 100644 --- a/include/linux/auxiliary_bus.h +++ b/include/linux/auxiliary_bus.h @@ -271,6 +271,6 @@ void auxiliary_driver_unregister(struct auxiliary_driver *auxdrv); struct auxiliary_device *auxiliary_find_device(struct device *start, const void *data, - int (*match)(struct device *dev, const void *data)); + device_match_t match); #endif /* _AUXILIARY_BUS_H_ */ diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 807831d6bf0f..cdc4757217f9 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -126,6 +126,9 @@ struct bus_attribute { int __must_check bus_create_file(const struct bus_type *bus, struct bus_attribute *attr); void bus_remove_file(const struct bus_type *bus, struct bus_attribute *attr); +/* Matching function type for drivers/base APIs to find a specific device */ +typedef int (*device_match_t)(struct device *dev, const void *data); + /* Generic device matching functions that all busses can use to match with */ int device_match_name(struct device *dev, const void *name); int device_match_of_node(struct device *dev, const void *np); @@ -139,8 +142,7 @@ int device_match_any(struct device *dev, const void *unused); int bus_for_each_dev(const struct bus_type *bus, struct device *start, void *data, int (*fn)(struct device *dev, void *data)); struct device *bus_find_device(const struct bus_type *bus, struct device *start, - const void *data, - int (*match)(struct device *dev, const void *data)); + const void *data, device_match_t match); /** * bus_find_device_by_name - device iterator for locating a particular device * of a specific name. diff --git a/include/linux/device/class.h b/include/linux/device/class.h index c576b49c55c2..518c9c83d64b 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -95,7 +95,7 @@ void class_dev_iter_exit(struct class_dev_iter *iter); int class_for_each_device(const struct class *class, const struct device *start, void *data, int (*fn)(struct device *dev, void *data)); struct device *class_find_device(const struct class *class, const struct device *start, - const void *data, int (*match)(struct device *, const void *)); + const void *data, device_match_t match); /** * class_find_device_by_name - device iterator for locating a particular device diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h index 1fc8b68786de..5c04b8e3833b 100644 --- a/include/linux/device/driver.h +++ b/include/linux/device/driver.h @@ -157,7 +157,7 @@ int __must_check driver_for_each_device(struct device_driver *drv, struct device void *data, int (*fn)(struct device *dev, void *)); struct device *driver_find_device(const struct device_driver *drv, struct device *start, const void *data, - int (*match)(struct device *dev, const void *data)); + device_match_t match); /** * driver_find_device_by_name - device iterator for locating a particular device -- cgit v1.2.3 From 24e041e1e48d06f25a12caaf73728a4ec2e511fe Mon Sep 17 00:00:00 2001 From: Kunwu Chan Date: Fri, 23 Aug 2024 15:55:44 +0800 Subject: platform: Make platform_bus_type constant Since commit d492cc2573a0 ("driver core: device.h: make struct bus_type a const *"), the driver core can properly handle constant struct bus_type, move the platform_bus_type variable to be a constant structure as well, placing it into read-only memory which can not be modified at runtime. Cc: Greg Kroah-Hartman Suggested-by: Greg Kroah-Hartman Signed-off-by: Kunwu Chan Link: https://lore.kernel.org/r/20240823075544.144426-1-kunwu.chan@linux.dev Signed-off-by: Greg Kroah-Hartman --- drivers/base/platform.c | 2 +- include/linux/platform_device.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 4c3ee6521ba5..6f2a33722c52 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -1474,7 +1474,7 @@ static const struct dev_pm_ops platform_dev_pm_ops = { USE_PLATFORM_PM_SLEEP_OPS }; -struct bus_type platform_bus_type = { +const struct bus_type platform_bus_type = { .name = "platform", .dev_groups = platform_dev_groups, .match = platform_match, diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index d422db6eec63..7132623e4658 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -52,7 +52,7 @@ struct platform_device { extern int platform_device_register(struct platform_device *); extern void platform_device_unregister(struct platform_device *); -extern struct bus_type platform_bus_type; +extern const struct bus_type platform_bus_type; extern struct device platform_bus; extern struct resource *platform_get_resource(struct platform_device *, -- cgit v1.2.3 From 8064952c65045f05ee2671fe437770e50c151776 Mon Sep 17 00:00:00 2001 From: Stuart Hayes Date: Thu, 22 Aug 2024 15:28:04 -0500 Subject: driver core: shut down devices asynchronously Add code to allow asynchronous shutdown of devices, ensuring that each device is shut down before its parents & suppliers. Only devices with drivers that have async_shutdown_enable enabled will be shut down asynchronously. This can dramatically reduce system shutdown/reboot time on systems that have multiple devices that take many seconds to shut down (like certain NVMe drives). On one system tested, the shutdown time went from 11 minutes without this patch to 55 seconds with the patch. Signed-off-by: Stuart Hayes Signed-off-by: David Jeffery Reviewed-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Reviewed-by: Keith Busch Tested-by: Keith Busch Link: https://lore.kernel.org/r/20240822202805.6379-4-stuart.w.hayes@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/base.h | 4 ++++ drivers/base/core.c | 54 ++++++++++++++++++++++++++++++++++++++++++- include/linux/device/driver.h | 2 ++ 3 files changed, 59 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/base/base.h b/drivers/base/base.h index 8cf04a557bdb..ea18aa70f151 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -10,6 +10,7 @@ * shared outside of the drivers/base/ directory. * */ +#include #include /** @@ -97,6 +98,8 @@ struct driver_private { * the device; typically because it depends on another driver getting * probed first. * @async_driver - pointer to device driver awaiting probe via async_probe + * @shutdown_after - used during device shutdown to ensure correct shutdown + * ordering. * @device - pointer back to the struct device that this structure is * associated with. * @dead - This device is currently either in the process of or has been @@ -114,6 +117,7 @@ struct device_private { struct list_head deferred_probe; const struct device_driver *async_driver; char *deferred_probe_reason; + async_cookie_t shutdown_after; struct device *device; u8 dead:1; }; diff --git a/drivers/base/core.c b/drivers/base/core.c index 8598421cbb7f..6113bc1092ae 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -9,6 +9,7 @@ */ #include +#include #include #include #include @@ -3524,6 +3525,7 @@ static int device_private_init(struct device *dev) klist_init(&dev->p->klist_children, klist_children_get, klist_children_put); INIT_LIST_HEAD(&dev->p->deferred_probe); + dev->p->shutdown_after = 0; return 0; } @@ -4779,6 +4781,8 @@ out: } EXPORT_SYMBOL_GPL(device_change_owner); +static ASYNC_DOMAIN(sd_domain); + static void shutdown_one_device(struct device *dev) { /* hold lock to avoid race with probe/release */ @@ -4814,12 +4818,34 @@ static void shutdown_one_device(struct device *dev) put_device(dev->parent); } +/** + * shutdown_one_device_async + * @data: the pointer to the struct device to be shutdown + * @cookie: not used + * + * Shuts down one device, after waiting for shutdown_after to complete. + * shutdown_after should be set to the cookie of the last child or consumer + * of this device to be shutdown (if any), or to the cookie of the previous + * device to be shut down for devices that don't enable asynchronous shutdown. + */ +static void shutdown_one_device_async(void *data, async_cookie_t cookie) +{ + struct device *dev = data; + + async_synchronize_cookie_domain(dev->p->shutdown_after + 1, &sd_domain); + + shutdown_one_device(dev); +} + /** * device_shutdown - call ->shutdown() on each device to shutdown. */ void device_shutdown(void) { struct device *dev, *parent; + async_cookie_t cookie = 0; + struct device_link *link; + int idx; wait_for_device_probe(); device_block_probing(); @@ -4850,11 +4876,37 @@ void device_shutdown(void) list_del_init(&dev->kobj.entry); spin_unlock(&devices_kset->list_lock); - shutdown_one_device(dev); + + /* + * Set cookie for devices that will be shut down synchronously + */ + if (!dev->driver || !dev->driver->async_shutdown_enable) + dev->p->shutdown_after = cookie; + + get_device(dev); + get_device(parent); + + cookie = async_schedule_domain(shutdown_one_device_async, + dev, &sd_domain); + /* + * Ensure parent & suppliers wait for this device to shut down + */ + if (parent) { + parent->p->shutdown_after = cookie; + put_device(parent); + } + + idx = device_links_read_lock(); + list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, + device_links_read_lock_held()) + link->supplier->p->shutdown_after = cookie; + device_links_read_unlock(idx); + put_device(dev); spin_lock(&devices_kset->list_lock); } spin_unlock(&devices_kset->list_lock); + async_synchronize_full_domain(&sd_domain); } /* diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h index 5c04b8e3833b..14c9211b82d6 100644 --- a/include/linux/device/driver.h +++ b/include/linux/device/driver.h @@ -56,6 +56,7 @@ enum probe_type { * @mod_name: Used for built-in modules. * @suppress_bind_attrs: Disables bind/unbind via sysfs. * @probe_type: Type of the probe (synchronous or asynchronous) to use. + * @async_shutdown_enable: Enables devices to be shutdown asynchronously. * @of_match_table: The open firmware table. * @acpi_match_table: The ACPI match table. * @probe: Called to query the existence of a specific device, @@ -102,6 +103,7 @@ struct device_driver { bool suppress_bind_attrs; /* disables bind/unbind via sysfs */ enum probe_type probe_type; + bool async_shutdown_enable; const struct of_device_id *of_match_table; const struct acpi_device_id *acpi_match_table; -- cgit v1.2.3 From 8ab0f4605d5ce3c0d386b3828b07719f1e8e0505 Mon Sep 17 00:00:00 2001 From: Kunwu Chan Date: Fri, 23 Aug 2024 14:24:40 +0800 Subject: bus: fsl-mc: make fsl_mc_bus_type const Since commit d492cc2573a0 ("driver core: device.h: make struct bus_type a const *"), the driver core can properly handle constant struct bus_type, move the fsl_mc_bus_type variable to be a constant structure as well, placing it into read-only memory which can not be modified at runtime. Cc: Greg Kroah-Hartman Suggested-by: Greg Kroah-Hartman Signed-off-by: Kunwu Chan Acked-by: Christophe Leroy # for Link: https://lore.kernel.org/r/20240823062440.113628-1-kunwu.chan@linux.dev Signed-off-by: Greg Kroah-Hartman --- drivers/bus/fsl-mc/fsl-mc-bus.c | 2 +- include/linux/fsl/mc.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c index dd68b8191a0a..930d8a3ba722 100644 --- a/drivers/bus/fsl-mc/fsl-mc-bus.c +++ b/drivers/bus/fsl-mc/fsl-mc-bus.c @@ -309,7 +309,7 @@ static struct attribute *fsl_mc_bus_attrs[] = { ATTRIBUTE_GROUPS(fsl_mc_bus); -struct bus_type fsl_mc_bus_type = { +const struct bus_type fsl_mc_bus_type = { .name = "fsl-mc", .match = fsl_mc_bus_match, .uevent = fsl_mc_bus_uevent, diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index 083c860fd28e..c90ec889bfc2 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -436,7 +436,7 @@ void fsl_mc_free_irqs(struct fsl_mc_device *mc_dev); struct fsl_mc_device *fsl_mc_get_endpoint(struct fsl_mc_device *mc_dev, u16 if_id); -extern struct bus_type fsl_mc_bus_type; +extern const struct bus_type fsl_mc_bus_type; extern struct device_type fsl_mc_bus_dprc_type; extern struct device_type fsl_mc_bus_dpni_type; -- cgit v1.2.3 From 4c0a6a0ac902dbf184ae7be1f1fce225cc0b7380 Mon Sep 17 00:00:00 2001 From: Chanwoo Lee Date: Thu, 29 Aug 2024 11:47:09 +0900 Subject: mmc: core: Replace the argument of mmc_sd_switch() with defines Replace with already defined values for readability. While at it, let's also change the mode-parameter from an int to bool, as the only used values are 0 or 1. Signed-off-by: Chanwoo Lee Link: https://lore.kernel.org/r/20240829024709.402285-1-cw9316.lee@samsung.com Signed-off-by: Ulf Hansson --- drivers/mmc/core/sd.c | 13 ++++++++----- drivers/mmc/core/sd_ops.c | 3 +-- include/linux/mmc/host.h | 3 ++- 3 files changed, 11 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c index ee37ad14e79e..d7318c2647da 100644 --- a/drivers/mmc/core/sd.c +++ b/drivers/mmc/core/sd.c @@ -346,7 +346,7 @@ static int mmc_read_switch(struct mmc_card *card) * The argument does not matter, as the support bits do not * change with the arguments. */ - err = mmc_sd_switch(card, 0, 0, 0, status); + err = mmc_sd_switch(card, SD_SWITCH_CHECK, 0, 0, status); if (err) { /* * If the host or the card can't do the switch, @@ -402,7 +402,8 @@ int mmc_sd_switch_hs(struct mmc_card *card) if (!status) return -ENOMEM; - err = mmc_sd_switch(card, 1, 0, HIGH_SPEED_BUS_SPEED, status); + err = mmc_sd_switch(card, SD_SWITCH_SET, 0, + HIGH_SPEED_BUS_SPEED, status); if (err) goto out; @@ -434,7 +435,8 @@ static int sd_select_driver_type(struct mmc_card *card, u8 *status) card_drv_type, &drv_type); if (drive_strength) { - err = mmc_sd_switch(card, 1, 2, drive_strength, status); + err = mmc_sd_switch(card, SD_SWITCH_SET, 2, + drive_strength, status); if (err) return err; if ((status[15] & 0xF) != drive_strength) { @@ -514,7 +516,7 @@ static int sd_set_bus_speed_mode(struct mmc_card *card, u8 *status) return 0; } - err = mmc_sd_switch(card, 1, 0, card->sd_bus_speed, status); + err = mmc_sd_switch(card, SD_SWITCH_SET, 0, card->sd_bus_speed, status); if (err) return err; @@ -605,7 +607,8 @@ static int sd_set_current_limit(struct mmc_card *card, u8 *status) current_limit = SD_SET_CURRENT_LIMIT_200; if (current_limit != SD_SET_CURRENT_NO_CHANGE) { - err = mmc_sd_switch(card, 1, 3, current_limit, status); + err = mmc_sd_switch(card, SD_SWITCH_SET, 3, + current_limit, status); if (err) return err; diff --git a/drivers/mmc/core/sd_ops.c b/drivers/mmc/core/sd_ops.c index 8b9b34286ef3..f93c392040ae 100644 --- a/drivers/mmc/core/sd_ops.c +++ b/drivers/mmc/core/sd_ops.c @@ -336,14 +336,13 @@ int mmc_app_send_scr(struct mmc_card *card) return 0; } -int mmc_sd_switch(struct mmc_card *card, int mode, int group, +int mmc_sd_switch(struct mmc_card *card, bool mode, int group, u8 value, u8 *resp) { u32 cmd_args; /* NOTE: caller guarantees resp is heap-allocated */ - mode = !!mode; value &= 0xF; cmd_args = mode << 31 | 0x00FFFFFF; cmd_args &= ~(0xF << (group * 4)); diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index ac01cd1622ef..6a31ed02d3ff 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -648,7 +648,8 @@ static inline void mmc_debugfs_err_stats_inc(struct mmc_host *host, host->err_stats[stat] += 1; } -int mmc_sd_switch(struct mmc_card *card, int mode, int group, u8 value, u8 *resp); +int mmc_sd_switch(struct mmc_card *card, bool mode, int group, + u8 value, u8 *resp); int mmc_send_status(struct mmc_card *card, u32 *status); int mmc_send_tuning(struct mmc_host *host, u32 opcode, int *cmd_error); int mmc_send_abort_tuning(struct mmc_host *host, u32 opcode); -- cgit v1.2.3 From 7df7c204c678e24cd32d33360538670b7b90e330 Mon Sep 17 00:00:00 2001 From: Pankaj Raghav Date: Thu, 22 Aug 2024 15:50:18 +0200 Subject: xfs: enable block size larger than page size support Page cache now has the ability to have a minimum order when allocating a folio which is a prerequisite to add support for block size > page size. Signed-off-by: Pankaj Raghav Signed-off-by: Luis Chamberlain Link: https://lore.kernel.org/r/20240827-xfs-fix-wformat-bs-gt-ps-v1-1-aec6717609e0@kernel.org # fix folded Link: https://lore.kernel.org/r/20240822135018.1931258-11-kernel@pankajraghav.com Reviewed-by: Darrick J. Wong Reviewed-by: Dave Chinner Signed-off-by: Christian Brauner --- fs/xfs/libxfs/xfs_ialloc.c | 5 +++++ fs/xfs/libxfs/xfs_shared.h | 3 +++ fs/xfs/xfs_icache.c | 6 ++++-- fs/xfs/xfs_mount.c | 1 - fs/xfs/xfs_super.c | 28 ++++++++++++++++++++-------- include/linux/pagemap.h | 13 +++++++++++++ 6 files changed, 45 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index 0af5b7a33d05..1921b689888b 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -3033,6 +3033,11 @@ xfs_ialloc_setup_geometry( igeo->ialloc_align = mp->m_dalign; else igeo->ialloc_align = 0; + + if (mp->m_sb.sb_blocksize > PAGE_SIZE) + igeo->min_folio_order = mp->m_sb.sb_blocklog - PAGE_SHIFT; + else + igeo->min_folio_order = 0; } /* Compute the location of the root directory inode that is laid out by mkfs. */ diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h index 2f7413afbf46..33b84a3a83ff 100644 --- a/fs/xfs/libxfs/xfs_shared.h +++ b/fs/xfs/libxfs/xfs_shared.h @@ -224,6 +224,9 @@ struct xfs_ino_geometry { /* precomputed value for di_flags2 */ uint64_t new_diflags2; + /* minimum folio order of a page cache allocation */ + unsigned int min_folio_order; + }; #endif /* __XFS_SHARED_H__ */ diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index cf629302d48e..0fcf235e5023 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -88,7 +88,8 @@ xfs_inode_alloc( /* VFS doesn't initialise i_mode! */ VFS_I(ip)->i_mode = 0; - mapping_set_large_folios(VFS_I(ip)->i_mapping); + mapping_set_folio_min_order(VFS_I(ip)->i_mapping, + M_IGEO(mp)->min_folio_order); XFS_STATS_INC(mp, vn_active); ASSERT(atomic_read(&ip->i_pincount) == 0); @@ -325,7 +326,8 @@ xfs_reinit_inode( inode->i_uid = uid; inode->i_gid = gid; inode->i_state = state; - mapping_set_large_folios(inode->i_mapping); + mapping_set_folio_min_order(inode->i_mapping, + M_IGEO(mp)->min_folio_order); return error; } diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 3949f720b535..c6933440f806 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -134,7 +134,6 @@ xfs_sb_validate_fsb_count( { uint64_t max_bytes; - ASSERT(PAGE_SHIFT >= sbp->sb_blocklog); ASSERT(sbp->sb_blocklog >= BBSHIFT); if (check_shl_overflow(nblocks, sbp->sb_blocklog, &max_bytes)) diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 27e9f749c4c7..e8cc7900911e 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1638,16 +1638,28 @@ xfs_fs_fill_super( goto out_free_sb; } - /* - * Until this is fixed only page-sized or smaller data blocks work. - */ if (mp->m_sb.sb_blocksize > PAGE_SIZE) { - xfs_warn(mp, - "File system with blocksize %d bytes. " - "Only pagesize (%ld) or less will currently work.", + size_t max_folio_size = mapping_max_folio_size_supported(); + + if (!xfs_has_crc(mp)) { + xfs_warn(mp, +"V4 Filesystem with blocksize %d bytes. Only pagesize (%ld) or less is supported.", mp->m_sb.sb_blocksize, PAGE_SIZE); - error = -ENOSYS; - goto out_free_sb; + error = -ENOSYS; + goto out_free_sb; + } + + if (mp->m_sb.sb_blocksize > max_folio_size) { + xfs_warn(mp, +"block size (%u bytes) not supported; Only block size (%zu) or less is supported", + mp->m_sb.sb_blocksize, max_folio_size); + error = -ENOSYS; + goto out_free_sb; + } + + xfs_warn(mp, +"EXPERIMENTAL: V5 Filesystem with Large Block Size (%d bytes) enabled.", + mp->m_sb.sb_blocksize); } /* Ensure this filesystem fits in the page cache limits */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 4cc170949e9c..55b254d951da 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -374,6 +374,19 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) #define MAX_XAS_ORDER (XA_CHUNK_SHIFT * 2 - 1) #define MAX_PAGECACHE_ORDER min(MAX_XAS_ORDER, PREFERRED_MAX_PAGECACHE_ORDER) +/* + * mapping_max_folio_size_supported() - Check the max folio size supported + * + * The filesystem should call this function at mount time if there is a + * requirement on the folio mapping size in the page cache. + */ +static inline size_t mapping_max_folio_size_supported(void) +{ + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) + return 1U << (PAGE_SHIFT + MAX_PAGECACHE_ORDER); + return PAGE_SIZE; +} + /* * mapping_set_folio_order_range() - Set the orders supported by a file. * @mapping: The address space of the file. -- cgit v1.2.3 From 31754ea6cbbc08d5bbe1fa290320c3048d8d98a3 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 27 Aug 2024 06:51:36 -0400 Subject: iomap: add a private argument for iomap_file_buffered_write In order to switch fuse over to using iomap for buffered writes we need to be able to have the struct file for the original write, in case we have to read in the page to make it uptodate. Handle this by using the existing private field in the iomap_iter, and add the argument to iomap_file_buffered_write. This will allow us to pass the file in through the iomap buffered write path, and is flexible for any other file systems needs. Signed-off-by: Josef Bacik Link: https://lore.kernel.org/r/7f55c7c32275004ba00cddf862d970e6e633f750.1724755651.git.josef@toxicpanda.com Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner --- block/fops.c | 2 +- fs/gfs2/file.c | 2 +- fs/iomap/buffered-io.c | 3 ++- fs/xfs/xfs_file.c | 2 +- fs/zonefs/file.c | 2 +- include/linux/iomap.h | 2 +- 6 files changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/block/fops.c b/block/fops.c index 9825c1713a49..d16a6dddb12a 100644 --- a/block/fops.c +++ b/block/fops.c @@ -665,7 +665,7 @@ blkdev_direct_write(struct kiocb *iocb, struct iov_iter *from) static ssize_t blkdev_buffered_write(struct kiocb *iocb, struct iov_iter *from) { - return iomap_file_buffered_write(iocb, from, &blkdev_iomap_ops); + return iomap_file_buffered_write(iocb, from, &blkdev_iomap_ops, NULL); } /* diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 08982937b5df..f7dd64856c9b 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -1057,7 +1057,7 @@ retry: } pagefault_disable(); - ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops); + ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops, NULL); pagefault_enable(); if (ret > 0) written += ret; diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index d745f718bcde..e79d11701553 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1022,13 +1022,14 @@ retry: ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *i, - const struct iomap_ops *ops) + const struct iomap_ops *ops, void *private) { struct iomap_iter iter = { .inode = iocb->ki_filp->f_mapping->host, .pos = iocb->ki_pos, .len = iov_iter_count(i), .flags = IOMAP_WRITE, + .private = private, }; ssize_t ret; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 4cdc54dc9686..e9c693bb20bc 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -760,7 +760,7 @@ write_retry: trace_xfs_file_buffered_write(iocb, from); ret = iomap_file_buffered_write(iocb, from, - &xfs_buffered_write_iomap_ops); + &xfs_buffered_write_iomap_ops, NULL); /* * If we hit a space limit, try to free up some lingering preallocated diff --git a/fs/zonefs/file.c b/fs/zonefs/file.c index 3b103715acc9..35166c92420c 100644 --- a/fs/zonefs/file.c +++ b/fs/zonefs/file.c @@ -563,7 +563,7 @@ static ssize_t zonefs_file_buffered_write(struct kiocb *iocb, if (ret <= 0) goto inode_unlock; - ret = iomap_file_buffered_write(iocb, from, &zonefs_write_iomap_ops); + ret = iomap_file_buffered_write(iocb, from, &zonefs_write_iomap_ops, NULL); if (ret == -EIO) zonefs_io_error(inode, true); diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 6fc1c858013d..f792b37f7627 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -257,7 +257,7 @@ static inline const struct iomap *iomap_iter_srcmap(const struct iomap_iter *i) } ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, - const struct iomap_ops *ops); + const struct iomap_ops *ops, void *private); int iomap_file_buffered_write_punch_delalloc(struct inode *inode, struct iomap *iomap, loff_t pos, loff_t length, ssize_t written, int (*punch)(struct inode *inode, loff_t pos, loff_t length)); -- cgit v1.2.3 From 6f634eb080161baa4811a39f5ec07923ede092bc Mon Sep 17 00:00:00 2001 From: Pankaj Raghav Date: Tue, 27 Aug 2024 10:42:07 +0200 Subject: filemap: fix htmldoc warning for mapping_align_index() Stephen reported that there is a kernel build warning due to a missing description of a parameter in mapping_align_index(). Add the missing index parameter in the comment description. Signed-off-by: Pankaj Raghav Link: https://lore.kernel.org/r/20240827084206.106347-2-kernel@pankajraghav.com Fixes: ab95d23bab22 ("filemap: allocate mapping_min_order folios in the page cache") Reported-by: Stephen Rothwell Signed-off-by: Christian Brauner --- include/linux/pagemap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 55b254d951da..6c0dde447c98 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -470,6 +470,7 @@ mapping_min_folio_nrpages(struct address_space *mapping) /** * mapping_align_index() - Align index for this mapping. * @mapping: The address_space. + * @index: The page index. * * The index of a folio must be naturally aligned. If you are adding a * new folio to the page cache and need to know what index to give it, -- cgit v1.2.3 From 4686cc598f669dea1b50dde1568e6c65c355bc67 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 14 Aug 2024 00:25:51 +0200 Subject: sched: Clean up DL server vs core sched Abide by the simple rule: pick_next_task() := pick_task() + set_next_task(.first = true) This allows us to trivially get rid of server_pick_next() and things collapse nicely. Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20240813224015.837303391@infradead.org --- include/linux/sched.h | 1 - kernel/sched/deadline.c | 18 +++++++----------- kernel/sched/fair.c | 13 +------------ kernel/sched/sched.h | 1 - 4 files changed, 8 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 3709dedbab59..57cf27a3045c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -692,7 +692,6 @@ struct sched_dl_entity { */ struct rq *rq; dl_server_has_tasks_f server_has_tasks; - dl_server_pick_f server_pick_next; dl_server_pick_f server_pick_task; #ifdef CONFIG_RT_MUTEXES diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index f7ac7cff9b5e..2ea929ce9e4f 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1665,12 +1665,10 @@ void dl_server_stop(struct sched_dl_entity *dl_se) void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq, dl_server_has_tasks_f has_tasks, - dl_server_pick_f pick_next, dl_server_pick_f pick_task) { dl_se->rq = rq; dl_se->server_has_tasks = has_tasks; - dl_se->server_pick_next = pick_next; dl_se->server_pick_task = pick_task; } @@ -2404,9 +2402,8 @@ static struct sched_dl_entity *pick_next_dl_entity(struct dl_rq *dl_rq) /* * __pick_next_task_dl - Helper to pick the next -deadline task to run. * @rq: The runqueue to pick the next task from. - * @peek: If true, just peek at the next task. Only relevant for dlserver. */ -static struct task_struct *__pick_next_task_dl(struct rq *rq, bool peek) +static struct task_struct *__pick_task_dl(struct rq *rq) { struct sched_dl_entity *dl_se; struct dl_rq *dl_rq = &rq->dl; @@ -2420,10 +2417,7 @@ again: WARN_ON_ONCE(!dl_se); if (dl_server(dl_se)) { - if (IS_ENABLED(CONFIG_SMP) && peek) - p = dl_se->server_pick_task(dl_se); - else - p = dl_se->server_pick_next(dl_se); + p = dl_se->server_pick_task(dl_se); if (!p) { dl_se->dl_yielded = 1; update_curr_dl_se(rq, dl_se, 0); @@ -2440,7 +2434,7 @@ again: #ifdef CONFIG_SMP static struct task_struct *pick_task_dl(struct rq *rq) { - return __pick_next_task_dl(rq, true); + return __pick_task_dl(rq); } #endif @@ -2448,11 +2442,13 @@ static struct task_struct *pick_next_task_dl(struct rq *rq) { struct task_struct *p; - p = __pick_next_task_dl(rq, false); + p = __pick_task_dl(rq); if (!p) return p; - if (!p->dl_server) + if (p->dl_server) + p->sched_class->set_next_task(rq, p, true); + else set_next_task_dl(rq, p, true); return p; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index eaeb8b2ad834..8379100905b8 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -8862,16 +8862,7 @@ static bool fair_server_has_tasks(struct sched_dl_entity *dl_se) static struct task_struct *fair_server_pick_task(struct sched_dl_entity *dl_se) { -#ifdef CONFIG_SMP return pick_task_fair(dl_se->rq); -#else - return NULL; -#endif -} - -static struct task_struct *fair_server_pick_next(struct sched_dl_entity *dl_se) -{ - return pick_next_task_fair(dl_se->rq, NULL, NULL); } void fair_server_init(struct rq *rq) @@ -8880,9 +8871,7 @@ void fair_server_init(struct rq *rq) init_dl_entity(dl_se); - dl_server_init(dl_se, rq, fair_server_has_tasks, fair_server_pick_next, - fair_server_pick_task); - + dl_server_init(dl_se, rq, fair_server_has_tasks, fair_server_pick_task); } /* diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index d33311d6a738..80605e2da483 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -362,7 +362,6 @@ extern void dl_server_start(struct sched_dl_entity *dl_se); extern void dl_server_stop(struct sched_dl_entity *dl_se); extern void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq, dl_server_has_tasks_f has_tasks, - dl_server_pick_f pick_next, dl_server_pick_f pick_task); extern void dl_server_update_idle_time(struct rq *rq, -- cgit v1.2.3 From 631598c419985327110135efb696d9f9fe67bffd Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Wed, 14 Aug 2024 11:26:29 +0200 Subject: iio: dac: ad5449: drop support for platform data There are no longer any users of the platform data struct. Remove support for it from the driver. Signed-off-by: Bartosz Golaszewski Link: https://patch.msgid.link/20240814092629.9862-1-brgl@bgdev.pl Signed-off-by: Jonathan Cameron --- drivers/iio/dac/ad5449.c | 15 ++------------ include/linux/platform_data/ad5449.h | 39 ------------------------------------ 2 files changed, 2 insertions(+), 52 deletions(-) delete mode 100644 include/linux/platform_data/ad5449.h (limited to 'include/linux') diff --git a/drivers/iio/dac/ad5449.c b/drivers/iio/dac/ad5449.c index 4572d6f49275..953fcfa2110b 100644 --- a/drivers/iio/dac/ad5449.c +++ b/drivers/iio/dac/ad5449.c @@ -20,8 +20,6 @@ #include #include -#include - #define AD5449_MAX_CHANNELS 2 #define AD5449_MAX_VREFS 2 @@ -268,7 +266,6 @@ static const char *ad5449_vref_name(struct ad5449 *st, int n) static int ad5449_spi_probe(struct spi_device *spi) { - struct ad5449_platform_data *pdata = spi->dev.platform_data; const struct spi_device_id *id = spi_get_device_id(spi); struct iio_dev *indio_dev; struct ad5449 *st; @@ -306,16 +303,8 @@ static int ad5449_spi_probe(struct spi_device *spi) mutex_init(&st->lock); if (st->chip_info->has_ctrl) { - unsigned int ctrl = 0x00; - if (pdata) { - if (pdata->hardware_clear_to_midscale) - ctrl |= AD5449_CTRL_HCLR_TO_MIDSCALE; - ctrl |= pdata->sdo_mode << AD5449_CTRL_SDO_OFFSET; - st->has_sdo = pdata->sdo_mode != AD5449_SDO_DISABLED; - } else { - st->has_sdo = true; - } - ad5449_write(indio_dev, AD5449_CMD_CTRL, ctrl); + st->has_sdo = true; + ad5449_write(indio_dev, AD5449_CMD_CTRL, 0x0); } ret = iio_device_register(indio_dev); diff --git a/include/linux/platform_data/ad5449.h b/include/linux/platform_data/ad5449.h deleted file mode 100644 index d687ef5726c2..000000000000 --- a/include/linux/platform_data/ad5449.h +++ /dev/null @@ -1,39 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * AD5415, AD5426, AD5429, AD5432, AD5439, AD5443, AD5449 Digital to Analog - * Converter driver. - * - * Copyright 2012 Analog Devices Inc. - * Author: Lars-Peter Clausen - */ - -#ifndef __LINUX_PLATFORM_DATA_AD5449_H__ -#define __LINUX_PLATFORM_DATA_AD5449_H__ - -/** - * enum ad5449_sdo_mode - AD5449 SDO pin configuration - * @AD5449_SDO_DRIVE_FULL: Drive the SDO pin with full strength. - * @AD5449_SDO_DRIVE_WEAK: Drive the SDO pin with not full strength. - * @AD5449_SDO_OPEN_DRAIN: Operate the SDO pin in open-drain mode. - * @AD5449_SDO_DISABLED: Disable the SDO pin, in this mode it is not possible to - * read back from the device. - */ -enum ad5449_sdo_mode { - AD5449_SDO_DRIVE_FULL = 0x0, - AD5449_SDO_DRIVE_WEAK = 0x1, - AD5449_SDO_OPEN_DRAIN = 0x2, - AD5449_SDO_DISABLED = 0x3, -}; - -/** - * struct ad5449_platform_data - Platform data for the ad5449 DAC driver - * @sdo_mode: SDO pin mode - * @hardware_clear_to_midscale: Whether asserting the hardware CLR pin sets the - * outputs to midscale (true) or to zero scale(false). - */ -struct ad5449_platform_data { - enum ad5449_sdo_mode sdo_mode; - bool hardware_clear_to_midscale; -}; - -#endif -- cgit v1.2.3 From 33f339a1ba54e56bba57ee9a77c71e385ab4825c Mon Sep 17 00:00:00 2001 From: Tze-nan Wu Date: Fri, 30 Aug 2024 16:25:17 +0800 Subject: bpf, net: Fix a potential race in do_sock_getsockopt() There's a potential race when `cgroup_bpf_enabled(CGROUP_GETSOCKOPT)` is false during the execution of `BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN`, but becomes true when `BPF_CGROUP_RUN_PROG_GETSOCKOPT` is called. This inconsistency can lead to `BPF_CGROUP_RUN_PROG_GETSOCKOPT` receiving an "-EFAULT" from `__cgroup_bpf_run_filter_getsockopt(max_optlen=0)`. Scenario shown as below: `process A` `process B` ----------- ------------ BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN enable CGROUP_GETSOCKOPT BPF_CGROUP_RUN_PROG_GETSOCKOPT (-EFAULT) To resolve this, remove the `BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN` macro and directly uses `copy_from_sockptr` to ensure that `max_optlen` is always set before `BPF_CGROUP_RUN_PROG_GETSOCKOPT` is invoked. Fixes: 0d01da6afc54 ("bpf: implement getsockopt and setsockopt hooks") Co-developed-by: Yanghui Li Signed-off-by: Yanghui Li Co-developed-by: Cheng-Jui Wang Signed-off-by: Cheng-Jui Wang Signed-off-by: Tze-nan Wu Acked-by: Stanislav Fomichev Acked-by: Alexei Starovoitov Link: https://patch.msgid.link/20240830082518.23243-1-Tze-nan.Wu@mediatek.com Signed-off-by: Jakub Kicinski --- include/linux/bpf-cgroup.h | 9 --------- net/socket.c | 4 ++-- 2 files changed, 2 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index fb3c3e7181e6..ce91d9b2acb9 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -390,14 +390,6 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, __ret; \ }) -#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) \ -({ \ - int __ret = 0; \ - if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT)) \ - copy_from_sockptr(&__ret, optlen, sizeof(int)); \ - __ret; \ -}) - #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, optlen, \ max_optlen, retval) \ ({ \ @@ -518,7 +510,6 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(atype, major, minor, access) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos) ({ 0; }) -#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, \ optlen, max_optlen, retval) ({ retval; }) #define BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sock, level, optname, optval, \ diff --git a/net/socket.c b/net/socket.c index fcbdd5bc47ac..0a2bd22ec105 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2362,7 +2362,7 @@ INDIRECT_CALLABLE_DECLARE(bool tcp_bpf_bypass_getsockopt(int level, int do_sock_getsockopt(struct socket *sock, bool compat, int level, int optname, sockptr_t optval, sockptr_t optlen) { - int max_optlen __maybe_unused; + int max_optlen __maybe_unused = 0; const struct proto_ops *ops; int err; @@ -2371,7 +2371,7 @@ int do_sock_getsockopt(struct socket *sock, bool compat, int level, return err; if (!compat) - max_optlen = BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen); + copy_from_sockptr(&max_optlen, optlen, sizeof(int)); ops = READ_ONCE(sock->ops); if (level == SOL_SOCKET) { -- cgit v1.2.3 From 7cb9b5fa218caa899f4288865c4598357bcce4e9 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 3 Sep 2024 15:38:25 -0500 Subject: PCI: endpoint: Fix enum pci_epc_bar_type kerneldoc e01c9797c0eb ("PCI: endpoint: Clean up hardware description for BARs") added enum pci_epc_bar_type with incomplete kerneldoc. Add the missing piece. Signed-off-by: Bjorn Helgaas --- include/linux/pci-epc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index 85bdf2adb760..697cc190747d 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -149,6 +149,7 @@ struct pci_epc { }; /** + * enum pci_epc_bar_type - configurability of endpoint BAR * @BAR_PROGRAMMABLE: The BAR mask can be configured by the EPC. * @BAR_FIXED: The BAR mask is fixed by the hardware. * @BAR_RESERVED: The BAR should not be touched by an EPF driver. -- cgit v1.2.3 From 364ea7ccaef917a3068236a19a4b31a0623b561a Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 31 Aug 2024 16:20:39 +0200 Subject: power: supply: Change usb_types from an array into a bitmask The bit_types array just hold a list of valid enum power_supply_usb_type values which map to 0 - 9. This can easily be represented as a bitmap. This reduces the size of struct power_supply_desc and further reduces the data section size by drivers no longer needing to store the array. This also unifies how usb_types are handled with charge_behaviours, which allows power_supply_show_usb_type() to be removed. Signed-off-by: Hans de Goede Reviewed-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20240831142039.28830-7-hdegoede@redhat.com Signed-off-by: Sebastian Reichel --- drivers/extcon/extcon-intel-cht-wc.c | 15 ++++------ drivers/phy/ti/phy-tusb1210.c | 11 ++----- drivers/power/supply/axp20x_usb_power.c | 13 +++----- drivers/power/supply/bq256xx_charger.c | 15 ++++------ drivers/power/supply/cros_usbpd-charger.c | 22 +++++--------- drivers/power/supply/lenovo_yoga_c630_battery.c | 7 +---- drivers/power/supply/mp2629_charger.c | 15 ++++------ drivers/power/supply/mt6360_charger.c | 13 +++----- drivers/power/supply/mt6370-charger.c | 13 +++----- drivers/power/supply/power_supply_core.c | 4 --- drivers/power/supply/power_supply_sysfs.c | 40 +++---------------------- drivers/power/supply/qcom_battmgr.c | 37 ++++++++++++----------- drivers/power/supply/qcom_pmi8998_charger.c | 13 +++----- drivers/power/supply/rk817_charger.c | 9 ++---- drivers/power/supply/rn5t618_power.c | 13 +++----- drivers/power/supply/rt9467-charger.c | 13 +++----- drivers/power/supply/rt9471.c | 15 ++++------ drivers/power/supply/ucs1002_power.c | 15 ++++------ drivers/usb/typec/anx7411.c | 11 ++----- drivers/usb/typec/rt1719.c | 11 ++----- drivers/usb/typec/tcpm/tcpm.c | 11 ++----- drivers/usb/typec/tipd/core.c | 9 ++---- drivers/usb/typec/ucsi/psy.c | 11 ++----- include/linux/power_supply.h | 3 +- 24 files changed, 102 insertions(+), 237 deletions(-) (limited to 'include/linux') diff --git a/drivers/extcon/extcon-intel-cht-wc.c b/drivers/extcon/extcon-intel-cht-wc.c index 733c470c3102..93552dc3c895 100644 --- a/drivers/extcon/extcon-intel-cht-wc.c +++ b/drivers/extcon/extcon-intel-cht-wc.c @@ -461,14 +461,6 @@ static int cht_wc_extcon_psy_get_prop(struct power_supply *psy, return 0; } -static const enum power_supply_usb_type cht_wc_extcon_psy_usb_types[] = { - POWER_SUPPLY_USB_TYPE_SDP, - POWER_SUPPLY_USB_TYPE_CDP, - POWER_SUPPLY_USB_TYPE_DCP, - POWER_SUPPLY_USB_TYPE_ACA, - POWER_SUPPLY_USB_TYPE_UNKNOWN, -}; - static const enum power_supply_property cht_wc_extcon_psy_props[] = { POWER_SUPPLY_PROP_USB_TYPE, POWER_SUPPLY_PROP_ONLINE, @@ -477,8 +469,11 @@ static const enum power_supply_property cht_wc_extcon_psy_props[] = { static const struct power_supply_desc cht_wc_extcon_psy_desc = { .name = "cht_wcove_pwrsrc", .type = POWER_SUPPLY_TYPE_USB, - .usb_types = cht_wc_extcon_psy_usb_types, - .num_usb_types = ARRAY_SIZE(cht_wc_extcon_psy_usb_types), + .usb_types = BIT(POWER_SUPPLY_USB_TYPE_SDP) | + BIT(POWER_SUPPLY_USB_TYPE_CDP) | + BIT(POWER_SUPPLY_USB_TYPE_DCP) | + BIT(POWER_SUPPLY_USB_TYPE_ACA) | + BIT(POWER_SUPPLY_USB_TYPE_UNKNOWN), .properties = cht_wc_extcon_psy_props, .num_properties = ARRAY_SIZE(cht_wc_extcon_psy_props), .get_property = cht_wc_extcon_psy_get_prop, diff --git a/drivers/phy/ti/phy-tusb1210.c b/drivers/phy/ti/phy-tusb1210.c index 751fecd466e3..c3ae9d7948d7 100644 --- a/drivers/phy/ti/phy-tusb1210.c +++ b/drivers/phy/ti/phy-tusb1210.c @@ -411,12 +411,6 @@ static int tusb1210_psy_get_prop(struct power_supply *psy, return 0; } -static const enum power_supply_usb_type tusb1210_psy_usb_types[] = { - POWER_SUPPLY_USB_TYPE_SDP, - POWER_SUPPLY_USB_TYPE_DCP, - POWER_SUPPLY_USB_TYPE_UNKNOWN, -}; - static const enum power_supply_property tusb1210_psy_props[] = { POWER_SUPPLY_PROP_ONLINE, POWER_SUPPLY_PROP_USB_TYPE, @@ -426,8 +420,9 @@ static const enum power_supply_property tusb1210_psy_props[] = { static const struct power_supply_desc tusb1210_psy_desc = { .name = "tusb1211-charger-detect", .type = POWER_SUPPLY_TYPE_USB, - .usb_types = tusb1210_psy_usb_types, - .num_usb_types = ARRAY_SIZE(tusb1210_psy_usb_types), + .usb_types = BIT(POWER_SUPPLY_USB_TYPE_SDP) | + BIT(POWER_SUPPLY_USB_TYPE_DCP) | + BIT(POWER_SUPPLY_USB_TYPE_UNKNOWN), .properties = tusb1210_psy_props, .num_properties = ARRAY_SIZE(tusb1210_psy_props), .get_property = tusb1210_psy_get_prop, diff --git a/drivers/power/supply/axp20x_usb_power.c b/drivers/power/supply/axp20x_usb_power.c index dae7e5cfc54e..38ea2388df21 100644 --- a/drivers/power/supply/axp20x_usb_power.c +++ b/drivers/power/supply/axp20x_usb_power.c @@ -412,13 +412,6 @@ static enum power_supply_property axp813_usb_power_properties[] = { POWER_SUPPLY_PROP_USB_TYPE, }; -static enum power_supply_usb_type axp813_usb_types[] = { - POWER_SUPPLY_USB_TYPE_SDP, - POWER_SUPPLY_USB_TYPE_DCP, - POWER_SUPPLY_USB_TYPE_CDP, - POWER_SUPPLY_USB_TYPE_UNKNOWN, -}; - static const struct power_supply_desc axp20x_usb_power_desc = { .name = "axp20x-usb", .type = POWER_SUPPLY_TYPE_USB, @@ -447,8 +440,10 @@ static const struct power_supply_desc axp813_usb_power_desc = { .property_is_writeable = axp20x_usb_power_prop_writeable, .get_property = axp20x_usb_power_get_property, .set_property = axp20x_usb_power_set_property, - .usb_types = axp813_usb_types, - .num_usb_types = ARRAY_SIZE(axp813_usb_types), + .usb_types = BIT(POWER_SUPPLY_USB_TYPE_SDP) | + BIT(POWER_SUPPLY_USB_TYPE_CDP) | + BIT(POWER_SUPPLY_USB_TYPE_DCP) | + BIT(POWER_SUPPLY_USB_TYPE_UNKNOWN), }; static const char * const axp20x_irq_names[] = { diff --git a/drivers/power/supply/bq256xx_charger.c b/drivers/power/supply/bq256xx_charger.c index 1a935bc88510..5514d1896bb8 100644 --- a/drivers/power/supply/bq256xx_charger.c +++ b/drivers/power/supply/bq256xx_charger.c @@ -334,14 +334,6 @@ static const int bq25618_619_ichg_values[] = { 1290000, 1360000, 1430000, 1500000 }; -static enum power_supply_usb_type bq256xx_usb_type[] = { - POWER_SUPPLY_USB_TYPE_SDP, - POWER_SUPPLY_USB_TYPE_CDP, - POWER_SUPPLY_USB_TYPE_DCP, - POWER_SUPPLY_USB_TYPE_UNKNOWN, - POWER_SUPPLY_USB_TYPE_ACA, -}; - static int bq256xx_array_parse(int array_size, int val, const int array[]) { int i = 0; @@ -1252,8 +1244,11 @@ static int bq256xx_property_is_writeable(struct power_supply *psy, static const struct power_supply_desc bq256xx_power_supply_desc = { .name = "bq256xx-charger", .type = POWER_SUPPLY_TYPE_USB, - .usb_types = bq256xx_usb_type, - .num_usb_types = ARRAY_SIZE(bq256xx_usb_type), + .usb_types = BIT(POWER_SUPPLY_USB_TYPE_SDP) | + BIT(POWER_SUPPLY_USB_TYPE_CDP) | + BIT(POWER_SUPPLY_USB_TYPE_DCP) | + BIT(POWER_SUPPLY_USB_TYPE_ACA) | + BIT(POWER_SUPPLY_USB_TYPE_UNKNOWN), .properties = bq256xx_power_supply_props, .num_properties = ARRAY_SIZE(bq256xx_power_supply_props), .get_property = bq256xx_get_charger_property, diff --git a/drivers/power/supply/cros_usbpd-charger.c b/drivers/power/supply/cros_usbpd-charger.c index 8008e31c0c09..bed3e2e9bfea 100644 --- a/drivers/power/supply/cros_usbpd-charger.c +++ b/drivers/power/supply/cros_usbpd-charger.c @@ -73,17 +73,6 @@ static enum power_supply_property cros_usbpd_dedicated_charger_props[] = { POWER_SUPPLY_PROP_VOLTAGE_NOW, }; -static enum power_supply_usb_type cros_usbpd_charger_usb_types[] = { - POWER_SUPPLY_USB_TYPE_UNKNOWN, - POWER_SUPPLY_USB_TYPE_SDP, - POWER_SUPPLY_USB_TYPE_DCP, - POWER_SUPPLY_USB_TYPE_CDP, - POWER_SUPPLY_USB_TYPE_C, - POWER_SUPPLY_USB_TYPE_PD, - POWER_SUPPLY_USB_TYPE_PD_DRP, - POWER_SUPPLY_USB_TYPE_APPLE_BRICK_ID -}; - /* Input voltage/current limit in mV/mA. Default to none. */ static u16 input_voltage_limit = EC_POWER_LIMIT_NONE; static u16 input_current_limit = EC_POWER_LIMIT_NONE; @@ -643,9 +632,14 @@ static int cros_usbpd_charger_probe(struct platform_device *pd) psy_desc->properties = cros_usbpd_charger_props; psy_desc->num_properties = ARRAY_SIZE(cros_usbpd_charger_props); - psy_desc->usb_types = cros_usbpd_charger_usb_types; - psy_desc->num_usb_types = - ARRAY_SIZE(cros_usbpd_charger_usb_types); + psy_desc->usb_types = BIT(POWER_SUPPLY_USB_TYPE_UNKNOWN) | + BIT(POWER_SUPPLY_USB_TYPE_SDP) | + BIT(POWER_SUPPLY_USB_TYPE_DCP) | + BIT(POWER_SUPPLY_USB_TYPE_CDP) | + BIT(POWER_SUPPLY_USB_TYPE_C) | + BIT(POWER_SUPPLY_USB_TYPE_PD) | + BIT(POWER_SUPPLY_USB_TYPE_PD_DRP) | + BIT(POWER_SUPPLY_USB_TYPE_APPLE_BRICK_ID); } psy_desc->name = port->name; diff --git a/drivers/power/supply/lenovo_yoga_c630_battery.c b/drivers/power/supply/lenovo_yoga_c630_battery.c index d4d422cc5353..f98f65e00831 100644 --- a/drivers/power/supply/lenovo_yoga_c630_battery.c +++ b/drivers/power/supply/lenovo_yoga_c630_battery.c @@ -353,15 +353,10 @@ static enum power_supply_property yoga_c630_psy_adpt_properties[] = { POWER_SUPPLY_PROP_USB_TYPE, }; -static const enum power_supply_usb_type yoga_c630_psy_adpt_usb_type[] = { - POWER_SUPPLY_USB_TYPE_C, -}; - static const struct power_supply_desc yoga_c630_psy_adpt_psy_desc = { .name = "yoga-c630-adapter", .type = POWER_SUPPLY_TYPE_USB, - .usb_types = yoga_c630_psy_adpt_usb_type, - .num_usb_types = ARRAY_SIZE(yoga_c630_psy_adpt_usb_type), + .usb_types = BIT(POWER_SUPPLY_USB_TYPE_C), .properties = yoga_c630_psy_adpt_properties, .num_properties = ARRAY_SIZE(yoga_c630_psy_adpt_properties), .get_property = yoga_c630_psy_adpt_get_property, diff --git a/drivers/power/supply/mp2629_charger.c b/drivers/power/supply/mp2629_charger.c index 3a2a28fbba73..d281c1059629 100644 --- a/drivers/power/supply/mp2629_charger.c +++ b/drivers/power/supply/mp2629_charger.c @@ -94,14 +94,6 @@ struct mp2629_prop { int shift; }; -static enum power_supply_usb_type mp2629_usb_types[] = { - POWER_SUPPLY_USB_TYPE_SDP, - POWER_SUPPLY_USB_TYPE_DCP, - POWER_SUPPLY_USB_TYPE_CDP, - POWER_SUPPLY_USB_TYPE_PD_DRP, - POWER_SUPPLY_USB_TYPE_UNKNOWN -}; - static enum power_supply_property mp2629_charger_usb_props[] = { POWER_SUPPLY_PROP_ONLINE, POWER_SUPPLY_PROP_USB_TYPE, @@ -487,8 +479,11 @@ unlock: static const struct power_supply_desc mp2629_usb_desc = { .name = "mp2629_usb", .type = POWER_SUPPLY_TYPE_USB, - .usb_types = mp2629_usb_types, - .num_usb_types = ARRAY_SIZE(mp2629_usb_types), + .usb_types = BIT(POWER_SUPPLY_USB_TYPE_SDP) | + BIT(POWER_SUPPLY_USB_TYPE_CDP) | + BIT(POWER_SUPPLY_USB_TYPE_DCP) | + BIT(POWER_SUPPLY_USB_TYPE_PD_DRP) | + BIT(POWER_SUPPLY_USB_TYPE_UNKNOWN), .properties = mp2629_charger_usb_props, .num_properties = ARRAY_SIZE(mp2629_charger_usb_props), .get_property = mp2629_charger_usb_get_prop, diff --git a/drivers/power/supply/mt6360_charger.c b/drivers/power/supply/mt6360_charger.c index aca123783efc..e99e55148976 100644 --- a/drivers/power/supply/mt6360_charger.c +++ b/drivers/power/supply/mt6360_charger.c @@ -154,13 +154,6 @@ enum mt6360_pmu_chg_type { MT6360_CHG_TYPE_MAX, }; -static enum power_supply_usb_type mt6360_charger_usb_types[] = { - POWER_SUPPLY_USB_TYPE_UNKNOWN, - POWER_SUPPLY_USB_TYPE_SDP, - POWER_SUPPLY_USB_TYPE_DCP, - POWER_SUPPLY_USB_TYPE_CDP, -}; - static int mt6360_get_chrdet_ext_stat(struct mt6360_chg_info *mci, bool *pwr_rdy) { @@ -574,8 +567,10 @@ static const struct power_supply_desc mt6360_charger_desc = { .get_property = mt6360_charger_get_property, .set_property = mt6360_charger_set_property, .property_is_writeable = mt6360_charger_property_is_writeable, - .usb_types = mt6360_charger_usb_types, - .num_usb_types = ARRAY_SIZE(mt6360_charger_usb_types), + .usb_types = BIT(POWER_SUPPLY_USB_TYPE_SDP) | + BIT(POWER_SUPPLY_USB_TYPE_CDP) | + BIT(POWER_SUPPLY_USB_TYPE_DCP) | + BIT(POWER_SUPPLY_USB_TYPE_UNKNOWN), }; static const struct regulator_ops mt6360_chg_otg_ops = { diff --git a/drivers/power/supply/mt6370-charger.c b/drivers/power/supply/mt6370-charger.c index e24fce087d80..ad8793bf997e 100644 --- a/drivers/power/supply/mt6370-charger.c +++ b/drivers/power/supply/mt6370-charger.c @@ -624,13 +624,6 @@ static enum power_supply_property mt6370_chg_properties[] = { POWER_SUPPLY_PROP_USB_TYPE, }; -static enum power_supply_usb_type mt6370_chg_usb_types[] = { - POWER_SUPPLY_USB_TYPE_UNKNOWN, - POWER_SUPPLY_USB_TYPE_SDP, - POWER_SUPPLY_USB_TYPE_CDP, - POWER_SUPPLY_USB_TYPE_DCP, -}; - static const struct power_supply_desc mt6370_chg_psy_desc = { .name = "mt6370-charger", .type = POWER_SUPPLY_TYPE_USB, @@ -639,8 +632,10 @@ static const struct power_supply_desc mt6370_chg_psy_desc = { .get_property = mt6370_chg_get_property, .set_property = mt6370_chg_set_property, .property_is_writeable = mt6370_chg_property_is_writeable, - .usb_types = mt6370_chg_usb_types, - .num_usb_types = ARRAY_SIZE(mt6370_chg_usb_types), + .usb_types = BIT(POWER_SUPPLY_USB_TYPE_SDP) | + BIT(POWER_SUPPLY_USB_TYPE_CDP) | + BIT(POWER_SUPPLY_USB_TYPE_DCP) | + BIT(POWER_SUPPLY_USB_TYPE_UNKNOWN), }; static const struct regulator_ops mt6370_chg_otg_ops = { diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c index 8f6025acd10a..4fa3d3414b8c 100644 --- a/drivers/power/supply/power_supply_core.c +++ b/drivers/power/supply/power_supply_core.c @@ -1361,10 +1361,6 @@ __power_supply_register(struct device *parent, pr_warn("%s: Expected proper parent device for '%s'\n", __func__, desc->name); - if (psy_has_property(desc, POWER_SUPPLY_PROP_USB_TYPE) && - (!desc->usb_types || !desc->num_usb_types)) - return ERR_PTR(-EINVAL); - psy = kzalloc(sizeof(*psy), GFP_KERNEL); if (!psy) return ERR_PTR(-ENOMEM); diff --git a/drivers/power/supply/power_supply_sysfs.c b/drivers/power/supply/power_supply_sysfs.c index c98a6de59d3b..16b3c5880cd8 100644 --- a/drivers/power/supply/power_supply_sysfs.c +++ b/drivers/power/supply/power_supply_sysfs.c @@ -268,40 +268,6 @@ static ssize_t power_supply_show_enum_with_available( return count; } -static ssize_t power_supply_show_usb_type(struct device *dev, - const struct power_supply_desc *desc, - union power_supply_propval *value, - char *buf) -{ - enum power_supply_usb_type usb_type; - ssize_t count = 0; - bool match = false; - int i; - - for (i = 0; i < desc->num_usb_types; ++i) { - usb_type = desc->usb_types[i]; - - if (value->intval == usb_type) { - count += sysfs_emit_at(buf, count, "[%s] ", - POWER_SUPPLY_USB_TYPE_TEXT[usb_type]); - match = true; - } else { - count += sysfs_emit_at(buf, count, "%s ", - POWER_SUPPLY_USB_TYPE_TEXT[usb_type]); - } - } - - if (!match) { - dev_warn(dev, "driver reporting unsupported connected type\n"); - return -EINVAL; - } - - if (count) - buf[count - 1] = '\n'; - - return count; -} - static ssize_t power_supply_show_property(struct device *dev, struct device_attribute *attr, char *buf) { @@ -331,8 +297,10 @@ static ssize_t power_supply_show_property(struct device *dev, switch (psp) { case POWER_SUPPLY_PROP_USB_TYPE: - ret = power_supply_show_usb_type(dev, psy->desc, - &value, buf); + ret = power_supply_show_enum_with_available( + dev, POWER_SUPPLY_USB_TYPE_TEXT, + ARRAY_SIZE(POWER_SUPPLY_USB_TYPE_TEXT), + psy->desc->usb_types, value.intval, buf); break; case POWER_SUPPLY_PROP_CHARGE_BEHAVIOUR: ret = power_supply_charge_behaviour_show(dev, psy->desc->charge_behaviours, diff --git a/drivers/power/supply/qcom_battmgr.c b/drivers/power/supply/qcom_battmgr.c index 46f36dcb185c..56c8021383da 100644 --- a/drivers/power/supply/qcom_battmgr.c +++ b/drivers/power/supply/qcom_battmgr.c @@ -786,19 +786,6 @@ static int qcom_battmgr_usb_get_property(struct power_supply *psy, return 0; } -static const enum power_supply_usb_type usb_psy_supported_types[] = { - POWER_SUPPLY_USB_TYPE_UNKNOWN, - POWER_SUPPLY_USB_TYPE_SDP, - POWER_SUPPLY_USB_TYPE_DCP, - POWER_SUPPLY_USB_TYPE_CDP, - POWER_SUPPLY_USB_TYPE_ACA, - POWER_SUPPLY_USB_TYPE_C, - POWER_SUPPLY_USB_TYPE_PD, - POWER_SUPPLY_USB_TYPE_PD_DRP, - POWER_SUPPLY_USB_TYPE_PD_PPS, - POWER_SUPPLY_USB_TYPE_APPLE_BRICK_ID, -}; - static const enum power_supply_property sc8280xp_usb_props[] = { POWER_SUPPLY_PROP_ONLINE, }; @@ -809,8 +796,16 @@ static const struct power_supply_desc sc8280xp_usb_psy_desc = { .properties = sc8280xp_usb_props, .num_properties = ARRAY_SIZE(sc8280xp_usb_props), .get_property = qcom_battmgr_usb_get_property, - .usb_types = usb_psy_supported_types, - .num_usb_types = ARRAY_SIZE(usb_psy_supported_types), + .usb_types = BIT(POWER_SUPPLY_USB_TYPE_UNKNOWN) | + BIT(POWER_SUPPLY_USB_TYPE_SDP) | + BIT(POWER_SUPPLY_USB_TYPE_DCP) | + BIT(POWER_SUPPLY_USB_TYPE_CDP) | + BIT(POWER_SUPPLY_USB_TYPE_ACA) | + BIT(POWER_SUPPLY_USB_TYPE_C) | + BIT(POWER_SUPPLY_USB_TYPE_PD) | + BIT(POWER_SUPPLY_USB_TYPE_PD_DRP) | + BIT(POWER_SUPPLY_USB_TYPE_PD_PPS) | + BIT(POWER_SUPPLY_USB_TYPE_APPLE_BRICK_ID), }; static const enum power_supply_property sm8350_usb_props[] = { @@ -829,8 +824,16 @@ static const struct power_supply_desc sm8350_usb_psy_desc = { .properties = sm8350_usb_props, .num_properties = ARRAY_SIZE(sm8350_usb_props), .get_property = qcom_battmgr_usb_get_property, - .usb_types = usb_psy_supported_types, - .num_usb_types = ARRAY_SIZE(usb_psy_supported_types), + .usb_types = BIT(POWER_SUPPLY_USB_TYPE_UNKNOWN) | + BIT(POWER_SUPPLY_USB_TYPE_SDP) | + BIT(POWER_SUPPLY_USB_TYPE_DCP) | + BIT(POWER_SUPPLY_USB_TYPE_CDP) | + BIT(POWER_SUPPLY_USB_TYPE_ACA) | + BIT(POWER_SUPPLY_USB_TYPE_C) | + BIT(POWER_SUPPLY_USB_TYPE_PD) | + BIT(POWER_SUPPLY_USB_TYPE_PD_DRP) | + BIT(POWER_SUPPLY_USB_TYPE_PD_PPS) | + BIT(POWER_SUPPLY_USB_TYPE_APPLE_BRICK_ID), }; static const u8 sm8350_wls_prop_map[] = { diff --git a/drivers/power/supply/qcom_pmi8998_charger.c b/drivers/power/supply/qcom_pmi8998_charger.c index 9bb777406013..81acbd8b2169 100644 --- a/drivers/power/supply/qcom_pmi8998_charger.c +++ b/drivers/power/supply/qcom_pmi8998_charger.c @@ -411,13 +411,6 @@ static enum power_supply_property smb2_properties[] = { POWER_SUPPLY_PROP_USB_TYPE, }; -static enum power_supply_usb_type smb2_usb_types[] = { - POWER_SUPPLY_USB_TYPE_UNKNOWN, - POWER_SUPPLY_USB_TYPE_SDP, - POWER_SUPPLY_USB_TYPE_DCP, - POWER_SUPPLY_USB_TYPE_CDP, -}; - static int smb2_get_prop_usb_online(struct smb2_chip *chip, int *val) { unsigned int stat; @@ -775,8 +768,10 @@ static irqreturn_t smb2_handle_wdog_bark(int irq, void *data) static const struct power_supply_desc smb2_psy_desc = { .name = "pmi8998_charger", .type = POWER_SUPPLY_TYPE_USB, - .usb_types = smb2_usb_types, - .num_usb_types = ARRAY_SIZE(smb2_usb_types), + .usb_types = BIT(POWER_SUPPLY_USB_TYPE_SDP) | + BIT(POWER_SUPPLY_USB_TYPE_CDP) | + BIT(POWER_SUPPLY_USB_TYPE_DCP) | + BIT(POWER_SUPPLY_USB_TYPE_UNKNOWN), .properties = smb2_properties, .num_properties = ARRAY_SIZE(smb2_properties), .get_property = smb2_get_property, diff --git a/drivers/power/supply/rk817_charger.c b/drivers/power/supply/rk817_charger.c index 7ca91739c6cc..a3d377a32b49 100644 --- a/drivers/power/supply/rk817_charger.c +++ b/drivers/power/supply/rk817_charger.c @@ -673,11 +673,6 @@ static enum power_supply_property rk817_chg_props[] = { POWER_SUPPLY_PROP_VOLTAGE_AVG, }; -static enum power_supply_usb_type rk817_usb_type[] = { - POWER_SUPPLY_USB_TYPE_DCP, - POWER_SUPPLY_USB_TYPE_UNKNOWN, -}; - static const struct power_supply_desc rk817_bat_desc = { .name = "rk817-battery", .type = POWER_SUPPLY_TYPE_BATTERY, @@ -689,8 +684,8 @@ static const struct power_supply_desc rk817_bat_desc = { static const struct power_supply_desc rk817_chg_desc = { .name = "rk817-charger", .type = POWER_SUPPLY_TYPE_USB, - .usb_types = rk817_usb_type, - .num_usb_types = ARRAY_SIZE(rk817_usb_type), + .usb_types = BIT(POWER_SUPPLY_USB_TYPE_DCP) | + BIT(POWER_SUPPLY_USB_TYPE_UNKNOWN), .properties = rk817_chg_props, .num_properties = ARRAY_SIZE(rk817_chg_props), .get_property = rk817_chg_get_prop, diff --git a/drivers/power/supply/rn5t618_power.c b/drivers/power/supply/rn5t618_power.c index ebea3522a2ac..40dec55a9f73 100644 --- a/drivers/power/supply/rn5t618_power.c +++ b/drivers/power/supply/rn5t618_power.c @@ -70,13 +70,6 @@ struct rn5t618_power_info { int irq; }; -static enum power_supply_usb_type rn5t618_usb_types[] = { - POWER_SUPPLY_USB_TYPE_SDP, - POWER_SUPPLY_USB_TYPE_DCP, - POWER_SUPPLY_USB_TYPE_CDP, - POWER_SUPPLY_USB_TYPE_UNKNOWN -}; - static enum power_supply_property rn5t618_usb_props[] = { /* input current limit is not very accurate */ POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT, @@ -681,8 +674,10 @@ static const struct power_supply_desc rn5t618_adp_desc = { static const struct power_supply_desc rn5t618_usb_desc = { .name = "rn5t618-usb", .type = POWER_SUPPLY_TYPE_USB, - .usb_types = rn5t618_usb_types, - .num_usb_types = ARRAY_SIZE(rn5t618_usb_types), + .usb_types = BIT(POWER_SUPPLY_USB_TYPE_SDP) | + BIT(POWER_SUPPLY_USB_TYPE_CDP) | + BIT(POWER_SUPPLY_USB_TYPE_DCP) | + BIT(POWER_SUPPLY_USB_TYPE_UNKNOWN), .properties = rn5t618_usb_props, .num_properties = ARRAY_SIZE(rn5t618_usb_props), .get_property = rn5t618_usb_get_property, diff --git a/drivers/power/supply/rt9467-charger.c b/drivers/power/supply/rt9467-charger.c index f935bd761ac1..235169c85c5d 100644 --- a/drivers/power/supply/rt9467-charger.c +++ b/drivers/power/supply/rt9467-charger.c @@ -630,13 +630,6 @@ out: return ret; } -static const enum power_supply_usb_type rt9467_chg_usb_types[] = { - POWER_SUPPLY_USB_TYPE_UNKNOWN, - POWER_SUPPLY_USB_TYPE_SDP, - POWER_SUPPLY_USB_TYPE_DCP, - POWER_SUPPLY_USB_TYPE_CDP, -}; - static const enum power_supply_property rt9467_chg_properties[] = { POWER_SUPPLY_PROP_STATUS, POWER_SUPPLY_PROP_ONLINE, @@ -771,8 +764,10 @@ static int rt9467_chg_prop_is_writeable(struct power_supply *psy, static const struct power_supply_desc rt9467_chg_psy_desc = { .name = "rt9467-charger", .type = POWER_SUPPLY_TYPE_USB, - .usb_types = rt9467_chg_usb_types, - .num_usb_types = ARRAY_SIZE(rt9467_chg_usb_types), + .usb_types = BIT(POWER_SUPPLY_USB_TYPE_SDP) | + BIT(POWER_SUPPLY_USB_TYPE_CDP) | + BIT(POWER_SUPPLY_USB_TYPE_DCP) | + BIT(POWER_SUPPLY_USB_TYPE_UNKNOWN), .properties = rt9467_chg_properties, .num_properties = ARRAY_SIZE(rt9467_chg_properties), .property_is_writeable = rt9467_chg_prop_is_writeable, diff --git a/drivers/power/supply/rt9471.c b/drivers/power/supply/rt9471.c index 868b0703d15c..c04af1ee89c6 100644 --- a/drivers/power/supply/rt9471.c +++ b/drivers/power/supply/rt9471.c @@ -333,14 +333,6 @@ static enum power_supply_property rt9471_charger_properties[] = { POWER_SUPPLY_PROP_MANUFACTURER, }; -static enum power_supply_usb_type rt9471_charger_usb_types[] = { - POWER_SUPPLY_USB_TYPE_UNKNOWN, - POWER_SUPPLY_USB_TYPE_SDP, - POWER_SUPPLY_USB_TYPE_DCP, - POWER_SUPPLY_USB_TYPE_CDP, - POWER_SUPPLY_USB_TYPE_APPLE_BRICK_ID, -}; - static int rt9471_charger_property_is_writeable(struct power_supply *psy, enum power_supply_property psp) { @@ -726,8 +718,11 @@ static int rt9471_register_psy(struct rt9471_chip *chip) desc->name = psy_name; desc->type = POWER_SUPPLY_TYPE_USB; - desc->usb_types = rt9471_charger_usb_types; - desc->num_usb_types = ARRAY_SIZE(rt9471_charger_usb_types); + desc->usb_types = BIT(POWER_SUPPLY_USB_TYPE_SDP) | + BIT(POWER_SUPPLY_USB_TYPE_CDP) | + BIT(POWER_SUPPLY_USB_TYPE_DCP) | + BIT(POWER_SUPPLY_USB_TYPE_APPLE_BRICK_ID) | + BIT(POWER_SUPPLY_USB_TYPE_UNKNOWN); desc->properties = rt9471_charger_properties; desc->num_properties = ARRAY_SIZE(rt9471_charger_properties); desc->get_property = rt9471_charger_get_property; diff --git a/drivers/power/supply/ucs1002_power.c b/drivers/power/supply/ucs1002_power.c index b67d5b03d93e..7382bec6a43c 100644 --- a/drivers/power/supply/ucs1002_power.c +++ b/drivers/power/supply/ucs1002_power.c @@ -296,14 +296,6 @@ static int ucs1002_set_max_current(struct ucs1002_info *info, u32 val) return 0; } -static enum power_supply_usb_type ucs1002_usb_types[] = { - POWER_SUPPLY_USB_TYPE_PD, - POWER_SUPPLY_USB_TYPE_SDP, - POWER_SUPPLY_USB_TYPE_DCP, - POWER_SUPPLY_USB_TYPE_CDP, - POWER_SUPPLY_USB_TYPE_UNKNOWN, -}; - static int ucs1002_set_usb_type(struct ucs1002_info *info, int val) { unsigned int mode; @@ -431,8 +423,11 @@ static int ucs1002_property_is_writeable(struct power_supply *psy, static const struct power_supply_desc ucs1002_charger_desc = { .name = "ucs1002", .type = POWER_SUPPLY_TYPE_USB, - .usb_types = ucs1002_usb_types, - .num_usb_types = ARRAY_SIZE(ucs1002_usb_types), + .usb_types = BIT(POWER_SUPPLY_USB_TYPE_SDP) | + BIT(POWER_SUPPLY_USB_TYPE_CDP) | + BIT(POWER_SUPPLY_USB_TYPE_DCP) | + BIT(POWER_SUPPLY_USB_TYPE_PD) | + BIT(POWER_SUPPLY_USB_TYPE_UNKNOWN), .get_property = ucs1002_get_property, .set_property = ucs1002_set_property, .property_is_writeable = ucs1002_property_is_writeable, diff --git a/drivers/usb/typec/anx7411.c b/drivers/usb/typec/anx7411.c index 5a5bf3532ad7..31e3e9544bc0 100644 --- a/drivers/usb/typec/anx7411.c +++ b/drivers/usb/typec/anx7411.c @@ -1339,12 +1339,6 @@ static void anx7411_get_gpio_irq(struct anx7411_data *ctx) dev_err(dev, "failed to get GPIO IRQ\n"); } -static enum power_supply_usb_type anx7411_psy_usb_types[] = { - POWER_SUPPLY_USB_TYPE_C, - POWER_SUPPLY_USB_TYPE_PD, - POWER_SUPPLY_USB_TYPE_PD_PPS, -}; - static enum power_supply_property anx7411_psy_props[] = { POWER_SUPPLY_PROP_USB_TYPE, POWER_SUPPLY_PROP_ONLINE, @@ -1422,8 +1416,9 @@ static int anx7411_psy_register(struct anx7411_data *ctx) psy_desc->name = psy_name; psy_desc->type = POWER_SUPPLY_TYPE_USB; - psy_desc->usb_types = anx7411_psy_usb_types; - psy_desc->num_usb_types = ARRAY_SIZE(anx7411_psy_usb_types); + psy_desc->usb_types = BIT(POWER_SUPPLY_USB_TYPE_C) | + BIT(POWER_SUPPLY_USB_TYPE_PD) | + BIT(POWER_SUPPLY_USB_TYPE_PD_PPS); psy_desc->properties = anx7411_psy_props; psy_desc->num_properties = ARRAY_SIZE(anx7411_psy_props); diff --git a/drivers/usb/typec/rt1719.c b/drivers/usb/typec/rt1719.c index be02d420920e..0b0c23a0b014 100644 --- a/drivers/usb/typec/rt1719.c +++ b/drivers/usb/typec/rt1719.c @@ -109,12 +109,6 @@ struct rt1719_data { u16 conn_stat; }; -static const enum power_supply_usb_type rt1719_psy_usb_types[] = { - POWER_SUPPLY_USB_TYPE_C, - POWER_SUPPLY_USB_TYPE_PD, - POWER_SUPPLY_USB_TYPE_PD_PPS -}; - static const enum power_supply_property rt1719_psy_properties[] = { POWER_SUPPLY_PROP_ONLINE, POWER_SUPPLY_PROP_USB_TYPE, @@ -572,8 +566,9 @@ static int devm_rt1719_psy_register(struct rt1719_data *data) data->psy_desc.name = psy_name; data->psy_desc.type = POWER_SUPPLY_TYPE_USB; - data->psy_desc.usb_types = rt1719_psy_usb_types; - data->psy_desc.num_usb_types = ARRAY_SIZE(rt1719_psy_usb_types); + data->psy_desc.usb_types = BIT(POWER_SUPPLY_USB_TYPE_C) | + BIT(POWER_SUPPLY_USB_TYPE_PD) | + BIT(POWER_SUPPLY_USB_TYPE_PD_PPS); data->psy_desc.properties = rt1719_psy_properties; data->psy_desc.num_properties = ARRAY_SIZE(rt1719_psy_properties); data->psy_desc.get_property = rt1719_psy_get_property; diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 26f9006e95e1..0bd9c9569fb7 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -7484,12 +7484,6 @@ static int tcpm_psy_prop_writeable(struct power_supply *psy, } } -static enum power_supply_usb_type tcpm_psy_usb_types[] = { - POWER_SUPPLY_USB_TYPE_C, - POWER_SUPPLY_USB_TYPE_PD, - POWER_SUPPLY_USB_TYPE_PD_PPS, -}; - static const char *tcpm_psy_name_prefix = "tcpm-source-psy-"; static int devm_tcpm_psy_register(struct tcpm_port *port) @@ -7510,8 +7504,9 @@ static int devm_tcpm_psy_register(struct tcpm_port *port) port_dev_name); port->psy_desc.name = psy_name; port->psy_desc.type = POWER_SUPPLY_TYPE_USB; - port->psy_desc.usb_types = tcpm_psy_usb_types; - port->psy_desc.num_usb_types = ARRAY_SIZE(tcpm_psy_usb_types); + port->psy_desc.usb_types = BIT(POWER_SUPPLY_USB_TYPE_C) | + BIT(POWER_SUPPLY_USB_TYPE_PD) | + BIT(POWER_SUPPLY_USB_TYPE_PD_PPS); port->psy_desc.properties = tcpm_psy_props; port->psy_desc.num_properties = ARRAY_SIZE(tcpm_psy_props); port->psy_desc.get_property = tcpm_psy_get_prop; diff --git a/drivers/usb/typec/tipd/core.c b/drivers/usb/typec/tipd/core.c index ea768b19a7f1..7512f0c3f6cb 100644 --- a/drivers/usb/typec/tipd/core.c +++ b/drivers/usb/typec/tipd/core.c @@ -150,11 +150,6 @@ static enum power_supply_property tps6598x_psy_props[] = { POWER_SUPPLY_PROP_ONLINE, }; -static enum power_supply_usb_type tps6598x_psy_usb_types[] = { - POWER_SUPPLY_USB_TYPE_C, - POWER_SUPPLY_USB_TYPE_PD, -}; - static const char *tps6598x_psy_name_prefix = "tps6598x-source-psy-"; /* @@ -827,8 +822,8 @@ static int devm_tps6598_psy_register(struct tps6598x *tps) tps->psy_desc.name = psy_name; tps->psy_desc.type = POWER_SUPPLY_TYPE_USB; - tps->psy_desc.usb_types = tps6598x_psy_usb_types; - tps->psy_desc.num_usb_types = ARRAY_SIZE(tps6598x_psy_usb_types); + tps->psy_desc.usb_types = BIT(POWER_SUPPLY_USB_TYPE_C) | + BIT(POWER_SUPPLY_USB_TYPE_PD); tps->psy_desc.properties = tps6598x_psy_props; tps->psy_desc.num_properties = ARRAY_SIZE(tps6598x_psy_props); tps->psy_desc.get_property = tps6598x_psy_get_prop; diff --git a/drivers/usb/typec/ucsi/psy.c b/drivers/usb/typec/ucsi/psy.c index e623d80e177c..1c631c7855a9 100644 --- a/drivers/usb/typec/ucsi/psy.c +++ b/drivers/usb/typec/ucsi/psy.c @@ -254,12 +254,6 @@ static int ucsi_psy_get_prop(struct power_supply *psy, } } -static enum power_supply_usb_type ucsi_psy_usb_types[] = { - POWER_SUPPLY_USB_TYPE_C, - POWER_SUPPLY_USB_TYPE_PD, - POWER_SUPPLY_USB_TYPE_PD_PPS, -}; - int ucsi_register_port_psy(struct ucsi_connector *con) { struct power_supply_config psy_cfg = {}; @@ -276,8 +270,9 @@ int ucsi_register_port_psy(struct ucsi_connector *con) con->psy_desc.name = psy_name; con->psy_desc.type = POWER_SUPPLY_TYPE_USB; - con->psy_desc.usb_types = ucsi_psy_usb_types; - con->psy_desc.num_usb_types = ARRAY_SIZE(ucsi_psy_usb_types); + con->psy_desc.usb_types = BIT(POWER_SUPPLY_USB_TYPE_C) | + BIT(POWER_SUPPLY_USB_TYPE_PD) | + BIT(POWER_SUPPLY_USB_TYPE_PD_PPS); con->psy_desc.properties = ucsi_psy_props; con->psy_desc.num_properties = ARRAY_SIZE(ucsi_psy_props); con->psy_desc.get_property = ucsi_psy_get_prop; diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 72dc7e45c90c..910d407ebe63 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -243,8 +243,7 @@ struct power_supply_desc { const char *name; enum power_supply_type type; u8 charge_behaviours; - const enum power_supply_usb_type *usb_types; - size_t num_usb_types; + u32 usb_types; const enum power_supply_property *properties; size_t num_properties; -- cgit v1.2.3 From 8f62819aaace77dd85037ae766eb767f8c4417ce Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 23 Aug 2024 11:33:23 +0200 Subject: PCI/pwrctl: Rescan bus on a separate thread If we trigger the bus rescan from sysfs, we'll try to lock the PCI rescan mutex recursively and deadlock - the platform device will be populated and probed on the same thread that handles the sysfs write. Add a workqueue to the pwrctl code on which we schedule the rescan for controlled PCI devices. While at it: add a new interface for initializing the pwrctl context where we'd now assign the parent device address and initialize the workqueue. Link: https://lore.kernel.org/r/20240823093323.33450-3-brgl@bgdev.pl Fixes: 4565d2652a37 ("PCI/pwrctl: Add PCI power control core code") Reported-by: Konrad Dybcio Signed-off-by: Bartosz Golaszewski Signed-off-by: Bjorn Helgaas Reviewed-by: Manivannan Sadhasivam --- drivers/pci/pwrctl/core.c | 26 +++++++++++++++++++++++--- drivers/pci/pwrctl/pci-pwrctl-pwrseq.c | 2 +- include/linux/pci-pwrctl.h | 3 +++ 3 files changed, 27 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pwrctl/core.c b/drivers/pci/pwrctl/core.c index feca26ad2f6a..01d913b60316 100644 --- a/drivers/pci/pwrctl/core.c +++ b/drivers/pci/pwrctl/core.c @@ -48,6 +48,28 @@ static int pci_pwrctl_notify(struct notifier_block *nb, unsigned long action, return NOTIFY_DONE; } +static void rescan_work_func(struct work_struct *work) +{ + struct pci_pwrctl *pwrctl = container_of(work, struct pci_pwrctl, work); + + pci_lock_rescan_remove(); + pci_rescan_bus(to_pci_dev(pwrctl->dev->parent)->bus); + pci_unlock_rescan_remove(); +} + +/** + * pci_pwrctl_init() - Initialize the PCI power control context struct + * + * @pwrctl: PCI power control data + * @dev: Parent device + */ +void pci_pwrctl_init(struct pci_pwrctl *pwrctl, struct device *dev) +{ + pwrctl->dev = dev; + INIT_WORK(&pwrctl->work, rescan_work_func); +} +EXPORT_SYMBOL_GPL(pci_pwrctl_init); + /** * pci_pwrctl_device_set_ready() - Notify the pwrctl subsystem that the PCI * device is powered-up and ready to be detected. @@ -74,9 +96,7 @@ int pci_pwrctl_device_set_ready(struct pci_pwrctl *pwrctl) if (ret) return ret; - pci_lock_rescan_remove(); - pci_rescan_bus(to_pci_dev(pwrctl->dev->parent)->bus); - pci_unlock_rescan_remove(); + schedule_work(&pwrctl->work); return 0; } diff --git a/drivers/pci/pwrctl/pci-pwrctl-pwrseq.c b/drivers/pci/pwrctl/pci-pwrctl-pwrseq.c index c7a113a76c0c..f07758c9edad 100644 --- a/drivers/pci/pwrctl/pci-pwrctl-pwrseq.c +++ b/drivers/pci/pwrctl/pci-pwrctl-pwrseq.c @@ -50,7 +50,7 @@ static int pci_pwrctl_pwrseq_probe(struct platform_device *pdev) if (ret) return ret; - data->ctx.dev = dev; + pci_pwrctl_init(&data->ctx, dev); ret = devm_pci_pwrctl_device_set_ready(dev, &data->ctx); if (ret) diff --git a/include/linux/pci-pwrctl.h b/include/linux/pci-pwrctl.h index 45e9cfe740e4..0d23dddf59ec 100644 --- a/include/linux/pci-pwrctl.h +++ b/include/linux/pci-pwrctl.h @@ -7,6 +7,7 @@ #define __PCI_PWRCTL_H__ #include +#include struct device; struct device_link; @@ -41,8 +42,10 @@ struct pci_pwrctl { /* Private: don't use. */ struct notifier_block nb; struct device_link *link; + struct work_struct work; }; +void pci_pwrctl_init(struct pci_pwrctl *pwrctl, struct device *dev); int pci_pwrctl_device_set_ready(struct pci_pwrctl *pwrctl); void pci_pwrctl_device_unset_ready(struct pci_pwrctl *pwrctl); int devm_pci_pwrctl_device_set_ready(struct device *dev, -- cgit v1.2.3 From de6c85bf918ea52d5c680f0d130b37ee2ff152d6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 28 Aug 2024 09:02:47 +0300 Subject: dma-mapping: clearly mark DMA ops as an architecture feature DMA ops are a helper for architectures and not for drivers to override the DMA implementation. Unfortunately driver authors keep ignoring this. Make the fact more clear by renaming the symbol to ARCH_HAS_DMA_OPS and having the two drivers overriding their dma_ops depend on that. These drivers should probably be marked broken, but we can give them a bit of a grace period for that. Signed-off-by: Christoph Hellwig Reviewed-by: Thomas Gleixner Acked-by: Sakari Ailus # for IPU6 Acked-by: Robin Murphy --- arch/Kconfig | 9 +++++++++ arch/alpha/Kconfig | 2 +- arch/arm/Kconfig | 2 +- arch/arm64/Kconfig | 1 + arch/mips/Kconfig | 2 +- arch/parisc/Kconfig | 2 +- arch/powerpc/Kconfig | 2 +- arch/s390/Kconfig | 2 +- arch/sparc/Kconfig | 2 +- arch/x86/Kconfig | 2 +- drivers/macintosh/macio_asic.c | 4 ++-- drivers/media/pci/intel/ipu6/Kconfig | 7 ++++++- drivers/vdpa/Kconfig | 7 ++++++- drivers/xen/Kconfig | 4 ++-- include/linux/device.h | 2 +- include/linux/dma-map-ops.h | 6 +++--- kernel/dma/Kconfig | 9 ++------- kernel/dma/Makefile | 2 +- 18 files changed, 41 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/arch/Kconfig b/arch/Kconfig index 975dd22a2dbd..61c4ec048787 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -17,6 +17,15 @@ config CPU_MITIGATIONS def_bool y endif +# +# Selected by architectures that need custom DMA operations for e.g. legacy +# IOMMUs not handled by dma-iommu. Drivers must never select this symbol. +# +config ARCH_HAS_DMA_OPS + depends on HAS_DMA + select DMA_OPS_HELPERS + bool + menu "General architecture-dependent options" config ARCH_HAS_SUBPAGE_FAULTS diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index 50ff06d5b799..109a4cddcd13 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -4,12 +4,12 @@ config ALPHA default y select ARCH_32BIT_USTAT_F_TINODE select ARCH_HAS_CURRENT_STACK_POINTER + select ARCH_HAS_DMA_OPS if PCI select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO select ARCH_NO_PREEMPT select ARCH_NO_SG_CHAIN select ARCH_USE_CMPXCHG_LOCKREF - select DMA_OPS if PCI select FORCE_PCI select PCI_DOMAINS if PCI select PCI_SYSCALL if PCI diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 54b2bb817a7f..f5f7995a2f8f 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -10,6 +10,7 @@ config ARM select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DEBUG_VIRTUAL if MMU select ARCH_HAS_DMA_ALLOC if MMU + select ARCH_HAS_DMA_OPS select ARCH_HAS_DMA_WRITE_COMBINE if !ARM_DMA_MEM_BUFFERABLE select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FORTIFY_SOURCE @@ -54,7 +55,6 @@ config ARM select DCACHE_WORD_ACCESS if HAVE_EFFICIENT_UNALIGNED_ACCESS select DMA_DECLARE_COHERENT select DMA_GLOBAL_POOL if !MMU - select DMA_OPS select DMA_NONCOHERENT_MMAP if MMU select EDAC_SUPPORT select EDAC_ATOMIC_SCRUB diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index a2f8ff354ca6..40940cbde435 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -24,6 +24,7 @@ config ARM64 select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEBUG_VM_PGTABLE + select ARCH_HAS_DMA_OPS if XEN select ARCH_HAS_DMA_PREP_COHERENT select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI select ARCH_HAS_FAST_MULTIPLIER diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 60077e576935..023ad33a7e94 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -8,6 +8,7 @@ config MIPS select ARCH_HAS_CPU_FINALIZE_INIT select ARCH_HAS_CURRENT_STACK_POINTER if !CC_IS_CLANG || CLANG_VERSION >= 140000 select ARCH_HAS_DEBUG_VIRTUAL if !64BIT + select ARCH_HAS_DMA_OPS if MACH_JAZZ select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_KCOV select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE if !EVA @@ -393,7 +394,6 @@ config MACH_JAZZ select ARC_PROMLIB select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO - select DMA_OPS select FW_ARC select FW_ARC32 select ARCH_MAY_HAVE_PC_FDC diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index b0a2ac3ba916..859835a0692c 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -10,6 +10,7 @@ config PARISC select ARCH_WANT_FRAME_POINTERS select ARCH_HAS_CPU_CACHE_ALIASING select ARCH_HAS_DMA_ALLOC if PA11 + select ARCH_HAS_DMA_OPS select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_STRICT_KERNEL_RWX select ARCH_HAS_STRICT_MODULE_RWX @@ -23,7 +24,6 @@ config PARISC select ARCH_HAS_CACHE_LINE_SIZE select ARCH_HAS_DEBUG_VM_PGTABLE select HAVE_RELIABLE_STACKTRACE - select DMA_OPS select RTC_CLASS select RTC_DRV_GENERIC select INIT_ALL_POSSIBLE diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index d7b09b064a8a..f87fc0375a92 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -133,6 +133,7 @@ config PPC select ARCH_HAS_DEBUG_WX if STRICT_KERNEL_RWX select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_DMA_MAP_DIRECT if PPC_PSERIES + select ARCH_HAS_DMA_OPS if PPC64 select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_KCOV @@ -185,7 +186,6 @@ config PPC select CPUMASK_OFFSTACK if NR_CPUS >= 8192 select DCACHE_WORD_ACCESS if PPC64 && CPU_LITTLE_ENDIAN select DMA_OPS_BYPASS if PPC64 - select DMA_OPS if PPC64 select DYNAMIC_FTRACE if FUNCTION_TRACER select EDAC_ATOMIC_SCRUB select EDAC_SUPPORT diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index a822f952f64a..f31f6b85c25c 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -70,6 +70,7 @@ config S390 select ARCH_HAS_DEBUG_VM_PGTABLE select ARCH_HAS_DEBUG_WX select ARCH_HAS_DEVMEM_IS_ALLOWED + select ARCH_HAS_DMA_OPS if PCI select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FORCE_DMA_UNENCRYPTED select ARCH_HAS_FORTIFY_SOURCE @@ -137,7 +138,6 @@ config S390 select BUILDTIME_TABLE_SORT select CLONE_BACKWARDS2 select DCACHE_WORD_ACCESS if !KMSAN - select DMA_OPS if PCI select DYNAMIC_FTRACE if FUNCTION_TRACER select FUNCTION_ALIGNMENT_8B if CC_IS_GCC select FUNCTION_ALIGNMENT_16B if !CC_IS_GCC diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 11bf9d312318..dcfdb7f1dae9 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -14,9 +14,9 @@ config SPARC bool default y select ARCH_HAS_CPU_CACHE_ALIASING + select ARCH_HAS_DMA_OPS select ARCH_MIGHT_HAVE_PC_PARPORT if SPARC64 && PCI select ARCH_MIGHT_HAVE_PC_SERIO - select DMA_OPS select OF select OF_PROMTREE select HAVE_ASM_MODVERSIONS diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 007bab9f2a0e..9e2e7d361019 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -79,6 +79,7 @@ config X86 select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEBUG_VM_PGTABLE if !X86_PAE select ARCH_HAS_DEVMEM_IS_ALLOWED + select ARCH_HAS_DMA_OPS if GART_IOMMU || XEN select ARCH_HAS_EARLY_DEBUG if KGDB select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FAST_MULTIPLIER @@ -943,7 +944,6 @@ config DMI config GART_IOMMU bool "Old AMD GART IOMMU support" - select DMA_OPS select IOMMU_HELPER select SWIOTLB depends on X86_64 && PCI && AMD_NB diff --git a/drivers/macintosh/macio_asic.c b/drivers/macintosh/macio_asic.c index 13626205530d..bede200e32e8 100644 --- a/drivers/macintosh/macio_asic.c +++ b/drivers/macintosh/macio_asic.c @@ -387,7 +387,7 @@ static struct macio_dev * macio_add_one_device(struct macio_chip *chip, dma_set_max_seg_size(&dev->ofdev.dev, 65536); dma_set_seg_boundary(&dev->ofdev.dev, 0xffffffff); -#if defined(CONFIG_PCI) && defined(CONFIG_DMA_OPS) +#if defined(CONFIG_PCI) && defined(CONFIG_ARCH_HAS_DMA_OPS) /* Set the DMA ops to the ones from the PCI device, this could be * fishy if we didn't know that on PowerMac it's always direct ops * or iommu ops that will work fine @@ -396,7 +396,7 @@ static struct macio_dev * macio_add_one_device(struct macio_chip *chip, */ dev->ofdev.dev.archdata = chip->lbus.pdev->dev.archdata; dev->ofdev.dev.dma_ops = chip->lbus.pdev->dev.dma_ops; -#endif /* CONFIG_PCI && CONFIG_DMA_OPS */ +#endif /* CONFIG_PCI && CONFIG_ARCH_HAS_DMA_OPS */ #ifdef DEBUG printk("preparing mdev @%p, ofdev @%p, dev @%p, kobj @%p\n", diff --git a/drivers/media/pci/intel/ipu6/Kconfig b/drivers/media/pci/intel/ipu6/Kconfig index 40e20f0aa5ae..49e4fb696573 100644 --- a/drivers/media/pci/intel/ipu6/Kconfig +++ b/drivers/media/pci/intel/ipu6/Kconfig @@ -4,8 +4,13 @@ config VIDEO_INTEL_IPU6 depends on VIDEO_DEV depends on X86 && X86_64 && HAS_DMA depends on IPU_BRIDGE || !IPU_BRIDGE + # + # This driver incorrectly tries to override the dma_ops. It should + # never have done that, but for now keep it working on architectures + # that use dma ops + # + depends on ARCH_HAS_DMA_OPS select AUXILIARY_BUS - select DMA_OPS select IOMMU_IOVA select VIDEO_V4L2_SUBDEV_API select MEDIA_CONTROLLER diff --git a/drivers/vdpa/Kconfig b/drivers/vdpa/Kconfig index b08de3b77061..559fb9d3271f 100644 --- a/drivers/vdpa/Kconfig +++ b/drivers/vdpa/Kconfig @@ -35,7 +35,12 @@ config VDPA_SIM_BLOCK config VDPA_USER tristate "VDUSE (vDPA Device in Userspace) support" depends on EVENTFD && MMU && HAS_DMA - select DMA_OPS + # + # This driver incorrectly tries to override the dma_ops. It should + # never have done that, but for now keep it working on architectures + # that use dma ops + # + depends on ARCH_HAS_DMA_OPS select VHOST_IOTLB select IOMMU_IOVA help diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index d5989871dd5d..f7d6f47971fd 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -177,8 +177,8 @@ config XEN_GRANT_DMA_ALLOC config SWIOTLB_XEN def_bool y + depends on ARCH_HAS_DMA_OPS depends on XEN_PV || ARM || ARM64 - select DMA_OPS select SWIOTLB config XEN_PCI_STUB @@ -348,10 +348,10 @@ config XEN_GRANT_DMA_IOMMU config XEN_GRANT_DMA_OPS bool - select DMA_OPS config XEN_VIRTIO bool "Xen virtio support" + depends on ARCH_HAS_DMA_OPS depends on VIRTIO select XEN_GRANT_DMA_OPS select XEN_GRANT_DMA_IOMMU if OF diff --git a/include/linux/device.h b/include/linux/device.h index 1c5280d28bc3..b4bde8d22697 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -750,7 +750,7 @@ struct device { struct dev_pin_info *pins; #endif struct dev_msi_info msi; -#ifdef CONFIG_DMA_OPS +#ifdef CONFIG_ARCH_HAS_DMA_OPS const struct dma_map_ops *dma_ops; #endif u64 *dma_mask; /* dma mask (if dma'able device) */ diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 077b15c93bb8..9668ddf3696e 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -75,7 +75,7 @@ struct dma_map_ops { unsigned long (*get_merge_boundary)(struct device *dev); }; -#ifdef CONFIG_DMA_OPS +#ifdef CONFIG_ARCH_HAS_DMA_OPS #include static inline const struct dma_map_ops *get_dma_ops(struct device *dev) @@ -90,7 +90,7 @@ static inline void set_dma_ops(struct device *dev, { dev->dma_ops = dma_ops; } -#else /* CONFIG_DMA_OPS */ +#else /* CONFIG_ARCH_HAS_DMA_OPS */ static inline const struct dma_map_ops *get_dma_ops(struct device *dev) { return NULL; @@ -99,7 +99,7 @@ static inline void set_dma_ops(struct device *dev, const struct dma_map_ops *dma_ops) { } -#endif /* CONFIG_DMA_OPS */ +#endif /* CONFIG_ARCH_HAS_DMA_OPS */ #ifdef CONFIG_DMA_CMA extern struct cma *dma_contiguous_default_area; diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig index 21bae1700836..4c0dcd909121 100644 --- a/kernel/dma/Kconfig +++ b/kernel/dma/Kconfig @@ -11,11 +11,6 @@ config HAS_DMA config DMA_OPS_HELPERS bool -config DMA_OPS - depends on HAS_DMA - select DMA_OPS_HELPERS - bool - # # IOMMU drivers that can bypass the IOMMU code and optionally use the direct # mapping fast path should select this option and set the dma_ops_bypass @@ -113,8 +108,8 @@ config DMA_BOUNCE_UNALIGNED_KMALLOC config DMA_NEED_SYNC def_bool ARCH_HAS_SYNC_DMA_FOR_DEVICE || ARCH_HAS_SYNC_DMA_FOR_CPU || \ - ARCH_HAS_SYNC_DMA_FOR_CPU_ALL || DMA_API_DEBUG || DMA_OPS || \ - SWIOTLB + ARCH_HAS_SYNC_DMA_FOR_CPU_ALL || DMA_API_DEBUG || \ + ARCH_HAS_DMA_OPS || SWIOTLB config DMA_RESTRICTED_POOL bool "DMA Restricted Pool" diff --git a/kernel/dma/Makefile b/kernel/dma/Makefile index 2e6e933cf7f3..6977033444a3 100644 --- a/kernel/dma/Makefile +++ b/kernel/dma/Makefile @@ -2,7 +2,7 @@ obj-$(CONFIG_HAS_DMA) += mapping.o direct.o obj-$(CONFIG_DMA_OPS_HELPERS) += ops_helpers.o -obj-$(CONFIG_DMA_OPS) += dummy.o +obj-$(CONFIG_ARCH_HAS_DMA_OPS) += dummy.o obj-$(CONFIG_DMA_CMA) += contiguous.o obj-$(CONFIG_DMA_DECLARE_COHERENT) += coherent.o obj-$(CONFIG_DMA_API_DEBUG) += debug.o -- cgit v1.2.3 From 73ed0baae66df50359c876f65f41179d6ebd2716 Mon Sep 17 00:00:00 2001 From: Chris Li Date: Tue, 30 Jul 2024 23:49:13 -0700 Subject: mm: swap: swap cluster switch to double link list MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "mm: swap: mTHP swap allocator base on swap cluster order", v5. This is the short term solutions "swap cluster order" listed in my "Swap Abstraction" discussion slice 8 in the recent LSF/MM conference. When commit 845982eb264bc "mm: swap: allow storage of all mTHP orders" is introduced, it only allocates the mTHP swap entries from the new empty cluster list.  It has a fragmentation issue reported by Barry. https://lore.kernel.org/all/CAGsJ_4zAcJkuW016Cfi6wicRr8N9X+GJJhgMQdSMp+Ah+NSgNQ@mail.gmail.com/ The reason is that all the empty clusters have been exhausted while there are plenty of free swap entries in the cluster that are not 100% free. Remember the swap allocation order in the cluster. Keep track of the per order non full cluster list for later allocation. This series gives the swap SSD allocation a new separate code path from the HDD allocation. The new allocator use cluster list only and do not global scan swap_map[] without lock any more. This streamline the swap allocation for SSD. The code matches the execution flow much better. User impact: For users that allocate and free mix order mTHP swapping, It greatly improves the success rate of the mTHP swap allocation after the initial phase. It also performs faster when the swapfile is close to full, because the allocator can get the non full cluster from a list rather than scanning a lot of swap_map entries.  With Barry's mthp test program V2: Without: $ ./thp_swap_allocator_test -a Iteration 1: swpout inc: 32, swpout fallback inc: 192, Fallback percentage: 85.71% Iteration 2: swpout inc: 0, swpout fallback inc: 231, Fallback percentage: 100.00% Iteration 3: swpout inc: 0, swpout fallback inc: 227, Fallback percentage: 100.00% ... Iteration 98: swpout inc: 0, swpout fallback inc: 224, Fallback percentage: 100.00% Iteration 99: swpout inc: 0, swpout fallback inc: 215, Fallback percentage: 100.00% Iteration 100: swpout inc: 0, swpout fallback inc: 222, Fallback percentage: 100.00% $ ./thp_swap_allocator_test -a -s Iteration 1: swpout inc: 0, swpout fallback inc: 224, Fallback percentage: 100.00% Iteration 2: swpout inc: 0, swpout fallback inc: 218, Fallback percentage: 100.00% Iteration 3: swpout inc: 0, swpout fallback inc: 222, Fallback percentage: 100.00% .. Iteration 98: swpout inc: 0, swpout fallback inc: 228, Fallback percentage: 100.00% Iteration 99: swpout inc: 0, swpout fallback inc: 230, Fallback percentage: 100.00% Iteration 100: swpout inc: 0, swpout fallback inc: 229, Fallback percentage: 100.00% $ ./thp_swap_allocator_test -s Iteration 1: swpout inc: 0, swpout fallback inc: 224, Fallback percentage: 100.00% Iteration 2: swpout inc: 0, swpout fallback inc: 218, Fallback percentage: 100.00% Iteration 3: swpout inc: 0, swpout fallback inc: 222, Fallback percentage: 100.00% .. Iteration 98: swpout inc: 0, swpout fallback inc: 228, Fallback percentage: 100.00% Iteration 99: swpout inc: 0, swpout fallback inc: 230, Fallback percentage: 100.00% Iteration 100: swpout inc: 0, swpout fallback inc: 229, Fallback percentage: 100.00% $ ./thp_swap_allocator_test Iteration 1: swpout inc: 0, swpout fallback inc: 224, Fallback percentage: 100.00% Iteration 2: swpout inc: 0, swpout fallback inc: 218, Fallback percentage: 100.00% Iteration 3: swpout inc: 0, swpout fallback inc: 222, Fallback percentage: 100.00% .. Iteration 98: swpout inc: 0, swpout fallback inc: 228, Fallback percentage: 100.00% Iteration 99: swpout inc: 0, swpout fallback inc: 230, Fallback percentage: 100.00% Iteration 100: swpout inc: 0, swpout fallback inc: 229, Fallback percentage: 100.00% With: # with all 0.00% filter out $ ./thp_swap_allocator_test -a | grep -v "0.00%" $ # all result are 0.00% $ ./thp_swap_allocator_test -a -s | grep -v "0.00%" ./thp_swap_allocator_test -a -s | grep -v "0.00%" Iteration 14: swpout inc: 223, swpout fallback inc: 3, Fallback percentage: 1.33% Iteration 19: swpout inc: 219, swpout fallback inc: 7, Fallback percentage: 3.10% Iteration 28: swpout inc: 225, swpout fallback inc: 1, Fallback percentage: 0.44% Iteration 29: swpout inc: 227, swpout fallback inc: 1, Fallback percentage: 0.44% Iteration 34: swpout inc: 220, swpout fallback inc: 8, Fallback percentage: 3.51% Iteration 35: swpout inc: 222, swpout fallback inc: 11, Fallback percentage: 4.72% Iteration 38: swpout inc: 217, swpout fallback inc: 4, Fallback percentage: 1.81% Iteration 40: swpout inc: 222, swpout fallback inc: 6, Fallback percentage: 2.63% Iteration 42: swpout inc: 221, swpout fallback inc: 2, Fallback percentage: 0.90% Iteration 43: swpout inc: 215, swpout fallback inc: 7, Fallback percentage: 3.15% Iteration 47: swpout inc: 226, swpout fallback inc: 2, Fallback percentage: 0.88% Iteration 49: swpout inc: 217, swpout fallback inc: 1, Fallback percentage: 0.46% Iteration 52: swpout inc: 221, swpout fallback inc: 8, Fallback percentage: 3.49% Iteration 56: swpout inc: 224, swpout fallback inc: 4, Fallback percentage: 1.75% Iteration 58: swpout inc: 214, swpout fallback inc: 5, Fallback percentage: 2.28% Iteration 62: swpout inc: 220, swpout fallback inc: 3, Fallback percentage: 1.35% Iteration 64: swpout inc: 224, swpout fallback inc: 1, Fallback percentage: 0.44% Iteration 67: swpout inc: 221, swpout fallback inc: 1, Fallback percentage: 0.45% Iteration 75: swpout inc: 220, swpout fallback inc: 9, Fallback percentage: 3.93% Iteration 82: swpout inc: 227, swpout fallback inc: 1, Fallback percentage: 0.44% Iteration 86: swpout inc: 211, swpout fallback inc: 12, Fallback percentage: 5.38% Iteration 89: swpout inc: 226, swpout fallback inc: 2, Fallback percentage: 0.88% Iteration 93: swpout inc: 220, swpout fallback inc: 1, Fallback percentage: 0.45% Iteration 94: swpout inc: 224, swpout fallback inc: 1, Fallback percentage: 0.44% Iteration 96: swpout inc: 221, swpout fallback inc: 6, Fallback percentage: 2.64% Iteration 98: swpout inc: 227, swpout fallback inc: 1, Fallback percentage: 0.44% Iteration 99: swpout inc: 227, swpout fallback inc: 3, Fallback percentage: 1.30% $ ./thp_swap_allocator_test ./thp_swap_allocator_test Iteration 1: swpout inc: 233, swpout fallback inc: 0, Fallback percentage: 0.00% Iteration 2: swpout inc: 131, swpout fallback inc: 101, Fallback percentage: 43.53% Iteration 3: swpout inc: 71, swpout fallback inc: 155, Fallback percentage: 68.58% Iteration 4: swpout inc: 55, swpout fallback inc: 168, Fallback percentage: 75.34% Iteration 5: swpout inc: 35, swpout fallback inc: 191, Fallback percentage: 84.51% Iteration 6: swpout inc: 25, swpout fallback inc: 199, Fallback percentage: 88.84% Iteration 7: swpout inc: 23, swpout fallback inc: 205, Fallback percentage: 89.91% Iteration 8: swpout inc: 9, swpout fallback inc: 219, Fallback percentage: 96.05% Iteration 9: swpout inc: 13, swpout fallback inc: 213, Fallback percentage: 94.25% Iteration 10: swpout inc: 12, swpout fallback inc: 216, Fallback percentage: 94.74% Iteration 11: swpout inc: 16, swpout fallback inc: 213, Fallback percentage: 93.01% Iteration 12: swpout inc: 10, swpout fallback inc: 210, Fallback percentage: 95.45% Iteration 13: swpout inc: 16, swpout fallback inc: 212, Fallback percentage: 92.98% Iteration 14: swpout inc: 12, swpout fallback inc: 212, Fallback percentage: 94.64% Iteration 15: swpout inc: 15, swpout fallback inc: 211, Fallback percentage: 93.36% Iteration 16: swpout inc: 15, swpout fallback inc: 200, Fallback percentage: 93.02% Iteration 17: swpout inc: 9, swpout fallback inc: 220, Fallback percentage: 96.07% $ ./thp_swap_allocator_test -s ./thp_swap_allocator_test -s Iteration 1: swpout inc: 233, swpout fallback inc: 0, Fallback percentage: 0.00% Iteration 2: swpout inc: 97, swpout fallback inc: 135, Fallback percentage: 58.19% Iteration 3: swpout inc: 42, swpout fallback inc: 192, Fallback percentage: 82.05% Iteration 4: swpout inc: 19, swpout fallback inc: 214, Fallback percentage: 91.85% Iteration 5: swpout inc: 12, swpout fallback inc: 213, Fallback percentage: 94.67% Iteration 6: swpout inc: 11, swpout fallback inc: 217, Fallback percentage: 95.18% Iteration 7: swpout inc: 9, swpout fallback inc: 214, Fallback percentage: 95.96% Iteration 8: swpout inc: 8, swpout fallback inc: 213, Fallback percentage: 96.38% Iteration 9: swpout inc: 2, swpout fallback inc: 223, Fallback percentage: 99.11% Iteration 10: swpout inc: 2, swpout fallback inc: 228, Fallback percentage: 99.13% Iteration 11: swpout inc: 4, swpout fallback inc: 214, Fallback percentage: 98.17% Iteration 12: swpout inc: 5, swpout fallback inc: 226, Fallback percentage: 97.84% Iteration 13: swpout inc: 3, swpout fallback inc: 212, Fallback percentage: 98.60% Iteration 14: swpout inc: 0, swpout fallback inc: 222, Fallback percentage: 100.00% Iteration 15: swpout inc: 3, swpout fallback inc: 222, Fallback percentage: 98.67% Iteration 16: swpout inc: 4, swpout fallback inc: 223, Fallback percentage: 98.24% ========= Kernel compile under tmpfs with cgroup memory.max = 470M. 12 core 24 hyperthreading, 32 jobs. 10 Run each group SSD swap 10 runs average, 20G swap partition: With: user 2929.064 system 1479.381 : 1376.89 1398.22 1444.64 1477.39 1479.04 1497.27 1504.47 1531.4 1532.92 1551.57 real 1441.324 Without: user 2910.872 system 1482.732 : 1440.01 1451.4 1462.01 1467.47 1467.51 1469.3 1470.19 1496.32 1544.1 1559.01 real 1580.822 Two zram swap: zram0 3.0G zram1 20G. The idea is forcing the zram0 almost full then overflow to zram1: With: user 4320.301 system 4272.403 : 4236.24 4262.81 4264.75 4269.13 4269.44 4273.06 4279.85 4285.98 4289.64 4293.13 real 431.759 Without user 4301.393 system 4387.672 : 4374.47 4378.3 4380.95 4382.84 4383.06 4388.05 4389.76 4397.16 4398.23 4403.9 real 433.979 ------ more test result from Kaiui ---------- Test with build linux kernel using a 4G ZRAM, 1G memory.max limit on top of shmem: System info: 32 Core AMD Zen2, 64G total memory. Test 3 times using only 4K pages: ================================= With: ----- 1838.74user 2411.21system 2:37.86elapsed 2692%CPU (0avgtext+0avgdata 847060maxresident)k 1839.86user 2465.77system 2:39.35elapsed 2701%CPU (0avgtext+0avgdata 847060maxresident)k 1840.26user 2454.68system 2:39.43elapsed 2693%CPU (0avgtext+0avgdata 847060maxresident)k Summary (~4.6% improment of system time): User: 1839.62 System: 2443.89: 2465.77 2454.68 2411.21 Real: 158.88 Without: -------- 1837.99user 2575.95system 2:43.09elapsed 2706%CPU (0avgtext+0avgdata 846520maxresident)k 1838.32user 2555.15system 2:42.52elapsed 2709%CPU (0avgtext+0avgdata 846520maxresident)k 1843.02user 2561.55system 2:43.35elapsed 2702%CPU (0avgtext+0avgdata 846520maxresident)k Summary: User: 1839.78 System: 2564.22: 2575.95 2555.15 2561.55 Real: 162.99 Test 5 times using enabled all mTHP pages: ========================================== With: ----- 1796.44user 2937.33system 2:59.09elapsed 2643%CPU (0avgtext+0avgdata 846936maxresident)k 1802.55user 3002.32system 2:54.68elapsed 2750%CPU (0avgtext+0avgdata 847072maxresident)k 1806.59user 2986.53system 2:55.17elapsed 2736%CPU (0avgtext+0avgdata 847092maxresident)k 1803.27user 2982.40system 2:54.49elapsed 2742%CPU (0avgtext+0avgdata 846796maxresident)k 1807.43user 3036.08system 2:56.06elapsed 2751%CPU (0avgtext+0avgdata 846488maxresident)k Summary (~8.4% improvement of system time): User: 1803.25 System: 2988.93: 2937.33 3002.32 2986.53 2982.40 3036.08 Real: 175.90 mTHP swapout status: /sys/kernel/mm/transparent_hugepage/hugepages-32kB/stats/swpout:347721 /sys/kernel/mm/transparent_hugepage/hugepages-32kB/stats/swpout_fallback:3110 /sys/kernel/mm/transparent_hugepage/hugepages-512kB/stats/swpout:3365 /sys/kernel/mm/transparent_hugepage/hugepages-512kB/stats/swpout_fallback:8269 /sys/kernel/mm/transparent_hugepage/hugepages-2048kB/stats/swpout:24 /sys/kernel/mm/transparent_hugepage/hugepages-2048kB/stats/swpout_fallback:3341 /sys/kernel/mm/transparent_hugepage/hugepages-1024kB/stats/swpout:145 /sys/kernel/mm/transparent_hugepage/hugepages-1024kB/stats/swpout_fallback:5038 /sys/kernel/mm/transparent_hugepage/hugepages-64kB/stats/swpout:322737 /sys/kernel/mm/transparent_hugepage/hugepages-64kB/stats/swpout_fallback:36808 /sys/kernel/mm/transparent_hugepage/hugepages-16kB/stats/swpout:380455 /sys/kernel/mm/transparent_hugepage/hugepages-16kB/stats/swpout_fallback:1010 /sys/kernel/mm/transparent_hugepage/hugepages-256kB/stats/swpout:24973 /sys/kernel/mm/transparent_hugepage/hugepages-256kB/stats/swpout_fallback:13223 /sys/kernel/mm/transparent_hugepage/hugepages-128kB/stats/swpout:197348 /sys/kernel/mm/transparent_hugepage/hugepages-128kB/stats/swpout_fallback:80541 Without: -------- 1794.41user 3151.29system 3:05.97elapsed 2659%CPU (0avgtext+0avgdata 846704maxresident)k 1810.27user 3304.48system 3:05.38elapsed 2759%CPU (0avgtext+0avgdata 846636maxresident)k 1809.84user 3254.85system 3:03.83elapsed 2755%CPU (0avgtext+0avgdata 846952maxresident)k 1813.54user 3259.56system 3:04.28elapsed 2752%CPU (0avgtext+0avgdata 846848maxresident)k 1829.97user 3338.40system 3:07.32elapsed 2759%CPU (0avgtext+0avgdata 847024maxresident)k Summary: User: 1811.61 System: 3261.72 : 3151.29 3304.48 3254.85 3259.56 3338.40 Real: 185.356 mTHP swapout status: hugepages-32kB/stats/swpout:35630 hugepages-32kB/stats/swpout_fallback:1809908 hugepages-512kB/stats/swpout:523 hugepages-512kB/stats/swpout_fallback:55235 hugepages-2048kB/stats/swpout:53 hugepages-2048kB/stats/swpout_fallback:17264 hugepages-1024kB/stats/swpout:85 hugepages-1024kB/stats/swpout_fallback:24979 hugepages-64kB/stats/swpout:30117 hugepages-64kB/stats/swpout_fallback:1825399 hugepages-16kB/stats/swpout:42775 hugepages-16kB/stats/swpout_fallback:1951123 hugepages-256kB/stats/swpout:2326 hugepages-256kB/stats/swpout_fallback:170165 hugepages-128kB/stats/swpout:17925 hugepages-128kB/stats/swpout_fallback:1309757 This patch (of 9): Previously, the swap cluster used a cluster index as a pointer to construct a custom single link list type "swap_cluster_list". The next cluster pointer is shared with the cluster->count. It prevents puting the non free cluster into a list. Change the cluster to use the standard double link list instead. This allows tracing the nonfull cluster in the follow up patch. That way, it is faster to get to the nonfull cluster of that order. Remove the cluster getter/setter for accessing the cluster struct member. The list operation is protected by the swap_info_struct->lock. Change cluster code to use "struct swap_cluster_info *" to reference the cluster rather than by using index. That is more consistent with the list manipulation. It avoids the repeat adding index to the cluser_info. The code is easier to understand. Remove the cluster next pointer is NULL flag, the double link list can handle the empty list pretty well. The "swap_cluster_info" struct is two pointer bigger, because 512 swap entries share one swap_cluster_info struct, it has very little impact on the average memory usage per swap entry. For 1TB swapfile, the swap cluster data structure increases from 8MB to 24MB. Other than the list conversion, there is no real function change in this patch. Link: https://lkml.kernel.org/r/20240730-swap-allocator-v5-0-cb9c148b9297@kernel.org Link: https://lkml.kernel.org/r/20240730-swap-allocator-v5-1-cb9c148b9297@kernel.org Signed-off-by: Chris Li Reported-by: Barry Song <21cnbao@gmail.com> Reviewed-by: "Huang, Ying" Cc: Hugh Dickins Cc: Kairui Song Cc: Kalesh Singh Cc: Ryan Roberts Signed-off-by: Andrew Morton --- include/linux/swap.h | 25 ++---- mm/swapfile.c | 226 ++++++++++++++------------------------------------- 2 files changed, 71 insertions(+), 180 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 5b920fa2315b..ead568f04f81 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -243,22 +243,20 @@ enum { * free clusters are organized into a list. We fetch an entry from the list to * get a free cluster. * - * The data field stores next cluster if the cluster is free or cluster usage - * counter otherwise. The flags field determines if a cluster is free. This is - * protected by swap_info_struct.lock. + * The flags field determines if a cluster is free. This is + * protected by cluster lock. */ struct swap_cluster_info { spinlock_t lock; /* * Protect swap_cluster_info fields - * and swap_info_struct->swap_map - * elements correspond to the swap - * cluster + * other than list, and swap_info_struct->swap_map + * elements corresponding to the swap cluster. */ - unsigned int data:24; - unsigned int flags:8; + u16 count; + u8 flags; + struct list_head list; }; #define CLUSTER_FLAG_FREE 1 /* This cluster is free */ -#define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */ /* * The first page in the swap file is the swap header, which is always marked @@ -283,11 +281,6 @@ struct percpu_cluster { unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */ }; -struct swap_cluster_list { - struct swap_cluster_info head; - struct swap_cluster_info tail; -}; - /* * The in-memory structure used to track swap areas. */ @@ -300,7 +293,7 @@ struct swap_info_struct { unsigned int max; /* extent of the swap_map */ unsigned char *swap_map; /* vmalloc'ed array of usage counts */ struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */ - struct swap_cluster_list free_clusters; /* free clusters list */ + struct list_head free_clusters; /* free clusters list */ unsigned int lowest_bit; /* index of first free in swap_map */ unsigned int highest_bit; /* index of last free in swap_map */ unsigned int pages; /* total of usable pages of swap */ @@ -331,7 +324,7 @@ struct swap_info_struct { * list. */ struct work_struct discard_work; /* discard worker */ - struct swap_cluster_list discard_clusters; /* discard clusters list */ + struct list_head discard_clusters; /* discard clusters list */ struct plist_node avail_lists[]; /* * entries in swap_avail_heads, one * entry per node. diff --git a/mm/swapfile.c b/mm/swapfile.c index 02bb4986a2c2..46d98d804451 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -290,62 +290,15 @@ static void discard_swap_cluster(struct swap_info_struct *si, #endif #define LATENCY_LIMIT 256 -static inline void cluster_set_flag(struct swap_cluster_info *info, - unsigned int flag) -{ - info->flags = flag; -} - -static inline unsigned int cluster_count(struct swap_cluster_info *info) -{ - return info->data; -} - -static inline void cluster_set_count(struct swap_cluster_info *info, - unsigned int c) -{ - info->data = c; -} - -static inline void cluster_set_count_flag(struct swap_cluster_info *info, - unsigned int c, unsigned int f) -{ - info->flags = f; - info->data = c; -} - -static inline unsigned int cluster_next(struct swap_cluster_info *info) -{ - return info->data; -} - -static inline void cluster_set_next(struct swap_cluster_info *info, - unsigned int n) -{ - info->data = n; -} - -static inline void cluster_set_next_flag(struct swap_cluster_info *info, - unsigned int n, unsigned int f) -{ - info->flags = f; - info->data = n; -} - static inline bool cluster_is_free(struct swap_cluster_info *info) { return info->flags & CLUSTER_FLAG_FREE; } -static inline bool cluster_is_null(struct swap_cluster_info *info) -{ - return info->flags & CLUSTER_FLAG_NEXT_NULL; -} - -static inline void cluster_set_null(struct swap_cluster_info *info) +static inline unsigned int cluster_index(struct swap_info_struct *si, + struct swap_cluster_info *ci) { - info->flags = CLUSTER_FLAG_NEXT_NULL; - info->data = 0; + return ci - si->cluster_info; } static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si, @@ -394,65 +347,11 @@ static inline void unlock_cluster_or_swap_info(struct swap_info_struct *si, spin_unlock(&si->lock); } -static inline bool cluster_list_empty(struct swap_cluster_list *list) -{ - return cluster_is_null(&list->head); -} - -static inline unsigned int cluster_list_first(struct swap_cluster_list *list) -{ - return cluster_next(&list->head); -} - -static void cluster_list_init(struct swap_cluster_list *list) -{ - cluster_set_null(&list->head); - cluster_set_null(&list->tail); -} - -static void cluster_list_add_tail(struct swap_cluster_list *list, - struct swap_cluster_info *ci, - unsigned int idx) -{ - if (cluster_list_empty(list)) { - cluster_set_next_flag(&list->head, idx, 0); - cluster_set_next_flag(&list->tail, idx, 0); - } else { - struct swap_cluster_info *ci_tail; - unsigned int tail = cluster_next(&list->tail); - - /* - * Nested cluster lock, but both cluster locks are - * only acquired when we held swap_info_struct->lock - */ - ci_tail = ci + tail; - spin_lock_nested(&ci_tail->lock, SINGLE_DEPTH_NESTING); - cluster_set_next(ci_tail, idx); - spin_unlock(&ci_tail->lock); - cluster_set_next_flag(&list->tail, idx, 0); - } -} - -static unsigned int cluster_list_del_first(struct swap_cluster_list *list, - struct swap_cluster_info *ci) -{ - unsigned int idx; - - idx = cluster_next(&list->head); - if (cluster_next(&list->tail) == idx) { - cluster_set_null(&list->head); - cluster_set_null(&list->tail); - } else - cluster_set_next_flag(&list->head, - cluster_next(&ci[idx]), 0); - - return idx; -} - /* Add a cluster to discard list and schedule it to do discard */ static void swap_cluster_schedule_discard(struct swap_info_struct *si, - unsigned int idx) + struct swap_cluster_info *ci) { + unsigned int idx = cluster_index(si, ci); /* * If scan_swap_map_slots() can't find a free cluster, it will check * si->swap_map directly. To make sure the discarding cluster isn't @@ -462,17 +361,14 @@ static void swap_cluster_schedule_discard(struct swap_info_struct *si, memset(si->swap_map + idx * SWAPFILE_CLUSTER, SWAP_MAP_BAD, SWAPFILE_CLUSTER); - cluster_list_add_tail(&si->discard_clusters, si->cluster_info, idx); - + list_add_tail(&ci->list, &si->discard_clusters); schedule_work(&si->discard_work); } -static void __free_cluster(struct swap_info_struct *si, unsigned long idx) +static void __free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { - struct swap_cluster_info *ci = si->cluster_info; - - cluster_set_flag(ci + idx, CLUSTER_FLAG_FREE); - cluster_list_add_tail(&si->free_clusters, ci, idx); + ci->flags = CLUSTER_FLAG_FREE; + list_add_tail(&ci->list, &si->free_clusters); } /* @@ -481,24 +377,25 @@ static void __free_cluster(struct swap_info_struct *si, unsigned long idx) */ static void swap_do_scheduled_discard(struct swap_info_struct *si) { - struct swap_cluster_info *info, *ci; + struct swap_cluster_info *ci; unsigned int idx; - info = si->cluster_info; - - while (!cluster_list_empty(&si->discard_clusters)) { - idx = cluster_list_del_first(&si->discard_clusters, info); + while (!list_empty(&si->discard_clusters)) { + ci = list_first_entry(&si->discard_clusters, struct swap_cluster_info, list); + list_del(&ci->list); + idx = cluster_index(si, ci); spin_unlock(&si->lock); discard_swap_cluster(si, idx * SWAPFILE_CLUSTER, SWAPFILE_CLUSTER); spin_lock(&si->lock); - ci = lock_cluster(si, idx * SWAPFILE_CLUSTER); - __free_cluster(si, idx); + + spin_lock(&ci->lock); + __free_cluster(si, ci); memset(si->swap_map + idx * SWAPFILE_CLUSTER, 0, SWAPFILE_CLUSTER); - unlock_cluster(ci); + spin_unlock(&ci->lock); } } @@ -521,20 +418,21 @@ static void swap_users_ref_free(struct percpu_ref *ref) complete(&si->comp); } -static void alloc_cluster(struct swap_info_struct *si, unsigned long idx) +static struct swap_cluster_info *alloc_cluster(struct swap_info_struct *si, unsigned long idx) { - struct swap_cluster_info *ci = si->cluster_info; + struct swap_cluster_info *ci = list_first_entry(&si->free_clusters, + struct swap_cluster_info, list); - VM_BUG_ON(cluster_list_first(&si->free_clusters) != idx); - cluster_list_del_first(&si->free_clusters, ci); - cluster_set_count_flag(ci + idx, 0, 0); + VM_BUG_ON(cluster_index(si, ci) != idx); + list_del(&ci->list); + ci->count = 0; + ci->flags = 0; + return ci; } -static void free_cluster(struct swap_info_struct *si, unsigned long idx) +static void free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { - struct swap_cluster_info *ci = si->cluster_info + idx; - - VM_BUG_ON(cluster_count(ci) != 0); + VM_BUG_ON(ci->count != 0); /* * If the swap is discardable, prepare discard the cluster * instead of free it immediately. The cluster will be freed @@ -542,11 +440,11 @@ static void free_cluster(struct swap_info_struct *si, unsigned long idx) */ if ((si->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) == (SWP_WRITEOK | SWP_PAGE_DISCARD)) { - swap_cluster_schedule_discard(si, idx); + swap_cluster_schedule_discard(si, ci); return; } - __free_cluster(si, idx); + __free_cluster(si, ci); } /* @@ -559,15 +457,15 @@ static void add_cluster_info_page(struct swap_info_struct *p, unsigned long count) { unsigned long idx = page_nr / SWAPFILE_CLUSTER; + struct swap_cluster_info *ci = cluster_info + idx; if (!cluster_info) return; - if (cluster_is_free(&cluster_info[idx])) + if (cluster_is_free(ci)) alloc_cluster(p, idx); - VM_BUG_ON(cluster_count(&cluster_info[idx]) + count > SWAPFILE_CLUSTER); - cluster_set_count(&cluster_info[idx], - cluster_count(&cluster_info[idx]) + count); + VM_BUG_ON(ci->count + count > SWAPFILE_CLUSTER); + ci->count += count; } /* @@ -581,24 +479,20 @@ static void inc_cluster_info_page(struct swap_info_struct *p, } /* - * The cluster corresponding to page_nr decreases one usage. If the usage - * counter becomes 0, which means no page in the cluster is in using, we can - * optionally discard the cluster and add it to free cluster list. + * The cluster ci decreases one usage. If the usage counter becomes 0, + * which means no page in the cluster is in use, we can optionally discard + * the cluster and add it to free cluster list. */ -static void dec_cluster_info_page(struct swap_info_struct *p, - struct swap_cluster_info *cluster_info, unsigned long page_nr) +static void dec_cluster_info_page(struct swap_info_struct *p, struct swap_cluster_info *ci) { - unsigned long idx = page_nr / SWAPFILE_CLUSTER; - - if (!cluster_info) + if (!p->cluster_info) return; - VM_BUG_ON(cluster_count(&cluster_info[idx]) == 0); - cluster_set_count(&cluster_info[idx], - cluster_count(&cluster_info[idx]) - 1); + VM_BUG_ON(ci->count == 0); + ci->count--; - if (cluster_count(&cluster_info[idx]) == 0) - free_cluster(p, idx); + if (!ci->count) + free_cluster(p, ci); } /* @@ -611,10 +505,12 @@ scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si, { struct percpu_cluster *percpu_cluster; bool conflict; + struct swap_cluster_info *first = list_first_entry(&si->free_clusters, + struct swap_cluster_info, list); offset /= SWAPFILE_CLUSTER; - conflict = !cluster_list_empty(&si->free_clusters) && - offset != cluster_list_first(&si->free_clusters) && + conflict = !list_empty(&si->free_clusters) && + offset != cluster_index(si, first) && cluster_is_free(&si->cluster_info[offset]); if (!conflict) @@ -655,10 +551,10 @@ new_cluster: cluster = this_cpu_ptr(si->percpu_cluster); tmp = cluster->next[order]; if (tmp == SWAP_NEXT_INVALID) { - if (!cluster_list_empty(&si->free_clusters)) { - tmp = cluster_next(&si->free_clusters.head) * - SWAPFILE_CLUSTER; - } else if (!cluster_list_empty(&si->discard_clusters)) { + if (!list_empty(&si->free_clusters)) { + ci = list_first_entry(&si->free_clusters, struct swap_cluster_info, list); + tmp = cluster_index(si, ci) * SWAPFILE_CLUSTER; + } else if (!list_empty(&si->discard_clusters)) { /* * we don't have free cluster but have some clusters in * discarding, do discard now and reclaim them, then @@ -1062,8 +958,9 @@ static void swap_free_cluster(struct swap_info_struct *si, unsigned long idx) ci = lock_cluster(si, offset); memset(si->swap_map + offset, 0, SWAPFILE_CLUSTER); - cluster_set_count_flag(ci, 0, 0); - free_cluster(si, idx); + ci->count = 0; + ci->flags = 0; + free_cluster(si, ci); unlock_cluster(ci); swap_range_free(si, offset, SWAPFILE_CLUSTER); } @@ -1336,7 +1233,7 @@ static void swap_entry_free(struct swap_info_struct *p, swp_entry_t entry) count = p->swap_map[offset]; VM_BUG_ON(count != SWAP_HAS_CACHE); p->swap_map[offset] = 0; - dec_cluster_info_page(p, p->cluster_info, offset); + dec_cluster_info_page(p, ci); unlock_cluster(ci); mem_cgroup_uncharge_swap(entry, 1); @@ -3011,8 +2908,8 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p, nr_good_pages = maxpages - 1; /* omit header page */ - cluster_list_init(&p->free_clusters); - cluster_list_init(&p->discard_clusters); + INIT_LIST_HEAD(&p->free_clusters); + INIT_LIST_HEAD(&p->discard_clusters); for (i = 0; i < swap_header->info.nr_badpages; i++) { unsigned int page_nr = swap_header->info.badpages[i]; @@ -3063,14 +2960,15 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p, for (k = 0; k < SWAP_CLUSTER_COLS; k++) { j = (k + col) % SWAP_CLUSTER_COLS; for (i = 0; i < DIV_ROUND_UP(nr_clusters, SWAP_CLUSTER_COLS); i++) { + struct swap_cluster_info *ci; idx = i * SWAP_CLUSTER_COLS + j; + ci = cluster_info + idx; if (idx >= nr_clusters) continue; - if (cluster_count(&cluster_info[idx])) + if (ci->count) continue; - cluster_set_flag(&cluster_info[idx], CLUSTER_FLAG_FREE); - cluster_list_add_tail(&p->free_clusters, cluster_info, - idx); + ci->flags = CLUSTER_FLAG_FREE; + list_add_tail(&ci->list, &p->free_clusters); } } return nr_extents; -- cgit v1.2.3 From d07a46a4ac18786e7f4c98fb08525ed80dd1f642 Mon Sep 17 00:00:00 2001 From: Chris Li Date: Tue, 30 Jul 2024 23:49:14 -0700 Subject: mm: swap: mTHP allocate swap entries from nonfull list MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Track the nonfull cluster as well as the empty cluster on lists. Each order has one nonfull cluster list. The cluster will remember which order it was used during new cluster allocation. When the cluster has free entry, add to the nonfull[order] list.  When the free cluster list is empty, also allocate from the nonempty list of that order. This improves the mTHP swap allocation success rate. There are limitations if the distribution of numbers of different orders of mTHP changes a lot. e.g. there are a lot of nonfull cluster assign to order A while later time there are a lot of order B allocation while very little allocation in order A. Currently the cluster used by order A will not reused by order B unless the cluster is 100% empty. Link: https://lkml.kernel.org/r/20240730-swap-allocator-v5-2-cb9c148b9297@kernel.org Signed-off-by: Chris Li Reported-by: Barry Song <21cnbao@gmail.com> Cc: "Huang, Ying" Cc: Hugh Dickins Cc: Kairui Song Cc: Kalesh Singh Cc: Ryan Roberts Signed-off-by: Andrew Morton --- include/linux/swap.h | 4 ++++ mm/swapfile.c | 38 +++++++++++++++++++++++++++++++++++--- 2 files changed, 39 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index ead568f04f81..7007a3c2336c 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -254,9 +254,11 @@ struct swap_cluster_info { */ u16 count; u8 flags; + u8 order; struct list_head list; }; #define CLUSTER_FLAG_FREE 1 /* This cluster is free */ +#define CLUSTER_FLAG_NONFULL 2 /* This cluster is on nonfull list */ /* * The first page in the swap file is the swap header, which is always marked @@ -294,6 +296,8 @@ struct swap_info_struct { unsigned char *swap_map; /* vmalloc'ed array of usage counts */ struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */ struct list_head free_clusters; /* free clusters list */ + struct list_head nonfull_clusters[SWAP_NR_ORDERS]; + /* list of cluster that contains at least one free slot */ unsigned int lowest_bit; /* index of first free in swap_map */ unsigned int highest_bit; /* index of last free in swap_map */ unsigned int pages; /* total of usable pages of swap */ diff --git a/mm/swapfile.c b/mm/swapfile.c index 46d98d804451..b98df62c6c43 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -361,14 +361,22 @@ static void swap_cluster_schedule_discard(struct swap_info_struct *si, memset(si->swap_map + idx * SWAPFILE_CLUSTER, SWAP_MAP_BAD, SWAPFILE_CLUSTER); - list_add_tail(&ci->list, &si->discard_clusters); + VM_BUG_ON(ci->flags & CLUSTER_FLAG_FREE); + if (ci->flags & CLUSTER_FLAG_NONFULL) + list_move_tail(&ci->list, &si->discard_clusters); + else + list_add_tail(&ci->list, &si->discard_clusters); + ci->flags = 0; schedule_work(&si->discard_work); } static void __free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { + if (ci->flags & CLUSTER_FLAG_NONFULL) + list_move_tail(&ci->list, &si->free_clusters); + else + list_add_tail(&ci->list, &si->free_clusters); ci->flags = CLUSTER_FLAG_FREE; - list_add_tail(&ci->list, &si->free_clusters); } /* @@ -491,8 +499,15 @@ static void dec_cluster_info_page(struct swap_info_struct *p, struct swap_cluste VM_BUG_ON(ci->count == 0); ci->count--; - if (!ci->count) + if (!ci->count) { free_cluster(p, ci); + return; + } + + if (!(ci->flags & CLUSTER_FLAG_NONFULL)) { + list_add_tail(&ci->list, &p->nonfull_clusters[ci->order]); + ci->flags |= CLUSTER_FLAG_NONFULL; + } } /* @@ -553,6 +568,19 @@ new_cluster: if (tmp == SWAP_NEXT_INVALID) { if (!list_empty(&si->free_clusters)) { ci = list_first_entry(&si->free_clusters, struct swap_cluster_info, list); + list_del(&ci->list); + spin_lock(&ci->lock); + ci->order = order; + ci->flags = 0; + spin_unlock(&ci->lock); + tmp = cluster_index(si, ci) * SWAPFILE_CLUSTER; + } else if (!list_empty(&si->nonfull_clusters[order])) { + ci = list_first_entry(&si->nonfull_clusters[order], + struct swap_cluster_info, list); + list_del(&ci->list); + spin_lock(&ci->lock); + ci->flags = 0; + spin_unlock(&ci->lock); tmp = cluster_index(si, ci) * SWAPFILE_CLUSTER; } else if (!list_empty(&si->discard_clusters)) { /* @@ -959,6 +987,7 @@ static void swap_free_cluster(struct swap_info_struct *si, unsigned long idx) ci = lock_cluster(si, offset); memset(si->swap_map + offset, 0, SWAPFILE_CLUSTER); ci->count = 0; + ci->order = 0; ci->flags = 0; free_cluster(si, ci); unlock_cluster(ci); @@ -2911,6 +2940,9 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p, INIT_LIST_HEAD(&p->free_clusters); INIT_LIST_HEAD(&p->discard_clusters); + for (i = 0; i < SWAP_NR_ORDERS; i++) + INIT_LIST_HEAD(&p->nonfull_clusters[i]); + for (i = 0; i < swap_header->info.nr_badpages; i++) { unsigned int page_nr = swap_header->info.badpages[i]; if (page_nr == 0 || page_nr > swap_header->info.last_page) -- cgit v1.2.3 From 477cb7ba28892eda112c79d8f75d10edabfc3050 Mon Sep 17 00:00:00 2001 From: Kairui Song Date: Tue, 30 Jul 2024 23:49:19 -0700 Subject: mm: swap: add a fragment cluster list Now swap cluster allocator arranges the clusters in LRU style, so the "cold" cluster stay at the head of nonfull lists are the ones that were used for allocation long time ago and still partially occupied. So if allocator can't find enough contiguous slots to satisfy an high order allocation, it's unlikely there will be slot being free on them to satisfy the allocation, at least in a short period. As a result, nonfull cluster scanning will waste time repeatly scanning the unusable head of the list. Also, multiple CPUs could content on the same head cluster of nonfull list. Unlike free clusters which are removed from the list when any CPU starts using it, nonfull cluster stays on the head. So introduce a new list frag list, all scanned nonfull clusters will be moved to this list. Both for avoiding repeated scanning and contention. Frag list is still used as fallback for allocations, so if one CPU failed to allocate one order of slots, it can still steal other CPU's clusters. And order 0 will favor the fragmented clusters to better protect nonfull clusters If any slots on a fragment list are being freed, move the fragment list back to nonfull list indicating it worth another scan on the cluster. Compared to scan upon freeing a slot, this keep the scanning lazy and save some CPU if there are still other clusters to use. It may seems unneccessay to keep the fragmented cluster on list at all if they can't be used for specific order allocation. But this will start to make sense once reclaim dring scanning is ready. Link: https://lkml.kernel.org/r/20240730-swap-allocator-v5-7-cb9c148b9297@kernel.org Signed-off-by: Kairui Song Reported-by: Barry Song <21cnbao@gmail.com> Cc: Chris Li Cc: "Huang, Ying" Cc: Hugh Dickins Cc: Kalesh Singh Cc: Ryan Roberts Signed-off-by: Andrew Morton --- include/linux/swap.h | 3 +++ mm/swapfile.c | 41 +++++++++++++++++++++++++++++++++++++---- 2 files changed, 40 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 7007a3c2336c..c526cd3e7b31 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -259,6 +259,7 @@ struct swap_cluster_info { }; #define CLUSTER_FLAG_FREE 1 /* This cluster is free */ #define CLUSTER_FLAG_NONFULL 2 /* This cluster is on nonfull list */ +#define CLUSTER_FLAG_FRAG 4 /* This cluster is on nonfull list */ /* * The first page in the swap file is the swap header, which is always marked @@ -298,6 +299,8 @@ struct swap_info_struct { struct list_head free_clusters; /* free clusters list */ struct list_head nonfull_clusters[SWAP_NR_ORDERS]; /* list of cluster that contains at least one free slot */ + struct list_head frag_clusters[SWAP_NR_ORDERS]; + /* list of cluster that are fragmented or contented */ unsigned int lowest_bit; /* index of first free in swap_map */ unsigned int highest_bit; /* index of last free in swap_map */ unsigned int pages; /* total of usable pages of swap */ diff --git a/mm/swapfile.c b/mm/swapfile.c index 5e3c17c6bbd4..b0b726a9bf0a 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -572,7 +572,10 @@ static void dec_cluster_info_page(struct swap_info_struct *p, if (!(ci->flags & CLUSTER_FLAG_NONFULL)) { VM_BUG_ON(ci->flags & CLUSTER_FLAG_FREE); - list_add_tail(&ci->list, &p->nonfull_clusters[ci->order]); + if (ci->flags & CLUSTER_FLAG_FRAG) + list_move_tail(&ci->list, &p->nonfull_clusters[ci->order]); + else + list_add_tail(&ci->list, &p->nonfull_clusters[ci->order]); ci->flags = CLUSTER_FLAG_NONFULL; } } @@ -610,7 +613,8 @@ static inline void cluster_alloc_range(struct swap_info_struct *si, struct swap_ ci->count += nr_pages; if (ci->count == SWAPFILE_CLUSTER) { - VM_BUG_ON(!(ci->flags & (CLUSTER_FLAG_FREE | CLUSTER_FLAG_NONFULL))); + VM_BUG_ON(!(ci->flags & + (CLUSTER_FLAG_FREE | CLUSTER_FLAG_NONFULL | CLUSTER_FLAG_FRAG))); list_del(&ci->list); ci->flags = 0; } @@ -666,6 +670,7 @@ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int o struct percpu_cluster *cluster; struct swap_cluster_info *ci, *n; unsigned int offset, found = 0; + LIST_HEAD(fraged); new_cluster: lockdep_assert_held(&si->lock); @@ -686,13 +691,29 @@ new_cluster: if (order < PMD_ORDER) { list_for_each_entry_safe(ci, n, &si->nonfull_clusters[order], list) { + list_move_tail(&ci->list, &fraged); + ci->flags = CLUSTER_FLAG_FRAG; offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), &found, order, usage); if (found) - goto done; + break; } + + if (!found) { + list_for_each_entry_safe(ci, n, &si->frag_clusters[order], list) { + offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), + &found, order, usage); + if (found) + break; + } + } + + list_splice_tail(&fraged, &si->frag_clusters[order]); } + if (found) + goto done; + if (!list_empty(&si->discard_clusters)) { /* * we don't have free cluster but have some clusters in @@ -706,7 +727,17 @@ new_cluster: if (order) goto done; + /* Order 0 stealing from higher order */ for (int o = 1; o < SWAP_NR_ORDERS; o++) { + if (!list_empty(&si->frag_clusters[o])) { + ci = list_first_entry(&si->frag_clusters[o], + struct swap_cluster_info, list); + offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), &found, + 0, usage); + VM_BUG_ON(!found); + goto done; + } + if (!list_empty(&si->nonfull_clusters[o])) { ci = list_first_entry(&si->nonfull_clusters[o], struct swap_cluster_info, list); @@ -3008,8 +3039,10 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p, INIT_LIST_HEAD(&p->free_clusters); INIT_LIST_HEAD(&p->discard_clusters); - for (i = 0; i < SWAP_NR_ORDERS; i++) + for (i = 0; i < SWAP_NR_ORDERS; i++) { INIT_LIST_HEAD(&p->nonfull_clusters[i]); + INIT_LIST_HEAD(&p->frag_clusters[i]); + } for (i = 0; i < swap_header->info.nr_badpages; i++) { unsigned int page_nr = swap_header->info.badpages[i]; -- cgit v1.2.3 From 661383c6111a38c88df61af6bfbcfacd2ff20a67 Mon Sep 17 00:00:00 2001 From: Kairui Song Date: Tue, 30 Jul 2024 23:49:20 -0700 Subject: mm: swap: relaim the cached parts that got scanned This commit implements reclaim during scan for cluster allocator. Cluster scanning were unable to reuse SWAP_HAS_CACHE slots, which could result in low allocation success rate or early OOM. So to ensure maximum allocation success rate, integrate reclaiming with scanning. If found a range of suitable swap slots but fragmented due to HAS_CACHE, just try to reclaim the slots. Link: https://lkml.kernel.org/r/20240730-swap-allocator-v5-8-cb9c148b9297@kernel.org Signed-off-by: Kairui Song Reported-by: Barry Song <21cnbao@gmail.com> Cc: Chris Li Cc: "Huang, Ying" Cc: Hugh Dickins Cc: Kalesh Singh Cc: Ryan Roberts Signed-off-by: Andrew Morton --- include/linux/swap.h | 1 + mm/swapfile.c | 140 +++++++++++++++++++++++++++++++++++++++------------ 2 files changed, 110 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index c526cd3e7b31..e372122e4f45 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -301,6 +301,7 @@ struct swap_info_struct { /* list of cluster that contains at least one free slot */ struct list_head frag_clusters[SWAP_NR_ORDERS]; /* list of cluster that are fragmented or contented */ + unsigned int frag_cluster_nr[SWAP_NR_ORDERS]; unsigned int lowest_bit; /* index of first free in swap_map */ unsigned int highest_bit; /* index of last free in swap_map */ unsigned int pages; /* total of usable pages of swap */ diff --git a/mm/swapfile.c b/mm/swapfile.c index b0b726a9bf0a..ed5f85504f37 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -513,6 +513,10 @@ static void free_cluster(struct swap_info_struct *si, struct swap_cluster_info * VM_BUG_ON(ci->count != 0); lockdep_assert_held(&si->lock); lockdep_assert_held(&ci->lock); + + if (ci->flags & CLUSTER_FLAG_FRAG) + si->frag_cluster_nr[ci->order]--; + /* * If the swap is discardable, prepare discard the cluster * instead of free it immediately. The cluster will be freed @@ -572,31 +576,84 @@ static void dec_cluster_info_page(struct swap_info_struct *p, if (!(ci->flags & CLUSTER_FLAG_NONFULL)) { VM_BUG_ON(ci->flags & CLUSTER_FLAG_FREE); - if (ci->flags & CLUSTER_FLAG_FRAG) + if (ci->flags & CLUSTER_FLAG_FRAG) { + p->frag_cluster_nr[ci->order]--; list_move_tail(&ci->list, &p->nonfull_clusters[ci->order]); - else + } else { list_add_tail(&ci->list, &p->nonfull_clusters[ci->order]); + } ci->flags = CLUSTER_FLAG_NONFULL; } } -static inline bool cluster_scan_range(struct swap_info_struct *si, unsigned int start, - unsigned int nr_pages) +static bool cluster_reclaim_range(struct swap_info_struct *si, + struct swap_cluster_info *ci, + unsigned long start, unsigned long end) { - unsigned char *p = si->swap_map + start; - unsigned char *end = p + nr_pages; + unsigned char *map = si->swap_map; + unsigned long offset; + + spin_unlock(&ci->lock); + spin_unlock(&si->lock); + + for (offset = start; offset < end; offset++) { + switch (READ_ONCE(map[offset])) { + case 0: + continue; + case SWAP_HAS_CACHE: + if (__try_to_reclaim_swap(si, offset, TTRS_ANYWAY | TTRS_DIRECT) > 0) + continue; + goto out; + default: + goto out; + } + } +out: + spin_lock(&si->lock); + spin_lock(&ci->lock); - while (p < end) - if (*p++) + /* + * Recheck the range no matter reclaim succeeded or not, the slot + * could have been be freed while we are not holding the lock. + */ + for (offset = start; offset < end; offset++) + if (READ_ONCE(map[offset])) return false; return true; } +static bool cluster_scan_range(struct swap_info_struct *si, + struct swap_cluster_info *ci, + unsigned long start, unsigned int nr_pages) +{ + unsigned long offset, end = start + nr_pages; + unsigned char *map = si->swap_map; + bool need_reclaim = false; -static inline void cluster_alloc_range(struct swap_info_struct *si, struct swap_cluster_info *ci, - unsigned int start, unsigned char usage, - unsigned int order) + for (offset = start; offset < end; offset++) { + switch (READ_ONCE(map[offset])) { + case 0: + continue; + case SWAP_HAS_CACHE: + if (!vm_swap_full()) + return false; + need_reclaim = true; + continue; + default: + return false; + } + } + + if (need_reclaim) + return cluster_reclaim_range(si, ci, start, end); + + return true; +} + +static void cluster_alloc_range(struct swap_info_struct *si, struct swap_cluster_info *ci, + unsigned int start, unsigned char usage, + unsigned int order) { unsigned int nr_pages = 1 << order; @@ -615,6 +672,8 @@ static inline void cluster_alloc_range(struct swap_info_struct *si, struct swap_ if (ci->count == SWAPFILE_CLUSTER) { VM_BUG_ON(!(ci->flags & (CLUSTER_FLAG_FREE | CLUSTER_FLAG_NONFULL | CLUSTER_FLAG_FRAG))); + if (ci->flags & CLUSTER_FLAG_FRAG) + si->frag_cluster_nr[ci->order]--; list_del(&ci->list); ci->flags = 0; } @@ -640,7 +699,7 @@ static unsigned int alloc_swap_scan_cluster(struct swap_info_struct *si, unsigne } while (offset <= end) { - if (cluster_scan_range(si, offset, nr_pages)) { + if (cluster_scan_range(si, ci, offset, nr_pages)) { cluster_alloc_range(si, ci, offset, usage, order); *foundp = offset; if (ci->count == SWAPFILE_CLUSTER) { @@ -668,9 +727,8 @@ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int o unsigned char usage) { struct percpu_cluster *cluster; - struct swap_cluster_info *ci, *n; + struct swap_cluster_info *ci; unsigned int offset, found = 0; - LIST_HEAD(fraged); new_cluster: lockdep_assert_held(&si->lock); @@ -690,25 +748,42 @@ new_cluster: } if (order < PMD_ORDER) { - list_for_each_entry_safe(ci, n, &si->nonfull_clusters[order], list) { - list_move_tail(&ci->list, &fraged); + unsigned int frags = 0; + + while (!list_empty(&si->nonfull_clusters[order])) { + ci = list_first_entry(&si->nonfull_clusters[order], + struct swap_cluster_info, list); + list_move_tail(&ci->list, &si->frag_clusters[order]); ci->flags = CLUSTER_FLAG_FRAG; + si->frag_cluster_nr[order]++; offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), &found, order, usage); + frags++; if (found) break; } if (!found) { - list_for_each_entry_safe(ci, n, &si->frag_clusters[order], list) { + /* + * Nonfull clusters are moved to frag tail if we reached + * here, count them too, don't over scan the frag list. + */ + while (frags < si->frag_cluster_nr[order]) { + ci = list_first_entry(&si->frag_clusters[order], + struct swap_cluster_info, list); + /* + * Rotate the frag list to iterate, they were all failing + * high order allocation or moved here due to per-CPU usage, + * this help keeping usable cluster ahead. + */ + list_move_tail(&ci->list, &si->frag_clusters[order]); offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), &found, order, usage); + frags++; if (found) break; } } - - list_splice_tail(&fraged, &si->frag_clusters[order]); } if (found) @@ -729,25 +804,28 @@ new_cluster: /* Order 0 stealing from higher order */ for (int o = 1; o < SWAP_NR_ORDERS; o++) { - if (!list_empty(&si->frag_clusters[o])) { + /* + * Clusters here have at least one usable slots and can't fail order 0 + * allocation, but reclaim may drop si->lock and race with another user. + */ + while (!list_empty(&si->frag_clusters[o])) { ci = list_first_entry(&si->frag_clusters[o], struct swap_cluster_info, list); - offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), &found, - 0, usage); - VM_BUG_ON(!found); - goto done; + offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), + &found, 0, usage); + if (found) + goto done; } - if (!list_empty(&si->nonfull_clusters[o])) { - ci = list_first_entry(&si->nonfull_clusters[o], struct swap_cluster_info, - list); + while (!list_empty(&si->nonfull_clusters[o])) { + ci = list_first_entry(&si->nonfull_clusters[o], + struct swap_cluster_info, list); offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), &found, 0, usage); - VM_BUG_ON(!found); - goto done; + if (found) + goto done; } } - done: cluster->next[order] = offset; return found; @@ -3042,6 +3120,7 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p, for (i = 0; i < SWAP_NR_ORDERS; i++) { INIT_LIST_HEAD(&p->nonfull_clusters[i]); INIT_LIST_HEAD(&p->frag_clusters[i]); + p->frag_cluster_nr[i] = 0; } for (i = 0; i < swap_header->info.nr_badpages; i++) { @@ -3085,7 +3164,6 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p, if (!cluster_info) return nr_extents; - /* * Reduce false cache line sharing between cluster_info and * sharing same address space. -- cgit v1.2.3 From 2cacbdfdee65b18f9952620e762eab043d71b564 Mon Sep 17 00:00:00 2001 From: Kairui Song Date: Tue, 30 Jul 2024 23:49:21 -0700 Subject: mm: swap: add a adaptive full cluster cache reclaim Link all full cluster with one full list, and reclaim from it when the allocation have ran out of all usable clusters. There are many reason a folio can end up being in the swap cache while having no swap count reference. So the best way to search for such slots is still by iterating the swap clusters. With the list as an LRU, iterating from the oldest cluster and keep them rotating is a very doable and clean way to free up potentially not inuse clusters. When any allocation failure, try reclaim and rotate only one cluster. This is adaptive for high order allocations they can tolerate fallback. So this avoids latency, and give the full cluster list an fair chance to get reclaimed. It release the usage stress for the fallback order 0 allocation or following up high order allocation. If the swap device is getting very full, reclaim more aggresively to ensure no OOM will happen. This ensures order 0 heavy workload won't go OOM as order 0 won't fail if any cluster still have any space. [ryncsn@gmail.com: fix discard of full cluster] Link: https://lkml.kernel.org/r/CAMgjq7CWwK75_2Zi5P40K08pk9iqOcuWKL6khu=x4Yg_nXaQag@mail.gmail.com Link: https://lkml.kernel.org/r/20240730-swap-allocator-v5-9-cb9c148b9297@kernel.org Signed-off-by: Kairui Song Reported-by: Barry Song <21cnbao@gmail.com> Cc: Chris Li Cc: "Huang, Ying" Cc: Hugh Dickins Cc: Kalesh Singh Cc: Ryan Roberts Cc: David Hildenbrand Cc: Kairui Song Signed-off-by: Andrew Morton --- include/linux/swap.h | 2 ++ mm/swapfile.c | 68 ++++++++++++++++++++++++++++++++++++++++++---------- 2 files changed, 57 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index e372122e4f45..1c8f844a9f0f 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -260,6 +260,7 @@ struct swap_cluster_info { #define CLUSTER_FLAG_FREE 1 /* This cluster is free */ #define CLUSTER_FLAG_NONFULL 2 /* This cluster is on nonfull list */ #define CLUSTER_FLAG_FRAG 4 /* This cluster is on nonfull list */ +#define CLUSTER_FLAG_FULL 8 /* This cluster is on full list */ /* * The first page in the swap file is the swap header, which is always marked @@ -297,6 +298,7 @@ struct swap_info_struct { unsigned char *swap_map; /* vmalloc'ed array of usage counts */ struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */ struct list_head free_clusters; /* free clusters list */ + struct list_head full_clusters; /* full clusters list */ struct list_head nonfull_clusters[SWAP_NR_ORDERS]; /* list of cluster that contains at least one free slot */ struct list_head frag_clusters[SWAP_NR_ORDERS]; diff --git a/mm/swapfile.c b/mm/swapfile.c index ed5f85504f37..b36a16131696 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -440,10 +440,7 @@ static void swap_cluster_schedule_discard(struct swap_info_struct *si, SWAP_MAP_BAD, SWAPFILE_CLUSTER); VM_BUG_ON(ci->flags & CLUSTER_FLAG_FREE); - if (ci->flags & CLUSTER_FLAG_NONFULL) - list_move_tail(&ci->list, &si->discard_clusters); - else - list_add_tail(&ci->list, &si->discard_clusters); + list_move_tail(&ci->list, &si->discard_clusters); ci->flags = 0; schedule_work(&si->discard_work); } @@ -453,7 +450,7 @@ static void __free_cluster(struct swap_info_struct *si, struct swap_cluster_info lockdep_assert_held(&si->lock); lockdep_assert_held(&ci->lock); - if (ci->flags & CLUSTER_FLAG_NONFULL) + if (ci->flags) list_move_tail(&ci->list, &si->free_clusters); else list_add_tail(&ci->list, &si->free_clusters); @@ -480,7 +477,6 @@ static void swap_do_scheduled_discard(struct swap_info_struct *si) SWAPFILE_CLUSTER); spin_lock(&si->lock); - spin_lock(&ci->lock); __free_cluster(si, ci); memset(si->swap_map + idx * SWAPFILE_CLUSTER, @@ -576,12 +572,9 @@ static void dec_cluster_info_page(struct swap_info_struct *p, if (!(ci->flags & CLUSTER_FLAG_NONFULL)) { VM_BUG_ON(ci->flags & CLUSTER_FLAG_FREE); - if (ci->flags & CLUSTER_FLAG_FRAG) { + if (ci->flags & CLUSTER_FLAG_FRAG) p->frag_cluster_nr[ci->order]--; - list_move_tail(&ci->list, &p->nonfull_clusters[ci->order]); - } else { - list_add_tail(&ci->list, &p->nonfull_clusters[ci->order]); - } + list_move_tail(&ci->list, &p->nonfull_clusters[ci->order]); ci->flags = CLUSTER_FLAG_NONFULL; } } @@ -674,8 +667,8 @@ static void cluster_alloc_range(struct swap_info_struct *si, struct swap_cluster (CLUSTER_FLAG_FREE | CLUSTER_FLAG_NONFULL | CLUSTER_FLAG_FRAG))); if (ci->flags & CLUSTER_FLAG_FRAG) si->frag_cluster_nr[ci->order]--; - list_del(&ci->list); - ci->flags = 0; + list_move_tail(&ci->list, &si->full_clusters); + ci->flags = CLUSTER_FLAG_FULL; } } @@ -718,6 +711,46 @@ done: return offset; } +static void swap_reclaim_full_clusters(struct swap_info_struct *si) +{ + long to_scan = 1; + unsigned long offset, end; + struct swap_cluster_info *ci; + unsigned char *map = si->swap_map; + int nr_reclaim, total_reclaimed = 0; + + if (atomic_long_read(&nr_swap_pages) <= SWAPFILE_CLUSTER) + to_scan = si->inuse_pages / SWAPFILE_CLUSTER; + + while (!list_empty(&si->full_clusters)) { + ci = list_first_entry(&si->full_clusters, struct swap_cluster_info, list); + list_move_tail(&ci->list, &si->full_clusters); + offset = cluster_offset(si, ci); + end = min(si->max, offset + SWAPFILE_CLUSTER); + to_scan--; + + while (offset < end) { + if (READ_ONCE(map[offset]) == SWAP_HAS_CACHE) { + spin_unlock(&si->lock); + nr_reclaim = __try_to_reclaim_swap(si, offset, + TTRS_ANYWAY | TTRS_DIRECT); + spin_lock(&si->lock); + if (nr_reclaim > 0) { + offset += nr_reclaim; + total_reclaimed += nr_reclaim; + continue; + } else if (nr_reclaim < 0) { + offset += -nr_reclaim; + continue; + } + } + offset++; + } + if (to_scan <= 0 || total_reclaimed) + break; + } +} + /* * Try to get swap entries with specified order from current cpu's swap entry * pool (a cluster). This might involve allocating a new cluster for current CPU @@ -826,7 +859,15 @@ new_cluster: goto done; } } + done: + /* Try reclaim from full clusters if device is nearfull */ + if (vm_swap_full() && (!found || (si->pages - si->inuse_pages) < SWAPFILE_CLUSTER)) { + swap_reclaim_full_clusters(si); + if (!found && !order && si->pages != si->inuse_pages) + goto new_cluster; + } + cluster->next[order] = offset; return found; } @@ -3115,6 +3156,7 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p, nr_good_pages = maxpages - 1; /* omit header page */ INIT_LIST_HEAD(&p->free_clusters); + INIT_LIST_HEAD(&p->full_clusters); INIT_LIST_HEAD(&p->discard_clusters); for (i = 0; i < SWAP_NR_ORDERS; i++) { -- cgit v1.2.3 From 46bcce503197d1019ee5c49ccde978e31298e35f Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Wed, 7 Aug 2024 09:40:51 +0300 Subject: arch, mm: move definition of node_data to generic code Every architecture that supports NUMA defines node_data in the same way: struct pglist_data *node_data[MAX_NUMNODES]; No reason to keep multiple copies of this definition and its forward declarations, especially when such forward declaration is the only thing in include/asm/mmzone.h for many architectures. Add definition and declaration of node_data to generic code and drop architecture-specific versions. Link: https://lkml.kernel.org/r/20240807064110.1003856-8-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) Acked-by: David Hildenbrand Reviewed-by: Jonathan Cameron Acked-by: Davidlohr Bueso Tested-by: Zi Yan # for x86_64 and arm64 Tested-by: Jonathan Cameron [arm64 + CXL via QEMU] Acked-by: Dan Williams Cc: Alexander Gordeev Cc: Andreas Larsson Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christophe Leroy Cc: Dave Hansen Cc: David S. Miller Cc: Greg Kroah-Hartman Cc: Heiko Carstens Cc: Huacai Chen Cc: Ingo Molnar Cc: Jiaxun Yang Cc: John Paul Adrian Glaubitz Cc: Jonathan Corbet Cc: Michael Ellerman Cc: Palmer Dabbelt Cc: Rafael J. Wysocki Cc: Rob Herring (Arm) Cc: Samuel Holland Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/arm64/include/asm/Kbuild | 1 + arch/arm64/include/asm/mmzone.h | 13 ------------- arch/arm64/include/asm/topology.h | 1 + arch/loongarch/include/asm/Kbuild | 1 + arch/loongarch/include/asm/mmzone.h | 16 ---------------- arch/loongarch/include/asm/topology.h | 1 + arch/loongarch/kernel/numa.c | 3 --- arch/mips/include/asm/mach-ip27/mmzone.h | 4 ---- arch/mips/include/asm/mach-loongson64/mmzone.h | 4 ---- arch/mips/loongson64/numa.c | 2 -- arch/mips/sgi-ip27/ip27-memory.c | 3 --- arch/powerpc/include/asm/mmzone.h | 6 ------ arch/powerpc/mm/numa.c | 2 -- arch/riscv/include/asm/Kbuild | 1 + arch/riscv/include/asm/mmzone.h | 13 ------------- arch/riscv/include/asm/topology.h | 4 ++++ arch/s390/include/asm/Kbuild | 1 + arch/s390/include/asm/mmzone.h | 17 ----------------- arch/s390/kernel/numa.c | 3 --- arch/sh/include/asm/mmzone.h | 3 --- arch/sh/mm/numa.c | 3 --- arch/sparc/include/asm/mmzone.h | 4 ---- arch/sparc/mm/init_64.c | 2 -- arch/x86/include/asm/Kbuild | 1 + arch/x86/include/asm/mmzone.h | 6 ------ arch/x86/include/asm/mmzone_32.h | 17 ----------------- arch/x86/include/asm/mmzone_64.h | 18 ------------------ arch/x86/mm/numa.c | 3 --- drivers/base/arch_numa.c | 2 -- include/asm-generic/mmzone.h | 5 +++++ include/linux/numa.h | 3 +++ mm/numa.c | 3 +++ 32 files changed, 22 insertions(+), 144 deletions(-) delete mode 100644 arch/arm64/include/asm/mmzone.h delete mode 100644 arch/loongarch/include/asm/mmzone.h delete mode 100644 arch/riscv/include/asm/mmzone.h delete mode 100644 arch/s390/include/asm/mmzone.h delete mode 100644 arch/x86/include/asm/mmzone.h delete mode 100644 arch/x86/include/asm/mmzone_32.h delete mode 100644 arch/x86/include/asm/mmzone_64.h create mode 100644 include/asm-generic/mmzone.h (limited to 'include/linux') diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index 7d7d97ad3cd5..4e350df9a02d 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -9,6 +9,7 @@ syscall-y += unistd_compat_32.h generic-y += early_ioremap.h generic-y += mcs_spinlock.h +generic-y += mmzone.h generic-y += qrwlock.h generic-y += qspinlock.h generic-y += parport.h diff --git a/arch/arm64/include/asm/mmzone.h b/arch/arm64/include/asm/mmzone.h deleted file mode 100644 index fa17e01d9ab2..000000000000 --- a/arch/arm64/include/asm/mmzone.h +++ /dev/null @@ -1,13 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ASM_MMZONE_H -#define __ASM_MMZONE_H - -#ifdef CONFIG_NUMA - -#include - -extern struct pglist_data *node_data[]; -#define NODE_DATA(nid) (node_data[(nid)]) - -#endif /* CONFIG_NUMA */ -#endif /* __ASM_MMZONE_H */ diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h index 0f6ef432fb84..5fc3af9f8f29 100644 --- a/arch/arm64/include/asm/topology.h +++ b/arch/arm64/include/asm/topology.h @@ -5,6 +5,7 @@ #include #ifdef CONFIG_NUMA +#include struct pci_bus; int pcibus_to_node(struct pci_bus *bus); diff --git a/arch/loongarch/include/asm/Kbuild b/arch/loongarch/include/asm/Kbuild index 2bb3676429c0..8fa22cc52774 100644 --- a/arch/loongarch/include/asm/Kbuild +++ b/arch/loongarch/include/asm/Kbuild @@ -9,5 +9,6 @@ generic-y += qrwlock.h generic-y += qspinlock.h generic-y += user.h generic-y += ioctl.h +generic-y += mmzone.h generic-y += statfs.h generic-y += param.h diff --git a/arch/loongarch/include/asm/mmzone.h b/arch/loongarch/include/asm/mmzone.h deleted file mode 100644 index 2b9a90727e19..000000000000 --- a/arch/loongarch/include/asm/mmzone.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Author: Huacai Chen (chenhuacai@loongson.cn) - * Copyright (C) 2020-2022 Loongson Technology Corporation Limited - */ -#ifndef _ASM_MMZONE_H_ -#define _ASM_MMZONE_H_ - -#include -#include - -extern struct pglist_data *node_data[]; - -#define NODE_DATA(nid) (node_data[(nid)]) - -#endif /* _ASM_MMZONE_H_ */ diff --git a/arch/loongarch/include/asm/topology.h b/arch/loongarch/include/asm/topology.h index 66128dec0bf6..50273c9187d0 100644 --- a/arch/loongarch/include/asm/topology.h +++ b/arch/loongarch/include/asm/topology.h @@ -8,6 +8,7 @@ #include #ifdef CONFIG_NUMA +#include extern cpumask_t cpus_on_node[]; diff --git a/arch/loongarch/kernel/numa.c b/arch/loongarch/kernel/numa.c index 8fe21f868f72..acada671e020 100644 --- a/arch/loongarch/kernel/numa.c +++ b/arch/loongarch/kernel/numa.c @@ -27,10 +27,7 @@ #include int numa_off; -struct pglist_data *node_data[MAX_NUMNODES]; unsigned char node_distances[MAX_NUMNODES][MAX_NUMNODES]; - -EXPORT_SYMBOL(node_data); EXPORT_SYMBOL(node_distances); static struct numa_meminfo numa_meminfo; diff --git a/arch/mips/include/asm/mach-ip27/mmzone.h b/arch/mips/include/asm/mach-ip27/mmzone.h index 629c3f290203..56959eb9cb26 100644 --- a/arch/mips/include/asm/mach-ip27/mmzone.h +++ b/arch/mips/include/asm/mach-ip27/mmzone.h @@ -24,8 +24,4 @@ extern struct node_data *__node_data[]; #define hub_data(n) (&__node_data[(n)]->hub) -extern struct pglist_data *node_data[]; - -#define NODE_DATA(nid) (node_data[nid]) - #endif /* _ASM_MACH_MMZONE_H */ diff --git a/arch/mips/include/asm/mach-loongson64/mmzone.h b/arch/mips/include/asm/mach-loongson64/mmzone.h index 2effd5f8ed62..8fb70fd3c9c4 100644 --- a/arch/mips/include/asm/mach-loongson64/mmzone.h +++ b/arch/mips/include/asm/mach-loongson64/mmzone.h @@ -14,10 +14,6 @@ #define pa_to_nid(addr) (((addr) & 0xf00000000000) >> NODE_ADDRSPACE_SHIFT) #define nid_to_addrbase(nid) ((unsigned long)(nid) << NODE_ADDRSPACE_SHIFT) -extern struct pglist_data *node_data[]; - -#define NODE_DATA(n) (node_data[n]) - extern void __init prom_init_numa_memory(void); #endif /* _ASM_MACH_MMZONE_H */ diff --git a/arch/mips/loongson64/numa.c b/arch/mips/loongson64/numa.c index 64fcfaa885b6..d56238745744 100644 --- a/arch/mips/loongson64/numa.c +++ b/arch/mips/loongson64/numa.c @@ -29,8 +29,6 @@ unsigned char __node_distances[MAX_NUMNODES][MAX_NUMNODES]; EXPORT_SYMBOL(__node_distances); -struct pglist_data *node_data[MAX_NUMNODES]; -EXPORT_SYMBOL(node_data); cpumask_t __node_cpumask[MAX_NUMNODES]; EXPORT_SYMBOL(__node_cpumask); diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c index eb6d2fa41a8a..1963313f55d8 100644 --- a/arch/mips/sgi-ip27/ip27-memory.c +++ b/arch/mips/sgi-ip27/ip27-memory.c @@ -34,9 +34,6 @@ #define SLOT_PFNSHIFT (SLOT_SHIFT - PAGE_SHIFT) #define PFN_NASIDSHFT (NASID_SHFT - PAGE_SHIFT) -struct pglist_data *node_data[MAX_NUMNODES]; -EXPORT_SYMBOL(node_data); - struct node_data *__node_data[MAX_NUMNODES]; EXPORT_SYMBOL(__node_data); diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h index da827d2d0866..d99863cd6cde 100644 --- a/arch/powerpc/include/asm/mmzone.h +++ b/arch/powerpc/include/asm/mmzone.h @@ -20,12 +20,6 @@ #ifdef CONFIG_NUMA -extern struct pglist_data *node_data[]; -/* - * Return a pointer to the node data for node n. - */ -#define NODE_DATA(nid) (node_data[nid]) - /* * Following are specific to this numa platform. */ diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index aa89899f0c1a..0744a9a2944b 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -43,11 +43,9 @@ static char *cmdline __initdata; int numa_cpu_lookup_table[NR_CPUS]; cpumask_var_t node_to_cpumask_map[MAX_NUMNODES]; -struct pglist_data *node_data[MAX_NUMNODES]; EXPORT_SYMBOL(numa_cpu_lookup_table); EXPORT_SYMBOL(node_to_cpumask_map); -EXPORT_SYMBOL(node_data); static int primary_domain_index; static int n_mem_addr_cells, n_mem_size_cells; diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild index 5c589770f2a8..1461af12da6e 100644 --- a/arch/riscv/include/asm/Kbuild +++ b/arch/riscv/include/asm/Kbuild @@ -5,6 +5,7 @@ syscall-y += syscall_table_64.h generic-y += early_ioremap.h generic-y += flat.h generic-y += kvm_para.h +generic-y += mmzone.h generic-y += parport.h generic-y += spinlock.h generic-y += spinlock_types.h diff --git a/arch/riscv/include/asm/mmzone.h b/arch/riscv/include/asm/mmzone.h deleted file mode 100644 index fa17e01d9ab2..000000000000 --- a/arch/riscv/include/asm/mmzone.h +++ /dev/null @@ -1,13 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ASM_MMZONE_H -#define __ASM_MMZONE_H - -#ifdef CONFIG_NUMA - -#include - -extern struct pglist_data *node_data[]; -#define NODE_DATA(nid) (node_data[(nid)]) - -#endif /* CONFIG_NUMA */ -#endif /* __ASM_MMZONE_H */ diff --git a/arch/riscv/include/asm/topology.h b/arch/riscv/include/asm/topology.h index 61183688bdd5..fe1a8bf6902d 100644 --- a/arch/riscv/include/asm/topology.h +++ b/arch/riscv/include/asm/topology.h @@ -4,6 +4,10 @@ #include +#ifdef CONFIG_NUMA +#include +#endif + /* Replace task scheduler's default frequency-invariant accounting */ #define arch_scale_freq_tick topology_scale_freq_tick #define arch_set_freq_scale topology_set_freq_scale diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild index 4b904110d27c..297bf7157968 100644 --- a/arch/s390/include/asm/Kbuild +++ b/arch/s390/include/asm/Kbuild @@ -7,3 +7,4 @@ generated-y += unistd_nr.h generic-y += asm-offsets.h generic-y += kvm_types.h generic-y += mcs_spinlock.h +generic-y += mmzone.h diff --git a/arch/s390/include/asm/mmzone.h b/arch/s390/include/asm/mmzone.h deleted file mode 100644 index 73e3e7c6976c..000000000000 --- a/arch/s390/include/asm/mmzone.h +++ /dev/null @@ -1,17 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * NUMA support for s390 - * - * Copyright IBM Corp. 2015 - */ - -#ifndef _ASM_S390_MMZONE_H -#define _ASM_S390_MMZONE_H - -#ifdef CONFIG_NUMA - -extern struct pglist_data *node_data[]; -#define NODE_DATA(nid) (node_data[nid]) - -#endif /* CONFIG_NUMA */ -#endif /* _ASM_S390_MMZONE_H */ diff --git a/arch/s390/kernel/numa.c b/arch/s390/kernel/numa.c index 23ab9f02f278..ddc1448ea2e1 100644 --- a/arch/s390/kernel/numa.c +++ b/arch/s390/kernel/numa.c @@ -14,9 +14,6 @@ #include #include -struct pglist_data *node_data[MAX_NUMNODES]; -EXPORT_SYMBOL(node_data); - void __init numa_setup(void) { int nid; diff --git a/arch/sh/include/asm/mmzone.h b/arch/sh/include/asm/mmzone.h index 7b8dead2723d..63f88b465e39 100644 --- a/arch/sh/include/asm/mmzone.h +++ b/arch/sh/include/asm/mmzone.h @@ -5,9 +5,6 @@ #ifdef CONFIG_NUMA #include -extern struct pglist_data *node_data[]; -#define NODE_DATA(nid) (node_data[nid]) - static inline int pfn_to_nid(unsigned long pfn) { int nid; diff --git a/arch/sh/mm/numa.c b/arch/sh/mm/numa.c index 50f0dc1744d0..9bc212b5e762 100644 --- a/arch/sh/mm/numa.c +++ b/arch/sh/mm/numa.c @@ -14,9 +14,6 @@ #include #include -struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; -EXPORT_SYMBOL_GPL(node_data); - /* * On SH machines the conventional approach is to stash system RAM * in node 0, and other memory blocks in to node 1 and up, ordered by diff --git a/arch/sparc/include/asm/mmzone.h b/arch/sparc/include/asm/mmzone.h index a236d8aa893a..74eb2c71d077 100644 --- a/arch/sparc/include/asm/mmzone.h +++ b/arch/sparc/include/asm/mmzone.h @@ -6,10 +6,6 @@ #include -extern struct pglist_data *node_data[]; - -#define NODE_DATA(nid) (node_data[nid]) - extern int numa_cpu_lookup_table[]; extern cpumask_t numa_cpumask_lookup_table[]; diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 53d7cb5bbffe..c6c7f43cb1e8 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -1115,11 +1115,9 @@ static void init_node_masks_nonnuma(void) } #ifdef CONFIG_NUMA -struct pglist_data *node_data[MAX_NUMNODES]; EXPORT_SYMBOL(numa_cpu_lookup_table); EXPORT_SYMBOL(numa_cpumask_lookup_table); -EXPORT_SYMBOL(node_data); static int scan_pio_for_cfg_handle(struct mdesc_handle *md, u64 pio, u32 cfg_handle) diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild index a192bdea69e2..6c23d1661b17 100644 --- a/arch/x86/include/asm/Kbuild +++ b/arch/x86/include/asm/Kbuild @@ -11,3 +11,4 @@ generated-y += xen-hypercalls.h generic-y += early_ioremap.h generic-y += mcs_spinlock.h +generic-y += mmzone.h diff --git a/arch/x86/include/asm/mmzone.h b/arch/x86/include/asm/mmzone.h deleted file mode 100644 index c41b41edd691..000000000000 --- a/arch/x86/include/asm/mmzone.h +++ /dev/null @@ -1,6 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifdef CONFIG_X86_32 -# include -#else -# include -#endif diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h deleted file mode 100644 index 2d4515e8b7df..000000000000 --- a/arch/x86/include/asm/mmzone_32.h +++ /dev/null @@ -1,17 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Written by Pat Gaughen (gone@us.ibm.com) Mar 2002 - * - */ - -#ifndef _ASM_X86_MMZONE_32_H -#define _ASM_X86_MMZONE_32_H - -#include - -#ifdef CONFIG_NUMA -extern struct pglist_data *node_data[]; -#define NODE_DATA(nid) (node_data[nid]) -#endif /* CONFIG_NUMA */ - -#endif /* _ASM_X86_MMZONE_32_H */ diff --git a/arch/x86/include/asm/mmzone_64.h b/arch/x86/include/asm/mmzone_64.h deleted file mode 100644 index 0c585046f744..000000000000 --- a/arch/x86/include/asm/mmzone_64.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* K8 NUMA support */ -/* Copyright 2002,2003 by Andi Kleen, SuSE Labs */ -/* 2.5 Version loosely based on the NUMAQ Code by Pat Gaughen. */ -#ifndef _ASM_X86_MMZONE_64_H -#define _ASM_X86_MMZONE_64_H - -#ifdef CONFIG_NUMA - -#include -#include - -extern struct pglist_data *node_data[]; - -#define NODE_DATA(nid) (node_data[nid]) - -#endif -#endif /* _ASM_X86_MMZONE_64_H */ diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 6ce10e3c6228..7de725d6bb05 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -24,9 +24,6 @@ int numa_off; nodemask_t numa_nodes_parsed __initdata; -struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; -EXPORT_SYMBOL(node_data); - static struct numa_meminfo numa_meminfo __initdata_or_meminfo; static struct numa_meminfo numa_reserved_meminfo __initdata_or_meminfo; diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c index 555aee3ee8e7..ceac5b59bf2b 100644 --- a/drivers/base/arch_numa.c +++ b/drivers/base/arch_numa.c @@ -15,8 +15,6 @@ #include -struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; -EXPORT_SYMBOL(node_data); nodemask_t numa_nodes_parsed __initdata; static int cpu_to_node_map[NR_CPUS] = { [0 ... NR_CPUS-1] = NUMA_NO_NODE }; diff --git a/include/asm-generic/mmzone.h b/include/asm-generic/mmzone.h new file mode 100644 index 000000000000..2ab5193e8394 --- /dev/null +++ b/include/asm-generic/mmzone.h @@ -0,0 +1,5 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_GENERIC_MMZONE_H +#define _ASM_GENERIC_MMZONE_H + +#endif diff --git a/include/linux/numa.h b/include/linux/numa.h index eb19503604fe..e5841d4057ab 100644 --- a/include/linux/numa.h +++ b/include/linux/numa.h @@ -30,6 +30,9 @@ static inline bool numa_valid_node(int nid) #ifdef CONFIG_NUMA #include +extern struct pglist_data *node_data[]; +#define NODE_DATA(nid) (node_data[nid]) + /* Generic implementation available */ int numa_nearest_node(int node, unsigned int state); diff --git a/mm/numa.c b/mm/numa.c index 67ca6b8585c0..8c157d41c026 100644 --- a/mm/numa.c +++ b/mm/numa.c @@ -3,6 +3,9 @@ #include #include +struct pglist_data *node_data[MAX_NUMNODES]; +EXPORT_SYMBOL(node_data); + /* Stub functions: */ #ifndef memory_add_physaddr_to_nid -- cgit v1.2.3 From ec164cf1dd3df4ae58931b9b491b06a90d5c22d3 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Wed, 7 Aug 2024 09:40:52 +0300 Subject: mm: drop CONFIG_HAVE_ARCH_NODEDATA_EXTENSION There are no users of HAVE_ARCH_NODEDATA_EXTENSION left, so arch_alloc_nodedata() and arch_refresh_nodedata() are not needed anymore. Replace the call to arch_alloc_nodedata() in free_area_init() with a new helper alloc_offline_node_data(), remove arch_refresh_nodedata() and cleanup include/linux/memory_hotplug.h from the associated ifdefery. Link: https://lkml.kernel.org/r/20240807064110.1003856-9-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) Tested-by: Zi Yan # for x86_64 and arm64 Acked-by: Dan Williams Cc: Alexander Gordeev Cc: Andreas Larsson Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christophe Leroy Cc: Dave Hansen Cc: David Hildenbrand Cc: Davidlohr Bueso Cc: David S. Miller Cc: Greg Kroah-Hartman Cc: Heiko Carstens Cc: Huacai Chen Cc: Ingo Molnar Cc: Jiaxun Yang Cc: John Paul Adrian Glaubitz Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Michael Ellerman Cc: Palmer Dabbelt Cc: Rafael J. Wysocki Cc: Rob Herring (Arm) Cc: Samuel Holland Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/memory_hotplug.h | 48 ------------------------------------------ include/linux/numa.h | 4 ++++ mm/mm_init.c | 10 ++------- mm/numa.c | 12 +++++++++++ 4 files changed, 18 insertions(+), 56 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index ebe876930e78..b27ddce5d324 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -16,54 +16,6 @@ struct resource; struct vmem_altmap; struct dev_pagemap; -#ifdef CONFIG_HAVE_ARCH_NODEDATA_EXTENSION -/* - * For supporting node-hotadd, we have to allocate a new pgdat. - * - * If an arch has generic style NODE_DATA(), - * node_data[nid] = kzalloc() works well. But it depends on the architecture. - * - * In general, generic_alloc_nodedata() is used. - * - */ -extern pg_data_t *arch_alloc_nodedata(int nid); -extern void arch_refresh_nodedata(int nid, pg_data_t *pgdat); - -#else /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */ - -#define arch_alloc_nodedata(nid) generic_alloc_nodedata(nid) - -#ifdef CONFIG_NUMA -/* - * XXX: node aware allocation can't work well to get new node's memory at this time. - * Because, pgdat for the new node is not allocated/initialized yet itself. - * To use new node's memory, more consideration will be necessary. - */ -#define generic_alloc_nodedata(nid) \ -({ \ - memblock_alloc(sizeof(*pgdat), SMP_CACHE_BYTES); \ -}) - -extern pg_data_t *node_data[]; -static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) -{ - node_data[nid] = pgdat; -} - -#else /* !CONFIG_NUMA */ - -/* never called */ -static inline pg_data_t *generic_alloc_nodedata(int nid) -{ - BUG(); - return NULL; -} -static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) -{ -} -#endif /* CONFIG_NUMA */ -#endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */ - #ifdef CONFIG_MEMORY_HOTPLUG struct page *pfn_to_online_page(unsigned long pfn); diff --git a/include/linux/numa.h b/include/linux/numa.h index e5841d4057ab..b41b1569781b 100644 --- a/include/linux/numa.h +++ b/include/linux/numa.h @@ -33,6 +33,8 @@ static inline bool numa_valid_node(int nid) extern struct pglist_data *node_data[]; #define NODE_DATA(nid) (node_data[nid]) +void __init alloc_offline_node_data(int nid); + /* Generic implementation available */ int numa_nearest_node(int node, unsigned int state); @@ -60,6 +62,8 @@ static inline int phys_to_target_node(u64 start) { return 0; } + +static inline void alloc_offline_node_data(int nid) {} #endif #define numa_map_to_online_node(node) numa_nearest_node(node, N_ONLINE) diff --git a/mm/mm_init.c b/mm/mm_init.c index f3106b6299d3..4ba5607aaf19 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -1835,14 +1835,8 @@ void __init free_area_init(unsigned long *max_zone_pfn) for_each_node(nid) { pg_data_t *pgdat; - if (!node_online(nid)) { - /* Allocator not initialized yet */ - pgdat = arch_alloc_nodedata(nid); - if (!pgdat) - panic("Cannot allocate %zuB for node %d.\n", - sizeof(*pgdat), nid); - arch_refresh_nodedata(nid, pgdat); - } + if (!node_online(nid)) + alloc_offline_node_data(nid); pgdat = NODE_DATA(nid); free_area_init_node(nid); diff --git a/mm/numa.c b/mm/numa.c index 8c157d41c026..64e1b7d2c1ee 100644 --- a/mm/numa.c +++ b/mm/numa.c @@ -6,6 +6,18 @@ struct pglist_data *node_data[MAX_NUMNODES]; EXPORT_SYMBOL(node_data); +void __init alloc_offline_node_data(int nid) +{ + pg_data_t *pgdat; + + pgdat = memblock_alloc(sizeof(*pgdat), SMP_CACHE_BYTES); + if (!pgdat) + panic("Cannot allocate %zuB for node %d.\n", + sizeof(*pgdat), nid); + + node_data[nid] = pgdat; +} + /* Stub functions: */ #ifndef memory_add_physaddr_to_nid -- cgit v1.2.3 From 3515863d9f29dd476cdad875fbd558fc85b4c511 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Wed, 7 Aug 2024 09:40:53 +0300 Subject: arch, mm: pull out allocation of NODE_DATA to generic code Architectures that support NUMA duplicate the code that allocates NODE_DATA on the node-local memory with slight variations in reporting of the addresses where the memory was allocated. Use x86 version as the basis for the generic alloc_node_data() function and call this function in architecture specific numa initialization. Round up node data size to SMP_CACHE_BYTES rather than to PAGE_SIZE like x86 used to do since the bootmem era when allocation granularity was PAGE_SIZE anyway. Link: https://lkml.kernel.org/r/20240807064110.1003856-10-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) Acked-by: David Hildenbrand Reviewed-by: Jonathan Cameron Tested-by: Zi Yan # for x86_64 and arm64 Tested-by: Jonathan Cameron [arm64 + CXL via QEMU] Acked-by: Dan Williams Cc: Alexander Gordeev Cc: Andreas Larsson Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christophe Leroy Cc: Dave Hansen Cc: Davidlohr Bueso Cc: David S. Miller Cc: Greg Kroah-Hartman Cc: Heiko Carstens Cc: Huacai Chen Cc: Ingo Molnar Cc: Jiaxun Yang Cc: John Paul Adrian Glaubitz Cc: Jonathan Corbet Cc: Michael Ellerman Cc: Palmer Dabbelt Cc: Rafael J. Wysocki Cc: Rob Herring (Arm) Cc: Samuel Holland Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/loongarch/kernel/numa.c | 18 ------------------ arch/mips/loongson64/numa.c | 16 ++-------------- arch/powerpc/mm/numa.c | 24 +++--------------------- arch/sh/mm/init.c | 7 +------ arch/sparc/mm/init_64.c | 9 ++------- arch/x86/mm/numa.c | 34 +--------------------------------- drivers/base/arch_numa.c | 21 +-------------------- include/linux/numa.h | 1 + mm/numa.c | 27 +++++++++++++++++++++++++++ 9 files changed, 38 insertions(+), 119 deletions(-) (limited to 'include/linux') diff --git a/arch/loongarch/kernel/numa.c b/arch/loongarch/kernel/numa.c index acada671e020..84fe7f854820 100644 --- a/arch/loongarch/kernel/numa.c +++ b/arch/loongarch/kernel/numa.c @@ -187,24 +187,6 @@ int __init numa_add_memblk(int nid, u64 start, u64 end) return numa_add_memblk_to(nid, start, end, &numa_meminfo); } -static void __init alloc_node_data(int nid) -{ - void *nd; - unsigned long nd_pa; - size_t nd_sz = roundup(sizeof(pg_data_t), PAGE_SIZE); - - nd_pa = memblock_phys_alloc_try_nid(nd_sz, SMP_CACHE_BYTES, nid); - if (!nd_pa) { - pr_err("Cannot find %zu Byte for node_data (initial node: %d)\n", nd_sz, nid); - return; - } - - nd = __va(nd_pa); - - node_data[nid] = nd; - memset(nd, 0, sizeof(pg_data_t)); -} - static void __init node_mem_init(unsigned int node) { unsigned long start_pfn, end_pfn; diff --git a/arch/mips/loongson64/numa.c b/arch/mips/loongson64/numa.c index d56238745744..8388400d052f 100644 --- a/arch/mips/loongson64/numa.c +++ b/arch/mips/loongson64/numa.c @@ -81,12 +81,8 @@ static void __init init_topology_matrix(void) static void __init node_mem_init(unsigned int node) { - struct pglist_data *nd; unsigned long node_addrspace_offset; unsigned long start_pfn, end_pfn; - unsigned long nd_pa; - int tnid; - const size_t nd_size = roundup(sizeof(pg_data_t), SMP_CACHE_BYTES); node_addrspace_offset = nid_to_addrbase(node); pr_info("Node%d's addrspace_offset is 0x%lx\n", @@ -96,16 +92,8 @@ static void __init node_mem_init(unsigned int node) pr_info("Node%d: start_pfn=0x%lx, end_pfn=0x%lx\n", node, start_pfn, end_pfn); - nd_pa = memblock_phys_alloc_try_nid(nd_size, SMP_CACHE_BYTES, node); - if (!nd_pa) - panic("Cannot allocate %zu bytes for node %d data\n", - nd_size, node); - nd = __va(nd_pa); - memset(nd, 0, sizeof(struct pglist_data)); - tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT); - if (tnid != node) - pr_info("NODE_DATA(%d) on node %d\n", node, tnid); - node_data[node] = nd; + alloc_node_data(node); + NODE_DATA(node)->node_start_pfn = start_pfn; NODE_DATA(node)->node_spanned_pages = end_pfn - start_pfn; diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 0744a9a2944b..3c1da08304d0 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1093,27 +1093,9 @@ void __init dump_numa_cpu_topology(void) static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn) { u64 spanned_pages = end_pfn - start_pfn; - const size_t nd_size = roundup(sizeof(pg_data_t), SMP_CACHE_BYTES); - u64 nd_pa; - void *nd; - int tnid; - - nd_pa = memblock_phys_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); - if (!nd_pa) - panic("Cannot allocate %zu bytes for node %d data\n", - nd_size, nid); - - nd = __va(nd_pa); - - /* report and initialize */ - pr_info(" NODE_DATA [mem %#010Lx-%#010Lx]\n", - nd_pa, nd_pa + nd_size - 1); - tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT); - if (tnid != nid) - pr_info(" NODE_DATA(%d) on node %d\n", nid, tnid); - - node_data[nid] = nd; - memset(NODE_DATA(nid), 0, sizeof(pg_data_t)); + + alloc_node_data(nid); + NODE_DATA(nid)->node_id = nid; NODE_DATA(nid)->node_start_pfn = start_pfn; NODE_DATA(nid)->node_spanned_pages = spanned_pages; diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index d1fe90b2f5ff..2a88b0c9e70f 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -212,12 +212,7 @@ void __init allocate_pgdat(unsigned int nid) get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); #ifdef CONFIG_NUMA - NODE_DATA(nid) = memblock_alloc_try_nid( - sizeof(struct pglist_data), - SMP_CACHE_BYTES, MEMBLOCK_LOW_LIMIT, - MEMBLOCK_ALLOC_ACCESSIBLE, nid); - if (!NODE_DATA(nid)) - panic("Can't allocate pgdat for node %d\n", nid); + alloc_node_data(nid); #endif NODE_DATA(nid)->node_start_pfn = start_pfn; diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index c6c7f43cb1e8..21f8cbbd0581 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -1075,14 +1075,9 @@ static void __init allocate_node_data(int nid) { struct pglist_data *p; unsigned long start_pfn, end_pfn; -#ifdef CONFIG_NUMA - NODE_DATA(nid) = memblock_alloc_node(sizeof(struct pglist_data), - SMP_CACHE_BYTES, nid); - if (!NODE_DATA(nid)) { - prom_printf("Cannot allocate pglist_data for nid[%d]\n", nid); - prom_halt(); - } +#ifdef CONFIG_NUMA + alloc_node_data(nid); NODE_DATA(nid)->node_id = nid; #endif diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 7de725d6bb05..5e1dde26674b 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -191,39 +191,6 @@ int __init numa_add_memblk(int nid, u64 start, u64 end) return numa_add_memblk_to(nid, start, end, &numa_meminfo); } -/* Allocate NODE_DATA for a node on the local memory */ -static void __init alloc_node_data(int nid) -{ - const size_t nd_size = roundup(sizeof(pg_data_t), PAGE_SIZE); - u64 nd_pa; - void *nd; - int tnid; - - /* - * Allocate node data. Try node-local memory and then any node. - * Never allocate in DMA zone. - */ - nd_pa = memblock_phys_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); - if (!nd_pa) { - pr_err("Cannot find %zu bytes in any node (initial node: %d)\n", - nd_size, nid); - return; - } - nd = __va(nd_pa); - - /* report and initialize */ - printk(KERN_INFO "NODE_DATA(%d) allocated [mem %#010Lx-%#010Lx]\n", nid, - nd_pa, nd_pa + nd_size - 1); - tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT); - if (tnid != nid) - printk(KERN_INFO " NODE_DATA(%d) on node %d\n", nid, tnid); - - node_data[nid] = nd; - memset(NODE_DATA(nid), 0, sizeof(pg_data_t)); - - node_set_online(nid); -} - /** * numa_cleanup_meminfo - Cleanup a numa_meminfo * @mi: numa_meminfo to clean up @@ -571,6 +538,7 @@ static int __init numa_register_memblks(struct numa_meminfo *mi) continue; alloc_node_data(nid); + node_set_online(nid); } /* Dump memblock with node info and return. */ diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c index ceac5b59bf2b..b6af7475ec44 100644 --- a/drivers/base/arch_numa.c +++ b/drivers/base/arch_numa.c @@ -216,30 +216,11 @@ int __init numa_add_memblk(int nid, u64 start, u64 end) */ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn) { - const size_t nd_size = roundup(sizeof(pg_data_t), SMP_CACHE_BYTES); - u64 nd_pa; - void *nd; - int tnid; - if (start_pfn >= end_pfn) pr_info("Initmem setup node %d []\n", nid); - nd_pa = memblock_phys_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); - if (!nd_pa) - panic("Cannot allocate %zu bytes for node %d data\n", - nd_size, nid); - - nd = __va(nd_pa); - - /* report and initialize */ - pr_info("NODE_DATA [mem %#010Lx-%#010Lx]\n", - nd_pa, nd_pa + nd_size - 1); - tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT); - if (tnid != nid) - pr_info("NODE_DATA(%d) on node %d\n", nid, tnid); + alloc_node_data(nid); - node_data[nid] = nd; - memset(NODE_DATA(nid), 0, sizeof(pg_data_t)); NODE_DATA(nid)->node_id = nid; NODE_DATA(nid)->node_start_pfn = start_pfn; NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn; diff --git a/include/linux/numa.h b/include/linux/numa.h index b41b1569781b..3567e40329eb 100644 --- a/include/linux/numa.h +++ b/include/linux/numa.h @@ -33,6 +33,7 @@ static inline bool numa_valid_node(int nid) extern struct pglist_data *node_data[]; #define NODE_DATA(nid) (node_data[nid]) +void __init alloc_node_data(int nid); void __init alloc_offline_node_data(int nid); /* Generic implementation available */ diff --git a/mm/numa.c b/mm/numa.c index 64e1b7d2c1ee..1f1582dcdf4a 100644 --- a/mm/numa.c +++ b/mm/numa.c @@ -1,11 +1,38 @@ // SPDX-License-Identifier: GPL-2.0-or-later +#include #include #include struct pglist_data *node_data[MAX_NUMNODES]; EXPORT_SYMBOL(node_data); +/* Allocate NODE_DATA for a node on the local memory */ +void __init alloc_node_data(int nid) +{ + const size_t nd_size = roundup(sizeof(pg_data_t), SMP_CACHE_BYTES); + u64 nd_pa; + void *nd; + int tnid; + + /* Allocate node data. Try node-local memory and then any node. */ + nd_pa = memblock_phys_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); + if (!nd_pa) + panic("Cannot allocate %zu bytes for node %d data\n", + nd_size, nid); + nd = __va(nd_pa); + + /* report and initialize */ + pr_info("NODE_DATA(%d) allocated [mem %#010Lx-%#010Lx]\n", nid, + nd_pa, nd_pa + nd_size - 1); + tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT); + if (tnid != nid) + pr_info(" NODE_DATA(%d) on node %d\n", nid, tnid); + + node_data[nid] = nd; + memset(NODE_DATA(nid), 0, sizeof(pg_data_t)); +} + void __init alloc_offline_node_data(int nid) { pg_data_t *pgdat; -- cgit v1.2.3 From 87482708210ff3333adab4dc5f1a491793159d43 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Wed, 7 Aug 2024 09:41:01 +0300 Subject: mm: introduce numa_memblks Move code dealing with numa_memblks from arch/x86 to mm/ and add Kconfig options to let x86 select it in its Kconfig. This code will be later reused by arch_numa. No functional changes. Link: https://lkml.kernel.org/r/20240807064110.1003856-18-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) Tested-by: Zi Yan # for x86_64 and arm64 Reviewed-by: Jonathan Cameron Tested-by: Jonathan Cameron [arm64 + CXL via QEMU] Acked-by: Dan Williams Acked-by: David Hildenbrand Cc: Alexander Gordeev Cc: Andreas Larsson Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christophe Leroy Cc: Dave Hansen Cc: Davidlohr Bueso Cc: David S. Miller Cc: Greg Kroah-Hartman Cc: Heiko Carstens Cc: Huacai Chen Cc: Ingo Molnar Cc: Jiaxun Yang Cc: John Paul Adrian Glaubitz Cc: Jonathan Corbet Cc: Michael Ellerman Cc: Palmer Dabbelt Cc: Rafael J. Wysocki Cc: Rob Herring (Arm) Cc: Samuel Holland Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/x86/Kconfig | 1 + arch/x86/include/asm/numa.h | 3 - arch/x86/mm/amdtopology.c | 1 + arch/x86/mm/numa.c | 372 +---------------------------------------- arch/x86/mm/numa_emulation.c | 1 + arch/x86/mm/numa_internal.h | 15 +- drivers/acpi/numa/srat.c | 1 + drivers/of/of_numa.c | 1 + include/linux/numa_memblks.h | 35 ++++ mm/Kconfig | 3 + mm/Makefile | 1 + mm/numa_memblks.c | 385 +++++++++++++++++++++++++++++++++++++++++++ 12 files changed, 436 insertions(+), 383 deletions(-) create mode 100644 include/linux/numa_memblks.h create mode 100644 mm/numa_memblks.c (limited to 'include/linux') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 007bab9f2a0e..74afb59c6603 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -296,6 +296,7 @@ config X86 select NEED_PER_CPU_EMBED_FIRST_CHUNK select NEED_PER_CPU_PAGE_FIRST_CHUNK select NEED_SG_DMA_LENGTH + select NUMA_MEMBLKS if NUMA select PCI_DOMAINS if PCI select PCI_LOCKLESS_CONFIG if PCI select PERF_EVENTS diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h index 6fa5ea925aac..6e9a50bf03d4 100644 --- a/arch/x86/include/asm/numa.h +++ b/arch/x86/include/asm/numa.h @@ -10,8 +10,6 @@ #ifdef CONFIG_NUMA -#define NR_NODE_MEMBLKS (MAX_NUMNODES*2) - extern int numa_off; /* @@ -25,7 +23,6 @@ extern int numa_off; extern s16 __apicid_to_node[MAX_LOCAL_APIC]; extern nodemask_t numa_nodes_parsed __initdata; -extern int __init numa_add_memblk(int nodeid, u64 start, u64 end); extern void __init numa_set_distance(int from, int to, int distance); static inline void set_apicid_to_node(int apicid, s16 node) diff --git a/arch/x86/mm/amdtopology.c b/arch/x86/mm/amdtopology.c index 9332b36a1091..628833afee37 100644 --- a/arch/x86/mm/amdtopology.c +++ b/arch/x86/mm/amdtopology.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index bf56f667fe0f..0bada905f409 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -22,10 +23,6 @@ #include "numa_internal.h" int numa_off; -nodemask_t numa_nodes_parsed __initdata; - -static struct numa_meminfo numa_meminfo __initdata_or_meminfo; -static struct numa_meminfo numa_reserved_meminfo __initdata_or_meminfo; static int numa_distance_cnt; static u8 *numa_distance; @@ -121,194 +118,6 @@ void __init setup_node_to_cpumask_map(void) pr_debug("Node to cpumask map for %u nodes\n", nr_node_ids); } -static int __init numa_add_memblk_to(int nid, u64 start, u64 end, - struct numa_meminfo *mi) -{ - /* ignore zero length blks */ - if (start == end) - return 0; - - /* whine about and ignore invalid blks */ - if (start > end || nid < 0 || nid >= MAX_NUMNODES) { - pr_warn("Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n", - nid, start, end - 1); - return 0; - } - - if (mi->nr_blks >= NR_NODE_MEMBLKS) { - pr_err("too many memblk ranges\n"); - return -EINVAL; - } - - mi->blk[mi->nr_blks].start = start; - mi->blk[mi->nr_blks].end = end; - mi->blk[mi->nr_blks].nid = nid; - mi->nr_blks++; - return 0; -} - -/** - * numa_remove_memblk_from - Remove one numa_memblk from a numa_meminfo - * @idx: Index of memblk to remove - * @mi: numa_meminfo to remove memblk from - * - * Remove @idx'th numa_memblk from @mi by shifting @mi->blk[] and - * decrementing @mi->nr_blks. - */ -void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi) -{ - mi->nr_blks--; - memmove(&mi->blk[idx], &mi->blk[idx + 1], - (mi->nr_blks - idx) * sizeof(mi->blk[0])); -} - -/** - * numa_move_tail_memblk - Move a numa_memblk from one numa_meminfo to another - * @dst: numa_meminfo to append block to - * @idx: Index of memblk to remove - * @src: numa_meminfo to remove memblk from - */ -static void __init numa_move_tail_memblk(struct numa_meminfo *dst, int idx, - struct numa_meminfo *src) -{ - dst->blk[dst->nr_blks++] = src->blk[idx]; - numa_remove_memblk_from(idx, src); -} - -/** - * numa_add_memblk - Add one numa_memblk to numa_meminfo - * @nid: NUMA node ID of the new memblk - * @start: Start address of the new memblk - * @end: End address of the new memblk - * - * Add a new memblk to the default numa_meminfo. - * - * RETURNS: - * 0 on success, -errno on failure. - */ -int __init numa_add_memblk(int nid, u64 start, u64 end) -{ - return numa_add_memblk_to(nid, start, end, &numa_meminfo); -} - -/** - * numa_cleanup_meminfo - Cleanup a numa_meminfo - * @mi: numa_meminfo to clean up - * - * Sanitize @mi by merging and removing unnecessary memblks. Also check for - * conflicts and clear unused memblks. - * - * RETURNS: - * 0 on success, -errno on failure. - */ -int __init numa_cleanup_meminfo(struct numa_meminfo *mi) -{ - const u64 low = 0; - const u64 high = PFN_PHYS(max_pfn); - int i, j, k; - - /* first, trim all entries */ - for (i = 0; i < mi->nr_blks; i++) { - struct numa_memblk *bi = &mi->blk[i]; - - /* move / save reserved memory ranges */ - if (!memblock_overlaps_region(&memblock.memory, - bi->start, bi->end - bi->start)) { - numa_move_tail_memblk(&numa_reserved_meminfo, i--, mi); - continue; - } - - /* make sure all non-reserved blocks are inside the limits */ - bi->start = max(bi->start, low); - - /* preserve info for non-RAM areas above 'max_pfn': */ - if (bi->end > high) { - numa_add_memblk_to(bi->nid, high, bi->end, - &numa_reserved_meminfo); - bi->end = high; - } - - /* and there's no empty block */ - if (bi->start >= bi->end) - numa_remove_memblk_from(i--, mi); - } - - /* merge neighboring / overlapping entries */ - for (i = 0; i < mi->nr_blks; i++) { - struct numa_memblk *bi = &mi->blk[i]; - - for (j = i + 1; j < mi->nr_blks; j++) { - struct numa_memblk *bj = &mi->blk[j]; - u64 start, end; - - /* - * See whether there are overlapping blocks. Whine - * about but allow overlaps of the same nid. They - * will be merged below. - */ - if (bi->end > bj->start && bi->start < bj->end) { - if (bi->nid != bj->nid) { - pr_err("node %d [mem %#010Lx-%#010Lx] overlaps with node %d [mem %#010Lx-%#010Lx]\n", - bi->nid, bi->start, bi->end - 1, - bj->nid, bj->start, bj->end - 1); - return -EINVAL; - } - pr_warn("Warning: node %d [mem %#010Lx-%#010Lx] overlaps with itself [mem %#010Lx-%#010Lx]\n", - bi->nid, bi->start, bi->end - 1, - bj->start, bj->end - 1); - } - - /* - * Join together blocks on the same node, holes - * between which don't overlap with memory on other - * nodes. - */ - if (bi->nid != bj->nid) - continue; - start = min(bi->start, bj->start); - end = max(bi->end, bj->end); - for (k = 0; k < mi->nr_blks; k++) { - struct numa_memblk *bk = &mi->blk[k]; - - if (bi->nid == bk->nid) - continue; - if (start < bk->end && end > bk->start) - break; - } - if (k < mi->nr_blks) - continue; - printk(KERN_INFO "NUMA: Node %d [mem %#010Lx-%#010Lx] + [mem %#010Lx-%#010Lx] -> [mem %#010Lx-%#010Lx]\n", - bi->nid, bi->start, bi->end - 1, bj->start, - bj->end - 1, start, end - 1); - bi->start = start; - bi->end = end; - numa_remove_memblk_from(j--, mi); - } - } - - /* clear unused ones */ - for (i = mi->nr_blks; i < ARRAY_SIZE(mi->blk); i++) { - mi->blk[i].start = mi->blk[i].end = 0; - mi->blk[i].nid = NUMA_NO_NODE; - } - - return 0; -} - -/* - * Set nodes, which have memory in @mi, in *@nodemask. - */ -static void __init numa_nodemask_from_meminfo(nodemask_t *nodemask, - const struct numa_meminfo *mi) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(mi->blk); i++) - if (mi->blk[i].start != mi->blk[i].end && - mi->blk[i].nid != NUMA_NO_NODE) - node_set(mi->blk[i].nid, *nodemask); -} - /** * numa_reset_distance - Reset NUMA distance table * @@ -410,111 +219,13 @@ int __node_distance(int from, int to) } EXPORT_SYMBOL(__node_distance); -/* - * Mark all currently memblock-reserved physical memory (which covers the - * kernel's own memory ranges) as hot-unswappable. - */ -static void __init numa_clear_kernel_node_hotplug(void) -{ - nodemask_t reserved_nodemask = NODE_MASK_NONE; - struct memblock_region *mb_region; - int i; - - /* - * We have to do some preprocessing of memblock regions, to - * make them suitable for reservation. - * - * At this time, all memory regions reserved by memblock are - * used by the kernel, but those regions are not split up - * along node boundaries yet, and don't necessarily have their - * node ID set yet either. - * - * So iterate over all memory known to the x86 architecture, - * and use those ranges to set the nid in memblock.reserved. - * This will split up the memblock regions along node - * boundaries and will set the node IDs as well. - */ - for (i = 0; i < numa_meminfo.nr_blks; i++) { - struct numa_memblk *mb = numa_meminfo.blk + i; - int ret; - - ret = memblock_set_node(mb->start, mb->end - mb->start, &memblock.reserved, mb->nid); - WARN_ON_ONCE(ret); - } - - /* - * Now go over all reserved memblock regions, to construct a - * node mask of all kernel reserved memory areas. - * - * [ Note, when booting with mem=nn[kMG] or in a kdump kernel, - * numa_meminfo might not include all memblock.reserved - * memory ranges, because quirks such as trim_snb_memory() - * reserve specific pages for Sandy Bridge graphics. ] - */ - for_each_reserved_mem_region(mb_region) { - int nid = memblock_get_region_node(mb_region); - - if (nid != NUMA_NO_NODE) - node_set(nid, reserved_nodemask); - } - - /* - * Finally, clear the MEMBLOCK_HOTPLUG flag for all memory - * belonging to the reserved node mask. - * - * Note that this will include memory regions that reside - * on nodes that contain kernel memory - entire nodes - * become hot-unpluggable: - */ - for (i = 0; i < numa_meminfo.nr_blks; i++) { - struct numa_memblk *mb = numa_meminfo.blk + i; - - if (!node_isset(mb->nid, reserved_nodemask)) - continue; - - memblock_clear_hotplug(mb->start, mb->end - mb->start); - } -} - static int __init numa_register_memblks(struct numa_meminfo *mi) { - int i, nid; + int nid, err; - /* Account for nodes with cpus and no memory */ - node_possible_map = numa_nodes_parsed; - numa_nodemask_from_meminfo(&node_possible_map, mi); - if (WARN_ON(nodes_empty(node_possible_map))) - return -EINVAL; - - for (i = 0; i < mi->nr_blks; i++) { - struct numa_memblk *mb = &mi->blk[i]; - memblock_set_node(mb->start, mb->end - mb->start, - &memblock.memory, mb->nid); - } - - /* - * At very early time, the kernel have to use some memory such as - * loading the kernel image. We cannot prevent this anyway. So any - * node the kernel resides in should be un-hotpluggable. - * - * And when we come here, alloc node data won't fail. - */ - numa_clear_kernel_node_hotplug(); - - /* - * If sections array is gonna be used for pfn -> nid mapping, check - * whether its granularity is fine enough. - */ - if (IS_ENABLED(NODE_NOT_IN_PAGE_FLAGS)) { - unsigned long pfn_align = node_map_pfn_alignment(); - - if (pfn_align && pfn_align < PAGES_PER_SECTION) { - pr_warn("Node alignment %LuMB < min %LuMB, rejecting NUMA config\n", - PFN_PHYS(pfn_align) >> 20, - PFN_PHYS(PAGES_PER_SECTION) >> 20); - return -EINVAL; - } - } + err = numa_register_meminfo(mi); + if (err) + return err; if (!memblock_validate_numa_coverage(SZ_1M)) return -EINVAL; @@ -916,76 +627,3 @@ int memory_add_physaddr_to_nid(u64 start) EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); #endif - -static int __init cmp_memblk(const void *a, const void *b) -{ - const struct numa_memblk *ma = *(const struct numa_memblk **)a; - const struct numa_memblk *mb = *(const struct numa_memblk **)b; - - return (ma->start > mb->start) - (ma->start < mb->start); -} - -static struct numa_memblk *numa_memblk_list[NR_NODE_MEMBLKS] __initdata; - -/** - * numa_fill_memblks - Fill gaps in numa_meminfo memblks - * @start: address to begin fill - * @end: address to end fill - * - * Find and extend numa_meminfo memblks to cover the physical - * address range @start-@end - * - * RETURNS: - * 0 : Success - * NUMA_NO_MEMBLK : No memblks exist in address range @start-@end - */ - -int __init numa_fill_memblks(u64 start, u64 end) -{ - struct numa_memblk **blk = &numa_memblk_list[0]; - struct numa_meminfo *mi = &numa_meminfo; - int count = 0; - u64 prev_end; - - /* - * Create a list of pointers to numa_meminfo memblks that - * overlap start, end. The list is used to make in-place - * changes that fill out the numa_meminfo memblks. - */ - for (int i = 0; i < mi->nr_blks; i++) { - struct numa_memblk *bi = &mi->blk[i]; - - if (memblock_addrs_overlap(start, end - start, bi->start, - bi->end - bi->start)) { - blk[count] = &mi->blk[i]; - count++; - } - } - if (!count) - return NUMA_NO_MEMBLK; - - /* Sort the list of pointers in memblk->start order */ - sort(&blk[0], count, sizeof(blk[0]), cmp_memblk, NULL); - - /* Make sure the first/last memblks include start/end */ - blk[0]->start = min(blk[0]->start, start); - blk[count - 1]->end = max(blk[count - 1]->end, end); - - /* - * Fill any gaps by tracking the previous memblks - * end address and backfilling to it if needed. - */ - prev_end = blk[0]->end; - for (int i = 1; i < count; i++) { - struct numa_memblk *curr = blk[i]; - - if (prev_end >= curr->start) { - if (prev_end < curr->end) - prev_end = curr->end; - } else { - curr->start = prev_end; - prev_end = curr->end; - } - } - return 0; -} diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index 235f8a4eb2fa..33610026b7a3 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include "numa_internal.h" diff --git a/arch/x86/mm/numa_internal.h b/arch/x86/mm/numa_internal.h index 86860f279662..a51229a2f5af 100644 --- a/arch/x86/mm/numa_internal.h +++ b/arch/x86/mm/numa_internal.h @@ -5,23 +5,12 @@ #include #include -struct numa_memblk { - u64 start; - u64 end; - int nid; -}; - -struct numa_meminfo { - int nr_blks; - struct numa_memblk blk[NR_NODE_MEMBLKS]; -}; - -void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi); -int __init numa_cleanup_meminfo(struct numa_meminfo *mi); void __init numa_reset_distance(void); void __init x86_numa_init(void); +struct numa_meminfo; + #ifdef CONFIG_NUMA_EMU void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt); diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c index 44f91f2c6c5d..bec0dcd1f9c3 100644 --- a/drivers/acpi/numa/srat.c +++ b/drivers/acpi/numa/srat.c @@ -17,6 +17,7 @@ #include #include #include +#include static nodemask_t nodes_found_map = NODE_MASK_NONE; diff --git a/drivers/of/of_numa.c b/drivers/of/of_numa.c index 5949829a1b00..838747e319a2 100644 --- a/drivers/of/of_numa.c +++ b/drivers/of/of_numa.c @@ -10,6 +10,7 @@ #include #include #include +#include #include diff --git a/include/linux/numa_memblks.h b/include/linux/numa_memblks.h new file mode 100644 index 000000000000..6981cf97d2c9 --- /dev/null +++ b/include/linux/numa_memblks.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __NUMA_MEMBLKS_H +#define __NUMA_MEMBLKS_H + +#ifdef CONFIG_NUMA_MEMBLKS +#include + +#define NR_NODE_MEMBLKS (MAX_NUMNODES * 2) + +struct numa_memblk { + u64 start; + u64 end; + int nid; +}; + +struct numa_meminfo { + int nr_blks; + struct numa_memblk blk[NR_NODE_MEMBLKS]; +}; + +extern struct numa_meminfo numa_meminfo __initdata_or_meminfo; +extern struct numa_meminfo numa_reserved_meminfo __initdata_or_meminfo; + +int __init numa_add_memblk(int nodeid, u64 start, u64 end); +void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi); + +int __init numa_cleanup_meminfo(struct numa_meminfo *mi); +int __init numa_register_meminfo(struct numa_meminfo *mi); + +void __init numa_nodemask_from_meminfo(nodemask_t *nodemask, + const struct numa_meminfo *mi); + +#endif /* CONFIG_NUMA_MEMBLKS */ + +#endif /* __NUMA_MEMBLKS_H */ diff --git a/mm/Kconfig b/mm/Kconfig index 7b716ac80272..67700a127982 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -1267,6 +1267,9 @@ config IOMMU_MM_DATA config EXECMEM bool +config NUMA_MEMBLKS + bool + source "mm/damon/Kconfig" endmenu diff --git a/mm/Makefile b/mm/Makefile index 31fad7df64ad..0778dce4aef6 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -118,6 +118,7 @@ obj-$(CONFIG_Z3FOLD) += z3fold.o obj-$(CONFIG_GENERIC_EARLY_IOREMAP) += early_ioremap.o obj-$(CONFIG_CMA) += cma.o obj-$(CONFIG_NUMA) += numa.o +obj-$(CONFIG_NUMA_MEMBLKS) += numa_memblks.o obj-$(CONFIG_MEMORY_BALLOON) += balloon_compaction.o obj-$(CONFIG_PAGE_EXTENSION) += page_ext.o obj-$(CONFIG_PAGE_TABLE_CHECK) += page_table_check.o diff --git a/mm/numa_memblks.c b/mm/numa_memblks.c new file mode 100644 index 000000000000..72f191a94c66 --- /dev/null +++ b/mm/numa_memblks.c @@ -0,0 +1,385 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include +#include +#include +#include +#include +#include + +nodemask_t numa_nodes_parsed __initdata; + +struct numa_meminfo numa_meminfo __initdata_or_meminfo; +struct numa_meminfo numa_reserved_meminfo __initdata_or_meminfo; + +static int __init numa_add_memblk_to(int nid, u64 start, u64 end, + struct numa_meminfo *mi) +{ + /* ignore zero length blks */ + if (start == end) + return 0; + + /* whine about and ignore invalid blks */ + if (start > end || nid < 0 || nid >= MAX_NUMNODES) { + pr_warn("Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n", + nid, start, end - 1); + return 0; + } + + if (mi->nr_blks >= NR_NODE_MEMBLKS) { + pr_err("too many memblk ranges\n"); + return -EINVAL; + } + + mi->blk[mi->nr_blks].start = start; + mi->blk[mi->nr_blks].end = end; + mi->blk[mi->nr_blks].nid = nid; + mi->nr_blks++; + return 0; +} + +/** + * numa_remove_memblk_from - Remove one numa_memblk from a numa_meminfo + * @idx: Index of memblk to remove + * @mi: numa_meminfo to remove memblk from + * + * Remove @idx'th numa_memblk from @mi by shifting @mi->blk[] and + * decrementing @mi->nr_blks. + */ +void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi) +{ + mi->nr_blks--; + memmove(&mi->blk[idx], &mi->blk[idx + 1], + (mi->nr_blks - idx) * sizeof(mi->blk[0])); +} + +/** + * numa_move_tail_memblk - Move a numa_memblk from one numa_meminfo to another + * @dst: numa_meminfo to append block to + * @idx: Index of memblk to remove + * @src: numa_meminfo to remove memblk from + */ +static void __init numa_move_tail_memblk(struct numa_meminfo *dst, int idx, + struct numa_meminfo *src) +{ + dst->blk[dst->nr_blks++] = src->blk[idx]; + numa_remove_memblk_from(idx, src); +} + +/** + * numa_add_memblk - Add one numa_memblk to numa_meminfo + * @nid: NUMA node ID of the new memblk + * @start: Start address of the new memblk + * @end: End address of the new memblk + * + * Add a new memblk to the default numa_meminfo. + * + * RETURNS: + * 0 on success, -errno on failure. + */ +int __init numa_add_memblk(int nid, u64 start, u64 end) +{ + return numa_add_memblk_to(nid, start, end, &numa_meminfo); +} + +/** + * numa_cleanup_meminfo - Cleanup a numa_meminfo + * @mi: numa_meminfo to clean up + * + * Sanitize @mi by merging and removing unnecessary memblks. Also check for + * conflicts and clear unused memblks. + * + * RETURNS: + * 0 on success, -errno on failure. + */ +int __init numa_cleanup_meminfo(struct numa_meminfo *mi) +{ + const u64 low = 0; + const u64 high = PFN_PHYS(max_pfn); + int i, j, k; + + /* first, trim all entries */ + for (i = 0; i < mi->nr_blks; i++) { + struct numa_memblk *bi = &mi->blk[i]; + + /* move / save reserved memory ranges */ + if (!memblock_overlaps_region(&memblock.memory, + bi->start, bi->end - bi->start)) { + numa_move_tail_memblk(&numa_reserved_meminfo, i--, mi); + continue; + } + + /* make sure all non-reserved blocks are inside the limits */ + bi->start = max(bi->start, low); + + /* preserve info for non-RAM areas above 'max_pfn': */ + if (bi->end > high) { + numa_add_memblk_to(bi->nid, high, bi->end, + &numa_reserved_meminfo); + bi->end = high; + } + + /* and there's no empty block */ + if (bi->start >= bi->end) + numa_remove_memblk_from(i--, mi); + } + + /* merge neighboring / overlapping entries */ + for (i = 0; i < mi->nr_blks; i++) { + struct numa_memblk *bi = &mi->blk[i]; + + for (j = i + 1; j < mi->nr_blks; j++) { + struct numa_memblk *bj = &mi->blk[j]; + u64 start, end; + + /* + * See whether there are overlapping blocks. Whine + * about but allow overlaps of the same nid. They + * will be merged below. + */ + if (bi->end > bj->start && bi->start < bj->end) { + if (bi->nid != bj->nid) { + pr_err("node %d [mem %#010Lx-%#010Lx] overlaps with node %d [mem %#010Lx-%#010Lx]\n", + bi->nid, bi->start, bi->end - 1, + bj->nid, bj->start, bj->end - 1); + return -EINVAL; + } + pr_warn("Warning: node %d [mem %#010Lx-%#010Lx] overlaps with itself [mem %#010Lx-%#010Lx]\n", + bi->nid, bi->start, bi->end - 1, + bj->start, bj->end - 1); + } + + /* + * Join together blocks on the same node, holes + * between which don't overlap with memory on other + * nodes. + */ + if (bi->nid != bj->nid) + continue; + start = min(bi->start, bj->start); + end = max(bi->end, bj->end); + for (k = 0; k < mi->nr_blks; k++) { + struct numa_memblk *bk = &mi->blk[k]; + + if (bi->nid == bk->nid) + continue; + if (start < bk->end && end > bk->start) + break; + } + if (k < mi->nr_blks) + continue; + pr_info("NUMA: Node %d [mem %#010Lx-%#010Lx] + [mem %#010Lx-%#010Lx] -> [mem %#010Lx-%#010Lx]\n", + bi->nid, bi->start, bi->end - 1, bj->start, + bj->end - 1, start, end - 1); + bi->start = start; + bi->end = end; + numa_remove_memblk_from(j--, mi); + } + } + + /* clear unused ones */ + for (i = mi->nr_blks; i < ARRAY_SIZE(mi->blk); i++) { + mi->blk[i].start = mi->blk[i].end = 0; + mi->blk[i].nid = NUMA_NO_NODE; + } + + return 0; +} + +/* + * Set nodes, which have memory in @mi, in *@nodemask. + */ +void __init numa_nodemask_from_meminfo(nodemask_t *nodemask, + const struct numa_meminfo *mi) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(mi->blk); i++) + if (mi->blk[i].start != mi->blk[i].end && + mi->blk[i].nid != NUMA_NO_NODE) + node_set(mi->blk[i].nid, *nodemask); +} + +/* + * Mark all currently memblock-reserved physical memory (which covers the + * kernel's own memory ranges) as hot-unswappable. + */ +static void __init numa_clear_kernel_node_hotplug(void) +{ + nodemask_t reserved_nodemask = NODE_MASK_NONE; + struct memblock_region *mb_region; + int i; + + /* + * We have to do some preprocessing of memblock regions, to + * make them suitable for reservation. + * + * At this time, all memory regions reserved by memblock are + * used by the kernel, but those regions are not split up + * along node boundaries yet, and don't necessarily have their + * node ID set yet either. + * + * So iterate over all parsed memory blocks and use those ranges to + * set the nid in memblock.reserved. This will split up the + * memblock regions along node boundaries and will set the node IDs + * as well. + */ + for (i = 0; i < numa_meminfo.nr_blks; i++) { + struct numa_memblk *mb = numa_meminfo.blk + i; + int ret; + + ret = memblock_set_node(mb->start, mb->end - mb->start, + &memblock.reserved, mb->nid); + WARN_ON_ONCE(ret); + } + + /* + * Now go over all reserved memblock regions, to construct a + * node mask of all kernel reserved memory areas. + * + * [ Note, when booting with mem=nn[kMG] or in a kdump kernel, + * numa_meminfo might not include all memblock.reserved + * memory ranges, because quirks such as trim_snb_memory() + * reserve specific pages for Sandy Bridge graphics. ] + */ + for_each_reserved_mem_region(mb_region) { + int nid = memblock_get_region_node(mb_region); + + if (nid != MAX_NUMNODES) + node_set(nid, reserved_nodemask); + } + + /* + * Finally, clear the MEMBLOCK_HOTPLUG flag for all memory + * belonging to the reserved node mask. + * + * Note that this will include memory regions that reside + * on nodes that contain kernel memory - entire nodes + * become hot-unpluggable: + */ + for (i = 0; i < numa_meminfo.nr_blks; i++) { + struct numa_memblk *mb = numa_meminfo.blk + i; + + if (!node_isset(mb->nid, reserved_nodemask)) + continue; + + memblock_clear_hotplug(mb->start, mb->end - mb->start); + } +} + +int __init numa_register_meminfo(struct numa_meminfo *mi) +{ + int i; + + /* Account for nodes with cpus and no memory */ + node_possible_map = numa_nodes_parsed; + numa_nodemask_from_meminfo(&node_possible_map, mi); + if (WARN_ON(nodes_empty(node_possible_map))) + return -EINVAL; + + for (i = 0; i < mi->nr_blks; i++) { + struct numa_memblk *mb = &mi->blk[i]; + + memblock_set_node(mb->start, mb->end - mb->start, + &memblock.memory, mb->nid); + } + + /* + * At very early time, the kernel have to use some memory such as + * loading the kernel image. We cannot prevent this anyway. So any + * node the kernel resides in should be un-hotpluggable. + * + * And when we come here, alloc node data won't fail. + */ + numa_clear_kernel_node_hotplug(); + + /* + * If sections array is gonna be used for pfn -> nid mapping, check + * whether its granularity is fine enough. + */ + if (IS_ENABLED(NODE_NOT_IN_PAGE_FLAGS)) { + unsigned long pfn_align = node_map_pfn_alignment(); + + if (pfn_align && pfn_align < PAGES_PER_SECTION) { + pr_warn("Node alignment %LuMB < min %LuMB, rejecting NUMA config\n", + PFN_PHYS(pfn_align) >> 20, + PFN_PHYS(PAGES_PER_SECTION) >> 20); + return -EINVAL; + } + } + + return 0; +} + +static int __init cmp_memblk(const void *a, const void *b) +{ + const struct numa_memblk *ma = *(const struct numa_memblk **)a; + const struct numa_memblk *mb = *(const struct numa_memblk **)b; + + return (ma->start > mb->start) - (ma->start < mb->start); +} + +static struct numa_memblk *numa_memblk_list[NR_NODE_MEMBLKS] __initdata; + +/** + * numa_fill_memblks - Fill gaps in numa_meminfo memblks + * @start: address to begin fill + * @end: address to end fill + * + * Find and extend numa_meminfo memblks to cover the physical + * address range @start-@end + * + * RETURNS: + * 0 : Success + * NUMA_NO_MEMBLK : No memblks exist in address range @start-@end + */ + +int __init numa_fill_memblks(u64 start, u64 end) +{ + struct numa_memblk **blk = &numa_memblk_list[0]; + struct numa_meminfo *mi = &numa_meminfo; + int count = 0; + u64 prev_end; + + /* + * Create a list of pointers to numa_meminfo memblks that + * overlap start, end. The list is used to make in-place + * changes that fill out the numa_meminfo memblks. + */ + for (int i = 0; i < mi->nr_blks; i++) { + struct numa_memblk *bi = &mi->blk[i]; + + if (memblock_addrs_overlap(start, end - start, bi->start, + bi->end - bi->start)) { + blk[count] = &mi->blk[i]; + count++; + } + } + if (!count) + return NUMA_NO_MEMBLK; + + /* Sort the list of pointers in memblk->start order */ + sort(&blk[0], count, sizeof(blk[0]), cmp_memblk, NULL); + + /* Make sure the first/last memblks include start/end */ + blk[0]->start = min(blk[0]->start, start); + blk[count - 1]->end = max(blk[count - 1]->end, end); + + /* + * Fill any gaps by tracking the previous memblks + * end address and backfilling to it if needed. + */ + prev_end = blk[0]->end; + for (int i = 1; i < count; i++) { + struct numa_memblk *curr = blk[i]; + + if (prev_end >= curr->start) { + if (prev_end < curr->end) + prev_end = curr->end; + } else { + curr->start = prev_end; + prev_end = curr->end; + } + } + return 0; +} -- cgit v1.2.3 From 75f9d4cc4eb5e15dd5ce843e33de7f6346a0d4fa Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Wed, 7 Aug 2024 09:41:02 +0300 Subject: mm: move numa_distance and related code from x86 to numa_memblks Move code dealing with numa_distance array from arch/x86 to mm/numa_memblks.c This code will be later reused by arch_numa. No functional changes. Link: https://lkml.kernel.org/r/20240807064110.1003856-19-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) Tested-by: Zi Yan # for x86_64 and arm64 Reviewed-by: Jonathan Cameron Tested-by: Jonathan Cameron [arm64 + CXL via QEMU] Acked-by: Dan Williams Acked-by: David Hildenbrand Cc: Alexander Gordeev Cc: Andreas Larsson Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christophe Leroy Cc: Dave Hansen Cc: Davidlohr Bueso Cc: David S. Miller Cc: Greg Kroah-Hartman Cc: Heiko Carstens Cc: Huacai Chen Cc: Ingo Molnar Cc: Jiaxun Yang Cc: John Paul Adrian Glaubitz Cc: Jonathan Corbet Cc: Michael Ellerman Cc: Palmer Dabbelt Cc: Rafael J. Wysocki Cc: Rob Herring (Arm) Cc: Samuel Holland Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/x86/include/asm/numa.h | 2 - arch/x86/mm/numa.c | 104 ------------------------------------------- arch/x86/mm/numa_internal.h | 2 - include/linux/numa_memblks.h | 4 ++ mm/numa_memblks.c | 104 +++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 108 insertions(+), 108 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h index 6e9a50bf03d4..203100500f24 100644 --- a/arch/x86/include/asm/numa.h +++ b/arch/x86/include/asm/numa.h @@ -23,8 +23,6 @@ extern int numa_off; extern s16 __apicid_to_node[MAX_LOCAL_APIC]; extern nodemask_t numa_nodes_parsed __initdata; -extern void __init numa_set_distance(int from, int to, int distance); - static inline void set_apicid_to_node(int apicid, s16 node) { __apicid_to_node[apicid] = node; diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 0bada905f409..095502095503 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -24,9 +24,6 @@ int numa_off; -static int numa_distance_cnt; -static u8 *numa_distance; - static __init int numa_setup(char *opt) { if (!opt) @@ -118,107 +115,6 @@ void __init setup_node_to_cpumask_map(void) pr_debug("Node to cpumask map for %u nodes\n", nr_node_ids); } -/** - * numa_reset_distance - Reset NUMA distance table - * - * The current table is freed. The next numa_set_distance() call will - * create a new one. - */ -void __init numa_reset_distance(void) -{ - size_t size = numa_distance_cnt * numa_distance_cnt * sizeof(numa_distance[0]); - - /* numa_distance could be 1LU marking allocation failure, test cnt */ - if (numa_distance_cnt) - memblock_free(numa_distance, size); - numa_distance_cnt = 0; - numa_distance = NULL; /* enable table creation */ -} - -static int __init numa_alloc_distance(void) -{ - nodemask_t nodes_parsed; - size_t size; - int i, j, cnt = 0; - - /* size the new table and allocate it */ - nodes_parsed = numa_nodes_parsed; - numa_nodemask_from_meminfo(&nodes_parsed, &numa_meminfo); - - for_each_node_mask(i, nodes_parsed) - cnt = i; - cnt++; - size = cnt * cnt * sizeof(numa_distance[0]); - - numa_distance = memblock_alloc(size, PAGE_SIZE); - if (!numa_distance) { - pr_warn("Warning: can't allocate distance table!\n"); - /* don't retry until explicitly reset */ - numa_distance = (void *)1LU; - return -ENOMEM; - } - - numa_distance_cnt = cnt; - - /* fill with the default distances */ - for (i = 0; i < cnt; i++) - for (j = 0; j < cnt; j++) - numa_distance[i * cnt + j] = i == j ? - LOCAL_DISTANCE : REMOTE_DISTANCE; - printk(KERN_DEBUG "NUMA: Initialized distance table, cnt=%d\n", cnt); - - return 0; -} - -/** - * numa_set_distance - Set NUMA distance from one NUMA to another - * @from: the 'from' node to set distance - * @to: the 'to' node to set distance - * @distance: NUMA distance - * - * Set the distance from node @from to @to to @distance. If distance table - * doesn't exist, one which is large enough to accommodate all the currently - * known nodes will be created. - * - * If such table cannot be allocated, a warning is printed and further - * calls are ignored until the distance table is reset with - * numa_reset_distance(). - * - * If @from or @to is higher than the highest known node or lower than zero - * at the time of table creation or @distance doesn't make sense, the call - * is ignored. - * This is to allow simplification of specific NUMA config implementations. - */ -void __init numa_set_distance(int from, int to, int distance) -{ - if (!numa_distance && numa_alloc_distance() < 0) - return; - - if (from >= numa_distance_cnt || to >= numa_distance_cnt || - from < 0 || to < 0) { - pr_warn_once("Warning: node ids are out of bound, from=%d to=%d distance=%d\n", - from, to, distance); - return; - } - - if ((u8)distance != distance || - (from == to && distance != LOCAL_DISTANCE)) { - pr_warn_once("Warning: invalid distance parameter, from=%d to=%d distance=%d\n", - from, to, distance); - return; - } - - numa_distance[from * numa_distance_cnt + to] = distance; -} - -int __node_distance(int from, int to) -{ - if (from >= numa_distance_cnt || to >= numa_distance_cnt) - return from == to ? LOCAL_DISTANCE : REMOTE_DISTANCE; - return numa_distance[from * numa_distance_cnt + to]; -} -EXPORT_SYMBOL(__node_distance); - static int __init numa_register_memblks(struct numa_meminfo *mi) { int nid, err; diff --git a/arch/x86/mm/numa_internal.h b/arch/x86/mm/numa_internal.h index a51229a2f5af..249e3aaeadce 100644 --- a/arch/x86/mm/numa_internal.h +++ b/arch/x86/mm/numa_internal.h @@ -5,8 +5,6 @@ #include #include -void __init numa_reset_distance(void); - void __init x86_numa_init(void); struct numa_meminfo; diff --git a/include/linux/numa_memblks.h b/include/linux/numa_memblks.h index 6981cf97d2c9..968a590535ac 100644 --- a/include/linux/numa_memblks.h +++ b/include/linux/numa_memblks.h @@ -7,6 +7,10 @@ #define NR_NODE_MEMBLKS (MAX_NUMNODES * 2) +extern int numa_distance_cnt; +void __init numa_set_distance(int from, int to, int distance); +void __init numa_reset_distance(void); + struct numa_memblk { u64 start; u64 end; diff --git a/mm/numa_memblks.c b/mm/numa_memblks.c index 72f191a94c66..e3c3519725d4 100644 --- a/mm/numa_memblks.c +++ b/mm/numa_memblks.c @@ -7,11 +7,115 @@ #include #include +int numa_distance_cnt; +static u8 *numa_distance; + nodemask_t numa_nodes_parsed __initdata; struct numa_meminfo numa_meminfo __initdata_or_meminfo; struct numa_meminfo numa_reserved_meminfo __initdata_or_meminfo; +/** + * numa_reset_distance - Reset NUMA distance table + * + * The current table is freed. The next numa_set_distance() call will + * create a new one. + */ +void __init numa_reset_distance(void) +{ + size_t size = numa_distance_cnt * numa_distance_cnt * sizeof(numa_distance[0]); + + /* numa_distance could be 1LU marking allocation failure, test cnt */ + if (numa_distance_cnt) + memblock_free(numa_distance, size); + numa_distance_cnt = 0; + numa_distance = NULL; /* enable table creation */ +} + +static int __init numa_alloc_distance(void) +{ + nodemask_t nodes_parsed; + size_t size; + int i, j, cnt = 0; + + /* size the new table and allocate it */ + nodes_parsed = numa_nodes_parsed; + numa_nodemask_from_meminfo(&nodes_parsed, &numa_meminfo); + + for_each_node_mask(i, nodes_parsed) + cnt = i; + cnt++; + size = cnt * cnt * sizeof(numa_distance[0]); + + numa_distance = memblock_alloc(size, PAGE_SIZE); + if (!numa_distance) { + pr_warn("Warning: can't allocate distance table!\n"); + /* don't retry until explicitly reset */ + numa_distance = (void *)1LU; + return -ENOMEM; + } + + numa_distance_cnt = cnt; + + /* fill with the default distances */ + for (i = 0; i < cnt; i++) + for (j = 0; j < cnt; j++) + numa_distance[i * cnt + j] = i == j ? + LOCAL_DISTANCE : REMOTE_DISTANCE; + printk(KERN_DEBUG "NUMA: Initialized distance table, cnt=%d\n", cnt); + + return 0; +} + +/** + * numa_set_distance - Set NUMA distance from one NUMA to another + * @from: the 'from' node to set distance + * @to: the 'to' node to set distance + * @distance: NUMA distance + * + * Set the distance from node @from to @to to @distance. If distance table + * doesn't exist, one which is large enough to accommodate all the currently + * known nodes will be created. + * + * If such table cannot be allocated, a warning is printed and further + * calls are ignored until the distance table is reset with + * numa_reset_distance(). + * + * If @from or @to is higher than the highest known node or lower than zero + * at the time of table creation or @distance doesn't make sense, the call + * is ignored. + * This is to allow simplification of specific NUMA config implementations. + */ +void __init numa_set_distance(int from, int to, int distance) +{ + if (!numa_distance && numa_alloc_distance() < 0) + return; + + if (from >= numa_distance_cnt || to >= numa_distance_cnt || + from < 0 || to < 0) { + pr_warn_once("Warning: node ids are out of bound, from=%d to=%d distance=%d\n", + from, to, distance); + return; + } + + if ((u8)distance != distance || + (from == to && distance != LOCAL_DISTANCE)) { + pr_warn_once("Warning: invalid distance parameter, from=%d to=%d distance=%d\n", + from, to, distance); + return; + } + + numa_distance[from * numa_distance_cnt + to] = distance; +} + +int __node_distance(int from, int to) +{ + if (from >= numa_distance_cnt || to >= numa_distance_cnt) + return from == to ? LOCAL_DISTANCE : REMOTE_DISTANCE; + return numa_distance[from * numa_distance_cnt + to]; +} +EXPORT_SYMBOL(__node_distance); + static int __init numa_add_memblk_to(int nid, u64 start, u64 end, struct numa_meminfo *mi) { -- cgit v1.2.3 From b0c4e27c687177aa36048110a12cba94bf291452 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Wed, 7 Aug 2024 09:41:03 +0300 Subject: mm: introduce numa_emulation Move numa_emulation code from arch/x86 to mm/numa_emulation.c This code will be later reused by arch_numa. No functional changes. Link: https://lkml.kernel.org/r/20240807064110.1003856-20-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) Tested-by: Zi Yan # for x86_64 and arm64 Reviewed-by: Jonathan Cameron Tested-by: Jonathan Cameron [arm64 + CXL via QEMU] Acked-by: Dan Williams Cc: Alexander Gordeev Cc: Andreas Larsson Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christophe Leroy Cc: Dave Hansen Cc: David Hildenbrand Cc: Davidlohr Bueso Cc: David S. Miller Cc: Greg Kroah-Hartman Cc: Heiko Carstens Cc: Huacai Chen Cc: Ingo Molnar Cc: Jiaxun Yang Cc: John Paul Adrian Glaubitz Cc: Jonathan Corbet Cc: Michael Ellerman Cc: Palmer Dabbelt Cc: Rafael J. Wysocki Cc: Rob Herring (Arm) Cc: Samuel Holland Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/x86/Kconfig | 8 - arch/x86/include/asm/numa.h | 12 - arch/x86/mm/Makefile | 1 - arch/x86/mm/numa_emulation.c | 573 ------------------------------------------- arch/x86/mm/numa_internal.h | 11 - include/linux/numa_memblks.h | 17 ++ mm/Kconfig | 8 + mm/Makefile | 1 + mm/numa_emulation.c | 571 ++++++++++++++++++++++++++++++++++++++++++ 9 files changed, 597 insertions(+), 605 deletions(-) delete mode 100644 arch/x86/mm/numa_emulation.c create mode 100644 mm/numa_emulation.c (limited to 'include/linux') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 74afb59c6603..acd9745bf2ae 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1600,14 +1600,6 @@ config X86_64_ACPI_NUMA help Enable ACPI SRAT based node topology detection. -config NUMA_EMU - bool "NUMA emulation" - depends on NUMA - help - Enable NUMA emulation. A flat machine will be split - into virtual nodes when booted with "numa=fake=N", where N is the - number of nodes. This is only useful for debugging. - config NODES_SHIFT int "Maximum NUMA Nodes (as a power of 2)" if !MAXSMP range 1 10 diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h index 203100500f24..5469d7a7c40f 100644 --- a/arch/x86/include/asm/numa.h +++ b/arch/x86/include/asm/numa.h @@ -65,16 +65,4 @@ static inline void init_gi_nodes(void) { } void debug_cpumask_set_cpu(unsigned int cpu, int node, bool enable); #endif -#ifdef CONFIG_NUMA_EMU -int numa_emu_cmdline(char *str); -void __init numa_emu_update_cpu_to_node(int *emu_nid_to_phys, - unsigned int nr_emu_nids); -u64 __init numa_emu_dma_end(void); -#else /* CONFIG_NUMA_EMU */ -static inline int numa_emu_cmdline(char *str) -{ - return -EINVAL; -} -#endif /* CONFIG_NUMA_EMU */ - #endif /* _ASM_X86_NUMA_H */ diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 8d3a00e5c528..690fbf48e853 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -57,7 +57,6 @@ obj-$(CONFIG_MMIOTRACE_TEST) += testmmiotrace.o obj-$(CONFIG_NUMA) += numa.o numa_$(BITS).o obj-$(CONFIG_AMD_NUMA) += amdtopology.o obj-$(CONFIG_ACPI_NUMA) += srat.o -obj-$(CONFIG_NUMA_EMU) += numa_emulation.o obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS) += pkeys.o obj-$(CONFIG_RANDOMIZE_MEMORY) += kaslr.o diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c deleted file mode 100644 index 33610026b7a3..000000000000 --- a/arch/x86/mm/numa_emulation.c +++ /dev/null @@ -1,573 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * NUMA emulation - */ -#include -#include -#include -#include -#include -#include - -#include "numa_internal.h" - -#define FAKE_NODE_MIN_SIZE ((u64)32 << 20) -#define FAKE_NODE_MIN_HASH_MASK (~(FAKE_NODE_MIN_SIZE - 1UL)) - -static int emu_nid_to_phys[MAX_NUMNODES]; -static char *emu_cmdline __initdata; - -int __init numa_emu_cmdline(char *str) -{ - emu_cmdline = str; - return 0; -} - -static int __init emu_find_memblk_by_nid(int nid, const struct numa_meminfo *mi) -{ - int i; - - for (i = 0; i < mi->nr_blks; i++) - if (mi->blk[i].nid == nid) - return i; - return -ENOENT; -} - -static u64 __init mem_hole_size(u64 start, u64 end) -{ - unsigned long start_pfn = PFN_UP(start); - unsigned long end_pfn = PFN_DOWN(end); - - if (start_pfn < end_pfn) - return PFN_PHYS(absent_pages_in_range(start_pfn, end_pfn)); - return 0; -} - -/* - * Sets up nid to range from @start to @end. The return value is -errno if - * something went wrong, 0 otherwise. - */ -static int __init emu_setup_memblk(struct numa_meminfo *ei, - struct numa_meminfo *pi, - int nid, int phys_blk, u64 size) -{ - struct numa_memblk *eb = &ei->blk[ei->nr_blks]; - struct numa_memblk *pb = &pi->blk[phys_blk]; - - if (ei->nr_blks >= NR_NODE_MEMBLKS) { - pr_err("NUMA: Too many emulated memblks, failing emulation\n"); - return -EINVAL; - } - - ei->nr_blks++; - eb->start = pb->start; - eb->end = pb->start + size; - eb->nid = nid; - - if (emu_nid_to_phys[nid] == NUMA_NO_NODE) - emu_nid_to_phys[nid] = pb->nid; - - pb->start += size; - if (pb->start >= pb->end) { - WARN_ON_ONCE(pb->start > pb->end); - numa_remove_memblk_from(phys_blk, pi); - } - - printk(KERN_INFO "Faking node %d at [mem %#018Lx-%#018Lx] (%LuMB)\n", - nid, eb->start, eb->end - 1, (eb->end - eb->start) >> 20); - return 0; -} - -/* - * Sets up nr_nodes fake nodes interleaved over physical nodes ranging from addr - * to max_addr. - * - * Returns zero on success or negative on error. - */ -static int __init split_nodes_interleave(struct numa_meminfo *ei, - struct numa_meminfo *pi, - u64 addr, u64 max_addr, int nr_nodes) -{ - nodemask_t physnode_mask = numa_nodes_parsed; - u64 size; - int big; - int nid = 0; - int i, ret; - - if (nr_nodes <= 0) - return -1; - if (nr_nodes > MAX_NUMNODES) { - pr_info("numa=fake=%d too large, reducing to %d\n", - nr_nodes, MAX_NUMNODES); - nr_nodes = MAX_NUMNODES; - } - - /* - * Calculate target node size. x86_32 freaks on __udivdi3() so do - * the division in ulong number of pages and convert back. - */ - size = max_addr - addr - mem_hole_size(addr, max_addr); - size = PFN_PHYS((unsigned long)(size >> PAGE_SHIFT) / nr_nodes); - - /* - * Calculate the number of big nodes that can be allocated as a result - * of consolidating the remainder. - */ - big = ((size & ~FAKE_NODE_MIN_HASH_MASK) * nr_nodes) / - FAKE_NODE_MIN_SIZE; - - size &= FAKE_NODE_MIN_HASH_MASK; - if (!size) { - pr_err("Not enough memory for each node. " - "NUMA emulation disabled.\n"); - return -1; - } - - /* - * Continue to fill physical nodes with fake nodes until there is no - * memory left on any of them. - */ - while (!nodes_empty(physnode_mask)) { - for_each_node_mask(i, physnode_mask) { - u64 dma32_end = numa_emu_dma_end(); - u64 start, limit, end; - int phys_blk; - - phys_blk = emu_find_memblk_by_nid(i, pi); - if (phys_blk < 0) { - node_clear(i, physnode_mask); - continue; - } - start = pi->blk[phys_blk].start; - limit = pi->blk[phys_blk].end; - end = start + size; - - if (nid < big) - end += FAKE_NODE_MIN_SIZE; - - /* - * Continue to add memory to this fake node if its - * non-reserved memory is less than the per-node size. - */ - while (end - start - mem_hole_size(start, end) < size) { - end += FAKE_NODE_MIN_SIZE; - if (end > limit) { - end = limit; - break; - } - } - - /* - * If there won't be at least FAKE_NODE_MIN_SIZE of - * non-reserved memory in ZONE_DMA32 for the next node, - * this one must extend to the boundary. - */ - if (end < dma32_end && dma32_end - end - - mem_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE) - end = dma32_end; - - /* - * If there won't be enough non-reserved memory for the - * next node, this one must extend to the end of the - * physical node. - */ - if (limit - end - mem_hole_size(end, limit) < size) - end = limit; - - ret = emu_setup_memblk(ei, pi, nid++ % nr_nodes, - phys_blk, - min(end, limit) - start); - if (ret < 0) - return ret; - } - } - return 0; -} - -/* - * Returns the end address of a node so that there is at least `size' amount of - * non-reserved memory or `max_addr' is reached. - */ -static u64 __init find_end_of_node(u64 start, u64 max_addr, u64 size) -{ - u64 end = start + size; - - while (end - start - mem_hole_size(start, end) < size) { - end += FAKE_NODE_MIN_SIZE; - if (end > max_addr) { - end = max_addr; - break; - } - } - return end; -} - -static u64 uniform_size(u64 max_addr, u64 base, u64 hole, int nr_nodes) -{ - unsigned long max_pfn = PHYS_PFN(max_addr); - unsigned long base_pfn = PHYS_PFN(base); - unsigned long hole_pfns = PHYS_PFN(hole); - - return PFN_PHYS((max_pfn - base_pfn - hole_pfns) / nr_nodes); -} - -/* - * Sets up fake nodes of `size' interleaved over physical nodes ranging from - * `addr' to `max_addr'. - * - * Returns zero on success or negative on error. - */ -static int __init split_nodes_size_interleave_uniform(struct numa_meminfo *ei, - struct numa_meminfo *pi, - u64 addr, u64 max_addr, u64 size, - int nr_nodes, struct numa_memblk *pblk, - int nid) -{ - nodemask_t physnode_mask = numa_nodes_parsed; - int i, ret, uniform = 0; - u64 min_size; - - if ((!size && !nr_nodes) || (nr_nodes && !pblk)) - return -1; - - /* - * In the 'uniform' case split the passed in physical node by - * nr_nodes, in the non-uniform case, ignore the passed in - * physical block and try to create nodes of at least size - * @size. - * - * In the uniform case, split the nodes strictly by physical - * capacity, i.e. ignore holes. In the non-uniform case account - * for holes and treat @size as a minimum floor. - */ - if (!nr_nodes) - nr_nodes = MAX_NUMNODES; - else { - nodes_clear(physnode_mask); - node_set(pblk->nid, physnode_mask); - uniform = 1; - } - - if (uniform) { - min_size = uniform_size(max_addr, addr, 0, nr_nodes); - size = min_size; - } else { - /* - * The limit on emulated nodes is MAX_NUMNODES, so the - * size per node is increased accordingly if the - * requested size is too small. This creates a uniform - * distribution of node sizes across the entire machine - * (but not necessarily over physical nodes). - */ - min_size = uniform_size(max_addr, addr, - mem_hole_size(addr, max_addr), nr_nodes); - } - min_size = ALIGN(max(min_size, FAKE_NODE_MIN_SIZE), FAKE_NODE_MIN_SIZE); - if (size < min_size) { - pr_err("Fake node size %LuMB too small, increasing to %LuMB\n", - size >> 20, min_size >> 20); - size = min_size; - } - size = ALIGN_DOWN(size, FAKE_NODE_MIN_SIZE); - - /* - * Fill physical nodes with fake nodes of size until there is no memory - * left on any of them. - */ - while (!nodes_empty(physnode_mask)) { - for_each_node_mask(i, physnode_mask) { - u64 dma32_end = numa_emu_dma_end(); - u64 start, limit, end; - int phys_blk; - - phys_blk = emu_find_memblk_by_nid(i, pi); - if (phys_blk < 0) { - node_clear(i, physnode_mask); - continue; - } - - start = pi->blk[phys_blk].start; - limit = pi->blk[phys_blk].end; - - if (uniform) - end = start + size; - else - end = find_end_of_node(start, limit, size); - /* - * If there won't be at least FAKE_NODE_MIN_SIZE of - * non-reserved memory in ZONE_DMA32 for the next node, - * this one must extend to the boundary. - */ - if (end < dma32_end && dma32_end - end - - mem_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE) - end = dma32_end; - - /* - * If there won't be enough non-reserved memory for the - * next node, this one must extend to the end of the - * physical node. - */ - if ((limit - end - mem_hole_size(end, limit) < size) - && !uniform) - end = limit; - - ret = emu_setup_memblk(ei, pi, nid++ % MAX_NUMNODES, - phys_blk, - min(end, limit) - start); - if (ret < 0) - return ret; - } - } - return nid; -} - -static int __init split_nodes_size_interleave(struct numa_meminfo *ei, - struct numa_meminfo *pi, - u64 addr, u64 max_addr, u64 size) -{ - return split_nodes_size_interleave_uniform(ei, pi, addr, max_addr, size, - 0, NULL, 0); -} - -static int __init setup_emu2phys_nid(int *dfl_phys_nid) -{ - int i, max_emu_nid = 0; - - *dfl_phys_nid = NUMA_NO_NODE; - for (i = 0; i < ARRAY_SIZE(emu_nid_to_phys); i++) { - if (emu_nid_to_phys[i] != NUMA_NO_NODE) { - max_emu_nid = i; - if (*dfl_phys_nid == NUMA_NO_NODE) - *dfl_phys_nid = emu_nid_to_phys[i]; - } - } - - return max_emu_nid; -} - -/** - * numa_emulation - Emulate NUMA nodes - * @numa_meminfo: NUMA configuration to massage - * @numa_dist_cnt: The size of the physical NUMA distance table - * - * Emulate NUMA nodes according to the numa=fake kernel parameter. - * @numa_meminfo contains the physical memory configuration and is modified - * to reflect the emulated configuration on success. @numa_dist_cnt is - * used to determine the size of the physical distance table. - * - * On success, the following modifications are made. - * - * - @numa_meminfo is updated to reflect the emulated nodes. - * - * - __apicid_to_node[] is updated such that APIC IDs are mapped to the - * emulated nodes. - * - * - NUMA distance table is rebuilt to represent distances between emulated - * nodes. The distances are determined considering how emulated nodes - * are mapped to physical nodes and match the actual distances. - * - * - emu_nid_to_phys[] reflects how emulated nodes are mapped to physical - * nodes. This is used by numa_add_cpu() and numa_remove_cpu(). - * - * If emulation is not enabled or fails, emu_nid_to_phys[] is filled with - * identity mapping and no other modification is made. - */ -void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) -{ - static struct numa_meminfo ei __initdata; - static struct numa_meminfo pi __initdata; - const u64 max_addr = PFN_PHYS(max_pfn); - u8 *phys_dist = NULL; - size_t phys_size = numa_dist_cnt * numa_dist_cnt * sizeof(phys_dist[0]); - int max_emu_nid, dfl_phys_nid; - int i, j, ret; - - if (!emu_cmdline) - goto no_emu; - - memset(&ei, 0, sizeof(ei)); - pi = *numa_meminfo; - - for (i = 0; i < MAX_NUMNODES; i++) - emu_nid_to_phys[i] = NUMA_NO_NODE; - - /* - * If the numa=fake command-line contains a 'M' or 'G', it represents - * the fixed node size. Otherwise, if it is just a single number N, - * split the system RAM into N fake nodes. - */ - if (strchr(emu_cmdline, 'U')) { - nodemask_t physnode_mask = numa_nodes_parsed; - unsigned long n; - int nid = 0; - - n = simple_strtoul(emu_cmdline, &emu_cmdline, 0); - ret = -1; - for_each_node_mask(i, physnode_mask) { - /* - * The reason we pass in blk[0] is due to - * numa_remove_memblk_from() called by - * emu_setup_memblk() will delete entry 0 - * and then move everything else up in the pi.blk - * array. Therefore we should always be looking - * at blk[0]. - */ - ret = split_nodes_size_interleave_uniform(&ei, &pi, - pi.blk[0].start, pi.blk[0].end, 0, - n, &pi.blk[0], nid); - if (ret < 0) - break; - if (ret < n) { - pr_info("%s: phys: %d only got %d of %ld nodes, failing\n", - __func__, i, ret, n); - ret = -1; - break; - } - nid = ret; - } - } else if (strchr(emu_cmdline, 'M') || strchr(emu_cmdline, 'G')) { - u64 size; - - size = memparse(emu_cmdline, &emu_cmdline); - ret = split_nodes_size_interleave(&ei, &pi, 0, max_addr, size); - } else { - unsigned long n; - - n = simple_strtoul(emu_cmdline, &emu_cmdline, 0); - ret = split_nodes_interleave(&ei, &pi, 0, max_addr, n); - } - if (*emu_cmdline == ':') - emu_cmdline++; - - if (ret < 0) - goto no_emu; - - if (numa_cleanup_meminfo(&ei) < 0) { - pr_warn("NUMA: Warning: constructed meminfo invalid, disabling emulation\n"); - goto no_emu; - } - - /* copy the physical distance table */ - if (numa_dist_cnt) { - phys_dist = memblock_alloc(phys_size, PAGE_SIZE); - if (!phys_dist) { - pr_warn("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n"); - goto no_emu; - } - - for (i = 0; i < numa_dist_cnt; i++) - for (j = 0; j < numa_dist_cnt; j++) - phys_dist[i * numa_dist_cnt + j] = - node_distance(i, j); - } - - /* - * Determine the max emulated nid and the default phys nid to use - * for unmapped nodes. - */ - max_emu_nid = setup_emu2phys_nid(&dfl_phys_nid); - - /* commit */ - *numa_meminfo = ei; - - /* Make sure numa_nodes_parsed only contains emulated nodes */ - nodes_clear(numa_nodes_parsed); - for (i = 0; i < ARRAY_SIZE(ei.blk); i++) - if (ei.blk[i].start != ei.blk[i].end && - ei.blk[i].nid != NUMA_NO_NODE) - node_set(ei.blk[i].nid, numa_nodes_parsed); - - numa_emu_update_cpu_to_node(emu_nid_to_phys, ARRAY_SIZE(emu_nid_to_phys)); - - /* make sure all emulated nodes are mapped to a physical node */ - for (i = 0; i < ARRAY_SIZE(emu_nid_to_phys); i++) - if (emu_nid_to_phys[i] == NUMA_NO_NODE) - emu_nid_to_phys[i] = dfl_phys_nid; - - /* transform distance table */ - numa_reset_distance(); - for (i = 0; i < max_emu_nid + 1; i++) { - for (j = 0; j < max_emu_nid + 1; j++) { - int physi = emu_nid_to_phys[i]; - int physj = emu_nid_to_phys[j]; - int dist; - - if (get_option(&emu_cmdline, &dist) == 2) - ; - else if (physi >= numa_dist_cnt || physj >= numa_dist_cnt) - dist = physi == physj ? - LOCAL_DISTANCE : REMOTE_DISTANCE; - else - dist = phys_dist[physi * numa_dist_cnt + physj]; - - numa_set_distance(i, j, dist); - } - } - - /* free the copied physical distance table */ - memblock_free(phys_dist, phys_size); - return; - -no_emu: - /* No emulation. Build identity emu_nid_to_phys[] for numa_add_cpu() */ - for (i = 0; i < ARRAY_SIZE(emu_nid_to_phys); i++) - emu_nid_to_phys[i] = i; -} - -#ifndef CONFIG_DEBUG_PER_CPU_MAPS -void numa_add_cpu(unsigned int cpu) -{ - int physnid, nid; - - nid = early_cpu_to_node(cpu); - BUG_ON(nid == NUMA_NO_NODE || !node_online(nid)); - - physnid = emu_nid_to_phys[nid]; - - /* - * Map the cpu to each emulated node that is allocated on the physical - * node of the cpu's apic id. - */ - for_each_online_node(nid) - if (emu_nid_to_phys[nid] == physnid) - cpumask_set_cpu(cpu, node_to_cpumask_map[nid]); -} - -void numa_remove_cpu(unsigned int cpu) -{ - int i; - - for_each_online_node(i) - cpumask_clear_cpu(cpu, node_to_cpumask_map[i]); -} -#else /* !CONFIG_DEBUG_PER_CPU_MAPS */ -static void numa_set_cpumask(unsigned int cpu, bool enable) -{ - int nid, physnid; - - nid = early_cpu_to_node(cpu); - if (nid == NUMA_NO_NODE) { - /* early_cpu_to_node() already emits a warning and trace */ - return; - } - - physnid = emu_nid_to_phys[nid]; - - for_each_online_node(nid) { - if (emu_nid_to_phys[nid] != physnid) - continue; - - debug_cpumask_set_cpu(cpu, nid, enable); - } -} - -void numa_add_cpu(unsigned int cpu) -{ - numa_set_cpumask(cpu, true); -} - -void numa_remove_cpu(unsigned int cpu) -{ - numa_set_cpumask(cpu, false); -} -#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */ diff --git a/arch/x86/mm/numa_internal.h b/arch/x86/mm/numa_internal.h index 249e3aaeadce..11e1ff370c10 100644 --- a/arch/x86/mm/numa_internal.h +++ b/arch/x86/mm/numa_internal.h @@ -7,15 +7,4 @@ void __init x86_numa_init(void); -struct numa_meminfo; - -#ifdef CONFIG_NUMA_EMU -void __init numa_emulation(struct numa_meminfo *numa_meminfo, - int numa_dist_cnt); -#else -static inline void numa_emulation(struct numa_meminfo *numa_meminfo, - int numa_dist_cnt) -{ } -#endif - #endif /* __X86_MM_NUMA_INTERNAL_H */ diff --git a/include/linux/numa_memblks.h b/include/linux/numa_memblks.h index 968a590535ac..f81f98678074 100644 --- a/include/linux/numa_memblks.h +++ b/include/linux/numa_memblks.h @@ -34,6 +34,23 @@ int __init numa_register_meminfo(struct numa_meminfo *mi); void __init numa_nodemask_from_meminfo(nodemask_t *nodemask, const struct numa_meminfo *mi); +#ifdef CONFIG_NUMA_EMU +int numa_emu_cmdline(char *str); +void __init numa_emu_update_cpu_to_node(int *emu_nid_to_phys, + unsigned int nr_emu_nids); +u64 __init numa_emu_dma_end(void); +void __init numa_emulation(struct numa_meminfo *numa_meminfo, + int numa_dist_cnt); +#else +static inline void numa_emulation(struct numa_meminfo *numa_meminfo, + int numa_dist_cnt) +{ } +static inline int numa_emu_cmdline(char *str) +{ + return -EINVAL; +} +#endif /* CONFIG_NUMA_EMU */ + #endif /* CONFIG_NUMA_MEMBLKS */ #endif /* __NUMA_MEMBLKS_H */ diff --git a/mm/Kconfig b/mm/Kconfig index 67700a127982..3936fe4d26d9 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -1270,6 +1270,14 @@ config EXECMEM config NUMA_MEMBLKS bool +config NUMA_EMU + bool "NUMA emulation" + depends on NUMA_MEMBLKS + help + Enable NUMA emulation. A flat machine will be split + into virtual nodes when booted with "numa=fake=N", where N is the + number of nodes. This is only useful for debugging. + source "mm/damon/Kconfig" endmenu diff --git a/mm/Makefile b/mm/Makefile index 0778dce4aef6..d5639b036166 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -119,6 +119,7 @@ obj-$(CONFIG_GENERIC_EARLY_IOREMAP) += early_ioremap.o obj-$(CONFIG_CMA) += cma.o obj-$(CONFIG_NUMA) += numa.o obj-$(CONFIG_NUMA_MEMBLKS) += numa_memblks.o +obj-$(CONFIG_NUMA_EMU) += numa_emulation.o obj-$(CONFIG_MEMORY_BALLOON) += balloon_compaction.o obj-$(CONFIG_PAGE_EXTENSION) += page_ext.o obj-$(CONFIG_PAGE_TABLE_CHECK) += page_table_check.o diff --git a/mm/numa_emulation.c b/mm/numa_emulation.c new file mode 100644 index 000000000000..031fb9961bf7 --- /dev/null +++ b/mm/numa_emulation.c @@ -0,0 +1,571 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * NUMA emulation + */ +#include +#include +#include +#include +#include +#include + +#define FAKE_NODE_MIN_SIZE ((u64)32 << 20) +#define FAKE_NODE_MIN_HASH_MASK (~(FAKE_NODE_MIN_SIZE - 1UL)) + +static int emu_nid_to_phys[MAX_NUMNODES]; +static char *emu_cmdline __initdata; + +int __init numa_emu_cmdline(char *str) +{ + emu_cmdline = str; + return 0; +} + +static int __init emu_find_memblk_by_nid(int nid, const struct numa_meminfo *mi) +{ + int i; + + for (i = 0; i < mi->nr_blks; i++) + if (mi->blk[i].nid == nid) + return i; + return -ENOENT; +} + +static u64 __init mem_hole_size(u64 start, u64 end) +{ + unsigned long start_pfn = PFN_UP(start); + unsigned long end_pfn = PFN_DOWN(end); + + if (start_pfn < end_pfn) + return PFN_PHYS(absent_pages_in_range(start_pfn, end_pfn)); + return 0; +} + +/* + * Sets up nid to range from @start to @end. The return value is -errno if + * something went wrong, 0 otherwise. + */ +static int __init emu_setup_memblk(struct numa_meminfo *ei, + struct numa_meminfo *pi, + int nid, int phys_blk, u64 size) +{ + struct numa_memblk *eb = &ei->blk[ei->nr_blks]; + struct numa_memblk *pb = &pi->blk[phys_blk]; + + if (ei->nr_blks >= NR_NODE_MEMBLKS) { + pr_err("NUMA: Too many emulated memblks, failing emulation\n"); + return -EINVAL; + } + + ei->nr_blks++; + eb->start = pb->start; + eb->end = pb->start + size; + eb->nid = nid; + + if (emu_nid_to_phys[nid] == NUMA_NO_NODE) + emu_nid_to_phys[nid] = pb->nid; + + pb->start += size; + if (pb->start >= pb->end) { + WARN_ON_ONCE(pb->start > pb->end); + numa_remove_memblk_from(phys_blk, pi); + } + + printk(KERN_INFO "Faking node %d at [mem %#018Lx-%#018Lx] (%LuMB)\n", + nid, eb->start, eb->end - 1, (eb->end - eb->start) >> 20); + return 0; +} + +/* + * Sets up nr_nodes fake nodes interleaved over physical nodes ranging from addr + * to max_addr. + * + * Returns zero on success or negative on error. + */ +static int __init split_nodes_interleave(struct numa_meminfo *ei, + struct numa_meminfo *pi, + u64 addr, u64 max_addr, int nr_nodes) +{ + nodemask_t physnode_mask = numa_nodes_parsed; + u64 size; + int big; + int nid = 0; + int i, ret; + + if (nr_nodes <= 0) + return -1; + if (nr_nodes > MAX_NUMNODES) { + pr_info("numa=fake=%d too large, reducing to %d\n", + nr_nodes, MAX_NUMNODES); + nr_nodes = MAX_NUMNODES; + } + + /* + * Calculate target node size. x86_32 freaks on __udivdi3() so do + * the division in ulong number of pages and convert back. + */ + size = max_addr - addr - mem_hole_size(addr, max_addr); + size = PFN_PHYS((unsigned long)(size >> PAGE_SHIFT) / nr_nodes); + + /* + * Calculate the number of big nodes that can be allocated as a result + * of consolidating the remainder. + */ + big = ((size & ~FAKE_NODE_MIN_HASH_MASK) * nr_nodes) / + FAKE_NODE_MIN_SIZE; + + size &= FAKE_NODE_MIN_HASH_MASK; + if (!size) { + pr_err("Not enough memory for each node. " + "NUMA emulation disabled.\n"); + return -1; + } + + /* + * Continue to fill physical nodes with fake nodes until there is no + * memory left on any of them. + */ + while (!nodes_empty(physnode_mask)) { + for_each_node_mask(i, physnode_mask) { + u64 dma32_end = numa_emu_dma_end(); + u64 start, limit, end; + int phys_blk; + + phys_blk = emu_find_memblk_by_nid(i, pi); + if (phys_blk < 0) { + node_clear(i, physnode_mask); + continue; + } + start = pi->blk[phys_blk].start; + limit = pi->blk[phys_blk].end; + end = start + size; + + if (nid < big) + end += FAKE_NODE_MIN_SIZE; + + /* + * Continue to add memory to this fake node if its + * non-reserved memory is less than the per-node size. + */ + while (end - start - mem_hole_size(start, end) < size) { + end += FAKE_NODE_MIN_SIZE; + if (end > limit) { + end = limit; + break; + } + } + + /* + * If there won't be at least FAKE_NODE_MIN_SIZE of + * non-reserved memory in ZONE_DMA32 for the next node, + * this one must extend to the boundary. + */ + if (end < dma32_end && dma32_end - end - + mem_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE) + end = dma32_end; + + /* + * If there won't be enough non-reserved memory for the + * next node, this one must extend to the end of the + * physical node. + */ + if (limit - end - mem_hole_size(end, limit) < size) + end = limit; + + ret = emu_setup_memblk(ei, pi, nid++ % nr_nodes, + phys_blk, + min(end, limit) - start); + if (ret < 0) + return ret; + } + } + return 0; +} + +/* + * Returns the end address of a node so that there is at least `size' amount of + * non-reserved memory or `max_addr' is reached. + */ +static u64 __init find_end_of_node(u64 start, u64 max_addr, u64 size) +{ + u64 end = start + size; + + while (end - start - mem_hole_size(start, end) < size) { + end += FAKE_NODE_MIN_SIZE; + if (end > max_addr) { + end = max_addr; + break; + } + } + return end; +} + +static u64 uniform_size(u64 max_addr, u64 base, u64 hole, int nr_nodes) +{ + unsigned long max_pfn = PHYS_PFN(max_addr); + unsigned long base_pfn = PHYS_PFN(base); + unsigned long hole_pfns = PHYS_PFN(hole); + + return PFN_PHYS((max_pfn - base_pfn - hole_pfns) / nr_nodes); +} + +/* + * Sets up fake nodes of `size' interleaved over physical nodes ranging from + * `addr' to `max_addr'. + * + * Returns zero on success or negative on error. + */ +static int __init split_nodes_size_interleave_uniform(struct numa_meminfo *ei, + struct numa_meminfo *pi, + u64 addr, u64 max_addr, u64 size, + int nr_nodes, struct numa_memblk *pblk, + int nid) +{ + nodemask_t physnode_mask = numa_nodes_parsed; + int i, ret, uniform = 0; + u64 min_size; + + if ((!size && !nr_nodes) || (nr_nodes && !pblk)) + return -1; + + /* + * In the 'uniform' case split the passed in physical node by + * nr_nodes, in the non-uniform case, ignore the passed in + * physical block and try to create nodes of at least size + * @size. + * + * In the uniform case, split the nodes strictly by physical + * capacity, i.e. ignore holes. In the non-uniform case account + * for holes and treat @size as a minimum floor. + */ + if (!nr_nodes) + nr_nodes = MAX_NUMNODES; + else { + nodes_clear(physnode_mask); + node_set(pblk->nid, physnode_mask); + uniform = 1; + } + + if (uniform) { + min_size = uniform_size(max_addr, addr, 0, nr_nodes); + size = min_size; + } else { + /* + * The limit on emulated nodes is MAX_NUMNODES, so the + * size per node is increased accordingly if the + * requested size is too small. This creates a uniform + * distribution of node sizes across the entire machine + * (but not necessarily over physical nodes). + */ + min_size = uniform_size(max_addr, addr, + mem_hole_size(addr, max_addr), nr_nodes); + } + min_size = ALIGN(max(min_size, FAKE_NODE_MIN_SIZE), FAKE_NODE_MIN_SIZE); + if (size < min_size) { + pr_err("Fake node size %LuMB too small, increasing to %LuMB\n", + size >> 20, min_size >> 20); + size = min_size; + } + size = ALIGN_DOWN(size, FAKE_NODE_MIN_SIZE); + + /* + * Fill physical nodes with fake nodes of size until there is no memory + * left on any of them. + */ + while (!nodes_empty(physnode_mask)) { + for_each_node_mask(i, physnode_mask) { + u64 dma32_end = numa_emu_dma_end(); + u64 start, limit, end; + int phys_blk; + + phys_blk = emu_find_memblk_by_nid(i, pi); + if (phys_blk < 0) { + node_clear(i, physnode_mask); + continue; + } + + start = pi->blk[phys_blk].start; + limit = pi->blk[phys_blk].end; + + if (uniform) + end = start + size; + else + end = find_end_of_node(start, limit, size); + /* + * If there won't be at least FAKE_NODE_MIN_SIZE of + * non-reserved memory in ZONE_DMA32 for the next node, + * this one must extend to the boundary. + */ + if (end < dma32_end && dma32_end - end - + mem_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE) + end = dma32_end; + + /* + * If there won't be enough non-reserved memory for the + * next node, this one must extend to the end of the + * physical node. + */ + if ((limit - end - mem_hole_size(end, limit) < size) + && !uniform) + end = limit; + + ret = emu_setup_memblk(ei, pi, nid++ % MAX_NUMNODES, + phys_blk, + min(end, limit) - start); + if (ret < 0) + return ret; + } + } + return nid; +} + +static int __init split_nodes_size_interleave(struct numa_meminfo *ei, + struct numa_meminfo *pi, + u64 addr, u64 max_addr, u64 size) +{ + return split_nodes_size_interleave_uniform(ei, pi, addr, max_addr, size, + 0, NULL, 0); +} + +static int __init setup_emu2phys_nid(int *dfl_phys_nid) +{ + int i, max_emu_nid = 0; + + *dfl_phys_nid = NUMA_NO_NODE; + for (i = 0; i < ARRAY_SIZE(emu_nid_to_phys); i++) { + if (emu_nid_to_phys[i] != NUMA_NO_NODE) { + max_emu_nid = i; + if (*dfl_phys_nid == NUMA_NO_NODE) + *dfl_phys_nid = emu_nid_to_phys[i]; + } + } + + return max_emu_nid; +} + +/** + * numa_emulation - Emulate NUMA nodes + * @numa_meminfo: NUMA configuration to massage + * @numa_dist_cnt: The size of the physical NUMA distance table + * + * Emulate NUMA nodes according to the numa=fake kernel parameter. + * @numa_meminfo contains the physical memory configuration and is modified + * to reflect the emulated configuration on success. @numa_dist_cnt is + * used to determine the size of the physical distance table. + * + * On success, the following modifications are made. + * + * - @numa_meminfo is updated to reflect the emulated nodes. + * + * - __apicid_to_node[] is updated such that APIC IDs are mapped to the + * emulated nodes. + * + * - NUMA distance table is rebuilt to represent distances between emulated + * nodes. The distances are determined considering how emulated nodes + * are mapped to physical nodes and match the actual distances. + * + * - emu_nid_to_phys[] reflects how emulated nodes are mapped to physical + * nodes. This is used by numa_add_cpu() and numa_remove_cpu(). + * + * If emulation is not enabled or fails, emu_nid_to_phys[] is filled with + * identity mapping and no other modification is made. + */ +void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) +{ + static struct numa_meminfo ei __initdata; + static struct numa_meminfo pi __initdata; + const u64 max_addr = PFN_PHYS(max_pfn); + u8 *phys_dist = NULL; + size_t phys_size = numa_dist_cnt * numa_dist_cnt * sizeof(phys_dist[0]); + int max_emu_nid, dfl_phys_nid; + int i, j, ret; + + if (!emu_cmdline) + goto no_emu; + + memset(&ei, 0, sizeof(ei)); + pi = *numa_meminfo; + + for (i = 0; i < MAX_NUMNODES; i++) + emu_nid_to_phys[i] = NUMA_NO_NODE; + + /* + * If the numa=fake command-line contains a 'M' or 'G', it represents + * the fixed node size. Otherwise, if it is just a single number N, + * split the system RAM into N fake nodes. + */ + if (strchr(emu_cmdline, 'U')) { + nodemask_t physnode_mask = numa_nodes_parsed; + unsigned long n; + int nid = 0; + + n = simple_strtoul(emu_cmdline, &emu_cmdline, 0); + ret = -1; + for_each_node_mask(i, physnode_mask) { + /* + * The reason we pass in blk[0] is due to + * numa_remove_memblk_from() called by + * emu_setup_memblk() will delete entry 0 + * and then move everything else up in the pi.blk + * array. Therefore we should always be looking + * at blk[0]. + */ + ret = split_nodes_size_interleave_uniform(&ei, &pi, + pi.blk[0].start, pi.blk[0].end, 0, + n, &pi.blk[0], nid); + if (ret < 0) + break; + if (ret < n) { + pr_info("%s: phys: %d only got %d of %ld nodes, failing\n", + __func__, i, ret, n); + ret = -1; + break; + } + nid = ret; + } + } else if (strchr(emu_cmdline, 'M') || strchr(emu_cmdline, 'G')) { + u64 size; + + size = memparse(emu_cmdline, &emu_cmdline); + ret = split_nodes_size_interleave(&ei, &pi, 0, max_addr, size); + } else { + unsigned long n; + + n = simple_strtoul(emu_cmdline, &emu_cmdline, 0); + ret = split_nodes_interleave(&ei, &pi, 0, max_addr, n); + } + if (*emu_cmdline == ':') + emu_cmdline++; + + if (ret < 0) + goto no_emu; + + if (numa_cleanup_meminfo(&ei) < 0) { + pr_warn("NUMA: Warning: constructed meminfo invalid, disabling emulation\n"); + goto no_emu; + } + + /* copy the physical distance table */ + if (numa_dist_cnt) { + phys_dist = memblock_alloc(phys_size, PAGE_SIZE); + if (!phys_dist) { + pr_warn("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n"); + goto no_emu; + } + + for (i = 0; i < numa_dist_cnt; i++) + for (j = 0; j < numa_dist_cnt; j++) + phys_dist[i * numa_dist_cnt + j] = + node_distance(i, j); + } + + /* + * Determine the max emulated nid and the default phys nid to use + * for unmapped nodes. + */ + max_emu_nid = setup_emu2phys_nid(&dfl_phys_nid); + + /* commit */ + *numa_meminfo = ei; + + /* Make sure numa_nodes_parsed only contains emulated nodes */ + nodes_clear(numa_nodes_parsed); + for (i = 0; i < ARRAY_SIZE(ei.blk); i++) + if (ei.blk[i].start != ei.blk[i].end && + ei.blk[i].nid != NUMA_NO_NODE) + node_set(ei.blk[i].nid, numa_nodes_parsed); + + numa_emu_update_cpu_to_node(emu_nid_to_phys, ARRAY_SIZE(emu_nid_to_phys)); + + /* make sure all emulated nodes are mapped to a physical node */ + for (i = 0; i < ARRAY_SIZE(emu_nid_to_phys); i++) + if (emu_nid_to_phys[i] == NUMA_NO_NODE) + emu_nid_to_phys[i] = dfl_phys_nid; + + /* transform distance table */ + numa_reset_distance(); + for (i = 0; i < max_emu_nid + 1; i++) { + for (j = 0; j < max_emu_nid + 1; j++) { + int physi = emu_nid_to_phys[i]; + int physj = emu_nid_to_phys[j]; + int dist; + + if (get_option(&emu_cmdline, &dist) == 2) + ; + else if (physi >= numa_dist_cnt || physj >= numa_dist_cnt) + dist = physi == physj ? + LOCAL_DISTANCE : REMOTE_DISTANCE; + else + dist = phys_dist[physi * numa_dist_cnt + physj]; + + numa_set_distance(i, j, dist); + } + } + + /* free the copied physical distance table */ + memblock_free(phys_dist, phys_size); + return; + +no_emu: + /* No emulation. Build identity emu_nid_to_phys[] for numa_add_cpu() */ + for (i = 0; i < ARRAY_SIZE(emu_nid_to_phys); i++) + emu_nid_to_phys[i] = i; +} + +#ifndef CONFIG_DEBUG_PER_CPU_MAPS +void numa_add_cpu(unsigned int cpu) +{ + int physnid, nid; + + nid = early_cpu_to_node(cpu); + BUG_ON(nid == NUMA_NO_NODE || !node_online(nid)); + + physnid = emu_nid_to_phys[nid]; + + /* + * Map the cpu to each emulated node that is allocated on the physical + * node of the cpu's apic id. + */ + for_each_online_node(nid) + if (emu_nid_to_phys[nid] == physnid) + cpumask_set_cpu(cpu, node_to_cpumask_map[nid]); +} + +void numa_remove_cpu(unsigned int cpu) +{ + int i; + + for_each_online_node(i) + cpumask_clear_cpu(cpu, node_to_cpumask_map[i]); +} +#else /* !CONFIG_DEBUG_PER_CPU_MAPS */ +static void numa_set_cpumask(unsigned int cpu, bool enable) +{ + int nid, physnid; + + nid = early_cpu_to_node(cpu); + if (nid == NUMA_NO_NODE) { + /* early_cpu_to_node() already emits a warning and trace */ + return; + } + + physnid = emu_nid_to_phys[nid]; + + for_each_online_node(nid) { + if (emu_nid_to_phys[nid] != physnid) + continue; + + debug_cpumask_set_cpu(cpu, nid, enable); + } +} + +void numa_add_cpu(unsigned int cpu) +{ + numa_set_cpumask(cpu, true); +} + +void numa_remove_cpu(unsigned int cpu) +{ + numa_set_cpumask(cpu, false); +} +#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */ -- cgit v1.2.3 From 692d73d2f0f75e58828ab05872b3789ae1f486ef Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Wed, 7 Aug 2024 09:41:04 +0300 Subject: mm: numa_memblks: introduce numa_memblks_init Move most of x86::numa_init() to numa_memblks so that the latter will be more self-contained. With this numa_memblk data structures should not be exposed to the architecture specific code. Link: https://lkml.kernel.org/r/20240807064110.1003856-21-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) Tested-by: Zi Yan # for x86_64 and arm64 Reviewed-by: Jonathan Cameron Tested-by: Jonathan Cameron [arm64 + CXL via QEMU] Acked-by: Dan Williams Acked-by: David Hildenbrand Cc: Alexander Gordeev Cc: Andreas Larsson Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christophe Leroy Cc: Dave Hansen Cc: Davidlohr Bueso Cc: David S. Miller Cc: Greg Kroah-Hartman Cc: Heiko Carstens Cc: Huacai Chen Cc: Ingo Molnar Cc: Jiaxun Yang Cc: John Paul Adrian Glaubitz Cc: Jonathan Corbet Cc: Michael Ellerman Cc: Palmer Dabbelt Cc: Rafael J. Wysocki Cc: Rob Herring (Arm) Cc: Samuel Holland Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/x86/mm/numa.c | 40 ++++------------------------------------ include/linux/numa_memblks.h | 3 +++ mm/numa_memblks.c | 41 +++++++++++++++++++++++++++++++++++++++++ 3 files changed, 48 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 095502095503..d23287611449 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -115,13 +115,9 @@ void __init setup_node_to_cpumask_map(void) pr_debug("Node to cpumask map for %u nodes\n", nr_node_ids); } -static int __init numa_register_memblks(struct numa_meminfo *mi) +static int __init numa_register_nodes(void) { - int nid, err; - - err = numa_register_meminfo(mi); - if (err) - return err; + int nid; if (!memblock_validate_numa_coverage(SZ_1M)) return -EINVAL; @@ -175,39 +171,11 @@ static int __init numa_init(int (*init_func)(void)) for (i = 0; i < MAX_LOCAL_APIC; i++) set_apicid_to_node(i, NUMA_NO_NODE); - nodes_clear(numa_nodes_parsed); - nodes_clear(node_possible_map); - nodes_clear(node_online_map); - memset(&numa_meminfo, 0, sizeof(numa_meminfo)); - WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.memory, - NUMA_NO_NODE)); - WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.reserved, - NUMA_NO_NODE)); - /* In case that parsing SRAT failed. */ - WARN_ON(memblock_clear_hotplug(0, ULLONG_MAX)); - numa_reset_distance(); - - ret = init_func(); + ret = numa_memblks_init(init_func, /* memblock_force_top_down */ true); if (ret < 0) return ret; - /* - * We reset memblock back to the top-down direction - * here because if we configured ACPI_NUMA, we have - * parsed SRAT in init_func(). It is ok to have the - * reset here even if we did't configure ACPI_NUMA - * or acpi numa init fails and fallbacks to dummy - * numa init. - */ - memblock_set_bottom_up(false); - - ret = numa_cleanup_meminfo(&numa_meminfo); - if (ret < 0) - return ret; - - numa_emulation(&numa_meminfo, numa_distance_cnt); - - ret = numa_register_memblks(&numa_meminfo); + ret = numa_register_nodes(); if (ret < 0) return ret; diff --git a/include/linux/numa_memblks.h b/include/linux/numa_memblks.h index f81f98678074..07381320848f 100644 --- a/include/linux/numa_memblks.h +++ b/include/linux/numa_memblks.h @@ -34,6 +34,9 @@ int __init numa_register_meminfo(struct numa_meminfo *mi); void __init numa_nodemask_from_meminfo(nodemask_t *nodemask, const struct numa_meminfo *mi); +int __init numa_memblks_init(int (*init_func)(void), + bool memblock_force_top_down); + #ifdef CONFIG_NUMA_EMU int numa_emu_cmdline(char *str); void __init numa_emu_update_cpu_to_node(int *emu_nid_to_phys, diff --git a/mm/numa_memblks.c b/mm/numa_memblks.c index e3c3519725d4..7749b6f6b250 100644 --- a/mm/numa_memblks.c +++ b/mm/numa_memblks.c @@ -415,6 +415,47 @@ int __init numa_register_meminfo(struct numa_meminfo *mi) return 0; } +int __init numa_memblks_init(int (*init_func)(void), + bool memblock_force_top_down) +{ + int ret; + + nodes_clear(numa_nodes_parsed); + nodes_clear(node_possible_map); + nodes_clear(node_online_map); + memset(&numa_meminfo, 0, sizeof(numa_meminfo)); + WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.memory, + NUMA_NO_NODE)); + WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.reserved, + NUMA_NO_NODE)); + /* In case that parsing SRAT failed. */ + WARN_ON(memblock_clear_hotplug(0, ULLONG_MAX)); + numa_reset_distance(); + + ret = init_func(); + if (ret < 0) + return ret; + + /* + * We reset memblock back to the top-down direction + * here because if we configured ACPI_NUMA, we have + * parsed SRAT in init_func(). It is ok to have the + * reset here even if we did't configure ACPI_NUMA + * or acpi numa init fails and fallbacks to dummy + * numa init. + */ + if (memblock_force_top_down) + memblock_set_bottom_up(false); + + ret = numa_cleanup_meminfo(&numa_meminfo); + if (ret < 0) + return ret; + + numa_emulation(&numa_meminfo, numa_distance_cnt); + + return numa_register_meminfo(&numa_meminfo); +} + static int __init cmp_memblk(const void *a, const void *b) { const struct numa_memblk *ma = *(const struct numa_memblk **)a; -- cgit v1.2.3 From 317ef4598bdc48c0196adc02ed4edaf82af279f2 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Wed, 7 Aug 2024 09:41:05 +0300 Subject: mm: numa_memblks: make several functions and variables static Make functions and variables that are exclusively used by numa_memblks static. Move numa_nodemask_from_meminfo() before its callers to avoid forward declaration. Link: https://lkml.kernel.org/r/20240807064110.1003856-22-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) Tested-by: Zi Yan # for x86_64 and arm64 Reviewed-by: Jonathan Cameron Tested-by: Jonathan Cameron [arm64 + CXL via QEMU] Acked-by: Dan Williams Acked-by: David Hildenbrand Cc: Alexander Gordeev Cc: Andreas Larsson Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christophe Leroy Cc: Dave Hansen Cc: Davidlohr Bueso Cc: David S. Miller Cc: Greg Kroah-Hartman Cc: Heiko Carstens Cc: Huacai Chen Cc: Ingo Molnar Cc: Jiaxun Yang Cc: John Paul Adrian Glaubitz Cc: Jonathan Corbet Cc: Michael Ellerman Cc: Palmer Dabbelt Cc: Rafael J. Wysocki Cc: Rob Herring (Arm) Cc: Samuel Holland Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/numa_memblks.h | 8 -------- mm/numa_memblks.c | 36 ++++++++++++++++++------------------ 2 files changed, 18 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/numa_memblks.h b/include/linux/numa_memblks.h index 07381320848f..5c6e12ad0b7a 100644 --- a/include/linux/numa_memblks.h +++ b/include/linux/numa_memblks.h @@ -7,7 +7,6 @@ #define NR_NODE_MEMBLKS (MAX_NUMNODES * 2) -extern int numa_distance_cnt; void __init numa_set_distance(int from, int to, int distance); void __init numa_reset_distance(void); @@ -22,17 +21,10 @@ struct numa_meminfo { struct numa_memblk blk[NR_NODE_MEMBLKS]; }; -extern struct numa_meminfo numa_meminfo __initdata_or_meminfo; -extern struct numa_meminfo numa_reserved_meminfo __initdata_or_meminfo; - int __init numa_add_memblk(int nodeid, u64 start, u64 end); void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi); int __init numa_cleanup_meminfo(struct numa_meminfo *mi); -int __init numa_register_meminfo(struct numa_meminfo *mi); - -void __init numa_nodemask_from_meminfo(nodemask_t *nodemask, - const struct numa_meminfo *mi); int __init numa_memblks_init(int (*init_func)(void), bool memblock_force_top_down); diff --git a/mm/numa_memblks.c b/mm/numa_memblks.c index 7749b6f6b250..e97665a5e8ce 100644 --- a/mm/numa_memblks.c +++ b/mm/numa_memblks.c @@ -7,13 +7,27 @@ #include #include -int numa_distance_cnt; +static int numa_distance_cnt; static u8 *numa_distance; nodemask_t numa_nodes_parsed __initdata; -struct numa_meminfo numa_meminfo __initdata_or_meminfo; -struct numa_meminfo numa_reserved_meminfo __initdata_or_meminfo; +static struct numa_meminfo numa_meminfo __initdata_or_meminfo; +static struct numa_meminfo numa_reserved_meminfo __initdata_or_meminfo; + +/* + * Set nodes, which have memory in @mi, in *@nodemask. + */ +static void __init numa_nodemask_from_meminfo(nodemask_t *nodemask, + const struct numa_meminfo *mi) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(mi->blk); i++) + if (mi->blk[i].start != mi->blk[i].end && + mi->blk[i].nid != NUMA_NO_NODE) + node_set(mi->blk[i].nid, *nodemask); +} /** * numa_reset_distance - Reset NUMA distance table @@ -290,20 +304,6 @@ int __init numa_cleanup_meminfo(struct numa_meminfo *mi) return 0; } -/* - * Set nodes, which have memory in @mi, in *@nodemask. - */ -void __init numa_nodemask_from_meminfo(nodemask_t *nodemask, - const struct numa_meminfo *mi) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(mi->blk); i++) - if (mi->blk[i].start != mi->blk[i].end && - mi->blk[i].nid != NUMA_NO_NODE) - node_set(mi->blk[i].nid, *nodemask); -} - /* * Mark all currently memblock-reserved physical memory (which covers the * kernel's own memory ranges) as hot-unswappable. @@ -371,7 +371,7 @@ static void __init numa_clear_kernel_node_hotplug(void) } } -int __init numa_register_meminfo(struct numa_meminfo *mi) +static int __init numa_register_meminfo(struct numa_meminfo *mi) { int i; -- cgit v1.2.3 From 1b5695b02444660297cc54cab44f123ff28de2cc Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Wed, 7 Aug 2024 09:41:09 +0300 Subject: mm: make range-to-target_node lookup facility a part of numa_memblks The x86 implementation of range-to-target_node lookup (i.e. phys_to_target_node() and memory_add_physaddr_to_nid()) relies on numa_memblks. Since numa_memblks are now part of the generic code, move these functions from x86 to mm/numa_memblks.c and select CONFIG_NUMA_KEEP_MEMINFO when CONFIG_NUMA_MEMBLKS=y for dax and cxl. [rppt@kernel.org: fix build] Link: https://lkml.kernel.org/r/ZtVfSt_zloPdDqVB@kernel.org Link: https://lkml.kernel.org/r/20240807064110.1003856-26-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) Reviewed-by: Jonathan Cameron Tested-by: Zi Yan # for x86_64 and arm64 Tested-by: Jonathan Cameron [arm64 + CXL via QEMU] Reviewed-by: Dan Williams Acked-by: David Hildenbrand Cc: Alexander Gordeev Cc: Andreas Larsson Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christophe Leroy Cc: Dave Hansen Cc: Davidlohr Bueso Cc: David S. Miller Cc: Greg Kroah-Hartman Cc: Heiko Carstens Cc: Huacai Chen Cc: Ingo Molnar Cc: Jiaxun Yang Cc: John Paul Adrian Glaubitz Cc: Jonathan Corbet Cc: Michael Ellerman Cc: Palmer Dabbelt Cc: Rafael J. Wysocki Cc: Rob Herring (Arm) Cc: Samuel Holland Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/x86/include/asm/sparsemem.h | 9 --------- arch/x86/mm/numa.c | 38 -------------------------------------- drivers/cxl/Kconfig | 2 +- drivers/dax/Kconfig | 2 +- include/linux/numa_memblks.h | 7 +++++++ mm/numa.c | 1 + mm/numa_memblks.c | 38 ++++++++++++++++++++++++++++++++++++++ 7 files changed, 48 insertions(+), 49 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h index 64df897c0ee3..3918c7a434f5 100644 --- a/arch/x86/include/asm/sparsemem.h +++ b/arch/x86/include/asm/sparsemem.h @@ -31,13 +31,4 @@ #endif /* CONFIG_SPARSEMEM */ -#ifndef __ASSEMBLY__ -#ifdef CONFIG_NUMA_KEEP_MEMINFO -extern int phys_to_target_node(phys_addr_t start); -#define phys_to_target_node phys_to_target_node -extern int memory_add_physaddr_to_nid(u64 start); -#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid -#endif -#endif /* __ASSEMBLY__ */ - #endif /* _ASM_X86_SPARSEMEM_H */ diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index d23287611449..64e5cdb2460a 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -453,41 +453,3 @@ u64 __init numa_emu_dma_end(void) return PFN_PHYS(MAX_DMA32_PFN); } #endif /* CONFIG_NUMA_EMU */ - -#ifdef CONFIG_NUMA_KEEP_MEMINFO -static int meminfo_to_nid(struct numa_meminfo *mi, u64 start) -{ - int i; - - for (i = 0; i < mi->nr_blks; i++) - if (mi->blk[i].start <= start && mi->blk[i].end > start) - return mi->blk[i].nid; - return NUMA_NO_NODE; -} - -int phys_to_target_node(phys_addr_t start) -{ - int nid = meminfo_to_nid(&numa_meminfo, start); - - /* - * Prefer online nodes, but if reserved memory might be - * hot-added continue the search with reserved ranges. - */ - if (nid != NUMA_NO_NODE) - return nid; - - return meminfo_to_nid(&numa_reserved_meminfo, start); -} -EXPORT_SYMBOL_GPL(phys_to_target_node); - -int memory_add_physaddr_to_nid(u64 start) -{ - int nid = meminfo_to_nid(&numa_meminfo, start); - - if (nid == NUMA_NO_NODE) - nid = numa_meminfo.blk[0].nid; - return nid; -} -EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); - -#endif diff --git a/drivers/cxl/Kconfig b/drivers/cxl/Kconfig index 99b5c25be079..29c192f20082 100644 --- a/drivers/cxl/Kconfig +++ b/drivers/cxl/Kconfig @@ -6,7 +6,7 @@ menuconfig CXL_BUS select FW_UPLOAD select PCI_DOE select FIRMWARE_TABLE - select NUMA_KEEP_MEMINFO if (NUMA && X86) + select NUMA_KEEP_MEMINFO if NUMA_MEMBLKS help CXL is a bus that is electrically compatible with PCI Express, but layers three protocols on that signalling (CXL.io, CXL.cache, and diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig index a88744244149..d656e4c0eb84 100644 --- a/drivers/dax/Kconfig +++ b/drivers/dax/Kconfig @@ -30,7 +30,7 @@ config DEV_DAX_PMEM config DEV_DAX_HMEM tristate "HMEM DAX: direct access to 'specific purpose' memory" depends on EFI_SOFT_RESERVE - select NUMA_KEEP_MEMINFO if (NUMA && X86) + select NUMA_KEEP_MEMINFO if NUMA_MEMBLKS default DEV_DAX help EFI 2.8 platforms, and others, may advertise 'specific purpose' diff --git a/include/linux/numa_memblks.h b/include/linux/numa_memblks.h index 5c6e12ad0b7a..cfad6ce7e1bd 100644 --- a/include/linux/numa_memblks.h +++ b/include/linux/numa_memblks.h @@ -46,6 +46,13 @@ static inline int numa_emu_cmdline(char *str) } #endif /* CONFIG_NUMA_EMU */ +#ifdef CONFIG_NUMA_KEEP_MEMINFO +extern int phys_to_target_node(u64 start); +#define phys_to_target_node phys_to_target_node +extern int memory_add_physaddr_to_nid(u64 start); +#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid +#endif /* CONFIG_NUMA_KEEP_MEMINFO */ + #endif /* CONFIG_NUMA_MEMBLKS */ #endif /* __NUMA_MEMBLKS_H */ diff --git a/mm/numa.c b/mm/numa.c index 1f1582dcdf4a..e2eec07707d1 100644 --- a/mm/numa.c +++ b/mm/numa.c @@ -3,6 +3,7 @@ #include #include #include +#include struct pglist_data *node_data[MAX_NUMNODES]; EXPORT_SYMBOL(node_data); diff --git a/mm/numa_memblks.c b/mm/numa_memblks.c index c4037faa438b..be52b93a9c58 100644 --- a/mm/numa_memblks.c +++ b/mm/numa_memblks.c @@ -531,3 +531,41 @@ int __init numa_fill_memblks(u64 start, u64 end) } return 0; } + +#ifdef CONFIG_NUMA_KEEP_MEMINFO +static int meminfo_to_nid(struct numa_meminfo *mi, u64 start) +{ + int i; + + for (i = 0; i < mi->nr_blks; i++) + if (mi->blk[i].start <= start && mi->blk[i].end > start) + return mi->blk[i].nid; + return NUMA_NO_NODE; +} + +int phys_to_target_node(u64 start) +{ + int nid = meminfo_to_nid(&numa_meminfo, start); + + /* + * Prefer online nodes, but if reserved memory might be + * hot-added continue the search with reserved ranges. + */ + if (nid != NUMA_NO_NODE) + return nid; + + return meminfo_to_nid(&numa_reserved_meminfo, start); +} +EXPORT_SYMBOL_GPL(phys_to_target_node); + +int memory_add_physaddr_to_nid(u64 start) +{ + int nid = meminfo_to_nid(&numa_meminfo, start); + + if (nid == NUMA_NO_NODE) + nid = numa_meminfo.blk[0].nid; + return nid; +} +EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); + +#endif /* CONFIG_NUMA_KEEP_MEMINFO */ -- cgit v1.2.3 From 650180760be6bb448609d4d155eef3b728ace641 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Mon, 12 Aug 2024 15:42:02 +0800 Subject: mm: swap: extend swap_shmem_alloc() to support batch SWAP_MAP_SHMEM flag setting Patch series "support large folio swap-out and swap-in for shmem", v5. Shmem will support large folio allocation [1] [2] to get a better performance, however, the memory reclaim still splits the precious large folios when trying to swap-out shmem, which may lead to the memory fragmentation issue and can not take advantage of the large folio for shmeme. Moreover, the swap code already supports for swapping out large folio without split, and large folio swap-in[3] series is queued into mm-unstable branch. Hence this patch set also supports the large folio swap-out and swap-in for shmem. This patch (of 9): To support shmem large folio swap operations, add a new parameter to swap_shmem_alloc() that allows batch SWAP_MAP_SHMEM flag setting for shmem swap entries. While we are at it, using folio_nr_pages() to get the number of pages of the folio as a preparation. Link: https://lkml.kernel.org/r/cover.1723434324.git.baolin.wang@linux.alibaba.com Link: https://lkml.kernel.org/r/99f64115d04b285e009580eb177352c57119ffd0.1723434324.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Reviewed-by: Barry Song Cc: Chris Li Cc: Daniel Gomez Cc: David Hildenbrand Cc: "Huang, Ying" Cc: Hugh Dickins Cc: Kefeng Wang Cc: Lance Yang Cc: Matthew Wilcox Cc: Pankaj Raghav Cc: Ryan Roberts Cc: Yang Shi Cc: Zi Yan Signed-off-by: Andrew Morton --- include/linux/swap.h | 4 ++-- mm/shmem.c | 6 ++++-- mm/swapfile.c | 4 ++-- 3 files changed, 8 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 1c8f844a9f0f..248db1dd7812 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -481,7 +481,7 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry); extern swp_entry_t get_swap_page_of_type(int); extern int get_swap_pages(int n, swp_entry_t swp_entries[], int order); extern int add_swap_count_continuation(swp_entry_t, gfp_t); -extern void swap_shmem_alloc(swp_entry_t); +extern void swap_shmem_alloc(swp_entry_t, int); extern int swap_duplicate(swp_entry_t); extern int swapcache_prepare(swp_entry_t entry, int nr); extern void swap_free_nr(swp_entry_t entry, int nr_pages); @@ -548,7 +548,7 @@ static inline int add_swap_count_continuation(swp_entry_t swp, gfp_t gfp_mask) return 0; } -static inline void swap_shmem_alloc(swp_entry_t swp) +static inline void swap_shmem_alloc(swp_entry_t swp, int nr) { } diff --git a/mm/shmem.c b/mm/shmem.c index 4a5254bfd610..22cdc10f27ea 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1452,6 +1452,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); swp_entry_t swap; pgoff_t index; + int nr_pages; /* * Our capabilities prevent regular writeback or sync from ever calling @@ -1484,6 +1485,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) } index = folio->index; + nr_pages = folio_nr_pages(folio); /* * This is somewhat ridiculous, but without plumbing a SWAP_MAP_FALLOC @@ -1536,8 +1538,8 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) if (add_to_swap_cache(folio, swap, __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN, NULL) == 0) { - shmem_recalc_inode(inode, 0, 1); - swap_shmem_alloc(swap); + shmem_recalc_inode(inode, 0, nr_pages); + swap_shmem_alloc(swap, nr_pages); shmem_delete_from_page_cache(folio, swp_to_radix_entry(swap)); mutex_unlock(&shmem_swaplist_mutex); diff --git a/mm/swapfile.c b/mm/swapfile.c index 5e7cbdaf725d..8ff58be40544 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -3657,9 +3657,9 @@ unlock_out: * Help swapoff by noting that swap entry belongs to shmem/tmpfs * (in which case its reference count is never incremented). */ -void swap_shmem_alloc(swp_entry_t entry) +void swap_shmem_alloc(swp_entry_t entry, int nr) { - __swap_duplicate(entry, SWAP_MAP_SHMEM, 1); + __swap_duplicate(entry, SWAP_MAP_SHMEM, nr); } /* -- cgit v1.2.3 From 809bc86517cc408b5b8cb8e08e69096639432bc8 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Mon, 12 Aug 2024 15:42:10 +0800 Subject: mm: shmem: support large folio swap out Shmem will support large folio allocation [1] [2] to get a better performance, however, the memory reclaim still splits the precious large folios when trying to swap out shmem, which may lead to the memory fragmentation issue and can not take advantage of the large folio for shmeme. Moreover, the swap code already supports for swapping out large folio without split, hence this patch set supports the large folio swap out for shmem. Note the i915_gem_shmem driver still need to be split when swapping, thus add a new flag 'split_large_folio' for writeback_control to indicate spliting the large folio. [1] https://lore.kernel.org/all/cover.1717495894.git.baolin.wang@linux.alibaba.com/ [2] https://lore.kernel.org/all/20240515055719.32577-1-da.gomez@samsung.com/ [hughd@google.com: shmem_writepage() split folio at EOF before swapout] Link: https://lkml.kernel.org/r/aef55f8d-6040-692d-65e3-16150cce4440@google.com [baolin.wang@linux.alibaba.com: remove the wbc->split_large_folio per Hugh] Link: https://lkml.kernel.org/r/1236a002daa301b3b9ba73d6c0fab348427cf295.1724833399.git.baolin.wang@linux.alibaba.com Link: https://lkml.kernel.org/r/d80c21abd20e1b0f5ca66b330f074060fb2f082d.1723434324.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Signed-off-by: Hugh Dickins Cc: Barry Song Cc: Chris Li Cc: David Hildenbrand Cc: "Huang, Ying" Cc: Kefeng Wang Cc: Lance Yang Cc: Matthew Wilcox Cc: Pankaj Raghav Cc: Ryan Roberts Cc: Yang Shi Cc: Zi Yan Signed-off-by: Andrew Morton --- include/linux/writeback.h | 3 +++ mm/shmem.c | 28 ++++++++++++++++++++++------ mm/vmscan.c | 30 +++++++++++++++++++++++------- 3 files changed, 48 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 1a54676d843a..51278327b3c6 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -79,6 +79,9 @@ struct writeback_control { */ struct swap_iocb **swap_plug; + /* Target list for splitting a large folio */ + struct list_head *list; + /* internal fields used by the ->writepages implementation: */ struct folio_batch fbatch; pgoff_t index; diff --git a/mm/shmem.c b/mm/shmem.c index 4af6f3ea9c4f..1448a7a9a282 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -795,7 +795,6 @@ static int shmem_add_to_page_cache(struct folio *folio, VM_BUG_ON_FOLIO(index != round_down(index, nr), folio); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(!folio_test_swapbacked(folio), folio); - VM_BUG_ON(expected && folio_test_large(folio)); folio_ref_add(folio, nr); folio->mapping = mapping; @@ -1460,6 +1459,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) swp_entry_t swap; pgoff_t index; int nr_pages; + bool split = false; /* * Our capabilities prevent regular writeback or sync from ever calling @@ -1478,14 +1478,26 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) goto redirty; /* - * If /sys/kernel/mm/transparent_hugepage/shmem_enabled is "always" or - * "force", drivers/gpu/drm/i915/gem/i915_gem_shmem.c gets huge pages, - * and its shmem_writeback() needs them to be split when swapping. + * If CONFIG_THP_SWAP is not enabled, the large folio should be + * split when swapping. + * + * And shrinkage of pages beyond i_size does not split swap, so + * swapout of a large folio crossing i_size needs to split too + * (unless fallocate has been used to preallocate beyond EOF). */ if (folio_test_large(folio)) { + index = shmem_fallocend(inode, + DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE)); + if ((index > folio->index && index < folio_next_index(folio)) || + !IS_ENABLED(CONFIG_THP_SWAP)) + split = true; + } + + if (split) { +try_split: /* Ensure the subpages are still dirty */ folio_test_set_dirty(folio); - if (split_huge_page(page) < 0) + if (split_huge_page_to_list_to_order(page, wbc->list, 0)) goto redirty; folio = page_folio(page); folio_clear_dirty(folio); @@ -1527,8 +1539,12 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) } swap = folio_alloc_swap(folio); - if (!swap.val) + if (!swap.val) { + if (nr_pages > 1) + goto try_split; + goto redirty; + } /* * Add inode to shmem_unuse()'s list of swapped-out inodes, diff --git a/mm/vmscan.c b/mm/vmscan.c index 243b62b9f89d..1b6542aaf81e 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -628,7 +628,7 @@ typedef enum { * Calls ->writepage(). */ static pageout_t pageout(struct folio *folio, struct address_space *mapping, - struct swap_iocb **plug) + struct swap_iocb **plug, struct list_head *folio_list) { /* * If the folio is dirty, only perform writeback if that write @@ -676,6 +676,14 @@ static pageout_t pageout(struct folio *folio, struct address_space *mapping, .swap_plug = plug, }; + /* + * The large shmem folio can be split if CONFIG_THP_SWAP is + * not enabled or contiguous swap entries are failed to + * allocate. + */ + if (shmem_mapping(mapping) && folio_test_large(folio)) + wbc.list = folio_list; + folio_set_reclaim(folio); res = mapping->a_ops->writepage(&folio->page, &wbc); if (res < 0) @@ -1257,11 +1265,6 @@ retry: goto activate_locked_split; } } - } else if (folio_test_swapbacked(folio) && - folio_test_large(folio)) { - /* Split shmem folio */ - if (split_folio_to_list(folio, folio_list)) - goto keep_locked; } /* @@ -1362,12 +1365,25 @@ retry: * starts and then write it out here. */ try_to_unmap_flush_dirty(); - switch (pageout(folio, mapping, &plug)) { + switch (pageout(folio, mapping, &plug, folio_list)) { case PAGE_KEEP: goto keep_locked; case PAGE_ACTIVATE: + /* + * If shmem folio is split when writeback to swap, + * the tail pages will make their own pass through + * this function and be accounted then. + */ + if (nr_pages > 1 && !folio_test_large(folio)) { + sc->nr_scanned -= (nr_pages - 1); + nr_pages = 1; + } goto activate_locked; case PAGE_SUCCESS: + if (nr_pages > 1 && !folio_test_large(folio)) { + sc->nr_scanned -= (nr_pages - 1); + nr_pages = 1; + } stat->nr_pageout += nr_pages; if (folio_test_writeback(folio)) -- cgit v1.2.3 From f77f0c7514789577125c1b2df145703161736359 Mon Sep 17 00:00:00 2001 From: Kaiyang Zhao Date: Wed, 14 Aug 2024 17:42:27 +0000 Subject: mm,memcg: provide per-cgroup counters for NUMA balancing operations The ability to observe the demotion and promotion decisions made by the kernel on a per-cgroup basis is important for monitoring and tuning containerized workloads on machines equipped with tiered memory. Different containers in the system may experience drastically different memory tiering actions that cannot be distinguished from the global counters alone. For example, a container running a workload that has a much hotter memory accesses will likely see more promotions and fewer demotions, potentially depriving a colocated container of top tier memory to such an extent that its performance degrades unacceptably. For another example, some containers may exhibit longer periods between data reuse, causing much more numa_hint_faults than numa_pages_migrated. In this case, tuning hot_threshold_ms may be appropriate, but the signal can easily be lost if only global counters are available. In the long term, we hope to introduce per-cgroup control of promotion and demotion actions to implement memory placement policies in tiering. This patch set adds seven counters to memory.stat in a cgroup: numa_pages_migrated, numa_pte_updates, numa_hint_faults, pgdemote_kswapd, pgdemote_khugepaged, pgdemote_direct and pgpromote_success. pgdemote_* and pgpromote_success are also available in memory.numa_stat. count_memcg_events_mm() is added to count multiple event occurrences at once, and get_mem_cgroup_from_folio() is added because we need to get a reference to the memcg of a folio before it's migrated to track numa_pages_migrated. The accounting of PGDEMOTE_* is moved to shrink_inactive_list() before being changed to per-cgroup. [kaiyang2@cs.cmu.edu: add documentation of the memcg counters in cgroup-v2.rst] Link: https://lkml.kernel.org/r/20240814235122.252309-1-kaiyang2@cs.cmu.edu Link: https://lkml.kernel.org/r/20240814174227.30639-1-kaiyang2@cs.cmu.edu Signed-off-by: Kaiyang Zhao Cc: David Rientjes Cc: Johannes Weiner Cc: Michal Hocko Cc: Muchun Song Cc: Roman Gushchin Cc: Shakeel Butt Cc: Wei Xu Signed-off-by: Andrew Morton --- Documentation/admin-guide/cgroup-v2.rst | 19 ++++++++++++++ include/linux/memcontrol.h | 24 +++++++++++++++--- include/linux/vmstat.h | 1 + mm/memcontrol.c | 45 +++++++++++++++++++++++++++++++++ mm/memory.c | 3 +++ mm/mempolicy.c | 4 ++- mm/migrate.c | 7 +++-- mm/vmscan.c | 8 +++--- 8 files changed, 101 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index f0499884124d..d3344218010c 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1617,6 +1617,25 @@ The following nested keys are defined. Usually because failed to allocate some continuous swap space for the huge page. + numa_pages_migrated (npn) + Number of pages migrated by NUMA balancing. + + numa_pte_updates (npn) + Number of pages whose page table entries are modified by + NUMA balancing to produce NUMA hinting faults on access. + + numa_hint_faults (npn) + Number of NUMA hinting faults. + + pgdemote_kswapd + Number of pages demoted by kswapd. + + pgdemote_direct + Number of pages demoted directly. + + pgdemote_khugepaged + Number of pages demoted by khugepaged. + memory.numa_stat A read-only nested-keyed file which exists on non-root cgroups. diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index ed170399179a..fe05fdb92779 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -784,6 +784,8 @@ struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm); struct mem_cgroup *get_mem_cgroup_from_current(void); +struct mem_cgroup *get_mem_cgroup_from_folio(struct folio *folio); + struct lruvec *folio_lruvec_lock(struct folio *folio); struct lruvec *folio_lruvec_lock_irq(struct folio *folio); struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio, @@ -1028,8 +1030,8 @@ static inline void count_memcg_folio_events(struct folio *folio, count_memcg_events(memcg, idx, nr); } -static inline void count_memcg_event_mm(struct mm_struct *mm, - enum vm_event_item idx) +static inline void count_memcg_events_mm(struct mm_struct *mm, + enum vm_event_item idx, unsigned long count) { struct mem_cgroup *memcg; @@ -1039,10 +1041,16 @@ static inline void count_memcg_event_mm(struct mm_struct *mm, rcu_read_lock(); memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (likely(memcg)) - count_memcg_events(memcg, idx, 1); + count_memcg_events(memcg, idx, count); rcu_read_unlock(); } +static inline void count_memcg_event_mm(struct mm_struct *mm, + enum vm_event_item idx) +{ + count_memcg_events_mm(mm, idx, 1); +} + static inline void memcg_memory_event(struct mem_cgroup *memcg, enum memcg_memory_event event) { @@ -1262,6 +1270,11 @@ static inline struct mem_cgroup *get_mem_cgroup_from_current(void) return NULL; } +static inline struct mem_cgroup *get_mem_cgroup_from_folio(struct folio *folio) +{ + return NULL; +} + static inline struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css) { @@ -1484,6 +1497,11 @@ static inline void count_memcg_folio_events(struct folio *folio, { } +static inline void count_memcg_events_mm(struct mm_struct *mm, + enum vm_event_item idx, unsigned long count) +{ +} + static inline void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 9eb77c9007e6..d2761bf8ff32 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -32,6 +32,7 @@ struct reclaim_stat { unsigned nr_ref_keep; unsigned nr_unmap_fail; unsigned nr_lazyfree_fail; + unsigned nr_demoted; }; /* Stat data for system wide items */ diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 1decbd38216e..0370ce03ce4c 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -304,6 +304,12 @@ static const unsigned int memcg_node_stat_items[] = { #ifdef CONFIG_SWAP NR_SWAPCACHE, #endif +#ifdef CONFIG_NUMA_BALANCING + PGPROMOTE_SUCCESS, +#endif + PGDEMOTE_KSWAPD, + PGDEMOTE_DIRECT, + PGDEMOTE_KHUGEPAGED, }; static const unsigned int memcg_stat_items[] = { @@ -436,6 +442,11 @@ static const unsigned int memcg_vm_event_stat[] = { THP_SWPOUT, THP_SWPOUT_FALLBACK, #endif +#ifdef CONFIG_NUMA_BALANCING + NUMA_PAGE_MIGRATE, + NUMA_PTE_UPDATES, + NUMA_HINT_FAULTS, +#endif }; #define NR_MEMCG_EVENTS ARRAY_SIZE(memcg_vm_event_stat) @@ -935,6 +946,24 @@ again: return memcg; } +/** + * get_mem_cgroup_from_folio - Obtain a reference on a given folio's memcg. + * @folio: folio from which memcg should be extracted. + */ +struct mem_cgroup *get_mem_cgroup_from_folio(struct folio *folio) +{ + struct mem_cgroup *memcg = folio_memcg(folio); + + if (mem_cgroup_disabled()) + return NULL; + + rcu_read_lock(); + if (!memcg || WARN_ON_ONCE(!css_tryget(&memcg->css))) + memcg = root_mem_cgroup; + rcu_read_unlock(); + return memcg; +} + /** * mem_cgroup_iter - iterate over memory cgroup hierarchy * @root: hierarchy root @@ -1340,6 +1369,13 @@ static const struct memory_stat memory_stats[] = { { "workingset_restore_anon", WORKINGSET_RESTORE_ANON }, { "workingset_restore_file", WORKINGSET_RESTORE_FILE }, { "workingset_nodereclaim", WORKINGSET_NODERECLAIM }, + + { "pgdemote_kswapd", PGDEMOTE_KSWAPD }, + { "pgdemote_direct", PGDEMOTE_DIRECT }, + { "pgdemote_khugepaged", PGDEMOTE_KHUGEPAGED }, +#ifdef CONFIG_NUMA_BALANCING + { "pgpromote_success", PGPROMOTE_SUCCESS }, +#endif }; /* The actual unit of the state item, not the same as the output unit */ @@ -1364,6 +1400,9 @@ static int memcg_page_state_output_unit(int item) /* * Workingset state is actually in pages, but we export it to userspace * as a scalar count of events, so special case it here. + * + * Demotion and promotion activities are exported in pages, consistent + * with their global counterparts. */ switch (item) { case WORKINGSET_REFAULT_ANON: @@ -1373,6 +1412,12 @@ static int memcg_page_state_output_unit(int item) case WORKINGSET_RESTORE_ANON: case WORKINGSET_RESTORE_FILE: case WORKINGSET_NODERECLAIM: + case PGDEMOTE_KSWAPD: + case PGDEMOTE_DIRECT: + case PGDEMOTE_KHUGEPAGED: +#ifdef CONFIG_NUMA_BALANCING + case PGPROMOTE_SUCCESS: +#endif return 1; default: return memcg_page_state_unit(item); diff --git a/mm/memory.c b/mm/memory.c index d1c741a39630..c31ea300cdf6 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -5236,6 +5236,9 @@ int numa_migrate_check(struct folio *folio, struct vm_fault *vmf, vma_set_access_pid_bit(vma); count_vm_numa_event(NUMA_HINT_FAULTS); +#ifdef CONFIG_NUMA_BALANCING + count_memcg_folio_events(folio, NUMA_HINT_FAULTS, 1); +#endif if (folio_nid(folio) == numa_node_id()) { count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL); *flags |= TNF_FAULT_LOCAL; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index b3b5f376471f..b646fab3e45e 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -676,8 +676,10 @@ unsigned long change_prot_numa(struct vm_area_struct *vma, tlb_gather_mmu(&tlb, vma->vm_mm); nr_updated = change_protection(&tlb, vma, addr, end, MM_CP_PROT_NUMA); - if (nr_updated > 0) + if (nr_updated > 0) { count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated); + count_memcg_events_mm(vma->vm_mm, NUMA_PTE_UPDATES, nr_updated); + } tlb_finish_mmu(&tlb); diff --git a/mm/migrate.c b/mm/migrate.c index 66a5f73ebfdf..76cfc6c42eb3 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2614,6 +2614,8 @@ int migrate_misplaced_folio(struct folio *folio, struct vm_area_struct *vma, int nr_remaining; unsigned int nr_succeeded; LIST_HEAD(migratepages); + struct mem_cgroup *memcg = get_mem_cgroup_from_folio(folio); + struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); list_add(&folio->lru, &migratepages); nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_folio, @@ -2623,12 +2625,13 @@ int migrate_misplaced_folio(struct folio *folio, struct vm_area_struct *vma, putback_movable_pages(&migratepages); if (nr_succeeded) { count_vm_numa_events(NUMA_PAGE_MIGRATE, nr_succeeded); + count_memcg_events(memcg, NUMA_PAGE_MIGRATE, nr_succeeded); if ((sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) && !node_is_toptier(folio_nid(folio)) && node_is_toptier(node)) - mod_node_page_state(pgdat, PGPROMOTE_SUCCESS, - nr_succeeded); + mod_lruvec_state(lruvec, PGPROMOTE_SUCCESS, nr_succeeded); } + mem_cgroup_put(memcg); BUG_ON(!list_empty(&migratepages)); return nr_remaining ? -EAGAIN : 0; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 1b6542aaf81e..1b1fad0c1e11 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1016,9 +1016,6 @@ static unsigned int demote_folio_list(struct list_head *demote_folios, (unsigned long)&mtc, MIGRATE_ASYNC, MR_DEMOTION, &nr_succeeded); - mod_node_page_state(pgdat, PGDEMOTE_KSWAPD + reclaimer_offset(), - nr_succeeded); - return nr_succeeded; } @@ -1516,7 +1513,8 @@ keep: /* 'folio_list' is always empty here */ /* Migrate folios selected for demotion */ - nr_reclaimed += demote_folio_list(&demote_folios, pgdat); + stat->nr_demoted = demote_folio_list(&demote_folios, pgdat); + nr_reclaimed += stat->nr_demoted; /* Folios that could not be demoted are still in @demote_folios */ if (!list_empty(&demote_folios)) { /* Folios which weren't demoted go back on @folio_list */ @@ -1982,6 +1980,8 @@ static unsigned long shrink_inactive_list(unsigned long nr_to_scan, spin_lock_irq(&lruvec->lru_lock); move_folios_to_lru(lruvec, &folio_list); + __mod_lruvec_state(lruvec, PGDEMOTE_KSWAPD + reclaimer_offset(), + stat.nr_demoted); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); item = PGSTEAL_KSWAPD + reclaimer_offset(); if (!cgroup_reclaim(sc)) -- cgit v1.2.3 From e98337d11bbdfa3e3f0fb99aa93e40f97549e0cd Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Tue, 13 Aug 2024 21:54:49 -0600 Subject: mm/contig_alloc: support __GFP_COMP Patch series "mm/hugetlb: alloc/free gigantic folios", v2. Use __GFP_COMP for gigantic folios can greatly reduce not only the amount of code but also the allocation and free time. Approximate LOC to mm/hugetlb.c: +60, -240 Allocate and free 500 1GB hugeTLB memory without HVO by: time echo 500 >/sys/kernel/mm/hugepages/hugepages-1048576kB/nr_hugepages time echo 0 >/sys/kernel/mm/hugepages/hugepages-1048576kB/nr_hugepages Before After Alloc ~13s ~10s Free ~15s <1s The above magnitude generally holds for multiple x86 and arm64 CPU models. Perf profile before: Alloc - 99.99% alloc_pool_huge_folio - __alloc_fresh_hugetlb_folio - 83.23% alloc_contig_pages_noprof - 47.46% alloc_contig_range_noprof - 20.96% isolate_freepages_range 16.10% split_page - 14.10% start_isolate_page_range - 12.02% undo_isolate_page_range Free - update_and_free_pages_bulk - 87.71% free_contig_range - 76.02% free_unref_page - 41.30% free_unref_page_commit - 32.58% free_pcppages_bulk - 24.75% __free_one_page 13.96% _raw_spin_trylock 12.27% __update_and_free_hugetlb_folio Perf profile after: Alloc - 99.99% alloc_pool_huge_folio alloc_gigantic_folio - alloc_contig_pages_noprof - 59.15% alloc_contig_range_noprof - 20.72% start_isolate_page_range 20.64% prep_new_page - 17.13% undo_isolate_page_range Free - update_and_free_pages_bulk - __folio_put - __free_pages_ok 7.46% free_tail_page_prepare - 1.97% free_one_page 1.86% __free_one_page This patch (of 3): Support __GFP_COMP in alloc_contig_range(). When the flag is set, upon success the function returns a large folio prepared by prep_new_page(), rather than a range of order-0 pages prepared by split_free_pages() (which is renamed from split_map_pages()). alloc_contig_range() can be used to allocate folios larger than MAX_PAGE_ORDER, e.g., gigantic hugeTLB folios. So on the free path, free_one_page() needs to handle that by split_large_buddy(). [akpm@linux-foundation.org: fix folio_alloc_gigantic_noprof() WARN expression, per Yu Liao] Link: https://lkml.kernel.org/r/20240814035451.773331-1-yuzhao@google.com Link: https://lkml.kernel.org/r/20240814035451.773331-2-yuzhao@google.com Signed-off-by: Yu Zhao Acked-by: Zi Yan Cc: Matthew Wilcox (Oracle) Cc: Muchun Song Cc: Frank van der Linden Signed-off-by: Andrew Morton --- include/linux/gfp.h | 23 +++++++++++ mm/compaction.c | 41 +++---------------- mm/page_alloc.c | 111 +++++++++++++++++++++++++++++++++++++--------------- 3 files changed, 108 insertions(+), 67 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index f53f76e0b17e..03ba9563c6db 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -446,4 +446,27 @@ extern struct page *alloc_contig_pages_noprof(unsigned long nr_pages, gfp_t gfp_ #endif void free_contig_range(unsigned long pfn, unsigned long nr_pages); +#ifdef CONFIG_CONTIG_ALLOC +static inline struct folio *folio_alloc_gigantic_noprof(int order, gfp_t gfp, + int nid, nodemask_t *node) +{ + struct page *page; + + if (WARN_ON(!order || !(gfp & __GFP_COMP))) + return NULL; + + page = alloc_contig_pages_noprof(1 << order, gfp, nid, node); + + return page ? page_folio(page) : NULL; +} +#else +static inline struct folio *folio_alloc_gigantic_noprof(int order, gfp_t gfp, + int nid, nodemask_t *node) +{ + return NULL; +} +#endif +/* This should be paired with folio_put() rather than free_contig_range(). */ +#define folio_alloc_gigantic(...) alloc_hooks(folio_alloc_gigantic_noprof(__VA_ARGS__)) + #endif /* __LINUX_GFP_H */ diff --git a/mm/compaction.c b/mm/compaction.c index eb95e9b435d0..d1041fbce679 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -86,33 +86,6 @@ static struct page *mark_allocated_noprof(struct page *page, unsigned int order, } #define mark_allocated(...) alloc_hooks(mark_allocated_noprof(__VA_ARGS__)) -static void split_map_pages(struct list_head *freepages) -{ - unsigned int i, order; - struct page *page, *next; - LIST_HEAD(tmp_list); - - for (order = 0; order < NR_PAGE_ORDERS; order++) { - list_for_each_entry_safe(page, next, &freepages[order], lru) { - unsigned int nr_pages; - - list_del(&page->lru); - - nr_pages = 1 << order; - - mark_allocated(page, order, __GFP_MOVABLE); - if (order) - split_page(page, order); - - for (i = 0; i < nr_pages; i++) { - list_add(&page->lru, &tmp_list); - page++; - } - } - list_splice_init(&tmp_list, &freepages[0]); - } -} - static unsigned long release_free_list(struct list_head *freepages) { int order; @@ -742,11 +715,11 @@ isolate_fail: * * Non-free pages, invalid PFNs, or zone boundaries within the * [start_pfn, end_pfn) range are considered errors, cause function to - * undo its actions and return zero. + * undo its actions and return zero. cc->freepages[] are empty. * * Otherwise, function returns one-past-the-last PFN of isolated page * (which may be greater then end_pfn if end fell in a middle of - * a free page). + * a free page). cc->freepages[] contain free pages isolated. */ unsigned long isolate_freepages_range(struct compact_control *cc, @@ -754,10 +727,9 @@ isolate_freepages_range(struct compact_control *cc, { unsigned long isolated, pfn, block_start_pfn, block_end_pfn; int order; - struct list_head tmp_freepages[NR_PAGE_ORDERS]; for (order = 0; order < NR_PAGE_ORDERS; order++) - INIT_LIST_HEAD(&tmp_freepages[order]); + INIT_LIST_HEAD(&cc->freepages[order]); pfn = start_pfn; block_start_pfn = pageblock_start_pfn(pfn); @@ -788,7 +760,7 @@ isolate_freepages_range(struct compact_control *cc, break; isolated = isolate_freepages_block(cc, &isolate_start_pfn, - block_end_pfn, tmp_freepages, 0, true); + block_end_pfn, cc->freepages, 0, true); /* * In strict mode, isolate_freepages_block() returns 0 if @@ -807,13 +779,10 @@ isolate_freepages_range(struct compact_control *cc, if (pfn < end_pfn) { /* Loop terminated early, cleanup. */ - release_free_list(tmp_freepages); + release_free_list(cc->freepages); return 0; } - /* __isolate_free_page() does not map the pages */ - split_map_pages(tmp_freepages); - /* We don't use freelists for anything. */ return pfn; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 56a93805561a..da603080214c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1196,16 +1196,36 @@ static void free_pcppages_bulk(struct zone *zone, int count, spin_unlock_irqrestore(&zone->lock, flags); } +/* Split a multi-block free page into its individual pageblocks. */ +static void split_large_buddy(struct zone *zone, struct page *page, + unsigned long pfn, int order, fpi_t fpi) +{ + unsigned long end = pfn + (1 << order); + + VM_WARN_ON_ONCE(!IS_ALIGNED(pfn, 1 << order)); + /* Caller removed page from freelist, buddy info cleared! */ + VM_WARN_ON_ONCE(PageBuddy(page)); + + if (order > pageblock_order) + order = pageblock_order; + + while (pfn != end) { + int mt = get_pfnblock_migratetype(page, pfn); + + __free_one_page(page, pfn, zone, order, mt, fpi); + pfn += 1 << order; + page = pfn_to_page(pfn); + } +} + static void free_one_page(struct zone *zone, struct page *page, unsigned long pfn, unsigned int order, fpi_t fpi_flags) { unsigned long flags; - int migratetype; spin_lock_irqsave(&zone->lock, flags); - migratetype = get_pfnblock_migratetype(page, pfn); - __free_one_page(page, pfn, zone, order, migratetype, fpi_flags); + split_large_buddy(zone, page, pfn, order, fpi_flags); spin_unlock_irqrestore(&zone->lock, flags); } @@ -1697,27 +1717,6 @@ static unsigned long find_large_buddy(unsigned long start_pfn) return start_pfn; } -/* Split a multi-block free page into its individual pageblocks */ -static void split_large_buddy(struct zone *zone, struct page *page, - unsigned long pfn, int order) -{ - unsigned long end_pfn = pfn + (1 << order); - - VM_WARN_ON_ONCE(order <= pageblock_order); - VM_WARN_ON_ONCE(pfn & (pageblock_nr_pages - 1)); - - /* Caller removed page from freelist, buddy info cleared! */ - VM_WARN_ON_ONCE(PageBuddy(page)); - - while (pfn != end_pfn) { - int mt = get_pfnblock_migratetype(page, pfn); - - __free_one_page(page, pfn, zone, pageblock_order, mt, FPI_NONE); - pfn += pageblock_nr_pages; - page = pfn_to_page(pfn); - } -} - /** * move_freepages_block_isolate - move free pages in block for page isolation * @zone: the zone @@ -1758,7 +1757,7 @@ bool move_freepages_block_isolate(struct zone *zone, struct page *page, del_page_from_free_list(buddy, zone, order, get_pfnblock_migratetype(buddy, pfn)); set_pageblock_migratetype(page, migratetype); - split_large_buddy(zone, buddy, pfn, order); + split_large_buddy(zone, buddy, pfn, order, FPI_NONE); return true; } @@ -1769,7 +1768,7 @@ bool move_freepages_block_isolate(struct zone *zone, struct page *page, del_page_from_free_list(page, zone, order, get_pfnblock_migratetype(page, pfn)); set_pageblock_migratetype(page, migratetype); - split_large_buddy(zone, page, pfn, order); + split_large_buddy(zone, page, pfn, order, FPI_NONE); return true; } move: @@ -6437,6 +6436,31 @@ int __alloc_contig_migrate_range(struct compact_control *cc, return (ret < 0) ? ret : 0; } +static void split_free_pages(struct list_head *list) +{ + int order; + + for (order = 0; order < NR_PAGE_ORDERS; order++) { + struct page *page, *next; + int nr_pages = 1 << order; + + list_for_each_entry_safe(page, next, &list[order], lru) { + int i; + + post_alloc_hook(page, order, __GFP_MOVABLE); + if (!order) + continue; + + split_page(page, order); + + /* Add all subpages to the order-0 head, in sequence. */ + list_del(&page->lru); + for (i = 0; i < nr_pages; i++) + list_add_tail(&page[i].lru, &list[0]); + } + } +} + /** * alloc_contig_range() -- tries to allocate given range of pages * @start: start PFN to allocate @@ -6549,12 +6573,25 @@ int alloc_contig_range_noprof(unsigned long start, unsigned long end, goto done; } - /* Free head and tail (if any) */ - if (start != outer_start) - free_contig_range(outer_start, start - outer_start); - if (end != outer_end) - free_contig_range(end, outer_end - end); + if (!(gfp_mask & __GFP_COMP)) { + split_free_pages(cc.freepages); + /* Free head and tail (if any) */ + if (start != outer_start) + free_contig_range(outer_start, start - outer_start); + if (end != outer_end) + free_contig_range(end, outer_end - end); + } else if (start == outer_start && end == outer_end && is_power_of_2(end - start)) { + struct page *head = pfn_to_page(start); + int order = ilog2(end - start); + + check_new_pages(head, order); + prep_new_page(head, order, gfp_mask, 0); + } else { + ret = -EINVAL; + WARN(true, "PFN range: requested [%lu, %lu), allocated [%lu, %lu)\n", + start, end, outer_start, outer_end); + } done: undo_isolate_page_range(start, end, migratetype); return ret; @@ -6663,6 +6700,18 @@ struct page *alloc_contig_pages_noprof(unsigned long nr_pages, gfp_t gfp_mask, void free_contig_range(unsigned long pfn, unsigned long nr_pages) { unsigned long count = 0; + struct folio *folio = pfn_folio(pfn); + + if (folio_test_large(folio)) { + int expected = folio_nr_pages(folio); + + if (nr_pages == expected) + folio_put(folio); + else + WARN(true, "PFN %lu: nr_pages %lu != expected %d\n", + pfn, nr_pages, expected); + return; + } for (; nr_pages--; pfn++) { struct page *page = pfn_to_page(pfn); -- cgit v1.2.3 From 463586e9ff398f951a9a63d98a3b93f44434d20c Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Tue, 13 Aug 2024 21:54:50 -0600 Subject: mm/cma: add cma_{alloc,free}_folio() With alloc_contig_range() and free_contig_range() supporting large folios, CMA can allocate and free large folios too, by cma_alloc_folio() and cma_free_folio(). [yuzhao@google.com: fix WARN in cma_alloc_folio()] Link: https://lkml.kernel.org/r/Zsd0PgAQmbpR8jS6@google.com Link: https://lkml.kernel.org/r/20240814035451.773331-3-yuzhao@google.com Signed-off-by: Yu Zhao Acked-by: Zi Yan Cc: Frank van der Linden Cc: Matthew Wilcox (Oracle) Cc: Muchun Song Signed-off-by: Andrew Morton --- include/linux/cma.h | 16 ++++++++++++++++ mm/cma.c | 55 ++++++++++++++++++++++++++++++++++++++--------------- 2 files changed, 56 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cma.h b/include/linux/cma.h index 9db877506ea8..d15b64f51336 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -52,4 +52,20 @@ extern bool cma_release(struct cma *cma, const struct page *pages, unsigned long extern int cma_for_each_area(int (*it)(struct cma *cma, void *data), void *data); extern void cma_reserve_pages_on_error(struct cma *cma); + +#ifdef CONFIG_CMA +struct folio *cma_alloc_folio(struct cma *cma, int order, gfp_t gfp); +bool cma_free_folio(struct cma *cma, const struct folio *folio); +#else +static inline struct folio *cma_alloc_folio(struct cma *cma, int order, gfp_t gfp) +{ + return NULL; +} + +static inline bool cma_free_folio(struct cma *cma, const struct folio *folio) +{ + return false; +} +#endif + #endif diff --git a/mm/cma.c b/mm/cma.c index 95d6950e177b..2d9fae939283 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -403,18 +403,8 @@ static void cma_debug_show_areas(struct cma *cma) spin_unlock_irq(&cma->lock); } -/** - * cma_alloc() - allocate pages from contiguous area - * @cma: Contiguous memory region for which the allocation is performed. - * @count: Requested number of pages. - * @align: Requested alignment of pages (in PAGE_SIZE order). - * @no_warn: Avoid printing message about failed allocation - * - * This function allocates part of contiguous memory on specific - * contiguous memory area. - */ -struct page *cma_alloc(struct cma *cma, unsigned long count, - unsigned int align, bool no_warn) +static struct page *__cma_alloc(struct cma *cma, unsigned long count, + unsigned int align, gfp_t gfp) { unsigned long mask, offset; unsigned long pfn = -1; @@ -463,8 +453,7 @@ struct page *cma_alloc(struct cma *cma, unsigned long count, pfn = cma->base_pfn + (bitmap_no << cma->order_per_bit); mutex_lock(&cma_mutex); - ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA, - GFP_KERNEL | (no_warn ? __GFP_NOWARN : 0)); + ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA, gfp); mutex_unlock(&cma_mutex); if (ret == 0) { page = pfn_to_page(pfn); @@ -494,7 +483,7 @@ struct page *cma_alloc(struct cma *cma, unsigned long count, page_kasan_tag_reset(nth_page(page, i)); } - if (ret && !no_warn) { + if (ret && !(gfp & __GFP_NOWARN)) { pr_err_ratelimited("%s: %s: alloc failed, req-size: %lu pages, ret: %d\n", __func__, cma->name, count, ret); cma_debug_show_areas(cma); @@ -513,6 +502,34 @@ struct page *cma_alloc(struct cma *cma, unsigned long count, return page; } +/** + * cma_alloc() - allocate pages from contiguous area + * @cma: Contiguous memory region for which the allocation is performed. + * @count: Requested number of pages. + * @align: Requested alignment of pages (in PAGE_SIZE order). + * @no_warn: Avoid printing message about failed allocation + * + * This function allocates part of contiguous memory on specific + * contiguous memory area. + */ +struct page *cma_alloc(struct cma *cma, unsigned long count, + unsigned int align, bool no_warn) +{ + return __cma_alloc(cma, count, align, GFP_KERNEL | (no_warn ? __GFP_NOWARN : 0)); +} + +struct folio *cma_alloc_folio(struct cma *cma, int order, gfp_t gfp) +{ + struct page *page; + + if (WARN_ON(!order || !(gfp & __GFP_COMP))) + return NULL; + + page = __cma_alloc(cma, 1 << order, order, gfp); + + return page ? page_folio(page) : NULL; +} + bool cma_pages_valid(struct cma *cma, const struct page *pages, unsigned long count) { @@ -564,6 +581,14 @@ bool cma_release(struct cma *cma, const struct page *pages, return true; } +bool cma_free_folio(struct cma *cma, const struct folio *folio) +{ + if (WARN_ON(!folio_test_large(folio))) + return false; + + return cma_release(cma, &folio->page, folio_nr_pages(folio)); +} + int cma_for_each_area(int (*it)(struct cma *cma, void *data), void *data) { int i; -- cgit v1.2.3 From cf54f310d0d313bce6505d010a555948b0ae0e2a Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Tue, 13 Aug 2024 21:54:51 -0600 Subject: mm/hugetlb: use __GFP_COMP for gigantic folios Use __GFP_COMP for gigantic folios to greatly reduce not only the amount of code but also the allocation and free time. LOC (approximately): +60, -240 Allocate and free 500 1GB hugeTLB memory without HVO by: time echo 500 >/sys/kernel/mm/hugepages/hugepages-1048576kB/nr_hugepages time echo 0 >/sys/kernel/mm/hugepages/hugepages-1048576kB/nr_hugepages Before After Alloc ~13s ~10s Free ~15s <1s The above magnitude generally holds for multiple x86 and arm64 CPU models. Link: https://lkml.kernel.org/r/20240814035451.773331-4-yuzhao@google.com Signed-off-by: Yu Zhao Reported-by: Frank van der Linden Acked-by: Zi Yan Cc: Matthew Wilcox (Oracle) Cc: Muchun Song Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 9 +- mm/hugetlb.c | 290 ++++++++++-------------------------------------- 2 files changed, 61 insertions(+), 238 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 3100a52ceb73..98c47c394b89 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -896,10 +896,11 @@ static inline bool hugepage_movable_supported(struct hstate *h) /* Movability of hugepages depends on migration support. */ static inline gfp_t htlb_alloc_mask(struct hstate *h) { - if (hugepage_movable_supported(h)) - return GFP_HIGHUSER_MOVABLE; - else - return GFP_HIGHUSER; + gfp_t gfp = __GFP_COMP | __GFP_NOWARN; + + gfp |= hugepage_movable_supported(h) ? GFP_HIGHUSER_MOVABLE : GFP_HIGHUSER; + + return gfp; } static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index d2b9555e6c45..4461d27f7453 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -56,16 +56,6 @@ struct hstate hstates[HUGE_MAX_HSTATE]; #ifdef CONFIG_CMA static struct cma *hugetlb_cma[MAX_NUMNODES]; static unsigned long hugetlb_cma_size_in_node[MAX_NUMNODES] __initdata; -static bool hugetlb_cma_folio(struct folio *folio, unsigned int order) -{ - return cma_pages_valid(hugetlb_cma[folio_nid(folio)], &folio->page, - 1 << order); -} -#else -static bool hugetlb_cma_folio(struct folio *folio, unsigned int order) -{ - return false; -} #endif static unsigned long hugetlb_cma_size __initdata; @@ -100,6 +90,17 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, unsigned long start, unsigned long end); static struct resv_map *vma_resv_map(struct vm_area_struct *vma); +static void hugetlb_free_folio(struct folio *folio) +{ +#ifdef CONFIG_CMA + int nid = folio_nid(folio); + + if (cma_free_folio(hugetlb_cma[nid], folio)) + return; +#endif + folio_put(folio); +} + static inline bool subpool_is_free(struct hugepage_subpool *spool) { if (spool->count) @@ -1512,95 +1513,54 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) ((node = hstate_next_node_to_free(hs, mask)) || 1); \ nr_nodes--) -/* used to demote non-gigantic_huge pages as well */ -static void __destroy_compound_gigantic_folio(struct folio *folio, - unsigned int order, bool demote) -{ - int i; - int nr_pages = 1 << order; - struct page *p; - - atomic_set(&folio->_entire_mapcount, 0); - atomic_set(&folio->_large_mapcount, 0); - atomic_set(&folio->_pincount, 0); - - for (i = 1; i < nr_pages; i++) { - p = folio_page(folio, i); - p->flags &= ~PAGE_FLAGS_CHECK_AT_FREE; - p->mapping = NULL; - clear_compound_head(p); - if (!demote) - set_page_refcounted(p); - } - - __folio_clear_head(folio); -} - -static void destroy_compound_hugetlb_folio_for_demote(struct folio *folio, - unsigned int order) -{ - __destroy_compound_gigantic_folio(folio, order, true); -} - #ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE -static void destroy_compound_gigantic_folio(struct folio *folio, - unsigned int order) -{ - __destroy_compound_gigantic_folio(folio, order, false); -} - -static void free_gigantic_folio(struct folio *folio, unsigned int order) -{ - /* - * If the page isn't allocated using the cma allocator, - * cma_release() returns false. - */ -#ifdef CONFIG_CMA - int nid = folio_nid(folio); - - if (cma_release(hugetlb_cma[nid], &folio->page, 1 << order)) - return; -#endif - - free_contig_range(folio_pfn(folio), 1 << order); -} - #ifdef CONFIG_CONTIG_ALLOC static struct folio *alloc_gigantic_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { - struct page *page; - unsigned long nr_pages = pages_per_huge_page(h); + struct folio *folio; + int order = huge_page_order(h); + bool retried = false; + if (nid == NUMA_NO_NODE) nid = numa_mem_id(); - +retry: + folio = NULL; #ifdef CONFIG_CMA { int node; - if (hugetlb_cma[nid]) { - page = cma_alloc(hugetlb_cma[nid], nr_pages, - huge_page_order(h), true); - if (page) - return page_folio(page); - } + if (hugetlb_cma[nid]) + folio = cma_alloc_folio(hugetlb_cma[nid], order, gfp_mask); - if (!(gfp_mask & __GFP_THISNODE)) { + if (!folio && !(gfp_mask & __GFP_THISNODE)) { for_each_node_mask(node, *nodemask) { if (node == nid || !hugetlb_cma[node]) continue; - page = cma_alloc(hugetlb_cma[node], nr_pages, - huge_page_order(h), true); - if (page) - return page_folio(page); + folio = cma_alloc_folio(hugetlb_cma[node], order, gfp_mask); + if (folio) + break; } } } #endif + if (!folio) { + folio = folio_alloc_gigantic(order, gfp_mask, nid, nodemask); + if (!folio) + return NULL; + } - page = alloc_contig_pages(nr_pages, gfp_mask, nid, nodemask); - return page ? page_folio(page) : NULL; + if (folio_ref_freeze(folio, 1)) + return folio; + + pr_warn("HugeTLB: unexpected refcount on PFN %lu\n", folio_pfn(folio)); + hugetlb_free_folio(folio); + if (!retried) { + retried = true; + goto retry; + } + return NULL; } #else /* !CONFIG_CONTIG_ALLOC */ @@ -1617,10 +1577,6 @@ static struct folio *alloc_gigantic_folio(struct hstate *h, gfp_t gfp_mask, { return NULL; } -static inline void free_gigantic_folio(struct folio *folio, - unsigned int order) { } -static inline void destroy_compound_gigantic_folio(struct folio *folio, - unsigned int order) { } #endif /* @@ -1748,18 +1704,8 @@ static void __update_and_free_hugetlb_folio(struct hstate *h, folio_ref_unfreeze(folio, 1); - /* - * Non-gigantic pages demoted from CMA allocated gigantic pages - * need to be given back to CMA in free_gigantic_folio. - */ - if (hstate_is_gigantic(h) || - hugetlb_cma_folio(folio, huge_page_order(h))) { - destroy_compound_gigantic_folio(folio, huge_page_order(h)); - free_gigantic_folio(folio, huge_page_order(h)); - } else { - INIT_LIST_HEAD(&folio->_deferred_list); - folio_put(folio); - } + INIT_LIST_HEAD(&folio->_deferred_list); + hugetlb_free_folio(folio); } /* @@ -2032,95 +1978,6 @@ static void prep_new_hugetlb_folio(struct hstate *h, struct folio *folio, int ni spin_unlock_irq(&hugetlb_lock); } -static bool __prep_compound_gigantic_folio(struct folio *folio, - unsigned int order, bool demote) -{ - int i, j; - int nr_pages = 1 << order; - struct page *p; - - __folio_clear_reserved(folio); - for (i = 0; i < nr_pages; i++) { - p = folio_page(folio, i); - - /* - * For gigantic hugepages allocated through bootmem at - * boot, it's safer to be consistent with the not-gigantic - * hugepages and clear the PG_reserved bit from all tail pages - * too. Otherwise drivers using get_user_pages() to access tail - * pages may get the reference counting wrong if they see - * PG_reserved set on a tail page (despite the head page not - * having PG_reserved set). Enforcing this consistency between - * head and tail pages allows drivers to optimize away a check - * on the head page when they need know if put_page() is needed - * after get_user_pages(). - */ - if (i != 0) /* head page cleared above */ - __ClearPageReserved(p); - /* - * Subtle and very unlikely - * - * Gigantic 'page allocators' such as memblock or cma will - * return a set of pages with each page ref counted. We need - * to turn this set of pages into a compound page with tail - * page ref counts set to zero. Code such as speculative page - * cache adding could take a ref on a 'to be' tail page. - * We need to respect any increased ref count, and only set - * the ref count to zero if count is currently 1. If count - * is not 1, we return an error. An error return indicates - * the set of pages can not be converted to a gigantic page. - * The caller who allocated the pages should then discard the - * pages using the appropriate free interface. - * - * In the case of demote, the ref count will be zero. - */ - if (!demote) { - if (!page_ref_freeze(p, 1)) { - pr_warn("HugeTLB page can not be used due to unexpected inflated ref count\n"); - goto out_error; - } - } else { - VM_BUG_ON_PAGE(page_count(p), p); - } - if (i != 0) - set_compound_head(p, &folio->page); - } - __folio_set_head(folio); - /* we rely on prep_new_hugetlb_folio to set the hugetlb flag */ - folio_set_order(folio, order); - atomic_set(&folio->_entire_mapcount, -1); - atomic_set(&folio->_large_mapcount, -1); - atomic_set(&folio->_pincount, 0); - return true; - -out_error: - /* undo page modifications made above */ - for (j = 0; j < i; j++) { - p = folio_page(folio, j); - if (j != 0) - clear_compound_head(p); - set_page_refcounted(p); - } - /* need to clear PG_reserved on remaining tail pages */ - for (; j < nr_pages; j++) { - p = folio_page(folio, j); - __ClearPageReserved(p); - } - return false; -} - -static bool prep_compound_gigantic_folio(struct folio *folio, - unsigned int order) -{ - return __prep_compound_gigantic_folio(folio, order, false); -} - -static bool prep_compound_gigantic_folio_for_demote(struct folio *folio, - unsigned int order) -{ - return __prep_compound_gigantic_folio(folio, order, true); -} - /* * Find and lock address space (mapping) in write mode. * @@ -2159,7 +2016,6 @@ static struct folio *alloc_buddy_hugetlb_folio(struct hstate *h, */ if (node_alloc_noretry && node_isset(nid, *node_alloc_noretry)) alloc_try_hard = false; - gfp_mask |= __GFP_COMP|__GFP_NOWARN; if (alloc_try_hard) gfp_mask |= __GFP_RETRY_MAYFAIL; if (nid == NUMA_NO_NODE) @@ -2206,48 +2062,16 @@ retry: return folio; } -static struct folio *__alloc_fresh_hugetlb_folio(struct hstate *h, - gfp_t gfp_mask, int nid, nodemask_t *nmask, - nodemask_t *node_alloc_noretry) -{ - struct folio *folio; - bool retry = false; - -retry: - if (hstate_is_gigantic(h)) - folio = alloc_gigantic_folio(h, gfp_mask, nid, nmask); - else - folio = alloc_buddy_hugetlb_folio(h, gfp_mask, - nid, nmask, node_alloc_noretry); - if (!folio) - return NULL; - - if (hstate_is_gigantic(h)) { - if (!prep_compound_gigantic_folio(folio, huge_page_order(h))) { - /* - * Rare failure to convert pages to compound page. - * Free pages and try again - ONCE! - */ - free_gigantic_folio(folio, huge_page_order(h)); - if (!retry) { - retry = true; - goto retry; - } - return NULL; - } - } - - return folio; -} - static struct folio *only_alloc_fresh_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry) { struct folio *folio; - folio = __alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask, - node_alloc_noretry); + if (hstate_is_gigantic(h)) + folio = alloc_gigantic_folio(h, gfp_mask, nid, nmask); + else + folio = alloc_buddy_hugetlb_folio(h, gfp_mask, nid, nmask, node_alloc_noretry); if (folio) init_new_hugetlb_folio(h, folio); return folio; @@ -2265,7 +2089,10 @@ static struct folio *alloc_fresh_hugetlb_folio(struct hstate *h, { struct folio *folio; - folio = __alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask, NULL); + if (hstate_is_gigantic(h)) + folio = alloc_gigantic_folio(h, gfp_mask, nid, nmask); + else + folio = alloc_buddy_hugetlb_folio(h, gfp_mask, nid, nmask, NULL); if (!folio) return NULL; @@ -2549,9 +2376,8 @@ struct folio *alloc_buddy_hugetlb_folio_with_mpol(struct hstate *h, nid = huge_node(vma, addr, gfp_mask, &mpol, &nodemask); if (mpol_is_preferred_many(mpol)) { - gfp_t gfp = gfp_mask | __GFP_NOWARN; + gfp_t gfp = gfp_mask & ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); - gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); folio = alloc_surplus_hugetlb_folio(h, gfp, nid, nodemask); /* Fallback to all nodes if page==NULL */ @@ -3333,6 +3159,7 @@ static void __init hugetlb_folio_init_tail_vmemmap(struct folio *folio, for (pfn = head_pfn + start_page_number; pfn < end_pfn; pfn++) { struct page *page = pfn_to_page(pfn); + __ClearPageReserved(folio_page(folio, pfn - head_pfn)); __init_single_page(page, pfn, zone, nid); prep_compound_tail((struct page *)folio, pfn - head_pfn); ret = page_ref_freeze(page, 1); @@ -3949,21 +3776,16 @@ static long demote_free_hugetlb_folios(struct hstate *src, struct hstate *dst, continue; list_del(&folio->lru); - /* - * Use destroy_compound_hugetlb_folio_for_demote for all huge page - * sizes as it will not ref count folios. - */ - destroy_compound_hugetlb_folio_for_demote(folio, huge_page_order(src)); + + split_page_owner(&folio->page, huge_page_order(src), huge_page_order(dst)); + pgalloc_tag_split(&folio->page, 1 << huge_page_order(src)); for (i = 0; i < pages_per_huge_page(src); i += pages_per_huge_page(dst)) { struct page *page = folio_page(folio, i); - if (hstate_is_gigantic(dst)) - prep_compound_gigantic_folio_for_demote(page_folio(page), - dst->order); - else - prep_compound_page(page, dst->order); - set_page_private(page, 0); + page->mapping = NULL; + clear_compound_head(page); + prep_compound_page(page, dst->order); init_new_hugetlb_folio(dst, page_folio(page)); list_add(&page->lru, &dst_list); -- cgit v1.2.3 From d0b003ce97ad6518dea4b0ed70081df95de04179 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 16 Aug 2024 12:32:46 +0200 Subject: mm/rmap: use folio->_mapcount for small folios We have some cases left whereby we operate on small folios and still refer to page->_mapcount. Let's just use folio->_mapcount instead, which currently still overlays page->_mapcount, so no change. This change will make it easier to later spot any remaining users of page->_mapcount that target tail pages. Link: https://lkml.kernel.org/r/20240816103246.719209-1-david@redhat.com Signed-off-by: David Hildenbrand Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- include/linux/rmap.h | 4 ++-- mm/rmap.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 0978c64f49d8..91b5935e8485 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -331,7 +331,7 @@ static __always_inline void __folio_dup_file_rmap(struct folio *folio, switch (level) { case RMAP_LEVEL_PTE: if (!folio_test_large(folio)) { - atomic_inc(&page->_mapcount); + atomic_inc(&folio->_mapcount); break; } @@ -425,7 +425,7 @@ static __always_inline int __folio_try_dup_anon_rmap(struct folio *folio, if (!folio_test_large(folio)) { if (PageAnonExclusive(page)) ClearPageAnonExclusive(page); - atomic_inc(&page->_mapcount); + atomic_inc(&folio->_mapcount); break; } diff --git a/mm/rmap.c b/mm/rmap.c index a6b9cd0b2b18..1103a536e474 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1165,7 +1165,7 @@ static __always_inline unsigned int __folio_add_rmap(struct folio *folio, switch (level) { case RMAP_LEVEL_PTE: if (!folio_test_large(folio)) { - nr = atomic_inc_and_test(&page->_mapcount); + nr = atomic_inc_and_test(&folio->_mapcount); break; } @@ -1535,7 +1535,7 @@ static __always_inline void __folio_remove_rmap(struct folio *folio, switch (level) { case RMAP_LEVEL_PTE: if (!folio_test_large(folio)) { - nr = atomic_add_negative(-1, &page->_mapcount); + nr = atomic_add_negative(-1, &folio->_mapcount); break; } -- cgit v1.2.3 From 489a744e5fb16503b495ad1fa3dd1abf25b224e7 Mon Sep 17 00:00:00 2001 From: Danilo Krummrich Date: Tue, 13 Aug 2024 00:34:35 +0200 Subject: mm: krealloc: clarify valid usage of __GFP_ZERO Properly document that if __GFP_ZERO logic is requested, callers must ensure that, starting with the initial memory allocation, every subsequent call to this API for the same memory allocation is flagged with __GFP_ZERO. Otherwise, it is possible that __GFP_ZERO is not fully honored by this API. Link: https://lkml.kernel.org/r/20240812223707.32049-2-dakr@kernel.org Signed-off-by: Danilo Krummrich Acked-by: David Rientjes Cc: Christoph Lameter Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com> Cc: Joonsoo Kim Cc: Pekka Enberg Cc: Roman Gushchin Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/slab.h | 10 ++++++++++ mm/slab_common.c | 20 ++++++++++++++++++-- 2 files changed, 28 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index c9cb42203183..2282e67a01c7 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -733,6 +733,16 @@ static inline __alloc_size(1, 2) void *kmalloc_array_noprof(size_t n, size_t siz * @new_n: new number of elements to alloc * @new_size: new size of a single member of the array * @flags: the type of memory to allocate (see kmalloc) + * + * If __GFP_ZERO logic is requested, callers must ensure that, starting with the + * initial memory allocation, every subsequent call to this API for the same + * memory allocation is flagged with __GFP_ZERO. Otherwise, it is possible that + * __GFP_ZERO is not fully honored by this API. + * + * See krealloc_noprof() for further details. + * + * In any case, the contents of the object pointed to are preserved up to the + * lesser of the new and old sizes. */ static inline __realloc_size(2, 3) void * __must_check krealloc_array_noprof(void *p, size_t new_n, diff --git a/mm/slab_common.c b/mm/slab_common.c index cff602cedf8e..1b380eb3b4f2 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -1301,11 +1301,27 @@ __do_krealloc(const void *p, size_t new_size, gfp_t flags) * @new_size: how many bytes of memory are required. * @flags: the type of memory to allocate. * - * The contents of the object pointed to are preserved up to the - * lesser of the new and old sizes (__GFP_ZERO flag is effectively ignored). * If @p is %NULL, krealloc() behaves exactly like kmalloc(). If @new_size * is 0 and @p is not a %NULL pointer, the object pointed to is freed. * + * If __GFP_ZERO logic is requested, callers must ensure that, starting with the + * initial memory allocation, every subsequent call to this API for the same + * memory allocation is flagged with __GFP_ZERO. Otherwise, it is possible that + * __GFP_ZERO is not fully honored by this API. + * + * This is the case, since krealloc() only knows about the bucket size of an + * allocation (but not the exact size it was allocated with) and hence + * implements the following semantics for shrinking and growing buffers with + * __GFP_ZERO. + * + * new bucket + * 0 size size + * |--------|----------------| + * | keep | zero | + * + * In any case, the contents of the object pointed to are preserved up to the + * lesser of the new and old sizes. + * * Return: pointer to the allocated memory or %NULL in case of error */ void *krealloc_noprof(const void *p, size_t new_size, gfp_t flags) -- cgit v1.2.3 From a759e37fb46708029c9c3c56c3b62e6f24d85cf5 Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Sun, 18 Aug 2024 23:01:51 +0200 Subject: err.h: add ERR_PTR_PCPU(), PTR_ERR_PCPU() and IS_ERR_PCPU() macros Add ERR_PTR_PCPU(), PTR_ERR_PCPU() and IS_ERR_PCPU() macros that operate on pointers in the percpu address space. These macros remove the need for (__force void *) function argument casts (to avoid sparse -Wcast-from-as warnings). The patch will also avoid future build errors due to pointer address space mismatch with enabled strict percpu address space checks. Link: https://lkml.kernel.org/r/20240818210235.33481-1-ubizjak@gmail.com Signed-off-by: Uros Bizjak Acked-by: Catalin Marinas Signed-off-by: Andrew Morton --- include/linux/err.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/err.h b/include/linux/err.h index b5d9bb2a2349..a4dacd745fcf 100644 --- a/include/linux/err.h +++ b/include/linux/err.h @@ -41,6 +41,9 @@ static inline void * __must_check ERR_PTR(long error) return (void *) error; } +/* Return the pointer in the percpu address space. */ +#define ERR_PTR_PCPU(error) ((void __percpu *)(unsigned long)ERR_PTR(error)) + /** * PTR_ERR - Extract the error code from an error pointer. * @ptr: An error pointer. @@ -51,6 +54,9 @@ static inline long __must_check PTR_ERR(__force const void *ptr) return (long) ptr; } +/* Read an error pointer from the percpu address space. */ +#define PTR_ERR_PCPU(ptr) (PTR_ERR((const void *)(__force const unsigned long)(ptr))) + /** * IS_ERR - Detect an error pointer. * @ptr: The pointer to check. @@ -61,6 +67,9 @@ static inline bool __must_check IS_ERR(__force const void *ptr) return IS_ERR_VALUE((unsigned long)ptr); } +/* Read an error pointer from the percpu address space. */ +#define IS_ERR_PCPU(ptr) (IS_ERR((const void *)(__force const unsigned long)(ptr))) + /** * IS_ERR_OR_NULL - Detect an error pointer or a null pointer. * @ptr: The pointer to check. -- cgit v1.2.3 From ef5f379de302884b9b7ad9b62587a942a9f0bb55 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 20 Aug 2024 14:22:10 +0200 Subject: mm: always inline _compound_head() with CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP=y We already force-inline page_fixed_fake_head(), page_is_fake_head() and PageTail(), however the compiler might decide that _compound_head() is not worthy to be inlined, because of page_fixed_fake_head(). The result is that, for example, PageAnonExclusive() now might involve a function call when checking PageHuge(), which performs a page_folio()->_compound_head() call. This can lead to a slight regression of the stress-ng.clone benchmark. This is not super-urgent to fix, but always inlining _compound_head() seems like the obvious thing to do for this primitive, similar to the other ones. This change restores the slight regression and a compilation with CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP=y shows no relevant bloat [2]: add/remove: 15/14 grow/shrink: 79/87 up/down: 12836/-13917 (-1081) ... Total: Before=32786363, After=32785282, chg -0.00% [1] https://lkml.kernel.org/r/817150f2-abf7-430f-9973-540bd6cdd26f@intel.com [2] https://lore.kernel.org/all/116e117c-2821-401d-8e62-b85cdec37f4a@redhat.com/ Link: https://lkml.kernel.org/r/20240820122210.660140-1-david@redhat.com Fixes: c0bff412e67b ("mm: allow anon exclusive check over hugetlb tail pages") Signed-off-by: David Hildenbrand Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-lkp/202407301049.5051dc19-oliver.sang@intel.com Tested-by: Yin Fengwei Cc: Peter Xu Signed-off-by: Andrew Morton --- include/linux/page-flags.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 17175a328e6b..2515ae85f191 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -232,7 +232,7 @@ static __always_inline int page_is_fake_head(const struct page *page) return page_fixed_fake_head(page) != page; } -static inline unsigned long _compound_head(const struct page *page) +static __always_inline unsigned long _compound_head(const struct page *page) { unsigned long head = READ_ONCE(page->compound_head); -- cgit v1.2.3 From 0a2d82946be67e02fdf85a4010606bdc0546ba44 Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Tue, 20 Aug 2024 10:26:39 +0800 Subject: mm: allow read-ahead with IOCB_NOWAIT set Readahead support for IOCB_NOWAIT was introduced in commit 2e85abf053b9 ("mm: allow read-ahead with IOCB_NOWAIT set"). However, this implementation broke the semantics of IOCB_NOWAIT by potentially causing it to wait on I/O during memory reclamation. This behavior was later modified in commit efa8480a8316 ("fs: RWF_NOWAIT should imply IOCB_NOIO"). To resolve the blocking issue during memory reclamation, we can use memalloc_noio_{save,restore} to ensure non-blocking behavior. This change restores the original functionality, allowing preadv2(IOCB_NOWAIT) to trigger readahead if the file content is not present in the page cache. While this process may trigger direct memory reclamation, the __GFP_NORETRY flag is set in the readahead GFP flags, ensuring it won't block. A use case for this change is when we want to trigger readahead in the preadv2(2) syscall if the file cache is absent, but without waiting for certain filesystem locks, like xfs_ilock. A simple example is as follows: retry: if (preadv2(fd, iovec, cnt, offset, RWF_NOWAIT) < 0) { do_other_work(); goto retry; } Link: https://lore.gnuweeb.org/io-uring/20200624164127.GP21350@casper.infradead.org/ Link: https://lkml.kernel.org/r/20240820022639.89562-1-laoar.shao@gmail.com Signed-off-by: Yafang Shao Cc: Jens Axboe Cc: Matthew Wilcox Cc: Dave Chinner Cc: Jan Kara Cc: Christian Brauner Signed-off-by: Andrew Morton --- include/linux/fs.h | 1 - mm/filemap.c | 6 ++++++ 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 6ca11e241a24..8610242ec2ab 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3461,7 +3461,6 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags, if (flags & RWF_NOWAIT) { if (!(ki->ki_filp->f_mode & FMODE_NOWAIT)) return -EOPNOTSUPP; - kiocb_flags |= IOCB_NOIO; } if (flags & RWF_ATOMIC) { if (rw_type != WRITE) diff --git a/mm/filemap.c b/mm/filemap.c index fdaa1e5e3078..070dee9791a9 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -46,6 +46,7 @@ #include #include #include +#include #include #include #include "internal.h" @@ -2519,6 +2520,7 @@ static int filemap_get_pages(struct kiocb *iocb, size_t count, pgoff_t index = iocb->ki_pos >> PAGE_SHIFT; pgoff_t last_index; struct folio *folio; + unsigned int flags; int err = 0; /* "last_index" is the index of the page beyond the end of the read */ @@ -2531,8 +2533,12 @@ retry: if (!folio_batch_count(fbatch)) { if (iocb->ki_flags & IOCB_NOIO) return -EAGAIN; + if (iocb->ki_flags & IOCB_NOWAIT) + flags = memalloc_noio_save(); page_cache_sync_readahead(mapping, ra, filp, index, last_index - index); + if (iocb->ki_flags & IOCB_NOWAIT) + memalloc_noio_restore(flags); filemap_get_read_batch(mapping, index, last_index - 1, fbatch); } if (!folio_batch_count(fbatch)) { -- cgit v1.2.3 From e880034cf7182aa35962bd30dfc9fa60476d56a4 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 21 Aug 2024 18:39:10 +0100 Subject: mm: introduce page_mapcount_is_type() Resolve the awkward "and add one to this opaque constant" test into a self-documenting inline function. Link: https://lkml.kernel.org/r/20240821173914.2270383-3-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Acked-by: David Hildenbrand Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com> Cc: Kent Overstreet Signed-off-by: Andrew Morton --- fs/proc/internal.h | 3 +-- include/linux/mm.h | 3 +-- include/linux/page-flags.h | 12 +++++++++--- 3 files changed, 11 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/internal.h b/fs/proc/internal.h index a8a8576d8592..cc520168f8b6 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -166,8 +166,7 @@ static inline int folio_precise_page_mapcount(struct folio *folio, { int mapcount = atomic_read(&page->_mapcount) + 1; - /* Handle page_has_type() pages */ - if (mapcount < PAGE_MAPCOUNT_RESERVE + 1) + if (page_mapcount_is_type(mapcount)) mapcount = 0; if (folio_test_large(folio)) mapcount += folio_entire_mapcount(folio); diff --git a/include/linux/mm.h b/include/linux/mm.h index 0fde51c0532f..6f6053d7ea6f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1228,8 +1228,7 @@ static inline int folio_mapcount(const struct folio *folio) if (likely(!folio_test_large(folio))) { mapcount = atomic_read(&folio->_mapcount) + 1; - /* Handle page_has_type() pages */ - if (mapcount < PAGE_MAPCOUNT_RESERVE + 1) + if (page_mapcount_is_type(mapcount)) mapcount = 0; return mapcount; } diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 2515ae85f191..0b5484fdbca1 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -956,12 +956,18 @@ enum pagetype { #define folio_test_type(folio, flag) \ ((READ_ONCE(folio->page.page_type) & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) -static inline int page_type_has_type(unsigned int page_type) +static inline bool page_type_has_type(int page_type) { - return (int)page_type < PAGE_MAPCOUNT_RESERVE; + return page_type < PAGE_MAPCOUNT_RESERVE; } -static inline int page_has_type(const struct page *page) +/* This takes a mapcount which is one more than page->_mapcount */ +static inline bool page_mapcount_is_type(unsigned int mapcount) +{ + return page_type_has_type(mapcount - 1); +} + +static inline bool page_has_type(const struct page *page) { return page_type_has_type(READ_ONCE(page->page_type)); } -- cgit v1.2.3 From 4ffca5a96678c9fe1a39ec1e9c8fd326b57ea8a7 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 21 Aug 2024 18:39:11 +0100 Subject: mm: support only one page_type per page By using a few values in the top byte, users of page_type can store up to 24 bits of additional data in page_type. It also reduces the code size as (with replacement of READ_ONCE() with data_race()), the kernel can check just a single byte. eg: ffffffff811e3a79: 8b 47 30 mov 0x30(%rdi),%eax ffffffff811e3a7c: 55 push %rbp ffffffff811e3a7d: 48 89 e5 mov %rsp,%rbp ffffffff811e3a80: 25 00 00 00 82 and $0x82000000,%eax ffffffff811e3a85: 3d 00 00 00 80 cmp $0x80000000,%eax ffffffff811e3a8a: 74 4d je ffffffff811e3ad9 becomes: ffffffff811e3a69: 80 7f 33 f5 cmpb $0xf5,0x33(%rdi) ffffffff811e3a6d: 55 push %rbp ffffffff811e3a6e: 48 89 e5 mov %rsp,%rbp ffffffff811e3a71: 74 4d je ffffffff811e3ac0 replacing three instructions with one. [wangkefeng.wang@huawei.com: fix ubsan warnings] Link: https://lkml.kernel.org/r/2d19c48a-c550-4345-bf36-d05cd303c5de@huawei.com Link: https://lkml.kernel.org/r/20240821173914.2270383-4-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Acked-by: David Hildenbrand Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com> Cc: Kent Overstreet Signed-off-by: Andrew Morton --- include/linux/page-flags.h | 68 +++++++++++++++++++--------------------------- kernel/vmcore_info.c | 8 +++--- mm/debug.c | 31 ++++++++++++++++----- 3 files changed, 56 insertions(+), 51 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 0b5484fdbca1..7a1b2948b075 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -923,42 +923,29 @@ PAGEFLAG_FALSE(HasHWPoisoned, has_hwpoisoned) #endif /* - * For pages that are never mapped to userspace, - * page_type may be used. Because it is initialised to -1, we invert the - * sense of the bit, so __SetPageFoo *clears* the bit used for PageFoo, and - * __ClearPageFoo *sets* the bit used for PageFoo. We reserve a few high and - * low bits so that an underflow or overflow of _mapcount won't be - * mistaken for a page type value. + * For pages that do not use mapcount, page_type may be used. + * The low 24 bits of pagetype may be used for your own purposes, as long + * as you are careful to not affect the top 8 bits. The low bits of + * pagetype will be overwritten when you clear the page_type from the page. */ - enum pagetype { - PG_buddy = 0x40000000, - PG_offline = 0x20000000, - PG_table = 0x10000000, - PG_guard = 0x08000000, - PG_hugetlb = 0x04000000, - PG_slab = 0x02000000, - PG_zsmalloc = 0x01000000, - PG_unaccepted = 0x00800000, - - PAGE_TYPE_BASE = 0x80000000, - - /* - * Reserve 0xffff0000 - 0xfffffffe to catch _mapcount underflows and - * allow owners that set a type to reuse the lower 16 bit for their own - * purposes. - */ - PAGE_MAPCOUNT_RESERVE = ~0x0000ffff, + /* 0x00-0x7f are positive numbers, ie mapcount */ + /* Reserve 0x80-0xef for mapcount overflow. */ + PGTY_buddy = 0xf0, + PGTY_offline = 0xf1, + PGTY_table = 0xf2, + PGTY_guard = 0xf3, + PGTY_hugetlb = 0xf4, + PGTY_slab = 0xf5, + PGTY_zsmalloc = 0xf6, + PGTY_unaccepted = 0xf7, + + PGTY_mapcount_underflow = 0xff }; -#define PageType(page, flag) \ - ((READ_ONCE(page->page_type) & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) -#define folio_test_type(folio, flag) \ - ((READ_ONCE(folio->page.page_type) & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) - static inline bool page_type_has_type(int page_type) { - return page_type < PAGE_MAPCOUNT_RESERVE; + return page_type < (PGTY_mapcount_underflow << 24); } /* This takes a mapcount which is one more than page->_mapcount */ @@ -969,40 +956,41 @@ static inline bool page_mapcount_is_type(unsigned int mapcount) static inline bool page_has_type(const struct page *page) { - return page_type_has_type(READ_ONCE(page->page_type)); + return page_mapcount_is_type(data_race(page->page_type)); } #define FOLIO_TYPE_OPS(lname, fname) \ -static __always_inline bool folio_test_##fname(const struct folio *folio)\ +static __always_inline bool folio_test_##fname(const struct folio *folio) \ { \ - return folio_test_type(folio, PG_##lname); \ + return data_race(folio->page.page_type >> 24) == PGTY_##lname; \ } \ static __always_inline void __folio_set_##fname(struct folio *folio) \ { \ - VM_BUG_ON_FOLIO(!folio_test_type(folio, 0), folio); \ - folio->page.page_type &= ~PG_##lname; \ + VM_BUG_ON_FOLIO(data_race(folio->page.page_type) != UINT_MAX, \ + folio); \ + folio->page.page_type = (unsigned int)PGTY_##lname << 24; \ } \ static __always_inline void __folio_clear_##fname(struct folio *folio) \ { \ VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio); \ - folio->page.page_type |= PG_##lname; \ + folio->page.page_type = UINT_MAX; \ } #define PAGE_TYPE_OPS(uname, lname, fname) \ FOLIO_TYPE_OPS(lname, fname) \ static __always_inline int Page##uname(const struct page *page) \ { \ - return PageType(page, PG_##lname); \ + return data_race(page->page_type >> 24) == PGTY_##lname; \ } \ static __always_inline void __SetPage##uname(struct page *page) \ { \ - VM_BUG_ON_PAGE(!PageType(page, 0), page); \ - page->page_type &= ~PG_##lname; \ + VM_BUG_ON_PAGE(data_race(page->page_type) != UINT_MAX, page); \ + page->page_type = (unsigned int)PGTY_##lname << 24; \ } \ static __always_inline void __ClearPage##uname(struct page *page) \ { \ VM_BUG_ON_PAGE(!Page##uname(page), page); \ - page->page_type |= PG_##lname; \ + page->page_type = UINT_MAX; \ } /* diff --git a/kernel/vmcore_info.c b/kernel/vmcore_info.c index 8b4f8cc2e0ec..1fec61603ef3 100644 --- a/kernel/vmcore_info.c +++ b/kernel/vmcore_info.c @@ -198,17 +198,17 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_NUMBER(PG_private); VMCOREINFO_NUMBER(PG_swapcache); VMCOREINFO_NUMBER(PG_swapbacked); -#define PAGE_SLAB_MAPCOUNT_VALUE (~PG_slab) +#define PAGE_SLAB_MAPCOUNT_VALUE (PGTY_slab << 24) VMCOREINFO_NUMBER(PAGE_SLAB_MAPCOUNT_VALUE); #ifdef CONFIG_MEMORY_FAILURE VMCOREINFO_NUMBER(PG_hwpoison); #endif VMCOREINFO_NUMBER(PG_head_mask); -#define PAGE_BUDDY_MAPCOUNT_VALUE (~PG_buddy) +#define PAGE_BUDDY_MAPCOUNT_VALUE (PGTY_buddy << 24) VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE); -#define PAGE_HUGETLB_MAPCOUNT_VALUE (~PG_hugetlb) +#define PAGE_HUGETLB_MAPCOUNT_VALUE (PGTY_hugetlb << 24) VMCOREINFO_NUMBER(PAGE_HUGETLB_MAPCOUNT_VALUE); -#define PAGE_OFFLINE_MAPCOUNT_VALUE (~PG_offline) +#define PAGE_OFFLINE_MAPCOUNT_VALUE (PGTY_offline << 24) VMCOREINFO_NUMBER(PAGE_OFFLINE_MAPCOUNT_VALUE); #ifdef CONFIG_KALLSYMS diff --git a/mm/debug.c b/mm/debug.c index 9f8e34537957..aa57d3ffd4ed 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -36,11 +36,6 @@ const struct trace_print_flags pageflag_names[] = { {0, NULL} }; -const struct trace_print_flags pagetype_names[] = { - __def_pagetype_names, - {0, NULL} -}; - const struct trace_print_flags gfpflag_names[] = { __def_gfpflag_names, {0, NULL} @@ -51,6 +46,27 @@ const struct trace_print_flags vmaflag_names[] = { {0, NULL} }; +#define DEF_PAGETYPE_NAME(_name) [PGTY_##_name - 0xf0] = __stringify(_name) + +static const char *page_type_names[] = { + DEF_PAGETYPE_NAME(slab), + DEF_PAGETYPE_NAME(hugetlb), + DEF_PAGETYPE_NAME(offline), + DEF_PAGETYPE_NAME(guard), + DEF_PAGETYPE_NAME(table), + DEF_PAGETYPE_NAME(buddy), + DEF_PAGETYPE_NAME(unaccepted), +}; + +static const char *page_type_name(unsigned int page_type) +{ + unsigned i = (page_type >> 24) - 0xf0; + + if (i >= ARRAY_SIZE(page_type_names)) + return "unknown"; + return page_type_names[i]; +} + static void __dump_folio(struct folio *folio, struct page *page, unsigned long pfn, unsigned long idx) { @@ -58,7 +74,7 @@ static void __dump_folio(struct folio *folio, struct page *page, int mapcount = atomic_read(&page->_mapcount); char *type = ""; - mapcount = page_type_has_type(mapcount) ? 0 : mapcount + 1; + mapcount = page_mapcount_is_type(mapcount) ? 0 : mapcount + 1; pr_warn("page: refcount:%d mapcount:%d mapping:%p index:%#lx pfn:%#lx\n", folio_ref_count(folio), mapcount, mapping, folio->index + idx, pfn); @@ -92,7 +108,8 @@ static void __dump_folio(struct folio *folio, struct page *page, pr_warn("%sflags: %pGp%s\n", type, &folio->flags, is_migrate_cma_folio(folio, pfn) ? " CMA" : ""); if (page_has_type(&folio->page)) - pr_warn("page_type: %x\n", folio->page.page_type); + pr_warn("page_type: %x(%s)\n", folio->page.page_type >> 24, + page_type_name(folio->page.page_type)); print_hex_dump(KERN_WARNING, "raw: ", DUMP_PREFIX_NONE, 32, sizeof(unsigned long), page, -- cgit v1.2.3 From bf03c806993091d8fb2fc0e98f07a8ef251c78f3 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 21 Aug 2024 20:34:34 +0100 Subject: mm: remove PageActive Patch series "Simplify the page flags a little". In the course of our folio conversions, we have made many page flags only used on folios, so we can now remove the page-based accessors. This should cut down compile time a little, and prevent new users from cropping up. There is more that could be done in this area, but it would produce merge conflicts, so I'll sit on those patches until next merge window. We now have line of sight to removing PG_private_2 and PG_private. This patch (of 10): This flag is now only used on folios, so we can remove all the page accessors. [akpm@linux-foundation.org: fix arch/powerpc/mm/pgtable-frag.c] Link: https://lkml.kernel.org/r/20240821193445.2294269-1-willy@infradead.org Link: https://lkml.kernel.org/r/20240821193445.2294269-2-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- arch/powerpc/mm/pgtable-frag.c | 6 +++--- include/linux/page-flags.h | 5 +++-- 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/mm/pgtable-frag.c b/arch/powerpc/mm/pgtable-frag.c index 8c31802f97e8..e89f64a0f24a 100644 --- a/arch/powerpc/mm/pgtable-frag.c +++ b/arch/powerpc/mm/pgtable-frag.c @@ -136,10 +136,10 @@ void pte_fragment_free(unsigned long *table, int kernel) #ifdef CONFIG_TRANSPARENT_HUGEPAGE void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable) { - struct page *page; + struct folio *folio; - page = virt_to_page(pgtable); - SetPageActive(page); + folio = virt_to_folio(pgtable); + folio_set_active(folio); pte_fragment_free((unsigned long *)pgtable, 0); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 7a1b2948b075..34347bee1217 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -510,8 +510,9 @@ PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD) __CLEARPAGEFLAG(Dirty, dirty, PF_HEAD) PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD) TESTCLEARFLAG(LRU, lru, PF_HEAD) -PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD) - TESTCLEARFLAG(Active, active, PF_HEAD) +FOLIO_FLAG(active, FOLIO_HEAD_PAGE) + __FOLIO_CLEAR_FLAG(active, FOLIO_HEAD_PAGE) + FOLIO_TEST_CLEAR_FLAG(active, FOLIO_HEAD_PAGE) PAGEFLAG(Workingset, workingset, PF_HEAD) TESTCLEARFLAG(Workingset, workingset, PF_HEAD) PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */ -- cgit v1.2.3 From 0b7582803649e0e58e5f8c9a4ede362777bc7eec Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 21 Aug 2024 20:34:35 +0100 Subject: mm: remove PageSwapBacked This flag is now only used on folios, so we can remove all the page accessors. Link: https://lkml.kernel.org/r/20240821193445.2294269-3-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/page-flags.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 34347bee1217..cebb3dc0fd0c 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -528,9 +528,9 @@ PAGEFLAG(XenRemapped, xen_remapped, PF_NO_COMPOUND) PAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) __CLEARPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) __SETPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) -PAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) - __CLEARPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) - __SETPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) +FOLIO_FLAG(swapbacked, FOLIO_HEAD_PAGE) + __FOLIO_CLEAR_FLAG(swapbacked, FOLIO_HEAD_PAGE) + __FOLIO_SET_FLAG(swapbacked, FOLIO_HEAD_PAGE) /* * Private page markings that may be used by the filesystem that owns the page -- cgit v1.2.3 From 6f394ee9ddb4bd1879e42c9c8648a37f650bea99 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 21 Aug 2024 20:34:36 +0100 Subject: mm: remove PageReadahead This flag is now only used on folios, so we can remove all the page accessors. Link: https://lkml.kernel.org/r/20240821193445.2294269-4-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/page-flags.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index cebb3dc0fd0c..71444223d630 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -553,8 +553,8 @@ PAGEFLAG(MappedToDisk, mappedtodisk, PF_NO_TAIL) /* PG_readahead is only used for reads; PG_reclaim is only for writes */ PAGEFLAG(Reclaim, reclaim, PF_NO_TAIL) TESTCLEARFLAG(Reclaim, reclaim, PF_NO_TAIL) -PAGEFLAG(Readahead, readahead, PF_NO_COMPOUND) - TESTCLEARFLAG(Readahead, readahead, PF_NO_COMPOUND) +FOLIO_FLAG(readahead, FOLIO_HEAD_PAGE) + FOLIO_TEST_CLEAR_FLAG(readahead, FOLIO_HEAD_PAGE) #ifdef CONFIG_HIGHMEM /* -- cgit v1.2.3 From 32f51ead3d7771cdec29f75e08d50a76d2c6253d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 21 Aug 2024 20:34:37 +0100 Subject: mm: remove PageSwapCache This flag is now only used on folios, so we can remove all the page accessors and reword the comments that refer to them. Link: https://lkml.kernel.org/r/20240821193445.2294269-5-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/mm_types.h | 2 +- include/linux/page-flags.h | 11 +++-------- mm/ksm.c | 19 ++++++++++--------- mm/migrate.c | 3 ++- mm/shmem.c | 11 ++++++----- 5 files changed, 22 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 2419e60c9a7f..6e3bdf8e38bc 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -109,7 +109,7 @@ struct page { /** * @private: Mapping-private opaque data. * Usually used for buffer_heads if PagePrivate. - * Used for swp_entry_t if PageSwapCache. + * Used for swp_entry_t if swapcache flag set. * Indicates order in the buddy system if PageBuddy. */ unsigned long private; diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 71444223d630..b31d2c50b6f0 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -574,15 +574,10 @@ static __always_inline bool folio_test_swapcache(const struct folio *folio) test_bit(PG_swapcache, const_folio_flags(folio, 0)); } -static __always_inline bool PageSwapCache(const struct page *page) -{ - return folio_test_swapcache(page_folio(page)); -} - -SETPAGEFLAG(SwapCache, swapcache, PF_NO_TAIL) -CLEARPAGEFLAG(SwapCache, swapcache, PF_NO_TAIL) +FOLIO_SET_FLAG(swapcache, FOLIO_HEAD_PAGE) +FOLIO_CLEAR_FLAG(swapcache, FOLIO_HEAD_PAGE) #else -PAGEFLAG_FALSE(SwapCache, swapcache) +FOLIO_FLAG_FALSE(swapcache) #endif PAGEFLAG(Unevictable, unevictable, PF_HEAD) diff --git a/mm/ksm.c b/mm/ksm.c index 8e53666bc7b0..a2e2a521df0a 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -909,12 +909,13 @@ again: */ while (!folio_try_get(folio)) { /* - * Another check for page->mapping != expected_mapping would - * work here too. We have chosen the !PageSwapCache test to - * optimize the common case, when the page is or is about to - * be freed: PageSwapCache is cleared (under spin_lock_irq) - * in the ref_freeze section of __remove_mapping(); but Anon - * folio->mapping reset to NULL later, in free_pages_prepare(). + * Another check for folio->mapping != expected_mapping + * would work here too. We have chosen to test the + * swapcache flag to optimize the common case, when the + * folio is or is about to be freed: the swapcache flag + * is cleared (under spin_lock_irq) in the ref_freeze + * section of __remove_mapping(); but anon folio->mapping + * is reset to NULL later, in free_pages_prepare(). */ if (!folio_test_swapcache(folio)) goto stale; @@ -945,7 +946,7 @@ again: stale: /* - * We come here from above when page->mapping or !PageSwapCache + * We come here from above when folio->mapping or the swapcache flag * suggests that the node is stale; but it might be under migration. * We need smp_rmb(), matching the smp_wmb() in folio_migrate_ksm(), * before checking whether node->kpfn has been changed. @@ -1452,7 +1453,7 @@ static int try_to_merge_one_page(struct vm_area_struct *vma, goto out; /* - * We need the page lock to read a stable PageSwapCache in + * We need the folio lock to read a stable swapcache flag in * write_protect_page(). We use trylock_page() instead of * lock_page() because we don't want to wait here - we * prefer to continue scanning and merging different pages, @@ -3123,7 +3124,7 @@ void folio_migrate_ksm(struct folio *newfolio, struct folio *folio) * newfolio->mapping was set in advance; now we need smp_wmb() * to make sure that the new stable_node->kpfn is visible * to ksm_get_folio() before it can see that folio->mapping - * has gone stale (or that folio_test_swapcache has been cleared). + * has gone stale (or that the swapcache flag has been cleared). */ smp_wmb(); folio_set_stable_node(folio, NULL); diff --git a/mm/migrate.c b/mm/migrate.c index 76cfc6c42eb3..2250baa85ac2 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -639,7 +639,8 @@ void folio_migrate_flags(struct folio *newfolio, struct folio *folio) folio_migrate_ksm(newfolio, folio); /* * Please do not reorder this without considering how mm/ksm.c's - * ksm_get_folio() depends upon ksm_migrate_page() and PageSwapCache(). + * ksm_get_folio() depends upon ksm_migrate_page() and the + * swapcache flag. */ if (folio_test_swapcache(folio)) folio_clear_swapcache(folio); diff --git a/mm/shmem.c b/mm/shmem.c index 1448a7a9a282..866d46d0c43d 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -502,8 +502,8 @@ static int shmem_replace_entry(struct address_space *mapping, * Sometimes, before we decide whether to proceed or to fail, we must check * that an entry was not already brought back from swap by a racing thread. * - * Checking page is not enough: by the time a SwapCache page is locked, it - * might be reused, and again be SwapCache, using the same swap as before. + * Checking folio is not enough: by the time a swapcache folio is locked, it + * might be reused, and again be swapcache, using the same swap as before. */ static bool shmem_confirm_swap(struct address_space *mapping, pgoff_t index, swp_entry_t swap) @@ -1965,9 +1965,10 @@ static int shmem_replace_folio(struct folio **foliop, gfp_t gfp, if (unlikely(error)) { /* - * Is this possible? I think not, now that our callers check - * both PageSwapCache and page_private after getting page lock; - * but be defensive. Reverse old to newpage for clear and free. + * Is this possible? I think not, now that our callers + * check both the swapcache flag and folio->private + * after getting the folio lock; but be defensive. + * Reverse old to newpage for clear and free. */ old = new; } else { -- cgit v1.2.3 From cb29e7941d5d57576392a52c08077ef327ec8e17 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 21 Aug 2024 20:34:38 +0100 Subject: mm: remove PageUnevictable There is only one caller of PageUnevictable() left; convert it to call folio_test_unevictable() and remove all the page accessors. Link: https://lkml.kernel.org/r/20240821193445.2294269-6-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/page-flags.h | 6 +++--- mm/huge_memory.c | 16 ++++++++-------- 2 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index b31d2c50b6f0..2150502195d5 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -580,9 +580,9 @@ FOLIO_CLEAR_FLAG(swapcache, FOLIO_HEAD_PAGE) FOLIO_FLAG_FALSE(swapcache) #endif -PAGEFLAG(Unevictable, unevictable, PF_HEAD) - __CLEARPAGEFLAG(Unevictable, unevictable, PF_HEAD) - TESTCLEARFLAG(Unevictable, unevictable, PF_HEAD) +FOLIO_FLAG(unevictable, FOLIO_HEAD_PAGE) + __FOLIO_CLEAR_FLAG(unevictable, FOLIO_HEAD_PAGE) + FOLIO_TEST_CLEAR_FLAG(unevictable, FOLIO_HEAD_PAGE) #ifdef CONFIG_MMU PAGEFLAG(Mlocked, mlocked, PF_NO_TAIL) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index ef6d4f617c4a..8dfb912ebdaa 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2932,25 +2932,25 @@ static void remap_page(struct folio *folio, unsigned long nr) } } -static void lru_add_page_tail(struct page *head, struct page *tail, +static void lru_add_page_tail(struct folio *folio, struct page *tail, struct lruvec *lruvec, struct list_head *list) { - VM_BUG_ON_PAGE(!PageHead(head), head); - VM_BUG_ON_PAGE(PageLRU(tail), head); + VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); + VM_BUG_ON_FOLIO(PageLRU(tail), folio); lockdep_assert_held(&lruvec->lru_lock); if (list) { /* page reclaim is reclaiming a huge page */ - VM_WARN_ON(PageLRU(head)); + VM_WARN_ON(folio_test_lru(folio)); get_page(tail); list_add_tail(&tail->lru, list); } else { /* head is still on lru (and we have it frozen) */ - VM_WARN_ON(!PageLRU(head)); - if (PageUnevictable(tail)) + VM_WARN_ON(!folio_test_lru(folio)); + if (folio_test_unevictable(folio)) tail->mlock_count = 0; else - list_add_tail(&tail->lru, &head->lru); + list_add_tail(&tail->lru, &folio->lru); SetPageLRU(tail); } } @@ -3049,7 +3049,7 @@ static void __split_huge_page_tail(struct folio *folio, int tail, * pages to show after the currently processed elements - e.g. * migrate_pages */ - lru_add_page_tail(head, page_tail, lruvec, list); + lru_add_page_tail(folio, page_tail, lruvec, list); } static void __split_huge_page(struct page *page, struct list_head *list, -- cgit v1.2.3 From 99f86bbda31790f2ca0e365f02650585536929ab Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 21 Aug 2024 20:34:39 +0100 Subject: mm: remove PageMlocked This flag is now only used on folios, so we can remove all the page accessors. Link: https://lkml.kernel.org/r/20240821193445.2294269-7-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- Documentation/mm/unevictable-lru.rst | 4 ++-- include/linux/page-flags.h | 13 ++++++++----- 2 files changed, 10 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/Documentation/mm/unevictable-lru.rst b/Documentation/mm/unevictable-lru.rst index 2feb2ed51ae2..255ef12a432b 100644 --- a/Documentation/mm/unevictable-lru.rst +++ b/Documentation/mm/unevictable-lru.rst @@ -253,8 +253,8 @@ Basic Management mlocked pages - pages mapped into a VM_LOCKED VMA - are a class of unevictable pages. When such a page has been "noticed" by the memory management subsystem, -the page is marked with the PG_mlocked flag. This can be manipulated using the -PageMlocked() functions. +the folio is marked with the PG_mlocked flag. This can be manipulated using +folio_set_mlocked() and folio_clear_mlocked() functions. A PG_mlocked page will be placed on the unevictable list when it is added to the LRU. Such pages can be "noticed" by memory management in several places: diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 2150502195d5..08cce16c82aa 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -585,12 +585,15 @@ FOLIO_FLAG(unevictable, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(unevictable, FOLIO_HEAD_PAGE) #ifdef CONFIG_MMU -PAGEFLAG(Mlocked, mlocked, PF_NO_TAIL) - __CLEARPAGEFLAG(Mlocked, mlocked, PF_NO_TAIL) - TESTSCFLAG(Mlocked, mlocked, PF_NO_TAIL) +FOLIO_FLAG(mlocked, FOLIO_HEAD_PAGE) + __FOLIO_CLEAR_FLAG(mlocked, FOLIO_HEAD_PAGE) + FOLIO_TEST_CLEAR_FLAG(mlocked, FOLIO_HEAD_PAGE) + FOLIO_TEST_SET_FLAG(mlocked, FOLIO_HEAD_PAGE) #else -PAGEFLAG_FALSE(Mlocked, mlocked) __CLEARPAGEFLAG_NOOP(Mlocked, mlocked) - TESTSCFLAG_FALSE(Mlocked, mlocked) +FOLIO_FLAG_FALSE(mlocked) + __FOLIO_CLEAR_FLAG_NOOP(mlocked) + FOLIO_TEST_CLEAR_FLAG_FALSE(mlocked) + FOLIO_TEST_SET_FLAG_FALSE(mlocked) #endif #ifdef CONFIG_ARCH_USES_PG_UNCACHED -- cgit v1.2.3 From 3026bc1e82b695d69cde21712512922abe74aab9 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 21 Aug 2024 20:34:40 +0100 Subject: mm: remove PageOwnerPriv1 While there are many aliases for this flag, nobody actually uses the *PageOwnerPriv1() nor folio_*_owner_priv_1() accessors. Remove them. Link: https://lkml.kernel.org/r/20240821193445.2294269-8-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/page-flags.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 08cce16c82aa..458d2dc5124d 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -539,8 +539,6 @@ FOLIO_FLAG(swapbacked, FOLIO_HEAD_PAGE) */ PAGEFLAG(Private, private, PF_ANY) PAGEFLAG(Private2, private_2, PF_ANY) TESTSCFLAG(Private2, private_2, PF_ANY) -PAGEFLAG(OwnerPriv1, owner_priv_1, PF_ANY) - TESTCLEARFLAG(OwnerPriv1, owner_priv_1, PF_ANY) /* * Only test-and-set exist for PG_writeback. The unconditional operators are -- cgit v1.2.3 From 6dc151388e44957d471633ce70d72e3d27ae836d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 21 Aug 2024 20:34:41 +0100 Subject: mm: remove page_has_private() This function has no more callers, except folio_has_private(). Combine the two functions. Link: https://lkml.kernel.org/r/20240821193445.2294269-9-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/page-flags.h | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 458d2dc5124d..017205048cab 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -1175,20 +1175,15 @@ static __always_inline void __ClearPageAnonExclusive(struct page *page) #define PAGE_FLAGS_PRIVATE \ (1UL << PG_private | 1UL << PG_private_2) /** - * page_has_private - Determine if page has private stuff - * @page: The page to be checked + * folio_has_private - Determine if folio has private stuff + * @folio: The folio to be checked * - * Determine if a page has private stuff, indicating that release routines + * Determine if a folio has private stuff, indicating that release routines * should be invoked upon it. */ -static inline int page_has_private(const struct page *page) +static inline int folio_has_private(const struct folio *folio) { - return !!(page->flags & PAGE_FLAGS_PRIVATE); -} - -static inline bool folio_has_private(const struct folio *folio) -{ - return page_has_private(&folio->page); + return !!(folio->flags & PAGE_FLAGS_PRIVATE); } #undef PF_ANY -- cgit v1.2.3 From 02e1960aafac33721401dcd92e915325fdb524b2 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 21 Aug 2024 20:34:42 +0100 Subject: mm: rename PG_mappedtodisk to PG_owner_2 This flag has similar constraints to PG_owner_priv_1 -- it is ignored by core code, and is entirely for the use of the code which allocated the folio. Since the pagecache does not use it, individual filesystems can use it. The bufferhead code does use it, so filesystems which use the buffer cache must not use it for another purpose. Link: https://lkml.kernel.org/r/20240821193445.2294269-10-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- fs/proc/page.c | 2 +- include/linux/kernel-page-flags.h | 2 +- include/linux/page-flags.h | 24 ++++++++++++++++-------- include/trace/events/mmflags.h | 2 +- tools/mm/page-types.c | 10 +++++----- 5 files changed, 24 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/page.c b/fs/proc/page.c index 73a0f872d97f..e74e639893be 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -211,7 +211,7 @@ u64 stable_page_flags(const struct page *page) #endif u |= kpf_copy_bit(k, KPF_RESERVED, PG_reserved); - u |= kpf_copy_bit(k, KPF_MAPPEDTODISK, PG_mappedtodisk); + u |= kpf_copy_bit(k, KPF_OWNER_2, PG_owner_2); u |= kpf_copy_bit(k, KPF_PRIVATE, PG_private); u |= kpf_copy_bit(k, KPF_PRIVATE_2, PG_private_2); u |= kpf_copy_bit(k, KPF_OWNER_PRIVATE, PG_owner_priv_1); diff --git a/include/linux/kernel-page-flags.h b/include/linux/kernel-page-flags.h index 859f4b0c1b2b..7c587a711be1 100644 --- a/include/linux/kernel-page-flags.h +++ b/include/linux/kernel-page-flags.h @@ -10,7 +10,7 @@ */ #define KPF_RESERVED 32 #define KPF_MLOCKED 33 -#define KPF_MAPPEDTODISK 34 +#define KPF_OWNER_2 34 #define KPF_PRIVATE 35 #define KPF_PRIVATE_2 36 #define KPF_OWNER_PRIVATE 37 diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 017205048cab..1ff3d172c22c 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -101,12 +101,12 @@ enum pageflags { PG_waiters, /* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */ PG_active, PG_workingset, - PG_owner_priv_1, /* Owner use. If pagecache, fs may use*/ + PG_owner_priv_1, /* Owner use. If pagecache, fs may use */ + PG_owner_2, /* Owner use. If pagecache, fs may use */ PG_arch_1, PG_reserved, PG_private, /* If pagecache, has fs-private data */ PG_private_2, /* If pagecache, has fs aux data */ - PG_mappedtodisk, /* Has blocks allocated on-disk */ PG_reclaim, /* To be reclaimed asap */ PG_swapbacked, /* Page is backed by RAM/swap */ PG_unevictable, /* Page is "unevictable" */ @@ -131,6 +131,11 @@ enum pageflags { PG_readahead = PG_reclaim, + /* Anonymous memory (and shmem) */ + PG_swapcache = PG_owner_priv_1, /* Swap page: swp_entry_t in private */ + /* Some filesystems */ + PG_checked = PG_owner_priv_1, + /* * Depending on the way an anonymous folio can be mapped into a page * table (e.g., single PMD/PUD/CONT of the head page vs. PTE-mapped @@ -138,13 +143,13 @@ enum pageflags { * tail pages of an anonymous folio. For now, we only expect it to be * set on tail pages for PTE-mapped THP. */ - PG_anon_exclusive = PG_mappedtodisk, - - /* Filesystems */ - PG_checked = PG_owner_priv_1, + PG_anon_exclusive = PG_owner_2, - /* SwapBacked */ - PG_swapcache = PG_owner_priv_1, /* Swap page: swp_entry_t in private */ + /* + * Set if all buffer heads in the folio are mapped. + * Filesystems which do not use BHs can use it for their own purpose. + */ + PG_mappedtodisk = PG_owner_2, /* Two page bits are conscripted by FS-Cache to maintain local caching * state. These bits are set on pages belonging to the netfs's inodes @@ -540,6 +545,9 @@ FOLIO_FLAG(swapbacked, FOLIO_HEAD_PAGE) PAGEFLAG(Private, private, PF_ANY) PAGEFLAG(Private2, private_2, PF_ANY) TESTSCFLAG(Private2, private_2, PF_ANY) +/* owner_2 can be set on tail pages for anon memory */ +FOLIO_FLAG(owner_2, FOLIO_HEAD_PAGE) + /* * Only test-and-set exist for PG_writeback. The unconditional operators are * risky: they bypass page accounting. diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index c151cc21d367..3b51558cdc9b 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -107,13 +107,13 @@ DEF_PAGEFLAG_NAME(active), \ DEF_PAGEFLAG_NAME(workingset), \ DEF_PAGEFLAG_NAME(owner_priv_1), \ + DEF_PAGEFLAG_NAME(owner_2), \ DEF_PAGEFLAG_NAME(arch_1), \ DEF_PAGEFLAG_NAME(reserved), \ DEF_PAGEFLAG_NAME(private), \ DEF_PAGEFLAG_NAME(private_2), \ DEF_PAGEFLAG_NAME(writeback), \ DEF_PAGEFLAG_NAME(head), \ - DEF_PAGEFLAG_NAME(mappedtodisk), \ DEF_PAGEFLAG_NAME(reclaim), \ DEF_PAGEFLAG_NAME(swapbacked), \ DEF_PAGEFLAG_NAME(unevictable) \ diff --git a/tools/mm/page-types.c b/tools/mm/page-types.c index 8d5595b6c59f..8ca41c41105e 100644 --- a/tools/mm/page-types.c +++ b/tools/mm/page-types.c @@ -71,7 +71,7 @@ /* [32-] kernel hacking assistances */ #define KPF_RESERVED 32 #define KPF_MLOCKED 33 -#define KPF_MAPPEDTODISK 34 +#define KPF_OWNER_2 34 #define KPF_PRIVATE 35 #define KPF_PRIVATE_2 36 #define KPF_OWNER_PRIVATE 37 @@ -129,7 +129,7 @@ static const char * const page_flag_names[] = { [KPF_RESERVED] = "r:reserved", [KPF_MLOCKED] = "m:mlocked", - [KPF_MAPPEDTODISK] = "d:mappedtodisk", + [KPF_OWNER_2] = "d:owner_2", [KPF_PRIVATE] = "P:private", [KPF_PRIVATE_2] = "p:private_2", [KPF_OWNER_PRIVATE] = "O:owner_private", @@ -472,9 +472,9 @@ static int bit_mask_ok(uint64_t flags) static uint64_t expand_overloaded_flags(uint64_t flags, uint64_t pme) { - /* Anonymous pages overload PG_mappedtodisk */ - if ((flags & BIT(ANON)) && (flags & BIT(MAPPEDTODISK))) - flags ^= BIT(MAPPEDTODISK) | BIT(ANON_EXCLUSIVE); + /* Anonymous pages use PG_owner_2 for anon_exclusive */ + if ((flags & BIT(ANON)) && (flags & BIT(OWNER_2))) + flags ^= BIT(OWNER_2) | BIT(ANON_EXCLUSIVE); /* SLUB overloads several page flags */ if (flags & BIT(SLAB)) { -- cgit v1.2.3 From 7a87225ae2c6c317c7b80cf599e5cf0eee699196 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 21 Aug 2024 20:34:43 +0100 Subject: x86: remove PG_uncached Convert x86 to use PG_arch_2 instead of PG_uncached and remove PG_uncached. Link: https://lkml.kernel.org/r/20240821193445.2294269-11-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- .../features/vm/PG_uncached/arch-support.txt | 30 ---------------------- arch/arm64/Kconfig | 3 ++- arch/x86/Kconfig | 5 +--- arch/x86/mm/pat/memtype.c | 8 +++--- fs/proc/page.c | 8 +++--- include/linux/kernel-page-flags.h | 1 - include/linux/page-flags.h | 13 +++------- include/trace/events/mmflags.h | 23 ++++++++--------- mm/Kconfig | 9 +++---- mm/huge_memory.c | 4 ++- tools/mm/page-types.c | 3 +-- 11 files changed, 31 insertions(+), 76 deletions(-) delete mode 100644 Documentation/features/vm/PG_uncached/arch-support.txt (limited to 'include/linux') diff --git a/Documentation/features/vm/PG_uncached/arch-support.txt b/Documentation/features/vm/PG_uncached/arch-support.txt deleted file mode 100644 index 5a7508b8c967..000000000000 --- a/Documentation/features/vm/PG_uncached/arch-support.txt +++ /dev/null @@ -1,30 +0,0 @@ -# -# Feature name: PG_uncached -# Kconfig: ARCH_USES_PG_UNCACHED -# description: arch supports the PG_uncached page flag -# - ----------------------- - | arch |status| - ----------------------- - | alpha: | TODO | - | arc: | TODO | - | arm: | TODO | - | arm64: | TODO | - | csky: | TODO | - | hexagon: | TODO | - | loongarch: | TODO | - | m68k: | TODO | - | microblaze: | TODO | - | mips: | TODO | - | nios2: | TODO | - | openrisc: | TODO | - | parisc: | TODO | - | powerpc: | TODO | - | riscv: | TODO | - | s390: | TODO | - | sh: | TODO | - | sparc: | TODO | - | um: | TODO | - | x86: | ok | - | xtensa: | TODO | - ----------------------- diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index a2f8ff354ca6..6494848019a0 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -2100,7 +2100,8 @@ config ARM64_MTE depends on ARM64_PAN select ARCH_HAS_SUBPAGE_FAULTS select ARCH_USES_HIGH_VMA_FLAGS - select ARCH_USES_PG_ARCH_X + select ARCH_USES_PG_ARCH_2 + select ARCH_USES_PG_ARCH_3 help Memory Tagging (part of the ARMv8.5 Extensions) provides architectural support for run-time, always-on detection of diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index acd9745bf2ae..b74b9ee484da 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1799,6 +1799,7 @@ config X86_PAT def_bool y prompt "x86 PAT support" if EXPERT depends on MTRR + select ARCH_USES_PG_ARCH_2 help Use PAT attributes to setup page level cache control. @@ -1810,10 +1811,6 @@ config X86_PAT If unsure, say Y. -config ARCH_USES_PG_UNCACHED - def_bool y - depends on X86_PAT - config X86_UMIP def_bool y prompt "User Mode Instruction Prevention" if EXPERT diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index bdc2a240c2aa..1fa0bf6ed295 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -104,7 +104,7 @@ __setup("debugpat", pat_debug_setup); #ifdef CONFIG_X86_PAT /* - * X86 PAT uses page flags arch_1 and uncached together to keep track of + * X86 PAT uses page flags arch_1 and arch_2 together to keep track of * memory type of pages that have backing page struct. * * X86 PAT supports 4 different memory types: @@ -118,9 +118,9 @@ __setup("debugpat", pat_debug_setup); #define _PGMT_WB 0 #define _PGMT_WC (1UL << PG_arch_1) -#define _PGMT_UC_MINUS (1UL << PG_uncached) -#define _PGMT_WT (1UL << PG_uncached | 1UL << PG_arch_1) -#define _PGMT_MASK (1UL << PG_uncached | 1UL << PG_arch_1) +#define _PGMT_UC_MINUS (1UL << PG_arch_2) +#define _PGMT_WT (1UL << PG_arch_2 | 1UL << PG_arch_1) +#define _PGMT_MASK (1UL << PG_arch_2 | 1UL << PG_arch_1) #define _PGMT_CLEAR_MASK (~_PGMT_MASK) static inline enum page_cache_mode get_page_memtype(struct page *pg) diff --git a/fs/proc/page.c b/fs/proc/page.c index e74e639893be..a55f5acefa97 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -206,18 +206,16 @@ u64 stable_page_flags(const struct page *page) u |= kpf_copy_bit(page->flags, KPF_HWPOISON, PG_hwpoison); #endif -#ifdef CONFIG_ARCH_USES_PG_UNCACHED - u |= kpf_copy_bit(k, KPF_UNCACHED, PG_uncached); -#endif - u |= kpf_copy_bit(k, KPF_RESERVED, PG_reserved); u |= kpf_copy_bit(k, KPF_OWNER_2, PG_owner_2); u |= kpf_copy_bit(k, KPF_PRIVATE, PG_private); u |= kpf_copy_bit(k, KPF_PRIVATE_2, PG_private_2); u |= kpf_copy_bit(k, KPF_OWNER_PRIVATE, PG_owner_priv_1); u |= kpf_copy_bit(k, KPF_ARCH, PG_arch_1); -#ifdef CONFIG_ARCH_USES_PG_ARCH_X +#ifdef CONFIG_ARCH_USES_PG_ARCH_2 u |= kpf_copy_bit(k, KPF_ARCH_2, PG_arch_2); +#endif +#ifdef CONFIG_ARCH_USES_PG_ARCH_3 u |= kpf_copy_bit(k, KPF_ARCH_3, PG_arch_3); #endif diff --git a/include/linux/kernel-page-flags.h b/include/linux/kernel-page-flags.h index 7c587a711be1..196778a087c4 100644 --- a/include/linux/kernel-page-flags.h +++ b/include/linux/kernel-page-flags.h @@ -15,7 +15,6 @@ #define KPF_PRIVATE_2 36 #define KPF_OWNER_PRIVATE 37 #define KPF_ARCH 38 -#define KPF_UNCACHED 39 #define KPF_SOFTDIRTY 40 #define KPF_ARCH_2 41 #define KPF_ARCH_3 42 diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 1ff3d172c22c..2175ebceb41c 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -113,9 +113,6 @@ enum pageflags { #ifdef CONFIG_MMU PG_mlocked, /* Page is vma mlocked */ #endif -#ifdef CONFIG_ARCH_USES_PG_UNCACHED - PG_uncached, /* Page has been mapped as uncached */ -#endif #ifdef CONFIG_MEMORY_FAILURE PG_hwpoison, /* hardware poisoned page. Don't touch */ #endif @@ -123,8 +120,10 @@ enum pageflags { PG_young, PG_idle, #endif -#ifdef CONFIG_ARCH_USES_PG_ARCH_X +#ifdef CONFIG_ARCH_USES_PG_ARCH_2 PG_arch_2, +#endif +#ifdef CONFIG_ARCH_USES_PG_ARCH_3 PG_arch_3, #endif __NR_PAGEFLAGS, @@ -602,12 +601,6 @@ FOLIO_FLAG_FALSE(mlocked) FOLIO_TEST_SET_FLAG_FALSE(mlocked) #endif -#ifdef CONFIG_ARCH_USES_PG_UNCACHED -PAGEFLAG(Uncached, uncached, PF_NO_COMPOUND) -#else -PAGEFLAG_FALSE(Uncached, uncached) -#endif - #ifdef CONFIG_MEMORY_FAILURE PAGEFLAG(HWPoison, hwpoison, PF_ANY) TESTSCFLAG(HWPoison, hwpoison, PF_ANY) diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index 3b51558cdc9b..58f2699331b6 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -71,12 +71,6 @@ #define IF_HAVE_PG_MLOCK(_name) #endif -#ifdef CONFIG_ARCH_USES_PG_UNCACHED -#define IF_HAVE_PG_UNCACHED(_name) ,{1UL << PG_##_name, __stringify(_name)} -#else -#define IF_HAVE_PG_UNCACHED(_name) -#endif - #ifdef CONFIG_MEMORY_FAILURE #define IF_HAVE_PG_HWPOISON(_name) ,{1UL << PG_##_name, __stringify(_name)} #else @@ -89,10 +83,16 @@ #define IF_HAVE_PG_IDLE(_name) #endif -#ifdef CONFIG_ARCH_USES_PG_ARCH_X -#define IF_HAVE_PG_ARCH_X(_name) ,{1UL << PG_##_name, __stringify(_name)} +#ifdef CONFIG_ARCH_USES_PG_ARCH_2 +#define IF_HAVE_PG_ARCH_2(_name) ,{1UL << PG_##_name, __stringify(_name)} +#else +#define IF_HAVE_PG_ARCH_2(_name) +#endif + +#ifdef CONFIG_ARCH_USES_PG_ARCH_3 +#define IF_HAVE_PG_ARCH_3(_name) ,{1UL << PG_##_name, __stringify(_name)} #else -#define IF_HAVE_PG_ARCH_X(_name) +#define IF_HAVE_PG_ARCH_3(_name) #endif #define DEF_PAGEFLAG_NAME(_name) { 1UL << PG_##_name, __stringify(_name) } @@ -118,12 +118,11 @@ DEF_PAGEFLAG_NAME(swapbacked), \ DEF_PAGEFLAG_NAME(unevictable) \ IF_HAVE_PG_MLOCK(mlocked) \ -IF_HAVE_PG_UNCACHED(uncached) \ IF_HAVE_PG_HWPOISON(hwpoison) \ IF_HAVE_PG_IDLE(idle) \ IF_HAVE_PG_IDLE(young) \ -IF_HAVE_PG_ARCH_X(arch_2) \ -IF_HAVE_PG_ARCH_X(arch_3) +IF_HAVE_PG_ARCH_2(arch_2) \ +IF_HAVE_PG_ARCH_3(arch_3) #define show_page_flags(flags) \ (flags) ? __print_flags(flags, "|", \ diff --git a/mm/Kconfig b/mm/Kconfig index 5946dcdcaeda..8078a4b3c509 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -1079,13 +1079,10 @@ config ARCH_USES_HIGH_VMA_FLAGS config ARCH_HAS_PKEYS bool -config ARCH_USES_PG_ARCH_X +config ARCH_USES_PG_ARCH_2 + bool +config ARCH_USES_PG_ARCH_3 bool - help - Enable the definition of PG_arch_x page flags with x > 1. Only - suitable for 64-bit architectures with CONFIG_FLATMEM or - CONFIG_SPARSEMEM_VMEMMAP enabled, otherwise there may not be - enough room for additional bits in page->flags. config VM_EVENT_COUNTERS default y diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 8dfb912ebdaa..c4b45ad576f6 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2993,8 +2993,10 @@ static void __split_huge_page_tail(struct folio *folio, int tail, (1L << PG_workingset) | (1L << PG_locked) | (1L << PG_unevictable) | -#ifdef CONFIG_ARCH_USES_PG_ARCH_X +#ifdef CONFIG_ARCH_USES_PG_ARCH_2 (1L << PG_arch_2) | +#endif +#ifdef CONFIG_ARCH_USES_PG_ARCH_3 (1L << PG_arch_3) | #endif (1L << PG_dirty) | diff --git a/tools/mm/page-types.c b/tools/mm/page-types.c index 8ca41c41105e..fa050d5a48cd 100644 --- a/tools/mm/page-types.c +++ b/tools/mm/page-types.c @@ -76,7 +76,7 @@ #define KPF_PRIVATE_2 36 #define KPF_OWNER_PRIVATE 37 #define KPF_ARCH 38 -#define KPF_UNCACHED 39 +#define KPF_UNCACHED 39 /* unused */ #define KPF_SOFTDIRTY 40 #define KPF_ARCH_2 41 @@ -134,7 +134,6 @@ static const char * const page_flag_names[] = { [KPF_PRIVATE_2] = "p:private_2", [KPF_OWNER_PRIVATE] = "O:owner_private", [KPF_ARCH] = "h:arch", - [KPF_UNCACHED] = "c:uncached", [KPF_SOFTDIRTY] = "f:softdirty", [KPF_ARCH_2] = "H:arch_2", -- cgit v1.2.3 From 0ca0c24e3211586d44a31b3c4767fe3f43a008a7 Mon Sep 17 00:00:00 2001 From: Usama Arif Date: Fri, 23 Aug 2024 20:04:39 +0100 Subject: mm: store zero pages to be swapped out in a bitmap Patch series "mm: store zero pages to be swapped out in a bitmap", v8. As shown in the patch series that introduced the zswap same-filled optimization [1], 10-20% of the pages stored in zswap are same-filled. This is also observed across Meta's server fleet. By using VM counters in swap_writepage (not included in this patchseries) it was found that less than 1% of the same-filled pages to be swapped out are non-zero pages. For conventional swap setup (without zswap), rather than reading/writing these pages to flash resulting in increased I/O and flash wear, a bitmap can be used to mark these pages as zero at write time, and the pages can be filled at read time if the bit corresponding to the page is set. When using zswap with swap, this also means that a zswap_entry does not need to be allocated for zero filled pages resulting in memory savings which would offset the memory used for the bitmap. A similar attempt was made earlier in [2] where zswap would only track zero-filled pages instead of same-filled. This patchseries adds zero-filled pages optimization to swap (hence it can be used even if zswap is disabled) and removes the same-filled code from zswap (as only 1% of the same-filled pages are non-zero), simplifying code. [1] https://lore.kernel.org/all/20171018104832epcms5p1b2232e2236258de3d03d1344dde9fce0@epcms5p1/ [2] https://lore.kernel.org/lkml/20240325235018.2028408-1-yosryahmed@google.com/ This patch (of 2): Approximately 10-20% of pages to be swapped out are zero pages [1]. Rather than reading/writing these pages to flash resulting in increased I/O and flash wear, a bitmap can be used to mark these pages as zero at write time, and the pages can be filled at read time if the bit corresponding to the page is set. With this patch, NVMe writes in Meta server fleet decreased by almost 10% with conventional swap setup (zswap disabled). [1] https://lore.kernel.org/all/20171018104832epcms5p1b2232e2236258de3d03d1344dde9fce0@epcms5p1/ Link: https://lkml.kernel.org/r/20240823190545.979059-1-usamaarif642@gmail.com Link: https://lkml.kernel.org/r/20240823190545.979059-2-usamaarif642@gmail.com Signed-off-by: Usama Arif Reviewed-by: Chengming Zhou Reviewed-by: Yosry Ahmed Reviewed-by: Nhat Pham Acked-by: Johannes Weiner Cc: David Hildenbrand Cc: Hugh Dickins Cc: Matthew Wilcox (Oracle) Cc: Shakeel Butt Cc: Usama Arif Cc: Andi Kleen Signed-off-by: Andrew Morton --- include/linux/swap.h | 1 + mm/page_io.c | 118 ++++++++++++++++++++++++++++++++++++++++++++++++++- mm/swapfile.c | 38 ++++++++++++++--- 3 files changed, 151 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 248db1dd7812..ca533b478c21 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -296,6 +296,7 @@ struct swap_info_struct { signed char type; /* strange name for an index */ unsigned int max; /* extent of the swap_map */ unsigned char *swap_map; /* vmalloc'ed array of usage counts */ + unsigned long *zeromap; /* kvmalloc'ed bitmap to track zero pages */ struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */ struct list_head free_clusters; /* free clusters list */ struct list_head full_clusters; /* full clusters list */ diff --git a/mm/page_io.c b/mm/page_io.c index a00e2f615118..b6f1519d63b0 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -172,6 +172,80 @@ bad_bmap: goto out; } +static bool is_folio_zero_filled(struct folio *folio) +{ + unsigned int pos, last_pos; + unsigned long *data; + unsigned int i; + + last_pos = PAGE_SIZE / sizeof(*data) - 1; + for (i = 0; i < folio_nr_pages(folio); i++) { + data = kmap_local_folio(folio, i * PAGE_SIZE); + /* + * Check last word first, incase the page is zero-filled at + * the start and has non-zero data at the end, which is common + * in real-world workloads. + */ + if (data[last_pos]) { + kunmap_local(data); + return false; + } + for (pos = 0; pos < last_pos; pos++) { + if (data[pos]) { + kunmap_local(data); + return false; + } + } + kunmap_local(data); + } + + return true; +} + +static void swap_zeromap_folio_set(struct folio *folio) +{ + struct swap_info_struct *sis = swp_swap_info(folio->swap); + swp_entry_t entry; + unsigned int i; + + for (i = 0; i < folio_nr_pages(folio); i++) { + entry = page_swap_entry(folio_page(folio, i)); + set_bit(swp_offset(entry), sis->zeromap); + } +} + +static void swap_zeromap_folio_clear(struct folio *folio) +{ + struct swap_info_struct *sis = swp_swap_info(folio->swap); + swp_entry_t entry; + unsigned int i; + + for (i = 0; i < folio_nr_pages(folio); i++) { + entry = page_swap_entry(folio_page(folio, i)); + clear_bit(swp_offset(entry), sis->zeromap); + } +} + +/* + * Return the index of the first subpage which is not zero-filled + * according to swap_info_struct->zeromap. + * If all pages are zero-filled according to zeromap, it will return + * folio_nr_pages(folio). + */ +static unsigned int swap_zeromap_folio_test(struct folio *folio) +{ + struct swap_info_struct *sis = swp_swap_info(folio->swap); + swp_entry_t entry; + unsigned int i; + + for (i = 0; i < folio_nr_pages(folio); i++) { + entry = page_swap_entry(folio_page(folio, i)); + if (!test_bit(swp_offset(entry), sis->zeromap)) + return i; + } + return i; +} + /* * We may have stale swap cache pages in memory: notice * them here and get rid of the unnecessary final write. @@ -195,6 +269,25 @@ int swap_writepage(struct page *page, struct writeback_control *wbc) folio_unlock(folio); return ret; } + + /* + * Use a bitmap (zeromap) to avoid doing IO for zero-filled pages. + * The bits in zeromap are protected by the locked swapcache folio + * and atomic updates are used to protect against read-modify-write + * corruption due to other zero swap entries seeing concurrent updates. + */ + if (is_folio_zero_filled(folio)) { + swap_zeromap_folio_set(folio); + folio_unlock(folio); + return 0; + } else { + /* + * Clear bits this folio occupies in the zeromap to prevent + * zero data being read in from any previous zero writes that + * occupied the same swap entries. + */ + swap_zeromap_folio_clear(folio); + } if (zswap_store(folio)) { folio_unlock(folio); return 0; @@ -427,6 +520,26 @@ static void sio_read_complete(struct kiocb *iocb, long ret) mempool_free(sio, sio_pool); } +static bool swap_read_folio_zeromap(struct folio *folio) +{ + unsigned int idx = swap_zeromap_folio_test(folio); + + if (idx == 0) + return false; + + /* + * Swapping in a large folio that is partially in the zeromap is not + * currently handled. Return true without marking the folio uptodate so + * that an IO error is emitted (e.g. do_swap_page() will sigbus). + */ + if (WARN_ON_ONCE(idx < folio_nr_pages(folio))) + return true; + + folio_zero_range(folio, 0, folio_size(folio)); + folio_mark_uptodate(folio); + return true; +} + static void swap_read_folio_fs(struct folio *folio, struct swap_iocb **plug) { struct swap_info_struct *sis = swp_swap_info(folio->swap); @@ -517,7 +630,10 @@ void swap_read_folio(struct folio *folio, struct swap_iocb **plug) } delayacct_swapin_start(); - if (zswap_load(folio)) { + if (swap_read_folio_zeromap(folio)) { + folio_unlock(folio); + goto finish; + } else if (zswap_load(folio)) { folio_unlock(folio); goto finish; } diff --git a/mm/swapfile.c b/mm/swapfile.c index 03dc77457510..8e317c495bfb 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -940,6 +940,14 @@ static void swap_range_free(struct swap_info_struct *si, unsigned long offset, unsigned long begin = offset; unsigned long end = offset + nr_entries - 1; void (*swap_slot_free_notify)(struct block_device *, unsigned long); + unsigned int i; + + /* + * Use atomic clear_bit operations only on zeromap instead of non-atomic + * bitmap_clear to prevent adjacent bits corruption due to simultaneous writes. + */ + for (i = 0; i < nr_entries; i++) + clear_bit(offset + i, si->zeromap); if (offset < si->lowest_bit) si->lowest_bit = offset; @@ -2609,7 +2617,8 @@ static int swap_node(struct swap_info_struct *si) static void setup_swap_info(struct swap_info_struct *si, int prio, unsigned char *swap_map, - struct swap_cluster_info *cluster_info) + struct swap_cluster_info *cluster_info, + unsigned long *zeromap) { int i; @@ -2634,6 +2643,7 @@ static void setup_swap_info(struct swap_info_struct *si, int prio, } si->swap_map = swap_map; si->cluster_info = cluster_info; + si->zeromap = zeromap; } static void _enable_swap_info(struct swap_info_struct *si) @@ -2662,11 +2672,12 @@ static void _enable_swap_info(struct swap_info_struct *si) static void enable_swap_info(struct swap_info_struct *si, int prio, unsigned char *swap_map, - struct swap_cluster_info *cluster_info) + struct swap_cluster_info *cluster_info, + unsigned long *zeromap) { spin_lock(&swap_lock); spin_lock(&si->lock); - setup_swap_info(si, prio, swap_map, cluster_info); + setup_swap_info(si, prio, swap_map, cluster_info, zeromap); spin_unlock(&si->lock); spin_unlock(&swap_lock); /* @@ -2684,7 +2695,7 @@ static void reinsert_swap_info(struct swap_info_struct *si) { spin_lock(&swap_lock); spin_lock(&si->lock); - setup_swap_info(si, si->prio, si->swap_map, si->cluster_info); + setup_swap_info(si, si->prio, si->swap_map, si->cluster_info, si->zeromap); _enable_swap_info(si); spin_unlock(&si->lock); spin_unlock(&swap_lock); @@ -2709,6 +2720,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) { struct swap_info_struct *p = NULL; unsigned char *swap_map; + unsigned long *zeromap; struct swap_cluster_info *cluster_info; struct file *swap_file, *victim; struct address_space *mapping; @@ -2831,6 +2843,8 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) p->max = 0; swap_map = p->swap_map; p->swap_map = NULL; + zeromap = p->zeromap; + p->zeromap = NULL; cluster_info = p->cluster_info; p->cluster_info = NULL; spin_unlock(&p->lock); @@ -2843,6 +2857,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) free_percpu(p->cluster_next_cpu); p->cluster_next_cpu = NULL; vfree(swap_map); + kvfree(zeromap); kvfree(cluster_info); /* Destroy swap account information */ swap_cgroup_swapoff(p->type); @@ -3340,6 +3355,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) sector_t span; unsigned long maxpages; unsigned char *swap_map = NULL; + unsigned long *zeromap = NULL; struct swap_cluster_info *cluster_info = NULL; struct page *page = NULL; struct inode *inode = NULL; @@ -3430,6 +3446,17 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) goto bad_swap_unlock_inode; } + /* + * Use kvmalloc_array instead of bitmap_zalloc as the allocation order might + * be above MAX_PAGE_ORDER incase of a large swap file. + */ + zeromap = kvmalloc_array(BITS_TO_LONGS(maxpages), sizeof(long), + GFP_KERNEL | __GFP_ZERO); + if (!zeromap) { + error = -ENOMEM; + goto bad_swap_unlock_inode; + } + if (si->bdev && bdev_stable_writes(si->bdev)) si->flags |= SWP_STABLE_WRITES; @@ -3505,7 +3532,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) if (swap_flags & SWAP_FLAG_PREFER) prio = (swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT; - enable_swap_info(si, prio, swap_map, cluster_info); + enable_swap_info(si, prio, swap_map, cluster_info, zeromap); pr_info("Adding %uk swap on %s. Priority:%d extents:%d across:%lluk %s%s%s%s\n", K(si->pages), name->name, si->prio, nr_extents, @@ -3540,6 +3567,7 @@ bad_swap: si->flags = 0; spin_unlock(&swap_lock); vfree(swap_map); + kvfree(zeromap); kvfree(cluster_info); if (inced_nr_rotate_swap) atomic_dec(&nr_rotate_swap); -- cgit v1.2.3 From 63fc66f5b6b18f39269a66cf34d8cb7a24fbfe88 Mon Sep 17 00:00:00 2001 From: "Liam R. Howlett" Date: Fri, 30 Aug 2024 00:00:58 -0400 Subject: ipc/shm, mm: drop do_vma_munmap() The do_vma_munmap() wrapper existed for callers that didn't have a vma iterator and needed to check the vma mseal status prior to calling the underlying munmap(). All callers now use a vma iterator and since the mseal check has been moved to do_vmi_align_munmap() and the vmas are aligned, this function can just be called instead. do_vmi_align_munmap() can no longer be static as ipc/shm is using it and it is exported via the mm.h header. Link: https://lkml.kernel.org/r/20240830040101.822209-19-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Reviewed-by: Lorenzo Stoakes Cc: Bert Karwatzki Cc: Jeff Xu Cc: Jiri Olsa Cc: Kees Cook Cc: Lorenzo Stoakes Cc: Mark Brown Cc: Matthew Wilcox Cc: "Paul E. McKenney" Cc: Paul Moore Cc: Sidhartha Kumar Cc: Suren Baghdasaryan Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/mm.h | 6 +++--- ipc/shm.c | 8 ++++---- mm/mmap.c | 33 ++++++--------------------------- mm/vma.c | 12 ++++++------ mm/vma.h | 4 +--- 5 files changed, 20 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 6f6053d7ea6f..b0ff06d18c71 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3287,14 +3287,14 @@ extern unsigned long do_mmap(struct file *file, unsigned long addr, extern int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf, bool unlock); +int do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, + struct mm_struct *mm, unsigned long start, + unsigned long end, struct list_head *uf, bool unlock); extern int do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf); extern int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior); #ifdef CONFIG_MMU -extern int do_vma_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, - unsigned long start, unsigned long end, - struct list_head *uf, bool unlock); extern int __mm_populate(unsigned long addr, unsigned long len, int ignore_errors); static inline void mm_populate(unsigned long addr, unsigned long len) diff --git a/ipc/shm.c b/ipc/shm.c index 3e3071252dac..99564c870084 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -1778,8 +1778,8 @@ long ksys_shmdt(char __user *shmaddr) */ file = vma->vm_file; size = i_size_read(file_inode(vma->vm_file)); - do_vma_munmap(&vmi, vma, vma->vm_start, vma->vm_end, - NULL, false); + do_vmi_align_munmap(&vmi, vma, mm, vma->vm_start, + vma->vm_end, NULL, false); /* * We discovered the size of the shm segment, so * break out of here and fall through to the next @@ -1803,8 +1803,8 @@ long ksys_shmdt(char __user *shmaddr) if ((vma->vm_ops == &shm_vm_ops) && ((vma->vm_start - addr)/PAGE_SIZE == vma->vm_pgoff) && (vma->vm_file == file)) { - do_vma_munmap(&vmi, vma, vma->vm_start, vma->vm_end, - NULL, false); + do_vmi_align_munmap(&vmi, vma, mm, vma->vm_start, + vma->vm_end, NULL, false); } vma = vma_next(&vmi); diff --git a/mm/mmap.c b/mm/mmap.c index 4faadc54e89d..6485f2300692 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -169,11 +169,12 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) goto out; /* mapping intersects with an existing non-brk vma. */ /* * mm->brk must be protected by write mmap_lock. - * do_vma_munmap() will drop the lock on success, so update it - * before calling do_vma_munmap(). + * do_vmi_align_munmap() will drop the lock on success, so + * update it before calling do_vma_munmap(). */ mm->brk = brk; - if (do_vma_munmap(&vmi, brkvma, newbrk, oldbrk, &uf, true)) + if (do_vmi_align_munmap(&vmi, brkvma, mm, newbrk, oldbrk, &uf, + /* unlock = */ true)) goto out; goto success_unlocked; @@ -1479,9 +1480,9 @@ cannot_expand: vma->vm_file = get_file(file); /* * call_mmap() may map PTE, so ensure there are no existing PTEs - * call the vm_ops close function if one exists. + * and call the vm_ops close function if one exists. */ - vms_clean_up_area(&vms, &mas_detach, true); + vms_clean_up_area(&vms, &mas_detach); error = call_mmap(file, vma); if (error) goto unmap_and_free_vma; @@ -1744,28 +1745,6 @@ out: return ret; } -/* - * do_vma_munmap() - Unmap a full or partial vma. - * @vmi: The vma iterator pointing at the vma - * @vma: The first vma to be munmapped - * @start: the start of the address to unmap - * @end: The end of the address to unmap - * @uf: The userfaultfd list_head - * @unlock: Drop the lock on success - * - * unmaps a VMA mapping when the vma iterator is already in position. - * Does not handle alignment. - * - * Return: 0 on success drops the lock of so directed, error on failure and will - * still hold the lock. - */ -int do_vma_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, - unsigned long start, unsigned long end, struct list_head *uf, - bool unlock) -{ - return do_vmi_align_munmap(vmi, vma, vma->vm_mm, start, end, uf, unlock); -} - /* * do_brk_flags() - Increase the brk vma if the flags match. * @vmi: The vma iterator diff --git a/mm/vma.c b/mm/vma.c index d2d71d659d1e..713b2196d351 100644 --- a/mm/vma.c +++ b/mm/vma.c @@ -658,8 +658,8 @@ static inline void vms_clear_ptes(struct vma_munmap_struct *vms, */ mas_set(mas_detach, 1); lru_add_drain(); - tlb_gather_mmu(&tlb, vms->mm); - update_hiwater_rss(vms->mm); + tlb_gather_mmu(&tlb, vms->vma->vm_mm); + update_hiwater_rss(vms->vma->vm_mm); unmap_vmas(&tlb, mas_detach, vms->vma, vms->start, vms->end, vms->vma_count, mm_wr_locked); @@ -672,14 +672,14 @@ static inline void vms_clear_ptes(struct vma_munmap_struct *vms, } void vms_clean_up_area(struct vma_munmap_struct *vms, - struct ma_state *mas_detach, bool mm_wr_locked) + struct ma_state *mas_detach) { struct vm_area_struct *vma; if (!vms->nr_pages) return; - vms_clear_ptes(vms, mas_detach, mm_wr_locked); + vms_clear_ptes(vms, mas_detach, true); mas_set(mas_detach, 0); mas_for_each(mas_detach, vma, ULONG_MAX) if (vma->vm_ops && vma->vm_ops->close) @@ -702,7 +702,7 @@ void vms_complete_munmap_vmas(struct vma_munmap_struct *vms, struct vm_area_struct *vma; struct mm_struct *mm; - mm = vms->mm; + mm = current->mm; mm->map_count -= vms->vma_count; mm->locked_vm -= vms->locked_vm; if (vms->unlock) @@ -770,7 +770,7 @@ int vms_gather_munmap_vmas(struct vma_munmap_struct *vms, * its limit temporarily, to help free resources as expected. */ if (vms->end < vms->vma->vm_end && - vms->mm->map_count >= sysctl_max_map_count) + vms->vma->vm_mm->map_count >= sysctl_max_map_count) goto map_count_exceeded; /* Don't bother splitting the VMA if we can't unmap it anyway */ diff --git a/mm/vma.h b/mm/vma.h index 37b4b5d00b99..b59d470cc223 100644 --- a/mm/vma.h +++ b/mm/vma.h @@ -31,7 +31,6 @@ struct unlink_vma_file_batch { */ struct vma_munmap_struct { struct vma_iterator *vmi; - struct mm_struct *mm; struct vm_area_struct *vma; /* The first vma to munmap */ struct vm_area_struct *prev; /* vma before the munmap area */ struct vm_area_struct *next; /* vma after the munmap area */ @@ -114,7 +113,6 @@ static inline void init_vma_munmap(struct vma_munmap_struct *vms, unsigned long start, unsigned long end, struct list_head *uf, bool unlock) { - vms->mm = current->mm; vms->vmi = vmi; vms->vma = vma; if (vma) { @@ -142,7 +140,7 @@ void vms_complete_munmap_vmas(struct vma_munmap_struct *vms, struct ma_state *mas_detach); void vms_clean_up_area(struct vma_munmap_struct *vms, - struct ma_state *mas_detach, bool mm_wr_locked); + struct ma_state *mas_detach); /* * reattach_vmas() - Undo any munmap work and free resources -- cgit v1.2.3 From f1264e9531b0fbadf88e0b9c8143c546343b481c Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Tue, 27 Aug 2024 19:47:27 +0800 Subject: mm: migrate: add isolate_folio_to_list() Add isolate_folio_to_list() helper to try to isolate HugeTLB, no-LRU movable and LRU folios to a list, which will be reused by do_migrate_range() from memory hotplug soon, also drop the mf_isolate_folio() since we could directly use new helper in the soft_offline_in_use_page(). Link: https://lkml.kernel.org/r/20240827114728.3212578-5-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Acked-by: David Hildenbrand Acked-by: Miaohe Lin Tested-by: Miaohe Lin Cc: Dan Carpenter Cc: Jonathan Cameron Cc: Naoya Horiguchi Cc: Oscar Salvador Signed-off-by: Andrew Morton --- include/linux/migrate.h | 3 +++ mm/memory-failure.c | 48 +++++++++++++----------------------------------- mm/migrate.c | 26 ++++++++++++++++++++++++++ 3 files changed, 42 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 644be30b69c8..002e49b2ebd9 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -70,6 +70,7 @@ int migrate_pages(struct list_head *l, new_folio_t new, free_folio_t free, unsigned int *ret_succeeded); struct folio *alloc_migration_target(struct folio *src, unsigned long private); bool isolate_movable_page(struct page *page, isolate_mode_t mode); +bool isolate_folio_to_list(struct folio *folio, struct list_head *list); int migrate_huge_page_move_mapping(struct address_space *mapping, struct folio *dst, struct folio *src); @@ -91,6 +92,8 @@ static inline struct folio *alloc_migration_target(struct folio *src, { return NULL; } static inline bool isolate_movable_page(struct page *page, isolate_mode_t mode) { return false; } +static inline bool isolate_folio_to_list(struct folio *folio, struct list_head *list) + { return false; } static inline int migrate_huge_page_move_mapping(struct address_space *mapping, struct folio *dst, struct folio *src) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 1f4f31e6d91d..96ce31e5a203 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -2653,40 +2653,6 @@ EXPORT_SYMBOL(unpoison_memory); #undef pr_fmt #define pr_fmt(fmt) "Soft offline: " fmt -static bool mf_isolate_folio(struct folio *folio, struct list_head *pagelist) -{ - bool isolated = false; - - if (folio_test_hugetlb(folio)) { - isolated = isolate_hugetlb(folio, pagelist); - } else { - bool lru = !__folio_test_movable(folio); - - if (lru) - isolated = folio_isolate_lru(folio); - else - isolated = isolate_movable_page(&folio->page, - ISOLATE_UNEVICTABLE); - - if (isolated) { - list_add(&folio->lru, pagelist); - if (lru) - node_stat_add_folio(folio, NR_ISOLATED_ANON + - folio_is_file_lru(folio)); - } - } - - /* - * If we succeed to isolate the folio, we grabbed another refcount on - * the folio, so we can safely drop the one we got from get_any_page(). - * If we failed to isolate the folio, it means that we cannot go further - * and we will return an error, so drop the reference we got from - * get_any_page() as well. - */ - folio_put(folio); - return isolated; -} - /* * soft_offline_in_use_page handles hugetlb-pages and non-hugetlb pages. * If the page is a non-dirty unmapped page-cache page, it simply invalidates. @@ -2699,6 +2665,7 @@ static int soft_offline_in_use_page(struct page *page) struct folio *folio = page_folio(page); char const *msg_page[] = {"page", "hugepage"}; bool huge = folio_test_hugetlb(folio); + bool isolated; LIST_HEAD(pagelist); struct migration_target_control mtc = { .nid = NUMA_NO_NODE, @@ -2738,7 +2705,18 @@ static int soft_offline_in_use_page(struct page *page) return 0; } - if (mf_isolate_folio(folio, &pagelist)) { + isolated = isolate_folio_to_list(folio, &pagelist); + + /* + * If we succeed to isolate the folio, we grabbed another refcount on + * the folio, so we can safely drop the one we got from get_any_page(). + * If we failed to isolate the folio, it means that we cannot go further + * and we will return an error, so drop the reference we got from + * get_any_page() as well. + */ + folio_put(folio); + + if (isolated) { ret = migrate_pages(&pagelist, alloc_migration_target, NULL, (unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_FAILURE, NULL); if (!ret) { diff --git a/mm/migrate.c b/mm/migrate.c index 2250baa85ac2..ba4893d42618 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -178,6 +178,32 @@ void putback_movable_pages(struct list_head *l) } } +/* Must be called with an elevated refcount on the non-hugetlb folio */ +bool isolate_folio_to_list(struct folio *folio, struct list_head *list) +{ + bool isolated, lru; + + if (folio_test_hugetlb(folio)) + return isolate_hugetlb(folio, list); + + lru = !__folio_test_movable(folio); + if (lru) + isolated = folio_isolate_lru(folio); + else + isolated = isolate_movable_page(&folio->page, + ISOLATE_UNEVICTABLE); + + if (!isolated) + return false; + + list_add(&folio->lru, list); + if (lru) + node_stat_add_folio(folio, NR_ISOLATED_ANON + + folio_is_file_lru(folio)); + + return true; +} + /* * Restore a potential migration pte to a working pte entry */ -- cgit v1.2.3 From d29e741cad3f8f41df1834bf74df79380c1c6c6d Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 19 Aug 2024 17:17:04 +0200 Subject: gpio: davinci: drop platform data support There are no more any board files that use the platform data for gpio-davinci. We can remove the header defining it and port the code to no longer store any context in pdata. Reviewed-by: Linus Walleij Link: https://lore.kernel.org/r/20240819151705.37258-1-brgl@bgdev.pl Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-davinci.c | 89 +++++++++--------------------- include/linux/platform_data/gpio-davinci.h | 21 ------- 2 files changed, 25 insertions(+), 85 deletions(-) delete mode 100644 include/linux/platform_data/gpio-davinci.h (limited to 'include/linux') diff --git a/drivers/gpio/gpio-davinci.c b/drivers/gpio/gpio-davinci.c index 1d0175d6350b..7763b99f814a 100644 --- a/drivers/gpio/gpio-davinci.c +++ b/drivers/gpio/gpio-davinci.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include @@ -154,74 +153,37 @@ davinci_gpio_set(struct gpio_chip *chip, unsigned offset, int value) value ? &g->set_data : &g->clr_data); } -static struct davinci_gpio_platform_data * -davinci_gpio_get_pdata(struct platform_device *pdev) -{ - struct device_node *dn = pdev->dev.of_node; - struct davinci_gpio_platform_data *pdata; - int ret; - u32 val; - - if (!IS_ENABLED(CONFIG_OF) || !pdev->dev.of_node) - return dev_get_platdata(&pdev->dev); - - pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL); - if (!pdata) - return NULL; - - ret = of_property_read_u32(dn, "ti,ngpio", &val); - if (ret) - goto of_err; - - pdata->ngpio = val; - - ret = of_property_read_u32(dn, "ti,davinci-gpio-unbanked", &val); - if (ret) - goto of_err; - - pdata->gpio_unbanked = val; - - return pdata; - -of_err: - dev_err(&pdev->dev, "Populating pdata from DT failed: err %d\n", ret); - return NULL; -} - static int davinci_gpio_probe(struct platform_device *pdev) { int bank, i, ret = 0; - unsigned int ngpio, nbank, nirq; + unsigned int ngpio, nbank, nirq, gpio_unbanked; struct davinci_gpio_controller *chips; - struct davinci_gpio_platform_data *pdata; struct device *dev = &pdev->dev; - - pdata = davinci_gpio_get_pdata(pdev); - if (!pdata) { - dev_err(dev, "No platform data found\n"); - return -EINVAL; - } - - dev->platform_data = pdata; + struct device_node *dn = dev_of_node(dev); /* * The gpio banks conceptually expose a segmented bitmap, * and "ngpio" is one more than the largest zero-based * bit index that's valid. */ - ngpio = pdata->ngpio; - if (ngpio == 0) { - dev_err(dev, "How many GPIOs?\n"); - return -EINVAL; - } + ret = of_property_read_u32(dn, "ti,ngpio", &ngpio); + if (ret) + return dev_err_probe(dev, ret, "Failed to get the number of GPIOs\n"); + if (ngpio == 0) + return dev_err_probe(dev, -EINVAL, "How many GPIOs?\n"); /* * If there are unbanked interrupts then the number of * interrupts is equal to number of gpios else all are banked so * number of interrupts is equal to number of banks(each with 16 gpios) */ - if (pdata->gpio_unbanked) - nirq = pdata->gpio_unbanked; + ret = of_property_read_u32(dn, "ti,davinci-gpio-unbanked", + &gpio_unbanked); + if (ret) + return dev_err_probe(dev, ret, "Failed to get the unbanked GPIOs property\n"); + + if (gpio_unbanked) + nirq = gpio_unbanked; else nirq = DIV_ROUND_UP(ngpio, 16); @@ -252,7 +214,7 @@ static int davinci_gpio_probe(struct platform_device *pdev) chips->chip.set = davinci_gpio_set; chips->chip.ngpio = ngpio; - chips->chip.base = pdata->no_auto_base ? pdata->base : -1; + chips->chip.base = -1; #ifdef CONFIG_OF_GPIO chips->chip.parent = dev; @@ -261,6 +223,8 @@ static int davinci_gpio_probe(struct platform_device *pdev) #endif spin_lock_init(&chips->lock); + chips->gpio_unbanked = gpio_unbanked; + nbank = DIV_ROUND_UP(ngpio, 32); for (bank = 0; bank < nbank; bank++) chips->regs[bank] = gpio_base + offset_array[bank]; @@ -488,7 +452,6 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev) unsigned ngpio; struct device *dev = &pdev->dev; struct davinci_gpio_controller *chips = platform_get_drvdata(pdev); - struct davinci_gpio_platform_data *pdata = dev->platform_data; struct davinci_gpio_regs __iomem *g; struct irq_domain *irq_domain = NULL; struct irq_chip *irq_chip; @@ -502,7 +465,7 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev) if (dev->of_node) gpio_get_irq_chip = (gpio_get_irq_chip_cb_t)device_get_match_data(dev); - ngpio = pdata->ngpio; + ngpio = chips->chip.ngpio; clk = devm_clk_get(dev, "gpio"); if (IS_ERR(clk)) { @@ -514,7 +477,7 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev) if (ret) return ret; - if (!pdata->gpio_unbanked) { + if (chips->gpio_unbanked) { irq = devm_irq_alloc_descs(dev, -1, 0, ngpio, 0); if (irq < 0) { dev_err(dev, "Couldn't allocate IRQ numbers\n"); @@ -546,11 +509,11 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev) * controller only handling trigger modes. We currently assume no * IRQ mux conflicts; gpio_irq_type_unbanked() is only for GPIOs. */ - if (pdata->gpio_unbanked) { + if (chips->gpio_unbanked) { /* pass "bank 0" GPIO IRQs to AINTC */ chips->chip.to_irq = gpio_to_irq_unbanked; - chips->gpio_unbanked = pdata->gpio_unbanked; - binten = GENMASK(pdata->gpio_unbanked / 16, 0); + + binten = GENMASK(chips->gpio_unbanked / 16, 0); /* AINTC handles mask/unmask; GPIO handles triggering */ irq = chips->irqs[0]; @@ -564,7 +527,7 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev) writel_relaxed(~0, &g->set_rising); /* set the direct IRQs up to use that irqchip */ - for (gpio = 0; gpio < pdata->gpio_unbanked; gpio++) { + for (gpio = 0; gpio < chips->gpio_unbanked; gpio++) { irq_set_chip(chips->irqs[gpio], irq_chip); irq_set_handler_data(chips->irqs[gpio], chips); irq_set_status_flags(chips->irqs[gpio], @@ -675,8 +638,7 @@ static void davinci_gpio_restore_context(struct davinci_gpio_controller *chips, static int davinci_gpio_suspend(struct device *dev) { struct davinci_gpio_controller *chips = dev_get_drvdata(dev); - struct davinci_gpio_platform_data *pdata = dev_get_platdata(dev); - u32 nbank = DIV_ROUND_UP(pdata->ngpio, 32); + u32 nbank = DIV_ROUND_UP(chips->chip.ngpio, 32); davinci_gpio_save_context(chips, nbank); @@ -686,8 +648,7 @@ static int davinci_gpio_suspend(struct device *dev) static int davinci_gpio_resume(struct device *dev) { struct davinci_gpio_controller *chips = dev_get_drvdata(dev); - struct davinci_gpio_platform_data *pdata = dev_get_platdata(dev); - u32 nbank = DIV_ROUND_UP(pdata->ngpio, 32); + u32 nbank = DIV_ROUND_UP(chips->chip.ngpio, 32); davinci_gpio_restore_context(chips, nbank); diff --git a/include/linux/platform_data/gpio-davinci.h b/include/linux/platform_data/gpio-davinci.h deleted file mode 100644 index b82e44662efe..000000000000 --- a/include/linux/platform_data/gpio-davinci.h +++ /dev/null @@ -1,21 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * DaVinci GPIO Platform Related Defines - * - * Copyright (C) 2013 Texas Instruments Incorporated - https://www.ti.com/ - */ - -#ifndef __DAVINCI_GPIO_PLATFORM_H -#define __DAVINCI_GPIO_PLATFORM_H - -struct davinci_gpio_platform_data { - bool no_auto_base; - u32 base; - u32 ngpio; - u32 gpio_unbanked; -}; - -/* Convert GPIO signal to GPIO pin number */ -#define GPIO_TO_PIN(bank, gpio) (16 * (bank) + (gpio)) - -#endif -- cgit v1.2.3 From 8b1451f2f723f845c05b8bad3d4c45de284338b5 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 3 Sep 2024 21:54:28 -1000 Subject: sched_ext: Replace SCX_TASK_BAL_KEEP with SCX_RQ_BAL_KEEP SCX_TASK_BAL_KEEP is used by balance_one() to tell pick_next_task_scx() to keep running the current task. It's not really a task property. Replace it with SCX_RQ_BAL_KEEP which resides in rq->scx.flags and is a better fit for the usage. Also, the existing clearing rule is unnecessarily strict and makes it difficult to use with core-sched. Just clear it on entry to balance_one(). Signed-off-by: Tejun Heo --- include/linux/sched/ext.h | 1 - kernel/sched/ext.c | 20 +++++++++----------- kernel/sched/sched.h | 1 + 3 files changed, 10 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index 69f68e2121a8..db2a266113ac 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -71,7 +71,6 @@ struct scx_dispatch_q { /* scx_entity.flags */ enum scx_ent_flags { SCX_TASK_QUEUED = 1 << 0, /* on ext runqueue */ - SCX_TASK_BAL_KEEP = 1 << 1, /* balance decided to keep current */ SCX_TASK_RESET_RUNNABLE_AT = 1 << 2, /* runnable_at should be reset */ SCX_TASK_DEQD_FOR_SLEEP = 1 << 3, /* last dequeue was for SLEEP */ diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index be86dbfa75a8..fd979c69de1f 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -2508,6 +2508,7 @@ static int balance_one(struct rq *rq, struct task_struct *prev, bool local) lockdep_assert_rq_held(rq); rq->scx.flags |= SCX_RQ_IN_BALANCE; + rq->scx.flags &= ~SCX_RQ_BAL_KEEP; if (static_branch_unlikely(&scx_ops_cpu_preempt) && unlikely(rq->scx.cpu_released)) { @@ -2523,7 +2524,6 @@ static int balance_one(struct rq *rq, struct task_struct *prev, bool local) } if (prev_on_scx) { - WARN_ON_ONCE(local && (prev->scx.flags & SCX_TASK_BAL_KEEP)); update_curr_scx(rq); /* @@ -2538,13 +2538,13 @@ static int balance_one(struct rq *rq, struct task_struct *prev, bool local) * * When balancing a remote CPU for core-sched, there won't be a * following put_prev_task_scx() call and we don't own - * %SCX_TASK_BAL_KEEP. Instead, pick_task_scx() will test the - * same conditions later and pick @rq->curr accordingly. + * %SCX_RQ_BAL_KEEP. Instead, pick_task_scx() will test the same + * conditions later and pick @rq->curr accordingly. */ if ((prev->scx.flags & SCX_TASK_QUEUED) && prev->scx.slice && !scx_ops_bypassing()) { if (local) - prev->scx.flags |= SCX_TASK_BAL_KEEP; + rq->scx.flags |= SCX_RQ_BAL_KEEP; goto has_tasks; } } @@ -2604,7 +2604,7 @@ no_tasks: if ((prev->scx.flags & SCX_TASK_QUEUED) && (!static_branch_unlikely(&scx_ops_enq_last) || scx_ops_bypassing())) { if (local) - prev->scx.flags |= SCX_TASK_BAL_KEEP; + rq->scx.flags |= SCX_RQ_BAL_KEEP; goto has_tasks; } rq->scx.flags &= ~SCX_RQ_IN_BALANCE; @@ -2726,8 +2726,6 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p, SCX_CALL_OP_TASK(SCX_KF_REST, stopping, p, true); if (p->scx.flags & SCX_TASK_QUEUED) { - p->scx.flags &= ~SCX_TASK_BAL_KEEP; - set_task_runnable(rq, p); /* @@ -2772,8 +2770,8 @@ static struct task_struct *pick_next_task_scx(struct rq *rq, * if necessary and keep running @prev. Otherwise, pop the first one * from the local DSQ. */ - if (prev->scx.flags & SCX_TASK_BAL_KEEP) { - prev->scx.flags &= ~SCX_TASK_BAL_KEEP; + if ((rq->scx.flags & SCX_RQ_BAL_KEEP) && + !WARN_ON_ONCE(prev->sched_class != &ext_sched_class)) { p = prev; if (!p->scx.slice) p->scx.slice = SCX_SLICE_DFL; @@ -2841,7 +2839,7 @@ bool scx_prio_less(const struct task_struct *a, const struct task_struct *b, * * As put_prev_task_scx() hasn't been called on remote CPUs, we can't just look * at the first task in the local dsq. @rq->curr has to be considered explicitly - * to mimic %SCX_TASK_BAL_KEEP. + * to mimic %SCX_RQ_BAL_KEEP. */ static struct task_struct *pick_task_scx(struct rq *rq) { @@ -3872,7 +3870,7 @@ bool task_should_scx(struct task_struct *p) * * b. ops.dispatch() is ignored. * - * c. balance_scx() does not set %SCX_TASK_BAL_KEEP on non-zero slice as slice + * c. balance_scx() does not set %SCX_RQ_BAL_KEEP on non-zero slice as slice * can't be trusted. Whenever a tick triggers, the running task is rotated to * the tail of the queue with core_sched_at touched. * diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 1eda2ce31787..477e7a861d10 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -737,6 +737,7 @@ enum scx_rq_flags { */ SCX_RQ_ONLINE = 1 << 0, SCX_RQ_CAN_STOP_TICK = 1 << 1, + SCX_RQ_BAL_KEEP = 1 << 2, /* balance decided to keep current */ SCX_RQ_IN_WAKEUP = 1 << 16, SCX_RQ_IN_BALANCE = 1 << 17, -- cgit v1.2.3 From 47f218d108950984b24af81f66356ceda380eb74 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 29 Aug 2024 21:06:17 -0300 Subject: iommu/amd: Store the nid in io_pgtable_cfg instead of the domain We already have memory in the union here that is being wasted in AMD's case, use it to store the nid. Putting the nid here further isolates the io_pgtable code from the struct protection_domain. Fixup protection_domain_alloc so that the NID from the device is provided, at this point dev is never NULL for AMD so this will now allocate the first table pointer on the correct NUMA node. Signed-off-by: Jason Gunthorpe Reviewed-by: Vasant Hegde Link: https://lore.kernel.org/r/8-v2-831cdc4d00f3+1a315-amd_iopgtbl_jgg@nvidia.com Signed-off-by: Joerg Roedel --- drivers/iommu/amd/amd_iommu.h | 2 +- drivers/iommu/amd/amd_iommu_types.h | 1 - drivers/iommu/amd/io_pgtable.c | 8 +++++--- drivers/iommu/amd/io_pgtable_v2.c | 5 ++--- drivers/iommu/amd/iommu.c | 12 +++++++----- drivers/iommu/amd/pasid.c | 2 +- include/linux/io-pgtable.h | 4 ++++ 7 files changed, 20 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h index 8de6d6091454..29e6e71f7f9a 100644 --- a/drivers/iommu/amd/amd_iommu.h +++ b/drivers/iommu/amd/amd_iommu.h @@ -45,7 +45,7 @@ extern enum io_pgtable_fmt amd_iommu_pgtable; extern int amd_iommu_gpt_level; /* Protection domain ops */ -struct protection_domain *protection_domain_alloc(unsigned int type); +struct protection_domain *protection_domain_alloc(unsigned int type, int nid); void protection_domain_free(struct protection_domain *domain); struct iommu_domain *amd_iommu_domain_alloc_sva(struct device *dev, struct mm_struct *mm); diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index 7aa4f1983e40..30eb07acb8b1 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -571,7 +571,6 @@ struct protection_domain { struct amd_io_pgtable iop; spinlock_t lock; /* mostly used to lock the page table*/ u16 id; /* the domain id written to the device table */ - int nid; /* Node ID */ enum protection_domain_mode pd_mode; /* Track page table type */ bool dirty_tracking; /* dirty tracking is enabled in the domain */ unsigned dev_cnt; /* devices assigned to this domain */ diff --git a/drivers/iommu/amd/io_pgtable.c b/drivers/iommu/amd/io_pgtable.c index 53de1146928e..4492a5800b35 100644 --- a/drivers/iommu/amd/io_pgtable.c +++ b/drivers/iommu/amd/io_pgtable.c @@ -141,11 +141,12 @@ static bool increase_address_space(struct protection_domain *domain, unsigned long address, gfp_t gfp) { + struct io_pgtable_cfg *cfg = &domain->iop.pgtbl.cfg; unsigned long flags; bool ret = true; u64 *pte; - pte = iommu_alloc_page_node(domain->nid, gfp); + pte = iommu_alloc_page_node(cfg->amd.nid, gfp); if (!pte) return false; @@ -181,6 +182,7 @@ static u64 *alloc_pte(struct protection_domain *domain, gfp_t gfp, bool *updated) { + struct io_pgtable_cfg *cfg = &domain->iop.pgtbl.cfg; int level, end_lvl; u64 *pte, *page; @@ -232,7 +234,7 @@ static u64 *alloc_pte(struct protection_domain *domain, if (!IOMMU_PTE_PRESENT(__pte) || pte_level == PAGE_MODE_NONE) { - page = iommu_alloc_page_node(domain->nid, gfp); + page = iommu_alloc_page_node(cfg->amd.nid, gfp); if (!page) return NULL; @@ -559,7 +561,7 @@ static struct io_pgtable *v1_alloc_pgtable(struct io_pgtable_cfg *cfg, void *coo { struct amd_io_pgtable *pgtable = io_pgtable_cfg_to_data(cfg); - pgtable->root = iommu_alloc_page(GFP_KERNEL); + pgtable->root = iommu_alloc_page_node(cfg->amd.nid, GFP_KERNEL); if (!pgtable->root) return NULL; pgtable->mode = PAGE_MODE_3_LEVEL; diff --git a/drivers/iommu/amd/io_pgtable_v2.c b/drivers/iommu/amd/io_pgtable_v2.c index 45a6bc332639..1e3be8c5312b 100644 --- a/drivers/iommu/amd/io_pgtable_v2.c +++ b/drivers/iommu/amd/io_pgtable_v2.c @@ -251,7 +251,7 @@ static int iommu_v2_map_pages(struct io_pgtable_ops *ops, unsigned long iova, while (mapped_size < size) { map_size = get_alloc_page_size(pgsize); - pte = v2_alloc_pte(pdom->nid, pdom->iop.pgd, + pte = v2_alloc_pte(cfg->amd.nid, pdom->iop.pgd, iova, map_size, gfp, &updated); if (!pte) { ret = -EINVAL; @@ -359,10 +359,9 @@ static void v2_free_pgtable(struct io_pgtable *iop) static struct io_pgtable *v2_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie) { struct amd_io_pgtable *pgtable = io_pgtable_cfg_to_data(cfg); - struct protection_domain *pdom = (struct protection_domain *)cookie; int ias = IOMMU_IN_ADDR_BIT_SIZE; - pgtable->pgd = iommu_alloc_page_node(pdom->nid, GFP_KERNEL); + pgtable->pgd = iommu_alloc_page_node(cfg->amd.nid, GFP_KERNEL); if (!pgtable->pgd) return NULL; diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 212cc2801274..44231c3b6b71 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -2023,6 +2023,7 @@ static int do_attach(struct iommu_dev_data *dev_data, struct protection_domain *domain) { struct amd_iommu *iommu = get_amd_iommu_from_dev_data(dev_data); + struct io_pgtable_cfg *cfg = &domain->iop.pgtbl.cfg; int ret = 0; /* Update data structures */ @@ -2030,8 +2031,8 @@ static int do_attach(struct iommu_dev_data *dev_data, list_add(&dev_data->list, &domain->dev_list); /* Update NUMA Node ID */ - if (domain->nid == NUMA_NO_NODE) - domain->nid = dev_to_node(dev_data->dev); + if (cfg->amd.nid == NUMA_NO_NODE) + cfg->amd.nid = dev_to_node(dev_data->dev); /* Do reference counting */ domain->dev_iommu[iommu->index] += 1; @@ -2266,7 +2267,7 @@ void protection_domain_free(struct protection_domain *domain) kfree(domain); } -struct protection_domain *protection_domain_alloc(unsigned int type) +struct protection_domain *protection_domain_alloc(unsigned int type, int nid) { struct io_pgtable_ops *pgtbl_ops; struct protection_domain *domain; @@ -2283,7 +2284,7 @@ struct protection_domain *protection_domain_alloc(unsigned int type) spin_lock_init(&domain->lock); INIT_LIST_HEAD(&domain->dev_list); INIT_LIST_HEAD(&domain->dev_data_list); - domain->nid = NUMA_NO_NODE; + domain->iop.pgtbl.cfg.amd.nid = nid; switch (type) { /* No need to allocate io pgtable ops in passthrough mode */ @@ -2360,7 +2361,8 @@ static struct iommu_domain *do_iommu_domain_alloc(unsigned int type, if (dirty_tracking && !amd_iommu_hd_support(iommu)) return ERR_PTR(-EOPNOTSUPP); - domain = protection_domain_alloc(type); + domain = protection_domain_alloc(type, + dev ? dev_to_node(dev) : NUMA_NO_NODE); if (!domain) return ERR_PTR(-ENOMEM); diff --git a/drivers/iommu/amd/pasid.c b/drivers/iommu/amd/pasid.c index a68215f2b3e1..0657b9373be5 100644 --- a/drivers/iommu/amd/pasid.c +++ b/drivers/iommu/amd/pasid.c @@ -181,7 +181,7 @@ struct iommu_domain *amd_iommu_domain_alloc_sva(struct device *dev, struct protection_domain *pdom; int ret; - pdom = protection_domain_alloc(IOMMU_DOMAIN_SVA); + pdom = protection_domain_alloc(IOMMU_DOMAIN_SVA, dev_to_node(dev)); if (!pdom) return ERR_PTR(-ENOMEM); diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index f9a81761bfce..b1ecfc3cd5bc 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -171,6 +171,10 @@ struct io_pgtable_cfg { u64 ttbr[4]; u32 n_ttbrs; } apple_dart_cfg; + + struct { + int nid; + } amd; }; }; -- cgit v1.2.3 From 9f82f15ddfdd60bb9820f09737333b2345e22ab3 Mon Sep 17 00:00:00 2001 From: Joey Gouly Date: Thu, 22 Aug 2024 16:10:46 +0100 Subject: mm: use ARCH_PKEY_BITS to define VM_PKEY_BITN Use the new CONFIG_ARCH_PKEY_BITS to simplify setting these bits for different architectures. Signed-off-by: Joey Gouly Cc: Andrew Morton Cc: linux-fsdevel@vger.kernel.org Cc: linux-mm@kvack.org Acked-by: Dave Hansen Reviewed-by: Anshuman Khandual Link: https://lore.kernel.org/r/20240822151113.1479789-4-joey.gouly@arm.com Signed-off-by: Will Deacon --- fs/proc/task_mmu.c | 2 ++ include/linux/mm.h | 16 ++++++++++------ 2 files changed, 12 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 5f171ad7b436..2c5f4814aef9 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -976,7 +976,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) [ilog2(VM_PKEY_BIT0)] = "", [ilog2(VM_PKEY_BIT1)] = "", [ilog2(VM_PKEY_BIT2)] = "", +#if VM_PKEY_BIT3 [ilog2(VM_PKEY_BIT3)] = "", +#endif #if VM_PKEY_BIT4 [ilog2(VM_PKEY_BIT4)] = "", #endif diff --git a/include/linux/mm.h b/include/linux/mm.h index c4b238a20b76..fb6ccd93f589 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -330,12 +330,16 @@ extern unsigned int kobjsize(const void *objp); #endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */ #ifdef CONFIG_ARCH_HAS_PKEYS -# define VM_PKEY_SHIFT VM_HIGH_ARCH_BIT_0 -# define VM_PKEY_BIT0 VM_HIGH_ARCH_0 /* A protection key is a 4-bit value */ -# define VM_PKEY_BIT1 VM_HIGH_ARCH_1 /* on x86 and 5-bit value on ppc64 */ -# define VM_PKEY_BIT2 VM_HIGH_ARCH_2 -# define VM_PKEY_BIT3 VM_HIGH_ARCH_3 -#ifdef CONFIG_PPC +# define VM_PKEY_SHIFT VM_HIGH_ARCH_BIT_0 +# define VM_PKEY_BIT0 VM_HIGH_ARCH_0 +# define VM_PKEY_BIT1 VM_HIGH_ARCH_1 +# define VM_PKEY_BIT2 VM_HIGH_ARCH_2 +#if CONFIG_ARCH_PKEY_BITS > 3 +# define VM_PKEY_BIT3 VM_HIGH_ARCH_3 +#else +# define VM_PKEY_BIT3 0 +#endif +#if CONFIG_ARCH_PKEY_BITS > 4 # define VM_PKEY_BIT4 VM_HIGH_ARCH_4 #else # define VM_PKEY_BIT4 0 -- cgit v1.2.3 From facaa1373c9aabf8e34109a9cb205ad0f3a8584e Mon Sep 17 00:00:00 2001 From: Joey Gouly Date: Thu, 22 Aug 2024 16:10:55 +0100 Subject: arm64: re-order MTE VM_ flags VM_PKEY_BIT[012] will use VM_HIGH_ARCH_[012], move the MTE VM flags to accommodate this. Signed-off-by: Joey Gouly Cc: Catalin Marinas Cc: Will Deacon Acked-by: Catalin Marinas Link: https://lore.kernel.org/r/20240822151113.1479789-13-joey.gouly@arm.com Signed-off-by: Will Deacon --- include/linux/mm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index fb6ccd93f589..406512c16471 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -378,8 +378,8 @@ extern unsigned int kobjsize(const void *objp); #endif #if defined(CONFIG_ARM64_MTE) -# define VM_MTE VM_HIGH_ARCH_0 /* Use Tagged memory for access control */ -# define VM_MTE_ALLOWED VM_HIGH_ARCH_1 /* Tagged memory permitted */ +# define VM_MTE VM_HIGH_ARCH_4 /* Use Tagged memory for access control */ +# define VM_MTE_ALLOWED VM_HIGH_ARCH_5 /* Tagged memory permitted */ #else # define VM_MTE VM_NONE # define VM_MTE_ALLOWED VM_NONE -- cgit v1.2.3 From c6fb88a5270f4ba24859f5ecb61cfc731ef16300 Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Wed, 4 Sep 2024 21:51:50 +0900 Subject: firewire: core: allocate workqueue to handle isochronous contexts in card This commit adds a workqueue dedicated for isochronous context processing. The workqueue is allocated per instance of fw_card structure to satisfy the following characteristics descending from 1394 OHCI specification: In 1394 OHCI specification, memory pages are reserved to each isochronous context dedicated to DMA transmission. It allows to operate these per-context pages concurrently. Software can schedule hardware interrupt for several isochronous context to the same cycle, thus WQ_UNBOUND is specified. Additionally, it is sleepable to operate the content of pages, thus WQ_BH is not used. The isochronous context delivers the packets with time stamp, thus WQ_HIGHPRI is specified for semi real-time data such as IEC 61883-1/6 protocol implemented by ALSA firewire stack. The isochronous context is not used by the implementation of SCSI over IEEE1394 protocol (sbp2), thus WQ_MEM_RECLAIM is not specified. It is useful for users to adjust cpu affinity of the workqueue depending on their work loads, thus WQ_SYS is specified to expose the attributes to user space. Tested-by: Edmund Raile Link: https://lore.kernel.org/r/20240904125155.461886-2-o-takashi@sakamocchi.jp Signed-off-by: Takashi Sakamoto --- drivers/firewire/core-card.c | 33 ++++++++++++++++++++++++++++++--- drivers/firewire/core.h | 4 ++-- drivers/firewire/ohci.c | 2 +- include/linux/firewire.h | 2 ++ 4 files changed, 35 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/firewire/core-card.c b/drivers/firewire/core-card.c index e80b762888fa..01354b9de8b2 100644 --- a/drivers/firewire/core-card.c +++ b/drivers/firewire/core-card.c @@ -571,11 +571,30 @@ void fw_card_initialize(struct fw_card *card, } EXPORT_SYMBOL(fw_card_initialize); -int fw_card_add(struct fw_card *card, - u32 max_receive, u32 link_speed, u64 guid) +int fw_card_add(struct fw_card *card, u32 max_receive, u32 link_speed, u64 guid, + unsigned int supported_isoc_contexts) { + struct workqueue_struct *isoc_wq; int ret; + // This workqueue should be: + // * != WQ_BH Sleepable. + // * == WQ_UNBOUND Any core can process data for isoc context. The + // implementation of unit protocol could consumes the core + // longer somehow. + // * != WQ_MEM_RECLAIM Not used for any backend of block device. + // * == WQ_FREEZABLE Isochronous communication is at regular interval in real + // time, thus should be drained if possible at freeze phase. + // * == WQ_HIGHPRI High priority to process semi-realtime timestamped data. + // * == WQ_SYSFS Parameters are available via sysfs. + // * max_active == n_it + n_ir A hardIRQ could notify events for multiple isochronous + // contexts if they are scheduled to the same cycle. + isoc_wq = alloc_workqueue("firewire-isoc-card%u", + WQ_UNBOUND | WQ_FREEZABLE | WQ_HIGHPRI | WQ_SYSFS, + supported_isoc_contexts, card->index); + if (!isoc_wq) + return -ENOMEM; + card->max_receive = max_receive; card->link_speed = link_speed; card->guid = guid; @@ -584,9 +603,12 @@ int fw_card_add(struct fw_card *card, generate_config_rom(card, tmp_config_rom); ret = card->driver->enable(card, tmp_config_rom, config_rom_length); - if (ret < 0) + if (ret < 0) { + destroy_workqueue(isoc_wq); return ret; + } + card->isoc_wq = isoc_wq; list_add_tail(&card->link, &card_list); return 0; @@ -708,6 +730,8 @@ void fw_core_remove_card(struct fw_card *card) { struct fw_card_driver dummy_driver = dummy_driver_template; + might_sleep(); + card->driver->update_phy_reg(card, 4, PHY_LINK_ACTIVE | PHY_CONTENDER, 0); fw_schedule_bus_reset(card, false, true); @@ -719,6 +743,7 @@ void fw_core_remove_card(struct fw_card *card) dummy_driver.free_iso_context = card->driver->free_iso_context; dummy_driver.stop_iso = card->driver->stop_iso; card->driver = &dummy_driver; + drain_workqueue(card->isoc_wq); scoped_guard(spinlock_irqsave, &card->lock) fw_destroy_nodes(card); @@ -727,6 +752,8 @@ void fw_core_remove_card(struct fw_card *card) fw_card_put(card); wait_for_completion(&card->done); + destroy_workqueue(card->isoc_wq); + WARN_ON(!list_empty(&card->transaction_list)); } EXPORT_SYMBOL(fw_core_remove_card); diff --git a/drivers/firewire/core.h b/drivers/firewire/core.h index 57d101c01e36..96ae366889e0 100644 --- a/drivers/firewire/core.h +++ b/drivers/firewire/core.h @@ -115,8 +115,8 @@ struct fw_card_driver { void fw_card_initialize(struct fw_card *card, const struct fw_card_driver *driver, struct device *device); -int fw_card_add(struct fw_card *card, - u32 max_receive, u32 link_speed, u64 guid); +int fw_card_add(struct fw_card *card, u32 max_receive, u32 link_speed, u64 guid, + unsigned int supported_isoc_contexts); void fw_core_remove_card(struct fw_card *card); int fw_compute_block_crc(__be32 *block); void fw_schedule_bm_work(struct fw_card *card, unsigned long delay); diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index 3930fdd56155..50627b8fc38f 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -3827,7 +3827,7 @@ static int pci_probe(struct pci_dev *dev, goto fail_msi; } - err = fw_card_add(&ohci->card, max_receive, link_speed, guid); + err = fw_card_add(&ohci->card, max_receive, link_speed, guid, ohci->n_it + ohci->n_ir); if (err) goto fail_irq; diff --git a/include/linux/firewire.h b/include/linux/firewire.h index 1cca14cf5652..10e135d60824 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -134,6 +134,8 @@ struct fw_card { __be32 topology_map[(CSR_TOPOLOGY_MAP_END - CSR_TOPOLOGY_MAP) / 4]; __be32 maint_utility_register; + + struct workqueue_struct *isoc_wq; }; static inline struct fw_card *fw_card_get(struct fw_card *card) -- cgit v1.2.3 From 4f55ad754d6b7b6fa4ebcfd8c50f7e53e661a78e Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Wed, 4 Sep 2024 21:51:51 +0900 Subject: firewire: core: add local API to queue work item to workqueue specific to isochronous contexts In the previous commit, the workqueue is added per the instance of fw_card structure for isochronous contexts. The workqueue is designed to be used by the implementation of fw_card_driver structure underlying the fw_card. This commit adds some local APIs to be used by the implementation. Tested-by: Edmund Raile Link: https://lore.kernel.org/r/20240904125155.461886-3-o-takashi@sakamocchi.jp Signed-off-by: Takashi Sakamoto --- drivers/firewire/core-iso.c | 30 ++++++++++++++++++++++++++++-- drivers/firewire/core.h | 10 ++++++++++ include/linux/firewire.h | 1 + 3 files changed, 39 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/firewire/core-iso.c b/drivers/firewire/core-iso.c index 101433b8bb51..af76fa1823f1 100644 --- a/drivers/firewire/core-iso.c +++ b/drivers/firewire/core-iso.c @@ -211,21 +211,47 @@ EXPORT_SYMBOL(fw_iso_context_queue_flush); int fw_iso_context_flush_completions(struct fw_iso_context *ctx) { + int err; + trace_isoc_outbound_flush_completions(ctx); trace_isoc_inbound_single_flush_completions(ctx); trace_isoc_inbound_multiple_flush_completions(ctx); - return ctx->card->driver->flush_iso_completions(ctx); + might_sleep(); + + // Avoid dead lock due to programming mistake. + if (WARN_ON(current_work() == &ctx->work)) + return 0; + + disable_work_sync(&ctx->work); + + err = ctx->card->driver->flush_iso_completions(ctx); + + enable_work(&ctx->work); + + return err; } EXPORT_SYMBOL(fw_iso_context_flush_completions); int fw_iso_context_stop(struct fw_iso_context *ctx) { + int err; + trace_isoc_outbound_stop(ctx); trace_isoc_inbound_single_stop(ctx); trace_isoc_inbound_multiple_stop(ctx); - return ctx->card->driver->stop_iso(ctx); + might_sleep(); + + // Avoid dead lock due to programming mistake. + if (WARN_ON(current_work() == &ctx->work)) + return 0; + + err = ctx->card->driver->stop_iso(ctx); + + cancel_work_sync(&ctx->work); + + return err; } EXPORT_SYMBOL(fw_iso_context_stop); diff --git a/drivers/firewire/core.h b/drivers/firewire/core.h index 96ae366889e0..2874f316156a 100644 --- a/drivers/firewire/core.h +++ b/drivers/firewire/core.h @@ -159,6 +159,16 @@ int fw_iso_buffer_alloc(struct fw_iso_buffer *buffer, int page_count); int fw_iso_buffer_map_dma(struct fw_iso_buffer *buffer, struct fw_card *card, enum dma_data_direction direction); +static inline void fw_iso_context_init_work(struct fw_iso_context *ctx, work_func_t func) +{ + INIT_WORK(&ctx->work, func); +} + +static inline void fw_iso_context_queue_work(struct fw_iso_context *ctx) +{ + queue_work(ctx->card->isoc_wq, &ctx->work); +} + /* -topology */ diff --git a/include/linux/firewire.h b/include/linux/firewire.h index 10e135d60824..72f497b61739 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -511,6 +511,7 @@ union fw_iso_callback { struct fw_iso_context { struct fw_card *card; + struct work_struct work; int type; int channel; int speed; -- cgit v1.2.3 From bd07d864522e7c3e4ee364e91aee8754992f5855 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Wed, 4 Sep 2024 14:11:20 +0206 Subject: printk: nbcon: Add function for printers to reacquire ownership Since ownership can be lost at any time due to handover or takeover, a printing context _must_ be prepared to back out immediately and carefully. However, there are scenarios where the printing context must reacquire ownership in order to finalize or revert hardware changes. One such example is when interrupts are disabled during printing. No other context will automagically re-enable the interrupts. For this case, the disabling context _must_ reacquire nbcon ownership so that it can re-enable the interrupts. Provide nbcon_reacquire_nobuf() for exactly this purpose. It allows a printing context to reacquire ownership using the same priority as its previous ownership. Note that after a successful reacquire the printing context will have no output buffer because that has been lost. This function cannot be used to resume printing. Signed-off-by: John Ogness Reviewed-by: Petr Mladek Link: https://lore.kernel.org/r/20240904120536.115780-2-john.ogness@linutronix.de Signed-off-by: Petr Mladek --- include/linux/console.h | 6 ++++ kernel/printk/nbcon.c | 74 ++++++++++++++++++++++++++++++++++++++++++++----- 2 files changed, 73 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index 9a13f91b0c43..88050d30a9cc 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -366,6 +366,10 @@ struct console { * * The callback should allow the takeover whenever it is safe. It * increases the chance to see messages when the system is in trouble. + * If the driver must reacquire ownership in order to finalize or + * revert hardware changes, nbcon_reacquire_nobuf() can be used. + * However, on reacquire the buffer content is no longer available. A + * reacquire cannot be used to resume printing. * * The callback can be called from any context (including NMI). * Therefore it must avoid usage of any locking and instead rely @@ -558,12 +562,14 @@ extern void nbcon_cpu_emergency_exit(void); extern bool nbcon_can_proceed(struct nbcon_write_context *wctxt); extern bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt); extern bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt); +extern void nbcon_reacquire_nobuf(struct nbcon_write_context *wctxt); #else static inline void nbcon_cpu_emergency_enter(void) { } static inline void nbcon_cpu_emergency_exit(void) { } static inline bool nbcon_can_proceed(struct nbcon_write_context *wctxt) { return false; } static inline bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt) { return false; } static inline bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt) { return false; } +static inline void nbcon_reacquire_nobuf(struct nbcon_write_context *wctxt) { } #endif extern int console_set_on_cmdline; diff --git a/kernel/printk/nbcon.c b/kernel/printk/nbcon.c index cf62f675c673..8a1bf6f94bce 100644 --- a/kernel/printk/nbcon.c +++ b/kernel/printk/nbcon.c @@ -830,6 +830,19 @@ out: return nbcon_context_can_proceed(ctxt, &cur); } +static void nbcon_write_context_set_buf(struct nbcon_write_context *wctxt, + char *buf, unsigned int len) +{ + struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); + struct console *con = ctxt->console; + struct nbcon_state cur; + + wctxt->outbuf = buf; + wctxt->len = len; + nbcon_state_read(con, &cur); + wctxt->unsafe_takeover = cur.unsafe_takeover; +} + /** * nbcon_enter_unsafe - Enter an unsafe region in the driver * @wctxt: The write context that was handed to the write function @@ -845,8 +858,12 @@ out: bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); + bool is_owner; - return nbcon_context_enter_unsafe(ctxt); + is_owner = nbcon_context_enter_unsafe(ctxt); + if (!is_owner) + nbcon_write_context_set_buf(wctxt, NULL, 0); + return is_owner; } EXPORT_SYMBOL_GPL(nbcon_enter_unsafe); @@ -865,11 +882,43 @@ EXPORT_SYMBOL_GPL(nbcon_enter_unsafe); bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); + bool ret; - return nbcon_context_exit_unsafe(ctxt); + ret = nbcon_context_exit_unsafe(ctxt); + if (!ret) + nbcon_write_context_set_buf(wctxt, NULL, 0); + return ret; } EXPORT_SYMBOL_GPL(nbcon_exit_unsafe); +/** + * nbcon_reacquire_nobuf - Reacquire a console after losing ownership + * while printing + * @wctxt: The write context that was handed to the write callback + * + * Since ownership can be lost at any time due to handover or takeover, a + * printing context _must_ be prepared to back out immediately and + * carefully. However, there are scenarios where the printing context must + * reacquire ownership in order to finalize or revert hardware changes. + * + * This function allows a printing context to reacquire ownership using the + * same priority as its previous ownership. + * + * Note that after a successful reacquire the printing context will have no + * output buffer because that has been lost. This function cannot be used to + * resume printing. + */ +void nbcon_reacquire_nobuf(struct nbcon_write_context *wctxt) +{ + struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); + + while (!nbcon_context_try_acquire(ctxt)) + cpu_relax(); + + nbcon_write_context_set_buf(wctxt, NULL, 0); +} +EXPORT_SYMBOL_GPL(nbcon_reacquire_nobuf); + /** * nbcon_emit_next_record - Emit a record in the acquired context * @wctxt: The write context that will be handed to the write function @@ -895,7 +944,6 @@ static bool nbcon_emit_next_record(struct nbcon_write_context *wctxt) .pbufs = ctxt->pbufs, }; unsigned long con_dropped; - struct nbcon_state cur; unsigned long dropped; /* @@ -930,10 +978,7 @@ static bool nbcon_emit_next_record(struct nbcon_write_context *wctxt) goto update_con; /* Initialize the write context for driver callbacks. */ - wctxt->outbuf = &pmsg.pbufs->outbuf[0]; - wctxt->len = pmsg.outbuf_len; - nbcon_state_read(con, &cur); - wctxt->unsafe_takeover = cur.unsafe_takeover; + nbcon_write_context_set_buf(wctxt, &pmsg.pbufs->outbuf[0], pmsg.outbuf_len); if (con->write_atomic) { con->write_atomic(con, wctxt); @@ -947,6 +992,21 @@ static bool nbcon_emit_next_record(struct nbcon_write_context *wctxt) return false; } + if (!wctxt->outbuf) { + /* + * Ownership was lost and reacquired by the driver. Handle it + * as if ownership was lost. + */ + nbcon_context_release(ctxt); + return false; + } + + /* + * Ownership may have been lost but _not_ reacquired by the driver. + * This case is detected and handled when entering unsafe to update + * dropped/seq values. + */ + /* * Since any dropped message was successfully output, reset the * dropped count for the console. -- cgit v1.2.3 From 76f258bf3f2aae570209319944703a92ac64e29e Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 4 Sep 2024 14:11:25 +0206 Subject: printk: nbcon: Introduce printer kthreads Provide the main implementation for running a printer kthread per nbcon console that is takeover/handover aware. This includes: - new mandatory write_thread() callback - kthread creation - kthread main printing loop - kthread wakeup mechanism - kthread shutdown kthread creation is a bit tricky because consoles may register before kthreads can be created. In such cases, registration will succeed, even though no kthread exists. Once kthreads can be created, an early_initcall will set @printk_kthreads_ready. If there are no registered boot consoles, the early_initcall creates the kthreads for all registered nbcon consoles. If kthread creation fails, the related console is unregistered. If there are registered boot consoles when @printk_kthreads_ready is set, no kthreads are created until the final boot console unregisters. Once kthread creation finally occurs, @printk_kthreads_running is set so that the system knows kthreads are available for all registered nbcon consoles. If @printk_kthreads_running is already set when the console is registering, the kthread is created during registration. If kthread creation fails, the registration will fail. Until @printk_kthreads_running is set, console printing occurs directly via the console_lock. kthread shutdown on system shutdown/reboot is necessary to ensure the printer kthreads finish their printing so that the system can cleanly transition back to direct printing via the console_lock in order to reliably push out the final shutdown/reboot messages. @printk_kthreads_running is cleared before shutting down the individual kthreads. The kthread uses a new mandatory write_thread() callback that is called with both device_lock() and the console context acquired. The console ownership handling is necessary for synchronization against write_atomic() which is synchronized only via the console context ownership. The device_lock() serializes acquiring the console context with NBCON_PRIO_NORMAL. It is needed in case the device_lock() does not disable preemption. It prevents the following race: CPU0 CPU1 [ task A ] nbcon_context_try_acquire() # success with NORMAL prio # .unsafe == false; // safe for takeover [ schedule: task A -> B ] WARN_ON() nbcon_atomic_flush_pending() nbcon_context_try_acquire() # success with EMERGENCY prio # flushing nbcon_context_release() # HERE: con->nbcon_state is free # to take by anyone !!! nbcon_context_try_acquire() # success with NORMAL prio [ task B ] [ schedule: task B -> A ] nbcon_enter_unsafe() nbcon_context_can_proceed() BUG: nbcon_context_can_proceed() returns "true" because the console is owned by a context on CPU0 with NBCON_PRIO_NORMAL. But it should return "false". The console is owned by a context from task B and we do the check in a context from task A. Note that with these changes, the printer kthreads do not yet take over full responsibility for nbcon printing during normal operation. These changes only focus on the lifecycle of the kthreads. Co-developed-by: John Ogness Signed-off-by: John Ogness Signed-off-by: Thomas Gleixner (Intel) Reviewed-by: Petr Mladek Link: https://lore.kernel.org/r/20240904120536.115780-7-john.ogness@linutronix.de Signed-off-by: Petr Mladek --- include/linux/console.h | 40 ++++++++ kernel/printk/internal.h | 27 ++++++ kernel/printk/nbcon.c | 245 +++++++++++++++++++++++++++++++++++++++++++++++ kernel/printk/printk.c | 108 +++++++++++++++++++++ 4 files changed, 420 insertions(+) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index 88050d30a9cc..788ce9c829f6 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -16,7 +16,9 @@ #include #include +#include #include +#include #include #include @@ -324,6 +326,9 @@ struct nbcon_write_context { * @nbcon_seq: Sequence number of the next record for nbcon to print * @nbcon_device_ctxt: Context available for non-printing operations * @pbufs: Pointer to nbcon private buffer + * @kthread: Printer kthread for this console + * @rcuwait: RCU-safe wait object for @kthread waking + * @irq_work: Defer @kthread waking to IRQ work context */ struct console { char name[16]; @@ -377,6 +382,37 @@ struct console { */ void (*write_atomic)(struct console *con, struct nbcon_write_context *wctxt); + /** + * @write_thread: + * + * NBCON callback to write out text in task context. + * + * This callback must be called only in task context with both + * device_lock() and the nbcon console acquired with + * NBCON_PRIO_NORMAL. + * + * The same rules for console ownership verification and unsafe + * sections handling applies as with write_atomic(). + * + * The console ownership handling is necessary for synchronization + * against write_atomic() which is synchronized only via the context. + * + * The device_lock() provides the primary serialization for operations + * on the device. It might be as relaxed (mutex)[*] or as tight + * (disabled preemption and interrupts) as needed. It allows + * the kthread to operate in the least restrictive mode[**]. + * + * [*] Standalone nbcon_context_try_acquire() is not safe with + * the preemption enabled, see nbcon_owner_matches(). But it + * can be safe when always called in the preemptive context + * under the device_lock(). + * + * [**] The device_lock() makes sure that nbcon_context_try_acquire() + * would never need to spin which is important especially with + * PREEMPT_RT. + */ + void (*write_thread)(struct console *con, struct nbcon_write_context *wctxt); + /** * @device_lock: * @@ -423,7 +459,11 @@ struct console { atomic_t __private nbcon_state; atomic_long_t __private nbcon_seq; struct nbcon_context __private nbcon_device_ctxt; + struct printk_buffers *pbufs; + struct task_struct *kthread; + struct rcuwait rcuwait; + struct irq_work irq_work; }; #ifdef CONFIG_LOCKDEP diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h index ad631824e7e5..14f7fc71e20d 100644 --- a/kernel/printk/internal.h +++ b/kernel/printk/internal.h @@ -48,6 +48,7 @@ struct printk_ringbuffer; struct dev_printk_info; extern struct printk_ringbuffer *prb; +extern bool printk_kthreads_running; __printf(4, 0) int vprintk_store(int facility, int level, @@ -90,6 +91,9 @@ enum nbcon_prio nbcon_get_default_prio(void); void nbcon_atomic_flush_pending(void); bool nbcon_legacy_emit_next_record(struct console *con, bool *handover, int cookie); +bool nbcon_kthread_create(struct console *con); +void nbcon_kthread_stop(struct console *con); +void nbcon_kthreads_wake(void); /* * Check if the given console is currently capable and allowed to print @@ -125,12 +129,34 @@ static inline bool console_is_usable(struct console *con, short flags, bool use_ return true; } +/** + * nbcon_kthread_wake - Wake up a console printing thread + * @con: Console to operate on + */ +static inline void nbcon_kthread_wake(struct console *con) +{ + /* + * Guarantee any new records can be seen by tasks preparing to wait + * before this context checks if the rcuwait is empty. + * + * The full memory barrier in rcuwait_wake_up() pairs with the full + * memory barrier within set_current_state() of + * ___rcuwait_wait_event(), which is called after prepare_to_rcuwait() + * adds the waiter but before it has checked the wait condition. + * + * This pairs with nbcon_kthread_func:A. + */ + rcuwait_wake_up(&con->rcuwait); /* LMM(nbcon_kthread_wake:A) */ +} + #else #define PRINTK_PREFIX_MAX 0 #define PRINTK_MESSAGE_MAX 0 #define PRINTKRB_RECORD_MAX 0 +#define printk_kthreads_running (false) + /* * In !PRINTK builds we still export console_sem * semaphore and some of console functions (console_unlock()/etc.), so @@ -149,6 +175,7 @@ static inline enum nbcon_prio nbcon_get_default_prio(void) { return NBCON_PRIO_N static inline void nbcon_atomic_flush_pending(void) { } static inline bool nbcon_legacy_emit_next_record(struct console *con, bool *handover, int cookie) { return false; } +static inline void nbcon_kthread_wake(struct console *con) { } static inline bool console_is_usable(struct console *con, short flags, bool use_atomic) { return false; } diff --git a/kernel/printk/nbcon.c b/kernel/printk/nbcon.c index bc684ff5028a..388322c74349 100644 --- a/kernel/printk/nbcon.c +++ b/kernel/printk/nbcon.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -952,6 +953,9 @@ static bool nbcon_emit_next_record(struct nbcon_write_context *wctxt, bool use_a * implemented the necessary callback for writing: i.e. legacy * consoles and, when atomic, nbcon consoles with no write_atomic(). * Handle it as if ownership was lost and try to continue. + * + * Note that for nbcon consoles the write_thread() callback is + * mandatory and was already checked in nbcon_alloc(). */ if (WARN_ON_ONCE((use_atomic && !con->write_atomic) || !(console_srcu_read_flags(con) & CON_NBCON))) { @@ -995,6 +999,8 @@ static bool nbcon_emit_next_record(struct nbcon_write_context *wctxt, bool use_a if (use_atomic) con->write_atomic(con, wctxt); + else + con->write_thread(con, wctxt); if (!wctxt->outbuf) { /* @@ -1036,6 +1042,228 @@ update_con: return nbcon_context_exit_unsafe(ctxt); } +/** + * nbcon_kthread_should_wakeup - Check whether a printer thread should wakeup + * @con: Console to operate on + * @ctxt: The nbcon context from nbcon_context_try_acquire() + * + * Return: True if the thread should shutdown or if the console is + * allowed to print and a record is available. False otherwise. + * + * After the thread wakes up, it must first check if it should shutdown before + * attempting any printing. + */ +static bool nbcon_kthread_should_wakeup(struct console *con, struct nbcon_context *ctxt) +{ + bool ret = false; + short flags; + int cookie; + + if (kthread_should_stop()) + return true; + + cookie = console_srcu_read_lock(); + + flags = console_srcu_read_flags(con); + if (console_is_usable(con, flags, false)) { + /* Bring the sequence in @ctxt up to date */ + ctxt->seq = nbcon_seq_read(con); + + ret = prb_read_valid(prb, ctxt->seq, NULL); + } + + console_srcu_read_unlock(cookie); + return ret; +} + +/** + * nbcon_kthread_func - The printer thread function + * @__console: Console to operate on + * + * Return: 0 + */ +static int nbcon_kthread_func(void *__console) +{ + struct console *con = __console; + struct nbcon_write_context wctxt = { + .ctxt.console = con, + .ctxt.prio = NBCON_PRIO_NORMAL, + }; + struct nbcon_context *ctxt = &ACCESS_PRIVATE(&wctxt, ctxt); + short con_flags; + bool backlog; + int cookie; + +wait_for_event: + /* + * Guarantee this task is visible on the rcuwait before + * checking the wake condition. + * + * The full memory barrier within set_current_state() of + * ___rcuwait_wait_event() pairs with the full memory + * barrier within rcuwait_has_sleeper(). + * + * This pairs with rcuwait_has_sleeper:A and nbcon_kthread_wake:A. + */ + rcuwait_wait_event(&con->rcuwait, + nbcon_kthread_should_wakeup(con, ctxt), + TASK_INTERRUPTIBLE); /* LMM(nbcon_kthread_func:A) */ + + do { + if (kthread_should_stop()) + return 0; + + backlog = false; + + /* + * Keep the srcu read lock around the entire operation so that + * synchronize_srcu() can guarantee that the kthread stopped + * or suspended printing. + */ + cookie = console_srcu_read_lock(); + + con_flags = console_srcu_read_flags(con); + + if (console_is_usable(con, con_flags, false)) { + unsigned long lock_flags; + + con->device_lock(con, &lock_flags); + + /* + * Ensure this stays on the CPU to make handover and + * takeover possible. + */ + cant_migrate(); + + if (nbcon_context_try_acquire(ctxt)) { + /* + * If the emit fails, this context is no + * longer the owner. + */ + if (nbcon_emit_next_record(&wctxt, false)) { + nbcon_context_release(ctxt); + backlog = ctxt->backlog; + } + } + + con->device_unlock(con, lock_flags); + } + + console_srcu_read_unlock(cookie); + + cond_resched(); + + } while (backlog); + + goto wait_for_event; +} + +/** + * nbcon_irq_work - irq work to wake console printer thread + * @irq_work: The irq work to operate on + */ +static void nbcon_irq_work(struct irq_work *irq_work) +{ + struct console *con = container_of(irq_work, struct console, irq_work); + + nbcon_kthread_wake(con); +} + +static inline bool rcuwait_has_sleeper(struct rcuwait *w) +{ + /* + * Guarantee any new records can be seen by tasks preparing to wait + * before this context checks if the rcuwait is empty. + * + * This full memory barrier pairs with the full memory barrier within + * set_current_state() of ___rcuwait_wait_event(), which is called + * after prepare_to_rcuwait() adds the waiter but before it has + * checked the wait condition. + * + * This pairs with nbcon_kthread_func:A. + */ + smp_mb(); /* LMM(rcuwait_has_sleeper:A) */ + return rcuwait_active(w); +} + +/** + * nbcon_kthreads_wake - Wake up printing threads using irq_work + */ +void nbcon_kthreads_wake(void) +{ + struct console *con; + int cookie; + + if (!printk_kthreads_running) + return; + + cookie = console_srcu_read_lock(); + for_each_console_srcu(con) { + if (!(console_srcu_read_flags(con) & CON_NBCON)) + continue; + + /* + * Only schedule irq_work if the printing thread is + * actively waiting. If not waiting, the thread will + * notice by itself that it has work to do. + */ + if (rcuwait_has_sleeper(&con->rcuwait)) + irq_work_queue(&con->irq_work); + } + console_srcu_read_unlock(cookie); +} + +/* + * nbcon_kthread_stop - Stop a console printer thread + * @con: Console to operate on + */ +void nbcon_kthread_stop(struct console *con) +{ + lockdep_assert_console_list_lock_held(); + + if (!con->kthread) + return; + + kthread_stop(con->kthread); + con->kthread = NULL; +} + +/** + * nbcon_kthread_create - Create a console printer thread + * @con: Console to operate on + * + * Return: True if the kthread was started or already exists. + * Otherwise false and @con must not be registered. + * + * This function is called when it will be expected that nbcon consoles are + * flushed using the kthread. The messages printed with NBCON_PRIO_NORMAL + * will be no longer flushed by the legacy loop. This is why failure must + * be fatal for console registration. + * + * If @con was already registered and this function fails, @con must be + * unregistered before the global state variable @printk_kthreads_running + * can be set. + */ +bool nbcon_kthread_create(struct console *con) +{ + struct task_struct *kt; + + lockdep_assert_console_list_lock_held(); + + if (con->kthread) + return true; + + kt = kthread_run(nbcon_kthread_func, con, "pr/%s%d", con->name, con->index); + if (WARN_ON(IS_ERR(kt))) { + con_printk(KERN_ERR, con, "failed to start printing thread\n"); + return false; + } + + con->kthread = kt; + + return true; +} + /* Track the nbcon emergency nesting per CPU. */ static DEFINE_PER_CPU(unsigned int, nbcon_pcpu_emergency_nesting); static unsigned int early_nbcon_pcpu_emergency_nesting __initdata; @@ -1396,6 +1624,12 @@ bool nbcon_alloc(struct console *con) { struct nbcon_state state = { }; + /* The write_thread() callback is mandatory. */ + if (WARN_ON(!con->write_thread)) + return false; + + rcuwait_init(&con->rcuwait); + init_irq_work(&con->irq_work, nbcon_irq_work); nbcon_state_set(con, &state); /* @@ -1418,6 +1652,14 @@ bool nbcon_alloc(struct console *con) con_printk(KERN_ERR, con, "failed to allocate printing buffer\n"); return false; } + + if (printk_kthreads_running) { + if (!nbcon_kthread_create(con)) { + kfree(con->pbufs); + con->pbufs = NULL; + return false; + } + } } return true; @@ -1431,6 +1673,9 @@ void nbcon_free(struct console *con) { struct nbcon_state state = { }; + if (printk_kthreads_running) + nbcon_kthread_stop(con); + nbcon_state_set(con, &state); /* Boot consoles share global printk buffers. */ diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 846306ac2663..f27c76c3b5cf 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -34,6 +34,7 @@ #include #include #include +#include #include #include #include @@ -496,6 +497,9 @@ static u64 syslog_seq; static size_t syslog_partial; static bool syslog_time; +/* True when _all_ printer threads are available for printing. */ +bool printk_kthreads_running; + struct latched_seq { seqcount_latch_t latch; u64 val[2]; @@ -3027,6 +3031,8 @@ static bool console_emit_next_record(struct console *con, bool *handover, int co return false; } +static inline void printk_kthreads_check_locked(void) { } + #endif /* CONFIG_PRINTK */ /* @@ -3387,6 +3393,102 @@ void console_start(struct console *console) } EXPORT_SYMBOL(console_start); +#ifdef CONFIG_PRINTK +static int unregister_console_locked(struct console *console); + +/* True when system boot is far enough to create printer threads. */ +static bool printk_kthreads_ready __ro_after_init; + +/** + * printk_kthreads_shutdown - shutdown all threaded printers + * + * On system shutdown all threaded printers are stopped. This allows printk + * to transition back to atomic printing, thus providing a robust mechanism + * for the final shutdown/reboot messages to be output. + */ +static void printk_kthreads_shutdown(void) +{ + struct console *con; + + console_list_lock(); + if (printk_kthreads_running) { + printk_kthreads_running = false; + + for_each_console(con) { + if (con->flags & CON_NBCON) + nbcon_kthread_stop(con); + } + + /* + * The threads may have been stopped while printing a + * backlog. Flush any records left over. + */ + nbcon_atomic_flush_pending(); + } + console_list_unlock(); +} + +static struct syscore_ops printk_syscore_ops = { + .shutdown = printk_kthreads_shutdown, +}; + +/* + * If appropriate, start nbcon kthreads and set @printk_kthreads_running. + * If any kthreads fail to start, those consoles are unregistered. + * + * Must be called under console_list_lock(). + */ +static void printk_kthreads_check_locked(void) +{ + struct hlist_node *tmp; + struct console *con; + + lockdep_assert_console_list_lock_held(); + + if (!printk_kthreads_ready) + return; + + /* + * Printer threads cannot be started as long as any boot console is + * registered because there is no way to synchronize the hardware + * registers between boot console code and regular console code. + * It can only be known that there will be no new boot consoles when + * an nbcon console is registered. + */ + if (have_boot_console || !have_nbcon_console) { + /* Clear flag in case all nbcon consoles unregistered. */ + printk_kthreads_running = false; + return; + } + + if (printk_kthreads_running) + return; + + hlist_for_each_entry_safe(con, tmp, &console_list, node) { + if (!(con->flags & CON_NBCON)) + continue; + + if (!nbcon_kthread_create(con)) + unregister_console_locked(con); + } + + printk_kthreads_running = true; +} + +static int __init printk_set_kthreads_ready(void) +{ + register_syscore_ops(&printk_syscore_ops); + + console_list_lock(); + printk_kthreads_ready = true; + printk_kthreads_check_locked(); + console_list_unlock(); + + return 0; +} +early_initcall(printk_set_kthreads_ready); +#endif /* CONFIG_PRINTK */ + static int __read_mostly keep_bootcon; static int __init keep_bootcon_setup(char *str) @@ -3745,6 +3847,9 @@ void register_console(struct console *newcon) unregister_console_locked(con); } } + + /* Changed console list, may require printer threads to start/stop. */ + printk_kthreads_check_locked(); unlock: console_list_unlock(); } @@ -3841,6 +3946,9 @@ static int unregister_console_locked(struct console *console) if (!found_nbcon_con) have_nbcon_console = found_nbcon_con; + /* Changed console list, may require printer threads to start/stop. */ + printk_kthreads_check_locked(); + return res; } -- cgit v1.2.3 From 5102981d5e2a5a7a12424b5d26c7524ac2899898 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Wed, 4 Sep 2024 14:11:30 +0206 Subject: printk: nbcon: Show replay message on takeover An emergency or panic context can takeover console ownership while the current owner was printing a printk message. The atomic printer will re-print the message that the previous owner was printing. However, this can look confusing to the user and may even seem as though a message was lost. [3430014.1 [3430014.181123] usb 1-2: Product: USB Audio Add a new field @nbcon_prev_seq to struct console to track the sequence number to print that was assigned to the previous console owner. If this matches the sequence number to print that the current owner is assigned, then a takeover must have occurred. In this case, print an additional message to inform the user that the previous message is being printed again. [3430014.1 ** replaying previous printk message ** [3430014.181123] usb 1-2: Product: USB Audio Signed-off-by: John Ogness Reviewed-by: Petr Mladek Link: https://lore.kernel.org/r/20240904120536.115780-12-john.ogness@linutronix.de Signed-off-by: Petr Mladek --- include/linux/console.h | 2 ++ kernel/printk/internal.h | 1 + kernel/printk/nbcon.c | 26 ++++++++++++++++++++++++++ kernel/printk/printk.c | 11 +++++++++++ 4 files changed, 40 insertions(+) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index 788ce9c829f6..eba367bf605d 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -325,6 +325,7 @@ struct nbcon_write_context { * @nbcon_state: State for nbcon consoles * @nbcon_seq: Sequence number of the next record for nbcon to print * @nbcon_device_ctxt: Context available for non-printing operations + * @nbcon_prev_seq: Seq num the previous nbcon owner was assigned to print * @pbufs: Pointer to nbcon private buffer * @kthread: Printer kthread for this console * @rcuwait: RCU-safe wait object for @kthread waking @@ -459,6 +460,7 @@ struct console { atomic_t __private nbcon_state; atomic_long_t __private nbcon_seq; struct nbcon_context __private nbcon_device_ctxt; + atomic_long_t __private nbcon_prev_seq; struct printk_buffers *pbufs; struct task_struct *kthread; diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h index 8166e24f8780..c365d25b13c7 100644 --- a/kernel/printk/internal.h +++ b/kernel/printk/internal.h @@ -319,4 +319,5 @@ bool printk_get_next_message(struct printk_message *pmsg, u64 seq, #ifdef CONFIG_PRINTK void console_prepend_dropped(struct printk_message *pmsg, unsigned long dropped); +void console_prepend_replay(struct printk_message *pmsg); #endif diff --git a/kernel/printk/nbcon.c b/kernel/printk/nbcon.c index 5146ce9853a3..98440889d222 100644 --- a/kernel/printk/nbcon.c +++ b/kernel/printk/nbcon.c @@ -946,7 +946,9 @@ static bool nbcon_emit_next_record(struct nbcon_write_context *wctxt, bool use_a .pbufs = ctxt->pbufs, }; unsigned long con_dropped; + struct nbcon_state cur; unsigned long dropped; + unsigned long ulseq; /* * This function should never be called for consoles that have not @@ -987,6 +989,29 @@ static bool nbcon_emit_next_record(struct nbcon_write_context *wctxt, bool use_a if (dropped && !is_extended) console_prepend_dropped(&pmsg, dropped); + /* + * If the previous owner was assigned the same record, this context + * has taken over ownership and is replaying the record. Prepend a + * message to let the user know the record is replayed. + */ + ulseq = atomic_long_read(&ACCESS_PRIVATE(con, nbcon_prev_seq)); + if (__ulseq_to_u64seq(prb, ulseq) == pmsg.seq) { + console_prepend_replay(&pmsg); + } else { + /* + * Ensure this context is still the owner before trying to + * update @nbcon_prev_seq. Otherwise the value in @ulseq may + * not be from the previous owner and instead be some later + * value from the context that took over ownership. + */ + nbcon_state_read(con, &cur); + if (!nbcon_context_can_proceed(ctxt, &cur)) + return false; + + atomic_long_try_cmpxchg(&ACCESS_PRIVATE(con, nbcon_prev_seq), &ulseq, + __u64seq_to_ulseq(pmsg.seq)); + } + if (!nbcon_context_exit_unsafe(ctxt)) return false; @@ -1646,6 +1671,7 @@ bool nbcon_alloc(struct console *con) rcuwait_init(&con->rcuwait); init_irq_work(&con->irq_work, nbcon_irq_work); + atomic_long_set(&ACCESS_PRIVATE(con, nbcon_prev_seq), -1UL); nbcon_state_set(con, &state); /* diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index e9458569bcfd..c27dc54f4151 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2902,6 +2902,17 @@ void console_prepend_dropped(struct printk_message *pmsg, unsigned long dropped) console_prepend_message(pmsg, "** %lu printk messages dropped **\n", dropped); } +/* + * Prepend the message in @pmsg->pbufs->outbuf with a "replay message". + * @pmsg->outbuf_len is updated appropriately. + * + * @pmsg is the printk message to prepend. + */ +void console_prepend_replay(struct printk_message *pmsg) +{ + console_prepend_message(pmsg, "** replaying previous printk message **\n"); +} + /* * Read and format the specified record (or a later record if the specified * record is not available). -- cgit v1.2.3 From a4d398a573d0f0c98c39d4af1866a3edaec4959c Mon Sep 17 00:00:00 2001 From: Kunwu Chan Date: Mon, 2 Sep 2024 07:43:23 +0100 Subject: ARM: 9416/1: amba: make amba_bustype constant Since commit d492cc2573a0 ("driver core: device.h: make struct bus_type a const *"), the driver core can properly handle constant struct bus_type, move the amba_bustype variable to be a constant structure as well, placing it into read-only memory which can not be modified at runtime. Cc: Greg Kroah-Hartman Suggested-by: Greg Kroah-Hartman Signed-off-by: Kunwu Chan Signed-off-by: Russell King (Oracle) --- drivers/amba/bus.c | 2 +- include/linux/amba/bus.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c index 34bc880ca20b..0230c43377c1 100644 --- a/drivers/amba/bus.c +++ b/drivers/amba/bus.c @@ -435,7 +435,7 @@ static const struct dev_pm_ops amba_pm = { * DMA configuration for platform and AMBA bus is same. So here we reuse * platform's DMA config routine. */ -struct bus_type amba_bustype = { +const struct bus_type amba_bustype = { .name = "amba", .dev_groups = amba_dev_groups, .match = amba_match, diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index 958a55bcc708..dda2f3ea89cb 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -105,7 +105,7 @@ enum amba_vendor { AMBA_VENDOR_LSI = 0xb6, }; -extern struct bus_type amba_bustype; +extern const struct bus_type amba_bustype; #define to_amba_device(d) container_of_const(d, struct amba_device, dev) -- cgit v1.2.3 From 593377036e50de89132bc1222800174fde0780ec Mon Sep 17 00:00:00 2001 From: Leonardo Bras Date: Fri, 10 May 2024 23:05:56 -0300 Subject: kvm: Note an RCU quiescent state on guest exit As of today, KVM notes a quiescent state only in guest entry, which is good as it avoids the guest being interrupted for current RCU operations. While the guest vcpu runs, it can be interrupted by a timer IRQ that will check for any RCU operations waiting for this CPU. In case there are any of such, it invokes rcu_core() in order to sched-out the current thread and note a quiescent state. This occasional schedule work will introduce tens of microsseconds of latency, which is really bad for vcpus running latency-sensitive applications, such as real-time workloads. So, note a quiescent state in guest exit, so the interrupted guests is able to deal with any pending RCU operations before being required to invoke rcu_core(), and thus avoid the overhead of related scheduler work. Signed-off-by: Leonardo Bras Acked-by: Paul E. McKenney Acked-by: Sean Christopherson Message-ID: <20240511020557.1198200-1-leobras@redhat.com> Signed-off-by: Paolo Bonzini --- include/linux/context_tracking.h | 6 ++++-- include/linux/kvm_host.h | 10 +++++++++- 2 files changed, 13 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 6e76b9dba00e..8a78fabeafc3 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -80,10 +80,12 @@ static __always_inline bool context_tracking_guest_enter(void) return context_tracking_enabled_this_cpu(); } -static __always_inline void context_tracking_guest_exit(void) +static __always_inline bool context_tracking_guest_exit(void) { if (context_tracking_enabled()) __ct_user_exit(CONTEXT_GUEST); + + return context_tracking_enabled_this_cpu(); } #define CT_WARN_ON(cond) WARN_ON(context_tracking_enabled() && (cond)) @@ -98,7 +100,7 @@ static inline void exception_exit(enum ctx_state prev_ctx) { } static inline int ct_state(void) { return -1; } static inline int __ct_state(void) { return -1; } static __always_inline bool context_tracking_guest_enter(void) { return false; } -static __always_inline void context_tracking_guest_exit(void) { } +static __always_inline bool context_tracking_guest_exit(void) { return false; } #define CT_WARN_ON(cond) do { } while (0) #endif /* !CONFIG_CONTEXT_TRACKING_USER */ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index b23c6d48392f..0d5125a3e31a 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -485,7 +485,15 @@ static __always_inline void guest_state_enter_irqoff(void) */ static __always_inline void guest_context_exit_irqoff(void) { - context_tracking_guest_exit(); + /* + * Guest mode is treated as a quiescent state, see + * guest_context_enter_irqoff() for more details. + */ + if (!context_tracking_guest_exit()) { + instrumentation_begin(); + rcu_virt_note_context_switch(); + instrumentation_end(); + } } /* -- cgit v1.2.3 From 2097154a10c6ee78be8796411e5d0ad81ee06ed6 Mon Sep 17 00:00:00 2001 From: Alexander Mikhalitsyn Date: Tue, 3 Sep 2024 17:16:12 +0200 Subject: namespace: introduce SB_I_NOIDMAP flag Right now we determine if filesystem support vfs idmappings or not basing on the FS_ALLOW_IDMAP flag presence. This "static" way works perfecly well for local filesystems like ext4, xfs, btrfs, etc. But for network-like filesystems like fuse, cephfs this approach is not ideal, because sometimes proper support of vfs idmaps requires some extensions for the on-wire protocol, which implies that changes have to be made not only in the Linux kernel code but also in the 3rd party components like libfuse, cephfs MDS server and so on. We have seen that issue during our work on cephfs idmapped mounts [1] with Christian, but right now I'm working on the idmapped mounts support for fuse/virtiofs and I think that it is a right time for this extension. [1] 5ccd8530dd7 ("ceph: handle idmapped mounts in create_request_message()") Suggested-by: Christian Brauner Signed-off-by: Alexander Mikhalitsyn Reviewed-by: Christian Brauner Signed-off-by: Miklos Szeredi --- fs/namespace.c | 4 ++++ include/linux/fs.h | 1 + 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/fs/namespace.c b/fs/namespace.c index 328087a4df8a..d1702285c915 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -4436,6 +4436,10 @@ static int can_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt) if (!(m->mnt_sb->s_type->fs_flags & FS_ALLOW_IDMAP)) return -EINVAL; + /* The filesystem has turned off idmapped mounts. */ + if (m->mnt_sb->s_iflags & SB_I_NOIDMAP) + return -EINVAL; + /* We're not controlling the superblock. */ if (!ns_capable(fs_userns, CAP_SYS_ADMIN)) return -EPERM; diff --git a/include/linux/fs.h b/include/linux/fs.h index fd34b5755c0b..6ff547ef21f2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1189,6 +1189,7 @@ extern int send_sigurg(struct fown_struct *fown); #define SB_I_TS_EXPIRY_WARNED 0x00000400 /* warned about timestamp range expiry */ #define SB_I_RETIRED 0x00000800 /* superblock shouldn't be reused */ #define SB_I_NOUMASK 0x00001000 /* VFS does not apply umask */ +#define SB_I_NOIDMAP 0x00002000 /* No idmapped mounts on this superblock */ /* Possible states of 'frozen' field */ enum { -- cgit v1.2.3 From 071f24ad28cdcdfa544fdb79b1b1d2b423717a11 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 29 Aug 2024 21:35:54 -0700 Subject: KVM: Rename arch hooks related to per-CPU virtualization enabling Rename the per-CPU hooks used to enable virtualization in hardware to align with the KVM-wide helpers in kvm_main.c, and to better capture that the callbacks are invoked on every online CPU. No functional change intended. Suggested-by: Paolo Bonzini Signed-off-by: Sean Christopherson Reviewed-by: Kai Huang Message-ID: <20240830043600.127750-5-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/arm64/kvm/arm.c | 6 +++--- arch/loongarch/kvm/main.c | 4 ++-- arch/mips/kvm/mips.c | 4 ++-- arch/riscv/kvm/main.c | 4 ++-- arch/x86/kvm/x86.c | 6 +++--- include/linux/kvm_host.h | 4 ++-- virt/kvm/kvm_main.c | 4 ++-- 7 files changed, 16 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 9bef7638342e..9c8f5390ec63 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -2163,7 +2163,7 @@ static void cpu_hyp_uninit(void *discard) } } -int kvm_arch_hardware_enable(void) +int kvm_arch_enable_virtualization_cpu(void) { /* * Most calls to this function are made with migration @@ -2183,7 +2183,7 @@ int kvm_arch_hardware_enable(void) return 0; } -void kvm_arch_hardware_disable(void) +void kvm_arch_disable_virtualization_cpu(void) { kvm_timer_cpu_down(); kvm_vgic_cpu_down(); @@ -2379,7 +2379,7 @@ static int __init do_pkvm_init(u32 hyp_va_bits) /* * The stub hypercalls are now disabled, so set our local flag to - * prevent a later re-init attempt in kvm_arch_hardware_enable(). + * prevent a later re-init attempt in kvm_arch_enable_virtualization_cpu(). */ __this_cpu_write(kvm_hyp_initialized, 1); preempt_enable(); diff --git a/arch/loongarch/kvm/main.c b/arch/loongarch/kvm/main.c index 844736b99d38..27e9b94c0a0b 100644 --- a/arch/loongarch/kvm/main.c +++ b/arch/loongarch/kvm/main.c @@ -261,7 +261,7 @@ long kvm_arch_dev_ioctl(struct file *filp, return -ENOIOCTLCMD; } -int kvm_arch_hardware_enable(void) +int kvm_arch_enable_virtualization_cpu(void) { unsigned long env, gcfg = 0; @@ -300,7 +300,7 @@ int kvm_arch_hardware_enable(void) return 0; } -void kvm_arch_hardware_disable(void) +void kvm_arch_disable_virtualization_cpu(void) { write_csr_gcfg(0); write_csr_gstat(0); diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index b5de770b092e..52e1f275351e 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -125,12 +125,12 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) return 1; } -int kvm_arch_hardware_enable(void) +int kvm_arch_enable_virtualization_cpu(void) { return kvm_mips_callbacks->hardware_enable(); } -void kvm_arch_hardware_disable(void) +void kvm_arch_disable_virtualization_cpu(void) { kvm_mips_callbacks->hardware_disable(); } diff --git a/arch/riscv/kvm/main.c b/arch/riscv/kvm/main.c index bab2ec34cd87..f3427f6de608 100644 --- a/arch/riscv/kvm/main.c +++ b/arch/riscv/kvm/main.c @@ -20,7 +20,7 @@ long kvm_arch_dev_ioctl(struct file *filp, return -EINVAL; } -int kvm_arch_hardware_enable(void) +int kvm_arch_enable_virtualization_cpu(void) { csr_write(CSR_HEDELEG, KVM_HEDELEG_DEFAULT); csr_write(CSR_HIDELEG, KVM_HIDELEG_DEFAULT); @@ -35,7 +35,7 @@ int kvm_arch_hardware_enable(void) return 0; } -void kvm_arch_hardware_disable(void) +void kvm_arch_disable_virtualization_cpu(void) { kvm_riscv_aia_disable(); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 70219e406987..1182baf0d487 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -355,7 +355,7 @@ static void kvm_on_user_return(struct user_return_notifier *urn) /* * Disabling irqs at this point since the following code could be - * interrupted and executed through kvm_arch_hardware_disable() + * interrupted and executed through kvm_arch_disable_virtualization_cpu() */ local_irq_save(flags); if (msrs->registered) { @@ -12512,7 +12512,7 @@ void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) } EXPORT_SYMBOL_GPL(kvm_vcpu_deliver_sipi_vector); -int kvm_arch_hardware_enable(void) +int kvm_arch_enable_virtualization_cpu(void) { struct kvm *kvm; struct kvm_vcpu *vcpu; @@ -12608,7 +12608,7 @@ int kvm_arch_hardware_enable(void) return 0; } -void kvm_arch_hardware_disable(void) +void kvm_arch_disable_virtualization_cpu(void) { kvm_x86_call(hardware_disable)(); drop_user_return_notifiers(); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index b23c6d48392f..4ceecba64f93 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1521,8 +1521,8 @@ static inline void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu) {} #endif #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING -int kvm_arch_hardware_enable(void); -void kvm_arch_hardware_disable(void); +int kvm_arch_enable_virtualization_cpu(void); +void kvm_arch_disable_virtualization_cpu(void); #endif int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 4efbf9f84149..7ada2b669d51 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -5583,7 +5583,7 @@ static int kvm_enable_virtualization_cpu(void) if (__this_cpu_read(virtualization_enabled)) return 0; - if (kvm_arch_hardware_enable()) { + if (kvm_arch_enable_virtualization_cpu()) { pr_info("kvm: enabling virtualization on CPU%d failed\n", raw_smp_processor_id()); return -EIO; @@ -5608,7 +5608,7 @@ static void kvm_disable_virtualization_cpu(void *ign) if (!__this_cpu_read(virtualization_enabled)) return; - kvm_arch_hardware_disable(); + kvm_arch_disable_virtualization_cpu(); __this_cpu_write(virtualization_enabled, false); } -- cgit v1.2.3 From b67107a251b01161956892352d53fb122346eda1 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 29 Aug 2024 21:35:58 -0700 Subject: KVM: Add arch hooks for enabling/disabling virtualization Add arch hooks that are invoked when KVM enables/disable virtualization. x86 will use the hooks to register an "emergency disable" callback, which is essentially an x86-specific shutdown notifier that is used when the kernel is doing an emergency reboot/shutdown/kexec. Add comments for the declarations to help arch code understand exactly when the callbacks are invoked. Alternatively, the APIs themselves could communicate most of the same info, but kvm_arch_pre_enable_virtualization() and kvm_arch_post_disable_virtualization() are a bit cumbersome, and make it a bit less obvious that they are intended to be implemented as a pair. Reviewed-by: Chao Gao Reviewed-by: Kai Huang Acked-by: Kai Huang Tested-by: Farrah Chen Signed-off-by: Sean Christopherson Message-ID: <20240830043600.127750-9-seanjc@google.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 14 ++++++++++++++ virt/kvm/kvm_main.c | 14 ++++++++++++++ 2 files changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 4ceecba64f93..dfd6ad66efcc 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1521,6 +1521,20 @@ static inline void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu) {} #endif #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING +/* + * kvm_arch_{enable,disable}_virtualization() are called on one CPU, under + * kvm_usage_lock, immediately after/before 0=>1 and 1=>0 transitions of + * kvm_usage_count, i.e. at the beginning of the generic hardware enabling + * sequence, and at the end of the generic hardware disabling sequence. + */ +void kvm_arch_enable_virtualization(void); +void kvm_arch_disable_virtualization(void); +/* + * kvm_arch_{enable,disable}_virtualization_cpu() are called on "every" CPU to + * do the actual twiddling of hardware bits. The hooks are called on all + * online CPUs when KVM enables/disabled virtualization, and on a single CPU + * when that CPU is onlined/offlined (including for Resume/Suspend). + */ int kvm_arch_enable_virtualization_cpu(void); void kvm_arch_disable_virtualization_cpu(void); #endif diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 3a18da68b0ca..5f9a66df7bfb 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -5581,6 +5581,16 @@ static DEFINE_PER_CPU(bool, virtualization_enabled); static DEFINE_MUTEX(kvm_usage_lock); static int kvm_usage_count; +__weak void kvm_arch_enable_virtualization(void) +{ + +} + +__weak void kvm_arch_disable_virtualization(void) +{ + +} + static int kvm_enable_virtualization_cpu(void) { if (__this_cpu_read(virtualization_enabled)) @@ -5680,6 +5690,8 @@ static int kvm_enable_virtualization(void) if (kvm_usage_count++) return 0; + kvm_arch_enable_virtualization(); + r = cpuhp_setup_state(CPUHP_AP_KVM_ONLINE, "kvm/cpu:online", kvm_online_cpu, kvm_offline_cpu); if (r) @@ -5710,6 +5722,7 @@ err_rebooting: unregister_syscore_ops(&kvm_syscore_ops); cpuhp_remove_state(CPUHP_AP_KVM_ONLINE); err_cpuhp: + kvm_arch_disable_virtualization(); --kvm_usage_count; return r; } @@ -5723,6 +5736,7 @@ static void kvm_disable_virtualization(void) unregister_syscore_ops(&kvm_syscore_ops); cpuhp_remove_state(CPUHP_AP_KVM_ONLINE); + kvm_arch_disable_virtualization(); } static int kvm_init_virtualization(void) -- cgit v1.2.3 From 940ce73bdec5a020fec058ba947d2bf627462c53 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 4 Sep 2024 11:08:44 -0700 Subject: bpf: Remove the insn_buf array stack usage from the inline_bpf_loop() This patch removes the insn_buf array stack usage from the inline_bpf_loop(). Instead, the env->insn_buf is used. The usage in inline_bpf_loop() needs more than 16 insn, so the INSN_BUF_SIZE needs to be increased from 16 to 32. The compiler stack size warning on the verifier is gone after this change. Cc: Eduard Zingerman Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20240904180847.56947-2-martin.lau@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 2 +- kernel/bpf/verifier.c | 83 ++++++++++++++++++++++---------------------- 2 files changed, 43 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 2e20207315a9..8458632824a4 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -24,7 +24,7 @@ */ #define TMP_STR_BUF_LEN 320 /* Patch buffer size */ -#define INSN_BUF_SIZE 16 +#define INSN_BUF_SIZE 32 /* Liveness marks, used for registers and spilled-regs (in stack slots). * Read marks propagate upwards until they find a write mark; they record that diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 217eb0eafa2a..8bfb14d1eb7a 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -21232,7 +21232,7 @@ static struct bpf_prog *inline_bpf_loop(struct bpf_verifier_env *env, int position, s32 stack_base, u32 callback_subprogno, - u32 *cnt) + u32 *total_cnt) { s32 r6_offset = stack_base + 0 * BPF_REG_SIZE; s32 r7_offset = stack_base + 1 * BPF_REG_SIZE; @@ -21241,55 +21241,56 @@ static struct bpf_prog *inline_bpf_loop(struct bpf_verifier_env *env, int reg_loop_cnt = BPF_REG_7; int reg_loop_ctx = BPF_REG_8; + struct bpf_insn *insn_buf = env->insn_buf; struct bpf_prog *new_prog; u32 callback_start; u32 call_insn_offset; s32 callback_offset; + u32 cnt = 0; /* This represents an inlined version of bpf_iter.c:bpf_loop, * be careful to modify this code in sync. */ - struct bpf_insn insn_buf[] = { - /* Return error and jump to the end of the patch if - * expected number of iterations is too big. - */ - BPF_JMP_IMM(BPF_JLE, BPF_REG_1, BPF_MAX_LOOPS, 2), - BPF_MOV32_IMM(BPF_REG_0, -E2BIG), - BPF_JMP_IMM(BPF_JA, 0, 0, 16), - /* spill R6, R7, R8 to use these as loop vars */ - BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, r6_offset), - BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_7, r7_offset), - BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_8, r8_offset), - /* initialize loop vars */ - BPF_MOV64_REG(reg_loop_max, BPF_REG_1), - BPF_MOV32_IMM(reg_loop_cnt, 0), - BPF_MOV64_REG(reg_loop_ctx, BPF_REG_3), - /* loop header, - * if reg_loop_cnt >= reg_loop_max skip the loop body - */ - BPF_JMP_REG(BPF_JGE, reg_loop_cnt, reg_loop_max, 5), - /* callback call, - * correct callback offset would be set after patching - */ - BPF_MOV64_REG(BPF_REG_1, reg_loop_cnt), - BPF_MOV64_REG(BPF_REG_2, reg_loop_ctx), - BPF_CALL_REL(0), - /* increment loop counter */ - BPF_ALU64_IMM(BPF_ADD, reg_loop_cnt, 1), - /* jump to loop header if callback returned 0 */ - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, -6), - /* return value of bpf_loop, - * set R0 to the number of iterations - */ - BPF_MOV64_REG(BPF_REG_0, reg_loop_cnt), - /* restore original values of R6, R7, R8 */ - BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_10, r6_offset), - BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_10, r7_offset), - BPF_LDX_MEM(BPF_DW, BPF_REG_8, BPF_REG_10, r8_offset), - }; - *cnt = ARRAY_SIZE(insn_buf); - new_prog = bpf_patch_insn_data(env, position, insn_buf, *cnt); + /* Return error and jump to the end of the patch if + * expected number of iterations is too big. + */ + insn_buf[cnt++] = BPF_JMP_IMM(BPF_JLE, BPF_REG_1, BPF_MAX_LOOPS, 2); + insn_buf[cnt++] = BPF_MOV32_IMM(BPF_REG_0, -E2BIG); + insn_buf[cnt++] = BPF_JMP_IMM(BPF_JA, 0, 0, 16); + /* spill R6, R7, R8 to use these as loop vars */ + insn_buf[cnt++] = BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, r6_offset); + insn_buf[cnt++] = BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_7, r7_offset); + insn_buf[cnt++] = BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_8, r8_offset); + /* initialize loop vars */ + insn_buf[cnt++] = BPF_MOV64_REG(reg_loop_max, BPF_REG_1); + insn_buf[cnt++] = BPF_MOV32_IMM(reg_loop_cnt, 0); + insn_buf[cnt++] = BPF_MOV64_REG(reg_loop_ctx, BPF_REG_3); + /* loop header, + * if reg_loop_cnt >= reg_loop_max skip the loop body + */ + insn_buf[cnt++] = BPF_JMP_REG(BPF_JGE, reg_loop_cnt, reg_loop_max, 5); + /* callback call, + * correct callback offset would be set after patching + */ + insn_buf[cnt++] = BPF_MOV64_REG(BPF_REG_1, reg_loop_cnt); + insn_buf[cnt++] = BPF_MOV64_REG(BPF_REG_2, reg_loop_ctx); + insn_buf[cnt++] = BPF_CALL_REL(0); + /* increment loop counter */ + insn_buf[cnt++] = BPF_ALU64_IMM(BPF_ADD, reg_loop_cnt, 1); + /* jump to loop header if callback returned 0 */ + insn_buf[cnt++] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, -6); + /* return value of bpf_loop, + * set R0 to the number of iterations + */ + insn_buf[cnt++] = BPF_MOV64_REG(BPF_REG_0, reg_loop_cnt); + /* restore original values of R6, R7, R8 */ + insn_buf[cnt++] = BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_10, r6_offset); + insn_buf[cnt++] = BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_10, r7_offset); + insn_buf[cnt++] = BPF_LDX_MEM(BPF_DW, BPF_REG_8, BPF_REG_10, r8_offset); + + *total_cnt = cnt; + new_prog = bpf_patch_insn_data(env, position, insn_buf, cnt); if (!new_prog) return new_prog; -- cgit v1.2.3 From a8532fac7b5d27b8d62008a89593dccb6f9786ef Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 30 Aug 2024 22:02:34 -1000 Subject: sched_ext: TASK_DEAD tasks must be switched into SCX on ops_enable During scx_ops_enable(), SCX needs to invoke the sleepable ops.init_task() on every task. To do this, it does get_task_struct() on each iterated task, drop the lock and then call ops.init_task(). However, a TASK_DEAD task may already have lost all its usage count and be waiting for RCU grace period to be freed. If get_task_struct() is called on such task, use-after-free can happen. To avoid such situations, scx_ops_enable() skips initialization of TASK_DEAD tasks, which seems safe as they are never going to be scheduled again. Unfortunately, a racing sched_setscheduler(2) can grab the task before the task is unhashed and then continue to e.g. move the task from RT to SCX after TASK_DEAD is set and ops_enable skipped the task. As the task hasn't gone through scx_ops_init_task(), scx_ops_enable_task() called from switching_to_scx() triggers the following warning: sched_ext: Invalid task state transition 0 -> 3 for stress-ng-race-[2872] WARNING: CPU: 6 PID: 2367 at kernel/sched/ext.c:3327 scx_ops_enable_task+0x18f/0x1f0 ... RIP: 0010:scx_ops_enable_task+0x18f/0x1f0 ... switching_to_scx+0x13/0xa0 __sched_setscheduler+0x84e/0xa50 do_sched_setscheduler+0x104/0x1c0 __x64_sys_sched_setscheduler+0x18/0x30 do_syscall_64+0x7b/0x140 entry_SYSCALL_64_after_hwframe+0x76/0x7e As in the ops_disable path, it just doesn't seem like a good idea to leave any task in an inconsistent state, even when the task is dead. The root cause is ops_enable not being able to tell reliably whether a task is truly dead (no one else is looking at it and it's about to be freed) and was testing TASK_DEAD instead. Fix it by testing the task's usage count directly. - ops_init no longer ignores TASK_DEAD tasks. As now all users iterate all tasks, @include_dead is removed from scx_task_iter_next_locked() along with dead task filtering. - tryget_task_struct() is added. Tasks are skipped iff tryget_task_struct() fails. Signed-off-by: Tejun Heo Cc: David Vernet Cc: Peter Zijlstra --- include/linux/sched/task.h | 5 +++++ kernel/sched/ext.c | 30 +++++++++++++----------------- 2 files changed, 18 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 4df2f9055587..0f2aeb37bbb0 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -120,6 +120,11 @@ static inline struct task_struct *get_task_struct(struct task_struct *t) return t; } +static inline struct task_struct *tryget_task_struct(struct task_struct *t) +{ + return refcount_inc_not_zero(&t->usage) ? t : NULL; +} + extern void __put_task_struct(struct task_struct *t); extern void __put_task_struct_rcu_cb(struct rcu_head *rhp); diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index c04fc6e3ddb4..5fd2bfc01403 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -1240,11 +1240,10 @@ static struct task_struct *scx_task_iter_next(struct scx_task_iter *iter) * whether they would like to filter out dead tasks. See scx_task_iter_init() * for details. */ -static struct task_struct * -scx_task_iter_next_locked(struct scx_task_iter *iter, bool include_dead) +static struct task_struct *scx_task_iter_next_locked(struct scx_task_iter *iter) { struct task_struct *p; -retry: + scx_task_iter_rq_unlock(iter); while ((p = scx_task_iter_next(iter))) { @@ -1282,16 +1281,6 @@ retry: iter->rq = task_rq_lock(p, &iter->rf); iter->locked = p; - /* - * If we see %TASK_DEAD, @p already disabled preemption, is about to do - * the final __schedule(), won't ever need to be scheduled again and can - * thus be safely ignored. If we don't see %TASK_DEAD, @p can't enter - * the final __schedle() while we're locking its rq and thus will stay - * alive until the rq is unlocked. - */ - if (!include_dead && READ_ONCE(p->__state) == TASK_DEAD) - goto retry; - return p; } @@ -4001,7 +3990,7 @@ static void scx_ops_disable_workfn(struct kthread_work *work) * The BPF scheduler is going away. All tasks including %TASK_DEAD ones * must be switched out and exited synchronously. */ - while ((p = scx_task_iter_next_locked(&sti, true))) { + while ((p = scx_task_iter_next_locked(&sti))) { const struct sched_class *old_class = p->sched_class; struct sched_enq_and_set_ctx ctx; @@ -4632,8 +4621,15 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) spin_lock_irq(&scx_tasks_lock); scx_task_iter_init(&sti); - while ((p = scx_task_iter_next_locked(&sti, false))) { - get_task_struct(p); + while ((p = scx_task_iter_next_locked(&sti))) { + /* + * @p may already be dead, have lost all its usages counts and + * be waiting for RCU grace period before being freed. @p can't + * be initialized for SCX in such cases and should be ignored. + */ + if (!tryget_task_struct(p)) + continue; + scx_task_iter_rq_unlock(&sti); spin_unlock_irq(&scx_tasks_lock); @@ -4686,7 +4682,7 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) WRITE_ONCE(scx_switching_all, !(ops->flags & SCX_OPS_SWITCH_PARTIAL)); scx_task_iter_init(&sti); - while ((p = scx_task_iter_next_locked(&sti, false))) { + while ((p = scx_task_iter_next_locked(&sti))) { const struct sched_class *old_class = p->sched_class; struct sched_enq_and_set_ctx ctx; -- cgit v1.2.3 From 8195136669661fdfe54e9a8923c33b31c92fc1da Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 4 Sep 2024 10:24:59 -1000 Subject: sched_ext: Add cgroup support Add sched_ext_ops operations to init/exit cgroups, and track task migrations and config changes. A BPF scheduler may not implement or implement only subset of cgroup features. The implemented features can be indicated using %SCX_OPS_HAS_CGOUP_* flags. If cgroup configuration makes use of features that are not implemented, a warning is triggered. While a BPF scheduler is being enabled and disabled, relevant cgroup operations are locked out using scx_cgroup_rwsem. This avoids situations like task prep taking place while the task is being moved across cgroups, making things easier for BPF schedulers. v7: - cgroup interface file visibility toggling is dropped in favor just warning messages. Dynamically changing interface visiblity caused more confusion than helping. v6: - Updated to reflect the removal of SCX_KF_SLEEPABLE. - Updated to use CONFIG_GROUP_SCHED_WEIGHT and fixes for !CONFIG_FAIR_GROUP_SCHED && CONFIG_EXT_GROUP_SCHED. v5: - Flipped the locking order between scx_cgroup_rwsem and cpus_read_lock() to avoid locking order conflict w/ cpuset. Better documentation around locking. - sched_move_task() takes an early exit if the source and destination are identical. This triggered the warning in scx_cgroup_can_attach() as it left p->scx.cgrp_moving_from uncleared. Updated the cgroup migration path so that ops.cgroup_prep_move() is skipped for identity migrations so that its invocations always match ops.cgroup_move() one-to-one. v4: - Example schedulers moved into their own patches. - Fix build failure when !CONFIG_CGROUP_SCHED, reported by Andrea Righi. v3: - Make scx_example_pair switch all tasks by default. - Convert to BPF inline iterators. - scx_bpf_task_cgroup() is added to determine the current cgroup from CPU controller's POV. This allows BPF schedulers to accurately track CPU cgroup membership. - scx_example_flatcg added. This demonstrates flattened hierarchy implementation of CPU cgroup control and shows significant performance improvement when cgroups which are nested multiple levels are under competition. v2: - Build fixes for different CONFIG combinations. Signed-off-by: Tejun Heo Reviewed-by: David Vernet Acked-by: Josh Don Acked-by: Hao Luo Acked-by: Barret Rhoden Reported-by: kernel test robot Cc: Andrea Righi --- include/linux/sched/ext.h | 3 + init/Kconfig | 6 + kernel/sched/core.c | 67 ++- kernel/sched/ext.c | 519 +++++++++++++++++++++++- kernel/sched/ext.h | 22 + kernel/sched/sched.h | 5 + tools/sched_ext/include/scx/common.bpf.h | 1 + tools/testing/selftests/sched_ext/maximal.bpf.c | 32 ++ 8 files changed, 636 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index db2a266113ac..dc646cca4fcf 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -188,6 +188,9 @@ struct sched_ext_entity { bool disallow; /* reject switching into SCX */ /* cold fields */ +#ifdef CONFIG_EXT_GROUP_SCHED + struct cgroup *cgrp_moving_from; +#endif /* must be the last field, see init_scx_entity() */ struct list_head tasks_node; }; diff --git a/init/Kconfig b/init/Kconfig index 84332d3594d0..8c11ed61ca67 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1055,6 +1055,12 @@ config RT_GROUP_SCHED realtime bandwidth for them. See Documentation/scheduler/sched-rt-group.rst for more information. +config EXT_GROUP_SCHED + bool + depends on SCHED_CLASS_EXT && CGROUP_SCHED + select GROUP_SCHED_WEIGHT + default y + endif #CGROUP_SCHED config SCHED_MM_CID diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d302115b1522..b01b63e78d5e 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -8364,6 +8364,9 @@ void __init sched_init(void) root_task_group.shares = ROOT_TASK_GROUP_LOAD; init_cfs_bandwidth(&root_task_group.cfs_bandwidth, NULL); #endif /* CONFIG_FAIR_GROUP_SCHED */ +#ifdef CONFIG_EXT_GROUP_SCHED + root_task_group.scx_weight = CGROUP_WEIGHT_DFL; +#endif /* CONFIG_EXT_GROUP_SCHED */ #ifdef CONFIG_RT_GROUP_SCHED root_task_group.rt_se = (struct sched_rt_entity **)ptr; ptr += nr_cpu_ids * sizeof(void **); @@ -8801,6 +8804,7 @@ struct task_group *sched_create_group(struct task_group *parent) if (!alloc_rt_sched_group(tg, parent)) goto err; + scx_group_set_weight(tg, CGROUP_WEIGHT_DFL); alloc_uclamp_sched_group(tg, parent); return tg; @@ -8928,6 +8932,7 @@ void sched_move_task(struct task_struct *tsk) put_prev_task(rq, tsk); sched_change_group(tsk, group); + scx_move_task(tsk); if (queued) enqueue_task(rq, tsk, queue_flags); @@ -8965,6 +8970,11 @@ static int cpu_cgroup_css_online(struct cgroup_subsys_state *css) { struct task_group *tg = css_tg(css); struct task_group *parent = css_tg(css->parent); + int ret; + + ret = scx_tg_online(tg); + if (ret) + return ret; if (parent) sched_online_group(tg, parent); @@ -8979,6 +8989,13 @@ static int cpu_cgroup_css_online(struct cgroup_subsys_state *css) return 0; } +static void cpu_cgroup_css_offline(struct cgroup_subsys_state *css) +{ + struct task_group *tg = css_tg(css); + + scx_tg_offline(tg); +} + static void cpu_cgroup_css_released(struct cgroup_subsys_state *css) { struct task_group *tg = css_tg(css); @@ -8996,9 +9013,9 @@ static void cpu_cgroup_css_free(struct cgroup_subsys_state *css) sched_unregister_group(tg); } -#ifdef CONFIG_RT_GROUP_SCHED static int cpu_cgroup_can_attach(struct cgroup_taskset *tset) { +#ifdef CONFIG_RT_GROUP_SCHED struct task_struct *task; struct cgroup_subsys_state *css; @@ -9006,9 +9023,9 @@ static int cpu_cgroup_can_attach(struct cgroup_taskset *tset) if (!sched_rt_can_attach(css_tg(css), task)) return -EINVAL; } - return 0; -} #endif + return scx_cgroup_can_attach(tset); +} static void cpu_cgroup_attach(struct cgroup_taskset *tset) { @@ -9017,6 +9034,13 @@ static void cpu_cgroup_attach(struct cgroup_taskset *tset) cgroup_taskset_for_each(task, css, tset) sched_move_task(task); + + scx_cgroup_finish_attach(); +} + +static void cpu_cgroup_cancel_attach(struct cgroup_taskset *tset) +{ + scx_cgroup_cancel_attach(tset); } #ifdef CONFIG_UCLAMP_TASK_GROUP @@ -9196,15 +9220,25 @@ static int cpu_uclamp_max_show(struct seq_file *sf, void *v) #ifdef CONFIG_GROUP_SCHED_WEIGHT static unsigned long tg_weight(struct task_group *tg) { +#ifdef CONFIG_FAIR_GROUP_SCHED return scale_load_down(tg->shares); +#else + return sched_weight_from_cgroup(tg->scx_weight); +#endif } static int cpu_shares_write_u64(struct cgroup_subsys_state *css, struct cftype *cftype, u64 shareval) { + int ret; + if (shareval > scale_load_down(ULONG_MAX)) shareval = MAX_SHARES; - return sched_group_set_shares(css_tg(css), scale_load(shareval)); + ret = sched_group_set_shares(css_tg(css), scale_load(shareval)); + if (!ret) + scx_group_set_weight(css_tg(css), + sched_weight_to_cgroup(shareval)); + return ret; } static u64 cpu_shares_read_u64(struct cgroup_subsys_state *css, @@ -9595,7 +9629,12 @@ static s64 cpu_idle_read_s64(struct cgroup_subsys_state *css, static int cpu_idle_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, s64 idle) { - return sched_group_set_idle(css_tg(css), idle); + int ret; + + ret = sched_group_set_idle(css_tg(css), idle); + if (!ret) + scx_group_set_idle(css_tg(css), idle); + return ret; } #endif @@ -9722,13 +9761,17 @@ static int cpu_weight_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, u64 cgrp_weight) { unsigned long weight; + int ret; if (cgrp_weight < CGROUP_WEIGHT_MIN || cgrp_weight > CGROUP_WEIGHT_MAX) return -ERANGE; weight = sched_weight_from_cgroup(cgrp_weight); - return sched_group_set_shares(css_tg(css), scale_load(weight)); + ret = sched_group_set_shares(css_tg(css), scale_load(weight)); + if (!ret) + scx_group_set_weight(css_tg(css), cgrp_weight); + return ret; } static s64 cpu_weight_nice_read_s64(struct cgroup_subsys_state *css, @@ -9753,7 +9796,7 @@ static int cpu_weight_nice_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, s64 nice) { unsigned long weight; - int idx; + int idx, ret; if (nice < MIN_NICE || nice > MAX_NICE) return -ERANGE; @@ -9762,7 +9805,11 @@ static int cpu_weight_nice_write_s64(struct cgroup_subsys_state *css, idx = array_index_nospec(idx, 40); weight = sched_prio_to_weight[idx]; - return sched_group_set_shares(css_tg(css), scale_load(weight)); + ret = sched_group_set_shares(css_tg(css), scale_load(weight)); + if (!ret) + scx_group_set_weight(css_tg(css), + sched_weight_to_cgroup(weight)); + return ret; } #endif /* CONFIG_GROUP_SCHED_WEIGHT */ @@ -9878,14 +9925,14 @@ static struct cftype cpu_files[] = { struct cgroup_subsys cpu_cgrp_subsys = { .css_alloc = cpu_cgroup_css_alloc, .css_online = cpu_cgroup_css_online, + .css_offline = cpu_cgroup_css_offline, .css_released = cpu_cgroup_css_released, .css_free = cpu_cgroup_css_free, .css_extra_stat_show = cpu_extra_stat_show, .css_local_stat_show = cpu_local_stat_show, -#ifdef CONFIG_RT_GROUP_SCHED .can_attach = cpu_cgroup_can_attach, -#endif .attach = cpu_cgroup_attach, + .cancel_attach = cpu_cgroup_cancel_attach, .legacy_cftypes = cpu_legacy_files, .dfl_cftypes = cpu_files, .early_init = true, diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 5fd2bfc01403..bba9d805dc2b 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -116,10 +116,16 @@ enum scx_ops_flags { */ SCX_OPS_SWITCH_PARTIAL = 1LLU << 3, + /* + * CPU cgroup support flags + */ + SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16, /* cpu.weight */ + SCX_OPS_ALL_FLAGS = SCX_OPS_KEEP_BUILTIN_IDLE | SCX_OPS_ENQ_LAST | SCX_OPS_ENQ_EXITING | - SCX_OPS_SWITCH_PARTIAL, + SCX_OPS_SWITCH_PARTIAL | + SCX_OPS_HAS_CGROUP_WEIGHT, }; /* argument container for ops.init_task() */ @@ -129,6 +135,10 @@ struct scx_init_task_args { * to the scheduler transition path. */ bool fork; +#ifdef CONFIG_EXT_GROUP_SCHED + /* the cgroup the task is joining */ + struct cgroup *cgroup; +#endif }; /* argument container for ops.exit_task() */ @@ -137,6 +147,12 @@ struct scx_exit_task_args { bool cancelled; }; +/* argument container for ops->cgroup_init() */ +struct scx_cgroup_init_args { + /* the weight of the cgroup [1..10000] */ + u32 weight; +}; + enum scx_cpu_preempt_reason { /* next task is being scheduled by &sched_class_rt */ SCX_CPU_PREEMPT_RT, @@ -501,6 +517,79 @@ struct sched_ext_ops { */ void (*dump_task)(struct scx_dump_ctx *ctx, struct task_struct *p); +#ifdef CONFIG_EXT_GROUP_SCHED + /** + * cgroup_init - Initialize a cgroup + * @cgrp: cgroup being initialized + * @args: init arguments, see the struct definition + * + * Either the BPF scheduler is being loaded or @cgrp created, initialize + * @cgrp for sched_ext. This operation may block. + * + * Return 0 for success, -errno for failure. An error return while + * loading will abort loading of the BPF scheduler. During cgroup + * creation, it will abort the specific cgroup creation. + */ + s32 (*cgroup_init)(struct cgroup *cgrp, + struct scx_cgroup_init_args *args); + + /** + * cgroup_exit - Exit a cgroup + * @cgrp: cgroup being exited + * + * Either the BPF scheduler is being unloaded or @cgrp destroyed, exit + * @cgrp for sched_ext. This operation my block. + */ + void (*cgroup_exit)(struct cgroup *cgrp); + + /** + * cgroup_prep_move - Prepare a task to be moved to a different cgroup + * @p: task being moved + * @from: cgroup @p is being moved from + * @to: cgroup @p is being moved to + * + * Prepare @p for move from cgroup @from to @to. This operation may + * block and can be used for allocations. + * + * Return 0 for success, -errno for failure. An error return aborts the + * migration. + */ + s32 (*cgroup_prep_move)(struct task_struct *p, + struct cgroup *from, struct cgroup *to); + + /** + * cgroup_move - Commit cgroup move + * @p: task being moved + * @from: cgroup @p is being moved from + * @to: cgroup @p is being moved to + * + * Commit the move. @p is dequeued during this operation. + */ + void (*cgroup_move)(struct task_struct *p, + struct cgroup *from, struct cgroup *to); + + /** + * cgroup_cancel_move - Cancel cgroup move + * @p: task whose cgroup move is being canceled + * @from: cgroup @p was being moved from + * @to: cgroup @p was being moved to + * + * @p was cgroup_prep_move()'d but failed before reaching cgroup_move(). + * Undo the preparation. + */ + void (*cgroup_cancel_move)(struct task_struct *p, + struct cgroup *from, struct cgroup *to); + + /** + * cgroup_set_weight - A cgroup's weight is being changed + * @cgrp: cgroup whose weight is being updated + * @weight: new weight [1..10000] + * + * Update @tg's weight to @weight. + */ + void (*cgroup_set_weight)(struct cgroup *cgrp, u32 weight); +#endif /* CONFIG_CGROUPS */ + /* * All online ops must come before ops.cpu_online(). */ @@ -683,6 +772,11 @@ enum scx_kick_flags { SCX_KICK_WAIT = 1LLU << 2, }; +enum scx_tg_flags { + SCX_TG_ONLINE = 1U << 0, + SCX_TG_INITED = 1U << 1, +}; + enum scx_ops_enable_state { SCX_OPS_PREPPING, SCX_OPS_ENABLING, @@ -3235,6 +3329,28 @@ static void task_tick_scx(struct rq *rq, struct task_struct *curr, int queued) resched_curr(rq); } +#ifdef CONFIG_EXT_GROUP_SCHED +static struct cgroup *tg_cgrp(struct task_group *tg) +{ + /* + * If CGROUP_SCHED is disabled, @tg is NULL. If @tg is an autogroup, + * @tg->css.cgroup is NULL. In both cases, @tg can be treated as the + * root cgroup. + */ + if (tg && tg->css.cgroup) + return tg->css.cgroup; + else + return &cgrp_dfl_root.cgrp; +} + +#define SCX_INIT_TASK_ARGS_CGROUP(tg) .cgroup = tg_cgrp(tg), + +#else /* CONFIG_EXT_GROUP_SCHED */ + +#define SCX_INIT_TASK_ARGS_CGROUP(tg) + +#endif /* CONFIG_EXT_GROUP_SCHED */ + static enum scx_task_state scx_get_task_state(const struct task_struct *p) { return (p->scx.flags & SCX_TASK_STATE_MASK) >> SCX_TASK_STATE_SHIFT; @@ -3279,6 +3395,7 @@ static int scx_ops_init_task(struct task_struct *p, struct task_group *tg, bool if (SCX_HAS_OP(init_task)) { struct scx_init_task_args args = { + SCX_INIT_TASK_ARGS_CGROUP(tg) .fork = fork, }; @@ -3343,7 +3460,7 @@ static void scx_ops_enable_task(struct task_struct *p) scx_set_task_state(p, SCX_TASK_ENABLED); if (SCX_HAS_OP(set_weight)) - SCX_CALL_OP(SCX_KF_REST, set_weight, p, p->scx.weight); + SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, p, p->scx.weight); } static void scx_ops_disable_task(struct task_struct *p) @@ -3555,6 +3672,219 @@ bool scx_can_stop_tick(struct rq *rq) } #endif +#ifdef CONFIG_EXT_GROUP_SCHED + +DEFINE_STATIC_PERCPU_RWSEM(scx_cgroup_rwsem); +static bool cgroup_warned_missing_weight; +static bool cgroup_warned_missing_idle; + +static void scx_cgroup_warn_missing_weight(struct task_group *tg) +{ + if (scx_ops_enable_state() == SCX_OPS_DISABLED || + cgroup_warned_missing_weight) + return; + + if ((scx_ops.flags & SCX_OPS_HAS_CGROUP_WEIGHT) || !tg->css.parent) + return; + + pr_warn("sched_ext: \"%s\" does not implement cgroup cpu.weight\n", + scx_ops.name); + cgroup_warned_missing_weight = true; +} + +static void scx_cgroup_warn_missing_idle(struct task_group *tg) +{ + if (scx_ops_enable_state() == SCX_OPS_DISABLED || + cgroup_warned_missing_idle) + return; + + if (!tg->idle) + return; + + pr_warn("sched_ext: \"%s\" does not implement cgroup cpu.idle\n", + scx_ops.name); + cgroup_warned_missing_idle = true; +} + +int scx_tg_online(struct task_group *tg) +{ + int ret = 0; + + WARN_ON_ONCE(tg->scx_flags & (SCX_TG_ONLINE | SCX_TG_INITED)); + + percpu_down_read(&scx_cgroup_rwsem); + + scx_cgroup_warn_missing_weight(tg); + + if (SCX_HAS_OP(cgroup_init)) { + struct scx_cgroup_init_args args = { .weight = tg->scx_weight }; + + ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init, + tg->css.cgroup, &args); + if (!ret) + tg->scx_flags |= SCX_TG_ONLINE | SCX_TG_INITED; + else + ret = ops_sanitize_err("cgroup_init", ret); + } else { + tg->scx_flags |= SCX_TG_ONLINE; + } + + percpu_up_read(&scx_cgroup_rwsem); + return ret; +} + +void scx_tg_offline(struct task_group *tg) +{ + WARN_ON_ONCE(!(tg->scx_flags & SCX_TG_ONLINE)); + + percpu_down_read(&scx_cgroup_rwsem); + + if (SCX_HAS_OP(cgroup_exit) && (tg->scx_flags & SCX_TG_INITED)) + SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, tg->css.cgroup); + tg->scx_flags &= ~(SCX_TG_ONLINE | SCX_TG_INITED); + + percpu_up_read(&scx_cgroup_rwsem); +} + +int scx_cgroup_can_attach(struct cgroup_taskset *tset) +{ + struct cgroup_subsys_state *css; + struct task_struct *p; + int ret; + + /* released in scx_finish/cancel_attach() */ + percpu_down_read(&scx_cgroup_rwsem); + + if (!scx_enabled()) + return 0; + + cgroup_taskset_for_each(p, css, tset) { + struct cgroup *from = tg_cgrp(task_group(p)); + struct cgroup *to = tg_cgrp(css_tg(css)); + + WARN_ON_ONCE(p->scx.cgrp_moving_from); + + /* + * sched_move_task() omits identity migrations. Let's match the + * behavior so that ops.cgroup_prep_move() and ops.cgroup_move() + * always match one-to-one. + */ + if (from == to) + continue; + + if (SCX_HAS_OP(cgroup_prep_move)) { + ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_prep_move, + p, from, css->cgroup); + if (ret) + goto err; + } + + p->scx.cgrp_moving_from = from; + } + + return 0; + +err: + cgroup_taskset_for_each(p, css, tset) { + if (SCX_HAS_OP(cgroup_cancel_move) && p->scx.cgrp_moving_from) + SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, p, + p->scx.cgrp_moving_from, css->cgroup); + p->scx.cgrp_moving_from = NULL; + } + + percpu_up_read(&scx_cgroup_rwsem); + return ops_sanitize_err("cgroup_prep_move", ret); +} + +void scx_move_task(struct task_struct *p) +{ + if (!scx_enabled()) + return; + + /* + * We're called from sched_move_task() which handles both cgroup and + * autogroup moves. Ignore the latter. + * + * Also ignore exiting tasks, because in the exit path tasks transition + * from the autogroup to the root group, so task_group_is_autogroup() + * alone isn't able to catch exiting autogroup tasks. This is safe for + * cgroup_move(), because cgroup migrations never happen for PF_EXITING + * tasks. + */ + if (task_group_is_autogroup(task_group(p)) || (p->flags & PF_EXITING)) + return; + + /* + * @p must have ops.cgroup_prep_move() called on it and thus + * cgrp_moving_from set. + */ + if (SCX_HAS_OP(cgroup_move) && !WARN_ON_ONCE(!p->scx.cgrp_moving_from)) + SCX_CALL_OP_TASK(SCX_KF_UNLOCKED, cgroup_move, p, + p->scx.cgrp_moving_from, tg_cgrp(task_group(p))); + p->scx.cgrp_moving_from = NULL; +} + +void scx_cgroup_finish_attach(void) +{ + percpu_up_read(&scx_cgroup_rwsem); +} + +void scx_cgroup_cancel_attach(struct cgroup_taskset *tset) +{ + struct cgroup_subsys_state *css; + struct task_struct *p; + + if (!scx_enabled()) + goto out_unlock; + + cgroup_taskset_for_each(p, css, tset) { + if (SCX_HAS_OP(cgroup_cancel_move) && p->scx.cgrp_moving_from) + SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, p, + p->scx.cgrp_moving_from, css->cgroup); + p->scx.cgrp_moving_from = NULL; + } +out_unlock: + percpu_up_read(&scx_cgroup_rwsem); +} + +void scx_group_set_weight(struct task_group *tg, unsigned long weight) +{ + percpu_down_read(&scx_cgroup_rwsem); + + if (tg->scx_weight != weight) { + if (SCX_HAS_OP(cgroup_set_weight)) + SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_set_weight, + tg_cgrp(tg), weight); + tg->scx_weight = weight; + } + + percpu_up_read(&scx_cgroup_rwsem); +} + +void scx_group_set_idle(struct task_group *tg, bool idle) +{ + percpu_down_read(&scx_cgroup_rwsem); + scx_cgroup_warn_missing_idle(tg); + percpu_up_read(&scx_cgroup_rwsem); +} + +static void scx_cgroup_lock(void) +{ + percpu_down_write(&scx_cgroup_rwsem); +} + +static void scx_cgroup_unlock(void) +{ + percpu_up_write(&scx_cgroup_rwsem); +} + +#else /* CONFIG_EXT_GROUP_SCHED */ + +static inline void scx_cgroup_lock(void) {} +static inline void scx_cgroup_unlock(void) {} + +#endif /* CONFIG_EXT_GROUP_SCHED */ + /* * Omitted operations: * @@ -3686,6 +4016,96 @@ out_unlock_rcu: rcu_read_unlock(); } +#ifdef CONFIG_EXT_GROUP_SCHED +static void scx_cgroup_exit(void) +{ + struct cgroup_subsys_state *css; + + percpu_rwsem_assert_held(&scx_cgroup_rwsem); + + /* + * scx_tg_on/offline() are excluded through scx_cgroup_rwsem. If we walk + * cgroups and exit all the inited ones, all online cgroups are exited. + */ + rcu_read_lock(); + css_for_each_descendant_post(css, &root_task_group.css) { + struct task_group *tg = css_tg(css); + + if (!(tg->scx_flags & SCX_TG_INITED)) + continue; + tg->scx_flags &= ~SCX_TG_INITED; + + if (!scx_ops.cgroup_exit) + continue; + + if (WARN_ON_ONCE(!css_tryget(css))) + continue; + rcu_read_unlock(); + + SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, css->cgroup); + + rcu_read_lock(); + css_put(css); + } + rcu_read_unlock(); +} + +static int scx_cgroup_init(void) +{ + struct cgroup_subsys_state *css; + int ret; + + percpu_rwsem_assert_held(&scx_cgroup_rwsem); + + cgroup_warned_missing_weight = false; + cgroup_warned_missing_idle = false; + + /* + * scx_tg_on/offline() are excluded thorugh scx_cgroup_rwsem. If we walk + * cgroups and init, all online cgroups are initialized. + */ + rcu_read_lock(); + css_for_each_descendant_pre(css, &root_task_group.css) { + struct task_group *tg = css_tg(css); + struct scx_cgroup_init_args args = { .weight = tg->scx_weight }; + + scx_cgroup_warn_missing_weight(tg); + scx_cgroup_warn_missing_idle(tg); + + if ((tg->scx_flags & + (SCX_TG_ONLINE | SCX_TG_INITED)) != SCX_TG_ONLINE) + continue; + + if (!scx_ops.cgroup_init) { + tg->scx_flags |= SCX_TG_INITED; + continue; + } + + if (WARN_ON_ONCE(!css_tryget(css))) + continue; + rcu_read_unlock(); + + ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init, + css->cgroup, &args); + if (ret) { + css_put(css); + return ret; + } + tg->scx_flags |= SCX_TG_INITED; + + rcu_read_lock(); + css_put(css); + } + rcu_read_unlock(); + + return 0; +} + +#else +static void scx_cgroup_exit(void) {} +static int scx_cgroup_init(void) { return 0; } +#endif + /******************************************************************************** * Sysfs interface and ops enable/disable. @@ -3978,11 +4398,12 @@ static void scx_ops_disable_workfn(struct kthread_work *work) WRITE_ONCE(scx_switching_all, false); /* - * Avoid racing against fork. See scx_ops_enable() for explanation on - * the locking order. + * Avoid racing against fork and cgroup changes. See scx_ops_enable() + * for explanation on the locking order. */ percpu_down_write(&scx_fork_rwsem); cpus_read_lock(); + scx_cgroup_lock(); spin_lock_irq(&scx_tasks_lock); scx_task_iter_init(&sti); @@ -4018,6 +4439,9 @@ static void scx_ops_disable_workfn(struct kthread_work *work) static_branch_disable_cpuslocked(&scx_builtin_idle_enabled); synchronize_rcu(); + scx_cgroup_exit(); + + scx_cgroup_unlock(); cpus_read_unlock(); percpu_up_write(&scx_fork_rwsem); @@ -4574,11 +4998,17 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) scx_watchdog_timeout / 2); /* - * Lock out forks before opening the floodgate so that they don't wander - * into the operations prematurely. + * Lock out forks, cgroup on/offlining and moves before opening the + * floodgate so that they don't wander into the operations prematurely. + * + * We don't need to keep the CPUs stable but static_branch_*() requires + * cpus_read_lock() and scx_cgroup_rwsem must nest inside + * cpu_hotplug_lock because of the following dependency chain: + * + * cpu_hotplug_lock --> cgroup_threadgroup_rwsem --> scx_cgroup_rwsem * - * We don't need to keep the CPUs stable but grab cpus_read_lock() to - * ease future locking changes for cgroup suport. + * So, we need to do cpus_read_lock() before scx_cgroup_lock() and use + * static_branch_*_cpuslocked(). * * Note that cpu_hotplug_lock must nest inside scx_fork_rwsem due to the * following dependency chain: @@ -4587,6 +5017,7 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) */ percpu_down_write(&scx_fork_rwsem); cpus_read_lock(); + scx_cgroup_lock(); check_hotplug_seq(ops); @@ -4609,6 +5040,14 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) static_branch_disable_cpuslocked(&scx_builtin_idle_enabled); } + /* + * All cgroups should be initialized before letting in tasks. cgroup + * on/offlining and task migrations are already locked out. + */ + ret = scx_cgroup_init(); + if (ret) + goto err_disable_unlock_all; + static_branch_enable_cpuslocked(&__scx_ops_enabled); /* @@ -4700,6 +5139,7 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) spin_unlock_irq(&scx_tasks_lock); preempt_enable(); + scx_cgroup_unlock(); cpus_read_unlock(); percpu_up_write(&scx_fork_rwsem); @@ -4734,6 +5174,7 @@ err_unlock: return ret; err_disable_unlock_all: + scx_cgroup_unlock(); percpu_up_write(&scx_fork_rwsem); err_disable_unlock_cpus: cpus_read_unlock(); @@ -4928,6 +5369,11 @@ static int bpf_scx_check_member(const struct btf_type *t, switch (moff) { case offsetof(struct sched_ext_ops, init_task): +#ifdef CONFIG_EXT_GROUP_SCHED + case offsetof(struct sched_ext_ops, cgroup_init): + case offsetof(struct sched_ext_ops, cgroup_exit): + case offsetof(struct sched_ext_ops, cgroup_prep_move): +#endif case offsetof(struct sched_ext_ops, cpu_online): case offsetof(struct sched_ext_ops, cpu_offline): case offsetof(struct sched_ext_ops, init): @@ -5002,6 +5448,14 @@ static s32 init_task_stub(struct task_struct *p, struct scx_init_task_args *args static void exit_task_stub(struct task_struct *p, struct scx_exit_task_args *args) {} static void enable_stub(struct task_struct *p) {} static void disable_stub(struct task_struct *p) {} +#ifdef CONFIG_EXT_GROUP_SCHED +static s32 cgroup_init_stub(struct cgroup *cgrp, struct scx_cgroup_init_args *args) { return -EINVAL; } +static void cgroup_exit_stub(struct cgroup *cgrp) {} +static s32 cgroup_prep_move_stub(struct task_struct *p, struct cgroup *from, struct cgroup *to) { return -EINVAL; } +static void cgroup_move_stub(struct task_struct *p, struct cgroup *from, struct cgroup *to) {} +static void cgroup_cancel_move_stub(struct task_struct *p, struct cgroup *from, struct cgroup *to) {} +static void cgroup_set_weight_stub(struct cgroup *cgrp, u32 weight) {} +#endif static void cpu_online_stub(s32 cpu) {} static void cpu_offline_stub(s32 cpu) {} static s32 init_stub(void) { return -EINVAL; } @@ -5031,6 +5485,14 @@ static struct sched_ext_ops __bpf_ops_sched_ext_ops = { .exit_task = exit_task_stub, .enable = enable_stub, .disable = disable_stub, +#ifdef CONFIG_EXT_GROUP_SCHED + .cgroup_init = cgroup_init_stub, + .cgroup_exit = cgroup_exit_stub, + .cgroup_prep_move = cgroup_prep_move_stub, + .cgroup_move = cgroup_move_stub, + .cgroup_cancel_move = cgroup_cancel_move_stub, + .cgroup_set_weight = cgroup_set_weight_stub, +#endif .cpu_online = cpu_online_stub, .cpu_offline = cpu_offline_stub, .init = init_stub, @@ -5280,7 +5742,8 @@ void __init init_sched_ext_class(void) * definitions so that BPF scheduler implementations can use them * through the generated vmlinux.h. */ - WRITE_ONCE(v, SCX_ENQ_WAKEUP | SCX_DEQ_SLEEP | SCX_KICK_PREEMPT); + WRITE_ONCE(v, SCX_ENQ_WAKEUP | SCX_DEQ_SLEEP | SCX_KICK_PREEMPT | + SCX_TG_ONLINE); BUG_ON(rhashtable_init(&dsq_hash, &dsq_hash_params)); init_dsq(&scx_dsq_global, SCX_DSQ_GLOBAL); @@ -6340,6 +6803,41 @@ __bpf_kfunc struct rq *scx_bpf_cpu_rq(s32 cpu) return cpu_rq(cpu); } +/** + * scx_bpf_task_cgroup - Return the sched cgroup of a task + * @p: task of interest + * + * @p->sched_task_group->css.cgroup represents the cgroup @p is associated with + * from the scheduler's POV. SCX operations should use this function to + * determine @p's current cgroup as, unlike following @p->cgroups, + * @p->sched_task_group is protected by @p's rq lock and thus atomic w.r.t. all + * rq-locked operations. Can be called on the parameter tasks of rq-locked + * operations. The restriction guarantees that @p's rq is locked by the caller. + */ +#ifdef CONFIG_CGROUP_SCHED +__bpf_kfunc struct cgroup *scx_bpf_task_cgroup(struct task_struct *p) +{ + struct task_group *tg = p->sched_task_group; + struct cgroup *cgrp = &cgrp_dfl_root.cgrp; + + if (!scx_kf_allowed_on_arg_tasks(__SCX_KF_RQ_LOCKED, p)) + goto out; + + /* + * A task_group may either be a cgroup or an autogroup. In the latter + * case, @tg->css.cgroup is %NULL. A task_group can't become the other + * kind once created. + */ + if (tg && tg->css.cgroup) + cgrp = tg->css.cgroup; + else + cgrp = &cgrp_dfl_root.cgrp; +out: + cgroup_get(cgrp); + return cgrp; +} +#endif + __bpf_kfunc_end_defs(); BTF_KFUNCS_START(scx_kfunc_ids_any) @@ -6368,6 +6866,9 @@ BTF_ID_FLAGS(func, scx_bpf_pick_any_cpu, KF_RCU) BTF_ID_FLAGS(func, scx_bpf_task_running, KF_RCU) BTF_ID_FLAGS(func, scx_bpf_task_cpu, KF_RCU) BTF_ID_FLAGS(func, scx_bpf_cpu_rq) +#ifdef CONFIG_CGROUP_SCHED +BTF_ID_FLAGS(func, scx_bpf_task_cgroup, KF_RCU | KF_ACQUIRE) +#endif BTF_KFUNCS_END(scx_kfunc_ids_any) static const struct btf_kfunc_id_set scx_kfunc_set_any = { diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h index 32d3a51f591a..246019519231 100644 --- a/kernel/sched/ext.h +++ b/kernel/sched/ext.h @@ -67,3 +67,25 @@ static inline void scx_update_idle(struct rq *rq, bool idle) #else static inline void scx_update_idle(struct rq *rq, bool idle) {} #endif + +#ifdef CONFIG_CGROUP_SCHED +#ifdef CONFIG_EXT_GROUP_SCHED +int scx_tg_online(struct task_group *tg); +void scx_tg_offline(struct task_group *tg); +int scx_cgroup_can_attach(struct cgroup_taskset *tset); +void scx_move_task(struct task_struct *p); +void scx_cgroup_finish_attach(void); +void scx_cgroup_cancel_attach(struct cgroup_taskset *tset); +void scx_group_set_weight(struct task_group *tg, unsigned long cgrp_weight); +void scx_group_set_idle(struct task_group *tg, bool idle); +#else /* CONFIG_EXT_GROUP_SCHED */ +static inline int scx_tg_online(struct task_group *tg) { return 0; } +static inline void scx_tg_offline(struct task_group *tg) {} +static inline int scx_cgroup_can_attach(struct cgroup_taskset *tset) { return 0; } +static inline void scx_move_task(struct task_struct *p) {} +static inline void scx_cgroup_finish_attach(void) {} +static inline void scx_cgroup_cancel_attach(struct cgroup_taskset *tset) {} +static inline void scx_group_set_weight(struct task_group *tg, unsigned long cgrp_weight) {} +static inline void scx_group_set_idle(struct task_group *tg, bool idle) {} +#endif /* CONFIG_EXT_GROUP_SCHED */ +#endif /* CONFIG_CGROUP_SCHED */ diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 0163f4af1c6e..b912752197d4 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -459,6 +459,11 @@ struct task_group { struct rt_bandwidth rt_bandwidth; #endif +#ifdef CONFIG_EXT_GROUP_SCHED + u32 scx_flags; /* SCX_TG_* */ + u32 scx_weight; +#endif + struct rcu_head rcu; struct list_head list; diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h index 20280df62857..457462b19966 100644 --- a/tools/sched_ext/include/scx/common.bpf.h +++ b/tools/sched_ext/include/scx/common.bpf.h @@ -61,6 +61,7 @@ s32 scx_bpf_pick_any_cpu(const cpumask_t *cpus_allowed, u64 flags) __ksym; bool scx_bpf_task_running(const struct task_struct *p) __ksym; s32 scx_bpf_task_cpu(const struct task_struct *p) __ksym; struct rq *scx_bpf_cpu_rq(s32 cpu) __ksym; +struct cgroup *scx_bpf_task_cgroup(struct task_struct *p) __ksym; static inline __attribute__((format(printf, 1, 2))) void ___scx_bpf_bstr_format_checker(const char *fmt, ...) {} diff --git a/tools/testing/selftests/sched_ext/maximal.bpf.c b/tools/testing/selftests/sched_ext/maximal.bpf.c index 44612fdaf399..00bfa9cb95d3 100644 --- a/tools/testing/selftests/sched_ext/maximal.bpf.c +++ b/tools/testing/selftests/sched_ext/maximal.bpf.c @@ -95,6 +95,32 @@ void BPF_STRUCT_OPS(maximal_exit_task, struct task_struct *p, void BPF_STRUCT_OPS(maximal_disable, struct task_struct *p) {} +s32 BPF_STRUCT_OPS(maximal_cgroup_init, struct cgroup *cgrp, + struct scx_cgroup_init_args *args) +{ + return 0; +} + +void BPF_STRUCT_OPS(maximal_cgroup_exit, struct cgroup *cgrp) +{} + +s32 BPF_STRUCT_OPS(maximal_cgroup_prep_move, struct task_struct *p, + struct cgroup *from, struct cgroup *to) +{ + return 0; +} + +void BPF_STRUCT_OPS(maximal_cgroup_move, struct task_struct *p, + struct cgroup *from, struct cgroup *to) +{} + +void BPF_STRUCT_OPS(maximal_cgroup_cancel_move, struct task_struct *p, + struct cgroup *from, struct cgroup *to) +{} + +void BPF_STRUCT_OPS(maximal_cgroup_set_weight, struct cgroup *cgrp, u32 weight) +{} + s32 BPF_STRUCT_OPS_SLEEPABLE(maximal_init) { return 0; @@ -126,6 +152,12 @@ struct sched_ext_ops maximal_ops = { .enable = maximal_enable, .exit_task = maximal_exit_task, .disable = maximal_disable, + .cgroup_init = maximal_cgroup_init, + .cgroup_exit = maximal_cgroup_exit, + .cgroup_prep_move = maximal_cgroup_prep_move, + .cgroup_move = maximal_cgroup_move, + .cgroup_cancel_move = maximal_cgroup_cancel_move, + .cgroup_set_weight = maximal_cgroup_set_weight, .init = maximal_init, .exit = maximal_exit, .name = "maximal", -- cgit v1.2.3 From 4e893545ef8712d25f3176790ebb95beb073637e Mon Sep 17 00:00:00 2001 From: Mariusz Tkaczyk Date: Wed, 4 Sep 2024 12:48:47 +0200 Subject: PCI/NPEM: Add Native PCIe Enclosure Management support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Native PCIe Enclosure Management (NPEM, PCIe r6.1 sec 6.28) allows managing LEDs in storage enclosures. NPEM is indication oriented and it does not give direct access to LEDs. Although each indication *could* represent an individual LED, multiple indications could also be represented as a single, multi-color LED or a single LED blinking in a specific interval. The specification leaves that open. Each enabled indication (capability register bit on) is represented as a ledclass_dev which can be controlled through sysfs. For every ledclass device only 2 brightness states are allowed: LED_ON (1) or LED_OFF (0). This corresponds to the NPEM control register (Indication bit on/off). Ledclass devices appear in sysfs as child devices (subdirectory) of PCI device which has an NPEM Extended Capability and indication is enabled in NPEM capability register. For example, these are LEDs created for pcieport "10000:02:05.0" on my setup: leds/ ├── 10000:02:05.0:enclosure:fail ├── 10000:02:05.0:enclosure:locate ├── 10000:02:05.0:enclosure:ok └── 10000:02:05.0:enclosure:rebuild They can be also found in "/sys/class/leds" directory. The parent PCIe device domain/bus/device/function address is used to guarantee uniqueness across leds subsystem. To enable/disable a "fail" indication, the "brightness" file can be edited: echo 1 > ./leds/10000:02:05.0:enclosure:fail/brightness echo 0 > ./leds/10000:02:05.0:enclosure:fail/brightness PCIe r6.1, sec 7.9.19.2 defines the possible indications. Multiple indications for same parent PCIe device can conflict and hardware may update them when processing new request. To avoid issues, driver refresh all indications by reading back control register. This driver expects to be the exclusive NPEM extended capability manager. It waits up to 1 second after imposing new request, it doesn't verify if controller is busy before write, and it assumes the mutex lock gives protection from concurrent updates. If _DSM LED management is available, we assume the platform may be using NPEM for its own purposes (see PCI Firmware Spec r3.3 sec 4.7), so the driver does not use NPEM. A future patch will add _DSM support; an info message notes whether NPEM or _DSM is being used. NPEM is a PCIe extended capability so it should be registered in pcie_init_capabilities() but it is not possible due to LED dependency. The parent pci_device must be added earlier for led_classdev_register() to be successful. NPEM does not require configuration on kernel side, so it is safe to register LED devices later. Link: https://lore.kernel.org/r/20240904104848.23480-3-mariusz.tkaczyk@linux.intel.com Suggested-by: Lukas Wunner Signed-off-by: Mariusz Tkaczyk Signed-off-by: Bjorn Helgaas Tested-by: Stuart Hayes Reviewed-by: Christoph Hellwig Reviewed-by: Ilpo Järvinen --- Documentation/ABI/testing/sysfs-bus-pci | 63 +++++ drivers/pci/Kconfig | 9 + drivers/pci/Makefile | 1 + drivers/pci/npem.c | 423 ++++++++++++++++++++++++++++++++ drivers/pci/pci.h | 8 + drivers/pci/probe.c | 2 + drivers/pci/remove.c | 2 + include/linux/pci.h | 3 + include/uapi/linux/pci_regs.h | 35 +++ 9 files changed, 546 insertions(+) create mode 100644 drivers/pci/npem.c (limited to 'include/linux') diff --git a/Documentation/ABI/testing/sysfs-bus-pci b/Documentation/ABI/testing/sysfs-bus-pci index ecf47559f495..9ddbb1364698 100644 --- a/Documentation/ABI/testing/sysfs-bus-pci +++ b/Documentation/ABI/testing/sysfs-bus-pci @@ -500,3 +500,66 @@ Description: console drivers from the device. Raw users of pci-sysfs resourceN attributes must be terminated prior to resizing. Success of the resizing operation is not guaranteed. + +What: /sys/bus/pci/devices/.../leds/*:enclosure:*/brightness +What: /sys/class/leds/*:enclosure:*/brightness +Date: August 2024 +KernelVersion: 6.12 +Description: + LED indications on PCIe storage enclosures which are controlled + through the NPEM interface (Native PCIe Enclosure Management, + PCIe r6.1 sec 6.28) are accessible as led class devices, both + below /sys/class/leds and below NPEM-capable PCI devices. + + Although these led class devices could be manipulated manually, + in practice they are typically manipulated automatically by an + application such as ledmon(8). + + The name of a led class device is as follows: + :enclosure: + where: + + - is the domain, bus, device and function number + (e.g. 10000:02:05.0) + - is a short description of the LED indication + + Valid indications per PCIe r6.1 table 6-27 are: + + - ok (drive is functioning normally) + - locate (drive is being identified by an admin) + - fail (drive is not functioning properly) + - rebuild (drive is part of an array that is rebuilding) + - pfa (drive is predicted to fail soon) + - hotspare (drive is marked to be used as a replacement) + - ica (drive is part of an array that is degraded) + - ifa (drive is part of an array that is failed) + - idt (drive is not the right type for the connector) + - disabled (drive is disabled, removal is safe) + - specific0 to specific7 (enclosure-specific indications) + + Broadly, the indications fall into one of these categories: + + - to signify drive state (ok, locate, fail, idt, disabled) + - to signify drive role or state in a software RAID array + (rebuild, pfa, hotspare, ica, ifa) + - to signify any other role or state (specific0 to specific7) + + Mandatory indications per PCIe r6.1 sec 7.9.19.2 comprise: + ok, locate, fail, rebuild. All others are optional. + A led class device is only visible if the corresponding + indication is supported by the device. + + To manipulate the indications, write 0 (LED_OFF) or 1 (LED_ON) + to the "brightness" file. Note that manipulating an indication + may implicitly manipulate other indications at the vendor's + discretion. E.g. when the user lights up the "ok" indication, + the vendor may choose to automatically turn off the "fail" + indication. The current state of an indication can be + retrieved by reading its "brightness" file. + + The PCIe Base Specification allows vendors leeway to choose + different colors or blinking patterns for the indications, + but they typically follow the IBPI standard. E.g. the "locate" + indication is usually presented as one or two LEDs blinking at + 4 Hz frequency: + https://en.wikipedia.org/wiki/International_Blinking_Pattern_Interpretation diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig index aa4d1833f442..0d94e4a967d8 100644 --- a/drivers/pci/Kconfig +++ b/drivers/pci/Kconfig @@ -143,6 +143,15 @@ config PCI_IOV If unsure, say N. +config PCI_NPEM + bool "Native PCIe Enclosure Management" + depends on LEDS_CLASS=y + help + Support for Native PCIe Enclosure Management. It allows managing LED + indications in storage enclosures. Enclosure must support following + indications: OK, Locate, Fail, Rebuild, other indications are + optional. + config PCI_PRI bool "PCI PRI support" select PCI_ATS diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile index 8ddad57934a6..374c5c06d92f 100644 --- a/drivers/pci/Makefile +++ b/drivers/pci/Makefile @@ -35,6 +35,7 @@ obj-$(CONFIG_XEN_PCIDEV_FRONTEND) += xen-pcifront.o obj-$(CONFIG_VGA_ARB) += vgaarb.o obj-$(CONFIG_PCI_DOE) += doe.o obj-$(CONFIG_PCI_DYNAMIC_OF_NODES) += of_property.o +obj-$(CONFIG_PCI_NPEM) += npem.o # Endpoint library must be initialized before its users obj-$(CONFIG_PCI_ENDPOINT) += endpoint/ diff --git a/drivers/pci/npem.c b/drivers/pci/npem.c new file mode 100644 index 000000000000..5fe33d145108 --- /dev/null +++ b/drivers/pci/npem.c @@ -0,0 +1,423 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe Enclosure management driver created for LED interfaces based on + * indications. It says *what indications* blink but does not specify *how* + * they blink - it is hardware defined. + * + * The driver name refers to Native PCIe Enclosure Management. It is + * first indication oriented standard with specification. + * + * Native PCIe Enclosure Management (NPEM) + * PCIe Base Specification r6.1 sec 6.28, 7.9.19 + * + * Copyright (c) 2023-2024 Intel Corporation + * Mariusz Tkaczyk + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "pci.h" + +struct indication { + u32 bit; + const char *name; +}; + +static const struct indication npem_indications[] = { + {PCI_NPEM_IND_OK, "enclosure:ok"}, + {PCI_NPEM_IND_LOCATE, "enclosure:locate"}, + {PCI_NPEM_IND_FAIL, "enclosure:fail"}, + {PCI_NPEM_IND_REBUILD, "enclosure:rebuild"}, + {PCI_NPEM_IND_PFA, "enclosure:pfa"}, + {PCI_NPEM_IND_HOTSPARE, "enclosure:hotspare"}, + {PCI_NPEM_IND_ICA, "enclosure:ica"}, + {PCI_NPEM_IND_IFA, "enclosure:ifa"}, + {PCI_NPEM_IND_IDT, "enclosure:idt"}, + {PCI_NPEM_IND_DISABLED, "enclosure:disabled"}, + {PCI_NPEM_IND_SPEC_0, "enclosure:specific_0"}, + {PCI_NPEM_IND_SPEC_1, "enclosure:specific_1"}, + {PCI_NPEM_IND_SPEC_2, "enclosure:specific_2"}, + {PCI_NPEM_IND_SPEC_3, "enclosure:specific_3"}, + {PCI_NPEM_IND_SPEC_4, "enclosure:specific_4"}, + {PCI_NPEM_IND_SPEC_5, "enclosure:specific_5"}, + {PCI_NPEM_IND_SPEC_6, "enclosure:specific_6"}, + {PCI_NPEM_IND_SPEC_7, "enclosure:specific_7"}, + {0, NULL} +}; + +#define for_each_indication(ind, inds) \ + for (ind = inds; ind->bit; ind++) + +/* + * The driver has internal list of supported indications. Ideally, the driver + * should not touch bits that are not defined and for which LED devices are + * not exposed but in reality, it needs to turn them off. + * + * Otherwise, there will be no possibility to turn off indications turned on by + * other utilities or turned on by default and it leads to bad user experience. + * + * Additionally, it excludes NPEM commands like RESET or ENABLE. + */ +static u32 reg_to_indications(u32 caps, const struct indication *inds) +{ + const struct indication *ind; + u32 supported_indications = 0; + + for_each_indication(ind, inds) + supported_indications |= ind->bit; + + return caps & supported_indications; +} + +/** + * struct npem_led - LED details + * @indication: indication details + * @npem: NPEM device + * @name: LED name + * @led: LED device + */ +struct npem_led { + const struct indication *indication; + struct npem *npem; + char name[LED_MAX_NAME_SIZE]; + struct led_classdev led; +}; + +/** + * struct npem_ops - backend specific callbacks + * @get_active_indications: get active indications + * npem: NPEM device + * inds: response buffer + * @set_active_indications: set new indications + * npem: npem device + * inds: bit mask to set + * @inds: supported indications array, set of indications is backend specific + * @name: backend name + */ +struct npem_ops { + int (*get_active_indications)(struct npem *npem, u32 *inds); + int (*set_active_indications)(struct npem *npem, u32 inds); + const struct indication *inds; + const char *name; +}; + +/** + * struct npem - NPEM device properties + * @dev: PCI device this driver is attached to + * @ops: backend specific callbacks + * @lock: serializes concurrent access to NPEM device by multiple LED devices + * @pos: cached offset of NPEM Capability Register in Configuration Space; + * only used if NPEM registers are accessed directly and not through _DSM + * @supported_indications: cached bit mask of supported indications; + * non-indication and reserved bits in the NPEM Capability Register are + * cleared in this bit mask + * @active_indications: cached bit mask of active indications; + * non-indication and reserved bits in the NPEM Control Register are + * cleared in this bit mask + * @led_cnt: size of @leds array + * @leds: array containing LED class devices of all supported LEDs + */ +struct npem { + struct pci_dev *dev; + const struct npem_ops *ops; + struct mutex lock; + u16 pos; + u32 supported_indications; + u32 active_indications; + int led_cnt; + struct npem_led leds[]; +}; + +static int npem_read_reg(struct npem *npem, u16 reg, u32 *val) +{ + int ret = pci_read_config_dword(npem->dev, npem->pos + reg, val); + + return pcibios_err_to_errno(ret); +} + +static int npem_write_ctrl(struct npem *npem, u32 reg) +{ + int pos = npem->pos + PCI_NPEM_CTRL; + int ret = pci_write_config_dword(npem->dev, pos, reg); + + return pcibios_err_to_errno(ret); +} + +static int npem_get_active_indications(struct npem *npem, u32 *inds) +{ + u32 ctrl; + int ret; + + ret = npem_read_reg(npem, PCI_NPEM_CTRL, &ctrl); + if (ret) + return ret; + + /* If PCI_NPEM_CTRL_ENABLE is not set then no indication should blink */ + if (!(ctrl & PCI_NPEM_CTRL_ENABLE)) { + *inds = 0; + return 0; + } + + *inds = ctrl & npem->supported_indications; + + return 0; +} + +static int npem_set_active_indications(struct npem *npem, u32 inds) +{ + int ctrl, ret, ret_val; + u32 cc_status; + + lockdep_assert_held(&npem->lock); + + /* This bit is always required */ + ctrl = inds | PCI_NPEM_CTRL_ENABLE; + + ret = npem_write_ctrl(npem, ctrl); + if (ret) + return ret; + + /* + * For the case where a NPEM command has not completed immediately, + * it is recommended that software not continuously "spin" on polling + * the status register, but rather poll under interrupt at a reduced + * rate; for example at 10 ms intervals. + * + * PCIe r6.1 sec 6.28 "Implementation Note: Software Polling of NPEM + * Command Completed" + */ + ret = read_poll_timeout(npem_read_reg, ret_val, + ret_val || (cc_status & PCI_NPEM_STATUS_CC), + 10 * USEC_PER_MSEC, USEC_PER_SEC, false, npem, + PCI_NPEM_STATUS, &cc_status); + if (ret) + return ret; + if (ret_val) + return ret_val; + + /* + * All writes to control register, including writes that do not change + * the register value, are NPEM commands and should eventually result + * in a command completion indication in the NPEM Status Register. + * + * PCIe Base Specification r6.1 sec 7.9.19.3 + * + * Register may not be updated, or other conflicting bits may be + * cleared. Spec is not strict here. Read NPEM Control register after + * write to keep cache in-sync. + */ + return npem_get_active_indications(npem, &npem->active_indications); +} + +static const struct npem_ops npem_ops = { + .get_active_indications = npem_get_active_indications, + .set_active_indications = npem_set_active_indications, + .name = "Native PCIe Enclosure Management", + .inds = npem_indications, +}; + +#define DSM_GUID GUID_INIT(0x5d524d9d, 0xfff9, 0x4d4b, 0x8c, 0xb7, 0x74, 0x7e,\ + 0xd5, 0x1e, 0x19, 0x4d) +#define GET_SUPPORTED_STATES_DSM 1 +#define GET_STATE_DSM 2 +#define SET_STATE_DSM 3 + +static const guid_t dsm_guid = DSM_GUID; + +static bool npem_has_dsm(struct pci_dev *pdev) +{ + acpi_handle handle; + + handle = ACPI_HANDLE(&pdev->dev); + if (!handle) + return false; + + return acpi_check_dsm(handle, &dsm_guid, 0x1, + BIT(GET_SUPPORTED_STATES_DSM) | + BIT(GET_STATE_DSM) | BIT(SET_STATE_DSM)); +} + +/* + * The status of each indicator is cached on first brightness_ get/set time + * and updated at write time. brightness_get() is only responsible for + * reflecting the last written/cached value. + */ +static enum led_brightness brightness_get(struct led_classdev *led) +{ + struct npem_led *nled = container_of(led, struct npem_led, led); + struct npem *npem = nled->npem; + int ret, val = 0; + + ret = mutex_lock_interruptible(&npem->lock); + if (ret) + return ret; + + if (npem->active_indications & nled->indication->bit) + val = 1; + + mutex_unlock(&npem->lock); + return val; +} + +static int brightness_set(struct led_classdev *led, + enum led_brightness brightness) +{ + struct npem_led *nled = container_of(led, struct npem_led, led); + struct npem *npem = nled->npem; + u32 indications; + int ret; + + ret = mutex_lock_interruptible(&npem->lock); + if (ret) + return ret; + + if (brightness == 0) + indications = npem->active_indications & ~(nled->indication->bit); + else + indications = npem->active_indications | nled->indication->bit; + + ret = npem->ops->set_active_indications(npem, indications); + + mutex_unlock(&npem->lock); + return ret; +} + +static void npem_free(struct npem *npem) +{ + struct npem_led *nled; + int cnt; + + if (!npem) + return; + + for (cnt = 0; cnt < npem->led_cnt; cnt++) { + nled = &npem->leds[cnt]; + + if (nled->name[0]) + led_classdev_unregister(&nled->led); + } + + mutex_destroy(&npem->lock); + kfree(npem); +} + +static int pci_npem_set_led_classdev(struct npem *npem, struct npem_led *nled) +{ + struct led_classdev *led = &nled->led; + struct led_init_data init_data = {}; + char *name = nled->name; + int ret; + + init_data.devicename = pci_name(npem->dev); + init_data.default_label = nled->indication->name; + + ret = led_compose_name(&npem->dev->dev, &init_data, name); + if (ret) + return ret; + + led->name = name; + led->brightness_set_blocking = brightness_set; + led->brightness_get = brightness_get; + led->max_brightness = 1; + led->default_trigger = "none"; + led->flags = 0; + + ret = led_classdev_register(&npem->dev->dev, led); + if (ret) + /* Clear the name to indicate that it is not registered. */ + name[0] = 0; + return ret; +} + +static int pci_npem_init(struct pci_dev *dev, const struct npem_ops *ops, + int pos, u32 caps) +{ + u32 supported = reg_to_indications(caps, ops->inds); + int supported_cnt = hweight32(supported); + const struct indication *indication; + struct npem_led *nled; + struct npem *npem; + int led_idx = 0; + int ret; + + npem = kzalloc(struct_size(npem, leds, supported_cnt), GFP_KERNEL); + if (!npem) + return -ENOMEM; + + npem->supported_indications = supported; + npem->led_cnt = supported_cnt; + npem->pos = pos; + npem->dev = dev; + npem->ops = ops; + + ret = npem->ops->get_active_indications(npem, + &npem->active_indications); + if (ret) + return ret; + + mutex_init(&npem->lock); + + for_each_indication(indication, npem_indications) { + if (!(npem->supported_indications & indication->bit)) + continue; + + nled = &npem->leds[led_idx++]; + nled->indication = indication; + nled->npem = npem; + + ret = pci_npem_set_led_classdev(npem, nled); + if (ret) { + npem_free(npem); + return ret; + } + } + + dev->npem = npem; + return 0; +} + +void pci_npem_remove(struct pci_dev *dev) +{ + npem_free(dev->npem); +} + +void pci_npem_create(struct pci_dev *dev) +{ + const struct npem_ops *ops = &npem_ops; + int pos = 0, ret; + u32 cap; + + if (npem_has_dsm(dev)) { + /* + * OS should use the DSM for LED control if it is available + * PCI Firmware Spec r3.3 sec 4.7. + */ + pci_info(dev, "Not configuring %s because _DSM is present\n", + ops->name); + return; + } else { + pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_NPEM); + if (pos == 0) + return; + + if (pci_read_config_dword(dev, pos + PCI_NPEM_CAP, &cap) != 0 || + (cap & PCI_NPEM_CAP_CAPABLE) == 0) + return; + } + + pci_info(dev, "Configuring %s\n", ops->name); + + ret = pci_npem_init(dev, ops, pos, cap); + if (ret) + pci_err(dev, "Failed to register %s, err: %d\n", ops->name, + ret); +} diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 79c8398f3938..554fd9dfe25c 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -398,6 +398,14 @@ static inline void pci_doe_destroy(struct pci_dev *pdev) { } static inline void pci_doe_disconnected(struct pci_dev *pdev) { } #endif +#ifdef CONFIG_PCI_NPEM +void pci_npem_create(struct pci_dev *dev); +void pci_npem_remove(struct pci_dev *dev); +#else +static inline void pci_npem_create(struct pci_dev *dev) { } +static inline void pci_npem_remove(struct pci_dev *dev) { } +#endif + /** * pci_dev_set_io_state - Set the new error state if possible. * diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index b14b9876c030..17ee559c31a4 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2593,6 +2593,8 @@ void pci_device_add(struct pci_dev *dev, struct pci_bus *bus) dev->match_driver = false; ret = device_add(&dev->dev); WARN_ON(ret < 0); + + pci_npem_create(dev); } struct pci_dev *pci_scan_single_device(struct pci_bus *bus, int devfn) diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c index 910387e5bdbf..da9629c3a688 100644 --- a/drivers/pci/remove.c +++ b/drivers/pci/remove.c @@ -34,6 +34,8 @@ static void pci_destroy_dev(struct pci_dev *dev) if (!dev->dev.kobj.parent) return; + pci_npem_remove(dev); + device_del(&dev->dev); down_write(&pci_bus_sem); diff --git a/include/linux/pci.h b/include/linux/pci.h index 4cf89a4b4cbc..c9db853e269f 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -516,6 +516,9 @@ struct pci_dev { #endif #ifdef CONFIG_PCI_DOE struct xarray doe_mbs; /* Data Object Exchange mailboxes */ +#endif +#ifdef CONFIG_PCI_NPEM + struct npem *npem; /* Native PCIe Enclosure Management */ #endif u16 acs_cap; /* ACS Capability offset */ phys_addr_t rom; /* Physical address if not from BAR */ diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 94c00996e633..9751b413f3d6 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -740,6 +740,7 @@ #define PCI_EXT_CAP_ID_DVSEC 0x23 /* Designated Vendor-Specific */ #define PCI_EXT_CAP_ID_DLF 0x25 /* Data Link Feature */ #define PCI_EXT_CAP_ID_PL_16GT 0x26 /* Physical Layer 16.0 GT/s */ +#define PCI_EXT_CAP_ID_NPEM 0x29 /* Native PCIe Enclosure Management */ #define PCI_EXT_CAP_ID_PL_32GT 0x2A /* Physical Layer 32.0 GT/s */ #define PCI_EXT_CAP_ID_DOE 0x2E /* Data Object Exchange */ #define PCI_EXT_CAP_ID_MAX PCI_EXT_CAP_ID_DOE @@ -1121,6 +1122,40 @@ #define PCI_PL_16GT_LE_CTRL_USP_TX_PRESET_MASK 0x000000F0 #define PCI_PL_16GT_LE_CTRL_USP_TX_PRESET_SHIFT 4 +/* Native PCIe Enclosure Management */ +#define PCI_NPEM_CAP 0x04 /* NPEM capability register */ +#define PCI_NPEM_CAP_CAPABLE 0x00000001 /* NPEM Capable */ + +#define PCI_NPEM_CTRL 0x08 /* NPEM control register */ +#define PCI_NPEM_CTRL_ENABLE 0x00000001 /* NPEM Enable */ + +/* + * Native PCIe Enclosure Management indication bits and Reset command bit + * are corresponding for capability and control registers. + */ +#define PCI_NPEM_CMD_RESET 0x00000002 /* Reset Command */ +#define PCI_NPEM_IND_OK 0x00000004 /* OK */ +#define PCI_NPEM_IND_LOCATE 0x00000008 /* Locate */ +#define PCI_NPEM_IND_FAIL 0x00000010 /* Fail */ +#define PCI_NPEM_IND_REBUILD 0x00000020 /* Rebuild */ +#define PCI_NPEM_IND_PFA 0x00000040 /* Predicted Failure Analysis */ +#define PCI_NPEM_IND_HOTSPARE 0x00000080 /* Hot Spare */ +#define PCI_NPEM_IND_ICA 0x00000100 /* In Critical Array */ +#define PCI_NPEM_IND_IFA 0x00000200 /* In Failed Array */ +#define PCI_NPEM_IND_IDT 0x00000400 /* Device Type */ +#define PCI_NPEM_IND_DISABLED 0x00000800 /* Disabled */ +#define PCI_NPEM_IND_SPEC_0 0x01000000 +#define PCI_NPEM_IND_SPEC_1 0x02000000 +#define PCI_NPEM_IND_SPEC_2 0x04000000 +#define PCI_NPEM_IND_SPEC_3 0x08000000 +#define PCI_NPEM_IND_SPEC_4 0x10000000 +#define PCI_NPEM_IND_SPEC_5 0x20000000 +#define PCI_NPEM_IND_SPEC_6 0x40000000 +#define PCI_NPEM_IND_SPEC_7 0x80000000 + +#define PCI_NPEM_STATUS 0x0c /* NPEM status register */ +#define PCI_NPEM_STATUS_CC 0x00000001 /* Command Completed */ + /* Data Object Exchange */ #define PCI_DOE_CAP 0x04 /* DOE Capabilities Register */ #define PCI_DOE_CAP_INT_SUP 0x00000001 /* Interrupt Support */ -- cgit v1.2.3 From 73425800ac948cb78063b897a0c345d788f3594d Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 5 Jun 2024 11:26:24 +0100 Subject: netfs, cifs: Move CIFS_INO_MODIFIED_ATTR to netfs_inode Move CIFS_INO_MODIFIED_ATTR to netfs_inode as NETFS_ICTX_MODIFIED_ATTR and then make netfs_perform_write() set it. This means that cifs doesn't need to implement the ->post_modify() hook. Signed-off-by: David Howells cc: Jeff Layton cc: Steve French cc: Paulo Alcantara cc: linux-cifs@vger.kernel.org cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/20240814203850.2240469-7-dhowells@redhat.com/ # v2 Signed-off-by: Christian Brauner --- fs/netfs/buffered_write.c | 10 ++++++++-- fs/smb/client/cifsglob.h | 1 - fs/smb/client/file.c | 9 +-------- include/linux/netfs.h | 1 + 4 files changed, 10 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c index 327e5904b090..d7eae597e54d 100644 --- a/fs/netfs/buffered_write.c +++ b/fs/netfs/buffered_write.c @@ -372,8 +372,14 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, } while (iov_iter_count(iter)); out: - if (likely(written) && ctx->ops->post_modify) - ctx->ops->post_modify(inode); + if (likely(written)) { + /* Set indication that ctime and mtime got updated in case + * close is deferred. + */ + set_bit(NETFS_ICTX_MODIFIED_ATTR, &ctx->flags); + if (unlikely(ctx->ops->post_modify)) + ctx->ops->post_modify(inode); + } if (unlikely(wreq)) { ret2 = netfs_end_writethrough(wreq, &wbc, writethrough); diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 9eae8649f90c..bfbcf310807f 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -1550,7 +1550,6 @@ struct cifsInodeInfo { #define CIFS_INO_DELETE_PENDING (3) /* delete pending on server */ #define CIFS_INO_INVALID_MAPPING (4) /* pagecache is invalid */ #define CIFS_INO_LOCK (5) /* lock bit for synchronization */ -#define CIFS_INO_MODIFIED_ATTR (6) /* Indicate change in mtime/ctime */ #define CIFS_INO_CLOSE_ON_LOCK (7) /* Not to defer the close when lock is set */ unsigned long flags; spinlock_t writers_lock; diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 2d387485f05b..283c9b6d9094 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -316,12 +316,6 @@ static void cifs_rreq_done(struct netfs_io_request *rreq) inode_set_atime_to_ts(inode, inode_get_mtime(inode)); } -static void cifs_post_modify(struct inode *inode) -{ - /* Indication to update ctime and mtime as close is deferred */ - set_bit(CIFS_INO_MODIFIED_ATTR, &CIFS_I(inode)->flags); -} - static void cifs_free_request(struct netfs_io_request *rreq) { struct cifs_io_request *req = container_of(rreq, struct cifs_io_request, rreq); @@ -372,7 +366,6 @@ const struct netfs_request_ops cifs_req_ops = { .clamp_length = cifs_clamp_length, .issue_read = cifs_req_issue_read, .done = cifs_rreq_done, - .post_modify = cifs_post_modify, .begin_writeback = cifs_begin_writeback, .prepare_write = cifs_prepare_write, .issue_write = cifs_issue_write, @@ -1396,7 +1389,7 @@ int cifs_close(struct inode *inode, struct file *file) dclose = kmalloc(sizeof(struct cifs_deferred_close), GFP_KERNEL); if ((cfile->status_file_deleted == false) && (smb2_can_defer_close(inode, dclose))) { - if (test_and_clear_bit(CIFS_INO_MODIFIED_ATTR, &cinode->flags)) { + if (test_and_clear_bit(NETFS_ICTX_MODIFIED_ATTR, &cinode->netfs.flags)) { inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); } diff --git a/include/linux/netfs.h b/include/linux/netfs.h index c47443e7a97e..71c748c53a1f 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -73,6 +73,7 @@ struct netfs_inode { #define NETFS_ICTX_ODIRECT 0 /* The file has DIO in progress */ #define NETFS_ICTX_UNBUFFERED 1 /* I/O should not use the pagecache */ #define NETFS_ICTX_WRITETHROUGH 2 /* Write-through caching */ +#define NETFS_ICTX_MODIFIED_ATTR 3 /* Indicate change in mtime/ctime */ }; /* -- cgit v1.2.3 From 52d55922e0f1db1f580c9f91c174d2392bfad481 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 7 Jun 2024 09:02:58 +0100 Subject: netfs: Move max_len/max_nr_segs from netfs_io_subrequest to netfs_io_stream Move max_len/max_nr_segs from struct netfs_io_subrequest to struct netfs_io_stream as we only issue one subreq at a time and then don't need these values again for that subreq unless and until we have to retry it - in which case we want to renegotiate them. Signed-off-by: David Howells cc: Jeff Layton cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/20240814203850.2240469-8-dhowells@redhat.com/ # v2 Signed-off-by: Christian Brauner --- fs/afs/write.c | 4 +++- fs/cachefiles/io.c | 5 +++-- fs/netfs/io.c | 4 ++-- fs/netfs/write_collect.c | 10 +++++----- fs/netfs/write_issue.c | 14 +++++++------- fs/smb/client/file.c | 13 +++++++------ include/linux/netfs.h | 4 ++-- 7 files changed, 29 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/fs/afs/write.c b/fs/afs/write.c index e959640694c2..34107b55f834 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -89,10 +89,12 @@ static const struct afs_operation_ops afs_store_data_operation = { */ void afs_prepare_write(struct netfs_io_subrequest *subreq) { + struct netfs_io_stream *stream = &subreq->rreq->io_streams[subreq->stream_nr]; + //if (test_bit(NETFS_SREQ_RETRYING, &subreq->flags)) // subreq->max_len = 512 * 1024; //else - subreq->max_len = 256 * 1024 * 1024; + stream->sreq_max_len = 256 * 1024 * 1024; } /* diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c index a91acd03ee12..5b82ba7785cd 100644 --- a/fs/cachefiles/io.c +++ b/fs/cachefiles/io.c @@ -627,11 +627,12 @@ static void cachefiles_prepare_write_subreq(struct netfs_io_subrequest *subreq) { struct netfs_io_request *wreq = subreq->rreq; struct netfs_cache_resources *cres = &wreq->cache_resources; + struct netfs_io_stream *stream = &wreq->io_streams[subreq->stream_nr]; _enter("W=%x[%x] %llx", wreq->debug_id, subreq->debug_index, subreq->start); - subreq->max_len = MAX_RW_COUNT; - subreq->max_nr_segs = BIO_MAX_VECS; + stream->sreq_max_len = MAX_RW_COUNT; + stream->sreq_max_segs = BIO_MAX_VECS; if (!cachefiles_cres_file(cres)) { if (!fscache_wait_for_operation(cres, FSCACHE_WANT_WRITE)) diff --git a/fs/netfs/io.c b/fs/netfs/io.c index 943128507af5..ad9580c2dd6c 100644 --- a/fs/netfs/io.c +++ b/fs/netfs/io.c @@ -624,9 +624,9 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq, goto out; } - if (subreq->max_nr_segs) { + if (rreq->io_streams[0].sreq_max_segs) { lsize = netfs_limit_iter(io_iter, 0, subreq->len, - subreq->max_nr_segs); + rreq->io_streams[0].sreq_max_segs); if (subreq->len > lsize) { subreq->len = lsize; trace_netfs_sreq(subreq, netfs_sreq_trace_limited); diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c index ae7a2043f670..90abc21cc019 100644 --- a/fs/netfs/write_collect.c +++ b/fs/netfs/write_collect.c @@ -238,7 +238,7 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, __set_bit(NETFS_SREQ_RETRYING, &subreq->flags); stream->prepare_write(subreq); - part = min(len, subreq->max_len); + part = min(len, stream->sreq_max_len); subreq->len = part; subreq->start = start; subreq->transferred = 0; @@ -278,8 +278,6 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, subreq = netfs_alloc_subrequest(wreq); subreq->source = to->source; subreq->start = start; - subreq->max_len = len; - subreq->max_nr_segs = INT_MAX; subreq->debug_index = atomic_inc_return(&wreq->subreq_counter); subreq->stream_nr = to->stream_nr; __set_bit(NETFS_SREQ_RETRYING, &subreq->flags); @@ -293,10 +291,12 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, to = list_next_entry(to, rreq_link); trace_netfs_sreq(subreq, netfs_sreq_trace_retry); + stream->sreq_max_len = len; + stream->sreq_max_segs = INT_MAX; switch (stream->source) { case NETFS_UPLOAD_TO_SERVER: netfs_stat(&netfs_n_wh_upload); - subreq->max_len = min(len, wreq->wsize); + stream->sreq_max_len = umin(len, wreq->wsize); break; case NETFS_WRITE_TO_CACHE: netfs_stat(&netfs_n_wh_write); @@ -307,7 +307,7 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, stream->prepare_write(subreq); - part = min(len, subreq->max_len); + part = umin(len, stream->sreq_max_len); subreq->len = subreq->transferred + part; len -= part; start += part; diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 44f35a0faaca..34e541afd79b 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -158,8 +158,6 @@ static void netfs_prepare_write(struct netfs_io_request *wreq, subreq = netfs_alloc_subrequest(wreq); subreq->source = stream->source; subreq->start = start; - subreq->max_len = ULONG_MAX; - subreq->max_nr_segs = INT_MAX; subreq->stream_nr = stream->stream_nr; _enter("R=%x[%x]", wreq->debug_id, subreq->debug_index); @@ -170,10 +168,12 @@ static void netfs_prepare_write(struct netfs_io_request *wreq, trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); + stream->sreq_max_len = UINT_MAX; + stream->sreq_max_segs = INT_MAX; switch (stream->source) { case NETFS_UPLOAD_TO_SERVER: netfs_stat(&netfs_n_wh_upload); - subreq->max_len = wreq->wsize; + stream->sreq_max_len = wreq->wsize; break; case NETFS_WRITE_TO_CACHE: netfs_stat(&netfs_n_wh_write); @@ -290,13 +290,13 @@ int netfs_advance_write(struct netfs_io_request *wreq, netfs_prepare_write(wreq, stream, start); subreq = stream->construct; - part = min(subreq->max_len - subreq->len, len); - _debug("part %zx/%zx %zx/%zx", subreq->len, subreq->max_len, part, len); + part = umin(stream->sreq_max_len - subreq->len, len); + _debug("part %zx/%zx %zx/%zx", subreq->len, stream->sreq_max_len, part, len); subreq->len += part; subreq->nr_segs++; - if (subreq->len >= subreq->max_len || - subreq->nr_segs >= subreq->max_nr_segs || + if (subreq->len >= stream->sreq_max_len || + subreq->nr_segs >= stream->sreq_max_segs || to_eof) { netfs_issue_write(wreq, stream); subreq = NULL; diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 283c9b6d9094..ceef7048cad2 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -49,6 +49,7 @@ static void cifs_prepare_write(struct netfs_io_subrequest *subreq) struct cifs_io_subrequest *wdata = container_of(subreq, struct cifs_io_subrequest, subreq); struct cifs_io_request *req = wdata->req; + struct netfs_io_stream *stream = &req->rreq.io_streams[subreq->stream_nr]; struct TCP_Server_Info *server; struct cifsFileInfo *open_file = req->cfile; size_t wsize = req->rreq.wsize; @@ -73,7 +74,7 @@ retry: } } - rc = server->ops->wait_mtu_credits(server, wsize, &wdata->subreq.max_len, + rc = server->ops->wait_mtu_credits(server, wsize, &stream->sreq_max_len, &wdata->credits); if (rc < 0) { subreq->error = rc; @@ -92,7 +93,7 @@ retry: #ifdef CONFIG_CIFS_SMB_DIRECT if (server->smbd_conn) - subreq->max_nr_segs = server->smbd_conn->max_frmr_depth; + stream->sreq_max_segs = server->smbd_conn->max_frmr_depth; #endif } @@ -150,11 +151,11 @@ static void cifs_netfs_invalidate_cache(struct netfs_io_request *wreq) static bool cifs_clamp_length(struct netfs_io_subrequest *subreq) { struct netfs_io_request *rreq = subreq->rreq; + struct netfs_io_stream *stream = &rreq->io_streams[subreq->stream_nr]; struct cifs_io_subrequest *rdata = container_of(subreq, struct cifs_io_subrequest, subreq); struct cifs_io_request *req = container_of(subreq->rreq, struct cifs_io_request, rreq); struct TCP_Server_Info *server = req->server; struct cifs_sb_info *cifs_sb = CIFS_SB(rreq->inode->i_sb); - size_t rsize; int rc; rdata->xid = get_xid(); @@ -168,7 +169,7 @@ static bool cifs_clamp_length(struct netfs_io_subrequest *subreq) rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->rsize, - &rsize, &rdata->credits); + &stream->sreq_max_len, &rdata->credits); if (rc) { subreq->error = rc; return false; @@ -184,12 +185,12 @@ static bool cifs_clamp_length(struct netfs_io_subrequest *subreq) server->credits, server->in_flight, 0, cifs_trace_rw_credits_read_submit); - subreq->len = umin(subreq->len, rsize); + subreq->len = umin(subreq->len, stream->sreq_max_len); rdata->actual_len = subreq->len; #ifdef CONFIG_CIFS_SMB_DIRECT if (server->smbd_conn) - subreq->max_nr_segs = server->smbd_conn->max_frmr_depth; + stream->sreq_max_segs = server->smbd_conn->max_frmr_depth; #endif return true; } diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 71c748c53a1f..eea5ea2842f6 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -134,6 +134,8 @@ static inline struct netfs_group *netfs_folio_group(struct folio *folio) struct netfs_io_stream { /* Submission tracking */ struct netfs_io_subrequest *construct; /* Op being constructed */ + size_t sreq_max_len; /* Maximum size of a subrequest */ + unsigned int sreq_max_segs; /* 0 or max number of segments in an iterator */ unsigned int submit_off; /* Folio offset we're submitting from */ unsigned int submit_len; /* Amount of data left to submit */ unsigned int submit_max_len; /* Amount I/O can be rounded up to */ @@ -177,14 +179,12 @@ struct netfs_io_subrequest { struct list_head rreq_link; /* Link in rreq->subrequests */ struct iov_iter io_iter; /* Iterator for this subrequest */ unsigned long long start; /* Where to start the I/O */ - size_t max_len; /* Maximum size of the I/O */ size_t len; /* Size of the I/O */ size_t transferred; /* Amount of data transferred */ refcount_t ref; short error; /* 0 or error that occurred */ unsigned short debug_index; /* Index in list (for debugging output) */ unsigned int nr_segs; /* Number of segs in io_iter */ - unsigned int max_nr_segs; /* 0 or max number of segments in an iterator */ enum netfs_io_source source; /* Where to read from/write to */ unsigned char stream_nr; /* I/O stream this belongs to */ unsigned long flags; -- cgit v1.2.3 From 51e9a86a4f75c6dc8531407b2ab2ccc4ad137e5a Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 9 Jul 2024 09:45:46 +0100 Subject: netfs: Reserve netfs_sreq_source 0 as unset/unknown Reserve the 0-valued netfs_sreq_source to mean unset or unknown so that it can be seen in the trace as such rather than appearing as download-from-server when it's going to get switched to something else. Signed-off-by: David Howells cc: Jeff Layton cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/20240814203850.2240469-9-dhowells@redhat.com/ # v2 Signed-off-by: Christian Brauner --- include/linux/netfs.h | 1 + include/trace/events/netfs.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index eea5ea2842f6..37f8ce9c0284 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -43,6 +43,7 @@ static inline void folio_start_private_2(struct folio *folio) #define NETFS_BUF_PAGECACHE_MARK XA_MARK_1 /* - Page needs wb/dirty flag wrangling */ enum netfs_io_source { + NETFS_SOURCE_UNKNOWN, NETFS_FILL_WITH_ZEROES, NETFS_DOWNLOAD_FROM_SERVER, NETFS_READ_FROM_CACHE, diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index a4fd5dea52f4..f4105b8e5894 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -60,6 +60,7 @@ E_(netfs_rreq_trace_write_done, "WR-DONE") #define netfs_sreq_sources \ + EM(NETFS_SOURCE_UNKNOWN, "----") \ EM(NETFS_FILL_WITH_ZEROES, "ZERO") \ EM(NETFS_DOWNLOAD_FROM_SERVER, "DOWN") \ EM(NETFS_READ_FROM_CACHE, "READ") \ -- cgit v1.2.3 From c57de2a9259d7dc18a7a425fca91c77502263d8a Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 9 Jul 2024 09:43:38 +0100 Subject: netfs: Remove NETFS_COPY_TO_CACHE Remove NETFS_COPY_TO_CACHE as it isn't used anymore. Signed-off-by: David Howells cc: Jeff Layton cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/20240814203850.2240469-10-dhowells@redhat.com/ # v2 Signed-off-by: Christian Brauner --- fs/netfs/main.c | 3 +-- include/linux/netfs.h | 3 +-- include/trace/events/netfs.h | 3 +-- 3 files changed, 3 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/fs/netfs/main.c b/fs/netfs/main.c index 5f0f438e5d21..1ee712bb3610 100644 --- a/fs/netfs/main.c +++ b/fs/netfs/main.c @@ -37,11 +37,10 @@ static const char *netfs_origins[nr__netfs_io_origin] = { [NETFS_READAHEAD] = "RA", [NETFS_READPAGE] = "RP", [NETFS_READ_FOR_WRITE] = "RW", - [NETFS_COPY_TO_CACHE] = "CC", + [NETFS_DIO_READ] = "DR", [NETFS_WRITEBACK] = "WB", [NETFS_WRITETHROUGH] = "WT", [NETFS_UNBUFFERED_WRITE] = "UW", - [NETFS_DIO_READ] = "DR", [NETFS_DIO_WRITE] = "DW", }; diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 37f8ce9c0284..63ab2c775a21 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -207,11 +207,10 @@ enum netfs_io_origin { NETFS_READAHEAD, /* This read was triggered by readahead */ NETFS_READPAGE, /* This read is a synchronous read */ NETFS_READ_FOR_WRITE, /* This read is to prepare a write */ - NETFS_COPY_TO_CACHE, /* This write is to copy a read to the cache */ + NETFS_DIO_READ, /* This is a direct I/O read */ NETFS_WRITEBACK, /* This write was triggered by writepages */ NETFS_WRITETHROUGH, /* This write was made by netfs_perform_write() */ NETFS_UNBUFFERED_WRITE, /* This is an unbuffered write */ - NETFS_DIO_READ, /* This is a direct I/O read */ NETFS_DIO_WRITE, /* This is a direct I/O write */ nr__netfs_io_origin } __mode(byte); diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index f4105b8e5894..47cd11aaccac 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -34,11 +34,10 @@ EM(NETFS_READAHEAD, "RA") \ EM(NETFS_READPAGE, "RP") \ EM(NETFS_READ_FOR_WRITE, "RW") \ - EM(NETFS_COPY_TO_CACHE, "CC") \ + EM(NETFS_DIO_READ, "DR") \ EM(NETFS_WRITEBACK, "WB") \ EM(NETFS_WRITETHROUGH, "WT") \ EM(NETFS_UNBUFFERED_WRITE, "UW") \ - EM(NETFS_DIO_READ, "DR") \ E_(NETFS_DIO_WRITE, "DW") #define netfs_rreq_traces \ -- cgit v1.2.3 From f9ecc2febf6fd6ad53208a1c0e1b5066ee65dd8b Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Fri, 12 Jul 2024 19:18:20 +0200 Subject: pwm: Don't export pwm_capture() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is only a single caller of this function, and that's in drivers/pwm/core.c itself. So don't export the function. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20240712171821.1470833-2-u.kleine-koenig@baylibre.com Signed-off-by: Uwe Kleine-König --- drivers/pwm/core.c | 5 ++--- include/linux/pwm.h | 10 ---------- 2 files changed, 2 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c index 8acbcf5b6673..56d91c11f0d4 100644 --- a/drivers/pwm/core.c +++ b/drivers/pwm/core.c @@ -325,8 +325,8 @@ EXPORT_SYMBOL_GPL(pwm_adjust_config); * * Returns: 0 on success or a negative error code on failure. */ -int pwm_capture(struct pwm_device *pwm, struct pwm_capture *result, - unsigned long timeout) +static int pwm_capture(struct pwm_device *pwm, struct pwm_capture *result, + unsigned long timeout) { if (!pwm || !pwm->chip->ops) return -EINVAL; @@ -338,7 +338,6 @@ int pwm_capture(struct pwm_device *pwm, struct pwm_capture *result, return pwm->chip->ops->capture(pwm->chip, pwm, result, timeout); } -EXPORT_SYMBOL_GPL(pwm_capture); static struct pwm_chip *pwmchip_find_by_name(const char *name) { diff --git a/include/linux/pwm.h b/include/linux/pwm.h index f8c2dc12dbd3..8acd60b53f58 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -394,9 +394,6 @@ static inline bool pwm_might_sleep(struct pwm_device *pwm) } /* PWM provider APIs */ -int pwm_capture(struct pwm_device *pwm, struct pwm_capture *result, - unsigned long timeout); - void pwmchip_put(struct pwm_chip *chip); struct pwm_chip *pwmchip_alloc(struct device *parent, unsigned int npwm, size_t sizeof_priv); struct pwm_chip *devm_pwmchip_alloc(struct device *parent, unsigned int npwm, size_t sizeof_priv); @@ -462,13 +459,6 @@ static inline void pwm_disable(struct pwm_device *pwm) might_sleep(); } -static inline int pwm_capture(struct pwm_device *pwm, - struct pwm_capture *result, - unsigned long timeout) -{ - return -EINVAL; -} - static inline void pwmchip_put(struct pwm_chip *chip) { } -- cgit v1.2.3 From 4356d575ef0f39a3e8e0ce0c40d84ce900ac3b61 Mon Sep 17 00:00:00 2001 From: Aleksa Sarai Date: Wed, 28 Aug 2024 20:19:43 +1000 Subject: fhandle: expose u64 mount id to name_to_handle_at(2) Now that we provide a unique 64-bit mount ID interface in statx(2), we can now provide a race-free way for name_to_handle_at(2) to provide a file handle and corresponding mount without needing to worry about racing with /proc/mountinfo parsing or having to open a file just to do statx(2). While this is not necessary if you are using AT_EMPTY_PATH and don't care about an extra statx(2) call, users that pass full paths into name_to_handle_at(2) need to know which mount the file handle comes from (to make sure they don't try to open_by_handle_at a file handle from a different filesystem) and switching to AT_EMPTY_PATH would require allocating a file for every name_to_handle_at(2) call, turning err = name_to_handle_at(-EBADF, "/foo/bar/baz", &handle, &mntid, AT_HANDLE_MNT_ID_UNIQUE); into int fd = openat(-EBADF, "/foo/bar/baz", O_PATH | O_CLOEXEC); err1 = name_to_handle_at(fd, "", &handle, &unused_mntid, AT_EMPTY_PATH); err2 = statx(fd, "", AT_EMPTY_PATH, STATX_MNT_ID_UNIQUE, &statxbuf); mntid = statxbuf.stx_mnt_id; close(fd); Reviewed-by: Jeff Layton Signed-off-by: Aleksa Sarai Link: https://lore.kernel.org/r/20240828-exportfs-u64-mount-id-v3-2-10c2c4c16708@cyphar.com Reviewed-by: Jan Kara Reviewed-by: Josef Bacik Signed-off-by: Christian Brauner --- fs/fhandle.c | 29 ++++++++++++++++++++++------- include/linux/syscalls.h | 2 +- include/uapi/linux/fcntl.h | 1 + 3 files changed, 24 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/fs/fhandle.c b/fs/fhandle.c index 6e8cea16790e..8cb665629f4a 100644 --- a/fs/fhandle.c +++ b/fs/fhandle.c @@ -16,7 +16,8 @@ static long do_sys_name_to_handle(const struct path *path, struct file_handle __user *ufh, - int __user *mnt_id, int fh_flags) + void __user *mnt_id, bool unique_mntid, + int fh_flags) { long retval; struct file_handle f_handle; @@ -69,9 +70,19 @@ static long do_sys_name_to_handle(const struct path *path, } else retval = 0; /* copy the mount id */ - if (put_user(real_mount(path->mnt)->mnt_id, mnt_id) || - copy_to_user(ufh, handle, - struct_size(handle, f_handle, handle_bytes))) + if (unique_mntid) { + if (put_user(real_mount(path->mnt)->mnt_id_unique, + (u64 __user *) mnt_id)) + retval = -EFAULT; + } else { + if (put_user(real_mount(path->mnt)->mnt_id, + (int __user *) mnt_id)) + retval = -EFAULT; + } + /* copy the handle */ + if (retval != -EFAULT && + copy_to_user(ufh, handle, + struct_size(handle, f_handle, handle_bytes))) retval = -EFAULT; kfree(handle); return retval; @@ -83,6 +94,7 @@ static long do_sys_name_to_handle(const struct path *path, * @name: name that should be converted to handle. * @handle: resulting file handle * @mnt_id: mount id of the file system containing the file + * (u64 if AT_HANDLE_MNT_ID_UNIQUE, otherwise int) * @flag: flag value to indicate whether to follow symlink or not * and whether a decodable file handle is required. * @@ -92,7 +104,7 @@ static long do_sys_name_to_handle(const struct path *path, * value required. */ SYSCALL_DEFINE5(name_to_handle_at, int, dfd, const char __user *, name, - struct file_handle __user *, handle, int __user *, mnt_id, + struct file_handle __user *, handle, void __user *, mnt_id, int, flag) { struct path path; @@ -100,7 +112,8 @@ SYSCALL_DEFINE5(name_to_handle_at, int, dfd, const char __user *, name, int fh_flags; int err; - if (flag & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH | AT_HANDLE_FID)) + if (flag & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH | AT_HANDLE_FID | + AT_HANDLE_MNT_ID_UNIQUE)) return -EINVAL; lookup_flags = (flag & AT_SYMLINK_FOLLOW) ? LOOKUP_FOLLOW : 0; @@ -109,7 +122,9 @@ SYSCALL_DEFINE5(name_to_handle_at, int, dfd, const char __user *, name, lookup_flags |= LOOKUP_EMPTY; err = user_path_at(dfd, name, lookup_flags, &path); if (!err) { - err = do_sys_name_to_handle(&path, handle, mnt_id, fh_flags); + err = do_sys_name_to_handle(&path, handle, mnt_id, + flag & AT_HANDLE_MNT_ID_UNIQUE, + fh_flags); path_put(&path); } return err; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 4bcf6754738d..5758104921e6 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -870,7 +870,7 @@ asmlinkage long sys_fanotify_mark(int fanotify_fd, unsigned int flags, #endif asmlinkage long sys_name_to_handle_at(int dfd, const char __user *name, struct file_handle __user *handle, - int __user *mnt_id, int flag); + void __user *mnt_id, int flag); asmlinkage long sys_open_by_handle_at(int mountdirfd, struct file_handle __user *handle, int flags); diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h index 38a6d66d9e88..87e2dec79fea 100644 --- a/include/uapi/linux/fcntl.h +++ b/include/uapi/linux/fcntl.h @@ -152,6 +152,7 @@ #define AT_HANDLE_FID 0x200 /* File handle is needed to compare object identity and may not be usable with open_by_handle_at(2). */ +#define AT_HANDLE_MNT_ID_UNIQUE 0x001 /* Return the u64 unique mount ID. */ #if defined(__KERNEL__) #define AT_GETATTR_NOSEC 0x80000000 -- cgit v1.2.3 From 19156263cb1f24128a9ba6ef7340be5cbacc3d22 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Thu, 5 Sep 2024 10:14:05 +0300 Subject: dma-mapping: use IOMMU DMA calls for common alloc/free page calls MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Common alloca and free pages routines are called when IOMMU DMA is used, and internally it calls to DMA ops structure which is not available for default IOMMU. This patch adds necessary if checks to call IOMMU DMA. It fixes the following crash: Unable to handle kernel NULL pointer dereference at virtual address 0000000000000040 Mem abort info: ESR = 0x0000000096000006 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x06: level 2 translation fault Data abort info: ISV = 0, ISS = 0x00000006, ISS2 = 0x00000000 CM = 0, WnR = 0, TnD = 0, TagAccess = 0 GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 user pgtable: 4k pages, 48-bit VAs, pgdp=00000000d20bb000 [0000000000000040] pgd=08000000d20c1003 , p4d=08000000d20c1003 , pud=08000000d20c2003, pmd=0000000000000000 Internal error: Oops: 0000000096000006 [#1] PREEMPT SMP Modules linked in: ipv6 hci_uart venus_core btqca v4l2_mem2mem btrtl qcom_spmi_adc5 sbs_battery btbcm qcom_vadc_common cros_ec_typec videobuf2_v4l2 leds_cros_ec cros_kbd_led_backlight cros_ec_chardev videodev elan_i2c videobuf2_common qcom_stats mc bluetooth coresight_stm stm_core ecdh_generic ecc pwrseq_core panel_edp icc_bwmon ath10k_snoc ath10k_core ath mac80211 phy_qcom_qmp_combo aux_bridge libarc4 coresight_replicator coresight_etm4x coresight_tmc coresight_funnel cfg80211 rfkill coresight qcom_wdt cbmem ramoops reed_solomon pwm_bl coreboot_table backlight crct10dif_ce CPU: 7 UID: 0 PID: 70 Comm: kworker/u32:4 Not tainted 6.11.0-rc6-next-20240903-00003-gdfc6015d0711 #660 Hardware name: Google Lazor Limozeen without Touchscreen (rev5 - rev8) (DT) Workqueue: events_unbound deferred_probe_work_func hub 2-1:1.0: 4 ports detected pstate: 80400009 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : dma_common_alloc_pages+0x54/0x1b4 lr : dma_common_alloc_pages+0x4c/0x1b4 sp : ffff8000807d3730 x29: ffff8000807d3730 x28: ffff02a7d312f880 x27: 0000000000000001 x26: 000000000000c000 x25: 0000000000000000 x24: 0000000000000001 x23: ffff02a7d23b6898 x22: 0000000000006cc0 x21: 000000000000c000 x20: ffff02a7858bf410 x19: fffffe0a60006000 x18: 0000000000000001 x17: 00000000000000d5 x16: 1fffe054f0bcc261 x15: 0000000000000001 x14: ffff02a7844dc680 x13: 0000000000100180 x12: dead000000000100 x11: dead000000000122 x10: 00000000001001ff x9 : ffff02a87f7b7b00 x8 : ffff02a87f7b7b00 x7 : ffff405977d6b000 x6 : ffff8000807d3310 x5 : ffff02a87f6b6398 x4 : 0000000000000001 x3 : ffff405977d6b000 x2 : ffff02a7844dc600 x1 : 0000000100000000 x0 : fffffe0a60006000 Call trace: dma_common_alloc_pages+0x54/0x1b4 __dma_alloc_pages+0x68/0x90 dma_alloc_pages+0x10/0x1c snd_dma_noncoherent_alloc+0x28/0x8c __snd_dma_alloc_pages+0x30/0x50 snd_dma_alloc_dir_pages+0x40/0x80 do_alloc_pages+0xb8/0x13c preallocate_pcm_pages+0x6c/0xf8 preallocate_pages+0x160/0x1a4 snd_pcm_set_managed_buffer_all+0x64/0xb0 lpass_platform_pcm_new+0xc0/0xe8 snd_soc_pcm_component_new+0x3c/0xc8 soc_new_pcm+0x4fc/0x668 snd_soc_bind_card+0xabc/0xbac snd_soc_register_card+0xf0/0x108 devm_snd_soc_register_card+0x4c/0xa4 sc7180_snd_platform_probe+0x180/0x224 platform_probe+0x68/0xc0 really_probe+0xbc/0x298 __driver_probe_device+0x78/0x12c driver_probe_device+0x3c/0x15c __device_attach_driver+0xb8/0x134 bus_for_each_drv+0x84/0xe0 __device_attach+0x9c/0x188 device_initial_probe+0x14/0x20 bus_probe_device+0xac/0xb0 deferred_probe_work_func+0x88/0xc0 process_one_work+0x14c/0x28c worker_thread+0x2cc/0x3d4 kthread+0x114/0x118 ret_from_fork+0x10/0x20 Code: f9411c19 940000c9 aa0003f3 b4000460 (f9402326) ---[ end trace 0000000000000000 ]--- Fixes: b5c58b2fdc42 ("dma-mapping: direct calls for dma-iommu") Closes: https://lore.kernel.org/all/10431dfd-ce04-4e0f-973b-c78477303c18@notapiano Reported-by: Nícolas F. R. A. Prado #KernelCI Signed-off-by: Leon Romanovsky Tested-by: Nícolas F. R. A. Prado Signed-off-by: Christoph Hellwig --- include/linux/iommu-dma.h | 8 ++++++++ kernel/dma/mapping.c | 12 ------------ kernel/dma/ops_helpers.c | 14 +++++++++++--- 3 files changed, 19 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu-dma.h b/include/linux/iommu-dma.h index d30a58bf00fd..1bb55ca1ab79 100644 --- a/include/linux/iommu-dma.h +++ b/include/linux/iommu-dma.h @@ -10,6 +10,10 @@ #include #ifdef CONFIG_IOMMU_DMA +static inline bool use_dma_iommu(struct device *dev) +{ + return dev->dma_iommu; +} dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, unsigned long attrs); @@ -49,6 +53,10 @@ void iommu_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sgl, void iommu_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sgl, int nelems, enum dma_data_direction dir); #else +static inline bool use_dma_iommu(struct device *dev) +{ + return false; +} static inline dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, unsigned long attrs) diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index b50ae3d198a6..056f27962f69 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -114,18 +114,6 @@ void *dmam_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, } EXPORT_SYMBOL(dmam_alloc_attrs); -#ifdef CONFIG_IOMMU_DMA -static bool use_dma_iommu(struct device *dev) -{ - return dev->dma_iommu; -} -#else -static bool use_dma_iommu(struct device *dev) -{ - return false; -} -#endif - static bool dma_go_direct(struct device *dev, dma_addr_t mask, const struct dma_map_ops *ops) { diff --git a/kernel/dma/ops_helpers.c b/kernel/dma/ops_helpers.c index af4a6ef48ce0..9afd569eadb9 100644 --- a/kernel/dma/ops_helpers.c +++ b/kernel/dma/ops_helpers.c @@ -4,6 +4,7 @@ * the allocated memory contains normal pages in the direct kernel mapping. */ #include +#include static struct page *dma_common_vaddr_to_page(void *cpu_addr) { @@ -70,8 +71,12 @@ struct page *dma_common_alloc_pages(struct device *dev, size_t size, if (!page) return NULL; - *dma_handle = ops->map_page(dev, page, 0, size, dir, - DMA_ATTR_SKIP_CPU_SYNC); + if (use_dma_iommu(dev)) + *dma_handle = iommu_dma_map_page(dev, page, 0, size, dir, + DMA_ATTR_SKIP_CPU_SYNC); + else + *dma_handle = ops->map_page(dev, page, 0, size, dir, + DMA_ATTR_SKIP_CPU_SYNC); if (*dma_handle == DMA_MAPPING_ERROR) { dma_free_contiguous(dev, page, size); return NULL; @@ -86,7 +91,10 @@ void dma_common_free_pages(struct device *dev, size_t size, struct page *page, { const struct dma_map_ops *ops = get_dma_ops(dev); - if (ops->unmap_page) + if (use_dma_iommu(dev)) + iommu_dma_unmap_page(dev, dma_handle, size, dir, + DMA_ATTR_SKIP_CPU_SYNC); + else if (ops->unmap_page) ops->unmap_page(dev, dma_handle, size, dir, DMA_ATTR_SKIP_CPU_SYNC); dma_free_contiguous(dev, page, size); -- cgit v1.2.3 From 59da880afed211c989ef65da577b24215ce57774 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 3 Sep 2024 10:45:58 -0700 Subject: uprobes: get rid of enum uprobe_filter_ctx in uprobe filter callbacks It serves no purpose beyond adding unnecessray argument passed to the filter callback. Just get rid of it, no one is actually using it. Signed-off-by: Andrii Nakryiko Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Oleg Nesterov Link: https://lore.kernel.org/r/20240903174603.3554182-4-andrii@kernel.org --- include/linux/uprobes.h | 10 +--------- kernel/events/uprobes.c | 18 +++++++----------- kernel/trace/bpf_trace.c | 3 +-- kernel/trace/trace_uprobe.c | 9 +++------ 4 files changed, 12 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index f50df1fa93e7..63ae2ade3487 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -28,20 +28,12 @@ struct page; #define MAX_URETPROBE_DEPTH 64 -enum uprobe_filter_ctx { - UPROBE_FILTER_REGISTER, - UPROBE_FILTER_UNREGISTER, - UPROBE_FILTER_MMAP, -}; - struct uprobe_consumer { int (*handler)(struct uprobe_consumer *self, struct pt_regs *regs); int (*ret_handler)(struct uprobe_consumer *self, unsigned long func, struct pt_regs *regs); - bool (*filter)(struct uprobe_consumer *self, - enum uprobe_filter_ctx ctx, - struct mm_struct *mm); + bool (*filter)(struct uprobe_consumer *self, struct mm_struct *mm); struct uprobe_consumer *next; }; diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index d228d2ba30bb..87b499cd2334 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -918,21 +918,19 @@ static int prepare_uprobe(struct uprobe *uprobe, struct file *file, return ret; } -static inline bool consumer_filter(struct uprobe_consumer *uc, - enum uprobe_filter_ctx ctx, struct mm_struct *mm) +static inline bool consumer_filter(struct uprobe_consumer *uc, struct mm_struct *mm) { - return !uc->filter || uc->filter(uc, ctx, mm); + return !uc->filter || uc->filter(uc, mm); } -static bool filter_chain(struct uprobe *uprobe, - enum uprobe_filter_ctx ctx, struct mm_struct *mm) +static bool filter_chain(struct uprobe *uprobe, struct mm_struct *mm) { struct uprobe_consumer *uc; bool ret = false; down_read(&uprobe->consumer_rwsem); for (uc = uprobe->consumers; uc; uc = uc->next) { - ret = consumer_filter(uc, ctx, mm); + ret = consumer_filter(uc, mm); if (ret) break; } @@ -1099,12 +1097,10 @@ register_for_each_vma(struct uprobe *uprobe, struct uprobe_consumer *new) if (is_register) { /* consult only the "caller", new consumer. */ - if (consumer_filter(new, - UPROBE_FILTER_REGISTER, mm)) + if (consumer_filter(new, mm)) err = install_breakpoint(uprobe, mm, vma, info->vaddr); } else if (test_bit(MMF_HAS_UPROBES, &mm->flags)) { - if (!filter_chain(uprobe, - UPROBE_FILTER_UNREGISTER, mm)) + if (!filter_chain(uprobe, mm)) err |= remove_breakpoint(uprobe, mm, info->vaddr); } @@ -1387,7 +1383,7 @@ int uprobe_mmap(struct vm_area_struct *vma) */ list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) { if (!fatal_signal_pending(current) && - filter_chain(uprobe, UPROBE_FILTER_MMAP, vma->vm_mm)) { + filter_chain(uprobe, vma->vm_mm)) { unsigned long vaddr = offset_to_vaddr(vma, uprobe->offset); install_breakpoint(uprobe, vma->vm_mm, vma, vaddr); } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 90cd30e9723e..c99bf0617602 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -3320,8 +3320,7 @@ static int uprobe_prog_run(struct bpf_uprobe *uprobe, } static bool -uprobe_multi_link_filter(struct uprobe_consumer *con, enum uprobe_filter_ctx ctx, - struct mm_struct *mm) +uprobe_multi_link_filter(struct uprobe_consumer *con, struct mm_struct *mm) { struct bpf_uprobe *uprobe; diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 52e76a73fa7c..7eb79e0a5352 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1078,9 +1078,7 @@ print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *e return trace_handle_return(s); } -typedef bool (*filter_func_t)(struct uprobe_consumer *self, - enum uprobe_filter_ctx ctx, - struct mm_struct *mm); +typedef bool (*filter_func_t)(struct uprobe_consumer *self, struct mm_struct *mm); static int trace_uprobe_enable(struct trace_uprobe *tu, filter_func_t filter) { @@ -1339,8 +1337,7 @@ static int uprobe_perf_open(struct trace_event_call *call, return err; } -static bool uprobe_perf_filter(struct uprobe_consumer *uc, - enum uprobe_filter_ctx ctx, struct mm_struct *mm) +static bool uprobe_perf_filter(struct uprobe_consumer *uc, struct mm_struct *mm) { struct trace_uprobe_filter *filter; struct trace_uprobe *tu; @@ -1426,7 +1423,7 @@ static void __uprobe_perf_func(struct trace_uprobe *tu, static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs, struct uprobe_cpu_buffer **ucbp) { - if (!uprobe_perf_filter(&tu->consumer, 0, current->mm)) + if (!uprobe_perf_filter(&tu->consumer, current->mm)) return UPROBE_HANDLER_REMOVE; if (!is_ret_probe(tu)) -- cgit v1.2.3 From cc01bd044e6a521d2cd128f685ee8d23ef0067f2 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 3 Sep 2024 10:45:59 -0700 Subject: uprobes: travers uprobe's consumer list locklessly under SRCU protection uprobe->register_rwsem is one of a few big bottlenecks to scalability of uprobes, so we need to get rid of it to improve uprobe performance and multi-CPU scalability. First, we turn uprobe's consumer list to a typical doubly-linked list and utilize existing RCU-aware helpers for traversing such lists, as well as adding and removing elements from it. For entry uprobes we already have SRCU protection active since before uprobe lookup. For uretprobe we keep refcount, guaranteeing that uprobe won't go away from under us, but we add SRCU protection around consumer list traversal. Lastly, to keep handler_chain()'s UPROBE_HANDLER_REMOVE handling simple, we remember whether any removal was requested during handler calls, but then we double-check the decision under a proper register_rwsem using consumers' filter callbacks. Handler removal is very rare, so this extra lock won't hurt performance, overall, but we also avoid the need for any extra protection (e.g., seqcount locks). Signed-off-by: Andrii Nakryiko Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Oleg Nesterov Link: https://lore.kernel.org/r/20240903174603.3554182-5-andrii@kernel.org --- include/linux/uprobes.h | 10 ++++- kernel/events/uprobes.c | 104 ++++++++++++++++++++++++++++-------------------- 2 files changed, 70 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index 63ae2ade3487..f112b56e9479 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -29,13 +29,21 @@ struct page; #define MAX_URETPROBE_DEPTH 64 struct uprobe_consumer { + /* + * handler() can return UPROBE_HANDLER_REMOVE to signal the need to + * unregister uprobe for current process. If UPROBE_HANDLER_REMOVE is + * returned, filter() callback has to be implemented as well and it + * should return false to "confirm" the decision to uninstall uprobe + * for the current process. If filter() is omitted or returns true, + * UPROBE_HANDLER_REMOVE is effectively ignored. + */ int (*handler)(struct uprobe_consumer *self, struct pt_regs *regs); int (*ret_handler)(struct uprobe_consumer *self, unsigned long func, struct pt_regs *regs); bool (*filter)(struct uprobe_consumer *self, struct mm_struct *mm); - struct uprobe_consumer *next; + struct list_head cons_node; }; #ifdef CONFIG_UPROBES diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 87b499cd2334..e15c0306e535 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -59,7 +59,7 @@ struct uprobe { struct rw_semaphore register_rwsem; struct rw_semaphore consumer_rwsem; struct list_head pending_list; - struct uprobe_consumer *consumers; + struct list_head consumers; struct inode *inode; /* Also hold a ref to inode */ struct rcu_head rcu; loff_t offset; @@ -783,6 +783,7 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset, uprobe->inode = inode; uprobe->offset = offset; uprobe->ref_ctr_offset = ref_ctr_offset; + INIT_LIST_HEAD(&uprobe->consumers); init_rwsem(&uprobe->register_rwsem); init_rwsem(&uprobe->consumer_rwsem); RB_CLEAR_NODE(&uprobe->rb_node); @@ -808,32 +809,19 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset, static void consumer_add(struct uprobe *uprobe, struct uprobe_consumer *uc) { down_write(&uprobe->consumer_rwsem); - uc->next = uprobe->consumers; - uprobe->consumers = uc; + list_add_rcu(&uc->cons_node, &uprobe->consumers); up_write(&uprobe->consumer_rwsem); } /* * For uprobe @uprobe, delete the consumer @uc. - * Return true if the @uc is deleted successfully - * or return false. + * Should never be called with consumer that's not part of @uprobe->consumers. */ -static bool consumer_del(struct uprobe *uprobe, struct uprobe_consumer *uc) +static void consumer_del(struct uprobe *uprobe, struct uprobe_consumer *uc) { - struct uprobe_consumer **con; - bool ret = false; - down_write(&uprobe->consumer_rwsem); - for (con = &uprobe->consumers; *con; con = &(*con)->next) { - if (*con == uc) { - *con = uc->next; - ret = true; - break; - } - } + list_del_rcu(&uc->cons_node); up_write(&uprobe->consumer_rwsem); - - return ret; } static int __copy_insn(struct address_space *mapping, struct file *filp, @@ -929,7 +917,8 @@ static bool filter_chain(struct uprobe *uprobe, struct mm_struct *mm) bool ret = false; down_read(&uprobe->consumer_rwsem); - for (uc = uprobe->consumers; uc; uc = uc->next) { + list_for_each_entry_srcu(uc, &uprobe->consumers, cons_node, + srcu_read_lock_held(&uprobes_srcu)) { ret = consumer_filter(uc, mm); if (ret) break; @@ -1125,18 +1114,29 @@ void uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc) int err; down_write(&uprobe->register_rwsem); - if (WARN_ON(!consumer_del(uprobe, uc))) { - err = -ENOENT; - } else { - err = register_for_each_vma(uprobe, NULL); - /* TODO : cant unregister? schedule a worker thread */ - if (unlikely(err)) - uprobe_warn(current, "unregister, leaking uprobe"); - } + consumer_del(uprobe, uc); + err = register_for_each_vma(uprobe, NULL); up_write(&uprobe->register_rwsem); - if (!err) - put_uprobe(uprobe); + /* TODO : cant unregister? schedule a worker thread */ + if (unlikely(err)) { + uprobe_warn(current, "unregister, leaking uprobe"); + goto out_sync; + } + + put_uprobe(uprobe); + +out_sync: + /* + * Now that handler_chain() and handle_uretprobe_chain() iterate over + * uprobe->consumers list under RCU protection without holding + * uprobe->register_rwsem, we need to wait for RCU grace period to + * make sure that we can't call into just unregistered + * uprobe_consumer's callbacks anymore. If we don't do that, fast and + * unlucky enough caller can free consumer's memory and cause + * handler_chain() or handle_uretprobe_chain() to do an use-after-free. + */ + synchronize_srcu(&uprobes_srcu); } EXPORT_SYMBOL_GPL(uprobe_unregister); @@ -1214,13 +1214,20 @@ EXPORT_SYMBOL_GPL(uprobe_register); int uprobe_apply(struct uprobe *uprobe, struct uprobe_consumer *uc, bool add) { struct uprobe_consumer *con; - int ret = -ENOENT; + int ret = -ENOENT, srcu_idx; down_write(&uprobe->register_rwsem); - for (con = uprobe->consumers; con && con != uc ; con = con->next) - ; - if (con) - ret = register_for_each_vma(uprobe, add ? uc : NULL); + + srcu_idx = srcu_read_lock(&uprobes_srcu); + list_for_each_entry_srcu(con, &uprobe->consumers, cons_node, + srcu_read_lock_held(&uprobes_srcu)) { + if (con == uc) { + ret = register_for_each_vma(uprobe, add ? uc : NULL); + break; + } + } + srcu_read_unlock(&uprobes_srcu, srcu_idx); + up_write(&uprobe->register_rwsem); return ret; @@ -2085,10 +2092,12 @@ static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs) struct uprobe_consumer *uc; int remove = UPROBE_HANDLER_REMOVE; bool need_prep = false; /* prepare return uprobe, when needed */ + bool has_consumers = false; - down_read(&uprobe->register_rwsem); current->utask->auprobe = &uprobe->arch; - for (uc = uprobe->consumers; uc; uc = uc->next) { + + list_for_each_entry_srcu(uc, &uprobe->consumers, cons_node, + srcu_read_lock_held(&uprobes_srcu)) { int rc = 0; if (uc->handler) { @@ -2101,17 +2110,24 @@ static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs) need_prep = true; remove &= rc; + has_consumers = true; } current->utask->auprobe = NULL; if (need_prep && !remove) prepare_uretprobe(uprobe, regs); /* put bp at return */ - if (remove && uprobe->consumers) { - WARN_ON(!uprobe_is_active(uprobe)); - unapply_uprobe(uprobe, current->mm); + if (remove && has_consumers) { + down_read(&uprobe->register_rwsem); + + /* re-check that removal is still required, this time under lock */ + if (!filter_chain(uprobe, current->mm)) { + WARN_ON(!uprobe_is_active(uprobe)); + unapply_uprobe(uprobe, current->mm); + } + + up_read(&uprobe->register_rwsem); } - up_read(&uprobe->register_rwsem); } static void @@ -2119,13 +2135,15 @@ handle_uretprobe_chain(struct return_instance *ri, struct pt_regs *regs) { struct uprobe *uprobe = ri->uprobe; struct uprobe_consumer *uc; + int srcu_idx; - down_read(&uprobe->register_rwsem); - for (uc = uprobe->consumers; uc; uc = uc->next) { + srcu_idx = srcu_read_lock(&uprobes_srcu); + list_for_each_entry_srcu(uc, &uprobe->consumers, cons_node, + srcu_read_lock_held(&uprobes_srcu)) { if (uc->ret_handler) uc->ret_handler(uc, ri->func, regs); } - up_read(&uprobe->register_rwsem); + srcu_read_unlock(&uprobes_srcu, srcu_idx); } static struct return_instance *find_next_ret_chain(struct return_instance *ri) -- cgit v1.2.3 From 04b01625da130c7521b768996cd5e48052198b97 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 3 Sep 2024 10:46:00 -0700 Subject: perf/uprobe: split uprobe_unregister() With uprobe_unregister() having grown a synchronize_srcu(), it becomes fairly slow to call. Esp. since both users of this API call it in a loop. Peel off the sync_srcu() and do it once, after the loop. We also need to add uprobe_unregister_sync() into uprobe_register()'s error handling path, as we need to be careful about returning to the caller before we have a guarantee that partially attached consumer won't be called anymore. This is an unlikely slow path and this should be totally fine to be slow in the case of a failed attach. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: "Peter Zijlstra (Intel)" Co-developed-by: Andrii Nakryiko Signed-off-by: Andrii Nakryiko Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Oleg Nesterov Link: https://lore.kernel.org/r/20240903174603.3554182-6-andrii@kernel.org --- include/linux/uprobes.h | 8 ++++++-- kernel/events/uprobes.c | 21 +++++++++++++++------ kernel/trace/bpf_trace.c | 5 ++++- kernel/trace/trace_uprobe.c | 6 +++++- .../testing/selftests/bpf/bpf_testmod/bpf_testmod.c | 3 ++- 5 files changed, 32 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index f112b56e9479..2b294bf1881f 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -115,7 +115,8 @@ extern unsigned long uprobe_get_trap_addr(struct pt_regs *regs); extern int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t); extern struct uprobe *uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc); extern int uprobe_apply(struct uprobe *uprobe, struct uprobe_consumer *uc, bool); -extern void uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc); +extern void uprobe_unregister_nosync(struct uprobe *uprobe, struct uprobe_consumer *uc); +extern void uprobe_unregister_sync(void); extern int uprobe_mmap(struct vm_area_struct *vma); extern void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern void uprobe_start_dup_mmap(void); @@ -164,7 +165,10 @@ uprobe_apply(struct uprobe* uprobe, struct uprobe_consumer *uc, bool add) return -ENOSYS; } static inline void -uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc) +uprobe_unregister_nosync(struct uprobe *uprobe, struct uprobe_consumer *uc) +{ +} +static inline void uprobe_unregister_sync(void) { } static inline int uprobe_mmap(struct vm_area_struct *vma) diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index e15c0306e535..694f6790e848 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1105,11 +1105,11 @@ register_for_each_vma(struct uprobe *uprobe, struct uprobe_consumer *new) } /** - * uprobe_unregister - unregister an already registered probe. + * uprobe_unregister_nosync - unregister an already registered probe. * @uprobe: uprobe to remove * @uc: identify which probe if multiple probes are colocated. */ -void uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc) +void uprobe_unregister_nosync(struct uprobe *uprobe, struct uprobe_consumer *uc) { int err; @@ -1121,12 +1121,15 @@ void uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc) /* TODO : cant unregister? schedule a worker thread */ if (unlikely(err)) { uprobe_warn(current, "unregister, leaking uprobe"); - goto out_sync; + return; } put_uprobe(uprobe); +} +EXPORT_SYMBOL_GPL(uprobe_unregister_nosync); -out_sync: +void uprobe_unregister_sync(void) +{ /* * Now that handler_chain() and handle_uretprobe_chain() iterate over * uprobe->consumers list under RCU protection without holding @@ -1138,7 +1141,7 @@ out_sync: */ synchronize_srcu(&uprobes_srcu); } -EXPORT_SYMBOL_GPL(uprobe_unregister); +EXPORT_SYMBOL_GPL(uprobe_unregister_sync); /** * uprobe_register - register a probe @@ -1196,7 +1199,13 @@ struct uprobe *uprobe_register(struct inode *inode, up_write(&uprobe->register_rwsem); if (ret) { - uprobe_unregister(uprobe, uc); + uprobe_unregister_nosync(uprobe, uc); + /* + * Registration might have partially succeeded, so we can have + * this consumer being called right at this time. We need to + * sync here. It's ok, it's unlikely slow path. + */ + uprobe_unregister_sync(); return ERR_PTR(ret); } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index c99bf0617602..ac0a01cc8634 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -3184,7 +3184,10 @@ static void bpf_uprobe_unregister(struct bpf_uprobe *uprobes, u32 cnt) u32 i; for (i = 0; i < cnt; i++) - uprobe_unregister(uprobes[i].uprobe, &uprobes[i].consumer); + uprobe_unregister_nosync(uprobes[i].uprobe, &uprobes[i].consumer); + + if (cnt) + uprobe_unregister_sync(); } static void bpf_uprobe_multi_link_release(struct bpf_link *link) diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 7eb79e0a5352..f7443e996b1b 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1097,6 +1097,7 @@ static int trace_uprobe_enable(struct trace_uprobe *tu, filter_func_t filter) static void __probe_event_disable(struct trace_probe *tp) { struct trace_uprobe *tu; + bool sync = false; tu = container_of(tp, struct trace_uprobe, tp); WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter)); @@ -1105,9 +1106,12 @@ static void __probe_event_disable(struct trace_probe *tp) if (!tu->uprobe) continue; - uprobe_unregister(tu->uprobe, &tu->consumer); + uprobe_unregister_nosync(tu->uprobe, &tu->consumer); + sync = true; tu->uprobe = NULL; } + if (sync) + uprobe_unregister_sync(); } static int probe_event_enable(struct trace_event_call *call, diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index 3c0515a27842..1fc16657cf42 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -475,7 +475,8 @@ static void testmod_unregister_uprobe(void) mutex_lock(&testmod_uprobe_mutex); if (uprobe.uprobe) { - uprobe_unregister(uprobe.uprobe, &uprobe.consumer); + uprobe_unregister_nosync(uprobe.uprobe, &uprobe.consumer); + uprobe_unregister_sync(); path_put(&uprobe.path); uprobe.uprobe = NULL; } -- cgit v1.2.3 From 50a38035ed5ccc2ab8a28eaf70c3c7a87e060345 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 3 Sep 2024 10:46:01 -0700 Subject: rbtree: provide rb_find_rcu() / rb_find_add_rcu() Much like latch_tree, add two RCU methods for the regular RB-tree, which can be used in conjunction with a seqcount to provide lockless lookups. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: "Peter Zijlstra (Intel)" Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Oleg Nesterov Reviewed-by: "Masami Hiramatsu (Google)" Link: https://lore.kernel.org/r/20240903174603.3554182-7-andrii@kernel.org --- include/linux/rbtree.h | 67 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 67 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h index f7edca369eda..7c173aa64e1e 100644 --- a/include/linux/rbtree.h +++ b/include/linux/rbtree.h @@ -244,6 +244,42 @@ rb_find_add(struct rb_node *node, struct rb_root *tree, return NULL; } +/** + * rb_find_add_rcu() - find equivalent @node in @tree, or add @node + * @node: node to look-for / insert + * @tree: tree to search / modify + * @cmp: operator defining the node order + * + * Adds a Store-Release for link_node. + * + * Returns the rb_node matching @node, or NULL when no match is found and @node + * is inserted. + */ +static __always_inline struct rb_node * +rb_find_add_rcu(struct rb_node *node, struct rb_root *tree, + int (*cmp)(struct rb_node *, const struct rb_node *)) +{ + struct rb_node **link = &tree->rb_node; + struct rb_node *parent = NULL; + int c; + + while (*link) { + parent = *link; + c = cmp(node, parent); + + if (c < 0) + link = &parent->rb_left; + else if (c > 0) + link = &parent->rb_right; + else + return parent; + } + + rb_link_node_rcu(node, parent, link); + rb_insert_color(node, tree); + return NULL; +} + /** * rb_find() - find @key in tree @tree * @key: key to match @@ -272,6 +308,37 @@ rb_find(const void *key, const struct rb_root *tree, return NULL; } +/** + * rb_find_rcu() - find @key in tree @tree + * @key: key to match + * @tree: tree to search + * @cmp: operator defining the node order + * + * Notably, tree descent vs concurrent tree rotations is unsound and can result + * in false-negatives. + * + * Returns the rb_node matching @key or NULL. + */ +static __always_inline struct rb_node * +rb_find_rcu(const void *key, const struct rb_root *tree, + int (*cmp)(const void *key, const struct rb_node *)) +{ + struct rb_node *node = tree->rb_node; + + while (node) { + int c = cmp(key, node); + + if (c < 0) + node = rcu_dereference_raw(node->rb_left); + else if (c > 0) + node = rcu_dereference_raw(node->rb_right); + else + return node; + } + + return NULL; +} + /** * rb_find_first() - find the first @key in @tree * @key: key to match -- cgit v1.2.3 From e04e2b760ddbe3d7b283a05898c3a029085cd8cd Mon Sep 17 00:00:00 2001 From: Armin Wolf Date: Sun, 1 Sep 2024 05:10:52 +0200 Subject: platform/x86: wmi: Pass event data directly to legacy notify handlers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The current legacy WMI handlers are susceptible to picking up wrong WMI event data on systems where different WMI devices share some notification IDs. Prevent this by letting the WMI driver core taking care of retrieving the event data. This also simplifies the legacy WMI handlers and their implementation inside the WMI driver core. Reviewed-by: Ilpo Järvinen Reviewed-by: Hans de Goede Signed-off-by: Armin Wolf Link: https://lore.kernel.org/r/20240901031055.3030-3-W_Armin@gmx.de Signed-off-by: Hans de Goede --- drivers/hwmon/hp-wmi-sensors.c | 22 +++++----------- drivers/platform/x86/acer-wmi.c | 16 +----------- drivers/platform/x86/asus-wmi.c | 19 +++----------- drivers/platform/x86/dell/dell-wmi-aio.c | 13 +--------- drivers/platform/x86/hp/hp-wmi.c | 16 +----------- drivers/platform/x86/huawei-wmi.c | 14 +---------- drivers/platform/x86/lg-laptop.c | 13 +--------- drivers/platform/x86/msi-wmi.c | 20 +++------------ drivers/platform/x86/toshiba-wmi.c | 15 +---------- drivers/platform/x86/wmi.c | 43 +++++++++++++------------------- include/linux/acpi.h | 2 +- 11 files changed, 37 insertions(+), 156 deletions(-) (limited to 'include/linux') diff --git a/drivers/hwmon/hp-wmi-sensors.c b/drivers/hwmon/hp-wmi-sensors.c index dfa1d6926dea..d6bdad26feb1 100644 --- a/drivers/hwmon/hp-wmi-sensors.c +++ b/drivers/hwmon/hp-wmi-sensors.c @@ -1597,15 +1597,13 @@ static void hp_wmi_devm_notify_remove(void *ignored) } /* hp_wmi_notify - WMI event notification handler */ -static void hp_wmi_notify(u32 value, void *context) +static void hp_wmi_notify(union acpi_object *wobj, void *context) { struct hp_wmi_info *temp_info[HP_WMI_MAX_INSTANCES] = {}; - struct acpi_buffer out = { ACPI_ALLOCATE_BUFFER, NULL }; struct hp_wmi_sensors *state = context; struct device *dev = &state->wdev->dev; struct hp_wmi_event event = {}; struct hp_wmi_info *fan_info; - union acpi_object *wobj; acpi_status err; int event_type; u8 count; @@ -1630,20 +1628,15 @@ static void hp_wmi_notify(u32 value, void *context) * HPBIOS_BIOSEvent instance. */ - mutex_lock(&state->lock); - - err = wmi_get_event_data(value, &out); - if (ACPI_FAILURE(err)) - goto out_unlock; - - wobj = out.pointer; if (!wobj) - goto out_unlock; + return; + + mutex_lock(&state->lock); err = populate_event_from_wobj(dev, &event, wobj); if (err) { dev_warn(dev, "Bad event data (ACPI type %d)\n", wobj->type); - goto out_free_wobj; + goto out_free; } event_type = classify_event(event.name, event.category); @@ -1668,13 +1661,10 @@ static void hp_wmi_notify(u32 value, void *context) break; } -out_free_wobj: - kfree(wobj); - +out_free: devm_kfree(dev, event.name); devm_kfree(dev, event.description); -out_unlock: mutex_unlock(&state->lock); } diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c index 349169d050c5..7169b84ccdb6 100644 --- a/drivers/platform/x86/acer-wmi.c +++ b/drivers/platform/x86/acer-wmi.c @@ -2223,39 +2223,25 @@ static void acer_rfkill_exit(void) } } -static void acer_wmi_notify(u32 value, void *context) +static void acer_wmi_notify(union acpi_object *obj, void *context) { - struct acpi_buffer response = { ACPI_ALLOCATE_BUFFER, NULL }; - union acpi_object *obj; struct event_return_value return_value; - acpi_status status; u16 device_state; const struct key_entry *key; u32 scancode; - status = wmi_get_event_data(value, &response); - if (status != AE_OK) { - pr_warn("bad event status 0x%x\n", status); - return; - } - - obj = (union acpi_object *)response.pointer; - if (!obj) return; if (obj->type != ACPI_TYPE_BUFFER) { pr_warn("Unknown response received %d\n", obj->type); - kfree(obj); return; } if (obj->buffer.length != 8) { pr_warn("Unknown buffer length %d\n", obj->buffer.length); - kfree(obj); return; } return_value = *((struct event_return_value *)obj->buffer.pointer); - kfree(obj); switch (return_value.function) { case WMID_HOTKEY_EVENT: diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 9979c4c67b47..6f56305f9f83 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -4201,28 +4201,15 @@ static void asus_wmi_fnlock_update(struct asus_wmi *asus) /* WMI events *****************************************************************/ -static int asus_wmi_get_event_code(u32 value) +static int asus_wmi_get_event_code(union acpi_object *obj) { - struct acpi_buffer response = { ACPI_ALLOCATE_BUFFER, NULL }; - union acpi_object *obj; - acpi_status status; int code; - status = wmi_get_event_data(value, &response); - if (ACPI_FAILURE(status)) { - pr_warn("Failed to get WMI notify code: %s\n", - acpi_format_exception(status)); - return -EIO; - } - - obj = (union acpi_object *)response.pointer; - if (obj && obj->type == ACPI_TYPE_INTEGER) code = (int)(obj->integer.value & WMI_EVENT_MASK); else code = -EIO; - kfree(obj); return code; } @@ -4288,10 +4275,10 @@ static void asus_wmi_handle_event_code(int code, struct asus_wmi *asus) pr_info("Unknown key code 0x%x\n", code); } -static void asus_wmi_notify(u32 value, void *context) +static void asus_wmi_notify(union acpi_object *obj, void *context) { struct asus_wmi *asus = context; - int code = asus_wmi_get_event_code(value); + int code = asus_wmi_get_event_code(obj); if (code < 0) { pr_warn("Failed to get notify code: %d\n", code); diff --git a/drivers/platform/x86/dell/dell-wmi-aio.c b/drivers/platform/x86/dell/dell-wmi-aio.c index c7b7f1e403fb..54096495719b 100644 --- a/drivers/platform/x86/dell/dell-wmi-aio.c +++ b/drivers/platform/x86/dell/dell-wmi-aio.c @@ -70,20 +70,10 @@ static bool dell_wmi_aio_event_check(u8 *buffer, int length) return false; } -static void dell_wmi_aio_notify(u32 value, void *context) +static void dell_wmi_aio_notify(union acpi_object *obj, void *context) { - struct acpi_buffer response = { ACPI_ALLOCATE_BUFFER, NULL }; - union acpi_object *obj; struct dell_wmi_event *event; - acpi_status status; - status = wmi_get_event_data(value, &response); - if (status != AE_OK) { - pr_info("bad event status 0x%x\n", status); - return; - } - - obj = (union acpi_object *)response.pointer; if (obj) { unsigned int scancode = 0; @@ -114,7 +104,6 @@ static void dell_wmi_aio_notify(u32 value, void *context) break; } } - kfree(obj); } static int __init dell_wmi_aio_input_setup(void) diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c index 876e0a97cee1..8c05e0dd2a21 100644 --- a/drivers/platform/x86/hp/hp-wmi.c +++ b/drivers/platform/x86/hp/hp-wmi.c @@ -834,28 +834,16 @@ static struct attribute *hp_wmi_attrs[] = { }; ATTRIBUTE_GROUPS(hp_wmi); -static void hp_wmi_notify(u32 value, void *context) +static void hp_wmi_notify(union acpi_object *obj, void *context) { - struct acpi_buffer response = { ACPI_ALLOCATE_BUFFER, NULL }; u32 event_id, event_data; - union acpi_object *obj; - acpi_status status; u32 *location; int key_code; - status = wmi_get_event_data(value, &response); - if (status != AE_OK) { - pr_info("bad event status 0x%x\n", status); - return; - } - - obj = (union acpi_object *)response.pointer; - if (!obj) return; if (obj->type != ACPI_TYPE_BUFFER) { pr_info("Unknown response received %d\n", obj->type); - kfree(obj); return; } @@ -872,10 +860,8 @@ static void hp_wmi_notify(u32 value, void *context) event_data = *(location + 2); } else { pr_info("Unknown buffer length %d\n", obj->buffer.length); - kfree(obj); return; } - kfree(obj); switch (event_id) { case HPWMI_DOCK_EVENT: diff --git a/drivers/platform/x86/huawei-wmi.c b/drivers/platform/x86/huawei-wmi.c index 09d476dd832e..d81fd5df4a00 100644 --- a/drivers/platform/x86/huawei-wmi.c +++ b/drivers/platform/x86/huawei-wmi.c @@ -734,26 +734,14 @@ static void huawei_wmi_process_key(struct input_dev *idev, int code) sparse_keymap_report_entry(idev, key, 1, true); } -static void huawei_wmi_input_notify(u32 value, void *context) +static void huawei_wmi_input_notify(union acpi_object *obj, void *context) { struct input_dev *idev = (struct input_dev *)context; - struct acpi_buffer response = { ACPI_ALLOCATE_BUFFER, NULL }; - union acpi_object *obj; - acpi_status status; - status = wmi_get_event_data(value, &response); - if (ACPI_FAILURE(status)) { - dev_err(&idev->dev, "Unable to get event data\n"); - return; - } - - obj = (union acpi_object *)response.pointer; if (obj && obj->type == ACPI_TYPE_INTEGER) huawei_wmi_process_key(idev, obj->integer.value); else dev_err(&idev->dev, "Bad response type\n"); - - kfree(response.pointer); } static int huawei_wmi_input_setup(struct device *dev, const char *guid) diff --git a/drivers/platform/x86/lg-laptop.c b/drivers/platform/x86/lg-laptop.c index 55d31d4fefd6..4b57102c7f62 100644 --- a/drivers/platform/x86/lg-laptop.c +++ b/drivers/platform/x86/lg-laptop.c @@ -205,21 +205,11 @@ static union acpi_object *lg_wmbb(struct device *dev, u32 method_id, u32 arg1, u return (union acpi_object *)buffer.pointer; } -static void wmi_notify(u32 value, void *context) +static void wmi_notify(union acpi_object *obj, void *context) { - struct acpi_buffer response = { ACPI_ALLOCATE_BUFFER, NULL }; - union acpi_object *obj; - acpi_status status; long data = (long)context; pr_debug("event guid %li\n", data); - status = wmi_get_event_data(value, &response); - if (ACPI_FAILURE(status)) { - pr_err("Bad event status 0x%x\n", status); - return; - } - - obj = (union acpi_object *)response.pointer; if (!obj) return; @@ -241,7 +231,6 @@ static void wmi_notify(u32 value, void *context) pr_debug("Type: %i Eventcode: 0x%llx\n", obj->type, obj->integer.value); - kfree(response.pointer); } static void wmi_input_setup(void) diff --git a/drivers/platform/x86/msi-wmi.c b/drivers/platform/x86/msi-wmi.c index fd318cdfe313..4a7ac85c4db4 100644 --- a/drivers/platform/x86/msi-wmi.c +++ b/drivers/platform/x86/msi-wmi.c @@ -170,20 +170,9 @@ static const struct backlight_ops msi_backlight_ops = { .update_status = bl_set_status, }; -static void msi_wmi_notify(u32 value, void *context) +static void msi_wmi_notify(union acpi_object *obj, void *context) { - struct acpi_buffer response = { ACPI_ALLOCATE_BUFFER, NULL }; struct key_entry *key; - union acpi_object *obj; - acpi_status status; - - status = wmi_get_event_data(value, &response); - if (status != AE_OK) { - pr_info("bad event status 0x%x\n", status); - return; - } - - obj = (union acpi_object *)response.pointer; if (obj && obj->type == ACPI_TYPE_INTEGER) { int eventcode = obj->integer.value; @@ -192,7 +181,7 @@ static void msi_wmi_notify(u32 value, void *context) eventcode); if (!key) { pr_info("Unknown key pressed - %x\n", eventcode); - goto msi_wmi_notify_exit; + return; } if (event_wmi->quirk_last_pressed) { @@ -204,7 +193,7 @@ static void msi_wmi_notify(u32 value, void *context) pr_debug("Suppressed key event 0x%X - " "Last press was %lld us ago\n", key->code, ktime_to_us(diff)); - goto msi_wmi_notify_exit; + return; } last_pressed = cur; } @@ -221,9 +210,6 @@ static void msi_wmi_notify(u32 value, void *context) } } else pr_info("Unknown event received\n"); - -msi_wmi_notify_exit: - kfree(response.pointer); } static int __init msi_wmi_backlight_setup(void) diff --git a/drivers/platform/x86/toshiba-wmi.c b/drivers/platform/x86/toshiba-wmi.c index 77c35529ab6f..12c46455e8dc 100644 --- a/drivers/platform/x86/toshiba-wmi.c +++ b/drivers/platform/x86/toshiba-wmi.c @@ -32,26 +32,13 @@ static const struct key_entry toshiba_wmi_keymap[] __initconst = { { KE_END, 0 } }; -static void toshiba_wmi_notify(u32 value, void *context) +static void toshiba_wmi_notify(union acpi_object *obj, void *context) { - struct acpi_buffer response = { ACPI_ALLOCATE_BUFFER, NULL }; - union acpi_object *obj; - acpi_status status; - - status = wmi_get_event_data(value, &response); - if (ACPI_FAILURE(status)) { - pr_err("Bad event status 0x%x\n", status); - return; - } - - obj = (union acpi_object *)response.pointer; if (!obj) return; /* TODO: Add proper checks once we have data */ pr_debug("Unknown event received, obj type %x\n", obj->type); - - kfree(response.pointer); } static const struct dmi_system_id toshiba_wmi_dmi_table[] __initconst = { diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c index 1d0b2d6040d1..6ab181dd94ab 100644 --- a/drivers/platform/x86/wmi.c +++ b/drivers/platform/x86/wmi.c @@ -1227,40 +1227,33 @@ static int wmi_notify_device(struct device *dev, void *data) if (!(wblock->gblock.flags & ACPI_WMI_EVENT && wblock->gblock.notify_id == *event)) return 0; + /* The ACPI WMI specification says that _WED should be + * evaluated every time an notification is received, even + * if no consumers are present. + * + * Some firmware implementations actually depend on this + * by using a queue for events which will fill up if the + * WMI driver core stops evaluating _WED due to missing + * WMI event consumers. + */ + ret = wmi_get_notify_data(wblock, &obj); + if (ret < 0) + return -EIO; + down_read(&wblock->notify_lock); /* The WMI driver notify handler conflicts with the legacy WMI handler. * Because of this the WMI driver notify handler takes precedence. */ if (wblock->dev.dev.driver && wblock->driver_ready) { - ret = wmi_get_notify_data(wblock, &obj); - if (ret >= 0) { - wmi_notify_driver(wblock, obj); - kfree(obj); - } + wmi_notify_driver(wblock, obj); } else { - if (wblock->handler) { - wblock->handler(*event, wblock->handler_data); - } else { - /* The ACPI WMI specification says that _WED should be - * evaluated every time an notification is received, even - * if no consumers are present. - * - * Some firmware implementations actually depend on this - * by using a queue for events which will fill up if the - * WMI driver core stops evaluating _WED due to missing - * WMI event consumers. - * - * Because of this we need this seemingly useless call to - * wmi_get_notify_data() which in turn evaluates _WED. - */ - ret = wmi_get_notify_data(wblock, &obj); - if (ret >= 0) - kfree(obj); - } - + if (wblock->handler) + wblock->handler(obj, wblock->handler_data); } up_read(&wblock->notify_lock); + kfree(obj); + acpi_bus_generate_netlink_event("wmi", acpi_dev_name(wblock->acpi_device), *event, 0); return -EBUSY; diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 0687a442fec7..eed105b1fbfb 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -386,7 +386,7 @@ extern bool acpi_is_pnp_device(struct acpi_device *); #if defined(CONFIG_ACPI_WMI) || defined(CONFIG_ACPI_WMI_MODULE) -typedef void (*wmi_notify_handler) (u32 value, void *context); +typedef void (*wmi_notify_handler) (union acpi_object *data, void *context); int wmi_instance_count(const char *guid); -- cgit v1.2.3 From 79a56f4c8fa629ac79ada8f4b746195bd91f09c7 Mon Sep 17 00:00:00 2001 From: Armin Wolf Date: Sun, 1 Sep 2024 05:10:53 +0200 Subject: platform/x86: wmi: Remove wmi_get_event_data() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since the WMI driver core now takes care of retrieving the WMI event data even for legacy WMI notify handlers, this function is no longer used. Remove it to prevent WMI drivers from messing up the ACPI firmware on some machines. Reviewed-by: Ilpo Järvinen Reviewed-by: Hans de Goede Signed-off-by: Armin Wolf Link: https://lore.kernel.org/r/20240901031055.3030-4-W_Armin@gmx.de Signed-off-by: Hans de Goede --- drivers/platform/x86/wmi.c | 57 ---------------------------------------------- include/linux/acpi.h | 1 - 2 files changed, 58 deletions(-) (limited to 'include/linux') diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c index 6ab181dd94ab..c7f0754f74b4 100644 --- a/drivers/platform/x86/wmi.c +++ b/drivers/platform/x86/wmi.c @@ -199,23 +199,6 @@ static int wmidev_match_guid(struct device *dev, const void *data) return 0; } -static int wmidev_match_notify_id(struct device *dev, const void *data) -{ - struct wmi_block *wblock = dev_to_wblock(dev); - const u32 *notify_id = data; - - /* Legacy GUID-based functions are restricted to only see - * a single WMI device for each GUID. - */ - if (test_bit(WMI_GUID_DUPLICATED, &wblock->flags)) - return 0; - - if (wblock->gblock.flags & ACPI_WMI_EVENT && wblock->gblock.notify_id == *notify_id) - return 1; - - return 0; -} - static const struct bus_type wmi_bus_type; static struct wmi_device *wmi_find_device_by_guid(const char *guid_string) @@ -235,17 +218,6 @@ static struct wmi_device *wmi_find_device_by_guid(const char *guid_string) return dev_to_wdev(dev); } -static struct wmi_device *wmi_find_event_by_notify_id(const u32 notify_id) -{ - struct device *dev; - - dev = bus_find_device(&wmi_bus_type, NULL, ¬ify_id, wmidev_match_notify_id); - if (!dev) - return ERR_PTR(-ENODEV); - - return to_wmi_device(dev); -} - static void wmi_device_put(struct wmi_device *wdev) { put_device(&wdev->dev); @@ -649,35 +621,6 @@ acpi_status wmi_remove_notify_handler(const char *guid) } EXPORT_SYMBOL_GPL(wmi_remove_notify_handler); -/** - * wmi_get_event_data - Get WMI data associated with an event (deprecated) - * - * @event: Event to find - * @out: Buffer to hold event data - * - * Get extra data associated with an WMI event, the caller needs to free @out. - * - * Return: acpi_status signaling success or error. - */ -acpi_status wmi_get_event_data(u32 event, struct acpi_buffer *out) -{ - struct wmi_block *wblock; - struct wmi_device *wdev; - acpi_status status; - - wdev = wmi_find_event_by_notify_id(event); - if (IS_ERR(wdev)) - return AE_NOT_FOUND; - - wblock = container_of(wdev, struct wmi_block, dev); - status = get_event_data(wblock, out); - - wmi_device_put(wdev); - - return status; -} -EXPORT_SYMBOL_GPL(wmi_get_event_data); - /** * wmi_has_guid - Check if a GUID is available * @guid_string: 36 char string of the form fa50ff2b-f2e8-45de-83fa-65417f2f49ba diff --git a/include/linux/acpi.h b/include/linux/acpi.h index eed105b1fbfb..3cbe4b57bc73 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -401,7 +401,6 @@ extern acpi_status wmi_set_block(const char *guid, u8 instance, extern acpi_status wmi_install_notify_handler(const char *guid, wmi_notify_handler handler, void *data); extern acpi_status wmi_remove_notify_handler(const char *guid); -extern acpi_status wmi_get_event_data(u32 event, struct acpi_buffer *out); extern bool wmi_has_guid(const char *guid); extern char *wmi_get_acpi_device_uid(const char *guid); -- cgit v1.2.3 From 3e6a7e3cda773adacc2fa4b9623d0a8c0f904d50 Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Tue, 27 Aug 2024 09:59:38 -0700 Subject: iommufd: Reorder struct forward declarations Reorder struct forward declarations to alphabetic order to simplify maintenance, as upcoming patches will add more to the list. No functional change intended. Link: https://patch.msgid.link/r/c5dd87100f6f01389b838c63237e28c5dd373358.1724776335.git.nicolinc@nvidia.com Signed-off-by: Nicolin Chen Signed-off-by: Jason Gunthorpe --- include/linux/iommufd.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h index c2f2f6b9148e..30f832a60ccb 100644 --- a/include/linux/iommufd.h +++ b/include/linux/iommufd.h @@ -11,12 +11,12 @@ #include struct device; -struct iommufd_device; -struct page; -struct iommufd_ctx; -struct iommufd_access; struct file; struct iommu_group; +struct iommufd_access; +struct iommufd_ctx; +struct iommufd_device; +struct page; struct iommufd_device *iommufd_device_bind(struct iommufd_ctx *ictx, struct device *dev, u32 *id); -- cgit v1.2.3 From 6ff4cd1160afafc12ad1603e3d2f39256e4b708d Mon Sep 17 00:00:00 2001 From: Hongbo Li Date: Tue, 27 Aug 2024 10:45:15 +0800 Subject: lib/string_choices: Add str_true_false()/str_false_true() helper Add str_true_false()/str_false_true() helper to return "true" or "false" string literal. Signed-off-by: Hongbo Li Link: https://lore.kernel.org/r/20240827024517.914100-2-lihongbo22@huawei.com Signed-off-by: Kees Cook --- include/linux/string_choices.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/string_choices.h b/include/linux/string_choices.h index 1320bcdcb89c..ebcc56b28ede 100644 --- a/include/linux/string_choices.h +++ b/include/linux/string_choices.h @@ -48,6 +48,12 @@ static inline const char *str_up_down(bool v) } #define str_down_up(v) str_up_down(!(v)) +static inline const char *str_true_false(bool v) +{ + return v ? "true" : "false"; +} +#define str_false_true(v) str_true_false(!(v)) + /** * str_plural - Return the simple pluralization based on English counts * @num: Number used for deciding pluralization -- cgit v1.2.3 From c2708ba91c3c1fba424b77de83b6fc45cbf38c46 Mon Sep 17 00:00:00 2001 From: Hongbo Li Date: Thu, 5 Sep 2024 17:25:39 +0800 Subject: lib/string_choices: Introduce several opposite string choice helpers Similar to the exists helper: str_enable_disable/ str_enabled_disabled/str_on_off/str_yes_no helpers, we can add the opposite helpers. That's str_disable_enable, str_disabled_enabled, str_off_on and str_no_yes. There are more than 10 cases currently (expect str_disable_enable now has 3 use cases) exist in the code can be replaced with these helper. Signed-off-by: Hongbo Li Acked-by: Andy Shevchenko Link: https://lore.kernel.org/r/20240905092540.2962122-2-lihongbo22@huawei.com Signed-off-by: Kees Cook --- include/linux/string_choices.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/string_choices.h b/include/linux/string_choices.h index ebcc56b28ede..fd067992260a 100644 --- a/include/linux/string_choices.h +++ b/include/linux/string_choices.h @@ -8,11 +8,13 @@ static inline const char *str_enable_disable(bool v) { return v ? "enable" : "disable"; } +#define str_disable_enable(v) str_enable_disable(!(v)) static inline const char *str_enabled_disabled(bool v) { return v ? "enabled" : "disabled"; } +#define str_disabled_enabled(v) str_enabled_disabled(!(v)) static inline const char *str_hi_lo(bool v) { @@ -36,11 +38,13 @@ static inline const char *str_on_off(bool v) { return v ? "on" : "off"; } +#define str_off_on(v) str_on_off(!(v)) static inline const char *str_yes_no(bool v) { return v ? "yes" : "no"; } +#define str_no_yes(v) str_yes_no(!(v)) static inline const char *str_up_down(bool v) { -- cgit v1.2.3 From c121d5cc3a993cdbfab46a152bdd50227a4d5e8c Mon Sep 17 00:00:00 2001 From: Hongbo Li Date: Thu, 5 Sep 2024 17:25:40 +0800 Subject: lib/string_choices: Add some comments to make more clear for string choices helpers. Add some comments to explain why we should use string_choices helpers. Signed-off-by: Hongbo Li Acked-by: Andy Shevchenko Link: https://lore.kernel.org/r/20240905092540.2962122-3-lihongbo22@huawei.com Signed-off-by: Kees Cook --- include/linux/string_choices.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/string_choices.h b/include/linux/string_choices.h index fd067992260a..120ca0f28e95 100644 --- a/include/linux/string_choices.h +++ b/include/linux/string_choices.h @@ -2,6 +2,19 @@ #ifndef _LINUX_STRING_CHOICES_H_ #define _LINUX_STRING_CHOICES_H_ +/* + * Here provide a series of helpers in the str_$TRUE_$FALSE format (you can + * also expand some helpers as needed), where $TRUE and $FALSE are their + * corresponding literal strings. These helpers can be used in the printing + * and also in other places where constant strings are required. Using these + * helpers offers the following benefits: + * 1) Reducing the hardcoding of strings, which makes the code more elegant + * through these simple literal-meaning helpers. + * 2) Unifying the output, which prevents the same string from being printed + * in various forms, such as enable/disable, enabled/disabled, en/dis. + * 3) Deduping by the linker, which results in a smaller binary file. + */ + #include static inline const char *str_enable_disable(bool v) -- cgit v1.2.3 From 1ae497c78f01855f3695b58481311ffdd429b028 Mon Sep 17 00:00:00 2001 From: Shung-Hsi Yu Date: Thu, 5 Sep 2024 13:52:32 +0800 Subject: bpf: use type_may_be_null() helper for nullable-param check Commit 980ca8ceeae6 ("bpf: check bpf_dummy_struct_ops program params for test runs") does bitwise AND between reg_type and PTR_MAYBE_NULL, which is correct, but due to type difference the compiler complains: net/bpf/bpf_dummy_struct_ops.c:118:31: warning: bitwise operation between different enumeration types ('const enum bpf_reg_type' and 'enum bpf_type_flag') [-Wenum-enum-conversion] 118 | if (info && (info->reg_type & PTR_MAYBE_NULL)) | ~~~~~~~~~~~~~~ ^ ~~~~~~~~~~~~~~ Workaround the warning by moving the type_may_be_null() helper from verifier.c into bpf_verifier.h, and reuse it here to check whether param is nullable. Fixes: 980ca8ceeae6 ("bpf: check bpf_dummy_struct_ops program params for test runs") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202404241956.HEiRYwWq-lkp@intel.com/ Signed-off-by: Shung-Hsi Yu Acked-by: Eduard Zingerman Link: https://lore.kernel.org/r/20240905055233.70203-1-shung-hsi.yu@suse.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 5 +++++ kernel/bpf/verifier.c | 5 ----- net/bpf/bpf_dummy_struct_ops.c | 2 +- 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 8458632824a4..4513372c5bc8 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -927,6 +927,11 @@ static inline bool type_is_sk_pointer(enum bpf_reg_type type) type == PTR_TO_XDP_SOCK; } +static inline bool type_may_be_null(u32 type) +{ + return type & PTR_MAYBE_NULL; +} + static inline void mark_reg_scratched(struct bpf_verifier_env *env, u32 regno) { env->scratched_regs |= 1U << regno; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index b806afeba212..53d0556fbbf3 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -383,11 +383,6 @@ static void verbose_invalid_scalar(struct bpf_verifier_env *env, verbose(env, " should have been in [%d, %d]\n", range.minval, range.maxval); } -static bool type_may_be_null(u32 type) -{ - return type & PTR_MAYBE_NULL; -} - static bool reg_not_null(const struct bpf_reg_state *reg) { enum bpf_reg_type type; diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c index 3ea52b05adfb..f71f67c6896b 100644 --- a/net/bpf/bpf_dummy_struct_ops.c +++ b/net/bpf/bpf_dummy_struct_ops.c @@ -115,7 +115,7 @@ static int check_test_run_args(struct bpf_prog *prog, struct bpf_dummy_ops_test_ offset = btf_ctx_arg_offset(bpf_dummy_ops_btf, func_proto, arg_no); info = find_ctx_arg_info(prog->aux, offset); - if (info && (info->reg_type & PTR_MAYBE_NULL)) + if (info && type_may_be_null(info->reg_type)) continue; return -EINVAL; -- cgit v1.2.3 From 706ae6446494b4523d33b0d96ea1fd9d50ca9be6 Mon Sep 17 00:00:00 2001 From: Nikita Shubin Date: Wed, 4 Sep 2024 14:41:07 +0300 Subject: clk: fixed-rate: add devm_clk_hw_register_fixed_rate_parent_data() Add devm_clk_hw_register_fixed_rate_parent_data(), devres-managed helper to register fixed-rate clock with parent_data. Signed-off-by: Nikita Shubin Link: https://lore.kernel.org/r/20240904-devm_clk_hw_register_fixed_rate_parent_data-v1-1-7f14d6b456e5@maquefel.me Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 4a537260f655..7e43caabb54b 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -393,6 +393,20 @@ struct clk *clk_register_fixed_rate(struct device *dev, const char *name, #define devm_clk_hw_register_fixed_rate(dev, name, parent_name, flags, fixed_rate) \ __clk_hw_register_fixed_rate((dev), NULL, (name), (parent_name), NULL, \ NULL, (flags), (fixed_rate), 0, 0, true) +/** + * devm_clk_hw_register_fixed_rate_parent_data - register fixed-rate clock with + * the clock framework + * @dev: device that is registering this clock + * @name: name of this clock + * @parent_data: parent clk data + * @flags: framework-specific flags + * @fixed_rate: non-adjustable clock rate + */ +#define devm_clk_hw_register_fixed_rate_parent_data(dev, name, parent_data, flags, \ + fixed_rate) \ + __clk_hw_register_fixed_rate((dev), NULL, (name), NULL, NULL, \ + (parent_data), (flags), (fixed_rate), 0, \ + 0, true) /** * clk_hw_register_fixed_rate_parent_hw - register fixed-rate clock with * the clock framework -- cgit v1.2.3 From 9934a1bd45b2b03f6d1204a6ae2780d3b009799f Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 5 Aug 2024 10:57:31 +0200 Subject: clk: provide devm_clk_get_optional_enabled_with_rate() There are clock users in the kernel that can't use devm_clk_get_optional_enabled() as they need to set rate after getting the clock and before enabling it. Provide a managed helper that wraps these operations in the correct order. Signed-off-by: Bartosz Golaszewski Link: https://lore.kernel.org/r/20240805-clk-new-helper-v2-1-e5fdd1e1d729@linaro.org Signed-off-by: Stephen Boyd --- drivers/clk/clk-devres.c | 28 ++++++++++++++++++++++++++++ include/linux/clk.h | 33 +++++++++++++++++++++++++++++++++ 2 files changed, 61 insertions(+) (limited to 'include/linux') diff --git a/drivers/clk/clk-devres.c b/drivers/clk/clk-devres.c index 90e6078fb6e1..82ae1f26e634 100644 --- a/drivers/clk/clk-devres.c +++ b/drivers/clk/clk-devres.c @@ -99,6 +99,34 @@ struct clk *devm_clk_get_optional_enabled(struct device *dev, const char *id) } EXPORT_SYMBOL_GPL(devm_clk_get_optional_enabled); +struct clk *devm_clk_get_optional_enabled_with_rate(struct device *dev, + const char *id, + unsigned long rate) +{ + struct clk *clk; + int ret; + + clk = __devm_clk_get(dev, id, clk_get_optional, NULL, + clk_disable_unprepare); + if (IS_ERR(clk)) + return ERR_CAST(clk); + + ret = clk_set_rate(clk, rate); + if (ret) + goto out_put_clk; + + ret = clk_prepare_enable(clk); + if (ret) + goto out_put_clk; + + return clk; + +out_put_clk: + devm_clk_put(dev, clk); + return ERR_PTR(ret); +} +EXPORT_SYMBOL_GPL(devm_clk_get_optional_enabled_with_rate); + struct clk_bulk_devres { struct clk_bulk_data *clks; int num_clks; diff --git a/include/linux/clk.h b/include/linux/clk.h index 0fa56d672532..851a0f2cf42c 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -640,6 +640,32 @@ struct clk *devm_clk_get_optional_prepared(struct device *dev, const char *id); */ struct clk *devm_clk_get_optional_enabled(struct device *dev, const char *id); +/** + * devm_clk_get_optional_enabled_with_rate - devm_clk_get_optional() + + * clk_set_rate() + + * clk_prepare_enable() + * @dev: device for clock "consumer" + * @id: clock consumer ID + * @rate: new clock rate + * + * Context: May sleep. + * + * Return: a struct clk corresponding to the clock producer, or + * valid IS_ERR() condition containing errno. The implementation + * uses @dev and @id to determine the clock consumer, and thereby + * the clock producer. If no such clk is found, it returns NULL + * which serves as a dummy clk. That's the only difference compared + * to devm_clk_get_enabled(). + * + * The returned clk (if valid) is prepared and enabled and rate was set. + * + * The clock will automatically be disabled, unprepared and freed + * when the device is unbound from the bus. + */ +struct clk *devm_clk_get_optional_enabled_with_rate(struct device *dev, + const char *id, + unsigned long rate); + /** * devm_get_clk_from_child - lookup and obtain a managed reference to a * clock producer from child node. @@ -982,6 +1008,13 @@ static inline struct clk *devm_clk_get_optional_enabled(struct device *dev, return NULL; } +static inline struct clk * +devm_clk_get_optional_enabled_with_rate(struct device *dev, const char *id, + unsigned long rate) +{ + return NULL; +} + static inline int __must_check devm_clk_bulk_get(struct device *dev, int num_clks, struct clk_bulk_data *clks) { -- cgit v1.2.3 From 08062af0a52107a243f7608fd972edb54ca5b7f8 Mon Sep 17 00:00:00 2001 From: Joe Damato Date: Wed, 4 Sep 2024 15:34:30 +0000 Subject: net: napi: Prevent overflow of napi_defer_hard_irqs In commit 6f8b12d661d0 ("net: napi: add hard irqs deferral feature") napi_defer_irqs was added to net_device and napi_defer_irqs_count was added to napi_struct, both as type int. This value never goes below zero, so there is not reason for it to be a signed int. Change the type for both from int to u32, and add an overflow check to sysfs to limit the value to S32_MAX. The limit of S32_MAX was chosen because the practical limit before this patch was S32_MAX (anything larger was an overflow) and thus there are no behavioral changes introduced. If the extra bit is needed in the future, the limit can be raised. Before this patch: $ sudo bash -c 'echo 2147483649 > /sys/class/net/eth4/napi_defer_hard_irqs' $ cat /sys/class/net/eth4/napi_defer_hard_irqs -2147483647 After this patch: $ sudo bash -c 'echo 2147483649 > /sys/class/net/eth4/napi_defer_hard_irqs' bash: line 0: echo: write error: Numerical result out of range Similarly, /sys/class/net/XXXXX/tx_queue_len is defined as unsigned: include/linux/netdevice.h: unsigned int tx_queue_len; And has an overflow check: dev_change_tx_queue_len(..., unsigned long new_len): if (new_len != (unsigned int)new_len) return -ERANGE; Suggested-by: Jakub Kicinski Signed-off-by: Joe Damato Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20240904153431.307932-1-jdamato@fastly.com Signed-off-by: Jakub Kicinski --- Documentation/networking/net_cachelines/net_device.rst | 2 +- include/linux/netdevice.h | 4 ++-- net/core/net-sysfs.c | 6 +++++- 3 files changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst index 56d4bbaf8a2c..22b07c814f4a 100644 --- a/Documentation/networking/net_cachelines/net_device.rst +++ b/Documentation/networking/net_cachelines/net_device.rst @@ -99,7 +99,7 @@ unsigned_int num_rx_queues unsigned_int real_num_rx_queues - read_mostly get_rps_cpu struct_bpf_prog* xdp_prog - read_mostly netif_elide_gro() unsigned_long gro_flush_timeout - read_mostly napi_complete_done -int napi_defer_hard_irqs - read_mostly napi_complete_done +u32 napi_defer_hard_irqs - read_mostly napi_complete_done unsigned_int gro_max_size - read_mostly skb_gro_receive unsigned_int gro_ipv4_max_size - read_mostly skb_gro_receive rx_handler_func_t* rx_handler read_mostly - __netif_receive_skb_core diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ca5f0dda733b..b47c00657bd0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -356,7 +356,7 @@ struct napi_struct { unsigned long state; int weight; - int defer_hard_irqs_count; + u32 defer_hard_irqs_count; unsigned long gro_bitmask; int (*poll)(struct napi_struct *, int); #ifdef CONFIG_NETPOLL @@ -2075,7 +2075,7 @@ struct net_device { unsigned int real_num_rx_queues; struct netdev_rx_queue *_rx; unsigned long gro_flush_timeout; - int napi_defer_hard_irqs; + u32 napi_defer_hard_irqs; unsigned int gro_max_size; unsigned int gro_ipv4_max_size; rx_handler_func_t __rcu *rx_handler; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 01a9fb54ef42..146a271a74e0 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -32,6 +32,7 @@ #ifdef CONFIG_SYSFS static const char fmt_hex[] = "%#x\n"; static const char fmt_dec[] = "%d\n"; +static const char fmt_uint[] = "%u\n"; static const char fmt_ulong[] = "%lu\n"; static const char fmt_u64[] = "%llu\n"; @@ -425,6 +426,9 @@ NETDEVICE_SHOW_RW(gro_flush_timeout, fmt_ulong); static int change_napi_defer_hard_irqs(struct net_device *dev, unsigned long val) { + if (val > S32_MAX) + return -ERANGE; + WRITE_ONCE(dev->napi_defer_hard_irqs, val); return 0; } @@ -438,7 +442,7 @@ static ssize_t napi_defer_hard_irqs_store(struct device *dev, return netdev_store(dev, attr, buf, len, change_napi_defer_hard_irqs); } -NETDEVICE_SHOW_RW(napi_defer_hard_irqs, fmt_dec); +NETDEVICE_SHOW_RW(napi_defer_hard_irqs, fmt_uint); static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) -- cgit v1.2.3 From de35996d4b364749194c5b473d1912578880833e Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Sun, 4 Aug 2024 18:47:08 -0700 Subject: Input: matrix_keypad - remove support for platform data There are no more users of struct matrix_keypad_platform_data in the kernel, remove support for it from the driver. Acked-by: Arnd Bergmann Reviewed-by: Linus Walleij Link: https://lore.kernel.org/r/20240805014710.1961677-6-dmitry.torokhov@gmail.com Signed-off-by: Dmitry Torokhov --- drivers/input/keyboard/matrix_keypad.c | 74 ++-------------------------------- include/linux/input/matrix_keypad.h | 48 ---------------------- 2 files changed, 3 insertions(+), 119 deletions(-) (limited to 'include/linux') diff --git a/drivers/input/keyboard/matrix_keypad.c b/drivers/input/keyboard/matrix_keypad.c index 5f7e6f27e9c5..3c38bae576ed 100644 --- a/drivers/input/keyboard/matrix_keypad.c +++ b/drivers/input/keyboard/matrix_keypad.c @@ -271,55 +271,6 @@ static int matrix_keypad_resume(struct device *dev) static DEFINE_SIMPLE_DEV_PM_OPS(matrix_keypad_pm_ops, matrix_keypad_suspend, matrix_keypad_resume); -static int matrix_keypad_init_pdata_gpio(struct platform_device *pdev, - const struct matrix_keypad_platform_data *pdata, - struct matrix_keypad *keypad) -{ - int i, err; - - keypad->num_col_gpios = pdata->num_col_gpios; - keypad->num_row_gpios = pdata->num_row_gpios; - - /* initialized strobe lines as outputs, activated */ - for (i = 0; i < pdata->num_col_gpios; i++) { - err = devm_gpio_request(&pdev->dev, - pdata->col_gpios[i], "matrix_kbd_col"); - if (err) { - dev_err(&pdev->dev, - "failed to request GPIO%d for COL%d\n", - pdata->col_gpios[i], i); - return err; - } - - keypad->col_gpios[i] = gpio_to_desc(pdata->col_gpios[i]); - - if (pdata->active_low ^ gpiod_is_active_low(keypad->col_gpios[i])) - gpiod_toggle_active_low(keypad->col_gpios[i]); - - gpiod_direction_output(keypad->col_gpios[i], 1); - } - - for (i = 0; i < pdata->num_row_gpios; i++) { - err = devm_gpio_request(&pdev->dev, - pdata->row_gpios[i], "matrix_kbd_row"); - if (err) { - dev_err(&pdev->dev, - "failed to request GPIO%d for ROW%d\n", - pdata->row_gpios[i], i); - return err; - } - - keypad->row_gpios[i] = gpio_to_desc(pdata->row_gpios[i]); - - if (pdata->active_low ^ gpiod_is_active_low(keypad->row_gpios[i])) - gpiod_toggle_active_low(keypad->row_gpios[i]); - - gpiod_direction_input(keypad->row_gpios[i]); - } - - return 0; -} - static int matrix_keypad_init_gpio(struct platform_device *pdev, struct matrix_keypad *keypad) { @@ -420,11 +371,8 @@ static int matrix_keypad_setup_interrupts(struct platform_device *pdev, static int matrix_keypad_probe(struct platform_device *pdev) { - const struct matrix_keypad_platform_data *pdata = - dev_get_platdata(&pdev->dev); struct matrix_keypad *keypad; struct input_dev *input_dev; - bool autorepeat; bool wakeup; int err; @@ -448,16 +396,7 @@ static int matrix_keypad_probe(struct platform_device *pdev) device_property_read_u32(&pdev->dev, "col-scan-delay-us", &keypad->col_scan_delay_us); - if (pdata) { - keypad->col_scan_delay_us = pdata->col_scan_delay_us; - keypad->debounce_ms = pdata->debounce_ms; - keypad->drive_inactive_cols = pdata->drive_inactive_cols; - } - - if (pdata) - err = matrix_keypad_init_pdata_gpio(pdev, pdata, keypad); - else - err = matrix_keypad_init_gpio(pdev, keypad); + err = matrix_keypad_init_gpio(pdev, keypad); if (err) return err; @@ -472,8 +411,7 @@ static int matrix_keypad_probe(struct platform_device *pdev) input_dev->open = matrix_keypad_start; input_dev->close = matrix_keypad_stop; - err = matrix_keypad_build_keymap(pdata ? pdata->keymap_data : NULL, - NULL, + err = matrix_keypad_build_keymap(NULL, NULL, keypad->num_row_gpios, keypad->num_col_gpios, NULL, input_dev); @@ -482,11 +420,7 @@ static int matrix_keypad_probe(struct platform_device *pdev) return -ENOMEM; } - autorepeat = !device_property_read_bool(&pdev->dev, - "linux,no-autorepeat"); - if (autorepeat && pdata->no_autorepeat) - autorepeat = false; - if (autorepeat) + if (!device_property_read_bool(&pdev->dev, "linux,no-autorepeat")) __set_bit(EV_REP, input_dev->evbit); input_set_capability(input_dev, EV_MSC, MSC_SCAN); @@ -499,8 +433,6 @@ static int matrix_keypad_probe(struct platform_device *pdev) wakeup = device_property_read_bool(&pdev->dev, "wakeup-source") || /* legacy */ device_property_read_bool(&pdev->dev, "linux,wakeup"); - if (!wakeup && pdata) - wakeup = pdata->wakeup; device_init_wakeup(&pdev->dev, wakeup); platform_set_drvdata(pdev, keypad); diff --git a/include/linux/input/matrix_keypad.h b/include/linux/input/matrix_keypad.h index b8d8d69eba29..90867f44ab4d 100644 --- a/include/linux/input/matrix_keypad.h +++ b/include/linux/input/matrix_keypad.h @@ -34,52 +34,6 @@ struct matrix_keymap_data { unsigned int keymap_size; }; -/** - * struct matrix_keypad_platform_data - platform-dependent keypad data - * @keymap_data: pointer to &matrix_keymap_data - * @row_gpios: pointer to array of gpio numbers representing rows - * @col_gpios: pointer to array of gpio numbers reporesenting colums - * @num_row_gpios: actual number of row gpios used by device - * @num_col_gpios: actual number of col gpios used by device - * @col_scan_delay_us: delay, measured in microseconds, that is - * needed before we can keypad after activating column gpio - * @debounce_ms: debounce interval in milliseconds - * @clustered_irq: may be specified if interrupts of all row/column GPIOs - * are bundled to one single irq - * @clustered_irq_flags: flags that are needed for the clustered irq - * @active_low: gpio polarity - * @wakeup: controls whether the device should be set up as wakeup - * source - * @no_autorepeat: disable key autorepeat - * @drive_inactive_cols: drive inactive columns during scan, rather than - * making them inputs. - * - * This structure represents platform-specific data that use used by - * matrix_keypad driver to perform proper initialization. - */ -struct matrix_keypad_platform_data { - const struct matrix_keymap_data *keymap_data; - - const unsigned int *row_gpios; - const unsigned int *col_gpios; - - unsigned int num_row_gpios; - unsigned int num_col_gpios; - - unsigned int col_scan_delay_us; - - /* key debounce interval in milli-second */ - unsigned int debounce_ms; - - unsigned int clustered_irq; - unsigned int clustered_irq_flags; - - bool active_low; - bool wakeup; - bool no_autorepeat; - bool drive_inactive_cols; -}; - int matrix_keypad_build_keymap(const struct matrix_keymap_data *keymap_data, const char *keymap_name, unsigned int rows, unsigned int cols, @@ -88,6 +42,4 @@ int matrix_keypad_build_keymap(const struct matrix_keymap_data *keymap_data, int matrix_keypad_parse_properties(struct device *dev, unsigned int *rows, unsigned int *cols); -#define matrix_keypad_parse_of_params matrix_keypad_parse_properties - #endif /* _MATRIX_KEYPAD_H */ -- cgit v1.2.3 From f820b43754cdbd078a0d17122b281f42cbcd2155 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Fri, 23 Aug 2024 22:50:27 -0700 Subject: Input: zforce_ts - remove support for platfrom data There are no in-tree users of platform data and any new ones should either use device tree or static device properties, so let's remove platform data support. Tested-by: Andreas Kemnade # Tolino Shine2HD Link: https://lore.kernel.org/r/20240824055047.1706392-4-dmitry.torokhov@gmail.com Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/zforce_ts.c | 56 ++++++++++----------------------- include/linux/platform_data/zforce_ts.h | 15 --------- 2 files changed, 16 insertions(+), 55 deletions(-) delete mode 100644 include/linux/platform_data/zforce_ts.h (limited to 'include/linux') diff --git a/drivers/input/touchscreen/zforce_ts.c b/drivers/input/touchscreen/zforce_ts.c index 350cec8508a3..5a8f79b800e6 100644 --- a/drivers/input/touchscreen/zforce_ts.c +++ b/drivers/input/touchscreen/zforce_ts.c @@ -9,21 +9,19 @@ * Author: Pieter Truter */ -#include -#include -#include -#include -#include -#include #include -#include #include -#include +#include +#include +#include #include #include -#include -#include +#include +#include #include +#include +#include +#include #define WAIT_TIMEOUT msecs_to_jiffies(1000) @@ -108,7 +106,6 @@ struct zforce_ts { struct i2c_client *client; struct input_dev *input; struct touchscreen_properties prop; - const struct zforce_ts_platdata *pdata; char phys[32]; struct regulator *reg_vdd; @@ -702,39 +699,24 @@ static void zforce_reset(void *data) regulator_disable(ts->reg_vdd); } -static struct zforce_ts_platdata *zforce_parse_dt(struct device *dev) +static void zforce_ts_parse_legacy_properties(struct zforce_ts *ts) { - struct zforce_ts_platdata *pdata; - struct device_node *np = dev->of_node; - - if (!np) - return ERR_PTR(-ENOENT); + u32 x_max = 0; + u32 y_max = 0; - pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL); - if (!pdata) { - dev_err(dev, "failed to allocate platform data\n"); - return ERR_PTR(-ENOMEM); - } - - of_property_read_u32(np, "x-size", &pdata->x_max); - of_property_read_u32(np, "y-size", &pdata->y_max); + device_property_read_u32(&ts->client->dev, "x-size", &x_max); + input_set_abs_params(ts->input, ABS_MT_POSITION_X, 0, x_max, 0, 0); - return pdata; + device_property_read_u32(&ts->client->dev, "y-size", &y_max); + input_set_abs_params(ts->input, ABS_MT_POSITION_Y, 0, y_max, 0, 0); } static int zforce_probe(struct i2c_client *client) { - const struct zforce_ts_platdata *pdata = dev_get_platdata(&client->dev); struct zforce_ts *ts; struct input_dev *input_dev; int ret; - if (!pdata) { - pdata = zforce_parse_dt(&client->dev); - if (IS_ERR(pdata)) - return PTR_ERR(pdata); - } - ts = devm_kzalloc(&client->dev, sizeof(struct zforce_ts), GFP_KERNEL); if (!ts) return -ENOMEM; @@ -822,7 +804,6 @@ static int zforce_probe(struct i2c_client *client) mutex_init(&ts->access_mutex); mutex_init(&ts->command_mutex); - ts->pdata = pdata; ts->client = client; ts->input = input_dev; @@ -837,12 +818,7 @@ static int zforce_probe(struct i2c_client *client) __set_bit(EV_SYN, input_dev->evbit); __set_bit(EV_ABS, input_dev->evbit); - /* For multi touch */ - input_set_abs_params(input_dev, ABS_MT_POSITION_X, 0, - pdata->x_max, 0, 0); - input_set_abs_params(input_dev, ABS_MT_POSITION_Y, 0, - pdata->y_max, 0, 0); - + zforce_ts_parse_legacy_properties(ts); touchscreen_parse_properties(input_dev, true, &ts->prop); if (ts->prop.max_x == 0 || ts->prop.max_y == 0) { dev_err(&client->dev, "no size specified\n"); diff --git a/include/linux/platform_data/zforce_ts.h b/include/linux/platform_data/zforce_ts.h deleted file mode 100644 index 2463a4a856a6..000000000000 --- a/include/linux/platform_data/zforce_ts.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* drivers/input/touchscreen/zforce.c - * - * Copyright (C) 2012-2013 MundoReader S.L. - */ - -#ifndef _LINUX_INPUT_ZFORCE_TS_H -#define _LINUX_INPUT_ZFORCE_TS_H - -struct zforce_ts_platdata { - unsigned int x_max; - unsigned int y_max; -}; - -#endif /* _LINUX_INPUT_ZFORCE_TS_H */ -- cgit v1.2.3 From 23de126f9248a2f9218175ea0dd1c1403e334440 Mon Sep 17 00:00:00 2001 From: Pieter Van Trappen Date: Wed, 4 Sep 2024 08:27:42 +0200 Subject: net: dsa: microchip: replace unclear KSZ8830 strings Replace ksz8830 with ksz88x3 for CHIP_ID definition and other strings. This due to KSZ8830 not being an actual switch but the Chip ID shared among KSZ8863/8873 switches, impossible to differentiate from their Chip ID or Revision ID registers. Now all KSZ*_CHIP_ID macros refer to actual, existing switches which removes confusion. Signed-off-by: Pieter Van Trappen Acked-by: Arun Ramadoss Signed-off-by: David S. Miller --- drivers/net/dsa/microchip/ksz8.c | 2 +- drivers/net/dsa/microchip/ksz8863_smi.c | 4 +-- drivers/net/dsa/microchip/ksz_common.c | 48 ++++++++++++++--------------- drivers/net/dsa/microchip/ksz_common.h | 4 +-- drivers/net/dsa/microchip/ksz_spi.c | 6 ++-- include/linux/platform_data/microchip-ksz.h | 2 +- 6 files changed, 33 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/microchip/ksz8.c b/drivers/net/dsa/microchip/ksz8.c index 7af3c0853505..da7110d67558 100644 --- a/drivers/net/dsa/microchip/ksz8.c +++ b/drivers/net/dsa/microchip/ksz8.c @@ -194,7 +194,7 @@ int ksz8_change_mtu(struct ksz_device *dev, int port, int mtu) case KSZ8794_CHIP_ID: case KSZ8765_CHIP_ID: return ksz8795_change_mtu(dev, frame_size); - case KSZ8830_CHIP_ID: + case KSZ88X3_CHIP_ID: case KSZ8864_CHIP_ID: case KSZ8895_CHIP_ID: return ksz8863_change_mtu(dev, frame_size); diff --git a/drivers/net/dsa/microchip/ksz8863_smi.c b/drivers/net/dsa/microchip/ksz8863_smi.c index 5711a59e2ac9..a8bfcd917bf7 100644 --- a/drivers/net/dsa/microchip/ksz8863_smi.c +++ b/drivers/net/dsa/microchip/ksz8863_smi.c @@ -199,11 +199,11 @@ static void ksz8863_smi_shutdown(struct mdio_device *mdiodev) static const struct of_device_id ksz8863_dt_ids[] = { { .compatible = "microchip,ksz8863", - .data = &ksz_switch_chips[KSZ8830] + .data = &ksz_switch_chips[KSZ88X3] }, { .compatible = "microchip,ksz8873", - .data = &ksz_switch_chips[KSZ8830] + .data = &ksz_switch_chips[KSZ88X3] }, { }, }; diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index cd116de3ddb8..4e8710c7cb7b 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -246,16 +246,16 @@ static const struct ksz_drive_strength ksz9477_drive_strengths[] = { { SW_DRIVE_STRENGTH_28MA, 28000 }, }; -/* ksz8830_drive_strengths - Drive strength mapping for KSZ8830, KSZ8873, .. +/* ksz88x3_drive_strengths - Drive strength mapping for KSZ8863, KSZ8873, .. * variants. * This values are documented in KSZ8873 and KSZ8863 datasheets. */ -static const struct ksz_drive_strength ksz8830_drive_strengths[] = { +static const struct ksz_drive_strength ksz88x3_drive_strengths[] = { { 0, 8000 }, { KSZ8873_DRIVE_STRENGTH_16MA, 16000 }, }; -static void ksz8830_phylink_mac_config(struct phylink_config *config, +static void ksz88x3_phylink_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state); static void ksz_phylink_mac_config(struct phylink_config *config, @@ -265,8 +265,8 @@ static void ksz_phylink_mac_link_down(struct phylink_config *config, unsigned int mode, phy_interface_t interface); -static const struct phylink_mac_ops ksz8830_phylink_mac_ops = { - .mac_config = ksz8830_phylink_mac_config, +static const struct phylink_mac_ops ksz88x3_phylink_mac_ops = { + .mac_config = ksz88x3_phylink_mac_config, .mac_link_down = ksz_phylink_mac_link_down, .mac_link_up = ksz8_phylink_mac_link_up, }; @@ -1442,8 +1442,8 @@ const struct ksz_chip_data ksz_switch_chips[] = { .internal_phy = {true, true, true, true, false}, }, - [KSZ8830] = { - .chip_id = KSZ8830_CHIP_ID, + [KSZ88X3] = { + .chip_id = KSZ88X3_CHIP_ID, .dev_name = "KSZ8863/KSZ8873", .num_vlans = 16, .num_alus = 0, @@ -1453,7 +1453,7 @@ const struct ksz_chip_data ksz_switch_chips[] = { .num_tx_queues = 4, .num_ipms = 4, .ops = &ksz88xx_dev_ops, - .phylink_mac_ops = &ksz8830_phylink_mac_ops, + .phylink_mac_ops = &ksz88x3_phylink_mac_ops, .mib_names = ksz88xx_mib_names, .mib_cnt = ARRAY_SIZE(ksz88xx_mib_names), .reg_mib_cnt = MIB_COUNTER_NUM, @@ -1487,7 +1487,7 @@ const struct ksz_chip_data ksz_switch_chips[] = { .num_tx_queues = 4, .num_ipms = 4, .ops = &ksz88xx_dev_ops, - .phylink_mac_ops = &ksz8830_phylink_mac_ops, + .phylink_mac_ops = &ksz88x3_phylink_mac_ops, .mib_names = ksz88xx_mib_names, .mib_cnt = ARRAY_SIZE(ksz88xx_mib_names), .reg_mib_cnt = MIB_COUNTER_NUM, @@ -1510,7 +1510,7 @@ const struct ksz_chip_data ksz_switch_chips[] = { .num_tx_queues = 4, .num_ipms = 4, .ops = &ksz88xx_dev_ops, - .phylink_mac_ops = &ksz8830_phylink_mac_ops, + .phylink_mac_ops = &ksz88x3_phylink_mac_ops, .mib_names = ksz88xx_mib_names, .mib_cnt = ARRAY_SIZE(ksz88xx_mib_names), .reg_mib_cnt = MIB_COUNTER_NUM, @@ -2724,7 +2724,7 @@ static u32 ksz_get_phy_flags(struct dsa_switch *ds, int port) struct ksz_device *dev = ds->priv; switch (dev->chip_id) { - case KSZ8830_CHIP_ID: + case KSZ88X3_CHIP_ID: /* Silicon Errata Sheet (DS80000830A): * Port 1 does not work with LinkMD Cable-Testing. * Port 1 does not respond to received PAUSE control frames. @@ -3050,7 +3050,7 @@ static enum dsa_tag_protocol ksz_get_tag_protocol(struct dsa_switch *ds, if (ksz_is_ksz87xx(dev) || ksz_is_8895_family(dev)) proto = DSA_TAG_PROTO_KSZ8795; - if (dev->chip_id == KSZ8830_CHIP_ID || + if (dev->chip_id == KSZ88X3_CHIP_ID || dev->chip_id == KSZ8563_CHIP_ID || dev->chip_id == KSZ9893_CHIP_ID || dev->chip_id == KSZ9563_CHIP_ID) @@ -3162,7 +3162,7 @@ static int ksz_max_mtu(struct dsa_switch *ds, int port) case KSZ8794_CHIP_ID: case KSZ8765_CHIP_ID: return KSZ8795_HUGE_PACKET_SIZE - VLAN_ETH_HLEN - ETH_FCS_LEN; - case KSZ8830_CHIP_ID: + case KSZ88X3_CHIP_ID: case KSZ8864_CHIP_ID: case KSZ8895_CHIP_ID: return KSZ8863_HUGE_PACKET_SIZE - VLAN_ETH_HLEN - ETH_FCS_LEN; @@ -3334,7 +3334,7 @@ phy_interface_t ksz_get_xmii(struct ksz_device *dev, int port, bool gbit) return interface; } -static void ksz8830_phylink_mac_config(struct phylink_config *config, +static void ksz88x3_phylink_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) { @@ -3518,7 +3518,7 @@ static int ksz_switch_detect(struct ksz_device *dev) break; case KSZ88_FAMILY_ID: if (id2 == KSZ88_CHIP_ID_63) - dev->chip_id = KSZ8830_CHIP_ID; + dev->chip_id = KSZ88X3_CHIP_ID; else return -ENODEV; break; @@ -4592,24 +4592,24 @@ static int ksz9477_drive_strength_write(struct ksz_device *dev, } /** - * ksz8830_drive_strength_write() - Set the drive strength configuration for - * KSZ8830 compatible chip variants. + * ksz88x3_drive_strength_write() - Set the drive strength configuration for + * KSZ8863 compatible chip variants. * @dev: ksz device * @props: Array of drive strength properties to be set * @num_props: Number of properties in the array * - * This function applies the specified drive strength settings to KSZ8830 chip + * This function applies the specified drive strength settings to KSZ88X3 chip * variants (KSZ8873, KSZ8863). * It ensures the configurations align with what the chip variant supports and * warns or errors out on unsupported settings. * * Return: 0 on success, error code otherwise */ -static int ksz8830_drive_strength_write(struct ksz_device *dev, +static int ksz88x3_drive_strength_write(struct ksz_device *dev, struct ksz_driver_strength_prop *props, int num_props) { - size_t array_size = ARRAY_SIZE(ksz8830_drive_strengths); + size_t array_size = ARRAY_SIZE(ksz88x3_drive_strengths); int microamp; int i, ret; @@ -4622,10 +4622,10 @@ static int ksz8830_drive_strength_write(struct ksz_device *dev, } microamp = props[KSZ_DRIVER_STRENGTH_IO].value; - ret = ksz_drive_strength_to_reg(ksz8830_drive_strengths, array_size, + ret = ksz_drive_strength_to_reg(ksz88x3_drive_strengths, array_size, microamp); if (ret < 0) { - ksz_drive_strength_error(dev, ksz8830_drive_strengths, + ksz_drive_strength_error(dev, ksz88x3_drive_strengths, array_size, microamp); return ret; } @@ -4685,8 +4685,8 @@ static int ksz_parse_drive_strength(struct ksz_device *dev) return 0; switch (dev->chip_id) { - case KSZ8830_CHIP_ID: - return ksz8830_drive_strength_write(dev, of_props, + case KSZ88X3_CHIP_ID: + return ksz88x3_drive_strength_write(dev, of_props, ARRAY_SIZE(of_props)); case KSZ8795_CHIP_ID: case KSZ8794_CHIP_ID: diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index e08d5a1339f4..bec846e20682 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -200,7 +200,7 @@ enum ksz_model { KSZ8795, KSZ8794, KSZ8765, - KSZ8830, + KSZ88X3, KSZ8864, KSZ8895, KSZ9477, @@ -628,7 +628,7 @@ static inline bool ksz_is_ksz87xx(struct ksz_device *dev) static inline bool ksz_is_ksz88x3(struct ksz_device *dev) { - return dev->chip_id == KSZ8830_CHIP_ID; + return dev->chip_id == KSZ88X3_CHIP_ID; } static inline bool ksz_is_8895_family(struct ksz_device *dev) diff --git a/drivers/net/dsa/microchip/ksz_spi.c b/drivers/net/dsa/microchip/ksz_spi.c index f4287310e89f..e3e341431f09 100644 --- a/drivers/net/dsa/microchip/ksz_spi.c +++ b/drivers/net/dsa/microchip/ksz_spi.c @@ -54,7 +54,7 @@ static int ksz_spi_probe(struct spi_device *spi) if (!chip) return -EINVAL; - if (chip->chip_id == KSZ8830_CHIP_ID) + if (chip->chip_id == KSZ88X3_CHIP_ID) regmap_config = ksz8863_regmap_config; else if (chip->chip_id == KSZ8795_CHIP_ID || chip->chip_id == KSZ8794_CHIP_ID || @@ -137,7 +137,7 @@ static const struct of_device_id ksz_dt_ids[] = { }, { .compatible = "microchip,ksz8863", - .data = &ksz_switch_chips[KSZ8830] + .data = &ksz_switch_chips[KSZ88X3] }, { .compatible = "microchip,ksz8864", @@ -145,7 +145,7 @@ static const struct of_device_id ksz_dt_ids[] = { }, { .compatible = "microchip,ksz8873", - .data = &ksz_switch_chips[KSZ8830] + .data = &ksz_switch_chips[KSZ88X3] }, { .compatible = "microchip,ksz8895", diff --git a/include/linux/platform_data/microchip-ksz.h b/include/linux/platform_data/microchip-ksz.h index d074019474f5..2ee1a679e592 100644 --- a/include/linux/platform_data/microchip-ksz.h +++ b/include/linux/platform_data/microchip-ksz.h @@ -27,7 +27,7 @@ enum ksz_chip_id { KSZ8795_CHIP_ID = 0x8795, KSZ8794_CHIP_ID = 0x8794, KSZ8765_CHIP_ID = 0x8765, - KSZ8830_CHIP_ID = 0x8830, + KSZ88X3_CHIP_ID = 0x8830, KSZ8864_CHIP_ID = 0x8864, KSZ8895_CHIP_ID = 0x8895, KSZ9477_CHIP_ID = 0x00947700, -- cgit v1.2.3 From 56bd72e9cd8272687aa2a8eccddabc5526cd7845 Mon Sep 17 00:00:00 2001 From: Marek Maslanka Date: Mon, 12 Aug 2024 18:41:42 +0000 Subject: clocksource: acpi_pm: Add external callback for suspend/resume Provides the capability to register an external callback for the ACPI PM timer, which is called during the suspend and resume processes. Signed-off-by: Marek Maslanka Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20240812184150.1079924-1-mmaslanka@google.com Signed-off-by: Daniel Lezcano --- drivers/clocksource/acpi_pm.c | 32 ++++++++++++++++++++++++++++++++ include/linux/acpi_pmtmr.h | 13 +++++++++++++ 2 files changed, 45 insertions(+) (limited to 'include/linux') diff --git a/drivers/clocksource/acpi_pm.c b/drivers/clocksource/acpi_pm.c index 82338773602c..b4330a01a566 100644 --- a/drivers/clocksource/acpi_pm.c +++ b/drivers/clocksource/acpi_pm.c @@ -25,6 +25,10 @@ #include #include +static void *suspend_resume_cb_data; + +static void (*suspend_resume_callback)(void *data, bool suspend); + /* * The I/O port the PMTMR resides at. * The location is detected during setup_arch(), @@ -58,6 +62,32 @@ u32 acpi_pm_read_verified(void) return v2; } +void acpi_pmtmr_register_suspend_resume_callback(void (*cb)(void *data, bool suspend), void *data) +{ + suspend_resume_callback = cb; + suspend_resume_cb_data = data; +} +EXPORT_SYMBOL_GPL(acpi_pmtmr_register_suspend_resume_callback); + +void acpi_pmtmr_unregister_suspend_resume_callback(void) +{ + suspend_resume_callback = NULL; + suspend_resume_cb_data = NULL; +} +EXPORT_SYMBOL_GPL(acpi_pmtmr_unregister_suspend_resume_callback); + +static void acpi_pm_suspend(struct clocksource *cs) +{ + if (suspend_resume_callback) + suspend_resume_callback(suspend_resume_cb_data, true); +} + +static void acpi_pm_resume(struct clocksource *cs) +{ + if (suspend_resume_callback) + suspend_resume_callback(suspend_resume_cb_data, false); +} + static u64 acpi_pm_read(struct clocksource *cs) { return (u64)read_pmtmr(); @@ -69,6 +99,8 @@ static struct clocksource clocksource_acpi_pm = { .read = acpi_pm_read, .mask = (u64)ACPI_PM_MASK, .flags = CLOCK_SOURCE_IS_CONTINUOUS, + .suspend = acpi_pm_suspend, + .resume = acpi_pm_resume, }; diff --git a/include/linux/acpi_pmtmr.h b/include/linux/acpi_pmtmr.h index 50d88bf1498d..0ded9220d379 100644 --- a/include/linux/acpi_pmtmr.h +++ b/include/linux/acpi_pmtmr.h @@ -26,6 +26,19 @@ static inline u32 acpi_pm_read_early(void) return acpi_pm_read_verified() & ACPI_PM_MASK; } +/** + * Register callback for suspend and resume event + * + * @cb Callback triggered on suspend and resume + * @data Data passed with the callback + */ +void acpi_pmtmr_register_suspend_resume_callback(void (*cb)(void *data, bool suspend), void *data); + +/** + * Remove registered callback for suspend and resume event + */ +void acpi_pmtmr_unregister_suspend_resume_callback(void); + #else static inline u32 acpi_pm_read_early(void) -- cgit v1.2.3 From 3f4c0ad490cc55db5b375a2e19c67159cb255795 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Mon, 26 Aug 2024 12:14:04 +0200 Subject: mtd: nand: Rename the NAND IO iteration helper Soon a helper for iterating over blocks will be needed (for continuous read purposes). In order to clarify the intend of this helper, let's rename it with the "page" wording inside. While at it, improve the doc and fix a typo. Signed-off-by: Miquel Raynal Reviewed-by: Pratyush Yadav Link: https://lore.kernel.org/linux-mtd/20240826101412.20644-2-miquel.raynal@bootlin.com --- include/linux/mtd/nand.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index b2996dc987ff..92e06ac33815 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -906,19 +906,19 @@ static inline void nanddev_pos_next_page(struct nand_device *nand, } /** - * nand_io_iter_init - Initialize a NAND I/O iterator + * nand_io_page_iter_init - Initialize a NAND I/O iterator * @nand: NAND device * @offs: absolute offset * @req: MTD request * @iter: NAND I/O iterator * * Initializes a NAND iterator based on the information passed by the MTD - * layer. + * layer for page jumps. */ -static inline void nanddev_io_iter_init(struct nand_device *nand, - enum nand_page_io_req_type reqtype, - loff_t offs, struct mtd_oob_ops *req, - struct nand_io_iter *iter) +static inline void nanddev_io_page_iter_init(struct nand_device *nand, + enum nand_page_io_req_type reqtype, + loff_t offs, struct mtd_oob_ops *req, + struct nand_io_iter *iter) { struct mtd_info *mtd = nanddev_to_mtd(nand); @@ -990,10 +990,10 @@ static inline bool nanddev_io_iter_end(struct nand_device *nand, * @req: MTD I/O request * @iter: NAND I/O iterator * - * Should be used for iterate over pages that are contained in an MTD request. + * Should be used for iterating over pages that are contained in an MTD request. */ #define nanddev_io_for_each_page(nand, type, start, req, iter) \ - for (nanddev_io_iter_init(nand, type, start, req, iter); \ + for (nanddev_io_page_iter_init(nand, type, start, req, iter); \ !nanddev_io_iter_end(nand, iter); \ nanddev_io_iter_next_page(nand, iter)) -- cgit v1.2.3 From 8adf1ac24ba8ee34b8fd36ebf159004ec472fca0 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Mon, 26 Aug 2024 12:14:05 +0200 Subject: mtd: nand: Introduce a block iterator In order to be able to iterate easily across eraseblocks rather than pages, let's introduce a block iterator inspired from the page iterator. The main usage of this iterator will be for continuous/sequential reads, where it is interesting to use a single request rather than split the requests in smaller chunks (ie. pages) that can be hardly optimized. So a "continuous" boolean get's added for this purpose. Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20240826101412.20644-3-miquel.raynal@bootlin.com --- include/linux/mtd/nand.h | 74 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 74 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 92e06ac33815..1e4208040956 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -103,6 +103,8 @@ enum nand_page_io_req_type { * @ooblen: the number of OOB bytes to read from/write to this page * @oobbuf: buffer to store OOB data in or get OOB data from * @mode: one of the %MTD_OPS_XXX mode + * @continuous: no need to start over the operation at the end of each page, the + * NAND device will automatically prepare the next one * * This object is used to pass per-page I/O requests to NAND sub-layers. This * way all useful information are already formatted in a useful way and @@ -125,6 +127,7 @@ struct nand_page_io_req { void *in; } oobbuf; int mode; + bool continuous; }; const struct mtd_ooblayout_ops *nand_get_small_page_ooblayout(void); @@ -937,6 +940,43 @@ static inline void nanddev_io_page_iter_init(struct nand_device *nand, iter->req.ooblen = min_t(unsigned int, iter->oobbytes_per_page - iter->req.ooboffs, iter->oobleft); + iter->req.continuous = false; +} + +/** + * nand_io_block_iter_init - Initialize a NAND I/O iterator + * @nand: NAND device + * @offs: absolute offset + * @req: MTD request + * @iter: NAND I/O iterator + * + * Initializes a NAND iterator based on the information passed by the MTD + * layer for block jumps (no OOB) + * + * In practice only reads may leverage this iterator. + */ +static inline void nanddev_io_block_iter_init(struct nand_device *nand, + enum nand_page_io_req_type reqtype, + loff_t offs, struct mtd_oob_ops *req, + struct nand_io_iter *iter) +{ + unsigned int offs_in_eb; + + iter->req.type = reqtype; + iter->req.mode = req->mode; + iter->req.dataoffs = nanddev_offs_to_pos(nand, offs, &iter->req.pos); + iter->req.ooboffs = 0; + iter->oobbytes_per_page = 0; + iter->dataleft = req->len; + iter->oobleft = 0; + iter->req.databuf.in = req->datbuf; + offs_in_eb = (nand->memorg.pagesize * iter->req.pos.page) + iter->req.dataoffs; + iter->req.datalen = min_t(unsigned int, + nanddev_eraseblock_size(nand) - offs_in_eb, + iter->dataleft); + iter->req.oobbuf.in = NULL; + iter->req.ooblen = 0; + iter->req.continuous = true; } /** @@ -962,6 +1002,25 @@ static inline void nanddev_io_iter_next_page(struct nand_device *nand, iter->oobleft); } +/** + * nand_io_iter_next_block - Move to the next block + * @nand: NAND device + * @iter: NAND I/O iterator + * + * Updates the @iter to point to the next block. + * No OOB handling available. + */ +static inline void nanddev_io_iter_next_block(struct nand_device *nand, + struct nand_io_iter *iter) +{ + nanddev_pos_next_eraseblock(nand, &iter->req.pos); + iter->dataleft -= iter->req.datalen; + iter->req.databuf.in += iter->req.datalen; + iter->req.dataoffs = 0; + iter->req.datalen = min_t(unsigned int, nanddev_eraseblock_size(nand), + iter->dataleft); +} + /** * nand_io_iter_end - Should end iteration or not * @nand: NAND device @@ -997,6 +1056,21 @@ static inline bool nanddev_io_iter_end(struct nand_device *nand, !nanddev_io_iter_end(nand, iter); \ nanddev_io_iter_next_page(nand, iter)) +/** + * nand_io_for_each_block - Iterate over all NAND pages contained in an MTD I/O + * request, one block at a time + * @nand: NAND device + * @start: start address to read/write from + * @req: MTD I/O request + * @iter: NAND I/O iterator + * + * Should be used for iterating over blocks that are contained in an MTD request. + */ +#define nanddev_io_for_each_block(nand, type, start, req, iter) \ + for (nanddev_io_block_iter_init(nand, type, start, req, iter); \ + !nanddev_io_iter_end(nand, iter); \ + nanddev_io_iter_next_block(nand, iter)) + bool nanddev_isbad(struct nand_device *nand, const struct nand_pos *pos); bool nanddev_isreserved(struct nand_device *nand, const struct nand_pos *pos); int nanddev_markbad(struct nand_device *nand, const struct nand_pos *pos); -- cgit v1.2.3 From 631cfdd0520d19b7f4fc13b834fd9c8b46c6dbac Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Mon, 26 Aug 2024 12:14:07 +0200 Subject: mtd: spi-nand: Add continuous read support A regular page read consist in: - Asking one page of content from the NAND array to be loaded in the chip's SRAM, - Waiting for the operation to be done, - Retrieving the data (I/O phase) from the chip's SRAM. When reading several sequential pages, the above operation is repeated over and over. There is however a way to optimize these accesses, by enabling continuous reads. The feature requires the NAND chip to have a second internal SRAM area plus a bit of additional internal logic to trigger another internal transfer between the NAND array and the second SRAM area while the I/O phase is ongoing. Once the first I/O phase is done, the host can continue reading more data, continuously, as the chip will automatically switch to the second SRAM content (which has already been loaded) and in turns trigger the next load into the first SRAM area again. From an instruction perspective, the command op-codes are different, but the same cycles are required. The only difference is that after a continuous read (which is stopped by a CS deassert), the host must observe a delay of tRST. However, because there is no guarantee in Linux regarding the actual state of the CS pin after a transfer (in order to speed-up the next transfer if targeting the same device), it was necessary to manually end the continuous read with a configuration register write operation. Continuous reads have two main drawbacks: * They only work on full pages (column address ignored) * Only the main data area is pulled, out-of-band bytes are not accessible. Said otherwise, the feature can only be useful with on-die ECC engines. Performance wise, measures have been performed on a Zynq platform using Macronix SPI-NAND controller with a Macronix chip (based on the flash_speed tool modified for testing sequential reads): - 1-1-1 mode: performances improved from +3% (2-pages) up to +10% after a dozen pages. - 1-1-4 mode: performances improved from +15% (2-pages) up to +40% after a dozen pages. This series is based on a previous work from Macronix engineer Jaime Liao. Signed-off-by: Miquel Raynal Reviewed-by: Pratyush Yadav Link: https://lore.kernel.org/linux-mtd/20240826101412.20644-5-miquel.raynal@bootlin.com --- drivers/mtd/nand/spi/core.c | 176 ++++++++++++++++++++++++++++++++++++++++++-- include/linux/mtd/spinand.h | 16 ++++ 2 files changed, 184 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c index 1f468ed93c8e..04041287b129 100644 --- a/drivers/mtd/nand/spi/core.c +++ b/drivers/mtd/nand/spi/core.c @@ -200,6 +200,12 @@ static int spinand_ecc_enable(struct spinand_device *spinand, enable ? CFG_ECC_ENABLE : 0); } +static int spinand_cont_read_enable(struct spinand_device *spinand, + bool enable) +{ + return spinand->set_cont_read(spinand, enable); +} + static int spinand_check_ecc_status(struct spinand_device *spinand, u8 status) { struct nand_device *nand = spinand_to_nand(spinand); @@ -311,10 +317,22 @@ static int spinand_ondie_ecc_finish_io_req(struct nand_device *nand, /* Finish a page read: check the status, report errors/bitflips */ ret = spinand_check_ecc_status(spinand, engine_conf->status); - if (ret == -EBADMSG) + if (ret == -EBADMSG) { mtd->ecc_stats.failed++; - else if (ret > 0) - mtd->ecc_stats.corrected += ret; + } else if (ret > 0) { + unsigned int pages; + + /* + * Continuous reads don't allow us to get the detail, + * so we may exagerate the actual number of corrected bitflips. + */ + if (!req->continuous) + pages = 1; + else + pages = req->datalen / nanddev_page_size(nand); + + mtd->ecc_stats.corrected += ret * pages; + } return ret; } @@ -369,7 +387,11 @@ static int spinand_read_from_cache_op(struct spinand_device *spinand, if (req->datalen) { buf = spinand->databuf; - nbytes = nanddev_page_size(nand); + if (!req->continuous) + nbytes = nanddev_page_size(nand); + else + nbytes = round_up(req->dataoffs + req->datalen, + nanddev_page_size(nand)); column = 0; } @@ -397,6 +419,13 @@ static int spinand_read_from_cache_op(struct spinand_device *spinand, nbytes -= ret; column += ret; buf += ret; + + /* + * Dirmap accesses are allowed to toggle the CS. + * Toggling the CS during a continuous read is forbidden. + */ + if (nbytes && req->continuous) + return -EIO; } if (req->datalen) @@ -672,6 +701,125 @@ static int spinand_mtd_regular_page_read(struct mtd_info *mtd, loff_t from, return ret; } +static int spinand_mtd_continuous_page_read(struct mtd_info *mtd, loff_t from, + struct mtd_oob_ops *ops, + unsigned int *max_bitflips) +{ + struct spinand_device *spinand = mtd_to_spinand(mtd); + struct nand_device *nand = mtd_to_nanddev(mtd); + struct nand_io_iter iter; + u8 status; + int ret; + + ret = spinand_cont_read_enable(spinand, true); + if (ret) + return ret; + + /* + * The cache is divided into two halves. While one half of the cache has + * the requested data, the other half is loaded with the next chunk of data. + * Therefore, the host can read out the data continuously from page to page. + * Each data read must be a multiple of 4-bytes and full pages should be read; + * otherwise, the data output might get out of sequence from one read command + * to another. + */ + nanddev_io_for_each_block(nand, NAND_PAGE_READ, from, ops, &iter) { + ret = spinand_select_target(spinand, iter.req.pos.target); + if (ret) + goto end_cont_read; + + ret = nand_ecc_prepare_io_req(nand, &iter.req); + if (ret) + goto end_cont_read; + + ret = spinand_load_page_op(spinand, &iter.req); + if (ret) + goto end_cont_read; + + ret = spinand_wait(spinand, SPINAND_READ_INITIAL_DELAY_US, + SPINAND_READ_POLL_DELAY_US, NULL); + if (ret < 0) + goto end_cont_read; + + ret = spinand_read_from_cache_op(spinand, &iter.req); + if (ret) + goto end_cont_read; + + ops->retlen += iter.req.datalen; + + ret = spinand_read_status(spinand, &status); + if (ret) + goto end_cont_read; + + spinand_ondie_ecc_save_status(nand, status); + + ret = nand_ecc_finish_io_req(nand, &iter.req); + if (ret < 0) + goto end_cont_read; + + *max_bitflips = max_t(unsigned int, *max_bitflips, ret); + ret = 0; + } + +end_cont_read: + /* + * Once all the data has been read out, the host can either pull CS# + * high and wait for tRST or manually clear the bit in the configuration + * register to terminate the continuous read operation. We have no + * guarantee the SPI controller drivers will effectively deassert the CS + * when we expect them to, so take the register based approach. + */ + spinand_cont_read_enable(spinand, false); + + return ret; +} + +static void spinand_cont_read_init(struct spinand_device *spinand) +{ + struct nand_device *nand = spinand_to_nand(spinand); + enum nand_ecc_engine_type engine_type = nand->ecc.ctx.conf.engine_type; + + /* OOBs cannot be retrieved so external/on-host ECC engine won't work */ + if (spinand->set_cont_read && + (engine_type == NAND_ECC_ENGINE_TYPE_ON_DIE || + engine_type == NAND_ECC_ENGINE_TYPE_NONE)) { + spinand->cont_read_possible = true; + } +} + +static bool spinand_use_cont_read(struct mtd_info *mtd, loff_t from, + struct mtd_oob_ops *ops) +{ + struct nand_device *nand = mtd_to_nanddev(mtd); + struct spinand_device *spinand = nand_to_spinand(nand); + struct nand_pos start_pos, end_pos; + + if (!spinand->cont_read_possible) + return false; + + /* OOBs won't be retrieved */ + if (ops->ooblen || ops->oobbuf) + return false; + + nanddev_offs_to_pos(nand, from, &start_pos); + nanddev_offs_to_pos(nand, from + ops->len - 1, &end_pos); + + /* + * Continuous reads never cross LUN boundaries. Some devices don't + * support crossing planes boundaries. Some devices don't even support + * crossing blocks boundaries. The common case being to read through UBI, + * we will very rarely read two consequent blocks or more, so it is safer + * and easier (can be improved) to only enable continuous reads when + * reading within the same erase block. + */ + if (start_pos.target != end_pos.target || + start_pos.plane != end_pos.plane || + start_pos.eraseblock != end_pos.eraseblock) + return false; + + return start_pos.page < end_pos.page; +} + static int spinand_mtd_read(struct mtd_info *mtd, loff_t from, struct mtd_oob_ops *ops) { @@ -684,7 +832,10 @@ static int spinand_mtd_read(struct mtd_info *mtd, loff_t from, old_stats = mtd->ecc_stats; - ret = spinand_mtd_regular_page_read(mtd, from, ops, &max_bitflips); + if (spinand_use_cont_read(mtd, from, ops)) + ret = spinand_mtd_continuous_page_read(mtd, from, ops, &max_bitflips); + else + ret = spinand_mtd_regular_page_read(mtd, from, ops, &max_bitflips); if (ops->stats) { ops->stats->uncorrectable_errors += @@ -874,6 +1025,9 @@ static int spinand_create_dirmap(struct spinand_device *spinand, }; struct spi_mem_dirmap_desc *desc; + if (spinand->cont_read_possible) + info.length = nanddev_eraseblock_size(nand); + /* The plane number is passed in MSB just above the column address */ info.offset = plane << fls(nand->memorg.pagesize); @@ -1107,6 +1261,7 @@ int spinand_match_and_init(struct spinand_device *spinand, spinand->flags = table[i].flags; spinand->id.len = 1 + table[i].devid.len; spinand->select_target = table[i].select_target; + spinand->set_cont_read = table[i].set_cont_read; op = spinand_select_op_variant(spinand, info->op_variants.read_cache); @@ -1248,9 +1403,8 @@ static int spinand_init(struct spinand_device *spinand) * may use this buffer for DMA access. * Memory allocated by devm_ does not guarantee DMA-safe alignment. */ - spinand->databuf = kzalloc(nanddev_page_size(nand) + - nanddev_per_page_oobsize(nand), - GFP_KERNEL); + spinand->databuf = kzalloc(nanddev_eraseblock_size(nand), + GFP_KERNEL); if (!spinand->databuf) { ret = -ENOMEM; goto err_free_bufs; @@ -1279,6 +1433,12 @@ static int spinand_init(struct spinand_device *spinand) if (ret) goto err_cleanup_nanddev; + /* + * Continuous read can only be enabled with an on-die ECC engine, so the + * ECC initialization must have happened previously. + */ + spinand_cont_read_init(spinand); + mtd->_read_oob = spinand_mtd_read; mtd->_write_oob = spinand_mtd_write; mtd->_block_isbad = spinand_mtd_block_isbad; diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index 5c19ead60499..14dce347dc46 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -336,6 +336,7 @@ struct spinand_ondie_ecc_conf { * @op_variants.update_cache: variants of the update-cache operation * @select_target: function used to select a target/die. Required only for * multi-die chips + * @set_cont_read: enable/disable continuous cached reads * * Each SPI NAND manufacturer driver should have a spinand_info table * describing all the chips supported by the driver. @@ -354,6 +355,8 @@ struct spinand_info { } op_variants; int (*select_target)(struct spinand_device *spinand, unsigned int target); + int (*set_cont_read)(struct spinand_device *spinand, + bool enable); }; #define SPINAND_ID(__method, ...) \ @@ -379,6 +382,9 @@ struct spinand_info { #define SPINAND_SELECT_TARGET(__func) \ .select_target = __func, +#define SPINAND_CONT_READ(__set_cont_read) \ + .set_cont_read = __set_cont_read, + #define SPINAND_INFO(__model, __id, __memorg, __eccreq, __op_variants, \ __flags, ...) \ { \ @@ -422,6 +428,12 @@ struct spinand_dirmap { * passed in spi_mem_op be DMA-able, so we can't based the bufs on * the stack * @manufacturer: SPI NAND manufacturer information + * @cont_read_possible: Field filled by the core once the whole system + * configuration is known to tell whether continuous reads are + * suitable to use or not in general with this chip/configuration. + * A per-transfer check must of course be done to ensure it is + * actually relevant to enable this feature. + * @set_cont_read: Enable/disable the continuous read feature * @priv: manufacturer private data */ struct spinand_device { @@ -451,6 +463,10 @@ struct spinand_device { u8 *scratchbuf; const struct spinand_manufacturer *manufacturer; void *priv; + + bool cont_read_possible; + int (*set_cont_read)(struct spinand_device *spinand, + bool enable); }; /** -- cgit v1.2.3 From a06f2e7cc4de104b14971e08d37f9d08c256b053 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Mon, 26 Aug 2024 12:14:08 +0200 Subject: mtd: spi-nand: Expose spinand_write_reg_op() This helper function will soon be used from a vendor driver, let's export it through the spinand.h header. No need for any export, as there is currently no reason for any module to need it. Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20240826101412.20644-6-miquel.raynal@bootlin.com --- drivers/mtd/nand/spi/core.c | 2 +- include/linux/mtd/spinand.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c index 04041287b129..b5c6d755ade1 100644 --- a/drivers/mtd/nand/spi/core.c +++ b/drivers/mtd/nand/spi/core.c @@ -34,7 +34,7 @@ static int spinand_read_reg_op(struct spinand_device *spinand, u8 reg, u8 *val) return 0; } -static int spinand_write_reg_op(struct spinand_device *spinand, u8 reg, u8 val) +int spinand_write_reg_op(struct spinand_device *spinand, u8 reg, u8 val) { struct spi_mem_op op = SPINAND_SET_FEATURE_OP(reg, spinand->scratchbuf); diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index 14dce347dc46..8dbf67ca710a 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -533,6 +533,7 @@ int spinand_match_and_init(struct spinand_device *spinand, enum spinand_readid_method rdid_method); int spinand_upd_cfg(struct spinand_device *spinand, u8 mask, u8 val); +int spinand_write_reg_op(struct spinand_device *spinand, u8 reg, u8 val); int spinand_select_target(struct spinand_device *spinand, unsigned int target); #endif /* __LINUX_MTD_SPINAND_H */ -- cgit v1.2.3 From bb2ac59f8205165fce5aee9135bd1e2ea9b1a74b Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Fri, 16 Aug 2024 01:18:23 +0100 Subject: mfd: axp20x: AXP717: Add support for boost regulator The AXP717 also contains a boost regulator, to provide the 5V USB VBUS rail when running on battery. Add the registers to the MFD description to be able to use them from the regulator driver. Signed-off-by: Andre Przywara Reviewed-by: John Watts Acked-by: Lee Jones Reviewed-by: Chen-Yu Tsai Link: https://patch.msgid.link/20240816001824.6028-3-andre.przywara@arm.com Signed-off-by: Mark Brown --- drivers/mfd/axp20x.c | 2 ++ include/linux/mfd/axp20x.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/drivers/mfd/axp20x.c b/drivers/mfd/axp20x.c index dacd3c96c9f5..16950c3206d7 100644 --- a/drivers/mfd/axp20x.c +++ b/drivers/mfd/axp20x.c @@ -209,6 +209,8 @@ static const struct regmap_access_table axp313a_volatile_table = { }; static const struct regmap_range axp717_writeable_ranges[] = { + regmap_reg_range(AXP717_MODULE_EN_CONTROL_2, AXP717_MODULE_EN_CONTROL_2), + regmap_reg_range(AXP717_BOOST_CONTROL, AXP717_BOOST_CONTROL), regmap_reg_range(AXP717_IRQ0_EN, AXP717_IRQ4_EN), regmap_reg_range(AXP717_IRQ0_STATE, AXP717_IRQ4_STATE), regmap_reg_range(AXP717_DCDC_OUTPUT_CONTROL, AXP717_CPUSLDO_CONTROL), diff --git a/include/linux/mfd/axp20x.h b/include/linux/mfd/axp20x.h index 8c0a33a2e9ce..3758f986491c 100644 --- a/include/linux/mfd/axp20x.h +++ b/include/linux/mfd/axp20x.h @@ -115,6 +115,8 @@ enum axp20x_variants { #define AXP313A_IRQ_STATE 0x21 #define AXP717_ON_INDICATE 0x00 +#define AXP717_MODULE_EN_CONTROL_2 0x19 +#define AXP717_BOOST_CONTROL 0x1e #define AXP717_IRQ0_EN 0x40 #define AXP717_IRQ1_EN 0x41 #define AXP717_IRQ2_EN 0x42 -- cgit v1.2.3 From 22dfe2ea1d63f15d8b9661e7690ac0a03159db6a Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Fri, 16 Aug 2024 01:18:24 +0100 Subject: regulator: axp20x: AXP717: Add boost regulator The AXP717 also contains an adjustable boost regulator, to provide the 5V USB VBUS rail when running on battery. Add the regulator description that states the voltage range this regulator can cover. Signed-off-by: Andre Przywara Reviewed-by: John Watts Reviewed-by: Chen-Yu Tsai Link: https://patch.msgid.link/20240816001824.6028-4-andre.przywara@arm.com Signed-off-by: Mark Brown --- drivers/regulator/axp20x-regulator.c | 4 ++++ include/linux/mfd/axp20x.h | 1 + 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c index f3c447ecdc3b..a8e91d9d028b 100644 --- a/drivers/regulator/axp20x-regulator.c +++ b/drivers/regulator/axp20x-regulator.c @@ -143,6 +143,7 @@ #define AXP717_DCDC3_NUM_VOLTAGES 103 #define AXP717_DCDC_V_OUT_MASK GENMASK(6, 0) #define AXP717_LDO_V_OUT_MASK GENMASK(4, 0) +#define AXP717_BOOST_V_OUT_MASK GENMASK(7, 4) #define AXP803_PWR_OUT_DCDC1_MASK BIT_MASK(0) #define AXP803_PWR_OUT_DCDC2_MASK BIT_MASK(1) @@ -834,6 +835,9 @@ static const struct regulator_desc axp717_regulators[] = { AXP_DESC(AXP717, CPUSLDO, "cpusldo", "vin1", 500, 1400, 50, AXP717_CPUSLDO_CONTROL, AXP717_LDO_V_OUT_MASK, AXP717_LDO1_OUTPUT_CONTROL, BIT(4)), + AXP_DESC(AXP717, BOOST, "boost", "vin1", 4550, 5510, 64, + AXP717_BOOST_CONTROL, AXP717_BOOST_V_OUT_MASK, + AXP717_MODULE_EN_CONTROL_2, BIT(4)), }; /* DCDC ranges shared with AXP813 */ diff --git a/include/linux/mfd/axp20x.h b/include/linux/mfd/axp20x.h index 3758f986491c..e0cd66bd3b6d 100644 --- a/include/linux/mfd/axp20x.h +++ b/include/linux/mfd/axp20x.h @@ -486,6 +486,7 @@ enum { AXP717_CLDO3, AXP717_CLDO4, AXP717_CPUSLDO, + AXP717_BOOST, AXP717_REG_ID_MAX, }; -- cgit v1.2.3 From 78f76b09c915d7281317d8e082c4c02f325a0366 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Wed, 17 Jul 2024 17:48:16 +0900 Subject: ata: libata: Move sata_std_hardreset() definition to libata-sata.c Unlike ata_std_prereset() and ata_std_postreset(), the function sata_std_hardreset() applies only to SATA devices, as its name implies. So move its definition to libata-sata.c. Together with this, also move the definition of sata_port_ops to libata-sata.c, where it belongs. Signed-off-by: Damien Le Moal Reviewed-by: Niklas Cassel Reviewed-by: Hannes Reinecke --- drivers/ata/libata-core.c | 35 ----------------------------------- drivers/ata/libata-sata.c | 36 ++++++++++++++++++++++++++++++++++++ include/linux/libata.h | 9 +++++++-- 3 files changed, 43 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index b957eb900a00..b5a051bbb01f 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -72,14 +72,6 @@ const struct ata_port_operations ata_base_port_ops = { .end_eh = ata_std_end_eh, }; -const struct ata_port_operations sata_port_ops = { - .inherits = &ata_base_port_ops, - - .qc_defer = ata_std_qc_defer, - .hardreset = sata_std_hardreset, -}; -EXPORT_SYMBOL_GPL(sata_port_ops); - static unsigned int ata_dev_init_params(struct ata_device *dev, u16 heads, u16 sectors); static unsigned int ata_dev_set_xfermode(struct ata_device *dev); @@ -3676,33 +3668,6 @@ int ata_std_prereset(struct ata_link *link, unsigned long deadline) } EXPORT_SYMBOL_GPL(ata_std_prereset); -/** - * sata_std_hardreset - COMRESET w/o waiting or classification - * @link: link to reset - * @class: resulting class of attached device - * @deadline: deadline jiffies for the operation - * - * Standard SATA COMRESET w/o waiting or classification. - * - * LOCKING: - * Kernel thread context (may sleep) - * - * RETURNS: - * 0 if link offline, -EAGAIN if link online, -errno on errors. - */ -int sata_std_hardreset(struct ata_link *link, unsigned int *class, - unsigned long deadline) -{ - const unsigned int *timing = sata_ehc_deb_timing(&link->eh_context); - bool online; - int rc; - - /* do hardreset */ - rc = sata_link_hardreset(link, timing, deadline, &online, NULL); - return online ? -EAGAIN : rc; -} -EXPORT_SYMBOL_GPL(sata_std_hardreset); - /** * ata_std_postreset - standard postreset callback * @link: the target ata_link diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c index 124e2b2ea3c0..40f70de94fbd 100644 --- a/drivers/ata/libata-sata.c +++ b/drivers/ata/libata-sata.c @@ -706,6 +706,34 @@ int sata_link_hardreset(struct ata_link *link, const unsigned int *timing, } EXPORT_SYMBOL_GPL(sata_link_hardreset); +/** + * sata_std_hardreset - COMRESET w/o waiting or classification + * @link: link to reset + * @class: resulting class of attached device + * @deadline: deadline jiffies for the operation + * + * Standard SATA COMRESET w/o waiting or classification. + * + * LOCKING: + * Kernel thread context (may sleep) + * + * RETURNS: + * 0 if link offline, -EAGAIN if link online, -errno on errors. + */ +int sata_std_hardreset(struct ata_link *link, unsigned int *class, + unsigned long deadline) +{ + const unsigned int *timing = sata_ehc_deb_timing(&link->eh_context); + bool online; + int rc; + + rc = sata_link_hardreset(link, timing, deadline, &online, NULL); + if (online) + return -EAGAIN; + return rc; +} +EXPORT_SYMBOL_GPL(sata_std_hardreset); + /** * ata_qc_complete_multiple - Complete multiple qcs successfully * @ap: port in question @@ -1654,3 +1682,11 @@ void ata_eh_analyze_ncq_error(struct ata_link *link) ehc->i.err_mask &= ~AC_ERR_DEV; } EXPORT_SYMBOL_GPL(ata_eh_analyze_ncq_error); + +const struct ata_port_operations sata_port_ops = { + .inherits = &ata_base_port_ops, + + .qc_defer = ata_std_qc_defer, + .hardreset = sata_std_hardreset, +}; +EXPORT_SYMBOL_GPL(sata_port_ops); diff --git a/include/linux/libata.h b/include/linux/libata.h index 6552e90753ae..d52ae7723c05 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1104,8 +1104,6 @@ static inline bool ata_port_is_frozen(const struct ata_port *ap) extern int ata_std_prereset(struct ata_link *link, unsigned long deadline); extern int ata_wait_after_reset(struct ata_link *link, unsigned long deadline, int (*check_ready)(struct ata_link *link)); -extern int sata_std_hardreset(struct ata_link *link, unsigned int *class, - unsigned long deadline); extern void ata_std_postreset(struct ata_link *link, unsigned int *classes); extern struct ata_host *ata_host_alloc(struct device *dev, int n_ports); @@ -1229,6 +1227,8 @@ extern int sata_scr_read(struct ata_link *link, int reg, u32 *val); extern int sata_scr_write(struct ata_link *link, int reg, u32 val); extern int sata_scr_write_flush(struct ata_link *link, int reg, u32 val); extern int sata_set_spd(struct ata_link *link); +int sata_std_hardreset(struct ata_link *link, unsigned int *class, + unsigned long deadline); extern int sata_link_hardreset(struct ata_link *link, const unsigned int *timing, unsigned long deadline, bool *online, int (*check_ready)(struct ata_link *)); @@ -1256,6 +1256,11 @@ static inline int sata_scr_write_flush(struct ata_link *link, int reg, u32 val) return -EOPNOTSUPP; } static inline int sata_set_spd(struct ata_link *link) { return -EOPNOTSUPP; } +static inline int sata_std_hardreset(struct ata_link *link, unsigned int *class, + unsigned long deadline) +{ + return -EOPNOTSUPP; +} static inline int sata_link_hardreset(struct ata_link *link, const unsigned int *timing, unsigned long deadline, -- cgit v1.2.3 From 10e807637f288f9963340a30ae8da9bb06beca3c Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Mon, 10 Jun 2024 19:11:31 +0900 Subject: ata: libata: Rename ata_eh_read_sense_success_ncq_log() The function ata_eh_read_sense_success_ncq_log() does more that just reading the sense data for successful NCQ commands log page as it also sets the sense data for all commands listed in the log page. Rename this function to ata_eh_get_ncq_success_sense() to better describe what the function does. Furthermore, since this function is only called from ata_eh_get_success_sense() in libata-eh.c, there is no need to export it and its declaration can be moved to drivers/ata/libata.h. To be consistent with this change, the function ata_eh_read_sense_success_non_ncq() is also renamed to ata_eh_get_non_ncq_success_sense(). Signed-off-by: Damien Le Moal Reviewed-by: Niklas Cassel Reviewed-by: Hannes Reinecke --- drivers/ata/libata-eh.c | 6 +++--- drivers/ata/libata-sata.c | 7 +++---- drivers/ata/libata.h | 5 +++++ include/linux/libata.h | 5 ----- 4 files changed, 11 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 7de97ee8e78b..d2747a0d684c 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -1962,7 +1962,7 @@ static inline bool ata_eh_quiet(struct ata_queued_cmd *qc) return qc->flags & ATA_QCFLAG_QUIET; } -static int ata_eh_read_sense_success_non_ncq(struct ata_link *link) +static int ata_eh_get_non_ncq_success_sense(struct ata_link *link) { struct ata_port *ap = link->ap; struct ata_queued_cmd *qc; @@ -2013,9 +2013,9 @@ static void ata_eh_get_success_sense(struct ata_link *link) * request sense ext command to retrieve the sense data. */ if (link->sactive) - ret = ata_eh_read_sense_success_ncq_log(link); + ret = ata_eh_get_ncq_success_sense(link); else - ret = ata_eh_read_sense_success_non_ncq(link); + ret = ata_eh_get_non_ncq_success_sense(link); if (ret) goto out; diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c index 40f70de94fbd..4e063cb42018 100644 --- a/drivers/ata/libata-sata.c +++ b/drivers/ata/libata-sata.c @@ -1487,8 +1487,8 @@ static int ata_eh_read_log_10h(struct ata_device *dev, } /** - * ata_eh_read_sense_success_ncq_log - Read the sense data for successful - * NCQ commands log + * ata_eh_get_ncq_success_sense - Read and process the sense data for + * successful NCQ commands log page * @link: ATA link to get sense data for * * Read the sense data for successful NCQ commands log page to obtain @@ -1501,7 +1501,7 @@ static int ata_eh_read_log_10h(struct ata_device *dev, * RETURNS: * 0 on success, -errno otherwise. */ -int ata_eh_read_sense_success_ncq_log(struct ata_link *link) +int ata_eh_get_ncq_success_sense(struct ata_link *link) { struct ata_device *dev = link->device; struct ata_port *ap = dev->link->ap; @@ -1571,7 +1571,6 @@ int ata_eh_read_sense_success_ncq_log(struct ata_link *link) return ret; } -EXPORT_SYMBOL_GPL(ata_eh_read_sense_success_ncq_log); /** * ata_eh_analyze_ncq_error - analyze NCQ error diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h index 3df17da08c7f..2a9d1bbf2482 100644 --- a/drivers/ata/libata.h +++ b/drivers/ata/libata.h @@ -95,11 +95,16 @@ extern unsigned int ata_read_log_page(struct ata_device *dev, u8 log, /* libata-sata.c */ #ifdef CONFIG_SATA_HOST int sata_down_spd_limit(struct ata_link *link, u32 spd_limit); +int ata_eh_get_ncq_success_sense(struct ata_link *link); #else static inline int sata_down_spd_limit(struct ata_link *link, u32 spd_limit) { return -EOPNOTSUPP; } +static inline int ata_eh_get_ncq_success_sense(struct ata_link *link) +{ + return -EOPNOTSUPP; +} #endif /* libata-acpi.c */ diff --git a/include/linux/libata.h b/include/linux/libata.h index d52ae7723c05..55a6b57742bc 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1234,7 +1234,6 @@ extern int sata_link_hardreset(struct ata_link *link, bool *online, int (*check_ready)(struct ata_link *)); extern int sata_link_resume(struct ata_link *link, const unsigned int *params, unsigned long deadline); -extern int ata_eh_read_sense_success_ncq_log(struct ata_link *link); extern void ata_eh_analyze_ncq_error(struct ata_link *link); #else static inline const unsigned int * @@ -1277,10 +1276,6 @@ static inline int sata_link_resume(struct ata_link *link, { return -EOPNOTSUPP; } -static inline int ata_eh_read_sense_success_ncq_log(struct ata_link *link) -{ - return -EOPNOTSUPP; -} static inline void ata_eh_analyze_ncq_error(struct ata_link *link) { } #endif extern int sata_link_debounce(struct ata_link *link, -- cgit v1.2.3 From da65bbdd3bc1e8d2193e01167a413d90d9988c04 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Wed, 28 Aug 2024 11:07:43 +0900 Subject: ata: libata: Move sector_buf from struct ata_port to struct ata_device The 512B buffer sector_buf field of struct ata_port is used for scanning devices as well as during error recovery with ata EH. This buffer is thus useless if a port does not have a device connected to it. And also given that commands using this buffer are issued to devices, and not to ports, move this buffer definition from struct ata_port to struct ata_device. This change slightly increases system memory usage for systems using a port-multiplier as in that case we do not need a per-device buffer for scanning devices (PMP does not allow parallel scanning) nor for EH (as when entering EH we are guaranteed that all commands to all devices connected to the PMP have completed or have been aborted). However, this change reduces memory usage on systems that have many ports with only few devices rives connected, which is a much more common use case than the PMP use case. Suggested-by: Niklas Cassel Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Reviewed-by: Niklas Cassel --- drivers/ata/libata-core.c | 63 +++++++++++++++++++--------------------------- drivers/ata/libata-eh.c | 2 +- drivers/ata/libata-pmp.c | 3 +-- drivers/ata/libata-sata.c | 2 +- drivers/ata/libata-zpodd.c | 2 +- include/linux/libata.h | 4 ++- 6 files changed, 33 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index b5a051bbb01f..32325a1c07af 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2125,19 +2125,16 @@ retry: static int ata_log_supported(struct ata_device *dev, u8 log) { - struct ata_port *ap = dev->link->ap; - if (dev->quirks & ATA_QUIRK_NO_LOG_DIR) return 0; - if (ata_read_log_page(dev, ATA_LOG_DIRECTORY, 0, ap->sector_buf, 1)) + if (ata_read_log_page(dev, ATA_LOG_DIRECTORY, 0, dev->sector_buf, 1)) return 0; - return get_unaligned_le16(&ap->sector_buf[log * 2]); + return get_unaligned_le16(&dev->sector_buf[log * 2]); } static bool ata_identify_page_supported(struct ata_device *dev, u8 page) { - struct ata_port *ap = dev->link->ap; unsigned int err, i; if (dev->quirks & ATA_QUIRK_NO_ID_DEV_LOG) @@ -2160,13 +2157,13 @@ static bool ata_identify_page_supported(struct ata_device *dev, u8 page) * Read IDENTIFY DEVICE data log, page 0, to figure out if the page is * supported. */ - err = ata_read_log_page(dev, ATA_LOG_IDENTIFY_DEVICE, 0, ap->sector_buf, - 1); + err = ata_read_log_page(dev, ATA_LOG_IDENTIFY_DEVICE, 0, + dev->sector_buf, 1); if (err) return false; - for (i = 0; i < ap->sector_buf[8]; i++) { - if (ap->sector_buf[9 + i] == page) + for (i = 0; i < dev->sector_buf[8]; i++) { + if (dev->sector_buf[9 + i] == page) return true; } @@ -2218,7 +2215,6 @@ static inline bool ata_dev_knobble(struct ata_device *dev) static void ata_dev_config_ncq_send_recv(struct ata_device *dev) { - struct ata_port *ap = dev->link->ap; unsigned int err_mask; if (!ata_log_supported(dev, ATA_LOG_NCQ_SEND_RECV)) { @@ -2226,12 +2222,12 @@ static void ata_dev_config_ncq_send_recv(struct ata_device *dev) return; } err_mask = ata_read_log_page(dev, ATA_LOG_NCQ_SEND_RECV, - 0, ap->sector_buf, 1); + 0, dev->sector_buf, 1); if (!err_mask) { u8 *cmds = dev->ncq_send_recv_cmds; dev->flags |= ATA_DFLAG_NCQ_SEND_RECV; - memcpy(cmds, ap->sector_buf, ATA_LOG_NCQ_SEND_RECV_SIZE); + memcpy(cmds, dev->sector_buf, ATA_LOG_NCQ_SEND_RECV_SIZE); if (dev->quirks & ATA_QUIRK_NO_NCQ_TRIM) { ata_dev_dbg(dev, "disabling queued TRIM support\n"); @@ -2243,7 +2239,6 @@ static void ata_dev_config_ncq_send_recv(struct ata_device *dev) static void ata_dev_config_ncq_non_data(struct ata_device *dev) { - struct ata_port *ap = dev->link->ap; unsigned int err_mask; if (!ata_log_supported(dev, ATA_LOG_NCQ_NON_DATA)) { @@ -2252,17 +2247,14 @@ static void ata_dev_config_ncq_non_data(struct ata_device *dev) return; } err_mask = ata_read_log_page(dev, ATA_LOG_NCQ_NON_DATA, - 0, ap->sector_buf, 1); - if (!err_mask) { - u8 *cmds = dev->ncq_non_data_cmds; - - memcpy(cmds, ap->sector_buf, ATA_LOG_NCQ_NON_DATA_SIZE); - } + 0, dev->sector_buf, 1); + if (!err_mask) + memcpy(dev->ncq_non_data_cmds, dev->sector_buf, + ATA_LOG_NCQ_NON_DATA_SIZE); } static void ata_dev_config_ncq_prio(struct ata_device *dev) { - struct ata_port *ap = dev->link->ap; unsigned int err_mask; if (!ata_identify_page_supported(dev, ATA_LOG_SATA_SETTINGS)) @@ -2271,12 +2263,11 @@ static void ata_dev_config_ncq_prio(struct ata_device *dev) err_mask = ata_read_log_page(dev, ATA_LOG_IDENTIFY_DEVICE, ATA_LOG_SATA_SETTINGS, - ap->sector_buf, - 1); + dev->sector_buf, 1); if (err_mask) goto not_supported; - if (!(ap->sector_buf[ATA_LOG_NCQ_PRIO_OFFSET] & BIT(3))) + if (!(dev->sector_buf[ATA_LOG_NCQ_PRIO_OFFSET] & BIT(3))) goto not_supported; dev->flags |= ATA_DFLAG_NCQ_PRIO; @@ -2392,9 +2383,8 @@ static void ata_dev_config_sense_reporting(struct ata_device *dev) static void ata_dev_config_zac(struct ata_device *dev) { - struct ata_port *ap = dev->link->ap; unsigned int err_mask; - u8 *identify_buf = ap->sector_buf; + u8 *identify_buf = dev->sector_buf; dev->zac_zones_optimal_open = U32_MAX; dev->zac_zones_optimal_nonseq = U32_MAX; @@ -2446,7 +2436,6 @@ static void ata_dev_config_zac(struct ata_device *dev) static void ata_dev_config_trusted(struct ata_device *dev) { - struct ata_port *ap = dev->link->ap; u64 trusted_cap; unsigned int err; @@ -2460,11 +2449,11 @@ static void ata_dev_config_trusted(struct ata_device *dev) } err = ata_read_log_page(dev, ATA_LOG_IDENTIFY_DEVICE, ATA_LOG_SECURITY, - ap->sector_buf, 1); + dev->sector_buf, 1); if (err) return; - trusted_cap = get_unaligned_le64(&ap->sector_buf[40]); + trusted_cap = get_unaligned_le64(&dev->sector_buf[40]); if (!(trusted_cap & (1ULL << 63))) { ata_dev_dbg(dev, "Trusted Computing capability qword not valid!\n"); @@ -2492,12 +2481,12 @@ static void ata_dev_config_cdl(struct ata_device *dev) err_mask = ata_read_log_page(dev, ATA_LOG_IDENTIFY_DEVICE, ATA_LOG_SUPPORTED_CAPABILITIES, - ap->sector_buf, 1); + dev->sector_buf, 1); if (err_mask) goto not_supported; /* Check Command Duration Limit Supported bits */ - val = get_unaligned_le64(&ap->sector_buf[168]); + val = get_unaligned_le64(&dev->sector_buf[168]); if (!(val & BIT_ULL(63)) || !(val & BIT_ULL(0))) goto not_supported; @@ -2510,7 +2499,7 @@ static void ata_dev_config_cdl(struct ata_device *dev) * We must have support for the sense data for successful NCQ commands * log indicated by the successful NCQ command sense data supported bit. */ - val = get_unaligned_le64(&ap->sector_buf[8]); + val = get_unaligned_le64(&dev->sector_buf[8]); if (!(val & BIT_ULL(63)) || !(val & BIT_ULL(47))) { ata_dev_warn(dev, "CDL supported but Successful NCQ Command Sense Data is not supported\n"); @@ -2530,11 +2519,11 @@ static void ata_dev_config_cdl(struct ata_device *dev) */ err_mask = ata_read_log_page(dev, ATA_LOG_IDENTIFY_DEVICE, ATA_LOG_CURRENT_SETTINGS, - ap->sector_buf, 1); + dev->sector_buf, 1); if (err_mask) goto not_supported; - val = get_unaligned_le64(&ap->sector_buf[8]); + val = get_unaligned_le64(&dev->sector_buf[8]); cdl_enabled = val & BIT_ULL(63) && val & BIT_ULL(21); if (dev->flags & ATA_DFLAG_CDL_ENABLED) { if (!cdl_enabled) { @@ -2591,13 +2580,13 @@ static void ata_dev_config_cdl(struct ata_device *dev) * Command duration limits is supported: cache the CDL log page 18h * (command duration descriptors). */ - err_mask = ata_read_log_page(dev, ATA_LOG_CDL, 0, ap->sector_buf, 1); + err_mask = ata_read_log_page(dev, ATA_LOG_CDL, 0, dev->sector_buf, 1); if (err_mask) { ata_dev_warn(dev, "Read Command Duration Limits log failed\n"); goto not_supported; } - memcpy(dev->cdl, ap->sector_buf, ATA_LOG_CDL_SIZE); + memcpy(dev->cdl, dev->sector_buf, ATA_LOG_CDL_SIZE); dev->flags |= ATA_DFLAG_CDL; return; @@ -2689,7 +2678,7 @@ nofua: static void ata_dev_config_devslp(struct ata_device *dev) { - u8 *sata_setting = dev->link->ap->sector_buf; + u8 *sata_setting = dev->sector_buf; unsigned int err_mask; int i, j; @@ -3759,7 +3748,7 @@ static int ata_dev_same_device(struct ata_device *dev, unsigned int new_class, int ata_dev_reread_id(struct ata_device *dev, unsigned int readid_flags) { unsigned int class = dev->class; - u16 *id = (void *)dev->link->ap->sector_buf; + u16 *id = (void *)dev->sector_buf; int rc; /* read ID data */ diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index d2747a0d684c..ed535e1b4225 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -3284,7 +3284,7 @@ static int atapi_eh_clear_ua(struct ata_device *dev) int i; for (i = 0; i < ATA_EH_UA_TRIES; i++) { - u8 *sense_buffer = dev->link->ap->sector_buf; + u8 *sense_buffer = dev->sector_buf; u8 sense_key = 0; unsigned int err_mask; diff --git a/drivers/ata/libata-pmp.c b/drivers/ata/libata-pmp.c index e2e9cbd405fa..d5d189328ae6 100644 --- a/drivers/ata/libata-pmp.c +++ b/drivers/ata/libata-pmp.c @@ -648,8 +648,7 @@ static int sata_pmp_same_pmp(struct ata_device *dev, const u32 *new_gscr) static int sata_pmp_revalidate(struct ata_device *dev, unsigned int new_class) { struct ata_link *link = dev->link; - struct ata_port *ap = link->ap; - u32 *gscr = (void *)ap->sector_buf; + u32 *gscr = (void *)dev->sector_buf; int rc; ata_eh_about_to_do(link, NULL, ATA_EH_REVALIDATE); diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c index 4e063cb42018..498430db86f7 100644 --- a/drivers/ata/libata-sata.c +++ b/drivers/ata/libata-sata.c @@ -1448,7 +1448,7 @@ EXPORT_SYMBOL_GPL(sata_async_notification); static int ata_eh_read_log_10h(struct ata_device *dev, int *tag, struct ata_taskfile *tf) { - u8 *buf = dev->link->ap->sector_buf; + u8 *buf = dev->sector_buf; unsigned int err_mask; u8 csum; int i; diff --git a/drivers/ata/libata-zpodd.c b/drivers/ata/libata-zpodd.c index eefda51f97d3..4b83b517caec 100644 --- a/drivers/ata/libata-zpodd.c +++ b/drivers/ata/libata-zpodd.c @@ -112,7 +112,7 @@ static bool zpready(struct ata_device *dev) if (!ret || sense_key != NOT_READY) return false; - sense_buf = dev->link->ap->sector_buf; + sense_buf = dev->sector_buf; ret = atapi_eh_request_sense(dev, sense_buf, sense_key); if (ret) return false; diff --git a/include/linux/libata.h b/include/linux/libata.h index 55a6b57742bc..aac38dcd2230 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -769,6 +769,9 @@ struct ata_device { int spdn_cnt; /* ering is CLEAR_END, read comment above CLEAR_END */ struct ata_ering ering; + + /* For EH */ + u8 sector_buf[ATA_SECT_SIZE] ____cacheline_aligned; }; /* Fields between ATA_DEVICE_CLEAR_BEGIN and ATA_DEVICE_CLEAR_END are @@ -916,7 +919,6 @@ struct ata_port { #endif /* owned by EH */ u8 *ncq_sense_buf; - u8 sector_buf[ATA_SECT_SIZE] ____cacheline_aligned; }; /* The following initializer overrides a method to NULL whether one of -- cgit v1.2.3 From 602bcf212637633d537ee74bf39c6bc5722efb9b Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Wed, 17 Jul 2024 17:55:31 +0900 Subject: ata: libata: Improve CDL resource management The ncq_sense_buf buffer field of struct ata_port is allocated and used only for devices that support the Command Duration Limits (CDL) feature. However, the cdl buffer of struct ata_device, which is used to cache the command duration limits log page for devices supporting CDL is always allocated as part of struct ata_device, which is wasteful of memory for devices that do not support this feature. Clean this up by defining both buffers as part of the new ata_cdl structure and allocating this structure only for devices that support the CDL feature. This new structure is attached to struct ata_device using the cdl pointer. The functions ata_dev_init_cdl_resources() and ata_dev_cleanup_cdl_resources() are defined to manage this new structure allocation, initialization and freeing when a port is removed or a device disabled. ata_dev_init_cdl_resources() is called from ata_dev_config_cdl() only for devices that support CDL. ata_dev_cleanup_cdl_resources() is called from ata_dev_free_resources() to free the ata_cdl structure when a device is being disabled by EH. Note that the name of the former cdl log buffer of struct ata_device is changed to desc_log_buf to make it clearer that it is a buffer for the limit descriptors log page. This change reduces the size of struct ata_device, thus reducing memory usage for ATA devices that do not support the CDL feature. Signed-off-by: Damien Le Moal Reviewed-by: Niklas Cassel --- drivers/ata/libata-core.c | 61 ++++++++++++++++++++++++++++------------------- drivers/ata/libata-sata.c | 2 +- drivers/ata/libata-scsi.c | 2 +- drivers/ata/libata.h | 1 + include/linux/libata.h | 21 ++++++++++++---- 5 files changed, 57 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index bfd452b0d46d..082179c38e1b 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2464,12 +2464,41 @@ static void ata_dev_config_trusted(struct ata_device *dev) dev->flags |= ATA_DFLAG_TRUSTED; } +void ata_dev_cleanup_cdl_resources(struct ata_device *dev) +{ + kfree(dev->cdl); + dev->cdl = NULL; +} + +static int ata_dev_init_cdl_resources(struct ata_device *dev) +{ + struct ata_cdl *cdl = dev->cdl; + unsigned int err_mask; + + if (!cdl) { + cdl = kzalloc(sizeof(*cdl), GFP_KERNEL); + if (!cdl) + return -ENOMEM; + dev->cdl = cdl; + } + + err_mask = ata_read_log_page(dev, ATA_LOG_CDL, 0, cdl->desc_log_buf, + ATA_LOG_CDL_SIZE / ATA_SECT_SIZE); + if (err_mask) { + ata_dev_warn(dev, "Read Command Duration Limits log failed\n"); + ata_dev_cleanup_cdl_resources(dev); + return -EIO; + } + + return 0; +} + static void ata_dev_config_cdl(struct ata_device *dev) { - struct ata_port *ap = dev->link->ap; unsigned int err_mask; bool cdl_enabled; u64 val; + int ret; if (ata_id_major_version(dev->id) < 11) goto not_supported; @@ -2564,37 +2593,20 @@ static void ata_dev_config_cdl(struct ata_device *dev) } } - /* - * Allocate a buffer to handle reading the sense data for successful - * NCQ Commands log page for commands using a CDL with one of the limit - * policy set to 0xD (successful completion with sense data available - * bit set). - */ - if (!ap->ncq_sense_buf) { - ap->ncq_sense_buf = kmalloc(ATA_LOG_SENSE_NCQ_SIZE, GFP_KERNEL); - if (!ap->ncq_sense_buf) - goto not_supported; - } - - /* - * Command duration limits is supported: cache the CDL log page 18h - * (command duration descriptors). - */ - err_mask = ata_read_log_page(dev, ATA_LOG_CDL, 0, dev->sector_buf, 1); - if (err_mask) { - ata_dev_warn(dev, "Read Command Duration Limits log failed\n"); + /* CDL is supported: allocate and initialize needed resources. */ + ret = ata_dev_init_cdl_resources(dev); + if (ret) { + ata_dev_warn(dev, "Initialize CDL resources failed\n"); goto not_supported; } - memcpy(dev->cdl, dev->sector_buf, ATA_LOG_CDL_SIZE); dev->flags |= ATA_DFLAG_CDL; return; not_supported: dev->flags &= ~(ATA_DFLAG_CDL | ATA_DFLAG_CDL_ENABLED); - kfree(ap->ncq_sense_buf); - ap->ncq_sense_buf = NULL; + ata_dev_cleanup_cdl_resources(dev); } static int ata_dev_config_lba(struct ata_device *dev) @@ -5451,7 +5463,6 @@ void ata_port_free(struct ata_port *ap) kfree(ap->pmp_link); kfree(ap->slave_link); - kfree(ap->ncq_sense_buf); ida_free(&ata_ida, ap->print_id); kfree(ap); } @@ -5989,6 +6000,8 @@ void ata_dev_free_resources(struct ata_device *dev) { if (zpodd_dev_enabled(dev)) zpodd_exit(dev); + + ata_dev_cleanup_cdl_resources(dev); } /** diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c index 498430db86f7..c8b119a06bb2 100644 --- a/drivers/ata/libata-sata.c +++ b/drivers/ata/libata-sata.c @@ -1505,7 +1505,7 @@ int ata_eh_get_ncq_success_sense(struct ata_link *link) { struct ata_device *dev = link->device; struct ata_port *ap = dev->link->ap; - u8 *buf = ap->ncq_sense_buf; + u8 *buf = dev->cdl->ncq_sense_log_buf; struct ata_queued_cmd *qc; unsigned int err_mask, tag; u8 *sense, sk = 0, asc = 0, ascq = 0; diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 4fb45565c142..9f75d26808bf 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -2248,7 +2248,7 @@ static inline u16 ata_xlat_cdl_limit(u8 *buf) static unsigned int ata_msense_control_spgt2(struct ata_device *dev, u8 *buf, u8 spg) { - u8 *b, *cdl = dev->cdl, *desc; + u8 *b, *cdl = dev->cdl->desc_log_buf, *desc; u32 policy; int i; diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h index 927d77bde7ef..0337be4faec7 100644 --- a/drivers/ata/libata.h +++ b/drivers/ata/libata.h @@ -90,6 +90,7 @@ extern int ata_cmd_ioctl(struct scsi_device *scsidev, void __user *arg); extern const char *sata_spd_string(unsigned int spd); extern unsigned int ata_read_log_page(struct ata_device *dev, u8 log, u8 page, void *buf, unsigned int sectors); +void ata_dev_cleanup_cdl_resources(struct ata_device *dev); #define to_ata_port(d) container_of(d, struct ata_port, tdev) diff --git a/include/linux/libata.h b/include/linux/libata.h index aac38dcd2230..9b4a6ff03235 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -700,6 +700,21 @@ struct ata_cpr_log { struct ata_cpr cpr[] __counted_by(nr_cpr); }; +struct ata_cdl { + /* + * Buffer to cache the CDL log page 18h (command duration descriptors) + * for SCSI-ATA translation. + */ + u8 desc_log_buf[ATA_LOG_CDL_SIZE]; + + /* + * Buffer to handle reading the sense data for successful NCQ Commands + * log page for commands using a CDL with one of the limits policy set + * to 0xD (successful completion with sense data available bit set). + */ + u8 ncq_sense_log_buf[ATA_LOG_SENSE_NCQ_SIZE]; +}; + struct ata_device { struct ata_link *link; unsigned int devno; /* 0 or 1 */ @@ -762,8 +777,8 @@ struct ata_device { /* Concurrent positioning ranges */ struct ata_cpr_log *cpr_log; - /* Command Duration Limits log support */ - u8 cdl[ATA_LOG_CDL_SIZE]; + /* Command Duration Limits support */ + struct ata_cdl *cdl; /* error history */ int spdn_cnt; @@ -917,8 +932,6 @@ struct ata_port { #ifdef CONFIG_ATA_ACPI struct ata_acpi_gtm __acpi_init_gtm; /* use ata_acpi_init_gtm() */ #endif - /* owned by EH */ - u8 *ncq_sense_buf; }; /* The following initializer overrides a method to NULL whether one of -- cgit v1.2.3 From 446216bd8e5d4a3ffc9738f6adffc98fbfdcc582 Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Sun, 8 Sep 2024 13:05:48 +0900 Subject: firewire: core: expose kernel API to schedule work item to process isochronous context In packet-per-buffer mode for isochronous context of 1394 OHCI, software can schedule hardIRQ to the buffer in which the content of isochronous packet is processed. The actual behaviour is different between isochronous receive (IR) and transmit (IT) contexts in respect to isochronous cycle in which the hardIRQ occurs. In IR context, the hardIRQ occurs when the buffer is filled actually by the content of received packet. If there are any isochronous cycles in which the packet transmission is skipped, it is postponed to generate the hardIRQ in respect to the isochronous cycle. In IT context, software can schedule the content of packet every isochronous cycle including skipping, therefore the hardIRQ occurs in the isochronous cycle to which the software scheduled. ALSA firewire stack uses the packet-per-buffer mode for both IR/IT contexts. To process time stamp per packet (or per sample in some cases) steadily for media clock recovery against unexpected transmission skips, it uses an IT context to operate all of isochronous contexts by calls of fw_iso_context_flush_completions() in the bottom-half of hardIRQ for the IT context. Although it looks well to handle all of isochronous contexts in a single bottom-half context, it relatively takes longer time. In the future code integration (not yet), it is possible to apply parallelism method to process these context. In the case, it is useful to allow unit drivers to schedule work items to process these isochronous contexts. As a preparation, this commit exposes fw_iso_context_schedule_flush_completions() as a kernel API available by unit drivers. It is renamed from fw_iso_context_queue_work() since it is a counter part of fw_iso_context_flush_completions(). Link: https://lore.kernel.org/r/20240908040549.75304-2-o-takashi@sakamocchi.jp Signed-off-by: Takashi Sakamoto --- Documentation/driver-api/firewire.rst | 2 ++ drivers/firewire/core.h | 5 ----- drivers/firewire/ohci.c | 4 ++-- include/linux/firewire.h | 17 +++++++++++++++++ 4 files changed, 21 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/Documentation/driver-api/firewire.rst b/Documentation/driver-api/firewire.rst index d3cfa73cbb2b..28a32410f7d2 100644 --- a/Documentation/driver-api/firewire.rst +++ b/Documentation/driver-api/firewire.rst @@ -43,6 +43,8 @@ Firewire core transaction interfaces Firewire Isochronous I/O interfaces =================================== +.. kernel-doc:: include/linux/firewire.h + :functions: fw_iso_context_schedule_flush_completions .. kernel-doc:: drivers/firewire/core-iso.c :export: diff --git a/drivers/firewire/core.h b/drivers/firewire/core.h index 2874f316156a..0ae2c84ecafe 100644 --- a/drivers/firewire/core.h +++ b/drivers/firewire/core.h @@ -164,11 +164,6 @@ static inline void fw_iso_context_init_work(struct fw_iso_context *ctx, work_fun INIT_WORK(&ctx->work, func); } -static inline void fw_iso_context_queue_work(struct fw_iso_context *ctx) -{ - queue_work(ctx->card->isoc_wq, &ctx->work); -} - /* -topology */ diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index d0b1fccc450f..3a911cfb5ff3 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -2283,7 +2283,7 @@ static irqreturn_t irq_handler(int irq, void *data) while (iso_event) { i = ffs(iso_event) - 1; - fw_iso_context_queue_work(&ohci->ir_context_list[i].base); + fw_iso_context_schedule_flush_completions(&ohci->ir_context_list[i].base); iso_event &= ~(1 << i); } } @@ -2294,7 +2294,7 @@ static irqreturn_t irq_handler(int irq, void *data) while (iso_event) { i = ffs(iso_event) - 1; - fw_iso_context_queue_work(&ohci->it_context_list[i].base); + fw_iso_context_schedule_flush_completions(&ohci->it_context_list[i].base); iso_event &= ~(1 << i); } } diff --git a/include/linux/firewire.h b/include/linux/firewire.h index 72f497b61739..f815d12deda0 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -531,6 +531,23 @@ int fw_iso_context_queue(struct fw_iso_context *ctx, unsigned long payload); void fw_iso_context_queue_flush(struct fw_iso_context *ctx); int fw_iso_context_flush_completions(struct fw_iso_context *ctx); + +/** + * fw_iso_context_schedule_flush_completions() - schedule work item to process isochronous context. + * @ctx: the isochronous context + * + * Schedule a work item on workqueue to process the isochronous context. The registered callback + * function is called in the worker if some packets have been already transferred since the last + * time. If it is required to process the context in the current context, + * fw_iso_context_flush_completions() is available instead. + * + * Context: Any context. + */ +static inline void fw_iso_context_schedule_flush_completions(struct fw_iso_context *ctx) +{ + queue_work(ctx->card->isoc_wq, &ctx->work); +} + int fw_iso_context_start(struct fw_iso_context *ctx, int cycle, int sync, int tags); int fw_iso_context_stop(struct fw_iso_context *ctx); -- cgit v1.2.3 From 1d07085402d122f223bda3f8b72bea37a46ee0c9 Mon Sep 17 00:00:00 2001 From: Bibo Mao Date: Sat, 7 Sep 2024 16:27:20 +0800 Subject: smp: Mark smp_prepare_boot_cpu() __init smp_prepare_boot_cpu() is only called during boot, hence mark it as __init. Signed-off-by: Bibo Mao Signed-off-by: Thomas Gleixner Reviewed-by: Huacai Chen Link: https://lore.kernel.org/all/20240907082720.452148-1-maobibo@loongson.cn --- arch/loongarch/kernel/smp.c | 2 +- arch/mips/kernel/smp.c | 2 +- arch/powerpc/kernel/smp.c | 2 +- include/linux/smp.h | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index ca405ab86aae..be2655c4c414 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -476,7 +476,7 @@ core_initcall(ipi_pm_init); #endif /* Preload SMP state for boot cpu */ -void smp_prepare_boot_cpu(void) +void __init smp_prepare_boot_cpu(void) { unsigned int cpu, node, rr_node; diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index 0362fc5df7b0..39e193cad2b9 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -439,7 +439,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus) } /* preload SMP state for boot cpu */ -void smp_prepare_boot_cpu(void) +void __init smp_prepare_boot_cpu(void) { if (mp_ops->prepare_boot_cpu) mp_ops->prepare_boot_cpu(); diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 46e6d2cd7a2d..4ab9b8cee77a 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1166,7 +1166,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus) cpu_smt_set_num_threads(num_threads, threads_per_core); } -void smp_prepare_boot_cpu(void) +void __init smp_prepare_boot_cpu(void) { BUG_ON(smp_processor_id() != boot_cpuid); #ifdef CONFIG_PPC64 diff --git a/include/linux/smp.h b/include/linux/smp.h index fcd61dfe2af3..6a0813c905d0 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -109,7 +109,7 @@ static inline void on_each_cpu_cond(smp_cond_func_t cond_func, * Architecture specific boot CPU setup. Defined as empty weak function in * init/main.c. Architectures can override it. */ -void smp_prepare_boot_cpu(void); +void __init smp_prepare_boot_cpu(void); #ifdef CONFIG_SMP -- cgit v1.2.3 From c259acab839e57eab0318f32da4ae803a8d59397 Mon Sep 17 00:00:00 2001 From: Mahesh Bandewar Date: Wed, 4 Sep 2024 07:13:05 -0700 Subject: ptp/ioctl: support MONOTONIC{,_RAW} timestamps for PTP_SYS_OFFSET_EXTENDED The ability to read the PHC (Physical Hardware Clock) alongside multiple system clocks is currently dependent on the specific hardware architecture. This limitation restricts the use of PTP_SYS_OFFSET_PRECISE to certain hardware configurations. The generic soultion which would work across all architectures is to read the PHC along with the latency to perform PHC-read as offered by PTP_SYS_OFFSET_EXTENDED which provides pre and post timestamps. However, these timestamps are currently limited to the CLOCK_REALTIME timebase. Since CLOCK_REALTIME is affected by NTP (or similar time synchronization services), it can experience significant jumps forward or backward. This hinders the precise latency measurements that PTP_SYS_OFFSET_EXTENDED is designed to provide. This problem could be addressed by supporting MONOTONIC_RAW timestamps within PTP_SYS_OFFSET_EXTENDED. Unlike CLOCK_REALTIME or CLOCK_MONOTONIC, the MONOTONIC_RAW timebase is unaffected by NTP adjustments. This enhancement can be implemented by utilizing one of the three reserved words within the PTP_SYS_OFFSET_EXTENDED struct to pass the clock-id for timestamps. The current behavior aligns with clock-id for CLOCK_REALTIME timebase (value of 0), ensuring backward compatibility of the UAPI. Signed-off-by: Mahesh Bandewar Signed-off-by: Vadim Fedorenko Signed-off-by: David S. Miller --- drivers/ptp/ptp_chardev.c | 8 ++++++-- include/linux/ptp_clock_kernel.h | 36 ++++++++++++++++++++++++++++++++---- include/uapi/linux/ptp_clock.h | 24 ++++++++++++++++++------ 3 files changed, 56 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c index 2067b0120d08..ea96a14d72d1 100644 --- a/drivers/ptp/ptp_chardev.c +++ b/drivers/ptp/ptp_chardev.c @@ -359,11 +359,15 @@ long ptp_ioctl(struct posix_clock_context *pccontext, unsigned int cmd, extoff = NULL; break; } - if (extoff->n_samples > PTP_MAX_SAMPLES - || extoff->rsv[0] || extoff->rsv[1] || extoff->rsv[2]) { + if (extoff->n_samples > PTP_MAX_SAMPLES || + extoff->rsv[0] || extoff->rsv[1] || + (extoff->clockid != CLOCK_REALTIME && + extoff->clockid != CLOCK_MONOTONIC && + extoff->clockid != CLOCK_MONOTONIC_RAW)) { err = -EINVAL; break; } + sts.clockid = extoff->clockid; for (i = 0; i < extoff->n_samples; i++) { err = ptp->info->gettimex64(ptp->info, &ts, &sts); if (err) diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 6e4b8206c7d0..c892d22ce0a7 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -47,10 +47,12 @@ struct system_device_crosststamp; * struct ptp_system_timestamp - system time corresponding to a PHC timestamp * @pre_ts: system timestamp before capturing PHC * @post_ts: system timestamp after capturing PHC + * @clockid: clock-base used for capturing the system timestamps */ struct ptp_system_timestamp { struct timespec64 pre_ts; struct timespec64 post_ts; + clockid_t clockid; }; /** @@ -457,14 +459,40 @@ static inline ktime_t ptp_convert_timestamp(const ktime_t *hwtstamp, static inline void ptp_read_system_prets(struct ptp_system_timestamp *sts) { - if (sts) - ktime_get_real_ts64(&sts->pre_ts); + if (sts) { + switch (sts->clockid) { + case CLOCK_REALTIME: + ktime_get_real_ts64(&sts->pre_ts); + break; + case CLOCK_MONOTONIC: + ktime_get_ts64(&sts->pre_ts); + break; + case CLOCK_MONOTONIC_RAW: + ktime_get_raw_ts64(&sts->pre_ts); + break; + default: + break; + } + } } static inline void ptp_read_system_postts(struct ptp_system_timestamp *sts) { - if (sts) - ktime_get_real_ts64(&sts->post_ts); + if (sts) { + switch (sts->clockid) { + case CLOCK_REALTIME: + ktime_get_real_ts64(&sts->post_ts); + break; + case CLOCK_MONOTONIC: + ktime_get_ts64(&sts->post_ts); + break; + case CLOCK_MONOTONIC_RAW: + ktime_get_raw_ts64(&sts->post_ts); + break; + default: + break; + } + } } #endif diff --git a/include/uapi/linux/ptp_clock.h b/include/uapi/linux/ptp_clock.h index 053b40d642de..18eefa6d93d6 100644 --- a/include/uapi/linux/ptp_clock.h +++ b/include/uapi/linux/ptp_clock.h @@ -155,13 +155,25 @@ struct ptp_sys_offset { struct ptp_clock_time ts[2 * PTP_MAX_SAMPLES + 1]; }; +/* + * ptp_sys_offset_extended - data structure for IOCTL operation + * PTP_SYS_OFFSET_EXTENDED + * + * @n_samples: Desired number of measurements. + * @clockid: clockid of a clock-base used for pre/post timestamps. + * @rsv: Reserved for future use. + * @ts: Array of samples in the form [pre-TS, PHC, post-TS]. The + * kernel provides @n_samples. + * + * Starting from kernel 6.12 and onwards, the first word of the reserved-field + * is used for @clockid. That's backward compatible since previous kernel + * expect all three reserved words (@rsv[3]) to be 0 while the clockid (first + * word in the new structure) for CLOCK_REALTIME is '0'. + */ struct ptp_sys_offset_extended { - unsigned int n_samples; /* Desired number of measurements. */ - unsigned int rsv[3]; /* Reserved for future use. */ - /* - * Array of [system, phc, system] time stamps. The kernel will provide - * 3*n_samples time stamps. - */ + unsigned int n_samples; + __kernel_clockid_t clockid; + unsigned int rsv[2]; struct ptp_clock_time ts[PTP_MAX_SAMPLES][3]; }; -- cgit v1.2.3 From 1fcb932c8b5ce86219d7dedcd63659351a43291c Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 4 Jul 2024 00:56:40 +0200 Subject: rcu/nocb: Simplify (de-)offloading state machine Now that the (de-)offloading process can only apply to offline CPUs, there is no more concurrency between rcu_core and nocb kthreads. Also the mutation now happens on empty queues. Therefore the state machine can be reduced to a single bit called SEGCBLIST_OFFLOADED. Simplify the transition as follows: * Upon offloading: queue the rdp to be added to the rcuog list and wait for the rcuog kthread to set the SEGCBLIST_OFFLOADED bit. Unpark rcuo kthread. * Upon de-offloading: Park rcuo kthread. Queue the rdp to be removed from the rcuog list and wait for the rcuog kthread to clear the SEGCBLIST_OFFLOADED bit. Signed-off-by: Frederic Weisbecker Signed-off-by: Paul E. McKenney Reviewed-by: Paul E. McKenney Signed-off-by: Neeraj Upadhyay --- include/linux/rcu_segcblist.h | 4 +- kernel/rcu/rcu_segcblist.c | 11 ---- kernel/rcu/rcu_segcblist.h | 2 +- kernel/rcu/tree_nocb.h | 138 ++++++++++++++++++++---------------------- 4 files changed, 68 insertions(+), 87 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcu_segcblist.h b/include/linux/rcu_segcblist.h index 1ef1bb54853d..2fdc2208f1ca 100644 --- a/include/linux/rcu_segcblist.h +++ b/include/linux/rcu_segcblist.h @@ -185,9 +185,7 @@ struct rcu_cblist { * ---------------------------------------------------------------------------- */ #define SEGCBLIST_ENABLED BIT(0) -#define SEGCBLIST_LOCKING BIT(1) -#define SEGCBLIST_KTHREAD_GP BIT(2) -#define SEGCBLIST_OFFLOADED BIT(3) +#define SEGCBLIST_OFFLOADED BIT(1) struct rcu_segcblist { struct rcu_head *head; diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c index 1693ea22ef1b..298a2c573f02 100644 --- a/kernel/rcu/rcu_segcblist.c +++ b/kernel/rcu/rcu_segcblist.c @@ -260,17 +260,6 @@ void rcu_segcblist_disable(struct rcu_segcblist *rsclp) rcu_segcblist_clear_flags(rsclp, SEGCBLIST_ENABLED); } -/* - * Mark the specified rcu_segcblist structure as offloaded (or not) - */ -void rcu_segcblist_offload(struct rcu_segcblist *rsclp, bool offload) -{ - if (offload) - rcu_segcblist_set_flags(rsclp, SEGCBLIST_LOCKING | SEGCBLIST_OFFLOADED); - else - rcu_segcblist_clear_flags(rsclp, SEGCBLIST_OFFLOADED); -} - /* * Does the specified rcu_segcblist structure contain callbacks that * are ready to be invoked? diff --git a/kernel/rcu/rcu_segcblist.h b/kernel/rcu/rcu_segcblist.h index 7a0962dfee86..259904075636 100644 --- a/kernel/rcu/rcu_segcblist.h +++ b/kernel/rcu/rcu_segcblist.h @@ -89,7 +89,7 @@ static inline bool rcu_segcblist_is_enabled(struct rcu_segcblist *rsclp) static inline bool rcu_segcblist_is_offloaded(struct rcu_segcblist *rsclp) { if (IS_ENABLED(CONFIG_RCU_NOCB_CPU) && - rcu_segcblist_test_flags(rsclp, SEGCBLIST_LOCKING)) + rcu_segcblist_test_flags(rsclp, SEGCBLIST_OFFLOADED)) return true; return false; diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h index 24daf606de0c..857024ee0349 100644 --- a/kernel/rcu/tree_nocb.h +++ b/kernel/rcu/tree_nocb.h @@ -604,37 +604,33 @@ static void call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *head, } } -static int nocb_gp_toggle_rdp(struct rcu_data *rdp) +static void nocb_gp_toggle_rdp(struct rcu_data *rdp_gp, struct rcu_data *rdp) { struct rcu_segcblist *cblist = &rdp->cblist; unsigned long flags; - int ret; - rcu_nocb_lock_irqsave(rdp, flags); - if (rcu_segcblist_test_flags(cblist, SEGCBLIST_OFFLOADED) && - !rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_GP)) { + /* + * Locking orders future de-offloaded callbacks enqueue against previous + * handling of this rdp. Ie: Make sure rcuog is done with this rdp before + * deoffloaded callbacks can be enqueued. + */ + raw_spin_lock_irqsave(&rdp->nocb_lock, flags); + if (!rcu_segcblist_test_flags(cblist, SEGCBLIST_OFFLOADED)) { /* * Offloading. Set our flag and notify the offload worker. * We will handle this rdp until it ever gets de-offloaded. */ - rcu_segcblist_set_flags(cblist, SEGCBLIST_KTHREAD_GP); - ret = 1; - } else if (!rcu_segcblist_test_flags(cblist, SEGCBLIST_OFFLOADED) && - rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_GP)) { + list_add_tail(&rdp->nocb_entry_rdp, &rdp_gp->nocb_head_rdp); + rcu_segcblist_set_flags(cblist, SEGCBLIST_OFFLOADED); + } else { /* * De-offloading. Clear our flag and notify the de-offload worker. * We will ignore this rdp until it ever gets re-offloaded. */ - rcu_segcblist_clear_flags(cblist, SEGCBLIST_KTHREAD_GP); - ret = 0; - } else { - WARN_ON_ONCE(1); - ret = -1; + list_del(&rdp->nocb_entry_rdp); + rcu_segcblist_clear_flags(cblist, SEGCBLIST_OFFLOADED); } - - rcu_nocb_unlock_irqrestore(rdp, flags); - - return ret; + raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); } static void nocb_gp_sleep(struct rcu_data *my_rdp, int cpu) @@ -841,14 +837,7 @@ static void nocb_gp_wait(struct rcu_data *my_rdp) } if (rdp_toggling) { - int ret; - - ret = nocb_gp_toggle_rdp(rdp_toggling); - if (ret == 1) - list_add_tail(&rdp_toggling->nocb_entry_rdp, &my_rdp->nocb_head_rdp); - else if (ret == 0) - list_del(&rdp_toggling->nocb_entry_rdp); - + nocb_gp_toggle_rdp(my_rdp, rdp_toggling); swake_up_one(&rdp_toggling->nocb_state_wq); } @@ -1018,16 +1007,11 @@ void rcu_nocb_flush_deferred_wakeup(void) } EXPORT_SYMBOL_GPL(rcu_nocb_flush_deferred_wakeup); -static int rdp_offload_toggle(struct rcu_data *rdp, - bool offload, unsigned long flags) - __releases(rdp->nocb_lock) +static int rcu_nocb_queue_toggle_rdp(struct rcu_data *rdp) { - struct rcu_segcblist *cblist = &rdp->cblist; struct rcu_data *rdp_gp = rdp->nocb_gp_rdp; bool wake_gp = false; - - rcu_segcblist_offload(cblist, offload); - rcu_nocb_unlock_irqrestore(rdp, flags); + unsigned long flags; raw_spin_lock_irqsave(&rdp_gp->nocb_gp_lock, flags); // Queue this rdp for add/del to/from the list to iterate on rcuog @@ -1041,9 +1025,25 @@ static int rdp_offload_toggle(struct rcu_data *rdp, return wake_gp; } +static bool rcu_nocb_rdp_deoffload_wait_cond(struct rcu_data *rdp) +{ + unsigned long flags; + bool ret; + + /* + * Locking makes sure rcuog is done handling this rdp before deoffloaded + * enqueue can happen. Also it keeps the SEGCBLIST_OFFLOADED flag stable + * while the ->nocb_lock is held. + */ + raw_spin_lock_irqsave(&rdp->nocb_lock, flags); + ret = !rcu_segcblist_test_flags(&rdp->cblist, SEGCBLIST_OFFLOADED); + raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); + + return ret; +} + static int rcu_nocb_rdp_deoffload(struct rcu_data *rdp) { - struct rcu_segcblist *cblist = &rdp->cblist; unsigned long flags; int wake_gp; struct rcu_data *rdp_gp = rdp->nocb_gp_rdp; @@ -1056,51 +1056,42 @@ static int rcu_nocb_rdp_deoffload(struct rcu_data *rdp) /* Flush all callbacks from segcblist and bypass */ rcu_barrier(); + /* + * Make sure the rcuoc kthread isn't in the middle of a nocb locked + * sequence while offloading is deactivated, along with nocb locking. + */ + if (rdp->nocb_cb_kthread) + kthread_park(rdp->nocb_cb_kthread); + rcu_nocb_lock_irqsave(rdp, flags); WARN_ON_ONCE(rcu_cblist_n_cbs(&rdp->nocb_bypass)); WARN_ON_ONCE(rcu_segcblist_n_cbs(&rdp->cblist)); + rcu_nocb_unlock_irqrestore(rdp, flags); - wake_gp = rdp_offload_toggle(rdp, false, flags); + wake_gp = rcu_nocb_queue_toggle_rdp(rdp); mutex_lock(&rdp_gp->nocb_gp_kthread_mutex); + if (rdp_gp->nocb_gp_kthread) { if (wake_gp) wake_up_process(rdp_gp->nocb_gp_kthread); swait_event_exclusive(rdp->nocb_state_wq, - !rcu_segcblist_test_flags(cblist, - SEGCBLIST_KTHREAD_GP)); - if (rdp->nocb_cb_kthread) - kthread_park(rdp->nocb_cb_kthread); + rcu_nocb_rdp_deoffload_wait_cond(rdp)); } else { /* * No kthread to clear the flags for us or remove the rdp from the nocb list * to iterate. Do it here instead. Locking doesn't look stricly necessary * but we stick to paranoia in this rare path. */ - rcu_nocb_lock_irqsave(rdp, flags); - rcu_segcblist_clear_flags(&rdp->cblist, SEGCBLIST_KTHREAD_GP); - rcu_nocb_unlock_irqrestore(rdp, flags); + raw_spin_lock_irqsave(&rdp->nocb_lock, flags); + rcu_segcblist_clear_flags(&rdp->cblist, SEGCBLIST_OFFLOADED); + raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); list_del(&rdp->nocb_entry_rdp); } - mutex_unlock(&rdp_gp->nocb_gp_kthread_mutex); - /* - * Lock one last time to acquire latest callback updates from kthreads - * so we can later handle callbacks locally without locking. - */ - rcu_nocb_lock_irqsave(rdp, flags); - /* - * Theoretically we could clear SEGCBLIST_LOCKING after the nocb - * lock is released but how about being paranoid for once? - */ - rcu_segcblist_clear_flags(cblist, SEGCBLIST_LOCKING); - /* - * Without SEGCBLIST_LOCKING, we can't use - * rcu_nocb_unlock_irqrestore() anymore. - */ - raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); + mutex_unlock(&rdp_gp->nocb_gp_kthread_mutex); return 0; } @@ -1129,10 +1120,20 @@ int rcu_nocb_cpu_deoffload(int cpu) } EXPORT_SYMBOL_GPL(rcu_nocb_cpu_deoffload); -static int rcu_nocb_rdp_offload(struct rcu_data *rdp) +static bool rcu_nocb_rdp_offload_wait_cond(struct rcu_data *rdp) { - struct rcu_segcblist *cblist = &rdp->cblist; unsigned long flags; + bool ret; + + raw_spin_lock_irqsave(&rdp->nocb_lock, flags); + ret = rcu_segcblist_test_flags(&rdp->cblist, SEGCBLIST_OFFLOADED); + raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); + + return ret; +} + +static int rcu_nocb_rdp_offload(struct rcu_data *rdp) +{ int wake_gp; struct rcu_data *rdp_gp = rdp->nocb_gp_rdp; @@ -1152,20 +1153,14 @@ static int rcu_nocb_rdp_offload(struct rcu_data *rdp) WARN_ON_ONCE(rcu_cblist_n_cbs(&rdp->nocb_bypass)); WARN_ON_ONCE(rcu_segcblist_n_cbs(&rdp->cblist)); - /* - * Can't use rcu_nocb_lock_irqsave() before SEGCBLIST_LOCKING - * is set. - */ - raw_spin_lock_irqsave(&rdp->nocb_lock, flags); - - wake_gp = rdp_offload_toggle(rdp, true, flags); + wake_gp = rcu_nocb_queue_toggle_rdp(rdp); if (wake_gp) wake_up_process(rdp_gp->nocb_gp_kthread); - kthread_unpark(rdp->nocb_cb_kthread); - swait_event_exclusive(rdp->nocb_state_wq, - rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_GP)); + rcu_nocb_rdp_offload_wait_cond(rdp)); + + kthread_unpark(rdp->nocb_cb_kthread); return 0; } @@ -1340,8 +1335,7 @@ void __init rcu_init_nohz(void) rdp = per_cpu_ptr(&rcu_data, cpu); if (rcu_segcblist_empty(&rdp->cblist)) rcu_segcblist_init(&rdp->cblist); - rcu_segcblist_offload(&rdp->cblist, true); - rcu_segcblist_set_flags(&rdp->cblist, SEGCBLIST_KTHREAD_GP); + rcu_segcblist_set_flags(&rdp->cblist, SEGCBLIST_OFFLOADED); } rcu_organize_nocb_kthreads(); } -- cgit v1.2.3 From bd7c8ff9fef4b21a97f9b30a7364845ee6eaaf23 Mon Sep 17 00:00:00 2001 From: Anna-Maria Behnsen Date: Wed, 4 Sep 2024 15:04:53 +0200 Subject: treewide: Fix wrong singular form of jiffies in comments There are several comments all over the place, which uses a wrong singular form of jiffies. Replace 'jiffie' by 'jiffy'. No functional change. Signed-off-by: Anna-Maria Behnsen Signed-off-by: Thomas Gleixner Acked-by: Geert Uytterhoeven # m68k Link: https://lore.kernel.org/all/20240904-devel-anna-maria-b4-timers-flseep-v1-3-e98760256370@linutronix.de --- Documentation/admin-guide/media/vivid.rst | 2 +- Documentation/timers/timers-howto.rst | 2 +- .../translations/sp_SP/scheduler/sched-design-CFS.rst | 2 +- arch/arm/mach-versatile/spc.c | 2 +- arch/m68k/q40/q40ints.c | 2 +- arch/x86/kernel/cpu/mce/dev-mcelog.c | 2 +- drivers/char/ipmi/ipmi_ssif.c | 2 +- drivers/dma-buf/st-dma-fence.c | 2 +- drivers/gpu/drm/i915/gem/i915_gem_wait.c | 2 +- drivers/gpu/drm/i915/gt/selftest_execlists.c | 4 ++-- drivers/gpu/drm/i915/i915_utils.c | 2 +- drivers/gpu/drm/v3d/v3d_bo.c | 2 +- drivers/isdn/mISDN/dsp_cmx.c | 2 +- drivers/net/ethernet/marvell/mvmdio.c | 2 +- fs/xfs/xfs_buf.h | 2 +- include/linux/jiffies.h | 2 +- include/linux/timekeeper_internal.h | 2 +- kernel/time/alarmtimer.c | 2 +- kernel/time/clockevents.c | 2 +- kernel/time/hrtimer.c | 2 +- kernel/time/posix-timers.c | 4 ++-- kernel/time/timer.c | 12 ++++++------ lib/Kconfig.debug | 2 +- net/batman-adv/types.h | 2 +- 24 files changed, 31 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/media/vivid.rst b/Documentation/admin-guide/media/vivid.rst index 1306f19ecb5a..c9d301ab46a3 100644 --- a/Documentation/admin-guide/media/vivid.rst +++ b/Documentation/admin-guide/media/vivid.rst @@ -328,7 +328,7 @@ and an HDMI input, one input for each input type. Those are described in more detail below. Special attention has been given to the rate at which new frames become -available. The jitter will be around 1 jiffie (that depends on the HZ +available. The jitter will be around 1 jiffy (that depends on the HZ configuration of your kernel, so usually 1/100, 1/250 or 1/1000 of a second), but the long-term behavior is exactly following the framerate. So a framerate of 59.94 Hz is really different from 60 Hz. If the framerate diff --git a/Documentation/timers/timers-howto.rst b/Documentation/timers/timers-howto.rst index 5c169e3d29a8..ef7a4652ccc9 100644 --- a/Documentation/timers/timers-howto.rst +++ b/Documentation/timers/timers-howto.rst @@ -19,7 +19,7 @@ it really need to delay in atomic context?" If so... ATOMIC CONTEXT: You must use the `*delay` family of functions. These - functions use the jiffie estimation of clock speed + functions use the jiffy estimation of clock speed and will busy wait for enough loop cycles to achieve the desired delay: diff --git a/Documentation/translations/sp_SP/scheduler/sched-design-CFS.rst b/Documentation/translations/sp_SP/scheduler/sched-design-CFS.rst index 90a153cad4e8..731c266beb1a 100644 --- a/Documentation/translations/sp_SP/scheduler/sched-design-CFS.rst +++ b/Documentation/translations/sp_SP/scheduler/sched-design-CFS.rst @@ -109,7 +109,7 @@ para que se ejecute, y la tarea en ejecución es interrumpida. ================================== CFS usa una granularidad de nanosegundos y no depende de ningún -jiffie o detalles como HZ. De este modo, el gestor de tareas CFS no tiene +jiffy o detalles como HZ. De este modo, el gestor de tareas CFS no tiene noción de "ventanas de tiempo" de la forma en que tenía el gestor de tareas previo, y tampoco tiene heurísticos. Únicamente hay un parámetro central ajustable (se ha de cambiar en CONFIG_SCHED_DEBUG): diff --git a/arch/arm/mach-versatile/spc.c b/arch/arm/mach-versatile/spc.c index 5e44170e1a9a..790092734cf6 100644 --- a/arch/arm/mach-versatile/spc.c +++ b/arch/arm/mach-versatile/spc.c @@ -73,7 +73,7 @@ /* * Even though the SPC takes max 3-5 ms to complete any OPP/COMMS - * operation, the operation could start just before jiffie is about + * operation, the operation could start just before jiffy is about * to be incremented. So setting timeout value of 20ms = 2jiffies@100Hz */ #define TIMEOUT_US 20000 diff --git a/arch/m68k/q40/q40ints.c b/arch/m68k/q40/q40ints.c index 10f1f294e91f..14b774b9d308 100644 --- a/arch/m68k/q40/q40ints.c +++ b/arch/m68k/q40/q40ints.c @@ -106,7 +106,7 @@ void __init q40_init_IRQ(void) * this stuff doesn't really belong here.. */ -int ql_ticks; /* 200Hz ticks since last jiffie */ +int ql_ticks; /* 200Hz ticks since last jiffy */ static int sound_ticks; #define SVOL 45 diff --git a/arch/x86/kernel/cpu/mce/dev-mcelog.c b/arch/x86/kernel/cpu/mce/dev-mcelog.c index a05ac0716ecf..a3aa0199222e 100644 --- a/arch/x86/kernel/cpu/mce/dev-mcelog.c +++ b/arch/x86/kernel/cpu/mce/dev-mcelog.c @@ -314,7 +314,7 @@ static ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf, /* * Need to give user space some time to set everything up, - * so do it a jiffie or two later everywhere. + * so do it a jiffy or two later everywhere. */ schedule_timeout(2); diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c index 96ad571d041a..e093028391af 100644 --- a/drivers/char/ipmi/ipmi_ssif.c +++ b/drivers/char/ipmi/ipmi_ssif.c @@ -980,7 +980,7 @@ static void msg_written_handler(struct ssif_info *ssif_info, int result, ipmi_ssif_unlock_cond(ssif_info, flags); start_get(ssif_info); } else { - /* Wait a jiffie then request the next message */ + /* Wait a jiffy then request the next message */ ssif_info->waiting_alert = true; ssif_info->retries_left = SSIF_RECV_RETRIES; if (!ssif_info->stopping) diff --git a/drivers/dma-buf/st-dma-fence.c b/drivers/dma-buf/st-dma-fence.c index 6a1bfcd0cc21..cf2ce3744ce6 100644 --- a/drivers/dma-buf/st-dma-fence.c +++ b/drivers/dma-buf/st-dma-fence.c @@ -402,7 +402,7 @@ static int test_wait_timeout(void *arg) if (dma_fence_wait_timeout(wt.f, false, 2) == -ETIME) { if (timer_pending(&wt.timer)) { - pr_notice("Timer did not fire within the jiffie!\n"); + pr_notice("Timer did not fire within the jiffy!\n"); err = 0; /* not our fault! */ } else { pr_err("Wait reported incomplete after timeout\n"); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_wait.c b/drivers/gpu/drm/i915/gem/i915_gem_wait.c index d4b918fb11ce..1f55e62044a4 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_wait.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_wait.c @@ -266,7 +266,7 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file) if (ret == -ETIME && !nsecs_to_jiffies(args->timeout_ns)) args->timeout_ns = 0; - /* Asked to wait beyond the jiffie/scheduler precision? */ + /* Asked to wait beyond the jiffy/scheduler precision? */ if (ret == -ETIME && args->timeout_ns) ret = -EAGAIN; } diff --git a/drivers/gpu/drm/i915/gt/selftest_execlists.c b/drivers/gpu/drm/i915/gt/selftest_execlists.c index 4202df5b8c12..222ca7c44951 100644 --- a/drivers/gpu/drm/i915/gt/selftest_execlists.c +++ b/drivers/gpu/drm/i915/gt/selftest_execlists.c @@ -93,7 +93,7 @@ static int wait_for_reset(struct intel_engine_cs *engine, return -EINVAL; } - /* Give the request a jiffie to complete after flushing the worker */ + /* Give the request a jiffy to complete after flushing the worker */ if (i915_request_wait(rq, 0, max(0l, (long)(timeout - jiffies)) + 1) < 0) { pr_err("%s: hanging request %llx:%lld did not complete\n", @@ -3426,7 +3426,7 @@ static int live_preempt_timeout(void *arg) cpu_relax(); saved_timeout = engine->props.preempt_timeout_ms; - engine->props.preempt_timeout_ms = 1; /* in ms, -> 1 jiffie */ + engine->props.preempt_timeout_ms = 1; /* in ms, -> 1 jiffy */ i915_request_get(rq); i915_request_add(rq); diff --git a/drivers/gpu/drm/i915/i915_utils.c b/drivers/gpu/drm/i915/i915_utils.c index 6f9e7b354b54..f2ba51c20e97 100644 --- a/drivers/gpu/drm/i915/i915_utils.c +++ b/drivers/gpu/drm/i915/i915_utils.c @@ -110,7 +110,7 @@ void set_timer_ms(struct timer_list *t, unsigned long timeout) * Paranoia to make sure the compiler computes the timeout before * loading 'jiffies' as jiffies is volatile and may be updated in * the background by a timer tick. All to reduce the complexity - * of the addition and reduce the risk of losing a jiffie. + * of the addition and reduce the risk of losing a jiffy. */ barrier(); diff --git a/drivers/gpu/drm/v3d/v3d_bo.c b/drivers/gpu/drm/v3d/v3d_bo.c index a165cbcdd27b..9eafe53a8f41 100644 --- a/drivers/gpu/drm/v3d/v3d_bo.c +++ b/drivers/gpu/drm/v3d/v3d_bo.c @@ -279,7 +279,7 @@ v3d_wait_bo_ioctl(struct drm_device *dev, void *data, else args->timeout_ns = 0; - /* Asked to wait beyond the jiffie/scheduler precision? */ + /* Asked to wait beyond the jiffy/scheduler precision? */ if (ret == -ETIME && args->timeout_ns) ret = -EAGAIN; diff --git a/drivers/isdn/mISDN/dsp_cmx.c b/drivers/isdn/mISDN/dsp_cmx.c index 61cb45c5d0d8..53fad9487574 100644 --- a/drivers/isdn/mISDN/dsp_cmx.c +++ b/drivers/isdn/mISDN/dsp_cmx.c @@ -82,7 +82,7 @@ * - has multiple clocks. * - has no usable clock due to jitter or packet loss (VoIP). * In this case the system's clock is used. The clock resolution depends on - * the jiffie resolution. + * the jiffy resolution. * * If a member joins a conference: * diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c index 9190eff6c0bb..e1d003fdbc2e 100644 --- a/drivers/net/ethernet/marvell/mvmdio.c +++ b/drivers/net/ethernet/marvell/mvmdio.c @@ -104,7 +104,7 @@ static int orion_mdio_wait_ready(const struct orion_mdio_ops *ops, return 0; } else { /* wait_event_timeout does not guarantee a delay of at - * least one whole jiffie, so timeout must be no less + * least one whole jiffy, so timeout must be no less * than two. */ timeout = max(usecs_to_jiffies(MVMDIO_SMI_TIMEOUT), 2); diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index b1580644501f..209a389f2abc 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -210,7 +210,7 @@ struct xfs_buf { * success the write is considered to be failed permanently and the * iodone handler will take appropriate action. * - * For retry timeouts, we record the jiffie of the first failure. This + * For retry timeouts, we record the jiffy of the first failure. This * means that we can change the retry timeout for buffers already under * I/O and thus avoid getting stuck in a retry loop with a long timeout. * diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index d9f1435a5a13..1220f0fbe5bf 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -418,7 +418,7 @@ extern unsigned long preset_lpj; #define NSEC_CONVERSION ((unsigned long)((((u64)1 << NSEC_JIFFIE_SC) +\ TICK_NSEC -1) / (u64)TICK_NSEC)) /* - * The maximum jiffie value is (MAX_INT >> 1). Here we translate that + * The maximum jiffy value is (MAX_INT >> 1). Here we translate that * into seconds. The 64-bit case will overflow if we are not careful, * so use the messy SH_DIV macro to do it. Still all constants. */ diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index 84ff2844df2a..902c20ef495a 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -73,7 +73,7 @@ struct tk_read_base { * @overflow_seen: Overflow warning flag (DEBUG_TIMEKEEPING) * * Note: For timespec(64) based interfaces wall_to_monotonic is what - * we need to add to xtime (or xtime corrected for sub jiffie times) + * we need to add to xtime (or xtime corrected for sub jiffy times) * to get to monotonic time. Monotonic is pegged at zero at system * boot time, so wall_to_monotonic will be negative, however, we will * ALWAYS keep the tv_nsec part positive so we can use the usual diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 76bd4fda3472..8bf888641694 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -493,7 +493,7 @@ static u64 __alarm_forward_now(struct alarm *alarm, ktime_t interval, bool throt * promised in the context of posix_timer_fn() never * materialized, but someone should really work on it. * - * To prevent DOS fake @now to be 1 jiffie out which keeps + * To prevent DOS fake @now to be 1 jiffy out which keeps * the overrun accounting correct but creates an * inconsistency vs. timer_gettime(2). */ diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 60a6484831b1..78c7bd64d0dd 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -190,7 +190,7 @@ int clockevents_tick_resume(struct clock_event_device *dev) #ifdef CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST -/* Limit min_delta to a jiffie */ +/* Limit min_delta to a jiffy */ #define MIN_DELTA_LIMIT (NSEC_PER_SEC / HZ) /** diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index a023946f8558..e834b2bd83df 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1177,7 +1177,7 @@ static inline ktime_t hrtimer_update_lowres(struct hrtimer *timer, ktime_t tim, /* * CONFIG_TIME_LOW_RES indicates that the system has no way to return * granular time values. For relative timers we add hrtimer_resolution - * (i.e. one jiffie) to prevent short timeouts. + * (i.e. one jiffy) to prevent short timeouts. */ timer->is_rel = mode & HRTIMER_MODE_REL; if (timer->is_rel) diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 1cc830ef93a7..4576aaed13b2 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -339,14 +339,14 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer) * change to the signal handling code. * * For now let timers with an interval less than a - * jiffie expire every jiffie and recheck for a + * jiffy expire every jiffy and recheck for a * valid signal handler. * * This avoids interrupt starvation in case of a * very small interval, which would expire the * timer immediately again. * - * Moving now ahead of time by one jiffie tricks + * Moving now ahead of time by one jiffy tricks * hrtimer_forward() to expire the timer later, * while it still maintains the overrun accuracy * for the price of a slight inconsistency in the diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 5e021a2d8d61..2b38f3035a3e 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -365,7 +365,7 @@ static unsigned long round_jiffies_common(unsigned long j, int cpu, rem = j % HZ; /* - * If the target jiffie is just after a whole second (which can happen + * If the target jiffy is just after a whole second (which can happen * due to delays of the timer irq, long irq off times etc etc) then * we should round down to the whole second, not up. Use 1/4th second * as cutoff for this rounding as an extreme upper bound for this. @@ -1930,7 +1930,7 @@ static void timer_recalc_next_expiry(struct timer_base *base) * bits are zero, we look at the next level as is. If not we * need to advance it by one because that's going to be the * next expiring bucket in that level. base->clk is the next - * expiring jiffie. So in case of: + * expiring jiffy. So in case of: * * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0 * 0 0 0 0 0 0 @@ -1995,7 +1995,7 @@ static u64 cmp_next_hrtimer_event(u64 basem, u64 expires) return basem; /* - * Round up to the next jiffie. High resolution timers are + * Round up to the next jiffy. High resolution timers are * off, so the hrtimers are expired in the tick and we need to * make sure that this tick really expires the timer to avoid * a ping pong of the nohz stop code. @@ -2254,7 +2254,7 @@ static inline u64 __get_next_timer_interrupt(unsigned long basej, u64 basem, base_global, &tevt); /* - * If the next event is only one jiffie ahead there is no need to call + * If the next event is only one jiffy ahead there is no need to call * timer migration hierarchy related functions. The value for the next * global timer in @tevt struct equals then KTIME_MAX. This is also * true, when the timer base is idle. @@ -2486,11 +2486,11 @@ static void run_local_timers(void) * updated. When this update is missed, this isn't a * problem, as an IPI is executed nevertheless when the CPU * was idle before. When the CPU wasn't idle but the update - * is missed, then the timer would expire one jiffie late - + * is missed, then the timer would expire one jiffy late - * bad luck. * * Those unlikely corner cases where the worst outcome is only a - * one jiffie delay or a superfluous raise of the softirq are + * one jiffy delay or a superfluous raise of the softirq are * not that expensive as doing the check always while holding * the lock. * diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index a30c03a66172..a40aa606cd04 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -97,7 +97,7 @@ config BOOT_PRINTK_DELAY using "boot_delay=N". It is likely that you would also need to use "lpj=M" to preset - the "loops per jiffie" value. + the "loops per jiffy" value. See a previous boot log for the "lpj" value to use for your system, and then set "lpj=M" before setting "boot_delay=N". NOTE: Using this option may adversely affect SMP systems. diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 00840d5784fe..04f6398b3a40 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -287,7 +287,7 @@ struct batadv_frag_table_entry { /** @lock: lock to protect the list of fragments */ spinlock_t lock; - /** @timestamp: time (jiffie) of last received fragment */ + /** @timestamp: time (jiffy) of last received fragment */ unsigned long timestamp; /** @seqno: sequence number of the fragments in the list */ -- cgit v1.2.3 From ca229bdbef29be207c8666f106acc3bf50736c05 Mon Sep 17 00:00:00 2001 From: Cheng Ming Lin Date: Mon, 9 Sep 2024 17:26:42 +0800 Subject: mtd: spinand: Add support for setting plane select bits Add two flags for inserting the Plane Select bit into the column address during the write_to_cache and the read_from_cache operation. Add the SPINAND_HAS_PROG_PLANE_SELECT_BIT flag for serial NAND flash that require inserting the Plane Select bit into the column address during the write_to_cache operation. Add the SPINAND_HAS_READ_PLANE_SELECT_BIT flag for serial NAND flash that require inserting the Plane Select bit into the column address during the read_from_cache operation. Signed-off-by: Cheng Ming Lin Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20240909092643.2434479-2-linchengming884@gmail.com --- drivers/mtd/nand/spi/core.c | 6 ++++++ include/linux/mtd/spinand.h | 2 ++ 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c index b5c6d755ade1..4d76f9f71a0e 100644 --- a/drivers/mtd/nand/spi/core.c +++ b/drivers/mtd/nand/spi/core.c @@ -408,6 +408,9 @@ static int spinand_read_from_cache_op(struct spinand_device *spinand, else rdesc = spinand->dirmaps[req->pos.plane].rdesc_ecc; + if (spinand->flags & SPINAND_HAS_READ_PLANE_SELECT_BIT) + column |= req->pos.plane << fls(nanddev_page_size(nand)); + while (nbytes) { ret = spi_mem_dirmap_read(rdesc, column, nbytes, buf); if (ret < 0) @@ -489,6 +492,9 @@ static int spinand_write_to_cache_op(struct spinand_device *spinand, else wdesc = spinand->dirmaps[req->pos.plane].wdesc_ecc; + if (spinand->flags & SPINAND_HAS_PROG_PLANE_SELECT_BIT) + column |= req->pos.plane << fls(nanddev_page_size(nand)); + while (nbytes) { ret = spi_mem_dirmap_write(wdesc, column, nbytes, buf); if (ret < 0) diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index 8dbf67ca710a..702e5fb13dae 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -312,6 +312,8 @@ struct spinand_ecc_info { #define SPINAND_HAS_QE_BIT BIT(0) #define SPINAND_HAS_CR_FEAT_BIT BIT(1) +#define SPINAND_HAS_PROG_PLANE_SELECT_BIT BIT(2) +#define SPINAND_HAS_READ_PLANE_SELECT_BIT BIT(3) /** * struct spinand_ondie_ecc_conf - private SPI-NAND on-die ECC engine structure -- cgit v1.2.3 From d688d65a847ff910146eff51e70f4b7049895eb5 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 30 Aug 2024 15:04:49 +0200 Subject: fs: add generic_llseek_cookie() This is similar to generic_file_llseek() but allows the caller to specify a cookie that will be updated to indicate that a seek happened. Caller's requiring that information in their readdir implementations can use that. Link: https://lore.kernel.org/r/20240830-vfs-file-f_version-v1-8-6d3e4816aa7b@kernel.org Reviewed-by: Jan Kara Reviewed-by: Jeff Layton Signed-off-by: Christian Brauner --- fs/read_write.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/fs.h | 2 ++ 2 files changed, 47 insertions(+) (limited to 'include/linux') diff --git a/fs/read_write.c b/fs/read_write.c index b07e48cd81d1..fb519e55c8e8 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -180,6 +180,51 @@ generic_file_llseek_size(struct file *file, loff_t offset, int whence, } EXPORT_SYMBOL(generic_file_llseek_size); +/** + * generic_llseek_cookie - versioned llseek implementation + * @file: file structure to seek on + * @offset: file offset to seek to + * @whence: type of seek + * @cookie: cookie to update + * + * See generic_file_llseek for a general description and locking assumptions. + * + * In contrast to generic_file_llseek, this function also resets a + * specified cookie to indicate a seek took place. + */ +loff_t generic_llseek_cookie(struct file *file, loff_t offset, int whence, + u64 *cookie) +{ + struct inode *inode = file->f_mapping->host; + loff_t maxsize = inode->i_sb->s_maxbytes; + loff_t eof = i_size_read(inode); + int ret; + + if (WARN_ON_ONCE(!cookie)) + return -EINVAL; + + /* + * Require that this is only used for directories that guarantee + * synchronization between readdir and seek so that an update to + * @cookie is correctly synchronized with concurrent readdir. + */ + if (WARN_ON_ONCE(!(file->f_mode & FMODE_ATOMIC_POS))) + return -EINVAL; + + ret = must_set_pos(file, &offset, whence, eof); + if (ret < 0) + return ret; + if (ret == 0) + return offset; + + /* No need to hold f_lock because we know that f_pos_lock is held. */ + if (whence == SEEK_CUR) + return vfs_setpos_cookie(file, file->f_pos + offset, maxsize, cookie); + + return vfs_setpos_cookie(file, offset, maxsize, cookie); +} +EXPORT_SYMBOL(generic_llseek_cookie); + /** * generic_file_llseek - generic llseek implementation for regular files * @file: file structure to seek on diff --git a/include/linux/fs.h b/include/linux/fs.h index 58c91a52cad1..3e6b3c1afb31 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3202,6 +3202,8 @@ extern loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize); extern loff_t generic_file_llseek(struct file *file, loff_t offset, int whence); extern loff_t generic_file_llseek_size(struct file *file, loff_t offset, int whence, loff_t maxsize, loff_t eof); +loff_t generic_llseek_cookie(struct file *file, loff_t offset, int whence, + u64 *cookie); extern loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size); extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t); -- cgit v1.2.3 From 88d2ae0e6eb84e1ed58f339c6a0de16c24fa2a60 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Thu, 8 Aug 2024 11:18:21 -0400 Subject: inode: make __iget() a static inline bcachefs is switching to an rhashtable for vfs inodes instead of the standard inode.c hashtable, so we need this exported, or - a static inline makes more sense for a single atomic_inc(). Signed-off-by: Kent Overstreet --- fs/inode.c | 8 -------- include/linux/fs.h | 9 ++++++++- 2 files changed, 8 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/fs/inode.c b/fs/inode.c index 86670941884b..5e7dcdeedd4d 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -438,14 +438,6 @@ static void init_once(void *foo) inode_init_once(inode); } -/* - * inode->i_lock must be held - */ -void __iget(struct inode *inode) -{ - atomic_inc(&inode->i_count); -} - /* * get additional reference to inode; caller must already hold one. */ diff --git a/include/linux/fs.h b/include/linux/fs.h index fd34b5755c0b..8fc4bad3b6ae 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3094,7 +3094,14 @@ static inline bool is_zero_ino(ino_t ino) return (u32)ino == 0; } -extern void __iget(struct inode * inode); +/* + * inode->i_lock must be held + */ +static inline void __iget(struct inode *inode) +{ + atomic_inc(&inode->i_count); +} + extern void iget_failed(struct inode *); extern void clear_inode(struct inode *); extern void __destroy_inode(struct inode *); -- cgit v1.2.3 From f6594633817374a64a5fb31007bd810cad1425ff Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Mon, 17 Jun 2024 19:00:33 -0400 Subject: lib/generic-radix-tree.c: genradix_ptr_inlined() Provide an inlined fast path Signed-off-by: Kent Overstreet --- include/linux/generic-radix-tree.h | 75 ++++++++++++++++++++++++++++++++++++++ lib/generic-radix-tree.c | 64 +------------------------------- 2 files changed, 76 insertions(+), 63 deletions(-) (limited to 'include/linux') diff --git a/include/linux/generic-radix-tree.h b/include/linux/generic-radix-tree.h index f3512fddf3d7..8a3e1e886d1c 100644 --- a/include/linux/generic-radix-tree.h +++ b/include/linux/generic-radix-tree.h @@ -48,6 +48,49 @@ struct genradix_root; #define GENRADIX_NODE_SHIFT 9 #define GENRADIX_NODE_SIZE (1U << GENRADIX_NODE_SHIFT) +#define GENRADIX_ARY (GENRADIX_NODE_SIZE / sizeof(struct genradix_node *)) +#define GENRADIX_ARY_SHIFT ilog2(GENRADIX_ARY) + +/* depth that's needed for a genradix that can address up to ULONG_MAX: */ +#define GENRADIX_MAX_DEPTH \ + DIV_ROUND_UP(BITS_PER_LONG - GENRADIX_NODE_SHIFT, GENRADIX_ARY_SHIFT) + +#define GENRADIX_DEPTH_MASK \ + ((unsigned long) (roundup_pow_of_two(GENRADIX_MAX_DEPTH + 1) - 1)) + +static inline int genradix_depth_shift(unsigned depth) +{ + return GENRADIX_NODE_SHIFT + GENRADIX_ARY_SHIFT * depth; +} + +/* + * Returns size (of data, in bytes) that a tree of a given depth holds: + */ +static inline size_t genradix_depth_size(unsigned depth) +{ + return 1UL << genradix_depth_shift(depth); +} + +static inline unsigned genradix_root_to_depth(struct genradix_root *r) +{ + return (unsigned long) r & GENRADIX_DEPTH_MASK; +} + +static inline struct genradix_node *genradix_root_to_node(struct genradix_root *r) +{ + return (void *) ((unsigned long) r & ~GENRADIX_DEPTH_MASK); +} + +struct genradix_node { + union { + /* Interior node: */ + struct genradix_node *children[GENRADIX_ARY]; + + /* Leaf: */ + u8 data[GENRADIX_NODE_SIZE]; + }; +}; + struct __genradix { struct genradix_root *root; }; @@ -128,6 +171,30 @@ static inline size_t __idx_to_offset(size_t idx, size_t obj_size) #define __genradix_idx_to_offset(_radix, _idx) \ __idx_to_offset(_idx, __genradix_obj_size(_radix)) +static inline void *__genradix_ptr_inlined(struct __genradix *radix, size_t offset) +{ + struct genradix_root *r = READ_ONCE(radix->root); + struct genradix_node *n = genradix_root_to_node(r); + unsigned level = genradix_root_to_depth(r); + unsigned shift = genradix_depth_shift(level); + + if (unlikely(ilog2(offset) >= genradix_depth_shift(level))) + return NULL; + + while (n && shift > GENRADIX_NODE_SHIFT) { + shift -= GENRADIX_ARY_SHIFT; + n = n->children[offset >> shift]; + offset &= (1UL << shift) - 1; + } + + return n ? &n->data[offset] : NULL; +} + +#define genradix_ptr_inlined(_radix, _idx) \ + (__genradix_cast(_radix) \ + __genradix_ptr_inlined(&(_radix)->tree, \ + __genradix_idx_to_offset(_radix, _idx))) + void *__genradix_ptr(struct __genradix *, size_t); /** @@ -144,6 +211,14 @@ void *__genradix_ptr(struct __genradix *, size_t); void *__genradix_ptr_alloc(struct __genradix *, size_t, gfp_t); +#define genradix_ptr_alloc_inlined(_radix, _idx, _gfp) \ + (__genradix_cast(_radix) \ + (__genradix_ptr_inlined(&(_radix)->tree, \ + __genradix_idx_to_offset(_radix, _idx)) ?: \ + __genradix_ptr_alloc(&(_radix)->tree, \ + __genradix_idx_to_offset(_radix, _idx), \ + _gfp))) + /** * genradix_ptr_alloc - get a pointer to a genradix entry, allocating it * if necessary diff --git a/lib/generic-radix-tree.c b/lib/generic-radix-tree.c index fa692c86f069..4efae0663049 100644 --- a/lib/generic-radix-tree.c +++ b/lib/generic-radix-tree.c @@ -5,75 +5,13 @@ #include #include -#define GENRADIX_ARY (GENRADIX_NODE_SIZE / sizeof(struct genradix_node *)) -#define GENRADIX_ARY_SHIFT ilog2(GENRADIX_ARY) - -struct genradix_node { - union { - /* Interior node: */ - struct genradix_node *children[GENRADIX_ARY]; - - /* Leaf: */ - u8 data[GENRADIX_NODE_SIZE]; - }; -}; - -static inline int genradix_depth_shift(unsigned depth) -{ - return GENRADIX_NODE_SHIFT + GENRADIX_ARY_SHIFT * depth; -} - -/* - * Returns size (of data, in bytes) that a tree of a given depth holds: - */ -static inline size_t genradix_depth_size(unsigned depth) -{ - return 1UL << genradix_depth_shift(depth); -} - -/* depth that's needed for a genradix that can address up to ULONG_MAX: */ -#define GENRADIX_MAX_DEPTH \ - DIV_ROUND_UP(BITS_PER_LONG - GENRADIX_NODE_SHIFT, GENRADIX_ARY_SHIFT) - -#define GENRADIX_DEPTH_MASK \ - ((unsigned long) (roundup_pow_of_two(GENRADIX_MAX_DEPTH + 1) - 1)) - -static inline unsigned genradix_root_to_depth(struct genradix_root *r) -{ - return (unsigned long) r & GENRADIX_DEPTH_MASK; -} - -static inline struct genradix_node *genradix_root_to_node(struct genradix_root *r) -{ - return (void *) ((unsigned long) r & ~GENRADIX_DEPTH_MASK); -} - /* * Returns pointer to the specified byte @offset within @radix, or NULL if not * allocated */ void *__genradix_ptr(struct __genradix *radix, size_t offset) { - struct genradix_root *r = READ_ONCE(radix->root); - struct genradix_node *n = genradix_root_to_node(r); - unsigned level = genradix_root_to_depth(r); - - if (ilog2(offset) >= genradix_depth_shift(level)) - return NULL; - - while (1) { - if (!n) - return NULL; - if (!level) - break; - - level--; - - n = n->children[offset >> genradix_depth_shift(level)]; - offset &= genradix_depth_size(level) - 1; - } - - return &n->data[offset]; + return __genradix_ptr_inlined(radix, offset); } EXPORT_SYMBOL(__genradix_ptr); -- cgit v1.2.3 From b3f9da79e7783ca4f1c1d4214af976c548629c1d Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sat, 10 Aug 2024 23:14:44 -0400 Subject: lib/generic-radix-tree.c: add preallocation Signed-off-by: Kent Overstreet --- include/linux/generic-radix-tree.h | 38 ++++++++++++++++++++++++++++++++------ lib/generic-radix-tree.c | 16 +++++----------- 2 files changed, 37 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/generic-radix-tree.h b/include/linux/generic-radix-tree.h index 8a3e1e886d1c..5b51c3d582d6 100644 --- a/include/linux/generic-radix-tree.h +++ b/include/linux/generic-radix-tree.h @@ -41,6 +41,7 @@ #include #include #include +#include #include struct genradix_root; @@ -81,6 +82,10 @@ static inline struct genradix_node *genradix_root_to_node(struct genradix_root * return (void *) ((unsigned long) r & ~GENRADIX_DEPTH_MASK); } +struct __genradix { + struct genradix_root *root; +}; + struct genradix_node { union { /* Interior node: */ @@ -91,9 +96,15 @@ struct genradix_node { }; }; -struct __genradix { - struct genradix_root *root; -}; +static inline struct genradix_node *genradix_alloc_node(gfp_t gfp_mask) +{ + return kzalloc(GENRADIX_NODE_SIZE, gfp_mask); +} + +static inline void genradix_free_node(struct genradix_node *node) +{ + kfree(node); +} /* * NOTE: currently, sizeof(_type) must not be larger than GENRADIX_NODE_SIZE: @@ -209,7 +220,8 @@ void *__genradix_ptr(struct __genradix *, size_t); __genradix_ptr(&(_radix)->tree, \ __genradix_idx_to_offset(_radix, _idx))) -void *__genradix_ptr_alloc(struct __genradix *, size_t, gfp_t); +void *__genradix_ptr_alloc(struct __genradix *, size_t, + struct genradix_node **, gfp_t); #define genradix_ptr_alloc_inlined(_radix, _idx, _gfp) \ (__genradix_cast(_radix) \ @@ -217,7 +229,15 @@ void *__genradix_ptr_alloc(struct __genradix *, size_t, gfp_t); __genradix_idx_to_offset(_radix, _idx)) ?: \ __genradix_ptr_alloc(&(_radix)->tree, \ __genradix_idx_to_offset(_radix, _idx), \ - _gfp))) + NULL, _gfp))) + +#define genradix_ptr_alloc_preallocated_inlined(_radix, _idx, _new_node, _gfp)\ + (__genradix_cast(_radix) \ + (__genradix_ptr_inlined(&(_radix)->tree, \ + __genradix_idx_to_offset(_radix, _idx)) ?: \ + __genradix_ptr_alloc(&(_radix)->tree, \ + __genradix_idx_to_offset(_radix, _idx), \ + _new_node, _gfp))) /** * genradix_ptr_alloc - get a pointer to a genradix entry, allocating it @@ -232,7 +252,13 @@ void *__genradix_ptr_alloc(struct __genradix *, size_t, gfp_t); (__genradix_cast(_radix) \ __genradix_ptr_alloc(&(_radix)->tree, \ __genradix_idx_to_offset(_radix, _idx), \ - _gfp)) + NULL, _gfp)) + +#define genradix_ptr_alloc_preallocated(_radix, _idx, _new_node, _gfp)\ + (__genradix_cast(_radix) \ + __genradix_ptr_alloc(&(_radix)->tree, \ + __genradix_idx_to_offset(_radix, _idx), \ + _new_node, _gfp)) struct genradix_iter { size_t offset; diff --git a/lib/generic-radix-tree.c b/lib/generic-radix-tree.c index 4efae0663049..79e067b51488 100644 --- a/lib/generic-radix-tree.c +++ b/lib/generic-radix-tree.c @@ -15,27 +15,21 @@ void *__genradix_ptr(struct __genradix *radix, size_t offset) } EXPORT_SYMBOL(__genradix_ptr); -static inline struct genradix_node *genradix_alloc_node(gfp_t gfp_mask) -{ - return kzalloc(GENRADIX_NODE_SIZE, gfp_mask); -} - -static inline void genradix_free_node(struct genradix_node *node) -{ - kfree(node); -} - /* * Returns pointer to the specified byte @offset within @radix, allocating it if * necessary - newly allocated slots are always zeroed out: */ void *__genradix_ptr_alloc(struct __genradix *radix, size_t offset, + struct genradix_node **preallocated, gfp_t gfp_mask) { struct genradix_root *v = READ_ONCE(radix->root); struct genradix_node *n, *new_node = NULL; unsigned level; + if (preallocated) + swap(new_node, *preallocated); + /* Increase tree depth if necessary: */ while (1) { struct genradix_root *r = v, *new_root; @@ -219,7 +213,7 @@ int __genradix_prealloc(struct __genradix *radix, size_t size, size_t offset; for (offset = 0; offset < size; offset += GENRADIX_NODE_SIZE) - if (!__genradix_ptr_alloc(radix, offset, gfp_mask)) + if (!__genradix_ptr_alloc(radix, offset, NULL, gfp_mask)) return -ENOMEM; return 0; -- cgit v1.2.3 From f877f1d81b2ffcac341ff62ae076d7ad5ba83f46 Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Mon, 9 Sep 2024 23:00:18 +0900 Subject: firewire: core: use mutex to coordinate concurrent calls to flush completions In current implementation, test_and_set_bit_lock() is used to mediate concurrent calls of ohci_flush_iso_completions(). However, the ad-hoc usage of atomic operations is not preferable. This commit uses mutex_trylock() as the similar operations. The core function is responsible for the mediation, instead of 1394 OHCI driver. Link: https://lore.kernel.org/r/20240909140018.65289-3-o-takashi@sakamocchi.jp Signed-off-by: Takashi Sakamoto --- drivers/firewire/core-iso.c | 11 +++++++++-- drivers/firewire/ohci.c | 37 ++++++++++++++----------------------- include/linux/firewire.h | 1 + 3 files changed, 24 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/drivers/firewire/core-iso.c b/drivers/firewire/core-iso.c index 9f41c78878ad..1405d2e9cb2c 100644 --- a/drivers/firewire/core-iso.c +++ b/drivers/firewire/core-iso.c @@ -157,6 +157,7 @@ struct fw_iso_context *fw_iso_context_create(struct fw_card *card, ctx->callback.sc = callback; ctx->callback_data = callback_data; INIT_WORK(&ctx->work, flush_completions_work); + mutex_init(&ctx->flushing_completions_mutex); trace_isoc_outbound_allocate(ctx, channel, speed); trace_isoc_inbound_single_allocate(ctx, channel, header_size); @@ -173,6 +174,8 @@ void fw_iso_context_destroy(struct fw_iso_context *ctx) trace_isoc_inbound_multiple_destroy(ctx); ctx->card->driver->free_iso_context(ctx); + + mutex_destroy(&ctx->flushing_completions_mutex); } EXPORT_SYMBOL(fw_iso_context_destroy); @@ -226,7 +229,7 @@ EXPORT_SYMBOL(fw_iso_context_queue_flush); * to process the context asynchronously, fw_iso_context_schedule_flush_completions() is available * instead. * - * Context: Process context. + * Context: Process context due to mutex_trylock(). */ int fw_iso_context_flush_completions(struct fw_iso_context *ctx) { @@ -234,7 +237,11 @@ int fw_iso_context_flush_completions(struct fw_iso_context *ctx) trace_isoc_inbound_single_flush_completions(ctx); trace_isoc_inbound_multiple_flush_completions(ctx); - return ctx->card->driver->flush_iso_completions(ctx); + scoped_cond_guard(mutex_try, /* nothing to do */, &ctx->flushing_completions_mutex) { + return ctx->card->driver->flush_iso_completions(ctx); + } + + return 0; } EXPORT_SYMBOL(fw_iso_context_flush_completions); diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index 02ff0363d3ad..b182998a77f4 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -166,7 +166,6 @@ struct iso_context { struct context context; void *header; size_t header_length; - unsigned long flushing_completions; u32 mc_buffer_bus; u16 mc_completed; u16 last_timestamp; @@ -3579,31 +3578,23 @@ static void ohci_flush_queue_iso(struct fw_iso_context *base) static int ohci_flush_iso_completions(struct fw_iso_context *base) { struct iso_context *ctx = container_of(base, struct iso_context, base); - int ret = 0; - if (!test_and_set_bit_lock(0, &ctx->flushing_completions)) { - // Note that tasklet softIRQ is not used to process isochronous context anymore. - context_tasklet((unsigned long)&ctx->context); + // Note that tasklet softIRQ is not used to process isochronous context anymore. + context_tasklet((unsigned long)&ctx->context); - switch (base->type) { - case FW_ISO_CONTEXT_TRANSMIT: - case FW_ISO_CONTEXT_RECEIVE: - if (ctx->header_length != 0) - flush_iso_completions(ctx, FW_ISO_CONTEXT_COMPLETIONS_CAUSE_FLUSH); - break; - case FW_ISO_CONTEXT_RECEIVE_MULTICHANNEL: - if (ctx->mc_completed != 0) - flush_ir_buffer_fill(ctx); - break; - default: - ret = -ENOSYS; - } - - clear_bit_unlock(0, &ctx->flushing_completions); - smp_mb__after_atomic(); + switch (base->type) { + case FW_ISO_CONTEXT_TRANSMIT: + case FW_ISO_CONTEXT_RECEIVE: + if (ctx->header_length != 0) + flush_iso_completions(ctx, FW_ISO_CONTEXT_COMPLETIONS_CAUSE_FLUSH); + return 0; + case FW_ISO_CONTEXT_RECEIVE_MULTICHANNEL: + if (ctx->mc_completed != 0) + flush_ir_buffer_fill(ctx); + return 0; + default: + return -ENOSYS; } - - return ret; } static const struct fw_card_driver ohci_driver = { diff --git a/include/linux/firewire.h b/include/linux/firewire.h index f815d12deda0..19e8c5f9537c 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -512,6 +512,7 @@ union fw_iso_callback { struct fw_iso_context { struct fw_card *card; struct work_struct work; + struct mutex flushing_completions_mutex; int type; int channel; int speed; -- cgit v1.2.3 From 34c626c3004a73ee7da5072be48ddff9c2902902 Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Mon, 16 Jan 2023 01:16:43 +0200 Subject: net/mlx5: Added missing mlx5_ifc definition for HW Steering Add mlx5_ifc definitions that are required for HWS support. Note that due to change in the mlx5_ifc_flow_table_context_bits structure that now includes both SWS and HWS bits in a union, this patch also includes small change in one of SWS files that was required for compilation. Reviewed-by: Hamdan Agbariya Signed-off-by: Yevgeny Kliteynik Signed-off-by: Saeed Mahameed --- .../ethernet/mellanox/mlx5/core/steering/dr_cmd.c | 12 +- include/linux/mlx5/mlx5_ifc.h | 189 ++++++++++++++++++--- 2 files changed, 167 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c index 8c2a34a0d6be..baefb9a3fa05 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c @@ -251,9 +251,9 @@ int mlx5dr_cmd_query_flow_table(struct mlx5_core_dev *dev, output->level = MLX5_GET(query_flow_table_out, out, flow_table_context.level); output->sw_owner_icm_root_1 = MLX5_GET64(query_flow_table_out, out, - flow_table_context.sw_owner_icm_root_1); + flow_table_context.sws.sw_owner_icm_root_1); output->sw_owner_icm_root_0 = MLX5_GET64(query_flow_table_out, out, - flow_table_context.sw_owner_icm_root_0); + flow_table_context.sws.sw_owner_icm_root_0); return 0; } @@ -480,15 +480,15 @@ int mlx5dr_cmd_create_flow_table(struct mlx5_core_dev *mdev, */ if (attr->table_type == MLX5_FLOW_TABLE_TYPE_NIC_RX) { MLX5_SET64(flow_table_context, ft_mdev, - sw_owner_icm_root_0, attr->icm_addr_rx); + sws.sw_owner_icm_root_0, attr->icm_addr_rx); } else if (attr->table_type == MLX5_FLOW_TABLE_TYPE_NIC_TX) { MLX5_SET64(flow_table_context, ft_mdev, - sw_owner_icm_root_0, attr->icm_addr_tx); + sws.sw_owner_icm_root_0, attr->icm_addr_tx); } else if (attr->table_type == MLX5_FLOW_TABLE_TYPE_FDB) { MLX5_SET64(flow_table_context, ft_mdev, - sw_owner_icm_root_0, attr->icm_addr_rx); + sws.sw_owner_icm_root_0, attr->icm_addr_rx); MLX5_SET64(flow_table_context, ft_mdev, - sw_owner_icm_root_1, attr->icm_addr_tx); + sws.sw_owner_icm_root_1, attr->icm_addr_tx); } } diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 234ad6f16e92..b6f8e3834bd3 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -80,23 +80,15 @@ enum { enum { MLX5_OBJ_TYPE_SW_ICM = 0x0008, - MLX5_OBJ_TYPE_HEADER_MODIFY_ARGUMENT = 0x23, -}; - -enum { - MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM = (1ULL << MLX5_OBJ_TYPE_SW_ICM), - MLX5_GENERAL_OBJ_TYPES_CAP_GENEVE_TLV_OPT = (1ULL << 11), - MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q = (1ULL << 13), - MLX5_GENERAL_OBJ_TYPES_CAP_HEADER_MODIFY_ARGUMENT = - (1ULL << MLX5_OBJ_TYPE_HEADER_MODIFY_ARGUMENT), - MLX5_GENERAL_OBJ_TYPES_CAP_MACSEC_OFFLOAD = (1ULL << 39), -}; - -enum { MLX5_OBJ_TYPE_GENEVE_TLV_OPT = 0x000b, MLX5_OBJ_TYPE_VIRTIO_NET_Q = 0x000d, MLX5_OBJ_TYPE_VIRTIO_Q_COUNTERS = 0x001c, MLX5_OBJ_TYPE_MATCH_DEFINER = 0x0018, + MLX5_OBJ_TYPE_HEADER_MODIFY_ARGUMENT = 0x23, + MLX5_OBJ_TYPE_STC = 0x0040, + MLX5_OBJ_TYPE_RTC = 0x0041, + MLX5_OBJ_TYPE_STE = 0x0042, + MLX5_OBJ_TYPE_MODIFY_HDR_PATTERN = 0x0043, MLX5_OBJ_TYPE_PAGE_TRACK = 0x46, MLX5_OBJ_TYPE_MKEY = 0xff01, MLX5_OBJ_TYPE_QP = 0xff02, @@ -112,6 +104,16 @@ enum { MLX5_OBJ_TYPE_RQT = 0xff0e, MLX5_OBJ_TYPE_FLOW_COUNTER = 0xff0f, MLX5_OBJ_TYPE_CQ = 0xff10, + MLX5_OBJ_TYPE_FT_ALIAS = 0xff15, +}; + +enum { + MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM = (1ULL << MLX5_OBJ_TYPE_SW_ICM), + MLX5_GENERAL_OBJ_TYPES_CAP_GENEVE_TLV_OPT = (1ULL << 11), + MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q = (1ULL << 13), + MLX5_GENERAL_OBJ_TYPES_CAP_HEADER_MODIFY_ARGUMENT = + (1ULL << MLX5_OBJ_TYPE_HEADER_MODIFY_ARGUMENT), + MLX5_GENERAL_OBJ_TYPES_CAP_MACSEC_OFFLOAD = (1ULL << 39), }; enum { @@ -313,6 +315,7 @@ enum { MLX5_CMD_OP_MODIFY_VHCA_STATE = 0xb0e, MLX5_CMD_OP_SYNC_CRYPTO = 0xb12, MLX5_CMD_OP_ALLOW_OTHER_VHCA_ACCESS = 0xb16, + MLX5_CMD_OP_GENERATE_WQE = 0xb17, MLX5_CMD_OP_MAX }; @@ -485,7 +488,13 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 reserved_at_66[0x2]; u8 reformat_add_macsec[0x1]; u8 reformat_remove_macsec[0x1]; - u8 reserved_at_6a[0xe]; + u8 reparse[0x1]; + u8 reserved_at_6b[0x1]; + u8 cross_vhca_object[0x1]; + u8 reformat_l2_to_l3_audp_tunnel[0x1]; + u8 reformat_l3_audp_tunnel_to_l2[0x1]; + u8 ignore_flow_level_rtc_valid[0x1]; + u8 reserved_at_70[0x8]; u8 log_max_ft_num[0x8]; u8 reserved_at_80[0x10]; @@ -522,7 +531,15 @@ struct mlx5_ifc_ipv6_layout_bits { u8 ipv6[16][0x8]; }; +struct mlx5_ifc_ipv6_simple_layout_bits { + u8 ipv6_127_96[0x20]; + u8 ipv6_95_64[0x20]; + u8 ipv6_63_32[0x20]; + u8 ipv6_31_0[0x20]; +}; + union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits { + struct mlx5_ifc_ipv6_simple_layout_bits ipv6_simple_layout; struct mlx5_ifc_ipv6_layout_bits ipv6_layout; struct mlx5_ifc_ipv4_layout_bits ipv4_layout; u8 reserved_at_0[0x80]; @@ -911,7 +928,9 @@ struct mlx5_ifc_flow_table_eswitch_cap_bits { u8 reserved_at_8[0x5]; u8 fdb_uplink_hairpin[0x1]; u8 fdb_multi_path_any_table_limit_regc[0x1]; - u8 reserved_at_f[0x3]; + u8 reserved_at_f[0x1]; + u8 fdb_dynamic_tunnel[0x1]; + u8 reserved_at_11[0x1]; u8 fdb_multi_path_any_table[0x1]; u8 reserved_at_13[0x2]; u8 fdb_modify_header_fwd_to_table[0x1]; @@ -950,6 +969,73 @@ struct mlx5_ifc_flow_table_eswitch_cap_bits { u8 reserved_at_1900[0x6700]; }; +struct mlx5_ifc_wqe_based_flow_table_cap_bits { + u8 reserved_at_0[0x3]; + u8 log_max_num_ste[0x5]; + u8 reserved_at_8[0x3]; + u8 log_max_num_stc[0x5]; + u8 reserved_at_10[0x3]; + u8 log_max_num_rtc[0x5]; + u8 reserved_at_18[0x3]; + u8 log_max_num_header_modify_pattern[0x5]; + + u8 rtc_hash_split_table[0x1]; + u8 rtc_linear_lookup_table[0x1]; + u8 reserved_at_22[0x1]; + u8 stc_alloc_log_granularity[0x5]; + u8 reserved_at_28[0x3]; + u8 stc_alloc_log_max[0x5]; + u8 reserved_at_30[0x3]; + u8 ste_alloc_log_granularity[0x5]; + u8 reserved_at_38[0x3]; + u8 ste_alloc_log_max[0x5]; + + u8 reserved_at_40[0xb]; + u8 rtc_reparse_mode[0x5]; + u8 reserved_at_50[0x3]; + u8 rtc_index_mode[0x5]; + u8 reserved_at_58[0x3]; + u8 rtc_log_depth_max[0x5]; + + u8 reserved_at_60[0x10]; + u8 ste_format[0x10]; + + u8 stc_action_type[0x80]; + + u8 header_insert_type[0x10]; + u8 header_remove_type[0x10]; + + u8 trivial_match_definer[0x20]; + + u8 reserved_at_140[0x1b]; + u8 rtc_max_num_hash_definer_gen_wqe[0x5]; + + u8 reserved_at_160[0x18]; + u8 access_index_mode[0x8]; + + u8 reserved_at_180[0x10]; + u8 ste_format_gen_wqe[0x10]; + + u8 linear_match_definer_reg_c3[0x20]; + + u8 fdb_jump_to_tir_stc[0x1]; + u8 reserved_at_1c1[0x1f]; +}; + +struct mlx5_ifc_esw_cap_bits { + u8 reserved_at_0[0x1d]; + u8 merged_eswitch[0x1]; + u8 reserved_at_1e[0x2]; + + u8 reserved_at_20[0x40]; + + u8 esw_manager_vport_number_valid[0x1]; + u8 reserved_at_61[0xf]; + u8 esw_manager_vport_number[0x10]; + + u8 reserved_at_80[0x780]; +}; + enum { MLX5_COUNTER_SOURCE_ESWITCH = 0x0, MLX5_COUNTER_FLOW_ESWITCH = 0x1, @@ -1443,9 +1529,13 @@ enum { }; enum { + MLX5_FLEX_IPV4_OVER_VXLAN_ENABLED = 1 << 0, + MLX5_FLEX_IPV6_OVER_VXLAN_ENABLED = 1 << 1, + MLX5_FLEX_IPV6_OVER_IP_ENABLED = 1 << 2, MLX5_FLEX_PARSER_GENEVE_ENABLED = 1 << 3, MLX5_FLEX_PARSER_MPLS_OVER_GRE_ENABLED = 1 << 4, MLX5_FLEX_PARSER_MPLS_OVER_UDP_ENABLED = 1 << 5, + MLX5_FLEX_P_BIT_VXLAN_GPE_ENABLED = 1 << 6, MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED = 1 << 7, MLX5_FLEX_PARSER_ICMP_V4_ENABLED = 1 << 8, MLX5_FLEX_PARSER_ICMP_V6_ENABLED = 1 << 9, @@ -1650,7 +1740,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 pci_sync_for_fw_update_event[0x1]; u8 reserved_at_1f2[0x6]; u8 init2_lag_tx_port_affinity[0x1]; - u8 reserved_at_1fa[0x3]; + u8 reserved_at_1fa[0x2]; + u8 wqe_based_flow_table_update_cap[0x1]; u8 cqe_version[0x4]; u8 compact_address_vector[0x1]; @@ -1959,7 +2050,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_760[0x3]; u8 log_max_num_header_modify_argument[0x5]; - u8 reserved_at_768[0x4]; + u8 log_header_modify_argument_granularity_offset[0x4]; u8 log_header_modify_argument_granularity[0x4]; u8 reserved_at_770[0x3]; u8 log_header_modify_argument_max_alloc[0x5]; @@ -2006,7 +2097,8 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 reserved_at_140[0x60]; u8 flow_table_type_2_type[0x8]; - u8 reserved_at_1a8[0x3]; + u8 reserved_at_1a8[0x2]; + u8 format_select_dw_8_6_ext[0x1]; u8 log_min_mkey_entity_size[0x5]; u8 reserved_at_1b0[0x10]; @@ -2022,6 +2114,16 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 reserved_at_250[0x10]; u8 reserved_at_260[0x120]; + + u8 format_select_dw_gtpu_dw_0[0x8]; + u8 format_select_dw_gtpu_dw_1[0x8]; + u8 format_select_dw_gtpu_dw_2[0x8]; + u8 format_select_dw_gtpu_first_ext_dw_0[0x8]; + + u8 generate_wqe_type[0x20]; + + u8 reserved_at_2c0[0xc0]; + u8 reserved_at_380[0xb]; u8 min_mkey_log_entity_size_fixed_buffer[0x5]; u8 ec_vf_vport_base[0x10]; @@ -2037,9 +2139,11 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 reserved_at_400[0x1]; u8 min_mkey_log_entity_size_fixed_buffer_valid[0x1]; - u8 reserved_at_402[0x1e]; + u8 reserved_at_402[0xe]; + u8 return_reg_id[0x10]; - u8 reserved_at_420[0x20]; + u8 reserved_at_420[0x1c]; + u8 flow_table_hash_type[0x4]; u8 reserved_at_440[0x8]; u8 max_num_eqs_24b[0x18]; @@ -2086,7 +2190,7 @@ struct mlx5_ifc_extended_dest_format_bits { u8 reserved_at_60[0x20]; }; -union mlx5_ifc_dest_format_struct_flow_counter_list_auto_bits { +union mlx5_ifc_dest_format_flow_counter_list_auto_bits { struct mlx5_ifc_extended_dest_format_bits extended_dest_format; struct mlx5_ifc_flow_counter_list_bits flow_counter_list; }; @@ -2178,7 +2282,10 @@ struct mlx5_ifc_wq_bits { u8 reserved_at_139[0x4]; u8 log_wqe_stride_size[0x3]; - u8 reserved_at_140[0x80]; + u8 dbr_umem_id[0x20]; + u8 wq_umem_id[0x20]; + + u8 wq_umem_offset[0x40]; u8 headers_mkey[0x20]; @@ -3562,6 +3669,8 @@ union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_per_protocol_networking_offload_caps_bits per_protocol_networking_offload_caps; struct mlx5_ifc_flow_table_nic_cap_bits flow_table_nic_cap; struct mlx5_ifc_flow_table_eswitch_cap_bits flow_table_eswitch_cap; + struct mlx5_ifc_wqe_based_flow_table_cap_bits wqe_based_flow_table_cap; + struct mlx5_ifc_esw_cap_bits esw_cap; struct mlx5_ifc_e_switch_cap_bits e_switch_cap; struct mlx5_ifc_port_selection_cap_bits port_selection_cap; struct mlx5_ifc_qos_cap_bits qos_cap; @@ -3678,7 +3787,7 @@ struct mlx5_ifc_flow_context_bits { u8 reserved_at_1300[0x500]; - union mlx5_ifc_dest_format_struct_flow_counter_list_auto_bits destination[]; + union mlx5_ifc_dest_format_flow_counter_list_auto_bits destination[]; }; enum { @@ -3919,7 +4028,8 @@ struct mlx5_ifc_sqc_bits { u8 reg_umr[0x1]; u8 allow_swp[0x1]; u8 hairpin[0x1]; - u8 reserved_at_f[0xb]; + u8 non_wire[0x1]; + u8 reserved_at_10[0xa]; u8 ts_format[0x2]; u8 reserved_at_1c[0x4]; @@ -4961,6 +5071,16 @@ struct mlx5_ifc_set_fte_in_bits { struct mlx5_ifc_flow_context_bits flow_context; }; +struct mlx5_ifc_dest_format_bits { + u8 destination_type[0x8]; + u8 destination_id[0x18]; + + u8 destination_eswitch_owner_vhca_id_valid[0x1]; + u8 packet_reformat[0x1]; + u8 reserved_at_22[0xe]; + u8 destination_eswitch_owner_vhca_id[0x10]; +}; + struct mlx5_ifc_rts2rts_qp_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -6127,7 +6247,8 @@ struct mlx5_ifc_flow_table_context_bits { u8 termination_table[0x1]; u8 table_miss_action[0x4]; u8 level[0x8]; - u8 reserved_at_10[0x8]; + u8 rtc_valid[0x1]; + u8 reserved_at_11[0x7]; u8 log_size[0x8]; u8 reserved_at_20[0x8]; @@ -6137,11 +6258,21 @@ struct mlx5_ifc_flow_table_context_bits { u8 lag_master_next_table_id[0x18]; u8 reserved_at_60[0x60]; + union { + struct { + u8 sw_owner_icm_root_1[0x40]; + + u8 sw_owner_icm_root_0[0x40]; + } sws; + struct { + u8 rtc_id_0[0x20]; - u8 sw_owner_icm_root_1[0x40]; + u8 rtc_id_1[0x20]; - u8 sw_owner_icm_root_0[0x40]; + u8 reserved_at_100[0x40]; + } hws; + }; }; struct mlx5_ifc_query_flow_table_out_bits { @@ -8923,7 +9054,9 @@ struct mlx5_ifc_create_qp_in_bits { struct mlx5_ifc_qpc_bits qpc; - u8 reserved_at_800[0x60]; + u8 wq_umem_offset[0x40]; + + u8 wq_umem_id[0x20]; u8 wq_umem_valid[0x1]; u8 reserved_at_861[0x1f]; -- cgit v1.2.3 From 00b9f0daefd7670356e592d418c890acf9179c94 Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Tue, 17 Jan 2023 17:14:51 +0200 Subject: net/mlx5: Added missing definitions in preparation for HW Steering As part of preparation for HWS, added missing definitions in qp.h and fs_core.h: - FS_FT_FDB_RX/TX table types that are used by HWS in addition to an existing FS_FT_FDB - MLX5_WQE_CTRL_INITIATOR_SMALL_FENCE that is used by HWS to require fence in WQE Reviewed-by: Hamdan Agbariya Signed-off-by: Yevgeny Kliteynik Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.h | 8 ++++++-- include/linux/mlx5/qp.h | 1 + 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 78eb6b7097e1..6201647d6156 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -110,7 +110,9 @@ enum fs_flow_table_type { FS_FT_RDMA_RX = 0X7, FS_FT_RDMA_TX = 0X8, FS_FT_PORT_SEL = 0X9, - FS_FT_MAX_TYPE = FS_FT_PORT_SEL, + FS_FT_FDB_RX = 0xa, + FS_FT_FDB_TX = 0xb, + FS_FT_MAX_TYPE = FS_FT_FDB_TX, }; enum fs_flow_table_op_mod { @@ -368,7 +370,9 @@ struct mlx5_flow_root_namespace *find_root(struct fs_node *node); (type == FS_FT_RDMA_RX) ? MLX5_CAP_FLOWTABLE_RDMA_RX(mdev, cap) : \ (type == FS_FT_RDMA_TX) ? MLX5_CAP_FLOWTABLE_RDMA_TX(mdev, cap) : \ (type == FS_FT_PORT_SEL) ? MLX5_CAP_FLOWTABLE_PORT_SELECTION(mdev, cap) : \ - (BUILD_BUG_ON_ZERO(FS_FT_PORT_SEL != FS_FT_MAX_TYPE))\ + (type == FS_FT_FDB_RX) ? MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) : \ + (type == FS_FT_FDB_TX) ? MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) : \ + (BUILD_BUG_ON_ZERO(FS_FT_FDB_TX != FS_FT_MAX_TYPE))\ ) #endif diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index ad1ce650146c..fc7eeff99a8a 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -149,6 +149,7 @@ enum { MLX5_WQE_CTRL_CQ_UPDATE = 2 << 2, MLX5_WQE_CTRL_CQ_UPDATE_AND_EQE = 3 << 2, MLX5_WQE_CTRL_SOLICITED = 1 << 1, + MLX5_WQE_CTRL_INITIATOR_SMALL_FENCE = 1 << 5, }; enum { -- cgit v1.2.3 From 452ef7f86036392005940de54228d42ca0044192 Mon Sep 17 00:00:00 2001 From: Carolina Jubran Date: Mon, 5 Aug 2024 10:03:20 +0300 Subject: net/mlx5: Add missing masks and QoS bit masks for scheduling elements Add the missing masks for supported element types and Transmit Scheduling Arbiter (TSAR) types in scheduling elements. Also, add the corresponding bit masks for these types in the QoS capabilities of a NIC scheduler. Fixes: 214baf22870c ("net/mlx5e: Support HTB offload") Signed-off-by: Carolina Jubran Reviewed-by: Cosmin Ratiu Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index cab228cf51c6..cfdf984a95a8 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1027,7 +1027,8 @@ struct mlx5_ifc_qos_cap_bits { u8 max_tsar_bw_share[0x20]; - u8 reserved_at_100[0x20]; + u8 nic_element_type[0x10]; + u8 nic_tsar_type[0x10]; u8 reserved_at_120[0x3]; u8 log_meter_aso_granularity[0x5]; @@ -3966,6 +3967,7 @@ enum { ELEMENT_TYPE_CAP_MASK_VPORT = 1 << 1, ELEMENT_TYPE_CAP_MASK_VPORT_TC = 1 << 2, ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC = 1 << 3, + ELEMENT_TYPE_CAP_MASK_QUEUE_GROUP = 1 << 4, }; struct mlx5_ifc_scheduling_context_bits { @@ -4675,6 +4677,12 @@ enum { TSAR_ELEMENT_TSAR_TYPE_ETS = 0x2, }; +enum { + TSAR_TYPE_CAP_MASK_DWRR = 1 << 0, + TSAR_TYPE_CAP_MASK_ROUND_ROBIN = 1 << 1, + TSAR_TYPE_CAP_MASK_ETS = 1 << 2, +}; + struct mlx5_ifc_tsar_element_bits { u8 reserved_at_0[0x8]; u8 tsar_type[0x8]; -- cgit v1.2.3 From 3dc95a3edd0a86b4a59670b3fafcc64c7d83e2e7 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Wed, 4 Sep 2024 17:47:45 +0200 Subject: netdevice: add netdev_tx_reset_subqueue() shorthand Add a shorthand similar to other net*_subqueue() helpers for resetting the queue by its index w/o obtaining &netdev_tx_queue beforehand manually. Reviewed-by: Przemek Kitszel Signed-off-by: Alexander Lobakin Signed-off-by: Tony Nguyen --- include/linux/netdevice.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b47c00657bd0..44d1dbb54ffe 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3568,6 +3568,17 @@ static inline void netdev_tx_reset_queue(struct netdev_queue *q) #endif } +/** + * netdev_tx_reset_subqueue - reset the BQL stats and state of a netdev queue + * @dev: network device + * @qid: stack index of the queue to reset + */ +static inline void netdev_tx_reset_subqueue(const struct net_device *dev, + u32 qid) +{ + netdev_tx_reset_queue(netdev_get_tx_queue(dev, qid)); +} + /** * netdev_reset_queue - reset the packets and bytes count of a network device * @dev_queue: network device @@ -3577,7 +3588,7 @@ static inline void netdev_tx_reset_queue(struct netdev_queue *q) */ static inline void netdev_reset_queue(struct net_device *dev_queue) { - netdev_tx_reset_queue(netdev_get_tx_queue(dev_queue, 0)); + netdev_tx_reset_subqueue(dev_queue, 0); } /** -- cgit v1.2.3 From 40a895fd9a358eea16901026360bd2cd3ca691a7 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Thu, 5 Sep 2024 15:35:45 -0700 Subject: cxl: move cxl headers to new include/cxl/ directory Group all cxl related kernel headers into include/cxl/ directory. Reviewed-by: Alison Schofield Reviewed-by: Ira Weiny Link: https://patch.msgid.link/20240905223711.1990186-2-dave.jiang@intel.com Signed-off-by: Dave Jiang --- MAINTAINERS | 3 +- drivers/acpi/apei/einj-cxl.c | 2 +- drivers/acpi/apei/ghes.c | 2 +- drivers/cxl/core/port.c | 2 +- drivers/cxl/cxlmem.h | 2 +- include/cxl/einj.h | 44 +++++++++++ include/cxl/event.h | 175 +++++++++++++++++++++++++++++++++++++++++++ include/linux/cxl-event.h | 175 ------------------------------------------- include/linux/einj-cxl.h | 44 ----------- 9 files changed, 224 insertions(+), 225 deletions(-) create mode 100644 include/cxl/einj.h create mode 100644 include/cxl/event.h delete mode 100644 include/linux/cxl-event.h delete mode 100644 include/linux/einj-cxl.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index fe83ba7194ea..df59354af438 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5620,8 +5620,7 @@ L: linux-cxl@vger.kernel.org S: Maintained F: Documentation/driver-api/cxl F: drivers/cxl/ -F: include/linux/einj-cxl.h -F: include/linux/cxl-event.h +F: include/cxl/ F: include/uapi/linux/cxl_mem.h F: tools/testing/cxl/ diff --git a/drivers/acpi/apei/einj-cxl.c b/drivers/acpi/apei/einj-cxl.c index 8b8be0c90709..4f81a119ec08 100644 --- a/drivers/acpi/apei/einj-cxl.c +++ b/drivers/acpi/apei/einj-cxl.c @@ -7,9 +7,9 @@ * * Author: Ben Cheatham */ -#include #include #include +#include #include "apei-internal.h" diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 623cc0cb4a65..ada93cfde9ba 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -27,7 +27,6 @@ #include #include #include -#include #include #include #include @@ -50,6 +49,7 @@ #include #include #include +#include #include #include "apei-internal.h" diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index 7ca57285a7b7..a5e6f3d23cfb 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -3,7 +3,6 @@ #include #include #include -#include #include #include #include @@ -11,6 +10,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index afb53d058d62..a81a8982bf93 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -6,8 +6,8 @@ #include #include #include -#include #include +#include #include "cxl.h" /* CXL 2.0 8.2.8.5.1.1 Memory Device Status Register */ diff --git a/include/cxl/einj.h b/include/cxl/einj.h new file mode 100644 index 000000000000..624ff6ff41f9 --- /dev/null +++ b/include/cxl/einj.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * CXL protocol Error INJection support. + * + * Copyright (c) 2023 Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Ben Cheatham + */ +#ifndef EINJ_CXL_H +#define EINJ_CXL_H + +#include +#include + +struct pci_dev; +struct seq_file; + +#if IS_ENABLED(CONFIG_ACPI_APEI_EINJ_CXL) +int einj_cxl_available_error_type_show(struct seq_file *m, void *v); +int einj_cxl_inject_error(struct pci_dev *dport_dev, u64 type); +int einj_cxl_inject_rch_error(u64 rcrb, u64 type); +bool einj_cxl_is_initialized(void); +#else /* !IS_ENABLED(CONFIG_ACPI_APEI_EINJ_CXL) */ +static inline int einj_cxl_available_error_type_show(struct seq_file *m, + void *v) +{ + return -ENXIO; +} + +static inline int einj_cxl_inject_error(struct pci_dev *dport_dev, u64 type) +{ + return -ENXIO; +} + +static inline int einj_cxl_inject_rch_error(u64 rcrb, u64 type) +{ + return -ENXIO; +} + +static inline bool einj_cxl_is_initialized(void) { return false; } +#endif /* CONFIG_ACPI_APEI_EINJ_CXL */ + +#endif /* EINJ_CXL_H */ diff --git a/include/cxl/event.h b/include/cxl/event.h new file mode 100644 index 000000000000..0bea1afbd747 --- /dev/null +++ b/include/cxl/event.h @@ -0,0 +1,175 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2023 Intel Corporation. */ +#ifndef _LINUX_CXL_EVENT_H +#define _LINUX_CXL_EVENT_H + +#include +#include +#include + +/* + * Common Event Record Format + * CXL rev 3.0 section 8.2.9.2.1; Table 8-42 + */ +struct cxl_event_record_hdr { + u8 length; + u8 flags[3]; + __le16 handle; + __le16 related_handle; + __le64 timestamp; + u8 maint_op_class; + u8 reserved[15]; +} __packed; + +struct cxl_event_media_hdr { + struct cxl_event_record_hdr hdr; + __le64 phys_addr; + u8 descriptor; + u8 type; + u8 transaction_type; + /* + * The meaning of Validity Flags from bit 2 is + * different across DRAM and General Media records + */ + u8 validity_flags[2]; + u8 channel; + u8 rank; +} __packed; + +#define CXL_EVENT_RECORD_DATA_LENGTH 0x50 +struct cxl_event_generic { + struct cxl_event_record_hdr hdr; + u8 data[CXL_EVENT_RECORD_DATA_LENGTH]; +} __packed; + +/* + * General Media Event Record + * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43 + */ +#define CXL_EVENT_GEN_MED_COMP_ID_SIZE 0x10 +struct cxl_event_gen_media { + struct cxl_event_media_hdr media_hdr; + u8 device[3]; + u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE]; + u8 reserved[46]; +} __packed; + +/* + * DRAM Event Record - DER + * CXL rev 3.0 section 8.2.9.2.1.2; Table 3-44 + */ +#define CXL_EVENT_DER_CORRECTION_MASK_SIZE 0x20 +struct cxl_event_dram { + struct cxl_event_media_hdr media_hdr; + u8 nibble_mask[3]; + u8 bank_group; + u8 bank; + u8 row[3]; + u8 column[2]; + u8 correction_mask[CXL_EVENT_DER_CORRECTION_MASK_SIZE]; + u8 reserved[0x17]; +} __packed; + +/* + * Get Health Info Record + * CXL rev 3.0 section 8.2.9.8.3.1; Table 8-100 + */ +struct cxl_get_health_info { + u8 health_status; + u8 media_status; + u8 add_status; + u8 life_used; + u8 device_temp[2]; + u8 dirty_shutdown_cnt[4]; + u8 cor_vol_err_cnt[4]; + u8 cor_per_err_cnt[4]; +} __packed; + +/* + * Memory Module Event Record + * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45 + */ +struct cxl_event_mem_module { + struct cxl_event_record_hdr hdr; + u8 event_type; + struct cxl_get_health_info info; + u8 reserved[0x3d]; +} __packed; + +union cxl_event { + struct cxl_event_generic generic; + struct cxl_event_gen_media gen_media; + struct cxl_event_dram dram; + struct cxl_event_mem_module mem_module; + /* dram & gen_media event header */ + struct cxl_event_media_hdr media_hdr; +} __packed; + +/* + * Common Event Record Format; in event logs + * CXL rev 3.0 section 8.2.9.2.1; Table 8-42 + */ +struct cxl_event_record_raw { + uuid_t id; + union cxl_event event; +} __packed; + +enum cxl_event_type { + CXL_CPER_EVENT_GENERIC, + CXL_CPER_EVENT_GEN_MEDIA, + CXL_CPER_EVENT_DRAM, + CXL_CPER_EVENT_MEM_MODULE, +}; + +#define CPER_CXL_DEVICE_ID_VALID BIT(0) +#define CPER_CXL_DEVICE_SN_VALID BIT(1) +#define CPER_CXL_COMP_EVENT_LOG_VALID BIT(2) +struct cxl_cper_event_rec { + struct { + u32 length; + u64 validation_bits; + struct cper_cxl_event_devid { + u16 vendor_id; + u16 device_id; + u8 func_num; + u8 device_num; + u8 bus_num; + u16 segment_num; + u16 slot_num; /* bits 2:0 reserved */ + u8 reserved; + } __packed device_id; + struct cper_cxl_event_sn { + u32 lower_dw; + u32 upper_dw; + } __packed dev_serial_num; + } __packed hdr; + + union cxl_event event; +} __packed; + +struct cxl_cper_work_data { + enum cxl_event_type event_type; + struct cxl_cper_event_rec rec; +}; + +#ifdef CONFIG_ACPI_APEI_GHES +int cxl_cper_register_work(struct work_struct *work); +int cxl_cper_unregister_work(struct work_struct *work); +int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd); +#else +static inline int cxl_cper_register_work(struct work_struct *work) +{ + return 0; +} + +static inline int cxl_cper_unregister_work(struct work_struct *work) +{ + return 0; +} +static inline int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd) +{ + return 0; +} +#endif + +#endif /* _LINUX_CXL_EVENT_H */ diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h deleted file mode 100644 index 0bea1afbd747..000000000000 --- a/include/linux/cxl-event.h +++ /dev/null @@ -1,175 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2023 Intel Corporation. */ -#ifndef _LINUX_CXL_EVENT_H -#define _LINUX_CXL_EVENT_H - -#include -#include -#include - -/* - * Common Event Record Format - * CXL rev 3.0 section 8.2.9.2.1; Table 8-42 - */ -struct cxl_event_record_hdr { - u8 length; - u8 flags[3]; - __le16 handle; - __le16 related_handle; - __le64 timestamp; - u8 maint_op_class; - u8 reserved[15]; -} __packed; - -struct cxl_event_media_hdr { - struct cxl_event_record_hdr hdr; - __le64 phys_addr; - u8 descriptor; - u8 type; - u8 transaction_type; - /* - * The meaning of Validity Flags from bit 2 is - * different across DRAM and General Media records - */ - u8 validity_flags[2]; - u8 channel; - u8 rank; -} __packed; - -#define CXL_EVENT_RECORD_DATA_LENGTH 0x50 -struct cxl_event_generic { - struct cxl_event_record_hdr hdr; - u8 data[CXL_EVENT_RECORD_DATA_LENGTH]; -} __packed; - -/* - * General Media Event Record - * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43 - */ -#define CXL_EVENT_GEN_MED_COMP_ID_SIZE 0x10 -struct cxl_event_gen_media { - struct cxl_event_media_hdr media_hdr; - u8 device[3]; - u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE]; - u8 reserved[46]; -} __packed; - -/* - * DRAM Event Record - DER - * CXL rev 3.0 section 8.2.9.2.1.2; Table 3-44 - */ -#define CXL_EVENT_DER_CORRECTION_MASK_SIZE 0x20 -struct cxl_event_dram { - struct cxl_event_media_hdr media_hdr; - u8 nibble_mask[3]; - u8 bank_group; - u8 bank; - u8 row[3]; - u8 column[2]; - u8 correction_mask[CXL_EVENT_DER_CORRECTION_MASK_SIZE]; - u8 reserved[0x17]; -} __packed; - -/* - * Get Health Info Record - * CXL rev 3.0 section 8.2.9.8.3.1; Table 8-100 - */ -struct cxl_get_health_info { - u8 health_status; - u8 media_status; - u8 add_status; - u8 life_used; - u8 device_temp[2]; - u8 dirty_shutdown_cnt[4]; - u8 cor_vol_err_cnt[4]; - u8 cor_per_err_cnt[4]; -} __packed; - -/* - * Memory Module Event Record - * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45 - */ -struct cxl_event_mem_module { - struct cxl_event_record_hdr hdr; - u8 event_type; - struct cxl_get_health_info info; - u8 reserved[0x3d]; -} __packed; - -union cxl_event { - struct cxl_event_generic generic; - struct cxl_event_gen_media gen_media; - struct cxl_event_dram dram; - struct cxl_event_mem_module mem_module; - /* dram & gen_media event header */ - struct cxl_event_media_hdr media_hdr; -} __packed; - -/* - * Common Event Record Format; in event logs - * CXL rev 3.0 section 8.2.9.2.1; Table 8-42 - */ -struct cxl_event_record_raw { - uuid_t id; - union cxl_event event; -} __packed; - -enum cxl_event_type { - CXL_CPER_EVENT_GENERIC, - CXL_CPER_EVENT_GEN_MEDIA, - CXL_CPER_EVENT_DRAM, - CXL_CPER_EVENT_MEM_MODULE, -}; - -#define CPER_CXL_DEVICE_ID_VALID BIT(0) -#define CPER_CXL_DEVICE_SN_VALID BIT(1) -#define CPER_CXL_COMP_EVENT_LOG_VALID BIT(2) -struct cxl_cper_event_rec { - struct { - u32 length; - u64 validation_bits; - struct cper_cxl_event_devid { - u16 vendor_id; - u16 device_id; - u8 func_num; - u8 device_num; - u8 bus_num; - u16 segment_num; - u16 slot_num; /* bits 2:0 reserved */ - u8 reserved; - } __packed device_id; - struct cper_cxl_event_sn { - u32 lower_dw; - u32 upper_dw; - } __packed dev_serial_num; - } __packed hdr; - - union cxl_event event; -} __packed; - -struct cxl_cper_work_data { - enum cxl_event_type event_type; - struct cxl_cper_event_rec rec; -}; - -#ifdef CONFIG_ACPI_APEI_GHES -int cxl_cper_register_work(struct work_struct *work); -int cxl_cper_unregister_work(struct work_struct *work); -int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd); -#else -static inline int cxl_cper_register_work(struct work_struct *work) -{ - return 0; -} - -static inline int cxl_cper_unregister_work(struct work_struct *work) -{ - return 0; -} -static inline int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd) -{ - return 0; -} -#endif - -#endif /* _LINUX_CXL_EVENT_H */ diff --git a/include/linux/einj-cxl.h b/include/linux/einj-cxl.h deleted file mode 100644 index 624ff6ff41f9..000000000000 --- a/include/linux/einj-cxl.h +++ /dev/null @@ -1,44 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * CXL protocol Error INJection support. - * - * Copyright (c) 2023 Advanced Micro Devices, Inc. - * All Rights Reserved. - * - * Author: Ben Cheatham - */ -#ifndef EINJ_CXL_H -#define EINJ_CXL_H - -#include -#include - -struct pci_dev; -struct seq_file; - -#if IS_ENABLED(CONFIG_ACPI_APEI_EINJ_CXL) -int einj_cxl_available_error_type_show(struct seq_file *m, void *v); -int einj_cxl_inject_error(struct pci_dev *dport_dev, u64 type); -int einj_cxl_inject_rch_error(u64 rcrb, u64 type); -bool einj_cxl_is_initialized(void); -#else /* !IS_ENABLED(CONFIG_ACPI_APEI_EINJ_CXL) */ -static inline int einj_cxl_available_error_type_show(struct seq_file *m, - void *v) -{ - return -ENXIO; -} - -static inline int einj_cxl_inject_error(struct pci_dev *dport_dev, u64 type) -{ - return -ENXIO; -} - -static inline int einj_cxl_inject_rch_error(u64 rcrb, u64 type) -{ - return -ENXIO; -} - -static inline bool einj_cxl_is_initialized(void) { return false; } -#endif /* CONFIG_ACPI_APEI_EINJ_CXL */ - -#endif /* EINJ_CXL_H */ -- cgit v1.2.3 From 246d3aa3e53151fa150f10257ddd8a4facd31a6a Mon Sep 17 00:00:00 2001 From: Ryan Roberts Date: Thu, 8 Aug 2024 12:18:46 +0100 Subject: mm: cleanup count_mthp_stat() definition Patch series "Shmem mTHP controls and stats improvements", v3. This is a small series to tidy up the way the shmem controls and stats are exposed. These patches were previously part of the series at [2], but I decided to split them out since they can go in independently. This patch (of 2): Let's move count_mthp_stat() so that it's always defined, even when THP is disabled. Previously uses of the function in files such as shmem.c, which are compiled even when THP is disabled, required ugly THP ifdeferry. With this cleanup, we can remove those ifdefs and the function resolves to a nop when THP is disabled. I shortly plan to call count_mthp_stat() from more THP-invariant source files. Link: https://lkml.kernel.org/r/20240808111849.651867-1-ryan.roberts@arm.com Link: https://lkml.kernel.org/r/20240808111849.651867-2-ryan.roberts@arm.com Signed-off-by: Ryan Roberts Acked-by: Barry Song Reviewed-by: Baolin Wang Reviewed-by: Lance Yang Acked-by: David Hildenbrand Cc: Gavin Shan Cc: Hugh Dickins Cc: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/huge_mm.h | 70 ++++++++++++++++++++++++------------------------- mm/memory.c | 2 -- mm/shmem.c | 6 ----- 3 files changed, 35 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 6370026689e0..4c32058cacfe 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -114,6 +114,41 @@ extern struct kobj_attribute thpsize_shmem_enabled_attr; #define HPAGE_PUD_MASK (~(HPAGE_PUD_SIZE - 1)) #define HPAGE_PUD_SIZE ((1UL) << HPAGE_PUD_SHIFT) +enum mthp_stat_item { + MTHP_STAT_ANON_FAULT_ALLOC, + MTHP_STAT_ANON_FAULT_FALLBACK, + MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE, + MTHP_STAT_SWPOUT, + MTHP_STAT_SWPOUT_FALLBACK, + MTHP_STAT_SHMEM_ALLOC, + MTHP_STAT_SHMEM_FALLBACK, + MTHP_STAT_SHMEM_FALLBACK_CHARGE, + MTHP_STAT_SPLIT, + MTHP_STAT_SPLIT_FAILED, + MTHP_STAT_SPLIT_DEFERRED, + __MTHP_STAT_COUNT +}; + +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && defined(CONFIG_SYSFS) +struct mthp_stat { + unsigned long stats[ilog2(MAX_PTRS_PER_PTE) + 1][__MTHP_STAT_COUNT]; +}; + +DECLARE_PER_CPU(struct mthp_stat, mthp_stats); + +static inline void count_mthp_stat(int order, enum mthp_stat_item item) +{ + if (order <= 0 || order > PMD_ORDER) + return; + + this_cpu_inc(mthp_stats.stats[order][item]); +} +#else +static inline void count_mthp_stat(int order, enum mthp_stat_item item) +{ +} +#endif + #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern unsigned long transparent_hugepage_flags; @@ -269,41 +304,6 @@ struct thpsize { #define to_thpsize(kobj) container_of(kobj, struct thpsize, kobj) -enum mthp_stat_item { - MTHP_STAT_ANON_FAULT_ALLOC, - MTHP_STAT_ANON_FAULT_FALLBACK, - MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE, - MTHP_STAT_SWPOUT, - MTHP_STAT_SWPOUT_FALLBACK, - MTHP_STAT_SHMEM_ALLOC, - MTHP_STAT_SHMEM_FALLBACK, - MTHP_STAT_SHMEM_FALLBACK_CHARGE, - MTHP_STAT_SPLIT, - MTHP_STAT_SPLIT_FAILED, - MTHP_STAT_SPLIT_DEFERRED, - __MTHP_STAT_COUNT -}; - -struct mthp_stat { - unsigned long stats[ilog2(MAX_PTRS_PER_PTE) + 1][__MTHP_STAT_COUNT]; -}; - -#ifdef CONFIG_SYSFS -DECLARE_PER_CPU(struct mthp_stat, mthp_stats); - -static inline void count_mthp_stat(int order, enum mthp_stat_item item) -{ - if (order <= 0 || order > PMD_ORDER) - return; - - this_cpu_inc(mthp_stats.stats[order][item]); -} -#else -static inline void count_mthp_stat(int order, enum mthp_stat_item item) -{ -} -#endif - #define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ (1<vm_mm, MM_ANONPAGES, nr_pages); -#ifdef CONFIG_TRANSPARENT_HUGEPAGE count_mthp_stat(folio_order(folio), MTHP_STAT_ANON_FAULT_ALLOC); -#endif folio_add_new_anon_rmap(folio, vma, addr, RMAP_EXCLUSIVE); folio_add_lru_vma(folio, vma); setpte: diff --git a/mm/shmem.c b/mm/shmem.c index 866d46d0c43d..800cec9dc534 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1808,9 +1808,7 @@ static struct folio *shmem_alloc_and_add_folio(struct vm_fault *vmf, if (pages == HPAGE_PMD_NR) count_vm_event(THP_FILE_FALLBACK); -#ifdef CONFIG_TRANSPARENT_HUGEPAGE count_mthp_stat(order, MTHP_STAT_SHMEM_FALLBACK); -#endif order = next_order(&suitable_orders, order); } } else { @@ -1835,10 +1833,8 @@ allocated: count_vm_event(THP_FILE_FALLBACK); count_vm_event(THP_FILE_FALLBACK_CHARGE); } -#ifdef CONFIG_TRANSPARENT_HUGEPAGE count_mthp_stat(folio_order(folio), MTHP_STAT_SHMEM_FALLBACK); count_mthp_stat(folio_order(folio), MTHP_STAT_SHMEM_FALLBACK_CHARGE); -#endif } goto unlock; } @@ -2332,9 +2328,7 @@ repeat: if (!IS_ERR(folio)) { if (folio_test_pmd_mappable(folio)) count_vm_event(THP_FILE_ALLOC); -#ifdef CONFIG_TRANSPARENT_HUGEPAGE count_mthp_stat(folio_order(folio), MTHP_STAT_SHMEM_ALLOC); -#endif goto alloced; } if (PTR_ERR(folio) == -EEXIST) -- cgit v1.2.3 From 5d65c8d758f2596c008009e39bb2614deed2c730 Mon Sep 17 00:00:00 2001 From: Barry Song Date: Sat, 24 Aug 2024 13:04:40 +1200 Subject: mm: count the number of anonymous THPs per size Patch series "mm: count the number of anonymous THPs per size", v4. Knowing the number of transparent anon THPs in the system is crucial for performance analysis. It helps in understanding the ratio and distribution of THPs versus small folios throughout the system. Additionally, partial unmapping by userspace can lead to significant waste of THPs over time and increase memory reclamation pressure. We need this information for comprehensive system tuning. This patch (of 2): Let's track for each anonymous THP size, how many of them are currently allocated. We'll track the complete lifespan of an anon THP, starting when it becomes an anon THP ("large anon folio") (->mapping gets set), until it gets freed (->mapping gets cleared). Introduce a new "nr_anon" counter per THP size and adjust the corresponding counter in the following cases: * We allocate a new THP and call folio_add_new_anon_rmap() to map it the first time and turn it into an anon THP. * We split an anon THP into multiple smaller ones. * We migrate an anon THP, when we prepare the destination. * We free an anon THP back to the buddy. Note that AnonPages in /proc/meminfo currently tracks the total number of *mapped* anonymous *pages*, and therefore has slightly different semantics. In the future, we might also want to track "nr_anon_mapped" for each THP size, which might be helpful when comparing it to the number of allocated anon THPs (long-term pinning, stuck in swapcache, memory leaks, ...). Further note that for now, we only track anon THPs after they got their ->mapping set, for example via folio_add_new_anon_rmap(). If we would allocate some in the swapcache, they will only show up in the statistics for now after they have been mapped to user space the first time, where we call folio_add_new_anon_rmap(). [akpm@linux-foundation.org: documentation fixups, per David] Link: https://lkml.kernel.org/r/3e8add35-e26b-443b-8a04-1078f4bc78f6@redhat.com Link: https://lkml.kernel.org/r/20240824010441.21308-1-21cnbao@gmail.com Link: https://lkml.kernel.org/r/20240824010441.21308-2-21cnbao@gmail.com Signed-off-by: Barry Song Acked-by: David Hildenbrand Cc: Baolin Wang Cc: Chris Li Cc: Chuanhua Han Cc: Kairui Song Cc: Kalesh Singh Cc: Lance Yang Cc: Ryan Roberts Cc: Shuai Yuan Cc: Usama Arif Cc: Zi Yan Signed-off-by: Andrew Morton --- Documentation/admin-guide/mm/transhuge.rst | 5 +++++ include/linux/huge_mm.h | 15 +++++++++++++-- mm/huge_memory.c | 13 ++++++++++--- mm/migrate.c | 4 ++++ mm/page_alloc.c | 5 ++++- mm/rmap.c | 1 + 6 files changed, 37 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst index 79435c537e21..d6874234a09a 100644 --- a/Documentation/admin-guide/mm/transhuge.rst +++ b/Documentation/admin-guide/mm/transhuge.rst @@ -551,6 +551,11 @@ split_deferred it would free up some memory. Pages on split queue are going to be split under memory pressure, if splitting is possible. +nr_anon + the number of anonymous THP we have in the whole system. These THPs + might be currently entirely mapped or have partially unmapped/unused + subpages. + As the system ages, allocating huge pages may be expensive as the system uses memory compaction to copy data around memory to free a huge page for use. There are some counters in ``/proc/vmstat`` to help diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 4c32058cacfe..2ee2971e4e10 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -126,6 +126,7 @@ enum mthp_stat_item { MTHP_STAT_SPLIT, MTHP_STAT_SPLIT_FAILED, MTHP_STAT_SPLIT_DEFERRED, + MTHP_STAT_NR_ANON, __MTHP_STAT_COUNT }; @@ -136,14 +137,24 @@ struct mthp_stat { DECLARE_PER_CPU(struct mthp_stat, mthp_stats); -static inline void count_mthp_stat(int order, enum mthp_stat_item item) +static inline void mod_mthp_stat(int order, enum mthp_stat_item item, int delta) { if (order <= 0 || order > PMD_ORDER) return; - this_cpu_inc(mthp_stats.stats[order][item]); + this_cpu_add(mthp_stats.stats[order][item], delta); +} + +static inline void count_mthp_stat(int order, enum mthp_stat_item item) +{ + mod_mthp_stat(order, item, 1); } + #else +static inline void mod_mthp_stat(int order, enum mthp_stat_item item, int delta) +{ +} + static inline void count_mthp_stat(int order, enum mthp_stat_item item) { } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 3e872ee724cc..ea57c51d478d 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -597,6 +597,7 @@ DEFINE_MTHP_STAT_ATTR(shmem_fallback_charge, MTHP_STAT_SHMEM_FALLBACK_CHARGE); DEFINE_MTHP_STAT_ATTR(split, MTHP_STAT_SPLIT); DEFINE_MTHP_STAT_ATTR(split_failed, MTHP_STAT_SPLIT_FAILED); DEFINE_MTHP_STAT_ATTR(split_deferred, MTHP_STAT_SPLIT_DEFERRED); +DEFINE_MTHP_STAT_ATTR(nr_anon, MTHP_STAT_NR_ANON); static struct attribute *anon_stats_attrs[] = { &anon_fault_alloc_attr.attr, @@ -607,6 +608,7 @@ static struct attribute *anon_stats_attrs[] = { &swpout_fallback_attr.attr, #endif &split_deferred_attr.attr, + &nr_anon_attr.attr, NULL, }; @@ -3314,8 +3316,9 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, struct deferred_split *ds_queue = get_deferred_split_queue(folio); /* reset xarray order to new order after split */ XA_STATE_ORDER(xas, &folio->mapping->i_pages, folio->index, new_order); - struct anon_vma *anon_vma = NULL; + bool is_anon = folio_test_anon(folio); struct address_space *mapping = NULL; + struct anon_vma *anon_vma = NULL; int order = folio_order(folio); int extra_pins, ret; pgoff_t end; @@ -3327,7 +3330,7 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, if (new_order >= folio_order(folio)) return -EINVAL; - if (folio_test_anon(folio)) { + if (is_anon) { /* order-1 is not supported for anonymous THP. */ if (new_order == 1) { VM_WARN_ONCE(1, "Cannot split to order-1 folio"); @@ -3367,7 +3370,7 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, if (folio_test_writeback(folio)) return -EBUSY; - if (folio_test_anon(folio)) { + if (is_anon) { /* * The caller does not necessarily hold an mmap_lock that would * prevent the anon_vma disappearing so we first we take a @@ -3480,6 +3483,10 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, } } + if (is_anon) { + mod_mthp_stat(order, MTHP_STAT_NR_ANON, -1); + mod_mthp_stat(new_order, MTHP_STAT_NR_ANON, 1 << (order - new_order)); + } __split_huge_page(page, list, end, new_order); ret = 0; } else { diff --git a/mm/migrate.c b/mm/migrate.c index ba4893d42618..6f9c62c746be 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -449,6 +449,8 @@ static int __folio_migrate_mapping(struct address_space *mapping, /* No turning back from here */ newfolio->index = folio->index; newfolio->mapping = folio->mapping; + if (folio_test_anon(folio) && folio_test_large(folio)) + mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON, 1); if (folio_test_swapbacked(folio)) __folio_set_swapbacked(newfolio); @@ -473,6 +475,8 @@ static int __folio_migrate_mapping(struct address_space *mapping, */ newfolio->index = folio->index; newfolio->mapping = folio->mapping; + if (folio_test_anon(folio) && folio_test_large(folio)) + mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON, 1); folio_ref_add(newfolio, nr); /* add cache reference */ if (folio_test_swapbacked(folio)) { __folio_set_swapbacked(newfolio); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6dd0b409e3c2..3469ca78bf7a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1084,8 +1084,11 @@ __always_inline bool free_pages_prepare(struct page *page, (page + i)->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; } } - if (PageMappingFlags(page)) + if (PageMappingFlags(page)) { + if (PageAnon(page)) + mod_mthp_stat(order, MTHP_STAT_NR_ANON, -1); page->mapping = NULL; + } if (is_check_pages_enabled()) { if (free_page_is_bad(page)) bad++; diff --git a/mm/rmap.c b/mm/rmap.c index 1103a536e474..78529cf0fd66 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1467,6 +1467,7 @@ void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma, } __folio_mod_stat(folio, nr, nr_pmdmapped); + mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON, 1); } static __always_inline void __folio_add_file_rmap(struct folio *folio, -- cgit v1.2.3 From 8175ebfd302abe6fbdca9037f763ecbfdb8db572 Mon Sep 17 00:00:00 2001 From: Barry Song Date: Sat, 24 Aug 2024 13:04:41 +1200 Subject: mm: count the number of partially mapped anonymous THPs per size When a THP is added to the deferred_list due to partially mapped, its partial pages are unused, leading to wasted memory and potentially increasing memory reclamation pressure. Detailing the specifics of how unmapping occurs is quite difficult and not that useful, so we adopt a simple approach: each time a THP enters the deferred_list, we increment the count by 1; whenever it leaves for any reason, we decrement the count by 1. Link: https://lkml.kernel.org/r/20240824010441.21308-3-21cnbao@gmail.com Signed-off-by: Barry Song Acked-by: David Hildenbrand Cc: Baolin Wang Cc: Chris Li Cc: Chuanhua Han Cc: Kairui Song Cc: Kalesh Singh Cc: Lance Yang Cc: Ryan Roberts Cc: Shuai Yuan Cc: Usama Arif Cc: Zi Yan Signed-off-by: Andrew Morton --- Documentation/admin-guide/mm/transhuge.rst | 7 +++++++ include/linux/huge_mm.h | 1 + mm/huge_memory.c | 6 ++++++ 3 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst index d6874234a09a..56a086900651 100644 --- a/Documentation/admin-guide/mm/transhuge.rst +++ b/Documentation/admin-guide/mm/transhuge.rst @@ -556,6 +556,13 @@ nr_anon might be currently entirely mapped or have partially unmapped/unused subpages. +nr_anon_partially_mapped + the number of anonymous THP which are likely partially mapped, possibly + wasting memory, and have been queued for deferred memory reclamation. + Note that in corner some cases (e.g., failed migration), we might detect + an anonymous THP as "partially mapped" and count it here, even though it + is not actually partially mapped anymore. + As the system ages, allocating huge pages may be expensive as the system uses memory compaction to copy data around memory to free a huge page for use. There are some counters in ``/proc/vmstat`` to help diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 2ee2971e4e10..4902e2f7e896 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -127,6 +127,7 @@ enum mthp_stat_item { MTHP_STAT_SPLIT_FAILED, MTHP_STAT_SPLIT_DEFERRED, MTHP_STAT_NR_ANON, + MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, __MTHP_STAT_COUNT }; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index ea57c51d478d..efc625086dc7 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -598,6 +598,7 @@ DEFINE_MTHP_STAT_ATTR(split, MTHP_STAT_SPLIT); DEFINE_MTHP_STAT_ATTR(split_failed, MTHP_STAT_SPLIT_FAILED); DEFINE_MTHP_STAT_ATTR(split_deferred, MTHP_STAT_SPLIT_DEFERRED); DEFINE_MTHP_STAT_ATTR(nr_anon, MTHP_STAT_NR_ANON); +DEFINE_MTHP_STAT_ATTR(nr_anon_partially_mapped, MTHP_STAT_NR_ANON_PARTIALLY_MAPPED); static struct attribute *anon_stats_attrs[] = { &anon_fault_alloc_attr.attr, @@ -609,6 +610,7 @@ static struct attribute *anon_stats_attrs[] = { #endif &split_deferred_attr.attr, &nr_anon_attr.attr, + &nr_anon_partially_mapped_attr.attr, NULL, }; @@ -3457,6 +3459,7 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, if (folio_order(folio) > 1 && !list_empty(&folio->_deferred_list)) { ds_queue->split_queue_len--; + mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); /* * Reinitialize page_deferred_list after removing the * page from the split_queue, otherwise a subsequent @@ -3523,6 +3526,7 @@ void __folio_undo_large_rmappable(struct folio *folio) spin_lock_irqsave(&ds_queue->split_queue_lock, flags); if (!list_empty(&folio->_deferred_list)) { ds_queue->split_queue_len--; + mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); list_del_init(&folio->_deferred_list); } spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); @@ -3564,6 +3568,7 @@ void deferred_split_folio(struct folio *folio) if (folio_test_pmd_mappable(folio)) count_vm_event(THP_DEFERRED_SPLIT_PAGE); count_mthp_stat(folio_order(folio), MTHP_STAT_SPLIT_DEFERRED); + mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, 1); list_add_tail(&folio->_deferred_list, &ds_queue->split_queue); ds_queue->split_queue_len++; #ifdef CONFIG_MEMCG @@ -3611,6 +3616,7 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, list_move(&folio->_deferred_list, &list); } else { /* We lost race with folio_put() */ + mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); list_del_init(&folio->_deferred_list); ds_queue->split_queue_len--; } -- cgit v1.2.3 From b7315fbb64736acad3cd33851884b222b00dc0f4 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Sun, 25 Aug 2024 21:23:20 -0700 Subject: mm/damon/core: introduce per-context region priorities histogram buffer Patch series "replace per-quota region priorities histogram buffer with per-context one". Each DAMOS quota (struct damos_quota) maintains a histogram for total regions size per its prioritization score. DAMOS calcultes minimum prioritization score of regions that are ok to apply the DAMOS action to while respecting the quota. The histogram is constructed only for the calculation of the minimum score in damos_adjust_quota() for each quota which called by kdamond_fn(). Hence, there is no real reason to have per-quota histogram. Only per-kdamond histogram is needed, since parallel kdamonds could have races otherwise. The current implementation is only wasting the memory, and can easily cause unintended stack usage[1]. So, introducing a per-kdamond histogram and replacing the per-quota one with it would be the right solution for the issue. However, supporting multiple DAMON contexts per kdamond is still an ongoing work[2] without a clear estimated time of arrival. Meanwhile, per-context histogram could be an effective and straightforward solution having no blocker. Let's fix the problem first in the way. This patch (of 4): Introduce per-context buffer for region priority scores-total size histogram. Same to the per-quota one (->histogram of struct damos_quota), the new buffer is hidden from DAMON API users by being defined as a private field of DAMON context structure. It is dynamically allocated and de-allocated at the beginning and ending of the execution of the kdamond by kdamond_fn() itself. [1] commit 0742cadf5e4c ("mm/damon/lru_sort: adjust local variable to dynamic allocation") [2] https://lore.kernel.org/20240531122320.909060-1-yorha.op@gmail.com Link: https://lkml.kernel.org/r/20240826042323.87025-1-sj@kernel.org Link: https://lkml.kernel.org/r/20240826042323.87025-2-sj@kernel.org Signed-off-by: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/damon.h | 2 ++ mm/damon/core.c | 5 +++++ 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 27c546bfc6d4..60cb8eada3d6 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -630,6 +630,8 @@ struct damon_ctx { unsigned long next_ops_update_sis; /* for waiting until the execution of the kdamond_fn is started */ struct completion kdamond_started; + /* for scheme quotas prioritization */ + unsigned long *regions_score_histogram; /* public: */ struct task_struct *kdamond; diff --git a/mm/damon/core.c b/mm/damon/core.c index 086294279b07..40266d85eebf 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -1957,6 +1957,10 @@ static int kdamond_fn(void *data) ctx->ops.init(ctx); if (ctx->callback.before_start && ctx->callback.before_start(ctx)) goto done; + ctx->regions_score_histogram = kmalloc_array(DAMOS_MAX_SCORE + 1, + sizeof(*ctx->regions_score_histogram), GFP_KERNEL); + if (!ctx->regions_score_histogram) + goto done; sz_limit = damon_region_sz_limit(ctx); @@ -2034,6 +2038,7 @@ done: ctx->callback.before_terminate(ctx); if (ctx->ops.cleanup) ctx->ops.cleanup(ctx); + kfree(ctx->regions_score_histogram); pr_debug("kdamond (%d) finishes\n", current->pid); mutex_lock(&ctx->kdamond_lock); -- cgit v1.2.3 From e3bcb1672583f2e1cf456e4303ce562a3cc775c0 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Sun, 25 Aug 2024 21:23:22 -0700 Subject: mm/damon/core: remove per-scheme region priority histogram buffer Nobody is reading from or writing to the per-scheme region priorities histogram buffer. It is only wasting memory. Remove it. Link: https://lkml.kernel.org/r/20240826042323.87025-4-sj@kernel.org Signed-off-by: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/damon.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 60cb8eada3d6..a67f2c4940e9 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -233,7 +233,6 @@ struct damos_quota { unsigned long charge_addr_from; /* For prioritization */ - unsigned long histogram[DAMOS_MAX_SCORE + 1]; unsigned int min_score; /* For feedback loop */ -- cgit v1.2.3 From 17d75422604f0b92869aa17cb44f60958212f033 Mon Sep 17 00:00:00 2001 From: Barry Song Date: Sat, 31 Aug 2024 08:28:22 +1200 Subject: mm: document __GFP_NOFAIL must be blockable MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Non-blocking allocation with __GFP_NOFAIL is not supported and may still result in NULL pointers (if we don't return NULL, we result in busy-loop within non-sleepable contexts): static inline struct page * __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, struct alloc_context *ac) { ... /* * Make sure that __GFP_NOFAIL request doesn't leak out and make sure * we always retry */ if (gfp_mask & __GFP_NOFAIL) { /* * All existing users of the __GFP_NOFAIL are blockable, so warn * of any new users that actually require GFP_NOWAIT */ if (WARN_ON_ONCE_GFP(!can_direct_reclaim, gfp_mask)) goto fail; ... } ... fail: warn_alloc(gfp_mask, ac->nodemask, "page allocation failure: order:%u", order); got_pg: return page; } Highlight this in the documentation of __GFP_NOFAIL so that non-mm subsystems can reject any illegal usage of __GFP_NOFAIL with GFP_ATOMIC, GFP_NOWAIT, etc. Link: https://lkml.kernel.org/r/20240830202823.21478-3-21cnbao@gmail.com Signed-off-by: Barry Song Acked-by: Michal Hocko Reviewed-by: Christoph Hellwig Acked-by: Vlastimil Babka Acked-by: Davidlohr Bueso Acked-by: David Hildenbrand Cc: Christoph Lameter Cc: David Rientjes Cc: "Eugenio Pérez" Cc: Hailong.Liu Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com> Cc: Jason Wang Cc: Joonsoo Kim Cc: Kees Cook Cc: Linus Torvalds Cc: Lorenzo Stoakes Cc: Maxime Coquelin Cc: "Michael S. Tsirkin" Cc: Pekka Enberg Cc: Roman Gushchin Cc: Uladzislau Rezki (Sony) Cc: Xuan Zhuo Cc: Christoph Hellwig Cc: Xie Yongji Cc: Yafang Shao Signed-off-by: Andrew Morton --- include/linux/gfp_types.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h index 313be4ad79fd..4a1fa7706b0c 100644 --- a/include/linux/gfp_types.h +++ b/include/linux/gfp_types.h @@ -215,7 +215,8 @@ enum { * the caller still has to check for failures) while costly requests try to be * not disruptive and back off even without invoking the OOM killer. * The following three modifiers might be used to override some of these - * implicit rules. + * implicit rules. Please note that all of them must be used along with + * %__GFP_DIRECT_RECLAIM flag. * * %__GFP_NORETRY: The VM implementation will try only very lightweight * memory direct reclaim to get some memory under memory pressure (thus @@ -246,6 +247,8 @@ enum { * cannot handle allocation failures. The allocation could block * indefinitely but will never return with failure. Testing for * failure is pointless. + * It _must_ be blockable and used together with __GFP_DIRECT_RECLAIM. + * It should _never_ be used in non-sleepable contexts. * New users should be evaluated carefully (and the flag should be * used only when there is no reasonable failure policy) but it is * definitely preferable to use the flag rather than opencode endless -- cgit v1.2.3 From 903edea6c53f097f5f0c847fdbbfab0c6c44f241 Mon Sep 17 00:00:00 2001 From: Barry Song Date: Sat, 31 Aug 2024 08:28:23 +1200 Subject: mm: warn about illegal __GFP_NOFAIL usage in a more appropriate location and manner MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Three points for this change: 1. We should consolidate all warnings in one place. Currently, the order > 1 warning is in the hotpath, while others are in less likely scenarios. Moving all warnings to the slowpath will reduce the overhead for order > 1 and increase the visibility of other warnings. 2. We currently have two warnings for order: one for order > 1 in the hotpath and another for order > costly_order in the laziest path. I suggest standardizing on order > 1 since it's been in use for a long time. 3. We don't need to check for __GFP_NOWARN in this case. __GFP_NOWARN is meant to suppress allocation failure reports, but here we're dealing with bug detection, not allocation failures. So replace WARN_ON_ONCE_GFP by WARN_ON_ONCE. [v-songbaohua@oppo.com: also update the doc for __GFP_NOFAIL with order > 1] Link: https://lkml.kernel.org/r/20240903223935.1697-1-21cnbao@gmail.com Link: https://lkml.kernel.org/r/20240830202823.21478-4-21cnbao@gmail.com Signed-off-by: Barry Song Suggested-by: Vlastimil Babka Reviewed-by: Vlastimil Babka Acked-by: David Hildenbrand Acked-by: Michal Hocko Cc: Christoph Hellwig Cc: Christoph Lameter Cc: Davidlohr Bueso Cc: David Rientjes Cc: "Eugenio Pérez" Cc: Hailong.Liu Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com> Cc: Jason Wang Cc: Joonsoo Kim Cc: Kees Cook Cc: Linus Torvalds Cc: Lorenzo Stoakes Cc: Maxime Coquelin Cc: "Michael S. Tsirkin" Cc: Pekka Enberg Cc: Roman Gushchin Cc: Uladzislau Rezki (Sony) Cc: Xie Yongji Cc: Xuan Zhuo Cc: Yafang Shao Signed-off-by: Andrew Morton --- include/linux/gfp_types.h | 3 ++- mm/page_alloc.c | 50 +++++++++++++++++++++++------------------------ 2 files changed, 27 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h index 4a1fa7706b0c..65db9349f905 100644 --- a/include/linux/gfp_types.h +++ b/include/linux/gfp_types.h @@ -253,7 +253,8 @@ enum { * used only when there is no reasonable failure policy) but it is * definitely preferable to use the flag rather than opencode endless * loop around allocator. - * Using this flag for costly allocations is _highly_ discouraged. + * Allocating pages from the buddy with __GFP_NOFAIL and order > 1 is + * not supported. Please consider using kvmalloc() instead. */ #define __GFP_IO ((__force gfp_t)___GFP_IO) #define __GFP_FS ((__force gfp_t)___GFP_FS) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 3469ca78bf7a..23509b823e2b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3032,12 +3032,6 @@ struct page *rmqueue(struct zone *preferred_zone, { struct page *page; - /* - * We most definitely don't want callers attempting to - * allocate greater than order-1 page units with __GFP_NOFAIL. - */ - WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1)); - if (likely(pcp_allowed_order(order))) { page = rmqueue_pcplist(preferred_zone, zone, order, migratetype, alloc_flags); @@ -4175,6 +4169,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, { bool can_direct_reclaim = gfp_mask & __GFP_DIRECT_RECLAIM; bool can_compact = gfp_compaction_allowed(gfp_mask); + bool nofail = gfp_mask & __GFP_NOFAIL; const bool costly_order = order > PAGE_ALLOC_COSTLY_ORDER; struct page *page = NULL; unsigned int alloc_flags; @@ -4187,6 +4182,25 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, unsigned int zonelist_iter_cookie; int reserve_flags; + if (unlikely(nofail)) { + /* + * We most definitely don't want callers attempting to + * allocate greater than order-1 page units with __GFP_NOFAIL. + */ + WARN_ON_ONCE(order > 1); + /* + * Also we don't support __GFP_NOFAIL without __GFP_DIRECT_RECLAIM, + * otherwise, we may result in lockup. + */ + WARN_ON_ONCE(!can_direct_reclaim); + /* + * PF_MEMALLOC request from this context is rather bizarre + * because we cannot reclaim anything and only can loop waiting + * for somebody to do a work for us. + */ + WARN_ON_ONCE(current->flags & PF_MEMALLOC); + } + restart: compaction_retries = 0; no_progress_loops = 0; @@ -4404,29 +4418,15 @@ nopage: * Make sure that __GFP_NOFAIL request doesn't leak out and make sure * we always retry */ - if (gfp_mask & __GFP_NOFAIL) { + if (unlikely(nofail)) { /* - * All existing users of the __GFP_NOFAIL are blockable, so warn - * of any new users that actually require GFP_NOWAIT + * Lacking direct_reclaim we can't do anything to reclaim memory, + * we disregard these unreasonable nofail requests and still + * return NULL */ - if (WARN_ON_ONCE_GFP(!can_direct_reclaim, gfp_mask)) + if (!can_direct_reclaim) goto fail; - /* - * PF_MEMALLOC request from this context is rather bizarre - * because we cannot reclaim anything and only can loop waiting - * for somebody to do a work for us - */ - WARN_ON_ONCE_GFP(current->flags & PF_MEMALLOC, gfp_mask); - - /* - * non failing costly orders are a hard requirement which we - * are not prepared for much so let's warn about these users - * so that we can identify them and convert them to something - * else. - */ - WARN_ON_ONCE_GFP(costly_order, gfp_mask); - /* * Help non-failing allocations by giving some access to memory * reserves normally used for high priority non-blocking -- cgit v1.2.3 From b1f202060afeb7fcb98473929d26fd3d2093b067 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Fri, 30 Aug 2024 11:03:36 +0100 Subject: mm: remap unused subpages to shared zeropage when splitting isolated thp Patch series "mm: split underused THPs", v5. The current upstream default policy for THP is always. However, Meta uses madvise in production as the current THP=always policy vastly overprovisions THPs in sparsely accessed memory areas, resulting in excessive memory pressure and premature OOM killing. Using madvise + relying on khugepaged has certain drawbacks over THP=always. Using madvise hints mean THPs aren't "transparent" and require userspace changes. Waiting for khugepaged to scan memory and collapse pages into THP can be slow and unpredictable in terms of performance (i.e. you dont know when the collapse will happen), while production environments require predictable performance. If there is enough memory available, its better for both performance and predictability to have a THP from fault time, i.e. THP=always rather than wait for khugepaged to collapse it, and deal with sparsely populated THPs when the system is running out of memory. This patch series is an attempt to mitigate the issue of running out of memory when THP is always enabled. During runtime whenever a THP is being faulted in or collapsed by khugepaged, the THP is added to a list. Whenever memory reclaim happens, the kernel runs the deferred_split shrinker which goes through the list and checks if the THP was underused, i.e. how many of the base 4K pages of the entire THP were zero-filled. If this number goes above a certain threshold, the shrinker will attempt to split that THP. Then at remap time, the pages that were zero-filled are mapped to the shared zeropage, hence saving memory. This method avoids the downside of wasting memory in areas where THP is sparsely filled when THP is always enabled, while still providing the upside THPs like reduced TLB misses without having to use madvise. Meta production workloads that were CPU bound (>99% CPU utilzation) were tested with THP shrinker. The results after 2 hours are as follows: | THP=madvise | THP=always | THP=always | | | + shrinker series | | | + max_ptes_none=409 ----------------------------------------------------------------------------- Performance improvement | - | +1.8% | +1.7% (over THP=madvise) | | | ----------------------------------------------------------------------------- Memory usage | 54.6G | 58.8G (+7.7%) | 55.9G (+2.4%) ----------------------------------------------------------------------------- max_ptes_none=409 means that any THP that has more than 409 out of 512 (80%) zero filled filled pages will be split. To test out the patches, the below commands without the shrinker will invoke OOM killer immediately and kill stress, but will not fail with the shrinker: echo 450 > /sys/kernel/mm/transparent_hugepage/khugepaged/max_ptes_none mkdir /sys/fs/cgroup/test echo $$ > /sys/fs/cgroup/test/cgroup.procs echo 20M > /sys/fs/cgroup/test/memory.max echo 0 > /sys/fs/cgroup/test/memory.swap.max # allocate twice memory.max for each stress worker and touch 40/512 of # each THP, i.e. vm-stride 50K. # With the shrinker, max_ptes_none of 470 and below won't invoke OOM # killer. # Without the shrinker, OOM killer is invoked immediately irrespective # of max_ptes_none value and kills stress. stress --vm 1 --vm-bytes 40M --vm-stride 50K This patch (of 5): Here being unused means containing only zeros and inaccessible to userspace. When splitting an isolated thp under reclaim or migration, the unused subpages can be mapped to the shared zeropage, hence saving memory. This is particularly helpful when the internal fragmentation of a thp is high, i.e. it has many untouched subpages. This is also a prerequisite for THP low utilization shrinker which will be introduced in later patches, where underutilized THPs are split, and the zero-filled pages are freed saving memory. Link: https://lkml.kernel.org/r/20240830100438.3623486-1-usamaarif642@gmail.com Link: https://lkml.kernel.org/r/20240830100438.3623486-3-usamaarif642@gmail.com Signed-off-by: Yu Zhao Signed-off-by: Usama Arif Tested-by: Shuang Zhai Cc: Alexander Zhu Cc: Barry Song Cc: David Hildenbrand Cc: Domenico Cerasuolo Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Kairui Song Cc: Matthew Wilcox Cc: Mike Rapoport Cc: Nico Pache Cc: Rik van Riel Cc: Roman Gushchin Cc: Ryan Roberts Cc: Shakeel Butt Cc: Shuang Zhai Cc: Hugh Dickins Signed-off-by: Andrew Morton --- include/linux/rmap.h | 7 ++++- mm/huge_memory.c | 8 +++--- mm/migrate.c | 72 +++++++++++++++++++++++++++++++++++++++++++++------- mm/migrate_device.c | 4 +-- 4 files changed, 75 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 91b5935e8485..d5e93e44322e 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -745,7 +745,12 @@ int folio_mkclean(struct folio *); int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, struct vm_area_struct *vma); -void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked); +enum rmp_flags { + RMP_LOCKED = 1 << 0, + RMP_USE_SHARED_ZEROPAGE = 1 << 1, +}; + +void remove_migration_ptes(struct folio *src, struct folio *dst, int flags); /* * rmap_walk_control: To control rmap traversing for specific needs diff --git a/mm/huge_memory.c b/mm/huge_memory.c index efc625086dc7..6b69309e002f 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3004,7 +3004,7 @@ bool unmap_huge_pmd_locked(struct vm_area_struct *vma, unsigned long addr, return false; } -static void remap_page(struct folio *folio, unsigned long nr) +static void remap_page(struct folio *folio, unsigned long nr, int flags) { int i = 0; @@ -3012,7 +3012,7 @@ static void remap_page(struct folio *folio, unsigned long nr) if (!folio_test_anon(folio)) return; for (;;) { - remove_migration_ptes(folio, folio, true); + remove_migration_ptes(folio, folio, RMP_LOCKED | flags); i += folio_nr_pages(folio); if (i >= nr) break; @@ -3222,7 +3222,7 @@ static void __split_huge_page(struct page *page, struct list_head *list, if (nr_dropped) shmem_uncharge(folio->mapping->host, nr_dropped); - remap_page(folio, nr); + remap_page(folio, nr, PageAnon(head) ? RMP_USE_SHARED_ZEROPAGE : 0); /* * set page to its compound_head when split to non order-0 pages, so @@ -3498,7 +3498,7 @@ fail: if (mapping) xas_unlock(&xas); local_irq_enable(); - remap_page(folio, folio_nr_pages(folio)); + remap_page(folio, folio_nr_pages(folio), 0); ret = -EAGAIN; } diff --git a/mm/migrate.c b/mm/migrate.c index 6f9c62c746be..d039863e014b 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -204,13 +204,57 @@ bool isolate_folio_to_list(struct folio *folio, struct list_head *list) return true; } +static bool try_to_map_unused_to_zeropage(struct page_vma_mapped_walk *pvmw, + struct folio *folio, + unsigned long idx) +{ + struct page *page = folio_page(folio, idx); + bool contains_data; + pte_t newpte; + void *addr; + + VM_BUG_ON_PAGE(PageCompound(page), page); + VM_BUG_ON_PAGE(!PageAnon(page), page); + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(pte_present(*pvmw->pte), page); + + if (folio_test_mlocked(folio) || (pvmw->vma->vm_flags & VM_LOCKED) || + mm_forbids_zeropage(pvmw->vma->vm_mm)) + return false; + + /* + * The pmd entry mapping the old thp was flushed and the pte mapping + * this subpage has been non present. If the subpage is only zero-filled + * then map it to the shared zeropage. + */ + addr = kmap_local_page(page); + contains_data = memchr_inv(addr, 0, PAGE_SIZE); + kunmap_local(addr); + + if (contains_data) + return false; + + newpte = pte_mkspecial(pfn_pte(my_zero_pfn(pvmw->address), + pvmw->vma->vm_page_prot)); + set_pte_at(pvmw->vma->vm_mm, pvmw->address, pvmw->pte, newpte); + + dec_mm_counter(pvmw->vma->vm_mm, mm_counter(folio)); + return true; +} + +struct rmap_walk_arg { + struct folio *folio; + bool map_unused_to_zeropage; +}; + /* * Restore a potential migration pte to a working pte entry */ static bool remove_migration_pte(struct folio *folio, - struct vm_area_struct *vma, unsigned long addr, void *old) + struct vm_area_struct *vma, unsigned long addr, void *arg) { - DEFINE_FOLIO_VMA_WALK(pvmw, old, vma, addr, PVMW_SYNC | PVMW_MIGRATION); + struct rmap_walk_arg *rmap_walk_arg = arg; + DEFINE_FOLIO_VMA_WALK(pvmw, rmap_walk_arg->folio, vma, addr, PVMW_SYNC | PVMW_MIGRATION); while (page_vma_mapped_walk(&pvmw)) { rmap_t rmap_flags = RMAP_NONE; @@ -234,6 +278,9 @@ static bool remove_migration_pte(struct folio *folio, continue; } #endif + if (rmap_walk_arg->map_unused_to_zeropage && + try_to_map_unused_to_zeropage(&pvmw, folio, idx)) + continue; folio_get(folio); pte = mk_pte(new, READ_ONCE(vma->vm_page_prot)); @@ -312,14 +359,21 @@ static bool remove_migration_pte(struct folio *folio, * Get rid of all migration entries and replace them by * references to the indicated page. */ -void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked) +void remove_migration_ptes(struct folio *src, struct folio *dst, int flags) { + struct rmap_walk_arg rmap_walk_arg = { + .folio = src, + .map_unused_to_zeropage = flags & RMP_USE_SHARED_ZEROPAGE, + }; + struct rmap_walk_control rwc = { .rmap_one = remove_migration_pte, - .arg = src, + .arg = &rmap_walk_arg, }; - if (locked) + VM_BUG_ON_FOLIO((flags & RMP_USE_SHARED_ZEROPAGE) && (src != dst), src); + + if (flags & RMP_LOCKED) rmap_walk_locked(dst, &rwc); else rmap_walk(dst, &rwc); @@ -934,7 +988,7 @@ static int writeout(struct address_space *mapping, struct folio *folio) * At this point we know that the migration attempt cannot * be successful. */ - remove_migration_ptes(folio, folio, false); + remove_migration_ptes(folio, folio, 0); rc = mapping->a_ops->writepage(&folio->page, &wbc); @@ -1098,7 +1152,7 @@ static void migrate_folio_undo_src(struct folio *src, struct list_head *ret) { if (page_was_mapped) - remove_migration_ptes(src, src, false); + remove_migration_ptes(src, src, 0); /* Drop an anon_vma reference if we took one */ if (anon_vma) put_anon_vma(anon_vma); @@ -1336,7 +1390,7 @@ static int migrate_folio_move(free_folio_t put_new_folio, unsigned long private, lru_add_drain(); if (old_page_state & PAGE_WAS_MAPPED) - remove_migration_ptes(src, dst, false); + remove_migration_ptes(src, dst, 0); out_unlock_both: folio_unlock(dst); @@ -1474,7 +1528,7 @@ static int unmap_and_move_huge_page(new_folio_t get_new_folio, if (page_was_mapped) remove_migration_ptes(src, - rc == MIGRATEPAGE_SUCCESS ? dst : src, false); + rc == MIGRATEPAGE_SUCCESS ? dst : src, 0); unlock_put_anon: folio_unlock(dst); diff --git a/mm/migrate_device.c b/mm/migrate_device.c index 8d687de88a03..9cf26592ac93 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -424,7 +424,7 @@ static unsigned long migrate_device_unmap(unsigned long *src_pfns, continue; folio = page_folio(page); - remove_migration_ptes(folio, folio, false); + remove_migration_ptes(folio, folio, 0); src_pfns[i] = 0; folio_unlock(folio); @@ -840,7 +840,7 @@ void migrate_device_finalize(unsigned long *src_pfns, dst = src; } - remove_migration_ptes(src, dst, false); + remove_migration_ptes(src, dst, 0); folio_unlock(src); if (folio_is_zone_device(src)) -- cgit v1.2.3 From 8422acdc97ed5839692b45f800dbfb78abe65a94 Mon Sep 17 00:00:00 2001 From: Usama Arif Date: Fri, 30 Aug 2024 11:03:38 +0100 Subject: mm: introduce a pageflag for partially mapped folios Currently folio->_deferred_list is used to keep track of partially_mapped folios that are going to be split under memory pressure. In the next patch, all THPs that are faulted in and collapsed by khugepaged are also going to be tracked using _deferred_list. This patch introduces a pageflag to be able to distinguish between partially mapped folios and others in the deferred_list at split time in deferred_split_scan. Its needed as __folio_remove_rmap decrements _mapcount, _large_mapcount and _entire_mapcount, hence it won't be possible to distinguish between partially mapped folios and others in deferred_split_scan. Eventhough it introduces an extra flag to track if the folio is partially mapped, there is no functional change intended with this patch and the flag is not useful in this patch itself, it will become useful in the next patch when _deferred_list has non partially mapped folios. Link: https://lkml.kernel.org/r/20240830100438.3623486-5-usamaarif642@gmail.com Signed-off-by: Usama Arif Cc: Alexander Zhu Cc: Barry Song Cc: David Hildenbrand Cc: Domenico Cerasuolo Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Kairui Song Cc: Matthew Wilcox Cc: Mike Rapoport Cc: Nico Pache Cc: Rik van Riel Cc: Roman Gushchin Cc: Ryan Roberts Cc: Shakeel Butt Cc: Shuang Zhai Cc: Yu Zhao Cc: Shuang Zhai Cc: Hugh Dickins Signed-off-by: Andrew Morton --- include/linux/huge_mm.h | 4 ++-- include/linux/page-flags.h | 13 ++++++++++++- mm/huge_memory.c | 41 ++++++++++++++++++++++++++++++----------- mm/memcontrol.c | 3 ++- mm/migrate.c | 3 ++- mm/page_alloc.c | 5 +++-- mm/rmap.c | 5 +++-- mm/vmscan.c | 3 ++- 8 files changed, 56 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 4902e2f7e896..e3896ebf0f94 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -333,7 +333,7 @@ static inline int split_huge_page(struct page *page) { return split_huge_page_to_list_to_order(page, NULL, 0); } -void deferred_split_folio(struct folio *folio); +void deferred_split_folio(struct folio *folio, bool partially_mapped); void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long address, bool freeze, struct folio *folio); @@ -507,7 +507,7 @@ static inline int split_huge_page(struct page *page) { return 0; } -static inline void deferred_split_folio(struct folio *folio) {} +static inline void deferred_split_folio(struct folio *folio, bool partially_mapped) {} #define split_huge_pmd(__vma, __pmd, __address) \ do { } while (0) diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 2175ebceb41c..1b3a76710487 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -186,6 +186,7 @@ enum pageflags { /* At least one page in this folio has the hwpoison flag set */ PG_has_hwpoisoned = PG_active, PG_large_rmappable = PG_workingset, /* anon or file-backed */ + PG_partially_mapped = PG_reclaim, /* was identified to be partially mapped */ }; #define PAGEFLAGS_MASK ((1UL << NR_PAGEFLAGS) - 1) @@ -859,8 +860,18 @@ static inline void ClearPageCompound(struct page *page) ClearPageHead(page); } FOLIO_FLAG(large_rmappable, FOLIO_SECOND_PAGE) +FOLIO_TEST_FLAG(partially_mapped, FOLIO_SECOND_PAGE) +/* + * PG_partially_mapped is protected by deferred_split split_queue_lock, + * so its safe to use non-atomic set/clear. + */ +__FOLIO_SET_FLAG(partially_mapped, FOLIO_SECOND_PAGE) +__FOLIO_CLEAR_FLAG(partially_mapped, FOLIO_SECOND_PAGE) #else FOLIO_FLAG_FALSE(large_rmappable) +FOLIO_TEST_FLAG_FALSE(partially_mapped) +__FOLIO_SET_FLAG_NOOP(partially_mapped) +__FOLIO_CLEAR_FLAG_NOOP(partially_mapped) #endif #define PG_head_mask ((1UL << PG_head)) @@ -1171,7 +1182,7 @@ static __always_inline void __ClearPageAnonExclusive(struct page *page) */ #define PAGE_FLAGS_SECOND \ (0xffUL /* order */ | 1UL << PG_has_hwpoisoned | \ - 1UL << PG_large_rmappable) + 1UL << PG_large_rmappable | 1UL << PG_partially_mapped) #define PAGE_FLAGS_PRIVATE \ (1UL << PG_private | 1UL << PG_private_2) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 6b69309e002f..9bc435bef2e6 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3459,7 +3459,11 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, if (folio_order(folio) > 1 && !list_empty(&folio->_deferred_list)) { ds_queue->split_queue_len--; - mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); + if (folio_test_partially_mapped(folio)) { + __folio_clear_partially_mapped(folio); + mod_mthp_stat(folio_order(folio), + MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); + } /* * Reinitialize page_deferred_list after removing the * page from the split_queue, otherwise a subsequent @@ -3526,13 +3530,18 @@ void __folio_undo_large_rmappable(struct folio *folio) spin_lock_irqsave(&ds_queue->split_queue_lock, flags); if (!list_empty(&folio->_deferred_list)) { ds_queue->split_queue_len--; - mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); + if (folio_test_partially_mapped(folio)) { + __folio_clear_partially_mapped(folio); + mod_mthp_stat(folio_order(folio), + MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); + } list_del_init(&folio->_deferred_list); } spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); } -void deferred_split_folio(struct folio *folio) +/* partially_mapped=false won't clear PG_partially_mapped folio flag */ +void deferred_split_folio(struct folio *folio, bool partially_mapped) { struct deferred_split *ds_queue = get_deferred_split_queue(folio); #ifdef CONFIG_MEMCG @@ -3560,15 +3569,21 @@ void deferred_split_folio(struct folio *folio) if (folio_test_swapcache(folio)) return; - if (!list_empty(&folio->_deferred_list)) - return; - spin_lock_irqsave(&ds_queue->split_queue_lock, flags); + if (partially_mapped) { + if (!folio_test_partially_mapped(folio)) { + __folio_set_partially_mapped(folio); + if (folio_test_pmd_mappable(folio)) + count_vm_event(THP_DEFERRED_SPLIT_PAGE); + count_mthp_stat(folio_order(folio), MTHP_STAT_SPLIT_DEFERRED); + mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, 1); + + } + } else { + /* partially mapped folios cannot become non-partially mapped */ + VM_WARN_ON_FOLIO(folio_test_partially_mapped(folio), folio); + } if (list_empty(&folio->_deferred_list)) { - if (folio_test_pmd_mappable(folio)) - count_vm_event(THP_DEFERRED_SPLIT_PAGE); - count_mthp_stat(folio_order(folio), MTHP_STAT_SPLIT_DEFERRED); - mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, 1); list_add_tail(&folio->_deferred_list, &ds_queue->split_queue); ds_queue->split_queue_len++; #ifdef CONFIG_MEMCG @@ -3616,7 +3631,11 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, list_move(&folio->_deferred_list, &list); } else { /* We lost race with folio_put() */ - mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); + if (folio_test_partially_mapped(folio)) { + __folio_clear_partially_mapped(folio); + mod_mthp_stat(folio_order(folio), + MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); + } list_del_init(&folio->_deferred_list); ds_queue->split_queue_len--; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 0370ce03ce4c..5abff3b0cae5 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4645,7 +4645,8 @@ static void uncharge_folio(struct folio *folio, struct uncharge_gather *ug) VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); VM_BUG_ON_FOLIO(folio_order(folio) > 1 && !folio_test_hugetlb(folio) && - !list_empty(&folio->_deferred_list), folio); + !list_empty(&folio->_deferred_list) && + folio_test_partially_mapped(folio), folio); /* * Nobody should be changing or seriously looking at diff --git a/mm/migrate.c b/mm/migrate.c index d039863e014b..35cc9d35064b 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1766,7 +1766,8 @@ static int migrate_pages_batch(struct list_head *from, * use _deferred_list. */ if (nr_pages > 2 && - !list_empty(&folio->_deferred_list)) { + !list_empty(&folio->_deferred_list) && + folio_test_partially_mapped(folio)) { if (!try_split_folio(folio, split_folios, mode)) { nr_failed++; stats->nr_thp_failed += is_thp; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 23509b823e2b..ea4c44c3cfc0 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -962,8 +962,9 @@ static int free_tail_page_prepare(struct page *head_page, struct page *page) break; case 2: /* the second tail page: deferred_list overlaps ->mapping */ - if (unlikely(!list_empty(&folio->_deferred_list))) { - bad_page(page, "on deferred list"); + if (unlikely(!list_empty(&folio->_deferred_list) && + folio_test_partially_mapped(folio))) { + bad_page(page, "partially mapped folio on deferred list"); goto out; } break; diff --git a/mm/rmap.c b/mm/rmap.c index 78529cf0fd66..a8797d1b3d49 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1579,8 +1579,9 @@ static __always_inline void __folio_remove_rmap(struct folio *folio, * Check partially_mapped first to ensure it is a large folio. */ if (partially_mapped && folio_test_anon(folio) && - list_empty(&folio->_deferred_list)) - deferred_split_folio(folio); + !folio_test_partially_mapped(folio)) + deferred_split_folio(folio, true); + __folio_mod_stat(folio, -nr, -nr_pmdmapped); /* diff --git a/mm/vmscan.c b/mm/vmscan.c index 1b1fad0c1e11..8163b24bec75 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1238,7 +1238,8 @@ retry: * Split partially mapped folios right away. * We can free the unmapped pages without IO. */ - if (data_race(!list_empty(&folio->_deferred_list)) && + if (data_race(!list_empty(&folio->_deferred_list) && + folio_test_partially_mapped(folio)) && split_folio_to_list(folio, folio_list)) goto activate_locked; } -- cgit v1.2.3 From dafff3f4c850c98e15501bc6ee20581f9a013dcc Mon Sep 17 00:00:00 2001 From: Usama Arif Date: Fri, 30 Aug 2024 11:03:39 +0100 Subject: mm: split underused THPs This is an attempt to mitigate the issue of running out of memory when THP is always enabled. During runtime whenever a THP is being faulted in (__do_huge_pmd_anonymous_page) or collapsed by khugepaged (collapse_huge_page), the THP is added to _deferred_list. Whenever memory reclaim happens in linux, the kernel runs the deferred_split shrinker which goes through the _deferred_list. If the folio was partially mapped, the shrinker attempts to split it. If the folio is not partially mapped, the shrinker checks if the THP was underused, i.e. how many of the base 4K pages of the entire THP were zero-filled. If this number goes above a certain threshold (decided by /sys/kernel/mm/transparent_hugepage/khugepaged/max_ptes_none), the shrinker will attempt to split that THP. Then at remap time, the pages that were zero-filled are mapped to the shared zeropage, hence saving memory. Link: https://lkml.kernel.org/r/20240830100438.3623486-6-usamaarif642@gmail.com Signed-off-by: Usama Arif Suggested-by: Rik van Riel Co-authored-by: Johannes Weiner Cc: Alexander Zhu Cc: Barry Song Cc: David Hildenbrand Cc: Domenico Cerasuolo Cc: Jonathan Corbet Cc: Kairui Song Cc: Matthew Wilcox Cc: Mike Rapoport Cc: Nico Pache Cc: Roman Gushchin Cc: Ryan Roberts Cc: Shakeel Butt Cc: Shuang Zhai Cc: Yu Zhao Cc: Shuang Zhai Cc: Hugh Dickins Signed-off-by: Andrew Morton --- Documentation/admin-guide/mm/transhuge.rst | 6 +++ include/linux/khugepaged.h | 1 + include/linux/vm_event_item.h | 1 + mm/huge_memory.c | 60 +++++++++++++++++++++++++++++- mm/khugepaged.c | 3 +- mm/vmstat.c | 1 + 6 files changed, 69 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst index 56a086900651..aca0cff852b8 100644 --- a/Documentation/admin-guide/mm/transhuge.rst +++ b/Documentation/admin-guide/mm/transhuge.rst @@ -471,6 +471,12 @@ thp_deferred_split_page splitting it would free up some memory. Pages on split queue are going to be split under memory pressure. +thp_underused_split_page + is incremented when a huge page on the split queue was split + because it was underused. A THP is underused if the number of + zero pages in the THP is above a certain threshold + (/sys/kernel/mm/transparent_hugepage/khugepaged/max_ptes_none). + thp_split_pmd is incremented every time a PMD split into table of PTEs. This can happen, for instance, when application calls mprotect() or diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h index f68865e19b0b..30baae91b225 100644 --- a/include/linux/khugepaged.h +++ b/include/linux/khugepaged.h @@ -4,6 +4,7 @@ #include /* MMF_VM_HUGEPAGE */ +extern unsigned int khugepaged_max_ptes_none __read_mostly; #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern struct attribute_group khugepaged_attr_group; diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index aae5c7c5cfb4..aed952d04132 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -105,6 +105,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, THP_SPLIT_PAGE, THP_SPLIT_PAGE_FAILED, THP_DEFERRED_SPLIT_PAGE, + THP_UNDERUSED_SPLIT_PAGE, THP_SPLIT_PMD, THP_SCAN_EXCEED_NONE_PTE, THP_SCAN_EXCEED_SWAP_PTE, diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 9bc435bef2e6..cec5bce046a0 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1187,6 +1187,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR); mm_inc_nr_ptes(vma->vm_mm); + deferred_split_folio(folio, false); spin_unlock(vmf->ptl); count_vm_event(THP_FAULT_ALLOC); count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_ALLOC); @@ -3608,6 +3609,39 @@ static unsigned long deferred_split_count(struct shrinker *shrink, return READ_ONCE(ds_queue->split_queue_len); } +static bool thp_underused(struct folio *folio) +{ + int num_zero_pages = 0, num_filled_pages = 0; + void *kaddr; + int i; + + if (khugepaged_max_ptes_none == HPAGE_PMD_NR - 1) + return false; + + for (i = 0; i < folio_nr_pages(folio); i++) { + kaddr = kmap_local_folio(folio, i * PAGE_SIZE); + if (!memchr_inv(kaddr, 0, PAGE_SIZE)) { + num_zero_pages++; + if (num_zero_pages > khugepaged_max_ptes_none) { + kunmap_local(kaddr); + return true; + } + } else { + /* + * Another path for early exit once the number + * of non-zero filled pages exceeds threshold. + */ + num_filled_pages++; + if (num_filled_pages >= HPAGE_PMD_NR - khugepaged_max_ptes_none) { + kunmap_local(kaddr); + return false; + } + } + kunmap_local(kaddr); + } + return false; +} + static unsigned long deferred_split_scan(struct shrinker *shrink, struct shrink_control *sc) { @@ -3645,13 +3679,35 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); list_for_each_entry_safe(folio, next, &list, _deferred_list) { + bool did_split = false; + bool underused = false; + + if (!folio_test_partially_mapped(folio)) { + underused = thp_underused(folio); + if (!underused) + goto next; + } if (!folio_trylock(folio)) goto next; - /* split_huge_page() removes page from list on success */ - if (!split_folio(folio)) + if (!split_folio(folio)) { + did_split = true; + if (underused) + count_vm_event(THP_UNDERUSED_SPLIT_PAGE); split++; + } folio_unlock(folio); next: + /* + * split_folio() removes folio from list on success. + * Only add back to the queue if folio is partially mapped. + * If thp_underused returns false, or if split_folio fails + * in the case it was underused, then consider it used and + * don't add it back to split_queue. + */ + if (!did_split && !folio_test_partially_mapped(folio)) { + list_del_init(&folio->_deferred_list); + ds_queue->split_queue_len--; + } folio_put(folio); } diff --git a/mm/khugepaged.c b/mm/khugepaged.c index ab646018ce25..32100041aef3 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -85,7 +85,7 @@ static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait); * * Note that these are only respected if collapse was initiated by khugepaged. */ -static unsigned int khugepaged_max_ptes_none __read_mostly; +unsigned int khugepaged_max_ptes_none __read_mostly; static unsigned int khugepaged_max_ptes_swap __read_mostly; static unsigned int khugepaged_max_ptes_shared __read_mostly; @@ -1237,6 +1237,7 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address, pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, address, pmd, _pmd); update_mmu_cache_pmd(vma, address, pmd); + deferred_split_folio(folio, false); spin_unlock(pmd_ptl); folio = NULL; diff --git a/mm/vmstat.c b/mm/vmstat.c index aea58e9fce60..b5a4cea423e1 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1385,6 +1385,7 @@ const char * const vmstat_text[] = { "thp_split_page", "thp_split_page_failed", "thp_deferred_split_page", + "thp_underused_split_page", "thp_split_pmd", "thp_scan_exceed_none_pte", "thp_scan_exceed_swap_pte", -- cgit v1.2.3 From 0a6fff20d36bc81156a49649f622b152330fed3c Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sun, 1 Sep 2024 16:24:59 -0400 Subject: mm: fix folio_alloc_noprof() folio_alloc_noprof) wasn't calling the _noprof version, causing allocations to be accounted here instead of to the caller Link: https://lkml.kernel.org/r/20240901202459.4867-1-kent.overstreet@linux.dev Signed-off-by: Kent Overstreet Signed-off-by: Andrew Morton --- include/linux/gfp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 03ba9563c6db..a951de920e20 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -319,7 +319,7 @@ static inline struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order } static inline struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order) { - return __folio_alloc_node(gfp, order, numa_node_id()); + return __folio_alloc_node_noprof(gfp, order, numa_node_id()); } static inline struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *mpol, pgoff_t ilx, int nid) -- cgit v1.2.3 From 6050df6d706f58b2240bfabece9f406170104d57 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Fri, 9 Aug 2024 02:01:15 +0000 Subject: maple_tree: fix comment typo on ma_flag of allocation tree The maple tree flag of allocation tree is MT_FLAGS_ALLOC_RANGE. Just correct it. Link: https://lkml.kernel.org/r/20240809020115.31575-1-richard.weiyang@gmail.com Signed-off-by: Wei Yang Reviewed-by: Liam R. Howlett Signed-off-by: Andrew Morton --- include/linux/maple_tree.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h index 8e1504a81cd2..c2c11004085e 100644 --- a/include/linux/maple_tree.h +++ b/include/linux/maple_tree.h @@ -52,9 +52,9 @@ * bit in the node type. This is possible by using bit 1 to indicate if bit 2 * is part of the type or the slot. * - * Once the type is decided, the decision of an allocation range type or a range - * type is done by examining the immutable tree flag for the MAPLE_ALLOC_RANGE - * flag. + * Once the type is decided, the decision of an allocation range type or a + * range type is done by examining the immutable tree flag for the + * MT_FLAGS_ALLOC_RANGE flag. * * Node types: * 0x??1 = Root -- cgit v1.2.3 From 4fc4187984e5dbd7ad63c3acf0b228fa9bf298d3 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Mon, 2 Sep 2024 19:55:49 +0900 Subject: lib: zstd: export API needed for dictionary support Patch series "zram: introduce custom comp backends API", v7. This series introduces support for run-time compression algorithms tuning, so users, for instance, can adjust compression/acceleration levels and provide pre-trained compression/decompression dictionaries which certain algorithms support. At this point we stop supporting (old/deprecated) comp API. We may add new acomp API support in the future, but before that zram needs to undergo some major rework (we are not ready for async compression). Some benchmarks for reference (look at column #2) *** init zstd /sys/block/zram0/mm_stat 1750659072 504622188 514355200 0 514355200 1 0 34204 34204 *** init zstd dict=/home/ss/zstd-dict-amd64 /sys/block/zram0/mm_stat 1750650880 465908890 475398144 0 475398144 1 0 34185 34185 *** init zstd level=8 dict=/home/ss/zstd-dict-amd64 /sys/block/zram0/mm_stat 1750654976 430803319 439873536 0 439873536 1 0 34185 34185 *** init lz4 /sys/block/zram0/mm_stat 1750646784 664266564 677060608 0 677060608 1 0 34288 34288 *** init lz4 dict=/home/ss/lz4-dict-amd64 /sys/block/zram0/mm_stat 1750650880 619990300 632102912 0 632102912 1 0 34278 34278 *** init lz4hc /sys/block/zram0/mm_stat 1750630400 609023822 621232128 0 621232128 1 0 34288 34288 *** init lz4hc dict=/home/ss/lz4-dict-amd64 /sys/block/zram0/mm_stat 1750659072 505133172 515231744 0 515231744 1 0 34278 34278 Recompress init zram zstd (prio=0), zstd level=5 (prio 1), zstd with dict (prio 2) *** zstd /sys/block/zram0/mm_stat 1750982656 504630584 514269184 0 514269184 1 0 34204 34204 *** idle recompress priority=1 (zstd level=5) /sys/block/zram0/mm_stat 1750982656 488645601 525438976 0 514269184 1 0 34204 34204 *** idle recompress priority=2 (zstd dict) /sys/block/zram0/mm_stat 1750982656 460869640 517914624 0 514269184 1 0 34185 34204 This patch (of 24): We need to export a number of API functions that enable advanced zstd usage - C/D dictionaries, dictionaries sharing between contexts, etc. Link: https://lkml.kernel.org/r/20240902105656.1383858-1-senozhatsky@chromium.org Link: https://lkml.kernel.org/r/20240902105656.1383858-2-senozhatsky@chromium.org Signed-off-by: Sergey Senozhatsky Cc: Nick Terrell Cc: Minchan Kim Cc: Sergey Senozhatsky Signed-off-by: Andrew Morton --- include/linux/zstd.h | 167 ++++++++++++++++++++++++++++++++++++++ lib/zstd/zstd_compress_module.c | 49 +++++++++++ lib/zstd/zstd_decompress_module.c | 36 ++++++++ 3 files changed, 252 insertions(+) (limited to 'include/linux') diff --git a/include/linux/zstd.h b/include/linux/zstd.h index 113408eef6ec..b2c7cf310c8f 100644 --- a/include/linux/zstd.h +++ b/include/linux/zstd.h @@ -77,6 +77,30 @@ int zstd_min_clevel(void); */ int zstd_max_clevel(void); +/** + * zstd_default_clevel() - default compression level + * + * Return: Default compression level. + */ +int zstd_default_clevel(void); + +/** + * struct zstd_custom_mem - custom memory allocation + */ +typedef ZSTD_customMem zstd_custom_mem; + +/** + * struct zstd_dict_load_method - Dictionary load method. + * See zstd_lib.h. + */ +typedef ZSTD_dictLoadMethod_e zstd_dict_load_method; + +/** + * struct zstd_dict_content_type - Dictionary context type. + * See zstd_lib.h. + */ +typedef ZSTD_dictContentType_e zstd_dict_content_type; + /* ====== Parameter Selection ====== */ /** @@ -136,6 +160,19 @@ typedef ZSTD_parameters zstd_parameters; zstd_parameters zstd_get_params(int level, unsigned long long estimated_src_size); + +/** + * zstd_get_cparams() - returns zstd_compression_parameters for selected level + * @level: The compression level + * @estimated_src_size: The estimated source size to compress or 0 + * if unknown. + * @dict_size: Dictionary size. + * + * Return: The selected zstd_compression_parameters. + */ +zstd_compression_parameters zstd_get_cparams(int level, + unsigned long long estimated_src_size, size_t dict_size); + /* ====== Single-pass Compression ====== */ typedef ZSTD_CCtx zstd_cctx; @@ -180,6 +217,71 @@ zstd_cctx *zstd_init_cctx(void *workspace, size_t workspace_size); size_t zstd_compress_cctx(zstd_cctx *cctx, void *dst, size_t dst_capacity, const void *src, size_t src_size, const zstd_parameters *parameters); +/** + * zstd_create_cctx_advanced() - Create compression context + * @custom_mem: Custom allocator. + * + * Return: NULL on error, pointer to compression context otherwise. + */ +zstd_cctx *zstd_create_cctx_advanced(zstd_custom_mem custom_mem); + +/** + * zstd_free_cctx() - Free compression context + * @cdict: Pointer to compression context. + * + * Return: Always 0. + */ +size_t zstd_free_cctx(zstd_cctx* cctx); + +/** + * struct zstd_cdict - Compression dictionary. + * See zstd_lib.h. + */ +typedef ZSTD_CDict zstd_cdict; + +/** + * zstd_create_cdict_byreference() - Create compression dictionary + * @dict: Pointer to dictionary buffer. + * @dict_size: Size of the dictionary buffer. + * @dict_load_method: Dictionary load method. + * @dict_content_type: Dictionary content type. + * @custom_mem: Memory allocator. + * + * Note, this uses @dict by reference (ZSTD_dlm_byRef), so it should be + * free before zstd_cdict is destroyed. + * + * Return: NULL on error, pointer to compression dictionary + * otherwise. + */ +zstd_cdict *zstd_create_cdict_byreference(const void *dict, size_t dict_size, + zstd_compression_parameters cparams, + zstd_custom_mem custom_mem); + +/** + * zstd_free_cdict() - Free compression dictionary + * @cdict: Pointer to compression dictionary. + * + * Return: Always 0. + */ +size_t zstd_free_cdict(zstd_cdict* cdict); + +/** + * zstd_compress_using_cdict() - compress src into dst using a dictionary + * @cctx: The context. Must have been initialized with zstd_init_cctx(). + * @dst: The buffer to compress src into. + * @dst_capacity: The size of the destination buffer. May be any size, but + * ZSTD_compressBound(srcSize) is guaranteed to be large enough. + * @src: The data to compress. + * @src_size: The size of the data to compress. + * @cdict: The dictionary to be used. + * + * Return: The compressed size or an error, which can be checked using + * zstd_is_error(). + */ +size_t zstd_compress_using_cdict(zstd_cctx *cctx, void *dst, + size_t dst_capacity, const void *src, size_t src_size, + const zstd_cdict *cdict); + /* ====== Single-pass Decompression ====== */ typedef ZSTD_DCtx zstd_dctx; @@ -220,6 +322,71 @@ zstd_dctx *zstd_init_dctx(void *workspace, size_t workspace_size); size_t zstd_decompress_dctx(zstd_dctx *dctx, void *dst, size_t dst_capacity, const void *src, size_t src_size); +/** + * struct zstd_ddict - Decompression dictionary. + * See zstd_lib.h. + */ +typedef ZSTD_DDict zstd_ddict; + +/** + * zstd_create_ddict_byreference() - Create decompression dictionary + * @dict: Pointer to dictionary buffer. + * @dict_size: Size of the dictionary buffer. + * @dict_load_method: Dictionary load method. + * @dict_content_type: Dictionary content type. + * @custom_mem: Memory allocator. + * + * Note, this uses @dict by reference (ZSTD_dlm_byRef), so it should be + * free before zstd_ddict is destroyed. + * + * Return: NULL on error, pointer to decompression dictionary + * otherwise. + */ +zstd_ddict *zstd_create_ddict_byreference(const void *dict, size_t dict_size, + zstd_custom_mem custom_mem); +/** + * zstd_free_ddict() - Free decompression dictionary + * @dict: Pointer to the dictionary. + * + * Return: Always 0. + */ +size_t zstd_free_ddict(zstd_ddict *ddict); + +/** + * zstd_create_dctx_advanced() - Create decompression context + * @custom_mem: Custom allocator. + * + * Return: NULL on error, pointer to decompression context otherwise. + */ +zstd_dctx *zstd_create_dctx_advanced(zstd_custom_mem custom_mem); + +/** + * zstd_free_dctx() -- Free decompression context + * @dctx: Pointer to decompression context. + * Return: Always 0. + */ +size_t zstd_free_dctx(zstd_dctx *dctx); + +/** + * zstd_decompress_using_ddict() - decompress src into dst using a dictionary + * @dctx: The decompression context. + * @dst: The buffer to decompress src into. + * @dst_capacity: The size of the destination buffer. Must be at least as large + * as the decompressed size. If the caller cannot upper bound the + * decompressed size, then it's better to use the streaming API. + * @src: The zstd compressed data to decompress. Multiple concatenated + * frames and skippable frames are allowed. + * @src_size: The exact size of the data to decompress. + * @ddict: The dictionary to be used. + * + * Return: The decompressed size or an error, which can be checked using + * zstd_is_error(). + */ +size_t zstd_decompress_using_ddict(zstd_dctx *dctx, + void *dst, size_t dst_capacity, const void *src, size_t src_size, + const zstd_ddict *ddict); + + /* ====== Streaming Buffers ====== */ /** diff --git a/lib/zstd/zstd_compress_module.c b/lib/zstd/zstd_compress_module.c index 04e1b5c01d9b..bd8784449b31 100644 --- a/lib/zstd/zstd_compress_module.c +++ b/lib/zstd/zstd_compress_module.c @@ -66,6 +66,12 @@ int zstd_max_clevel(void) } EXPORT_SYMBOL(zstd_max_clevel); +int zstd_default_clevel(void) +{ + return ZSTD_defaultCLevel(); +} +EXPORT_SYMBOL(zstd_default_clevel); + size_t zstd_compress_bound(size_t src_size) { return ZSTD_compressBound(src_size); @@ -79,6 +85,13 @@ zstd_parameters zstd_get_params(int level, } EXPORT_SYMBOL(zstd_get_params); +zstd_compression_parameters zstd_get_cparams(int level, + unsigned long long estimated_src_size, size_t dict_size) +{ + return ZSTD_getCParams(level, estimated_src_size, dict_size); +} +EXPORT_SYMBOL(zstd_get_cparams); + size_t zstd_cctx_workspace_bound(const zstd_compression_parameters *cparams) { return ZSTD_estimateCCtxSize_usingCParams(*cparams); @@ -93,6 +106,33 @@ zstd_cctx *zstd_init_cctx(void *workspace, size_t workspace_size) } EXPORT_SYMBOL(zstd_init_cctx); +zstd_cctx *zstd_create_cctx_advanced(zstd_custom_mem custom_mem) +{ + return ZSTD_createCCtx_advanced(custom_mem); +} +EXPORT_SYMBOL(zstd_create_cctx_advanced); + +size_t zstd_free_cctx(zstd_cctx *cctx) +{ + return ZSTD_freeCCtx(cctx); +} +EXPORT_SYMBOL(zstd_free_cctx); + +zstd_cdict *zstd_create_cdict_byreference(const void *dict, size_t dict_size, + zstd_compression_parameters cparams, + zstd_custom_mem custom_mem) +{ + return ZSTD_createCDict_advanced(dict, dict_size, ZSTD_dlm_byRef, + ZSTD_dct_auto, cparams, custom_mem); +} +EXPORT_SYMBOL(zstd_create_cdict_byreference); + +size_t zstd_free_cdict(zstd_cdict *cdict) +{ + return ZSTD_freeCDict(cdict); +} +EXPORT_SYMBOL(zstd_free_cdict); + size_t zstd_compress_cctx(zstd_cctx *cctx, void *dst, size_t dst_capacity, const void *src, size_t src_size, const zstd_parameters *parameters) { @@ -101,6 +141,15 @@ size_t zstd_compress_cctx(zstd_cctx *cctx, void *dst, size_t dst_capacity, } EXPORT_SYMBOL(zstd_compress_cctx); +size_t zstd_compress_using_cdict(zstd_cctx *cctx, void *dst, + size_t dst_capacity, const void *src, size_t src_size, + const ZSTD_CDict *cdict) +{ + return ZSTD_compress_usingCDict(cctx, dst, dst_capacity, + src, src_size, cdict); +} +EXPORT_SYMBOL(zstd_compress_using_cdict); + size_t zstd_cstream_workspace_bound(const zstd_compression_parameters *cparams) { return ZSTD_estimateCStreamSize_usingCParams(*cparams); diff --git a/lib/zstd/zstd_decompress_module.c b/lib/zstd/zstd_decompress_module.c index f4ed952ed485..469fc3059be0 100644 --- a/lib/zstd/zstd_decompress_module.c +++ b/lib/zstd/zstd_decompress_module.c @@ -44,6 +44,33 @@ size_t zstd_dctx_workspace_bound(void) } EXPORT_SYMBOL(zstd_dctx_workspace_bound); +zstd_dctx *zstd_create_dctx_advanced(zstd_custom_mem custom_mem) +{ + return ZSTD_createDCtx_advanced(custom_mem); +} +EXPORT_SYMBOL(zstd_create_dctx_advanced); + +size_t zstd_free_dctx(zstd_dctx *dctx) +{ + return ZSTD_freeDCtx(dctx); +} +EXPORT_SYMBOL(zstd_free_dctx); + +zstd_ddict *zstd_create_ddict_byreference(const void *dict, size_t dict_size, + zstd_custom_mem custom_mem) +{ + return ZSTD_createDDict_advanced(dict, dict_size, ZSTD_dlm_byRef, + ZSTD_dct_auto, custom_mem); + +} +EXPORT_SYMBOL(zstd_create_ddict_byreference); + +size_t zstd_free_ddict(zstd_ddict *ddict) +{ + return ZSTD_freeDDict(ddict); +} +EXPORT_SYMBOL(zstd_free_ddict); + zstd_dctx *zstd_init_dctx(void *workspace, size_t workspace_size) { if (workspace == NULL) @@ -59,6 +86,15 @@ size_t zstd_decompress_dctx(zstd_dctx *dctx, void *dst, size_t dst_capacity, } EXPORT_SYMBOL(zstd_decompress_dctx); +size_t zstd_decompress_using_ddict(zstd_dctx *dctx, + void *dst, size_t dst_capacity, const void* src, size_t src_size, + const zstd_ddict* ddict) +{ + return ZSTD_decompress_usingDDict(dctx, dst, dst_capacity, src, + src_size, ddict); +} +EXPORT_SYMBOL(zstd_decompress_using_ddict); + size_t zstd_dstream_workspace_bound(size_t max_window_size) { return ZSTD_estimateDStreamSize(max_window_size); -- cgit v1.2.3 From e1e4cfd01a6e75dd4c810aeac115340805cf63ff Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Tue, 3 Sep 2024 11:19:28 -0400 Subject: mm,tmpfs: consider end of file write in shmem_is_huge Take the end of a file write into consideration when deciding whether or not to use huge pages for tmpfs files when the tmpfs filesystem is mounted with huge=within_size This allows large writes that append to the end of a file to automatically use large pages. Doing 4MB sequential writes without fallocate to a 16GB tmpfs file with fio. The numbers without THP or with huge=always stay the same, but the performance with huge=within_size now matches that of huge=always. huge before after 4kB pages 1560 MB/s 1560 MB/s within_size 1560 MB/s 4720 MB/s always: 4720 MB/s 4720 MB/s [akpm@linux-foundation.org: coding-style cleanups] Link: https://lkml.kernel.org/r/20240903111928.7171e60c@imladris.surriel.com Signed-off-by: Rik van Riel Reviewed-by: Baolin Wang Tested-by: Baolin Wang Cc: Darrick J. Wong Cc: Hugh Dickins Cc: Matthew Wilcox Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- fs/xfs/scrub/xfile.c | 6 ++--- fs/xfs/xfs_buf_mem.c | 2 +- include/linux/shmem_fs.h | 8 +++---- mm/huge_memory.c | 2 +- mm/khugepaged.c | 2 +- mm/shmem.c | 59 +++++++++++++++++++++++++----------------------- mm/userfaultfd.c | 2 +- 7 files changed, 42 insertions(+), 39 deletions(-) (limited to 'include/linux') diff --git a/fs/xfs/scrub/xfile.c b/fs/xfs/scrub/xfile.c index 9b5d98fe1f8a..c753c79df203 100644 --- a/fs/xfs/scrub/xfile.c +++ b/fs/xfs/scrub/xfile.c @@ -126,7 +126,7 @@ xfile_load( unsigned int len; unsigned int offset; - if (shmem_get_folio(inode, pos >> PAGE_SHIFT, &folio, + if (shmem_get_folio(inode, pos >> PAGE_SHIFT, 0, &folio, SGP_READ) < 0) break; if (!folio) { @@ -196,7 +196,7 @@ xfile_store( unsigned int len; unsigned int offset; - if (shmem_get_folio(inode, pos >> PAGE_SHIFT, &folio, + if (shmem_get_folio(inode, pos >> PAGE_SHIFT, 0, &folio, SGP_CACHE) < 0) break; if (filemap_check_wb_err(inode->i_mapping, 0)) { @@ -267,7 +267,7 @@ xfile_get_folio( i_size_write(inode, pos + len); pflags = memalloc_nofs_save(); - error = shmem_get_folio(inode, pos >> PAGE_SHIFT, &folio, + error = shmem_get_folio(inode, pos >> PAGE_SHIFT, 0, &folio, (flags & XFILE_ALLOC) ? SGP_CACHE : SGP_READ); memalloc_nofs_restore(pflags); if (error) diff --git a/fs/xfs/xfs_buf_mem.c b/fs/xfs/xfs_buf_mem.c index 9bb2d24de709..07bebbfb16ee 100644 --- a/fs/xfs/xfs_buf_mem.c +++ b/fs/xfs/xfs_buf_mem.c @@ -149,7 +149,7 @@ xmbuf_map_page( return -ENOMEM; } - error = shmem_get_folio(inode, pos >> PAGE_SHIFT, &folio, SGP_CACHE); + error = shmem_get_folio(inode, pos >> PAGE_SHIFT, 0, &folio, SGP_CACHE); if (error) return error; diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 1564d7d3ca61..515a9a6a3c6f 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -113,11 +113,11 @@ int shmem_unuse(unsigned int type); #ifdef CONFIG_TRANSPARENT_HUGEPAGE unsigned long shmem_allowable_huge_orders(struct inode *inode, struct vm_area_struct *vma, pgoff_t index, - bool shmem_huge_force); + loff_t write_end, bool shmem_huge_force); #else static inline unsigned long shmem_allowable_huge_orders(struct inode *inode, struct vm_area_struct *vma, pgoff_t index, - bool shmem_huge_force) + loff_t write_end, bool shmem_huge_force) { return 0; } @@ -143,8 +143,8 @@ enum sgp_type { SGP_FALLOC, /* like SGP_WRITE, but make existing page Uptodate */ }; -int shmem_get_folio(struct inode *inode, pgoff_t index, struct folio **foliop, - enum sgp_type sgp); +int shmem_get_folio(struct inode *inode, pgoff_t index, loff_t write_end, + struct folio **foliop, enum sgp_type sgp); struct folio *shmem_read_folio_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 691702e39f85..77092581f90d 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -164,7 +164,7 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, */ if (!in_pf && shmem_file(vma->vm_file)) return shmem_allowable_huge_orders(file_inode(vma->vm_file), - vma, vma->vm_pgoff, + vma, vma->vm_pgoff, 0, !enforce_sysfs); if (!vma_is_anonymous(vma)) { diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 32100041aef3..f9c39898eaff 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1870,7 +1870,7 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, if (xa_is_value(folio) || !folio_test_uptodate(folio)) { xas_unlock_irq(&xas); /* swap in or instantiate fallocated page */ - if (shmem_get_folio(mapping->host, index, + if (shmem_get_folio(mapping->host, index, 0, &folio, SGP_NOALLOC)) { result = SCAN_FAIL; goto xa_unlocked; diff --git a/mm/shmem.c b/mm/shmem.c index 553b99cb265e..74f093d88c78 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -549,7 +549,8 @@ static bool shmem_confirm_swap(struct address_space *mapping, static int shmem_huge __read_mostly = SHMEM_HUGE_NEVER; static bool __shmem_huge_global_enabled(struct inode *inode, pgoff_t index, - bool shmem_huge_force, struct vm_area_struct *vma, + loff_t write_end, bool shmem_huge_force, + struct vm_area_struct *vma, unsigned long vm_flags) { struct mm_struct *mm = vma ? vma->vm_mm : NULL; @@ -569,7 +570,8 @@ static bool __shmem_huge_global_enabled(struct inode *inode, pgoff_t index, return true; case SHMEM_HUGE_WITHIN_SIZE: index = round_up(index + 1, HPAGE_PMD_NR); - i_size = round_up(i_size_read(inode), PAGE_SIZE); + i_size = max(write_end, i_size_read(inode)); + i_size = round_up(i_size, PAGE_SIZE); if (i_size >> PAGE_SHIFT >= index) return true; fallthrough; @@ -583,14 +585,14 @@ static bool __shmem_huge_global_enabled(struct inode *inode, pgoff_t index, } static bool shmem_huge_global_enabled(struct inode *inode, pgoff_t index, - bool shmem_huge_force, struct vm_area_struct *vma, - unsigned long vm_flags) + loff_t write_end, bool shmem_huge_force, + struct vm_area_struct *vma, unsigned long vm_flags) { if (HPAGE_PMD_ORDER > MAX_PAGECACHE_ORDER) return false; - return __shmem_huge_global_enabled(inode, index, shmem_huge_force, - vma, vm_flags); + return __shmem_huge_global_enabled(inode, index, write_end, + shmem_huge_force, vma, vm_flags); } #if defined(CONFIG_SYSFS) @@ -770,8 +772,8 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, } static bool shmem_huge_global_enabled(struct inode *inode, pgoff_t index, - bool shmem_huge_force, struct vm_area_struct *vma, - unsigned long vm_flags) + loff_t write_end, bool shmem_huge_force, + struct vm_area_struct *vma, unsigned long vm_flags) { return false; } @@ -978,7 +980,7 @@ static struct folio *shmem_get_partial_folio(struct inode *inode, pgoff_t index) * (although in some cases this is just a waste of time). */ folio = NULL; - shmem_get_folio(inode, index, &folio, SGP_READ); + shmem_get_folio(inode, index, 0, &folio, SGP_READ); return folio; } @@ -1166,7 +1168,7 @@ static int shmem_getattr(struct mnt_idmap *idmap, STATX_ATTR_NODUMP); generic_fillattr(idmap, request_mask, inode, stat); - if (shmem_huge_global_enabled(inode, 0, false, NULL, 0)) + if (shmem_huge_global_enabled(inode, 0, 0, false, NULL, 0)) stat->blksize = HPAGE_PMD_SIZE; if (request_mask & STATX_BTIME) { @@ -1653,7 +1655,7 @@ static gfp_t limit_gfp_mask(gfp_t huge_gfp, gfp_t limit_gfp) #ifdef CONFIG_TRANSPARENT_HUGEPAGE unsigned long shmem_allowable_huge_orders(struct inode *inode, struct vm_area_struct *vma, pgoff_t index, - bool shmem_huge_force) + loff_t write_end, bool shmem_huge_force) { unsigned long mask = READ_ONCE(huge_shmem_orders_always); unsigned long within_size_orders = READ_ONCE(huge_shmem_orders_within_size); @@ -1670,8 +1672,8 @@ unsigned long shmem_allowable_huge_orders(struct inode *inode, if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED)) return 0; - global_huge = shmem_huge_global_enabled(inode, index, shmem_huge_force, - vma, vm_flags); + global_huge = shmem_huge_global_enabled(inode, index, write_end, + shmem_huge_force, vma, vm_flags); if (!vma || !vma_is_anon_shmem(vma)) { /* * For tmpfs, we now only support PMD sized THP if huge page @@ -2231,8 +2233,8 @@ unlock: * vmf and fault_type are only supplied by shmem_fault: otherwise they are NULL. */ static int shmem_get_folio_gfp(struct inode *inode, pgoff_t index, - struct folio **foliop, enum sgp_type sgp, gfp_t gfp, - struct vm_fault *vmf, vm_fault_t *fault_type) + loff_t write_end, struct folio **foliop, enum sgp_type sgp, + gfp_t gfp, struct vm_fault *vmf, vm_fault_t *fault_type) { struct vm_area_struct *vma = vmf ? vmf->vma : NULL; struct mm_struct *fault_mm; @@ -2312,7 +2314,7 @@ repeat: } /* Find hugepage orders that are allowed for anonymous shmem and tmpfs. */ - orders = shmem_allowable_huge_orders(inode, vma, index, false); + orders = shmem_allowable_huge_orders(inode, vma, index, write_end, false); if (orders > 0) { gfp_t huge_gfp; @@ -2413,6 +2415,7 @@ unlock: * shmem_get_folio - find, and lock a shmem folio. * @inode: inode to search * @index: the page index. + * @write_end: end of a write, could extend inode size * @foliop: pointer to the folio if found * @sgp: SGP_* flags to control behavior * @@ -2432,10 +2435,10 @@ unlock: * Context: May sleep. * Return: 0 if successful, else a negative error code. */ -int shmem_get_folio(struct inode *inode, pgoff_t index, struct folio **foliop, - enum sgp_type sgp) +int shmem_get_folio(struct inode *inode, pgoff_t index, loff_t write_end, + struct folio **foliop, enum sgp_type sgp) { - return shmem_get_folio_gfp(inode, index, foliop, sgp, + return shmem_get_folio_gfp(inode, index, write_end, foliop, sgp, mapping_gfp_mask(inode->i_mapping), NULL, NULL); } EXPORT_SYMBOL_GPL(shmem_get_folio); @@ -2530,7 +2533,7 @@ static vm_fault_t shmem_fault(struct vm_fault *vmf) } WARN_ON_ONCE(vmf->page != NULL); - err = shmem_get_folio_gfp(inode, vmf->pgoff, &folio, SGP_CACHE, + err = shmem_get_folio_gfp(inode, vmf->pgoff, 0, &folio, SGP_CACHE, gfp, vmf, &ret); if (err) return vmf_error(err); @@ -3040,7 +3043,7 @@ shmem_write_begin(struct file *file, struct address_space *mapping, return -EPERM; } - ret = shmem_get_folio(inode, index, &folio, SGP_WRITE); + ret = shmem_get_folio(inode, index, pos + len, &folio, SGP_WRITE); if (ret) return ret; @@ -3111,7 +3114,7 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) break; } - error = shmem_get_folio(inode, index, &folio, SGP_READ); + error = shmem_get_folio(inode, index, 0, &folio, SGP_READ); if (error) { if (error == -EINVAL) error = 0; @@ -3287,7 +3290,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, if (*ppos >= i_size_read(inode)) break; - error = shmem_get_folio(inode, *ppos / PAGE_SIZE, &folio, + error = shmem_get_folio(inode, *ppos / PAGE_SIZE, 0, &folio, SGP_READ); if (error) { if (error == -EINVAL) @@ -3477,8 +3480,8 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, else if (shmem_falloc.nr_unswapped > shmem_falloc.nr_falloced) error = -ENOMEM; else - error = shmem_get_folio(inode, index, &folio, - SGP_FALLOC); + error = shmem_get_folio(inode, index, offset + len, + &folio, SGP_FALLOC); if (error) { info->fallocend = undo_fallocend; /* Remove the !uptodate folios we added */ @@ -3829,7 +3832,7 @@ static int shmem_symlink(struct mnt_idmap *idmap, struct inode *dir, } else { inode_nohighmem(inode); inode->i_mapping->a_ops = &shmem_aops; - error = shmem_get_folio(inode, 0, &folio, SGP_WRITE); + error = shmem_get_folio(inode, 0, 0, &folio, SGP_WRITE); if (error) goto out_remove_offset; inode->i_op = &shmem_symlink_inode_operations; @@ -3875,7 +3878,7 @@ static const char *shmem_get_link(struct dentry *dentry, struct inode *inode, return ERR_PTR(-ECHILD); } } else { - error = shmem_get_folio(inode, 0, &folio, SGP_READ); + error = shmem_get_folio(inode, 0, 0, &folio, SGP_READ); if (error) return ERR_PTR(error); if (!folio) @@ -5343,7 +5346,7 @@ struct folio *shmem_read_folio_gfp(struct address_space *mapping, struct folio *folio; int error; - error = shmem_get_folio_gfp(inode, index, &folio, SGP_CACHE, + error = shmem_get_folio_gfp(inode, index, 0, &folio, SGP_CACHE, gfp, NULL, NULL); if (error) return ERR_PTR(error); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 966e6c81a685..a609b2927848 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -391,7 +391,7 @@ static int mfill_atomic_pte_continue(pmd_t *dst_pmd, struct page *page; int ret; - ret = shmem_get_folio(inode, pgoff, &folio, SGP_NOALLOC); + ret = shmem_get_folio(inode, pgoff, 0, &folio, SGP_NOALLOC); /* Our caller expects us to return -EFAULT if we failed to find folio */ if (ret == -ENOENT) ret = -EFAULT; -- cgit v1.2.3 From 25d4054cc97484f2555709ac233f955f674e026a Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 4 Sep 2024 17:57:59 +0100 Subject: mm: make arch_get_unmapped_area() take vm_flags by default Patch series "mm: Care about shadow stack guard gap when getting an unmapped area", v2. As covered in the commit log for c44357c2e76b ("x86/mm: care about shadow stack guard gap during placement") our current mmap() implementation does not take care to ensure that a new mapping isn't placed with existing mappings inside it's own guard gaps. This is particularly important for shadow stacks since if two shadow stacks end up getting placed adjacent to each other then they can overflow into each other which weakens the protection offered by the feature. On x86 there is a custom arch_get_unmapped_area() which was updated by the above commit to cover this case by specifying a start_gap for allocations with VM_SHADOW_STACK. Both arm64 and RISC-V have equivalent features and use the generic implementation of arch_get_unmapped_area() so let's make the equivalent change there so they also don't get shadow stack pages placed without guard pages. The arm64 and RISC-V shadow stack implementations are currently on the list: https://lore.kernel.org/r/20240829-arm64-gcs-v12-0-42fec94743 https://lore.kernel.org/lkml/20240403234054.2020347-1-debug@rivosinc.com/ Given the addition of the use of vm_flags in the generic implementation we also simplify the set of possibilities that have to be dealt with in the core code by making arch_get_unmapped_area() take vm_flags as standard. This is a bit invasive since the prototype change touches quite a few architectures but since the parameter is ignored the change is straightforward, the simplification for the generic code seems worth it. This patch (of 3): When we introduced arch_get_unmapped_area_vmflags() in 961148704acd ("mm: introduce arch_get_unmapped_area_vmflags()") we did so as part of properly supporting guard pages for shadow stacks on x86_64, which uses a custom arch_get_unmapped_area(). Equivalent features are also present on both arm64 and RISC-V, both of which use the generic implementation of arch_get_unmapped_area() and will require equivalent modification there. Rather than continue to deal with having two versions of the functions let's bite the bullet and have all implementations of arch_get_unmapped_area() take vm_flags as a parameter. The new parameter is currently ignored by all implementations other than x86. The only caller that doesn't have a vm_flags available is mm_get_unmapped_area(), as for the x86 implementation and the wrapper used on other architectures this is modified to supply no flags. No functional changes. Link: https://lkml.kernel.org/r/20240904-mm-generic-shadow-stack-guard-v2-0-a46b8b6dc0ed@kernel.org Link: https://lkml.kernel.org/r/20240904-mm-generic-shadow-stack-guard-v2-1-a46b8b6dc0ed@kernel.org Signed-off-by: Mark Brown Acked-by: Lorenzo Stoakes Reviewed-by: Liam R. Howlett Acked-by: Helge Deller [parisc] Cc: Alexander Gordeev Cc: Andreas Larsson Cc: Borislav Petkov Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Chris Zankel Cc: Dave Hansen Cc: David S. Miller Cc: "Edgecombe, Rick P" Cc: Gerald Schaefer Cc: Guo Ren Cc: Heiko Carstens Cc: "H. Peter Anvin" Cc: Huacai Chen Cc: Ingo Molnar Cc: Ivan Kokshaysky Cc: James Bottomley Cc: John Paul Adrian Glaubitz Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Naveen N Rao Cc: Nicholas Piggin Cc: Richard Henderson Cc: Rich Felker Cc: Russell King Cc: Sven Schnelle Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vineet Gupta Cc: Vlastimil Babka Cc: WANG Xuerui Cc: Yoshinori Sato Signed-off-by: Andrew Morton --- arch/alpha/kernel/osf_sys.c | 2 +- arch/arc/mm/mmap.c | 3 ++- arch/arm/mm/mmap.c | 7 ++++--- arch/csky/abiv1/mmap.c | 3 ++- arch/loongarch/mm/mmap.c | 5 +++-- arch/mips/mm/mmap.c | 5 +++-- arch/parisc/kernel/sys_parisc.c | 5 +++-- arch/parisc/mm/hugetlbpage.c | 2 +- arch/powerpc/mm/book3s64/slice.c | 6 ++++-- arch/s390/mm/mmap.c | 4 ++-- arch/sh/mm/mmap.c | 5 +++-- arch/sparc/kernel/sys_sparc_32.c | 2 +- arch/sparc/kernel/sys_sparc_64.c | 4 ++-- arch/x86/include/asm/pgtable_64.h | 1 - arch/x86/kernel/sys_x86_64.c | 21 +++------------------ arch/xtensa/kernel/syscall.c | 3 ++- include/linux/sched/mm.h | 23 ++++++++--------------- mm/mmap.c | 31 +++++++------------------------ 18 files changed, 51 insertions(+), 81 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index e5f881bc8288..8886ab539273 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -1229,7 +1229,7 @@ arch_get_unmapped_area_1(unsigned long addr, unsigned long len, unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, - unsigned long flags) + unsigned long flags, vm_flags_t vm_flags) { unsigned long limit; diff --git a/arch/arc/mm/mmap.c b/arch/arc/mm/mmap.c index 69a915297155..2185afe8d59f 100644 --- a/arch/arc/mm/mmap.c +++ b/arch/arc/mm/mmap.c @@ -23,7 +23,8 @@ */ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, - unsigned long len, unsigned long pgoff, unsigned long flags) + unsigned long len, unsigned long pgoff, + unsigned long flags, vm_flags_t vm_flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c index d65d0e6ed10a..3dbb383c26d5 100644 --- a/arch/arm/mm/mmap.c +++ b/arch/arm/mm/mmap.c @@ -28,7 +28,8 @@ */ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, - unsigned long len, unsigned long pgoff, unsigned long flags) + unsigned long len, unsigned long pgoff, + unsigned long flags, vm_flags_t vm_flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; @@ -78,8 +79,8 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, - const unsigned long len, const unsigned long pgoff, - const unsigned long flags) + const unsigned long len, const unsigned long pgoff, + const unsigned long flags, vm_flags_t vm_flags) { struct vm_area_struct *vma; struct mm_struct *mm = current->mm; diff --git a/arch/csky/abiv1/mmap.c b/arch/csky/abiv1/mmap.c index 7f826331d409..1047865e82a9 100644 --- a/arch/csky/abiv1/mmap.c +++ b/arch/csky/abiv1/mmap.c @@ -23,7 +23,8 @@ */ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, - unsigned long len, unsigned long pgoff, unsigned long flags) + unsigned long len, unsigned long pgoff, + unsigned long flags, vm_flags_t vm_flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; diff --git a/arch/loongarch/mm/mmap.c b/arch/loongarch/mm/mmap.c index 889030985135..914e82ff3f65 100644 --- a/arch/loongarch/mm/mmap.c +++ b/arch/loongarch/mm/mmap.c @@ -89,7 +89,8 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp, } unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr0, - unsigned long len, unsigned long pgoff, unsigned long flags) + unsigned long len, unsigned long pgoff, unsigned long flags, + vm_flags_t vm_flags) { return arch_get_unmapped_area_common(filp, addr0, len, pgoff, flags, UP); @@ -101,7 +102,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr0, */ unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr0, unsigned long len, unsigned long pgoff, - unsigned long flags) + unsigned long flags, vm_flags_t vm_flags) { return arch_get_unmapped_area_common(filp, addr0, len, pgoff, flags, DOWN); diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c index 7e11d7b58761..5d2a1225785b 100644 --- a/arch/mips/mm/mmap.c +++ b/arch/mips/mm/mmap.c @@ -98,7 +98,8 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp, } unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr0, - unsigned long len, unsigned long pgoff, unsigned long flags) + unsigned long len, unsigned long pgoff, unsigned long flags, + vm_flags_t vm_flags) { return arch_get_unmapped_area_common(filp, addr0, len, pgoff, flags, UP); @@ -110,7 +111,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr0, */ unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr0, unsigned long len, unsigned long pgoff, - unsigned long flags) + unsigned long flags, vm_flags_t vm_flags) { return arch_get_unmapped_area_common(filp, addr0, len, pgoff, flags, DOWN); diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index f7722451276e..f852fe274abe 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -167,7 +167,8 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp, } unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, - unsigned long len, unsigned long pgoff, unsigned long flags) + unsigned long len, unsigned long pgoff, unsigned long flags, + vm_flags_t vm_flags) { return arch_get_unmapped_area_common(filp, addr, len, pgoff, flags, UP); @@ -175,7 +176,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, - unsigned long flags) + unsigned long flags, vm_flags_t vm_flags) { return arch_get_unmapped_area_common(filp, addr, len, pgoff, flags, DOWN); diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c index 0356199bd9e7..aa664f7ddb63 100644 --- a/arch/parisc/mm/hugetlbpage.c +++ b/arch/parisc/mm/hugetlbpage.c @@ -40,7 +40,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, addr = ALIGN(addr, huge_page_size(h)); /* we need to make sure the colouring is OK */ - return arch_get_unmapped_area(file, addr, len, pgoff, flags); + return arch_get_unmapped_area(file, addr, len, pgoff, flags, 0); } diff --git a/arch/powerpc/mm/book3s64/slice.c b/arch/powerpc/mm/book3s64/slice.c index ef3ce37f1bb3..ada6bf896ef8 100644 --- a/arch/powerpc/mm/book3s64/slice.c +++ b/arch/powerpc/mm/book3s64/slice.c @@ -637,7 +637,8 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, - unsigned long flags) + unsigned long flags, + vm_flags_t vm_flags) { if (radix_enabled()) return generic_get_unmapped_area(filp, addr, len, pgoff, flags); @@ -650,7 +651,8 @@ unsigned long arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, const unsigned long len, const unsigned long pgoff, - const unsigned long flags) + const unsigned long flags, + vm_flags_t vm_flags) { if (radix_enabled()) return generic_get_unmapped_area_topdown(filp, addr0, len, pgoff, flags); diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index 206756946589..96efa061ce01 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -82,7 +82,7 @@ static int get_align_mask(struct file *filp, unsigned long flags) unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, - unsigned long flags) + unsigned long flags, vm_flags_t vm_flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; @@ -117,7 +117,7 @@ check_asce_limit: unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, - unsigned long flags) + unsigned long flags, vm_flags_t vm_flags) { struct vm_area_struct *vma; struct mm_struct *mm = current->mm; diff --git a/arch/sh/mm/mmap.c b/arch/sh/mm/mmap.c index bee329d4149a..c442734d9b0c 100644 --- a/arch/sh/mm/mmap.c +++ b/arch/sh/mm/mmap.c @@ -52,7 +52,8 @@ static inline unsigned long COLOUR_ALIGN(unsigned long addr, } unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, - unsigned long len, unsigned long pgoff, unsigned long flags) + unsigned long len, unsigned long pgoff, unsigned long flags, + vm_flags_t vm_flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; @@ -99,7 +100,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, const unsigned long len, const unsigned long pgoff, - const unsigned long flags) + const unsigned long flags, vm_flags_t vm_flags) { struct vm_area_struct *vma; struct mm_struct *mm = current->mm; diff --git a/arch/sparc/kernel/sys_sparc_32.c b/arch/sparc/kernel/sys_sparc_32.c index 08a19727795c..80822f922e76 100644 --- a/arch/sparc/kernel/sys_sparc_32.c +++ b/arch/sparc/kernel/sys_sparc_32.c @@ -39,7 +39,7 @@ SYSCALL_DEFINE0(getpagesize) return PAGE_SIZE; /* Possibly older binaries want 8192 on sun4's? */ } -unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) +unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { struct vm_unmapped_area_info info = {}; diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index d9c3b34ca744..acade309dc2f 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -87,7 +87,7 @@ static inline unsigned long COLOR_ALIGN(unsigned long addr, return base + off; } -unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) +unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { struct mm_struct *mm = current->mm; struct vm_area_struct * vma; @@ -146,7 +146,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi unsigned long arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, const unsigned long len, const unsigned long pgoff, - const unsigned long flags) + const unsigned long flags, vm_flags_t vm_flags) { struct vm_area_struct *vma; struct mm_struct *mm = current->mm; diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 3c4407271d08..7e9db77231ac 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -245,7 +245,6 @@ extern void cleanup_highmap(void); #define HAVE_ARCH_UNMAPPED_AREA #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN -#define HAVE_ARCH_UNMAPPED_AREA_VMFLAGS #define PAGE_AGP PAGE_KERNEL_NOCACHE #define HAVE_PAGE_AGP 1 diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 01d7cd85ef97..87f8c9a71c49 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -121,7 +121,7 @@ static inline unsigned long stack_guard_placement(vm_flags_t vm_flags) } unsigned long -arch_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, unsigned long len, +arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { struct mm_struct *mm = current->mm; @@ -158,7 +158,7 @@ arch_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, unsigned l } unsigned long -arch_get_unmapped_area_topdown_vmflags(struct file *filp, unsigned long addr0, +arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr0, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { @@ -228,20 +228,5 @@ bottomup: * can happen with large stack limits and large mmap() * allocations. */ - return arch_get_unmapped_area(filp, addr0, len, pgoff, flags); -} - -unsigned long -arch_get_unmapped_area(struct file *filp, unsigned long addr, - unsigned long len, unsigned long pgoff, unsigned long flags) -{ - return arch_get_unmapped_area_vmflags(filp, addr, len, pgoff, flags, 0); -} - -unsigned long -arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr, - const unsigned long len, const unsigned long pgoff, - const unsigned long flags) -{ - return arch_get_unmapped_area_topdown_vmflags(filp, addr, len, pgoff, flags, 0); + return arch_get_unmapped_area(filp, addr0, len, pgoff, flags, 0); } diff --git a/arch/xtensa/kernel/syscall.c b/arch/xtensa/kernel/syscall.c index b3c2450d6f23..dc54f854c2f5 100644 --- a/arch/xtensa/kernel/syscall.c +++ b/arch/xtensa/kernel/syscall.c @@ -55,7 +55,8 @@ asmlinkage long xtensa_fadvise64_64(int fd, int advice, #ifdef CONFIG_MMU unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, - unsigned long len, unsigned long pgoff, unsigned long flags) + unsigned long len, unsigned long pgoff, unsigned long flags, + vm_flags_t vm_flags) { struct vm_area_struct *vmm; struct vma_iterator vmi; diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 91546493c43d..c4d34abc45d4 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -179,27 +179,20 @@ static inline void mm_update_next_owner(struct mm_struct *mm) extern void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack); -extern unsigned long -arch_get_unmapped_area(struct file *, unsigned long, unsigned long, - unsigned long, unsigned long); -extern unsigned long + +unsigned long +arch_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags, vm_flags_t vm_flags); +unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, - unsigned long len, unsigned long pgoff, - unsigned long flags); + unsigned long len, unsigned long pgoff, + unsigned long flags, vm_flags_t); unsigned long mm_get_unmapped_area(struct mm_struct *mm, struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); -unsigned long -arch_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, - unsigned long len, unsigned long pgoff, - unsigned long flags, vm_flags_t vm_flags); -unsigned long -arch_get_unmapped_area_topdown_vmflags(struct file *filp, unsigned long addr, - unsigned long len, unsigned long pgoff, - unsigned long flags, vm_flags_t); - unsigned long mm_get_unmapped_area_vmflags(struct mm_struct *mm, struct file *filp, unsigned long addr, diff --git a/mm/mmap.c b/mm/mmap.c index 02f7b45c3076..98249266196e 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -770,7 +770,7 @@ generic_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, - unsigned long flags) + unsigned long flags, vm_flags_t vm_flags) { return generic_get_unmapped_area(filp, addr, len, pgoff, flags); } @@ -834,38 +834,21 @@ generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, - unsigned long flags) + unsigned long flags, vm_flags_t vm_flags) { return generic_get_unmapped_area_topdown(filp, addr, len, pgoff, flags); } #endif -#ifndef HAVE_ARCH_UNMAPPED_AREA_VMFLAGS -unsigned long -arch_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, unsigned long len, - unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) -{ - return arch_get_unmapped_area(filp, addr, len, pgoff, flags); -} - -unsigned long -arch_get_unmapped_area_topdown_vmflags(struct file *filp, unsigned long addr, - unsigned long len, unsigned long pgoff, - unsigned long flags, vm_flags_t vm_flags) -{ - return arch_get_unmapped_area_topdown(filp, addr, len, pgoff, flags); -} -#endif - unsigned long mm_get_unmapped_area_vmflags(struct mm_struct *mm, struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { if (test_bit(MMF_TOPDOWN, &mm->flags)) - return arch_get_unmapped_area_topdown_vmflags(filp, addr, len, pgoff, - flags, vm_flags); - return arch_get_unmapped_area_vmflags(filp, addr, len, pgoff, flags, vm_flags); + return arch_get_unmapped_area_topdown(filp, addr, len, pgoff, + flags, vm_flags); + return arch_get_unmapped_area(filp, addr, len, pgoff, flags, vm_flags); } unsigned long @@ -927,8 +910,8 @@ mm_get_unmapped_area(struct mm_struct *mm, struct file *file, unsigned long pgoff, unsigned long flags) { if (test_bit(MMF_TOPDOWN, &mm->flags)) - return arch_get_unmapped_area_topdown(file, addr, len, pgoff, flags); - return arch_get_unmapped_area(file, addr, len, pgoff, flags); + return arch_get_unmapped_area_topdown(file, addr, len, pgoff, flags, 0); + return arch_get_unmapped_area(file, addr, len, pgoff, flags, 0); } EXPORT_SYMBOL(mm_get_unmapped_area); -- cgit v1.2.3 From 540e00a729dfbefe0aa0d64b6dac1d1b620a1787 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 4 Sep 2024 17:58:00 +0100 Subject: mm: pass vm_flags to generic_get_unmapped_area() In preparation for using vm_flags to ensure guard pages for shadow stacks supply them as an argument to generic_get_unmapped_area(). The only user outside of the core code is the PowerPC book3s64 implementation which is trivially wrapping the generic implementation in the radix_enabled() case. No functional changes. Link: https://lkml.kernel.org/r/20240904-mm-generic-shadow-stack-guard-v2-2-a46b8b6dc0ed@kernel.org Signed-off-by: Mark Brown Acked-by: Lorenzo Stoakes Reviewed-by: Liam R. Howlett Acked-by: Michael Ellerman Cc: Alexander Gordeev Cc: Andreas Larsson Cc: Borislav Petkov Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Chris Zankel Cc: Dave Hansen Cc: David S. Miller Cc: "Edgecombe, Rick P" Cc: Gerald Schaefer Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: "H. Peter Anvin" Cc: Huacai Chen Cc: Ingo Molnar Cc: Ivan Kokshaysky Cc: James Bottomley Cc: John Paul Adrian Glaubitz Cc: Matt Turner Cc: Max Filippov Cc: Naveen N Rao Cc: Nicholas Piggin Cc: Richard Henderson Cc: Rich Felker Cc: Russell King Cc: Sven Schnelle Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vineet Gupta Cc: Vlastimil Babka Cc: WANG Xuerui Cc: Yoshinori Sato Signed-off-by: Andrew Morton --- arch/powerpc/mm/book3s64/slice.c | 4 ++-- include/linux/sched/mm.h | 4 ++-- mm/mmap.c | 10 ++++++---- 3 files changed, 10 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/mm/book3s64/slice.c b/arch/powerpc/mm/book3s64/slice.c index ada6bf896ef8..87307d0fc3b8 100644 --- a/arch/powerpc/mm/book3s64/slice.c +++ b/arch/powerpc/mm/book3s64/slice.c @@ -641,7 +641,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, vm_flags_t vm_flags) { if (radix_enabled()) - return generic_get_unmapped_area(filp, addr, len, pgoff, flags); + return generic_get_unmapped_area(filp, addr, len, pgoff, flags, vm_flags); return slice_get_unmapped_area(addr, len, flags, mm_ctx_user_psize(¤t->mm->context), 0); @@ -655,7 +655,7 @@ unsigned long arch_get_unmapped_area_topdown(struct file *filp, vm_flags_t vm_flags) { if (radix_enabled()) - return generic_get_unmapped_area_topdown(filp, addr0, len, pgoff, flags); + return generic_get_unmapped_area_topdown(filp, addr0, len, pgoff, flags, vm_flags); return slice_get_unmapped_area(addr0, len, flags, mm_ctx_user_psize(¤t->mm->context), 1); diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index c4d34abc45d4..07bb8d4181d7 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -204,11 +204,11 @@ unsigned long mm_get_unmapped_area_vmflags(struct mm_struct *mm, unsigned long generic_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, - unsigned long flags); + unsigned long flags, vm_flags_t vm_flags); unsigned long generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, - unsigned long flags); + unsigned long flags, vm_flags_t vm_flags); #else static inline void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) {} diff --git a/mm/mmap.c b/mm/mmap.c index 98249266196e..14d36be65ce7 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -738,7 +738,7 @@ unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info) unsigned long generic_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, - unsigned long flags) + unsigned long flags, vm_flags_t vm_flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; @@ -772,7 +772,8 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { - return generic_get_unmapped_area(filp, addr, len, pgoff, flags); + return generic_get_unmapped_area(filp, addr, len, pgoff, flags, + vm_flags); } #endif @@ -783,7 +784,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, - unsigned long flags) + unsigned long flags, vm_flags_t vm_flags) { struct vm_area_struct *vma, *prev; struct mm_struct *mm = current->mm; @@ -836,7 +837,8 @@ arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { - return generic_get_unmapped_area_topdown(filp, addr, len, pgoff, flags); + return generic_get_unmapped_area_topdown(filp, addr, len, pgoff, flags, + vm_flags); } #endif -- cgit v1.2.3 From 08e28de1160a712724268fd33d77b32f1bc84d1c Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Tue, 3 Sep 2024 09:36:28 +0200 Subject: uprobes: use vm_special_mapping close() functionality The following KASAN splat was shown: [ 44.505448] ================================================================== 20:37:27 [3421/145075] [ 44.505455] BUG: KASAN: slab-use-after-free in special_mapping_close+0x9c/0xc8 [ 44.505471] Read of size 8 at addr 00000000868dac48 by task sh/1384 [ 44.505479] [ 44.505486] CPU: 51 UID: 0 PID: 1384 Comm: sh Not tainted 6.11.0-rc6-next-20240902-dirty #1496 [ 44.505503] Hardware name: IBM 3931 A01 704 (z/VM 7.3.0) [ 44.505508] Call Trace: [ 44.505511] [<000b0324d2f78080>] dump_stack_lvl+0xd0/0x108 [ 44.505521] [<000b0324d2f5435c>] print_address_description.constprop.0+0x34/0x2e0 [ 44.505529] [<000b0324d2f5464c>] print_report+0x44/0x138 [ 44.505536] [<000b0324d1383192>] kasan_report+0xc2/0x140 [ 44.505543] [<000b0324d2f52904>] special_mapping_close+0x9c/0xc8 [ 44.505550] [<000b0324d12c7978>] remove_vma+0x78/0x120 [ 44.505557] [<000b0324d128a2c6>] exit_mmap+0x326/0x750 [ 44.505563] [<000b0324d0ba655a>] __mmput+0x9a/0x370 [ 44.505570] [<000b0324d0bbfbe0>] exit_mm+0x240/0x340 [ 44.505575] [<000b0324d0bc0228>] do_exit+0x548/0xd70 [ 44.505580] [<000b0324d0bc1102>] do_group_exit+0x132/0x390 [ 44.505586] [<000b0324d0bc13b6>] __s390x_sys_exit_group+0x56/0x60 [ 44.505592] [<000b0324d0adcbd6>] do_syscall+0x2f6/0x430 [ 44.505599] [<000b0324d2f78434>] __do_syscall+0xa4/0x170 [ 44.505606] [<000b0324d2f9454c>] system_call+0x74/0x98 [ 44.505614] [ 44.505616] Allocated by task 1384: [ 44.505621] kasan_save_stack+0x40/0x70 [ 44.505630] kasan_save_track+0x28/0x40 [ 44.505636] __kasan_kmalloc+0xa0/0xc0 [ 44.505642] __create_xol_area+0xfa/0x410 [ 44.505648] get_xol_area+0xb0/0xf0 [ 44.505652] uprobe_notify_resume+0x27a/0x470 [ 44.505657] irqentry_exit_to_user_mode+0x15e/0x1d0 [ 44.505664] pgm_check_handler+0x122/0x170 [ 44.505670] [ 44.505672] Freed by task 1384: [ 44.505676] kasan_save_stack+0x40/0x70 [ 44.505682] kasan_save_track+0x28/0x40 [ 44.505687] kasan_save_free_info+0x4a/0x70 [ 44.505693] __kasan_slab_free+0x5a/0x70 [ 44.505698] kfree+0xe8/0x3f0 [ 44.505704] __mmput+0x20/0x370 [ 44.505709] exit_mm+0x240/0x340 [ 44.505713] do_exit+0x548/0xd70 [ 44.505718] do_group_exit+0x132/0x390 [ 44.505722] __s390x_sys_exit_group+0x56/0x60 [ 44.505727] do_syscall+0x2f6/0x430 [ 44.505732] __do_syscall+0xa4/0x170 [ 44.505738] system_call+0x74/0x98 The problem is that uprobe_clear_state() kfree's struct xol_area, which contains struct vm_special_mapping *xol_mapping. This one is passed to _install_special_mapping() in xol_add_vma(). __mput reads: static inline void __mmput(struct mm_struct *mm) { VM_BUG_ON(atomic_read(&mm->mm_users)); uprobe_clear_state(mm); exit_aio(mm); ksm_exit(mm); khugepaged_exit(mm); /* must run before exit_mmap */ exit_mmap(mm); ... } So uprobe_clear_state() in the beginning free's the memory area containing the vm_special_mapping data, but exit_mmap() uses this address later via vma->vm_private_data (which was set in _install_special_mapping(). Fix this by moving uprobe_clear_state() to uprobes.c and use it as close() callback. [usama.anjum@collabora.com: remove unneeded condition] Link: https://lkml.kernel.org/r/20240906101825.177490-1-usama.anjum@collabora.com Link: https://lkml.kernel.org/r/20240903073629.2442754-1-svens@linux.ibm.com Fixes: 223febc6e557 ("mm: add optional close() to struct vm_special_mapping") Signed-off-by: Sven Schnelle Suggested-by: Linus Torvalds Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Masami Hiramatsu Cc: Michael Ellerman Cc: Namhyung Kim Cc: Oleg Nesterov Cc: Peter Zijlstra Signed-off-by: Andrew Morton --- include/linux/uprobes.h | 1 - kernel/events/uprobes.c | 36 +++++++++++++++++------------------- kernel/fork.c | 1 - 3 files changed, 17 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index b503fafb7fb3..493dc95d912c 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -126,7 +126,6 @@ extern int uprobe_pre_sstep_notifier(struct pt_regs *regs); extern void uprobe_notify_resume(struct pt_regs *regs); extern bool uprobe_deny_signal(void); extern bool arch_uprobe_skip_sstep(struct arch_uprobe *aup, struct pt_regs *regs); -extern void uprobe_clear_state(struct mm_struct *mm); extern int arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long addr); extern int arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs); extern int arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs); diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 73cc47708679..c2d6b2d64de2 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1482,6 +1482,22 @@ void * __weak arch_uprobe_trampoline(unsigned long *psize) return &insn; } +/* + * uprobe_clear_state - Free the area allocated for slots. + */ +static void uprobe_clear_state(const struct vm_special_mapping *sm, struct vm_area_struct *vma) +{ + struct xol_area *area = container_of(vma->vm_private_data, struct xol_area, xol_mapping); + + mutex_lock(&delayed_uprobe_lock); + delayed_uprobe_remove(NULL, vma->vm_mm); + mutex_unlock(&delayed_uprobe_lock); + + put_page(area->pages[0]); + kfree(area->bitmap); + kfree(area); +} + static struct xol_area *__create_xol_area(unsigned long vaddr) { struct mm_struct *mm = current->mm; @@ -1500,6 +1516,7 @@ static struct xol_area *__create_xol_area(unsigned long vaddr) area->xol_mapping.name = "[uprobes]"; area->xol_mapping.fault = NULL; + area->xol_mapping.close = uprobe_clear_state; area->xol_mapping.pages = area->pages; area->pages[0] = alloc_page(GFP_HIGHUSER); if (!area->pages[0]) @@ -1545,25 +1562,6 @@ static struct xol_area *get_xol_area(void) return area; } -/* - * uprobe_clear_state - Free the area allocated for slots. - */ -void uprobe_clear_state(struct mm_struct *mm) -{ - struct xol_area *area = mm->uprobes_state.xol_area; - - mutex_lock(&delayed_uprobe_lock); - delayed_uprobe_remove(NULL, mm); - mutex_unlock(&delayed_uprobe_lock); - - if (!area) - return; - - put_page(area->pages[0]); - kfree(area->bitmap); - kfree(area); -} - void uprobe_start_dup_mmap(void) { percpu_down_read(&dup_mmap_sem); diff --git a/kernel/fork.c b/kernel/fork.c index 3d590e51ce84..61070248a7d3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1338,7 +1338,6 @@ static inline void __mmput(struct mm_struct *mm) { VM_BUG_ON(atomic_read(&mm->mm_users)); - uprobe_clear_state(mm); exit_aio(mm); ksm_exit(mm); khugepaged_exit(mm); /* must run before exit_mmap */ -- cgit v1.2.3 From 0e40cf2a8b2c847950e025d5aa594bd545118d26 Mon Sep 17 00:00:00 2001 From: Kinsey Ho Date: Thu, 5 Sep 2024 00:30:50 +0000 Subject: cgroup: clarify css sibling linkage is protected by cgroup_mutex or RCU MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "Improve mem_cgroup_iter()", v4. Incremental cgroup iteration is being used again [1]. This patchset improves the reliability of mem_cgroup_iter(). It also improves simplicity and code readability. [1] https://lore.kernel.org/20240514202641.2821494-1-hannes@cmpxchg.org/ This patch (of 5): Explicitly document that css sibling/descendant linkage is protected by cgroup_mutex or RCU. Also, document in css_next_descendant_pre() and similar functions that it isn't necessary to hold a ref on @pos. The following changes in this patchset rely on this clarification for simplification in memcg iteration code. Link: https://lkml.kernel.org/r/20240905003058.1859929-1-kinseyho@google.com Link: https://lkml.kernel.org/r/20240905003058.1859929-2-kinseyho@google.com Suggested-by: Yosry Ahmed Reviewed-by: Michal Koutný Signed-off-by: Kinsey Ho Cc: Johannes Weiner Cc: Michal Hocko Cc: Muchun Song Cc: Roman Gushchin Cc: Shakeel Butt Cc: Tejun Heo Cc: Zefan Li Cc: Hugh Dickins Cc: T.J. Mercier Signed-off-by: Andrew Morton --- include/linux/cgroup-defs.h | 6 +++++- kernel/cgroup/cgroup.c | 16 +++++++++------- 2 files changed, 14 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 7fc2d0195f56..ca7e912b8355 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -172,7 +172,11 @@ struct cgroup_subsys_state { /* reference count - access via css_[try]get() and css_put() */ struct percpu_ref refcnt; - /* siblings list anchored at the parent's ->children */ + /* + * siblings list anchored at the parent's ->children + * + * linkage is protected by cgroup_mutex or RCU + */ struct list_head sibling; struct list_head children; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 0a97cb2ef124..ece2316e2bca 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -4602,8 +4602,9 @@ struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, * * While this function requires cgroup_mutex or RCU read locking, it * doesn't require the whole traversal to be contained in a single critical - * section. This function will return the correct next descendant as long - * as both @pos and @root are accessible and @pos is a descendant of @root. + * section. Additionally, it isn't necessary to hold onto a reference to @pos. + * This function will return the correct next descendant as long as both @pos + * and @root are accessible and @pos is a descendant of @root. * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the @@ -4651,8 +4652,9 @@ EXPORT_SYMBOL_GPL(css_next_descendant_pre); * * While this function requires cgroup_mutex or RCU read locking, it * doesn't require the whole traversal to be contained in a single critical - * section. This function will return the correct rightmost descendant as - * long as @pos is accessible. + * section. Additionally, it isn't necessary to hold onto a reference to @pos. + * This function will return the correct rightmost descendant as long as @pos + * is accessible. */ struct cgroup_subsys_state * css_rightmost_descendant(struct cgroup_subsys_state *pos) @@ -4696,9 +4698,9 @@ css_leftmost_descendant(struct cgroup_subsys_state *pos) * * While this function requires cgroup_mutex or RCU read locking, it * doesn't require the whole traversal to be contained in a single critical - * section. This function will return the correct next descendant as long - * as both @pos and @cgroup are accessible and @pos is a descendant of - * @cgroup. + * section. Additionally, it isn't necessary to hold onto a reference to @pos. + * This function will return the correct next descendant as long as both @pos + * and @cgroup are accessible and @pos is a descendant of @cgroup. * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the -- cgit v1.2.3 From ec0db74b4b1f249ffca4df450f54c17573114045 Mon Sep 17 00:00:00 2001 From: Kinsey Ho Date: Thu, 5 Sep 2024 00:30:53 +0000 Subject: mm: restart if multiple traversals raced MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently, if multiple reclaimers raced on the same position, the reclaimers which detect the race will still reclaim from the same memcg. Instead, the reclaimers which detect the race should move on to the next memcg in the hierarchy. So, in the case where multiple traversals race, jump back to the start of the mem_cgroup_iter() function to find the next memcg in the hierarchy to reclaim from. Link: https://lkml.kernel.org/r/20240905003058.1859929-5-kinseyho@google.com Reported-by: syzbot+e099d407346c45275ce9@syzkaller.appspotmail.com Closes: https://lore.kernel.org/000000000000817cf10620e20d33@google.com/ Signed-off-by: Kinsey Ho Reviewed-by: T.J. Mercier Cc: Johannes Weiner Cc: Michal Hocko Cc: Michal Koutný Cc: Muchun Song Cc: Roman Gushchin Cc: Shakeel Butt Cc: Tejun Heo Cc: Yosry Ahmed Cc: Zefan Li Cc: Hugh Dickins Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 4 ++-- mm/memcontrol.c | 26 +++++++++++++++++--------- 2 files changed, 19 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index fe05fdb92779..2ef94c74847d 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -57,7 +57,7 @@ enum memcg_memory_event { struct mem_cgroup_reclaim_cookie { pg_data_t *pgdat; - unsigned int generation; + int generation; }; #ifdef CONFIG_MEMCG @@ -78,7 +78,7 @@ struct lruvec_stats; struct mem_cgroup_reclaim_iter { struct mem_cgroup *position; /* scan generation, increased every round-trip */ - unsigned int generation; + atomic_t generation; }; /* diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 38e3251ed482..36cbc7730745 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -986,8 +986,8 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, struct mem_cgroup_reclaim_cookie *reclaim) { struct mem_cgroup_reclaim_iter *iter; - struct cgroup_subsys_state *css = NULL; - struct mem_cgroup *memcg = NULL; + struct cgroup_subsys_state *css; + struct mem_cgroup *memcg; struct mem_cgroup *pos = NULL; if (mem_cgroup_disabled()) @@ -998,19 +998,23 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, rcu_read_lock(); restart: + memcg = NULL; + if (reclaim) { + int gen; struct mem_cgroup_per_node *mz; mz = root->nodeinfo[reclaim->pgdat->node_id]; iter = &mz->iter; + gen = atomic_read(&iter->generation); /* * On start, join the current reclaim iteration cycle. * Exit when a concurrent walker completes it. */ if (!prev) - reclaim->generation = iter->generation; - else if (reclaim->generation != iter->generation) + reclaim->generation = gen; + else if (reclaim->generation != gen) goto out_unlock; pos = READ_ONCE(iter->position); @@ -1018,8 +1022,7 @@ restart: pos = prev; } - if (pos) - css = &pos->css; + css = pos ? &pos->css : NULL; for (;;) { css = css_next_descendant_pre(css, &root->css); @@ -1033,21 +1036,26 @@ restart: * and kicking, and don't take an extra reference. */ if (css == &root->css || css_tryget(css)) { - memcg = mem_cgroup_from_css(css); break; } } + memcg = mem_cgroup_from_css(css); + if (reclaim) { /* * The position could have already been updated by a competing * thread, so check that the value hasn't changed since we read * it to avoid reclaiming from the same cgroup twice. */ - (void)cmpxchg(&iter->position, pos, memcg); + if (cmpxchg(&iter->position, pos, memcg) != pos) { + if (css && css != &root->css) + css_put(css); + goto restart; + } if (!memcg) { - iter->generation++; + atomic_inc(&iter->generation); /* * Reclaimers share the hierarchy walk, and a -- cgit v1.2.3 From eebc0f48468e68b93393d11f75ad17385a9acca8 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Thu, 5 Sep 2024 22:21:06 -0600 Subject: mm/codetag: fix a typo Link: https://lkml.kernel.org/r/20240906042108.1150526-1-yuzhao@google.com Fixes: 22d407b164ff ("lib: add allocation tagging support for memory allocation profiling") Signed-off-by: Yu Zhao Acked-by: Suren Baghdasaryan Acked-by: Muchun Song Cc: Kent Overstreet Signed-off-by: Andrew Morton --- include/linux/alloc_tag.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h index 8c61ccd161ba..896491d9ebe8 100644 --- a/include/linux/alloc_tag.h +++ b/include/linux/alloc_tag.h @@ -70,7 +70,7 @@ static inline struct alloc_tag *ct_to_alloc_tag(struct codetag *ct) /* * When percpu variables are required to be defined as weak, static percpu * variables can't be used inside a function (see comments for DECLARE_PER_CPU_SECTION). - * Instead we will accound all module allocations to a single counter. + * Instead we will account all module allocations to a single counter. */ DECLARE_PER_CPU(struct alloc_tag_counters, _shared_alloc_tag); -- cgit v1.2.3 From 95599ef684d01136a8b77c16a7c853496786e173 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Thu, 5 Sep 2024 22:21:07 -0600 Subject: mm/codetag: fix pgalloc_tag_split() The current assumption is that a large folio can only be split into order-0 folios. That is not the case for hugeTLB demotion, nor for THP split: see commit c010d47f107f ("mm: thp: split huge page to any lower order pages"). When a large folio is split into ones of a lower non-zero order, only the new head pages should be tagged. Tagging tail pages can cause imbalanced "calls" counters, since only head pages are untagged by pgalloc_tag_sub() and the "calls" counts on tail pages are leaked, e.g., # echo 2048kB >/sys/kernel/mm/hugepages/hugepages-1048576kB/demote_size # echo 700 >/sys/kernel/mm/hugepages/hugepages-1048576kB/nr_hugepages # time echo 700 >/sys/kernel/mm/hugepages/hugepages-1048576kB/demote # echo 0 >/sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages # grep alloc_gigantic_folio /proc/allocinfo Before this patch: 0 549427200 mm/hugetlb.c:1549 func:alloc_gigantic_folio real 0m2.057s user 0m0.000s sys 0m2.051s After this patch: 0 0 mm/hugetlb.c:1549 func:alloc_gigantic_folio real 0m1.711s user 0m0.000s sys 0m1.704s Not tagging tail pages also improves the splitting time, e.g., by about 15% when demoting 1GB hugeTLB folios to 2MB ones, as shown above. Link: https://lkml.kernel.org/r/20240906042108.1150526-2-yuzhao@google.com Fixes: be25d1d4e822 ("mm: create new codetag references during page splitting") Signed-off-by: Yu Zhao Acked-by: Suren Baghdasaryan Cc: Kent Overstreet Cc: Muchun Song Cc: Signed-off-by: Andrew Morton --- include/linux/mm.h | 30 ++++++++++++++++++++++++++++++ include/linux/pgalloc_tag.h | 31 ------------------------------- mm/huge_memory.c | 2 +- mm/hugetlb.c | 2 +- mm/page_alloc.c | 4 ++-- 5 files changed, 34 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index b0ff06d18c71..6bb778cbaabf 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -4084,4 +4084,34 @@ void vma_pgtable_walk_end(struct vm_area_struct *vma); int reserve_mem_find_by_name(const char *name, phys_addr_t *start, phys_addr_t *size); +#ifdef CONFIG_MEM_ALLOC_PROFILING +static inline void pgalloc_tag_split(struct folio *folio, int old_order, int new_order) +{ + int i; + struct alloc_tag *tag; + unsigned int nr_pages = 1 << new_order; + + if (!mem_alloc_profiling_enabled()) + return; + + tag = pgalloc_tag_get(&folio->page); + if (!tag) + return; + + for (i = nr_pages; i < (1 << old_order); i += nr_pages) { + union codetag_ref *ref = get_page_tag_ref(folio_page(folio, i)); + + if (ref) { + /* Set new reference to point to the original tag */ + alloc_tag_ref_set(ref, tag); + put_page_tag_ref(ref); + } + } +} +#else /* !CONFIG_MEM_ALLOC_PROFILING */ +static inline void pgalloc_tag_split(struct folio *folio, int old_order, int new_order) +{ +} +#endif /* CONFIG_MEM_ALLOC_PROFILING */ + #endif /* _LINUX_MM_H */ diff --git a/include/linux/pgalloc_tag.h b/include/linux/pgalloc_tag.h index 207f0c83c8e9..59a3deb792a8 100644 --- a/include/linux/pgalloc_tag.h +++ b/include/linux/pgalloc_tag.h @@ -80,36 +80,6 @@ static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) } } -static inline void pgalloc_tag_split(struct page *page, unsigned int nr) -{ - int i; - struct page_ext *first_page_ext; - struct page_ext *page_ext; - union codetag_ref *ref; - struct alloc_tag *tag; - - if (!mem_alloc_profiling_enabled()) - return; - - first_page_ext = page_ext = page_ext_get(page); - if (unlikely(!page_ext)) - return; - - ref = codetag_ref_from_page_ext(page_ext); - if (!ref->ct) - goto out; - - tag = ct_to_alloc_tag(ref->ct); - page_ext = page_ext_next(page_ext); - for (i = 1; i < nr; i++) { - /* Set new reference to point to the original tag */ - alloc_tag_ref_set(codetag_ref_from_page_ext(page_ext), tag); - page_ext = page_ext_next(page_ext); - } -out: - page_ext_put(first_page_ext); -} - static inline struct alloc_tag *pgalloc_tag_get(struct page *page) { struct alloc_tag *tag = NULL; @@ -142,7 +112,6 @@ static inline void clear_page_tag_ref(struct page *page) {} static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, unsigned int nr) {} static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) {} -static inline void pgalloc_tag_split(struct page *page, unsigned int nr) {} static inline struct alloc_tag *pgalloc_tag_get(struct page *page) { return NULL; } static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) {} diff --git a/mm/huge_memory.c b/mm/huge_memory.c index f15f7faf2a63..cc2872f12030 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3226,7 +3226,7 @@ static void __split_huge_page(struct page *page, struct list_head *list, /* Caller disabled irqs, so they are still disabled here */ split_page_owner(head, order, new_order); - pgalloc_tag_split(head, 1 << order); + pgalloc_tag_split(folio, order, new_order); /* See comment in __split_huge_page_tail() */ if (folio_test_anon(folio)) { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3faf5aad142d..a8624c07d8bf 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3778,7 +3778,7 @@ static long demote_free_hugetlb_folios(struct hstate *src, struct hstate *dst, list_del(&folio->lru); split_page_owner(&folio->page, huge_page_order(src), huge_page_order(dst)); - pgalloc_tag_split(&folio->page, 1 << huge_page_order(src)); + pgalloc_tag_split(folio, huge_page_order(src), huge_page_order(dst)); for (i = 0; i < pages_per_huge_page(src); i += pages_per_huge_page(dst)) { struct page *page = folio_page(folio, i); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 74f13f676985..874e006f3d1c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2776,7 +2776,7 @@ void split_page(struct page *page, unsigned int order) for (i = 1; i < (1 << order); i++) set_page_refcounted(page + i); split_page_owner(page, order, 0); - pgalloc_tag_split(page, 1 << order); + pgalloc_tag_split(page_folio(page), order, 0); split_page_memcg(page, order, 0); } EXPORT_SYMBOL_GPL(split_page); @@ -4974,7 +4974,7 @@ static void *make_alloc_exact(unsigned long addr, unsigned int order, struct page *last = page + nr; split_page_owner(page, order, 0); - pgalloc_tag_split(page, 1 << order); + pgalloc_tag_split(page_folio(page), order, 0); split_page_memcg(page, order, 0); while (page < --last) set_page_refcounted(last); -- cgit v1.2.3 From e0a955bf7f61cb034d228736d81c1ab3a47a3dca Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Thu, 5 Sep 2024 22:21:08 -0600 Subject: mm/codetag: add pgalloc_tag_copy() Add pgalloc_tag_copy() to transfer the codetag from the old folio to the new one during migration. This makes original allocation sites persist cross migration rather than lump into the get_new_folio callbacks passed into migrate_pages(), e.g., compaction_alloc(): # echo 1 >/proc/sys/vm/compact_memory # grep compaction_alloc /proc/allocinfo Before this patch: 132968448 32463 mm/compaction.c:1880 func:compaction_alloc After this patch: 0 0 mm/compaction.c:1880 func:compaction_alloc Link: https://lkml.kernel.org/r/20240906042108.1150526-3-yuzhao@google.com Fixes: dcfe378c81f7 ("lib: introduce support for page allocation tagging") Signed-off-by: Yu Zhao Acked-by: Suren Baghdasaryan Cc: Kent Overstreet Cc: Muchun Song Cc: Signed-off-by: Andrew Morton --- include/linux/alloc_tag.h | 24 ++++++++++-------------- include/linux/mm.h | 27 +++++++++++++++++++++++++++ mm/migrate.c | 1 + 3 files changed, 38 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h index 896491d9ebe8..1f0a9ff23a2c 100644 --- a/include/linux/alloc_tag.h +++ b/include/linux/alloc_tag.h @@ -137,7 +137,16 @@ static inline void alloc_tag_sub_check(union codetag_ref *ref) {} /* Caller should verify both ref and tag to be valid */ static inline void __alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag) { + alloc_tag_add_check(ref, tag); + if (!ref || !tag) + return; + ref->ct = &tag->ct; +} + +static inline void alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag) +{ + __alloc_tag_ref_set(ref, tag); /* * We need in increment the call counter every time we have a new * allocation or when we split a large allocation into smaller ones. @@ -147,22 +156,9 @@ static inline void __alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag this_cpu_inc(tag->counters->calls); } -static inline void alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag) -{ - alloc_tag_add_check(ref, tag); - if (!ref || !tag) - return; - - __alloc_tag_ref_set(ref, tag); -} - static inline void alloc_tag_add(union codetag_ref *ref, struct alloc_tag *tag, size_t bytes) { - alloc_tag_add_check(ref, tag); - if (!ref || !tag) - return; - - __alloc_tag_ref_set(ref, tag); + alloc_tag_ref_set(ref, tag); this_cpu_add(tag->counters->bytes, bytes); } diff --git a/include/linux/mm.h b/include/linux/mm.h index 6bb778cbaabf..39f6faace590 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -4108,10 +4108,37 @@ static inline void pgalloc_tag_split(struct folio *folio, int old_order, int new } } } + +static inline void pgalloc_tag_copy(struct folio *new, struct folio *old) +{ + struct alloc_tag *tag; + union codetag_ref *ref; + + tag = pgalloc_tag_get(&old->page); + if (!tag) + return; + + ref = get_page_tag_ref(&new->page); + if (!ref) + return; + + /* Clear the old ref to the original allocation tag. */ + clear_page_tag_ref(&old->page); + /* Decrement the counters of the tag on get_new_folio. */ + alloc_tag_sub(ref, folio_nr_pages(new)); + + __alloc_tag_ref_set(ref, tag); + + put_page_tag_ref(ref); +} #else /* !CONFIG_MEM_ALLOC_PROFILING */ static inline void pgalloc_tag_split(struct folio *folio, int old_order, int new_order) { } + +static inline void pgalloc_tag_copy(struct folio *new, struct folio *old) +{ +} #endif /* CONFIG_MEM_ALLOC_PROFILING */ #endif /* _LINUX_MM_H */ diff --git a/mm/migrate.c b/mm/migrate.c index 0f6b78fd73aa..dfdb3a136bf8 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -743,6 +743,7 @@ void folio_migrate_flags(struct folio *newfolio, struct folio *folio) folio_set_readahead(newfolio); folio_copy_owner(newfolio, folio); + pgalloc_tag_copy(newfolio, folio); mem_cgroup_migrate(folio, newfolio); } -- cgit v1.2.3 From 6462dd53a26088a433f90a5c15822196f201037c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 9 Sep 2024 13:42:47 -1000 Subject: sched_ext: Compact struct bpf_iter_scx_dsq_kern struct scx_iter_scx_dsq is defined as 6 u64's and scx_dsq_iter_kern was using 5 of them. We want to add two more u64 fields but it's better if we do so while staying within scx_iter_scx_dsq to maintain binary compatibility. The way scx_iter_scx_dsq_kern is laid out is rather inefficient - the node field takes up three u64's but only one bit of the last u64 is used. Turn the bool into u32 flags and only use the lower 16 bits freeing up 48 bits - 16 bits for flags, 32 bits for a u32 - for use by struct bpf_iter_scx_dsq_kern. This allows moving the dsq_seq and flags fields of bpf_iter_scx_dsq_kern into the cursor field reducing the struct size by a full u64. No behavior changes intended. Signed-off-by: Tejun Heo --- include/linux/sched/ext.h | 10 +++++++++- kernel/sched/ext.c | 23 ++++++++++++----------- 2 files changed, 21 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index dc646cca4fcf..1ddbde64a31b 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -119,9 +119,17 @@ enum scx_kf_mask { __SCX_KF_TERMINAL = SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU | SCX_KF_REST, }; +enum scx_dsq_lnode_flags { + SCX_DSQ_LNODE_ITER_CURSOR = 1 << 0, + + /* high 16 bits can be for iter cursor flags */ + __SCX_DSQ_LNODE_PRIV_SHIFT = 16, +}; + struct scx_dsq_list_node { struct list_head node; - bool is_bpf_iter_cursor; + u32 flags; + u32 priv; /* can be used by iter cursor */ }; /* diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index cfb413285882..44a2d1b9e837 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -1191,7 +1191,7 @@ static struct task_struct *nldsq_next_task(struct scx_dispatch_q *dsq, dsq_lnode = container_of(list_node, struct scx_dsq_list_node, node); - } while (dsq_lnode->is_bpf_iter_cursor); + } while (dsq_lnode->flags & SCX_DSQ_LNODE_ITER_CURSOR); return container_of(dsq_lnode, struct task_struct, scx.dsq_list); } @@ -1209,16 +1209,15 @@ static struct task_struct *nldsq_next_task(struct scx_dispatch_q *dsq, */ enum scx_dsq_iter_flags { /* iterate in the reverse dispatch order */ - SCX_DSQ_ITER_REV = 1U << 0, + SCX_DSQ_ITER_REV = 1U << 16, - __SCX_DSQ_ITER_ALL_FLAGS = SCX_DSQ_ITER_REV, + __SCX_DSQ_ITER_USER_FLAGS = SCX_DSQ_ITER_REV, + __SCX_DSQ_ITER_ALL_FLAGS = __SCX_DSQ_ITER_USER_FLAGS, }; struct bpf_iter_scx_dsq_kern { struct scx_dsq_list_node cursor; struct scx_dispatch_q *dsq; - u32 dsq_seq; - u32 flags; } __attribute__((aligned(8))); struct bpf_iter_scx_dsq { @@ -1256,6 +1255,9 @@ static void scx_task_iter_init(struct scx_task_iter *iter) { lockdep_assert_held(&scx_tasks_lock); + BUILD_BUG_ON(__SCX_DSQ_ITER_ALL_FLAGS & + ((1U << __SCX_DSQ_LNODE_PRIV_SHIFT) - 1)); + iter->cursor = (struct sched_ext_entity){ .flags = SCX_TASK_CURSOR }; list_add(&iter->cursor.tasks_node, &scx_tasks); iter->locked = NULL; @@ -6285,7 +6287,7 @@ __bpf_kfunc int bpf_iter_scx_dsq_new(struct bpf_iter_scx_dsq *it, u64 dsq_id, BUILD_BUG_ON(__alignof__(struct bpf_iter_scx_dsq_kern) != __alignof__(struct bpf_iter_scx_dsq)); - if (flags & ~__SCX_DSQ_ITER_ALL_FLAGS) + if (flags & ~__SCX_DSQ_ITER_USER_FLAGS) return -EINVAL; kit->dsq = find_non_local_dsq(dsq_id); @@ -6293,9 +6295,8 @@ __bpf_kfunc int bpf_iter_scx_dsq_new(struct bpf_iter_scx_dsq *it, u64 dsq_id, return -ENOENT; INIT_LIST_HEAD(&kit->cursor.node); - kit->cursor.is_bpf_iter_cursor = true; - kit->dsq_seq = READ_ONCE(kit->dsq->seq); - kit->flags = flags; + kit->cursor.flags |= SCX_DSQ_LNODE_ITER_CURSOR | flags; + kit->cursor.priv = READ_ONCE(kit->dsq->seq); return 0; } @@ -6309,7 +6310,7 @@ __bpf_kfunc int bpf_iter_scx_dsq_new(struct bpf_iter_scx_dsq *it, u64 dsq_id, __bpf_kfunc struct task_struct *bpf_iter_scx_dsq_next(struct bpf_iter_scx_dsq *it) { struct bpf_iter_scx_dsq_kern *kit = (void *)it; - bool rev = kit->flags & SCX_DSQ_ITER_REV; + bool rev = kit->cursor.flags & SCX_DSQ_ITER_REV; struct task_struct *p; unsigned long flags; @@ -6330,7 +6331,7 @@ __bpf_kfunc struct task_struct *bpf_iter_scx_dsq_next(struct bpf_iter_scx_dsq *i */ do { p = nldsq_next_task(kit->dsq, p, rev); - } while (p && unlikely(u32_before(kit->dsq_seq, p->scx.dsq_seq))); + } while (p && unlikely(u32_before(kit->cursor.priv, p->scx.dsq_seq))); if (p) { if (rev) -- cgit v1.2.3 From 17245a195df4c86b1fd38718d8cdc532c040c08e Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 6 Sep 2024 09:10:59 -0700 Subject: net: remove dev_pick_tx_cpu_id() dev_pick_tx_cpu_id() has been introduced with two users by commit a4ea8a3dacc3 ("net: Add generic ndo_select_queue functions"). The use in AF_PACKET has been removed in 2019 by commit b71b5837f871 ("packet: rework packet_pick_tx_queue() to use common code selection") The other user was a Netlogic XLP driver, removed in 2021 by commit 47ac6f567c28 ("staging: Remove Netlogic XLP network driver"). It's relatively unlikely that any modern driver will need an .ndo_select_queue implementation which picks purely based on CPU ID and skips XPS, delete dev_pick_tx_cpu_id() Found by code inspection. Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20240906161059.715546-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 2 -- net/core/dev.c | 7 ------- 2 files changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b47c00657bd0..2e40a137dc12 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3085,8 +3085,6 @@ void dev_disable_lro(struct net_device *dev); int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb); u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); -u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev); int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev); int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id); diff --git a/net/core/dev.c b/net/core/dev.c index 22c3f14d9287..8f4dead64284 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4247,13 +4247,6 @@ u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, } EXPORT_SYMBOL(dev_pick_tx_zero); -u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev) -{ - return (u16)raw_smp_processor_id() % dev->real_num_tx_queues; -} -EXPORT_SYMBOL(dev_pick_tx_cpu_id); - u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { -- cgit v1.2.3 From 2f87e9cf0c9e21ab9be1fb2ba8520a1525359497 Mon Sep 17 00:00:00 2001 From: Cindy Lu Date: Wed, 31 Jul 2024 11:16:01 +0800 Subject: vdpa: support set mac address from vdpa tool Add new UAPI to support the mac address from vdpa tool Function vdpa_nl_cmd_dev_attr_set_doit() will get the new MAC address from the vdpa tool and then set it to the device. The usage is: vdpa dev set name vdpa_name mac **:**:**:**:**:** Here is example: root@L1# vdpa -jp dev config show vdpa0 { "config": { "vdpa0": { "mac": "82:4d:e9:5d:d7:e6", "link ": "up", "link_announce ": false, "mtu": 1500 } } } root@L1# vdpa dev set name vdpa0 mac 00:11:22:33:44:55 root@L1# vdpa -jp dev config show vdpa0 { "config": { "vdpa0": { "mac": "00:11:22:33:44:55", "link ": "up", "link_announce ": false, "mtu": 1500 } } } Signed-off-by: Cindy Lu Message-Id: <20240731031653.1047692-2-lulu@redhat.com> Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- drivers/vdpa/vdpa.c | 79 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/vdpa.h | 9 ++++++ include/uapi/linux/vdpa.h | 1 + 3 files changed, 89 insertions(+) (limited to 'include/linux') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 4dbd2e55a288..8a372b51c21a 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -1361,6 +1361,80 @@ dev_err: return err; } +static int vdpa_dev_net_device_attr_set(struct vdpa_device *vdev, + struct genl_info *info) +{ + struct vdpa_dev_set_config set_config = {}; + struct vdpa_mgmt_dev *mdev = vdev->mdev; + struct nlattr **nl_attrs = info->attrs; + const u8 *macaddr; + int err = -EOPNOTSUPP; + + down_write(&vdev->cf_lock); + if (nl_attrs[VDPA_ATTR_DEV_NET_CFG_MACADDR]) { + set_config.mask |= BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MACADDR); + macaddr = nla_data(nl_attrs[VDPA_ATTR_DEV_NET_CFG_MACADDR]); + + if (is_valid_ether_addr(macaddr)) { + ether_addr_copy(set_config.net.mac, macaddr); + if (mdev->ops->dev_set_attr) { + err = mdev->ops->dev_set_attr(mdev, vdev, + &set_config); + } else { + NL_SET_ERR_MSG_FMT_MOD(info->extack, + "Operation not supported by the device."); + } + } else { + NL_SET_ERR_MSG_FMT_MOD(info->extack, + "Invalid MAC address"); + } + } + up_write(&vdev->cf_lock); + return err; +} + +static int vdpa_nl_cmd_dev_attr_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct vdpa_device *vdev; + struct device *dev; + const char *name; + u64 classes; + int err = 0; + + if (!info->attrs[VDPA_ATTR_DEV_NAME]) + return -EINVAL; + + name = nla_data(info->attrs[VDPA_ATTR_DEV_NAME]); + + down_write(&vdpa_dev_lock); + dev = bus_find_device(&vdpa_bus, NULL, name, vdpa_name_match); + if (!dev) { + NL_SET_ERR_MSG_MOD(info->extack, "device not found"); + err = -ENODEV; + goto dev_err; + } + vdev = container_of(dev, struct vdpa_device, dev); + if (!vdev->mdev) { + NL_SET_ERR_MSG_MOD(info->extack, "unmanaged vdpa device"); + err = -EINVAL; + goto mdev_err; + } + classes = vdpa_mgmtdev_get_classes(vdev->mdev, NULL); + if (classes & BIT_ULL(VIRTIO_ID_NET)) { + err = vdpa_dev_net_device_attr_set(vdev, info); + } else { + NL_SET_ERR_MSG_FMT_MOD(info->extack, "%s device not supported", + name); + } + +mdev_err: + put_device(dev); +dev_err: + up_write(&vdpa_dev_lock); + return err; +} + static int vdpa_dev_config_dump(struct device *dev, void *data) { struct vdpa_device *vdev = container_of(dev, struct vdpa_device, dev); @@ -1497,6 +1571,11 @@ static const struct genl_ops vdpa_nl_ops[] = { .doit = vdpa_nl_cmd_dev_stats_get_doit, .flags = GENL_ADMIN_PERM, }, + { + .cmd = VDPA_CMD_DEV_ATTR_SET, + .doit = vdpa_nl_cmd_dev_attr_set_doit, + .flags = GENL_ADMIN_PERM, + }, }; static struct genl_family vdpa_nl_family __ro_after_init = { diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 7977ca03ac7a..2e7a30fe6b92 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -582,11 +582,20 @@ void vdpa_set_status(struct vdpa_device *vdev, u8 status); * @dev: vdpa device to remove * Driver need to remove the specified device by calling * _vdpa_unregister_device(). + * @dev_set_attr: change a vdpa device's attr after it was create + * @mdev: parent device to use for device + * @dev: vdpa device structure + * @config:Attributes to be set for the device. + * The driver needs to check the mask of the structure and then set + * the related information to the vdpa device. The driver must return 0 + * if set successfully. */ struct vdpa_mgmtdev_ops { int (*dev_add)(struct vdpa_mgmt_dev *mdev, const char *name, const struct vdpa_dev_set_config *config); void (*dev_del)(struct vdpa_mgmt_dev *mdev, struct vdpa_device *dev); + int (*dev_set_attr)(struct vdpa_mgmt_dev *mdev, struct vdpa_device *dev, + const struct vdpa_dev_set_config *config); }; /** diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index 842bf1201ac4..71edf2c70cc3 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -19,6 +19,7 @@ enum vdpa_command { VDPA_CMD_DEV_GET, /* can dump */ VDPA_CMD_DEV_CONFIG_GET, /* can dump */ VDPA_CMD_DEV_VSTATS_GET, + VDPA_CMD_DEV_ATTR_SET, }; enum vdpa_attr { -- cgit v1.2.3 From 11596dc3dfae572cc267dda2dc4dab9ae34668f3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 10 Sep 2024 07:39:05 +0300 Subject: iomap: pass flags to iomap_file_buffered_write_punch_delalloc To fix short write error handling, We'll need to figure out what operation iomap_file_buffered_write_punch_delalloc is called for. Pass the flags argument on to it, and reorder the argument list to match that of ->iomap_end so that the compiler only has to add the new punch argument to the end of it instead of reshuffling the registers. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20240910043949.3481298-4-hch@lst.de Reviewed-by: Darrick J. Wong Signed-off-by: Christian Brauner --- fs/iomap/buffered-io.c | 11 +++++------ fs/xfs/xfs_iomap.c | 5 +++-- include/linux/iomap.h | 10 ++++++---- 3 files changed, 14 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index a00b213967e5..363c8e6f7952 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -23,7 +23,6 @@ #define IOEND_BATCH_SIZE 4096 -typedef int (*iomap_punch_t)(struct inode *inode, loff_t offset, loff_t length); /* * Structure allocated for each folio to track per-block uptodate, dirty state * and I/O completions. @@ -1200,8 +1199,8 @@ static int iomap_write_delalloc_scan(struct inode *inode, * require sprinkling this code with magic "+ 1" and "- 1" arithmetic and expose * the code to subtle off-by-one bugs.... */ -static int iomap_write_delalloc_release(struct inode *inode, - loff_t start_byte, loff_t end_byte, iomap_punch_t punch) +static int iomap_write_delalloc_release(struct inode *inode, loff_t start_byte, + loff_t end_byte, unsigned flags, iomap_punch_t punch) { loff_t punch_start_byte = start_byte; loff_t scan_end_byte = min(i_size_read(inode), end_byte); @@ -1301,8 +1300,8 @@ out_unlock: * internal filesystem allocation lock */ int iomap_file_buffered_write_punch_delalloc(struct inode *inode, - struct iomap *iomap, loff_t pos, loff_t length, - ssize_t written, iomap_punch_t punch) + loff_t pos, loff_t length, ssize_t written, unsigned flags, + struct iomap *iomap, iomap_punch_t punch) { loff_t start_byte; loff_t end_byte; @@ -1330,7 +1329,7 @@ int iomap_file_buffered_write_punch_delalloc(struct inode *inode, if (start_byte >= end_byte) return 0; - return iomap_write_delalloc_release(inode, start_byte, end_byte, + return iomap_write_delalloc_release(inode, start_byte, end_byte, flags, punch); } EXPORT_SYMBOL_GPL(iomap_file_buffered_write_punch_delalloc); diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 72c981e3dc92..47b5c8358825 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1231,8 +1231,9 @@ xfs_buffered_write_iomap_end( struct xfs_mount *mp = XFS_M(inode->i_sb); int error; - error = iomap_file_buffered_write_punch_delalloc(inode, iomap, offset, - length, written, &xfs_buffered_write_delalloc_punch); + error = iomap_file_buffered_write_punch_delalloc(inode, offset, length, + written, flags, iomap, + &xfs_buffered_write_delalloc_punch); if (error && !xfs_is_shutdown(mp)) { xfs_alert(mp, "%s: unable to clean up ino 0x%llx", __func__, XFS_I(inode)->i_ino); diff --git a/include/linux/iomap.h b/include/linux/iomap.h index f792b37f7627..52626906ff35 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -258,10 +258,6 @@ static inline const struct iomap *iomap_iter_srcmap(const struct iomap_iter *i) ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, const struct iomap_ops *ops, void *private); -int iomap_file_buffered_write_punch_delalloc(struct inode *inode, - struct iomap *iomap, loff_t pos, loff_t length, ssize_t written, - int (*punch)(struct inode *inode, loff_t pos, loff_t length)); - int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops); void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops); bool iomap_is_partially_uptodate(struct folio *, size_t from, size_t count); @@ -277,6 +273,12 @@ int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, const struct iomap_ops *ops); vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops); + +typedef int (*iomap_punch_t)(struct inode *inode, loff_t offset, loff_t length); +int iomap_file_buffered_write_punch_delalloc(struct inode *inode, loff_t pos, + loff_t length, ssize_t written, unsigned flag, + struct iomap *iomap, iomap_punch_t punch); + int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len, const struct iomap_ops *ops); loff_t iomap_seek_hole(struct inode *inode, loff_t offset, -- cgit v1.2.3 From 492f53758fad4fde3e9a98696780f8b53f87cdae Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 10 Sep 2024 07:39:06 +0300 Subject: iomap: pass the iomap to the punch callback XFS will need to look at the flags in the iomap structure, so pass it down all the way to the callback. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20240910043949.3481298-5-hch@lst.de Reviewed-by: Darrick J. Wong Signed-off-by: Christian Brauner --- fs/iomap/buffered-io.c | 25 +++++++++++++------------ fs/xfs/xfs_iomap.c | 3 ++- include/linux/iomap.h | 3 ++- 3 files changed, 17 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 363c8e6f7952..87c996657a52 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1048,7 +1048,7 @@ EXPORT_SYMBOL_GPL(iomap_file_buffered_write); static int iomap_write_delalloc_ifs_punch(struct inode *inode, struct folio *folio, loff_t start_byte, loff_t end_byte, - iomap_punch_t punch) + struct iomap *iomap, iomap_punch_t punch) { unsigned int first_blk, last_blk, i; loff_t last_byte; @@ -1073,7 +1073,7 @@ static int iomap_write_delalloc_ifs_punch(struct inode *inode, for (i = first_blk; i <= last_blk; i++) { if (!ifs_block_is_dirty(folio, ifs, i)) { ret = punch(inode, folio_pos(folio) + (i << blkbits), - 1 << blkbits); + 1 << blkbits, iomap); if (ret) return ret; } @@ -1085,7 +1085,7 @@ static int iomap_write_delalloc_ifs_punch(struct inode *inode, static int iomap_write_delalloc_punch(struct inode *inode, struct folio *folio, loff_t *punch_start_byte, loff_t start_byte, loff_t end_byte, - iomap_punch_t punch) + struct iomap *iomap, iomap_punch_t punch) { int ret = 0; @@ -1095,14 +1095,14 @@ static int iomap_write_delalloc_punch(struct inode *inode, struct folio *folio, /* if dirty, punch up to offset */ if (start_byte > *punch_start_byte) { ret = punch(inode, *punch_start_byte, - start_byte - *punch_start_byte); + start_byte - *punch_start_byte, iomap); if (ret) return ret; } /* Punch non-dirty blocks within folio */ - ret = iomap_write_delalloc_ifs_punch(inode, folio, start_byte, - end_byte, punch); + ret = iomap_write_delalloc_ifs_punch(inode, folio, start_byte, end_byte, + iomap, punch); if (ret) return ret; @@ -1135,7 +1135,7 @@ static int iomap_write_delalloc_punch(struct inode *inode, struct folio *folio, */ static int iomap_write_delalloc_scan(struct inode *inode, loff_t *punch_start_byte, loff_t start_byte, loff_t end_byte, - iomap_punch_t punch) + struct iomap *iomap, iomap_punch_t punch) { while (start_byte < end_byte) { struct folio *folio; @@ -1151,7 +1151,7 @@ static int iomap_write_delalloc_scan(struct inode *inode, } ret = iomap_write_delalloc_punch(inode, folio, punch_start_byte, - start_byte, end_byte, punch); + start_byte, end_byte, iomap, punch); if (ret) { folio_unlock(folio); folio_put(folio); @@ -1200,7 +1200,8 @@ static int iomap_write_delalloc_scan(struct inode *inode, * the code to subtle off-by-one bugs.... */ static int iomap_write_delalloc_release(struct inode *inode, loff_t start_byte, - loff_t end_byte, unsigned flags, iomap_punch_t punch) + loff_t end_byte, unsigned flags, struct iomap *iomap, + iomap_punch_t punch) { loff_t punch_start_byte = start_byte; loff_t scan_end_byte = min(i_size_read(inode), end_byte); @@ -1253,7 +1254,7 @@ static int iomap_write_delalloc_release(struct inode *inode, loff_t start_byte, WARN_ON_ONCE(data_end > scan_end_byte); error = iomap_write_delalloc_scan(inode, &punch_start_byte, - start_byte, data_end, punch); + start_byte, data_end, iomap, punch); if (error) goto out_unlock; @@ -1263,7 +1264,7 @@ static int iomap_write_delalloc_release(struct inode *inode, loff_t start_byte, if (punch_start_byte < end_byte) error = punch(inode, punch_start_byte, - end_byte - punch_start_byte); + end_byte - punch_start_byte, iomap); out_unlock: filemap_invalidate_unlock(inode->i_mapping); return error; @@ -1330,7 +1331,7 @@ int iomap_file_buffered_write_punch_delalloc(struct inode *inode, return 0; return iomap_write_delalloc_release(inode, start_byte, end_byte, flags, - punch); + iomap, punch); } EXPORT_SYMBOL_GPL(iomap_file_buffered_write_punch_delalloc); diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 47b5c8358825..695e5bee776f 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1212,7 +1212,8 @@ static int xfs_buffered_write_delalloc_punch( struct inode *inode, loff_t offset, - loff_t length) + loff_t length, + struct iomap *iomap) { xfs_bmap_punch_delalloc_range(XFS_I(inode), offset, offset + length); return 0; diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 52626906ff35..ec2eab94f00a 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -274,7 +274,8 @@ int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops); -typedef int (*iomap_punch_t)(struct inode *inode, loff_t offset, loff_t length); +typedef int (*iomap_punch_t)(struct inode *inode, loff_t offset, loff_t length, + struct iomap *iomap); int iomap_file_buffered_write_punch_delalloc(struct inode *inode, loff_t pos, loff_t length, ssize_t written, unsigned flag, struct iomap *iomap, iomap_punch_t punch); -- cgit v1.2.3 From 4bceb9ba05aca23652567fb5f899cc7fcb12c8d0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 10 Sep 2024 07:39:07 +0300 Subject: iomap: remove the iomap_file_buffered_write_punch_delalloc return value iomap_file_buffered_write_punch_delalloc can only return errors if either the ->punch callback returned an error, or if someone changed the API of mapping_seek_hole_data to return a negative error code that is not -ENXIO. As the only instance of ->punch never returns an error, an such an error would be fatal anyway remove the entire error propagation and don't return an error code from iomap_file_buffered_write_punch_delalloc. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20240910043949.3481298-6-hch@lst.de Reviewed-by: Darrick J. Wong Signed-off-by: Christian Brauner --- fs/iomap/buffered-io.c | 82 +++++++++++++++++--------------------------------- fs/xfs/xfs_iomap.c | 17 ++--------- include/linux/iomap.h | 4 +-- 3 files changed, 33 insertions(+), 70 deletions(-) (limited to 'include/linux') diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 87c996657a52..b02545f8036e 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1046,7 +1046,7 @@ iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *i, } EXPORT_SYMBOL_GPL(iomap_file_buffered_write); -static int iomap_write_delalloc_ifs_punch(struct inode *inode, +static void iomap_write_delalloc_ifs_punch(struct inode *inode, struct folio *folio, loff_t start_byte, loff_t end_byte, struct iomap *iomap, iomap_punch_t punch) { @@ -1054,7 +1054,6 @@ static int iomap_write_delalloc_ifs_punch(struct inode *inode, loff_t last_byte; u8 blkbits = inode->i_blkbits; struct iomap_folio_state *ifs; - int ret = 0; /* * When we have per-block dirty tracking, there can be @@ -1064,47 +1063,35 @@ static int iomap_write_delalloc_ifs_punch(struct inode *inode, */ ifs = folio->private; if (!ifs) - return ret; + return; last_byte = min_t(loff_t, end_byte - 1, folio_pos(folio) + folio_size(folio) - 1); first_blk = offset_in_folio(folio, start_byte) >> blkbits; last_blk = offset_in_folio(folio, last_byte) >> blkbits; for (i = first_blk; i <= last_blk; i++) { - if (!ifs_block_is_dirty(folio, ifs, i)) { - ret = punch(inode, folio_pos(folio) + (i << blkbits), + if (!ifs_block_is_dirty(folio, ifs, i)) + punch(inode, folio_pos(folio) + (i << blkbits), 1 << blkbits, iomap); - if (ret) - return ret; - } } - - return ret; } - -static int iomap_write_delalloc_punch(struct inode *inode, struct folio *folio, +static void iomap_write_delalloc_punch(struct inode *inode, struct folio *folio, loff_t *punch_start_byte, loff_t start_byte, loff_t end_byte, struct iomap *iomap, iomap_punch_t punch) { - int ret = 0; - if (!folio_test_dirty(folio)) - return ret; + return; /* if dirty, punch up to offset */ if (start_byte > *punch_start_byte) { - ret = punch(inode, *punch_start_byte, - start_byte - *punch_start_byte, iomap); - if (ret) - return ret; + punch(inode, *punch_start_byte, start_byte - *punch_start_byte, + iomap); } /* Punch non-dirty blocks within folio */ - ret = iomap_write_delalloc_ifs_punch(inode, folio, start_byte, end_byte, + iomap_write_delalloc_ifs_punch(inode, folio, start_byte, end_byte, iomap, punch); - if (ret) - return ret; /* * Make sure the next punch start is correctly bound to @@ -1112,8 +1099,6 @@ static int iomap_write_delalloc_punch(struct inode *inode, struct folio *folio, */ *punch_start_byte = min_t(loff_t, end_byte, folio_pos(folio) + folio_size(folio)); - - return ret; } /* @@ -1133,13 +1118,12 @@ static int iomap_write_delalloc_punch(struct inode *inode, struct folio *folio, * This function uses [start_byte, end_byte) intervals (i.e. open ended) to * simplify range iterations. */ -static int iomap_write_delalloc_scan(struct inode *inode, +static void iomap_write_delalloc_scan(struct inode *inode, loff_t *punch_start_byte, loff_t start_byte, loff_t end_byte, struct iomap *iomap, iomap_punch_t punch) { while (start_byte < end_byte) { struct folio *folio; - int ret; /* grab locked page */ folio = filemap_lock_folio(inode->i_mapping, @@ -1150,20 +1134,14 @@ static int iomap_write_delalloc_scan(struct inode *inode, continue; } - ret = iomap_write_delalloc_punch(inode, folio, punch_start_byte, + iomap_write_delalloc_punch(inode, folio, punch_start_byte, start_byte, end_byte, iomap, punch); - if (ret) { - folio_unlock(folio); - folio_put(folio); - return ret; - } /* move offset to start of next folio in range */ start_byte = folio_next_index(folio) << PAGE_SHIFT; folio_unlock(folio); folio_put(folio); } - return 0; } /* @@ -1199,13 +1177,12 @@ static int iomap_write_delalloc_scan(struct inode *inode, * require sprinkling this code with magic "+ 1" and "- 1" arithmetic and expose * the code to subtle off-by-one bugs.... */ -static int iomap_write_delalloc_release(struct inode *inode, loff_t start_byte, +static void iomap_write_delalloc_release(struct inode *inode, loff_t start_byte, loff_t end_byte, unsigned flags, struct iomap *iomap, iomap_punch_t punch) { loff_t punch_start_byte = start_byte; loff_t scan_end_byte = min(i_size_read(inode), end_byte); - int error = 0; /* * Lock the mapping to avoid races with page faults re-instantiating @@ -1222,13 +1199,15 @@ static int iomap_write_delalloc_release(struct inode *inode, loff_t start_byte, /* * If there is no more data to scan, all that is left is to * punch out the remaining range. + * + * Note that mapping_seek_hole_data is only supposed to return + * either an offset or -ENXIO, so WARN on any other error as + * that would be an API change without updating the callers. */ if (start_byte == -ENXIO || start_byte == scan_end_byte) break; - if (start_byte < 0) { - error = start_byte; + if (WARN_ON_ONCE(start_byte < 0)) goto out_unlock; - } WARN_ON_ONCE(start_byte < punch_start_byte); WARN_ON_ONCE(start_byte > scan_end_byte); @@ -1238,10 +1217,8 @@ static int iomap_write_delalloc_release(struct inode *inode, loff_t start_byte, */ data_end = mapping_seek_hole_data(inode->i_mapping, start_byte, scan_end_byte, SEEK_HOLE); - if (data_end < 0) { - error = data_end; + if (WARN_ON_ONCE(data_end < 0)) goto out_unlock; - } /* * If we race with post-direct I/O invalidation of the page cache, @@ -1253,21 +1230,18 @@ static int iomap_write_delalloc_release(struct inode *inode, loff_t start_byte, WARN_ON_ONCE(data_end < start_byte); WARN_ON_ONCE(data_end > scan_end_byte); - error = iomap_write_delalloc_scan(inode, &punch_start_byte, - start_byte, data_end, iomap, punch); - if (error) - goto out_unlock; + iomap_write_delalloc_scan(inode, &punch_start_byte, start_byte, + data_end, iomap, punch); /* The next data search starts at the end of this one. */ start_byte = data_end; } if (punch_start_byte < end_byte) - error = punch(inode, punch_start_byte, - end_byte - punch_start_byte, iomap); + punch(inode, punch_start_byte, end_byte - punch_start_byte, + iomap); out_unlock: filemap_invalidate_unlock(inode->i_mapping); - return error; } /* @@ -1300,7 +1274,7 @@ out_unlock: * ->punch * internal filesystem allocation lock */ -int iomap_file_buffered_write_punch_delalloc(struct inode *inode, +void iomap_file_buffered_write_punch_delalloc(struct inode *inode, loff_t pos, loff_t length, ssize_t written, unsigned flags, struct iomap *iomap, iomap_punch_t punch) { @@ -1309,11 +1283,11 @@ int iomap_file_buffered_write_punch_delalloc(struct inode *inode, unsigned int blocksize = i_blocksize(inode); if (iomap->type != IOMAP_DELALLOC) - return 0; + return; /* If we didn't reserve the blocks, we're not allowed to punch them. */ if (!(iomap->flags & IOMAP_F_NEW)) - return 0; + return; /* * start_byte refers to the first unused block after a short write. If @@ -1328,10 +1302,10 @@ int iomap_file_buffered_write_punch_delalloc(struct inode *inode, /* Nothing to do if we've written the entire delalloc extent */ if (start_byte >= end_byte) - return 0; + return; - return iomap_write_delalloc_release(inode, start_byte, end_byte, flags, - iomap, punch); + iomap_write_delalloc_release(inode, start_byte, end_byte, flags, iomap, + punch); } EXPORT_SYMBOL_GPL(iomap_file_buffered_write_punch_delalloc); diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 695e5bee776f..1e11f48814c0 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1208,7 +1208,7 @@ out_unlock: return error; } -static int +static void xfs_buffered_write_delalloc_punch( struct inode *inode, loff_t offset, @@ -1216,7 +1216,6 @@ xfs_buffered_write_delalloc_punch( struct iomap *iomap) { xfs_bmap_punch_delalloc_range(XFS_I(inode), offset, offset + length); - return 0; } static int @@ -1228,18 +1227,8 @@ xfs_buffered_write_iomap_end( unsigned flags, struct iomap *iomap) { - - struct xfs_mount *mp = XFS_M(inode->i_sb); - int error; - - error = iomap_file_buffered_write_punch_delalloc(inode, offset, length, - written, flags, iomap, - &xfs_buffered_write_delalloc_punch); - if (error && !xfs_is_shutdown(mp)) { - xfs_alert(mp, "%s: unable to clean up ino 0x%llx", - __func__, XFS_I(inode)->i_ino); - return error; - } + iomap_file_buffered_write_punch_delalloc(inode, offset, length, written, + flags, iomap, &xfs_buffered_write_delalloc_punch); return 0; } diff --git a/include/linux/iomap.h b/include/linux/iomap.h index ec2eab94f00a..4ad12a3c8bae 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -274,9 +274,9 @@ int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops); -typedef int (*iomap_punch_t)(struct inode *inode, loff_t offset, loff_t length, +typedef void (*iomap_punch_t)(struct inode *inode, loff_t offset, loff_t length, struct iomap *iomap); -int iomap_file_buffered_write_punch_delalloc(struct inode *inode, loff_t pos, +void iomap_file_buffered_write_punch_delalloc(struct inode *inode, loff_t pos, loff_t length, ssize_t written, unsigned flag, struct iomap *iomap, iomap_punch_t punch); -- cgit v1.2.3 From 9028cdeb38e1f37d63cb3154799dd259b67e879e Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Thu, 5 Sep 2024 10:34:22 -0700 Subject: memcg: add charging of already allocated slab objects At the moment, the slab objects are charged to the memcg at the allocation time. However there are cases where slab objects are allocated at the time where the right target memcg to charge it to is not known. One such case is the network sockets for the incoming connection which are allocated in the softirq context. Couple hundred thousand connections are very normal on large loaded server and almost all of those sockets underlying those connections get allocated in the softirq context and thus not charged to any memcg. However later at the accept() time we know the right target memcg to charge. Let's add new API to charge already allocated objects, so we can have better accounting of the memory usage. To measure the performance impact of this change, tcp_crr is used from the neper [1] performance suite. Basically it is a network ping pong test with new connection for each ping pong. The server and the client are run inside 3 level of cgroup hierarchy using the following commands: Server: $ tcp_crr -6 Client: $ tcp_crr -6 -c -H ${server_ip} If the client and server run on different machines with 50 GBPS NIC, there is no visible impact of the change. For the same machine experiment with v6.11-rc5 as base. base (throughput) with-patch tcp_crr 14545 (+- 80) 14463 (+- 56) It seems like the performance impact is within the noise. Link: https://github.com/google/neper [1] Signed-off-by: Shakeel Butt Reviewed-by: Roman Gushchin Reviewed-by: Yosry Ahmed Acked-by: Paolo Abeni # net Signed-off-by: Vlastimil Babka --- include/linux/slab.h | 29 ++++++++++++++++++++++ mm/slab.h | 7 ++++++ mm/slub.c | 53 +++++++++++++++++++++++++++++++++++++++++ net/ipv4/inet_connection_sock.c | 5 ++-- 4 files changed, 92 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index eb2bf4629157..3be2a5ed4936 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -547,6 +547,35 @@ void *kmem_cache_alloc_lru_noprof(struct kmem_cache *s, struct list_lru *lru, gfp_t gfpflags) __assume_slab_alignment __malloc; #define kmem_cache_alloc_lru(...) alloc_hooks(kmem_cache_alloc_lru_noprof(__VA_ARGS__)) +/** + * kmem_cache_charge - memcg charge an already allocated slab memory + * @objp: address of the slab object to memcg charge + * @gfpflags: describe the allocation context + * + * kmem_cache_charge allows charging a slab object to the current memcg, + * primarily in cases where charging at allocation time might not be possible + * because the target memcg is not known (i.e. softirq context) + * + * The objp should be pointer returned by the slab allocator functions like + * kmalloc (with __GFP_ACCOUNT in flags) or kmem_cache_alloc. The memcg charge + * behavior can be controlled through gfpflags parameter, which affects how the + * necessary internal metadata can be allocated. Including __GFP_NOFAIL denotes + * that overcharging is requested instead of failure, but is not applied for the + * internal metadata allocation. + * + * There are several cases where it will return true even if the charging was + * not done: + * More specifically: + * + * 1. For !CONFIG_MEMCG or cgroup_disable=memory systems. + * 2. Already charged slab objects. + * 3. For slab objects from KMALLOC_NORMAL caches - allocated by kmalloc() + * without __GFP_ACCOUNT + * 4. Allocating internal metadata has failed + * + * Return: true if charge was successful otherwise false. + */ +bool kmem_cache_charge(void *objp, gfp_t gfpflags); void kmem_cache_free(struct kmem_cache *s, void *objp); kmem_buckets *kmem_buckets_create(const char *name, slab_flags_t flags, diff --git a/mm/slab.h b/mm/slab.h index dcdb56b8e7f5..9f907e930609 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -443,6 +443,13 @@ static inline bool is_kmalloc_cache(struct kmem_cache *s) return (s->flags & SLAB_KMALLOC); } +static inline bool is_kmalloc_normal(struct kmem_cache *s) +{ + if (!is_kmalloc_cache(s)) + return false; + return !(s->flags & (SLAB_CACHE_DMA|SLAB_ACCOUNT|SLAB_RECLAIM_ACCOUNT)); +} + /* Legal flag mask for kmem_cache_create(), for various configurations */ #define SLAB_CORE_FLAGS (SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA | \ SLAB_CACHE_DMA32 | SLAB_PANIC | \ diff --git a/mm/slub.c b/mm/slub.c index 95977f25a760..aa512de974e7 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2185,6 +2185,45 @@ void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab, void **p, __memcg_slab_free_hook(s, slab, p, objects, obj_exts); } + +static __fastpath_inline +bool memcg_slab_post_charge(void *p, gfp_t flags) +{ + struct slabobj_ext *slab_exts; + struct kmem_cache *s; + struct folio *folio; + struct slab *slab; + unsigned long off; + + folio = virt_to_folio(p); + if (!folio_test_slab(folio)) { + return folio_memcg_kmem(folio) || + (__memcg_kmem_charge_page(folio_page(folio, 0), flags, + folio_order(folio)) == 0); + } + + slab = folio_slab(folio); + s = slab->slab_cache; + + /* + * Ignore KMALLOC_NORMAL cache to avoid possible circular dependency + * of slab_obj_exts being allocated from the same slab and thus the slab + * becoming effectively unfreeable. + */ + if (is_kmalloc_normal(s)) + return true; + + /* Ignore already charged objects. */ + slab_exts = slab_obj_exts(slab); + if (slab_exts) { + off = obj_to_index(s, slab, p); + if (unlikely(slab_exts[off].objcg)) + return true; + } + + return __memcg_slab_post_alloc_hook(s, NULL, flags, 1, &p); +} + #else /* CONFIG_MEMCG */ static inline bool memcg_slab_post_alloc_hook(struct kmem_cache *s, struct list_lru *lru, @@ -2198,6 +2237,11 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab, void **p, int objects) { } + +static inline bool memcg_slab_post_charge(void *p, gfp_t flags) +{ + return true; +} #endif /* CONFIG_MEMCG */ #ifdef CONFIG_SLUB_RCU_DEBUG @@ -4105,6 +4149,15 @@ void *kmem_cache_alloc_lru_noprof(struct kmem_cache *s, struct list_lru *lru, } EXPORT_SYMBOL(kmem_cache_alloc_lru_noprof); +bool kmem_cache_charge(void *objp, gfp_t gfpflags) +{ + if (!memcg_kmem_online()) + return true; + + return memcg_slab_post_charge(objp, gfpflags); +} +EXPORT_SYMBOL(kmem_cache_charge); + /** * kmem_cache_alloc_node - Allocate an object on the specified node * @s: The cache to allocate from. diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 64d07b842e73..e25381bf32d0 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -714,6 +714,7 @@ struct sock *inet_csk_accept(struct sock *sk, struct proto_accept_arg *arg) out: release_sock(sk); if (newsk && mem_cgroup_sockets_enabled) { + gfp_t gfp = GFP_KERNEL | __GFP_NOFAIL; int amt = 0; /* atomically get the memory usage, set and charge the @@ -731,8 +732,8 @@ out: } if (amt) - mem_cgroup_charge_skmem(newsk->sk_memcg, amt, - GFP_KERNEL | __GFP_NOFAIL); + mem_cgroup_charge_skmem(newsk->sk_memcg, amt, gfp); + kmem_cache_charge(newsk, gfp); release_sock(newsk); } -- cgit v1.2.3 From 879fb3c274c12cb0892718e1e54f85fc406e3c7b Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 5 Sep 2024 09:56:45 +0200 Subject: slab: add struct kmem_cache_args Currently we have multiple kmem_cache_create*() variants that take up to seven separate parameters with one of the functions having to grow an eigth parameter in the future to handle both usercopy and a custom freelist pointer. Add a struct kmem_cache_args structure and move less common parameters into it. Core parameters such as name, object size, and flags continue to be passed separately. Add a new function __kmem_cache_create_args() that takes a struct kmem_cache_args pointer and port do_kmem_cache_create_usercopy() over to it. In follow-up patches we will port the other kmem_cache_create*() variants over to it as well. Reviewed-by: Kees Cook Reviewed-by: Jens Axboe Reviewed-by: Mike Rapoport (Microsoft) Reviewed-by: Vlastimil Babka Signed-off-by: Christian Brauner Reviewed-by: Roman Gushchin Signed-off-by: Vlastimil Babka --- include/linux/slab.h | 22 +++++++++++++++++ mm/slab_common.c | 67 +++++++++++++++++++++++++++++++++++++++------------- 2 files changed, 73 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 5b2da2cf31a8..2b8eeca7fd2c 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -240,6 +240,28 @@ struct mem_cgroup; */ bool slab_is_available(void); +/** + * struct kmem_cache_args - Less common arguments for kmem_cache_create() + * @align: The required alignment for the objects. + * @useroffset: Usercopy region offset + * @usersize: Usercopy region size + * @freeptr_offset: Custom offset for the free pointer in RCU caches + * @use_freeptr_offset: Whether a @freeptr_offset is used + * @ctor: A constructor for the objects. + */ +struct kmem_cache_args { + unsigned int align; + unsigned int useroffset; + unsigned int usersize; + unsigned int freeptr_offset; + bool use_freeptr_offset; + void (*ctor)(void *); +}; + +struct kmem_cache *__kmem_cache_create_args(const char *name, + unsigned int object_size, + struct kmem_cache_args *args, + slab_flags_t flags); struct kmem_cache *kmem_cache_create(const char *name, unsigned int size, unsigned int align, slab_flags_t flags, void (*ctor)(void *)); diff --git a/mm/slab_common.c b/mm/slab_common.c index 91e0e36e4379..0f13c045b8d1 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -248,14 +248,24 @@ out: return ERR_PTR(err); } -static struct kmem_cache * -do_kmem_cache_create_usercopy(const char *name, - unsigned int size, unsigned int freeptr_offset, - unsigned int align, slab_flags_t flags, - unsigned int useroffset, unsigned int usersize, - void (*ctor)(void *)) +/** + * __kmem_cache_create_args - Create a kmem cache + * @name: A string which is used in /proc/slabinfo to identify this cache. + * @object_size: The size of objects to be created in this cache. + * @args: Arguments for the cache creation (see struct kmem_cache_args). + * @flags: See %SLAB_* flags for an explanation of individual @flags. + * + * Cannot be called within a interrupt, but can be interrupted. + * + * Return: a pointer to the cache on success, NULL on failure. + */ +struct kmem_cache *__kmem_cache_create_args(const char *name, + unsigned int object_size, + struct kmem_cache_args *args, + slab_flags_t flags) { struct kmem_cache *s = NULL; + unsigned int freeptr_offset = UINT_MAX; const char *cache_name; int err; @@ -275,7 +285,7 @@ do_kmem_cache_create_usercopy(const char *name, mutex_lock(&slab_mutex); - err = kmem_cache_sanity_check(name, size); + err = kmem_cache_sanity_check(name, object_size); if (err) { goto out_unlock; } @@ -296,12 +306,14 @@ do_kmem_cache_create_usercopy(const char *name, /* Fail closed on bad usersize of useroffset values. */ if (!IS_ENABLED(CONFIG_HARDENED_USERCOPY) || - WARN_ON(!usersize && useroffset) || - WARN_ON(size < usersize || size - usersize < useroffset)) - usersize = useroffset = 0; - - if (!usersize) - s = __kmem_cache_alias(name, size, align, flags, ctor); + WARN_ON(!args->usersize && args->useroffset) || + WARN_ON(object_size < args->usersize || + object_size - args->usersize < args->useroffset)) + args->usersize = args->useroffset = 0; + + if (!args->usersize) + s = __kmem_cache_alias(name, object_size, args->align, flags, + args->ctor); if (s) goto out_unlock; @@ -311,9 +323,11 @@ do_kmem_cache_create_usercopy(const char *name, goto out_unlock; } - s = create_cache(cache_name, size, freeptr_offset, - calculate_alignment(flags, align, size), - flags, useroffset, usersize, ctor); + if (args->use_freeptr_offset) + freeptr_offset = args->freeptr_offset; + s = create_cache(cache_name, object_size, freeptr_offset, + calculate_alignment(flags, args->align, object_size), + flags, args->useroffset, args->usersize, args->ctor); if (IS_ERR(s)) { err = PTR_ERR(s); kfree_const(cache_name); @@ -335,6 +349,27 @@ out_unlock: } return s; } +EXPORT_SYMBOL(__kmem_cache_create_args); + +static struct kmem_cache * +do_kmem_cache_create_usercopy(const char *name, + unsigned int size, unsigned int freeptr_offset, + unsigned int align, slab_flags_t flags, + unsigned int useroffset, unsigned int usersize, + void (*ctor)(void *)) +{ + struct kmem_cache_args kmem_args = { + .align = align, + .use_freeptr_offset = freeptr_offset != UINT_MAX, + .freeptr_offset = freeptr_offset, + .useroffset = useroffset, + .usersize = usersize, + .ctor = ctor, + }; + + return __kmem_cache_create_args(name, size, &kmem_args, flags); +} + /** * kmem_cache_create_usercopy - Create a cache with a region suitable -- cgit v1.2.3 From 052d67b46bcd91b6785e8e6e047241814f6142a3 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 5 Sep 2024 09:56:53 +0200 Subject: slab: port KMEM_CACHE() to struct kmem_cache_args Make KMEM_CACHE() use struct kmem_cache_args. Reviewed-by: Kees Cook Reviewed-by: Jens Axboe Reviewed-by: Mike Rapoport (Microsoft) Reviewed-by: Vlastimil Babka Signed-off-by: Christian Brauner Reviewed-by: Roman Gushchin Signed-off-by: Vlastimil Babka --- include/linux/slab.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 2b8eeca7fd2c..1f38d94387cc 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -284,9 +284,11 @@ int kmem_cache_shrink(struct kmem_cache *s); * f.e. add ____cacheline_aligned_in_smp to the struct declaration * then the objects will be properly aligned in SMP configurations. */ -#define KMEM_CACHE(__struct, __flags) \ - kmem_cache_create(#__struct, sizeof(struct __struct), \ - __alignof__(struct __struct), (__flags), NULL) +#define KMEM_CACHE(__struct, __flags) \ + __kmem_cache_create_args(#__struct, sizeof(struct __struct), \ + &(struct kmem_cache_args) { \ + .align = __alignof__(struct __struct), \ + }, (__flags)) /* * To whitelist a single field for copying to/from usercopy, use this -- cgit v1.2.3 From 199cd13a745eb44fb4828bca373155293cdcfa5c Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 5 Sep 2024 09:56:54 +0200 Subject: slab: port KMEM_CACHE_USERCOPY() to struct kmem_cache_args Make KMEM_CACHE_USERCOPY() use struct kmem_cache_args. Reviewed-by: Kees Cook Reviewed-by: Jens Axboe Reviewed-by: Mike Rapoport (Microsoft) Reviewed-by: Vlastimil Babka Signed-off-by: Christian Brauner Reviewed-by: Roman Gushchin Signed-off-by: Vlastimil Babka --- include/linux/slab.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 1f38d94387cc..7e15a3a3edb1 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -294,12 +294,13 @@ int kmem_cache_shrink(struct kmem_cache *s); * To whitelist a single field for copying to/from usercopy, use this * macro instead for KMEM_CACHE() above. */ -#define KMEM_CACHE_USERCOPY(__struct, __flags, __field) \ - kmem_cache_create_usercopy(#__struct, \ - sizeof(struct __struct), \ - __alignof__(struct __struct), (__flags), \ - offsetof(struct __struct, __field), \ - sizeof_field(struct __struct, __field), NULL) +#define KMEM_CACHE_USERCOPY(__struct, __flags, __field) \ + __kmem_cache_create_args(#__struct, sizeof(struct __struct), \ + &(struct kmem_cache_args) { \ + .align = __alignof__(struct __struct), \ + .useroffset = offsetof(struct __struct, __field), \ + .usersize = sizeof_field(struct __struct, __field), \ + }, (__flags)) /* * Common kmalloc functions provided by all allocators -- cgit v1.2.3 From b2e7456b5c25c41eda7a8a15f7ccaa4e7579949f Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 5 Sep 2024 09:56:55 +0200 Subject: slab: create kmem_cache_create() compatibility layer Use _Generic() to create a compatibility layer that type switches on the third argument to either call __kmem_cache_create() or __kmem_cache_create_args(). If NULL is passed for the struct kmem_cache_args argument use default args making porting for callers that don't care about additional arguments easy. Reviewed-by: Kees Cook Reviewed-by: Jens Axboe Signed-off-by: Christian Brauner Reviewed-by: Mike Rapoport (Microsoft) Reviewed-by: Roman Gushchin Signed-off-by: Vlastimil Babka --- include/linux/slab.h | 29 ++++++++++++++++++++++++++--- mm/slab_common.c | 10 +++++----- 2 files changed, 31 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 7e15a3a3edb1..15eb0a0defd6 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -262,9 +262,10 @@ struct kmem_cache *__kmem_cache_create_args(const char *name, unsigned int object_size, struct kmem_cache_args *args, slab_flags_t flags); -struct kmem_cache *kmem_cache_create(const char *name, unsigned int size, - unsigned int align, slab_flags_t flags, - void (*ctor)(void *)); + +struct kmem_cache *__kmem_cache_create(const char *name, unsigned int size, + unsigned int align, slab_flags_t flags, + void (*ctor)(void *)); struct kmem_cache *kmem_cache_create_usercopy(const char *name, unsigned int size, unsigned int align, slab_flags_t flags, @@ -273,6 +274,28 @@ struct kmem_cache *kmem_cache_create_usercopy(const char *name, struct kmem_cache *kmem_cache_create_rcu(const char *name, unsigned int size, unsigned int freeptr_offset, slab_flags_t flags); + +/* If NULL is passed for @args, use this variant with default arguments. */ +static inline struct kmem_cache * +__kmem_cache_default_args(const char *name, unsigned int size, + struct kmem_cache_args *args, + slab_flags_t flags) +{ + struct kmem_cache_args kmem_default_args = {}; + + /* Make sure we don't get passed garbage. */ + if (WARN_ON_ONCE(args)) + return ERR_PTR(-EINVAL); + + return __kmem_cache_create_args(name, size, &kmem_default_args, flags); +} + +#define kmem_cache_create(__name, __object_size, __args, ...) \ + _Generic((__args), \ + struct kmem_cache_args *: __kmem_cache_create_args, \ + void *: __kmem_cache_default_args, \ + default: __kmem_cache_create)(__name, __object_size, __args, __VA_ARGS__) + void kmem_cache_destroy(struct kmem_cache *s); int kmem_cache_shrink(struct kmem_cache *s); diff --git a/mm/slab_common.c b/mm/slab_common.c index 19ae3dd6e36f..418459927670 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -383,7 +383,7 @@ kmem_cache_create_usercopy(const char *name, unsigned int size, EXPORT_SYMBOL(kmem_cache_create_usercopy); /** - * kmem_cache_create - Create a cache. + * __kmem_cache_create - Create a cache. * @name: A string which is used in /proc/slabinfo to identify this cache. * @size: The size of objects to be created in this cache. * @align: The required alignment for the objects. @@ -407,9 +407,9 @@ EXPORT_SYMBOL(kmem_cache_create_usercopy); * * Return: a pointer to the cache on success, NULL on failure. */ -struct kmem_cache * -kmem_cache_create(const char *name, unsigned int size, unsigned int align, - slab_flags_t flags, void (*ctor)(void *)) +struct kmem_cache *__kmem_cache_create(const char *name, unsigned int size, + unsigned int align, slab_flags_t flags, + void (*ctor)(void *)) { struct kmem_cache_args kmem_args = { .align = align, @@ -418,7 +418,7 @@ kmem_cache_create(const char *name, unsigned int size, unsigned int align, return __kmem_cache_create_args(name, size, &kmem_args, flags); } -EXPORT_SYMBOL(kmem_cache_create); +EXPORT_SYMBOL(__kmem_cache_create); /** * kmem_cache_create_rcu - Create a SLAB_TYPESAFE_BY_RCU cache. -- cgit v1.2.3 From 3d453e60f1a9c377d670d5fe306d3b9eed477bc0 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 5 Sep 2024 09:56:57 +0200 Subject: slab: remove kmem_cache_create_rcu() Now that we have ported all users of kmem_cache_create_rcu() to struct kmem_cache_args the function is unused and can be removed. Reviewed-by: Kees Cook Reviewed-by: Jens Axboe Reviewed-by: Mike Rapoport (Microsoft) Reviewed-by: Vlastimil Babka Signed-off-by: Christian Brauner Reviewed-by: Roman Gushchin Signed-off-by: Vlastimil Babka --- include/linux/slab.h | 3 --- mm/slab_common.c | 43 ------------------------------------------- 2 files changed, 46 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 15eb0a0defd6..cb82a6414a28 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -271,9 +271,6 @@ struct kmem_cache *kmem_cache_create_usercopy(const char *name, slab_flags_t flags, unsigned int useroffset, unsigned int usersize, void (*ctor)(void *)); -struct kmem_cache *kmem_cache_create_rcu(const char *name, unsigned int size, - unsigned int freeptr_offset, - slab_flags_t flags); /* If NULL is passed for @args, use this variant with default arguments. */ static inline struct kmem_cache * diff --git a/mm/slab_common.c b/mm/slab_common.c index 418459927670..9133b9fafcb1 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -420,49 +420,6 @@ struct kmem_cache *__kmem_cache_create(const char *name, unsigned int size, } EXPORT_SYMBOL(__kmem_cache_create); -/** - * kmem_cache_create_rcu - Create a SLAB_TYPESAFE_BY_RCU cache. - * @name: A string which is used in /proc/slabinfo to identify this cache. - * @size: The size of objects to be created in this cache. - * @freeptr_offset: The offset into the memory to the free pointer - * @flags: SLAB flags - * - * Cannot be called within an interrupt, but can be interrupted. - * - * See kmem_cache_create() for an explanation of possible @flags. - * - * By default SLAB_TYPESAFE_BY_RCU caches place the free pointer outside - * of the object. This might cause the object to grow in size. Callers - * that have a reason to avoid this can specify a custom free pointer - * offset in their struct where the free pointer will be placed. - * - * Note that placing the free pointer inside the object requires the - * caller to ensure that no fields are invalidated that are required to - * guard against object recycling (See SLAB_TYPESAFE_BY_RCU for - * details.). - * - * Using zero as a value for @freeptr_offset is valid. To request no - * offset UINT_MAX must be specified. - * - * Note that @ctor isn't supported with custom free pointers as a @ctor - * requires an external free pointer. - * - * Return: a pointer to the cache on success, NULL on failure. - */ -struct kmem_cache *kmem_cache_create_rcu(const char *name, unsigned int size, - unsigned int freeptr_offset, - slab_flags_t flags) -{ - struct kmem_cache_args kmem_args = { - .freeptr_offset = freeptr_offset, - .use_freeptr_offset = true, - }; - - return __kmem_cache_create_args(name, size, &kmem_args, - flags | SLAB_TYPESAFE_BY_RCU); -} -EXPORT_SYMBOL(kmem_cache_create_rcu); - static struct kmem_cache *kmem_buckets_cache __ro_after_init; /** -- cgit v1.2.3 From 0c9050b09cfb1ddb3fe4b2d401dca1fb674c825a Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 5 Sep 2024 09:56:58 +0200 Subject: slab: make kmem_cache_create_usercopy() static inline Make kmem_cache_create_usercopy() a static inline function. Signed-off-by: Christian Brauner Reviewed-by: Mike Rapoport (Microsoft) Reviewed-by: Roman Gushchin Signed-off-by: Vlastimil Babka --- include/linux/slab.h | 49 ++++++++++++++++++++++++++++++++++++++++++++----- mm/slab_common.c | 45 --------------------------------------------- 2 files changed, 44 insertions(+), 50 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index cb82a6414a28..634717c9f73b 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -266,11 +266,50 @@ struct kmem_cache *__kmem_cache_create_args(const char *name, struct kmem_cache *__kmem_cache_create(const char *name, unsigned int size, unsigned int align, slab_flags_t flags, void (*ctor)(void *)); -struct kmem_cache *kmem_cache_create_usercopy(const char *name, - unsigned int size, unsigned int align, - slab_flags_t flags, - unsigned int useroffset, unsigned int usersize, - void (*ctor)(void *)); + +/** + * kmem_cache_create_usercopy - Create a cache with a region suitable + * for copying to userspace + * @name: A string which is used in /proc/slabinfo to identify this cache. + * @size: The size of objects to be created in this cache. + * @align: The required alignment for the objects. + * @flags: SLAB flags + * @useroffset: Usercopy region offset + * @usersize: Usercopy region size + * @ctor: A constructor for the objects. + * + * Cannot be called within a interrupt, but can be interrupted. + * The @ctor is run when new pages are allocated by the cache. + * + * The flags are + * + * %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5) + * to catch references to uninitialised memory. + * + * %SLAB_RED_ZONE - Insert `Red` zones around the allocated memory to check + * for buffer overruns. + * + * %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware + * cacheline. This can be beneficial if you're counting cycles as closely + * as davem. + * + * Return: a pointer to the cache on success, NULL on failure. + */ +static inline struct kmem_cache * +kmem_cache_create_usercopy(const char *name, unsigned int size, + unsigned int align, slab_flags_t flags, + unsigned int useroffset, unsigned int usersize, + void (*ctor)(void *)) +{ + struct kmem_cache_args kmem_args = { + .align = align, + .ctor = ctor, + .useroffset = useroffset, + .usersize = usersize, + }; + + return __kmem_cache_create_args(name, size, &kmem_args, flags); +} /* If NULL is passed for @args, use this variant with default arguments. */ static inline struct kmem_cache * diff --git a/mm/slab_common.c b/mm/slab_common.c index 9133b9fafcb1..3477a3918afd 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -337,51 +337,6 @@ out_unlock: } EXPORT_SYMBOL(__kmem_cache_create_args); -/** - * kmem_cache_create_usercopy - Create a cache with a region suitable - * for copying to userspace - * @name: A string which is used in /proc/slabinfo to identify this cache. - * @size: The size of objects to be created in this cache. - * @align: The required alignment for the objects. - * @flags: SLAB flags - * @useroffset: Usercopy region offset - * @usersize: Usercopy region size - * @ctor: A constructor for the objects. - * - * Cannot be called within a interrupt, but can be interrupted. - * The @ctor is run when new pages are allocated by the cache. - * - * The flags are - * - * %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5) - * to catch references to uninitialised memory. - * - * %SLAB_RED_ZONE - Insert `Red` zones around the allocated memory to check - * for buffer overruns. - * - * %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware - * cacheline. This can be beneficial if you're counting cycles as closely - * as davem. - * - * Return: a pointer to the cache on success, NULL on failure. - */ -struct kmem_cache * -kmem_cache_create_usercopy(const char *name, unsigned int size, - unsigned int align, slab_flags_t flags, - unsigned int useroffset, unsigned int usersize, - void (*ctor)(void *)) -{ - struct kmem_cache_args kmem_args = { - .align = align, - .ctor = ctor, - .useroffset = useroffset, - .usersize = usersize, - }; - - return __kmem_cache_create_args(name, size, &kmem_args, flags); -} -EXPORT_SYMBOL(kmem_cache_create_usercopy); - /** * __kmem_cache_create - Create a cache. * @name: A string which is used in /proc/slabinfo to identify this cache. -- cgit v1.2.3 From 781aee755638dbb6dbfe022bdd2f732621ec9534 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 5 Sep 2024 09:56:59 +0200 Subject: slab: make __kmem_cache_create() static inline Make __kmem_cache_create() a static inline function. Signed-off-by: Christian Brauner Reviewed-by: Mike Rapoport (Microsoft) Reviewed-by: Roman Gushchin Signed-off-by: Vlastimil Babka --- include/linux/slab.h | 13 ++++++++++--- mm/slab_common.c | 38 -------------------------------------- 2 files changed, 10 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 634717c9f73b..331412a9f4f2 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -262,10 +262,17 @@ struct kmem_cache *__kmem_cache_create_args(const char *name, unsigned int object_size, struct kmem_cache_args *args, slab_flags_t flags); +static inline struct kmem_cache * +__kmem_cache_create(const char *name, unsigned int size, unsigned int align, + slab_flags_t flags, void (*ctor)(void *)) +{ + struct kmem_cache_args kmem_args = { + .align = align, + .ctor = ctor, + }; -struct kmem_cache *__kmem_cache_create(const char *name, unsigned int size, - unsigned int align, slab_flags_t flags, - void (*ctor)(void *)); + return __kmem_cache_create_args(name, size, &kmem_args, flags); +} /** * kmem_cache_create_usercopy - Create a cache with a region suitable diff --git a/mm/slab_common.c b/mm/slab_common.c index 3477a3918afd..30000dcf0736 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -337,44 +337,6 @@ out_unlock: } EXPORT_SYMBOL(__kmem_cache_create_args); -/** - * __kmem_cache_create - Create a cache. - * @name: A string which is used in /proc/slabinfo to identify this cache. - * @size: The size of objects to be created in this cache. - * @align: The required alignment for the objects. - * @flags: SLAB flags - * @ctor: A constructor for the objects. - * - * Cannot be called within a interrupt, but can be interrupted. - * The @ctor is run when new pages are allocated by the cache. - * - * The flags are - * - * %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5) - * to catch references to uninitialised memory. - * - * %SLAB_RED_ZONE - Insert `Red` zones around the allocated memory to check - * for buffer overruns. - * - * %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware - * cacheline. This can be beneficial if you're counting cycles as closely - * as davem. - * - * Return: a pointer to the cache on success, NULL on failure. - */ -struct kmem_cache *__kmem_cache_create(const char *name, unsigned int size, - unsigned int align, slab_flags_t flags, - void (*ctor)(void *)) -{ - struct kmem_cache_args kmem_args = { - .align = align, - .ctor = ctor, - }; - - return __kmem_cache_create_args(name, size, &kmem_args, flags); -} -EXPORT_SYMBOL(__kmem_cache_create); - static struct kmem_cache *kmem_buckets_cache __ro_after_init; /** -- cgit v1.2.3 From 4ba4f1afb6a9fed8ef896c2363076e36572f71da Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 2 Aug 2024 08:16:37 -0700 Subject: perf: Generic hotplug support for a PMU with a scope The perf subsystem assumes that the counters of a PMU are per-CPU. So the user space tool reads a counter from each CPU in the system wide mode. However, many PMUs don't have a per-CPU counter. The counter is effective for a scope, e.g., a die or a socket. To address this, a cpumask is exposed by the kernel driver to restrict to one CPU to stand for a specific scope. In case the given CPU is removed, the hotplug support has to be implemented for each such driver. The codes to support the cpumask and hotplug are very similar. - Expose a cpumask into sysfs - Pickup another CPU in the same scope if the given CPU is removed. - Invoke the perf_pmu_migrate_context() to migrate to a new CPU. - In event init, always set the CPU in the cpumask to event->cpu Similar duplicated codes are implemented for each such PMU driver. It would be good to introduce a generic infrastructure to avoid such duplication. 5 popular scopes are implemented here, core, die, cluster, pkg, and the system-wide. The scope can be set when a PMU is registered. If so, a "cpumask" is automatically exposed for the PMU. The "cpumask" is from the perf_online__mask, which is to track the active CPU for each scope. They are set when the first CPU of the scope is online via the generic perf hotplug support. When a corresponding CPU is removed, the perf_online__mask is updated accordingly and the PMU will be moved to a new CPU from the same scope if possible. Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20240802151643.1691631-2-kan.liang@linux.intel.com --- include/linux/perf_event.h | 18 +++++ kernel/events/core.c | 164 ++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 180 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 701549967c18..a3cbcd727366 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -295,6 +295,19 @@ struct perf_event_pmu_context; #define PERF_PMU_CAP_AUX_OUTPUT 0x0080 #define PERF_PMU_CAP_EXTENDED_HW_TYPE 0x0100 +/** + * pmu::scope + */ +enum perf_pmu_scope { + PERF_PMU_SCOPE_NONE = 0, + PERF_PMU_SCOPE_CORE, + PERF_PMU_SCOPE_DIE, + PERF_PMU_SCOPE_CLUSTER, + PERF_PMU_SCOPE_PKG, + PERF_PMU_SCOPE_SYS_WIDE, + PERF_PMU_MAX_SCOPE, +}; + struct perf_output_handle; #define PMU_NULL_DEV ((void *)(~0UL)) @@ -318,6 +331,11 @@ struct pmu { */ int capabilities; + /* + * PMU scope + */ + unsigned int scope; + int __percpu *pmu_disable_count; struct perf_cpu_pmu_context __percpu *cpu_pmu_context; atomic_t exclusive_cnt; /* < 0: cpu; > 0: tsk */ diff --git a/kernel/events/core.c b/kernel/events/core.c index 67e115d4ef96..5ff973513fac 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -436,6 +436,11 @@ static LIST_HEAD(pmus); static DEFINE_MUTEX(pmus_lock); static struct srcu_struct pmus_srcu; static cpumask_var_t perf_online_mask; +static cpumask_var_t perf_online_core_mask; +static cpumask_var_t perf_online_die_mask; +static cpumask_var_t perf_online_cluster_mask; +static cpumask_var_t perf_online_pkg_mask; +static cpumask_var_t perf_online_sys_mask; static struct kmem_cache *perf_event_cache; /* @@ -11578,10 +11583,60 @@ perf_event_mux_interval_ms_store(struct device *dev, } static DEVICE_ATTR_RW(perf_event_mux_interval_ms); +static inline const struct cpumask *perf_scope_cpu_topology_cpumask(unsigned int scope, int cpu) +{ + switch (scope) { + case PERF_PMU_SCOPE_CORE: + return topology_sibling_cpumask(cpu); + case PERF_PMU_SCOPE_DIE: + return topology_die_cpumask(cpu); + case PERF_PMU_SCOPE_CLUSTER: + return topology_cluster_cpumask(cpu); + case PERF_PMU_SCOPE_PKG: + return topology_core_cpumask(cpu); + case PERF_PMU_SCOPE_SYS_WIDE: + return cpu_online_mask; + } + + return NULL; +} + +static inline struct cpumask *perf_scope_cpumask(unsigned int scope) +{ + switch (scope) { + case PERF_PMU_SCOPE_CORE: + return perf_online_core_mask; + case PERF_PMU_SCOPE_DIE: + return perf_online_die_mask; + case PERF_PMU_SCOPE_CLUSTER: + return perf_online_cluster_mask; + case PERF_PMU_SCOPE_PKG: + return perf_online_pkg_mask; + case PERF_PMU_SCOPE_SYS_WIDE: + return perf_online_sys_mask; + } + + return NULL; +} + +static ssize_t cpumask_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct pmu *pmu = dev_get_drvdata(dev); + struct cpumask *mask = perf_scope_cpumask(pmu->scope); + + if (mask) + return cpumap_print_to_pagebuf(true, buf, mask); + return 0; +} + +static DEVICE_ATTR_RO(cpumask); + static struct attribute *pmu_dev_attrs[] = { &dev_attr_type.attr, &dev_attr_perf_event_mux_interval_ms.attr, &dev_attr_nr_addr_filters.attr, + &dev_attr_cpumask.attr, NULL, }; @@ -11593,6 +11648,10 @@ static umode_t pmu_dev_is_visible(struct kobject *kobj, struct attribute *a, int if (n == 2 && !pmu->nr_addr_filters) return 0; + /* cpumask */ + if (n == 3 && pmu->scope == PERF_PMU_SCOPE_NONE) + return 0; + return a->mode; } @@ -11677,6 +11736,11 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type) goto free_pdc; } + if (WARN_ONCE(pmu->scope >= PERF_PMU_MAX_SCOPE, "Can not register a pmu with an invalid scope.\n")) { + ret = -EINVAL; + goto free_pdc; + } + pmu->name = name; if (type >= 0) @@ -11831,6 +11895,22 @@ static int perf_try_init_event(struct pmu *pmu, struct perf_event *event) event_has_any_exclude_flag(event)) ret = -EINVAL; + if (pmu->scope != PERF_PMU_SCOPE_NONE && event->cpu >= 0) { + const struct cpumask *cpumask = perf_scope_cpu_topology_cpumask(pmu->scope, event->cpu); + struct cpumask *pmu_cpumask = perf_scope_cpumask(pmu->scope); + int cpu; + + if (pmu_cpumask && cpumask) { + cpu = cpumask_any_and(pmu_cpumask, cpumask); + if (cpu >= nr_cpu_ids) + ret = -ENODEV; + else + event->cpu = cpu; + } else { + ret = -ENODEV; + } + } + if (ret && event->destroy) event->destroy(event); } @@ -13784,6 +13864,12 @@ static void __init perf_event_init_all_cpus(void) int cpu; zalloc_cpumask_var(&perf_online_mask, GFP_KERNEL); + zalloc_cpumask_var(&perf_online_core_mask, GFP_KERNEL); + zalloc_cpumask_var(&perf_online_die_mask, GFP_KERNEL); + zalloc_cpumask_var(&perf_online_cluster_mask, GFP_KERNEL); + zalloc_cpumask_var(&perf_online_pkg_mask, GFP_KERNEL); + zalloc_cpumask_var(&perf_online_sys_mask, GFP_KERNEL); + for_each_possible_cpu(cpu) { swhash = &per_cpu(swevent_htable, cpu); @@ -13833,6 +13919,40 @@ static void __perf_event_exit_context(void *__info) raw_spin_unlock(&ctx->lock); } +static void perf_event_clear_cpumask(unsigned int cpu) +{ + int target[PERF_PMU_MAX_SCOPE]; + unsigned int scope; + struct pmu *pmu; + + cpumask_clear_cpu(cpu, perf_online_mask); + + for (scope = PERF_PMU_SCOPE_NONE + 1; scope < PERF_PMU_MAX_SCOPE; scope++) { + const struct cpumask *cpumask = perf_scope_cpu_topology_cpumask(scope, cpu); + struct cpumask *pmu_cpumask = perf_scope_cpumask(scope); + + target[scope] = -1; + if (WARN_ON_ONCE(!pmu_cpumask || !cpumask)) + continue; + + if (!cpumask_test_and_clear_cpu(cpu, pmu_cpumask)) + continue; + target[scope] = cpumask_any_but(cpumask, cpu); + if (target[scope] < nr_cpu_ids) + cpumask_set_cpu(target[scope], pmu_cpumask); + } + + /* migrate */ + list_for_each_entry_rcu(pmu, &pmus, entry, lockdep_is_held(&pmus_srcu)) { + if (pmu->scope == PERF_PMU_SCOPE_NONE || + WARN_ON_ONCE(pmu->scope >= PERF_PMU_MAX_SCOPE)) + continue; + + if (target[pmu->scope] >= 0 && target[pmu->scope] < nr_cpu_ids) + perf_pmu_migrate_context(pmu, cpu, target[pmu->scope]); + } +} + static void perf_event_exit_cpu_context(int cpu) { struct perf_cpu_context *cpuctx; @@ -13840,6 +13960,11 @@ static void perf_event_exit_cpu_context(int cpu) // XXX simplify cpuctx->online mutex_lock(&pmus_lock); + /* + * Clear the cpumasks, and migrate to other CPUs if possible. + * Must be invoked before the __perf_event_exit_context. + */ + perf_event_clear_cpumask(cpu); cpuctx = per_cpu_ptr(&perf_cpu_context, cpu); ctx = &cpuctx->ctx; @@ -13847,7 +13972,6 @@ static void perf_event_exit_cpu_context(int cpu) smp_call_function_single(cpu, __perf_event_exit_context, ctx, 1); cpuctx->online = 0; mutex_unlock(&ctx->mutex); - cpumask_clear_cpu(cpu, perf_online_mask); mutex_unlock(&pmus_lock); } #else @@ -13856,6 +13980,42 @@ static void perf_event_exit_cpu_context(int cpu) { } #endif +static void perf_event_setup_cpumask(unsigned int cpu) +{ + struct cpumask *pmu_cpumask; + unsigned int scope; + + cpumask_set_cpu(cpu, perf_online_mask); + + /* + * Early boot stage, the cpumask hasn't been set yet. + * The perf_online__masks includes the first CPU of each domain. + * Always uncondifionally set the boot CPU for the perf_online__masks. + */ + if (!topology_sibling_cpumask(cpu)) { + for (scope = PERF_PMU_SCOPE_NONE + 1; scope < PERF_PMU_MAX_SCOPE; scope++) { + pmu_cpumask = perf_scope_cpumask(scope); + if (WARN_ON_ONCE(!pmu_cpumask)) + continue; + cpumask_set_cpu(cpu, pmu_cpumask); + } + return; + } + + for (scope = PERF_PMU_SCOPE_NONE + 1; scope < PERF_PMU_MAX_SCOPE; scope++) { + const struct cpumask *cpumask = perf_scope_cpu_topology_cpumask(scope, cpu); + + pmu_cpumask = perf_scope_cpumask(scope); + + if (WARN_ON_ONCE(!pmu_cpumask || !cpumask)) + continue; + + if (!cpumask_empty(cpumask) && + cpumask_any_and(pmu_cpumask, cpumask) >= nr_cpu_ids) + cpumask_set_cpu(cpu, pmu_cpumask); + } +} + int perf_event_init_cpu(unsigned int cpu) { struct perf_cpu_context *cpuctx; @@ -13864,7 +14024,7 @@ int perf_event_init_cpu(unsigned int cpu) perf_swevent_init_cpu(cpu); mutex_lock(&pmus_lock); - cpumask_set_cpu(cpu, perf_online_mask); + perf_event_setup_cpumask(cpu); cpuctx = per_cpu_ptr(&perf_cpu_context, cpu); ctx = &cpuctx->ctx; -- cgit v1.2.3 From a48a36b316ae5d3ab83f9b545dba15998e96d59c Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 2 Aug 2024 08:16:38 -0700 Subject: perf: Add PERF_EV_CAP_READ_SCOPE Usually, an event can be read from any CPU of the scope. It doesn't need to be read from the advertised CPU. Add a new event cap, PERF_EV_CAP_READ_SCOPE. An event of a PMU with scope can be read from any active CPU in the scope. Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20240802151643.1691631-3-kan.liang@linux.intel.com --- include/linux/perf_event.h | 3 +++ kernel/events/core.c | 14 +++++++++++--- 2 files changed, 14 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index a3cbcd727366..794f66057878 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -636,10 +636,13 @@ typedef void (*perf_overflow_handler_t)(struct perf_event *, * PERF_EV_CAP_SIBLING: An event with this flag must be a group sibling and * cannot be a group leader. If an event with this flag is detached from the * group it is scheduled out and moved into an unrecoverable ERROR state. + * PERF_EV_CAP_READ_SCOPE: A CPU event that can be read from any CPU of the + * PMU scope where it is active. */ #define PERF_EV_CAP_SOFTWARE BIT(0) #define PERF_EV_CAP_READ_ACTIVE_PKG BIT(1) #define PERF_EV_CAP_SIBLING BIT(2) +#define PERF_EV_CAP_READ_SCOPE BIT(3) #define SWEVENT_HLIST_BITS 8 #define SWEVENT_HLIST_SIZE (1 << SWEVENT_HLIST_BITS) diff --git a/kernel/events/core.c b/kernel/events/core.c index 5ff973513fac..2766090de84e 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4556,16 +4556,24 @@ struct perf_read_data { int ret; }; +static inline const struct cpumask *perf_scope_cpu_topology_cpumask(unsigned int scope, int cpu); + static int __perf_event_read_cpu(struct perf_event *event, int event_cpu) { + int local_cpu = smp_processor_id(); u16 local_pkg, event_pkg; if ((unsigned)event_cpu >= nr_cpu_ids) return event_cpu; - if (event->group_caps & PERF_EV_CAP_READ_ACTIVE_PKG) { - int local_cpu = smp_processor_id(); + if (event->group_caps & PERF_EV_CAP_READ_SCOPE) { + const struct cpumask *cpumask = perf_scope_cpu_topology_cpumask(event->pmu->scope, event_cpu); + + if (cpumask && cpumask_test_cpu(local_cpu, cpumask)) + return local_cpu; + } + if (event->group_caps & PERF_EV_CAP_READ_ACTIVE_PKG) { event_pkg = topology_physical_package_id(event_cpu); local_pkg = topology_physical_package_id(local_cpu); @@ -11905,7 +11913,7 @@ static int perf_try_init_event(struct pmu *pmu, struct perf_event *event) if (cpu >= nr_cpu_ids) ret = -ENODEV; else - event->cpu = cpu; + event->event_caps |= PERF_EV_CAP_READ_SCOPE; } else { ret = -ENODEV; } -- cgit v1.2.3 From 08155c7f2a2cc6ff99886ea5743da274be24ebe4 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 2 Aug 2024 08:16:39 -0700 Subject: perf/x86/intel/cstate: Clean up cpumask and hotplug There are three cstate PMUs with different scopes, core, die and module. The scopes are supported by the generic perf_event subsystem now. Set the scope for each PMU and remove all the cpumask and hotplug codes. Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20240802151643.1691631-4-kan.liang@linux.intel.com --- arch/x86/events/intel/cstate.c | 142 ++--------------------------------------- include/linux/cpuhotplug.h | 2 - 2 files changed, 5 insertions(+), 139 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 9f116dfc4728..ae4ec16156bb 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -128,10 +128,6 @@ static ssize_t __cstate_##_var##_show(struct device *dev, \ static struct device_attribute format_attr_##_var = \ __ATTR(_name, 0444, __cstate_##_var##_show, NULL) -static ssize_t cstate_get_attr_cpumask(struct device *dev, - struct device_attribute *attr, - char *buf); - /* Model -> events mapping */ struct cstate_model { unsigned long core_events; @@ -206,22 +202,9 @@ static struct attribute_group cstate_format_attr_group = { .attrs = cstate_format_attrs, }; -static cpumask_t cstate_core_cpu_mask; -static DEVICE_ATTR(cpumask, S_IRUGO, cstate_get_attr_cpumask, NULL); - -static struct attribute *cstate_cpumask_attrs[] = { - &dev_attr_cpumask.attr, - NULL, -}; - -static struct attribute_group cpumask_attr_group = { - .attrs = cstate_cpumask_attrs, -}; - static const struct attribute_group *cstate_attr_groups[] = { &cstate_events_attr_group, &cstate_format_attr_group, - &cpumask_attr_group, NULL, }; @@ -269,8 +252,6 @@ static struct perf_msr pkg_msr[] = { [PERF_CSTATE_PKG_C10_RES] = { MSR_PKG_C10_RESIDENCY, &group_cstate_pkg_c10, test_msr }, }; -static cpumask_t cstate_pkg_cpu_mask; - /* cstate_module PMU */ static struct pmu cstate_module_pmu; static bool has_cstate_module; @@ -291,28 +272,9 @@ static struct perf_msr module_msr[] = { [PERF_CSTATE_MODULE_C6_RES] = { MSR_MODULE_C6_RES_MS, &group_cstate_module_c6, test_msr }, }; -static cpumask_t cstate_module_cpu_mask; - -static ssize_t cstate_get_attr_cpumask(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct pmu *pmu = dev_get_drvdata(dev); - - if (pmu == &cstate_core_pmu) - return cpumap_print_to_pagebuf(true, buf, &cstate_core_cpu_mask); - else if (pmu == &cstate_pkg_pmu) - return cpumap_print_to_pagebuf(true, buf, &cstate_pkg_cpu_mask); - else if (pmu == &cstate_module_pmu) - return cpumap_print_to_pagebuf(true, buf, &cstate_module_cpu_mask); - else - return 0; -} - static int cstate_pmu_event_init(struct perf_event *event) { u64 cfg = event->attr.config; - int cpu; if (event->attr.type != event->pmu->type) return -ENOENT; @@ -331,20 +293,13 @@ static int cstate_pmu_event_init(struct perf_event *event) if (!(core_msr_mask & (1 << cfg))) return -EINVAL; event->hw.event_base = core_msr[cfg].msr; - cpu = cpumask_any_and(&cstate_core_cpu_mask, - topology_sibling_cpumask(event->cpu)); } else if (event->pmu == &cstate_pkg_pmu) { if (cfg >= PERF_CSTATE_PKG_EVENT_MAX) return -EINVAL; cfg = array_index_nospec((unsigned long)cfg, PERF_CSTATE_PKG_EVENT_MAX); if (!(pkg_msr_mask & (1 << cfg))) return -EINVAL; - - event->event_caps |= PERF_EV_CAP_READ_ACTIVE_PKG; - event->hw.event_base = pkg_msr[cfg].msr; - cpu = cpumask_any_and(&cstate_pkg_cpu_mask, - topology_die_cpumask(event->cpu)); } else if (event->pmu == &cstate_module_pmu) { if (cfg >= PERF_CSTATE_MODULE_EVENT_MAX) return -EINVAL; @@ -352,16 +307,10 @@ static int cstate_pmu_event_init(struct perf_event *event) if (!(module_msr_mask & (1 << cfg))) return -EINVAL; event->hw.event_base = module_msr[cfg].msr; - cpu = cpumask_any_and(&cstate_module_cpu_mask, - topology_cluster_cpumask(event->cpu)); } else { return -ENOENT; } - if (cpu >= nr_cpu_ids) - return -ENODEV; - - event->cpu = cpu; event->hw.config = cfg; event->hw.idx = -1; return 0; @@ -412,84 +361,6 @@ static int cstate_pmu_event_add(struct perf_event *event, int mode) return 0; } -/* - * Check if exiting cpu is the designated reader. If so migrate the - * events when there is a valid target available - */ -static int cstate_cpu_exit(unsigned int cpu) -{ - unsigned int target; - - if (has_cstate_core && - cpumask_test_and_clear_cpu(cpu, &cstate_core_cpu_mask)) { - - target = cpumask_any_but(topology_sibling_cpumask(cpu), cpu); - /* Migrate events if there is a valid target */ - if (target < nr_cpu_ids) { - cpumask_set_cpu(target, &cstate_core_cpu_mask); - perf_pmu_migrate_context(&cstate_core_pmu, cpu, target); - } - } - - if (has_cstate_pkg && - cpumask_test_and_clear_cpu(cpu, &cstate_pkg_cpu_mask)) { - - target = cpumask_any_but(topology_die_cpumask(cpu), cpu); - /* Migrate events if there is a valid target */ - if (target < nr_cpu_ids) { - cpumask_set_cpu(target, &cstate_pkg_cpu_mask); - perf_pmu_migrate_context(&cstate_pkg_pmu, cpu, target); - } - } - - if (has_cstate_module && - cpumask_test_and_clear_cpu(cpu, &cstate_module_cpu_mask)) { - - target = cpumask_any_but(topology_cluster_cpumask(cpu), cpu); - /* Migrate events if there is a valid target */ - if (target < nr_cpu_ids) { - cpumask_set_cpu(target, &cstate_module_cpu_mask); - perf_pmu_migrate_context(&cstate_module_pmu, cpu, target); - } - } - return 0; -} - -static int cstate_cpu_init(unsigned int cpu) -{ - unsigned int target; - - /* - * If this is the first online thread of that core, set it in - * the core cpu mask as the designated reader. - */ - target = cpumask_any_and(&cstate_core_cpu_mask, - topology_sibling_cpumask(cpu)); - - if (has_cstate_core && target >= nr_cpu_ids) - cpumask_set_cpu(cpu, &cstate_core_cpu_mask); - - /* - * If this is the first online thread of that package, set it - * in the package cpu mask as the designated reader. - */ - target = cpumask_any_and(&cstate_pkg_cpu_mask, - topology_die_cpumask(cpu)); - if (has_cstate_pkg && target >= nr_cpu_ids) - cpumask_set_cpu(cpu, &cstate_pkg_cpu_mask); - - /* - * If this is the first online thread of that cluster, set it - * in the cluster cpu mask as the designated reader. - */ - target = cpumask_any_and(&cstate_module_cpu_mask, - topology_cluster_cpumask(cpu)); - if (has_cstate_module && target >= nr_cpu_ids) - cpumask_set_cpu(cpu, &cstate_module_cpu_mask); - - return 0; -} - static const struct attribute_group *core_attr_update[] = { &group_cstate_core_c1, &group_cstate_core_c3, @@ -526,6 +397,7 @@ static struct pmu cstate_core_pmu = { .stop = cstate_pmu_event_stop, .read = cstate_pmu_event_update, .capabilities = PERF_PMU_CAP_NO_INTERRUPT | PERF_PMU_CAP_NO_EXCLUDE, + .scope = PERF_PMU_SCOPE_CORE, .module = THIS_MODULE, }; @@ -541,6 +413,7 @@ static struct pmu cstate_pkg_pmu = { .stop = cstate_pmu_event_stop, .read = cstate_pmu_event_update, .capabilities = PERF_PMU_CAP_NO_INTERRUPT | PERF_PMU_CAP_NO_EXCLUDE, + .scope = PERF_PMU_SCOPE_PKG, .module = THIS_MODULE, }; @@ -556,6 +429,7 @@ static struct pmu cstate_module_pmu = { .stop = cstate_pmu_event_stop, .read = cstate_pmu_event_update, .capabilities = PERF_PMU_CAP_NO_INTERRUPT | PERF_PMU_CAP_NO_EXCLUDE, + .scope = PERF_PMU_SCOPE_CLUSTER, .module = THIS_MODULE, }; @@ -810,9 +684,6 @@ static int __init cstate_probe(const struct cstate_model *cm) static inline void cstate_cleanup(void) { - cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_CSTATE_ONLINE); - cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_CSTATE_STARTING); - if (has_cstate_core) perf_pmu_unregister(&cstate_core_pmu); @@ -827,11 +698,6 @@ static int __init cstate_init(void) { int err; - cpuhp_setup_state(CPUHP_AP_PERF_X86_CSTATE_STARTING, - "perf/x86/cstate:starting", cstate_cpu_init, NULL); - cpuhp_setup_state(CPUHP_AP_PERF_X86_CSTATE_ONLINE, - "perf/x86/cstate:online", NULL, cstate_cpu_exit); - if (has_cstate_core) { err = perf_pmu_register(&cstate_core_pmu, cstate_core_pmu.name, -1); if (err) { @@ -844,6 +710,8 @@ static int __init cstate_init(void) if (has_cstate_pkg) { if (topology_max_dies_per_package() > 1) { + /* CLX-AP is multi-die and the cstate is die-scope */ + cstate_pkg_pmu.scope = PERF_PMU_SCOPE_DIE; err = perf_pmu_register(&cstate_pkg_pmu, "cstate_die", -1); } else { diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 9316c39260e0..2101ae2ecfca 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -152,7 +152,6 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING, CPUHP_AP_PERF_X86_STARTING, CPUHP_AP_PERF_X86_AMD_IBS_STARTING, - CPUHP_AP_PERF_X86_CSTATE_STARTING, CPUHP_AP_PERF_XTENSA_STARTING, CPUHP_AP_ARM_VFP_STARTING, CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING, @@ -209,7 +208,6 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE, CPUHP_AP_PERF_X86_AMD_POWER_ONLINE, CPUHP_AP_PERF_X86_RAPL_ONLINE, - CPUHP_AP_PERF_X86_CSTATE_ONLINE, CPUHP_AP_PERF_S390_CF_ONLINE, CPUHP_AP_PERF_S390_SF_ONLINE, CPUHP_AP_PERF_ARM_CCI_ONLINE, -- cgit v1.2.3 From 740c1c84bfa3d8c63bd3b01fb570e7452f51fbd8 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 10 Sep 2024 10:26:17 +0800 Subject: spi: remove spi_controller_is_slave() and spi_slave_abort() spi_controller_is_slave() and spi_slave_abort() are all replaced, so they can be removed. No functional changed. Signed-off-by: Yang Yingliang Link: https://patch.msgid.link/20240910022618.1397-8-yangyingliang@huaweicloud.com Signed-off-by: Mark Brown --- drivers/spi/spi.c | 13 +------------ include/linux/spi/spi.h | 12 +----------- 2 files changed, 2 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index ea14c33bc831..c1dad30a4528 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -2934,21 +2934,10 @@ static struct class spi_master_class = { #ifdef CONFIG_SPI_SLAVE /** - * spi_slave_abort - abort the ongoing transfer request on an SPI slave + * spi_target_abort - abort the ongoing transfer request on an SPI slave * controller * @spi: device used for the current transfer */ -int spi_slave_abort(struct spi_device *spi) -{ - struct spi_controller *ctlr = spi->controller; - - if (spi_controller_is_slave(ctlr) && ctlr->slave_abort) - return ctlr->slave_abort(ctlr); - - return -ENOTSUPP; -} -EXPORT_SYMBOL_GPL(spi_slave_abort); - int spi_target_abort(struct spi_device *spi) { struct spi_controller *ctlr = spi->controller; diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index d47d5f14ff99..4b95663163e0 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -498,7 +498,6 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * controller has native support for memory like operations. * @mem_caps: controller capabilities for the handling of memory operations. * @unprepare_message: undo any work done by prepare_message(). - * @slave_abort: abort the ongoing transfer request on an SPI slave controller * @target_abort: abort the ongoing transfer request on an SPI target controller * @cs_gpiods: Array of GPIO descriptors to use as chip select lines; one per CS * number. Any individual value may be NULL for CS lines that @@ -725,10 +724,7 @@ struct spi_controller { struct spi_message *message); int (*unprepare_message)(struct spi_controller *ctlr, struct spi_message *message); - union { - int (*slave_abort)(struct spi_controller *ctlr); - int (*target_abort)(struct spi_controller *ctlr); - }; + int (*target_abort)(struct spi_controller *ctlr); /* * These hooks are for drivers that use a generic implementation @@ -802,11 +798,6 @@ static inline void spi_controller_put(struct spi_controller *ctlr) put_device(&ctlr->dev); } -static inline bool spi_controller_is_slave(struct spi_controller *ctlr) -{ - return IS_ENABLED(CONFIG_SPI_SLAVE) && ctlr->slave; -} - static inline bool spi_controller_is_target(struct spi_controller *ctlr) { return IS_ENABLED(CONFIG_SPI_SLAVE) && ctlr->target; @@ -1296,7 +1287,6 @@ extern int devm_spi_optimize_message(struct device *dev, struct spi_device *spi, extern int spi_setup(struct spi_device *spi); extern int spi_async(struct spi_device *spi, struct spi_message *message); -extern int spi_slave_abort(struct spi_device *spi); extern int spi_target_abort(struct spi_device *spi); static inline size_t -- cgit v1.2.3 From d6de45e3c6f3713d3825d3e2860c11d24e0f941f Mon Sep 17 00:00:00 2001 From: Bas Nieuwenhuizen Date: Tue, 10 Sep 2024 00:35:03 +0200 Subject: platform/x86: asus-wmi: Disable OOBE experience on Zenbook S 16 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The OOBE experience fades the keyboard backlight in & out continuously, and make the backlight uncontrollable using its device. Workaround taken from https://wiki.archlinux.org/index.php?title=ASUS_Zenbook_UM5606&diff=next&oldid=815547 Signed-off-by: Bas Nieuwenhuizen Reviewed-by: Luke D. Jones Link: https://lore.kernel.org/r/20240909223503.1445779-1-bas@basnieuwenhuizen.nl Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen --- drivers/platform/x86/asus-wmi.c | 10 ++++++++++ include/linux/platform_data/x86/asus-wmi.h | 1 + 2 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 37636e5a38e3..321a658e4554 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -1793,6 +1793,16 @@ static int asus_wmi_led_init(struct asus_wmi *asus) goto error; } + if (asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_OOBE)) { + /* + * Disable OOBE state, so that e.g. the keyboard backlight + * works. + */ + rv = asus_wmi_set_devstate(ASUS_WMI_DEVID_OOBE, 1, NULL); + if (rv) + goto error; + } + error: if (rv) asus_wmi_led_exit(asus); diff --git a/include/linux/platform_data/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h index 0aeeae1c1943..ae9bf7479e7b 100644 --- a/include/linux/platform_data/x86/asus-wmi.h +++ b/include/linux/platform_data/x86/asus-wmi.h @@ -62,6 +62,7 @@ #define ASUS_WMI_DEVID_KBD_BACKLIGHT 0x00050021 #define ASUS_WMI_DEVID_LIGHT_SENSOR 0x00050022 /* ?? */ #define ASUS_WMI_DEVID_LIGHTBAR 0x00050025 +#define ASUS_WMI_DEVID_OOBE 0x0005002F /* This can only be used to disable the screen, not re-enable */ #define ASUS_WMI_DEVID_SCREENPAD_POWER 0x00050031 /* Writing a brightness re-enables the screen if disabled */ -- cgit v1.2.3 From 070a5e6295e88a2b75cbfef04ff8b4ec05775e6d Mon Sep 17 00:00:00 2001 From: Furong Xu <0x1207@gmail.com> Date: Fri, 6 Sep 2024 22:30:06 +0800 Subject: net: stmmac: move stmmac_fpe_cfg to stmmac_priv data By moving the fpe_cfg field to the stmmac_priv data, stmmac_fpe_cfg becomes platform-data eventually, instead of a run-time config. Suggested-by: Serge Semin Signed-off-by: Furong Xu <0x1207@gmail.com> Reviewed-by: Vladimir Oltean Reviewed-by: Serge Semin Link: https://patch.msgid.link/d9b3d7ecb308c5e39778a4c8ae9df288a2754379.1725631883.git.0x1207@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/hwif.h | 2 ++ drivers/net/ethernet/stmicro/stmmac/stmmac.h | 30 ++++++++++++++++++++++- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 20 +++++++-------- drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c | 16 +++--------- include/linux/stmmac.h | 28 --------------------- 5 files changed, 44 insertions(+), 52 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index 7e90f34b8c88..68574798c03f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -28,6 +28,8 @@ struct stmmac_extra_stats; struct stmmac_priv; struct stmmac_safety_stats; +struct stmmac_fpe_cfg; +enum stmmac_mpacket_type; struct dma_desc; struct dma_extended_desc; struct dma_edesc; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index b23b920eedb1..458d6b16ce21 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -146,6 +146,33 @@ struct stmmac_channel { u32 index; }; +/* FPE link state */ +enum stmmac_fpe_state { + FPE_STATE_OFF = 0, + FPE_STATE_CAPABLE = 1, + FPE_STATE_ENTERING_ON = 2, + FPE_STATE_ON = 3, +}; + +/* FPE link-partner hand-shaking mPacket type */ +enum stmmac_mpacket_type { + MPACKET_VERIFY = 0, + MPACKET_RESPONSE = 1, +}; + +enum stmmac_fpe_task_state_t { + __FPE_REMOVING, + __FPE_TASK_SCHED, +}; + +struct stmmac_fpe_cfg { + bool enable; /* FPE enable */ + bool hs_enable; /* FPE handshake enable */ + enum stmmac_fpe_state lp_fpe_state; /* Link Partner FPE state */ + enum stmmac_fpe_state lo_fpe_state; /* Local station FPE state */ + u32 fpe_csr; /* MAC_FPE_CTRL_STS reg cache */ +}; + struct stmmac_tc_entry { bool in_use; bool in_hw; @@ -339,11 +366,12 @@ struct stmmac_priv { struct workqueue_struct *wq; struct work_struct service_task; - /* Workqueue for handling FPE hand-shaking */ + /* Frame Preemption feature (FPE) */ unsigned long fpe_task_state; struct workqueue_struct *fpe_wq; struct work_struct fpe_task; char wq_name[IFNAMSIZ + 4]; + struct stmmac_fpe_cfg fpe_cfg; /* TC Handling */ unsigned int tc_entries_max; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index d9fca8d1227c..529fe31f8b04 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -968,7 +968,7 @@ static void stmmac_mac_config(struct phylink_config *config, unsigned int mode, static void stmmac_fpe_link_state_handle(struct stmmac_priv *priv, bool is_up) { - struct stmmac_fpe_cfg *fpe_cfg = priv->plat->fpe_cfg; + struct stmmac_fpe_cfg *fpe_cfg = &priv->fpe_cfg; enum stmmac_fpe_state *lo_state = &fpe_cfg->lo_fpe_state; enum stmmac_fpe_state *lp_state = &fpe_cfg->lp_fpe_state; bool *hs_enable = &fpe_cfg->hs_enable; @@ -3536,7 +3536,7 @@ static int stmmac_hw_setup(struct net_device *dev, bool ptp_register) if (priv->dma_cap.fpesel) { stmmac_fpe_start_wq(priv); - if (priv->plat->fpe_cfg->enable) + if (priv->fpe_cfg.enable) stmmac_fpe_handshake(priv, true); } @@ -5982,7 +5982,7 @@ static int stmmac_set_features(struct net_device *netdev, static void stmmac_fpe_event_status(struct stmmac_priv *priv, int status) { - struct stmmac_fpe_cfg *fpe_cfg = priv->plat->fpe_cfg; + struct stmmac_fpe_cfg *fpe_cfg = &priv->fpe_cfg; enum stmmac_fpe_state *lo_state = &fpe_cfg->lo_fpe_state; enum stmmac_fpe_state *lp_state = &fpe_cfg->lp_fpe_state; bool *hs_enable = &fpe_cfg->hs_enable; @@ -7381,7 +7381,7 @@ static void stmmac_fpe_lp_task(struct work_struct *work) { struct stmmac_priv *priv = container_of(work, struct stmmac_priv, fpe_task); - struct stmmac_fpe_cfg *fpe_cfg = priv->plat->fpe_cfg; + struct stmmac_fpe_cfg *fpe_cfg = &priv->fpe_cfg; enum stmmac_fpe_state *lo_state = &fpe_cfg->lo_fpe_state; enum stmmac_fpe_state *lp_state = &fpe_cfg->lp_fpe_state; bool *hs_enable = &fpe_cfg->hs_enable; @@ -7427,17 +7427,17 @@ static void stmmac_fpe_lp_task(struct work_struct *work) void stmmac_fpe_handshake(struct stmmac_priv *priv, bool enable) { - if (priv->plat->fpe_cfg->hs_enable != enable) { + if (priv->fpe_cfg.hs_enable != enable) { if (enable) { stmmac_fpe_send_mpacket(priv, priv->ioaddr, - priv->plat->fpe_cfg, + &priv->fpe_cfg, MPACKET_VERIFY); } else { - priv->plat->fpe_cfg->lo_fpe_state = FPE_STATE_OFF; - priv->plat->fpe_cfg->lp_fpe_state = FPE_STATE_OFF; + priv->fpe_cfg.lo_fpe_state = FPE_STATE_OFF; + priv->fpe_cfg.lp_fpe_state = FPE_STATE_OFF; } - priv->plat->fpe_cfg->hs_enable = enable; + priv->fpe_cfg.hs_enable = enable; } } @@ -7898,7 +7898,7 @@ int stmmac_suspend(struct device *dev) if (priv->dma_cap.fpesel) { /* Disable FPE */ stmmac_fpe_configure(priv, priv->ioaddr, - priv->plat->fpe_cfg, + &priv->fpe_cfg, priv->plat->tx_queues_to_use, priv->plat->rx_queues_to_use, false); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 996f2bcd07a2..9cc41ed01882 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -282,16 +282,6 @@ static int tc_init(struct stmmac_priv *priv) if (ret) return -ENOMEM; - if (!priv->plat->fpe_cfg) { - priv->plat->fpe_cfg = devm_kzalloc(priv->device, - sizeof(*priv->plat->fpe_cfg), - GFP_KERNEL); - if (!priv->plat->fpe_cfg) - return -ENOMEM; - } else { - memset(priv->plat->fpe_cfg, 0, sizeof(*priv->plat->fpe_cfg)); - } - /* Fail silently as we can still use remaining features, e.g. CBS */ if (!dma_cap->frpsel) return 0; @@ -1076,7 +1066,7 @@ static int tc_taprio_configure(struct stmmac_priv *priv, /* Actual FPE register configuration will be done after FPE handshake * is success. */ - priv->plat->fpe_cfg->enable = fpe; + priv->fpe_cfg.enable = fpe; ret = stmmac_est_configure(priv, priv, priv->est, priv->plat->clk_ptp_rate); @@ -1109,9 +1099,9 @@ disable: mutex_unlock(&priv->est_lock); } - priv->plat->fpe_cfg->enable = false; + priv->fpe_cfg.enable = false; stmmac_fpe_configure(priv, priv->ioaddr, - priv->plat->fpe_cfg, + &priv->fpe_cfg, priv->plat->tx_queues_to_use, priv->plat->rx_queues_to_use, false); diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 338991c08f00..d79ff252cfdc 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -138,33 +138,6 @@ struct stmmac_txq_cfg { int tbs_en; }; -/* FPE link state */ -enum stmmac_fpe_state { - FPE_STATE_OFF = 0, - FPE_STATE_CAPABLE = 1, - FPE_STATE_ENTERING_ON = 2, - FPE_STATE_ON = 3, -}; - -/* FPE link-partner hand-shaking mPacket type */ -enum stmmac_mpacket_type { - MPACKET_VERIFY = 0, - MPACKET_RESPONSE = 1, -}; - -enum stmmac_fpe_task_state_t { - __FPE_REMOVING, - __FPE_TASK_SCHED, -}; - -struct stmmac_fpe_cfg { - bool enable; /* FPE enable */ - bool hs_enable; /* FPE handshake enable */ - enum stmmac_fpe_state lp_fpe_state; /* Link Partner FPE state */ - enum stmmac_fpe_state lo_fpe_state; /* Local station FPE state */ - u32 fpe_csr; /* MAC_FPE_CTRL_STS reg cache */ -}; - struct stmmac_safety_feature_cfg { u32 tsoee; u32 mrxpee; @@ -232,7 +205,6 @@ struct plat_stmmacenet_data { struct fwnode_handle *port_node; struct device_node *mdio_node; struct stmmac_dma_cfg *dma_cfg; - struct stmmac_fpe_cfg *fpe_cfg; struct stmmac_safety_feature_cfg *safety_feat_cfg; int clk_csr; int has_gmac; -- cgit v1.2.3 From d591f6804e7e1310881c9224d72247a2b65039af Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 27 Aug 2024 18:48:46 -0500 Subject: PCI: Wait for device readiness with Configuration RRS After a device reset, delays are required before the device can successfully complete config accesses. PCIe r6.0, sec 6.6, specifies some delays required before software can perform config accesses. Devices that require more time after those delays may respond to config accesses with Configuration Request Retry Status (RRS) completions. Callers of pci_dev_wait() are responsible for delays until the device can respond to config accesses. pci_dev_wait() waits any additional time until the device can successfully complete config accesses. Reading config space of devices that are not present or not ready typically returns ~0 (PCI_ERROR_RESPONSE). Previously we polled the Command register until we got a value other than ~0. This is sometimes a problem because Root Complex handling of RRS completions may include several retries and implementation-specific behavior that is invisible to software (see sec 2.3.2), so the exponential backoff in pci_dev_wait() may not work as intended. Linux enables Configuration RRS Software Visibility on all Root Ports that support it. If it is enabled, read the Vendor ID instead of the Command register. RRS completions cause immediate return of the 0x0001 reserved Vendor ID value, so the pci_dev_wait() backoff works correctly. When a read of Vendor ID eventually completes successfully by returning a non-0x0001 value (the Vendor ID or 0xffff for VFs), the device should be initialized and ready to respond to config requests. For conventional PCI devices or devices below Root Ports that don't support Configuration RRS Software Visibility, poll the Command register as before. This was developed independently, but is very similar to Stanislav Spassov's previous work at https://lore.kernel.org/linux-pci/20200223122057.6504-1-stanspas@amazon.com Link: https://lore.kernel.org/r/20240827234848.4429-2-helgaas@kernel.org Signed-off-by: Bjorn Helgaas Tested-by: Duc Dang --- drivers/pci/pci.c | 41 ++++++++++++++++++++++++++++------------- drivers/pci/pci.h | 5 +++++ drivers/pci/probe.c | 9 +++------ include/linux/pci.h | 1 + 4 files changed, 37 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index e3a49f66982d..fc2ecb7fe081 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1283,7 +1283,9 @@ static int pci_dev_wait(struct pci_dev *dev, char *reset_type, int timeout) { int delay = 1; bool retrain = false; - struct pci_dev *bridge; + struct pci_dev *root, *bridge; + + root = pcie_find_root_port(dev); if (pci_is_pcie(dev)) { bridge = pci_upstream_bridge(dev); @@ -1292,16 +1294,23 @@ static int pci_dev_wait(struct pci_dev *dev, char *reset_type, int timeout) } /* - * After reset, the device should not silently discard config - * requests, but it may still indicate that it needs more time by - * responding to them with CRS completions. The Root Port will - * generally synthesize ~0 (PCI_ERROR_RESPONSE) data to complete - * the read (except when CRS SV is enabled and the read was for the - * Vendor ID; in that case it synthesizes 0x0001 data). + * The caller has already waited long enough after a reset that the + * device should respond to config requests, but it may respond + * with Request Retry Status (RRS) if it needs more time to + * initialize. + * + * If the device is below a Root Port with Configuration RRS + * Software Visibility enabled, reading the Vendor ID returns a + * special data value if the device responded with RRS. Read the + * Vendor ID until we get non-RRS status. * - * Wait for the device to return a non-CRS completion. Read the - * Command register instead of Vendor ID so we don't have to - * contend with the CRS SV value. + * If there's no Root Port or Configuration RRS Software Visibility + * is not enabled, the device may still respond with RRS, but + * hardware may retry the config request. If no retries receive + * Successful Completion, hardware generally synthesizes ~0 + * (PCI_ERROR_RESPONSE) data to complete the read. Reading Vendor + * ID for VFs and non-existent devices also returns ~0, so read the + * Command register until it returns something other than ~0. */ for (;;) { u32 id; @@ -1311,9 +1320,15 @@ static int pci_dev_wait(struct pci_dev *dev, char *reset_type, int timeout) return -ENOTTY; } - pci_read_config_dword(dev, PCI_COMMAND, &id); - if (!PCI_POSSIBLE_ERROR(id)) - break; + if (root && root->config_crs_sv) { + pci_read_config_dword(dev, PCI_VENDOR_ID, &id); + if (!pci_bus_crs_vendor_id(id)) + break; + } else { + pci_read_config_dword(dev, PCI_COMMAND, &id); + if (!PCI_POSSIBLE_ERROR(id)) + break; + } if (delay > timeout) { pci_warn(dev, "not ready %dms after %s; giving up\n", diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 79c8398f3938..fa1997bc2667 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -139,6 +139,11 @@ bool pci_bridge_d3_possible(struct pci_dev *dev); void pci_bridge_d3_update(struct pci_dev *dev); int pci_bridge_wait_for_secondary_bus(struct pci_dev *dev, char *reset_type); +static inline bool pci_bus_crs_vendor_id(u32 l) +{ + return (l & 0xffff) == PCI_VENDOR_ID_PCI_SIG; +} + static inline void pci_wakeup_event(struct pci_dev *dev) { /* Wait 100 ms before the system can be put into a sleep state. */ diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index b14b9876c030..b1615da9eb6b 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -1209,9 +1209,11 @@ static void pci_enable_crs(struct pci_dev *pdev) /* Enable CRS Software Visibility if supported */ pcie_capability_read_word(pdev, PCI_EXP_RTCAP, &root_cap); - if (root_cap & PCI_EXP_RTCAP_CRSVIS) + if (root_cap & PCI_EXP_RTCAP_CRSVIS) { pcie_capability_set_word(pdev, PCI_EXP_RTCTL, PCI_EXP_RTCTL_CRSSVE); + pdev->config_crs_sv = 1; + } } static unsigned int pci_scan_child_bus_extend(struct pci_bus *bus, @@ -2343,11 +2345,6 @@ struct pci_dev *pci_alloc_dev(struct pci_bus *bus) } EXPORT_SYMBOL(pci_alloc_dev); -static bool pci_bus_crs_vendor_id(u32 l) -{ - return (l & 0xffff) == PCI_VENDOR_ID_PCI_SIG; -} - static bool pci_bus_wait_crs(struct pci_bus *bus, int devfn, u32 *l, int timeout) { diff --git a/include/linux/pci.h b/include/linux/pci.h index 4cf89a4b4cbc..121d8d94d6d0 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -371,6 +371,7 @@ struct pci_dev { can be generated */ unsigned int pme_poll:1; /* Poll device's PME status bit */ unsigned int pinned:1; /* Whether this dev is pinned */ + unsigned int config_crs_sv:1; /* Config CRS software visibility */ unsigned int imm_ready:1; /* Supports Immediate Readiness */ unsigned int d1_support:1; /* Low power state D1 is supported */ unsigned int d2_support:1; /* Low power state D2 is supported */ -- cgit v1.2.3 From 87f10faf166a9114aa0d4132298cad379de16fdd Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 27 Aug 2024 18:48:48 -0500 Subject: PCI: Rename CRS Completion Status to RRS PCIe r6.0 changed the abbreviation for "Configuration Request Retry Status" Completion Status from "CRS" to "RRS" and uses the terminology of "Configuration RRS Software Visibility" instead of "CRS Software Visibility". Align the Linux usage with the r6.0 spec language. No functional change intended. It's confusing to make this change, but I think "RRS" *is* a better abbreviation because it was easy to interpret "CRS" as "Completion Retry Status", which really didn't make any sense. Link: https://lore.kernel.org/r/20240827234848.4429-4-helgaas@kernel.org Signed-off-by: Bjorn Helgaas --- drivers/bcma/driver_pci_host.c | 10 ++--- drivers/pci/controller/dwc/pcie-tegra194.c | 18 ++++----- drivers/pci/controller/pci-aardvark.c | 64 +++++++++++++++--------------- drivers/pci/controller/pci-xgene.c | 6 +-- drivers/pci/controller/pcie-iproc.c | 18 ++++----- drivers/pci/pci-bridge-emul.c | 4 +- drivers/pci/pci.c | 4 +- drivers/pci/pci.h | 8 ++-- drivers/pci/probe.c | 28 ++++++------- include/linux/bcma/bcma_driver_pci.h | 2 +- include/linux/pci.h | 2 +- include/uapi/linux/pci_regs.h | 6 ++- 12 files changed, 86 insertions(+), 84 deletions(-) (limited to 'include/linux') diff --git a/drivers/bcma/driver_pci_host.c b/drivers/bcma/driver_pci_host.c index ed3be52ab63d..8540052d37c5 100644 --- a/drivers/bcma/driver_pci_host.c +++ b/drivers/bcma/driver_pci_host.c @@ -334,7 +334,7 @@ static u8 bcma_find_pci_capability(struct bcma_drv_pci *pc, unsigned int dev, } /* If the root port is capable of returning Config Request - * Retry Status (CRS) Completion Status to software then + * Retry Status (RRS) Completion Status to software then * enable the feature. */ static void bcma_core_pci_enable_crs(struct bcma_drv_pci *pc) @@ -348,10 +348,10 @@ static void bcma_core_pci_enable_crs(struct bcma_drv_pci *pc) NULL); root_cap = cap_ptr + PCI_EXP_RTCAP; bcma_extpci_read_config(pc, 0, 0, root_cap, &val16, sizeof(u16)); - if (val16 & BCMA_CORE_PCI_RC_CRS_VISIBILITY) { - /* Enable CRS software visibility */ + if (val16 & BCMA_CORE_PCI_RC_RRS_VISIBILITY) { + /* Enable Configuration RRS Software Visibility */ root_ctrl = cap_ptr + PCI_EXP_RTCTL; - val16 = PCI_EXP_RTCTL_CRSSVE; + val16 = PCI_EXP_RTCTL_RRS_SVE; bcma_extpci_read_config(pc, 0, 0, root_ctrl, &val16, sizeof(u16)); @@ -360,7 +360,7 @@ static void bcma_core_pci_enable_crs(struct bcma_drv_pci *pc) * 100 ms wait time from the end of Reset. If the device is * not done with its internal initialization, it must at * least return a completion TLP, with a completion status - * of "Configuration Request Retry Status (CRS)". The root + * of "Configuration Request Retry Status (RRS)". The root * complex must complete the request to the host by returning * a read-data value of 0001h for the Vendor ID field and * all 1s for any additional bytes included in the request. diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c index 4bf7b433417a..886354342ef1 100644 --- a/drivers/pci/controller/dwc/pcie-tegra194.c +++ b/drivers/pci/controller/dwc/pcie-tegra194.c @@ -183,11 +183,11 @@ #define GEN3_EQ_CONTROL_OFF_FB_MODE_MASK GENMASK(3, 0) #define PORT_LOGIC_AMBA_ERROR_RESPONSE_DEFAULT 0x8D0 -#define AMBA_ERROR_RESPONSE_CRS_SHIFT 3 -#define AMBA_ERROR_RESPONSE_CRS_MASK GENMASK(1, 0) -#define AMBA_ERROR_RESPONSE_CRS_OKAY 0 -#define AMBA_ERROR_RESPONSE_CRS_OKAY_FFFFFFFF 1 -#define AMBA_ERROR_RESPONSE_CRS_OKAY_FFFF0001 2 +#define AMBA_ERROR_RESPONSE_RRS_SHIFT 3 +#define AMBA_ERROR_RESPONSE_RRS_MASK GENMASK(1, 0) +#define AMBA_ERROR_RESPONSE_RRS_OKAY 0 +#define AMBA_ERROR_RESPONSE_RRS_OKAY_FFFFFFFF 1 +#define AMBA_ERROR_RESPONSE_RRS_OKAY_FFFF0001 2 #define MSIX_ADDR_MATCH_LOW_OFF 0x940 #define MSIX_ADDR_MATCH_LOW_OFF_EN BIT(0) @@ -907,11 +907,11 @@ static int tegra_pcie_dw_host_init(struct dw_pcie_rp *pp) dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, 0); - /* Enable as 0xFFFF0001 response for CRS */ + /* Enable as 0xFFFF0001 response for RRS */ val = dw_pcie_readl_dbi(pci, PORT_LOGIC_AMBA_ERROR_RESPONSE_DEFAULT); - val &= ~(AMBA_ERROR_RESPONSE_CRS_MASK << AMBA_ERROR_RESPONSE_CRS_SHIFT); - val |= (AMBA_ERROR_RESPONSE_CRS_OKAY_FFFF0001 << - AMBA_ERROR_RESPONSE_CRS_SHIFT); + val &= ~(AMBA_ERROR_RESPONSE_RRS_MASK << AMBA_ERROR_RESPONSE_RRS_SHIFT); + val |= (AMBA_ERROR_RESPONSE_RRS_OKAY_FFFF0001 << + AMBA_ERROR_RESPONSE_RRS_SHIFT); dw_pcie_writel_dbi(pci, PORT_LOGIC_AMBA_ERROR_RESPONSE_DEFAULT, val); /* Clear Slot Clock Configuration bit if SRNS configuration */ diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index e66594558ce2..afccae3bfbc6 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -50,7 +50,7 @@ #define PIO_COMPLETION_STATUS_MASK GENMASK(9, 7) #define PIO_COMPLETION_STATUS_OK 0 #define PIO_COMPLETION_STATUS_UR 1 -#define PIO_COMPLETION_STATUS_CRS 2 +#define PIO_COMPLETION_STATUS_RRS 2 #define PIO_COMPLETION_STATUS_CA 4 #define PIO_NON_POSTED_REQ BIT(10) #define PIO_ERR_STATUS BIT(11) @@ -262,7 +262,7 @@ enum { #define MSI_IRQ_NUM 32 -#define CFG_RD_CRS_VAL 0xffff0001 +#define CFG_RD_RRS_VAL 0xffff0001 struct advk_pcie { struct platform_device *pdev; @@ -649,7 +649,7 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie) advk_pcie_train_link(pcie); } -static int advk_pcie_check_pio_status(struct advk_pcie *pcie, bool allow_crs, u32 *val) +static int advk_pcie_check_pio_status(struct advk_pcie *pcie, bool allow_rrs, u32 *val) { struct device *dev = &pcie->pdev->dev; u32 reg; @@ -669,7 +669,7 @@ static int advk_pcie_check_pio_status(struct advk_pcie *pcie, bool allow_crs, u3 * 2) value Unsupported Request(1) of COMPLETION_STATUS(bit9:7) only * means a PIO write error, and for PIO read it is successful with * a read value of 0xFFFFFFFF. - * 3) value Completion Retry Status(CRS) of COMPLETION_STATUS(bit9:7) + * 3) value Config Request Retry Status(RRS) of COMPLETION_STATUS(bit9:7) * only means a PIO write error, and for PIO read it is successful * with a read value of 0xFFFF0001. * 4) value Completer Abort (CA) of COMPLETION_STATUS(bit9:7) means @@ -694,10 +694,10 @@ static int advk_pcie_check_pio_status(struct advk_pcie *pcie, bool allow_crs, u3 strcomp_status = "UR"; ret = -EOPNOTSUPP; break; - case PIO_COMPLETION_STATUS_CRS: - if (allow_crs && val) { - /* PCIe r4.0, sec 2.3.2, says: - * If CRS Software Visibility is enabled: + case PIO_COMPLETION_STATUS_RRS: + if (allow_rrs && val) { + /* PCIe r6.0, sec 2.3.2, says: + * If Configuration RRS Software Visibility is enabled: * For a Configuration Read Request that includes both * bytes of the Vendor ID field of a device Function's * Configuration Space Header, the Root Complex must @@ -706,22 +706,22 @@ static int advk_pcie_check_pio_status(struct advk_pcie *pcie, bool allow_crs, u3 * all '1's for any additional bytes included in the * request. * - * So CRS in this case is not an error status. + * So RRS in this case is not an error status. */ - *val = CFG_RD_CRS_VAL; + *val = CFG_RD_RRS_VAL; strcomp_status = NULL; ret = 0; break; } - /* PCIe r4.0, sec 2.3.2, says: - * If CRS Software Visibility is not enabled, the Root Complex + /* PCIe r6.0, sec 2.3.2, says: + * If RRS Software Visibility is not enabled, the Root Complex * must re-issue the Configuration Request as a new Request. - * If CRS Software Visibility is enabled: For a Configuration + * If RRS Software Visibility is enabled: For a Configuration * Write Request or for any other Configuration Read Request, * the Root Complex must re-issue the Configuration Request as * a new Request. * A Root Complex implementation may choose to limit the number - * of Configuration Request/CRS Completion Status loops before + * of Configuration Request/RRS Completion Status loops before * determining that something is wrong with the target of the * Request and taking appropriate action, e.g., complete the * Request to the host as a failed transaction. @@ -729,7 +729,7 @@ static int advk_pcie_check_pio_status(struct advk_pcie *pcie, bool allow_crs, u3 * So return -EAGAIN and caller (pci-aardvark.c driver) will * re-issue request again up to the PIO_RETRY_CNT retries. */ - strcomp_status = "CRS"; + strcomp_status = "RRS"; ret = -EAGAIN; break; case PIO_COMPLETION_STATUS_CA: @@ -920,8 +920,8 @@ advk_pci_bridge_emul_pcie_conf_write(struct pci_bridge_emul *bridge, case PCI_EXP_RTCTL: { u16 rootctl = le16_to_cpu(bridge->pcie_conf.rootctl); - /* Only emulation of PMEIE and CRSSVE bits is provided */ - rootctl &= PCI_EXP_RTCTL_PMEIE | PCI_EXP_RTCTL_CRSSVE; + /* Only emulation of PMEIE and RRS_SVE bits is provided */ + rootctl &= PCI_EXP_RTCTL_PMEIE | PCI_EXP_RTCTL_RRS_SVE; bridge->pcie_conf.rootctl = cpu_to_le16(rootctl); break; } @@ -1075,7 +1075,7 @@ static int advk_sw_pci_bridge_init(struct advk_pcie *pcie) bridge->pcie_conf.slotsta = cpu_to_le16(PCI_EXP_SLTSTA_PDS); /* Indicates supports for Completion Retry Status */ - bridge->pcie_conf.rootcap = cpu_to_le16(PCI_EXP_RTCAP_CRSVIS); + bridge->pcie_conf.rootcap = cpu_to_le16(PCI_EXP_RTCAP_RRS_SV); bridge->subsystem_vendor_id = advk_readl(pcie, PCIE_CORE_SSDEV_ID_REG) & 0xffff; bridge->subsystem_id = advk_readl(pcie, PCIE_CORE_SSDEV_ID_REG) >> 16; @@ -1141,7 +1141,7 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn, { struct advk_pcie *pcie = bus->sysdata; int retry_count; - bool allow_crs; + bool allow_rrs; u32 reg; int ret; @@ -1153,16 +1153,16 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn, size, val); /* - * Completion Retry Status is possible to return only when reading - * both bytes from PCI_VENDOR_ID at once and CRSSVE flag on Root - * Port is enabled. + * Configuration Request Retry Status (RRS) is possible to return + * only when reading both bytes from PCI_VENDOR_ID at once and + * RRS_SVE flag on Root Port is enabled. */ - allow_crs = (where == PCI_VENDOR_ID) && (size >= 2) && + allow_rrs = (where == PCI_VENDOR_ID) && (size >= 2) && (le16_to_cpu(pcie->bridge.pcie_conf.rootctl) & - PCI_EXP_RTCTL_CRSSVE); + PCI_EXP_RTCTL_RRS_SVE); if (advk_pcie_pio_is_running(pcie)) - goto try_crs; + goto try_rrs; /* Program the control register */ reg = advk_readl(pcie, PIO_CTRL); @@ -1189,12 +1189,12 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn, ret = advk_pcie_wait_pio(pcie); if (ret < 0) - goto try_crs; + goto try_rrs; retry_count += ret; /* Check PIO status and get the read result */ - ret = advk_pcie_check_pio_status(pcie, allow_crs, val); + ret = advk_pcie_check_pio_status(pcie, allow_rrs, val); } while (ret == -EAGAIN && retry_count < PIO_RETRY_CNT); if (ret < 0) @@ -1207,13 +1207,13 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn, return PCIBIOS_SUCCESSFUL; -try_crs: +try_rrs: /* - * If it is possible, return Completion Retry Status so that caller - * tries to issue the request again instead of failing. + * If it is possible, return Configuration Request Retry Status so + * that caller tries to issue the request again instead of failing. */ - if (allow_crs) { - *val = CFG_RD_CRS_VAL; + if (allow_rrs) { + *val = CFG_RD_RRS_VAL; return PCIBIOS_SUCCESSFUL; } diff --git a/drivers/pci/controller/pci-xgene.c b/drivers/pci/controller/pci-xgene.c index 8e457fa450a2..1e2ebbfa36d1 100644 --- a/drivers/pci/controller/pci-xgene.c +++ b/drivers/pci/controller/pci-xgene.c @@ -171,17 +171,17 @@ static int xgene_pcie_config_read32(struct pci_bus *bus, unsigned int devfn, /* * The v1 controller has a bug in its Configuration Request Retry - * Status (CRS) logic: when CRS Software Visibility is enabled and + * Status (RRS) logic: when RRS Software Visibility is enabled and * we read the Vendor and Device ID of a non-existent device, the * controller fabricates return data of 0xFFFF0001 ("device exists * but is not ready") instead of 0xFFFFFFFF (PCI_ERROR_RESPONSE) * ("device does not exist"). This causes the PCI core to retry * the read until it times out. Avoid this by not claiming to - * support CRS SV. + * support RRS SV. */ if (pci_is_root_bus(bus) && (port->version == XGENE_PCIE_IP_VER_1) && ((where & ~0x3) == XGENE_V1_PCI_EXP_CAP + PCI_EXP_RTCTL)) - *val &= ~(PCI_EXP_RTCAP_CRSVIS << 16); + *val &= ~(PCI_EXP_RTCAP_RRS_SV << 16); if (size <= 2) *val = (*val >> (8 * (where & 3))) & ((1 << (size * 8)) - 1); diff --git a/drivers/pci/controller/pcie-iproc.c b/drivers/pci/controller/pcie-iproc.c index 97f739a2c9f8..22134e95574b 100644 --- a/drivers/pci/controller/pcie-iproc.c +++ b/drivers/pci/controller/pcie-iproc.c @@ -54,7 +54,7 @@ #define CFG_RD_SUCCESS 0 #define CFG_RD_UR 1 -#define CFG_RD_CRS 2 +#define CFG_RD_RRS 2 #define CFG_RD_CA 3 #define CFG_RETRY_STATUS 0xffff0001 #define CFG_RETRY_STATUS_TIMEOUT_US 500000 /* 500 milliseconds */ @@ -485,31 +485,31 @@ static unsigned int iproc_pcie_cfg_retry(struct iproc_pcie *pcie, u32 status; /* - * As per PCIe spec r3.1, sec 2.3.2, CRS Software Visibility only + * As per PCIe r6.0, sec 2.3.2, Config RRS Software Visibility only * affects config reads of the Vendor ID. For config writes or any * other config reads, the Root may automatically reissue the * configuration request again as a new request. * * For config reads, this hardware returns CFG_RETRY_STATUS data - * when it receives a CRS completion, regardless of the address of - * the read or the CRS Software Visibility Enable bit. As a + * when it receives a RRS completion, regardless of the address of + * the read or the RRS Software Visibility Enable bit. As a * partial workaround for this, we retry in software any read that * returns CFG_RETRY_STATUS. * * Note that a non-Vendor ID config register may have a value of * CFG_RETRY_STATUS. If we read that, we can't distinguish it from - * a CRS completion, so we will incorrectly retry the read and + * a RRS completion, so we will incorrectly retry the read and * eventually return the wrong data (0xffffffff). */ data = readl(cfg_data_p); while (data == CFG_RETRY_STATUS && timeout--) { /* - * CRS state is set in CFG_RD status register + * RRS state is set in CFG_RD status register * This will handle the case where CFG_RETRY_STATUS is * valid config data. */ status = iproc_pcie_read_reg(pcie, IPROC_PCIE_CFG_RD_STATUS); - if (status != CFG_RD_CRS) + if (status != CFG_RD_RRS) return data; udelay(1); @@ -556,8 +556,8 @@ static void iproc_pcie_fix_cap(struct iproc_pcie *pcie, int where, u32 *val) break; case IPROC_PCI_EXP_CAP + PCI_EXP_RTCTL: - /* Don't advertise CRS SV support */ - *val &= ~(PCI_EXP_RTCAP_CRSVIS << 16); + /* Don't advertise RRS SV support */ + *val &= ~(PCI_EXP_RTCAP_RRS_SV << 16); break; default: diff --git a/drivers/pci/pci-bridge-emul.c b/drivers/pci/pci-bridge-emul.c index 9334b2dd4764..6658c1edd464 100644 --- a/drivers/pci/pci-bridge-emul.c +++ b/drivers/pci/pci-bridge-emul.c @@ -257,8 +257,8 @@ struct pci_bridge_reg_behavior pcie_cap_regs_behavior[PCI_CAP_PCIE_SIZEOF / 4] = */ .rw = (PCI_EXP_RTCTL_SECEE | PCI_EXP_RTCTL_SENFEE | PCI_EXP_RTCTL_SEFEE | PCI_EXP_RTCTL_PMEIE | - PCI_EXP_RTCTL_CRSSVE), - .ro = PCI_EXP_RTCAP_CRSVIS << 16, + PCI_EXP_RTCTL_RRS_SVE), + .ro = PCI_EXP_RTCAP_RRS_SV << 16, }, [PCI_EXP_RTSTA / 4] = { diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index fc2ecb7fe081..55d6124acb2d 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1320,9 +1320,9 @@ static int pci_dev_wait(struct pci_dev *dev, char *reset_type, int timeout) return -ENOTTY; } - if (root && root->config_crs_sv) { + if (root && root->config_rrs_sv) { pci_read_config_dword(dev, PCI_VENDOR_ID, &id); - if (!pci_bus_crs_vendor_id(id)) + if (!pci_bus_rrs_vendor_id(id)) break; } else { pci_read_config_dword(dev, PCI_COMMAND, &id); diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index fa1997bc2667..061cc1b48fd8 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -139,7 +139,7 @@ bool pci_bridge_d3_possible(struct pci_dev *dev); void pci_bridge_d3_update(struct pci_dev *dev); int pci_bridge_wait_for_secondary_bus(struct pci_dev *dev, char *reset_type); -static inline bool pci_bus_crs_vendor_id(u32 l) +static inline bool pci_bus_rrs_vendor_id(u32 l) { return (l & 0xffff) == PCI_VENDOR_ID_PCI_SIG; } @@ -295,10 +295,10 @@ void pci_put_host_bridge_device(struct device *dev); int pci_configure_extended_tags(struct pci_dev *dev, void *ign); bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *pl, - int crs_timeout); + int rrs_timeout); bool pci_bus_generic_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *pl, - int crs_timeout); -int pci_idt_bus_quirk(struct pci_bus *bus, int devfn, u32 *pl, int crs_timeout); + int rrs_timeout); +int pci_idt_bus_quirk(struct pci_bus *bus, int devfn, u32 *pl, int rrs_timeout); int pci_setup_device(struct pci_dev *dev); int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type, diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index b1615da9eb6b..e79d9bea32bf 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -1203,16 +1203,16 @@ struct pci_bus *pci_add_new_bus(struct pci_bus *parent, struct pci_dev *dev, } EXPORT_SYMBOL(pci_add_new_bus); -static void pci_enable_crs(struct pci_dev *pdev) +static void pci_enable_rrs_sv(struct pci_dev *pdev) { u16 root_cap = 0; - /* Enable CRS Software Visibility if supported */ + /* Enable Configuration RRS Software Visibility if supported */ pcie_capability_read_word(pdev, PCI_EXP_RTCAP, &root_cap); - if (root_cap & PCI_EXP_RTCAP_CRSVIS) { + if (root_cap & PCI_EXP_RTCAP_RRS_SV) { pcie_capability_set_word(pdev, PCI_EXP_RTCTL, - PCI_EXP_RTCTL_CRSSVE); - pdev->config_crs_sv = 1; + PCI_EXP_RTCTL_RRS_SVE); + pdev->config_rrs_sv = 1; } } @@ -1328,7 +1328,7 @@ static int pci_scan_bridge_extend(struct pci_bus *bus, struct pci_dev *dev, pci_write_config_word(dev, PCI_BRIDGE_CONTROL, bctl & ~PCI_BRIDGE_CTL_MASTER_ABORT); - pci_enable_crs(dev); + pci_enable_rrs_sv(dev); if ((secondary || subordinate) && !pcibios_assign_all_busses() && !is_cardbus && !broken) { @@ -2345,23 +2345,23 @@ struct pci_dev *pci_alloc_dev(struct pci_bus *bus) } EXPORT_SYMBOL(pci_alloc_dev); -static bool pci_bus_wait_crs(struct pci_bus *bus, int devfn, u32 *l, +static bool pci_bus_wait_rrs(struct pci_bus *bus, int devfn, u32 *l, int timeout) { int delay = 1; - if (!pci_bus_crs_vendor_id(*l)) - return true; /* not a CRS completion */ + if (!pci_bus_rrs_vendor_id(*l)) + return true; /* not a Configuration RRS completion */ if (!timeout) - return false; /* CRS, but caller doesn't want to wait */ + return false; /* RRS, but caller doesn't want to wait */ /* * We got the reserved Vendor ID that indicates a completion with - * Configuration Request Retry Status (CRS). Retry until we get a + * Configuration Request Retry Status (RRS). Retry until we get a * valid Vendor ID or we time out. */ - while (pci_bus_crs_vendor_id(*l)) { + while (pci_bus_rrs_vendor_id(*l)) { if (delay > timeout) { pr_warn("pci %04x:%02x:%02x.%d: not ready after %dms; giving up\n", pci_domain_nr(bus), bus->number, @@ -2400,8 +2400,8 @@ bool pci_bus_generic_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l, *l == 0x0000ffff || *l == 0xffff0000) return false; - if (pci_bus_crs_vendor_id(*l)) - return pci_bus_wait_crs(bus, devfn, l, timeout); + if (pci_bus_rrs_vendor_id(*l)) + return pci_bus_wait_rrs(bus, devfn, l, timeout); return true; } diff --git a/include/linux/bcma/bcma_driver_pci.h b/include/linux/bcma/bcma_driver_pci.h index 68da8dba5162..dba41b65ae0d 100644 --- a/include/linux/bcma/bcma_driver_pci.h +++ b/include/linux/bcma/bcma_driver_pci.h @@ -203,7 +203,7 @@ struct pci_dev; #define BCMA_CORE_PCI_MDIO_RXCTRL0 0x840 /* PCIE Root Capability Register bits (Host mode only) */ -#define BCMA_CORE_PCI_RC_CRS_VISIBILITY 0x0001 +#define BCMA_CORE_PCI_RC_RRS_VISIBILITY 0x0001 struct bcma_drv_pci; struct bcma_bus; diff --git a/include/linux/pci.h b/include/linux/pci.h index 121d8d94d6d0..27d8ce977674 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -371,7 +371,7 @@ struct pci_dev { can be generated */ unsigned int pme_poll:1; /* Poll device's PME status bit */ unsigned int pinned:1; /* Whether this dev is pinned */ - unsigned int config_crs_sv:1; /* Config CRS software visibility */ + unsigned int config_rrs_sv:1; /* Config RRS software visibility */ unsigned int imm_ready:1; /* Supports Immediate Readiness */ unsigned int d1_support:1; /* Low power state D1 is supported */ unsigned int d2_support:1; /* Low power state D2 is supported */ diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 94c00996e633..f94591f9f5e9 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -634,9 +634,11 @@ #define PCI_EXP_RTCTL_SENFEE 0x0002 /* System Error on Non-Fatal Error */ #define PCI_EXP_RTCTL_SEFEE 0x0004 /* System Error on Fatal Error */ #define PCI_EXP_RTCTL_PMEIE 0x0008 /* PME Interrupt Enable */ -#define PCI_EXP_RTCTL_CRSSVE 0x0010 /* CRS Software Visibility Enable */ +#define PCI_EXP_RTCTL_RRS_SVE 0x0010 /* Config RRS Software Visibility Enable */ +#define PCI_EXP_RTCTL_CRSSVE PCI_EXP_RTCTL_RRS_SVE /* compatibility */ #define PCI_EXP_RTCAP 0x1e /* Root Capabilities */ -#define PCI_EXP_RTCAP_CRSVIS 0x0001 /* CRS Software Visibility capability */ +#define PCI_EXP_RTCAP_RRS_SV 0x0001 /* Config RRS Software Visibility */ +#define PCI_EXP_RTCAP_CRSVIS PCI_EXP_RTCAP_RRS_SV /* compatibility */ #define PCI_EXP_RTSTA 0x20 /* Root Status */ #define PCI_EXP_RTSTA_PME_RQ_ID 0x0000ffff /* PME Requester ID */ #define PCI_EXP_RTSTA_PME 0x00010000 /* PME status */ -- cgit v1.2.3 From 884ee6dc85b959bc152f15bca80c30f06069e6c4 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Fri, 6 Sep 2024 14:27:24 +0800 Subject: f2fs: get rid of online repaire on corrupted directory syzbot reports a f2fs bug as below: kernel BUG at fs/f2fs/inode.c:896! RIP: 0010:f2fs_evict_inode+0x1598/0x15c0 fs/f2fs/inode.c:896 Call Trace: evict+0x532/0x950 fs/inode.c:704 dispose_list fs/inode.c:747 [inline] evict_inodes+0x5f9/0x690 fs/inode.c:797 generic_shutdown_super+0x9d/0x2d0 fs/super.c:627 kill_block_super+0x44/0x90 fs/super.c:1696 kill_f2fs_super+0x344/0x690 fs/f2fs/super.c:4898 deactivate_locked_super+0xc4/0x130 fs/super.c:473 cleanup_mnt+0x41f/0x4b0 fs/namespace.c:1373 task_work_run+0x24f/0x310 kernel/task_work.c:228 ptrace_notify+0x2d2/0x380 kernel/signal.c:2402 ptrace_report_syscall include/linux/ptrace.h:415 [inline] ptrace_report_syscall_exit include/linux/ptrace.h:477 [inline] syscall_exit_work+0xc6/0x190 kernel/entry/common.c:173 syscall_exit_to_user_mode_prepare kernel/entry/common.c:200 [inline] __syscall_exit_to_user_mode_work kernel/entry/common.c:205 [inline] syscall_exit_to_user_mode+0x279/0x370 kernel/entry/common.c:218 do_syscall_64+0x100/0x230 arch/x86/entry/common.c:89 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0010:f2fs_evict_inode+0x1598/0x15c0 fs/f2fs/inode.c:896 Online repaire on corrupted directory in f2fs_lookup() can generate dirty data/meta while racing w/ readonly remount, it may leave dirty inode after filesystem becomes readonly, however, checkpoint() will skips flushing dirty inode in a state of readonly mode, result in above panic. Let's get rid of online repaire in f2fs_lookup(), and leave the work to fsck.f2fs. Fixes: 510022a85839 ("f2fs: add F2FS_INLINE_DOTS to recover missing dot dentries") Reported-by: syzbot+ebea2790904673d7c618@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/000000000000a7b20f061ff2d56a@google.com Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/f2fs.h | 11 -------- fs/f2fs/namei.c | 68 ------------------------------------------------- include/linux/f2fs_fs.h | 2 +- 3 files changed, 1 insertion(+), 80 deletions(-) (limited to 'include/linux') diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 8d850192dfdf..0abb7bb39296 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -790,7 +790,6 @@ enum { FI_NEED_IPU, /* used for ipu per file */ FI_ATOMIC_FILE, /* indicate atomic file */ FI_DATA_EXIST, /* indicate data exists */ - FI_INLINE_DOTS, /* indicate inline dot dentries */ FI_SKIP_WRITES, /* should skip data page writeback */ FI_OPU_WRITE, /* used for opu per file */ FI_DIRTY_FILE, /* indicate regular/symlink has dirty pages */ @@ -3065,7 +3064,6 @@ static inline void __mark_inode_dirty_flag(struct inode *inode, return; fallthrough; case FI_DATA_EXIST: - case FI_INLINE_DOTS: case FI_PIN_FILE: case FI_COMPRESS_RELEASED: f2fs_mark_inode_dirty_sync(inode, true); @@ -3189,8 +3187,6 @@ static inline void get_inline_info(struct inode *inode, struct f2fs_inode *ri) set_bit(FI_INLINE_DENTRY, fi->flags); if (ri->i_inline & F2FS_DATA_EXIST) set_bit(FI_DATA_EXIST, fi->flags); - if (ri->i_inline & F2FS_INLINE_DOTS) - set_bit(FI_INLINE_DOTS, fi->flags); if (ri->i_inline & F2FS_EXTRA_ATTR) set_bit(FI_EXTRA_ATTR, fi->flags); if (ri->i_inline & F2FS_PIN_FILE) @@ -3211,8 +3207,6 @@ static inline void set_raw_inline(struct inode *inode, struct f2fs_inode *ri) ri->i_inline |= F2FS_INLINE_DENTRY; if (is_inode_flag_set(inode, FI_DATA_EXIST)) ri->i_inline |= F2FS_DATA_EXIST; - if (is_inode_flag_set(inode, FI_INLINE_DOTS)) - ri->i_inline |= F2FS_INLINE_DOTS; if (is_inode_flag_set(inode, FI_EXTRA_ATTR)) ri->i_inline |= F2FS_EXTRA_ATTR; if (is_inode_flag_set(inode, FI_PIN_FILE)) @@ -3293,11 +3287,6 @@ static inline int f2fs_exist_data(struct inode *inode) return is_inode_flag_set(inode, FI_DATA_EXIST); } -static inline int f2fs_has_inline_dots(struct inode *inode) -{ - return is_inode_flag_set(inode, FI_INLINE_DOTS); -} - static inline int f2fs_is_mmap_file(struct inode *inode) { return is_inode_flag_set(inode, FI_MMAP_FILE); diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 38b4750475db..57d46e1439de 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -457,62 +457,6 @@ struct dentry *f2fs_get_parent(struct dentry *child) return d_obtain_alias(f2fs_iget(child->d_sb, ino)); } -static int __recover_dot_dentries(struct inode *dir, nid_t pino) -{ - struct f2fs_sb_info *sbi = F2FS_I_SB(dir); - struct qstr dot = QSTR_INIT(".", 1); - struct f2fs_dir_entry *de; - struct page *page; - int err = 0; - - if (f2fs_readonly(sbi->sb)) { - f2fs_info(sbi, "skip recovering inline_dots inode (ino:%lu, pino:%u) in readonly mountpoint", - dir->i_ino, pino); - return 0; - } - - if (!S_ISDIR(dir->i_mode)) { - f2fs_err(sbi, "inconsistent inode status, skip recovering inline_dots inode (ino:%lu, i_mode:%u, pino:%u)", - dir->i_ino, dir->i_mode, pino); - set_sbi_flag(sbi, SBI_NEED_FSCK); - return -ENOTDIR; - } - - err = f2fs_dquot_initialize(dir); - if (err) - return err; - - f2fs_balance_fs(sbi, true); - - f2fs_lock_op(sbi); - - de = f2fs_find_entry(dir, &dot, &page); - if (de) { - f2fs_put_page(page, 0); - } else if (IS_ERR(page)) { - err = PTR_ERR(page); - goto out; - } else { - err = f2fs_do_add_link(dir, &dot, NULL, dir->i_ino, S_IFDIR); - if (err) - goto out; - } - - de = f2fs_find_entry(dir, &dotdot_name, &page); - if (de) - f2fs_put_page(page, 0); - else if (IS_ERR(page)) - err = PTR_ERR(page); - else - err = f2fs_do_add_link(dir, &dotdot_name, NULL, pino, S_IFDIR); -out: - if (!err) - clear_inode_flag(dir, FI_INLINE_DOTS); - - f2fs_unlock_op(sbi); - return err; -} - static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { @@ -522,7 +466,6 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry, struct dentry *new; nid_t ino = -1; int err = 0; - unsigned int root_ino = F2FS_ROOT_INO(F2FS_I_SB(dir)); struct f2fs_filename fname; trace_f2fs_lookup_start(dir, dentry, flags); @@ -558,17 +501,6 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry, goto out; } - if ((dir->i_ino == root_ino) && f2fs_has_inline_dots(dir)) { - err = __recover_dot_dentries(dir, root_ino); - if (err) - goto out_iput; - } - - if (f2fs_has_inline_dots(inode)) { - err = __recover_dot_dentries(inode, dir->i_ino); - if (err) - goto out_iput; - } if (IS_ENCRYPTED(dir) && (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) && !fscrypt_has_permitted_context(dir, inode)) { diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index f17f89a259e2..b0b821edfd97 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -278,7 +278,7 @@ struct node_footer { #define F2FS_INLINE_DATA 0x02 /* file inline data flag */ #define F2FS_INLINE_DENTRY 0x04 /* file inline dentry flag */ #define F2FS_DATA_EXIST 0x08 /* file inline data exist flag */ -#define F2FS_INLINE_DOTS 0x10 /* file having implicit dot dentries */ +#define F2FS_INLINE_DOTS 0x10 /* file having implicit dot dentries (obsolete) */ #define F2FS_EXTRA_ATTR 0x20 /* file having extra attribute */ #define F2FS_PIN_FILE 0x40 /* file should not be gced */ #define F2FS_COMPRESS_RELEASED 0x80 /* file released compressed blocks */ -- cgit v1.2.3 From 540c830212edc908361c39d40df21772a8bda308 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 9 Sep 2024 20:30:18 +0000 Subject: firmware: imx: remove duplicate scmi_imx_misc_ctrl_get() These two functions have a stub definition when CONFIG_IMX_SCMI_MISC_EXT is not set, which conflict with the global definition: In file included from drivers/firmware/imx/sm-misc.c:6: include/linux/firmware/imx/sm.h:30:1: error: expected identifier or '(' before '{' token 30 | { | ^ drivers/firmware/imx/sm-misc.c:26:5: error: redefinition of 'scmi_imx_misc_ctrl_get' 26 | int scmi_imx_misc_ctrl_get(u32 id, u32 *num, u32 *val) | ^~~~~~~~~~~~~~~~~~~~~~ include/linux/firmware/imx/sm.h:24:19: note: previous definition of 'scmi_imx_misc_ctrl_get' with type 'int(u32, u32 *, u32 *)' {aka 'int(unsigned int, unsigned int *, unsigned int *)'} 24 | static inline int scmi_imx_misc_ctrl_get(u32 id, u32 *num, u32 *val) | ^~~~~~~~~~~~~~~~~~~~~~ There is no real need for the #ifdef, and removing this avoids the build failure. Fixes: 0b4f8a68b292 ("firmware: imx: Add i.MX95 MISC driver") Link: https://lore.kernel.org/r/20240909203023.1275232-1-arnd@kernel.org Signed-off-by: Arnd Bergmann --- include/linux/firmware/imx/sm.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firmware/imx/sm.h b/include/linux/firmware/imx/sm.h index 62a2690e2abd..9b85a3f028d1 100644 --- a/include/linux/firmware/imx/sm.h +++ b/include/linux/firmware/imx/sm.h @@ -17,18 +17,7 @@ #define SCMI_IMX_CTRL_SAI4_MCLK 4 /* WAKE SAI4 MCLK */ #define SCMI_IMX_CTRL_SAI5_MCLK 5 /* WAKE SAI5 MCLK */ -#if IS_ENABLED(CONFIG_IMX_SCMI_MISC_EXT) int scmi_imx_misc_ctrl_get(u32 id, u32 *num, u32 *val); int scmi_imx_misc_ctrl_set(u32 id, u32 val); -#else -static inline int scmi_imx_misc_ctrl_get(u32 id, u32 *num, u32 *val) -{ - return -EOPNOTSUPP; -} -static inline int scmi_imx_misc_ctrl_set(u32 id, u32 val); -{ - return -EOPNOTSUPP; -} -#endif #endif -- cgit v1.2.3 From 4b3fc475c61fa8733a9acc9d743f6cc9ca4915f5 Mon Sep 17 00:00:00 2001 From: Russell King Date: Fri, 6 Sep 2024 16:05:07 +0530 Subject: net: phylink: Add phylink_set_fixed_link() to configure fixed link state in phylink The function allows for the configuration of a fixed link state for a given phylink instance. This addition is particularly useful for network devices that operate with a fixed link configuration, where the link parameters do not change dynamically. By using `phylink_set_fixed_link()`, drivers can easily set up the fixed link state during initialization or configuration changes. Reviewed-by: Andrew Lunn Signed-off-by: Russell King Signed-off-by: Raju Lakkaraju Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 42 ++++++++++++++++++++++++++++++++++++++++++ include/linux/phylink.h | 2 ++ 2 files changed, 44 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index ab4e9fc03017..4309317de3d1 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -1635,6 +1635,48 @@ static int phylink_register_sfp(struct phylink *pl, return ret; } +/** + * phylink_set_fixed_link() - set the fixed link + * @pl: a pointer to a &struct phylink returned from phylink_create() + * @state: a pointer to a struct phylink_link_state. + * + * This function is used when the link parameters are known and do not change, + * making it suitable for certain types of network connections. + * + * Returns: zero on success or negative error code. + */ +int phylink_set_fixed_link(struct phylink *pl, + const struct phylink_link_state *state) +{ + const struct phy_setting *s; + unsigned long *adv; + + if (pl->cfg_link_an_mode != MLO_AN_PHY || !state || + !test_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state)) + return -EINVAL; + + s = phy_lookup_setting(state->speed, state->duplex, + pl->supported, true); + if (!s) + return -EINVAL; + + adv = pl->link_config.advertising; + linkmode_zero(adv); + linkmode_set_bit(s->bit, adv); + linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, adv); + + pl->link_config.speed = state->speed; + pl->link_config.duplex = state->duplex; + pl->link_config.link = 1; + pl->link_config.an_complete = 1; + + pl->cfg_link_an_mode = MLO_AN_FIXED; + pl->cur_link_an_mode = pl->cfg_link_an_mode; + + return 0; +} +EXPORT_SYMBOL_GPL(phylink_set_fixed_link); + /** * phylink_create() - create a phylink instance * @config: a pointer to the target &struct phylink_config diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 2381e07429a2..5c01048860c4 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -598,6 +598,8 @@ int phylink_fwnode_phy_connect(struct phylink *pl, const struct fwnode_handle *fwnode, u32 flags); void phylink_disconnect_phy(struct phylink *); +int phylink_set_fixed_link(struct phylink *, + const struct phylink_link_state *); void phylink_mac_change(struct phylink *, bool up); void phylink_pcs_change(struct phylink_pcs *, bool up); -- cgit v1.2.3 From cef7dde8836ab09a3bfe96ada4f18ef2496eacc9 Mon Sep 17 00:00:00 2001 From: Michael Guralnik Date: Mon, 9 Sep 2024 13:04:57 +0300 Subject: net/mlx5: Expand mkey page size to support 6 bits Protect the usage of the 6th bit with the relevant capability to ensure we are using the new page sizes with FW that supports the bit extension. Signed-off-by: Michael Guralnik Link: https://patch.msgid.link/20240909100504.29797-2-michaelgur@nvidia.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/mlx5_ib.h | 27 ++++++++++++++++----------- drivers/infiniband/hw/mlx5/mr.c | 10 ++++------ drivers/infiniband/hw/mlx5/odp.c | 2 +- include/linux/mlx5/mlx5_ifc.h | 7 ++++--- 4 files changed, 25 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index 5505eb70939b..1c96f209cda6 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -63,17 +63,6 @@ __mlx5_log_page_size_to_bitmap(unsigned int log_pgsz_bits, return GENMASK(largest_pg_shift, pgsz_shift); } -/* - * For mkc users, instead of a page_offset the command has a start_iova which - * specifies both the page_offset and the on-the-wire IOVA - */ -#define mlx5_umem_find_best_pgsz(umem, typ, log_pgsz_fld, pgsz_shift, iova) \ - ib_umem_find_best_pgsz(umem, \ - __mlx5_log_page_size_to_bitmap( \ - __mlx5_bit_sz(typ, log_pgsz_fld), \ - pgsz_shift), \ - iova) - static __always_inline unsigned long __mlx5_page_offset_to_bitmask(unsigned int page_offset_bits, unsigned int offset_shift) @@ -1724,4 +1713,20 @@ static inline u32 smi_to_native_portnum(struct mlx5_ib_dev *dev, u32 port) return (port - 1) / dev->num_ports + 1; } +/* + * For mkc users, instead of a page_offset the command has a start_iova which + * specifies both the page_offset and the on-the-wire IOVA + */ +static __always_inline unsigned long +mlx5_umem_mkc_find_best_pgsz(struct mlx5_ib_dev *dev, struct ib_umem *umem, + u64 iova) +{ + int page_size_bits = + MLX5_CAP_GEN_2(dev->mdev, umr_log_entity_size_5) ? 6 : 5; + unsigned long bitmap = + __mlx5_log_page_size_to_bitmap(page_size_bits, 0); + + return ib_umem_find_best_pgsz(umem, bitmap, iova); +} + #endif /* MLX5_IB_H */ diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index d5b5cd73e20c..45d9dc9c6c8f 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -1120,8 +1120,7 @@ static struct mlx5_ib_mr *alloc_cacheable_mr(struct ib_pd *pd, if (umem->is_dmabuf) page_size = mlx5_umem_dmabuf_default_pgsz(umem, iova); else - page_size = mlx5_umem_find_best_pgsz(umem, mkc, log_page_size, - 0, iova); + page_size = mlx5_umem_mkc_find_best_pgsz(dev, umem, iova); if (WARN_ON(!page_size)) return ERR_PTR(-EINVAL); @@ -1426,8 +1425,8 @@ static struct ib_mr *create_real_mr(struct ib_pd *pd, struct ib_umem *umem, mr = alloc_cacheable_mr(pd, umem, iova, access_flags, MLX5_MKC_ACCESS_MODE_MTT); } else { - unsigned int page_size = mlx5_umem_find_best_pgsz( - umem, mkc, log_page_size, 0, iova); + unsigned int page_size = + mlx5_umem_mkc_find_best_pgsz(dev, umem, iova); mutex_lock(&dev->slow_path_mutex); mr = reg_create(pd, umem, iova, access_flags, page_size, @@ -1745,8 +1744,7 @@ static bool can_use_umr_rereg_pas(struct mlx5_ib_mr *mr, if (!mlx5r_umr_can_load_pas(dev, new_umem->length)) return false; - *page_size = - mlx5_umem_find_best_pgsz(new_umem, mkc, log_page_size, 0, iova); + *page_size = mlx5_umem_mkc_find_best_pgsz(dev, new_umem, iova); if (WARN_ON(!*page_size)) return false; return (mr->mmkey.cache_ent->rb_key.ndescs) >= diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index 44a3428ea342..221820874e7a 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -693,7 +693,7 @@ static int pagefault_dmabuf_mr(struct mlx5_ib_mr *mr, size_t bcnt, struct ib_umem_dmabuf *umem_dmabuf = to_ib_umem_dmabuf(mr->umem); u32 xlt_flags = 0; int err; - unsigned int page_size; + unsigned long page_size; if (flags & MLX5_PF_FLAGS_ENABLE) xlt_flags |= MLX5_IB_UPD_XLT_ENABLE; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 970c9d8473ef..ec1117d4e441 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1988,7 +1988,9 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 migratable[0x1]; u8 reserved_at_81[0x11]; u8 query_vuid[0x1]; - u8 reserved_at_93[0xd]; + u8 reserved_at_93[0x5]; + u8 umr_log_entity_size_5[0x1]; + u8 reserved_at_99[0x7]; u8 max_reformat_insert_size[0x8]; u8 max_reformat_insert_offset[0x8]; @@ -4212,8 +4214,7 @@ struct mlx5_ifc_mkc_bits { u8 reserved_at_1c0[0x19]; u8 relaxed_ordering_read[0x1]; - u8 reserved_at_1d9[0x1]; - u8 log_page_size[0x5]; + u8 log_page_size[0x6]; u8 reserved_at_1e0[0x20]; }; -- cgit v1.2.3 From 6cd9171d04cff79abe78c166927ab8563bf95fe5 Mon Sep 17 00:00:00 2001 From: Michael Guralnik Date: Mon, 9 Sep 2024 13:04:58 +0300 Subject: net/mlx5: Expose HW bits for Memory scheme ODP Expose IFC bits to support the new memory scheme on demand paging. Change the macro reading odp capabilities to be able to read from the new IFC layout and align the code in upper layers to be compiled. Signed-off-by: Michael Guralnik Link: https://patch.msgid.link/20240909100504.29797-3-michaelgur@nvidia.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/odp.c | 40 ++++++++++-------- drivers/net/ethernet/mellanox/mlx5/core/main.c | 28 ++++++------- include/linux/mlx5/device.h | 4 ++ include/linux/mlx5/mlx5_ifc.h | 57 +++++++++++++++++++++----- 4 files changed, 86 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index 221820874e7a..300504bf79d7 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -332,46 +332,46 @@ static void internal_fill_odp_caps(struct mlx5_ib_dev *dev) else dev->odp_max_size = BIT_ULL(MLX5_MAX_UMR_SHIFT + PAGE_SHIFT); - if (MLX5_CAP_ODP(dev->mdev, ud_odp_caps.send)) + if (MLX5_CAP_ODP_SCHEME(dev->mdev, ud_odp_caps.send)) caps->per_transport_caps.ud_odp_caps |= IB_ODP_SUPPORT_SEND; - if (MLX5_CAP_ODP(dev->mdev, ud_odp_caps.srq_receive)) + if (MLX5_CAP_ODP_SCHEME(dev->mdev, ud_odp_caps.srq_receive)) caps->per_transport_caps.ud_odp_caps |= IB_ODP_SUPPORT_SRQ_RECV; - if (MLX5_CAP_ODP(dev->mdev, rc_odp_caps.send)) + if (MLX5_CAP_ODP_SCHEME(dev->mdev, rc_odp_caps.send)) caps->per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_SEND; - if (MLX5_CAP_ODP(dev->mdev, rc_odp_caps.receive)) + if (MLX5_CAP_ODP_SCHEME(dev->mdev, rc_odp_caps.receive)) caps->per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_RECV; - if (MLX5_CAP_ODP(dev->mdev, rc_odp_caps.write)) + if (MLX5_CAP_ODP_SCHEME(dev->mdev, rc_odp_caps.write)) caps->per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_WRITE; - if (MLX5_CAP_ODP(dev->mdev, rc_odp_caps.read)) + if (MLX5_CAP_ODP_SCHEME(dev->mdev, rc_odp_caps.read)) caps->per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_READ; - if (MLX5_CAP_ODP(dev->mdev, rc_odp_caps.atomic)) + if (MLX5_CAP_ODP_SCHEME(dev->mdev, rc_odp_caps.atomic)) caps->per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_ATOMIC; - if (MLX5_CAP_ODP(dev->mdev, rc_odp_caps.srq_receive)) + if (MLX5_CAP_ODP_SCHEME(dev->mdev, rc_odp_caps.srq_receive)) caps->per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_SRQ_RECV; - if (MLX5_CAP_ODP(dev->mdev, xrc_odp_caps.send)) + if (MLX5_CAP_ODP_SCHEME(dev->mdev, xrc_odp_caps.send)) caps->per_transport_caps.xrc_odp_caps |= IB_ODP_SUPPORT_SEND; - if (MLX5_CAP_ODP(dev->mdev, xrc_odp_caps.receive)) + if (MLX5_CAP_ODP_SCHEME(dev->mdev, xrc_odp_caps.receive)) caps->per_transport_caps.xrc_odp_caps |= IB_ODP_SUPPORT_RECV; - if (MLX5_CAP_ODP(dev->mdev, xrc_odp_caps.write)) + if (MLX5_CAP_ODP_SCHEME(dev->mdev, xrc_odp_caps.write)) caps->per_transport_caps.xrc_odp_caps |= IB_ODP_SUPPORT_WRITE; - if (MLX5_CAP_ODP(dev->mdev, xrc_odp_caps.read)) + if (MLX5_CAP_ODP_SCHEME(dev->mdev, xrc_odp_caps.read)) caps->per_transport_caps.xrc_odp_caps |= IB_ODP_SUPPORT_READ; - if (MLX5_CAP_ODP(dev->mdev, xrc_odp_caps.atomic)) + if (MLX5_CAP_ODP_SCHEME(dev->mdev, xrc_odp_caps.atomic)) caps->per_transport_caps.xrc_odp_caps |= IB_ODP_SUPPORT_ATOMIC; - if (MLX5_CAP_ODP(dev->mdev, xrc_odp_caps.srq_receive)) + if (MLX5_CAP_ODP_SCHEME(dev->mdev, xrc_odp_caps.srq_receive)) caps->per_transport_caps.xrc_odp_caps |= IB_ODP_SUPPORT_SRQ_RECV; if (MLX5_CAP_GEN(dev->mdev, fixed_buffer_size) && @@ -388,13 +388,17 @@ static void mlx5_ib_page_fault_resume(struct mlx5_ib_dev *dev, int wq_num = pfault->event_subtype == MLX5_PFAULT_SUBTYPE_WQE ? pfault->wqe.wq_num : pfault->token; u32 in[MLX5_ST_SZ_DW(page_fault_resume_in)] = {}; + void *info; int err; MLX5_SET(page_fault_resume_in, in, opcode, MLX5_CMD_OP_PAGE_FAULT_RESUME); - MLX5_SET(page_fault_resume_in, in, page_fault_type, pfault->type); - MLX5_SET(page_fault_resume_in, in, token, pfault->token); - MLX5_SET(page_fault_resume_in, in, wq_number, wq_num); - MLX5_SET(page_fault_resume_in, in, error, !!error); + + info = MLX5_ADDR_OF(page_fault_resume_in, in, + page_fault_info.trans_page_fault_info); + MLX5_SET(trans_page_fault_info, info, page_fault_type, pfault->type); + MLX5_SET(trans_page_fault_info, info, fault_token, pfault->token); + MLX5_SET(trans_page_fault_info, info, wq_number, wq_num); + MLX5_SET(trans_page_fault_info, info, error, !!error); err = mlx5_cmd_exec_in(dev->mdev, page_fault_resume, in); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 5b7e6f4b5c7e..cc2aa46cff04 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -479,20 +479,20 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev, void *set_ctx) } \ } while (0) - ODP_CAP_SET_MAX(dev, ud_odp_caps.srq_receive); - ODP_CAP_SET_MAX(dev, rc_odp_caps.srq_receive); - ODP_CAP_SET_MAX(dev, xrc_odp_caps.srq_receive); - ODP_CAP_SET_MAX(dev, xrc_odp_caps.send); - ODP_CAP_SET_MAX(dev, xrc_odp_caps.receive); - ODP_CAP_SET_MAX(dev, xrc_odp_caps.write); - ODP_CAP_SET_MAX(dev, xrc_odp_caps.read); - ODP_CAP_SET_MAX(dev, xrc_odp_caps.atomic); - ODP_CAP_SET_MAX(dev, dc_odp_caps.srq_receive); - ODP_CAP_SET_MAX(dev, dc_odp_caps.send); - ODP_CAP_SET_MAX(dev, dc_odp_caps.receive); - ODP_CAP_SET_MAX(dev, dc_odp_caps.write); - ODP_CAP_SET_MAX(dev, dc_odp_caps.read); - ODP_CAP_SET_MAX(dev, dc_odp_caps.atomic); + ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.ud_odp_caps.srq_receive); + ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.rc_odp_caps.srq_receive); + ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.xrc_odp_caps.srq_receive); + ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.xrc_odp_caps.send); + ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.xrc_odp_caps.receive); + ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.xrc_odp_caps.write); + ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.xrc_odp_caps.read); + ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.xrc_odp_caps.atomic); + ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.dc_odp_caps.srq_receive); + ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.dc_odp_caps.send); + ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.dc_odp_caps.receive); + ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.dc_odp_caps.write); + ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.dc_odp_caps.read); + ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.dc_odp_caps.atomic); if (!do_set) return 0; diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index ba875a619b97..bd081f276654 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1369,6 +1369,10 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_ODP(mdev, cap)\ MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, cap) +#define MLX5_CAP_ODP_SCHEME(mdev, cap) \ + MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, \ + transport_page_fault_scheme_cap.cap) + #define MLX5_CAP_ODP_MAX(mdev, cap)\ MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->max, cap) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index ec1117d4e441..3e3336bb9191 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1326,11 +1326,13 @@ struct mlx5_ifc_atomic_caps_bits { u8 reserved_at_e0[0x720]; }; -struct mlx5_ifc_odp_cap_bits { +struct mlx5_ifc_odp_scheme_cap_bits { u8 reserved_at_0[0x40]; u8 sig[0x1]; - u8 reserved_at_41[0x1f]; + u8 reserved_at_41[0x4]; + u8 page_prefetch[0x1]; + u8 reserved_at_46[0x1a]; u8 reserved_at_60[0x20]; @@ -1344,7 +1346,20 @@ struct mlx5_ifc_odp_cap_bits { struct mlx5_ifc_odp_per_transport_service_cap_bits dc_odp_caps; - u8 reserved_at_120[0x6E0]; + u8 reserved_at_120[0xe0]; +}; + +struct mlx5_ifc_odp_cap_bits { + struct mlx5_ifc_odp_scheme_cap_bits transport_page_fault_scheme_cap; + + struct mlx5_ifc_odp_scheme_cap_bits memory_page_fault_scheme_cap; + + u8 reserved_at_400[0x200]; + + u8 mem_page_fault[0x1]; + u8 reserved_at_601[0x1f]; + + u8 reserved_at_620[0x1e0]; }; struct mlx5_ifc_tls_cap_bits { @@ -2034,7 +2049,8 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 min_mkey_log_entity_size_fixed_buffer[0x5]; u8 ec_vf_vport_base[0x10]; - u8 reserved_at_3a0[0x10]; + u8 reserved_at_3a0[0xa]; + u8 max_mkey_log_entity_size_mtt[0x6]; u8 max_rqt_vhca_id[0x10]; u8 reserved_at_3c0[0x20]; @@ -7258,6 +7274,30 @@ struct mlx5_ifc_qp_2err_in_bits { u8 reserved_at_60[0x20]; }; +struct mlx5_ifc_trans_page_fault_info_bits { + u8 error[0x1]; + u8 reserved_at_1[0x4]; + u8 page_fault_type[0x3]; + u8 wq_number[0x18]; + + u8 reserved_at_20[0x8]; + u8 fault_token[0x18]; +}; + +struct mlx5_ifc_mem_page_fault_info_bits { + u8 error[0x1]; + u8 reserved_at_1[0xf]; + u8 fault_token_47_32[0x10]; + + u8 fault_token_31_0[0x20]; +}; + +union mlx5_ifc_page_fault_resume_in_page_fault_info_auto_bits { + struct mlx5_ifc_trans_page_fault_info_bits trans_page_fault_info; + struct mlx5_ifc_mem_page_fault_info_bits mem_page_fault_info; + u8 reserved_at_0[0x40]; +}; + struct mlx5_ifc_page_fault_resume_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -7274,13 +7314,8 @@ struct mlx5_ifc_page_fault_resume_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 error[0x1]; - u8 reserved_at_41[0x4]; - u8 page_fault_type[0x3]; - u8 wq_number[0x18]; - - u8 reserved_at_60[0x8]; - u8 token[0x18]; + union mlx5_ifc_page_fault_resume_in_page_fault_info_auto_bits + page_fault_info; }; struct mlx5_ifc_nop_out_bits { -- cgit v1.2.3 From 64c68385a39bb676c76da36164ab696e8da78842 Mon Sep 17 00:00:00 2001 From: Michael Guralnik Date: Mon, 9 Sep 2024 13:04:59 +0300 Subject: RDMA/mlx5: Add new ODP memory scheme eqe format Add new fields to support the new memory scheme page fault and extend the token field to u64 as in the new scheme the token is 48 bit. Signed-off-by: Michael Guralnik Link: https://patch.msgid.link/20240909100504.29797-4-michaelgur@nvidia.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/odp.c | 48 ++++++++++++++++++++++++---------------- include/linux/mlx5/device.h | 22 +++++++++++++++++- 2 files changed, 50 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index 300504bf79d7..f01026d507a3 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -45,7 +45,7 @@ /* Contains the details of a pagefault. */ struct mlx5_pagefault { u32 bytes_committed; - u32 token; + u64 token; u8 event_subtype; u8 type; union { @@ -74,6 +74,14 @@ struct mlx5_pagefault { u32 rdma_op_len; u64 rdma_va; } rdma; + struct { + u64 va; + u32 mkey; + u32 fault_byte_count; + u32 prefetch_before_byte_count; + u32 prefetch_after_byte_count; + u8 flags; + } memory; }; struct mlx5_ib_pf_eq *eq; @@ -1273,7 +1281,7 @@ read_user: if (ret) mlx5_ib_err( dev, - "Failed reading a WQE following page fault, error %d, wqe_index %x, qpn %x\n", + "Failed reading a WQE following page fault, error %d, wqe_index %x, qpn %llx\n", ret, wqe_index, pfault->token); resolve_page_fault: @@ -1332,13 +1340,13 @@ static void mlx5_ib_mr_rdma_pfault_handler(struct mlx5_ib_dev *dev, } else if (ret < 0 || pages_in_range(address, length) > ret) { mlx5_ib_page_fault_resume(dev, pfault, 1); if (ret != -ENOENT) - mlx5_ib_dbg(dev, "PAGE FAULT error %d. QP 0x%x, type: 0x%x\n", + mlx5_ib_dbg(dev, "PAGE FAULT error %d. QP 0x%llx, type: 0x%x\n", ret, pfault->token, pfault->type); return; } mlx5_ib_page_fault_resume(dev, pfault, 0); - mlx5_ib_dbg(dev, "PAGE FAULT completed. QP 0x%x, type: 0x%x, prefetch_activated: %d\n", + mlx5_ib_dbg(dev, "PAGE FAULT completed. QP 0x%llx, type: 0x%x, prefetch_activated: %d\n", pfault->token, pfault->type, prefetch_activated); @@ -1354,7 +1362,7 @@ static void mlx5_ib_mr_rdma_pfault_handler(struct mlx5_ib_dev *dev, prefetch_len, &bytes_committed, NULL); if (ret < 0 && ret != -EAGAIN) { - mlx5_ib_dbg(dev, "Prefetch failed. ret: %d, QP 0x%x, address: 0x%.16llx, length = 0x%.16x\n", + mlx5_ib_dbg(dev, "Prefetch failed. ret: %d, QP 0x%llx, address: 0x%.16llx, length = 0x%.16x\n", ret, pfault->token, address, prefetch_len); } } @@ -1405,15 +1413,12 @@ static void mlx5_ib_eq_pf_process(struct mlx5_ib_pf_eq *eq) pf_eqe = &eqe->data.page_fault; pfault->event_subtype = eqe->sub_type; - pfault->bytes_committed = be32_to_cpu(pf_eqe->bytes_committed); - - mlx5_ib_dbg(eq->dev, - "PAGE_FAULT: subtype: 0x%02x, bytes_committed: 0x%06x\n", - eqe->sub_type, pfault->bytes_committed); switch (eqe->sub_type) { case MLX5_PFAULT_SUBTYPE_RDMA: /* RDMA based event */ + pfault->bytes_committed = + be32_to_cpu(pf_eqe->rdma.bytes_committed); pfault->type = be32_to_cpu(pf_eqe->rdma.pftype_token) >> 24; pfault->token = @@ -1427,10 +1432,12 @@ static void mlx5_ib_eq_pf_process(struct mlx5_ib_pf_eq *eq) be32_to_cpu(pf_eqe->rdma.rdma_op_len); pfault->rdma.rdma_va = be64_to_cpu(pf_eqe->rdma.rdma_va); - mlx5_ib_dbg(eq->dev, - "PAGE_FAULT: type:0x%x, token: 0x%06x, r_key: 0x%08x\n", - pfault->type, pfault->token, - pfault->rdma.r_key); + mlx5_ib_dbg( + eq->dev, + "PAGE_FAULT: subtype: 0x%02x, bytes_committed: 0x%06x, type:0x%x, token: 0x%06llx, r_key: 0x%08x\n", + eqe->sub_type, pfault->bytes_committed, + pfault->type, pfault->token, + pfault->rdma.r_key); mlx5_ib_dbg(eq->dev, "PAGE_FAULT: rdma_op_len: 0x%08x, rdma_va: 0x%016llx\n", pfault->rdma.rdma_op_len, @@ -1439,6 +1446,8 @@ static void mlx5_ib_eq_pf_process(struct mlx5_ib_pf_eq *eq) case MLX5_PFAULT_SUBTYPE_WQE: /* WQE based event */ + pfault->bytes_committed = + be32_to_cpu(pf_eqe->wqe.bytes_committed); pfault->type = (be32_to_cpu(pf_eqe->wqe.pftype_wq) >> 24) & 0x7; pfault->token = @@ -1450,11 +1459,12 @@ static void mlx5_ib_eq_pf_process(struct mlx5_ib_pf_eq *eq) be16_to_cpu(pf_eqe->wqe.wqe_index); pfault->wqe.packet_size = be16_to_cpu(pf_eqe->wqe.packet_length); - mlx5_ib_dbg(eq->dev, - "PAGE_FAULT: type:0x%x, token: 0x%06x, wq_num: 0x%06x, wqe_index: 0x%04x\n", - pfault->type, pfault->token, - pfault->wqe.wq_num, - pfault->wqe.wqe_index); + mlx5_ib_dbg( + eq->dev, + "PAGE_FAULT: subtype: 0x%02x, bytes_committed: 0x%06x, type:0x%x, token: 0x%06llx, wq_num: 0x%06x, wqe_index: 0x%04x\n", + eqe->sub_type, pfault->bytes_committed, + pfault->type, pfault->token, pfault->wqe.wq_num, + pfault->wqe.wqe_index); break; default: diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index bd081f276654..154095256d0d 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -211,6 +211,7 @@ enum { enum { MLX5_PFAULT_SUBTYPE_WQE = 0, MLX5_PFAULT_SUBTYPE_RDMA = 1, + MLX5_PFAULT_SUBTYPE_MEMORY = 2, }; enum wqe_page_fault_type { @@ -646,10 +647,11 @@ struct mlx5_eqe_page_req { __be32 rsvd1[5]; }; +#define MEMORY_SCHEME_PAGE_FAULT_GRANULARITY 4096 struct mlx5_eqe_page_fault { - __be32 bytes_committed; union { struct { + __be32 bytes_committed; u16 reserved1; __be16 wqe_index; u16 reserved2; @@ -659,6 +661,7 @@ struct mlx5_eqe_page_fault { __be32 pftype_wq; } __packed wqe; struct { + __be32 bytes_committed; __be32 r_key; u16 reserved1; __be16 packet_length; @@ -666,6 +669,23 @@ struct mlx5_eqe_page_fault { __be64 rdma_va; __be32 pftype_token; } __packed rdma; + struct { + u8 flags; + u8 reserved1; + __be16 post_demand_fault_pages; + __be16 pre_demand_fault_pages; + __be16 token47_32; + __be32 token31_0; + /* + * FW changed from specifying the fault size in byte + * count to 4k pages granularity. The size specified + * in pages uses bits 31:12, to keep backward + * compatibility. + */ + __be32 demand_fault_pages; + __be32 mkey; + __be64 va; + } __packed memory; } __packed; } __packed; -- cgit v1.2.3 From c912ac66b3fc92acb0079fff7d030e9be0756c36 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 9 Sep 2024 15:41:05 +0300 Subject: platform/x86: intel_scu_ipc: Move intel_scu_ipc.h out of arch/x86/include/asm This is a platform/x86 library that is mostly being used by other drivers not directly under arch/x86 anyway (with the exception of the Intel MID setup code) so it makes sense that it lives under the platform_data/x86/ directory instead. No functional changes intended. Suggested-by: Andy Shevchenko Signed-off-by: Mika Westerberg Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20240909124952.1152017-3-andriy.shevchenko@linux.intel.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede --- MAINTAINERS | 4 +- arch/x86/include/asm/intel_scu_ipc.h | 68 ------------------------- arch/x86/include/asm/intel_telemetry.h | 2 +- arch/x86/platform/intel-mid/intel-mid.c | 3 +- drivers/mfd/intel_pmc_bxt.c | 3 +- drivers/mfd/intel_soc_pmic_bxtwc.c | 3 +- drivers/mfd/intel_soc_pmic_mrfld.c | 3 +- drivers/platform/x86/intel_scu_ipc.c | 2 +- drivers/platform/x86/intel_scu_ipcutil.c | 2 +- drivers/platform/x86/intel_scu_pcidrv.c | 2 +- drivers/platform/x86/intel_scu_pltdrv.c | 2 +- drivers/usb/typec/mux/intel_pmc_mux.c | 3 +- drivers/watchdog/intel-mid_wdt.c | 3 +- include/linux/platform_data/x86/intel_scu_ipc.h | 68 +++++++++++++++++++++++++ 14 files changed, 82 insertions(+), 86 deletions(-) delete mode 100644 arch/x86/include/asm/intel_scu_ipc.h create mode 100644 include/linux/platform_data/x86/intel_scu_ipc.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 2ba2877c095d..3f3a8d8abf87 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11471,7 +11471,6 @@ M: Andy Shevchenko L: linux-kernel@vger.kernel.org S: Supported F: arch/x86/include/asm/intel-mid.h -F: arch/x86/include/asm/intel_scu_ipc.h F: arch/x86/pci/intel_mid_pci.c F: arch/x86/platform/intel-mid/ F: drivers/extcon/extcon-intel-mrfld.c @@ -11483,6 +11482,7 @@ F: drivers/staging/media/atomisp/ F: drivers/watchdog/intel-mid_wdt.c F: include/linux/mfd/intel_soc_pmic_mrfld.h F: include/linux/platform_data/intel-mid_wdt.h +F: include/linux/platform_data/x86/intel_scu_ipc.h INTEL P-Unit IPC DRIVER M: Zha Qipeng @@ -11546,8 +11546,8 @@ F: drivers/counter/intel-qep.c INTEL SCU DRIVERS M: Mika Westerberg S: Maintained -F: arch/x86/include/asm/intel_scu_ipc.h F: drivers/platform/x86/intel_scu_* +F: include/linux/platform_data/x86/intel_scu_ipc.h INTEL SDSI DRIVER M: David E. Box diff --git a/arch/x86/include/asm/intel_scu_ipc.h b/arch/x86/include/asm/intel_scu_ipc.h deleted file mode 100644 index 8537f597d20a..000000000000 --- a/arch/x86/include/asm/intel_scu_ipc.h +++ /dev/null @@ -1,68 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_X86_INTEL_SCU_IPC_H_ -#define _ASM_X86_INTEL_SCU_IPC_H_ - -#include - -struct device; -struct intel_scu_ipc_dev; - -/** - * struct intel_scu_ipc_data - Data used to configure SCU IPC - * @mem: Base address of SCU IPC MMIO registers - * @irq: The IRQ number used for SCU (optional) - */ -struct intel_scu_ipc_data { - struct resource mem; - int irq; -}; - -struct intel_scu_ipc_dev * -__intel_scu_ipc_register(struct device *parent, - const struct intel_scu_ipc_data *scu_data, - struct module *owner); - -#define intel_scu_ipc_register(parent, scu_data) \ - __intel_scu_ipc_register(parent, scu_data, THIS_MODULE) - -void intel_scu_ipc_unregister(struct intel_scu_ipc_dev *scu); - -struct intel_scu_ipc_dev * -__devm_intel_scu_ipc_register(struct device *parent, - const struct intel_scu_ipc_data *scu_data, - struct module *owner); - -#define devm_intel_scu_ipc_register(parent, scu_data) \ - __devm_intel_scu_ipc_register(parent, scu_data, THIS_MODULE) - -struct intel_scu_ipc_dev *intel_scu_ipc_dev_get(void); -void intel_scu_ipc_dev_put(struct intel_scu_ipc_dev *scu); -struct intel_scu_ipc_dev *devm_intel_scu_ipc_dev_get(struct device *dev); - -int intel_scu_ipc_dev_ioread8(struct intel_scu_ipc_dev *scu, u16 addr, - u8 *data); -int intel_scu_ipc_dev_iowrite8(struct intel_scu_ipc_dev *scu, u16 addr, - u8 data); -int intel_scu_ipc_dev_readv(struct intel_scu_ipc_dev *scu, u16 *addr, - u8 *data, size_t len); -int intel_scu_ipc_dev_writev(struct intel_scu_ipc_dev *scu, u16 *addr, - u8 *data, size_t len); - -int intel_scu_ipc_dev_update(struct intel_scu_ipc_dev *scu, u16 addr, - u8 data, u8 mask); - -int intel_scu_ipc_dev_simple_command(struct intel_scu_ipc_dev *scu, int cmd, - int sub); -int intel_scu_ipc_dev_command_with_size(struct intel_scu_ipc_dev *scu, int cmd, - int sub, const void *in, size_t inlen, - size_t size, void *out, size_t outlen); - -static inline int intel_scu_ipc_dev_command(struct intel_scu_ipc_dev *scu, int cmd, - int sub, const void *in, size_t inlen, - void *out, size_t outlen) -{ - return intel_scu_ipc_dev_command_with_size(scu, cmd, sub, in, inlen, - inlen, out, outlen); -} - -#endif diff --git a/arch/x86/include/asm/intel_telemetry.h b/arch/x86/include/asm/intel_telemetry.h index 8046e70dfd7c..43b7657febca 100644 --- a/arch/x86/include/asm/intel_telemetry.h +++ b/arch/x86/include/asm/intel_telemetry.h @@ -10,7 +10,7 @@ #define TELEM_MAX_EVENTS_SRAM 28 #define TELEM_MAX_OS_ALLOCATED_EVENTS 20 -#include +#include enum telemetry_unit { TELEM_PSS = 0, diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c index f83bbe0acd4a..a8e75f8c14fd 100644 --- a/arch/x86/platform/intel-mid/intel-mid.c +++ b/arch/x86/platform/intel-mid/intel-mid.c @@ -27,9 +27,10 @@ #include #include #include -#include #include +#include + #define IPCMSG_COLD_OFF 0x80 /* Only for Tangier */ #define IPCMSG_COLD_RESET 0xF1 diff --git a/drivers/mfd/intel_pmc_bxt.c b/drivers/mfd/intel_pmc_bxt.c index 9f01d38acc7f..e405d7513ca1 100644 --- a/drivers/mfd/intel_pmc_bxt.c +++ b/drivers/mfd/intel_pmc_bxt.c @@ -23,8 +23,7 @@ #include #include #include - -#include +#include /* Residency with clock rate at 19.2MHz to usecs */ #define S0IX_RESIDENCY_IN_USECS(d, s) \ diff --git a/drivers/mfd/intel_soc_pmic_bxtwc.c b/drivers/mfd/intel_soc_pmic_bxtwc.c index ba32cacfc499..ab3c94224dd1 100644 --- a/drivers/mfd/intel_soc_pmic_bxtwc.c +++ b/drivers/mfd/intel_soc_pmic_bxtwc.c @@ -15,8 +15,7 @@ #include #include #include - -#include +#include /* PMIC device registers */ #define REG_ADDR_MASK GENMASK(15, 8) diff --git a/drivers/mfd/intel_soc_pmic_mrfld.c b/drivers/mfd/intel_soc_pmic_mrfld.c index 71da861e8c27..77121775c1a3 100644 --- a/drivers/mfd/intel_soc_pmic_mrfld.c +++ b/drivers/mfd/intel_soc_pmic_mrfld.c @@ -12,11 +12,10 @@ #include #include #include +#include #include #include -#include - /* * Level 2 IRQs * diff --git a/drivers/platform/x86/intel_scu_ipc.c b/drivers/platform/x86/intel_scu_ipc.c index a68df4133403..5b16d29c93d7 100644 --- a/drivers/platform/x86/intel_scu_ipc.c +++ b/drivers/platform/x86/intel_scu_ipc.c @@ -23,7 +23,7 @@ #include #include -#include +#include /* IPC defines the following message types */ #define IPCMSG_PCNTRL 0xff /* Power controller unit read/write */ diff --git a/drivers/platform/x86/intel_scu_ipcutil.c b/drivers/platform/x86/intel_scu_ipcutil.c index 7d87cbd4b9c6..69b36ce41fa2 100644 --- a/drivers/platform/x86/intel_scu_ipcutil.c +++ b/drivers/platform/x86/intel_scu_ipcutil.c @@ -18,7 +18,7 @@ #include #include -#include +#include static int major; diff --git a/drivers/platform/x86/intel_scu_pcidrv.c b/drivers/platform/x86/intel_scu_pcidrv.c index dbf0310448da..d7f72d6deb44 100644 --- a/drivers/platform/x86/intel_scu_pcidrv.c +++ b/drivers/platform/x86/intel_scu_pcidrv.c @@ -11,7 +11,7 @@ #include #include -#include +#include static int intel_scu_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) diff --git a/drivers/platform/x86/intel_scu_pltdrv.c b/drivers/platform/x86/intel_scu_pltdrv.c index 56ec6ae4c824..0892362acd7b 100644 --- a/drivers/platform/x86/intel_scu_pltdrv.c +++ b/drivers/platform/x86/intel_scu_pltdrv.c @@ -15,7 +15,7 @@ #include #include -#include +#include static int intel_scu_platform_probe(struct platform_device *pdev) { diff --git a/drivers/usb/typec/mux/intel_pmc_mux.c b/drivers/usb/typec/mux/intel_pmc_mux.c index 56989a0d0f43..46b4c5c3a6be 100644 --- a/drivers/usb/typec/mux/intel_pmc_mux.c +++ b/drivers/usb/typec/mux/intel_pmc_mux.c @@ -8,6 +8,7 @@ #include #include +#include #include #include #include @@ -18,8 +19,6 @@ #include #include -#include - #define PMC_USBC_CMD 0xa7 /* Response status bits */ diff --git a/drivers/watchdog/intel-mid_wdt.c b/drivers/watchdog/intel-mid_wdt.c index 8d71f6a2236b..91c9c3950e44 100644 --- a/drivers/watchdog/intel-mid_wdt.c +++ b/drivers/watchdog/intel-mid_wdt.c @@ -21,8 +21,7 @@ #include #include - -#include +#include #define IPC_WATCHDOG 0xf8 diff --git a/include/linux/platform_data/x86/intel_scu_ipc.h b/include/linux/platform_data/x86/intel_scu_ipc.h new file mode 100644 index 000000000000..0ca9962e97f2 --- /dev/null +++ b/include/linux/platform_data/x86/intel_scu_ipc.h @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PLATFORM_X86_INTEL_SCU_IPC_H_ +#define __PLATFORM_X86_INTEL_SCU_IPC_H_ + +#include + +struct device; +struct intel_scu_ipc_dev; + +/** + * struct intel_scu_ipc_data - Data used to configure SCU IPC + * @mem: Base address of SCU IPC MMIO registers + * @irq: The IRQ number used for SCU (optional) + */ +struct intel_scu_ipc_data { + struct resource mem; + int irq; +}; + +struct intel_scu_ipc_dev * +__intel_scu_ipc_register(struct device *parent, + const struct intel_scu_ipc_data *scu_data, + struct module *owner); + +#define intel_scu_ipc_register(parent, scu_data) \ + __intel_scu_ipc_register(parent, scu_data, THIS_MODULE) + +void intel_scu_ipc_unregister(struct intel_scu_ipc_dev *scu); + +struct intel_scu_ipc_dev * +__devm_intel_scu_ipc_register(struct device *parent, + const struct intel_scu_ipc_data *scu_data, + struct module *owner); + +#define devm_intel_scu_ipc_register(parent, scu_data) \ + __devm_intel_scu_ipc_register(parent, scu_data, THIS_MODULE) + +struct intel_scu_ipc_dev *intel_scu_ipc_dev_get(void); +void intel_scu_ipc_dev_put(struct intel_scu_ipc_dev *scu); +struct intel_scu_ipc_dev *devm_intel_scu_ipc_dev_get(struct device *dev); + +int intel_scu_ipc_dev_ioread8(struct intel_scu_ipc_dev *scu, u16 addr, + u8 *data); +int intel_scu_ipc_dev_iowrite8(struct intel_scu_ipc_dev *scu, u16 addr, + u8 data); +int intel_scu_ipc_dev_readv(struct intel_scu_ipc_dev *scu, u16 *addr, + u8 *data, size_t len); +int intel_scu_ipc_dev_writev(struct intel_scu_ipc_dev *scu, u16 *addr, + u8 *data, size_t len); + +int intel_scu_ipc_dev_update(struct intel_scu_ipc_dev *scu, u16 addr, + u8 data, u8 mask); + +int intel_scu_ipc_dev_simple_command(struct intel_scu_ipc_dev *scu, int cmd, + int sub); +int intel_scu_ipc_dev_command_with_size(struct intel_scu_ipc_dev *scu, int cmd, + int sub, const void *in, size_t inlen, + size_t size, void *out, size_t outlen); + +static inline int intel_scu_ipc_dev_command(struct intel_scu_ipc_dev *scu, int cmd, + int sub, const void *in, size_t inlen, + void *out, size_t outlen) +{ + return intel_scu_ipc_dev_command_with_size(scu, cmd, sub, in, inlen, + inlen, out, outlen); +} + +#endif -- cgit v1.2.3 From 5f1cda51107fd5e53cd012bd1f6f39aede96bdbe Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 9 Sep 2024 15:41:06 +0300 Subject: platform/x86: intel_scu_wdt: Move intel_scu_wdt.h to x86 subfolder This is a platform/x86 library that can only be used on x86 devices. so it makes sense that it lives under the platform_data/x86/ directory instead. No functional changes intended. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20240909124952.1152017-4-andriy.shevchenko@linux.intel.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede --- drivers/platform/x86/intel_scu_wdt.c | 3 ++- drivers/watchdog/intel-mid_wdt.c | 2 +- include/linux/platform_data/intel-mid_wdt.h | 19 ------------------- include/linux/platform_data/x86/intel-mid_wdt.h | 19 +++++++++++++++++++ 4 files changed, 22 insertions(+), 21 deletions(-) delete mode 100644 include/linux/platform_data/intel-mid_wdt.h create mode 100644 include/linux/platform_data/x86/intel-mid_wdt.h (limited to 'include/linux') diff --git a/drivers/platform/x86/intel_scu_wdt.c b/drivers/platform/x86/intel_scu_wdt.c index d0b6637861d3..746d47d33406 100644 --- a/drivers/platform/x86/intel_scu_wdt.c +++ b/drivers/platform/x86/intel_scu_wdt.c @@ -9,13 +9,14 @@ #include #include #include -#include #include #include #include #include +#include + #define TANGIER_EXT_TIMER0_MSI 12 static struct platform_device wdt_dev = { diff --git a/drivers/watchdog/intel-mid_wdt.c b/drivers/watchdog/intel-mid_wdt.c index 91c9c3950e44..756d262dc580 100644 --- a/drivers/watchdog/intel-mid_wdt.c +++ b/drivers/watchdog/intel-mid_wdt.c @@ -20,7 +20,7 @@ #include #include -#include +#include #include #define IPC_WATCHDOG 0xf8 diff --git a/include/linux/platform_data/intel-mid_wdt.h b/include/linux/platform_data/intel-mid_wdt.h deleted file mode 100644 index 8dba70b4b020..000000000000 --- a/include/linux/platform_data/intel-mid_wdt.h +++ /dev/null @@ -1,19 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * intel-mid_wdt: generic Intel MID SCU watchdog driver - * - * Copyright (C) 2014 Intel Corporation. All rights reserved. - * Contact: David Cohen - */ - -#ifndef __INTEL_MID_WDT_H__ -#define __INTEL_MID_WDT_H__ - -#include - -struct intel_mid_wdt_pdata { - int irq; - int (*probe)(struct platform_device *pdev); -}; - -#endif /*__INTEL_MID_WDT_H__*/ diff --git a/include/linux/platform_data/x86/intel-mid_wdt.h b/include/linux/platform_data/x86/intel-mid_wdt.h new file mode 100644 index 000000000000..e5c0210d0fec --- /dev/null +++ b/include/linux/platform_data/x86/intel-mid_wdt.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * intel-mid_wdt: generic Intel MID SCU watchdog driver + * + * Copyright (C) 2014 Intel Corporation. All rights reserved. + * Contact: David Cohen + */ + +#ifndef __PLATFORM_X86_INTEL_MID_WDT_H_ +#define __PLATFORM_X86_INTEL_MID_WDT_H_ + +#include + +struct intel_mid_wdt_pdata { + int irq; + int (*probe)(struct platform_device *pdev); +}; + +#endif /* __PLATFORM_X86_INTEL_MID_WDT_H_ */ -- cgit v1.2.3 From d3bfbfb1248498656cd25c51e41c1e31219bd0dd Mon Sep 17 00:00:00 2001 From: Kundan Kumar Date: Wed, 11 Sep 2024 12:19:34 +0530 Subject: mm: release number of pages of a folio Add a new function unpin_user_folio() to put the refs of a folio by npages count. The check for BIO_PAGE_PINNED flag is removed as it is already checked in bio_release_pages(). Signed-off-by: Kundan Kumar Tested-by: Luis Chamberlain Reviewed-by: Matthew Wilcox (Oracle) Link: https://lore.kernel.org/r/20240911064935.5630-4-kundan.kumar@samsung.com Signed-off-by: Jens Axboe --- include/linux/mm.h | 1 + mm/gup.c | 13 +++++++++++++ 2 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index c4b238a20b76..2fd88cd5997d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1597,6 +1597,7 @@ void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages, void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages, bool make_dirty); void unpin_user_pages(struct page **pages, unsigned long npages); +void unpin_user_folio(struct folio *folio, unsigned long npages); void unpin_folios(struct folio **folios, unsigned long nfolios); static inline bool is_cow_mapping(vm_flags_t flags) diff --git a/mm/gup.c b/mm/gup.c index 54d0dc3831fb..02c46ae33028 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -415,6 +415,19 @@ void unpin_user_pages(struct page **pages, unsigned long npages) } EXPORT_SYMBOL(unpin_user_pages); +/** + * unpin_user_folio() - release pages of a folio + * @folio: pointer to folio to be released + * @npages: number of pages of same folio + * + * Release npages of the folio + */ +void unpin_user_folio(struct folio *folio, unsigned long npages) +{ + gup_put_folio(folio, npages, FOLL_PIN); +} +EXPORT_SYMBOL(unpin_user_folio); + /** * unpin_folios() - release an array of gup-pinned folios. * @folios: array of folios to be marked dirty and released. -- cgit v1.2.3 From b03ffc76b83c1a7d058454efbcf1bf0e345ef1c2 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Fri, 6 Sep 2024 15:13:31 +0200 Subject: soc: qcom: geni-se: add GP_LENGTH/IRQ_EN_SET/IRQ_EN_CLEAR registers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit For UART devices the M_GP_LENGTH is the TX word count. For other devices this is the transaction word count. For UART devices the S_GP_LENGTH is the RX word count. The IRQ_EN set/clear registers allow you to set or clear bits in the IRQ_EN register without needing a read-modify-write. Acked-by: Bjorn Andersson Signed-off-by: Douglas Anderson Link: https://lore.kernel.org/r/20240610152420.v4.1.Ife7ced506aef1be3158712aa3ff34a006b973559@changeid Tested-by: Nícolas F. R. A. Prado Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20240906131336.23625-4-johan+linaro@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/soc/qcom/geni-se.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/qcom/geni-se.h b/include/linux/soc/qcom/geni-se.h index 0f038a1a0330..c3bca9c0bf2c 100644 --- a/include/linux/soc/qcom/geni-se.h +++ b/include/linux/soc/qcom/geni-se.h @@ -88,11 +88,15 @@ struct geni_se { #define SE_GENI_M_IRQ_STATUS 0x610 #define SE_GENI_M_IRQ_EN 0x614 #define SE_GENI_M_IRQ_CLEAR 0x618 +#define SE_GENI_M_IRQ_EN_SET 0x61c +#define SE_GENI_M_IRQ_EN_CLEAR 0x620 #define SE_GENI_S_CMD0 0x630 #define SE_GENI_S_CMD_CTRL_REG 0x634 #define SE_GENI_S_IRQ_STATUS 0x640 #define SE_GENI_S_IRQ_EN 0x644 #define SE_GENI_S_IRQ_CLEAR 0x648 +#define SE_GENI_S_IRQ_EN_SET 0x64c +#define SE_GENI_S_IRQ_EN_CLEAR 0x650 #define SE_GENI_TX_FIFOn 0x700 #define SE_GENI_RX_FIFOn 0x780 #define SE_GENI_TX_FIFO_STATUS 0x800 @@ -101,6 +105,8 @@ struct geni_se { #define SE_GENI_RX_WATERMARK_REG 0x810 #define SE_GENI_RX_RFR_WATERMARK_REG 0x814 #define SE_GENI_IOS 0x908 +#define SE_GENI_M_GP_LENGTH 0x910 +#define SE_GENI_S_GP_LENGTH 0x914 #define SE_DMA_TX_IRQ_STAT 0xc40 #define SE_DMA_TX_IRQ_CLR 0xc44 #define SE_DMA_TX_FSM_RST 0xc58 @@ -234,6 +240,9 @@ struct geni_se { #define IO2_DATA_IN BIT(1) #define RX_DATA_IN BIT(0) +/* SE_GENI_M_GP_LENGTH and SE_GENI_S_GP_LENGTH fields */ +#define GP_LENGTH GENMASK(31, 0) + /* SE_DMA_TX_IRQ_STAT Register fields */ #define TX_DMA_DONE BIT(0) #define TX_EOT BIT(1) -- cgit v1.2.3 From 4c59c59ef3ab9275f2a8f84dcffbd16c285ce8ea Mon Sep 17 00:00:00 2001 From: Nick Chan Date: Wed, 11 Sep 2024 13:02:11 +0800 Subject: tty: serial: samsung: Use bit manipulation macros for APPLE_S5L_* New entries using BIT() will be added soon, so change the existing ones to use bit manipulation macros including BIT() and GENMASK() for consistency. Suggested-by: Krzysztof Kozlowski Tested-by: Janne Grunau Reviewed-by: Neal Gompa Signed-off-by: Nick Chan Reviewed-by: Andi Shyti Link: https://lore.kernel.org/r/20240911050741.14477-2-towinchenmi@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_s3c.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial_s3c.h b/include/linux/serial_s3c.h index 1672cf0810ef..2a934e20ca4b 100644 --- a/include/linux/serial_s3c.h +++ b/include/linux/serial_s3c.h @@ -249,9 +249,9 @@ #define APPLE_S5L_UCON_RXTO_ENA 9 #define APPLE_S5L_UCON_RXTHRESH_ENA 12 #define APPLE_S5L_UCON_TXTHRESH_ENA 13 -#define APPLE_S5L_UCON_RXTO_ENA_MSK (1 << APPLE_S5L_UCON_RXTO_ENA) -#define APPLE_S5L_UCON_RXTHRESH_ENA_MSK (1 << APPLE_S5L_UCON_RXTHRESH_ENA) -#define APPLE_S5L_UCON_TXTHRESH_ENA_MSK (1 << APPLE_S5L_UCON_TXTHRESH_ENA) +#define APPLE_S5L_UCON_RXTO_ENA_MSK BIT(APPLE_S5L_UCON_RXTO_ENA) +#define APPLE_S5L_UCON_RXTHRESH_ENA_MSK BIT(APPLE_S5L_UCON_RXTHRESH_ENA) +#define APPLE_S5L_UCON_TXTHRESH_ENA_MSK BIT(APPLE_S5L_UCON_TXTHRESH_ENA) #define APPLE_S5L_UCON_DEFAULT (S3C2410_UCON_TXIRQMODE | \ S3C2410_UCON_RXIRQMODE | \ @@ -260,10 +260,10 @@ APPLE_S5L_UCON_RXTHRESH_ENA_MSK | \ APPLE_S5L_UCON_TXTHRESH_ENA_MSK) -#define APPLE_S5L_UTRSTAT_RXTHRESH (1<<4) -#define APPLE_S5L_UTRSTAT_TXTHRESH (1<<5) -#define APPLE_S5L_UTRSTAT_RXTO (1<<9) -#define APPLE_S5L_UTRSTAT_ALL_FLAGS (0x3f0) +#define APPLE_S5L_UTRSTAT_RXTHRESH BIT(4) +#define APPLE_S5L_UTRSTAT_TXTHRESH BIT(5) +#define APPLE_S5L_UTRSTAT_RXTO BIT(9) +#define APPLE_S5L_UTRSTAT_ALL_FLAGS GENMASK(9, 4) #ifndef __ASSEMBLY__ -- cgit v1.2.3 From 5ed771f174726ae879945d4f148a9005ac909cb7 Mon Sep 17 00:00:00 2001 From: Nick Chan Date: Wed, 11 Sep 2024 13:02:13 +0800 Subject: tty: serial: samsung: Fix serial rx on Apple A7-A9 Apple's older A7-A9 SoCs seems to use bit 3 in UTRSTAT as RXTO, which is enabled by bit 11 in UCON. Access these bits in addition to the original RXTO and RXTO enable bits, to allow serial rx to function on A7-A9 SoCs. This change does not appear to affect the A10 SoC and up. Tested-by: Janne Grunau Reviewed-by: Neal Gompa Signed-off-by: Nick Chan Reviewed-by: Andi Shyti Link: https://lore.kernel.org/r/20240911050741.14477-4-towinchenmi@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/samsung_tty.c | 17 ++++++++++++----- include/linux/serial_s3c.h | 18 +++++++++++------- 2 files changed, 23 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/serial/samsung_tty.c b/drivers/tty/serial/samsung_tty.c index 3fdec06322ac..0d184ee2f9ce 100644 --- a/drivers/tty/serial/samsung_tty.c +++ b/drivers/tty/serial/samsung_tty.c @@ -550,6 +550,7 @@ static void s3c24xx_serial_stop_rx(struct uart_port *port) case TYPE_APPLE_S5L: s3c24xx_clear_bit(port, APPLE_S5L_UCON_RXTHRESH_ENA, S3C2410_UCON); s3c24xx_clear_bit(port, APPLE_S5L_UCON_RXTO_ENA, S3C2410_UCON); + s3c24xx_clear_bit(port, APPLE_S5L_UCON_RXTO_LEGACY_ENA, S3C2410_UCON); break; default: disable_irq_nosync(ourport->rx_irq); @@ -963,9 +964,11 @@ static irqreturn_t apple_serial_handle_irq(int irq, void *id) u32 pend = rd_regl(port, S3C2410_UTRSTAT); irqreturn_t ret = IRQ_NONE; - if (pend & (APPLE_S5L_UTRSTAT_RXTHRESH | APPLE_S5L_UTRSTAT_RXTO)) { + if (pend & (APPLE_S5L_UTRSTAT_RXTHRESH | APPLE_S5L_UTRSTAT_RXTO | + APPLE_S5L_UTRSTAT_RXTO_LEGACY)) { wr_regl(port, S3C2410_UTRSTAT, - APPLE_S5L_UTRSTAT_RXTHRESH | APPLE_S5L_UTRSTAT_RXTO); + APPLE_S5L_UTRSTAT_RXTHRESH | APPLE_S5L_UTRSTAT_RXTO | + APPLE_S5L_UTRSTAT_RXTO_LEGACY); ret = s3c24xx_serial_rx_irq(ourport); } if (pend & APPLE_S5L_UTRSTAT_TXTHRESH) { @@ -1190,7 +1193,8 @@ static void apple_s5l_serial_shutdown(struct uart_port *port) ucon = rd_regl(port, S3C2410_UCON); ucon &= ~(APPLE_S5L_UCON_TXTHRESH_ENA_MSK | APPLE_S5L_UCON_RXTHRESH_ENA_MSK | - APPLE_S5L_UCON_RXTO_ENA_MSK); + APPLE_S5L_UCON_RXTO_ENA_MSK | + APPLE_S5L_UCON_RXTO_LEGACY_ENA_MSK); wr_regl(port, S3C2410_UCON, ucon); wr_regl(port, S3C2410_UTRSTAT, APPLE_S5L_UTRSTAT_ALL_FLAGS); @@ -1287,6 +1291,7 @@ static int apple_s5l_serial_startup(struct uart_port *port) /* Enable Rx Interrupt */ s3c24xx_set_bit(port, APPLE_S5L_UCON_RXTHRESH_ENA, S3C2410_UCON); s3c24xx_set_bit(port, APPLE_S5L_UCON_RXTO_ENA, S3C2410_UCON); + s3c24xx_set_bit(port, APPLE_S5L_UCON_RXTO_LEGACY_ENA, S3C2410_UCON); return ret; } @@ -2143,13 +2148,15 @@ static int s3c24xx_serial_resume_noirq(struct device *dev) ucon &= ~(APPLE_S5L_UCON_TXTHRESH_ENA_MSK | APPLE_S5L_UCON_RXTHRESH_ENA_MSK | - APPLE_S5L_UCON_RXTO_ENA_MSK); + APPLE_S5L_UCON_RXTO_ENA_MSK | + APPLE_S5L_UCON_RXTO_LEGACY_ENA_MSK); if (ourport->tx_enabled) ucon |= APPLE_S5L_UCON_TXTHRESH_ENA_MSK; if (ourport->rx_enabled) ucon |= APPLE_S5L_UCON_RXTHRESH_ENA_MSK | - APPLE_S5L_UCON_RXTO_ENA_MSK; + APPLE_S5L_UCON_RXTO_ENA_MSK | + APPLE_S5L_UCON_RXTO_LEGACY_ENA_MSK; wr_regl(port, S3C2410_UCON, ucon); diff --git a/include/linux/serial_s3c.h b/include/linux/serial_s3c.h index 2a934e20ca4b..102aa33d956c 100644 --- a/include/linux/serial_s3c.h +++ b/include/linux/serial_s3c.h @@ -246,24 +246,28 @@ S5PV210_UFCON_TXTRIG4 | \ S5PV210_UFCON_RXTRIG4) -#define APPLE_S5L_UCON_RXTO_ENA 9 -#define APPLE_S5L_UCON_RXTHRESH_ENA 12 -#define APPLE_S5L_UCON_TXTHRESH_ENA 13 -#define APPLE_S5L_UCON_RXTO_ENA_MSK BIT(APPLE_S5L_UCON_RXTO_ENA) -#define APPLE_S5L_UCON_RXTHRESH_ENA_MSK BIT(APPLE_S5L_UCON_RXTHRESH_ENA) -#define APPLE_S5L_UCON_TXTHRESH_ENA_MSK BIT(APPLE_S5L_UCON_TXTHRESH_ENA) +#define APPLE_S5L_UCON_RXTO_ENA 9 +#define APPLE_S5L_UCON_RXTO_LEGACY_ENA 11 +#define APPLE_S5L_UCON_RXTHRESH_ENA 12 +#define APPLE_S5L_UCON_TXTHRESH_ENA 13 +#define APPLE_S5L_UCON_RXTO_ENA_MSK BIT(APPLE_S5L_UCON_RXTO_ENA) +#define APPLE_S5L_UCON_RXTO_LEGACY_ENA_MSK BIT(APPLE_S5L_UCON_RXTO_LEGACY_ENA) +#define APPLE_S5L_UCON_RXTHRESH_ENA_MSK BIT(APPLE_S5L_UCON_RXTHRESH_ENA) +#define APPLE_S5L_UCON_TXTHRESH_ENA_MSK BIT(APPLE_S5L_UCON_TXTHRESH_ENA) #define APPLE_S5L_UCON_DEFAULT (S3C2410_UCON_TXIRQMODE | \ S3C2410_UCON_RXIRQMODE | \ S3C2410_UCON_RXFIFO_TOI) #define APPLE_S5L_UCON_MASK (APPLE_S5L_UCON_RXTO_ENA_MSK | \ + APPLE_S5L_UCON_RXTO_LEGACY_ENA_MSK | \ APPLE_S5L_UCON_RXTHRESH_ENA_MSK | \ APPLE_S5L_UCON_TXTHRESH_ENA_MSK) +#define APPLE_S5L_UTRSTAT_RXTO_LEGACY BIT(3) #define APPLE_S5L_UTRSTAT_RXTHRESH BIT(4) #define APPLE_S5L_UTRSTAT_TXTHRESH BIT(5) #define APPLE_S5L_UTRSTAT_RXTO BIT(9) -#define APPLE_S5L_UTRSTAT_ALL_FLAGS GENMASK(9, 4) +#define APPLE_S5L_UTRSTAT_ALL_FLAGS GENMASK(9, 3) #ifndef __ASSEMBLY__ -- cgit v1.2.3 From 6746ee4c3a189f8b60694f01e7e29bc5ff7972e0 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 11 Sep 2024 17:34:37 +0100 Subject: io_uring/cmd: expose iowq to cmds When an io_uring request needs blocking context we offload it to the io_uring's thread pool called io-wq. We can get there off ->uring_cmd by returning -EAGAIN, but there is no straightforward way of doing that from an asynchronous callback. Add a helper that would transfer a command to a blocking context. Note, we do an extra hop via task_work before io_queue_iowq(), that's a limitation of io_uring infra we have that can likely be lifted later if that would ever become a problem. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/f735f807d7c8ba50c9452c69dfe5d3e9e535037b.1726072086.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/io_uring/cmd.h | 6 ++++++ io_uring/io_uring.c | 11 +++++++++++ io_uring/io_uring.h | 1 + io_uring/uring_cmd.c | 7 +++++++ 4 files changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h index 447fbfd32215..86ceb3383e49 100644 --- a/include/linux/io_uring/cmd.h +++ b/include/linux/io_uring/cmd.h @@ -48,6 +48,9 @@ void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd, void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd, unsigned int issue_flags); +/* Execute the request from a blocking context */ +void io_uring_cmd_issue_blocking(struct io_uring_cmd *ioucmd); + #else static inline int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, struct iov_iter *iter, void *ioucmd) @@ -67,6 +70,9 @@ static inline void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd, unsigned int issue_flags) { } +static inline void io_uring_cmd_issue_blocking(struct io_uring_cmd *ioucmd) +{ +} #endif /* diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 1aca501efaf6..86cf31902841 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -533,6 +533,17 @@ static void io_queue_iowq(struct io_kiocb *req) io_queue_linked_timeout(link); } +static void io_req_queue_iowq_tw(struct io_kiocb *req, struct io_tw_state *ts) +{ + io_queue_iowq(req); +} + +void io_req_queue_iowq(struct io_kiocb *req) +{ + req->io_task_work.func = io_req_queue_iowq_tw; + io_req_task_work_add(req); +} + static __cold void io_queue_deferred(struct io_ring_ctx *ctx) { while (!list_empty(&ctx->defer_list)) { diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index 65078e641390..9d70b2cf7b1e 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -94,6 +94,7 @@ int io_uring_alloc_task_context(struct task_struct *task, int io_ring_add_registered_file(struct io_uring_task *tctx, struct file *file, int start, int end); +void io_req_queue_iowq(struct io_kiocb *req); int io_poll_issue(struct io_kiocb *req, struct io_tw_state *ts); int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr); diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index 8391c7c7c1ec..39c3c816ec78 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -277,6 +277,13 @@ int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, } EXPORT_SYMBOL_GPL(io_uring_cmd_import_fixed); +void io_uring_cmd_issue_blocking(struct io_uring_cmd *ioucmd) +{ + struct io_kiocb *req = cmd_to_io_kiocb(ioucmd); + + io_req_queue_iowq(req); +} + static inline int io_uring_cmd_getsockopt(struct socket *sock, struct io_uring_cmd *cmd, unsigned int issue_flags) -- cgit v1.2.3 From a6ccb48e13662bcb98282e051512b9686b02d353 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 11 Sep 2024 17:34:38 +0100 Subject: io_uring/cmd: give inline space in request to cmds Some io_uring commands can use some inline space in io_kiocb. We have 32 bytes in struct io_uring_cmd, expose it. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/7ca779a61ee5e166e535d70df9c7f07b15d8a0ce.1726072086.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/io_uring/cmd.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h index 86ceb3383e49..c189d36ad55e 100644 --- a/include/linux/io_uring/cmd.h +++ b/include/linux/io_uring/cmd.h @@ -23,6 +23,15 @@ static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe) return sqe->cmd; } +static inline void io_uring_cmd_private_sz_check(size_t cmd_sz) +{ + BUILD_BUG_ON(cmd_sz > sizeof_field(struct io_uring_cmd, pdu)); +} +#define io_uring_cmd_to_pdu(cmd, pdu_type) ( \ + io_uring_cmd_private_sz_check(sizeof(pdu_type)), \ + ((pdu_type *)&(cmd)->pdu) \ +) + #if defined(CONFIG_IO_URING) int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, struct iov_iter *iter, void *ioucmd); -- cgit v1.2.3 From a12c883a0a6a005cfb3ad01feaf783e2248bfc3e Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 11 Sep 2024 17:34:39 +0100 Subject: filemap: introduce filemap_invalidate_pages kiocb_invalidate_pages() is useful for the write path, however not everything is backed by kiocb and we want to reuse the function for bio based discard implementation. Extract and and reuse a new helper called filemap_invalidate_pages(), which takes a argument indicating whether it should be non-blocking and might return -EAGAIN. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/f81374b52c92d0dce0f01a279d1eed42b54056aa.1726072086.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/pagemap.h | 2 ++ mm/filemap.c | 17 ++++++++++++----- 2 files changed, 14 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index d9c7edb6422b..e39c3a7ce33c 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -32,6 +32,8 @@ int invalidate_inode_pages2_range(struct address_space *mapping, pgoff_t start, pgoff_t end); int kiocb_invalidate_pages(struct kiocb *iocb, size_t count); void kiocb_invalidate_post_direct_write(struct kiocb *iocb, size_t count); +int filemap_invalidate_pages(struct address_space *mapping, + loff_t pos, loff_t end, bool nowait); int write_inode_now(struct inode *, int sync); int filemap_fdatawrite(struct address_space *); diff --git a/mm/filemap.c b/mm/filemap.c index 0ca9c1377b68..497e802325c9 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2712,14 +2712,12 @@ int kiocb_write_and_wait(struct kiocb *iocb, size_t count) } EXPORT_SYMBOL_GPL(kiocb_write_and_wait); -int kiocb_invalidate_pages(struct kiocb *iocb, size_t count) +int filemap_invalidate_pages(struct address_space *mapping, + loff_t pos, loff_t end, bool nowait) { - struct address_space *mapping = iocb->ki_filp->f_mapping; - loff_t pos = iocb->ki_pos; - loff_t end = pos + count - 1; int ret; - if (iocb->ki_flags & IOCB_NOWAIT) { + if (nowait) { /* we could block if there are any pages in the range */ if (filemap_range_has_page(mapping, pos, end)) return -EAGAIN; @@ -2738,6 +2736,15 @@ int kiocb_invalidate_pages(struct kiocb *iocb, size_t count) return invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, end >> PAGE_SHIFT); } + +int kiocb_invalidate_pages(struct kiocb *iocb, size_t count) +{ + struct address_space *mapping = iocb->ki_filp->f_mapping; + + return filemap_invalidate_pages(mapping, iocb->ki_pos, + iocb->ki_pos + count - 1, + iocb->ki_flags & IOCB_NOWAIT); +} EXPORT_SYMBOL_GPL(kiocb_invalidate_pages); /** -- cgit v1.2.3 From 45b8fc3096542a53bfd245a9ad8ef870384b4897 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 29 Aug 2024 10:42:27 -0700 Subject: lib/buildid: rename build_id_parse() into build_id_parse_nofault() Make it clear that build_id_parse() assumes that it can take no page fault by renaming it and current few users to build_id_parse_nofault(). Also add build_id_parse() stub which for now falls back to non-sleepable implementation, but will be changed in subsequent patches to take advantage of sleepable context. PROCMAP_QUERY ioctl() on /proc//maps file is using build_id_parse() and will automatically take advantage of more reliable sleepable context implementation. Reviewed-by: Eduard Zingerman Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20240829174232.3133883-6-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/buildid.h | 4 ++-- kernel/bpf/stackmap.c | 2 +- kernel/events/core.c | 2 +- lib/buildid.c | 25 ++++++++++++++++++++++--- 4 files changed, 26 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/buildid.h b/include/linux/buildid.h index 20aa3c2d89f7..014a88c41073 100644 --- a/include/linux/buildid.h +++ b/include/linux/buildid.h @@ -7,8 +7,8 @@ #define BUILD_ID_SIZE_MAX 20 struct vm_area_struct; -int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id, - __u32 *size); +int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id, __u32 *size); +int build_id_parse_nofault(struct vm_area_struct *vma, unsigned char *build_id, __u32 *size); int build_id_parse_buf(const void *buf, unsigned char *build_id, u32 buf_size); #if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID) || IS_ENABLED(CONFIG_VMCORE_INFO) diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index c99f8e5234ac..770ae8e88016 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -156,7 +156,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, goto build_id_valid; } vma = find_vma(current->mm, ips[i]); - if (!vma || build_id_parse(vma, id_offs[i].build_id, NULL)) { + if (!vma || build_id_parse_nofault(vma, id_offs[i].build_id, NULL)) { /* per entry fall back to ips */ id_offs[i].status = BPF_STACK_BUILD_ID_IP; id_offs[i].ip = ips[i]; diff --git a/kernel/events/core.c b/kernel/events/core.c index c973e3c11e03..c78a77f9dce4 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -8851,7 +8851,7 @@ got_name: mmap_event->event_id.header.size = sizeof(mmap_event->event_id) + size; if (atomic_read(&nr_build_id_events)) - build_id_parse(vma, mmap_event->build_id, &mmap_event->build_id_size); + build_id_parse_nofault(vma, mmap_event->build_id, &mmap_event->build_id_size); perf_iterate_sb(perf_event_mmap_output, mmap_event, diff --git a/lib/buildid.c b/lib/buildid.c index e8fc4aeb01f2..c1cbd34f3685 100644 --- a/lib/buildid.c +++ b/lib/buildid.c @@ -293,10 +293,12 @@ static int get_build_id_64(struct freader *r, unsigned char *build_id, __u32 *si * @build_id: buffer to store build id, at least BUILD_ID_SIZE long * @size: returns actual build id size in case of success * - * Return: 0 on success, -EINVAL otherwise + * Assumes no page fault can be taken, so if relevant portions of ELF file are + * not already paged in, fetching of build ID fails. + * + * Return: 0 on success; negative error, otherwise */ -int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id, - __u32 *size) +int build_id_parse_nofault(struct vm_area_struct *vma, unsigned char *build_id, __u32 *size) { const Elf32_Ehdr *ehdr; struct freader r; @@ -335,6 +337,23 @@ out: return ret; } +/* + * Parse build ID of ELF file mapped to VMA + * @vma: vma object + * @build_id: buffer to store build id, at least BUILD_ID_SIZE long + * @size: returns actual build id size in case of success + * + * Assumes faultable context and can cause page faults to bring in file data + * into page cache. + * + * Return: 0 on success; negative error, otherwise + */ +int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id, __u32 *size) +{ + /* fallback to non-faultable version for now */ + return build_id_parse_nofault(vma, build_id, size); +} + /** * build_id_parse_buf - Get build ID from a buffer * @buf: ELF note section(s) to parse -- cgit v1.2.3 From d4dd9775ec242425576af93daadb80a34083a53c Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 29 Aug 2024 10:42:31 -0700 Subject: bpf: wire up sleepable bpf_get_stack() and bpf_get_task_stack() helpers Add sleepable implementations of bpf_get_stack() and bpf_get_task_stack() helpers and allow them to be used from sleepable BPF program (e.g., sleepable uprobes). Note, the stack trace IPs capturing itself is not sleepable (that would need to be a separate project), only build ID fetching is sleepable and thus more reliable, as it will wait for data to be paged in, if necessary. For that we make use of sleepable build_id_parse() implementation. Now that build ID related internals in kernel/bpf/stackmap.c can be used both in sleepable and non-sleepable contexts, we need to add additional rcu_read_lock()/rcu_read_unlock() protection around fetching perf_callchain_entry, but with the refactoring in previous commit it's now pretty straightforward. We make sure to do rcu_read_unlock (in sleepable mode only) right before stack_map_get_build_id_offset() call which can sleep. By that time we don't have any more use of perf_callchain_entry. Note, bpf_get_task_stack() will fail for user mode if task != current. And for kernel mode build ID are irrelevant. So in that sense adding sleepable bpf_get_task_stack() implementation is a no-op. It feel right to wire this up for symmetry and completeness, but I'm open to just dropping it until we support `user && crosstask` condition. Reviewed-by: Eduard Zingerman Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20240829174232.3133883-10-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 ++ kernel/bpf/stackmap.c | 90 ++++++++++++++++++++++++++++++++++++++---------- kernel/trace/bpf_trace.c | 5 +-- 3 files changed, 77 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6f87fb014fba..7f3e8477d5e7 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -3200,7 +3200,9 @@ extern const struct bpf_func_proto bpf_get_current_uid_gid_proto; extern const struct bpf_func_proto bpf_get_current_comm_proto; extern const struct bpf_func_proto bpf_get_stackid_proto; extern const struct bpf_func_proto bpf_get_stack_proto; +extern const struct bpf_func_proto bpf_get_stack_sleepable_proto; extern const struct bpf_func_proto bpf_get_task_stack_proto; +extern const struct bpf_func_proto bpf_get_task_stack_sleepable_proto; extern const struct bpf_func_proto bpf_get_stackid_proto_pe; extern const struct bpf_func_proto bpf_get_stack_proto_pe; extern const struct bpf_func_proto bpf_sock_map_update_proto; diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 6457222b0b46..3615c06b7dfa 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -124,6 +124,12 @@ free_smap: return ERR_PTR(err); } +static int fetch_build_id(struct vm_area_struct *vma, unsigned char *build_id, bool may_fault) +{ + return may_fault ? build_id_parse(vma, build_id, NULL) + : build_id_parse_nofault(vma, build_id, NULL); +} + /* * Expects all id_offs[i].ip values to be set to correct initial IPs. * They will be subsequently: @@ -135,7 +141,7 @@ free_smap: * BPF_STACK_BUILD_ID_IP. */ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, - u32 trace_nr, bool user) + u32 trace_nr, bool user, bool may_fault) { int i; struct mmap_unlock_irq_work *work = NULL; @@ -166,7 +172,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, goto build_id_valid; } vma = find_vma(current->mm, ip); - if (!vma || build_id_parse_nofault(vma, id_offs[i].build_id, NULL)) { + if (!vma || fetch_build_id(vma, id_offs[i].build_id, may_fault)) { /* per entry fall back to ips */ id_offs[i].status = BPF_STACK_BUILD_ID_IP; memset(id_offs[i].build_id, 0, BUILD_ID_SIZE_MAX); @@ -257,7 +263,7 @@ static long __bpf_get_stackid(struct bpf_map *map, id_offs = (struct bpf_stack_build_id *)new_bucket->data; for (i = 0; i < trace_nr; i++) id_offs[i].ip = ips[i]; - stack_map_get_build_id_offset(id_offs, trace_nr, user); + stack_map_get_build_id_offset(id_offs, trace_nr, user, false /* !may_fault */); trace_len = trace_nr * sizeof(struct bpf_stack_build_id); if (hash_matches && bucket->nr == trace_nr && memcmp(bucket->data, new_bucket->data, trace_len) == 0) { @@ -398,7 +404,7 @@ const struct bpf_func_proto bpf_get_stackid_proto_pe = { static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, struct perf_callchain_entry *trace_in, - void *buf, u32 size, u64 flags) + void *buf, u32 size, u64 flags, bool may_fault) { u32 trace_nr, copy_len, elem_size, num_elem, max_depth; bool user_build_id = flags & BPF_F_USER_BUILD_ID; @@ -416,8 +422,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, if (kernel && user_build_id) goto clear; - elem_size = (user && user_build_id) ? sizeof(struct bpf_stack_build_id) - : sizeof(u64); + elem_size = user_build_id ? sizeof(struct bpf_stack_build_id) : sizeof(u64); if (unlikely(size % elem_size)) goto clear; @@ -438,6 +443,9 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, if (sysctl_perf_event_max_stack < max_depth) max_depth = sysctl_perf_event_max_stack; + if (may_fault) + rcu_read_lock(); /* need RCU for perf's callchain below */ + if (trace_in) trace = trace_in; else if (kernel && task) @@ -445,28 +453,35 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, else trace = get_perf_callchain(regs, 0, kernel, user, max_depth, crosstask, false); - if (unlikely(!trace)) - goto err_fault; - if (trace->nr < skip) + if (unlikely(!trace) || trace->nr < skip) { + if (may_fault) + rcu_read_unlock(); goto err_fault; + } trace_nr = trace->nr - skip; trace_nr = (trace_nr <= num_elem) ? trace_nr : num_elem; copy_len = trace_nr * elem_size; ips = trace->ip + skip; - if (user && user_build_id) { + if (user_build_id) { struct bpf_stack_build_id *id_offs = buf; u32 i; for (i = 0; i < trace_nr; i++) id_offs[i].ip = ips[i]; - stack_map_get_build_id_offset(buf, trace_nr, user); } else { memcpy(buf, ips, copy_len); } + /* trace/ips should not be dereferenced after this point */ + if (may_fault) + rcu_read_unlock(); + + if (user_build_id) + stack_map_get_build_id_offset(buf, trace_nr, user, may_fault); + if (size > copy_len) memset(buf + copy_len, 0, size - copy_len); return copy_len; @@ -481,7 +496,7 @@ clear: BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size, u64, flags) { - return __bpf_get_stack(regs, NULL, NULL, buf, size, flags); + return __bpf_get_stack(regs, NULL, NULL, buf, size, flags, false /* !may_fault */); } const struct bpf_func_proto bpf_get_stack_proto = { @@ -494,8 +509,24 @@ const struct bpf_func_proto bpf_get_stack_proto = { .arg4_type = ARG_ANYTHING, }; -BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf, - u32, size, u64, flags) +BPF_CALL_4(bpf_get_stack_sleepable, struct pt_regs *, regs, void *, buf, u32, size, + u64, flags) +{ + return __bpf_get_stack(regs, NULL, NULL, buf, size, flags, true /* may_fault */); +} + +const struct bpf_func_proto bpf_get_stack_sleepable_proto = { + .func = bpf_get_stack_sleepable, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_UNINIT_MEM, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, + .arg4_type = ARG_ANYTHING, +}; + +static long __bpf_get_task_stack(struct task_struct *task, void *buf, u32 size, + u64 flags, bool may_fault) { struct pt_regs *regs; long res = -EINVAL; @@ -505,12 +536,18 @@ BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf, regs = task_pt_regs(task); if (regs) - res = __bpf_get_stack(regs, task, NULL, buf, size, flags); + res = __bpf_get_stack(regs, task, NULL, buf, size, flags, may_fault); put_task_stack(task); return res; } +BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf, + u32, size, u64, flags) +{ + return __bpf_get_task_stack(task, buf, size, flags, false /* !may_fault */); +} + const struct bpf_func_proto bpf_get_task_stack_proto = { .func = bpf_get_task_stack, .gpl_only = false, @@ -522,6 +559,23 @@ const struct bpf_func_proto bpf_get_task_stack_proto = { .arg4_type = ARG_ANYTHING, }; +BPF_CALL_4(bpf_get_task_stack_sleepable, struct task_struct *, task, void *, buf, + u32, size, u64, flags) +{ + return __bpf_get_task_stack(task, buf, size, flags, true /* !may_fault */); +} + +const struct bpf_func_proto bpf_get_task_stack_sleepable_proto = { + .func = bpf_get_task_stack_sleepable, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], + .arg2_type = ARG_PTR_TO_UNINIT_MEM, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, + .arg4_type = ARG_ANYTHING, +}; + BPF_CALL_4(bpf_get_stack_pe, struct bpf_perf_event_data_kern *, ctx, void *, buf, u32, size, u64, flags) { @@ -533,7 +587,7 @@ BPF_CALL_4(bpf_get_stack_pe, struct bpf_perf_event_data_kern *, ctx, __u64 nr_kernel; if (!(event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)) - return __bpf_get_stack(regs, NULL, NULL, buf, size, flags); + return __bpf_get_stack(regs, NULL, NULL, buf, size, flags, false /* !may_fault */); if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK | BPF_F_USER_BUILD_ID))) @@ -553,7 +607,7 @@ BPF_CALL_4(bpf_get_stack_pe, struct bpf_perf_event_data_kern *, ctx, __u64 nr = trace->nr; trace->nr = nr_kernel; - err = __bpf_get_stack(regs, NULL, trace, buf, size, flags); + err = __bpf_get_stack(regs, NULL, trace, buf, size, flags, false /* !may_fault */); /* restore nr */ trace->nr = nr; @@ -565,7 +619,7 @@ BPF_CALL_4(bpf_get_stack_pe, struct bpf_perf_event_data_kern *, ctx, goto clear; flags = (flags & ~BPF_F_SKIP_FIELD_MASK) | skip; - err = __bpf_get_stack(regs, NULL, trace, buf, size, flags); + err = __bpf_get_stack(regs, NULL, trace, buf, size, flags, false /* !may_fault */); } return err; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 98e395f1baae..68b5905c6eb5 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1507,7 +1507,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_jiffies64: return &bpf_jiffies64_proto; case BPF_FUNC_get_task_stack: - return &bpf_get_task_stack_proto; + return prog->sleepable ? &bpf_get_task_stack_sleepable_proto + : &bpf_get_task_stack_proto; case BPF_FUNC_copy_from_user: return &bpf_copy_from_user_proto; case BPF_FUNC_copy_from_user_task: @@ -1563,7 +1564,7 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto; case BPF_FUNC_get_stack: - return &bpf_get_stack_proto; + return prog->sleepable ? &bpf_get_stack_sleepable_proto : &bpf_get_stack_proto; #ifdef CONFIG_BPF_KPROBE_OVERRIDE case BPF_FUNC_override_return: return &bpf_override_return_proto; -- cgit v1.2.3 From 6513eb3d3191574b58859ef2d6dc26c0277c6f81 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Tue, 10 Sep 2024 17:35:35 -0400 Subject: net: tighten bad gso csum offset check in virtio_net_hdr The referenced commit drops bad input, but has false positives. Tighten the check to avoid these. The check detects illegal checksum offload requests, which produce csum_start/csum_off beyond end of packet after segmentation. But it is based on two incorrect assumptions: 1. virtio_net_hdr_to_skb with VIRTIO_NET_HDR_GSO_TCP[46] implies GSO. True in callers that inject into the tx path, such as tap. But false in callers that inject into rx, like virtio-net. Here, the flags indicate GRO, and CHECKSUM_UNNECESSARY or CHECKSUM_NONE without VIRTIO_NET_HDR_F_NEEDS_CSUM is normal. 2. TSO requires checksum offload, i.e., ip_summed == CHECKSUM_PARTIAL. False, as tcp[46]_gso_segment will fix up csum_start and offset for all other ip_summed by calling __tcp_v4_send_check. Because of 2, we can limit the scope of the fix to virtio_net_hdr that do try to set these fields, with a bogus value. Link: https://lore.kernel.org/netdev/20240909094527.GA3048202@port70.net/ Fixes: 89add40066f9 ("net: drop bad gso csum_start and offset in virtio_net_hdr") Signed-off-by: Willem de Bruijn Acked-by: Jason Wang Acked-by: Michael S. Tsirkin Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20240910213553.839926-1-willemdebruijn.kernel@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/virtio_net.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 6c395a2600e8..276ca543ef44 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -173,7 +173,8 @@ retry: break; case SKB_GSO_TCPV4: case SKB_GSO_TCPV6: - if (skb->csum_offset != offsetof(struct tcphdr, check)) + if (skb->ip_summed == CHECKSUM_PARTIAL && + skb->csum_offset != offsetof(struct tcphdr, check)) return -EINVAL; break; } -- cgit v1.2.3 From 170aafe35cb98e0f3fbacb446ea86389fbce22ea Mon Sep 17 00:00:00 2001 From: Mina Almasry Date: Tue, 10 Sep 2024 17:14:47 +0000 Subject: netdev: support binding dma-buf to netdevice Add a netdev_dmabuf_binding struct which represents the dma-buf-to-netdevice binding. The netlink API will bind the dma-buf to rx queues on the netdevice. On the binding, the dma_buf_attach & dma_buf_map_attachment will occur. The entries in the sg_table from mapping will be inserted into a genpool to make it ready for allocation. The chunks in the genpool are owned by a dmabuf_chunk_owner struct which holds the dma-buf offset of the base of the chunk and the dma_addr of the chunk. Both are needed to use allocations that come from this chunk. We create a new type that represents an allocation from the genpool: net_iov. We setup the net_iov allocation size in the genpool to PAGE_SIZE for simplicity: to match the PAGE_SIZE normally allocated by the page pool and given to the drivers. The user can unbind the dmabuf from the netdevice by closing the netlink socket that established the binding. We do this so that the binding is automatically unbound even if the userspace process crashes. The binding and unbinding leaves an indicator in struct netdev_rx_queue that the given queue is bound, and the binding is actuated by resetting the rx queue using the queue API. The netdev_dmabuf_binding struct is refcounted, and releases its resources only when all the refs are released. Signed-off-by: Willem de Bruijn Signed-off-by: Kaiyuan Zhang Signed-off-by: Mina Almasry Reviewed-by: Pavel Begunkov # excluding netlink Acked-by: Daniel Vetter Reviewed-by: Jakub Kicinski Link: https://patch.msgid.link/20240910171458.219195-4-almasrymina@google.com Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/netdev.yaml | 4 + include/linux/netdevice.h | 2 + include/net/netdev_rx_queue.h | 2 + include/net/netmem.h | 8 + include/net/page_pool/types.h | 6 + net/Kconfig | 5 + net/core/Makefile | 1 + net/core/dev.c | 26 +++ net/core/devmem.c | 274 ++++++++++++++++++++++++++++++++ net/core/devmem.h | 124 +++++++++++++++ net/core/netdev-genl-gen.c | 4 + net/core/netdev-genl-gen.h | 4 + net/core/netdev-genl.c | 128 ++++++++++++++- net/ethtool/common.c | 8 + net/xdp/xsk_buff_pool.c | 5 + 15 files changed, 596 insertions(+), 5 deletions(-) create mode 100644 net/core/devmem.c create mode 100644 net/core/devmem.h (limited to 'include/linux') diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 4930e8142aa6..0c747530c275 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -667,6 +667,10 @@ operations: attributes: - id +kernel-family: + headers: [ "linux/list.h"] + sock-priv: struct list_head + mcast-groups: list: - diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2465bdb6037f..e87b5e488325 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3953,6 +3953,8 @@ u8 dev_xdp_prog_count(struct net_device *dev); int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf); u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode); +u32 dev_get_min_mp_channel_count(const struct net_device *dev); + int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb); diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h index e78ca52d67fb..ac34f5fb4f71 100644 --- a/include/net/netdev_rx_queue.h +++ b/include/net/netdev_rx_queue.h @@ -6,6 +6,7 @@ #include #include #include +#include /* This structure contains an instance of an RX queue. */ struct netdev_rx_queue { @@ -25,6 +26,7 @@ struct netdev_rx_queue { * Readers and writers must hold RTNL */ struct napi_struct *napi; + struct pp_memory_provider_params mp_params; } ____cacheline_aligned_in_smp; /* diff --git a/include/net/netmem.h b/include/net/netmem.h index 46cc9b89ac79..c23e224dd6a0 100644 --- a/include/net/netmem.h +++ b/include/net/netmem.h @@ -8,6 +8,14 @@ #ifndef _NET_NETMEM_H #define _NET_NETMEM_H +/* net_iov */ + +struct net_iov { + struct dmabuf_genpool_chunk_owner *owner; +}; + +/* netmem */ + /** * typedef netmem_ref - a nonexistent type marking a reference to generic * network memory. diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index 50569fed7868..4afd6dd56351 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -139,6 +139,10 @@ struct page_pool_stats { */ #define PAGE_POOL_FRAG_GROUP_ALIGN (4 * sizeof(long)) +struct pp_memory_provider_params { + void *mp_priv; +}; + struct page_pool { struct page_pool_params_fast p; @@ -197,6 +201,8 @@ struct page_pool { */ struct ptr_ring ring; + void *mp_priv; + #ifdef CONFIG_PAGE_POOL_STATS /* recycle stats are per-cpu to avoid locking */ struct page_pool_recycle_stats __percpu *recycle_stats; diff --git a/net/Kconfig b/net/Kconfig index d27d0deac0bf..7574b066d7cd 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -66,6 +66,11 @@ config SKB_DECRYPTED config SKB_EXTENSIONS bool +config NET_DEVMEM + def_bool y + depends on DMA_SHARED_BUFFER + depends on GENERIC_ALLOCATOR + menu "Networking options" source "net/packet/Kconfig" diff --git a/net/core/Makefile b/net/core/Makefile index f82232b358a2..c3ebbaf9c81e 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -44,3 +44,4 @@ obj-$(CONFIG_BPF_SYSCALL) += sock_map.o obj-$(CONFIG_BPF_SYSCALL) += bpf_sk_storage.o obj-$(CONFIG_OF) += of_net.o obj-$(CONFIG_NET_TEST) += net_test.o +obj-$(CONFIG_NET_DEVMEM) += devmem.o diff --git a/net/core/dev.c b/net/core/dev.c index 8f4dead64284..7818d7f6295e 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -161,6 +161,7 @@ #include #include "dev.h" +#include "devmem.h" #include "net-sysfs.h" static DEFINE_SPINLOCK(ptype_lock); @@ -9367,6 +9368,11 @@ int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf) if (!dev->netdev_ops->ndo_bpf) return -EOPNOTSUPP; + if (dev_get_min_mp_channel_count(dev)) { + NL_SET_ERR_MSG(bpf->extack, "unable to propagate XDP to device using memory provider"); + return -EBUSY; + } + return dev->netdev_ops->ndo_bpf(dev, bpf); } EXPORT_SYMBOL_GPL(dev_xdp_propagate); @@ -9399,6 +9405,11 @@ static int dev_xdp_install(struct net_device *dev, enum bpf_xdp_mode mode, struct netdev_bpf xdp; int err; + if (dev_get_min_mp_channel_count(dev)) { + NL_SET_ERR_MSG(extack, "unable to install XDP to device using memory provider"); + return -EBUSY; + } + memset(&xdp, 0, sizeof(xdp)); xdp.command = mode == XDP_MODE_HW ? XDP_SETUP_PROG_HW : XDP_SETUP_PROG; xdp.extack = extack; @@ -9823,6 +9834,20 @@ err_out: return err; } +u32 dev_get_min_mp_channel_count(const struct net_device *dev) +{ + int i; + + ASSERT_RTNL(); + + for (i = dev->real_num_rx_queues - 1; i >= 0; i--) + if (dev->_rx[i].mp_params.mp_priv) + /* The channel count is the idx plus 1. */ + return i + 1; + + return 0; +} + /** * dev_index_reserve() - allocate an ifindex in a namespace * @net: the applicable net namespace @@ -11359,6 +11384,7 @@ void unregister_netdevice_many_notify(struct list_head *head, dev_tcx_uninstall(dev); dev_xdp_uninstall(dev); bpf_dev_bound_netdev_unregister(dev); + dev_dmabuf_uninstall(dev); netdev_offload_xstats_disable_all(dev); diff --git a/net/core/devmem.c b/net/core/devmem.c new file mode 100644 index 000000000000..8dd7beb080d2 --- /dev/null +++ b/net/core/devmem.c @@ -0,0 +1,274 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Devmem TCP + * + * Authors: Mina Almasry + * Willem de Bruijn + * Kaiyuan Zhang +#include +#include +#include +#include +#include +#include +#include +#include + +#include "devmem.h" + +/* Device memory support */ + +/* Protected by rtnl_lock() */ +static DEFINE_XARRAY_FLAGS(net_devmem_dmabuf_bindings, XA_FLAGS_ALLOC1); + +static void net_devmem_dmabuf_free_chunk_owner(struct gen_pool *genpool, + struct gen_pool_chunk *chunk, + void *not_used) +{ + struct dmabuf_genpool_chunk_owner *owner = chunk->owner; + + kvfree(owner->niovs); + kfree(owner); +} + +void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding) +{ + size_t size, avail; + + gen_pool_for_each_chunk(binding->chunk_pool, + net_devmem_dmabuf_free_chunk_owner, NULL); + + size = gen_pool_size(binding->chunk_pool); + avail = gen_pool_avail(binding->chunk_pool); + + if (!WARN(size != avail, "can't destroy genpool. size=%zu, avail=%zu", + size, avail)) + gen_pool_destroy(binding->chunk_pool); + + dma_buf_unmap_attachment_unlocked(binding->attachment, binding->sgt, + DMA_FROM_DEVICE); + dma_buf_detach(binding->dmabuf, binding->attachment); + dma_buf_put(binding->dmabuf); + xa_destroy(&binding->bound_rxqs); + kfree(binding); +} + +void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding) +{ + struct netdev_rx_queue *rxq; + unsigned long xa_idx; + unsigned int rxq_idx; + + if (binding->list.next) + list_del(&binding->list); + + xa_for_each(&binding->bound_rxqs, xa_idx, rxq) { + WARN_ON(rxq->mp_params.mp_priv != binding); + + rxq->mp_params.mp_priv = NULL; + + rxq_idx = get_netdev_rx_queue_index(rxq); + + WARN_ON(netdev_rx_queue_restart(binding->dev, rxq_idx)); + } + + xa_erase(&net_devmem_dmabuf_bindings, binding->id); + + net_devmem_dmabuf_binding_put(binding); +} + +int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx, + struct net_devmem_dmabuf_binding *binding, + struct netlink_ext_ack *extack) +{ + struct netdev_rx_queue *rxq; + u32 xa_idx; + int err; + + if (rxq_idx >= dev->real_num_rx_queues) { + NL_SET_ERR_MSG(extack, "rx queue index out of range"); + return -ERANGE; + } + + rxq = __netif_get_rx_queue(dev, rxq_idx); + if (rxq->mp_params.mp_priv) { + NL_SET_ERR_MSG(extack, "designated queue already memory provider bound"); + return -EEXIST; + } + +#ifdef CONFIG_XDP_SOCKETS + if (rxq->pool) { + NL_SET_ERR_MSG(extack, "designated queue already in use by AF_XDP"); + return -EBUSY; + } +#endif + + err = xa_alloc(&binding->bound_rxqs, &xa_idx, rxq, xa_limit_32b, + GFP_KERNEL); + if (err) + return err; + + rxq->mp_params.mp_priv = binding; + + err = netdev_rx_queue_restart(dev, rxq_idx); + if (err) + goto err_xa_erase; + + return 0; + +err_xa_erase: + rxq->mp_params.mp_priv = NULL; + xa_erase(&binding->bound_rxqs, xa_idx); + + return err; +} + +struct net_devmem_dmabuf_binding * +net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd, + struct netlink_ext_ack *extack) +{ + struct net_devmem_dmabuf_binding *binding; + static u32 id_alloc_next; + struct scatterlist *sg; + struct dma_buf *dmabuf; + unsigned int sg_idx, i; + unsigned long virtual; + int err; + + dmabuf = dma_buf_get(dmabuf_fd); + if (IS_ERR(dmabuf)) + return ERR_CAST(dmabuf); + + binding = kzalloc_node(sizeof(*binding), GFP_KERNEL, + dev_to_node(&dev->dev)); + if (!binding) { + err = -ENOMEM; + goto err_put_dmabuf; + } + + binding->dev = dev; + + err = xa_alloc_cyclic(&net_devmem_dmabuf_bindings, &binding->id, + binding, xa_limit_32b, &id_alloc_next, + GFP_KERNEL); + if (err < 0) + goto err_free_binding; + + xa_init_flags(&binding->bound_rxqs, XA_FLAGS_ALLOC); + + refcount_set(&binding->ref, 1); + + binding->dmabuf = dmabuf; + + binding->attachment = dma_buf_attach(binding->dmabuf, dev->dev.parent); + if (IS_ERR(binding->attachment)) { + err = PTR_ERR(binding->attachment); + NL_SET_ERR_MSG(extack, "Failed to bind dmabuf to device"); + goto err_free_id; + } + + binding->sgt = dma_buf_map_attachment_unlocked(binding->attachment, + DMA_FROM_DEVICE); + if (IS_ERR(binding->sgt)) { + err = PTR_ERR(binding->sgt); + NL_SET_ERR_MSG(extack, "Failed to map dmabuf attachment"); + goto err_detach; + } + + /* For simplicity we expect to make PAGE_SIZE allocations, but the + * binding can be much more flexible than that. We may be able to + * allocate MTU sized chunks here. Leave that for future work... + */ + binding->chunk_pool = + gen_pool_create(PAGE_SHIFT, dev_to_node(&dev->dev)); + if (!binding->chunk_pool) { + err = -ENOMEM; + goto err_unmap; + } + + virtual = 0; + for_each_sgtable_dma_sg(binding->sgt, sg, sg_idx) { + dma_addr_t dma_addr = sg_dma_address(sg); + struct dmabuf_genpool_chunk_owner *owner; + size_t len = sg_dma_len(sg); + struct net_iov *niov; + + owner = kzalloc_node(sizeof(*owner), GFP_KERNEL, + dev_to_node(&dev->dev)); + if (!owner) { + err = -ENOMEM; + goto err_free_chunks; + } + + owner->base_virtual = virtual; + owner->base_dma_addr = dma_addr; + owner->num_niovs = len / PAGE_SIZE; + owner->binding = binding; + + err = gen_pool_add_owner(binding->chunk_pool, dma_addr, + dma_addr, len, dev_to_node(&dev->dev), + owner); + if (err) { + kfree(owner); + err = -EINVAL; + goto err_free_chunks; + } + + owner->niovs = kvmalloc_array(owner->num_niovs, + sizeof(*owner->niovs), + GFP_KERNEL); + if (!owner->niovs) { + err = -ENOMEM; + goto err_free_chunks; + } + + for (i = 0; i < owner->num_niovs; i++) { + niov = &owner->niovs[i]; + niov->owner = owner; + } + + virtual += len; + } + + return binding; + +err_free_chunks: + gen_pool_for_each_chunk(binding->chunk_pool, + net_devmem_dmabuf_free_chunk_owner, NULL); + gen_pool_destroy(binding->chunk_pool); +err_unmap: + dma_buf_unmap_attachment_unlocked(binding->attachment, binding->sgt, + DMA_FROM_DEVICE); +err_detach: + dma_buf_detach(dmabuf, binding->attachment); +err_free_id: + xa_erase(&net_devmem_dmabuf_bindings, binding->id); +err_free_binding: + kfree(binding); +err_put_dmabuf: + dma_buf_put(dmabuf); + return ERR_PTR(err); +} + +void dev_dmabuf_uninstall(struct net_device *dev) +{ + struct net_devmem_dmabuf_binding *binding; + struct netdev_rx_queue *rxq; + unsigned long xa_idx; + unsigned int i; + + for (i = 0; i < dev->real_num_rx_queues; i++) { + binding = dev->_rx[i].mp_params.mp_priv; + if (!binding) + continue; + + xa_for_each(&binding->bound_rxqs, xa_idx, rxq) + if (rxq == &dev->_rx[i]) { + xa_erase(&binding->bound_rxqs, xa_idx); + break; + } + } +} diff --git a/net/core/devmem.h b/net/core/devmem.h new file mode 100644 index 000000000000..c50f91d858dd --- /dev/null +++ b/net/core/devmem.h @@ -0,0 +1,124 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Device memory TCP support + * + * Authors: Mina Almasry + * Willem de Bruijn + * Kaiyuan Zhang + * + */ +#ifndef _NET_DEVMEM_H +#define _NET_DEVMEM_H + +struct netlink_ext_ack; + +struct net_devmem_dmabuf_binding { + struct dma_buf *dmabuf; + struct dma_buf_attachment *attachment; + struct sg_table *sgt; + struct net_device *dev; + struct gen_pool *chunk_pool; + + /* The user holds a ref (via the netlink API) for as long as they want + * the binding to remain alive. Each page pool using this binding holds + * a ref to keep the binding alive. Each allocated net_iov holds a + * ref. + * + * The binding undos itself and unmaps the underlying dmabuf once all + * those refs are dropped and the binding is no longer desired or in + * use. + */ + refcount_t ref; + + /* The list of bindings currently active. Used for netlink to notify us + * of the user dropping the bind. + */ + struct list_head list; + + /* rxq's this binding is active on. */ + struct xarray bound_rxqs; + + /* ID of this binding. Globally unique to all bindings currently + * active. + */ + u32 id; +}; + +#if defined(CONFIG_NET_DEVMEM) +/* Owner of the dma-buf chunks inserted into the gen pool. Each scatterlist + * entry from the dmabuf is inserted into the genpool as a chunk, and needs + * this owner struct to keep track of some metadata necessary to create + * allocations from this chunk. + */ +struct dmabuf_genpool_chunk_owner { + /* Offset into the dma-buf where this chunk starts. */ + unsigned long base_virtual; + + /* dma_addr of the start of the chunk. */ + dma_addr_t base_dma_addr; + + /* Array of net_iovs for this chunk. */ + struct net_iov *niovs; + size_t num_niovs; + + struct net_devmem_dmabuf_binding *binding; +}; + +void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding); +struct net_devmem_dmabuf_binding * +net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd, + struct netlink_ext_ack *extack); +void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding); +int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx, + struct net_devmem_dmabuf_binding *binding, + struct netlink_ext_ack *extack); +void dev_dmabuf_uninstall(struct net_device *dev); + +static inline void +net_devmem_dmabuf_binding_get(struct net_devmem_dmabuf_binding *binding) +{ + refcount_inc(&binding->ref); +} + +static inline void +net_devmem_dmabuf_binding_put(struct net_devmem_dmabuf_binding *binding) +{ + if (!refcount_dec_and_test(&binding->ref)) + return; + + __net_devmem_dmabuf_binding_free(binding); +} + +#else +static inline void +__net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding) +{ +} + +static inline struct net_devmem_dmabuf_binding * +net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd, + struct netlink_ext_ack *extack) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline void +net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding) +{ +} + +static inline int +net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx, + struct net_devmem_dmabuf_binding *binding, + struct netlink_ext_ack *extack) + +{ + return -EOPNOTSUPP; +} + +static inline void dev_dmabuf_uninstall(struct net_device *dev) +{ +} +#endif + +#endif /* _NET_DEVMEM_H */ diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index 6b7fe6035067..b28424ae06d5 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -9,6 +9,7 @@ #include "netdev-genl-gen.h" #include +#include /* Integer value ranges */ static const struct netlink_range_validation netdev_a_page_pool_id_range = { @@ -187,4 +188,7 @@ struct genl_family netdev_nl_family __ro_after_init = { .n_split_ops = ARRAY_SIZE(netdev_nl_ops), .mcgrps = netdev_nl_mcgrps, .n_mcgrps = ARRAY_SIZE(netdev_nl_mcgrps), + .sock_priv_size = sizeof(struct list_head), + .sock_priv_init = (void *)netdev_nl_sock_priv_init, + .sock_priv_destroy = (void *)netdev_nl_sock_priv_destroy, }; diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h index 67c34005750c..8cda334fd042 100644 --- a/net/core/netdev-genl-gen.h +++ b/net/core/netdev-genl-gen.h @@ -10,6 +10,7 @@ #include #include +#include /* Common nested types */ extern const struct nla_policy netdev_page_pool_info_nl_policy[NETDEV_A_PAGE_POOL_IFINDEX + 1]; @@ -40,4 +41,7 @@ enum { extern struct genl_family netdev_nl_family; +void netdev_nl_sock_priv_init(struct list_head *priv); +void netdev_nl_sock_priv_destroy(struct list_head *priv); + #endif /* _LINUX_NETDEV_GEN_H */ diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 699c34b9b03c..9153a8ab0cf8 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -3,16 +3,17 @@ #include #include #include +#include #include +#include +#include #include #include #include -#include -#include -#include -#include "netdev-genl-gen.h" #include "dev.h" +#include "devmem.h" +#include "netdev-genl-gen.h" struct netdev_nl_dump_ctx { unsigned long ifindex; @@ -723,10 +724,127 @@ int netdev_nl_qstats_get_dumpit(struct sk_buff *skb, return err; } -/* Stub */ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info) { + struct nlattr *tb[ARRAY_SIZE(netdev_queue_id_nl_policy)]; + struct net_devmem_dmabuf_binding *binding; + struct list_head *sock_binding_list; + u32 ifindex, dmabuf_fd, rxq_idx; + struct net_device *netdev; + struct sk_buff *rsp; + struct nlattr *attr; + int rem, err = 0; + void *hdr; + + if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_DEV_IFINDEX) || + GENL_REQ_ATTR_CHECK(info, NETDEV_A_DMABUF_FD) || + GENL_REQ_ATTR_CHECK(info, NETDEV_A_DMABUF_QUEUES)) + return -EINVAL; + + ifindex = nla_get_u32(info->attrs[NETDEV_A_DEV_IFINDEX]); + dmabuf_fd = nla_get_u32(info->attrs[NETDEV_A_DMABUF_FD]); + + sock_binding_list = genl_sk_priv_get(&netdev_nl_family, + NETLINK_CB(skb).sk); + if (IS_ERR(sock_binding_list)) + return PTR_ERR(sock_binding_list); + + rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!rsp) + return -ENOMEM; + + hdr = genlmsg_iput(rsp, info); + if (!hdr) { + err = -EMSGSIZE; + goto err_genlmsg_free; + } + + rtnl_lock(); + + netdev = __dev_get_by_index(genl_info_net(info), ifindex); + if (!netdev || !netif_device_present(netdev)) { + err = -ENODEV; + goto err_unlock; + } + + if (dev_xdp_prog_count(netdev)) { + NL_SET_ERR_MSG(info->extack, "unable to bind dmabuf to device with XDP program attached"); + err = -EEXIST; + goto err_unlock; + } + + binding = net_devmem_bind_dmabuf(netdev, dmabuf_fd, info->extack); + if (IS_ERR(binding)) { + err = PTR_ERR(binding); + goto err_unlock; + } + + nla_for_each_attr_type(attr, NETDEV_A_DMABUF_QUEUES, + genlmsg_data(info->genlhdr), + genlmsg_len(info->genlhdr), rem) { + err = nla_parse_nested( + tb, ARRAY_SIZE(netdev_queue_id_nl_policy) - 1, attr, + netdev_queue_id_nl_policy, info->extack); + if (err < 0) + goto err_unbind; + + if (NL_REQ_ATTR_CHECK(info->extack, attr, tb, NETDEV_A_QUEUE_ID) || + NL_REQ_ATTR_CHECK(info->extack, attr, tb, NETDEV_A_QUEUE_TYPE)) { + err = -EINVAL; + goto err_unbind; + } + + if (nla_get_u32(tb[NETDEV_A_QUEUE_TYPE]) != NETDEV_QUEUE_TYPE_RX) { + NL_SET_BAD_ATTR(info->extack, tb[NETDEV_A_QUEUE_TYPE]); + err = -EINVAL; + goto err_unbind; + } + + rxq_idx = nla_get_u32(tb[NETDEV_A_QUEUE_ID]); + + err = net_devmem_bind_dmabuf_to_queue(netdev, rxq_idx, binding, + info->extack); + if (err) + goto err_unbind; + } + + list_add(&binding->list, sock_binding_list); + + nla_put_u32(rsp, NETDEV_A_DMABUF_ID, binding->id); + genlmsg_end(rsp, hdr); + + err = genlmsg_reply(rsp, info); + if (err) + goto err_unbind; + + rtnl_unlock(); + return 0; + +err_unbind: + net_devmem_unbind_dmabuf(binding); +err_unlock: + rtnl_unlock(); +err_genlmsg_free: + nlmsg_free(rsp); + return err; +} + +void netdev_nl_sock_priv_init(struct list_head *priv) +{ + INIT_LIST_HEAD(priv); +} + +void netdev_nl_sock_priv_destroy(struct list_head *priv) +{ + struct net_devmem_dmabuf_binding *binding; + struct net_devmem_dmabuf_binding *temp; + + list_for_each_entry_safe(binding, temp, priv, list) { + rtnl_lock(); + net_devmem_unbind_dmabuf(binding); + rtnl_unlock(); + } } static int netdev_genl_netdevice_event(struct notifier_block *nb, diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 6c245e59bbc1..dd345efa114b 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -655,6 +655,7 @@ int ethtool_check_max_channel(struct net_device *dev, { u64 max_rxnfc_in_use; u32 max_rxfh_in_use; + int max_mp_in_use; /* ensure the new Rx count fits within the configured Rx flow * indirection table/rxnfc settings @@ -673,6 +674,13 @@ int ethtool_check_max_channel(struct net_device *dev, return -EINVAL; } + max_mp_in_use = dev_get_min_mp_channel_count(dev); + if (channels.combined_count + channels.rx_count <= max_mp_in_use) { + if (info) + GENL_SET_ERR_MSG_FMT(info, "requested channel counts are too low for existing memory provider setting (%d)", max_mp_in_use); + return -EINVAL; + } + return 0; } diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index c0e0204b9630..6b2756f95629 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -211,6 +211,11 @@ int xp_assign_dev(struct xsk_buff_pool *pool, goto err_unreg_pool; } + if (dev_get_min_mp_channel_count(netdev)) { + err = -EBUSY; + goto err_unreg_pool; + } + bpf.command = XDP_SETUP_XSK_POOL; bpf.xsk.pool = pool; bpf.xsk.queue_id = queue_id; -- cgit v1.2.3 From 9f6b619edf2e85746f261b42ae8f818a59d126f7 Mon Sep 17 00:00:00 2001 From: Mina Almasry Date: Tue, 10 Sep 2024 17:14:51 +0000 Subject: net: support non paged skb frags Make skb_frag_page() fail in the case where the frag is not backed by a page, and fix its relevant callers to handle this case. Signed-off-by: Mina Almasry Reviewed-by: Eric Dumazet Reviewed-by: Jakub Kicinski Link: https://patch.msgid.link/20240910171458.219195-8-almasrymina@google.com Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 42 +++++++++++++++++++++++++++++++++++++++++- include/linux/skbuff_ref.h | 9 ++++----- net/core/dev.c | 3 ++- net/core/gro.c | 3 ++- net/core/skbuff.c | 11 +++++++++++ net/ipv4/esp4.c | 3 ++- net/ipv4/tcp.c | 3 +++ net/ipv6/esp6.c | 3 ++- 8 files changed, 67 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5803eb8a157d..1019f14583c9 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3524,21 +3524,58 @@ static inline void skb_frag_off_copy(skb_frag_t *fragto, fragto->offset = fragfrom->offset; } +/* Return: true if the skb_frag contains a net_iov. */ +static inline bool skb_frag_is_net_iov(const skb_frag_t *frag) +{ + return netmem_is_net_iov(frag->netmem); +} + +/** + * skb_frag_net_iov - retrieve the net_iov referred to by fragment + * @frag: the fragment + * + * Return: the &struct net_iov associated with @frag. Returns NULL if this + * frag has no associated net_iov. + */ +static inline struct net_iov *skb_frag_net_iov(const skb_frag_t *frag) +{ + if (!skb_frag_is_net_iov(frag)) + return NULL; + + return netmem_to_net_iov(frag->netmem); +} + /** * skb_frag_page - retrieve the page referred to by a paged fragment * @frag: the paged fragment * - * Returns the &struct page associated with @frag. + * Return: the &struct page associated with @frag. Returns NULL if this frag + * has no associated page. */ static inline struct page *skb_frag_page(const skb_frag_t *frag) { + if (skb_frag_is_net_iov(frag)) + return NULL; + return netmem_to_page(frag->netmem); } +/** + * skb_frag_netmem - retrieve the netmem referred to by a fragment + * @frag: the fragment + * + * Return: the &netmem_ref associated with @frag. + */ +static inline netmem_ref skb_frag_netmem(const skb_frag_t *frag) +{ + return frag->netmem; +} + int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, unsigned int headroom); int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, struct bpf_prog *prog); + /** * skb_frag_address - gets the address of the data contained in a paged fragment * @frag: the paged fragment buffer @@ -3548,6 +3585,9 @@ int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, */ static inline void *skb_frag_address(const skb_frag_t *frag) { + if (!skb_frag_page(frag)) + return NULL; + return page_address(skb_frag_page(frag)) + skb_frag_off(frag); } diff --git a/include/linux/skbuff_ref.h b/include/linux/skbuff_ref.h index 16c241a23472..0f3c58007488 100644 --- a/include/linux/skbuff_ref.h +++ b/include/linux/skbuff_ref.h @@ -34,14 +34,13 @@ static inline void skb_frag_ref(struct sk_buff *skb, int f) bool napi_pp_put_page(netmem_ref netmem); -static inline void -skb_page_unref(struct page *page, bool recycle) +static inline void skb_page_unref(netmem_ref netmem, bool recycle) { #ifdef CONFIG_PAGE_POOL - if (recycle && napi_pp_put_page(page_to_netmem(page))) + if (recycle && napi_pp_put_page(netmem)) return; #endif - put_page(page); + put_page(netmem_to_page(netmem)); } /** @@ -54,7 +53,7 @@ skb_page_unref(struct page *page, bool recycle) */ static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) { - skb_page_unref(skb_frag_page(frag), recycle); + skb_page_unref(skb_frag_netmem(frag), recycle); } /** diff --git a/net/core/dev.c b/net/core/dev.c index 7818d7f6295e..517b934bdf9c 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3434,8 +3434,9 @@ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) if (!(dev->features & NETIF_F_HIGHDMA)) { for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + struct page *page = skb_frag_page(frag); - if (PageHighMem(skb_frag_page(frag))) + if (page && PageHighMem(page)) return 1; } } diff --git a/net/core/gro.c b/net/core/gro.c index 3abad1b567dd..802b4a062400 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -408,7 +408,8 @@ static inline void skb_gro_reset_offset(struct sk_buff *skb, u32 nhoff) pinfo = skb_shinfo(skb); frag0 = &pinfo->frags[0]; - if (pinfo->nr_frags && !PageHighMem(skb_frag_page(frag0)) && + if (pinfo->nr_frags && skb_frag_page(frag0) && + !PageHighMem(skb_frag_page(frag0)) && (!NET_IP_ALIGN || !((skb_frag_off(frag0) + nhoff) & 3))) { NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 8abcc28bb189..671c456b93f5 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1371,6 +1371,14 @@ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt) struct page *p; u8 *vaddr; + if (skb_frag_is_net_iov(frag)) { + printk("%sskb frag %d: not readable\n", level, i); + len -= skb_frag_size(frag); + if (!len) + break; + continue; + } + skb_frag_foreach_page(frag, skb_frag_off(frag), skb_frag_size(frag), p, p_off, p_len, copied) { @@ -3163,6 +3171,9 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, for (seg = 0; seg < skb_shinfo(skb)->nr_frags; seg++) { const skb_frag_t *f = &skb_shinfo(skb)->frags[seg]; + if (WARN_ON_ONCE(!skb_frag_page(f))) + return false; + if (__splice_segment(skb_frag_page(f), skb_frag_off(f), skb_frag_size(f), offset, len, spd, false, sk, pipe)) diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 47378ca41904..f3281312eb5e 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -115,7 +115,8 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb) */ if (req->src != req->dst) for (sg = sg_next(req->src); sg; sg = sg_next(sg)) - skb_page_unref(sg_page(sg), skb->pp_recycle); + skb_page_unref(page_to_netmem(sg_page(sg)), + skb->pp_recycle); } #ifdef CONFIG_INET_ESPINTCP diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index e359a9161445..06dcf89e2cca 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2177,6 +2177,9 @@ static int tcp_zerocopy_receive(struct sock *sk, break; } page = skb_frag_page(frags); + if (WARN_ON_ONCE(!page)) + break; + prefetchw(page); pages[pages_to_map++] = page; length += PAGE_SIZE; diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 3920e8aa1031..b2400c226a32 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -132,7 +132,8 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb) */ if (req->src != req->dst) for (sg = sg_next(req->src); sg; sg = sg_next(sg)) - skb_page_unref(sg_page(sg), skb->pp_recycle); + skb_page_unref(page_to_netmem(sg_page(sg)), + skb->pp_recycle); } #ifdef CONFIG_INET6_ESPINTCP -- cgit v1.2.3 From 65249feb6b3df9e17bab5911ee56fa7b0971e231 Mon Sep 17 00:00:00 2001 From: Mina Almasry Date: Tue, 10 Sep 2024 17:14:52 +0000 Subject: net: add support for skbs with unreadable frags For device memory TCP, we expect the skb headers to be available in host memory for access, and we expect the skb frags to be in device memory and unaccessible to the host. We expect there to be no mixing and matching of device memory frags (unaccessible) with host memory frags (accessible) in the same skb. Add a skb->devmem flag which indicates whether the frags in this skb are device memory frags or not. __skb_fill_netmem_desc() now checks frags added to skbs for net_iov, and marks the skb as skb->devmem accordingly. Add checks through the network stack to avoid accessing the frags of devmem skbs and avoid coalescing devmem skbs with non devmem skbs. Signed-off-by: Willem de Bruijn Signed-off-by: Kaiyuan Zhang Signed-off-by: Mina Almasry Reviewed-by: Eric Dumazet Reviewed-by: Jakub Kicinski Link: https://patch.msgid.link/20240910171458.219195-9-almasrymina@google.com Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 19 +++++++++++++++++-- include/net/tcp.h | 3 ++- net/core/datagram.c | 6 ++++++ net/core/dev.c | 4 ++++ net/core/skbuff.c | 43 +++++++++++++++++++++++++++++++++++++++++-- net/ipv4/tcp.c | 3 +++ net/ipv4/tcp_input.c | 13 ++++++++++--- net/ipv4/tcp_output.c | 5 ++++- net/packet/af_packet.c | 4 ++-- 9 files changed, 89 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 1019f14583c9..39f1d16f3628 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -827,6 +827,8 @@ enum skb_tstamp_type { * @csum_level: indicates the number of consecutive checksums found in * the packet minus one that have been verified as * CHECKSUM_UNNECESSARY (max 3) + * @unreadable: indicates that at least 1 of the fragments in this skb is + * unreadable. * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB * @slow_gro: state present at GRO time, slower prepare step required @@ -1008,7 +1010,7 @@ struct sk_buff { #if IS_ENABLED(CONFIG_IP_SCTP) __u8 csum_not_inet:1; #endif - + __u8 unreadable:1; #if defined(CONFIG_NET_SCHED) || defined(CONFIG_NET_XGRESS) __u16 tc_index; /* traffic control index */ #endif @@ -1824,6 +1826,12 @@ static inline void skb_zcopy_downgrade_managed(struct sk_buff *skb) __skb_zcopy_downgrade_managed(skb); } +/* Return true if frags in this skb are readable by the host. */ +static inline bool skb_frags_readable(const struct sk_buff *skb) +{ + return !skb->unreadable; +} + static inline void skb_mark_not_on_list(struct sk_buff *skb) { skb->next = NULL; @@ -2540,10 +2548,17 @@ static inline void skb_len_add(struct sk_buff *skb, int delta) static inline void __skb_fill_netmem_desc(struct sk_buff *skb, int i, netmem_ref netmem, int off, int size) { - struct page *page = netmem_to_page(netmem); + struct page *page; __skb_fill_netmem_desc_noacc(skb_shinfo(skb), i, netmem, off, size); + if (netmem_is_net_iov(netmem)) { + skb->unreadable = true; + return; + } + + page = netmem_to_page(netmem); + /* Propagate page pfmemalloc to the skb if we can. The problem is * that not all callers have unique ownership of the page but rely * on page_is_pfmemalloc doing the right thing(tm). diff --git a/include/net/tcp.h b/include/net/tcp.h index 2aac11e7e1cc..f77f812bfbe7 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1069,7 +1069,8 @@ static inline bool tcp_skb_can_collapse(const struct sk_buff *to, /* skb_cmp_decrypted() not needed, use tcp_write_collapse_fence() */ return likely(tcp_skb_can_collapse_to(to) && mptcp_skb_can_collapse(to, from) && - skb_pure_zcopy_same(to, from)); + skb_pure_zcopy_same(to, from) && + skb_frags_readable(to) == skb_frags_readable(from)); } static inline bool tcp_skb_can_collapse_rx(const struct sk_buff *to, diff --git a/net/core/datagram.c b/net/core/datagram.c index a40f733b37d7..f0693707aece 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -407,6 +407,9 @@ static int __skb_datagram_iter(const struct sk_buff *skb, int offset, return 0; } + if (!skb_frags_readable(skb)) + goto short_copy; + /* Copy paged appendix. Hmm... why does this look so complicated? */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; @@ -623,6 +626,9 @@ int zerocopy_fill_skb_from_iter(struct sk_buff *skb, { int frag = skb_shinfo(skb)->nr_frags; + if (!skb_frags_readable(skb)) + return -EFAULT; + while (length && iov_iter_count(from)) { struct page *head, *last_head = NULL; struct page *pages[MAX_SKB_FRAGS]; diff --git a/net/core/dev.c b/net/core/dev.c index 517b934bdf9c..1e740faf9e78 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3312,6 +3312,10 @@ int skb_checksum_help(struct sk_buff *skb) return -EINVAL; } + if (!skb_frags_readable(skb)) { + return -EFAULT; + } + /* Before computing a checksum, we should make sure no frag could * be modified by an external entity : checksum could be wrong. */ diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 671c456b93f5..74149dc4ee31 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1972,6 +1972,9 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) if (skb_shared(skb) || skb_unclone(skb, gfp_mask)) return -EINVAL; + if (!skb_frags_readable(skb)) + return -EFAULT; + if (!num_frags) goto release; @@ -2145,6 +2148,9 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) unsigned int size; int headerlen; + if (!skb_frags_readable(skb)) + return NULL; + if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)) return NULL; @@ -2483,6 +2489,9 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, struct sk_buff *n; int oldheadroom; + if (!skb_frags_readable(skb)) + return NULL; + if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)) return NULL; @@ -2827,6 +2836,9 @@ void *__pskb_pull_tail(struct sk_buff *skb, int delta) */ int i, k, eat = (skb->tail + delta) - skb->end; + if (!skb_frags_readable(skb)) + return NULL; + if (eat > 0 || skb_cloned(skb)) { if (pskb_expand_head(skb, 0, eat > 0 ? eat + 128 : 0, GFP_ATOMIC)) @@ -2980,6 +2992,9 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) to += copy; } + if (!skb_frags_readable(skb)) + goto fault; + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; skb_frag_t *f = &skb_shinfo(skb)->frags[i]; @@ -3168,6 +3183,9 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, /* * then map the fragments */ + if (!skb_frags_readable(skb)) + return false; + for (seg = 0; seg < skb_shinfo(skb)->nr_frags; seg++) { const skb_frag_t *f = &skb_shinfo(skb)->frags[seg]; @@ -3391,6 +3409,9 @@ int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len) from += copy; } + if (!skb_frags_readable(skb)) + goto fault; + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; int end; @@ -3470,6 +3491,9 @@ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len, pos = copy; } + if (WARN_ON_ONCE(!skb_frags_readable(skb))) + return 0; + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; @@ -3570,6 +3594,9 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, pos = copy; } + if (!skb_frags_readable(skb)) + return 0; + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; @@ -4061,6 +4088,7 @@ static inline void skb_split_inside_header(struct sk_buff *skb, skb_shinfo(skb1)->frags[i] = skb_shinfo(skb)->frags[i]; skb_shinfo(skb1)->nr_frags = skb_shinfo(skb)->nr_frags; + skb1->unreadable = skb->unreadable; skb_shinfo(skb)->nr_frags = 0; skb1->data_len = skb->data_len; skb1->len += skb1->data_len; @@ -4108,6 +4136,8 @@ static inline void skb_split_no_header(struct sk_buff *skb, pos += size; } skb_shinfo(skb1)->nr_frags = k; + + skb1->unreadable = skb->unreadable; } /** @@ -4345,6 +4375,9 @@ next_skb: return block_limit - abs_offset; } + if (!skb_frags_readable(st->cur_skb)) + return 0; + if (st->frag_idx == 0 && !st->frag_data) st->stepped_offset += skb_headlen(st->cur_skb); @@ -5992,7 +6025,10 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, if (to->pp_recycle != from->pp_recycle) return false; - if (len <= skb_tailroom(to)) { + if (skb_frags_readable(from) != skb_frags_readable(to)) + return false; + + if (len <= skb_tailroom(to) && skb_frags_readable(from)) { if (len) BUG_ON(skb_copy_bits(from, 0, skb_put(to, len), len)); *delta_truesize = 0; @@ -6169,6 +6205,9 @@ int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len) if (!pskb_may_pull(skb, write_len)) return -ENOMEM; + if (!skb_frags_readable(skb)) + return -EFAULT; + if (!skb_cloned(skb) || skb_clone_writable(skb, write_len)) return 0; @@ -6848,7 +6887,7 @@ void skb_condense(struct sk_buff *skb) { if (skb->data_len) { if (skb->data_len > skb->end - skb->tail || - skb_cloned(skb)) + skb_cloned(skb) || !skb_frags_readable(skb)) return; /* Nice, we can free page frag(s) right now */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 06dcf89e2cca..a2fac029a84a 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2160,6 +2160,9 @@ static int tcp_zerocopy_receive(struct sock *sk, skb = tcp_recv_skb(sk, seq, &offset); } + if (!skb_frags_readable(skb)) + break; + if (TCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, tss); zc->msg_flags |= TCP_CMSG_TS; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e37488d3453f..9f314dfa1490 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5391,6 +5391,9 @@ restart: for (end_of_skbs = true; skb != NULL && skb != tail; skb = n) { n = tcp_skb_next(skb, list); + if (!skb_frags_readable(skb)) + goto skip_this; + /* No new bits? It is possible on ofo queue. */ if (!before(start, TCP_SKB_CB(skb)->end_seq)) { skb = tcp_collapse_one(sk, skb, list, root); @@ -5411,17 +5414,20 @@ restart: break; } - if (n && n != tail && tcp_skb_can_collapse_rx(skb, n) && + if (n && n != tail && skb_frags_readable(n) && + tcp_skb_can_collapse_rx(skb, n) && TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(n)->seq) { end_of_skbs = false; break; } +skip_this: /* Decided to skip this, advance start seq. */ start = TCP_SKB_CB(skb)->end_seq; } if (end_of_skbs || - (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN))) + (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) || + !skb_frags_readable(skb)) return; __skb_queue_head_init(&tmp); @@ -5463,7 +5469,8 @@ restart: if (!skb || skb == tail || !tcp_skb_can_collapse_rx(nskb, skb) || - (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN))) + (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) || + !skb_frags_readable(skb)) goto end; } } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index cdd0def14427..4fd746bd4d54 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2344,7 +2344,8 @@ static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len) if (unlikely(TCP_SKB_CB(skb)->eor) || tcp_has_tx_tstamp(skb) || - !skb_pure_zcopy_same(skb, next)) + !skb_pure_zcopy_same(skb, next) || + skb_frags_readable(skb) != skb_frags_readable(next)) return false; len -= skb->len; @@ -3264,6 +3265,8 @@ static bool tcp_can_collapse(const struct sock *sk, const struct sk_buff *skb) return false; if (skb_cloned(skb)) return false; + if (!skb_frags_readable(skb)) + return false; /* Some heuristics for collapsing over SACK'd could be invented */ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) return false; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 4a364cdd445e..a705ec214254 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2216,7 +2216,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, } } - snaplen = skb->len; + snaplen = skb_frags_readable(skb) ? skb->len : skb_headlen(skb); res = run_filter(skb, sk, snaplen); if (!res) @@ -2336,7 +2336,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, } } - snaplen = skb->len; + snaplen = skb_frags_readable(skb) ? skb->len : skb_headlen(skb); res = run_filter(skb, sk, snaplen); if (!res) -- cgit v1.2.3 From 8f0b3cc9a4c102c24808c87f1bc943659d7a7f9f Mon Sep 17 00:00:00 2001 From: Mina Almasry Date: Tue, 10 Sep 2024 17:14:53 +0000 Subject: tcp: RX path for devmem TCP In tcp_recvmsg_locked(), detect if the skb being received by the user is a devmem skb. In this case - if the user provided the MSG_SOCK_DEVMEM flag - pass it to tcp_recvmsg_devmem() for custom handling. tcp_recvmsg_devmem() copies any data in the skb header to the linear buffer, and returns a cmsg to the user indicating the number of bytes returned in the linear buffer. tcp_recvmsg_devmem() then loops over the unaccessible devmem skb frags, and returns to the user a cmsg_devmem indicating the location of the data in the dmabuf device memory. cmsg_devmem contains this information: 1. the offset into the dmabuf where the payload starts. 'frag_offset'. 2. the size of the frag. 'frag_size'. 3. an opaque token 'frag_token' to return to the kernel when the buffer is to be released. The pages awaiting freeing are stored in the newly added sk->sk_user_frags, and each page passed to userspace is get_page()'d. This reference is dropped once the userspace indicates that it is done reading this page. All pages are released when the socket is destroyed. Signed-off-by: Willem de Bruijn Signed-off-by: Kaiyuan Zhang Signed-off-by: Mina Almasry Reviewed-by: Pavel Begunkov Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20240910171458.219195-10-almasrymina@google.com Signed-off-by: Jakub Kicinski --- arch/alpha/include/uapi/asm/socket.h | 5 + arch/mips/include/uapi/asm/socket.h | 5 + arch/parisc/include/uapi/asm/socket.h | 5 + arch/sparc/include/uapi/asm/socket.h | 5 + include/linux/socket.h | 1 + include/net/sock.h | 2 + include/uapi/asm-generic/socket.h | 5 + include/uapi/linux/uio.h | 13 ++ net/core/devmem.h | 22 +++ net/ipv4/tcp.c | 257 +++++++++++++++++++++++++++++++++- net/ipv4/tcp_ipv4.c | 16 +++ net/ipv4/tcp_minisocks.c | 2 + 12 files changed, 333 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index e94f621903fe..ef4656a41058 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -140,6 +140,11 @@ #define SO_PASSPIDFD 76 #define SO_PEERPIDFD 77 +#define SO_DEVMEM_LINEAR 78 +#define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR +#define SO_DEVMEM_DMABUF 79 +#define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 60ebaed28a4c..414807d55e33 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -151,6 +151,11 @@ #define SO_PASSPIDFD 76 #define SO_PEERPIDFD 77 +#define SO_DEVMEM_LINEAR 78 +#define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR +#define SO_DEVMEM_DMABUF 79 +#define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index be264c2b1a11..2b817efd4544 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -132,6 +132,11 @@ #define SO_PASSPIDFD 0x404A #define SO_PEERPIDFD 0x404B +#define SO_DEVMEM_LINEAR 78 +#define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR +#define SO_DEVMEM_DMABUF 79 +#define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 682da3714686..00248fc68977 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -133,6 +133,11 @@ #define SO_PASSPIDFD 0x0055 #define SO_PEERPIDFD 0x0056 +#define SO_DEVMEM_LINEAR 0x0057 +#define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR +#define SO_DEVMEM_DMABUF 0x0058 +#define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF + #if !defined(__KERNEL__) diff --git a/include/linux/socket.h b/include/linux/socket.h index df9cdb8bbfb8..d18cc47e89bd 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -327,6 +327,7 @@ struct ucred { * plain text and require encryption */ +#define MSG_SOCK_DEVMEM 0x2000000 /* Receive devmem skbs as cmsg */ #define MSG_ZEROCOPY 0x4000000 /* Use user data in kernel path */ #define MSG_SPLICE_PAGES 0x8000000 /* Splice the pages from the iterator in sendmsg() */ #define MSG_FASTOPEN 0x20000000 /* Send data in TCP SYN */ diff --git a/include/net/sock.h b/include/net/sock.h index f51d61fab059..c58ca8dd561b 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -337,6 +337,7 @@ struct sk_filter; * @sk_txtime_report_errors: set report errors mode for SO_TXTIME * @sk_txtime_unused: unused txtime flags * @ns_tracker: tracker for netns reference + * @sk_user_frags: xarray of pages the user is holding a reference on. */ struct sock { /* @@ -542,6 +543,7 @@ struct sock { #endif struct rcu_head sk_rcu; netns_tracker ns_tracker; + struct xarray sk_user_frags; }; struct sock_bh_locked { diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 8ce8a39a1e5f..e993edc9c0ee 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -135,6 +135,11 @@ #define SO_PASSPIDFD 76 #define SO_PEERPIDFD 77 +#define SO_DEVMEM_LINEAR 78 +#define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR +#define SO_DEVMEM_DMABUF 79 +#define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/include/uapi/linux/uio.h b/include/uapi/linux/uio.h index 059b1a9147f4..3a22ddae376a 100644 --- a/include/uapi/linux/uio.h +++ b/include/uapi/linux/uio.h @@ -20,6 +20,19 @@ struct iovec __kernel_size_t iov_len; /* Must be size_t (1003.1g) */ }; +struct dmabuf_cmsg { + __u64 frag_offset; /* offset into the dmabuf where the frag starts. + */ + __u32 frag_size; /* size of the frag. */ + __u32 frag_token; /* token representing this frag for + * DEVMEM_DONTNEED. + */ + __u32 dmabuf_id; /* dmabuf id this frag belongs to. */ + __u32 flags; /* Currently unused. Reserved for future + * uses. + */ +}; + /* * UIO_MAXIOV shall be at least 16 1003.1g (5.4.1.1) */ diff --git a/net/core/devmem.h b/net/core/devmem.h index b1db4877cff9..76099ef9c482 100644 --- a/net/core/devmem.h +++ b/net/core/devmem.h @@ -91,6 +91,19 @@ net_iov_binding(const struct net_iov *niov) return net_iov_owner(niov)->binding; } +static inline unsigned long net_iov_virtual_addr(const struct net_iov *niov) +{ + struct dmabuf_genpool_chunk_owner *owner = net_iov_owner(niov); + + return owner->base_virtual + + ((unsigned long)net_iov_idx(niov) << PAGE_SHIFT); +} + +static inline u32 net_iov_binding_id(const struct net_iov *niov) +{ + return net_iov_owner(niov)->binding->id; +} + static inline void net_devmem_dmabuf_binding_get(struct net_devmem_dmabuf_binding *binding) { @@ -153,6 +166,15 @@ static inline void net_devmem_free_dmabuf(struct net_iov *ppiov) { } +static inline unsigned long net_iov_virtual_addr(const struct net_iov *niov) +{ + return 0; +} + +static inline u32 net_iov_binding_id(const struct net_iov *niov) +{ + return 0; +} #endif #endif /* _NET_DEVMEM_H */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index a2fac029a84a..4f77bd862e95 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -285,6 +285,8 @@ #include #include +#include "../core/devmem.h" + /* Track pending CMSGs. */ enum { TCP_CMSG_INQ = 1, @@ -471,6 +473,7 @@ void tcp_init_sock(struct sock *sk) set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); sk_sockets_allocated_inc(sk); + xa_init_flags(&sk->sk_user_frags, XA_FLAGS_ALLOC1); } EXPORT_SYMBOL(tcp_init_sock); @@ -2328,6 +2331,220 @@ static int tcp_inq_hint(struct sock *sk) return inq; } +/* batch __xa_alloc() calls and reduce xa_lock()/xa_unlock() overhead. */ +struct tcp_xa_pool { + u8 max; /* max <= MAX_SKB_FRAGS */ + u8 idx; /* idx <= max */ + __u32 tokens[MAX_SKB_FRAGS]; + netmem_ref netmems[MAX_SKB_FRAGS]; +}; + +static void tcp_xa_pool_commit_locked(struct sock *sk, struct tcp_xa_pool *p) +{ + int i; + + /* Commit part that has been copied to user space. */ + for (i = 0; i < p->idx; i++) + __xa_cmpxchg(&sk->sk_user_frags, p->tokens[i], XA_ZERO_ENTRY, + (__force void *)p->netmems[i], GFP_KERNEL); + /* Rollback what has been pre-allocated and is no longer needed. */ + for (; i < p->max; i++) + __xa_erase(&sk->sk_user_frags, p->tokens[i]); + + p->max = 0; + p->idx = 0; +} + +static void tcp_xa_pool_commit(struct sock *sk, struct tcp_xa_pool *p) +{ + if (!p->max) + return; + + xa_lock_bh(&sk->sk_user_frags); + + tcp_xa_pool_commit_locked(sk, p); + + xa_unlock_bh(&sk->sk_user_frags); +} + +static int tcp_xa_pool_refill(struct sock *sk, struct tcp_xa_pool *p, + unsigned int max_frags) +{ + int err, k; + + if (p->idx < p->max) + return 0; + + xa_lock_bh(&sk->sk_user_frags); + + tcp_xa_pool_commit_locked(sk, p); + + for (k = 0; k < max_frags; k++) { + err = __xa_alloc(&sk->sk_user_frags, &p->tokens[k], + XA_ZERO_ENTRY, xa_limit_31b, GFP_KERNEL); + if (err) + break; + } + + xa_unlock_bh(&sk->sk_user_frags); + + p->max = k; + p->idx = 0; + return k ? 0 : err; +} + +/* On error, returns the -errno. On success, returns number of bytes sent to the + * user. May not consume all of @remaining_len. + */ +static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb, + unsigned int offset, struct msghdr *msg, + int remaining_len) +{ + struct dmabuf_cmsg dmabuf_cmsg = { 0 }; + struct tcp_xa_pool tcp_xa_pool; + unsigned int start; + int i, copy, n; + int sent = 0; + int err = 0; + + tcp_xa_pool.max = 0; + tcp_xa_pool.idx = 0; + do { + start = skb_headlen(skb); + + if (skb_frags_readable(skb)) { + err = -ENODEV; + goto out; + } + + /* Copy header. */ + copy = start - offset; + if (copy > 0) { + copy = min(copy, remaining_len); + + n = copy_to_iter(skb->data + offset, copy, + &msg->msg_iter); + if (n != copy) { + err = -EFAULT; + goto out; + } + + offset += copy; + remaining_len -= copy; + + /* First a dmabuf_cmsg for # bytes copied to user + * buffer. + */ + memset(&dmabuf_cmsg, 0, sizeof(dmabuf_cmsg)); + dmabuf_cmsg.frag_size = copy; + err = put_cmsg(msg, SOL_SOCKET, SO_DEVMEM_LINEAR, + sizeof(dmabuf_cmsg), &dmabuf_cmsg); + if (err || msg->msg_flags & MSG_CTRUNC) { + msg->msg_flags &= ~MSG_CTRUNC; + if (!err) + err = -ETOOSMALL; + goto out; + } + + sent += copy; + + if (remaining_len == 0) + goto out; + } + + /* after that, send information of dmabuf pages through a + * sequence of cmsg + */ + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + struct net_iov *niov; + u64 frag_offset; + int end; + + /* !skb_frags_readable() should indicate that ALL the + * frags in this skb are dmabuf net_iovs. We're checking + * for that flag above, but also check individual frags + * here. If the tcp stack is not setting + * skb_frags_readable() correctly, we still don't want + * to crash here. + */ + if (!skb_frag_net_iov(frag)) { + net_err_ratelimited("Found non-dmabuf skb with net_iov"); + err = -ENODEV; + goto out; + } + + niov = skb_frag_net_iov(frag); + end = start + skb_frag_size(frag); + copy = end - offset; + + if (copy > 0) { + copy = min(copy, remaining_len); + + frag_offset = net_iov_virtual_addr(niov) + + skb_frag_off(frag) + offset - + start; + dmabuf_cmsg.frag_offset = frag_offset; + dmabuf_cmsg.frag_size = copy; + err = tcp_xa_pool_refill(sk, &tcp_xa_pool, + skb_shinfo(skb)->nr_frags - i); + if (err) + goto out; + + /* Will perform the exchange later */ + dmabuf_cmsg.frag_token = tcp_xa_pool.tokens[tcp_xa_pool.idx]; + dmabuf_cmsg.dmabuf_id = net_iov_binding_id(niov); + + offset += copy; + remaining_len -= copy; + + err = put_cmsg(msg, SOL_SOCKET, + SO_DEVMEM_DMABUF, + sizeof(dmabuf_cmsg), + &dmabuf_cmsg); + if (err || msg->msg_flags & MSG_CTRUNC) { + msg->msg_flags &= ~MSG_CTRUNC; + if (!err) + err = -ETOOSMALL; + goto out; + } + + atomic_long_inc(&niov->pp_ref_count); + tcp_xa_pool.netmems[tcp_xa_pool.idx++] = skb_frag_netmem(frag); + + sent += copy; + + if (remaining_len == 0) + goto out; + } + start = end; + } + + tcp_xa_pool_commit(sk, &tcp_xa_pool); + if (!remaining_len) + goto out; + + /* if remaining_len is not satisfied yet, we need to go to the + * next frag in the frag_list to satisfy remaining_len. + */ + skb = skb_shinfo(skb)->frag_list ?: skb->next; + + offset = offset - start; + } while (skb); + + if (remaining_len) { + err = -EFAULT; + goto out; + } + +out: + tcp_xa_pool_commit(sk, &tcp_xa_pool); + if (!sent) + sent = err; + + return sent; +} + /* * This routine copies from a sock struct into the user buffer. * @@ -2341,6 +2558,7 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, int *cmsg_flags) { struct tcp_sock *tp = tcp_sk(sk); + int last_copied_dmabuf = -1; /* uninitialized */ int copied = 0; u32 peek_seq; u32 *seq; @@ -2520,15 +2738,44 @@ found_ok_skb: } if (!(flags & MSG_TRUNC)) { - err = skb_copy_datagram_msg(skb, offset, msg, used); - if (err) { - /* Exception. Bailout! */ - if (!copied) - copied = -EFAULT; + if (last_copied_dmabuf != -1 && + last_copied_dmabuf != !skb_frags_readable(skb)) break; + + if (skb_frags_readable(skb)) { + err = skb_copy_datagram_msg(skb, offset, msg, + used); + if (err) { + /* Exception. Bailout! */ + if (!copied) + copied = -EFAULT; + break; + } + } else { + if (!(flags & MSG_SOCK_DEVMEM)) { + /* dmabuf skbs can only be received + * with the MSG_SOCK_DEVMEM flag. + */ + if (!copied) + copied = -EFAULT; + + break; + } + + err = tcp_recvmsg_dmabuf(sk, skb, offset, msg, + used); + if (err <= 0) { + if (!copied) + copied = -EFAULT; + + break; + } + used = err; } } + last_copied_dmabuf = !skb_frags_readable(skb); + WRITE_ONCE(*seq, *seq + used); copied += used; len -= used; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index eb631e66ee03..5afe5e57c89b 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -79,6 +79,7 @@ #include #include #include +#include #include #include @@ -2512,10 +2513,25 @@ static void tcp_md5sig_info_free_rcu(struct rcu_head *head) } #endif +static void tcp_release_user_frags(struct sock *sk) +{ +#ifdef CONFIG_PAGE_POOL + unsigned long index; + void *netmem; + + xa_for_each(&sk->sk_user_frags, index, netmem) + WARN_ON_ONCE(!napi_pp_put_page((__force netmem_ref)netmem)); +#endif +} + void tcp_v4_destroy_sock(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + tcp_release_user_frags(sk); + + xa_destroy(&sk->sk_user_frags); + trace_tcp_destroy_sock(sk); tcp_clear_xmit_timers(sk); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index ad562272db2e..bb1fe1ba867a 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -628,6 +628,8 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, __TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS); + xa_init_flags(&newsk->sk_user_frags, XA_FLAGS_ALLOC1); + return newsk; } EXPORT_SYMBOL(tcp_create_openreq_child); -- cgit v1.2.3 From aa58bec064ab16224645776ce8e0af2fee46136a Mon Sep 17 00:00:00 2001 From: Parthiban Veerasooran Date: Mon, 9 Sep 2024 13:55:02 +0530 Subject: net: ethernet: oa_tc6: implement register write operation Implement register write operation according to the control communication specified in the OPEN Alliance 10BASE-T1x MACPHY Serial Interface document. Control write commands are used by the SPI host to write registers within the MAC-PHY. Each control write commands are composed of a 32 bits control command header followed by register write data. The MAC-PHY ignores the final 32 bits of data from the SPI host at the end of the control write command. The write command and data is also echoed from the MAC-PHY back to the SPI host to enable the SPI host to identify which register write failed in the case of any bus errors. Control write commands can write either a single register or multiple consecutive registers. When multiple consecutive registers are written, the address is automatically post-incremented by the MAC-PHY. Writing to any unimplemented or undefined registers shall be ignored and yield no effect. Reviewed-by: Andrew Lunn Signed-off-by: Parthiban Veerasooran Link: https://patch.msgid.link/20240909082514.262942-3-Parthiban.Veerasooran@microchip.com Signed-off-by: Jakub Kicinski --- MAINTAINERS | 2 + drivers/net/ethernet/Kconfig | 11 ++ drivers/net/ethernet/Makefile | 1 + drivers/net/ethernet/oa_tc6.c | 242 ++++++++++++++++++++++++++++++++++++++++++ include/linux/oa_tc6.h | 17 +++ 5 files changed, 273 insertions(+) create mode 100644 drivers/net/ethernet/oa_tc6.c create mode 100644 include/linux/oa_tc6.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index c291fe45e191..6c2315c1297c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17118,6 +17118,8 @@ M: Parthiban Veerasooran L: netdev@vger.kernel.org S: Maintained F: Documentation/networking/oa-tc6-framework.rst +F: drivers/include/linux/oa_tc6.h +F: drivers/net/ethernet/oa_tc6.c OPEN FIRMWARE AND FLATTENED DEVICE TREE M: Rob Herring diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig index 0baac25db4f8..9a542e3c9b05 100644 --- a/drivers/net/ethernet/Kconfig +++ b/drivers/net/ethernet/Kconfig @@ -158,6 +158,17 @@ config ETHOC help Say Y here if you want to use the OpenCores 10/100 Mbps Ethernet MAC. +config OA_TC6 + tristate "OPEN Alliance TC6 10BASE-T1x MAC-PHY support" + depends on SPI + select PHYLIB + help + This library implements OPEN Alliance TC6 10BASE-T1x MAC-PHY + Serial Interface protocol for supporting 10BASE-T1x MAC-PHYs. + + To know the implementation details, refer documentation in + . + source "drivers/net/ethernet/packetengines/Kconfig" source "drivers/net/ethernet/pasemi/Kconfig" source "drivers/net/ethernet/pensando/Kconfig" diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile index c03203439c0e..99fa180dedb8 100644 --- a/drivers/net/ethernet/Makefile +++ b/drivers/net/ethernet/Makefile @@ -105,3 +105,4 @@ obj-$(CONFIG_NET_VENDOR_XILINX) += xilinx/ obj-$(CONFIG_NET_VENDOR_XIRCOM) += xircom/ obj-$(CONFIG_NET_VENDOR_SYNOPSYS) += synopsys/ obj-$(CONFIG_NET_VENDOR_PENSANDO) += pensando/ +obj-$(CONFIG_OA_TC6) += oa_tc6.o diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c new file mode 100644 index 000000000000..24e9fd92d717 --- /dev/null +++ b/drivers/net/ethernet/oa_tc6.c @@ -0,0 +1,242 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * OPEN Alliance 10BASE‑T1x MAC‑PHY Serial Interface framework + * + * Author: Parthiban Veerasooran + */ + +#include +#include + +/* Control command header */ +#define OA_TC6_CTRL_HEADER_DATA_NOT_CTRL BIT(31) +#define OA_TC6_CTRL_HEADER_WRITE_NOT_READ BIT(29) +#define OA_TC6_CTRL_HEADER_MEM_MAP_SELECTOR GENMASK(27, 24) +#define OA_TC6_CTRL_HEADER_ADDR GENMASK(23, 8) +#define OA_TC6_CTRL_HEADER_LENGTH GENMASK(7, 1) +#define OA_TC6_CTRL_HEADER_PARITY BIT(0) + +#define OA_TC6_CTRL_HEADER_SIZE 4 +#define OA_TC6_CTRL_REG_VALUE_SIZE 4 +#define OA_TC6_CTRL_IGNORED_SIZE 4 +#define OA_TC6_CTRL_MAX_REGISTERS 128 +#define OA_TC6_CTRL_SPI_BUF_SIZE (OA_TC6_CTRL_HEADER_SIZE +\ + (OA_TC6_CTRL_MAX_REGISTERS *\ + OA_TC6_CTRL_REG_VALUE_SIZE) +\ + OA_TC6_CTRL_IGNORED_SIZE) + +/* Internal structure for MAC-PHY drivers */ +struct oa_tc6 { + struct spi_device *spi; + struct mutex spi_ctrl_lock; /* Protects spi control transfer */ + void *spi_ctrl_tx_buf; + void *spi_ctrl_rx_buf; +}; + +enum oa_tc6_header_type { + OA_TC6_CTRL_HEADER, +}; + +enum oa_tc6_register_op { + OA_TC6_CTRL_REG_WRITE = 1, +}; + +static int oa_tc6_spi_transfer(struct oa_tc6 *tc6, + enum oa_tc6_header_type header_type, u16 length) +{ + struct spi_transfer xfer = { 0 }; + struct spi_message msg; + + xfer.tx_buf = tc6->spi_ctrl_tx_buf; + xfer.rx_buf = tc6->spi_ctrl_rx_buf; + xfer.len = length; + + spi_message_init(&msg); + spi_message_add_tail(&xfer, &msg); + + return spi_sync(tc6->spi, &msg); +} + +static int oa_tc6_get_parity(u32 p) +{ + /* Public domain code snippet, lifted from + * http://www-graphics.stanford.edu/~seander/bithacks.html + */ + p ^= p >> 1; + p ^= p >> 2; + p = (p & 0x11111111U) * 0x11111111U; + + /* Odd parity is used here */ + return !((p >> 28) & 1); +} + +static __be32 oa_tc6_prepare_ctrl_header(u32 addr, u8 length, + enum oa_tc6_register_op reg_op) +{ + u32 header; + + header = FIELD_PREP(OA_TC6_CTRL_HEADER_DATA_NOT_CTRL, + OA_TC6_CTRL_HEADER) | + FIELD_PREP(OA_TC6_CTRL_HEADER_WRITE_NOT_READ, reg_op) | + FIELD_PREP(OA_TC6_CTRL_HEADER_MEM_MAP_SELECTOR, addr >> 16) | + FIELD_PREP(OA_TC6_CTRL_HEADER_ADDR, addr) | + FIELD_PREP(OA_TC6_CTRL_HEADER_LENGTH, length - 1); + header |= FIELD_PREP(OA_TC6_CTRL_HEADER_PARITY, + oa_tc6_get_parity(header)); + + return cpu_to_be32(header); +} + +static void oa_tc6_update_ctrl_write_data(struct oa_tc6 *tc6, u32 value[], + u8 length) +{ + __be32 *tx_buf = tc6->spi_ctrl_tx_buf + OA_TC6_CTRL_HEADER_SIZE; + + for (int i = 0; i < length; i++) + *tx_buf++ = cpu_to_be32(value[i]); +} + +static u16 oa_tc6_calculate_ctrl_buf_size(u8 length) +{ + /* Control command consists 4 bytes header + 4 bytes register value for + * each register + 4 bytes ignored value. + */ + return OA_TC6_CTRL_HEADER_SIZE + OA_TC6_CTRL_REG_VALUE_SIZE * length + + OA_TC6_CTRL_IGNORED_SIZE; +} + +static void oa_tc6_prepare_ctrl_spi_buf(struct oa_tc6 *tc6, u32 address, + u32 value[], u8 length, + enum oa_tc6_register_op reg_op) +{ + __be32 *tx_buf = tc6->spi_ctrl_tx_buf; + + *tx_buf = oa_tc6_prepare_ctrl_header(address, length, reg_op); + + oa_tc6_update_ctrl_write_data(tc6, value, length); +} + +static int oa_tc6_check_ctrl_write_reply(struct oa_tc6 *tc6, u8 size) +{ + u8 *tx_buf = tc6->spi_ctrl_tx_buf; + u8 *rx_buf = tc6->spi_ctrl_rx_buf; + + rx_buf += OA_TC6_CTRL_IGNORED_SIZE; + + /* The echoed control write must match with the one that was + * transmitted. + */ + if (memcmp(tx_buf, rx_buf, size - OA_TC6_CTRL_IGNORED_SIZE)) + return -EPROTO; + + return 0; +} + +static int oa_tc6_perform_ctrl(struct oa_tc6 *tc6, u32 address, u32 value[], + u8 length, enum oa_tc6_register_op reg_op) +{ + u16 size; + int ret; + + /* Prepare control command and copy to SPI control buffer */ + oa_tc6_prepare_ctrl_spi_buf(tc6, address, value, length, reg_op); + + size = oa_tc6_calculate_ctrl_buf_size(length); + + /* Perform SPI transfer */ + ret = oa_tc6_spi_transfer(tc6, OA_TC6_CTRL_HEADER, size); + if (ret) { + dev_err(&tc6->spi->dev, "SPI transfer failed for control: %d\n", + ret); + return ret; + } + + /* Check echoed/received control write command reply for errors */ + return oa_tc6_check_ctrl_write_reply(tc6, size); +} + +/** + * oa_tc6_write_registers - function for writing multiple consecutive registers. + * @tc6: oa_tc6 struct. + * @address: address of the first register to be written in the MAC-PHY. + * @value: values to be written from the starting register address @address. + * @length: number of consecutive registers to be written from @address. + * + * Maximum of 128 consecutive registers can be written starting at @address. + * + * Return: 0 on success otherwise failed. + */ +int oa_tc6_write_registers(struct oa_tc6 *tc6, u32 address, u32 value[], + u8 length) +{ + int ret; + + if (!length || length > OA_TC6_CTRL_MAX_REGISTERS) { + dev_err(&tc6->spi->dev, "Invalid register length parameter\n"); + return -EINVAL; + } + + mutex_lock(&tc6->spi_ctrl_lock); + ret = oa_tc6_perform_ctrl(tc6, address, value, length, + OA_TC6_CTRL_REG_WRITE); + mutex_unlock(&tc6->spi_ctrl_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(oa_tc6_write_registers); + +/** + * oa_tc6_write_register - function for writing a MAC-PHY register. + * @tc6: oa_tc6 struct. + * @address: register address of the MAC-PHY to be written. + * @value: value to be written in the @address register address of the MAC-PHY. + * + * Return: 0 on success otherwise failed. + */ +int oa_tc6_write_register(struct oa_tc6 *tc6, u32 address, u32 value) +{ + return oa_tc6_write_registers(tc6, address, &value, 1); +} +EXPORT_SYMBOL_GPL(oa_tc6_write_register); + +/** + * oa_tc6_init - allocates and initializes oa_tc6 structure. + * @spi: device with which data will be exchanged. + * + * Return: pointer reference to the oa_tc6 structure if the MAC-PHY + * initialization is successful otherwise NULL. + */ +struct oa_tc6 *oa_tc6_init(struct spi_device *spi) +{ + struct oa_tc6 *tc6; + + tc6 = devm_kzalloc(&spi->dev, sizeof(*tc6), GFP_KERNEL); + if (!tc6) + return NULL; + + tc6->spi = spi; + mutex_init(&tc6->spi_ctrl_lock); + + /* Set the SPI controller to pump at realtime priority */ + tc6->spi->rt = true; + spi_setup(tc6->spi); + + tc6->spi_ctrl_tx_buf = devm_kzalloc(&tc6->spi->dev, + OA_TC6_CTRL_SPI_BUF_SIZE, + GFP_KERNEL); + if (!tc6->spi_ctrl_tx_buf) + return NULL; + + tc6->spi_ctrl_rx_buf = devm_kzalloc(&tc6->spi->dev, + OA_TC6_CTRL_SPI_BUF_SIZE, + GFP_KERNEL); + if (!tc6->spi_ctrl_rx_buf) + return NULL; + + return tc6; +} +EXPORT_SYMBOL_GPL(oa_tc6_init); + +MODULE_DESCRIPTION("OPEN Alliance 10BASE‑T1x MAC‑PHY Serial Interface Lib"); +MODULE_AUTHOR("Parthiban Veerasooran "); +MODULE_LICENSE("GPL"); diff --git a/include/linux/oa_tc6.h b/include/linux/oa_tc6.h new file mode 100644 index 000000000000..99c490f1c8a8 --- /dev/null +++ b/include/linux/oa_tc6.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * OPEN Alliance 10BASE‑T1x MAC‑PHY Serial Interface framework + * + * Link: https://opensig.org/download/document/OPEN_Alliance_10BASET1x_MAC-PHY_Serial_Interface_V1.1.pdf + * + * Author: Parthiban Veerasooran + */ + +#include + +struct oa_tc6; + +struct oa_tc6 *oa_tc6_init(struct spi_device *spi); +int oa_tc6_write_register(struct oa_tc6 *tc6, u32 address, u32 value); +int oa_tc6_write_registers(struct oa_tc6 *tc6, u32 address, u32 value[], + u8 length); -- cgit v1.2.3 From 375d1e0278cca70ce801d52c6b95c7a3c00f249c Mon Sep 17 00:00:00 2001 From: Parthiban Veerasooran Date: Mon, 9 Sep 2024 13:55:03 +0530 Subject: net: ethernet: oa_tc6: implement register read operation Implement register read operation according to the control communication specified in the OPEN Alliance 10BASE-T1x MACPHY Serial Interface document. Control read commands are used by the SPI host to read registers within the MAC-PHY. Each control read commands are composed of a 32 bits control command header. The MAC-PHY ignores all data from the SPI host following the control header for the remainder of the control read command. Control read commands can read either a single register or multiple consecutive registers. When multiple consecutive registers are read, the address is automatically post-incremented by the MAC-PHY. Reading any unimplemented or undefined registers shall return zero. Reviewed-by: Andrew Lunn Signed-off-by: Parthiban Veerasooran Link: https://patch.msgid.link/20240909082514.262942-4-Parthiban.Veerasooran@microchip.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/oa_tc6.c | 84 +++++++++++++++++++++++++++++++++++++++++-- include/linux/oa_tc6.h | 3 ++ 2 files changed, 85 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c index 24e9fd92d717..72bab9234436 100644 --- a/drivers/net/ethernet/oa_tc6.c +++ b/drivers/net/ethernet/oa_tc6.c @@ -38,6 +38,7 @@ enum oa_tc6_header_type { }; enum oa_tc6_register_op { + OA_TC6_CTRL_REG_READ = 0, OA_TC6_CTRL_REG_WRITE = 1, }; @@ -113,7 +114,8 @@ static void oa_tc6_prepare_ctrl_spi_buf(struct oa_tc6 *tc6, u32 address, *tx_buf = oa_tc6_prepare_ctrl_header(address, length, reg_op); - oa_tc6_update_ctrl_write_data(tc6, value, length); + if (reg_op == OA_TC6_CTRL_REG_WRITE) + oa_tc6_update_ctrl_write_data(tc6, value, length); } static int oa_tc6_check_ctrl_write_reply(struct oa_tc6 *tc6, u8 size) @@ -132,6 +134,30 @@ static int oa_tc6_check_ctrl_write_reply(struct oa_tc6 *tc6, u8 size) return 0; } +static int oa_tc6_check_ctrl_read_reply(struct oa_tc6 *tc6, u8 size) +{ + u32 *rx_buf = tc6->spi_ctrl_rx_buf + OA_TC6_CTRL_IGNORED_SIZE; + u32 *tx_buf = tc6->spi_ctrl_tx_buf; + + /* The echoed control read header must match with the one that was + * transmitted. + */ + if (*tx_buf != *rx_buf) + return -EPROTO; + + return 0; +} + +static void oa_tc6_copy_ctrl_read_data(struct oa_tc6 *tc6, u32 value[], + u8 length) +{ + __be32 *rx_buf = tc6->spi_ctrl_rx_buf + OA_TC6_CTRL_IGNORED_SIZE + + OA_TC6_CTRL_HEADER_SIZE; + + for (int i = 0; i < length; i++) + value[i] = be32_to_cpu(*rx_buf++); +} + static int oa_tc6_perform_ctrl(struct oa_tc6 *tc6, u32 address, u32 value[], u8 length, enum oa_tc6_register_op reg_op) { @@ -152,8 +178,62 @@ static int oa_tc6_perform_ctrl(struct oa_tc6 *tc6, u32 address, u32 value[], } /* Check echoed/received control write command reply for errors */ - return oa_tc6_check_ctrl_write_reply(tc6, size); + if (reg_op == OA_TC6_CTRL_REG_WRITE) + return oa_tc6_check_ctrl_write_reply(tc6, size); + + /* Check echoed/received control read command reply for errors */ + ret = oa_tc6_check_ctrl_read_reply(tc6, size); + if (ret) + return ret; + + oa_tc6_copy_ctrl_read_data(tc6, value, length); + + return 0; +} + +/** + * oa_tc6_read_registers - function for reading multiple consecutive registers. + * @tc6: oa_tc6 struct. + * @address: address of the first register to be read in the MAC-PHY. + * @value: values to be read from the starting register address @address. + * @length: number of consecutive registers to be read from @address. + * + * Maximum of 128 consecutive registers can be read starting at @address. + * + * Return: 0 on success otherwise failed. + */ +int oa_tc6_read_registers(struct oa_tc6 *tc6, u32 address, u32 value[], + u8 length) +{ + int ret; + + if (!length || length > OA_TC6_CTRL_MAX_REGISTERS) { + dev_err(&tc6->spi->dev, "Invalid register length parameter\n"); + return -EINVAL; + } + + mutex_lock(&tc6->spi_ctrl_lock); + ret = oa_tc6_perform_ctrl(tc6, address, value, length, + OA_TC6_CTRL_REG_READ); + mutex_unlock(&tc6->spi_ctrl_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(oa_tc6_read_registers); + +/** + * oa_tc6_read_register - function for reading a MAC-PHY register. + * @tc6: oa_tc6 struct. + * @address: register address of the MAC-PHY to be read. + * @value: value read from the @address register address of the MAC-PHY. + * + * Return: 0 on success otherwise failed. + */ +int oa_tc6_read_register(struct oa_tc6 *tc6, u32 address, u32 *value) +{ + return oa_tc6_read_registers(tc6, address, value, 1); } +EXPORT_SYMBOL_GPL(oa_tc6_read_register); /** * oa_tc6_write_registers - function for writing multiple consecutive registers. diff --git a/include/linux/oa_tc6.h b/include/linux/oa_tc6.h index 99c490f1c8a8..85aeecf87306 100644 --- a/include/linux/oa_tc6.h +++ b/include/linux/oa_tc6.h @@ -15,3 +15,6 @@ struct oa_tc6 *oa_tc6_init(struct spi_device *spi); int oa_tc6_write_register(struct oa_tc6 *tc6, u32 address, u32 value); int oa_tc6_write_registers(struct oa_tc6 *tc6, u32 address, u32 value[], u8 length); +int oa_tc6_read_register(struct oa_tc6 *tc6, u32 address, u32 *value); +int oa_tc6_read_registers(struct oa_tc6 *tc6, u32 address, u32 value[], + u8 length); -- cgit v1.2.3 From 8f9bf857e43b3f75a098e3af3a6fec2d03203a1e Mon Sep 17 00:00:00 2001 From: Parthiban Veerasooran Date: Mon, 9 Sep 2024 13:55:06 +0530 Subject: net: ethernet: oa_tc6: implement internal PHY initialization Internal PHY is initialized as per the PHY register capability supported by the MAC-PHY. Direct PHY Register Access Capability indicates if PHY registers are directly accessible within the SPI register memory space. Indirect PHY Register Access Capability indicates if PHY registers are indirectly accessible through the MDIO/MDC registers MDIOACCn defined in OPEN Alliance specification. Currently the direct register access is only supported. Reviewed-by: Andrew Lunn Signed-off-by: Parthiban Veerasooran Link: https://patch.msgid.link/20240909082514.262942-7-Parthiban.Veerasooran@microchip.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/oa_tc6.c | 230 +++++++++++++++++++++++++++++++++++++++++- include/linux/oa_tc6.h | 4 +- include/uapi/linux/mdio.h | 1 + 3 files changed, 233 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c index 86b032cdbee1..fc276d881dc9 100644 --- a/drivers/net/ethernet/oa_tc6.c +++ b/drivers/net/ethernet/oa_tc6.c @@ -7,9 +7,15 @@ #include #include +#include +#include #include /* OPEN Alliance TC6 registers */ +/* Standard Capabilities Register */ +#define OA_TC6_REG_STDCAP 0x0002 +#define STDCAP_DIRECT_PHY_REG_ACCESS BIT(8) + /* Reset Control and Status Register */ #define OA_TC6_REG_RESET 0x0003 #define RESET_SWRESET BIT(0) /* Software Reset */ @@ -25,6 +31,10 @@ #define INT_MASK0_RX_BUFFER_OVERFLOW_ERR_MASK BIT(3) #define INT_MASK0_TX_PROTOCOL_ERR_MASK BIT(0) +/* PHY Clause 22 registers base address and mask */ +#define OA_TC6_PHY_STD_REG_ADDR_BASE 0xFF00 +#define OA_TC6_PHY_STD_REG_ADDR_MASK 0x1F + /* Control command header */ #define OA_TC6_CTRL_HEADER_DATA_NOT_CTRL BIT(31) #define OA_TC6_CTRL_HEADER_WRITE_NOT_READ BIT(29) @@ -33,6 +43,15 @@ #define OA_TC6_CTRL_HEADER_LENGTH GENMASK(7, 1) #define OA_TC6_CTRL_HEADER_PARITY BIT(0) +/* PHY – Clause 45 registers memory map selector (MMS) as per table 6 in the + * OPEN Alliance specification. + */ +#define OA_TC6_PHY_C45_PCS_MMS2 2 /* MMD 3 */ +#define OA_TC6_PHY_C45_PMA_PMD_MMS3 3 /* MMD 1 */ +#define OA_TC6_PHY_C45_VS_PLCA_MMS4 4 /* MMD 31 */ +#define OA_TC6_PHY_C45_AUTO_NEG_MMS5 5 /* MMD 7 */ +#define OA_TC6_PHY_C45_POWER_UNIT_MMS6 6 /* MMD 13 */ + #define OA_TC6_CTRL_HEADER_SIZE 4 #define OA_TC6_CTRL_REG_VALUE_SIZE 4 #define OA_TC6_CTRL_IGNORED_SIZE 4 @@ -46,6 +65,10 @@ /* Internal structure for MAC-PHY drivers */ struct oa_tc6 { + struct device *dev; + struct net_device *netdev; + struct phy_device *phydev; + struct mii_bus *mdiobus; struct spi_device *spi; struct mutex spi_ctrl_lock; /* Protects spi control transfer */ void *spi_ctrl_tx_buf; @@ -298,6 +321,191 @@ int oa_tc6_write_register(struct oa_tc6 *tc6, u32 address, u32 value) } EXPORT_SYMBOL_GPL(oa_tc6_write_register); +static int oa_tc6_check_phy_reg_direct_access_capability(struct oa_tc6 *tc6) +{ + u32 regval; + int ret; + + ret = oa_tc6_read_register(tc6, OA_TC6_REG_STDCAP, ®val); + if (ret) + return ret; + + if (!(regval & STDCAP_DIRECT_PHY_REG_ACCESS)) + return -ENODEV; + + return 0; +} + +static void oa_tc6_handle_link_change(struct net_device *netdev) +{ + phy_print_status(netdev->phydev); +} + +static int oa_tc6_mdiobus_read(struct mii_bus *bus, int addr, int regnum) +{ + struct oa_tc6 *tc6 = bus->priv; + u32 regval; + bool ret; + + ret = oa_tc6_read_register(tc6, OA_TC6_PHY_STD_REG_ADDR_BASE | + (regnum & OA_TC6_PHY_STD_REG_ADDR_MASK), + ®val); + if (ret) + return ret; + + return regval; +} + +static int oa_tc6_mdiobus_write(struct mii_bus *bus, int addr, int regnum, + u16 val) +{ + struct oa_tc6 *tc6 = bus->priv; + + return oa_tc6_write_register(tc6, OA_TC6_PHY_STD_REG_ADDR_BASE | + (regnum & OA_TC6_PHY_STD_REG_ADDR_MASK), + val); +} + +static int oa_tc6_get_phy_c45_mms(int devnum) +{ + switch (devnum) { + case MDIO_MMD_PCS: + return OA_TC6_PHY_C45_PCS_MMS2; + case MDIO_MMD_PMAPMD: + return OA_TC6_PHY_C45_PMA_PMD_MMS3; + case MDIO_MMD_VEND2: + return OA_TC6_PHY_C45_VS_PLCA_MMS4; + case MDIO_MMD_AN: + return OA_TC6_PHY_C45_AUTO_NEG_MMS5; + case MDIO_MMD_POWER_UNIT: + return OA_TC6_PHY_C45_POWER_UNIT_MMS6; + default: + return -EOPNOTSUPP; + } +} + +static int oa_tc6_mdiobus_read_c45(struct mii_bus *bus, int addr, int devnum, + int regnum) +{ + struct oa_tc6 *tc6 = bus->priv; + u32 regval; + int ret; + + ret = oa_tc6_get_phy_c45_mms(devnum); + if (ret < 0) + return ret; + + ret = oa_tc6_read_register(tc6, (ret << 16) | regnum, ®val); + if (ret) + return ret; + + return regval; +} + +static int oa_tc6_mdiobus_write_c45(struct mii_bus *bus, int addr, int devnum, + int regnum, u16 val) +{ + struct oa_tc6 *tc6 = bus->priv; + int ret; + + ret = oa_tc6_get_phy_c45_mms(devnum); + if (ret < 0) + return ret; + + return oa_tc6_write_register(tc6, (ret << 16) | regnum, val); +} + +static int oa_tc6_mdiobus_register(struct oa_tc6 *tc6) +{ + int ret; + + tc6->mdiobus = mdiobus_alloc(); + if (!tc6->mdiobus) { + netdev_err(tc6->netdev, "MDIO bus alloc failed\n"); + return -ENOMEM; + } + + tc6->mdiobus->priv = tc6; + tc6->mdiobus->read = oa_tc6_mdiobus_read; + tc6->mdiobus->write = oa_tc6_mdiobus_write; + /* OPEN Alliance 10BASE-T1x compliance MAC-PHYs will have both C22 and + * C45 registers space. If the PHY is discovered via C22 bus protocol it + * assumes it uses C22 protocol and always uses C22 registers indirect + * access to access C45 registers. This is because, we don't have a + * clean separation between C22/C45 register space and C22/C45 MDIO bus + * protocols. Resulting, PHY C45 registers direct access can't be used + * which can save multiple SPI bus access. To support this feature, PHY + * drivers can set .read_mmd/.write_mmd in the PHY driver to call + * .read_c45/.write_c45. Ex: drivers/net/phy/microchip_t1s.c + */ + tc6->mdiobus->read_c45 = oa_tc6_mdiobus_read_c45; + tc6->mdiobus->write_c45 = oa_tc6_mdiobus_write_c45; + tc6->mdiobus->name = "oa-tc6-mdiobus"; + tc6->mdiobus->parent = tc6->dev; + + snprintf(tc6->mdiobus->id, ARRAY_SIZE(tc6->mdiobus->id), "%s", + dev_name(&tc6->spi->dev)); + + ret = mdiobus_register(tc6->mdiobus); + if (ret) { + netdev_err(tc6->netdev, "Could not register MDIO bus\n"); + mdiobus_free(tc6->mdiobus); + return ret; + } + + return 0; +} + +static void oa_tc6_mdiobus_unregister(struct oa_tc6 *tc6) +{ + mdiobus_unregister(tc6->mdiobus); + mdiobus_free(tc6->mdiobus); +} + +static int oa_tc6_phy_init(struct oa_tc6 *tc6) +{ + int ret; + + ret = oa_tc6_check_phy_reg_direct_access_capability(tc6); + if (ret) { + netdev_err(tc6->netdev, + "Direct PHY register access is not supported by the MAC-PHY\n"); + return ret; + } + + ret = oa_tc6_mdiobus_register(tc6); + if (ret) + return ret; + + tc6->phydev = phy_find_first(tc6->mdiobus); + if (!tc6->phydev) { + netdev_err(tc6->netdev, "No PHY found\n"); + oa_tc6_mdiobus_unregister(tc6); + return -ENODEV; + } + + tc6->phydev->is_internal = true; + ret = phy_connect_direct(tc6->netdev, tc6->phydev, + &oa_tc6_handle_link_change, + PHY_INTERFACE_MODE_INTERNAL); + if (ret) { + netdev_err(tc6->netdev, "Can't attach PHY to %s\n", + tc6->mdiobus->id); + oa_tc6_mdiobus_unregister(tc6); + return ret; + } + + phy_attached_info(tc6->netdev->phydev); + + return 0; +} + +static void oa_tc6_phy_exit(struct oa_tc6 *tc6) +{ + phy_disconnect(tc6->phydev); + oa_tc6_mdiobus_unregister(tc6); +} + static int oa_tc6_read_status0(struct oa_tc6 *tc6) { u32 regval; @@ -354,11 +562,12 @@ static int oa_tc6_unmask_macphy_error_interrupts(struct oa_tc6 *tc6) /** * oa_tc6_init - allocates and initializes oa_tc6 structure. * @spi: device with which data will be exchanged. + * @netdev: network device interface structure. * * Return: pointer reference to the oa_tc6 structure if the MAC-PHY * initialization is successful otherwise NULL. */ -struct oa_tc6 *oa_tc6_init(struct spi_device *spi) +struct oa_tc6 *oa_tc6_init(struct spi_device *spi, struct net_device *netdev) { struct oa_tc6 *tc6; int ret; @@ -368,6 +577,8 @@ struct oa_tc6 *oa_tc6_init(struct spi_device *spi) return NULL; tc6->spi = spi; + tc6->netdev = netdev; + SET_NETDEV_DEV(netdev, &spi->dev); mutex_init(&tc6->spi_ctrl_lock); /* Set the SPI controller to pump at realtime priority */ @@ -400,10 +611,27 @@ struct oa_tc6 *oa_tc6_init(struct spi_device *spi) return NULL; } + ret = oa_tc6_phy_init(tc6); + if (ret) { + dev_err(&tc6->spi->dev, + "MAC internal PHY initialization failed: %d\n", ret); + return NULL; + } + return tc6; } EXPORT_SYMBOL_GPL(oa_tc6_init); +/** + * oa_tc6_exit - exit function. + * @tc6: oa_tc6 struct. + */ +void oa_tc6_exit(struct oa_tc6 *tc6) +{ + oa_tc6_phy_exit(tc6); +} +EXPORT_SYMBOL_GPL(oa_tc6_exit); + MODULE_DESCRIPTION("OPEN Alliance 10BASE‑T1x MAC‑PHY Serial Interface Lib"); MODULE_AUTHOR("Parthiban Veerasooran "); MODULE_LICENSE("GPL"); diff --git a/include/linux/oa_tc6.h b/include/linux/oa_tc6.h index 85aeecf87306..606ba9f1e663 100644 --- a/include/linux/oa_tc6.h +++ b/include/linux/oa_tc6.h @@ -7,11 +7,13 @@ * Author: Parthiban Veerasooran */ +#include #include struct oa_tc6; -struct oa_tc6 *oa_tc6_init(struct spi_device *spi); +struct oa_tc6 *oa_tc6_init(struct spi_device *spi, struct net_device *netdev); +void oa_tc6_exit(struct oa_tc6 *tc6); int oa_tc6_write_register(struct oa_tc6 *tc6, u32 address, u32 value); int oa_tc6_write_registers(struct oa_tc6 *tc6, u32 address, u32 value[], u8 length); diff --git a/include/uapi/linux/mdio.h b/include/uapi/linux/mdio.h index c0c8ec995b06..f0d3f268240d 100644 --- a/include/uapi/linux/mdio.h +++ b/include/uapi/linux/mdio.h @@ -23,6 +23,7 @@ #define MDIO_MMD_DTEXS 5 /* DTE Extender Sublayer */ #define MDIO_MMD_TC 6 /* Transmission Convergence */ #define MDIO_MMD_AN 7 /* Auto-Negotiation */ +#define MDIO_MMD_POWER_UNIT 13 /* PHY Power Unit */ #define MDIO_MMD_C22EXT 29 /* Clause 22 extension */ #define MDIO_MMD_VEND1 30 /* Vendor specific 1 */ #define MDIO_MMD_VEND2 31 /* Vendor specific 2 */ -- cgit v1.2.3 From 53fbde8ab21e8c2c6187159cc17fc10cbf20900a Mon Sep 17 00:00:00 2001 From: Parthiban Veerasooran Date: Mon, 9 Sep 2024 13:55:09 +0530 Subject: net: ethernet: oa_tc6: implement transmit path to transfer tx ethernet frames The transmit ethernet frame will be converted into multiple transmit data chunks. Each transmit data chunk consists of a 4 bytes header followed by a 64 bytes transmit data chunk payload. The 4 bytes data header occurs at the beginning of each transmit data chunk on MOSI. The data header contains the information needed to determine the validity and location of the transmit frame data within the data chunk payload. The number of transmit data chunks transmitted to mac-phy is limited to the number transmit credits available in the mac-phy. Initially the transmit credits will be updated from the buffer status register and then it will be updated from the footer received on each spi data transfer. The received footer will be examined for the transmit errors if any. Reviewed-by: Andrew Lunn Signed-off-by: Parthiban Veerasooran Link: https://patch.msgid.link/20240909082514.262942-10-Parthiban.Veerasooran@microchip.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/oa_tc6.c | 399 +++++++++++++++++++++++++++++++++++++++++- include/linux/oa_tc6.h | 1 + 2 files changed, 398 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c index 8958af863b6e..bbc4b7fce64c 100644 --- a/drivers/net/ethernet/oa_tc6.c +++ b/drivers/net/ethernet/oa_tc6.c @@ -27,6 +27,13 @@ /* Status Register #0 */ #define OA_TC6_REG_STATUS0 0x0008 #define STATUS0_RESETC BIT(6) /* Reset Complete */ +#define STATUS0_HEADER_ERROR BIT(5) +#define STATUS0_LOSS_OF_FRAME_ERROR BIT(4) +#define STATUS0_TX_PROTOCOL_ERROR BIT(0) + +/* Buffer Status Register */ +#define OA_TC6_REG_BUFFER_STATUS 0x000B +#define BUFFER_STATUS_TX_CREDITS_AVAILABLE GENMASK(15, 8) /* Interrupt Mask Register #0 */ #define OA_TC6_REG_INT_MASK0 0x000C @@ -47,6 +54,21 @@ #define OA_TC6_CTRL_HEADER_LENGTH GENMASK(7, 1) #define OA_TC6_CTRL_HEADER_PARITY BIT(0) +/* Data header */ +#define OA_TC6_DATA_HEADER_DATA_NOT_CTRL BIT(31) +#define OA_TC6_DATA_HEADER_DATA_VALID BIT(21) +#define OA_TC6_DATA_HEADER_START_VALID BIT(20) +#define OA_TC6_DATA_HEADER_START_WORD_OFFSET GENMASK(19, 16) +#define OA_TC6_DATA_HEADER_END_VALID BIT(14) +#define OA_TC6_DATA_HEADER_END_BYTE_OFFSET GENMASK(13, 8) +#define OA_TC6_DATA_HEADER_PARITY BIT(0) + +/* Data footer */ +#define OA_TC6_DATA_FOOTER_EXTENDED_STS BIT(31) +#define OA_TC6_DATA_FOOTER_RXD_HEADER_BAD BIT(30) +#define OA_TC6_DATA_FOOTER_CONFIG_SYNC BIT(29) +#define OA_TC6_DATA_FOOTER_TX_CREDITS GENMASK(5, 1) + /* PHY – Clause 45 registers memory map selector (MMS) as per table 6 in the * OPEN Alliance specification. */ @@ -64,6 +86,13 @@ (OA_TC6_CTRL_MAX_REGISTERS *\ OA_TC6_CTRL_REG_VALUE_SIZE) +\ OA_TC6_CTRL_IGNORED_SIZE) +#define OA_TC6_CHUNK_PAYLOAD_SIZE 64 +#define OA_TC6_DATA_HEADER_SIZE 4 +#define OA_TC6_CHUNK_SIZE (OA_TC6_DATA_HEADER_SIZE +\ + OA_TC6_CHUNK_PAYLOAD_SIZE) +#define OA_TC6_MAX_TX_CHUNKS 48 +#define OA_TC6_SPI_DATA_BUF_SIZE (OA_TC6_MAX_TX_CHUNKS *\ + OA_TC6_CHUNK_SIZE) #define STATUS0_RESETC_POLL_DELAY 1000 #define STATUS0_RESETC_POLL_TIMEOUT 1000000 @@ -77,10 +106,20 @@ struct oa_tc6 { struct mutex spi_ctrl_lock; /* Protects spi control transfer */ void *spi_ctrl_tx_buf; void *spi_ctrl_rx_buf; + void *spi_data_tx_buf; + void *spi_data_rx_buf; + struct sk_buff *ongoing_tx_skb; + struct sk_buff *waiting_tx_skb; + struct task_struct *spi_thread; + wait_queue_head_t spi_wq; + u16 tx_skb_offset; + u16 spi_data_tx_buf_offset; + u16 tx_credits; }; enum oa_tc6_header_type { OA_TC6_CTRL_HEADER, + OA_TC6_DATA_HEADER, }; enum oa_tc6_register_op { @@ -88,14 +127,34 @@ enum oa_tc6_register_op { OA_TC6_CTRL_REG_WRITE = 1, }; +enum oa_tc6_data_valid_info { + OA_TC6_DATA_INVALID, + OA_TC6_DATA_VALID, +}; + +enum oa_tc6_data_start_valid_info { + OA_TC6_DATA_START_INVALID, + OA_TC6_DATA_START_VALID, +}; + +enum oa_tc6_data_end_valid_info { + OA_TC6_DATA_END_INVALID, + OA_TC6_DATA_END_VALID, +}; + static int oa_tc6_spi_transfer(struct oa_tc6 *tc6, enum oa_tc6_header_type header_type, u16 length) { struct spi_transfer xfer = { 0 }; struct spi_message msg; - xfer.tx_buf = tc6->spi_ctrl_tx_buf; - xfer.rx_buf = tc6->spi_ctrl_rx_buf; + if (header_type == OA_TC6_DATA_HEADER) { + xfer.tx_buf = tc6->spi_data_tx_buf; + xfer.rx_buf = tc6->spi_data_rx_buf; + } else { + xfer.tx_buf = tc6->spi_ctrl_tx_buf; + xfer.rx_buf = tc6->spi_ctrl_rx_buf; + } xfer.len = length; spi_message_init(&msg); @@ -578,6 +637,309 @@ static int oa_tc6_enable_data_transfer(struct oa_tc6 *tc6) return oa_tc6_write_register(tc6, OA_TC6_REG_CONFIG0, value); } +static void oa_tc6_cleanup_ongoing_tx_skb(struct oa_tc6 *tc6) +{ + if (tc6->ongoing_tx_skb) { + tc6->netdev->stats.tx_dropped++; + kfree_skb(tc6->ongoing_tx_skb); + tc6->ongoing_tx_skb = NULL; + } +} + +static int oa_tc6_process_extended_status(struct oa_tc6 *tc6) +{ + u32 value; + int ret; + + ret = oa_tc6_read_register(tc6, OA_TC6_REG_STATUS0, &value); + if (ret) { + netdev_err(tc6->netdev, "STATUS0 register read failed: %d\n", + ret); + return ret; + } + + /* Clear the error interrupts status */ + ret = oa_tc6_write_register(tc6, OA_TC6_REG_STATUS0, value); + if (ret) { + netdev_err(tc6->netdev, "STATUS0 register write failed: %d\n", + ret); + return ret; + } + + if (FIELD_GET(STATUS0_TX_PROTOCOL_ERROR, value)) { + netdev_err(tc6->netdev, "Transmit protocol error\n"); + return -ENODEV; + } + /* TODO: Currently loss of frame and header errors are treated as + * non-recoverable errors. They will be handled in the next version. + */ + if (FIELD_GET(STATUS0_LOSS_OF_FRAME_ERROR, value)) { + netdev_err(tc6->netdev, "Loss of frame error\n"); + return -ENODEV; + } + if (FIELD_GET(STATUS0_HEADER_ERROR, value)) { + netdev_err(tc6->netdev, "Header error\n"); + return -ENODEV; + } + + return 0; +} + +static int oa_tc6_process_rx_chunk_footer(struct oa_tc6 *tc6, u32 footer) +{ + /* Process rx chunk footer for the following, + * 1. tx credits + * 2. errors if any from MAC-PHY + */ + tc6->tx_credits = FIELD_GET(OA_TC6_DATA_FOOTER_TX_CREDITS, footer); + + if (FIELD_GET(OA_TC6_DATA_FOOTER_EXTENDED_STS, footer)) { + int ret = oa_tc6_process_extended_status(tc6); + + if (ret) + return ret; + } + + /* TODO: Currently received header bad and configuration unsync errors + * are treated as non-recoverable errors. They will be handled in the + * next version. + */ + if (FIELD_GET(OA_TC6_DATA_FOOTER_RXD_HEADER_BAD, footer)) { + netdev_err(tc6->netdev, "Rxd header bad error\n"); + return -ENODEV; + } + + if (!FIELD_GET(OA_TC6_DATA_FOOTER_CONFIG_SYNC, footer)) { + netdev_err(tc6->netdev, "Config unsync error\n"); + return -ENODEV; + } + + return 0; +} + +static u32 oa_tc6_get_rx_chunk_footer(struct oa_tc6 *tc6, u16 footer_offset) +{ + u8 *rx_buf = tc6->spi_data_rx_buf; + __be32 footer; + + footer = *((__be32 *)&rx_buf[footer_offset]); + + return be32_to_cpu(footer); +} + +static int oa_tc6_process_spi_data_rx_buf(struct oa_tc6 *tc6, u16 length) +{ + u16 no_of_rx_chunks = length / OA_TC6_CHUNK_SIZE; + u32 footer; + int ret; + + /* All the rx chunks in the receive SPI data buffer are examined here */ + for (int i = 0; i < no_of_rx_chunks; i++) { + /* Last 4 bytes in each received chunk consist footer info */ + footer = oa_tc6_get_rx_chunk_footer(tc6, i * OA_TC6_CHUNK_SIZE + + OA_TC6_CHUNK_PAYLOAD_SIZE); + + ret = oa_tc6_process_rx_chunk_footer(tc6, footer); + if (ret) + return ret; + } + + return 0; +} + +static __be32 oa_tc6_prepare_data_header(bool data_valid, bool start_valid, + bool end_valid, u8 end_byte_offset) +{ + u32 header = FIELD_PREP(OA_TC6_DATA_HEADER_DATA_NOT_CTRL, + OA_TC6_DATA_HEADER) | + FIELD_PREP(OA_TC6_DATA_HEADER_DATA_VALID, data_valid) | + FIELD_PREP(OA_TC6_DATA_HEADER_START_VALID, start_valid) | + FIELD_PREP(OA_TC6_DATA_HEADER_END_VALID, end_valid) | + FIELD_PREP(OA_TC6_DATA_HEADER_END_BYTE_OFFSET, + end_byte_offset); + + header |= FIELD_PREP(OA_TC6_DATA_HEADER_PARITY, + oa_tc6_get_parity(header)); + + return cpu_to_be32(header); +} + +static void oa_tc6_add_tx_skb_to_spi_buf(struct oa_tc6 *tc6) +{ + enum oa_tc6_data_end_valid_info end_valid = OA_TC6_DATA_END_INVALID; + __be32 *tx_buf = tc6->spi_data_tx_buf + tc6->spi_data_tx_buf_offset; + u16 remaining_len = tc6->ongoing_tx_skb->len - tc6->tx_skb_offset; + u8 *tx_skb_data = tc6->ongoing_tx_skb->data + tc6->tx_skb_offset; + enum oa_tc6_data_start_valid_info start_valid; + u8 end_byte_offset = 0; + u16 length_to_copy; + + /* Initial value is assigned here to avoid more than 80 characters in + * the declaration place. + */ + start_valid = OA_TC6_DATA_START_INVALID; + + /* Set start valid if the current tx chunk contains the start of the tx + * ethernet frame. + */ + if (!tc6->tx_skb_offset) + start_valid = OA_TC6_DATA_START_VALID; + + /* If the remaining tx skb length is more than the chunk payload size of + * 64 bytes then copy only 64 bytes and leave the ongoing tx skb for + * next tx chunk. + */ + length_to_copy = min_t(u16, remaining_len, OA_TC6_CHUNK_PAYLOAD_SIZE); + + /* Copy the tx skb data to the tx chunk payload buffer */ + memcpy(tx_buf + 1, tx_skb_data, length_to_copy); + tc6->tx_skb_offset += length_to_copy; + + /* Set end valid if the current tx chunk contains the end of the tx + * ethernet frame. + */ + if (tc6->ongoing_tx_skb->len == tc6->tx_skb_offset) { + end_valid = OA_TC6_DATA_END_VALID; + end_byte_offset = length_to_copy - 1; + tc6->tx_skb_offset = 0; + tc6->netdev->stats.tx_bytes += tc6->ongoing_tx_skb->len; + tc6->netdev->stats.tx_packets++; + kfree_skb(tc6->ongoing_tx_skb); + tc6->ongoing_tx_skb = NULL; + } + + *tx_buf = oa_tc6_prepare_data_header(OA_TC6_DATA_VALID, start_valid, + end_valid, end_byte_offset); + tc6->spi_data_tx_buf_offset += OA_TC6_CHUNK_SIZE; +} + +static u16 oa_tc6_prepare_spi_tx_buf_for_tx_skbs(struct oa_tc6 *tc6) +{ + u16 used_tx_credits; + + /* Get tx skbs and convert them into tx chunks based on the tx credits + * available. + */ + for (used_tx_credits = 0; used_tx_credits < tc6->tx_credits; + used_tx_credits++) { + if (!tc6->ongoing_tx_skb) { + tc6->ongoing_tx_skb = tc6->waiting_tx_skb; + tc6->waiting_tx_skb = NULL; + } + if (!tc6->ongoing_tx_skb) + break; + oa_tc6_add_tx_skb_to_spi_buf(tc6); + } + + return used_tx_credits * OA_TC6_CHUNK_SIZE; +} + +static int oa_tc6_try_spi_transfer(struct oa_tc6 *tc6) +{ + int ret; + + while (true) { + u16 spi_length = 0; + + tc6->spi_data_tx_buf_offset = 0; + + if (tc6->ongoing_tx_skb || tc6->waiting_tx_skb) + spi_length = oa_tc6_prepare_spi_tx_buf_for_tx_skbs(tc6); + + if (spi_length == 0) + break; + + ret = oa_tc6_spi_transfer(tc6, OA_TC6_DATA_HEADER, spi_length); + if (ret) { + netdev_err(tc6->netdev, "SPI data transfer failed: %d\n", + ret); + return ret; + } + + ret = oa_tc6_process_spi_data_rx_buf(tc6, spi_length); + if (ret) { + oa_tc6_cleanup_ongoing_tx_skb(tc6); + netdev_err(tc6->netdev, "Device error: %d\n", ret); + return ret; + } + + if (!tc6->waiting_tx_skb && netif_queue_stopped(tc6->netdev)) + netif_wake_queue(tc6->netdev); + } + + return 0; +} + +static int oa_tc6_spi_thread_handler(void *data) +{ + struct oa_tc6 *tc6 = data; + int ret; + + while (likely(!kthread_should_stop())) { + /* This kthread will be waken up if there is a tx skb */ + wait_event_interruptible(tc6->spi_wq, tc6->waiting_tx_skb || + kthread_should_stop()); + + if (kthread_should_stop()) + break; + + ret = oa_tc6_try_spi_transfer(tc6); + if (ret) + return ret; + } + + return 0; +} + +static int oa_tc6_update_buffer_status_from_register(struct oa_tc6 *tc6) +{ + u32 value; + int ret; + + /* Initially tx credits to be updated from the register as there is no + * data transfer performed yet. Later it will be updated from the rx + * footer. + */ + ret = oa_tc6_read_register(tc6, OA_TC6_REG_BUFFER_STATUS, &value); + if (ret) + return ret; + + tc6->tx_credits = FIELD_GET(BUFFER_STATUS_TX_CREDITS_AVAILABLE, value); + + return 0; +} + +/** + * oa_tc6_start_xmit - function for sending the tx skb which consists ethernet + * frame. + * @tc6: oa_tc6 struct. + * @skb: socket buffer in which the ethernet frame is stored. + * + * Return: NETDEV_TX_OK if the transmit ethernet frame skb added in the tx_skb_q + * otherwise returns NETDEV_TX_BUSY. + */ +netdev_tx_t oa_tc6_start_xmit(struct oa_tc6 *tc6, struct sk_buff *skb) +{ + if (tc6->waiting_tx_skb) { + netif_stop_queue(tc6->netdev); + return NETDEV_TX_BUSY; + } + + if (skb_linearize(skb)) { + dev_kfree_skb_any(skb); + tc6->netdev->stats.tx_dropped++; + return NETDEV_TX_OK; + } + + tc6->waiting_tx_skb = skb; + + /* Wake spi kthread to perform spi transfer */ + wake_up_interruptible(&tc6->spi_wq); + + return NETDEV_TX_OK; +} +EXPORT_SYMBOL_GPL(oa_tc6_start_xmit); + /** * oa_tc6_init - allocates and initializes oa_tc6 structure. * @spi: device with which data will be exchanged. @@ -616,6 +978,18 @@ struct oa_tc6 *oa_tc6_init(struct spi_device *spi, struct net_device *netdev) if (!tc6->spi_ctrl_rx_buf) return NULL; + tc6->spi_data_tx_buf = devm_kzalloc(&tc6->spi->dev, + OA_TC6_SPI_DATA_BUF_SIZE, + GFP_KERNEL); + if (!tc6->spi_data_tx_buf) + return NULL; + + tc6->spi_data_rx_buf = devm_kzalloc(&tc6->spi->dev, + OA_TC6_SPI_DATA_BUF_SIZE, + GFP_KERNEL); + if (!tc6->spi_data_rx_buf) + return NULL; + ret = oa_tc6_sw_reset_macphy(tc6); if (ret) { dev_err(&tc6->spi->dev, @@ -644,6 +1018,24 @@ struct oa_tc6 *oa_tc6_init(struct spi_device *spi, struct net_device *netdev) goto phy_exit; } + ret = oa_tc6_update_buffer_status_from_register(tc6); + if (ret) { + dev_err(&tc6->spi->dev, + "Failed to update buffer status: %d\n", ret); + goto phy_exit; + } + + init_waitqueue_head(&tc6->spi_wq); + + tc6->spi_thread = kthread_run(oa_tc6_spi_thread_handler, tc6, + "oa-tc6-spi-thread"); + if (IS_ERR(tc6->spi_thread)) { + dev_err(&tc6->spi->dev, "Failed to create SPI thread\n"); + goto phy_exit; + } + + sched_set_fifo(tc6->spi_thread); + return tc6; phy_exit: @@ -659,6 +1051,9 @@ EXPORT_SYMBOL_GPL(oa_tc6_init); void oa_tc6_exit(struct oa_tc6 *tc6) { oa_tc6_phy_exit(tc6); + kthread_stop(tc6->spi_thread); + dev_kfree_skb_any(tc6->ongoing_tx_skb); + dev_kfree_skb_any(tc6->waiting_tx_skb); } EXPORT_SYMBOL_GPL(oa_tc6_exit); diff --git a/include/linux/oa_tc6.h b/include/linux/oa_tc6.h index 606ba9f1e663..5c7811ac9cbe 100644 --- a/include/linux/oa_tc6.h +++ b/include/linux/oa_tc6.h @@ -20,3 +20,4 @@ int oa_tc6_write_registers(struct oa_tc6 *tc6, u32 address, u32 value[], int oa_tc6_read_register(struct oa_tc6 *tc6, u32 address, u32 *value); int oa_tc6_read_registers(struct oa_tc6 *tc6, u32 address, u32 value[], u8 length); +netdev_tx_t oa_tc6_start_xmit(struct oa_tc6 *tc6, struct sk_buff *skb); -- cgit v1.2.3 From afd42170c8a6e68edd3f3a7f2aacd2bfbedb58b2 Mon Sep 17 00:00:00 2001 From: Parthiban Veerasooran Date: Mon, 9 Sep 2024 13:55:12 +0530 Subject: net: ethernet: oa_tc6: add helper function to enable zero align rx frame Zero align receive frame feature can be enabled to align all receive ethernet frames data to start at the beginning of any receive data chunk payload with a start word offset (SWO) of zero. Receive frames may begin anywhere within the receive data chunk payload when this feature is not enabled. Reviewed-by: Andrew Lunn Signed-off-by: Parthiban Veerasooran Link: https://patch.msgid.link/20240909082514.262942-13-Parthiban.Veerasooran@microchip.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/oa_tc6.c | 24 ++++++++++++++++++++++++ include/linux/oa_tc6.h | 1 + 2 files changed, 25 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c index d3510dc19273..f9c0dcd965c2 100644 --- a/drivers/net/ethernet/oa_tc6.c +++ b/drivers/net/ethernet/oa_tc6.c @@ -23,6 +23,7 @@ /* Configuration Register #0 */ #define OA_TC6_REG_CONFIG0 0x0004 #define CONFIG0_SYNC BIT(15) +#define CONFIG0_ZARFE_ENABLE BIT(12) /* Status Register #0 */ #define OA_TC6_REG_STATUS0 0x0008 @@ -1163,6 +1164,29 @@ static irqreturn_t oa_tc6_macphy_isr(int irq, void *data) return IRQ_HANDLED; } +/** + * oa_tc6_zero_align_receive_frame_enable - function to enable zero align + * receive frame feature. + * @tc6: oa_tc6 struct. + * + * Return: 0 on success otherwise failed. + */ +int oa_tc6_zero_align_receive_frame_enable(struct oa_tc6 *tc6) +{ + u32 regval; + int ret; + + ret = oa_tc6_read_register(tc6, OA_TC6_REG_CONFIG0, ®val); + if (ret) + return ret; + + /* Set Zero-Align Receive Frame Enable */ + regval |= CONFIG0_ZARFE_ENABLE; + + return oa_tc6_write_register(tc6, OA_TC6_REG_CONFIG0, regval); +} +EXPORT_SYMBOL_GPL(oa_tc6_zero_align_receive_frame_enable); + /** * oa_tc6_start_xmit - function for sending the tx skb which consists ethernet * frame. diff --git a/include/linux/oa_tc6.h b/include/linux/oa_tc6.h index 5c7811ac9cbe..15f58e3c56c7 100644 --- a/include/linux/oa_tc6.h +++ b/include/linux/oa_tc6.h @@ -21,3 +21,4 @@ int oa_tc6_read_register(struct oa_tc6 *tc6, u32 address, u32 *value); int oa_tc6_read_registers(struct oa_tc6 *tc6, u32 address, u32 value[], u8 length); netdev_tx_t oa_tc6_start_xmit(struct oa_tc6 *tc6, struct sk_buff *skb); +int oa_tc6_zero_align_receive_frame_enable(struct oa_tc6 *tc6); -- cgit v1.2.3 From 5e9b50dea970ae6d3e1309d4254157099734a2af Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 30 Aug 2024 15:04:59 +0200 Subject: fs: add f_pipe Only regular files with FMODE_ATOMIC_POS and directories need f_pos_lock. Place a new f_pipe member in a union with f_pos_lock that they can use and make them stop abusing f_version in follow-up patches. Link: https://lore.kernel.org/r/20240830-vfs-file-f_version-v1-18-6d3e4816aa7b@kernel.org Reviewed-by: Jeff Layton Signed-off-by: Christian Brauner --- fs/file_table.c | 7 +++++++ include/linux/fs.h | 8 +++++++- 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/file_table.c b/fs/file_table.c index 3ef558f27a1c..7ce4d5dac080 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -156,6 +156,13 @@ static int init_file(struct file *f, int flags, const struct cred *cred) } spin_lock_init(&f->f_lock); + /* + * Note that f_pos_lock is only used for files raising + * FMODE_ATOMIC_POS and directories. Other files such as pipes + * don't need it and since f_pos_lock is in a union may reuse + * the space for other purposes. They are expected to initialize + * the respective member when opening the file. + */ mutex_init(&f->f_pos_lock); f->f_flags = flags; f->f_mode = OPEN_FMODE(flags); diff --git a/include/linux/fs.h b/include/linux/fs.h index 3e6b3c1afb31..ca4925008244 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1001,6 +1001,7 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) * @f_cred: stashed credentials of creator/opener * @f_path: path of the file * @f_pos_lock: lock protecting file position + * @f_pipe: specific to pipes * @f_pos: file position * @f_version: file version * @f_security: LSM security context of this file @@ -1026,7 +1027,12 @@ struct file { const struct cred *f_cred; /* --- cacheline 1 boundary (64 bytes) --- */ struct path f_path; - struct mutex f_pos_lock; + union { + /* regular files (with FMODE_ATOMIC_POS) and directories */ + struct mutex f_pos_lock; + /* pipes */ + u64 f_pipe; + }; loff_t f_pos; u64 f_version; /* --- cacheline 2 boundary (128 bytes) --- */ -- cgit v1.2.3 From 11068e0b64cbb540b96e577fcca0926242ecaf58 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 30 Aug 2024 15:05:01 +0200 Subject: fs: remove f_version Now that detecting concurrent seeks is done by the filesystems that require it we can remove f_version and free up 8 bytes for future extensions. Link: https://lore.kernel.org/r/20240830-vfs-file-f_version-v1-20-6d3e4816aa7b@kernel.org Reviewed-by: Jan Kara Reviewed-by: Jeff Layton Signed-off-by: Christian Brauner --- fs/read_write.c | 9 ++++----- include/linux/fs.h | 4 +--- 2 files changed, 5 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/fs/read_write.c b/fs/read_write.c index fb519e55c8e8..b19cce8e55b9 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -62,7 +62,8 @@ static loff_t vfs_setpos_cookie(struct file *file, loff_t offset, if (offset != file->f_pos) { file->f_pos = offset; - *cookie = 0; + if (cookie) + *cookie = 0; } return offset; } @@ -81,7 +82,7 @@ static loff_t vfs_setpos_cookie(struct file *file, loff_t offset, */ loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize) { - return vfs_setpos_cookie(file, offset, maxsize, &file->f_version); + return vfs_setpos_cookie(file, offset, maxsize, NULL); } EXPORT_SYMBOL(vfs_setpos); @@ -364,10 +365,8 @@ loff_t default_llseek(struct file *file, loff_t offset, int whence) } retval = -EINVAL; if (offset >= 0 || unsigned_offsets(file)) { - if (offset != file->f_pos) { + if (offset != file->f_pos) file->f_pos = offset; - file->f_version = 0; - } retval = offset; } out: diff --git a/include/linux/fs.h b/include/linux/fs.h index ca4925008244..7e11ce172140 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1003,7 +1003,6 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) * @f_pos_lock: lock protecting file position * @f_pipe: specific to pipes * @f_pos: file position - * @f_version: file version * @f_security: LSM security context of this file * @f_owner: file owner * @f_wb_err: writeback error @@ -1034,11 +1033,10 @@ struct file { u64 f_pipe; }; loff_t f_pos; - u64 f_version; - /* --- cacheline 2 boundary (128 bytes) --- */ #ifdef CONFIG_SECURITY void *f_security; #endif + /* --- cacheline 2 boundary (128 bytes) --- */ struct fown_struct *f_owner; errseq_t f_wb_err; errseq_t f_sb_err; -- cgit v1.2.3 From 2077006d4725c82c6e9612cec3a6c140921b067f Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Tue, 10 Sep 2024 10:16:39 +0200 Subject: uidgid: make sure we fit into one cacheline When I expanded uidgid mappings I intended for a struct uid_gid_map to fit into a single cacheline on x86 as they tend to be pretty performance sensitive (idmapped mounts etc). But a 4 byte hole was added that brought it over 64 bytes. Fix that by adding the static extent array and the extent counter into a substruct. C's type punning for unions guarantees that we can access ->nr_extents even if the last written to member wasn't within the same object. This is also what we rely on in struct_group() and friends. This of course relies on non-strict aliasing which we don't do. 99) If the member used to read the contents of a union object is not the same as the member last used to store a value in the object, the appropriate part of the object representation of the value is reinterpreted as an object representation in the new type as described in 6.2.6 (a process sometimes called "type punning"). Link: https://www.open-std.org/jtc1/sc22/wg14/www/docs/n2310.pdf Link: https://lore.kernel.org/r/20240910-work-uid_gid_map-v1-1-e6bc761363ed@kernel.org Reviewed-by: Jeff Layton Signed-off-by: Christian Brauner --- include/linux/user_namespace.h | 6 ++++-- kernel/user.c | 6 +++--- 2 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 6030a8235617..3625096d5f85 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -21,9 +21,11 @@ struct uid_gid_extent { }; struct uid_gid_map { /* 64 bytes -- 1 cache line */ - u32 nr_extents; union { - struct uid_gid_extent extent[UID_GID_MAP_MAX_BASE_EXTENTS]; + struct { + struct uid_gid_extent extent[UID_GID_MAP_MAX_BASE_EXTENTS]; + u32 nr_extents; + }; struct { struct uid_gid_extent *forward; struct uid_gid_extent *reverse; diff --git a/kernel/user.c b/kernel/user.c index aa1162deafe4..f46b1d41163b 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -36,33 +36,33 @@ EXPORT_SYMBOL_GPL(init_binfmt_misc); */ struct user_namespace init_user_ns = { .uid_map = { - .nr_extents = 1, { .extent[0] = { .first = 0, .lower_first = 0, .count = 4294967295U, }, + .nr_extents = 1, }, }, .gid_map = { - .nr_extents = 1, { .extent[0] = { .first = 0, .lower_first = 0, .count = 4294967295U, }, + .nr_extents = 1, }, }, .projid_map = { - .nr_extents = 1, { .extent[0] = { .first = 0, .lower_first = 0, .count = 4294967295U, }, + .nr_extents = 1, }, }, .ns.count = REFCOUNT_INIT(3), -- cgit v1.2.3 From db0aa2e9566fda2d23dc8f6c102856ead95578a4 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 19 Jun 2024 00:20:42 +0100 Subject: mm: Define struct folio_queue and ITER_FOLIOQ to handle a sequence of folios Define a data structure, struct folio_queue, to represent a sequence of folios and a kernel-internal I/O iterator type, ITER_FOLIOQ, to allow a list of folio_queue structures to be used to provide a buffer to iov_iter-taking functions, such as sendmsg and recvmsg. The folio_queue structure looks like: struct folio_queue { struct folio_batch vec; u8 orders[PAGEVEC_SIZE]; struct folio_queue *next; struct folio_queue *prev; unsigned long marks; unsigned long marks2; }; It does not use a list_head so that next and/or prev can be set to NULL at the ends of the list, allowing iov_iter-handling routines to determine that they *are* the ends without needing to store a head pointer in the iov_iter struct. A folio_batch struct is used to hold the folio pointers which allows the batch to be passed to batch handling functions. Two mark bits are available per slot. The intention is to use at least one of them to mark folios that need putting, but that might not be ultimately necessary. Accessor functions are used to access the slots to do the masking and an additional accessor function is used to indicate the size of the array. The order of each folio is also stored in the structure to avoid the need for iov_iter_advance() and iov_iter_revert() to have to query each folio to find its size. With careful barriering, this can be used as an extending buffer with new folios inserted and new folio_queue structs added without the need for a lock. Further, provided we always keep at least one struct in the buffer, we can also remove consumed folios and consumed structs from the head end as we without the need for locks. [Questions/thoughts] (1) To manage this, I need a head pointer, a tail pointer, a tail slot number (assuming insertion happens at the tail end and the next pointers point from head to tail). Should I put these into a struct of their own, say "folio_queue_head" or "rolling_buffer"? I will end up with two of these in netfs_io_request eventually, one keeping track of the pagecache I'm dealing with for buffered I/O and the other to hold a bounce buffer when we need one. (2) Should I make the slots {folio,off,len} or bio_vec? (3) This is intended to replace ITER_XARRAY eventually. Using an xarray in I/O iteration requires the taking of the RCU read lock, doing copying under the RCU read lock, walking the xarray (which may change under us), handling retries and dealing with special values. The advantage of ITER_XARRAY is that when we're dealing with the pagecache directly, we don't need any allocation - but if we're doing encrypted comms, there's a good chance we'd be using a bounce buffer anyway. This will require afs, erofs, cifs, orangefs and fscache to be converted to not use this. afs still uses it for dirs and symlinks; some of erofs usages should be easy to change, but there's one which won't be so easy; ceph's use via fscache can be fixed by porting ceph to netfslib; cifs is using xarray as a bounce buffer - that can be moved to use sheaves instead; and orangefs has a similar problem to erofs - maybe orangefs could use netfslib? Signed-off-by: David Howells cc: Matthew Wilcox cc: Jeff Layton cc: Steve French cc: Ilya Dryomov cc: Gao Xiang cc: Mike Marshall cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org cc: linux-afs@lists.infradead.org cc: linux-cifs@vger.kernel.org cc: ceph-devel@vger.kernel.org cc: linux-erofs@lists.ozlabs.org cc: devel@lists.orangefs.org Link: https://lore.kernel.org/r/20240814203850.2240469-13-dhowells@redhat.com/ # v2 Signed-off-by: Christian Brauner --- include/linux/folio_queue.h | 138 +++++++++++++++++++++++ include/linux/iov_iter.h | 57 ++++++++++ include/linux/uio.h | 12 ++ lib/iov_iter.c | 240 +++++++++++++++++++++++++++++++++++++++- lib/kunit_iov_iter.c | 259 ++++++++++++++++++++++++++++++++++++++++++++ lib/scatterlist.c | 69 +++++++++++- 6 files changed, 771 insertions(+), 4 deletions(-) create mode 100644 include/linux/folio_queue.h (limited to 'include/linux') diff --git a/include/linux/folio_queue.h b/include/linux/folio_queue.h new file mode 100644 index 000000000000..52773613bf23 --- /dev/null +++ b/include/linux/folio_queue.h @@ -0,0 +1,138 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Queue of folios definitions + * + * Copyright (C) 2024 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#ifndef _LINUX_FOLIO_QUEUE_H +#define _LINUX_FOLIO_QUEUE_H + +#include + +/* + * Segment in a queue of running buffers. Each segment can hold a number of + * folios and a portion of the queue can be referenced with the ITER_FOLIOQ + * iterator. The possibility exists of inserting non-folio elements into the + * queue (such as gaps). + * + * Explicit prev and next pointers are used instead of a list_head to make it + * easier to add segments to tail and remove them from the head without the + * need for a lock. + */ +struct folio_queue { + struct folio_batch vec; /* Folios in the queue segment */ + u8 orders[PAGEVEC_SIZE]; /* Order of each folio */ + struct folio_queue *next; /* Next queue segment or NULL */ + struct folio_queue *prev; /* Previous queue segment of NULL */ + unsigned long marks; /* 1-bit mark per folio */ + unsigned long marks2; /* Second 1-bit mark per folio */ +#if PAGEVEC_SIZE > BITS_PER_LONG +#error marks is not big enough +#endif +}; + +static inline void folioq_init(struct folio_queue *folioq) +{ + folio_batch_init(&folioq->vec); + folioq->next = NULL; + folioq->prev = NULL; + folioq->marks = 0; + folioq->marks2 = 0; +} + +static inline unsigned int folioq_nr_slots(const struct folio_queue *folioq) +{ + return PAGEVEC_SIZE; +} + +static inline unsigned int folioq_count(struct folio_queue *folioq) +{ + return folio_batch_count(&folioq->vec); +} + +static inline bool folioq_full(struct folio_queue *folioq) +{ + //return !folio_batch_space(&folioq->vec); + return folioq_count(folioq) >= folioq_nr_slots(folioq); +} + +static inline bool folioq_is_marked(const struct folio_queue *folioq, unsigned int slot) +{ + return test_bit(slot, &folioq->marks); +} + +static inline void folioq_mark(struct folio_queue *folioq, unsigned int slot) +{ + set_bit(slot, &folioq->marks); +} + +static inline void folioq_unmark(struct folio_queue *folioq, unsigned int slot) +{ + clear_bit(slot, &folioq->marks); +} + +static inline bool folioq_is_marked2(const struct folio_queue *folioq, unsigned int slot) +{ + return test_bit(slot, &folioq->marks2); +} + +static inline void folioq_mark2(struct folio_queue *folioq, unsigned int slot) +{ + set_bit(slot, &folioq->marks2); +} + +static inline void folioq_unmark2(struct folio_queue *folioq, unsigned int slot) +{ + clear_bit(slot, &folioq->marks2); +} + +static inline unsigned int __folio_order(struct folio *folio) +{ + if (!folio_test_large(folio)) + return 0; + return folio->_flags_1 & 0xff; +} + +static inline unsigned int folioq_append(struct folio_queue *folioq, struct folio *folio) +{ + unsigned int slot = folioq->vec.nr++; + + folioq->vec.folios[slot] = folio; + folioq->orders[slot] = __folio_order(folio); + return slot; +} + +static inline unsigned int folioq_append_mark(struct folio_queue *folioq, struct folio *folio) +{ + unsigned int slot = folioq->vec.nr++; + + folioq->vec.folios[slot] = folio; + folioq->orders[slot] = __folio_order(folio); + folioq_mark(folioq, slot); + return slot; +} + +static inline struct folio *folioq_folio(const struct folio_queue *folioq, unsigned int slot) +{ + return folioq->vec.folios[slot]; +} + +static inline unsigned int folioq_folio_order(const struct folio_queue *folioq, unsigned int slot) +{ + return folioq->orders[slot]; +} + +static inline size_t folioq_folio_size(const struct folio_queue *folioq, unsigned int slot) +{ + return PAGE_SIZE << folioq_folio_order(folioq, slot); +} + +static inline void folioq_clear(struct folio_queue *folioq, unsigned int slot) +{ + folioq->vec.folios[slot] = NULL; + folioq_unmark(folioq, slot); + folioq_unmark2(folioq, slot); +} + +#endif /* _LINUX_FOLIO_QUEUE_H */ diff --git a/include/linux/iov_iter.h b/include/linux/iov_iter.h index 270454a6703d..a223370a59a7 100644 --- a/include/linux/iov_iter.h +++ b/include/linux/iov_iter.h @@ -10,6 +10,7 @@ #include #include +#include typedef size_t (*iov_step_f)(void *iter_base, size_t progress, size_t len, void *priv, void *priv2); @@ -140,6 +141,60 @@ size_t iterate_bvec(struct iov_iter *iter, size_t len, void *priv, void *priv2, return progress; } +/* + * Handle ITER_FOLIOQ. + */ +static __always_inline +size_t iterate_folioq(struct iov_iter *iter, size_t len, void *priv, void *priv2, + iov_step_f step) +{ + const struct folio_queue *folioq = iter->folioq; + unsigned int slot = iter->folioq_slot; + size_t progress = 0, skip = iter->iov_offset; + + if (slot == folioq_nr_slots(folioq)) { + /* The iterator may have been extended. */ + folioq = folioq->next; + slot = 0; + } + + do { + struct folio *folio = folioq_folio(folioq, slot); + size_t part, remain, consumed; + size_t fsize; + void *base; + + if (!folio) + break; + + fsize = folioq_folio_size(folioq, slot); + base = kmap_local_folio(folio, skip); + part = umin(len, PAGE_SIZE - skip % PAGE_SIZE); + remain = step(base, progress, part, priv, priv2); + kunmap_local(base); + consumed = part - remain; + len -= consumed; + progress += consumed; + skip += consumed; + if (skip >= fsize) { + skip = 0; + slot++; + if (slot == folioq_nr_slots(folioq) && folioq->next) { + folioq = folioq->next; + slot = 0; + } + } + if (remain) + break; + } while (len); + + iter->folioq_slot = slot; + iter->folioq = folioq; + iter->iov_offset = skip; + iter->count -= progress; + return progress; +} + /* * Handle ITER_XARRAY. */ @@ -249,6 +304,8 @@ size_t iterate_and_advance2(struct iov_iter *iter, size_t len, void *priv, return iterate_bvec(iter, len, priv, priv2, step); if (iov_iter_is_kvec(iter)) return iterate_kvec(iter, len, priv, priv2, step); + if (iov_iter_is_folioq(iter)) + return iterate_folioq(iter, len, priv, priv2, step); if (iov_iter_is_xarray(iter)) return iterate_xarray(iter, len, priv, priv2, step); return iterate_discard(iter, len, priv, priv2, step); diff --git a/include/linux/uio.h b/include/linux/uio.h index 7020adedfa08..845d110acadc 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -11,6 +11,7 @@ #include struct page; +struct folio_queue; typedef unsigned int __bitwise iov_iter_extraction_t; @@ -25,6 +26,7 @@ enum iter_type { ITER_IOVEC, ITER_BVEC, ITER_KVEC, + ITER_FOLIOQ, ITER_XARRAY, ITER_DISCARD, }; @@ -66,6 +68,7 @@ struct iov_iter { const struct iovec *__iov; const struct kvec *kvec; const struct bio_vec *bvec; + const struct folio_queue *folioq; struct xarray *xarray; void __user *ubuf; }; @@ -74,6 +77,7 @@ struct iov_iter { }; union { unsigned long nr_segs; + u8 folioq_slot; loff_t xarray_start; }; }; @@ -126,6 +130,11 @@ static inline bool iov_iter_is_discard(const struct iov_iter *i) return iov_iter_type(i) == ITER_DISCARD; } +static inline bool iov_iter_is_folioq(const struct iov_iter *i) +{ + return iov_iter_type(i) == ITER_FOLIOQ; +} + static inline bool iov_iter_is_xarray(const struct iov_iter *i) { return iov_iter_type(i) == ITER_XARRAY; @@ -273,6 +282,9 @@ void iov_iter_kvec(struct iov_iter *i, unsigned int direction, const struct kvec void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_vec *bvec, unsigned long nr_segs, size_t count); void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count); +void iov_iter_folio_queue(struct iov_iter *i, unsigned int direction, + const struct folio_queue *folioq, + unsigned int first_slot, unsigned int offset, size_t count); void iov_iter_xarray(struct iov_iter *i, unsigned int direction, struct xarray *xarray, loff_t start, size_t count); ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages, diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 4a6a9f419bd7..97003155bfac 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -527,6 +527,39 @@ static void iov_iter_iovec_advance(struct iov_iter *i, size_t size) i->__iov = iov; } +static void iov_iter_folioq_advance(struct iov_iter *i, size_t size) +{ + const struct folio_queue *folioq = i->folioq; + unsigned int slot = i->folioq_slot; + + if (!i->count) + return; + i->count -= size; + + if (slot >= folioq_nr_slots(folioq)) { + folioq = folioq->next; + slot = 0; + } + + size += i->iov_offset; /* From beginning of current segment. */ + do { + size_t fsize = folioq_folio_size(folioq, slot); + + if (likely(size < fsize)) + break; + size -= fsize; + slot++; + if (slot >= folioq_nr_slots(folioq) && folioq->next) { + folioq = folioq->next; + slot = 0; + } + } while (size); + + i->iov_offset = size; + i->folioq_slot = slot; + i->folioq = folioq; +} + void iov_iter_advance(struct iov_iter *i, size_t size) { if (unlikely(i->count < size)) @@ -539,12 +572,40 @@ void iov_iter_advance(struct iov_iter *i, size_t size) iov_iter_iovec_advance(i, size); } else if (iov_iter_is_bvec(i)) { iov_iter_bvec_advance(i, size); + } else if (iov_iter_is_folioq(i)) { + iov_iter_folioq_advance(i, size); } else if (iov_iter_is_discard(i)) { i->count -= size; } } EXPORT_SYMBOL(iov_iter_advance); +static void iov_iter_folioq_revert(struct iov_iter *i, size_t unroll) +{ + const struct folio_queue *folioq = i->folioq; + unsigned int slot = i->folioq_slot; + + for (;;) { + size_t fsize; + + if (slot == 0) { + folioq = folioq->prev; + slot = folioq_nr_slots(folioq); + } + slot--; + + fsize = folioq_folio_size(folioq, slot); + if (unroll <= fsize) { + i->iov_offset = fsize - unroll; + break; + } + unroll -= fsize; + } + + i->folioq_slot = slot; + i->folioq = folioq; +} + void iov_iter_revert(struct iov_iter *i, size_t unroll) { if (!unroll) @@ -576,6 +637,9 @@ void iov_iter_revert(struct iov_iter *i, size_t unroll) } unroll -= n; } + } else if (iov_iter_is_folioq(i)) { + i->iov_offset = 0; + iov_iter_folioq_revert(i, unroll); } else { /* same logics for iovec and kvec */ const struct iovec *iov = iter_iov(i); while (1) { @@ -603,6 +667,9 @@ size_t iov_iter_single_seg_count(const struct iov_iter *i) if (iov_iter_is_bvec(i)) return min(i->count, i->bvec->bv_len - i->iov_offset); } + if (unlikely(iov_iter_is_folioq(i))) + return !i->count ? 0 : + umin(folioq_folio_size(i->folioq, i->folioq_slot), i->count); return i->count; } EXPORT_SYMBOL(iov_iter_single_seg_count); @@ -639,6 +706,36 @@ void iov_iter_bvec(struct iov_iter *i, unsigned int direction, } EXPORT_SYMBOL(iov_iter_bvec); +/** + * iov_iter_folio_queue - Initialise an I/O iterator to use the folios in a folio queue + * @i: The iterator to initialise. + * @direction: The direction of the transfer. + * @folioq: The starting point in the folio queue. + * @first_slot: The first slot in the folio queue to use + * @offset: The offset into the folio in the first slot to start at + * @count: The size of the I/O buffer in bytes. + * + * Set up an I/O iterator to either draw data out of the pages attached to an + * inode or to inject data into those pages. The pages *must* be prevented + * from evaporation, either by taking a ref on them or locking them by the + * caller. + */ +void iov_iter_folio_queue(struct iov_iter *i, unsigned int direction, + const struct folio_queue *folioq, unsigned int first_slot, + unsigned int offset, size_t count) +{ + BUG_ON(direction & ~1); + *i = (struct iov_iter) { + .iter_type = ITER_FOLIOQ, + .data_source = direction, + .folioq = folioq, + .folioq_slot = first_slot, + .count = count, + .iov_offset = offset, + }; +} +EXPORT_SYMBOL(iov_iter_folio_queue); + /** * iov_iter_xarray - Initialise an I/O iterator to use the pages in an xarray * @i: The iterator to initialise. @@ -765,12 +862,19 @@ bool iov_iter_is_aligned(const struct iov_iter *i, unsigned addr_mask, if (iov_iter_is_bvec(i)) return iov_iter_aligned_bvec(i, addr_mask, len_mask); + /* With both xarray and folioq types, we're dealing with whole folios. */ if (iov_iter_is_xarray(i)) { if (i->count & len_mask) return false; if ((i->xarray_start + i->iov_offset) & addr_mask) return false; } + if (iov_iter_is_folioq(i)) { + if (i->count & len_mask) + return false; + if (i->iov_offset & addr_mask) + return false; + } return true; } @@ -835,6 +939,9 @@ unsigned long iov_iter_alignment(const struct iov_iter *i) if (iov_iter_is_bvec(i)) return iov_iter_alignment_bvec(i); + /* With both xarray and folioq types, we're dealing with whole folios. */ + if (iov_iter_is_folioq(i)) + return i->iov_offset | i->count; if (iov_iter_is_xarray(i)) return (i->xarray_start + i->iov_offset) | i->count; @@ -887,6 +994,62 @@ static int want_pages_array(struct page ***res, size_t size, return count; } +static ssize_t iter_folioq_get_pages(struct iov_iter *iter, + struct page ***ppages, size_t maxsize, + unsigned maxpages, size_t *_start_offset) +{ + const struct folio_queue *folioq = iter->folioq; + struct page **pages; + unsigned int slot = iter->folioq_slot; + size_t extracted = 0, count = iter->count, iov_offset = iter->iov_offset; + + if (slot >= folioq_nr_slots(folioq)) { + folioq = folioq->next; + slot = 0; + if (WARN_ON(iov_offset != 0)) + return -EIO; + } + + maxpages = want_pages_array(ppages, maxsize, iov_offset & ~PAGE_MASK, maxpages); + if (!maxpages) + return -ENOMEM; + *_start_offset = iov_offset & ~PAGE_MASK; + pages = *ppages; + + for (;;) { + struct folio *folio = folioq_folio(folioq, slot); + size_t offset = iov_offset, fsize = folioq_folio_size(folioq, slot); + size_t part = PAGE_SIZE - offset % PAGE_SIZE; + + part = umin(part, umin(maxsize - extracted, fsize - offset)); + count -= part; + iov_offset += part; + extracted += part; + + *pages = folio_page(folio, offset / PAGE_SIZE); + get_page(*pages); + pages++; + maxpages--; + if (maxpages == 0 || extracted >= maxsize) + break; + + if (offset >= fsize) { + iov_offset = 0; + slot++; + if (slot == folioq_nr_slots(folioq) && folioq->next) { + folioq = folioq->next; + slot = 0; + } + } + } + + iter->count = count; + iter->iov_offset = iov_offset; + iter->folioq = folioq; + iter->folioq_slot = slot; + return extracted; +} + static ssize_t iter_xarray_populate_pages(struct page **pages, struct xarray *xa, pgoff_t index, unsigned int nr_pages) { @@ -1034,6 +1197,8 @@ static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i, } return maxsize; } + if (iov_iter_is_folioq(i)) + return iter_folioq_get_pages(i, pages, maxsize, maxpages, start); if (iov_iter_is_xarray(i)) return iter_xarray_get_pages(i, pages, maxsize, maxpages, start); return -EFAULT; @@ -1118,6 +1283,11 @@ int iov_iter_npages(const struct iov_iter *i, int maxpages) return iov_npages(i, maxpages); if (iov_iter_is_bvec(i)) return bvec_npages(i, maxpages); + if (iov_iter_is_folioq(i)) { + unsigned offset = i->iov_offset % PAGE_SIZE; + int npages = DIV_ROUND_UP(offset + i->count, PAGE_SIZE); + return min(npages, maxpages); + } if (iov_iter_is_xarray(i)) { unsigned offset = (i->xarray_start + i->iov_offset) % PAGE_SIZE; int npages = DIV_ROUND_UP(offset + i->count, PAGE_SIZE); @@ -1398,6 +1568,68 @@ void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state) i->nr_segs = state->nr_segs; } +/* + * Extract a list of contiguous pages from an ITER_FOLIOQ iterator. This does + * not get references on the pages, nor does it get a pin on them. + */ +static ssize_t iov_iter_extract_folioq_pages(struct iov_iter *i, + struct page ***pages, size_t maxsize, + unsigned int maxpages, + iov_iter_extraction_t extraction_flags, + size_t *offset0) +{ + const struct folio_queue *folioq = i->folioq; + struct page **p; + unsigned int nr = 0; + size_t extracted = 0, offset, slot = i->folioq_slot; + + if (slot >= folioq_nr_slots(folioq)) { + folioq = folioq->next; + slot = 0; + if (WARN_ON(i->iov_offset != 0)) + return -EIO; + } + + offset = i->iov_offset & ~PAGE_MASK; + *offset0 = offset; + + maxpages = want_pages_array(pages, maxsize, offset, maxpages); + if (!maxpages) + return -ENOMEM; + p = *pages; + + for (;;) { + struct folio *folio = folioq_folio(folioq, slot); + size_t offset = i->iov_offset, fsize = folioq_folio_size(folioq, slot); + size_t part = PAGE_SIZE - offset % PAGE_SIZE; + + if (offset < fsize) { + part = umin(part, umin(maxsize - extracted, fsize - offset)); + i->count -= part; + i->iov_offset += part; + extracted += part; + + p[nr++] = folio_page(folio, offset / PAGE_SIZE); + } + + if (nr >= maxpages || extracted >= maxsize) + break; + + if (i->iov_offset >= fsize) { + i->iov_offset = 0; + slot++; + if (slot == folioq_nr_slots(folioq) && folioq->next) { + folioq = folioq->next; + slot = 0; + } + } + } + + i->folioq = folioq; + i->folioq_slot = slot; + return extracted; +} + /* * Extract a list of contiguous pages from an ITER_XARRAY iterator. This does not * get references on the pages, nor does it get a pin on them. @@ -1618,8 +1850,8 @@ static ssize_t iov_iter_extract_user_pages(struct iov_iter *i, * added to the pages, but refs will not be taken. * iov_iter_extract_will_pin() will return true. * - * (*) If the iterator is ITER_KVEC, ITER_BVEC or ITER_XARRAY, the pages are - * merely listed; no extra refs or pins are obtained. + * (*) If the iterator is ITER_KVEC, ITER_BVEC, ITER_FOLIOQ or ITER_XARRAY, the + * pages are merely listed; no extra refs or pins are obtained. * iov_iter_extract_will_pin() will return 0. * * Note also: @@ -1654,6 +1886,10 @@ ssize_t iov_iter_extract_pages(struct iov_iter *i, return iov_iter_extract_bvec_pages(i, pages, maxsize, maxpages, extraction_flags, offset0); + if (iov_iter_is_folioq(i)) + return iov_iter_extract_folioq_pages(i, pages, maxsize, + maxpages, extraction_flags, + offset0); if (iov_iter_is_xarray(i)) return iov_iter_extract_xarray_pages(i, pages, maxsize, maxpages, extraction_flags, diff --git a/lib/kunit_iov_iter.c b/lib/kunit_iov_iter.c index 27e0c8ee71d8..13e15687675a 100644 --- a/lib/kunit_iov_iter.c +++ b/lib/kunit_iov_iter.c @@ -12,6 +12,7 @@ #include #include #include +#include #include MODULE_DESCRIPTION("iov_iter testing"); @@ -62,6 +63,9 @@ static void *__init iov_kunit_create_buffer(struct kunit *test, KUNIT_ASSERT_EQ(test, got, npages); } + for (int i = 0; i < npages; i++) + pages[i]->index = i; + buffer = vmap(pages, npages, VM_MAP | VM_MAP_PUT_PAGES, PAGE_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, buffer); @@ -362,6 +366,179 @@ stop: KUNIT_SUCCEED(test); } +static void iov_kunit_destroy_folioq(void *data) +{ + struct folio_queue *folioq, *next; + + for (folioq = data; folioq; folioq = next) { + next = folioq->next; + for (int i = 0; i < folioq_nr_slots(folioq); i++) + if (folioq_folio(folioq, i)) + folio_put(folioq_folio(folioq, i)); + kfree(folioq); + } +} + +static void __init iov_kunit_load_folioq(struct kunit *test, + struct iov_iter *iter, int dir, + struct folio_queue *folioq, + struct page **pages, size_t npages) +{ + struct folio_queue *p = folioq; + size_t size = 0; + int i; + + for (i = 0; i < npages; i++) { + if (folioq_full(p)) { + p->next = kzalloc(sizeof(struct folio_queue), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, p->next); + folioq_init(p->next); + p->next->prev = p; + p = p->next; + } + folioq_append(p, page_folio(pages[i])); + size += PAGE_SIZE; + } + iov_iter_folio_queue(iter, dir, folioq, 0, 0, size); +} + +static struct folio_queue *iov_kunit_create_folioq(struct kunit *test) +{ + struct folio_queue *folioq; + + folioq = kzalloc(sizeof(struct folio_queue), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, folioq); + kunit_add_action_or_reset(test, iov_kunit_destroy_folioq, folioq); + folioq_init(folioq); + return folioq; +} + +/* + * Test copying to a ITER_FOLIOQ-type iterator. + */ +static void __init iov_kunit_copy_to_folioq(struct kunit *test) +{ + const struct kvec_test_range *pr; + struct iov_iter iter; + struct folio_queue *folioq; + struct page **spages, **bpages; + u8 *scratch, *buffer; + size_t bufsize, npages, size, copied; + int i, patt; + + bufsize = 0x100000; + npages = bufsize / PAGE_SIZE; + + folioq = iov_kunit_create_folioq(test); + + scratch = iov_kunit_create_buffer(test, &spages, npages); + for (i = 0; i < bufsize; i++) + scratch[i] = pattern(i); + + buffer = iov_kunit_create_buffer(test, &bpages, npages); + memset(buffer, 0, bufsize); + + iov_kunit_load_folioq(test, &iter, READ, folioq, bpages, npages); + + i = 0; + for (pr = kvec_test_ranges; pr->from >= 0; pr++) { + size = pr->to - pr->from; + KUNIT_ASSERT_LE(test, pr->to, bufsize); + + iov_iter_folio_queue(&iter, READ, folioq, 0, 0, pr->to); + iov_iter_advance(&iter, pr->from); + copied = copy_to_iter(scratch + i, size, &iter); + + KUNIT_EXPECT_EQ(test, copied, size); + KUNIT_EXPECT_EQ(test, iter.count, 0); + KUNIT_EXPECT_EQ(test, iter.iov_offset, pr->to % PAGE_SIZE); + i += size; + if (test->status == KUNIT_FAILURE) + goto stop; + } + + /* Build the expected image in the scratch buffer. */ + patt = 0; + memset(scratch, 0, bufsize); + for (pr = kvec_test_ranges; pr->from >= 0; pr++) + for (i = pr->from; i < pr->to; i++) + scratch[i] = pattern(patt++); + + /* Compare the images */ + for (i = 0; i < bufsize; i++) { + KUNIT_EXPECT_EQ_MSG(test, buffer[i], scratch[i], "at i=%x", i); + if (buffer[i] != scratch[i]) + return; + } + +stop: + KUNIT_SUCCEED(test); +} + +/* + * Test copying from a ITER_FOLIOQ-type iterator. + */ +static void __init iov_kunit_copy_from_folioq(struct kunit *test) +{ + const struct kvec_test_range *pr; + struct iov_iter iter; + struct folio_queue *folioq; + struct page **spages, **bpages; + u8 *scratch, *buffer; + size_t bufsize, npages, size, copied; + int i, j; + + bufsize = 0x100000; + npages = bufsize / PAGE_SIZE; + + folioq = iov_kunit_create_folioq(test); + + buffer = iov_kunit_create_buffer(test, &bpages, npages); + for (i = 0; i < bufsize; i++) + buffer[i] = pattern(i); + + scratch = iov_kunit_create_buffer(test, &spages, npages); + memset(scratch, 0, bufsize); + + iov_kunit_load_folioq(test, &iter, READ, folioq, bpages, npages); + + i = 0; + for (pr = kvec_test_ranges; pr->from >= 0; pr++) { + size = pr->to - pr->from; + KUNIT_ASSERT_LE(test, pr->to, bufsize); + + iov_iter_folio_queue(&iter, WRITE, folioq, 0, 0, pr->to); + iov_iter_advance(&iter, pr->from); + copied = copy_from_iter(scratch + i, size, &iter); + + KUNIT_EXPECT_EQ(test, copied, size); + KUNIT_EXPECT_EQ(test, iter.count, 0); + KUNIT_EXPECT_EQ(test, iter.iov_offset, pr->to % PAGE_SIZE); + i += size; + } + + /* Build the expected image in the main buffer. */ + i = 0; + memset(buffer, 0, bufsize); + for (pr = kvec_test_ranges; pr->from >= 0; pr++) { + for (j = pr->from; j < pr->to; j++) { + buffer[i++] = pattern(j); + if (i >= bufsize) + goto stop; + } + } +stop: + + /* Compare the images */ + for (i = 0; i < bufsize; i++) { + KUNIT_EXPECT_EQ_MSG(test, scratch[i], buffer[i], "at i=%x", i); + if (scratch[i] != buffer[i]) + return; + } + + KUNIT_SUCCEED(test); +} + static void iov_kunit_destroy_xarray(void *data) { struct xarray *xarray = data; @@ -677,6 +854,85 @@ stop: KUNIT_SUCCEED(test); } +/* + * Test the extraction of ITER_FOLIOQ-type iterators. + */ +static void __init iov_kunit_extract_pages_folioq(struct kunit *test) +{ + const struct kvec_test_range *pr; + struct folio_queue *folioq; + struct iov_iter iter; + struct page **bpages, *pagelist[8], **pages = pagelist; + ssize_t len; + size_t bufsize, size = 0, npages; + int i, from; + + bufsize = 0x100000; + npages = bufsize / PAGE_SIZE; + + folioq = iov_kunit_create_folioq(test); + + iov_kunit_create_buffer(test, &bpages, npages); + iov_kunit_load_folioq(test, &iter, READ, folioq, bpages, npages); + + for (pr = kvec_test_ranges; pr->from >= 0; pr++) { + from = pr->from; + size = pr->to - from; + KUNIT_ASSERT_LE(test, pr->to, bufsize); + + iov_iter_folio_queue(&iter, WRITE, folioq, 0, 0, pr->to); + iov_iter_advance(&iter, from); + + do { + size_t offset0 = LONG_MAX; + + for (i = 0; i < ARRAY_SIZE(pagelist); i++) + pagelist[i] = (void *)(unsigned long)0xaa55aa55aa55aa55ULL; + + len = iov_iter_extract_pages(&iter, &pages, 100 * 1024, + ARRAY_SIZE(pagelist), 0, &offset0); + KUNIT_EXPECT_GE(test, len, 0); + if (len < 0) + break; + KUNIT_EXPECT_LE(test, len, size); + KUNIT_EXPECT_EQ(test, iter.count, size - len); + if (len == 0) + break; + size -= len; + KUNIT_EXPECT_GE(test, (ssize_t)offset0, 0); + KUNIT_EXPECT_LT(test, offset0, PAGE_SIZE); + + for (i = 0; i < ARRAY_SIZE(pagelist); i++) { + struct page *p; + ssize_t part = min_t(ssize_t, len, PAGE_SIZE - offset0); + int ix; + + KUNIT_ASSERT_GE(test, part, 0); + ix = from / PAGE_SIZE; + KUNIT_ASSERT_LT(test, ix, npages); + p = bpages[ix]; + KUNIT_EXPECT_PTR_EQ(test, pagelist[i], p); + KUNIT_EXPECT_EQ(test, offset0, from % PAGE_SIZE); + from += part; + len -= part; + KUNIT_ASSERT_GE(test, len, 0); + if (len == 0) + break; + offset0 = 0; + } + + if (test->status == KUNIT_FAILURE) + goto stop; + } while (iov_iter_count(&iter) > 0); + + KUNIT_EXPECT_EQ(test, size, 0); + KUNIT_EXPECT_EQ(test, iter.count, 0); + } + +stop: + KUNIT_SUCCEED(test); +} + /* * Test the extraction of ITER_XARRAY-type iterators. */ @@ -761,10 +1017,13 @@ static struct kunit_case __refdata iov_kunit_cases[] = { KUNIT_CASE(iov_kunit_copy_from_kvec), KUNIT_CASE(iov_kunit_copy_to_bvec), KUNIT_CASE(iov_kunit_copy_from_bvec), + KUNIT_CASE(iov_kunit_copy_to_folioq), + KUNIT_CASE(iov_kunit_copy_from_folioq), KUNIT_CASE(iov_kunit_copy_to_xarray), KUNIT_CASE(iov_kunit_copy_from_xarray), KUNIT_CASE(iov_kunit_extract_pages_kvec), KUNIT_CASE(iov_kunit_extract_pages_bvec), + KUNIT_CASE(iov_kunit_extract_pages_folioq), KUNIT_CASE(iov_kunit_extract_pages_xarray), {} }; diff --git a/lib/scatterlist.c b/lib/scatterlist.c index 7bc2220fea80..473b2646f71c 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -11,6 +11,7 @@ #include #include #include +#include /** * sg_next - return the next scatterlist entry in a list @@ -1261,6 +1262,67 @@ static ssize_t extract_kvec_to_sg(struct iov_iter *iter, return ret; } +/* + * Extract up to sg_max folios from an FOLIOQ-type iterator and add them to + * the scatterlist. The pages are not pinned. + */ +static ssize_t extract_folioq_to_sg(struct iov_iter *iter, + ssize_t maxsize, + struct sg_table *sgtable, + unsigned int sg_max, + iov_iter_extraction_t extraction_flags) +{ + const struct folio_queue *folioq = iter->folioq; + struct scatterlist *sg = sgtable->sgl + sgtable->nents; + unsigned int slot = iter->folioq_slot; + ssize_t ret = 0; + size_t offset = iter->iov_offset; + + BUG_ON(!folioq); + + if (slot >= folioq_nr_slots(folioq)) { + folioq = folioq->next; + if (WARN_ON_ONCE(!folioq)) + return 0; + slot = 0; + } + + do { + struct folio *folio = folioq_folio(folioq, slot); + size_t fsize = folioq_folio_size(folioq, slot); + + if (offset < fsize) { + size_t part = umin(maxsize - ret, fsize - offset); + + sg_set_page(sg, folio_page(folio, 0), part, offset); + sgtable->nents++; + sg++; + sg_max--; + offset += part; + ret += part; + } + + if (offset >= fsize) { + offset = 0; + slot++; + if (slot >= folioq_nr_slots(folioq)) { + if (!folioq->next) { + WARN_ON_ONCE(ret < iter->count); + break; + } + folioq = folioq->next; + slot = 0; + } + } + } while (sg_max > 0 && ret < maxsize); + + iter->folioq = folioq; + iter->folioq_slot = slot; + iter->iov_offset = offset; + iter->count -= ret; + return ret; +} + /* * Extract up to sg_max folios from an XARRAY-type iterator and add them to * the scatterlist. The pages are not pinned. @@ -1323,8 +1385,8 @@ static ssize_t extract_xarray_to_sg(struct iov_iter *iter, * addition of @sg_max elements. * * The pages referred to by UBUF- and IOVEC-type iterators are extracted and - * pinned; BVEC-, KVEC- and XARRAY-type are extracted but aren't pinned; PIPE- - * and DISCARD-type are not supported. + * pinned; BVEC-, KVEC-, FOLIOQ- and XARRAY-type are extracted but aren't + * pinned; DISCARD-type is not supported. * * No end mark is placed on the scatterlist; that's left to the caller. * @@ -1356,6 +1418,9 @@ ssize_t extract_iter_to_sg(struct iov_iter *iter, size_t maxsize, case ITER_KVEC: return extract_kvec_to_sg(iter, maxsize, sgtable, sg_max, extraction_flags); + case ITER_FOLIOQ: + return extract_folioq_to_sg(iter, maxsize, sgtable, sg_max, + extraction_flags); case ITER_XARRAY: return extract_xarray_to_sg(iter, maxsize, sgtable, sg_max, extraction_flags); -- cgit v1.2.3 From 197a3de607d92b3d72e69edf5470e0a8fae548cc Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 14 Aug 2024 16:14:21 +0100 Subject: iov_iter: Provide copy_folio_from_iter() Provide a copy_folio_from_iter() wrapper. Signed-off-by: David Howells cc: Alexander Viro cc: Christian Brauner cc: Matthew Wilcox cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org Link: https://lore.kernel.org/r/20240814203850.2240469-14-dhowells@redhat.com/ # v2 Signed-off-by: Christian Brauner --- include/linux/uio.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 845d110acadc..853f9de5aa05 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -189,6 +189,12 @@ static inline size_t copy_folio_to_iter(struct folio *folio, size_t offset, return copy_page_to_iter(&folio->page, offset, bytes, i); } +static inline size_t copy_folio_from_iter(struct folio *folio, size_t offset, + size_t bytes, struct iov_iter *i) +{ + return copy_page_from_iter(&folio->page, offset, bytes, i); +} + static inline size_t copy_folio_from_iter_atomic(struct folio *folio, size_t offset, size_t bytes, struct iov_iter *i) { -- cgit v1.2.3 From cd0277ed0c188dd40e7744e89299af7b78831ca4 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 29 May 2024 21:47:07 +0100 Subject: netfs: Use new folio_queue data type and iterator instead of xarray iter Make the netfs write-side routines use the new folio_queue struct to hold a rolling buffer of folios, with the issuer adding folios at the tail and the collector removing them from the head as they're processed instead of using an xarray. This will allow a subsequent patch to simplify the write collector. The primary mark (as tested by folioq_is_marked()) is used to note if the corresponding folio needs putting. Signed-off-by: David Howells cc: Jeff Layton cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/20240814203850.2240469-16-dhowells@redhat.com/ # v2 Signed-off-by: Christian Brauner --- fs/netfs/internal.h | 9 ++++- fs/netfs/misc.c | 76 +++++++++++++++++++++++++++++++++++++++ fs/netfs/objects.c | 1 + fs/netfs/stats.c | 4 ++- fs/netfs/write_collect.c | 84 +++++++++++++++++++++++--------------------- fs/netfs/write_issue.c | 28 +++++++-------- include/linux/netfs.h | 8 ++--- include/trace/events/netfs.h | 1 + 8 files changed, 150 insertions(+), 61 deletions(-) (limited to 'include/linux') diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h index f2920b4ee726..e1149e05a5c8 100644 --- a/fs/netfs/internal.h +++ b/fs/netfs/internal.h @@ -7,6 +7,7 @@ #include #include +#include #include #include #include @@ -64,6 +65,10 @@ static inline void netfs_proc_del_rreq(struct netfs_io_request *rreq) {} /* * misc.c */ +int netfs_buffer_append_folio(struct netfs_io_request *rreq, struct folio *folio, + bool needs_put); +struct folio_queue *netfs_delete_buffer_head(struct netfs_io_request *wreq); +void netfs_clear_buffer(struct netfs_io_request *rreq); /* * objects.c @@ -120,6 +125,7 @@ extern atomic_t netfs_n_wh_write_done; extern atomic_t netfs_n_wh_write_failed; extern atomic_t netfs_n_wb_lock_skip; extern atomic_t netfs_n_wb_lock_wait; +extern atomic_t netfs_n_folioq; int netfs_stats_show(struct seq_file *m, void *v); @@ -153,7 +159,8 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, loff_t start, enum netfs_io_origin origin); void netfs_reissue_write(struct netfs_io_stream *stream, - struct netfs_io_subrequest *subreq); + struct netfs_io_subrequest *subreq, + struct iov_iter *source); int netfs_advance_write(struct netfs_io_request *wreq, struct netfs_io_stream *stream, loff_t start, size_t len, bool to_eof); diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c index c1f321cf5999..4cd2f84415c1 100644 --- a/fs/netfs/misc.c +++ b/fs/netfs/misc.c @@ -8,6 +8,82 @@ #include #include "internal.h" +/* + * Append a folio to the rolling queue. + */ +int netfs_buffer_append_folio(struct netfs_io_request *rreq, struct folio *folio, + bool needs_put) +{ + struct folio_queue *tail = rreq->buffer_tail; + unsigned int slot, order = folio_order(folio); + + if (WARN_ON_ONCE(!rreq->buffer && tail) || + WARN_ON_ONCE(rreq->buffer && !tail)) + return -EIO; + + if (!tail || folioq_full(tail)) { + tail = kmalloc(sizeof(*tail), GFP_NOFS); + if (!tail) + return -ENOMEM; + netfs_stat(&netfs_n_folioq); + folioq_init(tail); + tail->prev = rreq->buffer_tail; + if (tail->prev) + tail->prev->next = tail; + rreq->buffer_tail = tail; + if (!rreq->buffer) { + rreq->buffer = tail; + iov_iter_folio_queue(&rreq->io_iter, ITER_SOURCE, tail, 0, 0, 0); + } + rreq->buffer_tail_slot = 0; + } + + rreq->io_iter.count += PAGE_SIZE << order; + + slot = folioq_append(tail, folio); + /* Store the counter after setting the slot. */ + smp_store_release(&rreq->buffer_tail_slot, slot); + return 0; +} + +/* + * Delete the head of a rolling queue. + */ +struct folio_queue *netfs_delete_buffer_head(struct netfs_io_request *wreq) +{ + struct folio_queue *head = wreq->buffer, *next = head->next; + + if (next) + next->prev = NULL; + netfs_stat_d(&netfs_n_folioq); + kfree(head); + wreq->buffer = next; + return next; +} + +/* + * Clear out a rolling queue. + */ +void netfs_clear_buffer(struct netfs_io_request *rreq) +{ + struct folio_queue *p; + + while ((p = rreq->buffer)) { + rreq->buffer = p->next; + for (int slot = 0; slot < folioq_nr_slots(p); slot++) { + struct folio *folio = folioq_folio(p, slot); + if (!folio) + continue; + if (folioq_is_marked(p, slot)) { + trace_netfs_folio(folio, netfs_folio_trace_put); + folio_put(folio); + } + } + netfs_stat_d(&netfs_n_folioq); + kfree(p); + } +} + /** * netfs_dirty_folio - Mark folio dirty and pin a cache object for writeback * @mapping: The mapping the folio belongs to. diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c index d6e9785ce7a3..4291cd405fc1 100644 --- a/fs/netfs/objects.c +++ b/fs/netfs/objects.c @@ -141,6 +141,7 @@ static void netfs_free_request(struct work_struct *work) } kvfree(rreq->direct_bv); } + netfs_clear_buffer(rreq); if (atomic_dec_and_test(&ictx->io_count)) wake_up_var(&ictx->io_count); diff --git a/fs/netfs/stats.c b/fs/netfs/stats.c index 5fe1c396e24f..5065289f5555 100644 --- a/fs/netfs/stats.c +++ b/fs/netfs/stats.c @@ -41,6 +41,7 @@ atomic_t netfs_n_wh_write_done; atomic_t netfs_n_wh_write_failed; atomic_t netfs_n_wb_lock_skip; atomic_t netfs_n_wb_lock_wait; +atomic_t netfs_n_folioq; int netfs_stats_show(struct seq_file *m, void *v) { @@ -76,9 +77,10 @@ int netfs_stats_show(struct seq_file *m, void *v) atomic_read(&netfs_n_wh_write), atomic_read(&netfs_n_wh_write_done), atomic_read(&netfs_n_wh_write_failed)); - seq_printf(m, "Objs : rr=%u sr=%u wsc=%u\n", + seq_printf(m, "Objs : rr=%u sr=%u foq=%u wsc=%u\n", atomic_read(&netfs_n_rh_rreq), atomic_read(&netfs_n_rh_sreq), + atomic_read(&netfs_n_folioq), atomic_read(&netfs_n_wh_wstream_conflict)); seq_printf(m, "WbLock : skip=%u wait=%u\n", atomic_read(&netfs_n_wb_lock_skip), diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c index 9a1b408d614c..7a41e76c1ba9 100644 --- a/fs/netfs/write_collect.c +++ b/fs/netfs/write_collect.c @@ -81,42 +81,6 @@ end_wb: return gcount; } -/* - * Get hold of a folio we have under writeback. We don't want to get the - * refcount on it. - */ -static struct folio *netfs_writeback_lookup_folio(struct netfs_io_request *wreq, loff_t pos) -{ - XA_STATE(xas, &wreq->mapping->i_pages, pos / PAGE_SIZE); - struct folio *folio; - - rcu_read_lock(); - - for (;;) { - xas_reset(&xas); - folio = xas_load(&xas); - if (xas_retry(&xas, folio)) - continue; - - if (!folio || xa_is_value(folio)) - kdebug("R=%08x: folio %lx (%llx) not present", - wreq->debug_id, xas.xa_index, pos / PAGE_SIZE); - BUG_ON(!folio || xa_is_value(folio)); - - if (folio == xas_reload(&xas)) - break; - } - - rcu_read_unlock(); - - if (WARN_ONCE(!folio_test_writeback(folio), - "R=%08x: folio %lx is not under writeback\n", - wreq->debug_id, folio->index)) { - trace_netfs_folio(folio, netfs_folio_trace_not_under_wback); - } - return folio; -} - /* * Unlock any folios we've finished with. */ @@ -124,13 +88,25 @@ static void netfs_writeback_unlock_folios(struct netfs_io_request *wreq, unsigned long long collected_to, unsigned int *notes) { + struct folio_queue *folioq = wreq->buffer; + unsigned int slot = wreq->buffer_head_slot; + + if (slot >= folioq_nr_slots(folioq)) { + folioq = netfs_delete_buffer_head(wreq); + slot = 0; + } + for (;;) { struct folio *folio; struct netfs_folio *finfo; unsigned long long fpos, fend; size_t fsize, flen; - folio = netfs_writeback_lookup_folio(wreq, wreq->cleaned_to); + folio = folioq_folio(folioq, slot); + if (WARN_ONCE(!folio_test_writeback(folio), + "R=%08x: folio %lx is not under writeback\n", + wreq->debug_id, folio->index)) + trace_netfs_folio(folio, netfs_folio_trace_not_under_wback); fpos = folio_pos(folio); fsize = folio_size(folio); @@ -155,9 +131,25 @@ static void netfs_writeback_unlock_folios(struct netfs_io_request *wreq, wreq->cleaned_to = fpos + fsize; *notes |= MADE_PROGRESS; + /* Clean up the head folioq. If we clear an entire folioq, then + * we can get rid of it provided it's not also the tail folioq + * being filled by the issuer. + */ + folioq_clear(folioq, slot); + slot++; + if (slot >= folioq_nr_slots(folioq)) { + if (READ_ONCE(wreq->buffer_tail) == folioq) + break; + folioq = netfs_delete_buffer_head(wreq); + slot = 0; + } + if (fpos + fsize >= collected_to) break; } + + wreq->buffer = folioq; + wreq->buffer_head_slot = slot; } /* @@ -188,9 +180,12 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, if (test_bit(NETFS_SREQ_FAILED, &subreq->flags)) break; if (__test_and_clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) { + struct iov_iter source = subreq->io_iter; + + iov_iter_revert(&source, subreq->len - source.count); __set_bit(NETFS_SREQ_RETRYING, &subreq->flags); netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); - netfs_reissue_write(stream, subreq); + netfs_reissue_write(stream, subreq, &source); } } return; @@ -200,6 +195,7 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, do { struct netfs_io_subrequest *subreq = NULL, *from, *to, *tmp; + struct iov_iter source; unsigned long long start, len; size_t part; bool boundary = false; @@ -227,6 +223,14 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, len += to->len; } + /* Determine the set of buffers we're going to use. Each + * subreq gets a subset of a single overall contiguous buffer. + */ + source = from->io_iter; + iov_iter_revert(&source, subreq->len - source.count); + iov_iter_advance(&source, from->transferred); + source.count = len; + /* Work through the sublist. */ subreq = from; list_for_each_entry_from(subreq, &stream->subrequests, rreq_link) { @@ -249,7 +253,7 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, boundary = true; netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); - netfs_reissue_write(stream, subreq); + netfs_reissue_write(stream, subreq, &source); if (subreq == to) break; } @@ -316,7 +320,7 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, boundary = false; } - netfs_reissue_write(stream, subreq); + netfs_reissue_write(stream, subreq, &source); if (!len) break; diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 7880a586343f..a75b62b202c5 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -213,9 +213,11 @@ static void netfs_prepare_write(struct netfs_io_request *wreq, * netfs_write_subrequest_terminated() when complete. */ static void netfs_do_issue_write(struct netfs_io_stream *stream, - struct netfs_io_subrequest *subreq) + struct netfs_io_subrequest *subreq, + struct iov_iter *source) { struct netfs_io_request *wreq = subreq->rreq; + size_t size = subreq->len - subreq->transferred; _enter("R=%x[%x],%zx", wreq->debug_id, subreq->debug_index, subreq->len); @@ -223,27 +225,20 @@ static void netfs_do_issue_write(struct netfs_io_stream *stream, return netfs_write_subrequest_terminated(subreq, subreq->error, false); // TODO: Use encrypted buffer - if (test_bit(NETFS_RREQ_USE_IO_ITER, &wreq->flags)) { - subreq->io_iter = wreq->io_iter; - iov_iter_advance(&subreq->io_iter, - subreq->start + subreq->transferred - wreq->start); - iov_iter_truncate(&subreq->io_iter, - subreq->len - subreq->transferred); - } else { - iov_iter_xarray(&subreq->io_iter, ITER_SOURCE, &wreq->mapping->i_pages, - subreq->start + subreq->transferred, - subreq->len - subreq->transferred); - } + subreq->io_iter = *source; + iov_iter_advance(source, size); + iov_iter_truncate(&subreq->io_iter, size); trace_netfs_sreq(subreq, netfs_sreq_trace_submit); stream->issue_write(subreq); } void netfs_reissue_write(struct netfs_io_stream *stream, - struct netfs_io_subrequest *subreq) + struct netfs_io_subrequest *subreq, + struct iov_iter *source) { __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); - netfs_do_issue_write(stream, subreq); + netfs_do_issue_write(stream, subreq, source); } static void netfs_issue_write(struct netfs_io_request *wreq, @@ -257,7 +252,7 @@ static void netfs_issue_write(struct netfs_io_request *wreq, if (subreq->start + subreq->len > wreq->start + wreq->submitted) WRITE_ONCE(wreq->submitted, subreq->start + subreq->len - wreq->start); - netfs_do_issue_write(stream, subreq); + netfs_do_issue_write(stream, subreq, &wreq->io_iter); } /* @@ -422,6 +417,9 @@ static int netfs_write_folio(struct netfs_io_request *wreq, trace_netfs_folio(folio, netfs_folio_trace_store_plus); } + /* Attach the folio to the rolling buffer. */ + netfs_buffer_append_folio(wreq, folio, false); + /* Move the submission point forward to allow for write-streaming data * not starting at the front of the page. We don't do write-streaming * with the cache as the cache requires DIO alignment. diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 63ab2c775a21..f7b444f4f251 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -38,10 +38,6 @@ static inline void folio_start_private_2(struct folio *folio) folio_set_private_2(folio); } -/* Marks used on xarray-based buffers */ -#define NETFS_BUF_PUT_MARK XA_MARK_0 /* - Page needs putting */ -#define NETFS_BUF_PAGECACHE_MARK XA_MARK_1 /* - Page needs wb/dirty flag wrangling */ - enum netfs_io_source { NETFS_SOURCE_UNKNOWN, NETFS_FILL_WITH_ZEROES, @@ -233,6 +229,8 @@ struct netfs_io_request { struct netfs_io_stream io_streams[2]; /* Streams of parallel I/O operations */ #define NR_IO_STREAMS 2 //wreq->nr_io_streams struct netfs_group *group; /* Writeback group being written back */ + struct folio_queue *buffer; /* Head of I/O buffer */ + struct folio_queue *buffer_tail; /* Tail of I/O buffer */ struct iov_iter iter; /* Unencrypted-side iterator */ struct iov_iter io_iter; /* I/O (Encrypted-side) iterator */ void *netfs_priv; /* Private data for the netfs */ @@ -254,6 +252,8 @@ struct netfs_io_request { short error; /* 0 or error that occurred */ enum netfs_io_origin origin; /* Origin of the request */ bool direct_bv_unpin; /* T if direct_bv[] must be unpinned */ + u8 buffer_head_slot; /* First slot in ->buffer */ + u8 buffer_tail_slot; /* Next slot in ->buffer_tail */ unsigned long long i_size; /* Size of the file */ unsigned long long start; /* Start position */ atomic64_t issued_to; /* Write issuer folio cursor */ diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 47cd11aaccac..4e13774a06e6 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -153,6 +153,7 @@ EM(netfs_folio_trace_mkwrite, "mkwrite") \ EM(netfs_folio_trace_mkwrite_plus, "mkwrite+") \ EM(netfs_folio_trace_not_under_wback, "!wback") \ + EM(netfs_folio_trace_put, "put") \ EM(netfs_folio_trace_read_gaps, "read-gaps") \ EM(netfs_folio_trace_redirtied, "redirtied") \ EM(netfs_folio_trace_store, "store") \ -- cgit v1.2.3 From 983cdcf8fe141b0ce16bc71959a5dc55bcb0764d Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 6 Jun 2024 07:48:55 +0100 Subject: netfs: Simplify the writeback code Use the new folio_queue structures to simplify the writeback code. The problem with referring to the i_pages xarray directly is that we may have gaps in the sequence of folios we're writing from that we need to skip when we're removing the writeback mark from the folios we're writing back from. At the moment the code tries to deal with this by carefully tracking the gaps in each writeback stream (eg. write to server and write to cache) and divining when there's a gap that spans folios (something that's not helped by folios not being a consistent size). Instead, the folio_queue buffer contains pointers only the folios we're dealing with, has them in ascending order and indicates a gap by placing non-consequitive folios next to each other. This makes it possible to track where we need to clean up to by just keeping track of where we've processed to on each stream and taking the minimum. Note that the I/O iterator is always rounded up to the end of the folio, even if that is beyond the EOF position, so that the cache can do DIO from the page. The excess space is cleared, though mmapped writes clobber it. Signed-off-by: David Howells cc: Jeff Layton cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/20240814203850.2240469-18-dhowells@redhat.com/ # v2 Signed-off-by: Christian Brauner --- fs/netfs/write_collect.c | 146 +++++++------------------------------------ fs/netfs/write_issue.c | 36 ++++++----- include/linux/netfs.h | 1 - include/trace/events/netfs.h | 33 +--------- 4 files changed, 45 insertions(+), 171 deletions(-) (limited to 'include/linux') diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c index 2a47af45faa0..4280dc6ec035 100644 --- a/fs/netfs/write_collect.c +++ b/fs/netfs/write_collect.c @@ -15,15 +15,11 @@ /* Notes made in the collector */ #define HIT_PENDING 0x01 /* A front op was still pending */ -#define SOME_EMPTY 0x02 /* One of more streams are empty */ -#define ALL_EMPTY 0x04 /* All streams are empty */ -#define MAYBE_DISCONTIG 0x08 /* A front op may be discontiguous (rounded to PAGE_SIZE) */ -#define NEED_REASSESS 0x10 /* Need to loop round and reassess */ -#define REASSESS_DISCONTIG 0x20 /* Reassess discontiguity if contiguity advances */ -#define MADE_PROGRESS 0x40 /* Made progress cleaning up a stream or the folio set */ -#define BUFFERED 0x80 /* The pagecache needs cleaning up */ -#define NEED_RETRY 0x100 /* A front op requests retrying */ -#define SAW_FAILURE 0x200 /* One stream or hit a permanent failure */ +#define NEED_REASSESS 0x02 /* Need to loop round and reassess */ +#define MADE_PROGRESS 0x04 /* Made progress cleaning up a stream or the folio set */ +#define BUFFERED 0x08 /* The pagecache needs cleaning up */ +#define NEED_RETRY 0x10 /* A front op requests retrying */ +#define SAW_FAILURE 0x20 /* One stream or hit a permanent failure */ /* * Successful completion of write of a folio to the server and/or cache. Note @@ -85,10 +81,10 @@ end_wb: * Unlock any folios we've finished with. */ static void netfs_writeback_unlock_folios(struct netfs_io_request *wreq, - unsigned long long collected_to, unsigned int *notes) { struct folio_queue *folioq = wreq->buffer; + unsigned long long collected_to = wreq->collected_to; unsigned int slot = wreq->buffer_head_slot; if (slot >= folioq_nr_slots(folioq)) { @@ -117,12 +113,6 @@ static void netfs_writeback_unlock_folios(struct netfs_io_request *wreq, trace_netfs_collect_folio(wreq, folio, fend, collected_to); - if (fpos + fsize > wreq->contiguity) { - trace_netfs_collect_contig(wreq, fpos + fsize, - netfs_contig_trace_unlock); - wreq->contiguity = fpos + fsize; - } - /* Unlock any folio we've transferred all of. */ if (collected_to < fend) break; @@ -380,7 +370,7 @@ static void netfs_collect_write_results(struct netfs_io_request *wreq) { struct netfs_io_subrequest *front, *remove; struct netfs_io_stream *stream; - unsigned long long collected_to; + unsigned long long collected_to, issued_to; unsigned int notes; int s; @@ -389,28 +379,21 @@ static void netfs_collect_write_results(struct netfs_io_request *wreq) trace_netfs_rreq(wreq, netfs_rreq_trace_collect); reassess_streams: + issued_to = atomic64_read(&wreq->issued_to); smp_rmb(); collected_to = ULLONG_MAX; - if (wreq->origin == NETFS_WRITEBACK) - notes = ALL_EMPTY | BUFFERED | MAYBE_DISCONTIG; - else if (wreq->origin == NETFS_WRITETHROUGH) - notes = ALL_EMPTY | BUFFERED; + if (wreq->origin == NETFS_WRITEBACK || + wreq->origin == NETFS_WRITETHROUGH) + notes = BUFFERED; else - notes = ALL_EMPTY; + notes = 0; /* Remove completed subrequests from the front of the streams and * advance the completion point on each stream. We stop when we hit * something that's in progress. The issuer thread may be adding stuff * to the tail whilst we're doing this. - * - * We must not, however, merge in discontiguities that span whole - * folios that aren't under writeback. This is made more complicated - * by the folios in the gap being of unpredictable sizes - if they even - * exist - but we don't want to look them up. */ for (s = 0; s < NR_IO_STREAMS; s++) { - loff_t rstart, rend; - stream = &wreq->io_streams[s]; /* Read active flag before list pointers */ if (!smp_load_acquire(&stream->active)) @@ -422,26 +405,10 @@ reassess_streams: //_debug("sreq [%x] %llx %zx/%zx", // front->debug_index, front->start, front->transferred, front->len); - /* Stall if there may be a discontinuity. */ - rstart = round_down(front->start, PAGE_SIZE); - if (rstart > wreq->contiguity) { - if (wreq->contiguity > stream->collected_to) { - trace_netfs_collect_gap(wreq, stream, - wreq->contiguity, 'D'); - stream->collected_to = wreq->contiguity; - } - notes |= REASSESS_DISCONTIG; - break; + if (stream->collected_to < front->start) { + trace_netfs_collect_gap(wreq, stream, issued_to, 'F'); + stream->collected_to = front->start; } - rend = round_up(front->start + front->len, PAGE_SIZE); - if (rend > wreq->contiguity) { - trace_netfs_collect_contig(wreq, rend, - netfs_contig_trace_collect); - wreq->contiguity = rend; - if (notes & REASSESS_DISCONTIG) - notes |= NEED_REASSESS; - } - notes &= ~MAYBE_DISCONTIG; /* Stall if the front is still undergoing I/O. */ if (test_bit(NETFS_SREQ_IN_PROGRESS, &front->flags)) { @@ -483,15 +450,6 @@ reassess_streams: front = list_first_entry_or_null(&stream->subrequests, struct netfs_io_subrequest, rreq_link); stream->front = front; - if (!front) { - unsigned long long jump_to = atomic64_read(&wreq->issued_to); - - if (stream->collected_to < jump_to) { - trace_netfs_collect_gap(wreq, stream, jump_to, 'A'); - stream->collected_to = jump_to; - } - } - spin_unlock_bh(&wreq->lock); netfs_put_subrequest(remove, false, notes & SAW_FAILURE ? @@ -499,10 +457,13 @@ reassess_streams: netfs_sreq_trace_put_done); } - if (front) - notes &= ~ALL_EMPTY; - else - notes |= SOME_EMPTY; + /* If we have an empty stream, we need to jump it forward + * otherwise the collection point will never advance. + */ + if (!front && issued_to > stream->collected_to) { + trace_netfs_collect_gap(wreq, stream, issued_to, 'E'); + stream->collected_to = issued_to; + } if (stream->collected_to < collected_to) collected_to = stream->collected_to; @@ -511,36 +472,6 @@ reassess_streams: if (collected_to != ULLONG_MAX && collected_to > wreq->collected_to) wreq->collected_to = collected_to; - /* If we have an empty stream, we need to jump it forward over any gap - * otherwise the collection point will never advance. - * - * Note that the issuer always adds to the stream with the lowest - * so-far submitted start, so if we see two consecutive subreqs in one - * stream with nothing between then in another stream, then the second - * stream has a gap that can be jumped. - */ - if (notes & SOME_EMPTY) { - unsigned long long jump_to = wreq->start + READ_ONCE(wreq->submitted); - - for (s = 0; s < NR_IO_STREAMS; s++) { - stream = &wreq->io_streams[s]; - if (stream->active && - stream->front && - stream->front->start < jump_to) - jump_to = stream->front->start; - } - - for (s = 0; s < NR_IO_STREAMS; s++) { - stream = &wreq->io_streams[s]; - if (stream->active && - !stream->front && - stream->collected_to < jump_to) { - trace_netfs_collect_gap(wreq, stream, jump_to, 'B'); - stream->collected_to = jump_to; - } - } - } - for (s = 0; s < NR_IO_STREAMS; s++) { stream = &wreq->io_streams[s]; if (stream->active) @@ -551,43 +482,14 @@ reassess_streams: /* Unlock any folios that we have now finished with. */ if (notes & BUFFERED) { - unsigned long long clean_to = min(wreq->collected_to, wreq->contiguity); - - if (wreq->cleaned_to < clean_to) - netfs_writeback_unlock_folios(wreq, clean_to, ¬es); + if (wreq->cleaned_to < wreq->collected_to) + netfs_writeback_unlock_folios(wreq, ¬es); } else { wreq->cleaned_to = wreq->collected_to; } // TODO: Discard encryption buffers - /* If all streams are discontiguous with the last folio we cleared, we - * may need to skip a set of folios. - */ - if ((notes & (MAYBE_DISCONTIG | ALL_EMPTY)) == MAYBE_DISCONTIG) { - unsigned long long jump_to = ULLONG_MAX; - - for (s = 0; s < NR_IO_STREAMS; s++) { - stream = &wreq->io_streams[s]; - if (stream->active && stream->front && - stream->front->start < jump_to) - jump_to = stream->front->start; - } - - trace_netfs_collect_contig(wreq, jump_to, netfs_contig_trace_jump); - wreq->contiguity = jump_to; - wreq->cleaned_to = jump_to; - wreq->collected_to = jump_to; - for (s = 0; s < NR_IO_STREAMS; s++) { - stream = &wreq->io_streams[s]; - if (stream->collected_to < jump_to) - stream->collected_to = jump_to; - } - //cond_resched(); - notes |= MADE_PROGRESS; - goto reassess_streams; - } - if (notes & NEED_RETRY) goto need_retry; if ((notes & MADE_PROGRESS) && test_bit(NETFS_RREQ_PAUSE, &wreq->flags)) { diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 9ead075962f0..25fb7e166cc0 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -107,7 +107,6 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, if (is_buffered && netfs_is_cache_enabled(ictx)) fscache_begin_write_operation(&wreq->cache_resources, netfs_i_cookie(ictx)); - wreq->contiguity = wreq->start; wreq->cleaned_to = wreq->start; wreq->io_streams[0].stream_nr = 0; @@ -158,6 +157,7 @@ static void netfs_prepare_write(struct netfs_io_request *wreq, subreq->source = stream->source; subreq->start = start; subreq->stream_nr = stream->stream_nr; + subreq->io_iter = wreq->io_iter; _enter("R=%x[%x]", wreq->debug_id, subreq->debug_index); @@ -213,22 +213,15 @@ static void netfs_prepare_write(struct netfs_io_request *wreq, * netfs_write_subrequest_terminated() when complete. */ static void netfs_do_issue_write(struct netfs_io_stream *stream, - struct netfs_io_subrequest *subreq, - struct iov_iter *source) + struct netfs_io_subrequest *subreq) { struct netfs_io_request *wreq = subreq->rreq; - size_t size = subreq->len - subreq->transferred; _enter("R=%x[%x],%zx", wreq->debug_id, subreq->debug_index, subreq->len); if (test_bit(NETFS_SREQ_FAILED, &subreq->flags)) return netfs_write_subrequest_terminated(subreq, subreq->error, false); - // TODO: Use encrypted buffer - subreq->io_iter = *source; - iov_iter_advance(source, size); - iov_iter_truncate(&subreq->io_iter, size); - trace_netfs_sreq(subreq, netfs_sreq_trace_submit); stream->issue_write(subreq); } @@ -237,8 +230,15 @@ void netfs_reissue_write(struct netfs_io_stream *stream, struct netfs_io_subrequest *subreq, struct iov_iter *source) { + size_t size = subreq->len - subreq->transferred; + + // TODO: Use encrypted buffer + subreq->io_iter = *source; + iov_iter_advance(source, size); + iov_iter_truncate(&subreq->io_iter, size); + __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); - netfs_do_issue_write(stream, subreq, source); + netfs_do_issue_write(stream, subreq); } static void netfs_issue_write(struct netfs_io_request *wreq, @@ -249,10 +249,8 @@ static void netfs_issue_write(struct netfs_io_request *wreq, if (!subreq) return; stream->construct = NULL; - - if (subreq->start + subreq->len > wreq->start + wreq->submitted) - WRITE_ONCE(wreq->submitted, subreq->start + subreq->len - wreq->start); - netfs_do_issue_write(stream, subreq, &wreq->io_iter); + subreq->io_iter.count = subreq->len; + netfs_do_issue_write(stream, subreq); } /* @@ -464,10 +462,11 @@ static int netfs_write_folio(struct netfs_io_request *wreq, if (choose_s < 0) break; stream = &wreq->io_streams[choose_s]; + wreq->io_iter.iov_offset = stream->submit_off; + atomic64_set(&wreq->issued_to, fpos + stream->submit_off); part = netfs_advance_write(wreq, stream, fpos + stream->submit_off, stream->submit_len, to_eof); - atomic64_set(&wreq->issued_to, fpos + stream->submit_off); stream->submit_off += part; stream->submit_max_len -= part; if (part > stream->submit_len) @@ -478,6 +477,8 @@ static int netfs_write_folio(struct netfs_io_request *wreq, debug = true; } + wreq->io_iter.iov_offset = 0; + iov_iter_advance(&wreq->io_iter, fsize); atomic64_set(&wreq->issued_to, fpos + fsize); if (!debug) @@ -526,10 +527,10 @@ int netfs_writepages(struct address_space *mapping, netfs_stat(&netfs_n_wh_writepages); do { - _debug("wbiter %lx %llx", folio->index, wreq->start + wreq->submitted); + _debug("wbiter %lx %llx", folio->index, atomic64_read(&wreq->issued_to)); /* It appears we don't have to handle cyclic writeback wrapping. */ - WARN_ON_ONCE(wreq && folio_pos(folio) < wreq->start + wreq->submitted); + WARN_ON_ONCE(wreq && folio_pos(folio) < atomic64_read(&wreq->issued_to)); if (netfs_folio_group(folio) != NETFS_FOLIO_COPY_TO_CACHE && unlikely(!test_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags))) { @@ -673,6 +674,7 @@ int netfs_unbuffered_write(struct netfs_io_request *wreq, bool may_wait, size_t part = netfs_advance_write(wreq, upload, start, len, false); start += part; len -= part; + iov_iter_advance(&wreq->io_iter, part); if (test_bit(NETFS_RREQ_PAUSE, &wreq->flags)) { trace_netfs_rreq(wreq, netfs_rreq_trace_wait_pause); wait_on_bit(&wreq->flags, NETFS_RREQ_PAUSE, TASK_UNINTERRUPTIBLE); diff --git a/include/linux/netfs.h b/include/linux/netfs.h index f7b444f4f251..bd0e3d147822 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -257,7 +257,6 @@ struct netfs_io_request { unsigned long long i_size; /* Size of the file */ unsigned long long start; /* Start position */ atomic64_t issued_to; /* Write issuer folio cursor */ - unsigned long long contiguity; /* Tracking for gaps in the writeback sequence */ unsigned long long collected_to; /* Point we've collected to */ unsigned long long cleaned_to; /* Position we've cleaned folios to */ pgoff_t no_unlock_folio; /* Don't unlock this folio after read */ diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 4e13774a06e6..58bf23002fc1 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -512,33 +512,6 @@ TRACE_EVENT(netfs_collect, __entry->start + __entry->len) ); -TRACE_EVENT(netfs_collect_contig, - TP_PROTO(const struct netfs_io_request *wreq, unsigned long long to, - enum netfs_collect_contig_trace type), - - TP_ARGS(wreq, to, type), - - TP_STRUCT__entry( - __field(unsigned int, wreq) - __field(enum netfs_collect_contig_trace, type) - __field(unsigned long long, contiguity) - __field(unsigned long long, to) - ), - - TP_fast_assign( - __entry->wreq = wreq->debug_id; - __entry->type = type; - __entry->contiguity = wreq->contiguity; - __entry->to = to; - ), - - TP_printk("R=%08x %llx -> %llx %s", - __entry->wreq, - __entry->contiguity, - __entry->to, - __print_symbolic(__entry->type, netfs_collect_contig_traces)) - ); - TRACE_EVENT(netfs_collect_sreq, TP_PROTO(const struct netfs_io_request *wreq, const struct netfs_io_subrequest *subreq), @@ -610,7 +583,6 @@ TRACE_EVENT(netfs_collect_state, __field(unsigned int, notes ) __field(unsigned long long, collected_to ) __field(unsigned long long, cleaned_to ) - __field(unsigned long long, contiguity ) ), TP_fast_assign( @@ -618,12 +590,11 @@ TRACE_EVENT(netfs_collect_state, __entry->notes = notes; __entry->collected_to = collected_to; __entry->cleaned_to = wreq->cleaned_to; - __entry->contiguity = wreq->contiguity; ), - TP_printk("R=%08x cto=%llx fto=%llx ctg=%llx n=%x", + TP_printk("R=%08x col=%llx cln=%llx n=%x", __entry->wreq, __entry->collected_to, - __entry->cleaned_to, __entry->contiguity, + __entry->cleaned_to, __entry->notes) ); -- cgit v1.2.3 From ee4cdf7ba857a894ad1650d6ab77669cbbfa329e Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 2 Jul 2024 00:40:22 +0100 Subject: netfs: Speed up buffered reading Improve the efficiency of buffered reads in a number of ways: (1) Overhaul the algorithm in general so that it's a lot more compact and split the read submission code between buffered and unbuffered versions. The unbuffered version can be vastly simplified. (2) Read-result collection is handed off to a work queue rather than being done in the I/O thread. Multiple subrequests can be processes simultaneously. (3) When a subrequest is collected, any folios it fully spans are collected and "spare" data on either side is donated to either the previous or the next subrequest in the sequence. Notes: (*) Readahead expansion is massively slows down fio, presumably because it causes a load of extra allocations, both folio and xarray, up front before RPC requests can be transmitted. (*) RDMA with cifs does appear to work, both with SIW and RXE. (*) PG_private_2-based reading and copy-to-cache is split out into its own file and altered to use folio_queue. Note that the copy to the cache now creates a new write transaction against the cache and adds the folios to be copied into it. This allows it to use part of the writeback I/O code. Signed-off-by: David Howells cc: Jeff Layton cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/20240814203850.2240469-20-dhowells@redhat.com/ # v2 Signed-off-by: Christian Brauner --- fs/9p/vfs_addr.c | 11 +- fs/afs/file.c | 21 +- fs/afs/fsclient.c | 9 +- fs/afs/yfsclient.c | 9 +- fs/ceph/addr.c | 76 +++-- fs/netfs/Makefile | 4 +- fs/netfs/buffered_read.c | 766 ++++++++++++++++++++++++++----------------- fs/netfs/direct_read.c | 147 ++++++++- fs/netfs/internal.h | 35 +- fs/netfs/iterator.c | 50 +++ fs/netfs/main.c | 4 +- fs/netfs/objects.c | 8 +- fs/netfs/read_collect.c | 544 ++++++++++++++++++++++++++++++ fs/netfs/read_pgpriv2.c | 264 +++++++++++++++ fs/netfs/read_retry.c | 256 +++++++++++++++ fs/netfs/stats.c | 6 +- fs/netfs/write_collect.c | 9 +- fs/netfs/write_issue.c | 17 +- fs/nfs/fscache.c | 19 +- fs/nfs/fscache.h | 7 +- fs/smb/client/cifsglob.h | 1 - fs/smb/client/cifssmb.c | 6 +- fs/smb/client/file.c | 82 ++--- fs/smb/client/smb2ops.c | 3 +- fs/smb/client/smb2pdu.c | 27 +- include/linux/folio_queue.h | 18 + include/linux/netfs.h | 26 +- include/trace/events/netfs.h | 103 +++++- 28 files changed, 2058 insertions(+), 470 deletions(-) create mode 100644 fs/netfs/read_collect.c create mode 100644 fs/netfs/read_pgpriv2.c create mode 100644 fs/netfs/read_retry.c (limited to 'include/linux') diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index 24fdc74caeba..819c75233235 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -68,17 +68,22 @@ static void v9fs_issue_read(struct netfs_io_subrequest *subreq) { struct netfs_io_request *rreq = subreq->rreq; struct p9_fid *fid = rreq->netfs_priv; + unsigned long long pos = subreq->start + subreq->transferred; int total, err; - total = p9_client_read(fid, subreq->start + subreq->transferred, - &subreq->io_iter, &err); + total = p9_client_read(fid, pos, &subreq->io_iter, &err); /* if we just extended the file size, any portion not in * cache won't be on server and is zeroes */ if (subreq->rreq->origin != NETFS_DIO_READ) __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); + if (pos + total >= i_size_read(rreq->inode)) + __set_bit(NETFS_SREQ_HIT_EOF, &subreq->flags); - netfs_subreq_terminated(subreq, err ?: total, false); + if (!err) + subreq->transferred += total; + + netfs_read_subreq_terminated(subreq, err, false); } /** diff --git a/fs/afs/file.c b/fs/afs/file.c index 5a9d16848ad5..492d857a3fa0 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -16,6 +16,7 @@ #include #include #include +#include #include "internal.h" static int afs_file_mmap(struct file *file, struct vm_area_struct *vma); @@ -242,9 +243,10 @@ static void afs_fetch_data_notify(struct afs_operation *op) req->error = error; if (subreq) { - if (subreq->rreq->origin != NETFS_DIO_READ) - __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); - netfs_subreq_terminated(subreq, error ?: req->actual_len, false); + subreq->rreq->i_size = req->file_size; + if (req->pos + req->actual_len >= req->file_size) + __set_bit(NETFS_SREQ_HIT_EOF, &subreq->flags); + netfs_read_subreq_terminated(subreq, error, false); req->subreq = NULL; } else if (req->done) { req->done(req); @@ -262,6 +264,12 @@ static void afs_fetch_data_success(struct afs_operation *op) afs_fetch_data_notify(op); } +static void afs_fetch_data_aborted(struct afs_operation *op) +{ + afs_check_for_remote_deletion(op); + afs_fetch_data_notify(op); +} + static void afs_fetch_data_put(struct afs_operation *op) { op->fetch.req->error = afs_op_error(op); @@ -272,7 +280,7 @@ static const struct afs_operation_ops afs_fetch_data_operation = { .issue_afs_rpc = afs_fs_fetch_data, .issue_yfs_rpc = yfs_fs_fetch_data, .success = afs_fetch_data_success, - .aborted = afs_check_for_remote_deletion, + .aborted = afs_fetch_data_aborted, .failed = afs_fetch_data_notify, .put = afs_fetch_data_put, }; @@ -294,7 +302,7 @@ int afs_fetch_data(struct afs_vnode *vnode, struct afs_read *req) op = afs_alloc_operation(req->key, vnode->volume); if (IS_ERR(op)) { if (req->subreq) - netfs_subreq_terminated(req->subreq, PTR_ERR(op), false); + netfs_read_subreq_terminated(req->subreq, PTR_ERR(op), false); return PTR_ERR(op); } @@ -313,7 +321,7 @@ static void afs_read_worker(struct work_struct *work) fsreq = afs_alloc_read(GFP_NOFS); if (!fsreq) - return netfs_subreq_terminated(subreq, -ENOMEM, false); + return netfs_read_subreq_terminated(subreq, -ENOMEM, false); fsreq->subreq = subreq; fsreq->pos = subreq->start + subreq->transferred; @@ -322,6 +330,7 @@ static void afs_read_worker(struct work_struct *work) fsreq->vnode = vnode; fsreq->iter = &subreq->io_iter; + trace_netfs_sreq(subreq, netfs_sreq_trace_submit); afs_fetch_data(fsreq->vnode, fsreq); afs_put_read(fsreq); } diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index 79cd30775b7a..098fa034a1cc 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -304,6 +304,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) struct afs_vnode_param *vp = &op->file[0]; struct afs_read *req = op->fetch.req; const __be32 *bp; + size_t count_before; int ret; _enter("{%u,%zu,%zu/%llu}", @@ -345,10 +346,14 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) /* extract the returned data */ case 2: - _debug("extract data %zu/%llu", - iov_iter_count(call->iter), req->actual_len); + count_before = call->iov_len; + _debug("extract data %zu/%llu", count_before, req->actual_len); ret = afs_extract_data(call, true); + if (req->subreq) { + req->subreq->transferred += count_before - call->iov_len; + netfs_read_subreq_progress(req->subreq, false); + } if (ret < 0) return ret; diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c index f521e66d3bf6..024227aba4cd 100644 --- a/fs/afs/yfsclient.c +++ b/fs/afs/yfsclient.c @@ -355,6 +355,7 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) struct afs_vnode_param *vp = &op->file[0]; struct afs_read *req = op->fetch.req; const __be32 *bp; + size_t count_before; int ret; _enter("{%u,%zu, %zu/%llu}", @@ -391,10 +392,14 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) /* extract the returned data */ case 2: - _debug("extract data %zu/%llu", - iov_iter_count(call->iter), req->actual_len); + count_before = call->iov_len; + _debug("extract data %zu/%llu", count_before, req->actual_len); ret = afs_extract_data(call, true); + if (req->subreq) { + req->subreq->transferred += count_before - call->iov_len; + netfs_read_subreq_progress(req->subreq, false); + } if (ret < 0) return ret; diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index c4744a02db75..c500c1fd6b9f 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -13,6 +13,7 @@ #include #include #include +#include #include "super.h" #include "mds_client.h" @@ -205,21 +206,6 @@ static void ceph_netfs_expand_readahead(struct netfs_io_request *rreq) } } -static bool ceph_netfs_clamp_length(struct netfs_io_subrequest *subreq) -{ - struct inode *inode = subreq->rreq->inode; - struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode); - struct ceph_inode_info *ci = ceph_inode(inode); - u64 objno, objoff; - u32 xlen; - - /* Truncate the extent at the end of the current block */ - ceph_calc_file_object_mapping(&ci->i_layout, subreq->start, subreq->len, - &objno, &objoff, &xlen); - subreq->len = min(xlen, fsc->mount_options->rsize); - return true; -} - static void finish_netfs_read(struct ceph_osd_request *req) { struct inode *inode = req->r_inode; @@ -264,7 +250,12 @@ static void finish_netfs_read(struct ceph_osd_request *req) calc_pages_for(osd_data->alignment, osd_data->length), false); } - netfs_subreq_terminated(subreq, err, false); + if (err > 0) { + subreq->transferred = err; + err = 0; + } + trace_netfs_sreq(subreq, netfs_sreq_trace_io_progress); + netfs_read_subreq_terminated(subreq, err, false); iput(req->r_inode); ceph_dec_osd_stopping_blocker(fsc->mdsc); } @@ -278,7 +269,6 @@ static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq) struct ceph_mds_request *req; struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb); struct ceph_inode_info *ci = ceph_inode(inode); - struct iov_iter iter; ssize_t err = 0; size_t len; int mode; @@ -301,6 +291,7 @@ static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq) req->r_args.getattr.mask = cpu_to_le32(CEPH_STAT_CAP_INLINE_DATA); req->r_num_caps = 2; + trace_netfs_sreq(subreq, netfs_sreq_trace_submit); err = ceph_mdsc_do_request(mdsc, NULL, req); if (err < 0) goto out; @@ -314,17 +305,36 @@ static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq) } len = min_t(size_t, iinfo->inline_len - subreq->start, subreq->len); - iov_iter_xarray(&iter, ITER_DEST, &rreq->mapping->i_pages, subreq->start, len); - err = copy_to_iter(iinfo->inline_data + subreq->start, len, &iter); - if (err == 0) + err = copy_to_iter(iinfo->inline_data + subreq->start, len, &subreq->io_iter); + if (err == 0) { err = -EFAULT; + } else { + subreq->transferred += err; + err = 0; + } ceph_mdsc_put_request(req); out: - netfs_subreq_terminated(subreq, err, false); + netfs_read_subreq_terminated(subreq, err, false); return true; } +static int ceph_netfs_prepare_read(struct netfs_io_subrequest *subreq) +{ + struct netfs_io_request *rreq = subreq->rreq; + struct inode *inode = rreq->inode; + struct ceph_inode_info *ci = ceph_inode(inode); + struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode); + u64 objno, objoff; + u32 xlen; + + /* Truncate the extent at the end of the current block */ + ceph_calc_file_object_mapping(&ci->i_layout, subreq->start, subreq->len, + &objno, &objoff, &xlen); + rreq->io_streams[0].sreq_max_len = umin(xlen, fsc->mount_options->rsize); + return 0; +} + static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) { struct netfs_io_request *rreq = subreq->rreq; @@ -334,9 +344,8 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) struct ceph_client *cl = fsc->client; struct ceph_osd_request *req = NULL; struct ceph_vino vino = ceph_vino(inode); - struct iov_iter iter; - int err = 0; - u64 len = subreq->len; + int err; + u64 len; bool sparse = IS_ENCRYPTED(inode) || ceph_test_mount_opt(fsc, SPARSEREAD); u64 off = subreq->start; int extent_cnt; @@ -349,6 +358,12 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) if (ceph_has_inline_data(ci) && ceph_netfs_issue_op_inline(subreq)) return; + // TODO: This rounding here is slightly dodgy. It *should* work, for + // now, as the cache only deals in blocks that are a multiple of + // PAGE_SIZE and fscrypt blocks are at most PAGE_SIZE. What needs to + // happen is for the fscrypt driving to be moved into netfslib and the + // data in the cache also to be stored encrypted. + len = subreq->len; ceph_fscrypt_adjust_off_and_len(inode, &off, &len); req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, vino, @@ -371,8 +386,6 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) doutc(cl, "%llx.%llx pos=%llu orig_len=%zu len=%llu\n", ceph_vinop(inode), subreq->start, subreq->len, len); - iov_iter_xarray(&iter, ITER_DEST, &rreq->mapping->i_pages, subreq->start, len); - /* * FIXME: For now, use CEPH_OSD_DATA_TYPE_PAGES instead of _ITER for * encrypted inodes. We'd need infrastructure that handles an iov_iter @@ -384,7 +397,7 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) struct page **pages; size_t page_off; - err = iov_iter_get_pages_alloc2(&iter, &pages, len, &page_off); + err = iov_iter_get_pages_alloc2(&subreq->io_iter, &pages, len, &page_off); if (err < 0) { doutc(cl, "%llx.%llx failed to allocate pages, %d\n", ceph_vinop(inode), err); @@ -399,7 +412,7 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0, false, false); } else { - osd_req_op_extent_osd_iter(req, 0, &iter); + osd_req_op_extent_osd_iter(req, 0, &subreq->io_iter); } if (!ceph_inc_osd_stopping_blocker(fsc->mdsc)) { err = -EIO; @@ -410,17 +423,19 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) req->r_inode = inode; ihold(inode); + trace_netfs_sreq(subreq, netfs_sreq_trace_submit); ceph_osdc_start_request(req->r_osdc, req); out: ceph_osdc_put_request(req); if (err) - netfs_subreq_terminated(subreq, err, false); + netfs_read_subreq_terminated(subreq, err, false); doutc(cl, "%llx.%llx result %d\n", ceph_vinop(inode), err); } static int ceph_init_request(struct netfs_io_request *rreq, struct file *file) { struct inode *inode = rreq->inode; + struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode); struct ceph_client *cl = ceph_inode_to_client(inode); int got = 0, want = CEPH_CAP_FILE_CACHE; struct ceph_netfs_request_data *priv; @@ -472,6 +487,7 @@ static int ceph_init_request(struct netfs_io_request *rreq, struct file *file) priv->caps = got; rreq->netfs_priv = priv; + rreq->io_streams[0].sreq_max_len = fsc->mount_options->rsize; out: if (ret < 0) @@ -496,9 +512,9 @@ static void ceph_netfs_free_request(struct netfs_io_request *rreq) const struct netfs_request_ops ceph_netfs_ops = { .init_request = ceph_init_request, .free_request = ceph_netfs_free_request, + .prepare_read = ceph_netfs_prepare_read, .issue_read = ceph_netfs_issue_read, .expand_readahead = ceph_netfs_expand_readahead, - .clamp_length = ceph_netfs_clamp_length, .check_write_begin = ceph_netfs_check_write_begin, }; diff --git a/fs/netfs/Makefile b/fs/netfs/Makefile index 8e6781e0b10b..d08b0bfb6756 100644 --- a/fs/netfs/Makefile +++ b/fs/netfs/Makefile @@ -5,12 +5,14 @@ netfs-y := \ buffered_write.o \ direct_read.o \ direct_write.o \ - io.o \ iterator.o \ locking.o \ main.o \ misc.o \ objects.o \ + read_collect.o \ + read_pgpriv2.o \ + read_retry.o \ write_collect.o \ write_issue.o diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 27c750d39476..c40e226053cc 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -9,266 +9,388 @@ #include #include "internal.h" -/* - * [DEPRECATED] Unlock the folios in a read operation for when the filesystem - * is using PG_private_2 and direct writing to the cache from here rather than - * marking the page for writeback. - * - * Note that we don't touch folio->private in this code. - */ -static void netfs_rreq_unlock_folios_pgpriv2(struct netfs_io_request *rreq, - size_t *account) +static void netfs_cache_expand_readahead(struct netfs_io_request *rreq, + unsigned long long *_start, + unsigned long long *_len, + unsigned long long i_size) { - struct netfs_io_subrequest *subreq; - struct folio *folio; - pgoff_t start_page = rreq->start / PAGE_SIZE; - pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1; - bool subreq_failed = false; + struct netfs_cache_resources *cres = &rreq->cache_resources; - XA_STATE(xas, &rreq->mapping->i_pages, start_page); + if (cres->ops && cres->ops->expand_readahead) + cres->ops->expand_readahead(cres, _start, _len, i_size); +} - /* Walk through the pagecache and the I/O request lists simultaneously. - * We may have a mixture of cached and uncached sections and we only - * really want to write out the uncached sections. This is slightly - * complicated by the possibility that we might have huge pages with a - * mixture inside. +static void netfs_rreq_expand(struct netfs_io_request *rreq, + struct readahead_control *ractl) +{ + /* Give the cache a chance to change the request parameters. The + * resultant request must contain the original region. */ - subreq = list_first_entry(&rreq->subrequests, - struct netfs_io_subrequest, rreq_link); - subreq_failed = (subreq->error < 0); + netfs_cache_expand_readahead(rreq, &rreq->start, &rreq->len, rreq->i_size); - trace_netfs_rreq(rreq, netfs_rreq_trace_unlock_pgpriv2); + /* Give the netfs a chance to change the request parameters. The + * resultant request must contain the original region. + */ + if (rreq->netfs_ops->expand_readahead) + rreq->netfs_ops->expand_readahead(rreq); - rcu_read_lock(); - xas_for_each(&xas, folio, last_page) { - loff_t pg_end; - bool pg_failed = false; - bool folio_started = false; + /* Expand the request if the cache wants it to start earlier. Note + * that the expansion may get further extended if the VM wishes to + * insert THPs and the preferred start and/or end wind up in the middle + * of THPs. + * + * If this is the case, however, the THP size should be an integer + * multiple of the cache granule size, so we get a whole number of + * granules to deal with. + */ + if (rreq->start != readahead_pos(ractl) || + rreq->len != readahead_length(ractl)) { + readahead_expand(ractl, rreq->start, rreq->len); + rreq->start = readahead_pos(ractl); + rreq->len = readahead_length(ractl); - if (xas_retry(&xas, folio)) - continue; + trace_netfs_read(rreq, readahead_pos(ractl), readahead_length(ractl), + netfs_read_trace_expanded); + } +} - pg_end = folio_pos(folio) + folio_size(folio) - 1; +/* + * Begin an operation, and fetch the stored zero point value from the cookie if + * available. + */ +static int netfs_begin_cache_read(struct netfs_io_request *rreq, struct netfs_inode *ctx) +{ + return fscache_begin_read_operation(&rreq->cache_resources, netfs_i_cookie(ctx)); +} - for (;;) { - loff_t sreq_end; +/* + * Decant the list of folios to read into a rolling buffer. + */ +static size_t netfs_load_buffer_from_ra(struct netfs_io_request *rreq, + struct folio_queue *folioq) +{ + unsigned int order, nr; + size_t size = 0; + + nr = __readahead_batch(rreq->ractl, (struct page **)folioq->vec.folios, + ARRAY_SIZE(folioq->vec.folios)); + folioq->vec.nr = nr; + for (int i = 0; i < nr; i++) { + struct folio *folio = folioq_folio(folioq, i); + + trace_netfs_folio(folio, netfs_folio_trace_read); + order = folio_order(folio); + folioq->orders[i] = order; + size += PAGE_SIZE << order; + } - if (!subreq) { - pg_failed = true; - break; - } + for (int i = nr; i < folioq_nr_slots(folioq); i++) + folioq_clear(folioq, i); - if (!folio_started && - test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags) && - fscache_operation_valid(&rreq->cache_resources)) { - trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); - folio_start_private_2(folio); - folio_started = true; - } + return size; +} - pg_failed |= subreq_failed; - sreq_end = subreq->start + subreq->len - 1; - if (pg_end < sreq_end) - break; +/* + * netfs_prepare_read_iterator - Prepare the subreq iterator for I/O + * @subreq: The subrequest to be set up + * + * Prepare the I/O iterator representing the read buffer on a subrequest for + * the filesystem to use for I/O (it can be passed directly to a socket). This + * is intended to be called from the ->issue_read() method once the filesystem + * has trimmed the request to the size it wants. + * + * Returns the limited size if successful and -ENOMEM if insufficient memory + * available. + * + * [!] NOTE: This must be run in the same thread as ->issue_read() was called + * in as we access the readahead_control struct. + */ +static ssize_t netfs_prepare_read_iterator(struct netfs_io_subrequest *subreq) +{ + struct netfs_io_request *rreq = subreq->rreq; + size_t rsize = subreq->len; + + if (subreq->source == NETFS_DOWNLOAD_FROM_SERVER) + rsize = umin(rsize, rreq->io_streams[0].sreq_max_len); + + if (rreq->ractl) { + /* If we don't have sufficient folios in the rolling buffer, + * extract a folioq's worth from the readahead region at a time + * into the buffer. Note that this acquires a ref on each page + * that we will need to release later - but we don't want to do + * that until after we've started the I/O. + */ + while (rreq->submitted < subreq->start + rsize) { + struct folio_queue *tail = rreq->buffer_tail, *new; + size_t added; + + new = kmalloc(sizeof(*new), GFP_NOFS); + if (!new) + return -ENOMEM; + netfs_stat(&netfs_n_folioq); + folioq_init(new); + new->prev = tail; + tail->next = new; + rreq->buffer_tail = new; + added = netfs_load_buffer_from_ra(rreq, new); + rreq->iter.count += added; + rreq->submitted += added; + } + } - *account += subreq->transferred; - if (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) { - subreq = list_next_entry(subreq, rreq_link); - subreq_failed = (subreq->error < 0); - } else { - subreq = NULL; - subreq_failed = false; - } + subreq->len = rsize; + if (unlikely(rreq->io_streams[0].sreq_max_segs)) { + size_t limit = netfs_limit_iter(&rreq->iter, 0, rsize, + rreq->io_streams[0].sreq_max_segs); - if (pg_end == sreq_end) - break; + if (limit < rsize) { + subreq->len = limit; + trace_netfs_sreq(subreq, netfs_sreq_trace_limited); } + } - if (!pg_failed) { - flush_dcache_folio(folio); - folio_mark_uptodate(folio); - } + subreq->io_iter = rreq->iter; - if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) { - if (folio->index == rreq->no_unlock_folio && - test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) - _debug("no unlock"); - else - folio_unlock(folio); + if (iov_iter_is_folioq(&subreq->io_iter)) { + if (subreq->io_iter.folioq_slot >= folioq_nr_slots(subreq->io_iter.folioq)) { + subreq->io_iter.folioq = subreq->io_iter.folioq->next; + subreq->io_iter.folioq_slot = 0; } + subreq->curr_folioq = (struct folio_queue *)subreq->io_iter.folioq; + subreq->curr_folioq_slot = subreq->io_iter.folioq_slot; + subreq->curr_folio_order = subreq->curr_folioq->orders[subreq->curr_folioq_slot]; } - rcu_read_unlock(); + + iov_iter_truncate(&subreq->io_iter, subreq->len); + iov_iter_advance(&rreq->iter, subreq->len); + return subreq->len; } -/* - * Unlock the folios in a read operation. We need to set PG_writeback on any - * folios we're going to write back before we unlock them. - * - * Note that if the deprecated NETFS_RREQ_USE_PGPRIV2 is set then we use - * PG_private_2 and do a direct write to the cache from here instead. - */ -void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) +static enum netfs_io_source netfs_cache_prepare_read(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq, + loff_t i_size) { - struct netfs_io_subrequest *subreq; - struct netfs_folio *finfo; - struct folio *folio; - pgoff_t start_page = rreq->start / PAGE_SIZE; - pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1; - size_t account = 0; - bool subreq_failed = false; + struct netfs_cache_resources *cres = &rreq->cache_resources; - XA_STATE(xas, &rreq->mapping->i_pages, start_page); + if (!cres->ops) + return NETFS_DOWNLOAD_FROM_SERVER; + return cres->ops->prepare_read(subreq, i_size); +} - if (test_bit(NETFS_RREQ_FAILED, &rreq->flags)) { - __clear_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags); - list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { - __clear_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); - } - } +static void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error, + bool was_async) +{ + struct netfs_io_subrequest *subreq = priv; - /* Handle deprecated PG_private_2 case. */ - if (test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) { - netfs_rreq_unlock_folios_pgpriv2(rreq, &account); - goto out; + if (transferred_or_error < 0) { + netfs_read_subreq_terminated(subreq, transferred_or_error, was_async); + return; } - /* Walk through the pagecache and the I/O request lists simultaneously. - * We may have a mixture of cached and uncached sections and we only - * really want to write out the uncached sections. This is slightly - * complicated by the possibility that we might have huge pages with a - * mixture inside. - */ - subreq = list_first_entry(&rreq->subrequests, - struct netfs_io_subrequest, rreq_link); - subreq_failed = (subreq->error < 0); - - trace_netfs_rreq(rreq, netfs_rreq_trace_unlock); + if (transferred_or_error > 0) + subreq->transferred += transferred_or_error; + netfs_read_subreq_terminated(subreq, 0, was_async); +} - rcu_read_lock(); - xas_for_each(&xas, folio, last_page) { - loff_t pg_end; - bool pg_failed = false; - bool wback_to_cache = false; +/* + * Issue a read against the cache. + * - Eats the caller's ref on subreq. + */ +static void netfs_read_cache_to_pagecache(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq) +{ + struct netfs_cache_resources *cres = &rreq->cache_resources; - if (xas_retry(&xas, folio)) - continue; + netfs_stat(&netfs_n_rh_read); + cres->ops->read(cres, subreq->start, &subreq->io_iter, NETFS_READ_HOLE_IGNORE, + netfs_cache_read_terminated, subreq); +} - pg_end = folio_pos(folio) + folio_size(folio) - 1; +/* + * Perform a read to the pagecache from a series of sources of different types, + * slicing up the region to be read according to available cache blocks and + * network rsize. + */ +static void netfs_read_to_pagecache(struct netfs_io_request *rreq) +{ + struct netfs_inode *ictx = netfs_inode(rreq->inode); + unsigned long long start = rreq->start; + ssize_t size = rreq->len; + int ret = 0; + + atomic_inc(&rreq->nr_outstanding); + + do { + struct netfs_io_subrequest *subreq; + enum netfs_io_source source = NETFS_DOWNLOAD_FROM_SERVER; + ssize_t slice; + + subreq = netfs_alloc_subrequest(rreq); + if (!subreq) { + ret = -ENOMEM; + break; + } - for (;;) { - loff_t sreq_end; + subreq->start = start; + subreq->len = size; + + atomic_inc(&rreq->nr_outstanding); + spin_lock_bh(&rreq->lock); + list_add_tail(&subreq->rreq_link, &rreq->subrequests); + subreq->prev_donated = rreq->prev_donated; + rreq->prev_donated = 0; + trace_netfs_sreq(subreq, netfs_sreq_trace_added); + spin_unlock_bh(&rreq->lock); + + source = netfs_cache_prepare_read(rreq, subreq, rreq->i_size); + subreq->source = source; + if (source == NETFS_DOWNLOAD_FROM_SERVER) { + unsigned long long zp = umin(ictx->zero_point, rreq->i_size); + size_t len = subreq->len; + + if (subreq->start >= zp) { + subreq->source = source = NETFS_FILL_WITH_ZEROES; + goto fill_with_zeroes; + } - if (!subreq) { - pg_failed = true; + if (len > zp - subreq->start) + len = zp - subreq->start; + if (len == 0) { + pr_err("ZERO-LEN READ: R=%08x[%x] l=%zx/%zx s=%llx z=%llx i=%llx", + rreq->debug_id, subreq->debug_index, + subreq->len, size, + subreq->start, ictx->zero_point, rreq->i_size); break; } + subreq->len = len; + + netfs_stat(&netfs_n_rh_download); + if (rreq->netfs_ops->prepare_read) { + ret = rreq->netfs_ops->prepare_read(subreq); + if (ret < 0) { + atomic_dec(&rreq->nr_outstanding); + netfs_put_subrequest(subreq, false, + netfs_sreq_trace_put_cancel); + break; + } + trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); + } - wback_to_cache |= test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); - pg_failed |= subreq_failed; - sreq_end = subreq->start + subreq->len - 1; - if (pg_end < sreq_end) + slice = netfs_prepare_read_iterator(subreq); + if (slice < 0) { + atomic_dec(&rreq->nr_outstanding); + netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_cancel); + ret = slice; break; - - account += subreq->transferred; - if (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) { - subreq = list_next_entry(subreq, rreq_link); - subreq_failed = (subreq->error < 0); - } else { - subreq = NULL; - subreq_failed = false; } - if (pg_end == sreq_end) - break; + rreq->netfs_ops->issue_read(subreq); + goto done; } - if (!pg_failed) { - flush_dcache_folio(folio); - finfo = netfs_folio_info(folio); - if (finfo) { - trace_netfs_folio(folio, netfs_folio_trace_filled_gaps); - if (finfo->netfs_group) - folio_change_private(folio, finfo->netfs_group); - else - folio_detach_private(folio); - kfree(finfo); - } - folio_mark_uptodate(folio); - if (wback_to_cache && !WARN_ON_ONCE(folio_get_private(folio) != NULL)) { - trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); - folio_attach_private(folio, NETFS_FOLIO_COPY_TO_CACHE); - filemap_dirty_folio(folio->mapping, folio); - } + fill_with_zeroes: + if (source == NETFS_FILL_WITH_ZEROES) { + subreq->source = NETFS_FILL_WITH_ZEROES; + trace_netfs_sreq(subreq, netfs_sreq_trace_submit); + netfs_stat(&netfs_n_rh_zero); + slice = netfs_prepare_read_iterator(subreq); + __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); + netfs_read_subreq_terminated(subreq, 0, false); + goto done; } - if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) { - if (folio->index == rreq->no_unlock_folio && - test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) - _debug("no unlock"); - else - folio_unlock(folio); + if (source == NETFS_READ_FROM_CACHE) { + trace_netfs_sreq(subreq, netfs_sreq_trace_submit); + slice = netfs_prepare_read_iterator(subreq); + netfs_read_cache_to_pagecache(rreq, subreq); + goto done; } - } - rcu_read_unlock(); -out: - task_io_account_read(account); - if (rreq->netfs_ops->done) - rreq->netfs_ops->done(rreq); -} + pr_err("Unexpected read source %u\n", source); + WARN_ON_ONCE(1); + break; -static void netfs_cache_expand_readahead(struct netfs_io_request *rreq, - unsigned long long *_start, - unsigned long long *_len, - unsigned long long i_size) -{ - struct netfs_cache_resources *cres = &rreq->cache_resources; + done: + size -= slice; + start += slice; + cond_resched(); + } while (size > 0); - if (cres->ops && cres->ops->expand_readahead) - cres->ops->expand_readahead(cres, _start, _len, i_size); + if (atomic_dec_and_test(&rreq->nr_outstanding)) + netfs_rreq_terminated(rreq, false); + + /* Defer error return as we may need to wait for outstanding I/O. */ + cmpxchg(&rreq->error, 0, ret); } -static void netfs_rreq_expand(struct netfs_io_request *rreq, - struct readahead_control *ractl) +/* + * Wait for the read operation to complete, successfully or otherwise. + */ +static int netfs_wait_for_read(struct netfs_io_request *rreq) { - /* Give the cache a chance to change the request parameters. The - * resultant request must contain the original region. - */ - netfs_cache_expand_readahead(rreq, &rreq->start, &rreq->len, rreq->i_size); + int ret; - /* Give the netfs a chance to change the request parameters. The - * resultant request must contain the original region. - */ - if (rreq->netfs_ops->expand_readahead) - rreq->netfs_ops->expand_readahead(rreq); + trace_netfs_rreq(rreq, netfs_rreq_trace_wait_ip); + wait_on_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS, TASK_UNINTERRUPTIBLE); + ret = rreq->error; + if (ret == 0 && rreq->submitted < rreq->len) { + trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read); + ret = -EIO; + } - /* Expand the request if the cache wants it to start earlier. Note - * that the expansion may get further extended if the VM wishes to - * insert THPs and the preferred start and/or end wind up in the middle - * of THPs. - * - * If this is the case, however, the THP size should be an integer - * multiple of the cache granule size, so we get a whole number of - * granules to deal with. - */ - if (rreq->start != readahead_pos(ractl) || - rreq->len != readahead_length(ractl)) { - readahead_expand(ractl, rreq->start, rreq->len); - rreq->start = readahead_pos(ractl); - rreq->len = readahead_length(ractl); + return ret; +} - trace_netfs_read(rreq, readahead_pos(ractl), readahead_length(ractl), - netfs_read_trace_expanded); - } +/* + * Set up the initial folioq of buffer folios in the rolling buffer and set the + * iterator to refer to it. + */ +static int netfs_prime_buffer(struct netfs_io_request *rreq) +{ + struct folio_queue *folioq; + size_t added; + + folioq = kmalloc(sizeof(*folioq), GFP_KERNEL); + if (!folioq) + return -ENOMEM; + netfs_stat(&netfs_n_folioq); + folioq_init(folioq); + rreq->buffer = folioq; + rreq->buffer_tail = folioq; + rreq->submitted = rreq->start; + iov_iter_folio_queue(&rreq->iter, ITER_DEST, folioq, 0, 0, 0); + + added = netfs_load_buffer_from_ra(rreq, folioq); + rreq->iter.count += added; + rreq->submitted += added; + return 0; } /* - * Begin an operation, and fetch the stored zero point value from the cookie if - * available. + * Drop the ref on each folio that we inherited from the VM readahead code. We + * still have the folio locks to pin the page until we complete the I/O. + * + * Note that we can't just release the batch in each queue struct as we use the + * occupancy count in other places. */ -static int netfs_begin_cache_read(struct netfs_io_request *rreq, struct netfs_inode *ctx) +static void netfs_put_ra_refs(struct folio_queue *folioq) { - return fscache_begin_read_operation(&rreq->cache_resources, netfs_i_cookie(ctx)); + struct folio_batch fbatch; + + folio_batch_init(&fbatch); + while (folioq) { + for (unsigned int slot = 0; slot < folioq_count(folioq); slot++) { + struct folio *folio = folioq_folio(folioq, slot); + if (!folio) + continue; + trace_netfs_folio(folio, netfs_folio_trace_read_put); + if (!folio_batch_add(&fbatch, folio)) + folio_batch_release(&fbatch); + } + folioq = folioq->next; + } + + folio_batch_release(&fbatch); } /** @@ -289,22 +411,17 @@ static int netfs_begin_cache_read(struct netfs_io_request *rreq, struct netfs_in void netfs_readahead(struct readahead_control *ractl) { struct netfs_io_request *rreq; - struct netfs_inode *ctx = netfs_inode(ractl->mapping->host); + struct netfs_inode *ictx = netfs_inode(ractl->mapping->host); + unsigned long long start = readahead_pos(ractl); + size_t size = readahead_length(ractl); int ret; - _enter("%lx,%x", readahead_index(ractl), readahead_count(ractl)); - - if (readahead_count(ractl) == 0) - return; - - rreq = netfs_alloc_request(ractl->mapping, ractl->file, - readahead_pos(ractl), - readahead_length(ractl), + rreq = netfs_alloc_request(ractl->mapping, ractl->file, start, size, NETFS_READAHEAD); if (IS_ERR(rreq)) return; - ret = netfs_begin_cache_read(rreq, ctx); + ret = netfs_begin_cache_read(rreq, ictx); if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) goto cleanup_free; @@ -314,18 +431,15 @@ void netfs_readahead(struct readahead_control *ractl) netfs_rreq_expand(rreq, ractl); - /* Set up the output buffer */ - iov_iter_xarray(&rreq->iter, ITER_DEST, &ractl->mapping->i_pages, - rreq->start, rreq->len); + rreq->ractl = ractl; + if (netfs_prime_buffer(rreq) < 0) + goto cleanup_free; + netfs_read_to_pagecache(rreq); - /* Drop the refs on the folios here rather than in the cache or - * filesystem. The locks will be dropped in netfs_rreq_unlock(). - */ - while (readahead_folio(ractl)) - ; + /* Release the folio refs whilst we're waiting for the I/O. */ + netfs_put_ra_refs(rreq->buffer); - netfs_begin_read(rreq, false); - netfs_put_request(rreq, false, netfs_rreq_trace_put_return); + netfs_put_request(rreq, true, netfs_rreq_trace_put_return); return; cleanup_free: @@ -334,6 +448,117 @@ cleanup_free: } EXPORT_SYMBOL(netfs_readahead); +/* + * Create a rolling buffer with a single occupying folio. + */ +static int netfs_create_singular_buffer(struct netfs_io_request *rreq, struct folio *folio) +{ + struct folio_queue *folioq; + + folioq = kmalloc(sizeof(*folioq), GFP_KERNEL); + if (!folioq) + return -ENOMEM; + + netfs_stat(&netfs_n_folioq); + folioq_init(folioq); + folioq_append(folioq, folio); + BUG_ON(folioq_folio(folioq, 0) != folio); + BUG_ON(folioq_folio_order(folioq, 0) != folio_order(folio)); + rreq->buffer = folioq; + rreq->buffer_tail = folioq; + rreq->submitted = rreq->start + rreq->len; + iov_iter_folio_queue(&rreq->iter, ITER_DEST, folioq, 0, 0, rreq->len); + rreq->ractl = (struct readahead_control *)1UL; + return 0; +} + +/* + * Read into gaps in a folio partially filled by a streaming write. + */ +static int netfs_read_gaps(struct file *file, struct folio *folio) +{ + struct netfs_io_request *rreq; + struct address_space *mapping = folio->mapping; + struct netfs_folio *finfo = netfs_folio_info(folio); + struct netfs_inode *ctx = netfs_inode(mapping->host); + struct folio *sink = NULL; + struct bio_vec *bvec; + unsigned int from = finfo->dirty_offset; + unsigned int to = from + finfo->dirty_len; + unsigned int off = 0, i = 0; + size_t flen = folio_size(folio); + size_t nr_bvec = flen / PAGE_SIZE + 2; + size_t part; + int ret; + + _enter("%lx", folio->index); + + rreq = netfs_alloc_request(mapping, file, folio_pos(folio), flen, NETFS_READ_GAPS); + if (IS_ERR(rreq)) { + ret = PTR_ERR(rreq); + goto alloc_error; + } + + ret = netfs_begin_cache_read(rreq, ctx); + if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) + goto discard; + + netfs_stat(&netfs_n_rh_read_folio); + trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_read_gaps); + + /* Fiddle the buffer so that a gap at the beginning and/or a gap at the + * end get copied to, but the middle is discarded. + */ + ret = -ENOMEM; + bvec = kmalloc_array(nr_bvec, sizeof(*bvec), GFP_KERNEL); + if (!bvec) + goto discard; + + sink = folio_alloc(GFP_KERNEL, 0); + if (!sink) { + kfree(bvec); + goto discard; + } + + trace_netfs_folio(folio, netfs_folio_trace_read_gaps); + + rreq->direct_bv = bvec; + rreq->direct_bv_count = nr_bvec; + if (from > 0) { + bvec_set_folio(&bvec[i++], folio, from, 0); + off = from; + } + while (off < to) { + part = min_t(size_t, to - off, PAGE_SIZE); + bvec_set_folio(&bvec[i++], sink, part, 0); + off += part; + } + if (to < flen) + bvec_set_folio(&bvec[i++], folio, flen - to, to); + iov_iter_bvec(&rreq->iter, ITER_DEST, bvec, i, rreq->len); + rreq->submitted = rreq->start + flen; + + netfs_read_to_pagecache(rreq); + + if (sink) + folio_put(sink); + + ret = netfs_wait_for_read(rreq); + if (ret == 0) { + flush_dcache_folio(folio); + folio_mark_uptodate(folio); + } + folio_unlock(folio); + netfs_put_request(rreq, false, netfs_rreq_trace_put_return); + return ret < 0 ? ret : 0; + +discard: + netfs_put_request(rreq, false, netfs_rreq_trace_put_discard); +alloc_error: + folio_unlock(folio); + return ret; +} + /** * netfs_read_folio - Helper to manage a read_folio request * @file: The file to read from @@ -353,9 +578,13 @@ int netfs_read_folio(struct file *file, struct folio *folio) struct address_space *mapping = folio->mapping; struct netfs_io_request *rreq; struct netfs_inode *ctx = netfs_inode(mapping->host); - struct folio *sink = NULL; int ret; + if (folio_test_dirty(folio)) { + trace_netfs_folio(folio, netfs_folio_trace_read_gaps); + return netfs_read_gaps(file, folio); + } + _enter("%lx", folio->index); rreq = netfs_alloc_request(mapping, file, @@ -374,54 +603,12 @@ int netfs_read_folio(struct file *file, struct folio *folio) trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_readpage); /* Set up the output buffer */ - if (folio_test_dirty(folio)) { - /* Handle someone trying to read from an unflushed streaming - * write. We fiddle the buffer so that a gap at the beginning - * and/or a gap at the end get copied to, but the middle is - * discarded. - */ - struct netfs_folio *finfo = netfs_folio_info(folio); - struct bio_vec *bvec; - unsigned int from = finfo->dirty_offset; - unsigned int to = from + finfo->dirty_len; - unsigned int off = 0, i = 0; - size_t flen = folio_size(folio); - size_t nr_bvec = flen / PAGE_SIZE + 2; - size_t part; - - ret = -ENOMEM; - bvec = kmalloc_array(nr_bvec, sizeof(*bvec), GFP_KERNEL); - if (!bvec) - goto discard; - - sink = folio_alloc(GFP_KERNEL, 0); - if (!sink) - goto discard; - - trace_netfs_folio(folio, netfs_folio_trace_read_gaps); - - rreq->direct_bv = bvec; - rreq->direct_bv_count = nr_bvec; - if (from > 0) { - bvec_set_folio(&bvec[i++], folio, from, 0); - off = from; - } - while (off < to) { - part = min_t(size_t, to - off, PAGE_SIZE); - bvec_set_folio(&bvec[i++], sink, part, 0); - off += part; - } - if (to < flen) - bvec_set_folio(&bvec[i++], folio, flen - to, to); - iov_iter_bvec(&rreq->iter, ITER_DEST, bvec, i, rreq->len); - } else { - iov_iter_xarray(&rreq->iter, ITER_DEST, &mapping->i_pages, - rreq->start, rreq->len); - } + ret = netfs_create_singular_buffer(rreq, folio); + if (ret < 0) + goto discard; - ret = netfs_begin_read(rreq, true); - if (sink) - folio_put(sink); + netfs_read_to_pagecache(rreq); + ret = netfs_wait_for_read(rreq); netfs_put_request(rreq, false, netfs_rreq_trace_put_return); return ret < 0 ? ret : 0; @@ -494,13 +681,10 @@ zero_out: * * Pre-read data for a write-begin request by drawing data from the cache if * possible, or the netfs if not. Space beyond the EOF is zero-filled. - * Multiple I/O requests from different sources will get munged together. If - * necessary, the readahead window can be expanded in either direction to a - * more convenient alighment for RPC efficiency or to make storage in the cache - * feasible. + * Multiple I/O requests from different sources will get munged together. * * The calling netfs must provide a table of operations, only one of which, - * issue_op, is mandatory. + * issue_read, is mandatory. * * The check_write_begin() operation can be provided to check for and flush * conflicting writes once the folio is grabbed and locked. It is passed a @@ -528,8 +712,6 @@ int netfs_write_begin(struct netfs_inode *ctx, pgoff_t index = pos >> PAGE_SHIFT; int ret; - DEFINE_READAHEAD(ractl, file, NULL, mapping, index); - retry: folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN, mapping_gfp_mask(mapping)); @@ -577,22 +759,13 @@ retry: netfs_stat(&netfs_n_rh_write_begin); trace_netfs_read(rreq, pos, len, netfs_read_trace_write_begin); - /* Expand the request to meet caching requirements and download - * preferences. - */ - ractl._nr_pages = folio_nr_pages(folio); - netfs_rreq_expand(rreq, &ractl); - /* Set up the output buffer */ - iov_iter_xarray(&rreq->iter, ITER_DEST, &mapping->i_pages, - rreq->start, rreq->len); - - /* We hold the folio locks, so we can drop the references */ - folio_get(folio); - while (readahead_folio(&ractl)) - ; + ret = netfs_create_singular_buffer(rreq, folio); + if (ret < 0) + goto error_put; - ret = netfs_begin_read(rreq, true); + netfs_read_to_pagecache(rreq); + ret = netfs_wait_for_read(rreq); if (ret < 0) goto error; netfs_put_request(rreq, false, netfs_rreq_trace_put_return); @@ -652,10 +825,13 @@ int netfs_prefetch_for_write(struct file *file, struct folio *folio, trace_netfs_read(rreq, start, flen, netfs_read_trace_prefetch_for_write); /* Set up the output buffer */ - iov_iter_xarray(&rreq->iter, ITER_DEST, &mapping->i_pages, - rreq->start, rreq->len); + ret = netfs_create_singular_buffer(rreq, folio); + if (ret < 0) + goto error_put; - ret = netfs_begin_read(rreq, true); + folioq_mark2(rreq->buffer, 0); + netfs_read_to_pagecache(rreq); + ret = netfs_wait_for_read(rreq); netfs_put_request(rreq, false, netfs_rreq_trace_put_return); return ret; diff --git a/fs/netfs/direct_read.c b/fs/netfs/direct_read.c index 10a1e4da6bda..b1a66a6e6bc2 100644 --- a/fs/netfs/direct_read.c +++ b/fs/netfs/direct_read.c @@ -16,6 +16,143 @@ #include #include "internal.h" +static void netfs_prepare_dio_read_iterator(struct netfs_io_subrequest *subreq) +{ + struct netfs_io_request *rreq = subreq->rreq; + size_t rsize; + + rsize = umin(subreq->len, rreq->io_streams[0].sreq_max_len); + subreq->len = rsize; + + if (unlikely(rreq->io_streams[0].sreq_max_segs)) { + size_t limit = netfs_limit_iter(&rreq->iter, 0, rsize, + rreq->io_streams[0].sreq_max_segs); + + if (limit < rsize) { + subreq->len = limit; + trace_netfs_sreq(subreq, netfs_sreq_trace_limited); + } + } + + trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); + + subreq->io_iter = rreq->iter; + iov_iter_truncate(&subreq->io_iter, subreq->len); + iov_iter_advance(&rreq->iter, subreq->len); +} + +/* + * Perform a read to a buffer from the server, slicing up the region to be read + * according to the network rsize. + */ +static int netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq) +{ + unsigned long long start = rreq->start; + ssize_t size = rreq->len; + int ret = 0; + + atomic_set(&rreq->nr_outstanding, 1); + + do { + struct netfs_io_subrequest *subreq; + ssize_t slice; + + subreq = netfs_alloc_subrequest(rreq); + if (!subreq) { + ret = -ENOMEM; + break; + } + + subreq->source = NETFS_DOWNLOAD_FROM_SERVER; + subreq->start = start; + subreq->len = size; + + atomic_inc(&rreq->nr_outstanding); + spin_lock_bh(&rreq->lock); + list_add_tail(&subreq->rreq_link, &rreq->subrequests); + subreq->prev_donated = rreq->prev_donated; + rreq->prev_donated = 0; + trace_netfs_sreq(subreq, netfs_sreq_trace_added); + spin_unlock_bh(&rreq->lock); + + netfs_stat(&netfs_n_rh_download); + if (rreq->netfs_ops->prepare_read) { + ret = rreq->netfs_ops->prepare_read(subreq); + if (ret < 0) { + atomic_dec(&rreq->nr_outstanding); + netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_cancel); + break; + } + } + + netfs_prepare_dio_read_iterator(subreq); + slice = subreq->len; + rreq->netfs_ops->issue_read(subreq); + + size -= slice; + start += slice; + rreq->submitted += slice; + + if (test_bit(NETFS_RREQ_BLOCKED, &rreq->flags) && + test_bit(NETFS_RREQ_NONBLOCK, &rreq->flags)) + break; + cond_resched(); + } while (size > 0); + + if (atomic_dec_and_test(&rreq->nr_outstanding)) + netfs_rreq_terminated(rreq, false); + return ret; +} + +/* + * Perform a read to an application buffer, bypassing the pagecache and the + * local disk cache. + */ +static int netfs_unbuffered_read(struct netfs_io_request *rreq, bool sync) +{ + int ret; + + _enter("R=%x %llx-%llx", + rreq->debug_id, rreq->start, rreq->start + rreq->len - 1); + + if (rreq->len == 0) { + pr_err("Zero-sized read [R=%x]\n", rreq->debug_id); + return -EIO; + } + + // TODO: Use bounce buffer if requested + + inode_dio_begin(rreq->inode); + + ret = netfs_dispatch_unbuffered_reads(rreq); + + if (!rreq->submitted) { + netfs_put_request(rreq, false, netfs_rreq_trace_put_no_submit); + inode_dio_end(rreq->inode); + ret = 0; + goto out; + } + + if (sync) { + trace_netfs_rreq(rreq, netfs_rreq_trace_wait_ip); + wait_on_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS, + TASK_UNINTERRUPTIBLE); + + ret = rreq->error; + if (ret == 0 && rreq->submitted < rreq->len && + rreq->origin != NETFS_DIO_READ) { + trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read); + ret = -EIO; + } + } else { + ret = -EIOCBQUEUED; + } + +out: + _leave(" = %d", ret); + return ret; +} + /** * netfs_unbuffered_read_iter_locked - Perform an unbuffered or direct I/O read * @iocb: The I/O control descriptor describing the read @@ -31,7 +168,7 @@ ssize_t netfs_unbuffered_read_iter_locked(struct kiocb *iocb, struct iov_iter *i struct netfs_io_request *rreq; ssize_t ret; size_t orig_count = iov_iter_count(iter); - bool async = !is_sync_kiocb(iocb); + bool sync = is_sync_kiocb(iocb); _enter(""); @@ -78,13 +215,13 @@ ssize_t netfs_unbuffered_read_iter_locked(struct kiocb *iocb, struct iov_iter *i // TODO: Set up bounce buffer if needed - if (async) + if (!sync) rreq->iocb = iocb; - ret = netfs_begin_read(rreq, is_sync_kiocb(iocb)); + ret = netfs_unbuffered_read(rreq, sync); if (ret < 0) goto out; /* May be -EIOCBQUEUED */ - if (!async) { + if (sync) { // TODO: Copy from bounce buffer iocb->ki_pos += rreq->transferred; ret = rreq->transferred; @@ -94,8 +231,6 @@ out: netfs_put_request(rreq, false, netfs_rreq_trace_put_return); if (ret > 0) orig_count -= ret; - if (ret != -EIOCBQUEUED) - iov_iter_revert(iter, orig_count - iov_iter_count(iter)); return ret; } EXPORT_SYMBOL(netfs_unbuffered_read_iter_locked); diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h index 21a3c7d13585..c9f0ed24cb7b 100644 --- a/fs/netfs/internal.h +++ b/fs/netfs/internal.h @@ -23,16 +23,9 @@ /* * buffered_read.c */ -void netfs_rreq_unlock_folios(struct netfs_io_request *rreq); int netfs_prefetch_for_write(struct file *file, struct folio *folio, size_t offset, size_t len); -/* - * io.c - */ -void netfs_rreq_work(struct work_struct *work); -int netfs_begin_read(struct netfs_io_request *rreq, bool sync); - /* * main.c */ @@ -90,6 +83,28 @@ static inline void netfs_see_request(struct netfs_io_request *rreq, trace_netfs_rreq_ref(rreq->debug_id, refcount_read(&rreq->ref), what); } +/* + * read_collect.c + */ +void netfs_read_termination_worker(struct work_struct *work); +void netfs_rreq_terminated(struct netfs_io_request *rreq, bool was_async); + +/* + * read_pgpriv2.c + */ +void netfs_pgpriv2_mark_copy_to_cache(struct netfs_io_subrequest *subreq, + struct netfs_io_request *rreq, + struct folio_queue *folioq, + int slot); +void netfs_pgpriv2_write_to_the_cache(struct netfs_io_request *rreq); +bool netfs_pgpriv2_unlock_copied_folios(struct netfs_io_request *wreq); + +/* + * read_retry.c + */ +void netfs_retry_reads(struct netfs_io_request *rreq); +void netfs_unlock_abandoned_read_pages(struct netfs_io_request *rreq); + /* * stats.c */ @@ -117,6 +132,7 @@ extern atomic_t netfs_n_wh_buffered_write; extern atomic_t netfs_n_wh_writethrough; extern atomic_t netfs_n_wh_dio_write; extern atomic_t netfs_n_wh_writepages; +extern atomic_t netfs_n_wh_copy_to_cache; extern atomic_t netfs_n_wh_wstream_conflict; extern atomic_t netfs_n_wh_upload; extern atomic_t netfs_n_wh_upload_done; @@ -162,6 +178,11 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, void netfs_reissue_write(struct netfs_io_stream *stream, struct netfs_io_subrequest *subreq, struct iov_iter *source); +void netfs_issue_write(struct netfs_io_request *wreq, + struct netfs_io_stream *stream); +int netfs_advance_write(struct netfs_io_request *wreq, + struct netfs_io_stream *stream, + loff_t start, size_t len, bool to_eof); struct netfs_io_request *netfs_begin_writethrough(struct kiocb *iocb, size_t len); int netfs_advance_writethrough(struct netfs_io_request *wreq, struct writeback_control *wbc, struct folio *folio, size_t copied, bool to_page_end, diff --git a/fs/netfs/iterator.c b/fs/netfs/iterator.c index b781bbbf1d8d..72a435e5fc6d 100644 --- a/fs/netfs/iterator.c +++ b/fs/netfs/iterator.c @@ -188,9 +188,59 @@ static size_t netfs_limit_xarray(const struct iov_iter *iter, size_t start_offse return min(span, max_size); } +/* + * Select the span of a folio queue iterator we're going to use. Limit it by + * both maximum size and maximum number of segments. Returns the size of the + * span in bytes. + */ +static size_t netfs_limit_folioq(const struct iov_iter *iter, size_t start_offset, + size_t max_size, size_t max_segs) +{ + const struct folio_queue *folioq = iter->folioq; + unsigned int nsegs = 0; + unsigned int slot = iter->folioq_slot; + size_t span = 0, n = iter->count; + + if (WARN_ON(!iov_iter_is_folioq(iter)) || + WARN_ON(start_offset > n) || + n == 0) + return 0; + max_size = umin(max_size, n - start_offset); + + if (slot >= folioq_nr_slots(folioq)) { + folioq = folioq->next; + slot = 0; + } + + start_offset += iter->iov_offset; + do { + size_t flen = folioq_folio_size(folioq, slot); + + if (start_offset < flen) { + span += flen - start_offset; + nsegs++; + start_offset = 0; + } else { + start_offset -= flen; + } + if (span >= max_size || nsegs >= max_segs) + break; + + slot++; + if (slot >= folioq_nr_slots(folioq)) { + folioq = folioq->next; + slot = 0; + } + } while (folioq); + + return umin(span, max_size); +} + size_t netfs_limit_iter(const struct iov_iter *iter, size_t start_offset, size_t max_size, size_t max_segs) { + if (iov_iter_is_folioq(iter)) + return netfs_limit_folioq(iter, start_offset, max_size, max_segs); if (iov_iter_is_bvec(iter)) return netfs_limit_bvec(iter, start_offset, max_size, max_segs); if (iov_iter_is_xarray(iter)) diff --git a/fs/netfs/main.c b/fs/netfs/main.c index 1ee712bb3610..4f7212ca3470 100644 --- a/fs/netfs/main.c +++ b/fs/netfs/main.c @@ -36,12 +36,14 @@ DEFINE_SPINLOCK(netfs_proc_lock); static const char *netfs_origins[nr__netfs_io_origin] = { [NETFS_READAHEAD] = "RA", [NETFS_READPAGE] = "RP", + [NETFS_READ_GAPS] = "RG", [NETFS_READ_FOR_WRITE] = "RW", [NETFS_DIO_READ] = "DR", [NETFS_WRITEBACK] = "WB", [NETFS_WRITETHROUGH] = "WT", [NETFS_UNBUFFERED_WRITE] = "UW", [NETFS_DIO_WRITE] = "DW", + [NETFS_PGPRIV2_COPY_TO_CACHE] = "2C", }; /* @@ -61,7 +63,7 @@ static int netfs_requests_seq_show(struct seq_file *m, void *v) rreq = list_entry(v, struct netfs_io_request, proc_link); seq_printf(m, - "%08x %s %3d %2lx %4d %3d @%04llx %llx/%llx", + "%08x %s %3d %2lx %4ld %3d @%04llx %llx/%llx", rreq->debug_id, netfs_origins[rreq->origin], refcount_read(&rreq->ref), diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c index 4291cd405fc1..31e388ec6e48 100644 --- a/fs/netfs/objects.c +++ b/fs/netfs/objects.c @@ -36,7 +36,6 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, memset(rreq, 0, kmem_cache_size(cache)); rreq->start = start; rreq->len = len; - rreq->upper_len = len; rreq->origin = origin; rreq->netfs_ops = ctx->ops; rreq->mapping = mapping; @@ -44,6 +43,8 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, rreq->i_size = i_size_read(inode); rreq->debug_id = atomic_inc_return(&debug_ids); rreq->wsize = INT_MAX; + rreq->io_streams[0].sreq_max_len = ULONG_MAX; + rreq->io_streams[0].sreq_max_segs = 0; spin_lock_init(&rreq->lock); INIT_LIST_HEAD(&rreq->io_streams[0].subrequests); INIT_LIST_HEAD(&rreq->io_streams[1].subrequests); @@ -52,9 +53,10 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, if (origin == NETFS_READAHEAD || origin == NETFS_READPAGE || + origin == NETFS_READ_GAPS || origin == NETFS_READ_FOR_WRITE || origin == NETFS_DIO_READ) - INIT_WORK(&rreq->work, netfs_rreq_work); + INIT_WORK(&rreq->work, netfs_read_termination_worker); else INIT_WORK(&rreq->work, netfs_write_collection_worker); @@ -163,7 +165,7 @@ void netfs_put_request(struct netfs_io_request *rreq, bool was_async, if (was_async) { rreq->work.func = netfs_free_request; if (!queue_work(system_unbound_wq, &rreq->work)) - BUG(); + WARN_ON(1); } else { netfs_free_request(&rreq->work); } diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c new file mode 100644 index 000000000000..b18c65ba5580 --- /dev/null +++ b/fs/netfs/read_collect.c @@ -0,0 +1,544 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Network filesystem read subrequest result collection, assessment and + * retrying. + * + * Copyright (C) 2024 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include +#include +#include +#include +#include +#include +#include "internal.h" + +/* + * Clear the unread part of an I/O request. + */ +static void netfs_clear_unread(struct netfs_io_subrequest *subreq) +{ + netfs_reset_iter(subreq); + WARN_ON_ONCE(subreq->len - subreq->transferred != iov_iter_count(&subreq->io_iter)); + iov_iter_zero(iov_iter_count(&subreq->io_iter), &subreq->io_iter); + if (subreq->start + subreq->transferred >= subreq->rreq->i_size) + __set_bit(NETFS_SREQ_HIT_EOF, &subreq->flags); +} + +/* + * Flush, mark and unlock a folio that's now completely read. If we want to + * cache the folio, we set the group to NETFS_FOLIO_COPY_TO_CACHE, mark it + * dirty and let writeback handle it. + */ +static void netfs_unlock_read_folio(struct netfs_io_subrequest *subreq, + struct netfs_io_request *rreq, + struct folio_queue *folioq, + int slot) +{ + struct netfs_folio *finfo; + struct folio *folio = folioq_folio(folioq, slot); + + flush_dcache_folio(folio); + folio_mark_uptodate(folio); + + if (!test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) { + finfo = netfs_folio_info(folio); + if (finfo) { + trace_netfs_folio(folio, netfs_folio_trace_filled_gaps); + if (finfo->netfs_group) + folio_change_private(folio, finfo->netfs_group); + else + folio_detach_private(folio); + kfree(finfo); + } + + if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) { + if (!WARN_ON_ONCE(folio_get_private(folio) != NULL)) { + trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); + folio_attach_private(folio, NETFS_FOLIO_COPY_TO_CACHE); + folio_mark_dirty(folio); + } + } else { + trace_netfs_folio(folio, netfs_folio_trace_read_done); + } + } else { + // TODO: Use of PG_private_2 is deprecated. + if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) + netfs_pgpriv2_mark_copy_to_cache(subreq, rreq, folioq, slot); + } + + if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) { + if (folio->index == rreq->no_unlock_folio && + test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) { + _debug("no unlock"); + } else { + trace_netfs_folio(folio, netfs_folio_trace_read_unlock); + folio_unlock(folio); + } + } +} + +/* + * Unlock any folios that are now completely read. Returns true if the + * subrequest is removed from the list. + */ +static bool netfs_consume_read_data(struct netfs_io_subrequest *subreq, bool was_async) +{ + struct netfs_io_subrequest *prev, *next; + struct netfs_io_request *rreq = subreq->rreq; + struct folio_queue *folioq = subreq->curr_folioq; + size_t avail, prev_donated, next_donated, fsize, part, excess; + loff_t fpos, start; + loff_t fend; + int slot = subreq->curr_folioq_slot; + + if (WARN(subreq->transferred > subreq->len, + "Subreq overread: R%x[%x] %zu > %zu", + rreq->debug_id, subreq->debug_index, + subreq->transferred, subreq->len)) + subreq->transferred = subreq->len; + +next_folio: + fsize = PAGE_SIZE << subreq->curr_folio_order; + fpos = round_down(subreq->start + subreq->consumed, fsize); + fend = fpos + fsize; + + if (WARN_ON_ONCE(!folioq) || + WARN_ON_ONCE(!folioq_folio(folioq, slot)) || + WARN_ON_ONCE(folioq_folio(folioq, slot)->index != fpos / PAGE_SIZE)) { + pr_err("R=%08x[%x] s=%llx-%llx ctl=%zx/%zx/%zx sl=%u\n", + rreq->debug_id, subreq->debug_index, + subreq->start, subreq->start + subreq->transferred - 1, + subreq->consumed, subreq->transferred, subreq->len, + slot); + if (folioq) { + struct folio *folio = folioq_folio(folioq, slot); + + pr_err("folioq: orders=%02x%02x%02x%02x\n", + folioq->orders[0], folioq->orders[1], + folioq->orders[2], folioq->orders[3]); + if (folio) + pr_err("folio: %llx-%llx ix=%llx o=%u qo=%u\n", + fpos, fend - 1, folio_pos(folio), folio_order(folio), + folioq_folio_order(folioq, slot)); + } + } + +donation_changed: + /* Try to consume the current folio if we've hit or passed the end of + * it. There's a possibility that this subreq doesn't start at the + * beginning of the folio, in which case we need to donate to/from the + * preceding subreq. + * + * We also need to include any potential donation back from the + * following subreq. + */ + prev_donated = READ_ONCE(subreq->prev_donated); + next_donated = READ_ONCE(subreq->next_donated); + if (prev_donated || next_donated) { + spin_lock_bh(&rreq->lock); + prev_donated = subreq->prev_donated; + next_donated = subreq->next_donated; + subreq->start -= prev_donated; + subreq->len += prev_donated; + subreq->transferred += prev_donated; + prev_donated = subreq->prev_donated = 0; + if (subreq->transferred == subreq->len) { + subreq->len += next_donated; + subreq->transferred += next_donated; + next_donated = subreq->next_donated = 0; + } + trace_netfs_sreq(subreq, netfs_sreq_trace_add_donations); + spin_unlock_bh(&rreq->lock); + } + + avail = subreq->transferred; + if (avail == subreq->len) + avail += next_donated; + start = subreq->start; + if (subreq->consumed == 0) { + start -= prev_donated; + avail += prev_donated; + } else { + start += subreq->consumed; + avail -= subreq->consumed; + } + part = umin(avail, fsize); + + trace_netfs_progress(subreq, start, avail, part); + + if (start + avail >= fend) { + if (fpos == start) { + /* Flush, unlock and mark for caching any folio we've just read. */ + subreq->consumed = fend - subreq->start; + netfs_unlock_read_folio(subreq, rreq, folioq, slot); + folioq_mark2(folioq, slot); + if (subreq->consumed >= subreq->len) + goto remove_subreq; + } else if (fpos < start) { + excess = fend - subreq->start; + + spin_lock_bh(&rreq->lock); + /* If we complete first on a folio split with the + * preceding subreq, donate to that subreq - otherwise + * we get the responsibility. + */ + if (subreq->prev_donated != prev_donated) { + spin_unlock_bh(&rreq->lock); + goto donation_changed; + } + + if (list_is_first(&subreq->rreq_link, &rreq->subrequests)) { + spin_unlock_bh(&rreq->lock); + pr_err("Can't donate prior to front\n"); + goto bad; + } + + prev = list_prev_entry(subreq, rreq_link); + WRITE_ONCE(prev->next_donated, prev->next_donated + excess); + subreq->start += excess; + subreq->len -= excess; + subreq->transferred -= excess; + trace_netfs_donate(rreq, subreq, prev, excess, + netfs_trace_donate_tail_to_prev); + trace_netfs_sreq(subreq, netfs_sreq_trace_donate_to_prev); + + if (subreq->consumed >= subreq->len) + goto remove_subreq_locked; + spin_unlock_bh(&rreq->lock); + } else { + pr_err("fpos > start\n"); + goto bad; + } + + /* Advance the rolling buffer to the next folio. */ + slot++; + if (slot >= folioq_nr_slots(folioq)) { + slot = 0; + folioq = folioq->next; + subreq->curr_folioq = folioq; + } + subreq->curr_folioq_slot = slot; + if (folioq && folioq_folio(folioq, slot)) + subreq->curr_folio_order = folioq->orders[slot]; + if (!was_async) + cond_resched(); + goto next_folio; + } + + /* Deal with partial progress. */ + if (subreq->transferred < subreq->len) + return false; + + /* Donate the remaining downloaded data to one of the neighbouring + * subrequests. Note that we may race with them doing the same thing. + */ + spin_lock_bh(&rreq->lock); + + if (subreq->prev_donated != prev_donated || + subreq->next_donated != next_donated) { + spin_unlock_bh(&rreq->lock); + cond_resched(); + goto donation_changed; + } + + /* Deal with the trickiest case: that this subreq is in the middle of a + * folio, not touching either edge, but finishes first. In such a + * case, we donate to the previous subreq, if there is one, so that the + * donation is only handled when that completes - and remove this + * subreq from the list. + * + * If the previous subreq finished first, we will have acquired their + * donation and should be able to unlock folios and/or donate nextwards. + */ + if (!subreq->consumed && + !prev_donated && + !list_is_first(&subreq->rreq_link, &rreq->subrequests)) { + prev = list_prev_entry(subreq, rreq_link); + WRITE_ONCE(prev->next_donated, prev->next_donated + subreq->len); + subreq->start += subreq->len; + subreq->len = 0; + subreq->transferred = 0; + trace_netfs_donate(rreq, subreq, prev, subreq->len, + netfs_trace_donate_to_prev); + trace_netfs_sreq(subreq, netfs_sreq_trace_donate_to_prev); + goto remove_subreq_locked; + } + + /* If we can't donate down the chain, donate up the chain instead. */ + excess = subreq->len - subreq->consumed + next_donated; + + if (!subreq->consumed) + excess += prev_donated; + + if (list_is_last(&subreq->rreq_link, &rreq->subrequests)) { + rreq->prev_donated = excess; + trace_netfs_donate(rreq, subreq, NULL, excess, + netfs_trace_donate_to_deferred_next); + } else { + next = list_next_entry(subreq, rreq_link); + WRITE_ONCE(next->prev_donated, excess); + trace_netfs_donate(rreq, subreq, next, excess, + netfs_trace_donate_to_next); + } + trace_netfs_sreq(subreq, netfs_sreq_trace_donate_to_next); + subreq->len = subreq->consumed; + subreq->transferred = subreq->consumed; + goto remove_subreq_locked; + +remove_subreq: + spin_lock_bh(&rreq->lock); +remove_subreq_locked: + subreq->consumed = subreq->len; + list_del(&subreq->rreq_link); + spin_unlock_bh(&rreq->lock); + netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_consumed); + return true; + +bad: + /* Errr... prev and next both donated to us, but insufficient to finish + * the folio. + */ + printk("R=%08x[%x] s=%llx-%llx %zx/%zx/%zx\n", + rreq->debug_id, subreq->debug_index, + subreq->start, subreq->start + subreq->transferred - 1, + subreq->consumed, subreq->transferred, subreq->len); + printk("folio: %llx-%llx\n", fpos, fend - 1); + printk("donated: prev=%zx next=%zx\n", prev_donated, next_donated); + printk("s=%llx av=%zx part=%zx\n", start, avail, part); + BUG(); +} + +/* + * Do page flushing and suchlike after DIO. + */ +static void netfs_rreq_assess_dio(struct netfs_io_request *rreq) +{ + struct netfs_io_subrequest *subreq; + unsigned int i; + + /* Collect unbuffered reads and direct reads, adding up the transfer + * sizes until we find the first short or failed subrequest. + */ + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + rreq->transferred += subreq->transferred; + + if (subreq->transferred < subreq->len || + test_bit(NETFS_SREQ_FAILED, &subreq->flags)) { + rreq->error = subreq->error; + break; + } + } + + if (rreq->origin == NETFS_DIO_READ) { + for (i = 0; i < rreq->direct_bv_count; i++) { + flush_dcache_page(rreq->direct_bv[i].bv_page); + // TODO: cifs marks pages in the destination buffer + // dirty under some circumstances after a read. Do we + // need to do that too? + set_page_dirty(rreq->direct_bv[i].bv_page); + } + } + + if (rreq->iocb) { + rreq->iocb->ki_pos += rreq->transferred; + if (rreq->iocb->ki_complete) + rreq->iocb->ki_complete( + rreq->iocb, rreq->error ? rreq->error : rreq->transferred); + } + if (rreq->netfs_ops->done) + rreq->netfs_ops->done(rreq); + if (rreq->origin == NETFS_DIO_READ) + inode_dio_end(rreq->inode); +} + +/* + * Assess the state of a read request and decide what to do next. + * + * Note that we're in normal kernel thread context at this point, possibly + * running on a workqueue. + */ +static void netfs_rreq_assess(struct netfs_io_request *rreq) +{ + trace_netfs_rreq(rreq, netfs_rreq_trace_assess); + + //netfs_rreq_is_still_valid(rreq); + + if (test_and_clear_bit(NETFS_RREQ_NEED_RETRY, &rreq->flags)) { + netfs_retry_reads(rreq); + return; + } + + if (rreq->origin == NETFS_DIO_READ || + rreq->origin == NETFS_READ_GAPS) + netfs_rreq_assess_dio(rreq); + task_io_account_read(rreq->transferred); + + trace_netfs_rreq(rreq, netfs_rreq_trace_wake_ip); + clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags); + wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS); + + trace_netfs_rreq(rreq, netfs_rreq_trace_done); + netfs_clear_subrequests(rreq, false); + netfs_unlock_abandoned_read_pages(rreq); + if (unlikely(test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags))) + netfs_pgpriv2_write_to_the_cache(rreq); +} + +void netfs_read_termination_worker(struct work_struct *work) +{ + struct netfs_io_request *rreq = + container_of(work, struct netfs_io_request, work); + netfs_see_request(rreq, netfs_rreq_trace_see_work); + netfs_rreq_assess(rreq); + netfs_put_request(rreq, false, netfs_rreq_trace_put_work_complete); +} + +/* + * Handle the completion of all outstanding I/O operations on a read request. + * We inherit a ref from the caller. + */ +void netfs_rreq_terminated(struct netfs_io_request *rreq, bool was_async) +{ + if (!was_async) + return netfs_rreq_assess(rreq); + if (!work_pending(&rreq->work)) { + netfs_get_request(rreq, netfs_rreq_trace_get_work); + if (!queue_work(system_unbound_wq, &rreq->work)) + netfs_put_request(rreq, was_async, netfs_rreq_trace_put_work_nq); + } +} + +/** + * netfs_read_subreq_progress - Note progress of a read operation. + * @subreq: The read request that has terminated. + * @was_async: True if we're in an asynchronous context. + * + * This tells the read side of netfs lib that a contributory I/O operation has + * made some progress and that it may be possible to unlock some folios. + * + * Before calling, the filesystem should update subreq->transferred to track + * the amount of data copied into the output buffer. + * + * If @was_async is true, the caller might be running in softirq or interrupt + * context and we can't sleep. + */ +void netfs_read_subreq_progress(struct netfs_io_subrequest *subreq, + bool was_async) +{ + struct netfs_io_request *rreq = subreq->rreq; + + trace_netfs_sreq(subreq, netfs_sreq_trace_progress); + + if (subreq->transferred > subreq->consumed && + (rreq->origin == NETFS_READAHEAD || + rreq->origin == NETFS_READPAGE || + rreq->origin == NETFS_READ_FOR_WRITE)) { + netfs_consume_read_data(subreq, was_async); + __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); + } +} +EXPORT_SYMBOL(netfs_read_subreq_progress); + +/** + * netfs_read_subreq_terminated - Note the termination of an I/O operation. + * @subreq: The I/O request that has terminated. + * @error: Error code indicating type of completion. + * @was_async: The termination was asynchronous + * + * This tells the read helper that a contributory I/O operation has terminated, + * one way or another, and that it should integrate the results. + * + * The caller indicates the outcome of the operation through @error, supplying + * 0 to indicate a successful or retryable transfer (if NETFS_SREQ_NEED_RETRY + * is set) or a negative error code. The helper will look after reissuing I/O + * operations as appropriate and writing downloaded data to the cache. + * + * Before calling, the filesystem should update subreq->transferred to track + * the amount of data copied into the output buffer. + * + * If @was_async is true, the caller might be running in softirq or interrupt + * context and we can't sleep. + */ +void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq, + int error, bool was_async) +{ + struct netfs_io_request *rreq = subreq->rreq; + + switch (subreq->source) { + case NETFS_READ_FROM_CACHE: + netfs_stat(&netfs_n_rh_read_done); + break; + case NETFS_DOWNLOAD_FROM_SERVER: + netfs_stat(&netfs_n_rh_download_done); + break; + default: + break; + } + + if (rreq->origin != NETFS_DIO_READ) { + /* Collect buffered reads. + * + * If the read completed validly short, then we can clear the + * tail before going on to unlock the folios. + */ + if (error == 0 && subreq->transferred < subreq->len && + (test_bit(NETFS_SREQ_HIT_EOF, &subreq->flags) || + test_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags))) { + netfs_clear_unread(subreq); + subreq->transferred = subreq->len; + trace_netfs_sreq(subreq, netfs_sreq_trace_clear); + } + if (subreq->transferred > subreq->consumed && + (rreq->origin == NETFS_READAHEAD || + rreq->origin == NETFS_READPAGE || + rreq->origin == NETFS_READ_FOR_WRITE)) { + netfs_consume_read_data(subreq, was_async); + __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); + } + rreq->transferred += subreq->transferred; + } + + /* Deal with retry requests, short reads and errors. If we retry + * but don't make progress, we abandon the attempt. + */ + if (!error && subreq->transferred < subreq->len) { + if (test_bit(NETFS_SREQ_HIT_EOF, &subreq->flags)) { + trace_netfs_sreq(subreq, netfs_sreq_trace_hit_eof); + } else { + trace_netfs_sreq(subreq, netfs_sreq_trace_short); + if (subreq->transferred > subreq->consumed) { + __set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); + __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); + set_bit(NETFS_RREQ_NEED_RETRY, &rreq->flags); + } else if (!__test_and_set_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags)) { + __set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); + set_bit(NETFS_RREQ_NEED_RETRY, &rreq->flags); + } else { + __set_bit(NETFS_SREQ_FAILED, &subreq->flags); + error = -ENODATA; + } + } + } + + subreq->error = error; + trace_netfs_sreq(subreq, netfs_sreq_trace_terminated); + + if (unlikely(error < 0)) { + trace_netfs_failure(rreq, subreq, error, netfs_fail_read); + if (subreq->source == NETFS_READ_FROM_CACHE) { + netfs_stat(&netfs_n_rh_read_failed); + } else { + netfs_stat(&netfs_n_rh_download_failed); + set_bit(NETFS_RREQ_FAILED, &rreq->flags); + rreq->error = subreq->error; + } + } + + if (atomic_dec_and_test(&rreq->nr_outstanding)) + netfs_rreq_terminated(rreq, was_async); + + netfs_put_subrequest(subreq, was_async, netfs_sreq_trace_put_terminated); +} +EXPORT_SYMBOL(netfs_read_subreq_terminated); diff --git a/fs/netfs/read_pgpriv2.c b/fs/netfs/read_pgpriv2.c new file mode 100644 index 000000000000..9439461d535f --- /dev/null +++ b/fs/netfs/read_pgpriv2.c @@ -0,0 +1,264 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Read with PG_private_2 [DEPRECATED]. + * + * Copyright (C) 2024 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include +#include +#include +#include +#include +#include +#include "internal.h" + +/* + * [DEPRECATED] Mark page as requiring copy-to-cache using PG_private_2. The + * third mark in the folio queue is used to indicate that this folio needs + * writing. + */ +void netfs_pgpriv2_mark_copy_to_cache(struct netfs_io_subrequest *subreq, + struct netfs_io_request *rreq, + struct folio_queue *folioq, + int slot) +{ + struct folio *folio = folioq_folio(folioq, slot); + + trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); + folio_start_private_2(folio); + folioq_mark3(folioq, slot); +} + +/* + * [DEPRECATED] Cancel PG_private_2 on all marked folios in the event of an + * unrecoverable error. + */ +static void netfs_pgpriv2_cancel(struct folio_queue *folioq) +{ + struct folio *folio; + int slot; + + while (folioq) { + if (!folioq->marks3) { + folioq = folioq->next; + continue; + } + + slot = __ffs(folioq->marks3); + folio = folioq_folio(folioq, slot); + + trace_netfs_folio(folio, netfs_folio_trace_cancel_copy); + folio_end_private_2(folio); + folioq_unmark3(folioq, slot); + } +} + +/* + * [DEPRECATED] Copy a folio to the cache with PG_private_2 set. + */ +static int netfs_pgpriv2_copy_folio(struct netfs_io_request *wreq, struct folio *folio) +{ + struct netfs_io_stream *cache = &wreq->io_streams[1]; + size_t fsize = folio_size(folio), flen = fsize; + loff_t fpos = folio_pos(folio), i_size; + bool to_eof = false; + + _enter(""); + + /* netfs_perform_write() may shift i_size around the page or from out + * of the page to beyond it, but cannot move i_size into or through the + * page since we have it locked. + */ + i_size = i_size_read(wreq->inode); + + if (fpos >= i_size) { + /* mmap beyond eof. */ + _debug("beyond eof"); + folio_end_private_2(folio); + return 0; + } + + if (fpos + fsize > wreq->i_size) + wreq->i_size = i_size; + + if (flen > i_size - fpos) { + flen = i_size - fpos; + to_eof = true; + } else if (flen == i_size - fpos) { + to_eof = true; + } + + _debug("folio %zx %zx", flen, fsize); + + trace_netfs_folio(folio, netfs_folio_trace_store_copy); + + /* Attach the folio to the rolling buffer. */ + if (netfs_buffer_append_folio(wreq, folio, false) < 0) + return -ENOMEM; + + cache->submit_max_len = fsize; + cache->submit_off = 0; + cache->submit_len = flen; + + /* Attach the folio to one or more subrequests. For a big folio, we + * could end up with thousands of subrequests if the wsize is small - + * but we might need to wait during the creation of subrequests for + * network resources (eg. SMB credits). + */ + do { + ssize_t part; + + wreq->io_iter.iov_offset = cache->submit_off; + + atomic64_set(&wreq->issued_to, fpos + cache->submit_off); + part = netfs_advance_write(wreq, cache, fpos + cache->submit_off, + cache->submit_len, to_eof); + cache->submit_off += part; + cache->submit_max_len -= part; + if (part > cache->submit_len) + cache->submit_len = 0; + else + cache->submit_len -= part; + } while (cache->submit_len > 0); + + wreq->io_iter.iov_offset = 0; + iov_iter_advance(&wreq->io_iter, fsize); + atomic64_set(&wreq->issued_to, fpos + fsize); + + if (flen < fsize) + netfs_issue_write(wreq, cache); + + _leave(" = 0"); + return 0; +} + +/* + * [DEPRECATED] Go through the buffer and write any folios that are marked with + * the third mark to the cache. + */ +void netfs_pgpriv2_write_to_the_cache(struct netfs_io_request *rreq) +{ + struct netfs_io_request *wreq; + struct folio_queue *folioq; + struct folio *folio; + int error = 0; + int slot = 0; + + _enter(""); + + if (!fscache_resources_valid(&rreq->cache_resources)) + goto couldnt_start; + + /* Need the first folio to be able to set up the op. */ + for (folioq = rreq->buffer; folioq; folioq = folioq->next) { + if (folioq->marks3) { + slot = __ffs(folioq->marks3); + break; + } + } + if (!folioq) + return; + folio = folioq_folio(folioq, slot); + + wreq = netfs_create_write_req(rreq->mapping, NULL, folio_pos(folio), + NETFS_PGPRIV2_COPY_TO_CACHE); + if (IS_ERR(wreq)) { + kleave(" [create %ld]", PTR_ERR(wreq)); + goto couldnt_start; + } + + trace_netfs_write(wreq, netfs_write_trace_copy_to_cache); + netfs_stat(&netfs_n_wh_copy_to_cache); + + for (;;) { + error = netfs_pgpriv2_copy_folio(wreq, folio); + if (error < 0) + break; + + folioq_unmark3(folioq, slot); + if (!folioq->marks3) { + folioq = folioq->next; + if (!folioq) + break; + } + + slot = __ffs(folioq->marks3); + folio = folioq_folio(folioq, slot); + } + + netfs_issue_write(wreq, &wreq->io_streams[1]); + smp_wmb(); /* Write lists before ALL_QUEUED. */ + set_bit(NETFS_RREQ_ALL_QUEUED, &wreq->flags); + + netfs_put_request(wreq, false, netfs_rreq_trace_put_return); + _leave(" = %d", error); +couldnt_start: + netfs_pgpriv2_cancel(rreq->buffer); +} + +/* + * [DEPRECATED] Remove the PG_private_2 mark from any folios we've finished + * copying. + */ +bool netfs_pgpriv2_unlock_copied_folios(struct netfs_io_request *wreq) +{ + struct folio_queue *folioq = wreq->buffer; + unsigned long long collected_to = wreq->collected_to; + unsigned int slot = wreq->buffer_head_slot; + bool made_progress = false; + + if (slot >= folioq_nr_slots(folioq)) { + folioq = netfs_delete_buffer_head(wreq); + slot = 0; + } + + for (;;) { + struct folio *folio; + unsigned long long fpos, fend; + size_t fsize, flen; + + folio = folioq_folio(folioq, slot); + if (WARN_ONCE(!folio_test_private_2(folio), + "R=%08x: folio %lx is not marked private_2\n", + wreq->debug_id, folio->index)) + trace_netfs_folio(folio, netfs_folio_trace_not_under_wback); + + fpos = folio_pos(folio); + fsize = folio_size(folio); + flen = fsize; + + fend = min_t(unsigned long long, fpos + flen, wreq->i_size); + + trace_netfs_collect_folio(wreq, folio, fend, collected_to); + + /* Unlock any folio we've transferred all of. */ + if (collected_to < fend) + break; + + trace_netfs_folio(folio, netfs_folio_trace_end_copy); + folio_end_private_2(folio); + wreq->cleaned_to = fpos + fsize; + made_progress = true; + + /* Clean up the head folioq. If we clear an entire folioq, then + * we can get rid of it provided it's not also the tail folioq + * being filled by the issuer. + */ + folioq_clear(folioq, slot); + slot++; + if (slot >= folioq_nr_slots(folioq)) { + if (READ_ONCE(wreq->buffer_tail) == folioq) + break; + folioq = netfs_delete_buffer_head(wreq); + slot = 0; + } + + if (fpos + fsize >= collected_to) + break; + } + + wreq->buffer = folioq; + wreq->buffer_head_slot = slot; + return made_progress; +} diff --git a/fs/netfs/read_retry.c b/fs/netfs/read_retry.c new file mode 100644 index 000000000000..0350592ea804 --- /dev/null +++ b/fs/netfs/read_retry.c @@ -0,0 +1,256 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Network filesystem read subrequest retrying. + * + * Copyright (C) 2024 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include +#include +#include "internal.h" + +static void netfs_reissue_read(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq) +{ + struct iov_iter *io_iter = &subreq->io_iter; + + if (iov_iter_is_folioq(io_iter)) { + subreq->curr_folioq = (struct folio_queue *)io_iter->folioq; + subreq->curr_folioq_slot = io_iter->folioq_slot; + subreq->curr_folio_order = subreq->curr_folioq->orders[subreq->curr_folioq_slot]; + } + + atomic_inc(&rreq->nr_outstanding); + __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); + netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); + subreq->rreq->netfs_ops->issue_read(subreq); +} + +/* + * Go through the list of failed/short reads, retrying all retryable ones. We + * need to switch failed cache reads to network downloads. + */ +static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) +{ + struct netfs_io_subrequest *subreq; + struct netfs_io_stream *stream0 = &rreq->io_streams[0]; + LIST_HEAD(sublist); + LIST_HEAD(queue); + + _enter("R=%x", rreq->debug_id); + + if (list_empty(&rreq->subrequests)) + return; + + if (rreq->netfs_ops->retry_request) + rreq->netfs_ops->retry_request(rreq, NULL); + + /* If there's no renegotiation to do, just resend each retryable subreq + * up to the first permanently failed one. + */ + if (!rreq->netfs_ops->prepare_read && + !test_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags)) { + struct netfs_io_subrequest *subreq; + + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + if (test_bit(NETFS_SREQ_FAILED, &subreq->flags)) + break; + if (__test_and_clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) { + netfs_reset_iter(subreq); + netfs_reissue_read(rreq, subreq); + } + } + return; + } + + /* Okay, we need to renegotiate all the download requests and flip any + * failed cache reads over to being download requests and negotiate + * those also. All fully successful subreqs have been removed from the + * list and any spare data from those has been donated. + * + * What we do is decant the list and rebuild it one subreq at a time so + * that we don't end up with donations jumping over a gap we're busy + * populating with smaller subrequests. In the event that the subreq + * we just launched finishes before we insert the next subreq, it'll + * fill in rreq->prev_donated instead. + + * Note: Alternatively, we could split the tail subrequest right before + * we reissue it and fix up the donations under lock. + */ + list_splice_init(&rreq->subrequests, &queue); + + do { + struct netfs_io_subrequest *from; + struct iov_iter source; + unsigned long long start, len; + size_t part, deferred_next_donated = 0; + bool boundary = false; + + /* Go through the subreqs and find the next span of contiguous + * buffer that we then rejig (cifs, for example, needs the + * rsize renegotiating) and reissue. + */ + from = list_first_entry(&queue, struct netfs_io_subrequest, rreq_link); + list_move_tail(&from->rreq_link, &sublist); + start = from->start + from->transferred; + len = from->len - from->transferred; + + _debug("from R=%08x[%x] s=%llx ctl=%zx/%zx/%zx", + rreq->debug_id, from->debug_index, + from->start, from->consumed, from->transferred, from->len); + + if (test_bit(NETFS_SREQ_FAILED, &from->flags) || + !test_bit(NETFS_SREQ_NEED_RETRY, &from->flags)) + goto abandon; + + deferred_next_donated = from->next_donated; + while ((subreq = list_first_entry_or_null( + &queue, struct netfs_io_subrequest, rreq_link))) { + if (subreq->start != start + len || + subreq->transferred > 0 || + !test_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) + break; + list_move_tail(&subreq->rreq_link, &sublist); + len += subreq->len; + deferred_next_donated = subreq->next_donated; + if (test_bit(NETFS_SREQ_BOUNDARY, &subreq->flags)) + break; + } + + _debug(" - range: %llx-%llx %llx", start, start + len - 1, len); + + /* Determine the set of buffers we're going to use. Each + * subreq gets a subset of a single overall contiguous buffer. + */ + netfs_reset_iter(from); + source = from->io_iter; + source.count = len; + + /* Work through the sublist. */ + while ((subreq = list_first_entry_or_null( + &sublist, struct netfs_io_subrequest, rreq_link))) { + list_del(&subreq->rreq_link); + + subreq->source = NETFS_DOWNLOAD_FROM_SERVER; + subreq->start = start - subreq->transferred; + subreq->len = len + subreq->transferred; + stream0->sreq_max_len = subreq->len; + + __clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); + __set_bit(NETFS_SREQ_RETRYING, &subreq->flags); + + spin_lock_bh(&rreq->lock); + list_add_tail(&subreq->rreq_link, &rreq->subrequests); + subreq->prev_donated += rreq->prev_donated; + rreq->prev_donated = 0; + trace_netfs_sreq(subreq, netfs_sreq_trace_retry); + spin_unlock_bh(&rreq->lock); + + BUG_ON(!len); + + /* Renegotiate max_len (rsize) */ + if (rreq->netfs_ops->prepare_read(subreq) < 0) { + trace_netfs_sreq(subreq, netfs_sreq_trace_reprep_failed); + __set_bit(NETFS_SREQ_FAILED, &subreq->flags); + } + + part = umin(len, stream0->sreq_max_len); + if (unlikely(rreq->io_streams[0].sreq_max_segs)) + part = netfs_limit_iter(&source, 0, part, stream0->sreq_max_segs); + subreq->len = subreq->transferred + part; + subreq->io_iter = source; + iov_iter_truncate(&subreq->io_iter, part); + iov_iter_advance(&source, part); + len -= part; + start += part; + if (!len) { + if (boundary) + __set_bit(NETFS_SREQ_BOUNDARY, &subreq->flags); + subreq->next_donated = deferred_next_donated; + } else { + __clear_bit(NETFS_SREQ_BOUNDARY, &subreq->flags); + subreq->next_donated = 0; + } + + netfs_reissue_read(rreq, subreq); + if (!len) + break; + + /* If we ran out of subrequests, allocate another. */ + if (list_empty(&sublist)) { + subreq = netfs_alloc_subrequest(rreq); + if (!subreq) + goto abandon; + subreq->source = NETFS_DOWNLOAD_FROM_SERVER; + subreq->start = start; + + /* We get two refs, but need just one. */ + netfs_put_subrequest(subreq, false, netfs_sreq_trace_new); + trace_netfs_sreq(subreq, netfs_sreq_trace_split); + list_add_tail(&subreq->rreq_link, &sublist); + } + } + + /* If we managed to use fewer subreqs, we can discard the + * excess. + */ + while ((subreq = list_first_entry_or_null( + &sublist, struct netfs_io_subrequest, rreq_link))) { + trace_netfs_sreq(subreq, netfs_sreq_trace_discard); + list_del(&subreq->rreq_link); + netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_done); + } + + } while (!list_empty(&queue)); + + return; + + /* If we hit ENOMEM, fail all remaining subrequests */ +abandon: + list_splice_init(&sublist, &queue); + list_for_each_entry(subreq, &queue, rreq_link) { + if (!subreq->error) + subreq->error = -ENOMEM; + __clear_bit(NETFS_SREQ_FAILED, &subreq->flags); + __clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); + __clear_bit(NETFS_SREQ_RETRYING, &subreq->flags); + } + spin_lock_bh(&rreq->lock); + list_splice_tail_init(&queue, &rreq->subrequests); + spin_unlock_bh(&rreq->lock); +} + +/* + * Retry reads. + */ +void netfs_retry_reads(struct netfs_io_request *rreq) +{ + trace_netfs_rreq(rreq, netfs_rreq_trace_resubmit); + + atomic_inc(&rreq->nr_outstanding); + + netfs_retry_read_subrequests(rreq); + + if (atomic_dec_and_test(&rreq->nr_outstanding)) + netfs_rreq_terminated(rreq, false); +} + +/* + * Unlock any the pages that haven't been unlocked yet due to abandoned + * subrequests. + */ +void netfs_unlock_abandoned_read_pages(struct netfs_io_request *rreq) +{ + struct folio_queue *p; + + for (p = rreq->buffer; p; p = p->next) { + for (int slot = 0; slot < folioq_count(p); slot++) { + struct folio *folio = folioq_folio(p, slot); + + if (folio && !folioq_is_marked2(p, slot)) { + trace_netfs_folio(folio, netfs_folio_trace_abandon); + folio_unlock(folio); + } + } + } +} diff --git a/fs/netfs/stats.c b/fs/netfs/stats.c index 5065289f5555..8e63516b40f6 100644 --- a/fs/netfs/stats.c +++ b/fs/netfs/stats.c @@ -32,6 +32,7 @@ atomic_t netfs_n_wh_buffered_write; atomic_t netfs_n_wh_writethrough; atomic_t netfs_n_wh_dio_write; atomic_t netfs_n_wh_writepages; +atomic_t netfs_n_wh_copy_to_cache; atomic_t netfs_n_wh_wstream_conflict; atomic_t netfs_n_wh_upload; atomic_t netfs_n_wh_upload_done; @@ -51,11 +52,12 @@ int netfs_stats_show(struct seq_file *m, void *v) atomic_read(&netfs_n_rh_read_folio), atomic_read(&netfs_n_rh_write_begin), atomic_read(&netfs_n_rh_write_zskip)); - seq_printf(m, "Writes : BW=%u WT=%u DW=%u WP=%u\n", + seq_printf(m, "Writes : BW=%u WT=%u DW=%u WP=%u 2C=%u\n", atomic_read(&netfs_n_wh_buffered_write), atomic_read(&netfs_n_wh_writethrough), atomic_read(&netfs_n_wh_dio_write), - atomic_read(&netfs_n_wh_writepages)); + atomic_read(&netfs_n_wh_writepages), + atomic_read(&netfs_n_wh_copy_to_cache)); seq_printf(m, "ZeroOps: ZR=%u sh=%u sk=%u\n", atomic_read(&netfs_n_rh_zero), atomic_read(&netfs_n_rh_short_read), diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c index 4280dc6ec035..1d438be2e1b4 100644 --- a/fs/netfs/write_collect.c +++ b/fs/netfs/write_collect.c @@ -87,6 +87,12 @@ static void netfs_writeback_unlock_folios(struct netfs_io_request *wreq, unsigned long long collected_to = wreq->collected_to; unsigned int slot = wreq->buffer_head_slot; + if (wreq->origin == NETFS_PGPRIV2_COPY_TO_CACHE) { + if (netfs_pgpriv2_unlock_copied_folios(wreq)) + *notes |= MADE_PROGRESS; + return; + } + if (slot >= folioq_nr_slots(folioq)) { folioq = netfs_delete_buffer_head(wreq); slot = 0; @@ -383,7 +389,8 @@ reassess_streams: smp_rmb(); collected_to = ULLONG_MAX; if (wreq->origin == NETFS_WRITEBACK || - wreq->origin == NETFS_WRITETHROUGH) + wreq->origin == NETFS_WRITETHROUGH || + wreq->origin == NETFS_PGPRIV2_COPY_TO_CACHE) notes = BUFFERED; else notes = 0; diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 25fb7e166cc0..975436d3dc3f 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -95,7 +95,8 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, struct netfs_io_request *wreq; struct netfs_inode *ictx; bool is_buffered = (origin == NETFS_WRITEBACK || - origin == NETFS_WRITETHROUGH); + origin == NETFS_WRITETHROUGH || + origin == NETFS_PGPRIV2_COPY_TO_CACHE); wreq = netfs_alloc_request(mapping, file, start, 0, origin); if (IS_ERR(wreq)) @@ -161,10 +162,6 @@ static void netfs_prepare_write(struct netfs_io_request *wreq, _enter("R=%x[%x]", wreq->debug_id, subreq->debug_index); - trace_netfs_sreq_ref(wreq->debug_id, subreq->debug_index, - refcount_read(&subreq->ref), - netfs_sreq_trace_new); - trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); stream->sreq_max_len = UINT_MAX; @@ -241,8 +238,8 @@ void netfs_reissue_write(struct netfs_io_stream *stream, netfs_do_issue_write(stream, subreq); } -static void netfs_issue_write(struct netfs_io_request *wreq, - struct netfs_io_stream *stream) +void netfs_issue_write(struct netfs_io_request *wreq, + struct netfs_io_stream *stream) { struct netfs_io_subrequest *subreq = stream->construct; @@ -259,9 +256,9 @@ static void netfs_issue_write(struct netfs_io_request *wreq, * we can avoid overrunning the credits obtained (cifs) and try to parallelise * content-crypto preparation with network writes. */ -static int netfs_advance_write(struct netfs_io_request *wreq, - struct netfs_io_stream *stream, - loff_t start, size_t len, bool to_eof) +int netfs_advance_write(struct netfs_io_request *wreq, + struct netfs_io_stream *stream, + loff_t start, size_t len, bool to_eof) { struct netfs_io_subrequest *subreq = stream->construct; size_t part; diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index 7a558dea75c4..810269ee0a50 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -267,6 +267,7 @@ static int nfs_netfs_init_request(struct netfs_io_request *rreq, struct file *fi rreq->debug_id = atomic_inc_return(&nfs_netfs_debug_id); /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */ __set_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags); + rreq->io_streams[0].sreq_max_len = NFS_SB(rreq->inode->i_sb)->rsize; return 0; } @@ -288,14 +289,6 @@ static struct nfs_netfs_io_data *nfs_netfs_alloc(struct netfs_io_subrequest *sre return netfs; } -static bool nfs_netfs_clamp_length(struct netfs_io_subrequest *sreq) -{ - size_t rsize = NFS_SB(sreq->rreq->inode->i_sb)->rsize; - - sreq->len = min(sreq->len, rsize); - return true; -} - static void nfs_netfs_issue_read(struct netfs_io_subrequest *sreq) { struct nfs_netfs_io_data *netfs; @@ -304,17 +297,18 @@ static void nfs_netfs_issue_read(struct netfs_io_subrequest *sreq) struct nfs_open_context *ctx = sreq->rreq->netfs_priv; struct page *page; unsigned long idx; + pgoff_t start, last; int err; - pgoff_t start = (sreq->start + sreq->transferred) >> PAGE_SHIFT; - pgoff_t last = ((sreq->start + sreq->len - - sreq->transferred - 1) >> PAGE_SHIFT); + + start = (sreq->start + sreq->transferred) >> PAGE_SHIFT; + last = ((sreq->start + sreq->len - sreq->transferred - 1) >> PAGE_SHIFT); nfs_pageio_init_read(&pgio, inode, false, &nfs_async_read_completion_ops); netfs = nfs_netfs_alloc(sreq); if (!netfs) - return netfs_subreq_terminated(sreq, -ENOMEM, false); + return netfs_read_subreq_terminated(sreq, -ENOMEM, false); pgio.pg_netfs = netfs; /* used in completion */ @@ -380,5 +374,4 @@ const struct netfs_request_ops nfs_netfs_ops = { .init_request = nfs_netfs_init_request, .free_request = nfs_netfs_free_request, .issue_read = nfs_netfs_issue_read, - .clamp_length = nfs_netfs_clamp_length }; diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h index e8adae1bc260..772d485e96d3 100644 --- a/fs/nfs/fscache.h +++ b/fs/nfs/fscache.h @@ -60,8 +60,6 @@ static inline void nfs_netfs_get(struct nfs_netfs_io_data *netfs) static inline void nfs_netfs_put(struct nfs_netfs_io_data *netfs) { - ssize_t final_len; - /* Only the last RPC completion should call netfs_subreq_terminated() */ if (!refcount_dec_and_test(&netfs->refcount)) return; @@ -74,8 +72,9 @@ static inline void nfs_netfs_put(struct nfs_netfs_io_data *netfs) * Correct the final length here to be no larger than the netfs subrequest * length, and thus avoid netfs's "Subreq overread" warning message. */ - final_len = min_t(s64, netfs->sreq->len, atomic64_read(&netfs->transferred)); - netfs_subreq_terminated(netfs->sreq, netfs->error ?: final_len, false); + netfs->sreq->transferred = min_t(s64, netfs->sreq->len, + atomic64_read(&netfs->transferred)); + netfs_read_subreq_terminated(netfs->sreq, netfs->error, false); kfree(netfs); } static inline void nfs_netfs_inode_init(struct nfs_inode *nfsi) diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index bfbcf310807f..9457c298dc39 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -1485,7 +1485,6 @@ struct cifs_io_subrequest { struct cifs_io_request *req; }; ssize_t got_bytes; - size_t actual_len; unsigned int xid; int result; bool have_xid; diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index 6dce70f17208..04f2a5441a89 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -1309,10 +1309,8 @@ cifs_readv_callback(struct mid_q_entry *mid) if (rdata->result == 0 || rdata->result == -EAGAIN) iov_iter_advance(&rdata->subreq.io_iter, rdata->got_bytes); rdata->credits.value = 0; - netfs_subreq_terminated(&rdata->subreq, - (rdata->result == 0 || rdata->result == -EAGAIN) ? - rdata->got_bytes : rdata->result, - false); + rdata->subreq.transferred += rdata->got_bytes; + netfs_read_subreq_terminated(&rdata->subreq, rdata->result, false); release_mid(mid); add_credits(server, &credits, 0); } diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index ceef7048cad2..bcde3f9c89e0 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -112,7 +112,6 @@ static void cifs_issue_write(struct netfs_io_subrequest *subreq) goto fail; } - wdata->actual_len = wdata->subreq.len; rc = adjust_credits(wdata->server, wdata, cifs_trace_rw_credits_issue_write_adjust); if (rc) goto fail; @@ -141,25 +140,22 @@ static void cifs_netfs_invalidate_cache(struct netfs_io_request *wreq) } /* - * Split the read up according to how many credits we can get for each piece. - * It's okay to sleep here if we need to wait for more credit to become - * available. - * - * We also choose the server and allocate an operation ID to be cleaned up - * later. + * Negotiate the size of a read operation on behalf of the netfs library. */ -static bool cifs_clamp_length(struct netfs_io_subrequest *subreq) +static int cifs_prepare_read(struct netfs_io_subrequest *subreq) { struct netfs_io_request *rreq = subreq->rreq; - struct netfs_io_stream *stream = &rreq->io_streams[subreq->stream_nr]; struct cifs_io_subrequest *rdata = container_of(subreq, struct cifs_io_subrequest, subreq); struct cifs_io_request *req = container_of(subreq->rreq, struct cifs_io_request, rreq); struct TCP_Server_Info *server = req->server; struct cifs_sb_info *cifs_sb = CIFS_SB(rreq->inode->i_sb); - int rc; + size_t size; + int rc = 0; - rdata->xid = get_xid(); - rdata->have_xid = true; + if (!rdata->have_xid) { + rdata->xid = get_xid(); + rdata->have_xid = true; + } rdata->server = server; if (cifs_sb->ctx->rsize == 0) @@ -167,13 +163,12 @@ static bool cifs_clamp_length(struct netfs_io_subrequest *subreq) server->ops->negotiate_rsize(tlink_tcon(req->cfile->tlink), cifs_sb->ctx); - rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->rsize, - &stream->sreq_max_len, &rdata->credits); - if (rc) { - subreq->error = rc; - return false; - } + &size, &rdata->credits); + if (rc) + return rc; + + rreq->io_streams[0].sreq_max_len = size; rdata->credits.in_flight_check = 1; rdata->credits.rreq_debug_id = rreq->debug_id; @@ -185,14 +180,11 @@ static bool cifs_clamp_length(struct netfs_io_subrequest *subreq) server->credits, server->in_flight, 0, cifs_trace_rw_credits_read_submit); - subreq->len = umin(subreq->len, stream->sreq_max_len); - rdata->actual_len = subreq->len; - #ifdef CONFIG_CIFS_SMB_DIRECT if (server->smbd_conn) - stream->sreq_max_segs = server->smbd_conn->max_frmr_depth; + rreq->io_streams[0].sreq_max_segs = server->smbd_conn->max_frmr_depth; #endif - return true; + return 0; } /* @@ -201,59 +193,41 @@ static bool cifs_clamp_length(struct netfs_io_subrequest *subreq) * to only read a portion of that, but as long as we read something, the netfs * helper will call us again so that we can issue another read. */ -static void cifs_req_issue_read(struct netfs_io_subrequest *subreq) +static void cifs_issue_read(struct netfs_io_subrequest *subreq) { struct netfs_io_request *rreq = subreq->rreq; struct cifs_io_subrequest *rdata = container_of(subreq, struct cifs_io_subrequest, subreq); struct cifs_io_request *req = container_of(subreq->rreq, struct cifs_io_request, rreq); struct TCP_Server_Info *server = req->server; - struct cifs_sb_info *cifs_sb = CIFS_SB(rreq->inode->i_sb); int rc = 0; cifs_dbg(FYI, "%s: op=%08x[%x] mapping=%p len=%zu/%zu\n", __func__, rreq->debug_id, subreq->debug_index, rreq->mapping, subreq->transferred, subreq->len); - if (test_bit(NETFS_SREQ_RETRYING, &subreq->flags)) { - /* - * As we're issuing a retry, we need to negotiate some new - * credits otherwise the server may reject the op with - * INVALID_PARAMETER. Note, however, we may get back less - * credit than we need to complete the op, in which case, we - * shorten the op and rely on additional rounds of retry. - */ - size_t rsize = umin(subreq->len - subreq->transferred, - cifs_sb->ctx->rsize); - - rc = server->ops->wait_mtu_credits(server, rsize, &rdata->actual_len, - &rdata->credits); - if (rc) - goto out; - - rdata->credits.in_flight_check = 1; - - trace_smb3_rw_credits(rdata->rreq->debug_id, - rdata->subreq.debug_index, - rdata->credits.value, - server->credits, server->in_flight, 0, - cifs_trace_rw_credits_read_resubmit); - } + rc = adjust_credits(server, rdata, cifs_trace_rw_credits_issue_read_adjust); + if (rc) + goto failed; if (req->cfile->invalidHandle) { do { rc = cifs_reopen_file(req->cfile, true); } while (rc == -EAGAIN); if (rc) - goto out; + goto failed; } if (subreq->rreq->origin != NETFS_DIO_READ) __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); + trace_netfs_sreq(subreq, netfs_sreq_trace_submit); rc = rdata->server->ops->async_readv(rdata); -out: if (rc) - netfs_subreq_terminated(subreq, rc, false); + goto failed; + return; + +failed: + netfs_read_subreq_terminated(subreq, rc, false); } /* @@ -364,8 +338,8 @@ const struct netfs_request_ops cifs_req_ops = { .init_request = cifs_init_request, .free_request = cifs_free_request, .free_subrequest = cifs_free_subrequest, - .clamp_length = cifs_clamp_length, - .issue_read = cifs_req_issue_read, + .prepare_read = cifs_prepare_read, + .issue_read = cifs_issue_read, .done = cifs_rreq_done, .begin_writeback = cifs_begin_writeback, .prepare_write = cifs_prepare_write, diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 4df84ebe8dbe..85f2878454f3 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -301,7 +301,8 @@ smb2_adjust_credits(struct TCP_Server_Info *server, unsigned int /*enum smb3_rw_credits_trace*/ trace) { struct cifs_credits *credits = &subreq->credits; - int new_val = DIV_ROUND_UP(subreq->actual_len, SMB2_MAX_BUFFER_SIZE); + int new_val = DIV_ROUND_UP(subreq->subreq.len - subreq->subreq.transferred, + SMB2_MAX_BUFFER_SIZE); int scredits, in_flight; if (!credits->value || credits->value == new_val) diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 88dc49d67037..95377bb91950 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -4498,9 +4498,7 @@ static void smb2_readv_worker(struct work_struct *work) struct cifs_io_subrequest *rdata = container_of(work, struct cifs_io_subrequest, subreq.work); - netfs_subreq_terminated(&rdata->subreq, - (rdata->result == 0 || rdata->result == -EAGAIN) ? - rdata->got_bytes : rdata->result, true); + netfs_read_subreq_terminated(&rdata->subreq, rdata->result, false); } static void @@ -4532,7 +4530,7 @@ smb2_readv_callback(struct mid_q_entry *mid) cifs_dbg(FYI, "%s: mid=%llu state=%d result=%d bytes=%zu/%zu\n", __func__, mid->mid, mid->mid_state, rdata->result, - rdata->actual_len, rdata->subreq.len - rdata->subreq.transferred); + rdata->got_bytes, rdata->subreq.len - rdata->subreq.transferred); switch (mid->mid_state) { case MID_RESPONSE_RECEIVED: @@ -4554,6 +4552,7 @@ smb2_readv_callback(struct mid_q_entry *mid) break; case MID_REQUEST_SUBMITTED: case MID_RETRY_NEEDED: + __set_bit(NETFS_SREQ_NEED_RETRY, &rdata->subreq.flags); rdata->result = -EAGAIN; if (server->sign && rdata->got_bytes) /* reset bytes number since we can not check a sign */ @@ -4588,7 +4587,7 @@ smb2_readv_callback(struct mid_q_entry *mid) rdata->req->cfile->fid.persistent_fid, tcon->tid, tcon->ses->Suid, rdata->subreq.start + rdata->subreq.transferred, - rdata->actual_len, + rdata->subreq.len - rdata->subreq.transferred, rdata->result); } else trace_smb3_read_done(rdata->rreq->debug_id, @@ -4603,9 +4602,9 @@ smb2_readv_callback(struct mid_q_entry *mid) __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); rdata->result = 0; } else { - if (rdata->got_bytes < rdata->actual_len && - rdata->subreq.start + rdata->subreq.transferred + rdata->got_bytes == - ictx->remote_i_size) { + size_t trans = rdata->subreq.transferred + rdata->got_bytes; + if (trans < rdata->subreq.len && + rdata->subreq.start + trans == ictx->remote_i_size) { __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); rdata->result = 0; } @@ -4614,6 +4613,10 @@ smb2_readv_callback(struct mid_q_entry *mid) server->credits, server->in_flight, 0, cifs_trace_rw_credits_read_response_clear); rdata->credits.value = 0; + rdata->subreq.transferred += rdata->got_bytes; + if (rdata->subreq.start + rdata->subreq.transferred >= rdata->subreq.rreq->i_size) + __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); + trace_netfs_sreq(&rdata->subreq, netfs_sreq_trace_io_progress); INIT_WORK(&rdata->subreq.work, smb2_readv_worker); queue_work(cifsiod_wq, &rdata->subreq.work); release_mid(mid); @@ -4648,7 +4651,7 @@ smb2_async_readv(struct cifs_io_subrequest *rdata) io_parms.tcon = tlink_tcon(rdata->req->cfile->tlink); io_parms.server = server = rdata->server; io_parms.offset = subreq->start + subreq->transferred; - io_parms.length = rdata->actual_len; + io_parms.length = subreq->len - subreq->transferred; io_parms.persistent_fid = rdata->req->cfile->fid.persistent_fid; io_parms.volatile_fid = rdata->req->cfile->fid.volatile_fid; io_parms.pid = rdata->req->pid; @@ -4669,7 +4672,7 @@ smb2_async_readv(struct cifs_io_subrequest *rdata) shdr = (struct smb2_hdr *)buf; if (rdata->credits.value > 0) { - shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(rdata->actual_len, + shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(io_parms.length, SMB2_MAX_BUFFER_SIZE)); credit_request = le16_to_cpu(shdr->CreditCharge) + 8; if (server->credits >= server->max_credits) @@ -4697,7 +4700,8 @@ smb2_async_readv(struct cifs_io_subrequest *rdata) rdata->xid, io_parms.persistent_fid, io_parms.tcon->tid, io_parms.tcon->ses->Suid, - io_parms.offset, rdata->actual_len, rc); + io_parms.offset, + subreq->len - subreq->transferred, rc); } async_readv_out: @@ -4880,6 +4884,7 @@ smb2_writev_callback(struct mid_q_entry *mid) server->credits, server->in_flight, 0, cifs_trace_rw_credits_write_response_clear); wdata->credits.value = 0; + trace_netfs_sreq(&wdata->subreq, netfs_sreq_trace_io_progress); cifs_write_subrequest_terminated(wdata, result ?: written, true); release_mid(mid); trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, 0, diff --git a/include/linux/folio_queue.h b/include/linux/folio_queue.h index 52773613bf23..955680c3bb5f 100644 --- a/include/linux/folio_queue.h +++ b/include/linux/folio_queue.h @@ -27,6 +27,7 @@ struct folio_queue { struct folio_queue *prev; /* Previous queue segment of NULL */ unsigned long marks; /* 1-bit mark per folio */ unsigned long marks2; /* Second 1-bit mark per folio */ + unsigned long marks3; /* Third 1-bit mark per folio */ #if PAGEVEC_SIZE > BITS_PER_LONG #error marks is not big enough #endif @@ -39,6 +40,7 @@ static inline void folioq_init(struct folio_queue *folioq) folioq->prev = NULL; folioq->marks = 0; folioq->marks2 = 0; + folioq->marks3 = 0; } static inline unsigned int folioq_nr_slots(const struct folio_queue *folioq) @@ -87,6 +89,21 @@ static inline void folioq_unmark2(struct folio_queue *folioq, unsigned int slot) clear_bit(slot, &folioq->marks2); } +static inline bool folioq_is_marked3(const struct folio_queue *folioq, unsigned int slot) +{ + return test_bit(slot, &folioq->marks3); +} + +static inline void folioq_mark3(struct folio_queue *folioq, unsigned int slot) +{ + set_bit(slot, &folioq->marks3); +} + +static inline void folioq_unmark3(struct folio_queue *folioq, unsigned int slot) +{ + clear_bit(slot, &folioq->marks3); +} + static inline unsigned int __folio_order(struct folio *folio) { if (!folio_test_large(folio)) @@ -133,6 +150,7 @@ static inline void folioq_clear(struct folio_queue *folioq, unsigned int slot) folioq->vec.folios[slot] = NULL; folioq_unmark(folioq, slot); folioq_unmark2(folioq, slot); + folioq_unmark3(folioq, slot); } #endif /* _LINUX_FOLIO_QUEUE_H */ diff --git a/include/linux/netfs.h b/include/linux/netfs.h index bd0e3d147822..c0f0c9c87d86 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -178,36 +178,43 @@ struct netfs_io_subrequest { unsigned long long start; /* Where to start the I/O */ size_t len; /* Size of the I/O */ size_t transferred; /* Amount of data transferred */ + size_t consumed; /* Amount of read data consumed */ + size_t prev_donated; /* Amount of data donated from previous subreq */ + size_t next_donated; /* Amount of data donated from next subreq */ refcount_t ref; short error; /* 0 or error that occurred */ unsigned short debug_index; /* Index in list (for debugging output) */ unsigned int nr_segs; /* Number of segs in io_iter */ enum netfs_io_source source; /* Where to read from/write to */ unsigned char stream_nr; /* I/O stream this belongs to */ + unsigned char curr_folioq_slot; /* Folio currently being read */ + unsigned char curr_folio_order; /* Order of folio */ + struct folio_queue *curr_folioq; /* Queue segment in which current folio resides */ unsigned long flags; #define NETFS_SREQ_COPY_TO_CACHE 0 /* Set if should copy the data to the cache */ #define NETFS_SREQ_CLEAR_TAIL 1 /* Set if the rest of the read should be cleared */ -#define NETFS_SREQ_SHORT_IO 2 /* Set if the I/O was short */ #define NETFS_SREQ_SEEK_DATA_READ 3 /* Set if ->read() should SEEK_DATA first */ #define NETFS_SREQ_NO_PROGRESS 4 /* Set if we didn't manage to read any data */ #define NETFS_SREQ_ONDEMAND 5 /* Set if it's from on-demand read mode */ #define NETFS_SREQ_BOUNDARY 6 /* Set if ends on hard boundary (eg. ceph object) */ +#define NETFS_SREQ_HIT_EOF 7 /* Set if short due to EOF */ #define NETFS_SREQ_IN_PROGRESS 8 /* Unlocked when the subrequest completes */ #define NETFS_SREQ_NEED_RETRY 9 /* Set if the filesystem requests a retry */ #define NETFS_SREQ_RETRYING 10 /* Set if we're retrying */ #define NETFS_SREQ_FAILED 11 /* Set if the subreq failed unretryably */ -#define NETFS_SREQ_HIT_EOF 12 /* Set if we hit the EOF */ }; enum netfs_io_origin { NETFS_READAHEAD, /* This read was triggered by readahead */ NETFS_READPAGE, /* This read is a synchronous read */ + NETFS_READ_GAPS, /* This read is a synchronous read to fill gaps */ NETFS_READ_FOR_WRITE, /* This read is to prepare a write */ NETFS_DIO_READ, /* This is a direct I/O read */ NETFS_WRITEBACK, /* This write was triggered by writepages */ NETFS_WRITETHROUGH, /* This write was made by netfs_perform_write() */ NETFS_UNBUFFERED_WRITE, /* This is an unbuffered write */ NETFS_DIO_WRITE, /* This is a direct I/O write */ + NETFS_PGPRIV2_COPY_TO_CACHE, /* [DEPRECATED] This is writing read data to the cache */ nr__netfs_io_origin } __mode(byte); @@ -224,6 +231,7 @@ struct netfs_io_request { struct address_space *mapping; /* The mapping being accessed */ struct kiocb *iocb; /* AIO completion vector */ struct netfs_cache_resources cache_resources; + struct readahead_control *ractl; /* Readahead descriptor */ struct list_head proc_link; /* Link in netfs_iorequests */ struct list_head subrequests; /* Contributory I/O operations */ struct netfs_io_stream io_streams[2]; /* Streams of parallel I/O operations */ @@ -244,12 +252,10 @@ struct netfs_io_request { unsigned int nr_group_rel; /* Number of refs to release on ->group */ spinlock_t lock; /* Lock for queuing subreqs */ atomic_t nr_outstanding; /* Number of ops in progress */ - atomic_t nr_copy_ops; /* Number of copy-to-cache ops in progress */ - size_t upper_len; /* Length can be extended to here */ unsigned long long submitted; /* Amount submitted for I/O so far */ unsigned long long len; /* Length of the request */ size_t transferred; /* Amount to be indicated as transferred */ - short error; /* 0 or error that occurred */ + long error; /* 0 or error that occurred */ enum netfs_io_origin origin; /* Origin of the request */ bool direct_bv_unpin; /* T if direct_bv[] must be unpinned */ u8 buffer_head_slot; /* First slot in ->buffer */ @@ -260,9 +266,9 @@ struct netfs_io_request { unsigned long long collected_to; /* Point we've collected to */ unsigned long long cleaned_to; /* Position we've cleaned folios to */ pgoff_t no_unlock_folio; /* Don't unlock this folio after read */ + size_t prev_donated; /* Fallback for subreq->prev_donated */ refcount_t ref; unsigned long flags; -#define NETFS_RREQ_INCOMPLETE_IO 0 /* Some ioreqs terminated short or with error */ #define NETFS_RREQ_COPY_TO_CACHE 1 /* Need to write to the cache */ #define NETFS_RREQ_NO_UNLOCK_FOLIO 2 /* Don't unlock no_unlock_folio on completion */ #define NETFS_RREQ_DONT_UNLOCK_FOLIOS 3 /* Don't unlock the folios on completion */ @@ -274,6 +280,7 @@ struct netfs_io_request { #define NETFS_RREQ_PAUSE 11 /* Pause subrequest generation */ #define NETFS_RREQ_USE_IO_ITER 12 /* Use ->io_iter rather than ->i_pages */ #define NETFS_RREQ_ALL_QUEUED 13 /* All subreqs are now queued */ +#define NETFS_RREQ_NEED_RETRY 14 /* Need to try retrying */ #define NETFS_RREQ_USE_PGPRIV2 31 /* [DEPRECATED] Use PG_private_2 to mark * write to cache on read */ const struct netfs_request_ops *netfs_ops; @@ -292,7 +299,7 @@ struct netfs_request_ops { /* Read request handling */ void (*expand_readahead)(struct netfs_io_request *rreq); - bool (*clamp_length)(struct netfs_io_subrequest *subreq); + int (*prepare_read)(struct netfs_io_subrequest *subreq); void (*issue_read)(struct netfs_io_subrequest *subreq); bool (*is_still_valid)(struct netfs_io_request *rreq); int (*check_write_begin)(struct file *file, loff_t pos, unsigned len, @@ -422,7 +429,10 @@ bool netfs_release_folio(struct folio *folio, gfp_t gfp); vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_group); /* (Sub)request management API. */ -void netfs_subreq_terminated(struct netfs_io_subrequest *, ssize_t, bool); +void netfs_read_subreq_progress(struct netfs_io_subrequest *subreq, + bool was_async); +void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq, + int error, bool was_async); void netfs_get_subrequest(struct netfs_io_subrequest *subreq, enum netfs_sreq_ref_trace what); void netfs_put_subrequest(struct netfs_io_subrequest *subreq, diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 58bf23002fc1..7b26463cb98f 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -20,6 +20,7 @@ EM(netfs_read_trace_expanded, "EXPANDED ") \ EM(netfs_read_trace_readahead, "READAHEAD") \ EM(netfs_read_trace_readpage, "READPAGE ") \ + EM(netfs_read_trace_read_gaps, "READ-GAPS") \ EM(netfs_read_trace_prefetch_for_write, "PREFETCHW") \ E_(netfs_read_trace_write_begin, "WRITEBEGN") @@ -33,12 +34,14 @@ #define netfs_rreq_origins \ EM(NETFS_READAHEAD, "RA") \ EM(NETFS_READPAGE, "RP") \ + EM(NETFS_READ_GAPS, "RG") \ EM(NETFS_READ_FOR_WRITE, "RW") \ EM(NETFS_DIO_READ, "DR") \ EM(NETFS_WRITEBACK, "WB") \ EM(NETFS_WRITETHROUGH, "WT") \ EM(NETFS_UNBUFFERED_WRITE, "UW") \ - E_(NETFS_DIO_WRITE, "DW") + EM(NETFS_DIO_WRITE, "DW") \ + E_(NETFS_PGPRIV2_COPY_TO_CACHE, "2C") #define netfs_rreq_traces \ EM(netfs_rreq_trace_assess, "ASSESS ") \ @@ -69,15 +72,25 @@ E_(NETFS_INVALID_WRITE, "INVL") #define netfs_sreq_traces \ + EM(netfs_sreq_trace_add_donations, "+DON ") \ + EM(netfs_sreq_trace_added, "ADD ") \ + EM(netfs_sreq_trace_clear, "CLEAR") \ EM(netfs_sreq_trace_discard, "DSCRD") \ + EM(netfs_sreq_trace_donate_to_prev, "DON-P") \ + EM(netfs_sreq_trace_donate_to_next, "DON-N") \ EM(netfs_sreq_trace_download_instead, "RDOWN") \ EM(netfs_sreq_trace_fail, "FAIL ") \ EM(netfs_sreq_trace_free, "FREE ") \ + EM(netfs_sreq_trace_hit_eof, "EOF ") \ + EM(netfs_sreq_trace_io_progress, "IO ") \ EM(netfs_sreq_trace_limited, "LIMIT") \ EM(netfs_sreq_trace_prepare, "PREP ") \ EM(netfs_sreq_trace_prep_failed, "PRPFL") \ - EM(netfs_sreq_trace_resubmit_short, "SHORT") \ + EM(netfs_sreq_trace_progress, "PRGRS") \ + EM(netfs_sreq_trace_reprep_failed, "REPFL") \ EM(netfs_sreq_trace_retry, "RETRY") \ + EM(netfs_sreq_trace_short, "SHORT") \ + EM(netfs_sreq_trace_split, "SPLIT") \ EM(netfs_sreq_trace_submit, "SUBMT") \ EM(netfs_sreq_trace_terminated, "TERM ") \ EM(netfs_sreq_trace_write, "WRITE") \ @@ -118,7 +131,7 @@ EM(netfs_sreq_trace_new, "NEW ") \ EM(netfs_sreq_trace_put_cancel, "PUT CANCEL ") \ EM(netfs_sreq_trace_put_clear, "PUT CLEAR ") \ - EM(netfs_sreq_trace_put_discard, "PUT DISCARD") \ + EM(netfs_sreq_trace_put_consumed, "PUT CONSUME") \ EM(netfs_sreq_trace_put_done, "PUT DONE ") \ EM(netfs_sreq_trace_put_failed, "PUT FAILED ") \ EM(netfs_sreq_trace_put_merged, "PUT MERGED ") \ @@ -138,6 +151,7 @@ EM(netfs_flush_content, "flush") \ EM(netfs_streaming_filled_page, "mod-streamw-f") \ EM(netfs_streaming_cont_filled_page, "mod-streamw-f+") \ + EM(netfs_folio_trace_abandon, "abandon") \ EM(netfs_folio_trace_cancel_copy, "cancel-copy") \ EM(netfs_folio_trace_clear, "clear") \ EM(netfs_folio_trace_clear_cc, "clear-cc") \ @@ -154,7 +168,11 @@ EM(netfs_folio_trace_mkwrite_plus, "mkwrite+") \ EM(netfs_folio_trace_not_under_wback, "!wback") \ EM(netfs_folio_trace_put, "put") \ + EM(netfs_folio_trace_read, "read") \ + EM(netfs_folio_trace_read_done, "read-done") \ EM(netfs_folio_trace_read_gaps, "read-gaps") \ + EM(netfs_folio_trace_read_put, "read-put") \ + EM(netfs_folio_trace_read_unlock, "read-unlock") \ EM(netfs_folio_trace_redirtied, "redirtied") \ EM(netfs_folio_trace_store, "store") \ EM(netfs_folio_trace_store_copy, "store-copy") \ @@ -167,6 +185,12 @@ EM(netfs_contig_trace_jump, "-->JUMP-->") \ E_(netfs_contig_trace_unlock, "Unlock") +#define netfs_donate_traces \ + EM(netfs_trace_donate_tail_to_prev, "tail-to-prev") \ + EM(netfs_trace_donate_to_prev, "to-prev") \ + EM(netfs_trace_donate_to_next, "to-next") \ + E_(netfs_trace_donate_to_deferred_next, "defer-next") + #ifndef __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY #define __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY @@ -184,6 +208,7 @@ enum netfs_rreq_ref_trace { netfs_rreq_ref_traces } __mode(byte); enum netfs_sreq_ref_trace { netfs_sreq_ref_traces } __mode(byte); enum netfs_folio_trace { netfs_folio_traces } __mode(byte); enum netfs_collect_contig_trace { netfs_collect_contig_traces } __mode(byte); +enum netfs_donate_trace { netfs_donate_traces } __mode(byte); #endif @@ -206,6 +231,7 @@ netfs_rreq_ref_traces; netfs_sreq_ref_traces; netfs_folio_traces; netfs_collect_contig_traces; +netfs_donate_traces; /* * Now redefine the EM() and E_() macros to map the enums to the strings that @@ -226,6 +252,7 @@ TRACE_EVENT(netfs_read, TP_STRUCT__entry( __field(unsigned int, rreq ) __field(unsigned int, cookie ) + __field(loff_t, i_size ) __field(loff_t, start ) __field(size_t, len ) __field(enum netfs_read_trace, what ) @@ -235,18 +262,19 @@ TRACE_EVENT(netfs_read, TP_fast_assign( __entry->rreq = rreq->debug_id; __entry->cookie = rreq->cache_resources.debug_id; + __entry->i_size = rreq->i_size; __entry->start = start; __entry->len = len; __entry->what = what; __entry->netfs_inode = rreq->inode->i_ino; ), - TP_printk("R=%08x %s c=%08x ni=%x s=%llx %zx", + TP_printk("R=%08x %s c=%08x ni=%x s=%llx l=%zx sz=%llx", __entry->rreq, __print_symbolic(__entry->what, netfs_read_traces), __entry->cookie, __entry->netfs_inode, - __entry->start, __entry->len) + __entry->start, __entry->len, __entry->i_size) ); TRACE_EVENT(netfs_rreq, @@ -651,6 +679,71 @@ TRACE_EVENT(netfs_collect_stream, __entry->collected_to, __entry->front) ); +TRACE_EVENT(netfs_progress, + TP_PROTO(const struct netfs_io_subrequest *subreq, + unsigned long long start, size_t avail, size_t part), + + TP_ARGS(subreq, start, avail, part), + + TP_STRUCT__entry( + __field(unsigned int, rreq) + __field(unsigned int, subreq) + __field(unsigned int, consumed) + __field(unsigned int, transferred) + __field(unsigned long long, f_start) + __field(unsigned int, f_avail) + __field(unsigned int, f_part) + __field(unsigned char, slot) + ), + + TP_fast_assign( + __entry->rreq = subreq->rreq->debug_id; + __entry->subreq = subreq->debug_index; + __entry->consumed = subreq->consumed; + __entry->transferred = subreq->transferred; + __entry->f_start = start; + __entry->f_avail = avail; + __entry->f_part = part; + __entry->slot = subreq->curr_folioq_slot; + ), + + TP_printk("R=%08x[%02x] s=%llx ct=%x/%x pa=%x/%x sl=%x", + __entry->rreq, __entry->subreq, __entry->f_start, + __entry->consumed, __entry->transferred, + __entry->f_part, __entry->f_avail, __entry->slot) + ); + +TRACE_EVENT(netfs_donate, + TP_PROTO(const struct netfs_io_request *rreq, + const struct netfs_io_subrequest *from, + const struct netfs_io_subrequest *to, + size_t amount, + enum netfs_donate_trace trace), + + TP_ARGS(rreq, from, to, amount, trace), + + TP_STRUCT__entry( + __field(unsigned int, rreq) + __field(unsigned int, from) + __field(unsigned int, to) + __field(unsigned int, amount) + __field(enum netfs_donate_trace, trace) + ), + + TP_fast_assign( + __entry->rreq = rreq->debug_id; + __entry->from = from->debug_index; + __entry->to = to ? to->debug_index : -1; + __entry->amount = amount; + __entry->trace = trace; + ), + + TP_printk("R=%08x[%02x] -> [%02x] %s am=%x", + __entry->rreq, __entry->from, __entry->to, + __print_symbolic(__entry->trace, netfs_donate_traces), + __entry->amount) + ); + #undef EM #undef E_ #endif /* _TRACE_NETFS_H */ -- cgit v1.2.3 From c4f1450ecccc5311db87f806998eda1c824c4e35 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 12 Jul 2024 12:44:30 +0100 Subject: cachefiles, netfs: Fix write to partial block at EOF Because it uses DIO writes, cachefiles is unable to make a write to the backing file if that write is not aligned to and sized according to the backing file's DIO block alignment. This makes it tricky to handle a write to the cache where the EOF on the network file is not correctly aligned. To get around this, netfslib attempts to tell the driver it is calling how much more data there is available beyond the EOF that it can use to pad the write (netfslib preclears the part of the folio above the EOF). However, it tries to tell the cache what the maximum length is, but doesn't calculate this correctly; and, in any case, cachefiles actually ignores the value and just skips the block. Fix this by: (1) Change the value passed to indicate the amount of extra data that can be added to the operation (now ->submit_extendable_to). This is much simpler to calculate as it's just the end of the folio minus the top of the data within the folio - rather than having to account for data spread over multiple folios. (2) Make cachefiles add some of this data if the subrequest it is given ends at the network file's i_size if the extra data is sufficient to pad out to a whole block. Signed-off-by: David Howells cc: Jeff Layton cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/20240814203850.2240469-22-dhowells@redhat.com/ # v2 Signed-off-by: Christian Brauner --- fs/cachefiles/io.c | 14 ++++++++++++++ fs/netfs/read_pgpriv2.c | 4 ++-- fs/netfs/write_issue.c | 5 ++--- include/linux/netfs.h | 2 +- 4 files changed, 19 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c index 5b82ba7785cd..6a821a959b59 100644 --- a/fs/cachefiles/io.c +++ b/fs/cachefiles/io.c @@ -648,6 +648,7 @@ static void cachefiles_issue_write(struct netfs_io_subrequest *subreq) struct netfs_cache_resources *cres = &wreq->cache_resources; struct cachefiles_object *object = cachefiles_cres_object(cres); struct cachefiles_cache *cache = object->volume->cache; + struct netfs_io_stream *stream = &wreq->io_streams[subreq->stream_nr]; const struct cred *saved_cred; size_t off, pre, post, len = subreq->len; loff_t start = subreq->start; @@ -661,6 +662,7 @@ static void cachefiles_issue_write(struct netfs_io_subrequest *subreq) if (off) { pre = CACHEFILES_DIO_BLOCK_SIZE - off; if (pre >= len) { + fscache_count_dio_misfit(); netfs_write_subrequest_terminated(subreq, len, false); return; } @@ -671,10 +673,22 @@ static void cachefiles_issue_write(struct netfs_io_subrequest *subreq) } /* We also need to end on the cache granularity boundary */ + if (start + len == wreq->i_size) { + size_t part = len % CACHEFILES_DIO_BLOCK_SIZE; + size_t need = CACHEFILES_DIO_BLOCK_SIZE - part; + + if (part && stream->submit_extendable_to >= need) { + len += need; + subreq->len += need; + subreq->io_iter.count += need; + } + } + post = len & (CACHEFILES_DIO_BLOCK_SIZE - 1); if (post) { len -= post; if (len == 0) { + fscache_count_dio_misfit(); netfs_write_subrequest_terminated(subreq, post, false); return; } diff --git a/fs/netfs/read_pgpriv2.c b/fs/netfs/read_pgpriv2.c index 9439461d535f..ba5af89d37fa 100644 --- a/fs/netfs/read_pgpriv2.c +++ b/fs/netfs/read_pgpriv2.c @@ -97,7 +97,7 @@ static int netfs_pgpriv2_copy_folio(struct netfs_io_request *wreq, struct folio if (netfs_buffer_append_folio(wreq, folio, false) < 0) return -ENOMEM; - cache->submit_max_len = fsize; + cache->submit_extendable_to = fsize; cache->submit_off = 0; cache->submit_len = flen; @@ -112,10 +112,10 @@ static int netfs_pgpriv2_copy_folio(struct netfs_io_request *wreq, struct folio wreq->io_iter.iov_offset = cache->submit_off; atomic64_set(&wreq->issued_to, fpos + cache->submit_off); + cache->submit_extendable_to = fsize - cache->submit_off; part = netfs_advance_write(wreq, cache, fpos + cache->submit_off, cache->submit_len, to_eof); cache->submit_off += part; - cache->submit_max_len -= part; if (part > cache->submit_len) cache->submit_len = 0; else diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 975436d3dc3f..f7d59f0bb8c2 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -283,6 +283,7 @@ int netfs_advance_write(struct netfs_io_request *wreq, _debug("part %zx/%zx %zx/%zx", subreq->len, stream->sreq_max_len, part, len); subreq->len += part; subreq->nr_segs++; + stream->submit_extendable_to -= part; if (subreq->len >= stream->sreq_max_len || subreq->nr_segs >= stream->sreq_max_segs || @@ -424,7 +425,6 @@ static int netfs_write_folio(struct netfs_io_request *wreq, */ for (int s = 0; s < NR_IO_STREAMS; s++) { stream = &wreq->io_streams[s]; - stream->submit_max_len = fsize; stream->submit_off = foff; stream->submit_len = flen; if ((stream->source == NETFS_WRITE_TO_CACHE && streamw) || @@ -432,7 +432,6 @@ static int netfs_write_folio(struct netfs_io_request *wreq, fgroup == NETFS_FOLIO_COPY_TO_CACHE)) { stream->submit_off = UINT_MAX; stream->submit_len = 0; - stream->submit_max_len = 0; } } @@ -462,10 +461,10 @@ static int netfs_write_folio(struct netfs_io_request *wreq, wreq->io_iter.iov_offset = stream->submit_off; atomic64_set(&wreq->issued_to, fpos + stream->submit_off); + stream->submit_extendable_to = fsize - stream->submit_off; part = netfs_advance_write(wreq, stream, fpos + stream->submit_off, stream->submit_len, to_eof); stream->submit_off += part; - stream->submit_max_len -= part; if (part > stream->submit_len) stream->submit_len = 0; else diff --git a/include/linux/netfs.h b/include/linux/netfs.h index c0f0c9c87d86..5eaceef41e6c 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -135,7 +135,7 @@ struct netfs_io_stream { unsigned int sreq_max_segs; /* 0 or max number of segments in an iterator */ unsigned int submit_off; /* Folio offset we're submitting from */ unsigned int submit_len; /* Amount of data left to submit */ - unsigned int submit_max_len; /* Amount I/O can be rounded up to */ + unsigned int submit_extendable_to; /* Amount I/O can be rounded up to */ void (*prepare_write)(struct netfs_io_subrequest *subreq); void (*issue_write)(struct netfs_io_subrequest *subreq); /* Collection tracking */ -- cgit v1.2.3 From 2982c8c19bab020e38da9d503aa21a3b389c53ac Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 26 Jul 2024 20:03:07 +0100 Subject: cifs: Use iterate_and_advance*() routines directly for hashing Replace the bespoke cifs iterators of ITER_BVEC and ITER_KVEC to do hashing with iterate_and_advance_kernel() - a variant on iterate_and_advance() that only supports kernel-internal ITER_* types and not UBUF/IOVEC types. The bespoke ITER_XARRAY is left because we don't really want to be calling crypto_shash_update() under the RCU read lock for large amounts of data; besides, ITER_XARRAY is going to be phased out. Signed-off-by: David Howells cc: Steve French cc: Paulo Alcantara cc: Tom Talpey cc: Enzo Matsumiya cc: linux-cifs@vger.kernel.org Link: https://lore.kernel.org/r/20240814203850.2240469-24-dhowells@redhat.com/ # v2 Signed-off-by: Christian Brauner --- fs/smb/client/cifsencrypt.c | 109 ++++++++++---------------------------------- include/linux/iov_iter.h | 47 +++++++++++++++++++ 2 files changed, 70 insertions(+), 86 deletions(-) (limited to 'include/linux') diff --git a/fs/smb/client/cifsencrypt.c b/fs/smb/client/cifsencrypt.c index 6322f0f68a17..991a1ab047e7 100644 --- a/fs/smb/client/cifsencrypt.c +++ b/fs/smb/client/cifsencrypt.c @@ -21,82 +21,10 @@ #include #include #include +#include #include "../common/arc4.h" #include -/* - * Hash data from a BVEC-type iterator. - */ -static int cifs_shash_bvec(const struct iov_iter *iter, ssize_t maxsize, - struct shash_desc *shash) -{ - const struct bio_vec *bv = iter->bvec; - unsigned long start = iter->iov_offset; - unsigned int i; - void *p; - int ret; - - for (i = 0; i < iter->nr_segs; i++) { - size_t off, len; - - len = bv[i].bv_len; - if (start >= len) { - start -= len; - continue; - } - - len = min_t(size_t, maxsize, len - start); - off = bv[i].bv_offset + start; - - p = kmap_local_page(bv[i].bv_page); - ret = crypto_shash_update(shash, p + off, len); - kunmap_local(p); - if (ret < 0) - return ret; - - maxsize -= len; - if (maxsize <= 0) - break; - start = 0; - } - - return 0; -} - -/* - * Hash data from a KVEC-type iterator. - */ -static int cifs_shash_kvec(const struct iov_iter *iter, ssize_t maxsize, - struct shash_desc *shash) -{ - const struct kvec *kv = iter->kvec; - unsigned long start = iter->iov_offset; - unsigned int i; - int ret; - - for (i = 0; i < iter->nr_segs; i++) { - size_t len; - - len = kv[i].iov_len; - if (start >= len) { - start -= len; - continue; - } - - len = min_t(size_t, maxsize, len - start); - ret = crypto_shash_update(shash, kv[i].iov_base + start, len); - if (ret < 0) - return ret; - maxsize -= len; - - if (maxsize <= 0) - break; - start = 0; - } - - return 0; -} - /* * Hash data from an XARRAY-type iterator. */ @@ -145,27 +73,36 @@ static ssize_t cifs_shash_xarray(const struct iov_iter *iter, ssize_t maxsize, return 0; } +static size_t cifs_shash_step(void *iter_base, size_t progress, size_t len, + void *priv, void *priv2) +{ + struct shash_desc *shash = priv; + int ret, *pret = priv2; + + ret = crypto_shash_update(shash, iter_base, len); + if (ret < 0) { + *pret = ret; + return len; + } + return 0; +} + /* * Pass the data from an iterator into a hash. */ static int cifs_shash_iter(const struct iov_iter *iter, size_t maxsize, struct shash_desc *shash) { - if (maxsize == 0) - return 0; + struct iov_iter tmp_iter = *iter; + int err = -EIO; - switch (iov_iter_type(iter)) { - case ITER_BVEC: - return cifs_shash_bvec(iter, maxsize, shash); - case ITER_KVEC: - return cifs_shash_kvec(iter, maxsize, shash); - case ITER_XARRAY: + if (iov_iter_type(iter) == ITER_XARRAY) return cifs_shash_xarray(iter, maxsize, shash); - default: - pr_err("cifs_shash_iter(%u) unsupported\n", iov_iter_type(iter)); - WARN_ON_ONCE(1); - return -EIO; - } + + if (iterate_and_advance_kernel(&tmp_iter, maxsize, shash, &err, + cifs_shash_step) != maxsize) + return err; + return 0; } int __cifs_calc_signature(struct smb_rqst *rqst, diff --git a/include/linux/iov_iter.h b/include/linux/iov_iter.h index a223370a59a7..c4aa58032faf 100644 --- a/include/linux/iov_iter.h +++ b/include/linux/iov_iter.h @@ -328,4 +328,51 @@ size_t iterate_and_advance(struct iov_iter *iter, size_t len, void *priv, return iterate_and_advance2(iter, len, priv, NULL, ustep, step); } +/** + * iterate_and_advance_kernel - Iterate over a kernel-internal iterator + * @iter: The iterator to iterate over. + * @len: The amount to iterate over. + * @priv: Data for the step functions. + * @priv2: More data for the step functions. + * @step: Function for other iterators; given kernel addresses. + * + * Iterate over the next part of an iterator, up to the specified length. The + * buffer is presented in segments, which for kernel iteration are broken up by + * physical pages and mapped, with the mapped address being presented. + * + * [!] Note This will only handle BVEC, KVEC, FOLIOQ, XARRAY and DISCARD-type + * iterators; it will not handle UBUF or IOVEC-type iterators. + * + * A step functions, @step, must be provided, one for handling mapped kernel + * addresses and the other is given user addresses which have the potential to + * fault since no pinning is performed. + * + * The step functions are passed the address and length of the segment, @priv, + * @priv2 and the amount of data so far iterated over (which can, for example, + * be added to @priv to point to the right part of a second buffer). The step + * functions should return the amount of the segment they didn't process (ie. 0 + * indicates complete processsing). + * + * This function returns the amount of data processed (ie. 0 means nothing was + * processed and the value of @len means processes to completion). + */ +static __always_inline +size_t iterate_and_advance_kernel(struct iov_iter *iter, size_t len, void *priv, + void *priv2, iov_step_f step) +{ + if (unlikely(iter->count < len)) + len = iter->count; + if (unlikely(!len)) + return 0; + if (iov_iter_is_bvec(iter)) + return iterate_bvec(iter, len, priv, priv2, step); + if (iov_iter_is_kvec(iter)) + return iterate_kvec(iter, len, priv, priv2, step); + if (iov_iter_is_folioq(iter)) + return iterate_folioq(iter, len, priv, priv2, step); + if (iov_iter_is_xarray(iter)) + return iterate_xarray(iter, len, priv, priv2, step); + return iterate_discard(iter, len, priv, priv2, step); +} + #endif /* _LINUX_IOV_ITER_H */ -- cgit v1.2.3 From c45b9a07b6392fa224ca76b89f24dae1046eef09 Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Thu, 12 Sep 2024 22:30:34 +0900 Subject: Revert "firewire: core: use mutex to coordinate concurrent calls to flush completions" This reverts commit d9605d67562505e27dcc0f71af418118d3db91e5, since this commit is on the following reverted changes. Link: https://lore.kernel.org/r/20240912133038.238786-2-o-takashi@sakamocchi.jp Signed-off-by: Takashi Sakamoto --- drivers/firewire/core-iso.c | 11 ++--------- drivers/firewire/ohci.c | 37 +++++++++++++++++++++++-------------- include/linux/firewire.h | 1 - 3 files changed, 25 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/drivers/firewire/core-iso.c b/drivers/firewire/core-iso.c index 1405d2e9cb2c..9f41c78878ad 100644 --- a/drivers/firewire/core-iso.c +++ b/drivers/firewire/core-iso.c @@ -157,7 +157,6 @@ struct fw_iso_context *fw_iso_context_create(struct fw_card *card, ctx->callback.sc = callback; ctx->callback_data = callback_data; INIT_WORK(&ctx->work, flush_completions_work); - mutex_init(&ctx->flushing_completions_mutex); trace_isoc_outbound_allocate(ctx, channel, speed); trace_isoc_inbound_single_allocate(ctx, channel, header_size); @@ -174,8 +173,6 @@ void fw_iso_context_destroy(struct fw_iso_context *ctx) trace_isoc_inbound_multiple_destroy(ctx); ctx->card->driver->free_iso_context(ctx); - - mutex_destroy(&ctx->flushing_completions_mutex); } EXPORT_SYMBOL(fw_iso_context_destroy); @@ -229,7 +226,7 @@ EXPORT_SYMBOL(fw_iso_context_queue_flush); * to process the context asynchronously, fw_iso_context_schedule_flush_completions() is available * instead. * - * Context: Process context due to mutex_trylock(). + * Context: Process context. */ int fw_iso_context_flush_completions(struct fw_iso_context *ctx) { @@ -237,11 +234,7 @@ int fw_iso_context_flush_completions(struct fw_iso_context *ctx) trace_isoc_inbound_single_flush_completions(ctx); trace_isoc_inbound_multiple_flush_completions(ctx); - scoped_cond_guard(mutex_try, /* nothing to do */, &ctx->flushing_completions_mutex) { - return ctx->card->driver->flush_iso_completions(ctx); - } - - return 0; + return ctx->card->driver->flush_iso_completions(ctx); } EXPORT_SYMBOL(fw_iso_context_flush_completions); diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index b182998a77f4..02ff0363d3ad 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -166,6 +166,7 @@ struct iso_context { struct context context; void *header; size_t header_length; + unsigned long flushing_completions; u32 mc_buffer_bus; u16 mc_completed; u16 last_timestamp; @@ -3578,23 +3579,31 @@ static void ohci_flush_queue_iso(struct fw_iso_context *base) static int ohci_flush_iso_completions(struct fw_iso_context *base) { struct iso_context *ctx = container_of(base, struct iso_context, base); + int ret = 0; - // Note that tasklet softIRQ is not used to process isochronous context anymore. - context_tasklet((unsigned long)&ctx->context); + if (!test_and_set_bit_lock(0, &ctx->flushing_completions)) { + // Note that tasklet softIRQ is not used to process isochronous context anymore. + context_tasklet((unsigned long)&ctx->context); - switch (base->type) { - case FW_ISO_CONTEXT_TRANSMIT: - case FW_ISO_CONTEXT_RECEIVE: - if (ctx->header_length != 0) - flush_iso_completions(ctx, FW_ISO_CONTEXT_COMPLETIONS_CAUSE_FLUSH); - return 0; - case FW_ISO_CONTEXT_RECEIVE_MULTICHANNEL: - if (ctx->mc_completed != 0) - flush_ir_buffer_fill(ctx); - return 0; - default: - return -ENOSYS; + switch (base->type) { + case FW_ISO_CONTEXT_TRANSMIT: + case FW_ISO_CONTEXT_RECEIVE: + if (ctx->header_length != 0) + flush_iso_completions(ctx, FW_ISO_CONTEXT_COMPLETIONS_CAUSE_FLUSH); + break; + case FW_ISO_CONTEXT_RECEIVE_MULTICHANNEL: + if (ctx->mc_completed != 0) + flush_ir_buffer_fill(ctx); + break; + default: + ret = -ENOSYS; + } + + clear_bit_unlock(0, &ctx->flushing_completions); + smp_mb__after_atomic(); } + + return ret; } static const struct fw_card_driver ohci_driver = { diff --git a/include/linux/firewire.h b/include/linux/firewire.h index 19e8c5f9537c..f815d12deda0 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -512,7 +512,6 @@ union fw_iso_callback { struct fw_iso_context { struct fw_card *card; struct work_struct work; - struct mutex flushing_completions_mutex; int type; int channel; int speed; -- cgit v1.2.3 From 4010cb1efda08ec6fd02ec5db9da909322ef352e Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Thu, 12 Sep 2024 22:30:37 +0900 Subject: firewire: core: update documentation of kernel APIs for flushing completions There is a slight difference between fw_iso_context_flush_completions() and fw_iso_context_schedule_flush_completions(). This commit updates the documentations for them. Link: https://lore.kernel.org/r/20240912133038.238786-5-o-takashi@sakamocchi.jp Signed-off-by: Takashi Sakamoto --- drivers/firewire/core-iso.c | 9 ++++++--- include/linux/firewire.h | 8 +++++--- 2 files changed, 11 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/firewire/core-iso.c b/drivers/firewire/core-iso.c index f2394f3ed194..a67493862c85 100644 --- a/drivers/firewire/core-iso.c +++ b/drivers/firewire/core-iso.c @@ -214,9 +214,12 @@ EXPORT_SYMBOL(fw_iso_context_queue_flush); * @ctx: the isochronous context * * Process the isochronous context in the current process context. The registered callback function - * is called if some packets have been already transferred since the last time. If it is required - * to process the context asynchronously, fw_iso_context_schedule_flush_completions() is available - * instead. + * is called when a queued packet buffer with the interrupt flag is completed, either after + * transmission in the IT context or after being filled in the IR context. Additionally, the + * callback function is also called for the packet buffer completed at last. Furthermore, the + * callback function is called as well when the header buffer in the context becomes full. If it is + * required to process the context asynchronously, fw_iso_context_schedule_flush_completions() is + * available instead. * * Context: Process context. May sleep due to disable_work_sync(). */ diff --git a/include/linux/firewire.h b/include/linux/firewire.h index f815d12deda0..b632eec3ab52 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -537,9 +537,11 @@ int fw_iso_context_flush_completions(struct fw_iso_context *ctx); * @ctx: the isochronous context * * Schedule a work item on workqueue to process the isochronous context. The registered callback - * function is called in the worker if some packets have been already transferred since the last - * time. If it is required to process the context in the current context, - * fw_iso_context_flush_completions() is available instead. + * function is called by the worker when a queued packet buffer with the interrupt flag is + * completed, either after transmission in the IT context or after being filled in the IR context. + * The callback function is also called when the header buffer in the context becomes full, If it + * is required to process the context in the current context, fw_iso_context_flush_completions() is + * available instead. * * Context: Any context. */ -- cgit v1.2.3 From ede5bbe488d162bcd572880e58f9044c9df84050 Mon Sep 17 00:00:00 2001 From: Nikita Shubin Date: Mon, 9 Sep 2024 11:10:27 +0300 Subject: ARM: ep93xx: add regmap aux_dev The following driver's should be instantiated by ep93xx syscon driver: - reboot - pinctrl - clock They all require access to DEVCFG register with a shared lock held, to avoid conflict writing to swlocked parts of DEVCFG. Provide common resources such as base, regmap and spinlock via auxiliary bus framework. Signed-off-by: Nikita Shubin Tested-by: Alexander Sverdlin Reviewed-by: Linus Walleij Reviewed-by: Stephen Boyd Acked-by: Vinod Koul Signed-off-by: Arnd Bergmann --- include/linux/soc/cirrus/ep93xx.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/cirrus/ep93xx.h b/include/linux/soc/cirrus/ep93xx.h index 56fbe2dc59b1..a27447971302 100644 --- a/include/linux/soc/cirrus/ep93xx.h +++ b/include/linux/soc/cirrus/ep93xx.h @@ -3,6 +3,18 @@ #define _SOC_EP93XX_H struct platform_device; +struct regmap; +struct spinlock_t; + +enum ep93xx_soc_model { + EP93XX_9301_SOC, + EP93XX_9307_SOC, + EP93XX_9312_SOC, +}; + +#include +#include +#include #define EP93XX_CHIP_REV_D0 3 #define EP93XX_CHIP_REV_D1 4 @@ -10,6 +22,20 @@ struct platform_device; #define EP93XX_CHIP_REV_E1 6 #define EP93XX_CHIP_REV_E2 7 +struct ep93xx_regmap_adev { + struct auxiliary_device adev; + struct regmap *map; + void __iomem *base; + spinlock_t *lock; + void (*write)(struct regmap *map, spinlock_t *lock, unsigned int reg, + unsigned int val); + void (*update_bits)(struct regmap *map, spinlock_t *lock, + unsigned int reg, unsigned int mask, unsigned int val); +}; + +#define to_ep93xx_regmap_adev(_adev) \ + container_of((_adev), struct ep93xx_regmap_adev, adev) + #ifdef CONFIG_ARCH_EP93XX int ep93xx_pwm_acquire_gpio(struct platform_device *pdev); void ep93xx_pwm_release_gpio(struct platform_device *pdev); -- cgit v1.2.3 From 2e7f55ce430240a5547b8a94b4c532fc8c20b18b Mon Sep 17 00:00:00 2001 From: Nikita Shubin Date: Mon, 9 Sep 2024 11:10:34 +0300 Subject: dmaengine: cirrus: Convert to DT for Cirrus EP93xx Convert Cirrus EP93xx DMA to device tree usage: - add OF ID match table with data - add of_probe for device tree - add xlate for m2m/m2p - drop subsys_initcall code - drop platform probe - drop platform structs usage >From now on it only supports device tree probing. Co-developed-by: Alexander Sverdlin Signed-off-by: Alexander Sverdlin Acked-by: Vinod Koul Signed-off-by: Nikita Shubin Tested-by: Alexander Sverdlin Signed-off-by: Arnd Bergmann --- drivers/dma/ep93xx_dma.c | 239 ++++++++++++++++++++++++------- include/linux/platform_data/dma-ep93xx.h | 6 + 2 files changed, 191 insertions(+), 54 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma/ep93xx_dma.c b/drivers/dma/ep93xx_dma.c index d6c60635e90d..17c8e2badee2 100644 --- a/drivers/dma/ep93xx_dma.c +++ b/drivers/dma/ep93xx_dma.c @@ -20,6 +20,8 @@ #include #include #include +#include +#include #include #include @@ -104,6 +106,11 @@ #define DMA_MAX_CHAN_BYTES 0xffff #define DMA_MAX_CHAN_DESCRIPTORS 32 +enum ep93xx_dma_type { + M2P_DMA, + M2M_DMA, +}; + struct ep93xx_dma_engine; static int ep93xx_dma_slave_config_write(struct dma_chan *chan, enum dma_transfer_direction dir, @@ -129,11 +136,17 @@ struct ep93xx_dma_desc { struct list_head node; }; +struct ep93xx_dma_chan_cfg { + u8 port; + enum dma_transfer_direction dir; +}; + /** * struct ep93xx_dma_chan - an EP93xx DMA M2P/M2M channel * @chan: dmaengine API channel * @edma: pointer to the engine device * @regs: memory mapped registers + * @dma_cfg: channel number, direction * @irq: interrupt number of the channel * @clk: clock used by this channel * @tasklet: channel specific tasklet used for callbacks @@ -157,14 +170,12 @@ struct ep93xx_dma_desc { * descriptor in the chain. When a descriptor is moved to the @active queue, * the first and chained descriptors are flattened into a single list. * - * @chan.private holds pointer to &struct ep93xx_dma_data which contains - * necessary channel configuration information. For memcpy channels this must - * be %NULL. */ struct ep93xx_dma_chan { struct dma_chan chan; const struct ep93xx_dma_engine *edma; void __iomem *regs; + struct ep93xx_dma_chan_cfg dma_cfg; int irq; struct clk *clk; struct tasklet_struct tasklet; @@ -216,6 +227,11 @@ struct ep93xx_dma_engine { struct ep93xx_dma_chan channels[] __counted_by(num_channels); }; +struct ep93xx_edma_data { + u32 id; + size_t num_channels; +}; + static inline struct device *chan2dev(struct ep93xx_dma_chan *edmac) { return &edmac->chan.dev->device; @@ -318,10 +334,9 @@ static void m2p_set_control(struct ep93xx_dma_chan *edmac, u32 control) static int m2p_hw_setup(struct ep93xx_dma_chan *edmac) { - struct ep93xx_dma_data *data = edmac->chan.private; u32 control; - writel(data->port & 0xf, edmac->regs + M2P_PPALLOC); + writel(edmac->dma_cfg.port & 0xf, edmac->regs + M2P_PPALLOC); control = M2P_CONTROL_CH_ERROR_INT | M2P_CONTROL_ICE | M2P_CONTROL_ENABLE; @@ -458,16 +473,15 @@ static int m2p_hw_interrupt(struct ep93xx_dma_chan *edmac) static int m2m_hw_setup(struct ep93xx_dma_chan *edmac) { - const struct ep93xx_dma_data *data = edmac->chan.private; u32 control = 0; - if (!data) { + if (edmac->dma_cfg.dir == DMA_MEM_TO_MEM) { /* This is memcpy channel, nothing to configure */ writel(control, edmac->regs + M2M_CONTROL); return 0; } - switch (data->port) { + switch (edmac->dma_cfg.port) { case EP93XX_DMA_SSP: /* * This was found via experimenting - anything less than 5 @@ -477,7 +491,7 @@ static int m2m_hw_setup(struct ep93xx_dma_chan *edmac) control = (5 << M2M_CONTROL_PWSC_SHIFT); control |= M2M_CONTROL_NO_HDSK; - if (data->direction == DMA_MEM_TO_DEV) { + if (edmac->dma_cfg.dir == DMA_MEM_TO_DEV) { control |= M2M_CONTROL_DAH; control |= M2M_CONTROL_TM_TX; control |= M2M_CONTROL_RSS_SSPTX; @@ -493,7 +507,7 @@ static int m2m_hw_setup(struct ep93xx_dma_chan *edmac) * This IDE part is totally untested. Values below are taken * from the EP93xx Users's Guide and might not be correct. */ - if (data->direction == DMA_MEM_TO_DEV) { + if (edmac->dma_cfg.dir == DMA_MEM_TO_DEV) { /* Worst case from the UG */ control = (3 << M2M_CONTROL_PWSC_SHIFT); control |= M2M_CONTROL_DAH; @@ -548,7 +562,6 @@ static void m2m_fill_desc(struct ep93xx_dma_chan *edmac) static void m2m_hw_submit(struct ep93xx_dma_chan *edmac) { - struct ep93xx_dma_data *data = edmac->chan.private; u32 control = readl(edmac->regs + M2M_CONTROL); /* @@ -574,7 +587,7 @@ static void m2m_hw_submit(struct ep93xx_dma_chan *edmac) control |= M2M_CONTROL_ENABLE; writel(control, edmac->regs + M2M_CONTROL); - if (!data) { + if (edmac->dma_cfg.dir == DMA_MEM_TO_MEM) { /* * For memcpy channels the software trigger must be asserted * in order to start the memcpy operation. @@ -636,7 +649,7 @@ static int m2m_hw_interrupt(struct ep93xx_dma_chan *edmac) */ if (ep93xx_dma_advance_active(edmac)) { m2m_fill_desc(edmac); - if (done && !edmac->chan.private) { + if (done && edmac->dma_cfg.dir == DMA_MEM_TO_MEM) { /* Software trigger for memcpy channel */ control = readl(edmac->regs + M2M_CONTROL); control |= M2M_CONTROL_START; @@ -867,25 +880,22 @@ static dma_cookie_t ep93xx_dma_tx_submit(struct dma_async_tx_descriptor *tx) static int ep93xx_dma_alloc_chan_resources(struct dma_chan *chan) { struct ep93xx_dma_chan *edmac = to_ep93xx_dma_chan(chan); - struct ep93xx_dma_data *data = chan->private; const char *name = dma_chan_name(chan); int ret, i; /* Sanity check the channel parameters */ if (!edmac->edma->m2m) { - if (!data) - return -EINVAL; - if (data->port < EP93XX_DMA_I2S1 || - data->port > EP93XX_DMA_IRDA) + if (edmac->dma_cfg.port < EP93XX_DMA_I2S1 || + edmac->dma_cfg.port > EP93XX_DMA_IRDA) return -EINVAL; - if (data->direction != ep93xx_dma_chan_direction(chan)) + if (edmac->dma_cfg.dir != ep93xx_dma_chan_direction(chan)) return -EINVAL; } else { - if (data) { - switch (data->port) { + if (edmac->dma_cfg.dir != DMA_MEM_TO_MEM) { + switch (edmac->dma_cfg.port) { case EP93XX_DMA_SSP: case EP93XX_DMA_IDE: - if (!is_slave_direction(data->direction)) + if (!is_slave_direction(edmac->dma_cfg.dir)) return -EINVAL; break; default: @@ -894,9 +904,6 @@ static int ep93xx_dma_alloc_chan_resources(struct dma_chan *chan) } } - if (data && data->name) - name = data->name; - ret = clk_prepare_enable(edmac->clk); if (ret) return ret; @@ -1315,36 +1322,53 @@ static void ep93xx_dma_issue_pending(struct dma_chan *chan) ep93xx_dma_advance_work(to_ep93xx_dma_chan(chan)); } -static int __init ep93xx_dma_probe(struct platform_device *pdev) +static struct ep93xx_dma_engine *ep93xx_dma_of_probe(struct platform_device *pdev) { - struct ep93xx_dma_platform_data *pdata = dev_get_platdata(&pdev->dev); + const struct ep93xx_edma_data *data; + struct device *dev = &pdev->dev; struct ep93xx_dma_engine *edma; struct dma_device *dma_dev; - int ret, i; + char dma_clk_name[5]; + int i; - edma = kzalloc(struct_size(edma, channels, pdata->num_channels), GFP_KERNEL); + data = device_get_match_data(dev); + if (!data) + return ERR_PTR(dev_err_probe(dev, -ENODEV, "No device match found\n")); + + edma = devm_kzalloc(dev, struct_size(edma, channels, data->num_channels), + GFP_KERNEL); if (!edma) - return -ENOMEM; + return ERR_PTR(-ENOMEM); + edma->m2m = data->id; + edma->num_channels = data->num_channels; dma_dev = &edma->dma_dev; - edma->m2m = platform_get_device_id(pdev)->driver_data; - edma->num_channels = pdata->num_channels; INIT_LIST_HEAD(&dma_dev->channels); - for (i = 0; i < pdata->num_channels; i++) { - const struct ep93xx_dma_chan_data *cdata = &pdata->channels[i]; + for (i = 0; i < edma->num_channels; i++) { struct ep93xx_dma_chan *edmac = &edma->channels[i]; edmac->chan.device = dma_dev; - edmac->regs = cdata->base; - edmac->irq = cdata->irq; + edmac->regs = devm_platform_ioremap_resource(pdev, i); + if (IS_ERR(edmac->regs)) + return edmac->regs; + + edmac->irq = fwnode_irq_get(dev_fwnode(dev), i); + if (edmac->irq < 0) + return ERR_PTR(edmac->irq); + edmac->edma = edma; - edmac->clk = clk_get(NULL, cdata->name); + if (edma->m2m) + sprintf(dma_clk_name, "m2m%u", i); + else + sprintf(dma_clk_name, "m2p%u", i); + + edmac->clk = devm_clk_get(dev, dma_clk_name); if (IS_ERR(edmac->clk)) { - dev_warn(&pdev->dev, "failed to get clock for %s\n", - cdata->name); - continue; + dev_err_probe(dev, PTR_ERR(edmac->clk), + "no %s clock found\n", dma_clk_name); + return ERR_CAST(edmac->clk); } spin_lock_init(&edmac->lock); @@ -1357,6 +1381,90 @@ static int __init ep93xx_dma_probe(struct platform_device *pdev) &dma_dev->channels); } + return edma; +} + +static bool ep93xx_m2p_dma_filter(struct dma_chan *chan, void *filter_param) +{ + struct ep93xx_dma_chan *echan = to_ep93xx_dma_chan(chan); + struct ep93xx_dma_chan_cfg *cfg = filter_param; + + if (cfg->dir != ep93xx_dma_chan_direction(chan)) + return false; + + echan->dma_cfg = *cfg; + return true; +} + +static struct dma_chan *ep93xx_m2p_dma_of_xlate(struct of_phandle_args *dma_spec, + struct of_dma *ofdma) +{ + struct ep93xx_dma_engine *edma = ofdma->of_dma_data; + dma_cap_mask_t mask = edma->dma_dev.cap_mask; + struct ep93xx_dma_chan_cfg dma_cfg; + u8 port = dma_spec->args[0]; + u8 direction = dma_spec->args[1]; + + if (port > EP93XX_DMA_IRDA) + return NULL; + + if (!is_slave_direction(direction)) + return NULL; + + dma_cfg.port = port; + dma_cfg.dir = direction; + + return __dma_request_channel(&mask, ep93xx_m2p_dma_filter, &dma_cfg, ofdma->of_node); +} + +static bool ep93xx_m2m_dma_filter(struct dma_chan *chan, void *filter_param) +{ + struct ep93xx_dma_chan *echan = to_ep93xx_dma_chan(chan); + struct ep93xx_dma_chan_cfg *cfg = filter_param; + + echan->dma_cfg = *cfg; + + return true; +} + +static struct dma_chan *ep93xx_m2m_dma_of_xlate(struct of_phandle_args *dma_spec, + struct of_dma *ofdma) +{ + struct ep93xx_dma_engine *edma = ofdma->of_dma_data; + dma_cap_mask_t mask = edma->dma_dev.cap_mask; + struct ep93xx_dma_chan_cfg dma_cfg; + u8 port = dma_spec->args[0]; + u8 direction = dma_spec->args[1]; + + if (!is_slave_direction(direction)) + return NULL; + + switch (port) { + case EP93XX_DMA_SSP: + case EP93XX_DMA_IDE: + break; + default: + return NULL; + } + + dma_cfg.port = port; + dma_cfg.dir = direction; + + return __dma_request_channel(&mask, ep93xx_m2m_dma_filter, &dma_cfg, ofdma->of_node); +} + +static int ep93xx_dma_probe(struct platform_device *pdev) +{ + struct ep93xx_dma_engine *edma; + struct dma_device *dma_dev; + int ret; + + edma = ep93xx_dma_of_probe(pdev); + if (!edma) + return PTR_ERR(edma); + + dma_dev = &edma->dma_dev; + dma_cap_zero(dma_dev->cap_mask); dma_cap_set(DMA_SLAVE, dma_dev->cap_mask); dma_cap_set(DMA_CYCLIC, dma_dev->cap_mask); @@ -1393,21 +1501,46 @@ static int __init ep93xx_dma_probe(struct platform_device *pdev) } ret = dma_async_device_register(dma_dev); - if (unlikely(ret)) { - for (i = 0; i < edma->num_channels; i++) { - struct ep93xx_dma_chan *edmac = &edma->channels[i]; - if (!IS_ERR_OR_NULL(edmac->clk)) - clk_put(edmac->clk); - } - kfree(edma); + if (ret) + return ret; + + if (edma->m2m) { + ret = of_dma_controller_register(pdev->dev.of_node, ep93xx_m2m_dma_of_xlate, + edma); } else { - dev_info(dma_dev->dev, "EP93xx M2%s DMA ready\n", - edma->m2m ? "M" : "P"); + ret = of_dma_controller_register(pdev->dev.of_node, ep93xx_m2p_dma_of_xlate, + edma); } + if (ret) + goto err_dma_unregister; + + dev_info(dma_dev->dev, "EP93xx M2%s DMA ready\n", edma->m2m ? "M" : "P"); + + return 0; + +err_dma_unregister: + dma_async_device_unregister(dma_dev); return ret; } +static const struct ep93xx_edma_data edma_m2p = { + .id = M2P_DMA, + .num_channels = 10, +}; + +static const struct ep93xx_edma_data edma_m2m = { + .id = M2M_DMA, + .num_channels = 2, +}; + +static const struct of_device_id ep93xx_dma_of_ids[] = { + { .compatible = "cirrus,ep9301-dma-m2p", .data = &edma_m2p }, + { .compatible = "cirrus,ep9301-dma-m2m", .data = &edma_m2m }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, ep93xx_dma_of_ids); + static const struct platform_device_id ep93xx_dma_driver_ids[] = { { "ep93xx-dma-m2p", 0 }, { "ep93xx-dma-m2m", 1 }, @@ -1417,15 +1550,13 @@ static const struct platform_device_id ep93xx_dma_driver_ids[] = { static struct platform_driver ep93xx_dma_driver = { .driver = { .name = "ep93xx-dma", + .of_match_table = ep93xx_dma_of_ids, }, .id_table = ep93xx_dma_driver_ids, + .probe = ep93xx_dma_probe, }; -static int __init ep93xx_dma_module_init(void) -{ - return platform_driver_probe(&ep93xx_dma_driver, ep93xx_dma_probe); -} -subsys_initcall(ep93xx_dma_module_init); +module_platform_driver(ep93xx_dma_driver); MODULE_AUTHOR("Mika Westerberg "); MODULE_DESCRIPTION("EP93xx DMA driver"); diff --git a/include/linux/platform_data/dma-ep93xx.h b/include/linux/platform_data/dma-ep93xx.h index eb9805bb3fe8..9ec5cdd5a1eb 100644 --- a/include/linux/platform_data/dma-ep93xx.h +++ b/include/linux/platform_data/dma-ep93xx.h @@ -3,8 +3,11 @@ #define __ASM_ARCH_DMA_H #include +#include #include #include +#include +#include /* * M2P channels. @@ -70,6 +73,9 @@ struct ep93xx_dma_platform_data { static inline bool ep93xx_dma_chan_is_m2p(struct dma_chan *chan) { + if (device_is_compatible(chan->device->dev, "cirrus,ep9301-dma-m2p")) + return true; + return !strcmp(dev_name(chan->device->dev), "ep93xx-dma-m2p"); } -- cgit v1.2.3 From b3ab5787e7acb02874ae86cbe13969d4dd01a585 Mon Sep 17 00:00:00 2001 From: Nikita Shubin Date: Mon, 9 Sep 2024 11:10:48 +0300 Subject: input: keypad: ep93xx: add DT support for Cirrus EP93xx - drop flags, they were not used anyway - add OF ID match table - process "autorepeat", "debounce-delay-ms", prescale from device tree - drop platform data usage and it's header - keymap goes from device tree now on Signed-off-by: Nikita Shubin Acked-by: Dmitry Torokhov Acked-by: Vinod Koul Signed-off-by: Arnd Bergmann --- arch/arm/mach-ep93xx/core.c | 46 --------------------- drivers/input/keyboard/ep93xx_keypad.c | 74 ++++++++++------------------------ include/linux/soc/cirrus/ep93xx.h | 4 -- 3 files changed, 22 insertions(+), 102 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/mach-ep93xx/core.c b/arch/arm/mach-ep93xx/core.c index 03bce5e9d1f1..b99c46d22c4d 100644 --- a/arch/arm/mach-ep93xx/core.c +++ b/arch/arm/mach-ep93xx/core.c @@ -697,52 +697,6 @@ void __init ep93xx_register_keypad(struct ep93xx_keypad_platform_data *data) platform_device_register(&ep93xx_keypad_device); } -int ep93xx_keypad_acquire_gpio(struct platform_device *pdev) -{ - int err; - int i; - - for (i = 0; i < 8; i++) { - err = gpio_request(EP93XX_GPIO_LINE_C(i), dev_name(&pdev->dev)); - if (err) - goto fail_gpio_c; - err = gpio_request(EP93XX_GPIO_LINE_D(i), dev_name(&pdev->dev)); - if (err) - goto fail_gpio_d; - } - - /* Enable the keypad controller; GPIO ports C and D used for keypad */ - ep93xx_devcfg_clear_bits(EP93XX_SYSCON_DEVCFG_KEYS | - EP93XX_SYSCON_DEVCFG_GONK); - - return 0; - -fail_gpio_d: - gpio_free(EP93XX_GPIO_LINE_C(i)); -fail_gpio_c: - for (--i; i >= 0; --i) { - gpio_free(EP93XX_GPIO_LINE_C(i)); - gpio_free(EP93XX_GPIO_LINE_D(i)); - } - return err; -} -EXPORT_SYMBOL(ep93xx_keypad_acquire_gpio); - -void ep93xx_keypad_release_gpio(struct platform_device *pdev) -{ - int i; - - for (i = 0; i < 8; i++) { - gpio_free(EP93XX_GPIO_LINE_C(i)); - gpio_free(EP93XX_GPIO_LINE_D(i)); - } - - /* Disable the keypad controller; GPIO ports C and D used for GPIO */ - ep93xx_devcfg_set_bits(EP93XX_SYSCON_DEVCFG_KEYS | - EP93XX_SYSCON_DEVCFG_GONK); -} -EXPORT_SYMBOL(ep93xx_keypad_release_gpio); - /************************************************************************* * EP93xx I2S audio peripheral handling *************************************************************************/ diff --git a/drivers/input/keyboard/ep93xx_keypad.c b/drivers/input/keyboard/ep93xx_keypad.c index 6b811d6bf625..dcbc50304a5a 100644 --- a/drivers/input/keyboard/ep93xx_keypad.c +++ b/drivers/input/keyboard/ep93xx_keypad.c @@ -6,20 +6,13 @@ * * Based on the pxa27x matrix keypad controller by Rodolfo Giometti. * - * NOTE: - * - * The 3-key reset is triggered by pressing the 3 keys in - * Row 0, Columns 2, 4, and 7 at the same time. This action can - * be disabled by setting the EP93XX_KEYPAD_DISABLE_3_KEY flag. - * - * Normal operation for the matrix does not autorepeat the key press. - * This action can be enabled by setting the EP93XX_KEYPAD_AUTOREPEAT - * flag. */ #include +#include #include #include +#include #include #include #include @@ -27,7 +20,6 @@ #include #include #include -#include #include /* @@ -61,12 +53,16 @@ #define KEY_REG_KEY1_MASK GENMASK(5, 0) #define KEY_REG_KEY1_SHIFT 0 +#define EP93XX_MATRIX_ROWS (8) +#define EP93XX_MATRIX_COLS (8) + #define EP93XX_MATRIX_SIZE (EP93XX_MATRIX_ROWS * EP93XX_MATRIX_COLS) struct ep93xx_keypad { - struct ep93xx_keypad_platform_data *pdata; struct input_dev *input_dev; struct clk *clk; + unsigned int debounce; + u16 prescale; void __iomem *mmio_base; @@ -133,23 +129,11 @@ static irqreturn_t ep93xx_keypad_irq_handler(int irq, void *dev_id) static void ep93xx_keypad_config(struct ep93xx_keypad *keypad) { - struct ep93xx_keypad_platform_data *pdata = keypad->pdata; unsigned int val = 0; - clk_set_rate(keypad->clk, pdata->clk_rate); - - if (pdata->flags & EP93XX_KEYPAD_DISABLE_3_KEY) - val |= KEY_INIT_DIS3KY; - if (pdata->flags & EP93XX_KEYPAD_DIAG_MODE) - val |= KEY_INIT_DIAG; - if (pdata->flags & EP93XX_KEYPAD_BACK_DRIVE) - val |= KEY_INIT_BACK; - if (pdata->flags & EP93XX_KEYPAD_TEST_MODE) - val |= KEY_INIT_T2; - - val |= ((pdata->debounce << KEY_INIT_DBNC_SHIFT) & KEY_INIT_DBNC_MASK); + val |= (keypad->debounce << KEY_INIT_DBNC_SHIFT) & KEY_INIT_DBNC_MASK; - val |= ((pdata->prescale << KEY_INIT_PRSCL_SHIFT) & KEY_INIT_PRSCL_MASK); + val |= (keypad->prescale << KEY_INIT_PRSCL_SHIFT) & KEY_INIT_PRSCL_MASK; __raw_writel(val, keypad->mmio_base + KEY_INIT); } @@ -220,17 +204,10 @@ static int ep93xx_keypad_resume(struct device *dev) static DEFINE_SIMPLE_DEV_PM_OPS(ep93xx_keypad_pm_ops, ep93xx_keypad_suspend, ep93xx_keypad_resume); -static void ep93xx_keypad_release_gpio_action(void *_pdev) -{ - struct platform_device *pdev = _pdev; - - ep93xx_keypad_release_gpio(pdev); -} - static int ep93xx_keypad_probe(struct platform_device *pdev) { + struct device *dev = &pdev->dev; struct ep93xx_keypad *keypad; - const struct matrix_keymap_data *keymap_data; struct input_dev *input_dev; int err; @@ -238,14 +215,6 @@ static int ep93xx_keypad_probe(struct platform_device *pdev) if (!keypad) return -ENOMEM; - keypad->pdata = dev_get_platdata(&pdev->dev); - if (!keypad->pdata) - return -EINVAL; - - keymap_data = keypad->pdata->keymap_data; - if (!keymap_data) - return -EINVAL; - keypad->irq = platform_get_irq(pdev, 0); if (keypad->irq < 0) return keypad->irq; @@ -254,19 +223,13 @@ static int ep93xx_keypad_probe(struct platform_device *pdev) if (IS_ERR(keypad->mmio_base)) return PTR_ERR(keypad->mmio_base); - err = ep93xx_keypad_acquire_gpio(pdev); - if (err) - return err; - - err = devm_add_action_or_reset(&pdev->dev, - ep93xx_keypad_release_gpio_action, pdev); - if (err) - return err; - keypad->clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(keypad->clk)) return PTR_ERR(keypad->clk); + device_property_read_u32(dev, "debounce-delay-ms", &keypad->debounce); + device_property_read_u16(dev, "cirrus,prescale", &keypad->prescale); + input_dev = devm_input_allocate_device(&pdev->dev); if (!input_dev) return -ENOMEM; @@ -278,13 +241,13 @@ static int ep93xx_keypad_probe(struct platform_device *pdev) input_dev->open = ep93xx_keypad_open; input_dev->close = ep93xx_keypad_close; - err = matrix_keypad_build_keymap(keymap_data, NULL, + err = matrix_keypad_build_keymap(NULL, NULL, EP93XX_MATRIX_ROWS, EP93XX_MATRIX_COLS, keypad->keycodes, input_dev); if (err) return err; - if (keypad->pdata->flags & EP93XX_KEYPAD_AUTOREPEAT) + if (device_property_read_bool(&pdev->dev, "autorepeat")) __set_bit(EV_REP, input_dev->evbit); input_set_drvdata(input_dev, keypad); @@ -313,10 +276,17 @@ static void ep93xx_keypad_remove(struct platform_device *pdev) dev_pm_clear_wake_irq(&pdev->dev); } +static const struct of_device_id ep93xx_keypad_of_ids[] = { + { .compatible = "cirrus,ep9307-keypad" }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, ep93xx_keypad_of_ids); + static struct platform_driver ep93xx_keypad_driver = { .driver = { .name = "ep93xx-keypad", .pm = pm_sleep_ptr(&ep93xx_keypad_pm_ops), + .of_match_table = ep93xx_keypad_of_ids, }, .probe = ep93xx_keypad_probe, .remove_new = ep93xx_keypad_remove, diff --git a/include/linux/soc/cirrus/ep93xx.h b/include/linux/soc/cirrus/ep93xx.h index a27447971302..8942bfaf1545 100644 --- a/include/linux/soc/cirrus/ep93xx.h +++ b/include/linux/soc/cirrus/ep93xx.h @@ -41,8 +41,6 @@ int ep93xx_pwm_acquire_gpio(struct platform_device *pdev); void ep93xx_pwm_release_gpio(struct platform_device *pdev); int ep93xx_ide_acquire_gpio(struct platform_device *pdev); void ep93xx_ide_release_gpio(struct platform_device *pdev); -int ep93xx_keypad_acquire_gpio(struct platform_device *pdev); -void ep93xx_keypad_release_gpio(struct platform_device *pdev); int ep93xx_i2s_acquire(void); void ep93xx_i2s_release(void); unsigned int ep93xx_chip_revision(void); @@ -52,8 +50,6 @@ static inline int ep93xx_pwm_acquire_gpio(struct platform_device *pdev) { return static inline void ep93xx_pwm_release_gpio(struct platform_device *pdev) {} static inline int ep93xx_ide_acquire_gpio(struct platform_device *pdev) { return 0; } static inline void ep93xx_ide_release_gpio(struct platform_device *pdev) {} -static inline int ep93xx_keypad_acquire_gpio(struct platform_device *pdev) { return 0; } -static inline void ep93xx_keypad_release_gpio(struct platform_device *pdev) {} static inline int ep93xx_i2s_acquire(void) { return 0; } static inline void ep93xx_i2s_release(void) {} static inline unsigned int ep93xx_chip_revision(void) { return 0; } -- cgit v1.2.3 From a48ac3dc569771c18fcafbc8351d820cc343c54a Mon Sep 17 00:00:00 2001 From: Nikita Shubin Date: Mon, 9 Sep 2024 11:10:58 +0300 Subject: pwm: ep93xx: drop legacy pinctrl MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Drop legacy gpio request/free since we are using pinctrl for this now. Signed-off-by: Nikita Shubin Acked-by: Uwe Kleine-König Acked-by: Thierry Reding Acked-by: Linus Walleij Acked-by: Vinod Koul Signed-off-by: Arnd Bergmann --- arch/arm/mach-ep93xx/core.c | 42 --------------------------------------- drivers/pwm/pwm-ep93xx.c | 18 ----------------- include/linux/soc/cirrus/ep93xx.h | 4 ---- 3 files changed, 64 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/mach-ep93xx/core.c b/arch/arm/mach-ep93xx/core.c index b99c46d22c4d..4ddf1a4cba33 100644 --- a/arch/arm/mach-ep93xx/core.c +++ b/arch/arm/mach-ep93xx/core.c @@ -577,48 +577,6 @@ void __init ep93xx_register_pwm(int pwm0, int pwm1) platform_device_register(&ep93xx_pwm1_device); } -int ep93xx_pwm_acquire_gpio(struct platform_device *pdev) -{ - int err; - - if (pdev->id == 0) { - err = 0; - } else if (pdev->id == 1) { - err = gpio_request(EP93XX_GPIO_LINE_EGPIO14, - dev_name(&pdev->dev)); - if (err) - return err; - err = gpio_direction_output(EP93XX_GPIO_LINE_EGPIO14, 0); - if (err) - goto fail; - - /* PWM 1 output on EGPIO[14] */ - ep93xx_devcfg_set_bits(EP93XX_SYSCON_DEVCFG_PONG); - } else { - err = -ENODEV; - } - - return err; - -fail: - gpio_free(EP93XX_GPIO_LINE_EGPIO14); - return err; -} -EXPORT_SYMBOL(ep93xx_pwm_acquire_gpio); - -void ep93xx_pwm_release_gpio(struct platform_device *pdev) -{ - if (pdev->id == 1) { - gpio_direction_input(EP93XX_GPIO_LINE_EGPIO14); - gpio_free(EP93XX_GPIO_LINE_EGPIO14); - - /* EGPIO[14] used for GPIO */ - ep93xx_devcfg_clear_bits(EP93XX_SYSCON_DEVCFG_PONG); - } -} -EXPORT_SYMBOL(ep93xx_pwm_release_gpio); - - /************************************************************************* * EP93xx video peripheral handling *************************************************************************/ diff --git a/drivers/pwm/pwm-ep93xx.c b/drivers/pwm/pwm-ep93xx.c index 67c3fdbf7ae3..994f89ac43b4 100644 --- a/drivers/pwm/pwm-ep93xx.c +++ b/drivers/pwm/pwm-ep93xx.c @@ -27,8 +27,6 @@ #include -#include /* for ep93xx_pwm_{acquire,release}_gpio() */ - #define EP93XX_PWMx_TERM_COUNT 0x00 #define EP93XX_PWMx_DUTY_CYCLE 0x04 #define EP93XX_PWMx_ENABLE 0x08 @@ -44,20 +42,6 @@ static inline struct ep93xx_pwm *to_ep93xx_pwm(struct pwm_chip *chip) return pwmchip_get_drvdata(chip); } -static int ep93xx_pwm_request(struct pwm_chip *chip, struct pwm_device *pwm) -{ - struct platform_device *pdev = to_platform_device(pwmchip_parent(chip)); - - return ep93xx_pwm_acquire_gpio(pdev); -} - -static void ep93xx_pwm_free(struct pwm_chip *chip, struct pwm_device *pwm) -{ - struct platform_device *pdev = to_platform_device(pwmchip_parent(chip)); - - ep93xx_pwm_release_gpio(pdev); -} - static int ep93xx_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, const struct pwm_state *state) { @@ -156,8 +140,6 @@ static int ep93xx_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, } static const struct pwm_ops ep93xx_pwm_ops = { - .request = ep93xx_pwm_request, - .free = ep93xx_pwm_free, .apply = ep93xx_pwm_apply, }; diff --git a/include/linux/soc/cirrus/ep93xx.h b/include/linux/soc/cirrus/ep93xx.h index 8942bfaf1545..f6376edc1b33 100644 --- a/include/linux/soc/cirrus/ep93xx.h +++ b/include/linux/soc/cirrus/ep93xx.h @@ -37,8 +37,6 @@ struct ep93xx_regmap_adev { container_of((_adev), struct ep93xx_regmap_adev, adev) #ifdef CONFIG_ARCH_EP93XX -int ep93xx_pwm_acquire_gpio(struct platform_device *pdev); -void ep93xx_pwm_release_gpio(struct platform_device *pdev); int ep93xx_ide_acquire_gpio(struct platform_device *pdev); void ep93xx_ide_release_gpio(struct platform_device *pdev); int ep93xx_i2s_acquire(void); @@ -46,8 +44,6 @@ void ep93xx_i2s_release(void); unsigned int ep93xx_chip_revision(void); #else -static inline int ep93xx_pwm_acquire_gpio(struct platform_device *pdev) { return 0; } -static inline void ep93xx_pwm_release_gpio(struct platform_device *pdev) {} static inline int ep93xx_ide_acquire_gpio(struct platform_device *pdev) { return 0; } static inline void ep93xx_ide_release_gpio(struct platform_device *pdev) {} static inline int ep93xx_i2s_acquire(void) { return 0; } -- cgit v1.2.3 From a632229be268dde8f6d407638b5cfba8b78201d6 Mon Sep 17 00:00:00 2001 From: Nikita Shubin Date: Mon, 9 Sep 2024 11:10:59 +0300 Subject: ata: pata_ep93xx: remove legacy pinctrl use Drop legacy acquire/release since we are using pinctrl for this now. Signed-off-by: Nikita Shubin Tested-by: Alexander Sverdlin Reviewed-by: Sergey Shtylyov Reviewed-by: Linus Walleij Reviewed-by: Andy Shevchenko Reviewed-by: Mark Brown Reviewed-by: Krzysztof Kozlowski Reviewed-by: Andy Shevchenko Acked-by: Damien Le Moal Acked-by: Vinod Koul Signed-off-by: Arnd Bergmann --- arch/arm/mach-ep93xx/core.c | 72 --------------------------------------- drivers/ata/pata_ep93xx.c | 25 ++++---------- include/linux/soc/cirrus/ep93xx.h | 4 --- 3 files changed, 6 insertions(+), 95 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/mach-ep93xx/core.c b/arch/arm/mach-ep93xx/core.c index 4ddf1a4cba33..9c6154bb37b5 100644 --- a/arch/arm/mach-ep93xx/core.c +++ b/arch/arm/mach-ep93xx/core.c @@ -779,78 +779,6 @@ void __init ep93xx_register_ide(void) platform_device_register(&ep93xx_ide_device); } -int ep93xx_ide_acquire_gpio(struct platform_device *pdev) -{ - int err; - int i; - - err = gpio_request(EP93XX_GPIO_LINE_EGPIO2, dev_name(&pdev->dev)); - if (err) - return err; - err = gpio_request(EP93XX_GPIO_LINE_EGPIO15, dev_name(&pdev->dev)); - if (err) - goto fail_egpio15; - for (i = 2; i < 8; i++) { - err = gpio_request(EP93XX_GPIO_LINE_E(i), dev_name(&pdev->dev)); - if (err) - goto fail_gpio_e; - } - for (i = 4; i < 8; i++) { - err = gpio_request(EP93XX_GPIO_LINE_G(i), dev_name(&pdev->dev)); - if (err) - goto fail_gpio_g; - } - for (i = 0; i < 8; i++) { - err = gpio_request(EP93XX_GPIO_LINE_H(i), dev_name(&pdev->dev)); - if (err) - goto fail_gpio_h; - } - - /* GPIO ports E[7:2], G[7:4] and H used by IDE */ - ep93xx_devcfg_clear_bits(EP93XX_SYSCON_DEVCFG_EONIDE | - EP93XX_SYSCON_DEVCFG_GONIDE | - EP93XX_SYSCON_DEVCFG_HONIDE); - return 0; - -fail_gpio_h: - for (--i; i >= 0; --i) - gpio_free(EP93XX_GPIO_LINE_H(i)); - i = 8; -fail_gpio_g: - for (--i; i >= 4; --i) - gpio_free(EP93XX_GPIO_LINE_G(i)); - i = 8; -fail_gpio_e: - for (--i; i >= 2; --i) - gpio_free(EP93XX_GPIO_LINE_E(i)); - gpio_free(EP93XX_GPIO_LINE_EGPIO15); -fail_egpio15: - gpio_free(EP93XX_GPIO_LINE_EGPIO2); - return err; -} -EXPORT_SYMBOL(ep93xx_ide_acquire_gpio); - -void ep93xx_ide_release_gpio(struct platform_device *pdev) -{ - int i; - - for (i = 2; i < 8; i++) - gpio_free(EP93XX_GPIO_LINE_E(i)); - for (i = 4; i < 8; i++) - gpio_free(EP93XX_GPIO_LINE_G(i)); - for (i = 0; i < 8; i++) - gpio_free(EP93XX_GPIO_LINE_H(i)); - gpio_free(EP93XX_GPIO_LINE_EGPIO15); - gpio_free(EP93XX_GPIO_LINE_EGPIO2); - - - /* GPIO ports E[7:2], G[7:4] and H used by GPIO */ - ep93xx_devcfg_set_bits(EP93XX_SYSCON_DEVCFG_EONIDE | - EP93XX_SYSCON_DEVCFG_GONIDE | - EP93XX_SYSCON_DEVCFG_HONIDE); -} -EXPORT_SYMBOL(ep93xx_ide_release_gpio); - /************************************************************************* * EP93xx ADC *************************************************************************/ diff --git a/drivers/ata/pata_ep93xx.c b/drivers/ata/pata_ep93xx.c index 13246a92e29f..a8555f630097 100644 --- a/drivers/ata/pata_ep93xx.c +++ b/drivers/ata/pata_ep93xx.c @@ -922,28 +922,18 @@ static int ep93xx_pata_probe(struct platform_device *pdev) void __iomem *ide_base; int err; - err = ep93xx_ide_acquire_gpio(pdev); - if (err) - return err; - /* INT[3] (IRQ_EP93XX_EXT3) line connected as pull down */ irq = platform_get_irq(pdev, 0); - if (irq < 0) { - err = irq; - goto err_rel_gpio; - } + if (irq < 0) + return irq; ide_base = devm_platform_get_and_ioremap_resource(pdev, 0, &mem_res); - if (IS_ERR(ide_base)) { - err = PTR_ERR(ide_base); - goto err_rel_gpio; - } + if (IS_ERR(ide_base)) + return PTR_ERR(ide_base); drv_data = devm_kzalloc(&pdev->dev, sizeof(*drv_data), GFP_KERNEL); - if (!drv_data) { - err = -ENOMEM; - goto err_rel_gpio; - } + if (!drv_data) + return -ENOMEM; drv_data->pdev = pdev; drv_data->ide_base = ide_base; @@ -1002,8 +992,6 @@ static int ep93xx_pata_probe(struct platform_device *pdev) err_rel_dma: ep93xx_pata_release_dma(drv_data); -err_rel_gpio: - ep93xx_ide_release_gpio(pdev); return err; } @@ -1015,7 +1003,6 @@ static void ep93xx_pata_remove(struct platform_device *pdev) ata_host_detach(host); ep93xx_pata_release_dma(drv_data); ep93xx_pata_clear_regs(drv_data->ide_base); - ep93xx_ide_release_gpio(pdev); } static const struct of_device_id ep93xx_pata_of_ids[] = { diff --git a/include/linux/soc/cirrus/ep93xx.h b/include/linux/soc/cirrus/ep93xx.h index f6376edc1b33..142c33a2d7db 100644 --- a/include/linux/soc/cirrus/ep93xx.h +++ b/include/linux/soc/cirrus/ep93xx.h @@ -37,15 +37,11 @@ struct ep93xx_regmap_adev { container_of((_adev), struct ep93xx_regmap_adev, adev) #ifdef CONFIG_ARCH_EP93XX -int ep93xx_ide_acquire_gpio(struct platform_device *pdev); -void ep93xx_ide_release_gpio(struct platform_device *pdev); int ep93xx_i2s_acquire(void); void ep93xx_i2s_release(void); unsigned int ep93xx_chip_revision(void); #else -static inline int ep93xx_ide_acquire_gpio(struct platform_device *pdev) { return 0; } -static inline void ep93xx_ide_release_gpio(struct platform_device *pdev) {} static inline int ep93xx_i2s_acquire(void) { return 0; } static inline void ep93xx_i2s_release(void) {} static inline unsigned int ep93xx_chip_revision(void) { return 0; } -- cgit v1.2.3 From e5ef574dda702e62081d5c7991949cbdb7f65c08 Mon Sep 17 00:00:00 2001 From: Nikita Shubin Date: Mon, 9 Sep 2024 11:11:00 +0300 Subject: ARM: ep93xx: delete all boardfiles Delete the ep93xx board files. Signed-off-by: Nikita Shubin Tested-by: Alexander Sverdlin Acked-by: Vinod Koul Signed-off-by: Arnd Bergmann --- arch/arm/mach-ep93xx/clock.c | 733 ------------------------ arch/arm/mach-ep93xx/core.c | 955 ------------------------------- arch/arm/mach-ep93xx/dma.c | 114 ---- arch/arm/mach-ep93xx/edb93xx.c | 368 ------------ arch/arm/mach-ep93xx/ep93xx-regs.h | 38 -- arch/arm/mach-ep93xx/gpio-ep93xx.h | 111 ---- arch/arm/mach-ep93xx/hardware.h | 25 - arch/arm/mach-ep93xx/irqs.h | 76 --- arch/arm/mach-ep93xx/platform.h | 42 -- arch/arm/mach-ep93xx/soc.h | 212 ------- arch/arm/mach-ep93xx/timer-ep93xx.c | 143 ----- arch/arm/mach-ep93xx/ts72xx.c | 422 -------------- arch/arm/mach-ep93xx/ts72xx.h | 94 --- arch/arm/mach-ep93xx/vision_ep9307.c | 321 ----------- include/linux/platform_data/spi-ep93xx.h | 15 - 15 files changed, 3669 deletions(-) delete mode 100644 arch/arm/mach-ep93xx/clock.c delete mode 100644 arch/arm/mach-ep93xx/core.c delete mode 100644 arch/arm/mach-ep93xx/dma.c delete mode 100644 arch/arm/mach-ep93xx/edb93xx.c delete mode 100644 arch/arm/mach-ep93xx/ep93xx-regs.h delete mode 100644 arch/arm/mach-ep93xx/gpio-ep93xx.h delete mode 100644 arch/arm/mach-ep93xx/hardware.h delete mode 100644 arch/arm/mach-ep93xx/irqs.h delete mode 100644 arch/arm/mach-ep93xx/platform.h delete mode 100644 arch/arm/mach-ep93xx/soc.h delete mode 100644 arch/arm/mach-ep93xx/timer-ep93xx.c delete mode 100644 arch/arm/mach-ep93xx/ts72xx.c delete mode 100644 arch/arm/mach-ep93xx/ts72xx.h delete mode 100644 arch/arm/mach-ep93xx/vision_ep9307.c delete mode 100644 include/linux/platform_data/spi-ep93xx.h (limited to 'include/linux') diff --git a/arch/arm/mach-ep93xx/clock.c b/arch/arm/mach-ep93xx/clock.c deleted file mode 100644 index e9f72a529b50..000000000000 --- a/arch/arm/mach-ep93xx/clock.c +++ /dev/null @@ -1,733 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * arch/arm/mach-ep93xx/clock.c - * Clock control for Cirrus EP93xx chips. - * - * Copyright (C) 2006 Lennert Buytenhek - */ - -#define pr_fmt(fmt) "ep93xx " KBUILD_MODNAME ": " fmt - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "hardware.h" - -#include - -#include "soc.h" - -static DEFINE_SPINLOCK(clk_lock); - -static char fclk_divisors[] = { 1, 2, 4, 8, 16, 1, 1, 1 }; -static char hclk_divisors[] = { 1, 2, 4, 5, 6, 8, 16, 32 }; -static char pclk_divisors[] = { 1, 2, 4, 8 }; - -static char adc_divisors[] = { 16, 4 }; -static char sclk_divisors[] = { 2, 4 }; -static char lrclk_divisors[] = { 32, 64, 128 }; - -static const char * const mux_parents[] = { - "xtali", - "pll1", - "pll2" -}; - -/* - * PLL rate = 14.7456 MHz * (X1FBD + 1) * (X2FBD + 1) / (X2IPD + 1) / 2^PS - */ -static unsigned long calc_pll_rate(unsigned long long rate, u32 config_word) -{ - int i; - - rate *= ((config_word >> 11) & 0x1f) + 1; /* X1FBD */ - rate *= ((config_word >> 5) & 0x3f) + 1; /* X2FBD */ - do_div(rate, (config_word & 0x1f) + 1); /* X2IPD */ - for (i = 0; i < ((config_word >> 16) & 3); i++) /* PS */ - rate >>= 1; - - return (unsigned long)rate; -} - -struct clk_psc { - struct clk_hw hw; - void __iomem *reg; - u8 bit_idx; - u32 mask; - u8 shift; - u8 width; - char *div; - u8 num_div; - spinlock_t *lock; -}; - -#define to_clk_psc(_hw) container_of(_hw, struct clk_psc, hw) - -static int ep93xx_clk_is_enabled(struct clk_hw *hw) -{ - struct clk_psc *psc = to_clk_psc(hw); - u32 val = readl(psc->reg); - - return (val & BIT(psc->bit_idx)) ? 1 : 0; -} - -static int ep93xx_clk_enable(struct clk_hw *hw) -{ - struct clk_psc *psc = to_clk_psc(hw); - unsigned long flags = 0; - u32 val; - - if (psc->lock) - spin_lock_irqsave(psc->lock, flags); - - val = __raw_readl(psc->reg); - val |= BIT(psc->bit_idx); - - ep93xx_syscon_swlocked_write(val, psc->reg); - - if (psc->lock) - spin_unlock_irqrestore(psc->lock, flags); - - return 0; -} - -static void ep93xx_clk_disable(struct clk_hw *hw) -{ - struct clk_psc *psc = to_clk_psc(hw); - unsigned long flags = 0; - u32 val; - - if (psc->lock) - spin_lock_irqsave(psc->lock, flags); - - val = __raw_readl(psc->reg); - val &= ~BIT(psc->bit_idx); - - ep93xx_syscon_swlocked_write(val, psc->reg); - - if (psc->lock) - spin_unlock_irqrestore(psc->lock, flags); -} - -static const struct clk_ops clk_ep93xx_gate_ops = { - .enable = ep93xx_clk_enable, - .disable = ep93xx_clk_disable, - .is_enabled = ep93xx_clk_is_enabled, -}; - -static struct clk_hw *ep93xx_clk_register_gate(const char *name, - const char *parent_name, - void __iomem *reg, - u8 bit_idx) -{ - struct clk_init_data init; - struct clk_psc *psc; - struct clk *clk; - - psc = kzalloc(sizeof(*psc), GFP_KERNEL); - if (!psc) - return ERR_PTR(-ENOMEM); - - init.name = name; - init.ops = &clk_ep93xx_gate_ops; - init.flags = CLK_SET_RATE_PARENT; - init.parent_names = (parent_name ? &parent_name : NULL); - init.num_parents = (parent_name ? 1 : 0); - - psc->reg = reg; - psc->bit_idx = bit_idx; - psc->hw.init = &init; - psc->lock = &clk_lock; - - clk = clk_register(NULL, &psc->hw); - if (IS_ERR(clk)) { - kfree(psc); - return ERR_CAST(clk); - } - - return &psc->hw; -} - -static u8 ep93xx_mux_get_parent(struct clk_hw *hw) -{ - struct clk_psc *psc = to_clk_psc(hw); - u32 val = __raw_readl(psc->reg); - - if (!(val & EP93XX_SYSCON_CLKDIV_ESEL)) - return 0; - - if (!(val & EP93XX_SYSCON_CLKDIV_PSEL)) - return 1; - - return 2; -} - -static int ep93xx_mux_set_parent_lock(struct clk_hw *hw, u8 index) -{ - struct clk_psc *psc = to_clk_psc(hw); - unsigned long flags = 0; - u32 val; - - if (index >= ARRAY_SIZE(mux_parents)) - return -EINVAL; - - if (psc->lock) - spin_lock_irqsave(psc->lock, flags); - - val = __raw_readl(psc->reg); - val &= ~(EP93XX_SYSCON_CLKDIV_ESEL | EP93XX_SYSCON_CLKDIV_PSEL); - - - if (index != 0) { - val |= EP93XX_SYSCON_CLKDIV_ESEL; - val |= (index - 1) ? EP93XX_SYSCON_CLKDIV_PSEL : 0; - } - - ep93xx_syscon_swlocked_write(val, psc->reg); - - if (psc->lock) - spin_unlock_irqrestore(psc->lock, flags); - - return 0; -} - -static bool is_best(unsigned long rate, unsigned long now, - unsigned long best) -{ - return abs(rate - now) < abs(rate - best); -} - -static int ep93xx_mux_determine_rate(struct clk_hw *hw, - struct clk_rate_request *req) -{ - unsigned long rate = req->rate; - struct clk *best_parent = NULL; - unsigned long __parent_rate; - unsigned long best_rate = 0, actual_rate, mclk_rate; - unsigned long best_parent_rate; - int __div = 0, __pdiv = 0; - int i; - - /* - * Try the two pll's and the external clock - * Because the valid predividers are 2, 2.5 and 3, we multiply - * all the clocks by 2 to avoid floating point math. - * - * This is based on the algorithm in the ep93xx raster guide: - * http://be-a-maverick.com/en/pubs/appNote/AN269REV1.pdf - * - */ - for (i = 0; i < ARRAY_SIZE(mux_parents); i++) { - struct clk *parent = clk_get_sys(mux_parents[i], NULL); - - __parent_rate = clk_get_rate(parent); - mclk_rate = __parent_rate * 2; - - /* Try each predivider value */ - for (__pdiv = 4; __pdiv <= 6; __pdiv++) { - __div = mclk_rate / (rate * __pdiv); - if (__div < 2 || __div > 127) - continue; - - actual_rate = mclk_rate / (__pdiv * __div); - if (is_best(rate, actual_rate, best_rate)) { - best_rate = actual_rate; - best_parent_rate = __parent_rate; - best_parent = parent; - } - } - } - - if (!best_parent) - return -EINVAL; - - req->best_parent_rate = best_parent_rate; - req->best_parent_hw = __clk_get_hw(best_parent); - req->rate = best_rate; - - return 0; -} - -static unsigned long ep93xx_ddiv_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate) -{ - struct clk_psc *psc = to_clk_psc(hw); - unsigned long rate = 0; - u32 val = __raw_readl(psc->reg); - int __pdiv = ((val >> EP93XX_SYSCON_CLKDIV_PDIV_SHIFT) & 0x03); - int __div = val & 0x7f; - - if (__div > 0) - rate = (parent_rate * 2) / ((__pdiv + 3) * __div); - - return rate; -} - -static int ep93xx_ddiv_set_rate(struct clk_hw *hw, unsigned long rate, - unsigned long parent_rate) -{ - struct clk_psc *psc = to_clk_psc(hw); - int pdiv = 0, div = 0; - unsigned long best_rate = 0, actual_rate, mclk_rate; - int __div = 0, __pdiv = 0; - u32 val; - - mclk_rate = parent_rate * 2; - - for (__pdiv = 4; __pdiv <= 6; __pdiv++) { - __div = mclk_rate / (rate * __pdiv); - if (__div < 2 || __div > 127) - continue; - - actual_rate = mclk_rate / (__pdiv * __div); - if (is_best(rate, actual_rate, best_rate)) { - pdiv = __pdiv - 3; - div = __div; - best_rate = actual_rate; - } - } - - if (!best_rate) - return -EINVAL; - - val = __raw_readl(psc->reg); - - /* Clear old dividers */ - val &= ~0x37f; - - /* Set the new pdiv and div bits for the new clock rate */ - val |= (pdiv << EP93XX_SYSCON_CLKDIV_PDIV_SHIFT) | div; - ep93xx_syscon_swlocked_write(val, psc->reg); - - return 0; -} - -static const struct clk_ops clk_ddiv_ops = { - .enable = ep93xx_clk_enable, - .disable = ep93xx_clk_disable, - .is_enabled = ep93xx_clk_is_enabled, - .get_parent = ep93xx_mux_get_parent, - .set_parent = ep93xx_mux_set_parent_lock, - .determine_rate = ep93xx_mux_determine_rate, - .recalc_rate = ep93xx_ddiv_recalc_rate, - .set_rate = ep93xx_ddiv_set_rate, -}; - -static struct clk_hw *clk_hw_register_ddiv(const char *name, - void __iomem *reg, - u8 bit_idx) -{ - struct clk_init_data init; - struct clk_psc *psc; - struct clk *clk; - - psc = kzalloc(sizeof(*psc), GFP_KERNEL); - if (!psc) - return ERR_PTR(-ENOMEM); - - init.name = name; - init.ops = &clk_ddiv_ops; - init.flags = 0; - init.parent_names = mux_parents; - init.num_parents = ARRAY_SIZE(mux_parents); - - psc->reg = reg; - psc->bit_idx = bit_idx; - psc->lock = &clk_lock; - psc->hw.init = &init; - - clk = clk_register(NULL, &psc->hw); - if (IS_ERR(clk)) { - kfree(psc); - return ERR_CAST(clk); - } - return &psc->hw; -} - -static unsigned long ep93xx_div_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate) -{ - struct clk_psc *psc = to_clk_psc(hw); - u32 val = __raw_readl(psc->reg); - u8 index = (val & psc->mask) >> psc->shift; - - if (index >= psc->num_div) - return 0; - - return DIV_ROUND_UP_ULL(parent_rate, psc->div[index]); -} - -static long ep93xx_div_round_rate(struct clk_hw *hw, unsigned long rate, - unsigned long *parent_rate) -{ - struct clk_psc *psc = to_clk_psc(hw); - unsigned long best = 0, now, maxdiv; - int i; - - maxdiv = psc->div[psc->num_div - 1]; - - for (i = 0; i < psc->num_div; i++) { - if ((rate * psc->div[i]) == *parent_rate) - return DIV_ROUND_UP_ULL((u64)*parent_rate, psc->div[i]); - - now = DIV_ROUND_UP_ULL((u64)*parent_rate, psc->div[i]); - - if (is_best(rate, now, best)) - best = now; - } - - if (!best) - best = DIV_ROUND_UP_ULL(*parent_rate, maxdiv); - - return best; -} - -static int ep93xx_div_set_rate(struct clk_hw *hw, unsigned long rate, - unsigned long parent_rate) -{ - struct clk_psc *psc = to_clk_psc(hw); - u32 val = __raw_readl(psc->reg) & ~psc->mask; - int i; - - for (i = 0; i < psc->num_div; i++) - if (rate == parent_rate / psc->div[i]) { - val |= i << psc->shift; - break; - } - - if (i == psc->num_div) - return -EINVAL; - - ep93xx_syscon_swlocked_write(val, psc->reg); - - return 0; -} - -static const struct clk_ops ep93xx_div_ops = { - .enable = ep93xx_clk_enable, - .disable = ep93xx_clk_disable, - .is_enabled = ep93xx_clk_is_enabled, - .recalc_rate = ep93xx_div_recalc_rate, - .round_rate = ep93xx_div_round_rate, - .set_rate = ep93xx_div_set_rate, -}; - -static struct clk_hw *clk_hw_register_div(const char *name, - const char *parent_name, - void __iomem *reg, - u8 enable_bit, - u8 shift, - u8 width, - char *clk_divisors, - u8 num_div) -{ - struct clk_init_data init; - struct clk_psc *psc; - struct clk *clk; - - psc = kzalloc(sizeof(*psc), GFP_KERNEL); - if (!psc) - return ERR_PTR(-ENOMEM); - - init.name = name; - init.ops = &ep93xx_div_ops; - init.flags = 0; - init.parent_names = (parent_name ? &parent_name : NULL); - init.num_parents = 1; - - psc->reg = reg; - psc->bit_idx = enable_bit; - psc->mask = GENMASK(shift + width - 1, shift); - psc->shift = shift; - psc->div = clk_divisors; - psc->num_div = num_div; - psc->lock = &clk_lock; - psc->hw.init = &init; - - clk = clk_register(NULL, &psc->hw); - if (IS_ERR(clk)) { - kfree(psc); - return ERR_CAST(clk); - } - return &psc->hw; -} - -struct ep93xx_gate { - unsigned int bit; - const char *dev_id; - const char *con_id; -}; - -static struct ep93xx_gate ep93xx_uarts[] = { - {EP93XX_SYSCON_DEVCFG_U1EN, "apb:uart1", NULL}, - {EP93XX_SYSCON_DEVCFG_U2EN, "apb:uart2", NULL}, - {EP93XX_SYSCON_DEVCFG_U3EN, "apb:uart3", NULL}, -}; - -static void __init ep93xx_uart_clock_init(void) -{ - unsigned int i; - struct clk_hw *hw; - u32 value; - unsigned int clk_uart_div; - - value = __raw_readl(EP93XX_SYSCON_PWRCNT); - if (value & EP93XX_SYSCON_PWRCNT_UARTBAUD) - clk_uart_div = 1; - else - clk_uart_div = 2; - - hw = clk_hw_register_fixed_factor(NULL, "uart", "xtali", 0, 1, clk_uart_div); - - /* parenting uart gate clocks to uart clock */ - for (i = 0; i < ARRAY_SIZE(ep93xx_uarts); i++) { - hw = ep93xx_clk_register_gate(ep93xx_uarts[i].dev_id, - "uart", - EP93XX_SYSCON_DEVCFG, - ep93xx_uarts[i].bit); - - clk_hw_register_clkdev(hw, NULL, ep93xx_uarts[i].dev_id); - } -} - -static struct ep93xx_gate ep93xx_dmas[] = { - {EP93XX_SYSCON_PWRCNT_DMA_M2P0, NULL, "m2p0"}, - {EP93XX_SYSCON_PWRCNT_DMA_M2P1, NULL, "m2p1"}, - {EP93XX_SYSCON_PWRCNT_DMA_M2P2, NULL, "m2p2"}, - {EP93XX_SYSCON_PWRCNT_DMA_M2P3, NULL, "m2p3"}, - {EP93XX_SYSCON_PWRCNT_DMA_M2P4, NULL, "m2p4"}, - {EP93XX_SYSCON_PWRCNT_DMA_M2P5, NULL, "m2p5"}, - {EP93XX_SYSCON_PWRCNT_DMA_M2P6, NULL, "m2p6"}, - {EP93XX_SYSCON_PWRCNT_DMA_M2P7, NULL, "m2p7"}, - {EP93XX_SYSCON_PWRCNT_DMA_M2P8, NULL, "m2p8"}, - {EP93XX_SYSCON_PWRCNT_DMA_M2P9, NULL, "m2p9"}, - {EP93XX_SYSCON_PWRCNT_DMA_M2M0, NULL, "m2m0"}, - {EP93XX_SYSCON_PWRCNT_DMA_M2M1, NULL, "m2m1"}, -}; - -static void __init ep93xx_dma_clock_init(void) -{ - unsigned int i; - struct clk_hw *hw; - int ret; - - for (i = 0; i < ARRAY_SIZE(ep93xx_dmas); i++) { - hw = clk_hw_register_gate(NULL, ep93xx_dmas[i].con_id, - "hclk", 0, - EP93XX_SYSCON_PWRCNT, - ep93xx_dmas[i].bit, - 0, - &clk_lock); - - ret = clk_hw_register_clkdev(hw, ep93xx_dmas[i].con_id, NULL); - if (ret) - pr_err("%s: failed to register lookup %s\n", - __func__, ep93xx_dmas[i].con_id); - } -} - -static int __init ep93xx_clock_init(void) -{ - u32 value; - struct clk_hw *hw; - unsigned long clk_pll1_rate; - unsigned long clk_f_rate; - unsigned long clk_h_rate; - unsigned long clk_p_rate; - unsigned long clk_pll2_rate; - unsigned int clk_f_div; - unsigned int clk_h_div; - unsigned int clk_p_div; - unsigned int clk_usb_div; - unsigned long clk_spi_div; - - hw = clk_hw_register_fixed_rate(NULL, "xtali", NULL, 0, EP93XX_EXT_CLK_RATE); - clk_hw_register_clkdev(hw, NULL, "xtali"); - - /* Determine the bootloader configured pll1 rate */ - value = __raw_readl(EP93XX_SYSCON_CLKSET1); - if (!(value & EP93XX_SYSCON_CLKSET1_NBYP1)) - clk_pll1_rate = EP93XX_EXT_CLK_RATE; - else - clk_pll1_rate = calc_pll_rate(EP93XX_EXT_CLK_RATE, value); - - hw = clk_hw_register_fixed_rate(NULL, "pll1", "xtali", 0, clk_pll1_rate); - clk_hw_register_clkdev(hw, NULL, "pll1"); - - /* Initialize the pll1 derived clocks */ - clk_f_div = fclk_divisors[(value >> 25) & 0x7]; - clk_h_div = hclk_divisors[(value >> 20) & 0x7]; - clk_p_div = pclk_divisors[(value >> 18) & 0x3]; - - hw = clk_hw_register_fixed_factor(NULL, "fclk", "pll1", 0, 1, clk_f_div); - clk_f_rate = clk_get_rate(hw->clk); - hw = clk_hw_register_fixed_factor(NULL, "hclk", "pll1", 0, 1, clk_h_div); - clk_h_rate = clk_get_rate(hw->clk); - hw = clk_hw_register_fixed_factor(NULL, "pclk", "hclk", 0, 1, clk_p_div); - clk_p_rate = clk_get_rate(hw->clk); - - clk_hw_register_clkdev(hw, "apb_pclk", NULL); - - ep93xx_dma_clock_init(); - - /* Determine the bootloader configured pll2 rate */ - value = __raw_readl(EP93XX_SYSCON_CLKSET2); - if (!(value & EP93XX_SYSCON_CLKSET2_NBYP2)) - clk_pll2_rate = EP93XX_EXT_CLK_RATE; - else if (value & EP93XX_SYSCON_CLKSET2_PLL2_EN) - clk_pll2_rate = calc_pll_rate(EP93XX_EXT_CLK_RATE, value); - else - clk_pll2_rate = 0; - - hw = clk_hw_register_fixed_rate(NULL, "pll2", "xtali", 0, clk_pll2_rate); - clk_hw_register_clkdev(hw, NULL, "pll2"); - - /* Initialize the pll2 derived clocks */ - /* - * These four bits set the divide ratio between the PLL2 - * output and the USB clock. - * 0000 - Divide by 1 - * 0001 - Divide by 2 - * 0010 - Divide by 3 - * 0011 - Divide by 4 - * 0100 - Divide by 5 - * 0101 - Divide by 6 - * 0110 - Divide by 7 - * 0111 - Divide by 8 - * 1000 - Divide by 9 - * 1001 - Divide by 10 - * 1010 - Divide by 11 - * 1011 - Divide by 12 - * 1100 - Divide by 13 - * 1101 - Divide by 14 - * 1110 - Divide by 15 - * 1111 - Divide by 1 - * On power-on-reset these bits are reset to 0000b. - */ - clk_usb_div = (((value >> 28) & 0xf) + 1); - hw = clk_hw_register_fixed_factor(NULL, "usb_clk", "pll2", 0, 1, clk_usb_div); - hw = clk_hw_register_gate(NULL, "ohci-platform", - "usb_clk", 0, - EP93XX_SYSCON_PWRCNT, - EP93XX_SYSCON_PWRCNT_USH_EN, - 0, - &clk_lock); - clk_hw_register_clkdev(hw, NULL, "ohci-platform"); - - /* - * EP93xx SSP clock rate was doubled in version E2. For more information - * see: - * http://www.cirrus.com/en/pubs/appNote/AN273REV4.pdf - */ - clk_spi_div = 1; - if (ep93xx_chip_revision() < EP93XX_CHIP_REV_E2) - clk_spi_div = 2; - hw = clk_hw_register_fixed_factor(NULL, "ep93xx-spi.0", "xtali", 0, 1, clk_spi_div); - clk_hw_register_clkdev(hw, NULL, "ep93xx-spi.0"); - - /* pwm clock */ - hw = clk_hw_register_fixed_factor(NULL, "pwm_clk", "xtali", 0, 1, 1); - clk_hw_register_clkdev(hw, "pwm_clk", NULL); - - pr_info("PLL1 running at %ld MHz, PLL2 at %ld MHz\n", - clk_pll1_rate / 1000000, clk_pll2_rate / 1000000); - pr_info("FCLK %ld MHz, HCLK %ld MHz, PCLK %ld MHz\n", - clk_f_rate / 1000000, clk_h_rate / 1000000, - clk_p_rate / 1000000); - - ep93xx_uart_clock_init(); - - /* touchscreen/adc clock */ - hw = clk_hw_register_div("ep93xx-adc", - "xtali", - EP93XX_SYSCON_KEYTCHCLKDIV, - EP93XX_SYSCON_KEYTCHCLKDIV_TSEN, - EP93XX_SYSCON_KEYTCHCLKDIV_ADIV, - 1, - adc_divisors, - ARRAY_SIZE(adc_divisors)); - - clk_hw_register_clkdev(hw, NULL, "ep93xx-adc"); - - /* keypad clock */ - hw = clk_hw_register_div("ep93xx-keypad", - "xtali", - EP93XX_SYSCON_KEYTCHCLKDIV, - EP93XX_SYSCON_KEYTCHCLKDIV_KEN, - EP93XX_SYSCON_KEYTCHCLKDIV_KDIV, - 1, - adc_divisors, - ARRAY_SIZE(adc_divisors)); - - clk_hw_register_clkdev(hw, NULL, "ep93xx-keypad"); - - /* On reset PDIV and VDIV is set to zero, while PDIV zero - * means clock disable, VDIV shouldn't be zero. - * So i set both dividers to minimum. - */ - /* ENA - Enable CLK divider. */ - /* PDIV - 00 - Disable clock */ - /* VDIV - at least 2 */ - /* Check and enable video clk registers */ - value = __raw_readl(EP93XX_SYSCON_VIDCLKDIV); - value |= (1 << EP93XX_SYSCON_CLKDIV_PDIV_SHIFT) | 2; - ep93xx_syscon_swlocked_write(value, EP93XX_SYSCON_VIDCLKDIV); - - /* check and enable i2s clk registers */ - value = __raw_readl(EP93XX_SYSCON_I2SCLKDIV); - value |= (1 << EP93XX_SYSCON_CLKDIV_PDIV_SHIFT) | 2; - ep93xx_syscon_swlocked_write(value, EP93XX_SYSCON_I2SCLKDIV); - - /* video clk */ - hw = clk_hw_register_ddiv("ep93xx-fb", - EP93XX_SYSCON_VIDCLKDIV, - EP93XX_SYSCON_CLKDIV_ENABLE); - - clk_hw_register_clkdev(hw, NULL, "ep93xx-fb"); - - /* i2s clk */ - hw = clk_hw_register_ddiv("mclk", - EP93XX_SYSCON_I2SCLKDIV, - EP93XX_SYSCON_CLKDIV_ENABLE); - - clk_hw_register_clkdev(hw, "mclk", "ep93xx-i2s"); - - /* i2s sclk */ -#define EP93XX_I2SCLKDIV_SDIV_SHIFT 16 -#define EP93XX_I2SCLKDIV_SDIV_WIDTH 1 - hw = clk_hw_register_div("sclk", - "mclk", - EP93XX_SYSCON_I2SCLKDIV, - EP93XX_SYSCON_I2SCLKDIV_SENA, - EP93XX_I2SCLKDIV_SDIV_SHIFT, - EP93XX_I2SCLKDIV_SDIV_WIDTH, - sclk_divisors, - ARRAY_SIZE(sclk_divisors)); - - clk_hw_register_clkdev(hw, "sclk", "ep93xx-i2s"); - - /* i2s lrclk */ -#define EP93XX_I2SCLKDIV_LRDIV32_SHIFT 17 -#define EP93XX_I2SCLKDIV_LRDIV32_WIDTH 3 - hw = clk_hw_register_div("lrclk", - "sclk", - EP93XX_SYSCON_I2SCLKDIV, - EP93XX_SYSCON_I2SCLKDIV_SENA, - EP93XX_I2SCLKDIV_LRDIV32_SHIFT, - EP93XX_I2SCLKDIV_LRDIV32_WIDTH, - lrclk_divisors, - ARRAY_SIZE(lrclk_divisors)); - - clk_hw_register_clkdev(hw, "lrclk", "ep93xx-i2s"); - - return 0; -} -postcore_initcall(ep93xx_clock_init); diff --git a/arch/arm/mach-ep93xx/core.c b/arch/arm/mach-ep93xx/core.c deleted file mode 100644 index 9c6154bb37b5..000000000000 --- a/arch/arm/mach-ep93xx/core.c +++ /dev/null @@ -1,955 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * arch/arm/mach-ep93xx/core.c - * Core routines for Cirrus EP93xx chips. - * - * Copyright (C) 2006 Lennert Buytenhek - * Copyright (C) 2007 Herbert Valerio Riedel - * - * Thanks go to Michael Burian and Ray Lehtiniemi for their key - * role in the ep93xx linux community. - */ - -#define pr_fmt(fmt) "ep93xx " KBUILD_MODNAME ": " fmt - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "hardware.h" -#include -#include -#include -#include - -#include "gpio-ep93xx.h" - -#include -#include - -#include "soc.h" -#include "irqs.h" - -/************************************************************************* - * Static I/O mappings that are needed for all EP93xx platforms - *************************************************************************/ -static struct map_desc ep93xx_io_desc[] __initdata = { - { - .virtual = EP93XX_AHB_VIRT_BASE, - .pfn = __phys_to_pfn(EP93XX_AHB_PHYS_BASE), - .length = EP93XX_AHB_SIZE, - .type = MT_DEVICE, - }, { - .virtual = EP93XX_APB_VIRT_BASE, - .pfn = __phys_to_pfn(EP93XX_APB_PHYS_BASE), - .length = EP93XX_APB_SIZE, - .type = MT_DEVICE, - }, -}; - -void __init ep93xx_map_io(void) -{ - iotable_init(ep93xx_io_desc, ARRAY_SIZE(ep93xx_io_desc)); -} - -/************************************************************************* - * EP93xx IRQ handling - *************************************************************************/ -void __init ep93xx_init_irq(void) -{ - vic_init(EP93XX_VIC1_BASE, IRQ_EP93XX_VIC0, EP93XX_VIC1_VALID_IRQ_MASK, 0); - vic_init(EP93XX_VIC2_BASE, IRQ_EP93XX_VIC1, EP93XX_VIC2_VALID_IRQ_MASK, 0); -} - - -/************************************************************************* - * EP93xx System Controller Software Locked register handling - *************************************************************************/ - -/* - * syscon_swlock prevents anything else from writing to the syscon - * block while a software locked register is being written. - */ -static DEFINE_SPINLOCK(syscon_swlock); - -void ep93xx_syscon_swlocked_write(unsigned int val, void __iomem *reg) -{ - unsigned long flags; - - spin_lock_irqsave(&syscon_swlock, flags); - - __raw_writel(0xaa, EP93XX_SYSCON_SWLOCK); - __raw_writel(val, reg); - - spin_unlock_irqrestore(&syscon_swlock, flags); -} - -void ep93xx_devcfg_set_clear(unsigned int set_bits, unsigned int clear_bits) -{ - unsigned long flags; - unsigned int val; - - spin_lock_irqsave(&syscon_swlock, flags); - - val = __raw_readl(EP93XX_SYSCON_DEVCFG); - val &= ~clear_bits; - val |= set_bits; - __raw_writel(0xaa, EP93XX_SYSCON_SWLOCK); - __raw_writel(val, EP93XX_SYSCON_DEVCFG); - - spin_unlock_irqrestore(&syscon_swlock, flags); -} - -/** - * ep93xx_chip_revision() - returns the EP93xx chip revision - * - * See "platform.h" for more information. - */ -unsigned int ep93xx_chip_revision(void) -{ - unsigned int v; - - v = __raw_readl(EP93XX_SYSCON_SYSCFG); - v &= EP93XX_SYSCON_SYSCFG_REV_MASK; - v >>= EP93XX_SYSCON_SYSCFG_REV_SHIFT; - return v; -} -EXPORT_SYMBOL_GPL(ep93xx_chip_revision); - -/************************************************************************* - * EP93xx GPIO - *************************************************************************/ -/* port A */ -static struct resource ep93xx_a_gpio_resources[] = { - DEFINE_RES_MEM_NAMED(EP93XX_GPIO_PHYS_BASE, 0x04, "data"), - DEFINE_RES_MEM_NAMED(EP93XX_GPIO_PHYS_BASE + 0x10, 0x04, "dir"), - DEFINE_RES_MEM_NAMED(EP93XX_GPIO_PHYS_BASE + 0x90, 0x1c, "intr"), - DEFINE_RES_IRQ(IRQ_EP93XX_GPIO_AB), -}; - -static struct platform_device ep93xx_a_gpio = { - .name = "gpio-ep93xx", - .id = 0, - .num_resources = ARRAY_SIZE(ep93xx_a_gpio_resources), - .resource = ep93xx_a_gpio_resources, -}; - -/* port B */ -static struct resource ep93xx_b_gpio_resources[] = { - DEFINE_RES_MEM_NAMED(EP93XX_GPIO_PHYS_BASE + 0x04, 0x04, "data"), - DEFINE_RES_MEM_NAMED(EP93XX_GPIO_PHYS_BASE + 0x14, 0x04, "dir"), - DEFINE_RES_MEM_NAMED(EP93XX_GPIO_PHYS_BASE + 0xac, 0x1c, "intr"), - DEFINE_RES_IRQ(IRQ_EP93XX_GPIO_AB), -}; - -static struct platform_device ep93xx_b_gpio = { - .name = "gpio-ep93xx", - .id = 1, - .num_resources = ARRAY_SIZE(ep93xx_b_gpio_resources), - .resource = ep93xx_b_gpio_resources, -}; - -/* port C */ -static struct resource ep93xx_c_gpio_resources[] = { - DEFINE_RES_MEM_NAMED(EP93XX_GPIO_PHYS_BASE + 0x08, 0x04, "data"), - DEFINE_RES_MEM_NAMED(EP93XX_GPIO_PHYS_BASE + 0x18, 0x04, "dir"), -}; - -static struct platform_device ep93xx_c_gpio = { - .name = "gpio-ep93xx", - .id = 2, - .num_resources = ARRAY_SIZE(ep93xx_c_gpio_resources), - .resource = ep93xx_c_gpio_resources, -}; - -/* port D */ -static struct resource ep93xx_d_gpio_resources[] = { - DEFINE_RES_MEM_NAMED(EP93XX_GPIO_PHYS_BASE + 0x0c, 0x04, "data"), - DEFINE_RES_MEM_NAMED(EP93XX_GPIO_PHYS_BASE + 0x1c, 0x04, "dir"), -}; - -static struct platform_device ep93xx_d_gpio = { - .name = "gpio-ep93xx", - .id = 3, - .num_resources = ARRAY_SIZE(ep93xx_d_gpio_resources), - .resource = ep93xx_d_gpio_resources, -}; - -/* port E */ -static struct resource ep93xx_e_gpio_resources[] = { - DEFINE_RES_MEM_NAMED(EP93XX_GPIO_PHYS_BASE + 0x20, 0x04, "data"), - DEFINE_RES_MEM_NAMED(EP93XX_GPIO_PHYS_BASE + 0x24, 0x04, "dir"), -}; - -static struct platform_device ep93xx_e_gpio = { - .name = "gpio-ep93xx", - .id = 4, - .num_resources = ARRAY_SIZE(ep93xx_e_gpio_resources), - .resource = ep93xx_e_gpio_resources, -}; - -/* port F */ -static struct resource ep93xx_f_gpio_resources[] = { - DEFINE_RES_MEM_NAMED(EP93XX_GPIO_PHYS_BASE + 0x30, 0x04, "data"), - DEFINE_RES_MEM_NAMED(EP93XX_GPIO_PHYS_BASE + 0x34, 0x04, "dir"), - DEFINE_RES_MEM_NAMED(EP93XX_GPIO_PHYS_BASE + 0x4c, 0x1c, "intr"), - DEFINE_RES_IRQ(IRQ_EP93XX_GPIO0MUX), - DEFINE_RES_IRQ(IRQ_EP93XX_GPIO1MUX), - DEFINE_RES_IRQ(IRQ_EP93XX_GPIO2MUX), - DEFINE_RES_IRQ(IRQ_EP93XX_GPIO3MUX), - DEFINE_RES_IRQ(IRQ_EP93XX_GPIO4MUX), - DEFINE_RES_IRQ(IRQ_EP93XX_GPIO5MUX), - DEFINE_RES_IRQ(IRQ_EP93XX_GPIO6MUX), - DEFINE_RES_IRQ(IRQ_EP93XX_GPIO7MUX), -}; - -static struct platform_device ep93xx_f_gpio = { - .name = "gpio-ep93xx", - .id = 5, - .num_resources = ARRAY_SIZE(ep93xx_f_gpio_resources), - .resource = ep93xx_f_gpio_resources, -}; - -/* port G */ -static struct resource ep93xx_g_gpio_resources[] = { - DEFINE_RES_MEM_NAMED(EP93XX_GPIO_PHYS_BASE + 0x38, 0x04, "data"), - DEFINE_RES_MEM_NAMED(EP93XX_GPIO_PHYS_BASE + 0x3c, 0x04, "dir"), -}; - -static struct platform_device ep93xx_g_gpio = { - .name = "gpio-ep93xx", - .id = 6, - .num_resources = ARRAY_SIZE(ep93xx_g_gpio_resources), - .resource = ep93xx_g_gpio_resources, -}; - -static struct platform_device *ep93xx_gpio_device[] __initdata = { - &ep93xx_a_gpio, - &ep93xx_b_gpio, - &ep93xx_c_gpio, - &ep93xx_d_gpio, - &ep93xx_e_gpio, - &ep93xx_f_gpio, - &ep93xx_g_gpio, -}; - -/************************************************************************* - * EP93xx peripheral handling - *************************************************************************/ -#define EP93XX_UART_MCR_OFFSET (0x0100) - -static void ep93xx_uart_set_mctrl(struct amba_device *dev, - void __iomem *base, unsigned int mctrl) -{ - unsigned int mcr; - - mcr = 0; - if (mctrl & TIOCM_RTS) - mcr |= 2; - if (mctrl & TIOCM_DTR) - mcr |= 1; - - __raw_writel(mcr, base + EP93XX_UART_MCR_OFFSET); -} - -static struct amba_pl010_data ep93xx_uart_data = { - .set_mctrl = ep93xx_uart_set_mctrl, -}; - -static AMBA_APB_DEVICE(uart1, "apb:uart1", 0x00041010, EP93XX_UART1_PHYS_BASE, - { IRQ_EP93XX_UART1 }, &ep93xx_uart_data); - -static AMBA_APB_DEVICE(uart2, "apb:uart2", 0x00041010, EP93XX_UART2_PHYS_BASE, - { IRQ_EP93XX_UART2 }, NULL); - -static AMBA_APB_DEVICE(uart3, "apb:uart3", 0x00041010, EP93XX_UART3_PHYS_BASE, - { IRQ_EP93XX_UART3 }, &ep93xx_uart_data); - -static struct resource ep93xx_rtc_resource[] = { - DEFINE_RES_MEM(EP93XX_RTC_PHYS_BASE, 0x10c), -}; - -static struct platform_device ep93xx_rtc_device = { - .name = "ep93xx-rtc", - .id = -1, - .num_resources = ARRAY_SIZE(ep93xx_rtc_resource), - .resource = ep93xx_rtc_resource, -}; - -/************************************************************************* - * EP93xx OHCI USB Host - *************************************************************************/ - -static struct clk *ep93xx_ohci_host_clock; - -static int ep93xx_ohci_power_on(struct platform_device *pdev) -{ - if (!ep93xx_ohci_host_clock) { - ep93xx_ohci_host_clock = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(ep93xx_ohci_host_clock)) - return PTR_ERR(ep93xx_ohci_host_clock); - } - - return clk_prepare_enable(ep93xx_ohci_host_clock); -} - -static void ep93xx_ohci_power_off(struct platform_device *pdev) -{ - clk_disable(ep93xx_ohci_host_clock); -} - -static struct usb_ohci_pdata ep93xx_ohci_pdata = { - .power_on = ep93xx_ohci_power_on, - .power_off = ep93xx_ohci_power_off, - .power_suspend = ep93xx_ohci_power_off, -}; - -static struct resource ep93xx_ohci_resources[] = { - DEFINE_RES_MEM(EP93XX_USB_PHYS_BASE, 0x1000), - DEFINE_RES_IRQ(IRQ_EP93XX_USB), -}; - -static u64 ep93xx_ohci_dma_mask = DMA_BIT_MASK(32); - -static struct platform_device ep93xx_ohci_device = { - .name = "ohci-platform", - .id = -1, - .num_resources = ARRAY_SIZE(ep93xx_ohci_resources), - .resource = ep93xx_ohci_resources, - .dev = { - .dma_mask = &ep93xx_ohci_dma_mask, - .coherent_dma_mask = DMA_BIT_MASK(32), - .platform_data = &ep93xx_ohci_pdata, - }, -}; - -/************************************************************************* - * EP93xx physmap'ed flash - *************************************************************************/ -static struct physmap_flash_data ep93xx_flash_data; - -static struct resource ep93xx_flash_resource = { - .flags = IORESOURCE_MEM, -}; - -static struct platform_device ep93xx_flash = { - .name = "physmap-flash", - .id = 0, - .dev = { - .platform_data = &ep93xx_flash_data, - }, - .num_resources = 1, - .resource = &ep93xx_flash_resource, -}; - -/** - * ep93xx_register_flash() - Register the external flash device. - * @width: bank width in octets - * @start: resource start address - * @size: resource size - */ -void __init ep93xx_register_flash(unsigned int width, - resource_size_t start, resource_size_t size) -{ - ep93xx_flash_data.width = width; - - ep93xx_flash_resource.start = start; - ep93xx_flash_resource.end = start + size - 1; - - platform_device_register(&ep93xx_flash); -} - - -/************************************************************************* - * EP93xx ethernet peripheral handling - *************************************************************************/ -static struct ep93xx_eth_data ep93xx_eth_data; - -static struct resource ep93xx_eth_resource[] = { - DEFINE_RES_MEM(EP93XX_ETHERNET_PHYS_BASE, 0x10000), - DEFINE_RES_IRQ(IRQ_EP93XX_ETHERNET), -}; - -static u64 ep93xx_eth_dma_mask = DMA_BIT_MASK(32); - -static struct platform_device ep93xx_eth_device = { - .name = "ep93xx-eth", - .id = -1, - .dev = { - .platform_data = &ep93xx_eth_data, - .coherent_dma_mask = DMA_BIT_MASK(32), - .dma_mask = &ep93xx_eth_dma_mask, - }, - .num_resources = ARRAY_SIZE(ep93xx_eth_resource), - .resource = ep93xx_eth_resource, -}; - -/** - * ep93xx_register_eth - Register the built-in ethernet platform device. - * @data: platform specific ethernet configuration (__initdata) - * @copy_addr: flag indicating that the MAC address should be copied - * from the IndAd registers (as programmed by the bootloader) - */ -void __init ep93xx_register_eth(struct ep93xx_eth_data *data, int copy_addr) -{ - if (copy_addr) - memcpy_fromio(data->dev_addr, EP93XX_ETHERNET_BASE + 0x50, 6); - - ep93xx_eth_data = *data; - platform_device_register(&ep93xx_eth_device); -} - - -/************************************************************************* - * EP93xx i2c peripheral handling - *************************************************************************/ - -/* All EP93xx devices use the same two GPIO pins for I2C bit-banging */ -static struct gpiod_lookup_table ep93xx_i2c_gpiod_table = { - .dev_id = "i2c-gpio.0", - .table = { - /* Use local offsets on gpiochip/port "G" */ - GPIO_LOOKUP_IDX("gpio-ep93xx.6", 1, NULL, 0, - GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN), - GPIO_LOOKUP_IDX("gpio-ep93xx.6", 0, NULL, 1, - GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN), - { } - }, -}; - -static struct platform_device ep93xx_i2c_device = { - .name = "i2c-gpio", - .id = 0, - .dev = { - .platform_data = NULL, - }, -}; - -/** - * ep93xx_register_i2c - Register the i2c platform device. - * @devices: platform specific i2c bus device information (__initdata) - * @num: the number of devices on the i2c bus - */ -void __init ep93xx_register_i2c(struct i2c_board_info *devices, int num) -{ - /* - * FIXME: this just sets the two pins as non-opendrain, as no - * platforms tries to do that anyway. Flag the applicable lines - * as open drain in the GPIO_LOOKUP above and the driver or - * gpiolib will handle open drain/open drain emulation as need - * be. Right now i2c-gpio emulates open drain which is not - * optimal. - */ - __raw_writel((0 << 1) | (0 << 0), - EP93XX_GPIO_EEDRIVE); - - i2c_register_board_info(0, devices, num); - gpiod_add_lookup_table(&ep93xx_i2c_gpiod_table); - platform_device_register(&ep93xx_i2c_device); -} - -/************************************************************************* - * EP93xx SPI peripheral handling - *************************************************************************/ -static struct ep93xx_spi_info ep93xx_spi_master_data; - -static struct resource ep93xx_spi_resources[] = { - DEFINE_RES_MEM(EP93XX_SPI_PHYS_BASE, 0x18), - DEFINE_RES_IRQ(IRQ_EP93XX_SSP), -}; - -static u64 ep93xx_spi_dma_mask = DMA_BIT_MASK(32); - -static struct platform_device ep93xx_spi_device = { - .name = "ep93xx-spi", - .id = 0, - .dev = { - .platform_data = &ep93xx_spi_master_data, - .coherent_dma_mask = DMA_BIT_MASK(32), - .dma_mask = &ep93xx_spi_dma_mask, - }, - .num_resources = ARRAY_SIZE(ep93xx_spi_resources), - .resource = ep93xx_spi_resources, -}; - -/** - * ep93xx_register_spi() - registers spi platform device - * @info: ep93xx board specific spi master info (__initdata) - * @devices: SPI devices to register (__initdata) - * @num: number of SPI devices to register - * - * This function registers platform device for the EP93xx SPI controller and - * also makes sure that SPI pins are muxed so that I2S is not using those pins. - */ -void __init ep93xx_register_spi(struct ep93xx_spi_info *info, - struct spi_board_info *devices, int num) -{ - /* - * When SPI is used, we need to make sure that I2S is muxed off from - * SPI pins. - */ - ep93xx_devcfg_clear_bits(EP93XX_SYSCON_DEVCFG_I2SONSSP); - - ep93xx_spi_master_data = *info; - spi_register_board_info(devices, num); - platform_device_register(&ep93xx_spi_device); -} - -/************************************************************************* - * EP93xx LEDs - *************************************************************************/ -static const struct gpio_led ep93xx_led_pins[] __initconst = { - { - .name = "platform:grled", - }, { - .name = "platform:rdled", - }, -}; - -static const struct gpio_led_platform_data ep93xx_led_data __initconst = { - .num_leds = ARRAY_SIZE(ep93xx_led_pins), - .leds = ep93xx_led_pins, -}; - -static struct gpiod_lookup_table ep93xx_leds_gpio_table = { - .dev_id = "leds-gpio", - .table = { - /* Use local offsets on gpiochip/port "E" */ - GPIO_LOOKUP_IDX("gpio-ep93xx.4", 0, NULL, 0, GPIO_ACTIVE_HIGH), - GPIO_LOOKUP_IDX("gpio-ep93xx.4", 1, NULL, 1, GPIO_ACTIVE_HIGH), - { } - }, -}; - -/************************************************************************* - * EP93xx pwm peripheral handling - *************************************************************************/ -static struct resource ep93xx_pwm0_resource[] = { - DEFINE_RES_MEM(EP93XX_PWM_PHYS_BASE, 0x10), -}; - -static struct platform_device ep93xx_pwm0_device = { - .name = "ep93xx-pwm", - .id = 0, - .num_resources = ARRAY_SIZE(ep93xx_pwm0_resource), - .resource = ep93xx_pwm0_resource, -}; - -static struct resource ep93xx_pwm1_resource[] = { - DEFINE_RES_MEM(EP93XX_PWM_PHYS_BASE + 0x20, 0x10), -}; - -static struct platform_device ep93xx_pwm1_device = { - .name = "ep93xx-pwm", - .id = 1, - .num_resources = ARRAY_SIZE(ep93xx_pwm1_resource), - .resource = ep93xx_pwm1_resource, -}; - -void __init ep93xx_register_pwm(int pwm0, int pwm1) -{ - if (pwm0) - platform_device_register(&ep93xx_pwm0_device); - - /* NOTE: EP9307 does not have PWMOUT1 (pin EGPIO14) */ - if (pwm1) - platform_device_register(&ep93xx_pwm1_device); -} - -/************************************************************************* - * EP93xx video peripheral handling - *************************************************************************/ -static struct ep93xxfb_mach_info ep93xxfb_data; - -static struct resource ep93xx_fb_resource[] = { - DEFINE_RES_MEM(EP93XX_RASTER_PHYS_BASE, 0x800), -}; - -static struct platform_device ep93xx_fb_device = { - .name = "ep93xx-fb", - .id = -1, - .dev = { - .platform_data = &ep93xxfb_data, - .coherent_dma_mask = DMA_BIT_MASK(32), - .dma_mask = &ep93xx_fb_device.dev.coherent_dma_mask, - }, - .num_resources = ARRAY_SIZE(ep93xx_fb_resource), - .resource = ep93xx_fb_resource, -}; - -/* The backlight use a single register in the framebuffer's register space */ -#define EP93XX_RASTER_REG_BRIGHTNESS 0x20 - -static struct resource ep93xx_bl_resources[] = { - DEFINE_RES_MEM(EP93XX_RASTER_PHYS_BASE + - EP93XX_RASTER_REG_BRIGHTNESS, 0x04), -}; - -static struct platform_device ep93xx_bl_device = { - .name = "ep93xx-bl", - .id = -1, - .num_resources = ARRAY_SIZE(ep93xx_bl_resources), - .resource = ep93xx_bl_resources, -}; - -/** - * ep93xx_register_fb - Register the framebuffer platform device. - * @data: platform specific framebuffer configuration (__initdata) - */ -void __init ep93xx_register_fb(struct ep93xxfb_mach_info *data) -{ - ep93xxfb_data = *data; - platform_device_register(&ep93xx_fb_device); - platform_device_register(&ep93xx_bl_device); -} - - -/************************************************************************* - * EP93xx matrix keypad peripheral handling - *************************************************************************/ -static struct ep93xx_keypad_platform_data ep93xx_keypad_data; - -static struct resource ep93xx_keypad_resource[] = { - DEFINE_RES_MEM(EP93XX_KEY_MATRIX_PHYS_BASE, 0x0c), - DEFINE_RES_IRQ(IRQ_EP93XX_KEY), -}; - -static struct platform_device ep93xx_keypad_device = { - .name = "ep93xx-keypad", - .id = -1, - .dev = { - .platform_data = &ep93xx_keypad_data, - }, - .num_resources = ARRAY_SIZE(ep93xx_keypad_resource), - .resource = ep93xx_keypad_resource, -}; - -/** - * ep93xx_register_keypad - Register the keypad platform device. - * @data: platform specific keypad configuration (__initdata) - */ -void __init ep93xx_register_keypad(struct ep93xx_keypad_platform_data *data) -{ - ep93xx_keypad_data = *data; - platform_device_register(&ep93xx_keypad_device); -} - -/************************************************************************* - * EP93xx I2S audio peripheral handling - *************************************************************************/ -static struct resource ep93xx_i2s_resource[] = { - DEFINE_RES_MEM(EP93XX_I2S_PHYS_BASE, 0x100), - DEFINE_RES_IRQ(IRQ_EP93XX_SAI), -}; - -static struct platform_device ep93xx_i2s_device = { - .name = "ep93xx-i2s", - .id = -1, - .num_resources = ARRAY_SIZE(ep93xx_i2s_resource), - .resource = ep93xx_i2s_resource, -}; - -static struct platform_device ep93xx_pcm_device = { - .name = "ep93xx-pcm-audio", - .id = -1, -}; - -void __init ep93xx_register_i2s(void) -{ - platform_device_register(&ep93xx_i2s_device); - platform_device_register(&ep93xx_pcm_device); -} - -#define EP93XX_SYSCON_DEVCFG_I2S_MASK (EP93XX_SYSCON_DEVCFG_I2SONSSP | \ - EP93XX_SYSCON_DEVCFG_I2SONAC97) - -#define EP93XX_I2SCLKDIV_MASK (EP93XX_SYSCON_I2SCLKDIV_ORIDE | \ - EP93XX_SYSCON_I2SCLKDIV_SPOL) - -int ep93xx_i2s_acquire(void) -{ - unsigned val; - - ep93xx_devcfg_set_clear(EP93XX_SYSCON_DEVCFG_I2SONAC97, - EP93XX_SYSCON_DEVCFG_I2S_MASK); - - /* - * This is potentially racy with the clock api for i2s_mclk, sclk and - * lrclk. Since the i2s driver is the only user of those clocks we - * rely on it to prevent parallel use of this function and the - * clock api for the i2s clocks. - */ - val = __raw_readl(EP93XX_SYSCON_I2SCLKDIV); - val &= ~EP93XX_I2SCLKDIV_MASK; - val |= EP93XX_SYSCON_I2SCLKDIV_ORIDE | EP93XX_SYSCON_I2SCLKDIV_SPOL; - ep93xx_syscon_swlocked_write(val, EP93XX_SYSCON_I2SCLKDIV); - - return 0; -} -EXPORT_SYMBOL(ep93xx_i2s_acquire); - -void ep93xx_i2s_release(void) -{ - ep93xx_devcfg_clear_bits(EP93XX_SYSCON_DEVCFG_I2S_MASK); -} -EXPORT_SYMBOL(ep93xx_i2s_release); - -/************************************************************************* - * EP93xx AC97 audio peripheral handling - *************************************************************************/ -static struct resource ep93xx_ac97_resources[] = { - DEFINE_RES_MEM(EP93XX_AAC_PHYS_BASE, 0xac), - DEFINE_RES_IRQ(IRQ_EP93XX_AACINTR), -}; - -static struct platform_device ep93xx_ac97_device = { - .name = "ep93xx-ac97", - .id = -1, - .num_resources = ARRAY_SIZE(ep93xx_ac97_resources), - .resource = ep93xx_ac97_resources, -}; - -void __init ep93xx_register_ac97(void) -{ - /* - * Make sure that the AC97 pins are not used by I2S. - */ - ep93xx_devcfg_clear_bits(EP93XX_SYSCON_DEVCFG_I2SONAC97); - - platform_device_register(&ep93xx_ac97_device); - platform_device_register(&ep93xx_pcm_device); -} - -/************************************************************************* - * EP93xx Watchdog - *************************************************************************/ -static struct resource ep93xx_wdt_resources[] = { - DEFINE_RES_MEM(EP93XX_WATCHDOG_PHYS_BASE, 0x08), -}; - -static struct platform_device ep93xx_wdt_device = { - .name = "ep93xx-wdt", - .id = -1, - .num_resources = ARRAY_SIZE(ep93xx_wdt_resources), - .resource = ep93xx_wdt_resources, -}; - -/************************************************************************* - * EP93xx IDE - *************************************************************************/ -static struct resource ep93xx_ide_resources[] = { - DEFINE_RES_MEM(EP93XX_IDE_PHYS_BASE, 0x38), - DEFINE_RES_IRQ(IRQ_EP93XX_EXT3), -}; - -static struct platform_device ep93xx_ide_device = { - .name = "ep93xx-ide", - .id = -1, - .dev = { - .dma_mask = &ep93xx_ide_device.dev.coherent_dma_mask, - .coherent_dma_mask = DMA_BIT_MASK(32), - }, - .num_resources = ARRAY_SIZE(ep93xx_ide_resources), - .resource = ep93xx_ide_resources, -}; - -void __init ep93xx_register_ide(void) -{ - platform_device_register(&ep93xx_ide_device); -} - -/************************************************************************* - * EP93xx ADC - *************************************************************************/ -static struct resource ep93xx_adc_resources[] = { - DEFINE_RES_MEM(EP93XX_ADC_PHYS_BASE, 0x28), - DEFINE_RES_IRQ(IRQ_EP93XX_TOUCH), -}; - -static struct platform_device ep93xx_adc_device = { - .name = "ep93xx-adc", - .id = -1, - .num_resources = ARRAY_SIZE(ep93xx_adc_resources), - .resource = ep93xx_adc_resources, -}; - -void __init ep93xx_register_adc(void) -{ - /* Power up ADC, deactivate Touch Screen Controller */ - ep93xx_devcfg_set_clear(EP93XX_SYSCON_DEVCFG_TIN, - EP93XX_SYSCON_DEVCFG_ADCPD); - - platform_device_register(&ep93xx_adc_device); -} - -/************************************************************************* - * EP93xx Security peripheral - *************************************************************************/ - -/* - * The Maverick Key is 256 bits of micro fuses blown at the factory during - * manufacturing to uniquely identify a part. - * - * See: http://arm.cirrus.com/forum/viewtopic.php?t=486&highlight=maverick+key - */ -#define EP93XX_SECURITY_REG(x) (EP93XX_SECURITY_BASE + (x)) -#define EP93XX_SECURITY_SECFLG EP93XX_SECURITY_REG(0x2400) -#define EP93XX_SECURITY_FUSEFLG EP93XX_SECURITY_REG(0x2410) -#define EP93XX_SECURITY_UNIQID EP93XX_SECURITY_REG(0x2440) -#define EP93XX_SECURITY_UNIQCHK EP93XX_SECURITY_REG(0x2450) -#define EP93XX_SECURITY_UNIQVAL EP93XX_SECURITY_REG(0x2460) -#define EP93XX_SECURITY_SECID1 EP93XX_SECURITY_REG(0x2500) -#define EP93XX_SECURITY_SECID2 EP93XX_SECURITY_REG(0x2504) -#define EP93XX_SECURITY_SECCHK1 EP93XX_SECURITY_REG(0x2520) -#define EP93XX_SECURITY_SECCHK2 EP93XX_SECURITY_REG(0x2524) -#define EP93XX_SECURITY_UNIQID2 EP93XX_SECURITY_REG(0x2700) -#define EP93XX_SECURITY_UNIQID3 EP93XX_SECURITY_REG(0x2704) -#define EP93XX_SECURITY_UNIQID4 EP93XX_SECURITY_REG(0x2708) -#define EP93XX_SECURITY_UNIQID5 EP93XX_SECURITY_REG(0x270c) - -static char ep93xx_soc_id[33]; - -static const char __init *ep93xx_get_soc_id(void) -{ - unsigned int id, id2, id3, id4, id5; - - if (__raw_readl(EP93XX_SECURITY_UNIQVAL) != 1) - return "bad Hamming code"; - - id = __raw_readl(EP93XX_SECURITY_UNIQID); - id2 = __raw_readl(EP93XX_SECURITY_UNIQID2); - id3 = __raw_readl(EP93XX_SECURITY_UNIQID3); - id4 = __raw_readl(EP93XX_SECURITY_UNIQID4); - id5 = __raw_readl(EP93XX_SECURITY_UNIQID5); - - if (id != id2) - return "invalid"; - - /* Toss the unique ID into the entropy pool */ - add_device_randomness(&id2, 4); - add_device_randomness(&id3, 4); - add_device_randomness(&id4, 4); - add_device_randomness(&id5, 4); - - snprintf(ep93xx_soc_id, sizeof(ep93xx_soc_id), - "%08x%08x%08x%08x", id2, id3, id4, id5); - - return ep93xx_soc_id; -} - -static const char __init *ep93xx_get_soc_rev(void) -{ - int rev = ep93xx_chip_revision(); - - switch (rev) { - case EP93XX_CHIP_REV_D0: - return "D0"; - case EP93XX_CHIP_REV_D1: - return "D1"; - case EP93XX_CHIP_REV_E0: - return "E0"; - case EP93XX_CHIP_REV_E1: - return "E1"; - case EP93XX_CHIP_REV_E2: - return "E2"; - default: - return "unknown"; - } -} - -static const char __init *ep93xx_get_machine_name(void) -{ - return kasprintf(GFP_KERNEL,"%s", machine_desc->name); -} - -static struct device __init *ep93xx_init_soc(void) -{ - struct soc_device_attribute *soc_dev_attr; - struct soc_device *soc_dev; - - soc_dev_attr = kzalloc(sizeof(*soc_dev_attr), GFP_KERNEL); - if (!soc_dev_attr) - return NULL; - - soc_dev_attr->machine = ep93xx_get_machine_name(); - soc_dev_attr->family = "Cirrus Logic EP93xx"; - soc_dev_attr->revision = ep93xx_get_soc_rev(); - soc_dev_attr->soc_id = ep93xx_get_soc_id(); - - soc_dev = soc_device_register(soc_dev_attr); - if (IS_ERR(soc_dev)) { - kfree(soc_dev_attr->machine); - kfree(soc_dev_attr); - return NULL; - } - - return soc_device_to_device(soc_dev); -} - -struct device __init *ep93xx_init_devices(void) -{ - struct device *parent; - unsigned int i; - - /* Disallow access to MaverickCrunch initially */ - ep93xx_devcfg_clear_bits(EP93XX_SYSCON_DEVCFG_CPENA); - - /* Default all ports to GPIO */ - ep93xx_devcfg_set_bits(EP93XX_SYSCON_DEVCFG_KEYS | - EP93XX_SYSCON_DEVCFG_GONK | - EP93XX_SYSCON_DEVCFG_EONIDE | - EP93XX_SYSCON_DEVCFG_GONIDE | - EP93XX_SYSCON_DEVCFG_HONIDE); - - parent = ep93xx_init_soc(); - - /* Get the GPIO working early, other devices need it */ - for (i = 0; i < ARRAY_SIZE(ep93xx_gpio_device); i++) - platform_device_register(ep93xx_gpio_device[i]); - - amba_device_register(&uart1_device, &iomem_resource); - amba_device_register(&uart2_device, &iomem_resource); - amba_device_register(&uart3_device, &iomem_resource); - - platform_device_register(&ep93xx_rtc_device); - platform_device_register(&ep93xx_ohci_device); - platform_device_register(&ep93xx_wdt_device); - - gpiod_add_lookup_table(&ep93xx_leds_gpio_table); - gpio_led_register_device(-1, &ep93xx_led_data); - - return parent; -} - -void ep93xx_restart(enum reboot_mode mode, const char *cmd) -{ - /* - * Set then clear the SWRST bit to initiate a software reset - */ - ep93xx_devcfg_set_bits(EP93XX_SYSCON_DEVCFG_SWRST); - ep93xx_devcfg_clear_bits(EP93XX_SYSCON_DEVCFG_SWRST); - - while (1) - ; -} diff --git a/arch/arm/mach-ep93xx/dma.c b/arch/arm/mach-ep93xx/dma.c deleted file mode 100644 index 74515acab8ef..000000000000 --- a/arch/arm/mach-ep93xx/dma.c +++ /dev/null @@ -1,114 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * arch/arm/mach-ep93xx/dma.c - * - * Platform support code for the EP93xx dmaengine driver. - * - * Copyright (C) 2011 Mika Westerberg - * - * This work is based on the original dma-m2p implementation with - * following copyrights: - * - * Copyright (C) 2006 Lennert Buytenhek - * Copyright (C) 2006 Applied Data Systems - * Copyright (C) 2009 Ryan Mallon - */ - -#include -#include -#include -#include -#include -#include - -#include -#include "hardware.h" - -#include "soc.h" - -#define DMA_CHANNEL(_name, _base, _irq) \ - { .name = (_name), .base = (_base), .irq = (_irq) } - -/* - * DMA M2P channels. - * - * On the EP93xx chip the following peripherals my be allocated to the 10 - * Memory to Internal Peripheral (M2P) channels (5 transmit + 5 receive). - * - * I2S contains 3 Tx and 3 Rx DMA Channels - * AAC contains 3 Tx and 3 Rx DMA Channels - * UART1 contains 1 Tx and 1 Rx DMA Channels - * UART2 contains 1 Tx and 1 Rx DMA Channels - * UART3 contains 1 Tx and 1 Rx DMA Channels - * IrDA contains 1 Tx and 1 Rx DMA Channels - * - * Registers are mapped statically in ep93xx_map_io(). - */ -static struct ep93xx_dma_chan_data ep93xx_dma_m2p_channels[] = { - DMA_CHANNEL("m2p0", EP93XX_DMA_BASE + 0x0000, IRQ_EP93XX_DMAM2P0), - DMA_CHANNEL("m2p1", EP93XX_DMA_BASE + 0x0040, IRQ_EP93XX_DMAM2P1), - DMA_CHANNEL("m2p2", EP93XX_DMA_BASE + 0x0080, IRQ_EP93XX_DMAM2P2), - DMA_CHANNEL("m2p3", EP93XX_DMA_BASE + 0x00c0, IRQ_EP93XX_DMAM2P3), - DMA_CHANNEL("m2p4", EP93XX_DMA_BASE + 0x0240, IRQ_EP93XX_DMAM2P4), - DMA_CHANNEL("m2p5", EP93XX_DMA_BASE + 0x0200, IRQ_EP93XX_DMAM2P5), - DMA_CHANNEL("m2p6", EP93XX_DMA_BASE + 0x02c0, IRQ_EP93XX_DMAM2P6), - DMA_CHANNEL("m2p7", EP93XX_DMA_BASE + 0x0280, IRQ_EP93XX_DMAM2P7), - DMA_CHANNEL("m2p8", EP93XX_DMA_BASE + 0x0340, IRQ_EP93XX_DMAM2P8), - DMA_CHANNEL("m2p9", EP93XX_DMA_BASE + 0x0300, IRQ_EP93XX_DMAM2P9), -}; - -static struct ep93xx_dma_platform_data ep93xx_dma_m2p_data = { - .channels = ep93xx_dma_m2p_channels, - .num_channels = ARRAY_SIZE(ep93xx_dma_m2p_channels), -}; - -static u64 ep93xx_dma_m2p_mask = DMA_BIT_MASK(32); - -static struct platform_device ep93xx_dma_m2p_device = { - .name = "ep93xx-dma-m2p", - .id = -1, - .dev = { - .platform_data = &ep93xx_dma_m2p_data, - .dma_mask = &ep93xx_dma_m2p_mask, - .coherent_dma_mask = DMA_BIT_MASK(32), - }, -}; - -/* - * DMA M2M channels. - * - * There are 2 M2M channels which support memcpy/memset and in addition simple - * hardware requests from/to SSP and IDE. We do not implement an external - * hardware requests. - * - * Registers are mapped statically in ep93xx_map_io(). - */ -static struct ep93xx_dma_chan_data ep93xx_dma_m2m_channels[] = { - DMA_CHANNEL("m2m0", EP93XX_DMA_BASE + 0x0100, IRQ_EP93XX_DMAM2M0), - DMA_CHANNEL("m2m1", EP93XX_DMA_BASE + 0x0140, IRQ_EP93XX_DMAM2M1), -}; - -static struct ep93xx_dma_platform_data ep93xx_dma_m2m_data = { - .channels = ep93xx_dma_m2m_channels, - .num_channels = ARRAY_SIZE(ep93xx_dma_m2m_channels), -}; - -static u64 ep93xx_dma_m2m_mask = DMA_BIT_MASK(32); - -static struct platform_device ep93xx_dma_m2m_device = { - .name = "ep93xx-dma-m2m", - .id = -1, - .dev = { - .platform_data = &ep93xx_dma_m2m_data, - .dma_mask = &ep93xx_dma_m2m_mask, - .coherent_dma_mask = DMA_BIT_MASK(32), - }, -}; - -static int __init ep93xx_dma_init(void) -{ - platform_device_register(&ep93xx_dma_m2p_device); - platform_device_register(&ep93xx_dma_m2m_device); - return 0; -} -arch_initcall(ep93xx_dma_init); diff --git a/arch/arm/mach-ep93xx/edb93xx.c b/arch/arm/mach-ep93xx/edb93xx.c deleted file mode 100644 index 356b0460c7ed..000000000000 --- a/arch/arm/mach-ep93xx/edb93xx.c +++ /dev/null @@ -1,368 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * arch/arm/mach-ep93xx/edb93xx.c - * Cirrus Logic EDB93xx Development Board support. - * - * EDB93XX, EDB9301, EDB9307A - * Copyright (C) 2008-2009 H Hartley Sweeten - * - * EDB9302 - * Copyright (C) 2006 George Kashperko - * - * EDB9302A, EDB9315, EDB9315A - * Copyright (C) 2006 Lennert Buytenhek - * - * EDB9307 - * Copyright (C) 2007 Herbert Valerio Riedel - * - * EDB9312 - * Copyright (C) 2006 Infosys Technologies Limited - * Toufeeq Hussain - */ - -#include -#include -#include -#include -#include -#include - -#include - -#include "hardware.h" -#include -#include -#include "gpio-ep93xx.h" - -#include -#include - -#include "soc.h" - -static void __init edb93xx_register_flash(void) -{ - if (machine_is_edb9307() || machine_is_edb9312() || - machine_is_edb9315()) { - ep93xx_register_flash(4, EP93XX_CS6_PHYS_BASE, SZ_32M); - } else { - ep93xx_register_flash(2, EP93XX_CS6_PHYS_BASE, SZ_16M); - } -} - -static struct ep93xx_eth_data __initdata edb93xx_eth_data = { - .phy_id = 1, -}; - - -/************************************************************************* - * EDB93xx i2c peripheral handling - *************************************************************************/ - -static struct i2c_board_info __initdata edb93xxa_i2c_board_info[] = { - { - I2C_BOARD_INFO("isl1208", 0x6f), - }, -}; - -static struct i2c_board_info __initdata edb93xx_i2c_board_info[] = { - { - I2C_BOARD_INFO("ds1337", 0x68), - }, -}; - -static void __init edb93xx_register_i2c(void) -{ - if (machine_is_edb9302a() || machine_is_edb9307a() || - machine_is_edb9315a()) { - ep93xx_register_i2c(edb93xxa_i2c_board_info, - ARRAY_SIZE(edb93xxa_i2c_board_info)); - } else if (machine_is_edb9302() || machine_is_edb9307() - || machine_is_edb9312() || machine_is_edb9315()) { - ep93xx_register_i2c(edb93xx_i2c_board_info, - ARRAY_SIZE(edb93xx_i2c_board_info)); - } -} - - -/************************************************************************* - * EDB93xx SPI peripheral handling - *************************************************************************/ -static struct cs4271_platform_data edb93xx_cs4271_data = { - /* Intentionally left blank */ -}; - -static struct spi_board_info edb93xx_spi_board_info[] __initdata = { - { - .modalias = "cs4271", - .platform_data = &edb93xx_cs4271_data, - .max_speed_hz = 6000000, - .bus_num = 0, - .chip_select = 0, - .mode = SPI_MODE_3, - }, -}; - -static struct gpiod_lookup_table edb93xx_spi_cs_gpio_table = { - .dev_id = "spi0", - .table = { - GPIO_LOOKUP("gpio-ep93xx.0", 6, "cs", GPIO_ACTIVE_LOW), - { }, - }, -}; - -static struct ep93xx_spi_info edb93xx_spi_info __initdata = { - /* Intentionally left blank */ -}; - -static struct gpiod_lookup_table edb93xx_cs4272_edb9301_gpio_table = { - .dev_id = "spi0.0", /* CS0 on SPI0 */ - .table = { - GPIO_LOOKUP("A", 1, "reset", GPIO_ACTIVE_LOW), - { }, - }, -}; - -static struct gpiod_lookup_table edb93xx_cs4272_edb9302_gpio_table = { - .dev_id = "spi0.0", /* CS0 on SPI0 */ - .table = { - GPIO_LOOKUP("H", 2, "reset", GPIO_ACTIVE_LOW), - { }, - }, -}; - -static struct gpiod_lookup_table edb93xx_cs4272_edb9315_gpio_table = { - .dev_id = "spi0.0", /* CS0 on SPI0 */ - .table = { - GPIO_LOOKUP("B", 6, "reset", GPIO_ACTIVE_LOW), - { }, - }, -}; - -static void __init edb93xx_register_spi(void) -{ - if (machine_is_edb9301() || machine_is_edb9302()) - gpiod_add_lookup_table(&edb93xx_cs4272_edb9301_gpio_table); - else if (machine_is_edb9302a() || machine_is_edb9307a()) - gpiod_add_lookup_table(&edb93xx_cs4272_edb9302_gpio_table); - else if (machine_is_edb9315a()) - gpiod_add_lookup_table(&edb93xx_cs4272_edb9315_gpio_table); - - gpiod_add_lookup_table(&edb93xx_spi_cs_gpio_table); - ep93xx_register_spi(&edb93xx_spi_info, edb93xx_spi_board_info, - ARRAY_SIZE(edb93xx_spi_board_info)); -} - - -/************************************************************************* - * EDB93xx I2S - *************************************************************************/ -static struct platform_device edb93xx_audio_device = { - .name = "edb93xx-audio", - .id = -1, -}; - -static int __init edb93xx_has_audio(void) -{ - return (machine_is_edb9301() || machine_is_edb9302() || - machine_is_edb9302a() || machine_is_edb9307a() || - machine_is_edb9315a()); -} - -static void __init edb93xx_register_i2s(void) -{ - if (edb93xx_has_audio()) { - ep93xx_register_i2s(); - platform_device_register(&edb93xx_audio_device); - } -} - - -/************************************************************************* - * EDB93xx pwm - *************************************************************************/ -static void __init edb93xx_register_pwm(void) -{ - if (machine_is_edb9301() || - machine_is_edb9302() || machine_is_edb9302a()) { - /* EP9301 and EP9302 only have pwm.1 (EGPIO14) */ - ep93xx_register_pwm(0, 1); - } else if (machine_is_edb9307() || machine_is_edb9307a()) { - /* EP9307 only has pwm.0 (PWMOUT) */ - ep93xx_register_pwm(1, 0); - } else { - /* EP9312 and EP9315 have both */ - ep93xx_register_pwm(1, 1); - } -} - - -/************************************************************************* - * EDB93xx framebuffer - *************************************************************************/ -static struct ep93xxfb_mach_info __initdata edb93xxfb_info = { - .flags = 0, -}; - -static int __init edb93xx_has_fb(void) -{ - /* These platforms have an ep93xx with video capability */ - return machine_is_edb9307() || machine_is_edb9307a() || - machine_is_edb9312() || machine_is_edb9315() || - machine_is_edb9315a(); -} - -static void __init edb93xx_register_fb(void) -{ - if (!edb93xx_has_fb()) - return; - - if (machine_is_edb9307a() || machine_is_edb9315a()) - edb93xxfb_info.flags |= EP93XXFB_USE_SDCSN0; - else - edb93xxfb_info.flags |= EP93XXFB_USE_SDCSN3; - - ep93xx_register_fb(&edb93xxfb_info); -} - - -/************************************************************************* - * EDB93xx IDE - *************************************************************************/ -static int __init edb93xx_has_ide(void) -{ - /* - * Although EDB9312 and EDB9315 do have IDE capability, they have - * INTRQ line wired as pull-up, which makes using IDE interface - * problematic. - */ - return machine_is_edb9312() || machine_is_edb9315() || - machine_is_edb9315a(); -} - -static void __init edb93xx_register_ide(void) -{ - if (!edb93xx_has_ide()) - return; - - ep93xx_register_ide(); -} - - -static void __init edb93xx_init_machine(void) -{ - ep93xx_init_devices(); - edb93xx_register_flash(); - ep93xx_register_eth(&edb93xx_eth_data, 1); - edb93xx_register_i2c(); - edb93xx_register_spi(); - edb93xx_register_i2s(); - edb93xx_register_pwm(); - edb93xx_register_fb(); - edb93xx_register_ide(); - ep93xx_register_adc(); -} - - -#ifdef CONFIG_MACH_EDB9301 -MACHINE_START(EDB9301, "Cirrus Logic EDB9301 Evaluation Board") - /* Maintainer: H Hartley Sweeten */ - .atag_offset = 0x100, - .nr_irqs = NR_EP93XX_IRQS, - .map_io = ep93xx_map_io, - .init_irq = ep93xx_init_irq, - .init_time = ep93xx_timer_init, - .init_machine = edb93xx_init_machine, - .restart = ep93xx_restart, -MACHINE_END -#endif - -#ifdef CONFIG_MACH_EDB9302 -MACHINE_START(EDB9302, "Cirrus Logic EDB9302 Evaluation Board") - /* Maintainer: George Kashperko */ - .atag_offset = 0x100, - .nr_irqs = NR_EP93XX_IRQS, - .map_io = ep93xx_map_io, - .init_irq = ep93xx_init_irq, - .init_time = ep93xx_timer_init, - .init_machine = edb93xx_init_machine, - .restart = ep93xx_restart, -MACHINE_END -#endif - -#ifdef CONFIG_MACH_EDB9302A -MACHINE_START(EDB9302A, "Cirrus Logic EDB9302A Evaluation Board") - /* Maintainer: Lennert Buytenhek */ - .atag_offset = 0x100, - .nr_irqs = NR_EP93XX_IRQS, - .map_io = ep93xx_map_io, - .init_irq = ep93xx_init_irq, - .init_time = ep93xx_timer_init, - .init_machine = edb93xx_init_machine, - .restart = ep93xx_restart, -MACHINE_END -#endif - -#ifdef CONFIG_MACH_EDB9307 -MACHINE_START(EDB9307, "Cirrus Logic EDB9307 Evaluation Board") - /* Maintainer: Herbert Valerio Riedel */ - .atag_offset = 0x100, - .nr_irqs = NR_EP93XX_IRQS, - .map_io = ep93xx_map_io, - .init_irq = ep93xx_init_irq, - .init_time = ep93xx_timer_init, - .init_machine = edb93xx_init_machine, - .restart = ep93xx_restart, -MACHINE_END -#endif - -#ifdef CONFIG_MACH_EDB9307A -MACHINE_START(EDB9307A, "Cirrus Logic EDB9307A Evaluation Board") - /* Maintainer: H Hartley Sweeten */ - .atag_offset = 0x100, - .nr_irqs = NR_EP93XX_IRQS, - .map_io = ep93xx_map_io, - .init_irq = ep93xx_init_irq, - .init_time = ep93xx_timer_init, - .init_machine = edb93xx_init_machine, - .restart = ep93xx_restart, -MACHINE_END -#endif - -#ifdef CONFIG_MACH_EDB9312 -MACHINE_START(EDB9312, "Cirrus Logic EDB9312 Evaluation Board") - /* Maintainer: Toufeeq Hussain */ - .atag_offset = 0x100, - .nr_irqs = NR_EP93XX_IRQS, - .map_io = ep93xx_map_io, - .init_irq = ep93xx_init_irq, - .init_time = ep93xx_timer_init, - .init_machine = edb93xx_init_machine, - .restart = ep93xx_restart, -MACHINE_END -#endif - -#ifdef CONFIG_MACH_EDB9315 -MACHINE_START(EDB9315, "Cirrus Logic EDB9315 Evaluation Board") - /* Maintainer: Lennert Buytenhek */ - .atag_offset = 0x100, - .nr_irqs = NR_EP93XX_IRQS, - .map_io = ep93xx_map_io, - .init_irq = ep93xx_init_irq, - .init_time = ep93xx_timer_init, - .init_machine = edb93xx_init_machine, - .restart = ep93xx_restart, -MACHINE_END -#endif - -#ifdef CONFIG_MACH_EDB9315A -MACHINE_START(EDB9315A, "Cirrus Logic EDB9315A Evaluation Board") - /* Maintainer: Lennert Buytenhek */ - .atag_offset = 0x100, - .nr_irqs = NR_EP93XX_IRQS, - .map_io = ep93xx_map_io, - .init_irq = ep93xx_init_irq, - .init_time = ep93xx_timer_init, - .init_machine = edb93xx_init_machine, - .restart = ep93xx_restart, -MACHINE_END -#endif diff --git a/arch/arm/mach-ep93xx/ep93xx-regs.h b/arch/arm/mach-ep93xx/ep93xx-regs.h deleted file mode 100644 index 8fa3646de0a4..000000000000 --- a/arch/arm/mach-ep93xx/ep93xx-regs.h +++ /dev/null @@ -1,38 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ASM_ARCH_EP93XX_REGS_H -#define __ASM_ARCH_EP93XX_REGS_H - -/* - * EP93xx linux memory map: - * - * virt phys size - * fe800000 5M per-platform mappings - * fed00000 80800000 2M APB - * fef00000 80000000 1M AHB - */ - -#define EP93XX_AHB_PHYS_BASE 0x80000000 -#define EP93XX_AHB_VIRT_BASE 0xfef00000 -#define EP93XX_AHB_SIZE 0x00100000 - -#define EP93XX_AHB_PHYS(x) (EP93XX_AHB_PHYS_BASE + (x)) -#define EP93XX_AHB_IOMEM(x) IOMEM(EP93XX_AHB_VIRT_BASE + (x)) - -#define EP93XX_APB_PHYS_BASE 0x80800000 -#define EP93XX_APB_VIRT_BASE 0xfed00000 -#define EP93XX_APB_SIZE 0x00200000 - -#define EP93XX_APB_PHYS(x) (EP93XX_APB_PHYS_BASE + (x)) -#define EP93XX_APB_IOMEM(x) IOMEM(EP93XX_APB_VIRT_BASE + (x)) - -/* APB UARTs */ -#define EP93XX_UART1_PHYS_BASE EP93XX_APB_PHYS(0x000c0000) -#define EP93XX_UART1_BASE EP93XX_APB_IOMEM(0x000c0000) - -#define EP93XX_UART2_PHYS_BASE EP93XX_APB_PHYS(0x000d0000) -#define EP93XX_UART2_BASE EP93XX_APB_IOMEM(0x000d0000) - -#define EP93XX_UART3_PHYS_BASE EP93XX_APB_PHYS(0x000e0000) -#define EP93XX_UART3_BASE EP93XX_APB_IOMEM(0x000e0000) - -#endif diff --git a/arch/arm/mach-ep93xx/gpio-ep93xx.h b/arch/arm/mach-ep93xx/gpio-ep93xx.h deleted file mode 100644 index 7b46eb7e5507..000000000000 --- a/arch/arm/mach-ep93xx/gpio-ep93xx.h +++ /dev/null @@ -1,111 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Include file for the EP93XX GPIO controller machine specifics */ - -#ifndef __GPIO_EP93XX_H -#define __GPIO_EP93XX_H - -#include "ep93xx-regs.h" - -#define EP93XX_GPIO_PHYS_BASE EP93XX_APB_PHYS(0x00040000) -#define EP93XX_GPIO_BASE EP93XX_APB_IOMEM(0x00040000) -#define EP93XX_GPIO_REG(x) (EP93XX_GPIO_BASE + (x)) -#define EP93XX_GPIO_F_INT_STATUS EP93XX_GPIO_REG(0x5c) -#define EP93XX_GPIO_A_INT_STATUS EP93XX_GPIO_REG(0xa0) -#define EP93XX_GPIO_B_INT_STATUS EP93XX_GPIO_REG(0xbc) -#define EP93XX_GPIO_EEDRIVE EP93XX_GPIO_REG(0xc8) - -/* GPIO port A. */ -#define EP93XX_GPIO_LINE_A(x) ((x) + 0) -#define EP93XX_GPIO_LINE_EGPIO0 EP93XX_GPIO_LINE_A(0) -#define EP93XX_GPIO_LINE_EGPIO1 EP93XX_GPIO_LINE_A(1) -#define EP93XX_GPIO_LINE_EGPIO2 EP93XX_GPIO_LINE_A(2) -#define EP93XX_GPIO_LINE_EGPIO3 EP93XX_GPIO_LINE_A(3) -#define EP93XX_GPIO_LINE_EGPIO4 EP93XX_GPIO_LINE_A(4) -#define EP93XX_GPIO_LINE_EGPIO5 EP93XX_GPIO_LINE_A(5) -#define EP93XX_GPIO_LINE_EGPIO6 EP93XX_GPIO_LINE_A(6) -#define EP93XX_GPIO_LINE_EGPIO7 EP93XX_GPIO_LINE_A(7) - -/* GPIO port B. */ -#define EP93XX_GPIO_LINE_B(x) ((x) + 8) -#define EP93XX_GPIO_LINE_EGPIO8 EP93XX_GPIO_LINE_B(0) -#define EP93XX_GPIO_LINE_EGPIO9 EP93XX_GPIO_LINE_B(1) -#define EP93XX_GPIO_LINE_EGPIO10 EP93XX_GPIO_LINE_B(2) -#define EP93XX_GPIO_LINE_EGPIO11 EP93XX_GPIO_LINE_B(3) -#define EP93XX_GPIO_LINE_EGPIO12 EP93XX_GPIO_LINE_B(4) -#define EP93XX_GPIO_LINE_EGPIO13 EP93XX_GPIO_LINE_B(5) -#define EP93XX_GPIO_LINE_EGPIO14 EP93XX_GPIO_LINE_B(6) -#define EP93XX_GPIO_LINE_EGPIO15 EP93XX_GPIO_LINE_B(7) - -/* GPIO port C. */ -#define EP93XX_GPIO_LINE_C(x) ((x) + 40) -#define EP93XX_GPIO_LINE_ROW0 EP93XX_GPIO_LINE_C(0) -#define EP93XX_GPIO_LINE_ROW1 EP93XX_GPIO_LINE_C(1) -#define EP93XX_GPIO_LINE_ROW2 EP93XX_GPIO_LINE_C(2) -#define EP93XX_GPIO_LINE_ROW3 EP93XX_GPIO_LINE_C(3) -#define EP93XX_GPIO_LINE_ROW4 EP93XX_GPIO_LINE_C(4) -#define EP93XX_GPIO_LINE_ROW5 EP93XX_GPIO_LINE_C(5) -#define EP93XX_GPIO_LINE_ROW6 EP93XX_GPIO_LINE_C(6) -#define EP93XX_GPIO_LINE_ROW7 EP93XX_GPIO_LINE_C(7) - -/* GPIO port D. */ -#define EP93XX_GPIO_LINE_D(x) ((x) + 24) -#define EP93XX_GPIO_LINE_COL0 EP93XX_GPIO_LINE_D(0) -#define EP93XX_GPIO_LINE_COL1 EP93XX_GPIO_LINE_D(1) -#define EP93XX_GPIO_LINE_COL2 EP93XX_GPIO_LINE_D(2) -#define EP93XX_GPIO_LINE_COL3 EP93XX_GPIO_LINE_D(3) -#define EP93XX_GPIO_LINE_COL4 EP93XX_GPIO_LINE_D(4) -#define EP93XX_GPIO_LINE_COL5 EP93XX_GPIO_LINE_D(5) -#define EP93XX_GPIO_LINE_COL6 EP93XX_GPIO_LINE_D(6) -#define EP93XX_GPIO_LINE_COL7 EP93XX_GPIO_LINE_D(7) - -/* GPIO port E. */ -#define EP93XX_GPIO_LINE_E(x) ((x) + 32) -#define EP93XX_GPIO_LINE_GRLED EP93XX_GPIO_LINE_E(0) -#define EP93XX_GPIO_LINE_RDLED EP93XX_GPIO_LINE_E(1) -#define EP93XX_GPIO_LINE_DIORn EP93XX_GPIO_LINE_E(2) -#define EP93XX_GPIO_LINE_IDECS1n EP93XX_GPIO_LINE_E(3) -#define EP93XX_GPIO_LINE_IDECS2n EP93XX_GPIO_LINE_E(4) -#define EP93XX_GPIO_LINE_IDEDA0 EP93XX_GPIO_LINE_E(5) -#define EP93XX_GPIO_LINE_IDEDA1 EP93XX_GPIO_LINE_E(6) -#define EP93XX_GPIO_LINE_IDEDA2 EP93XX_GPIO_LINE_E(7) - -/* GPIO port F. */ -#define EP93XX_GPIO_LINE_F(x) ((x) + 16) -#define EP93XX_GPIO_LINE_WP EP93XX_GPIO_LINE_F(0) -#define EP93XX_GPIO_LINE_MCCD1 EP93XX_GPIO_LINE_F(1) -#define EP93XX_GPIO_LINE_MCCD2 EP93XX_GPIO_LINE_F(2) -#define EP93XX_GPIO_LINE_MCBVD1 EP93XX_GPIO_LINE_F(3) -#define EP93XX_GPIO_LINE_MCBVD2 EP93XX_GPIO_LINE_F(4) -#define EP93XX_GPIO_LINE_VS1 EP93XX_GPIO_LINE_F(5) -#define EP93XX_GPIO_LINE_READY EP93XX_GPIO_LINE_F(6) -#define EP93XX_GPIO_LINE_VS2 EP93XX_GPIO_LINE_F(7) - -/* GPIO port G. */ -#define EP93XX_GPIO_LINE_G(x) ((x) + 48) -#define EP93XX_GPIO_LINE_EECLK EP93XX_GPIO_LINE_G(0) -#define EP93XX_GPIO_LINE_EEDAT EP93XX_GPIO_LINE_G(1) -#define EP93XX_GPIO_LINE_SLA0 EP93XX_GPIO_LINE_G(2) -#define EP93XX_GPIO_LINE_SLA1 EP93XX_GPIO_LINE_G(3) -#define EP93XX_GPIO_LINE_DD12 EP93XX_GPIO_LINE_G(4) -#define EP93XX_GPIO_LINE_DD13 EP93XX_GPIO_LINE_G(5) -#define EP93XX_GPIO_LINE_DD14 EP93XX_GPIO_LINE_G(6) -#define EP93XX_GPIO_LINE_DD15 EP93XX_GPIO_LINE_G(7) - -/* GPIO port H. */ -#define EP93XX_GPIO_LINE_H(x) ((x) + 56) -#define EP93XX_GPIO_LINE_DD0 EP93XX_GPIO_LINE_H(0) -#define EP93XX_GPIO_LINE_DD1 EP93XX_GPIO_LINE_H(1) -#define EP93XX_GPIO_LINE_DD2 EP93XX_GPIO_LINE_H(2) -#define EP93XX_GPIO_LINE_DD3 EP93XX_GPIO_LINE_H(3) -#define EP93XX_GPIO_LINE_DD4 EP93XX_GPIO_LINE_H(4) -#define EP93XX_GPIO_LINE_DD5 EP93XX_GPIO_LINE_H(5) -#define EP93XX_GPIO_LINE_DD6 EP93XX_GPIO_LINE_H(6) -#define EP93XX_GPIO_LINE_DD7 EP93XX_GPIO_LINE_H(7) - -/* maximum value for gpio line identifiers */ -#define EP93XX_GPIO_LINE_MAX EP93XX_GPIO_LINE_H(7) - -/* maximum value for irq capable line identifiers */ -#define EP93XX_GPIO_LINE_MAX_IRQ EP93XX_GPIO_LINE_F(7) - -#endif /* __GPIO_EP93XX_H */ diff --git a/arch/arm/mach-ep93xx/hardware.h b/arch/arm/mach-ep93xx/hardware.h deleted file mode 100644 index e7d850e04782..000000000000 --- a/arch/arm/mach-ep93xx/hardware.h +++ /dev/null @@ -1,25 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * arch/arm/mach-ep93xx/include/mach/hardware.h - */ - -#ifndef __ASM_ARCH_HARDWARE_H -#define __ASM_ARCH_HARDWARE_H - -#include "platform.h" - -/* - * The EP93xx has two external crystal oscillators. To generate the - * required high-frequency clocks, the processor uses two phase-locked- - * loops (PLLs) to multiply the incoming external clock signal to much - * higher frequencies that are then divided down by programmable dividers - * to produce the needed clocks. The PLLs operate independently of one - * another. - */ -#define EP93XX_EXT_CLK_RATE 14745600 -#define EP93XX_EXT_RTC_RATE 32768 - -#define EP93XX_KEYTCHCLK_DIV4 (EP93XX_EXT_CLK_RATE / 4) -#define EP93XX_KEYTCHCLK_DIV16 (EP93XX_EXT_CLK_RATE / 16) - -#endif diff --git a/arch/arm/mach-ep93xx/irqs.h b/arch/arm/mach-ep93xx/irqs.h deleted file mode 100644 index 353201b90c66..000000000000 --- a/arch/arm/mach-ep93xx/irqs.h +++ /dev/null @@ -1,76 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ASM_ARCH_IRQS_H -#define __ASM_ARCH_IRQS_H - -#define IRQ_EP93XX_VIC0 1 - -#define IRQ_EP93XX_COMMRX (IRQ_EP93XX_VIC0 + 2) -#define IRQ_EP93XX_COMMTX (IRQ_EP93XX_VIC0 + 3) -#define IRQ_EP93XX_TIMER1 (IRQ_EP93XX_VIC0 + 4) -#define IRQ_EP93XX_TIMER2 (IRQ_EP93XX_VIC0 + 5) -#define IRQ_EP93XX_AACINTR (IRQ_EP93XX_VIC0 + 6) -#define IRQ_EP93XX_DMAM2P0 (IRQ_EP93XX_VIC0 + 7) -#define IRQ_EP93XX_DMAM2P1 (IRQ_EP93XX_VIC0 + 8) -#define IRQ_EP93XX_DMAM2P2 (IRQ_EP93XX_VIC0 + 9) -#define IRQ_EP93XX_DMAM2P3 (IRQ_EP93XX_VIC0 + 10) -#define IRQ_EP93XX_DMAM2P4 (IRQ_EP93XX_VIC0 + 11) -#define IRQ_EP93XX_DMAM2P5 (IRQ_EP93XX_VIC0 + 12) -#define IRQ_EP93XX_DMAM2P6 (IRQ_EP93XX_VIC0 + 13) -#define IRQ_EP93XX_DMAM2P7 (IRQ_EP93XX_VIC0 + 14) -#define IRQ_EP93XX_DMAM2P8 (IRQ_EP93XX_VIC0 + 15) -#define IRQ_EP93XX_DMAM2P9 (IRQ_EP93XX_VIC0 + 16) -#define IRQ_EP93XX_DMAM2M0 (IRQ_EP93XX_VIC0 + 17) -#define IRQ_EP93XX_DMAM2M1 (IRQ_EP93XX_VIC0 + 18) -#define IRQ_EP93XX_GPIO0MUX (IRQ_EP93XX_VIC0 + 19) -#define IRQ_EP93XX_GPIO1MUX (IRQ_EP93XX_VIC0 + 20) -#define IRQ_EP93XX_GPIO2MUX (IRQ_EP93XX_VIC0 + 21) -#define IRQ_EP93XX_GPIO3MUX (IRQ_EP93XX_VIC0 + 22) -#define IRQ_EP93XX_UART1RX (IRQ_EP93XX_VIC0 + 23) -#define IRQ_EP93XX_UART1TX (IRQ_EP93XX_VIC0 + 24) -#define IRQ_EP93XX_UART2RX (IRQ_EP93XX_VIC0 + 25) -#define IRQ_EP93XX_UART2TX (IRQ_EP93XX_VIC0 + 26) -#define IRQ_EP93XX_UART3RX (IRQ_EP93XX_VIC0 + 27) -#define IRQ_EP93XX_UART3TX (IRQ_EP93XX_VIC0 + 28) -#define IRQ_EP93XX_KEY (IRQ_EP93XX_VIC0 + 29) -#define IRQ_EP93XX_TOUCH (IRQ_EP93XX_VIC0 + 30) -#define EP93XX_VIC1_VALID_IRQ_MASK 0x7ffffffc - -#define IRQ_EP93XX_VIC1 (IRQ_EP93XX_VIC0 + 32) - -#define IRQ_EP93XX_EXT0 (IRQ_EP93XX_VIC1 + 0) -#define IRQ_EP93XX_EXT1 (IRQ_EP93XX_VIC1 + 1) -#define IRQ_EP93XX_EXT2 (IRQ_EP93XX_VIC1 + 2) -#define IRQ_EP93XX_64HZ (IRQ_EP93XX_VIC1 + 3) -#define IRQ_EP93XX_WATCHDOG (IRQ_EP93XX_VIC1 + 4) -#define IRQ_EP93XX_RTC (IRQ_EP93XX_VIC1 + 5) -#define IRQ_EP93XX_IRDA (IRQ_EP93XX_VIC1 + 6) -#define IRQ_EP93XX_ETHERNET (IRQ_EP93XX_VIC1 + 7) -#define IRQ_EP93XX_EXT3 (IRQ_EP93XX_VIC1 + 8) -#define IRQ_EP93XX_PROG (IRQ_EP93XX_VIC1 + 9) -#define IRQ_EP93XX_1HZ (IRQ_EP93XX_VIC1 + 10) -#define IRQ_EP93XX_VSYNC (IRQ_EP93XX_VIC1 + 11) -#define IRQ_EP93XX_VIDEO_FIFO (IRQ_EP93XX_VIC1 + 12) -#define IRQ_EP93XX_SSP1RX (IRQ_EP93XX_VIC1 + 13) -#define IRQ_EP93XX_SSP1TX (IRQ_EP93XX_VIC1 + 14) -#define IRQ_EP93XX_GPIO4MUX (IRQ_EP93XX_VIC1 + 15) -#define IRQ_EP93XX_GPIO5MUX (IRQ_EP93XX_VIC1 + 16) -#define IRQ_EP93XX_GPIO6MUX (IRQ_EP93XX_VIC1 + 17) -#define IRQ_EP93XX_GPIO7MUX (IRQ_EP93XX_VIC1 + 18) -#define IRQ_EP93XX_TIMER3 (IRQ_EP93XX_VIC1 + 19) -#define IRQ_EP93XX_UART1 (IRQ_EP93XX_VIC1 + 20) -#define IRQ_EP93XX_SSP (IRQ_EP93XX_VIC1 + 21) -#define IRQ_EP93XX_UART2 (IRQ_EP93XX_VIC1 + 22) -#define IRQ_EP93XX_UART3 (IRQ_EP93XX_VIC1 + 23) -#define IRQ_EP93XX_USB (IRQ_EP93XX_VIC1 + 24) -#define IRQ_EP93XX_ETHERNET_PME (IRQ_EP93XX_VIC1 + 25) -#define IRQ_EP93XX_DSP (IRQ_EP93XX_VIC1 + 26) -#define IRQ_EP93XX_GPIO_AB (IRQ_EP93XX_VIC1 + 27) -#define IRQ_EP93XX_SAI (IRQ_EP93XX_VIC1 + 28) -#define EP93XX_VIC2_VALID_IRQ_MASK 0x1fffffff - -#define NR_EP93XX_IRQS (IRQ_EP93XX_VIC1 + 32 + 24) - -#define EP93XX_BOARD_IRQ(x) (NR_EP93XX_IRQS + (x)) -#define EP93XX_BOARD_IRQS 32 - -#endif diff --git a/arch/arm/mach-ep93xx/platform.h b/arch/arm/mach-ep93xx/platform.h deleted file mode 100644 index 5fb1b919133f..000000000000 --- a/arch/arm/mach-ep93xx/platform.h +++ /dev/null @@ -1,42 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * arch/arm/mach-ep93xx/include/mach/platform.h - */ - -#ifndef __ASSEMBLY__ - -#include -#include - -struct device; -struct i2c_board_info; -struct spi_board_info; -struct platform_device; -struct ep93xxfb_mach_info; -struct ep93xx_keypad_platform_data; -struct ep93xx_spi_info; - -void ep93xx_map_io(void); -void ep93xx_init_irq(void); - -void ep93xx_register_flash(unsigned int width, - resource_size_t start, resource_size_t size); - -void ep93xx_register_eth(struct ep93xx_eth_data *data, int copy_addr); -void ep93xx_register_i2c(struct i2c_board_info *devices, int num); -void ep93xx_register_spi(struct ep93xx_spi_info *info, - struct spi_board_info *devices, int num); -void ep93xx_register_fb(struct ep93xxfb_mach_info *data); -void ep93xx_register_pwm(int pwm0, int pwm1); -void ep93xx_register_keypad(struct ep93xx_keypad_platform_data *data); -void ep93xx_register_i2s(void); -void ep93xx_register_ac97(void); -void ep93xx_register_ide(void); -void ep93xx_register_adc(void); - -struct device *ep93xx_init_devices(void); -extern void ep93xx_timer_init(void); - -void ep93xx_restart(enum reboot_mode, const char *); - -#endif diff --git a/arch/arm/mach-ep93xx/soc.h b/arch/arm/mach-ep93xx/soc.h deleted file mode 100644 index 3245ebbd5069..000000000000 --- a/arch/arm/mach-ep93xx/soc.h +++ /dev/null @@ -1,212 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * arch/arm/mach-ep93xx/soc.h - * - * Copyright (C) 2012 Open Kernel Labs - * Copyright (C) 2012 Ryan Mallon - */ - -#ifndef _EP93XX_SOC_H -#define _EP93XX_SOC_H - -#include "ep93xx-regs.h" -#include "irqs.h" - -/* - * EP93xx Physical Memory Map: - * - * The ASDO pin is sampled at system reset to select a synchronous or - * asynchronous boot configuration. When ASDO is "1" (i.e. pulled-up) - * the synchronous boot mode is selected. When ASDO is "0" (i.e - * pulled-down) the asynchronous boot mode is selected. - * - * In synchronous boot mode nSDCE3 is decoded starting at physical address - * 0x00000000 and nCS0 is decoded starting at 0xf0000000. For asynchronous - * boot mode they are swapped with nCS0 decoded at 0x00000000 ann nSDCE3 - * decoded at 0xf0000000. - * - * There is known errata for the EP93xx dealing with External Memory - * Configurations. Please refer to "AN273: EP93xx Silicon Rev E Design - * Guidelines" for more information. This document can be found at: - * - * http://www.cirrus.com/en/pubs/appNote/AN273REV4.pdf - */ - -#define EP93XX_CS0_PHYS_BASE_ASYNC 0x00000000 /* ASDO Pin = 0 */ -#define EP93XX_SDCE3_PHYS_BASE_SYNC 0x00000000 /* ASDO Pin = 1 */ -#define EP93XX_CS1_PHYS_BASE 0x10000000 -#define EP93XX_CS2_PHYS_BASE 0x20000000 -#define EP93XX_CS3_PHYS_BASE 0x30000000 -#define EP93XX_PCMCIA_PHYS_BASE 0x40000000 -#define EP93XX_CS6_PHYS_BASE 0x60000000 -#define EP93XX_CS7_PHYS_BASE 0x70000000 -#define EP93XX_SDCE0_PHYS_BASE 0xc0000000 -#define EP93XX_SDCE1_PHYS_BASE 0xd0000000 -#define EP93XX_SDCE2_PHYS_BASE 0xe0000000 -#define EP93XX_SDCE3_PHYS_BASE_ASYNC 0xf0000000 /* ASDO Pin = 0 */ -#define EP93XX_CS0_PHYS_BASE_SYNC 0xf0000000 /* ASDO Pin = 1 */ - -/* AHB peripherals */ -#define EP93XX_DMA_BASE EP93XX_AHB_IOMEM(0x00000000) - -#define EP93XX_ETHERNET_PHYS_BASE EP93XX_AHB_PHYS(0x00010000) -#define EP93XX_ETHERNET_BASE EP93XX_AHB_IOMEM(0x00010000) - -#define EP93XX_USB_PHYS_BASE EP93XX_AHB_PHYS(0x00020000) -#define EP93XX_USB_BASE EP93XX_AHB_IOMEM(0x00020000) - -#define EP93XX_RASTER_PHYS_BASE EP93XX_AHB_PHYS(0x00030000) -#define EP93XX_RASTER_BASE EP93XX_AHB_IOMEM(0x00030000) - -#define EP93XX_GRAPHICS_ACCEL_BASE EP93XX_AHB_IOMEM(0x00040000) - -#define EP93XX_SDRAM_CONTROLLER_BASE EP93XX_AHB_IOMEM(0x00060000) - -#define EP93XX_PCMCIA_CONTROLLER_BASE EP93XX_AHB_IOMEM(0x00080000) - -#define EP93XX_BOOT_ROM_BASE EP93XX_AHB_IOMEM(0x00090000) - -#define EP93XX_IDE_PHYS_BASE EP93XX_AHB_PHYS(0x000a0000) -#define EP93XX_IDE_BASE EP93XX_AHB_IOMEM(0x000a0000) - -#define EP93XX_VIC1_BASE EP93XX_AHB_IOMEM(0x000b0000) - -#define EP93XX_VIC2_BASE EP93XX_AHB_IOMEM(0x000c0000) - -/* APB peripherals */ -#define EP93XX_TIMER_BASE EP93XX_APB_IOMEM(0x00010000) - -#define EP93XX_I2S_PHYS_BASE EP93XX_APB_PHYS(0x00020000) -#define EP93XX_I2S_BASE EP93XX_APB_IOMEM(0x00020000) - -#define EP93XX_SECURITY_BASE EP93XX_APB_IOMEM(0x00030000) - -#define EP93XX_AAC_PHYS_BASE EP93XX_APB_PHYS(0x00080000) -#define EP93XX_AAC_BASE EP93XX_APB_IOMEM(0x00080000) - -#define EP93XX_SPI_PHYS_BASE EP93XX_APB_PHYS(0x000a0000) -#define EP93XX_SPI_BASE EP93XX_APB_IOMEM(0x000a0000) - -#define EP93XX_IRDA_BASE EP93XX_APB_IOMEM(0x000b0000) - -#define EP93XX_KEY_MATRIX_PHYS_BASE EP93XX_APB_PHYS(0x000f0000) -#define EP93XX_KEY_MATRIX_BASE EP93XX_APB_IOMEM(0x000f0000) - -#define EP93XX_ADC_PHYS_BASE EP93XX_APB_PHYS(0x00100000) -#define EP93XX_ADC_BASE EP93XX_APB_IOMEM(0x00100000) -#define EP93XX_TOUCHSCREEN_BASE EP93XX_APB_IOMEM(0x00100000) - -#define EP93XX_PWM_PHYS_BASE EP93XX_APB_PHYS(0x00110000) -#define EP93XX_PWM_BASE EP93XX_APB_IOMEM(0x00110000) - -#define EP93XX_RTC_PHYS_BASE EP93XX_APB_PHYS(0x00120000) -#define EP93XX_RTC_BASE EP93XX_APB_IOMEM(0x00120000) - -#define EP93XX_WATCHDOG_PHYS_BASE EP93XX_APB_PHYS(0x00140000) -#define EP93XX_WATCHDOG_BASE EP93XX_APB_IOMEM(0x00140000) - -/* System controller */ -#define EP93XX_SYSCON_BASE EP93XX_APB_IOMEM(0x00130000) -#define EP93XX_SYSCON_REG(x) (EP93XX_SYSCON_BASE + (x)) -#define EP93XX_SYSCON_POWER_STATE EP93XX_SYSCON_REG(0x00) -#define EP93XX_SYSCON_PWRCNT EP93XX_SYSCON_REG(0x04) -#define EP93XX_SYSCON_PWRCNT_FIR_EN (1<<31) -#define EP93XX_SYSCON_PWRCNT_UARTBAUD (1<<29) -#define EP93XX_SYSCON_PWRCNT_USH_EN 28 -#define EP93XX_SYSCON_PWRCNT_DMA_M2M1 27 -#define EP93XX_SYSCON_PWRCNT_DMA_M2M0 26 -#define EP93XX_SYSCON_PWRCNT_DMA_M2P8 25 -#define EP93XX_SYSCON_PWRCNT_DMA_M2P9 24 -#define EP93XX_SYSCON_PWRCNT_DMA_M2P6 23 -#define EP93XX_SYSCON_PWRCNT_DMA_M2P7 22 -#define EP93XX_SYSCON_PWRCNT_DMA_M2P4 21 -#define EP93XX_SYSCON_PWRCNT_DMA_M2P5 20 -#define EP93XX_SYSCON_PWRCNT_DMA_M2P2 19 -#define EP93XX_SYSCON_PWRCNT_DMA_M2P3 18 -#define EP93XX_SYSCON_PWRCNT_DMA_M2P0 17 -#define EP93XX_SYSCON_PWRCNT_DMA_M2P1 16 -#define EP93XX_SYSCON_HALT EP93XX_SYSCON_REG(0x08) -#define EP93XX_SYSCON_STANDBY EP93XX_SYSCON_REG(0x0c) -#define EP93XX_SYSCON_CLKSET1 EP93XX_SYSCON_REG(0x20) -#define EP93XX_SYSCON_CLKSET1_NBYP1 (1<<23) -#define EP93XX_SYSCON_CLKSET2 EP93XX_SYSCON_REG(0x24) -#define EP93XX_SYSCON_CLKSET2_NBYP2 (1<<19) -#define EP93XX_SYSCON_CLKSET2_PLL2_EN (1<<18) -#define EP93XX_SYSCON_DEVCFG EP93XX_SYSCON_REG(0x80) -#define EP93XX_SYSCON_DEVCFG_SWRST (1<<31) -#define EP93XX_SYSCON_DEVCFG_D1ONG (1<<30) -#define EP93XX_SYSCON_DEVCFG_D0ONG (1<<29) -#define EP93XX_SYSCON_DEVCFG_IONU2 (1<<28) -#define EP93XX_SYSCON_DEVCFG_GONK (1<<27) -#define EP93XX_SYSCON_DEVCFG_TONG (1<<26) -#define EP93XX_SYSCON_DEVCFG_MONG (1<<25) -#define EP93XX_SYSCON_DEVCFG_U3EN 24 -#define EP93XX_SYSCON_DEVCFG_CPENA (1<<23) -#define EP93XX_SYSCON_DEVCFG_A2ONG (1<<22) -#define EP93XX_SYSCON_DEVCFG_A1ONG (1<<21) -#define EP93XX_SYSCON_DEVCFG_U2EN 20 -#define EP93XX_SYSCON_DEVCFG_EXVC (1<<19) -#define EP93XX_SYSCON_DEVCFG_U1EN 18 -#define EP93XX_SYSCON_DEVCFG_TIN (1<<17) -#define EP93XX_SYSCON_DEVCFG_HC3IN (1<<15) -#define EP93XX_SYSCON_DEVCFG_HC3EN (1<<14) -#define EP93XX_SYSCON_DEVCFG_HC1IN (1<<13) -#define EP93XX_SYSCON_DEVCFG_HC1EN (1<<12) -#define EP93XX_SYSCON_DEVCFG_HONIDE (1<<11) -#define EP93XX_SYSCON_DEVCFG_GONIDE (1<<10) -#define EP93XX_SYSCON_DEVCFG_PONG (1<<9) -#define EP93XX_SYSCON_DEVCFG_EONIDE (1<<8) -#define EP93XX_SYSCON_DEVCFG_I2SONSSP (1<<7) -#define EP93XX_SYSCON_DEVCFG_I2SONAC97 (1<<6) -#define EP93XX_SYSCON_DEVCFG_RASONP3 (1<<4) -#define EP93XX_SYSCON_DEVCFG_RAS (1<<3) -#define EP93XX_SYSCON_DEVCFG_ADCPD (1<<2) -#define EP93XX_SYSCON_DEVCFG_KEYS (1<<1) -#define EP93XX_SYSCON_DEVCFG_SHENA (1<<0) -#define EP93XX_SYSCON_VIDCLKDIV EP93XX_SYSCON_REG(0x84) -#define EP93XX_SYSCON_CLKDIV_ENABLE 15 -#define EP93XX_SYSCON_CLKDIV_ESEL (1<<14) -#define EP93XX_SYSCON_CLKDIV_PSEL (1<<13) -#define EP93XX_SYSCON_CLKDIV_PDIV_SHIFT 8 -#define EP93XX_SYSCON_I2SCLKDIV EP93XX_SYSCON_REG(0x8c) -#define EP93XX_SYSCON_I2SCLKDIV_SENA 31 -#define EP93XX_SYSCON_I2SCLKDIV_ORIDE (1<<29) -#define EP93XX_SYSCON_I2SCLKDIV_SPOL (1<<19) -#define EP93XX_I2SCLKDIV_SDIV (1 << 16) -#define EP93XX_I2SCLKDIV_LRDIV32 (0 << 17) -#define EP93XX_I2SCLKDIV_LRDIV64 (1 << 17) -#define EP93XX_I2SCLKDIV_LRDIV128 (2 << 17) -#define EP93XX_I2SCLKDIV_LRDIV_MASK (3 << 17) -#define EP93XX_SYSCON_KEYTCHCLKDIV EP93XX_SYSCON_REG(0x90) -#define EP93XX_SYSCON_KEYTCHCLKDIV_TSEN 31 -#define EP93XX_SYSCON_KEYTCHCLKDIV_ADIV 16 -#define EP93XX_SYSCON_KEYTCHCLKDIV_KEN 15 -#define EP93XX_SYSCON_KEYTCHCLKDIV_KDIV (1<<0) -#define EP93XX_SYSCON_SYSCFG EP93XX_SYSCON_REG(0x9c) -#define EP93XX_SYSCON_SYSCFG_REV_MASK (0xf0000000) -#define EP93XX_SYSCON_SYSCFG_REV_SHIFT (28) -#define EP93XX_SYSCON_SYSCFG_SBOOT (1<<8) -#define EP93XX_SYSCON_SYSCFG_LCSN7 (1<<7) -#define EP93XX_SYSCON_SYSCFG_LCSN6 (1<<6) -#define EP93XX_SYSCON_SYSCFG_LASDO (1<<5) -#define EP93XX_SYSCON_SYSCFG_LEEDA (1<<4) -#define EP93XX_SYSCON_SYSCFG_LEECLK (1<<3) -#define EP93XX_SYSCON_SYSCFG_LCSN2 (1<<1) -#define EP93XX_SYSCON_SYSCFG_LCSN1 (1<<0) -#define EP93XX_SYSCON_SWLOCK EP93XX_SYSCON_REG(0xc0) - -/* EP93xx System Controller software locked register write */ -void ep93xx_syscon_swlocked_write(unsigned int val, void __iomem *reg); -void ep93xx_devcfg_set_clear(unsigned int set_bits, unsigned int clear_bits); - -static inline void ep93xx_devcfg_set_bits(unsigned int bits) -{ - ep93xx_devcfg_set_clear(bits, 0x00); -} - -static inline void ep93xx_devcfg_clear_bits(unsigned int bits) -{ - ep93xx_devcfg_set_clear(0x00, bits); -} - -#endif /* _EP93XX_SOC_H */ diff --git a/arch/arm/mach-ep93xx/timer-ep93xx.c b/arch/arm/mach-ep93xx/timer-ep93xx.c deleted file mode 100644 index a9efa7bc2fa1..000000000000 --- a/arch/arm/mach-ep93xx/timer-ep93xx.c +++ /dev/null @@ -1,143 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include "soc.h" -#include "platform.h" - -/************************************************************************* - * Timer handling for EP93xx - ************************************************************************* - * The ep93xx has four internal timers. Timers 1, 2 (both 16 bit) and - * 3 (32 bit) count down at 508 kHz, are self-reloading, and can generate - * an interrupt on underflow. Timer 4 (40 bit) counts down at 983.04 kHz, - * is free-running, and can't generate interrupts. - * - * The 508 kHz timers are ideal for use for the timer interrupt, as the - * most common values of HZ divide 508 kHz nicely. We pick the 32 bit - * timer (timer 3) to get as long sleep intervals as possible when using - * CONFIG_NO_HZ. - * - * The higher clock rate of timer 4 makes it a better choice than the - * other timers for use as clock source and for sched_clock(), providing - * a stable 40 bit time base. - ************************************************************************* - */ -#define EP93XX_TIMER_REG(x) (EP93XX_TIMER_BASE + (x)) -#define EP93XX_TIMER1_LOAD EP93XX_TIMER_REG(0x00) -#define EP93XX_TIMER1_VALUE EP93XX_TIMER_REG(0x04) -#define EP93XX_TIMER1_CONTROL EP93XX_TIMER_REG(0x08) -#define EP93XX_TIMER123_CONTROL_ENABLE (1 << 7) -#define EP93XX_TIMER123_CONTROL_MODE (1 << 6) -#define EP93XX_TIMER123_CONTROL_CLKSEL (1 << 3) -#define EP93XX_TIMER1_CLEAR EP93XX_TIMER_REG(0x0c) -#define EP93XX_TIMER2_LOAD EP93XX_TIMER_REG(0x20) -#define EP93XX_TIMER2_VALUE EP93XX_TIMER_REG(0x24) -#define EP93XX_TIMER2_CONTROL EP93XX_TIMER_REG(0x28) -#define EP93XX_TIMER2_CLEAR EP93XX_TIMER_REG(0x2c) -#define EP93XX_TIMER4_VALUE_LOW EP93XX_TIMER_REG(0x60) -#define EP93XX_TIMER4_VALUE_HIGH EP93XX_TIMER_REG(0x64) -#define EP93XX_TIMER4_VALUE_HIGH_ENABLE (1 << 8) -#define EP93XX_TIMER3_LOAD EP93XX_TIMER_REG(0x80) -#define EP93XX_TIMER3_VALUE EP93XX_TIMER_REG(0x84) -#define EP93XX_TIMER3_CONTROL EP93XX_TIMER_REG(0x88) -#define EP93XX_TIMER3_CLEAR EP93XX_TIMER_REG(0x8c) - -#define EP93XX_TIMER123_RATE 508469 -#define EP93XX_TIMER4_RATE 983040 - -static u64 notrace ep93xx_read_sched_clock(void) -{ - u64 ret; - - ret = readl(EP93XX_TIMER4_VALUE_LOW); - ret |= ((u64) (readl(EP93XX_TIMER4_VALUE_HIGH) & 0xff) << 32); - return ret; -} - -static u64 ep93xx_clocksource_read(struct clocksource *c) -{ - u64 ret; - - ret = readl(EP93XX_TIMER4_VALUE_LOW); - ret |= ((u64) (readl(EP93XX_TIMER4_VALUE_HIGH) & 0xff) << 32); - return (u64) ret; -} - -static int ep93xx_clkevt_set_next_event(unsigned long next, - struct clock_event_device *evt) -{ - /* Default mode: periodic, off, 508 kHz */ - u32 tmode = EP93XX_TIMER123_CONTROL_MODE | - EP93XX_TIMER123_CONTROL_CLKSEL; - - /* Clear timer */ - writel(tmode, EP93XX_TIMER3_CONTROL); - - /* Set next event */ - writel(next, EP93XX_TIMER3_LOAD); - writel(tmode | EP93XX_TIMER123_CONTROL_ENABLE, - EP93XX_TIMER3_CONTROL); - return 0; -} - - -static int ep93xx_clkevt_shutdown(struct clock_event_device *evt) -{ - /* Disable timer */ - writel(0, EP93XX_TIMER3_CONTROL); - - return 0; -} - -static struct clock_event_device ep93xx_clockevent = { - .name = "timer1", - .features = CLOCK_EVT_FEAT_ONESHOT, - .set_state_shutdown = ep93xx_clkevt_shutdown, - .set_state_oneshot = ep93xx_clkevt_shutdown, - .tick_resume = ep93xx_clkevt_shutdown, - .set_next_event = ep93xx_clkevt_set_next_event, - .rating = 300, -}; - -static irqreturn_t ep93xx_timer_interrupt(int irq, void *dev_id) -{ - struct clock_event_device *evt = dev_id; - - /* Writing any value clears the timer interrupt */ - writel(1, EP93XX_TIMER3_CLEAR); - - evt->event_handler(evt); - - return IRQ_HANDLED; -} - -void __init ep93xx_timer_init(void) -{ - int irq = IRQ_EP93XX_TIMER3; - unsigned long flags = IRQF_TIMER | IRQF_IRQPOLL; - - /* Enable and register clocksource and sched_clock on timer 4 */ - writel(EP93XX_TIMER4_VALUE_HIGH_ENABLE, - EP93XX_TIMER4_VALUE_HIGH); - clocksource_mmio_init(NULL, "timer4", - EP93XX_TIMER4_RATE, 200, 40, - ep93xx_clocksource_read); - sched_clock_register(ep93xx_read_sched_clock, 40, - EP93XX_TIMER4_RATE); - - /* Set up clockevent on timer 3 */ - if (request_irq(irq, ep93xx_timer_interrupt, flags, "ep93xx timer", - &ep93xx_clockevent)) - pr_err("Failed to request irq %d (ep93xx timer)\n", irq); - clockevents_config_and_register(&ep93xx_clockevent, - EP93XX_TIMER123_RATE, - 1, - 0xffffffffU); -} diff --git a/arch/arm/mach-ep93xx/ts72xx.c b/arch/arm/mach-ep93xx/ts72xx.c deleted file mode 100644 index 0bbdf587c685..000000000000 --- a/arch/arm/mach-ep93xx/ts72xx.c +++ /dev/null @@ -1,422 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * arch/arm/mach-ep93xx/ts72xx.c - * Technologic Systems TS72xx SBC support. - * - * Copyright (C) 2006 Lennert Buytenhek - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "gpio-ep93xx.h" -#include "hardware.h" - -#include -#include -#include - -#include "soc.h" -#include "ts72xx.h" - -/************************************************************************* - * IO map - *************************************************************************/ -static struct map_desc ts72xx_io_desc[] __initdata = { - { - .virtual = (unsigned long)TS72XX_MODEL_VIRT_BASE, - .pfn = __phys_to_pfn(TS72XX_MODEL_PHYS_BASE), - .length = TS72XX_MODEL_SIZE, - .type = MT_DEVICE, - }, { - .virtual = (unsigned long)TS72XX_OPTIONS_VIRT_BASE, - .pfn = __phys_to_pfn(TS72XX_OPTIONS_PHYS_BASE), - .length = TS72XX_OPTIONS_SIZE, - .type = MT_DEVICE, - }, { - .virtual = (unsigned long)TS72XX_OPTIONS2_VIRT_BASE, - .pfn = __phys_to_pfn(TS72XX_OPTIONS2_PHYS_BASE), - .length = TS72XX_OPTIONS2_SIZE, - .type = MT_DEVICE, - }, { - .virtual = (unsigned long)TS72XX_CPLDVER_VIRT_BASE, - .pfn = __phys_to_pfn(TS72XX_CPLDVER_PHYS_BASE), - .length = TS72XX_CPLDVER_SIZE, - .type = MT_DEVICE, - } -}; - -static void __init ts72xx_map_io(void) -{ - ep93xx_map_io(); - iotable_init(ts72xx_io_desc, ARRAY_SIZE(ts72xx_io_desc)); -} - - -/************************************************************************* - * NAND flash - *************************************************************************/ -#define TS72XX_NAND_CONTROL_ADDR_LINE 22 /* 0xN0400000 */ -#define TS72XX_NAND_BUSY_ADDR_LINE 23 /* 0xN0800000 */ - -static void ts72xx_nand_hwcontrol(struct nand_chip *chip, - int cmd, unsigned int ctrl) -{ - if (ctrl & NAND_CTRL_CHANGE) { - void __iomem *addr = chip->legacy.IO_ADDR_R; - unsigned char bits; - - addr += (1 << TS72XX_NAND_CONTROL_ADDR_LINE); - - bits = __raw_readb(addr) & ~0x07; - bits |= (ctrl & NAND_NCE) << 2; /* bit 0 -> bit 2 */ - bits |= (ctrl & NAND_CLE); /* bit 1 -> bit 1 */ - bits |= (ctrl & NAND_ALE) >> 2; /* bit 2 -> bit 0 */ - - __raw_writeb(bits, addr); - } - - if (cmd != NAND_CMD_NONE) - __raw_writeb(cmd, chip->legacy.IO_ADDR_W); -} - -static int ts72xx_nand_device_ready(struct nand_chip *chip) -{ - void __iomem *addr = chip->legacy.IO_ADDR_R; - - addr += (1 << TS72XX_NAND_BUSY_ADDR_LINE); - - return !!(__raw_readb(addr) & 0x20); -} - -#define TS72XX_BOOTROM_PART_SIZE (SZ_16K) -#define TS72XX_REDBOOT_PART_SIZE (SZ_2M + SZ_1M) - -static struct mtd_partition ts72xx_nand_parts[] = { - { - .name = "TS-BOOTROM", - .offset = 0, - .size = TS72XX_BOOTROM_PART_SIZE, - .mask_flags = MTD_WRITEABLE, /* force read-only */ - }, { - .name = "Linux", - .offset = MTDPART_OFS_RETAIN, - .size = TS72XX_REDBOOT_PART_SIZE, - /* leave so much for last partition */ - }, { - .name = "RedBoot", - .offset = MTDPART_OFS_APPEND, - .size = MTDPART_SIZ_FULL, - .mask_flags = MTD_WRITEABLE, /* force read-only */ - }, -}; - -static struct platform_nand_data ts72xx_nand_data = { - .chip = { - .nr_chips = 1, - .chip_offset = 0, - .chip_delay = 15, - }, - .ctrl = { - .cmd_ctrl = ts72xx_nand_hwcontrol, - .dev_ready = ts72xx_nand_device_ready, - }, -}; - -static struct resource ts72xx_nand_resource[] = { - { - .start = 0, /* filled in later */ - .end = 0, /* filled in later */ - .flags = IORESOURCE_MEM, - }, -}; - -static struct platform_device ts72xx_nand_flash = { - .name = "gen_nand", - .id = -1, - .dev.platform_data = &ts72xx_nand_data, - .resource = ts72xx_nand_resource, - .num_resources = ARRAY_SIZE(ts72xx_nand_resource), -}; - -static void __init ts72xx_register_flash(struct mtd_partition *parts, int n, - resource_size_t start) -{ - /* - * TS7200 has NOR flash all other TS72xx board have NAND flash. - */ - if (board_is_ts7200()) { - ep93xx_register_flash(2, EP93XX_CS6_PHYS_BASE, SZ_16M); - } else { - ts72xx_nand_resource[0].start = start; - ts72xx_nand_resource[0].end = start + SZ_16M - 1; - - ts72xx_nand_data.chip.partitions = parts; - ts72xx_nand_data.chip.nr_partitions = n; - - platform_device_register(&ts72xx_nand_flash); - } -} - -/************************************************************************* - * RTC M48T86 - *************************************************************************/ -#define TS72XX_RTC_INDEX_PHYS_BASE (EP93XX_CS1_PHYS_BASE + 0x00800000) -#define TS72XX_RTC_DATA_PHYS_BASE (EP93XX_CS1_PHYS_BASE + 0x01700000) - -static struct resource ts72xx_rtc_resources[] = { - DEFINE_RES_MEM(TS72XX_RTC_INDEX_PHYS_BASE, 0x01), - DEFINE_RES_MEM(TS72XX_RTC_DATA_PHYS_BASE, 0x01), -}; - -static struct platform_device ts72xx_rtc_device = { - .name = "rtc-m48t86", - .id = -1, - .resource = ts72xx_rtc_resources, - .num_resources = ARRAY_SIZE(ts72xx_rtc_resources), -}; - -/************************************************************************* - * Watchdog (in CPLD) - *************************************************************************/ -#define TS72XX_WDT_CONTROL_PHYS_BASE (EP93XX_CS2_PHYS_BASE + 0x03800000) -#define TS72XX_WDT_FEED_PHYS_BASE (EP93XX_CS2_PHYS_BASE + 0x03c00000) - -static struct resource ts72xx_wdt_resources[] = { - DEFINE_RES_MEM(TS72XX_WDT_CONTROL_PHYS_BASE, 0x01), - DEFINE_RES_MEM(TS72XX_WDT_FEED_PHYS_BASE, 0x01), -}; - -static struct platform_device ts72xx_wdt_device = { - .name = "ts72xx-wdt", - .id = -1, - .resource = ts72xx_wdt_resources, - .num_resources = ARRAY_SIZE(ts72xx_wdt_resources), -}; - -/************************************************************************* - * ETH - *************************************************************************/ -static struct ep93xx_eth_data __initdata ts72xx_eth_data = { - .phy_id = 1, -}; - -/************************************************************************* - * SPI SD/MMC host - *************************************************************************/ -#define BK3_EN_SDCARD_PHYS_BASE 0x12400000 -#define BK3_EN_SDCARD_PWR 0x0 -#define BK3_DIS_SDCARD_PWR 0x0C -static void bk3_mmc_spi_setpower(struct device *dev, unsigned int vdd) -{ - void __iomem *pwr_sd = ioremap(BK3_EN_SDCARD_PHYS_BASE, SZ_4K); - - if (!pwr_sd) { - pr_err("Failed to enable SD card power!"); - return; - } - - pr_debug("%s: SD card pwr %s VDD:0x%x\n", __func__, - !!vdd ? "ON" : "OFF", vdd); - - if (!!vdd) - __raw_writeb(BK3_EN_SDCARD_PWR, pwr_sd); - else - __raw_writeb(BK3_DIS_SDCARD_PWR, pwr_sd); - - iounmap(pwr_sd); -} - -static struct mmc_spi_platform_data bk3_spi_mmc_data = { - .detect_delay = 500, - .powerup_msecs = 100, - .ocr_mask = MMC_VDD_32_33 | MMC_VDD_33_34, - .caps = MMC_CAP_NONREMOVABLE, - .setpower = bk3_mmc_spi_setpower, -}; - -/************************************************************************* - * SPI Bus - SD card access - *************************************************************************/ -static struct spi_board_info bk3_spi_board_info[] __initdata = { - { - .modalias = "mmc_spi", - .platform_data = &bk3_spi_mmc_data, - .max_speed_hz = 7.4E6, - .bus_num = 0, - .chip_select = 0, - .mode = SPI_MODE_0, - }, -}; - -/* - * This is a stub -> the FGPIO[3] pin is not connected on the schematic - * The all work is performed automatically by !SPI_FRAME (SFRM1) and - * goes through CPLD - */ -static struct gpiod_lookup_table bk3_spi_cs_gpio_table = { - .dev_id = "spi0", - .table = { - GPIO_LOOKUP("gpio-ep93xx.5", 3, "cs", GPIO_ACTIVE_LOW), - { }, - }, -}; - -static struct ep93xx_spi_info bk3_spi_master __initdata = { - .use_dma = 1, -}; - -/************************************************************************* - * TS72XX support code - *************************************************************************/ -#if IS_ENABLED(CONFIG_FPGA_MGR_TS73XX) - -/* Relative to EP93XX_CS1_PHYS_BASE */ -#define TS73XX_FPGA_LOADER_BASE 0x03c00000 - -static struct resource ts73xx_fpga_resources[] = { - { - .start = EP93XX_CS1_PHYS_BASE + TS73XX_FPGA_LOADER_BASE, - .end = EP93XX_CS1_PHYS_BASE + TS73XX_FPGA_LOADER_BASE + 1, - .flags = IORESOURCE_MEM, - }, -}; - -static struct platform_device ts73xx_fpga_device = { - .name = "ts73xx-fpga-mgr", - .id = -1, - .resource = ts73xx_fpga_resources, - .num_resources = ARRAY_SIZE(ts73xx_fpga_resources), -}; - -#endif - -/************************************************************************* - * SPI Bus - *************************************************************************/ -static struct spi_board_info ts72xx_spi_devices[] __initdata = { - { - .modalias = "tmp122", - .max_speed_hz = 2 * 1000 * 1000, - .bus_num = 0, - .chip_select = 0, - }, -}; - -static struct gpiod_lookup_table ts72xx_spi_cs_gpio_table = { - .dev_id = "spi0", - .table = { - /* DIO_17 */ - GPIO_LOOKUP("gpio-ep93xx.5", 2, "cs", GPIO_ACTIVE_LOW), - { }, - }, -}; - -static struct ep93xx_spi_info ts72xx_spi_info __initdata = { - /* Intentionally left blank */ -}; - -static void __init ts72xx_init_machine(void) -{ - ep93xx_init_devices(); - ts72xx_register_flash(ts72xx_nand_parts, ARRAY_SIZE(ts72xx_nand_parts), - is_ts9420_installed() ? - EP93XX_CS7_PHYS_BASE : EP93XX_CS6_PHYS_BASE); - platform_device_register(&ts72xx_rtc_device); - platform_device_register(&ts72xx_wdt_device); - - ep93xx_register_eth(&ts72xx_eth_data, 1); -#if IS_ENABLED(CONFIG_FPGA_MGR_TS73XX) - if (board_is_ts7300()) - platform_device_register(&ts73xx_fpga_device); -#endif - gpiod_add_lookup_table(&ts72xx_spi_cs_gpio_table); - ep93xx_register_spi(&ts72xx_spi_info, ts72xx_spi_devices, - ARRAY_SIZE(ts72xx_spi_devices)); -} - -MACHINE_START(TS72XX, "Technologic Systems TS-72xx SBC") - /* Maintainer: Lennert Buytenhek */ - .atag_offset = 0x100, - .nr_irqs = NR_EP93XX_IRQS, - .map_io = ts72xx_map_io, - .init_irq = ep93xx_init_irq, - .init_time = ep93xx_timer_init, - .init_machine = ts72xx_init_machine, - .restart = ep93xx_restart, -MACHINE_END - -/************************************************************************* - * EP93xx I2S audio peripheral handling - *************************************************************************/ -static struct resource ep93xx_i2s_resource[] = { - DEFINE_RES_MEM(EP93XX_I2S_PHYS_BASE, 0x100), - DEFINE_RES_IRQ_NAMED(IRQ_EP93XX_SAI, "spilink i2s slave"), -}; - -static struct platform_device ep93xx_i2s_device = { - .name = "ep93xx-spilink-i2s", - .id = -1, - .num_resources = ARRAY_SIZE(ep93xx_i2s_resource), - .resource = ep93xx_i2s_resource, -}; - -/************************************************************************* - * BK3 support code - *************************************************************************/ -static struct mtd_partition bk3_nand_parts[] = { - { - .name = "System", - .offset = 0x00000000, - .size = 0x01e00000, - }, { - .name = "Data", - .offset = 0x01e00000, - .size = 0x05f20000 - }, { - .name = "RedBoot", - .offset = 0x07d20000, - .size = 0x002e0000, - .mask_flags = MTD_WRITEABLE, /* force RO */ - }, -}; - -static void __init bk3_init_machine(void) -{ - ep93xx_init_devices(); - - ts72xx_register_flash(bk3_nand_parts, ARRAY_SIZE(bk3_nand_parts), - EP93XX_CS6_PHYS_BASE); - - ep93xx_register_eth(&ts72xx_eth_data, 1); - - gpiod_add_lookup_table(&bk3_spi_cs_gpio_table); - ep93xx_register_spi(&bk3_spi_master, bk3_spi_board_info, - ARRAY_SIZE(bk3_spi_board_info)); - - /* Configure ep93xx's I2S to use AC97 pins */ - ep93xx_devcfg_set_bits(EP93XX_SYSCON_DEVCFG_I2SONAC97); - platform_device_register(&ep93xx_i2s_device); -} - -MACHINE_START(BK3, "Liebherr controller BK3.1") - /* Maintainer: Lukasz Majewski */ - .atag_offset = 0x100, - .nr_irqs = NR_EP93XX_IRQS, - .map_io = ts72xx_map_io, - .init_irq = ep93xx_init_irq, - .init_time = ep93xx_timer_init, - .init_machine = bk3_init_machine, - .restart = ep93xx_restart, -MACHINE_END diff --git a/arch/arm/mach-ep93xx/ts72xx.h b/arch/arm/mach-ep93xx/ts72xx.h deleted file mode 100644 index 00b4941d29c9..000000000000 --- a/arch/arm/mach-ep93xx/ts72xx.h +++ /dev/null @@ -1,94 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * arch/arm/mach-ep93xx/include/mach/ts72xx.h - */ - -/* - * TS72xx memory map: - * - * virt phys size - * febff000 22000000 4K model number register (bits 0-2) - * febfe000 22400000 4K options register - * febfd000 22800000 4K options register #2 - * febfc000 23400000 4K CPLD version register - */ - -#ifndef __TS72XX_H_ -#define __TS72XX_H_ - -#define TS72XX_MODEL_PHYS_BASE 0x22000000 -#define TS72XX_MODEL_VIRT_BASE IOMEM(0xfebff000) -#define TS72XX_MODEL_SIZE 0x00001000 - -#define TS72XX_MODEL_TS7200 0x00 -#define TS72XX_MODEL_TS7250 0x01 -#define TS72XX_MODEL_TS7260 0x02 -#define TS72XX_MODEL_TS7300 0x03 -#define TS72XX_MODEL_TS7400 0x04 -#define TS72XX_MODEL_MASK 0x07 - - -#define TS72XX_OPTIONS_PHYS_BASE 0x22400000 -#define TS72XX_OPTIONS_VIRT_BASE IOMEM(0xfebfe000) -#define TS72XX_OPTIONS_SIZE 0x00001000 - -#define TS72XX_OPTIONS_COM2_RS485 0x02 -#define TS72XX_OPTIONS_MAX197 0x01 - - -#define TS72XX_OPTIONS2_PHYS_BASE 0x22800000 -#define TS72XX_OPTIONS2_VIRT_BASE IOMEM(0xfebfd000) -#define TS72XX_OPTIONS2_SIZE 0x00001000 - -#define TS72XX_OPTIONS2_TS9420 0x04 -#define TS72XX_OPTIONS2_TS9420_BOOT 0x02 - -#define TS72XX_CPLDVER_PHYS_BASE 0x23400000 -#define TS72XX_CPLDVER_VIRT_BASE IOMEM(0xfebfc000) -#define TS72XX_CPLDVER_SIZE 0x00001000 - -#ifndef __ASSEMBLY__ - -static inline int ts72xx_model(void) -{ - return __raw_readb(TS72XX_MODEL_VIRT_BASE) & TS72XX_MODEL_MASK; -} - -static inline int board_is_ts7200(void) -{ - return ts72xx_model() == TS72XX_MODEL_TS7200; -} - -static inline int board_is_ts7250(void) -{ - return ts72xx_model() == TS72XX_MODEL_TS7250; -} - -static inline int board_is_ts7260(void) -{ - return ts72xx_model() == TS72XX_MODEL_TS7260; -} - -static inline int board_is_ts7300(void) -{ - return ts72xx_model() == TS72XX_MODEL_TS7300; -} - -static inline int board_is_ts7400(void) -{ - return ts72xx_model() == TS72XX_MODEL_TS7400; -} - -static inline int is_max197_installed(void) -{ - return !!(__raw_readb(TS72XX_OPTIONS_VIRT_BASE) & - TS72XX_OPTIONS_MAX197); -} - -static inline int is_ts9420_installed(void) -{ - return !!(__raw_readb(TS72XX_OPTIONS2_VIRT_BASE) & - TS72XX_OPTIONS2_TS9420); -} -#endif -#endif /* __TS72XX_H_ */ diff --git a/arch/arm/mach-ep93xx/vision_ep9307.c b/arch/arm/mach-ep93xx/vision_ep9307.c deleted file mode 100644 index b3087b8eed3f..000000000000 --- a/arch/arm/mach-ep93xx/vision_ep9307.c +++ /dev/null @@ -1,321 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * arch/arm/mach-ep93xx/vision_ep9307.c - * Vision Engraving Systems EP9307 SoM support. - * - * Copyright (C) 2008-2011 Vision Engraving Systems - * H Hartley Sweeten - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include - -#include "hardware.h" -#include -#include -#include "gpio-ep93xx.h" - -#include -#include -#include - -#include "soc.h" - -/************************************************************************* - * Static I/O mappings for the FPGA - *************************************************************************/ -#define VISION_PHYS_BASE EP93XX_CS7_PHYS_BASE -#define VISION_VIRT_BASE 0xfebff000 - -static struct map_desc vision_io_desc[] __initdata = { - { - .virtual = VISION_VIRT_BASE, - .pfn = __phys_to_pfn(VISION_PHYS_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, -}; - -static void __init vision_map_io(void) -{ - ep93xx_map_io(); - - iotable_init(vision_io_desc, ARRAY_SIZE(vision_io_desc)); -} - -/************************************************************************* - * Ethernet - *************************************************************************/ -static struct ep93xx_eth_data vision_eth_data __initdata = { - .phy_id = 1, -}; - -/************************************************************************* - * Framebuffer - *************************************************************************/ -#define VISION_LCD_ENABLE EP93XX_GPIO_LINE_EGPIO1 - -static int vision_lcd_setup(struct platform_device *pdev) -{ - int err; - - err = gpio_request_one(VISION_LCD_ENABLE, GPIOF_INIT_HIGH, - dev_name(&pdev->dev)); - if (err) - return err; - - ep93xx_devcfg_clear_bits(EP93XX_SYSCON_DEVCFG_RAS | - EP93XX_SYSCON_DEVCFG_RASONP3 | - EP93XX_SYSCON_DEVCFG_EXVC); - - return 0; -} - -static void vision_lcd_teardown(struct platform_device *pdev) -{ - gpio_free(VISION_LCD_ENABLE); -} - -static void vision_lcd_blank(int blank_mode, struct fb_info *info) -{ - if (blank_mode) - gpio_set_value(VISION_LCD_ENABLE, 0); - else - gpio_set_value(VISION_LCD_ENABLE, 1); -} - -static struct ep93xxfb_mach_info ep93xxfb_info __initdata = { - .flags = EP93XXFB_USE_SDCSN0 | EP93XXFB_PCLK_FALLING, - .setup = vision_lcd_setup, - .teardown = vision_lcd_teardown, - .blank = vision_lcd_blank, -}; - - -/************************************************************************* - * GPIO Expanders - *************************************************************************/ -#define PCA9539_74_GPIO_BASE (EP93XX_GPIO_LINE_MAX + 1) -#define PCA9539_75_GPIO_BASE (PCA9539_74_GPIO_BASE + 16) -#define PCA9539_76_GPIO_BASE (PCA9539_75_GPIO_BASE + 16) -#define PCA9539_77_GPIO_BASE (PCA9539_76_GPIO_BASE + 16) - -static struct pca953x_platform_data pca953x_74_gpio_data = { - .gpio_base = PCA9539_74_GPIO_BASE, - .irq_base = EP93XX_BOARD_IRQ(0), -}; - -static struct pca953x_platform_data pca953x_75_gpio_data = { - .gpio_base = PCA9539_75_GPIO_BASE, - .irq_base = -1, -}; - -static struct pca953x_platform_data pca953x_76_gpio_data = { - .gpio_base = PCA9539_76_GPIO_BASE, - .irq_base = -1, -}; - -static struct pca953x_platform_data pca953x_77_gpio_data = { - .gpio_base = PCA9539_77_GPIO_BASE, - .irq_base = -1, -}; - -/************************************************************************* - * I2C Bus - *************************************************************************/ - -static struct i2c_board_info vision_i2c_info[] __initdata = { - { - I2C_BOARD_INFO("isl1208", 0x6f), - .irq = IRQ_EP93XX_EXT1, - }, { - I2C_BOARD_INFO("pca9539", 0x74), - .platform_data = &pca953x_74_gpio_data, - }, { - I2C_BOARD_INFO("pca9539", 0x75), - .platform_data = &pca953x_75_gpio_data, - }, { - I2C_BOARD_INFO("pca9539", 0x76), - .platform_data = &pca953x_76_gpio_data, - }, { - I2C_BOARD_INFO("pca9539", 0x77), - .platform_data = &pca953x_77_gpio_data, - }, -}; - -/************************************************************************* - * SPI CS4271 Audio Codec - *************************************************************************/ -static struct cs4271_platform_data vision_cs4271_data = { - /* Intentionally left blank */ -}; - -/************************************************************************* - * SPI Flash - *************************************************************************/ -static struct mtd_partition vision_spi_flash_partitions[] = { - { - .name = "SPI bootstrap", - .offset = 0, - .size = SZ_4K, - }, { - .name = "Bootstrap config", - .offset = MTDPART_OFS_APPEND, - .size = SZ_4K, - }, { - .name = "System config", - .offset = MTDPART_OFS_APPEND, - .size = MTDPART_SIZ_FULL, - }, -}; - -static struct flash_platform_data vision_spi_flash_data = { - .name = "SPI Flash", - .parts = vision_spi_flash_partitions, - .nr_parts = ARRAY_SIZE(vision_spi_flash_partitions), -}; - -/************************************************************************* - * SPI SD/MMC host - *************************************************************************/ -static struct mmc_spi_platform_data vision_spi_mmc_data = { - .detect_delay = 100, - .powerup_msecs = 100, - .ocr_mask = MMC_VDD_32_33 | MMC_VDD_33_34, - .caps2 = MMC_CAP2_RO_ACTIVE_HIGH, -}; - -static struct gpiod_lookup_table vision_spi_mmc_gpio_table = { - .dev_id = "mmc_spi.2", /* "mmc_spi @ CS2 */ - .table = { - /* Card detect */ - GPIO_LOOKUP_IDX("gpio-ep93xx.1", 7, NULL, 0, GPIO_ACTIVE_LOW), - /* Write protect */ - GPIO_LOOKUP_IDX("gpio-ep93xx.5", 0, NULL, 1, GPIO_ACTIVE_HIGH), - { }, - }, -}; - -/************************************************************************* - * SPI Bus - *************************************************************************/ -static struct spi_board_info vision_spi_board_info[] __initdata = { - { - .modalias = "cs4271", - .platform_data = &vision_cs4271_data, - .max_speed_hz = 6000000, - .bus_num = 0, - .chip_select = 0, - .mode = SPI_MODE_3, - }, { - .modalias = "sst25l", - .platform_data = &vision_spi_flash_data, - .max_speed_hz = 20000000, - .bus_num = 0, - .chip_select = 1, - .mode = SPI_MODE_3, - }, { - .modalias = "mmc_spi", - .platform_data = &vision_spi_mmc_data, - .max_speed_hz = 20000000, - .bus_num = 0, - .chip_select = 2, - .mode = SPI_MODE_3, - }, -}; - -static struct gpiod_lookup_table vision_spi_cs4271_gpio_table = { - .dev_id = "spi0.0", /* cs4271 @ CS0 */ - .table = { - /* RESET */ - GPIO_LOOKUP_IDX("H", 2, NULL, 0, GPIO_ACTIVE_LOW), - { }, - }, -}; - -static struct gpiod_lookup_table vision_spi_cs_gpio_table = { - .dev_id = "spi0", - .table = { - GPIO_LOOKUP_IDX("gpio-ep93xx.0", 6, "cs", 0, GPIO_ACTIVE_LOW), - GPIO_LOOKUP_IDX("gpio-ep93xx.0", 7, "cs", 1, GPIO_ACTIVE_LOW), - GPIO_LOOKUP_IDX("gpio-ep93xx.6", 2, "cs", 2, GPIO_ACTIVE_LOW), - { }, - }, -}; - -static struct ep93xx_spi_info vision_spi_master __initdata = { - .use_dma = 1, -}; - -/************************************************************************* - * I2S Audio - *************************************************************************/ -static struct platform_device vision_audio_device = { - .name = "edb93xx-audio", - .id = -1, -}; - -static void __init vision_register_i2s(void) -{ - ep93xx_register_i2s(); - platform_device_register(&vision_audio_device); -} - -/************************************************************************* - * Machine Initialization - *************************************************************************/ -static void __init vision_init_machine(void) -{ - ep93xx_init_devices(); - ep93xx_register_flash(2, EP93XX_CS6_PHYS_BASE, SZ_64M); - ep93xx_register_eth(&vision_eth_data, 1); - ep93xx_register_fb(&ep93xxfb_info); - ep93xx_register_pwm(1, 0); - - /* - * Request the gpio expander's interrupt gpio line now to prevent - * the kernel from doing a WARN in gpiolib:gpio_ensure_requested(). - */ - if (gpio_request_one(EP93XX_GPIO_LINE_F(7), GPIOF_DIR_IN, - "pca9539:74")) - pr_warn("cannot request interrupt gpio for pca9539:74\n"); - - vision_i2c_info[1].irq = gpio_to_irq(EP93XX_GPIO_LINE_F(7)); - - ep93xx_register_i2c(vision_i2c_info, - ARRAY_SIZE(vision_i2c_info)); - gpiod_add_lookup_table(&vision_spi_cs4271_gpio_table); - gpiod_add_lookup_table(&vision_spi_mmc_gpio_table); - gpiod_add_lookup_table(&vision_spi_cs_gpio_table); - ep93xx_register_spi(&vision_spi_master, vision_spi_board_info, - ARRAY_SIZE(vision_spi_board_info)); - vision_register_i2s(); -} - -MACHINE_START(VISION_EP9307, "Vision Engraving Systems EP9307") - /* Maintainer: H Hartley Sweeten */ - .atag_offset = 0x100, - .nr_irqs = NR_EP93XX_IRQS + EP93XX_BOARD_IRQS, - .map_io = vision_map_io, - .init_irq = ep93xx_init_irq, - .init_time = ep93xx_timer_init, - .init_machine = vision_init_machine, - .restart = ep93xx_restart, -MACHINE_END diff --git a/include/linux/platform_data/spi-ep93xx.h b/include/linux/platform_data/spi-ep93xx.h deleted file mode 100644 index b439f2a896e0..000000000000 --- a/include/linux/platform_data/spi-ep93xx.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ASM_MACH_EP93XX_SPI_H -#define __ASM_MACH_EP93XX_SPI_H - -struct spi_device; - -/** - * struct ep93xx_spi_info - EP93xx specific SPI descriptor - * @use_dma: use DMA for the transfers - */ -struct ep93xx_spi_info { - bool use_dma; -}; - -#endif /* __ASM_MACH_EP93XX_SPI_H */ -- cgit v1.2.3 From 43528a72526152f17a918973b3b8b6f383b90f98 Mon Sep 17 00:00:00 2001 From: Nikita Shubin Date: Mon, 9 Sep 2024 11:11:01 +0300 Subject: ARM: ep93xx: soc: drop defines Remove unnecessary defines, as we dropped board files. Signed-off-by: Nikita Shubin Tested-by: Alexander Sverdlin Acked-by: Vinod Koul Signed-off-by: Arnd Bergmann --- include/linux/platform_data/eth-ep93xx.h | 10 --------- include/linux/platform_data/keypad-ep93xx.h | 32 ----------------------------- include/linux/soc/cirrus/ep93xx.h | 13 ------------ 3 files changed, 55 deletions(-) delete mode 100644 include/linux/platform_data/eth-ep93xx.h delete mode 100644 include/linux/platform_data/keypad-ep93xx.h (limited to 'include/linux') diff --git a/include/linux/platform_data/eth-ep93xx.h b/include/linux/platform_data/eth-ep93xx.h deleted file mode 100644 index 8eef637a804d..000000000000 --- a/include/linux/platform_data/eth-ep93xx.h +++ /dev/null @@ -1,10 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_PLATFORM_DATA_ETH_EP93XX -#define _LINUX_PLATFORM_DATA_ETH_EP93XX - -struct ep93xx_eth_data { - unsigned char dev_addr[6]; - unsigned char phy_id; -}; - -#endif diff --git a/include/linux/platform_data/keypad-ep93xx.h b/include/linux/platform_data/keypad-ep93xx.h deleted file mode 100644 index 3054fced8509..000000000000 --- a/include/linux/platform_data/keypad-ep93xx.h +++ /dev/null @@ -1,32 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __KEYPAD_EP93XX_H -#define __KEYPAD_EP93XX_H - -struct matrix_keymap_data; - -/* flags for the ep93xx_keypad driver */ -#define EP93XX_KEYPAD_DISABLE_3_KEY (1<<0) /* disable 3-key reset */ -#define EP93XX_KEYPAD_DIAG_MODE (1<<1) /* diagnostic mode */ -#define EP93XX_KEYPAD_BACK_DRIVE (1<<2) /* back driving mode */ -#define EP93XX_KEYPAD_TEST_MODE (1<<3) /* scan only column 0 */ -#define EP93XX_KEYPAD_AUTOREPEAT (1<<4) /* enable key autorepeat */ - -/** - * struct ep93xx_keypad_platform_data - platform specific device structure - * @keymap_data: pointer to &matrix_keymap_data - * @debounce: debounce start count; terminal count is 0xff - * @prescale: row/column counter pre-scaler load value - * @flags: see above - */ -struct ep93xx_keypad_platform_data { - struct matrix_keymap_data *keymap_data; - unsigned int debounce; - unsigned int prescale; - unsigned int flags; - unsigned int clk_rate; -}; - -#define EP93XX_MATRIX_ROWS (8) -#define EP93XX_MATRIX_COLS (8) - -#endif /* __KEYPAD_EP93XX_H */ diff --git a/include/linux/soc/cirrus/ep93xx.h b/include/linux/soc/cirrus/ep93xx.h index 142c33a2d7db..3e6cf2b25a97 100644 --- a/include/linux/soc/cirrus/ep93xx.h +++ b/include/linux/soc/cirrus/ep93xx.h @@ -2,7 +2,6 @@ #ifndef _SOC_EP93XX_H #define _SOC_EP93XX_H -struct platform_device; struct regmap; struct spinlock_t; @@ -36,16 +35,4 @@ struct ep93xx_regmap_adev { #define to_ep93xx_regmap_adev(_adev) \ container_of((_adev), struct ep93xx_regmap_adev, adev) -#ifdef CONFIG_ARCH_EP93XX -int ep93xx_i2s_acquire(void); -void ep93xx_i2s_release(void); -unsigned int ep93xx_chip_revision(void); - -#else -static inline int ep93xx_i2s_acquire(void) { return 0; } -static inline void ep93xx_i2s_release(void) {} -static inline unsigned int ep93xx_chip_revision(void) { return 0; } - -#endif - #endif -- cgit v1.2.3 From a015b1828653b591de0aa5303c0dbc4235935f94 Mon Sep 17 00:00:00 2001 From: Nikita Shubin Date: Mon, 9 Sep 2024 11:11:03 +0300 Subject: dmaengine: cirrus: remove platform code Remove DMA platform header, from now on we use device tree for DMA clients. Acked-by: Vinod Koul Signed-off-by: Nikita Shubin Tested-by: Alexander Sverdlin Signed-off-by: Arnd Bergmann --- drivers/dma/ep93xx_dma.c | 48 ++++++++++++++- include/linux/platform_data/dma-ep93xx.h | 100 ------------------------------- 2 files changed, 46 insertions(+), 102 deletions(-) delete mode 100644 include/linux/platform_data/dma-ep93xx.h (limited to 'include/linux') diff --git a/drivers/dma/ep93xx_dma.c b/drivers/dma/ep93xx_dma.c index 17c8e2badee2..43c4241af7f5 100644 --- a/drivers/dma/ep93xx_dma.c +++ b/drivers/dma/ep93xx_dma.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -25,8 +26,6 @@ #include #include -#include - #include "dmaengine.h" /* M2P registers */ @@ -106,6 +105,26 @@ #define DMA_MAX_CHAN_BYTES 0xffff #define DMA_MAX_CHAN_DESCRIPTORS 32 +/* + * M2P channels. + * + * Note that these values are also directly used for setting the PPALLOC + * register. + */ +#define EP93XX_DMA_I2S1 0 +#define EP93XX_DMA_I2S2 1 +#define EP93XX_DMA_AAC1 2 +#define EP93XX_DMA_AAC2 3 +#define EP93XX_DMA_AAC3 4 +#define EP93XX_DMA_I2S3 5 +#define EP93XX_DMA_UART1 6 +#define EP93XX_DMA_UART2 7 +#define EP93XX_DMA_UART3 8 +#define EP93XX_DMA_IRDA 9 +/* M2M channels */ +#define EP93XX_DMA_SSP 10 +#define EP93XX_DMA_IDE 11 + enum ep93xx_dma_type { M2P_DMA, M2M_DMA, @@ -242,6 +261,31 @@ static struct ep93xx_dma_chan *to_ep93xx_dma_chan(struct dma_chan *chan) return container_of(chan, struct ep93xx_dma_chan, chan); } +static inline bool ep93xx_dma_chan_is_m2p(struct dma_chan *chan) +{ + if (device_is_compatible(chan->device->dev, "cirrus,ep9301-dma-m2p")) + return true; + + return !strcmp(dev_name(chan->device->dev), "ep93xx-dma-m2p"); +} + +/* + * ep93xx_dma_chan_direction - returns direction the channel can be used + * + * This function can be used in filter functions to find out whether the + * channel supports given DMA direction. Only M2P channels have such + * limitation, for M2M channels the direction is configurable. + */ +static inline enum dma_transfer_direction +ep93xx_dma_chan_direction(struct dma_chan *chan) +{ + if (!ep93xx_dma_chan_is_m2p(chan)) + return DMA_TRANS_NONE; + + /* even channels are for TX, odd for RX */ + return (chan->chan_id % 2 == 0) ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM; +} + /** * ep93xx_dma_set_active - set new active descriptor chain * @edmac: channel diff --git a/include/linux/platform_data/dma-ep93xx.h b/include/linux/platform_data/dma-ep93xx.h deleted file mode 100644 index 9ec5cdd5a1eb..000000000000 --- a/include/linux/platform_data/dma-ep93xx.h +++ /dev/null @@ -1,100 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ASM_ARCH_DMA_H -#define __ASM_ARCH_DMA_H - -#include -#include -#include -#include -#include -#include - -/* - * M2P channels. - * - * Note that these values are also directly used for setting the PPALLOC - * register. - */ -#define EP93XX_DMA_I2S1 0 -#define EP93XX_DMA_I2S2 1 -#define EP93XX_DMA_AAC1 2 -#define EP93XX_DMA_AAC2 3 -#define EP93XX_DMA_AAC3 4 -#define EP93XX_DMA_I2S3 5 -#define EP93XX_DMA_UART1 6 -#define EP93XX_DMA_UART2 7 -#define EP93XX_DMA_UART3 8 -#define EP93XX_DMA_IRDA 9 -/* M2M channels */ -#define EP93XX_DMA_SSP 10 -#define EP93XX_DMA_IDE 11 - -/** - * struct ep93xx_dma_data - configuration data for the EP93xx dmaengine - * @port: peripheral which is requesting the channel - * @direction: TX/RX channel - * @name: optional name for the channel, this is displayed in /proc/interrupts - * - * This information is passed as private channel parameter in a filter - * function. Note that this is only needed for slave/cyclic channels. For - * memcpy channels %NULL data should be passed. - */ -struct ep93xx_dma_data { - int port; - enum dma_transfer_direction direction; - const char *name; -}; - -/** - * struct ep93xx_dma_chan_data - platform specific data for a DMA channel - * @name: name of the channel, used for getting the right clock for the channel - * @base: mapped registers - * @irq: interrupt number used by this channel - */ -struct ep93xx_dma_chan_data { - const char *name; - void __iomem *base; - int irq; -}; - -/** - * struct ep93xx_dma_platform_data - platform data for the dmaengine driver - * @channels: array of channels which are passed to the driver - * @num_channels: number of channels in the array - * - * This structure is passed to the DMA engine driver via platform data. For - * M2P channels, contract is that even channels are for TX and odd for RX. - * There is no requirement for the M2M channels. - */ -struct ep93xx_dma_platform_data { - struct ep93xx_dma_chan_data *channels; - size_t num_channels; -}; - -static inline bool ep93xx_dma_chan_is_m2p(struct dma_chan *chan) -{ - if (device_is_compatible(chan->device->dev, "cirrus,ep9301-dma-m2p")) - return true; - - return !strcmp(dev_name(chan->device->dev), "ep93xx-dma-m2p"); -} - -/** - * ep93xx_dma_chan_direction - returns direction the channel can be used - * @chan: channel - * - * This function can be used in filter functions to find out whether the - * channel supports given DMA direction. Only M2P channels have such - * limitation, for M2M channels the direction is configurable. - */ -static inline enum dma_transfer_direction -ep93xx_dma_chan_direction(struct dma_chan *chan) -{ - if (!ep93xx_dma_chan_is_m2p(chan)) - return DMA_TRANS_NONE; - - /* even channels are for TX, odd for RX */ - return (chan->chan_id % 2 == 0) ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM; -} - -#endif /* __ASM_ARCH_DMA_H */ -- cgit v1.2.3 From 433d7ce2d86d21274838c9e8c796f4232cd13cdb Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 6 Aug 2024 15:38:12 -0700 Subject: security,bpf: constify struct path in bpf_token_create() LSM hook There is no reason why struct path pointer shouldn't be const-qualified when being passed into bpf_token_create() LSM hook. Add that const. Acked-by: Paul Moore (LSM/SELinux) Suggested-by: Al Viro Signed-off-by: Andrii Nakryiko --- include/linux/lsm_hook_defs.h | 2 +- include/linux/security.h | 4 ++-- security/security.c | 2 +- security/selinux/hooks.c | 2 +- 4 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 855db460e08b..462b55378241 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -431,7 +431,7 @@ LSM_HOOK(int, 0, bpf_prog_load, struct bpf_prog *prog, union bpf_attr *attr, struct bpf_token *token) LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free, struct bpf_prog *prog) LSM_HOOK(int, 0, bpf_token_create, struct bpf_token *token, union bpf_attr *attr, - struct path *path) + const struct path *path) LSM_HOOK(void, LSM_RET_VOID, bpf_token_free, struct bpf_token *token) LSM_HOOK(int, 0, bpf_token_cmd, const struct bpf_token *token, enum bpf_cmd cmd) LSM_HOOK(int, 0, bpf_token_capable, const struct bpf_token *token, int cap) diff --git a/include/linux/security.h b/include/linux/security.h index 1390f1efb4f0..31523a2c71c4 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -2137,7 +2137,7 @@ extern int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, struct bpf_token *token); extern void security_bpf_prog_free(struct bpf_prog *prog); extern int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, - struct path *path); + const struct path *path); extern void security_bpf_token_free(struct bpf_token *token); extern int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd); extern int security_bpf_token_capable(const struct bpf_token *token, int cap); @@ -2177,7 +2177,7 @@ static inline void security_bpf_prog_free(struct bpf_prog *prog) { } static inline int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, - struct path *path) + const struct path *path) { return 0; } diff --git a/security/security.c b/security/security.c index 8cee5b6c6e6d..d8d0b67ced25 100644 --- a/security/security.c +++ b/security/security.c @@ -5510,7 +5510,7 @@ int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, * Return: Returns 0 on success, error on failure. */ int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, - struct path *path) + const struct path *path) { return call_int_hook(bpf_token_create, token, attr, path); } diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 55c78c318ccd..0eec141a8f37 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -6965,7 +6965,7 @@ static void selinux_bpf_prog_free(struct bpf_prog *prog) } static int selinux_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, - struct path *path) + const struct path *path) { struct bpf_security_struct *bpfsec; -- cgit v1.2.3 From da2f660b3ba1be33310452959ab72d1d7ce39350 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Wed, 11 Sep 2024 13:17:46 -0700 Subject: net/mlx5: fs, make get_root_namespace API function As preparation for HW Steering support, where the function get_root_namespace() is needed to get root FDB, make it an API function and rename it to mlx5_get_root_namespace(). Reviewed-by: Yevgeny Kliteynik Signed-off-by: Moshe Shemesh Signed-off-by: Saeed Mahameed Reviewed-by: Jacob Keller Reviewed-by: Kalesh AP Link: https://patch.msgid.link/20240911201757.1505453-5-saeed@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 16 ++++++++-------- include/linux/mlx5/fs.h | 3 +++ 2 files changed, 11 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index a47d6419160d..e32725487702 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -3590,8 +3590,8 @@ out: } EXPORT_SYMBOL(mlx5_fs_remove_rx_underlay_qpn); -static struct mlx5_flow_root_namespace -*get_root_namespace(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type ns_type) +struct mlx5_flow_root_namespace * +mlx5_get_root_namespace(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type ns_type) { struct mlx5_flow_namespace *ns; @@ -3614,7 +3614,7 @@ struct mlx5_modify_hdr *mlx5_modify_header_alloc(struct mlx5_core_dev *dev, struct mlx5_modify_hdr *modify_hdr; int err; - root = get_root_namespace(dev, ns_type); + root = mlx5_get_root_namespace(dev, ns_type); if (!root) return ERR_PTR(-EOPNOTSUPP); @@ -3639,7 +3639,7 @@ void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, { struct mlx5_flow_root_namespace *root; - root = get_root_namespace(dev, modify_hdr->ns_type); + root = mlx5_get_root_namespace(dev, modify_hdr->ns_type); if (WARN_ON(!root)) return; root->cmds->modify_header_dealloc(root, modify_hdr); @@ -3655,7 +3655,7 @@ struct mlx5_pkt_reformat *mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, struct mlx5_flow_root_namespace *root; int err; - root = get_root_namespace(dev, ns_type); + root = mlx5_get_root_namespace(dev, ns_type); if (!root) return ERR_PTR(-EOPNOTSUPP); @@ -3681,7 +3681,7 @@ void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev, { struct mlx5_flow_root_namespace *root; - root = get_root_namespace(dev, pkt_reformat->ns_type); + root = mlx5_get_root_namespace(dev, pkt_reformat->ns_type); if (WARN_ON(!root)) return; root->cmds->packet_reformat_dealloc(root, pkt_reformat); @@ -3703,7 +3703,7 @@ mlx5_create_match_definer(struct mlx5_core_dev *dev, struct mlx5_flow_definer *definer; int id; - root = get_root_namespace(dev, ns_type); + root = mlx5_get_root_namespace(dev, ns_type); if (!root) return ERR_PTR(-EOPNOTSUPP); @@ -3727,7 +3727,7 @@ void mlx5_destroy_match_definer(struct mlx5_core_dev *dev, { struct mlx5_flow_root_namespace *root; - root = get_root_namespace(dev, definer->ns_type); + root = mlx5_get_root_namespace(dev, definer->ns_type); if (WARN_ON(!root)) return; diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 3fb428ce7d1c..b744e554f014 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -342,4 +342,7 @@ void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev, struct mlx5_pkt_reformat *reformat); u32 mlx5_flow_table_id(struct mlx5_flow_table *ft); + +struct mlx5_flow_root_namespace * +mlx5_get_root_namespace(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type ns_type); #endif -- cgit v1.2.3 From 9947204cdad97d22d171039019a4aad4d6899cdd Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Wed, 11 Sep 2024 13:17:51 -0700 Subject: net/mlx5: Add device cap for supporting hot reset in sync reset flow New devices with new FW can support sync reset for firmware activate using hot reset. Add capability for supporting it and add MFRL field to query from FW which type of PCI reset method to use while handling sync reset events. Signed-off-by: Moshe Shemesh Signed-off-by: Saeed Mahameed Reviewed-by: Jacob Keller Link: https://patch.msgid.link/20240911201757.1505453-10-saeed@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/mlx5/mlx5_ifc.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 2045575b70d4..620a5c305123 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1856,7 +1856,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_328[0x2]; u8 relaxed_ordering_read[0x1]; u8 log_max_pd[0x5]; - u8 reserved_at_330[0x6]; + u8 reserved_at_330[0x5]; + u8 pcie_reset_using_hotreset_method[0x1]; u8 pci_sync_for_fw_update_with_driver_unload[0x1]; u8 vnic_env_cnt_steering_fail[0x1]; u8 vport_counter_local_loopback[0x1]; @@ -11188,6 +11189,11 @@ struct mlx5_ifc_mcda_reg_bits { u8 data[][0x20]; }; +enum { + MLX5_MFRL_REG_PCI_RESET_METHOD_LINK_TOGGLE = 0, + MLX5_MFRL_REG_PCI_RESET_METHOD_HOT_RESET = 1, +}; + enum { MLX5_MFRL_REG_RESET_STATE_IDLE = 0, MLX5_MFRL_REG_RESET_STATE_IN_NEGOTIATION = 1, @@ -11215,7 +11221,8 @@ struct mlx5_ifc_mfrl_reg_bits { u8 pci_sync_for_fw_update_start[0x1]; u8 pci_sync_for_fw_update_resp[0x2]; u8 rst_type_sel[0x3]; - u8 reserved_at_28[0x4]; + u8 pci_reset_req_method[0x3]; + u8 reserved_at_2b[0x1]; u8 reset_state[0x4]; u8 reset_type[0x8]; u8 reset_level[0x8]; -- cgit v1.2.3 From 5bd877093fd0b2e9e5f0c03b466669f761b5849c Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Wed, 11 Sep 2024 13:17:55 -0700 Subject: net/mlx5: Add NOT_READY command return status Add a new command status MLX5_CMD_STAT_NOT_READY to handle cases where the firmware is not ready. Signed-off-by: Shay Drory Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed Reviewed-by: Jacob Keller Reviewed-by: Kalesh AP Link: https://patch.msgid.link/20240911201757.1505453-14-saeed@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 7 ++++++- include/linux/mlx5/device.h | 1 + 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 20768ef2e9d2..9af8ddb4a78f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -754,6 +754,8 @@ static const char *cmd_status_str(u8 status) return "bad resource"; case MLX5_CMD_STAT_RES_BUSY: return "resource busy"; + case MLX5_CMD_STAT_NOT_READY: + return "FW not ready"; case MLX5_CMD_STAT_LIM_ERR: return "limits exceeded"; case MLX5_CMD_STAT_BAD_RES_STATE_ERR: @@ -787,6 +789,7 @@ static int cmd_status_to_err(u8 status) case MLX5_CMD_STAT_BAD_SYS_STATE_ERR: return -EIO; case MLX5_CMD_STAT_BAD_RES_ERR: return -EINVAL; case MLX5_CMD_STAT_RES_BUSY: return -EBUSY; + case MLX5_CMD_STAT_NOT_READY: return -EAGAIN; case MLX5_CMD_STAT_LIM_ERR: return -ENOMEM; case MLX5_CMD_STAT_BAD_RES_STATE_ERR: return -EINVAL; case MLX5_CMD_STAT_IX_ERR: return -EINVAL; @@ -815,14 +818,16 @@ EXPORT_SYMBOL(mlx5_cmd_out_err); static void cmd_status_print(struct mlx5_core_dev *dev, void *in, void *out) { u16 opcode, op_mod; + u8 status; u16 uid; opcode = in_to_opcode(in); op_mod = MLX5_GET(mbox_in, in, op_mod); uid = MLX5_GET(mbox_in, in, uid); + status = MLX5_GET(mbox_out, out, status); if (!uid && opcode != MLX5_CMD_OP_DESTROY_MKEY && - opcode != MLX5_CMD_OP_CREATE_UCTX) + opcode != MLX5_CMD_OP_CREATE_UCTX && status != MLX5_CMD_STAT_NOT_READY) mlx5_cmd_out_err(dev, opcode, op_mod, out); } diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index a94bc9e3af96..d0f7d1f36c5e 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1449,6 +1449,7 @@ enum { MLX5_CMD_STAT_BAD_SYS_STATE_ERR = 0x4, MLX5_CMD_STAT_BAD_RES_ERR = 0x5, MLX5_CMD_STAT_RES_BUSY = 0x6, + MLX5_CMD_STAT_NOT_READY = 0x7, MLX5_CMD_STAT_LIM_ERR = 0x8, MLX5_CMD_STAT_BAD_RES_STATE_ERR = 0x9, MLX5_CMD_STAT_IX_ERR = 0xa, -- cgit v1.2.3 From 907936b6f4e630718cc31ddea79cc76a3e32080a Mon Sep 17 00:00:00 2001 From: Michael Guralnik Date: Mon, 9 Sep 2024 13:05:04 +0300 Subject: net/mlx5: Handle memory scheme ODP capabilities When running over new FW that supports the new memory scheme ODP, set the cap in the FW to signal the FW we are working in the new scheme. In the memory scheme ODP the per_transport_service capabilities are RO for the driver so we skip their setting. Signed-off-by: Michael Guralnik Link: https://patch.msgid.link/20240909100504.29797-9-michaelgur@nvidia.com Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 22 ++++++++++++++++++---- include/linux/mlx5/device.h | 10 +++++++--- 2 files changed, 25 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index cc2aa46cff04..4ec6507d094a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -454,8 +454,8 @@ static int handle_hca_cap_atomic(struct mlx5_core_dev *dev, void *set_ctx) static int handle_hca_cap_odp(struct mlx5_core_dev *dev, void *set_ctx) { + bool do_set = false, mem_page_fault = false; void *set_hca_cap; - bool do_set = false; int err; if (!IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING) || @@ -470,6 +470,17 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev, void *set_ctx) memcpy(set_hca_cap, dev->caps.hca[MLX5_CAP_ODP]->cur, MLX5_ST_SZ_BYTES(odp_cap)); + /* For best performance, enable memory scheme ODP only when + * it has page prefetch enabled. + */ + if (MLX5_CAP_ODP_MAX(dev, mem_page_fault) && + MLX5_CAP_ODP_MAX(dev, memory_page_fault_scheme_cap.page_prefetch)) { + mem_page_fault = true; + do_set = true; + MLX5_SET(odp_cap, set_hca_cap, mem_page_fault, mem_page_fault); + goto set; + } + #define ODP_CAP_SET_MAX(dev, field) \ do { \ u32 _res = MLX5_CAP_ODP_MAX(dev, field); \ @@ -494,10 +505,13 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev, void *set_ctx) ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.dc_odp_caps.read); ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.dc_odp_caps.atomic); - if (!do_set) - return 0; +set: + if (do_set) + err = set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_ODP); - return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_ODP); + mlx5_core_dbg(dev, "Using ODP %s scheme\n", + mem_page_fault ? "memory" : "transport"); + return err; } static int max_uc_list_get_devlink_param(struct mlx5_core_dev *dev) diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 154095256d0d..57c9b18c3adb 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1389,9 +1389,13 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_ODP(mdev, cap)\ MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, cap) -#define MLX5_CAP_ODP_SCHEME(mdev, cap) \ - MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, \ - transport_page_fault_scheme_cap.cap) +#define MLX5_CAP_ODP_SCHEME(mdev, cap) \ + (MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, \ + mem_page_fault) ? \ + MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, \ + memory_page_fault_scheme_cap.cap) : \ + MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, \ + transport_page_fault_scheme_cap.cap)) #define MLX5_CAP_ODP_MAX(mdev, cap)\ MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->max, cap) -- cgit v1.2.3 From 8d159eb2117b2e3697a31785662b653938f007cb Mon Sep 17 00:00:00 2001 From: Chiara Meiohas Date: Mon, 9 Sep 2024 20:30:23 +0300 Subject: RDMA/mlx5: Use IB set_netdev and get_netdev functions The IB layer provides a common interface to store and get net devices associated to an IB device port (ib_device_set_netdev() and ib_device_get_netdev()). Previously, mlx5_ib stored and managed the associated net devices internally. Replace internal net device management in mlx5_ib with ib_device_set_netdev() when attaching/detaching a net device and ib_device_get_netdev() when retrieving the net device. Export ib_device_get_netdev(). For mlx5 representors/PFs/VFs and lag creation we replace the netdev assignments with the IB set/get netdev functions. In active-backup mode lag the active slave net device is stored in the lag itself. To assure the net device stored in a lag bond IB device is the active slave we implement the following: - mlx5_core: when modifying the slave of a bond we send the internal driver event MLX5_DRIVER_EVENT_ACTIVE_BACKUP_LAG_CHANGE_LOWERSTATE. - mlx5_ib: when catching the event call ib_device_set_netdev() This patch also ensures the correct IB events are sent in switchdev lag. While at it, when in multiport eswitch mode, only a single IB device is created for all ports. The said IB device will receive all netdev events of its VFs once loaded, thus to avoid overwriting the mapping of PF IB device to PF netdev, ignore NETDEV_REGISTER events if the ib device has already been mapped to a netdev. Signed-off-by: Chiara Meiohas Signed-off-by: Michael Guralnik Link: https://patch.msgid.link/20240909173025.30422-6-michaelgur@nvidia.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/core/device.c | 4 + drivers/infiniband/hw/mlx5/ib_rep.c | 23 +-- drivers/infiniband/hw/mlx5/main.c | 183 +++++++++++++++------- drivers/infiniband/hw/mlx5/mlx5_ib.h | 3 +- drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c | 76 ++++----- include/linux/mlx5/device.h | 1 + include/linux/mlx5/driver.h | 2 +- include/rdma/ib_verbs.h | 2 + 8 files changed, 191 insertions(+), 103 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index b1377503cb9d..9e765c79a892 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -2236,6 +2236,9 @@ struct net_device *ib_device_get_netdev(struct ib_device *ib_dev, if (!rdma_is_port_valid(ib_dev, port)) return NULL; + if (!ib_dev->port_data) + return NULL; + pdata = &ib_dev->port_data[port]; /* @@ -2254,6 +2257,7 @@ struct net_device *ib_device_get_netdev(struct ib_device *ib_dev, return res; } +EXPORT_SYMBOL(ib_device_get_netdev); /** * ib_device_get_by_netdev - Find an IB device associated with a netdev diff --git a/drivers/infiniband/hw/mlx5/ib_rep.c b/drivers/infiniband/hw/mlx5/ib_rep.c index 1ad934685d80..49af1cfbe6d1 100644 --- a/drivers/infiniband/hw/mlx5/ib_rep.c +++ b/drivers/infiniband/hw/mlx5/ib_rep.c @@ -13,6 +13,7 @@ mlx5_ib_set_vport_rep(struct mlx5_core_dev *dev, int vport_index) { struct mlx5_ib_dev *ibdev; + struct net_device *ndev; ibdev = mlx5_eswitch_uplink_get_proto_dev(dev->priv.eswitch, REP_IB); if (!ibdev) @@ -20,12 +21,9 @@ mlx5_ib_set_vport_rep(struct mlx5_core_dev *dev, ibdev->port[vport_index].rep = rep; rep->rep_data[REP_IB].priv = ibdev; - write_lock(&ibdev->port[vport_index].roce.netdev_lock); - ibdev->port[vport_index].roce.netdev = - mlx5_ib_get_rep_netdev(rep->esw, rep->vport); - write_unlock(&ibdev->port[vport_index].roce.netdev_lock); + ndev = mlx5_ib_get_rep_netdev(rep->esw, rep->vport); - return 0; + return ib_device_set_netdev(&ibdev->ib_dev, ndev, vport_index + 1); } static void mlx5_ib_register_peer_vport_reps(struct mlx5_core_dev *mdev); @@ -104,11 +102,15 @@ mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) ibdev->is_rep = true; vport_index = rep->vport_index; ibdev->port[vport_index].rep = rep; - ibdev->ib_dev.phys_port_cnt = num_ports; - ibdev->port[vport_index].roce.netdev = - mlx5_ib_get_rep_netdev(lag_master->priv.eswitch, rep->vport); ibdev->mdev = lag_master; ibdev->num_ports = num_ports; + ibdev->ib_dev.phys_port_cnt = num_ports; + ret = ib_device_set_netdev(&ibdev->ib_dev, + mlx5_ib_get_rep_netdev(lag_master->priv.eswitch, + rep->vport), + vport_index + 1); + if (ret) + goto fail_add; ret = __mlx5_ib_add(ibdev, profile); if (ret) @@ -161,9 +163,8 @@ mlx5_ib_vport_rep_unload(struct mlx5_eswitch_rep *rep) } port = &dev->port[vport_index]; - write_lock(&port->roce.netdev_lock); - port->roce.netdev = NULL; - write_unlock(&port->roce.netdev_lock); + + ib_device_set_netdev(&dev->ib_dev, NULL, vport_index + 1); rep->rep_data[REP_IB].priv = NULL; port->rep = NULL; diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index ad8a2b5517bf..4999239c8f41 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -147,16 +147,52 @@ static struct mlx5_roce *mlx5_get_rep_roce(struct mlx5_ib_dev *dev, if (upper && port->rep->vport == MLX5_VPORT_UPLINK) continue; - - read_lock(&port->roce.netdev_lock); - rep_ndev = mlx5_ib_get_rep_netdev(port->rep->esw, - port->rep->vport); - if (rep_ndev == ndev) { - read_unlock(&port->roce.netdev_lock); + rep_ndev = ib_device_get_netdev(&dev->ib_dev, i + 1); + if (rep_ndev && rep_ndev == ndev) { + dev_put(rep_ndev); *port_num = i + 1; return &port->roce; } - read_unlock(&port->roce.netdev_lock); + + dev_put(rep_ndev); + } + + return NULL; +} + +static bool mlx5_netdev_send_event(struct mlx5_ib_dev *dev, + struct net_device *ndev, + struct net_device *upper, + struct net_device *ib_ndev) +{ + if (!dev->ib_active) + return false; + + /* Event is about our upper device */ + if (upper == ndev) + return true; + + /* RDMA device is not in lag and not in switchdev */ + if (!dev->is_rep && !upper && ndev == ib_ndev) + return true; + + /* RDMA devie is in switchdev */ + if (dev->is_rep && ndev == ib_ndev) + return true; + + return false; +} + +static struct net_device *mlx5_ib_get_rep_uplink_netdev(struct mlx5_ib_dev *ibdev) +{ + struct mlx5_ib_port *port; + int i; + + for (i = 0; i < ibdev->num_ports; i++) { + port = &ibdev->port[i]; + if (port->rep && port->rep->vport == MLX5_VPORT_UPLINK) { + return ib_device_get_netdev(&ibdev->ib_dev, i + 1); + } } return NULL; @@ -168,6 +204,7 @@ static int mlx5_netdev_event(struct notifier_block *this, struct mlx5_roce *roce = container_of(this, struct mlx5_roce, nb); struct net_device *ndev = netdev_notifier_info_to_dev(ptr); u32 port_num = roce->native_port_num; + struct net_device *ib_ndev = NULL; struct mlx5_core_dev *mdev; struct mlx5_ib_dev *ibdev; @@ -181,29 +218,38 @@ static int mlx5_netdev_event(struct notifier_block *this, /* Should already be registered during the load */ if (ibdev->is_rep) break; - write_lock(&roce->netdev_lock); + + ib_ndev = ib_device_get_netdev(&ibdev->ib_dev, port_num); + /* Exit if already registered */ + if (ib_ndev) + goto put_ndev; + if (ndev->dev.parent == mdev->device) - roce->netdev = ndev; - write_unlock(&roce->netdev_lock); + ib_device_set_netdev(&ibdev->ib_dev, ndev, port_num); break; case NETDEV_UNREGISTER: /* In case of reps, ib device goes away before the netdevs */ - write_lock(&roce->netdev_lock); - if (roce->netdev == ndev) - roce->netdev = NULL; - write_unlock(&roce->netdev_lock); - break; + if (ibdev->is_rep) + break; + ib_ndev = ib_device_get_netdev(&ibdev->ib_dev, port_num); + if (ib_ndev == ndev) + ib_device_set_netdev(&ibdev->ib_dev, NULL, port_num); + goto put_ndev; case NETDEV_CHANGE: case NETDEV_UP: case NETDEV_DOWN: { struct net_device *upper = NULL; - if (mlx5_lag_is_roce(mdev)) { + if (mlx5_lag_is_roce(mdev) || mlx5_lag_is_sriov(mdev)) { struct net_device *lag_ndev; - lag_ndev = mlx5_lag_get_roce_netdev(mdev); + if(mlx5_lag_is_roce(mdev)) + lag_ndev = ib_device_get_netdev(&ibdev->ib_dev, 1); + else /* sriov lag */ + lag_ndev = mlx5_ib_get_rep_uplink_netdev(ibdev); + if (lag_ndev) { upper = netdev_master_upper_dev_get(lag_ndev); dev_put(lag_ndev); @@ -216,18 +262,19 @@ static int mlx5_netdev_event(struct notifier_block *this, roce = mlx5_get_rep_roce(ibdev, ndev, upper, &port_num); if (!roce) return NOTIFY_DONE; - if ((upper == ndev || - ((!upper || ibdev->is_rep) && ndev == roce->netdev)) && - ibdev->ib_active) { + + ib_ndev = ib_device_get_netdev(&ibdev->ib_dev, port_num); + + if (mlx5_netdev_send_event(ibdev, ndev, upper, ib_ndev)) { struct ib_event ibev = { }; enum ib_port_state port_state; if (get_port_state(&ibdev->ib_dev, port_num, &port_state)) - goto done; + goto put_ndev; if (roce->last_port_state == port_state) - goto done; + goto put_ndev; roce->last_port_state = port_state; ibev.device = &ibdev->ib_dev; @@ -236,7 +283,7 @@ static int mlx5_netdev_event(struct notifier_block *this, else if (port_state == IB_PORT_ACTIVE) ibev.event = IB_EVENT_PORT_ACTIVE; else - goto done; + goto put_ndev; ibev.element.port_num = port_num; ib_dispatch_event(&ibev); @@ -247,39 +294,13 @@ static int mlx5_netdev_event(struct notifier_block *this, default: break; } +put_ndev: + dev_put(ib_ndev); done: mlx5_ib_put_native_port_mdev(ibdev, port_num); return NOTIFY_DONE; } -static struct net_device *mlx5_ib_get_netdev(struct ib_device *device, - u32 port_num) -{ - struct mlx5_ib_dev *ibdev = to_mdev(device); - struct net_device *ndev; - struct mlx5_core_dev *mdev; - - mdev = mlx5_ib_get_native_port_mdev(ibdev, port_num, NULL); - if (!mdev) - return NULL; - - if (mlx5_lag_is_roce(mdev)) { - ndev = mlx5_lag_get_roce_netdev(mdev); - goto out; - } - - /* Ensure ndev does not disappear before we invoke dev_hold() - */ - read_lock(&ibdev->port[port_num - 1].roce.netdev_lock); - ndev = ibdev->port[port_num - 1].roce.netdev; - dev_hold(ndev); - read_unlock(&ibdev->port[port_num - 1].roce.netdev_lock); - -out: - mlx5_ib_put_native_port_mdev(ibdev, port_num); - return ndev; -} - struct mlx5_core_dev *mlx5_ib_get_native_port_mdev(struct mlx5_ib_dev *ibdev, u32 ib_port_num, u32 *native_port_num) @@ -554,7 +575,7 @@ static int mlx5_query_port_roce(struct ib_device *device, u32 port_num, if (!put_mdev) goto out; - ndev = mlx5_ib_get_netdev(device, port_num); + ndev = ib_device_get_netdev(device, port_num); if (!ndev) goto out; @@ -3185,6 +3206,60 @@ static void get_dev_fw_str(struct ib_device *ibdev, char *str) fw_rev_sub(dev->mdev)); } +static int lag_event(struct notifier_block *nb, unsigned long event, void *data) +{ + struct mlx5_ib_dev *dev = container_of(nb, struct mlx5_ib_dev, + lag_events); + struct mlx5_core_dev *mdev = dev->mdev; + struct mlx5_ib_port *port; + struct net_device *ndev; + int i, err; + int portnum; + + portnum = 0; + switch (event) { + case MLX5_DRIVER_EVENT_ACTIVE_BACKUP_LAG_CHANGE_LOWERSTATE: + ndev = data; + if (ndev) { + if (!mlx5_lag_is_roce(mdev)) { + // sriov lag + for (i = 0; i < dev->num_ports; i++) { + port = &dev->port[i]; + if (port->rep && port->rep->vport == + MLX5_VPORT_UPLINK) { + portnum = i; + break; + } + } + } + err = ib_device_set_netdev(&dev->ib_dev, ndev, + portnum + 1); + dev_put(ndev); + if (err) + return err; + /* Rescan gids after new netdev assignment */ + rdma_roce_rescan_device(&dev->ib_dev); + } + break; + default: + return NOTIFY_DONE; + } + return NOTIFY_OK; +} + +static void mlx5e_lag_event_register(struct mlx5_ib_dev *dev) +{ + dev->lag_events.notifier_call = lag_event; + blocking_notifier_chain_register(&dev->mdev->priv.lag_nh, + &dev->lag_events); +} + +static void mlx5e_lag_event_unregister(struct mlx5_ib_dev *dev) +{ + blocking_notifier_chain_unregister(&dev->mdev->priv.lag_nh, + &dev->lag_events); +} + static int mlx5_eth_lag_init(struct mlx5_ib_dev *dev) { struct mlx5_core_dev *mdev = dev->mdev; @@ -3206,6 +3281,7 @@ static int mlx5_eth_lag_init(struct mlx5_ib_dev *dev) goto err_destroy_vport_lag; } + mlx5e_lag_event_register(dev); dev->flow_db->lag_demux_ft = ft; dev->lag_ports = mlx5_lag_get_num_ports(mdev); dev->lag_active = true; @@ -3223,6 +3299,7 @@ static void mlx5_eth_lag_cleanup(struct mlx5_ib_dev *dev) if (dev->lag_active) { dev->lag_active = false; + mlx5e_lag_event_unregister(dev); mlx5_destroy_flow_table(dev->flow_db->lag_demux_ft); dev->flow_db->lag_demux_ft = NULL; @@ -3939,7 +4016,6 @@ static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev) for (i = 0; i < dev->num_ports; i++) { spin_lock_init(&dev->port[i].mp.mpi_lock); - rwlock_init(&dev->port[i].roce.netdev_lock); dev->port[i].roce.dev = dev; dev->port[i].roce.native_port_num = i + 1; dev->port[i].roce.last_port_state = IB_PORT_DOWN; @@ -4204,7 +4280,6 @@ static const struct ib_device_ops mlx5_ib_dev_common_roce_ops = { .create_wq = mlx5_ib_create_wq, .destroy_rwq_ind_table = mlx5_ib_destroy_rwq_ind_table, .destroy_wq = mlx5_ib_destroy_wq, - .get_netdev = mlx5_ib_get_netdev, .modify_wq = mlx5_ib_modify_wq, INIT_RDMA_OBJ_SIZE(ib_rwq_ind_table, mlx5_ib_rwq_ind_table, diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index 59ce407ce505..23fd72f7f63d 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -888,8 +888,6 @@ struct mlx5_roce { /* Protect mlx5_ib_get_netdev from invoking dev_hold() with a NULL * netdev pointer */ - rwlock_t netdev_lock; - struct net_device *netdev; struct notifier_block nb; struct netdev_net_notifier nn; struct notifier_block mdev_nb; @@ -1138,6 +1136,7 @@ struct mlx5_ib_dev { /* protect accessing data_direct_dev */ struct mutex data_direct_lock; struct notifier_block mdev_events; + struct notifier_block lag_events; int num_ports; /* serialize update of capability mask */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index cf8045b92689..8577db3308cc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -445,6 +445,34 @@ static int _mlx5_modify_lag(struct mlx5_lag *ldev, u8 *ports) return mlx5_cmd_modify_lag(dev0, ldev->ports, ports); } +static struct net_device *mlx5_lag_active_backup_get_netdev(struct mlx5_core_dev *dev) +{ + struct net_device *ndev = NULL; + struct mlx5_lag *ldev; + unsigned long flags; + int i; + + spin_lock_irqsave(&lag_lock, flags); + ldev = mlx5_lag_dev(dev); + + if (!ldev) + goto unlock; + + for (i = 0; i < ldev->ports; i++) + if (ldev->tracker.netdev_state[i].tx_enabled) + ndev = ldev->pf[i].netdev; + if (!ndev) + ndev = ldev->pf[ldev->ports - 1].netdev; + + if (ndev) + dev_hold(ndev); + +unlock: + spin_unlock_irqrestore(&lag_lock, flags); + + return ndev; +} + void mlx5_modify_lag(struct mlx5_lag *ldev, struct lag_tracker *tracker) { @@ -477,9 +505,18 @@ void mlx5_modify_lag(struct mlx5_lag *ldev, } } - if (tracker->tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP && - !(ldev->mode == MLX5_LAG_MODE_ROCE)) - mlx5_lag_drop_rule_setup(ldev, tracker); + if (tracker->tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP) { + struct net_device *ndev = mlx5_lag_active_backup_get_netdev(dev0); + + if(!(ldev->mode == MLX5_LAG_MODE_ROCE)) + mlx5_lag_drop_rule_setup(ldev, tracker); + /** Only sriov and roce lag should have tracker->tx_type set so + * no need to check the mode + */ + blocking_notifier_call_chain(&dev0->priv.lag_nh, + MLX5_DRIVER_EVENT_ACTIVE_BACKUP_LAG_CHANGE_LOWERSTATE, + ndev); + } } static int mlx5_lag_set_port_sel_mode_roce(struct mlx5_lag *ldev, @@ -613,6 +650,7 @@ static int mlx5_create_lag(struct mlx5_lag *ldev, mlx5_core_err(dev0, "Failed to deactivate RoCE LAG; driver restart required\n"); } + BLOCKING_INIT_NOTIFIER_HEAD(&dev0->priv.lag_nh); return err; } @@ -1492,38 +1530,6 @@ void mlx5_lag_enable_change(struct mlx5_core_dev *dev) mlx5_queue_bond_work(ldev, 0); } -struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev) -{ - struct net_device *ndev = NULL; - struct mlx5_lag *ldev; - unsigned long flags; - int i; - - spin_lock_irqsave(&lag_lock, flags); - ldev = mlx5_lag_dev(dev); - - if (!(ldev && __mlx5_lag_is_roce(ldev))) - goto unlock; - - if (ldev->tracker.tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP) { - for (i = 0; i < ldev->ports; i++) - if (ldev->tracker.netdev_state[i].tx_enabled) - ndev = ldev->pf[i].netdev; - if (!ndev) - ndev = ldev->pf[ldev->ports - 1].netdev; - } else { - ndev = ldev->pf[MLX5_LAG_P1].netdev; - } - if (ndev) - dev_hold(ndev); - -unlock: - spin_unlock_irqrestore(&lag_lock, flags); - - return ndev; -} -EXPORT_SYMBOL(mlx5_lag_get_roce_netdev); - u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev, struct net_device *slave) { diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 57c9b18c3adb..dac33cfe9c0c 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -371,6 +371,7 @@ enum mlx5_driver_event { MLX5_DRIVER_EVENT_SF_PEER_DEVLINK, MLX5_DRIVER_EVENT_AFFILIATION_DONE, MLX5_DRIVER_EVENT_AFFILIATION_REMOVED, + MLX5_DRIVER_EVENT_ACTIVE_BACKUP_LAG_CHANGE_LOWERSTATE, }; enum { diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index a96438ded15f..46a7a3d11048 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -643,6 +643,7 @@ struct mlx5_priv { struct mlx5_sf_hw_table *sf_hw_table; struct mlx5_sf_table *sf_table; #endif + struct blocking_notifier_head lag_nh; }; enum mlx5_device_state { @@ -1181,7 +1182,6 @@ bool mlx5_lag_mode_is_hash(struct mlx5_core_dev *dev); bool mlx5_lag_is_master(struct mlx5_core_dev *dev); bool mlx5_lag_is_shared_fdb(struct mlx5_core_dev *dev); bool mlx5_lag_is_mpesw(struct mlx5_core_dev *dev); -struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev); u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev, struct net_device *slave); int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index a1dcf812d787..aa8ede439905 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -4453,6 +4453,8 @@ struct net_device *ib_get_net_dev_by_params(struct ib_device *dev, u32 port, const struct sockaddr *addr); int ib_device_set_netdev(struct ib_device *ib_dev, struct net_device *ndev, unsigned int port); +struct net_device *ib_device_get_netdev(struct ib_device *ib_dev, + u32 port); struct ib_wq *ib_create_wq(struct ib_pd *pd, struct ib_wq_init_attr *init_attr); int ib_destroy_wq_user(struct ib_wq *wq, struct ib_udata *udata); -- cgit v1.2.3 From 96f8052822e03c6f49b6b28fc1d6e5e0522ecbb9 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Thu, 12 Sep 2024 15:39:54 -0700 Subject: locking/mutex: Define mutex_init() once With CONFIG_PREEMPT_RT disabled __mutex_init() is a function. With CONFIG_PREEMPT_RT enabled, __mutex_init() is a macro. I assume this is why mutex_init() is defined twice as exactly the same macro. Prepare for introducing a new macro for mutex initialization by combining the two identical mutex_init() definitions into a single definition. This patch does not change any functionality because the C preprocessor expands macros when it encounters the macro name and not when a macro definition is encountered. See also commit bb630f9f7a7d ("locking/rtmutex: Add mutex variant for RT"). Acked-by: Peter Zijlstra (Intel) Cc: Thomas Gleixner Cc: Ingo Molnar Signed-off-by: Bart Van Assche Link: https://lore.kernel.org/r/20240912223956.3554086-2-bvanassche@acm.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mutex.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mutex.h b/include/linux/mutex.h index a561c629d89f..ef617089db19 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -49,7 +49,6 @@ static inline void mutex_destroy(struct mutex *lock) {} #endif -#ifndef CONFIG_PREEMPT_RT /** * mutex_init - initialize the mutex * @mutex: the mutex to be initialized @@ -65,6 +64,7 @@ do { \ __mutex_init((mutex), #mutex, &__key); \ } while (0) +#ifndef CONFIG_PREEMPT_RT #define __MUTEX_INITIALIZER(lockname) \ { .owner = ATOMIC_LONG_INIT(0) \ , .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(lockname.wait_lock) \ @@ -111,12 +111,6 @@ do { \ __mutex_rt_init((mutex), name, key); \ } while (0) -#define mutex_init(mutex) \ -do { \ - static struct lock_class_key __key; \ - \ - __mutex_init((mutex), #mutex, &__key); \ -} while (0) #endif /* CONFIG_PREEMPT_RT */ #ifdef CONFIG_DEBUG_MUTEXES -- cgit v1.2.3 From e837d833a13461c10f265a65ce6612e6dd43e76f Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Thu, 12 Sep 2024 15:39:55 -0700 Subject: locking/mutex: Introduce mutex_init_with_key() The following pattern occurs 5 times in kernel drivers: lockdep_register_key(key); __mutex_init(mutex, name, key); In several cases the 'name' argument matches #mutex. Hence, introduce the mutex_init_with_key() macro. This macro derives the 'name' argument from the 'mutex' argument. Suggested-by: Andy Shevchenko Acked-by: Peter Zijlstra (Intel) Reviewed-by: Andy Shevchenko Cc: Thomas Gleixner Cc: Ingo Molnar Signed-off-by: Bart Van Assche Link: https://lore.kernel.org/r/20240912223956.3554086-3-bvanassche@acm.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mutex.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mutex.h b/include/linux/mutex.h index ef617089db19..2bf91b57591b 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -64,6 +64,17 @@ do { \ __mutex_init((mutex), #mutex, &__key); \ } while (0) +/** + * mutex_init_with_key - initialize a mutex with a given lockdep key + * @mutex: the mutex to be initialized + * @key: the lockdep key to be associated with the mutex + * + * Initialize the mutex to the unlocked state. + * + * It is not allowed to initialize an already locked mutex. + */ +#define mutex_init_with_key(mutex, key) __mutex_init((mutex), #mutex, (key)) + #ifndef CONFIG_PREEMPT_RT #define __MUTEX_INITIALIZER(lockname) \ { .owner = ATOMIC_LONG_INIT(0) \ -- cgit v1.2.3 From 4b7ff9ab98af11a477d50f08382bcc4c2f899926 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Fri, 13 Sep 2024 10:15:56 +0200 Subject: mm, slab: restore kerneldoc for kmem_cache_create() As kmem_cache_create() became a _Generic() wrapper macro, it currently has no kerneldoc despite being the main API to use. Add it. Also adjust kmem_cache_create_usercopy() kerneldoc to indicate it is now a legacy wrapper. Also expand the kerneldoc for struct kmem_cache_args, especially for the freeptr_offset field, where important details were removed with the removal of kmem_cache_create_rcu(). Signed-off-by: Vlastimil Babka Reviewed-by: Christian Brauner --- include/linux/slab.h | 114 ++++++++++++++++++++++++++++++++++++++++----------- mm/slab_common.c | 10 +++-- 2 files changed, 98 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 331412a9f4f2..6a8ab7ef3af7 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -242,19 +242,72 @@ bool slab_is_available(void); /** * struct kmem_cache_args - Less common arguments for kmem_cache_create() - * @align: The required alignment for the objects. - * @useroffset: Usercopy region offset - * @usersize: Usercopy region size - * @freeptr_offset: Custom offset for the free pointer in RCU caches - * @use_freeptr_offset: Whether a @freeptr_offset is used - * @ctor: A constructor for the objects. + * + * Any uninitialized fields of the structure are interpreted as unused. The + * exception is @freeptr_offset where %0 is a valid value, so + * @use_freeptr_offset must be also set to %true in order to interpret the field + * as used. For @useroffset %0 is also valid, but only with non-%0 + * @usersize. + * + * When %NULL args is passed to kmem_cache_create(), it is equivalent to all + * fields unused. */ struct kmem_cache_args { + /** + * @align: The required alignment for the objects. + * + * %0 means no specific alignment is requested. + */ unsigned int align; + /** + * @useroffset: Usercopy region offset. + * + * %0 is a valid offset, when @usersize is non-%0 + */ unsigned int useroffset; + /** + * @usersize: Usercopy region size. + * + * %0 means no usercopy region is specified. + */ unsigned int usersize; + /** + * @freeptr_offset: Custom offset for the free pointer + * in &SLAB_TYPESAFE_BY_RCU caches + * + * By default &SLAB_TYPESAFE_BY_RCU caches place the free pointer + * outside of the object. This might cause the object to grow in size. + * Cache creators that have a reason to avoid this can specify a custom + * free pointer offset in their struct where the free pointer will be + * placed. + * + * Note that placing the free pointer inside the object requires the + * caller to ensure that no fields are invalidated that are required to + * guard against object recycling (See &SLAB_TYPESAFE_BY_RCU for + * details). + * + * Using %0 as a value for @freeptr_offset is valid. If @freeptr_offset + * is specified, %use_freeptr_offset must be set %true. + * + * Note that @ctor currently isn't supported with custom free pointers + * as a @ctor requires an external free pointer. + */ unsigned int freeptr_offset; + /** + * @use_freeptr_offset: Whether a @freeptr_offset is used. + */ bool use_freeptr_offset; + /** + * @ctor: A constructor for the objects. + * + * The constructor is invoked for each object in a newly allocated slab + * page. It is the cache user's responsibility to free object in the + * same state as after calling the constructor, or deal appropriately + * with any differences between a freshly constructed and a reallocated + * object. + * + * %NULL means no constructor. + */ void (*ctor)(void *); }; @@ -275,30 +328,20 @@ __kmem_cache_create(const char *name, unsigned int size, unsigned int align, } /** - * kmem_cache_create_usercopy - Create a cache with a region suitable - * for copying to userspace + * kmem_cache_create_usercopy - Create a kmem cache with a region suitable + * for copying to userspace. * @name: A string which is used in /proc/slabinfo to identify this cache. * @size: The size of objects to be created in this cache. * @align: The required alignment for the objects. * @flags: SLAB flags * @useroffset: Usercopy region offset * @usersize: Usercopy region size - * @ctor: A constructor for the objects. - * - * Cannot be called within a interrupt, but can be interrupted. - * The @ctor is run when new pages are allocated by the cache. - * - * The flags are + * @ctor: A constructor for the objects, or %NULL. * - * %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5) - * to catch references to uninitialised memory. - * - * %SLAB_RED_ZONE - Insert `Red` zones around the allocated memory to check - * for buffer overruns. - * - * %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware - * cacheline. This can be beneficial if you're counting cycles as closely - * as davem. + * This is a legacy wrapper, new code should use either KMEM_CACHE_USERCOPY() + * if whitelisting a single field is sufficient, or kmem_cache_create() with + * the necessary parameters passed via the args parameter (see + * &struct kmem_cache_args) * * Return: a pointer to the cache on success, NULL on failure. */ @@ -333,6 +376,31 @@ __kmem_cache_default_args(const char *name, unsigned int size, return __kmem_cache_create_args(name, size, &kmem_default_args, flags); } +/** + * kmem_cache_create - Create a kmem cache. + * @__name: A string which is used in /proc/slabinfo to identify this cache. + * @__object_size: The size of objects to be created in this cache. + * @__args: Optional arguments, see &struct kmem_cache_args. Passing %NULL + * means defaults will be used for all the arguments. + * + * This is currently implemented as a macro using ``_Generic()`` to call + * either the new variant of the function, or a legacy one. + * + * The new variant has 4 parameters: + * ``kmem_cache_create(name, object_size, args, flags)`` + * + * See __kmem_cache_create_args() which implements this. + * + * The legacy variant has 5 parameters: + * ``kmem_cache_create(name, object_size, align, flags, ctor)`` + * + * The align and ctor parameters map to the respective fields of + * &struct kmem_cache_args + * + * Context: Cannot be called within a interrupt, but can be interrupted. + * + * Return: a pointer to the cache on success, NULL on failure. + */ #define kmem_cache_create(__name, __object_size, __args, ...) \ _Generic((__args), \ struct kmem_cache_args *: __kmem_cache_create_args, \ diff --git a/mm/slab_common.c b/mm/slab_common.c index 30000dcf0736..86c2e6f4a1ce 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -239,13 +239,17 @@ out: } /** - * __kmem_cache_create_args - Create a kmem cache + * __kmem_cache_create_args - Create a kmem cache. * @name: A string which is used in /proc/slabinfo to identify this cache. * @object_size: The size of objects to be created in this cache. - * @args: Arguments for the cache creation (see struct kmem_cache_args). + * @args: Additional arguments for the cache creation (see + * &struct kmem_cache_args). * @flags: See %SLAB_* flags for an explanation of individual @flags. * - * Cannot be called within a interrupt, but can be interrupted. + * Not to be called directly, use the kmem_cache_create() wrapper with the same + * parameters. + * + * Context: Cannot be called within a interrupt, but can be interrupted. * * Return: a pointer to the cache on success, NULL on failure. */ -- cgit v1.2.3 From 6a36d828bdef0e02b1e6c12e2160f5b83be6aab5 Mon Sep 17 00:00:00 2001 From: "Dr. David Alan Gilbert" Date: Fri, 13 Sep 2024 02:09:55 +0100 Subject: driver core: attribute_container: Remove unused functions I can't find any use of 'attribute_container_add_class_device_adapter' or 'attribute_container_trigger' in git history. Their export decls went in 2006: commit 1740757e8f94 ("[PATCH] Driver Core: remove unused exports") and their docs disappeared in 2016: commit 47cb398dd75a ("Docs: sphinxify device-drivers.tmpl") Remove them. Signed-off-by: Dr. David Alan Gilbert Link: https://lore.kernel.org/r/20240913010955.1393995-1-linux@treblig.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/attribute_container.c | 48 +------------------------------------ include/linux/attribute_container.h | 6 ----- 2 files changed, 1 insertion(+), 53 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/attribute_container.c b/drivers/base/attribute_container.c index 01ef796c2055..b6f941a6ab69 100644 --- a/drivers/base/attribute_container.c +++ b/drivers/base/attribute_container.c @@ -346,8 +346,7 @@ attribute_container_device_trigger_safe(struct device *dev, * @fn: the function to execute for each classdev. * * This function is for executing a trigger when you need to know both - * the container and the classdev. If you only care about the - * container, then use attribute_container_trigger() instead. + * the container and the classdev. */ void attribute_container_device_trigger(struct device *dev, @@ -378,33 +377,6 @@ attribute_container_device_trigger(struct device *dev, mutex_unlock(&attribute_container_mutex); } -/** - * attribute_container_trigger - trigger a function for each matching container - * - * @dev: The generic device to activate the trigger for - * @fn: the function to trigger - * - * This routine triggers a function that only needs to know the - * matching containers (not the classdev) associated with a device. - * It is more lightweight than attribute_container_device_trigger, so - * should be used in preference unless the triggering function - * actually needs to know the classdev. - */ -void -attribute_container_trigger(struct device *dev, - int (*fn)(struct attribute_container *, - struct device *)) -{ - struct attribute_container *cont; - - mutex_lock(&attribute_container_mutex); - list_for_each_entry(cont, &attribute_container_list, node) { - if (cont->match(cont, dev)) - fn(cont, dev); - } - mutex_unlock(&attribute_container_mutex); -} - /** * attribute_container_add_attrs - add attributes * @@ -458,24 +430,6 @@ attribute_container_add_class_device(struct device *classdev) return attribute_container_add_attrs(classdev); } -/** - * attribute_container_add_class_device_adapter - simple adapter for triggers - * - * @cont: the container to register. - * @dev: the generic device to activate the trigger for - * @classdev: the class device to add - * - * This function is identical to attribute_container_add_class_device except - * that it is designed to be called from the triggers - */ -int -attribute_container_add_class_device_adapter(struct attribute_container *cont, - struct device *dev, - struct device *classdev) -{ - return attribute_container_add_class_device(classdev); -} - /** * attribute_container_remove_attrs - remove any attribute files * diff --git a/include/linux/attribute_container.h b/include/linux/attribute_container.h index e4004d1e6725..b3643de9931d 100644 --- a/include/linux/attribute_container.h +++ b/include/linux/attribute_container.h @@ -61,14 +61,8 @@ int attribute_container_device_trigger_safe(struct device *dev, int (*undo)(struct attribute_container *, struct device *, struct device *)); -void attribute_container_trigger(struct device *dev, - int (*fn)(struct attribute_container *, - struct device *)); int attribute_container_add_attrs(struct device *classdev); int attribute_container_add_class_device(struct device *classdev); -int attribute_container_add_class_device_adapter(struct attribute_container *cont, - struct device *dev, - struct device *classdev); void attribute_container_remove_attrs(struct device *classdev); void attribute_container_class_device_del(struct device *classdev); struct attribute_container *attribute_container_classdev_to_container(struct device *); -- cgit v1.2.3 From 2cb4acf2140be8a4f299c0b887cc314845ef6ec8 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Fri, 13 Sep 2024 07:11:42 -0700 Subject: hwmon: Remove devm_hwmon_device_unregister() API function devm_hwmon_device_unregister() has no in-tree user, and its implementation is wrong since it does not pass the to-be-removed hardware monitoring device as parameter. I do not envision a valid use for it; drivers needing it should not have called devm_hwmon_device_register_with_info() in the first place. Remove it. Reported-by: Matthew Sanders Closes: https://lore.kernel.org/linux-hwmon/488b3bdf870ea76c4b943dbe5fd15ac8113019dc.camel@kernel.org/ Signed-off-by: Guenter Roeck --- Documentation/hwmon/hwmon-kernel-api.rst | 7 ------- drivers/hwmon/hwmon.c | 18 ------------------ include/linux/hwmon.h | 1 - 3 files changed, 26 deletions(-) (limited to 'include/linux') diff --git a/Documentation/hwmon/hwmon-kernel-api.rst b/Documentation/hwmon/hwmon-kernel-api.rst index 6cacf7daf25c..8297acfa3a2d 100644 --- a/Documentation/hwmon/hwmon-kernel-api.rst +++ b/Documentation/hwmon/hwmon-kernel-api.rst @@ -38,8 +38,6 @@ register/unregister functions:: void hwmon_device_unregister(struct device *dev); - void devm_hwmon_device_unregister(struct device *dev); - char *hwmon_sanitize_name(const char *name); char *devm_hwmon_sanitize_name(struct device *dev, const char *name); @@ -64,11 +62,6 @@ monitoring device structure. This function must be called from the driver remove function if the hardware monitoring device was registered with hwmon_device_register_with_info. -devm_hwmon_device_unregister does not normally have to be called. It is only -needed for error handling, and only needed if the driver probe fails after -the call to devm_hwmon_device_register_with_info and if the automatic (device -managed) removal would be too late. - All supported hwmon device registration functions only accept valid device names. Device names including invalid characters (whitespace, '*', or '-') will be rejected. The 'name' parameter is mandatory. diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c index a362080d41fa..9c35c4d0369d 100644 --- a/drivers/hwmon/hwmon.c +++ b/drivers/hwmon/hwmon.c @@ -1188,24 +1188,6 @@ error: } EXPORT_SYMBOL_GPL(devm_hwmon_device_register_with_info); -static int devm_hwmon_match(struct device *dev, void *res, void *data) -{ - struct device **hwdev = res; - - return *hwdev == data; -} - -/** - * devm_hwmon_device_unregister - removes a previously registered hwmon device - * - * @dev: the parent device of the device to unregister - */ -void devm_hwmon_device_unregister(struct device *dev) -{ - WARN_ON(devres_release(dev, devm_hwmon_release, devm_hwmon_match, dev)); -} -EXPORT_SYMBOL_GPL(devm_hwmon_device_unregister); - static char *__hwmon_sanitize_name(struct device *dev, const char *old_name) { char *name, *p; diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index e94314760aab..5c6a421ad580 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -481,7 +481,6 @@ devm_hwmon_device_register_with_info(struct device *dev, const struct attribute_group **extra_groups); void hwmon_device_unregister(struct device *dev); -void devm_hwmon_device_unregister(struct device *dev); int hwmon_notify_event(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel); -- cgit v1.2.3 From d175ee98fe545d2c56df22751314584cce228307 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 2 Sep 2024 21:17:18 +0200 Subject: mm: Define VM_DROPPABLE for powerpc/32 Commit 9651fcedf7b9 ("mm: add MAP_DROPPABLE for designating always lazily freeable mappings") only adds VM_DROPPABLE for 64 bits architectures. In order to also use the getrandom vDSO implementation on powerpc/32, use VM_ARCH_1 for VM_DROPPABLE on powerpc/32. This is possible because VM_ARCH_1 is used for VM_SAO on powerpc and VM_SAO is only for powerpc/64. It is used in combination with PROT_SAO in some parts of code that are restricted to CONFIG_PPC64 through #ifdefs, it is therefore possible to define VM_SAO for CONFIG_PPC64 only. Signed-off-by: Christophe Leroy Acked-by: Michael Ellerman Signed-off-by: Jason A. Donenfeld --- fs/proc/task_mmu.c | 4 +++- include/linux/mm.h | 4 +++- include/trace/events/mmflags.h | 4 ++-- 3 files changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 5f171ad7b436..3a07e13e2f81 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -987,8 +987,10 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) #ifdef CONFIG_X86_USER_SHADOW_STACK [ilog2(VM_SHADOW_STACK)] = "ss", #endif -#ifdef CONFIG_64BIT +#if defined(CONFIG_64BIT) || defined(CONFIG_PPC32) [ilog2(VM_DROPPABLE)] = "dp", +#endif +#ifdef CONFIG_64BIT [ilog2(VM_SEALED)] = "sl", #endif }; diff --git a/include/linux/mm.h b/include/linux/mm.h index 6549d0979b28..028847f39442 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -359,7 +359,7 @@ extern unsigned int kobjsize(const void *objp); #if defined(CONFIG_X86) # define VM_PAT VM_ARCH_1 /* PAT reserves whole VMA at once (x86) */ -#elif defined(CONFIG_PPC) +#elif defined(CONFIG_PPC64) # define VM_SAO VM_ARCH_1 /* Strong Access Ordering (powerpc) */ #elif defined(CONFIG_PARISC) # define VM_GROWSUP VM_ARCH_1 @@ -409,6 +409,8 @@ extern unsigned int kobjsize(const void *objp); #ifdef CONFIG_64BIT #define VM_DROPPABLE_BIT 40 #define VM_DROPPABLE BIT(VM_DROPPABLE_BIT) +#elif defined(CONFIG_PPC32) +#define VM_DROPPABLE VM_ARCH_1 #else #define VM_DROPPABLE VM_NONE #endif diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index b63d211bd141..37265977d524 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -143,7 +143,7 @@ IF_HAVE_PG_ARCH_X(arch_3) #if defined(CONFIG_X86) #define __VM_ARCH_SPECIFIC_1 {VM_PAT, "pat" } -#elif defined(CONFIG_PPC) +#elif defined(CONFIG_PPC64) #define __VM_ARCH_SPECIFIC_1 {VM_SAO, "sao" } #elif defined(CONFIG_PARISC) #define __VM_ARCH_SPECIFIC_1 {VM_GROWSUP, "growsup" } @@ -165,7 +165,7 @@ IF_HAVE_PG_ARCH_X(arch_3) # define IF_HAVE_UFFD_MINOR(flag, name) #endif -#ifdef CONFIG_64BIT +#if defined(CONFIG_64BIT) || defined(CONFIG_PPC32) # define IF_HAVE_VM_DROPPABLE(flag, name) {flag, name}, #else # define IF_HAVE_VM_DROPPABLE(flag, name) -- cgit v1.2.3 From 2b018086143d638de8d67ae5be6e8c1afb413193 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Fri, 13 Sep 2024 11:28:46 -0700 Subject: blk-mq: unconditional nr_integrity_segments Always defining the field will make using it easier and less error prone in future patches. There shouldn't be any downside to this: the field fits in what would otherwise be a 2-byte hole, so we're not saving space by conditionally leaving it out. Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Signed-off-by: Keith Busch Link: https://lore.kernel.org/r/20240913182854.2445457-2-kbusch@meta.com Signed-off-by: Jens Axboe --- block/blk-mq.c | 2 -- include/linux/blk-mq.h | 3 --- 2 files changed, 5 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index 3f1f7d0b3ff3..ef3a2ed49956 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -376,9 +376,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, rq->io_start_time_ns = 0; rq->stats_sectors = 0; rq->nr_phys_segments = 0; -#if defined(CONFIG_BLK_DEV_INTEGRITY) rq->nr_integrity_segments = 0; -#endif rq->end_io = NULL; rq->end_io_data = NULL; diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 8d304b1d16b1..4fecf46ef681 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -149,10 +149,7 @@ struct request { * physical address coalescing is performed. */ unsigned short nr_phys_segments; - -#ifdef CONFIG_BLK_DEV_INTEGRITY unsigned short nr_integrity_segments; -#endif #ifdef CONFIG_BLK_INLINE_ENCRYPTION struct bio_crypt_ctx *crypt_ctx; -- cgit v1.2.3 From d2c5b1faccd5ef6352456f817e941945d3b3fe62 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Fri, 13 Sep 2024 11:28:50 -0700 Subject: block: provide a request helper for user integrity segments Provide a helper to keep the request flags and nr_integrity_segments in sync with the bio's integrity payload. This is an integrity equivalent to the normal data helper function, 'blk_rq_map_user()'. Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Kanchan Joshi Signed-off-by: Keith Busch Link: https://lore.kernel.org/r/20240913182854.2445457-6-kbusch@meta.com Signed-off-by: Jens Axboe --- block/bio-integrity.c | 1 - block/blk-integrity.c | 14 ++++++++++++++ drivers/nvme/host/ioctl.c | 6 ++---- include/linux/blk-integrity.h | 9 +++++++++ 4 files changed, 25 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/block/bio-integrity.c b/block/bio-integrity.c index 8d1fb38f745f..357a022eed41 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -371,7 +371,6 @@ free_bvec: kfree(bvec); return ret; } -EXPORT_SYMBOL_GPL(bio_integrity_map_user); /** * bio_integrity_prep - Prepare bio for integrity I/O diff --git a/block/blk-integrity.c b/block/blk-integrity.c index 84065691aaed..ddc742d58330 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -107,6 +107,20 @@ new_segment: } EXPORT_SYMBOL(blk_rq_map_integrity_sg); +int blk_rq_integrity_map_user(struct request *rq, void __user *ubuf, + ssize_t bytes, u32 seed) +{ + int ret = bio_integrity_map_user(rq->bio, ubuf, bytes, seed); + + if (ret) + return ret; + + rq->nr_integrity_segments = blk_rq_count_integrity_sg(rq->q, rq->bio); + rq->cmd_flags |= REQ_INTEGRITY; + return 0; +} +EXPORT_SYMBOL_GPL(blk_rq_integrity_map_user); + bool blk_integrity_merge_rq(struct request_queue *q, struct request *req, struct request *next) { diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index 1d769c842fbf..b9b79ccfabf8 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -3,7 +3,6 @@ * Copyright (c) 2011-2014, Intel Corporation. * Copyright (c) 2017-2021 Christoph Hellwig. */ -#include #include #include /* for force_successful_syscall_return */ #include @@ -153,11 +152,10 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer, bio_set_dev(bio, bdev); if (has_metadata) { - ret = bio_integrity_map_user(bio, meta_buffer, meta_len, - meta_seed); + ret = blk_rq_integrity_map_user(req, meta_buffer, meta_len, + meta_seed); if (ret) goto out_unmap; - req->cmd_flags |= REQ_INTEGRITY; } return ret; diff --git a/include/linux/blk-integrity.h b/include/linux/blk-integrity.h index de98049b7ded..793dbb1e0672 100644 --- a/include/linux/blk-integrity.h +++ b/include/linux/blk-integrity.h @@ -28,6 +28,8 @@ static inline bool queue_limits_stack_integrity_bdev(struct queue_limits *t, int blk_rq_map_integrity_sg(struct request_queue *, struct bio *, struct scatterlist *); int blk_rq_count_integrity_sg(struct request_queue *, struct bio *); +int blk_rq_integrity_map_user(struct request *rq, void __user *ubuf, + ssize_t bytes, u32 seed); static inline bool blk_integrity_queue_supports_integrity(struct request_queue *q) @@ -102,6 +104,13 @@ static inline int blk_rq_map_integrity_sg(struct request_queue *q, { return 0; } +static inline int blk_rq_integrity_map_user(struct request *rq, + void __user *ubuf, + ssize_t bytes, + u32 seed) +{ + return -EINVAL; +} static inline struct blk_integrity *bdev_get_integrity(struct block_device *b) { return NULL; -- cgit v1.2.3 From 76c313f658d2752e8527610677164aa7094ef7a5 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Fri, 13 Sep 2024 12:17:46 -0700 Subject: blk-integrity: improved sg segment mapping Make the integrity mapping more like data mapping, blk_rq_map_sg. Use the request to validate the segment count, and update the callers so they don't have to. Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Signed-off-by: Keith Busch Link: https://lore.kernel.org/r/20240913191746.2628196-1-kbusch@meta.com Signed-off-by: Jens Axboe --- block/blk-integrity.c | 15 +++++++++++---- drivers/nvme/host/rdma.c | 4 ++-- drivers/scsi/scsi_lib.c | 11 +++-------- include/linux/blk-integrity.h | 6 ++---- 4 files changed, 18 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/block/blk-integrity.c b/block/blk-integrity.c index 1d82b18e06f8..0a2b1c5d0ebf 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -62,19 +62,20 @@ new_segment: * * Description: Map the integrity vectors in request into a * scatterlist. The scatterlist must be big enough to hold all - * elements. I.e. sized using blk_rq_count_integrity_sg(). + * elements. I.e. sized using blk_rq_count_integrity_sg() or + * rq->nr_integrity_segments. */ -int blk_rq_map_integrity_sg(struct request_queue *q, struct bio *bio, - struct scatterlist *sglist) +int blk_rq_map_integrity_sg(struct request *rq, struct scatterlist *sglist) { struct bio_vec iv, ivprv = { NULL }; + struct request_queue *q = rq->q; struct scatterlist *sg = NULL; + struct bio *bio = rq->bio; unsigned int segments = 0; struct bvec_iter iter; int prev = 0; bio_for_each_integrity_vec(iv, bio, iter) { - if (prev) { if (!biovec_phys_mergeable(q, &ivprv, &iv)) goto new_segment; @@ -102,6 +103,12 @@ new_segment: if (sg) sg_mark_end(sg); + /* + * Something must have been wrong if the figured number of segment + * is bigger than number of req's physical integrity segments + */ + BUG_ON(segments > rq->nr_integrity_segments); + BUG_ON(segments > queue_max_integrity_segments(q)); return segments; } EXPORT_SYMBOL(blk_rq_map_integrity_sg); diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 256466bdaee7..c8fd0e8f0237 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1504,8 +1504,8 @@ static int nvme_rdma_dma_map_req(struct ib_device *ibdev, struct request *rq, goto out_unmap_sg; } - req->metadata_sgl->nents = blk_rq_map_integrity_sg(rq->q, - rq->bio, req->metadata_sgl->sg_table.sgl); + req->metadata_sgl->nents = blk_rq_map_integrity_sg(rq, + req->metadata_sgl->sg_table.sgl); *pi_count = ib_dma_map_sg(ibdev, req->metadata_sgl->sg_table.sgl, req->metadata_sgl->nents, diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index c602b0af745c..c2f6d0e1c03e 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1163,7 +1163,6 @@ blk_status_t scsi_alloc_sgtables(struct scsi_cmnd *cmd) if (blk_integrity_rq(rq)) { struct scsi_data_buffer *prot_sdb = cmd->prot_sdb; - int ivecs; if (WARN_ON_ONCE(!prot_sdb)) { /* @@ -1175,19 +1174,15 @@ blk_status_t scsi_alloc_sgtables(struct scsi_cmnd *cmd) goto out_free_sgtables; } - ivecs = rq->nr_integrity_segments; - if (sg_alloc_table_chained(&prot_sdb->table, ivecs, + if (sg_alloc_table_chained(&prot_sdb->table, + rq->nr_integrity_segments, prot_sdb->table.sgl, SCSI_INLINE_PROT_SG_CNT)) { ret = BLK_STS_RESOURCE; goto out_free_sgtables; } - count = blk_rq_map_integrity_sg(rq->q, rq->bio, - prot_sdb->table.sgl); - BUG_ON(count > ivecs); - BUG_ON(count > queue_max_integrity_segments(rq->q)); - + count = blk_rq_map_integrity_sg(rq, prot_sdb->table.sgl); cmd->prot_sdb = prot_sdb; cmd->prot_sdb->table.nents = count; } diff --git a/include/linux/blk-integrity.h b/include/linux/blk-integrity.h index 793dbb1e0672..676f8f860c47 100644 --- a/include/linux/blk-integrity.h +++ b/include/linux/blk-integrity.h @@ -25,8 +25,7 @@ static inline bool queue_limits_stack_integrity_bdev(struct queue_limits *t, } #ifdef CONFIG_BLK_DEV_INTEGRITY -int blk_rq_map_integrity_sg(struct request_queue *, struct bio *, - struct scatterlist *); +int blk_rq_map_integrity_sg(struct request *, struct scatterlist *); int blk_rq_count_integrity_sg(struct request_queue *, struct bio *); int blk_rq_integrity_map_user(struct request *rq, void __user *ubuf, ssize_t bytes, u32 seed); @@ -98,8 +97,7 @@ static inline int blk_rq_count_integrity_sg(struct request_queue *q, { return 0; } -static inline int blk_rq_map_integrity_sg(struct request_queue *q, - struct bio *b, +static inline int blk_rq_map_integrity_sg(struct request *q, struct scatterlist *s) { return 0; -- cgit v1.2.3 From 32556ce93bc45c730829083cb60f95a2728ea48b Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 13 Sep 2024 21:17:48 +0200 Subject: bpf: Fix helper writes to read-only maps Lonial found an issue that despite user- and BPF-side frozen BPF map (like in case of .rodata), it was still possible to write into it from a BPF program side through specific helpers having ARG_PTR_TO_{LONG,INT} as arguments. In check_func_arg() when the argument is as mentioned, the meta->raw_mode is never set. Later, check_helper_mem_access(), under the case of PTR_TO_MAP_VALUE as register base type, it assumes BPF_READ for the subsequent call to check_map_access_type() and given the BPF map is read-only it succeeds. The helpers really need to be annotated as ARG_PTR_TO_{LONG,INT} | MEM_UNINIT when results are written into them as opposed to read out of them. The latter indicates that it's okay to pass a pointer to uninitialized memory as the memory is written to anyway. However, ARG_PTR_TO_{LONG,INT} is a special case of ARG_PTR_TO_FIXED_SIZE_MEM just with additional alignment requirement. So it is better to just get rid of the ARG_PTR_TO_{LONG,INT} special cases altogether and reuse the fixed size memory types. For this, add MEM_ALIGNED to additionally ensure alignment given these helpers write directly into the args via * = val. The .arg*_size has been initialized reflecting the actual sizeof(*). MEM_ALIGNED can only be used in combination with MEM_FIXED_SIZE annotated argument types, since in !MEM_FIXED_SIZE cases the verifier does not know the buffer size a priori and therefore cannot blindly write * = val. Fixes: 57c3bb725a3d ("bpf: Introduce ARG_PTR_TO_{INT,LONG} arg types") Reported-by: Lonial Con Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Acked-by: Shung-Hsi Yu Link: https://lore.kernel.org/r/20240913191754.13290-3-daniel@iogearbox.net Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 7 +++++-- kernel/bpf/helpers.c | 6 ++++-- kernel/bpf/syscall.c | 3 ++- kernel/bpf/verifier.c | 41 +++++------------------------------------ kernel/trace/bpf_trace.c | 6 ++++-- net/core/filter.c | 6 ++++-- 6 files changed, 24 insertions(+), 45 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 7f3e8477d5e7..0c3893c47171 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -695,6 +695,11 @@ enum bpf_type_flag { /* DYNPTR points to xdp_buff */ DYNPTR_TYPE_XDP = BIT(16 + BPF_BASE_TYPE_BITS), + /* Memory must be aligned on some architectures, used in combination with + * MEM_FIXED_SIZE. + */ + MEM_ALIGNED = BIT(17 + BPF_BASE_TYPE_BITS), + __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; @@ -732,8 +737,6 @@ enum bpf_arg_type { ARG_ANYTHING, /* any (initialized) argument is ok */ ARG_PTR_TO_SPIN_LOCK, /* pointer to bpf_spin_lock */ ARG_PTR_TO_SOCK_COMMON, /* pointer to sock_common */ - ARG_PTR_TO_INT, /* pointer to int */ - ARG_PTR_TO_LONG, /* pointer to long */ ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */ ARG_PTR_TO_BTF_ID, /* pointer to in-kernel struct */ ARG_PTR_TO_RINGBUF_MEM, /* pointer to dynamically reserved ringbuf memory */ diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 5404bb964d83..5e97fdc6b20f 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -537,7 +537,8 @@ const struct bpf_func_proto bpf_strtol_proto = { .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_LONG, + .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg4_size = sizeof(s64), }; BPF_CALL_4(bpf_strtoul, const char *, buf, size_t, buf_len, u64, flags, @@ -563,7 +564,8 @@ const struct bpf_func_proto bpf_strtoul_proto = { .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_LONG, + .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg4_size = sizeof(u64), }; BPF_CALL_3(bpf_strncmp, const char *, s1, u32, s1_sz, const char *, s2) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 6988e432fc3d..a7cd3719e26a 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -5954,7 +5954,8 @@ static const struct bpf_func_proto bpf_kallsyms_lookup_name_proto = { .arg1_type = ARG_PTR_TO_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_LONG, + .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg4_size = sizeof(u64), }; static const struct bpf_func_proto * diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 068f763dcefb..7d62fd576089 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8301,16 +8301,6 @@ static bool arg_type_is_dynptr(enum bpf_arg_type type) return base_type(type) == ARG_PTR_TO_DYNPTR; } -static int int_ptr_type_to_size(enum bpf_arg_type type) -{ - if (type == ARG_PTR_TO_INT) - return sizeof(u32); - else if (type == ARG_PTR_TO_LONG) - return sizeof(u64); - - return -EINVAL; -} - static int resolve_map_arg_type(struct bpf_verifier_env *env, const struct bpf_call_arg_meta *meta, enum bpf_arg_type *arg_type) @@ -8383,16 +8373,6 @@ static const struct bpf_reg_types mem_types = { }, }; -static const struct bpf_reg_types int_ptr_types = { - .types = { - PTR_TO_STACK, - PTR_TO_PACKET, - PTR_TO_PACKET_META, - PTR_TO_MAP_KEY, - PTR_TO_MAP_VALUE, - }, -}; - static const struct bpf_reg_types spin_lock_types = { .types = { PTR_TO_MAP_VALUE, @@ -8453,8 +8433,6 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = { [ARG_PTR_TO_SPIN_LOCK] = &spin_lock_types, [ARG_PTR_TO_MEM] = &mem_types, [ARG_PTR_TO_RINGBUF_MEM] = &ringbuf_mem_types, - [ARG_PTR_TO_INT] = &int_ptr_types, - [ARG_PTR_TO_LONG] = &int_ptr_types, [ARG_PTR_TO_PERCPU_BTF_ID] = &percpu_btf_ptr_types, [ARG_PTR_TO_FUNC] = &func_ptr_types, [ARG_PTR_TO_STACK] = &stack_ptr_types, @@ -9017,9 +8995,11 @@ skip_type_check: */ meta->raw_mode = arg_type & MEM_UNINIT; if (arg_type & MEM_FIXED_SIZE) { - err = check_helper_mem_access(env, regno, - fn->arg_size[arg], false, - meta); + err = check_helper_mem_access(env, regno, fn->arg_size[arg], false, meta); + if (err) + return err; + if (arg_type & MEM_ALIGNED) + err = check_ptr_alignment(env, reg, 0, fn->arg_size[arg], true); } break; case ARG_CONST_SIZE: @@ -9044,17 +9024,6 @@ skip_type_check: if (err) return err; break; - case ARG_PTR_TO_INT: - case ARG_PTR_TO_LONG: - { - int size = int_ptr_type_to_size(arg_type); - - err = check_helper_mem_access(env, regno, size, false, meta); - if (err) - return err; - err = check_ptr_alignment(env, reg, 0, size, true); - break; - } case ARG_PTR_TO_CONST_STR: { err = check_reg_const_str(env, reg, regno); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 68b5905c6eb5..b3283c250e27 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1202,7 +1202,8 @@ static const struct bpf_func_proto bpf_get_func_arg_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, - .arg3_type = ARG_PTR_TO_LONG, + .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg3_size = sizeof(u64), }; BPF_CALL_2(get_func_ret, void *, ctx, u64 *, value) @@ -1218,7 +1219,8 @@ static const struct bpf_func_proto bpf_get_func_ret_proto = { .func = get_func_ret, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_LONG, + .arg2_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg2_size = sizeof(u64), }; BPF_CALL_1(get_func_arg_cnt, void *, ctx) diff --git a/net/core/filter.c b/net/core/filter.c index ecf2ddf633bf..d0550c87e520 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -6346,7 +6346,8 @@ static const struct bpf_func_proto bpf_skb_check_mtu_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, - .arg3_type = ARG_PTR_TO_INT, + .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg3_size = sizeof(u32), .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; @@ -6357,7 +6358,8 @@ static const struct bpf_func_proto bpf_xdp_check_mtu_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, - .arg3_type = ARG_PTR_TO_INT, + .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg3_size = sizeof(u32), .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; -- cgit v1.2.3 From 0cca961a026177af69044f10d6ae76d8ce043764 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Thu, 12 Sep 2024 11:00:25 +0530 Subject: PCI: Pass domain number to pci_bus_release_domain_nr() explicitly MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The pci_bus_release_domain_nr() API is supposed to free the domain number allocated by pci_bus_find_domain_nr(). Most of the callers of pci_bus_find_domain_nr(), store the domain number in pci_bus::domain_nr. As such, the pci_bus_release_domain_nr() implicitly frees the domain number by dereferencing 'struct pci_bus'. However, one of the callers of this API, the PCI endpoint subsystem, doesn't have 'struct pci_bus', so it only passes NULL. Due to this, the API will end up dereferencing the NULL pointer. To fix this issue, pass the domain number to this API explicitly. Since 'struct pci_bus' is not used for anything else other than extracting the domain number, it makes sense to pass the domain number directly. Fixes: 0328947c5032 ("PCI: endpoint: Assign PCI domain number for endpoint controllers") Closes: https://lore.kernel.org/linux-pci/c0c40ddb-bf64-4b22-9dd1-8dbb18aa2813@stanley.mountain Link: https://lore.kernel.org/linux-pci/20240912053025.25314-1-manivannan.sadhasivam@linaro.org Reported-by: Dan Carpenter Signed-off-by: Manivannan Sadhasivam [kwilczynski: commit log] Signed-off-by: Krzysztof Wilczyński --- drivers/pci/endpoint/pci-epc-core.c | 2 +- drivers/pci/pci.c | 14 +++++++------- drivers/pci/probe.c | 2 +- drivers/pci/remove.c | 2 +- include/linux/pci.h | 2 +- 5 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c index 085a2de8b923..17f007109255 100644 --- a/drivers/pci/endpoint/pci-epc-core.c +++ b/drivers/pci/endpoint/pci-epc-core.c @@ -840,7 +840,7 @@ void pci_epc_destroy(struct pci_epc *epc) device_unregister(&epc->dev); #ifdef CONFIG_PCI_DOMAINS_GENERIC - pci_bus_release_domain_nr(NULL, &epc->dev); + pci_bus_release_domain_nr(&epc->dev, epc->domain_nr); #endif } EXPORT_SYMBOL_GPL(pci_epc_destroy); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index e3a49f66982d..b86693c91753 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -6801,16 +6801,16 @@ static int of_pci_bus_find_domain_nr(struct device *parent) return ida_alloc(&pci_domain_nr_dynamic_ida, GFP_KERNEL); } -static void of_pci_bus_release_domain_nr(struct pci_bus *bus, struct device *parent) +static void of_pci_bus_release_domain_nr(struct device *parent, int domain_nr) { - if (bus->domain_nr < 0) + if (domain_nr < 0) return; /* Release domain from IDA where it was allocated. */ - if (of_get_pci_domain_nr(parent->of_node) == bus->domain_nr) - ida_free(&pci_domain_nr_static_ida, bus->domain_nr); + if (of_get_pci_domain_nr(parent->of_node) == domain_nr) + ida_free(&pci_domain_nr_static_ida, domain_nr); else - ida_free(&pci_domain_nr_dynamic_ida, bus->domain_nr); + ida_free(&pci_domain_nr_dynamic_ida, domain_nr); } int pci_bus_find_domain_nr(struct pci_bus *bus, struct device *parent) @@ -6819,11 +6819,11 @@ int pci_bus_find_domain_nr(struct pci_bus *bus, struct device *parent) acpi_pci_bus_find_domain_nr(bus); } -void pci_bus_release_domain_nr(struct pci_bus *bus, struct device *parent) +void pci_bus_release_domain_nr(struct device *parent, int domain_nr) { if (!acpi_disabled) return; - of_pci_bus_release_domain_nr(bus, parent); + of_pci_bus_release_domain_nr(parent, domain_nr); } #endif diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index b14b9876c030..e9e56bbb3b59 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -1061,7 +1061,7 @@ unregister: free: #ifdef CONFIG_PCI_DOMAINS_GENERIC - pci_bus_release_domain_nr(bus, parent); + pci_bus_release_domain_nr(parent, bus->domain_nr); #endif kfree(bus); return err; diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c index 910387e5bdbf..d2523fdf9bae 100644 --- a/drivers/pci/remove.c +++ b/drivers/pci/remove.c @@ -163,7 +163,7 @@ void pci_remove_root_bus(struct pci_bus *bus) #ifdef CONFIG_PCI_DOMAINS_GENERIC /* Release domain_nr if it was dynamically allocated */ if (host_bridge->domain_nr == PCI_DOMAIN_NR_NOT_SET) - pci_bus_release_domain_nr(bus, host_bridge->dev.parent); + pci_bus_release_domain_nr(host_bridge->dev.parent, bus->domain_nr); #endif pci_remove_bus(bus); diff --git a/include/linux/pci.h b/include/linux/pci.h index 4cf89a4b4cbc..37d97bef060f 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1884,7 +1884,7 @@ static inline int acpi_pci_bus_find_domain_nr(struct pci_bus *bus) { return 0; } #endif int pci_bus_find_domain_nr(struct pci_bus *bus, struct device *parent); -void pci_bus_release_domain_nr(struct pci_bus *bus, struct device *parent); +void pci_bus_release_domain_nr(struct device *parent, int domain_nr); #endif /* Some architectures require additional setup to direct VGA traffic */ -- cgit v1.2.3 From 1b8c9cb3151a541a4197d2bb449233064f747832 Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Thu, 12 Sep 2024 09:19:49 +0800 Subject: MIPS: Remove the obsoleted code for include/linux/mv643xx.h Most of the drivers which used this header have been deleted, most of these code is obsoleted, move the only defines that are actually used into arch/powerpc/platforms/chrp/pegasos_eth.c and delete the file completely. Signed-off-by: Gaosheng Cui Link: https://patch.msgid.link/20240912011949.2726928-1-cuigaosheng1@huawei.com Signed-off-by: Jakub Kicinski --- MAINTAINERS | 1 - arch/powerpc/platforms/chrp/pegasos_eth.c | 7 +- include/linux/mv643xx.h | 921 ------------------------------ 3 files changed, 5 insertions(+), 924 deletions(-) delete mode 100644 include/linux/mv643xx.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 0b1c49bf558d..77fcd6f802a5 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13593,7 +13593,6 @@ M: Sebastian Hesselbarth L: netdev@vger.kernel.org S: Maintained F: drivers/net/ethernet/marvell/mv643xx_eth.* -F: include/linux/mv643xx.h MARVELL MV88X3310 PHY DRIVER M: Russell King diff --git a/arch/powerpc/platforms/chrp/pegasos_eth.c b/arch/powerpc/platforms/chrp/pegasos_eth.c index 5c4f1a9ca154..6f4a41a9352a 100644 --- a/arch/powerpc/platforms/chrp/pegasos_eth.c +++ b/arch/powerpc/platforms/chrp/pegasos_eth.c @@ -14,7 +14,7 @@ #include #include #include -#include +#include #include #define PEGASOS2_MARVELL_REGBASE (0xf1000000) @@ -25,12 +25,15 @@ #define PEGASOS2_SRAM_BASE_ETH_PORT0 (PEGASOS2_SRAM_BASE) #define PEGASOS2_SRAM_BASE_ETH_PORT1 (PEGASOS2_SRAM_BASE_ETH_PORT0 + (PEGASOS2_SRAM_SIZE / 2) ) - #define PEGASOS2_SRAM_RXRING_SIZE (PEGASOS2_SRAM_SIZE/4) #define PEGASOS2_SRAM_TXRING_SIZE (PEGASOS2_SRAM_SIZE/4) #undef BE_VERBOSE +#define MV64340_BASE_ADDR_ENABLE 0x278 +#define MV64340_INTEGRATED_SRAM_BASE_ADDR 0x268 +#define MV64340_SRAM_CONFIG 0x380 + static struct resource mv643xx_eth_shared_resources[] = { [0] = { .name = "ethernet shared base", diff --git a/include/linux/mv643xx.h b/include/linux/mv643xx.h deleted file mode 100644 index 000b126acfb6..000000000000 --- a/include/linux/mv643xx.h +++ /dev/null @@ -1,921 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * mv643xx.h - MV-643XX Internal registers definition file. - * - * Copyright 2002 Momentum Computer, Inc. - * Author: Matthew Dharm - * Copyright 2002 GALILEO TECHNOLOGY, LTD. - */ -#ifndef __ASM_MV643XX_H -#define __ASM_MV643XX_H - -#include -#include -#include - -/****************************************/ -/* Processor Address Space */ -/****************************************/ - -/* DDR SDRAM BAR and size registers */ - -#define MV64340_CS_0_BASE_ADDR 0x008 -#define MV64340_CS_0_SIZE 0x010 -#define MV64340_CS_1_BASE_ADDR 0x208 -#define MV64340_CS_1_SIZE 0x210 -#define MV64340_CS_2_BASE_ADDR 0x018 -#define MV64340_CS_2_SIZE 0x020 -#define MV64340_CS_3_BASE_ADDR 0x218 -#define MV64340_CS_3_SIZE 0x220 - -/* Devices BAR and size registers */ - -#define MV64340_DEV_CS0_BASE_ADDR 0x028 -#define MV64340_DEV_CS0_SIZE 0x030 -#define MV64340_DEV_CS1_BASE_ADDR 0x228 -#define MV64340_DEV_CS1_SIZE 0x230 -#define MV64340_DEV_CS2_BASE_ADDR 0x248 -#define MV64340_DEV_CS2_SIZE 0x250 -#define MV64340_DEV_CS3_BASE_ADDR 0x038 -#define MV64340_DEV_CS3_SIZE 0x040 -#define MV64340_BOOTCS_BASE_ADDR 0x238 -#define MV64340_BOOTCS_SIZE 0x240 - -/* PCI 0 BAR and size registers */ - -#define MV64340_PCI_0_IO_BASE_ADDR 0x048 -#define MV64340_PCI_0_IO_SIZE 0x050 -#define MV64340_PCI_0_MEMORY0_BASE_ADDR 0x058 -#define MV64340_PCI_0_MEMORY0_SIZE 0x060 -#define MV64340_PCI_0_MEMORY1_BASE_ADDR 0x080 -#define MV64340_PCI_0_MEMORY1_SIZE 0x088 -#define MV64340_PCI_0_MEMORY2_BASE_ADDR 0x258 -#define MV64340_PCI_0_MEMORY2_SIZE 0x260 -#define MV64340_PCI_0_MEMORY3_BASE_ADDR 0x280 -#define MV64340_PCI_0_MEMORY3_SIZE 0x288 - -/* PCI 1 BAR and size registers */ -#define MV64340_PCI_1_IO_BASE_ADDR 0x090 -#define MV64340_PCI_1_IO_SIZE 0x098 -#define MV64340_PCI_1_MEMORY0_BASE_ADDR 0x0a0 -#define MV64340_PCI_1_MEMORY0_SIZE 0x0a8 -#define MV64340_PCI_1_MEMORY1_BASE_ADDR 0x0b0 -#define MV64340_PCI_1_MEMORY1_SIZE 0x0b8 -#define MV64340_PCI_1_MEMORY2_BASE_ADDR 0x2a0 -#define MV64340_PCI_1_MEMORY2_SIZE 0x2a8 -#define MV64340_PCI_1_MEMORY3_BASE_ADDR 0x2b0 -#define MV64340_PCI_1_MEMORY3_SIZE 0x2b8 - -/* SRAM base address */ -#define MV64340_INTEGRATED_SRAM_BASE_ADDR 0x268 - -/* internal registers space base address */ -#define MV64340_INTERNAL_SPACE_BASE_ADDR 0x068 - -/* Enables the CS , DEV_CS , PCI 0 and PCI 1 - windows above */ -#define MV64340_BASE_ADDR_ENABLE 0x278 - -/****************************************/ -/* PCI remap registers */ -/****************************************/ - /* PCI 0 */ -#define MV64340_PCI_0_IO_ADDR_REMAP 0x0f0 -#define MV64340_PCI_0_MEMORY0_LOW_ADDR_REMAP 0x0f8 -#define MV64340_PCI_0_MEMORY0_HIGH_ADDR_REMAP 0x320 -#define MV64340_PCI_0_MEMORY1_LOW_ADDR_REMAP 0x100 -#define MV64340_PCI_0_MEMORY1_HIGH_ADDR_REMAP 0x328 -#define MV64340_PCI_0_MEMORY2_LOW_ADDR_REMAP 0x2f8 -#define MV64340_PCI_0_MEMORY2_HIGH_ADDR_REMAP 0x330 -#define MV64340_PCI_0_MEMORY3_LOW_ADDR_REMAP 0x300 -#define MV64340_PCI_0_MEMORY3_HIGH_ADDR_REMAP 0x338 - /* PCI 1 */ -#define MV64340_PCI_1_IO_ADDR_REMAP 0x108 -#define MV64340_PCI_1_MEMORY0_LOW_ADDR_REMAP 0x110 -#define MV64340_PCI_1_MEMORY0_HIGH_ADDR_REMAP 0x340 -#define MV64340_PCI_1_MEMORY1_LOW_ADDR_REMAP 0x118 -#define MV64340_PCI_1_MEMORY1_HIGH_ADDR_REMAP 0x348 -#define MV64340_PCI_1_MEMORY2_LOW_ADDR_REMAP 0x310 -#define MV64340_PCI_1_MEMORY2_HIGH_ADDR_REMAP 0x350 -#define MV64340_PCI_1_MEMORY3_LOW_ADDR_REMAP 0x318 -#define MV64340_PCI_1_MEMORY3_HIGH_ADDR_REMAP 0x358 - -#define MV64340_CPU_PCI_0_HEADERS_RETARGET_CONTROL 0x3b0 -#define MV64340_CPU_PCI_0_HEADERS_RETARGET_BASE 0x3b8 -#define MV64340_CPU_PCI_1_HEADERS_RETARGET_CONTROL 0x3c0 -#define MV64340_CPU_PCI_1_HEADERS_RETARGET_BASE 0x3c8 -#define MV64340_CPU_GE_HEADERS_RETARGET_CONTROL 0x3d0 -#define MV64340_CPU_GE_HEADERS_RETARGET_BASE 0x3d8 -#define MV64340_CPU_IDMA_HEADERS_RETARGET_CONTROL 0x3e0 -#define MV64340_CPU_IDMA_HEADERS_RETARGET_BASE 0x3e8 - -/****************************************/ -/* CPU Control Registers */ -/****************************************/ - -#define MV64340_CPU_CONFIG 0x000 -#define MV64340_CPU_MODE 0x120 -#define MV64340_CPU_MASTER_CONTROL 0x160 -#define MV64340_CPU_CROSS_BAR_CONTROL_LOW 0x150 -#define MV64340_CPU_CROSS_BAR_CONTROL_HIGH 0x158 -#define MV64340_CPU_CROSS_BAR_TIMEOUT 0x168 - -/****************************************/ -/* SMP RegisterS */ -/****************************************/ - -#define MV64340_SMP_WHO_AM_I 0x200 -#define MV64340_SMP_CPU0_DOORBELL 0x214 -#define MV64340_SMP_CPU0_DOORBELL_CLEAR 0x21C -#define MV64340_SMP_CPU1_DOORBELL 0x224 -#define MV64340_SMP_CPU1_DOORBELL_CLEAR 0x22C -#define MV64340_SMP_CPU0_DOORBELL_MASK 0x234 -#define MV64340_SMP_CPU1_DOORBELL_MASK 0x23C -#define MV64340_SMP_SEMAPHOR0 0x244 -#define MV64340_SMP_SEMAPHOR1 0x24c -#define MV64340_SMP_SEMAPHOR2 0x254 -#define MV64340_SMP_SEMAPHOR3 0x25c -#define MV64340_SMP_SEMAPHOR4 0x264 -#define MV64340_SMP_SEMAPHOR5 0x26c -#define MV64340_SMP_SEMAPHOR6 0x274 -#define MV64340_SMP_SEMAPHOR7 0x27c - -/****************************************/ -/* CPU Sync Barrier Register */ -/****************************************/ - -#define MV64340_CPU_0_SYNC_BARRIER_TRIGGER 0x0c0 -#define MV64340_CPU_0_SYNC_BARRIER_VIRTUAL 0x0c8 -#define MV64340_CPU_1_SYNC_BARRIER_TRIGGER 0x0d0 -#define MV64340_CPU_1_SYNC_BARRIER_VIRTUAL 0x0d8 - -/****************************************/ -/* CPU Access Protect */ -/****************************************/ - -#define MV64340_CPU_PROTECT_WINDOW_0_BASE_ADDR 0x180 -#define MV64340_CPU_PROTECT_WINDOW_0_SIZE 0x188 -#define MV64340_CPU_PROTECT_WINDOW_1_BASE_ADDR 0x190 -#define MV64340_CPU_PROTECT_WINDOW_1_SIZE 0x198 -#define MV64340_CPU_PROTECT_WINDOW_2_BASE_ADDR 0x1a0 -#define MV64340_CPU_PROTECT_WINDOW_2_SIZE 0x1a8 -#define MV64340_CPU_PROTECT_WINDOW_3_BASE_ADDR 0x1b0 -#define MV64340_CPU_PROTECT_WINDOW_3_SIZE 0x1b8 - - -/****************************************/ -/* CPU Error Report */ -/****************************************/ - -#define MV64340_CPU_ERROR_ADDR_LOW 0x070 -#define MV64340_CPU_ERROR_ADDR_HIGH 0x078 -#define MV64340_CPU_ERROR_DATA_LOW 0x128 -#define MV64340_CPU_ERROR_DATA_HIGH 0x130 -#define MV64340_CPU_ERROR_PARITY 0x138 -#define MV64340_CPU_ERROR_CAUSE 0x140 -#define MV64340_CPU_ERROR_MASK 0x148 - -/****************************************/ -/* CPU Interface Debug Registers */ -/****************************************/ - -#define MV64340_PUNIT_SLAVE_DEBUG_LOW 0x360 -#define MV64340_PUNIT_SLAVE_DEBUG_HIGH 0x368 -#define MV64340_PUNIT_MASTER_DEBUG_LOW 0x370 -#define MV64340_PUNIT_MASTER_DEBUG_HIGH 0x378 -#define MV64340_PUNIT_MMASK 0x3e4 - -/****************************************/ -/* Integrated SRAM Registers */ -/****************************************/ - -#define MV64340_SRAM_CONFIG 0x380 -#define MV64340_SRAM_TEST_MODE 0X3F4 -#define MV64340_SRAM_ERROR_CAUSE 0x388 -#define MV64340_SRAM_ERROR_ADDR 0x390 -#define MV64340_SRAM_ERROR_ADDR_HIGH 0X3F8 -#define MV64340_SRAM_ERROR_DATA_LOW 0x398 -#define MV64340_SRAM_ERROR_DATA_HIGH 0x3a0 -#define MV64340_SRAM_ERROR_DATA_PARITY 0x3a8 - -/****************************************/ -/* SDRAM Configuration */ -/****************************************/ - -#define MV64340_SDRAM_CONFIG 0x1400 -#define MV64340_D_UNIT_CONTROL_LOW 0x1404 -#define MV64340_D_UNIT_CONTROL_HIGH 0x1424 -#define MV64340_SDRAM_TIMING_CONTROL_LOW 0x1408 -#define MV64340_SDRAM_TIMING_CONTROL_HIGH 0x140c -#define MV64340_SDRAM_ADDR_CONTROL 0x1410 -#define MV64340_SDRAM_OPEN_PAGES_CONTROL 0x1414 -#define MV64340_SDRAM_OPERATION 0x1418 -#define MV64340_SDRAM_MODE 0x141c -#define MV64340_EXTENDED_DRAM_MODE 0x1420 -#define MV64340_SDRAM_CROSS_BAR_CONTROL_LOW 0x1430 -#define MV64340_SDRAM_CROSS_BAR_CONTROL_HIGH 0x1434 -#define MV64340_SDRAM_CROSS_BAR_TIMEOUT 0x1438 -#define MV64340_SDRAM_ADDR_CTRL_PADS_CALIBRATION 0x14c0 -#define MV64340_SDRAM_DATA_PADS_CALIBRATION 0x14c4 - -/****************************************/ -/* SDRAM Error Report */ -/****************************************/ - -#define MV64340_SDRAM_ERROR_DATA_LOW 0x1444 -#define MV64340_SDRAM_ERROR_DATA_HIGH 0x1440 -#define MV64340_SDRAM_ERROR_ADDR 0x1450 -#define MV64340_SDRAM_RECEIVED_ECC 0x1448 -#define MV64340_SDRAM_CALCULATED_ECC 0x144c -#define MV64340_SDRAM_ECC_CONTROL 0x1454 -#define MV64340_SDRAM_ECC_ERROR_COUNTER 0x1458 - -/******************************************/ -/* Controlled Delay Line (CDL) Registers */ -/******************************************/ - -#define MV64340_DFCDL_CONFIG0 0x1480 -#define MV64340_DFCDL_CONFIG1 0x1484 -#define MV64340_DLL_WRITE 0x1488 -#define MV64340_DLL_READ 0x148c -#define MV64340_SRAM_ADDR 0x1490 -#define MV64340_SRAM_DATA0 0x1494 -#define MV64340_SRAM_DATA1 0x1498 -#define MV64340_SRAM_DATA2 0x149c -#define MV64340_DFCL_PROBE 0x14a0 - -/******************************************/ -/* Debug Registers */ -/******************************************/ - -#define MV64340_DUNIT_DEBUG_LOW 0x1460 -#define MV64340_DUNIT_DEBUG_HIGH 0x1464 -#define MV64340_DUNIT_MMASK 0X1b40 - -/****************************************/ -/* Device Parameters */ -/****************************************/ - -#define MV64340_DEVICE_BANK0_PARAMETERS 0x45c -#define MV64340_DEVICE_BANK1_PARAMETERS 0x460 -#define MV64340_DEVICE_BANK2_PARAMETERS 0x464 -#define MV64340_DEVICE_BANK3_PARAMETERS 0x468 -#define MV64340_DEVICE_BOOT_BANK_PARAMETERS 0x46c -#define MV64340_DEVICE_INTERFACE_CONTROL 0x4c0 -#define MV64340_DEVICE_INTERFACE_CROSS_BAR_CONTROL_LOW 0x4c8 -#define MV64340_DEVICE_INTERFACE_CROSS_BAR_CONTROL_HIGH 0x4cc -#define MV64340_DEVICE_INTERFACE_CROSS_BAR_TIMEOUT 0x4c4 - -/****************************************/ -/* Device interrupt registers */ -/****************************************/ - -#define MV64340_DEVICE_INTERRUPT_CAUSE 0x4d0 -#define MV64340_DEVICE_INTERRUPT_MASK 0x4d4 -#define MV64340_DEVICE_ERROR_ADDR 0x4d8 -#define MV64340_DEVICE_ERROR_DATA 0x4dc -#define MV64340_DEVICE_ERROR_PARITY 0x4e0 - -/****************************************/ -/* Device debug registers */ -/****************************************/ - -#define MV64340_DEVICE_DEBUG_LOW 0x4e4 -#define MV64340_DEVICE_DEBUG_HIGH 0x4e8 -#define MV64340_RUNIT_MMASK 0x4f0 - -/****************************************/ -/* PCI Slave Address Decoding registers */ -/****************************************/ - -#define MV64340_PCI_0_CS_0_BANK_SIZE 0xc08 -#define MV64340_PCI_1_CS_0_BANK_SIZE 0xc88 -#define MV64340_PCI_0_CS_1_BANK_SIZE 0xd08 -#define MV64340_PCI_1_CS_1_BANK_SIZE 0xd88 -#define MV64340_PCI_0_CS_2_BANK_SIZE 0xc0c -#define MV64340_PCI_1_CS_2_BANK_SIZE 0xc8c -#define MV64340_PCI_0_CS_3_BANK_SIZE 0xd0c -#define MV64340_PCI_1_CS_3_BANK_SIZE 0xd8c -#define MV64340_PCI_0_DEVCS_0_BANK_SIZE 0xc10 -#define MV64340_PCI_1_DEVCS_0_BANK_SIZE 0xc90 -#define MV64340_PCI_0_DEVCS_1_BANK_SIZE 0xd10 -#define MV64340_PCI_1_DEVCS_1_BANK_SIZE 0xd90 -#define MV64340_PCI_0_DEVCS_2_BANK_SIZE 0xd18 -#define MV64340_PCI_1_DEVCS_2_BANK_SIZE 0xd98 -#define MV64340_PCI_0_DEVCS_3_BANK_SIZE 0xc14 -#define MV64340_PCI_1_DEVCS_3_BANK_SIZE 0xc94 -#define MV64340_PCI_0_DEVCS_BOOT_BANK_SIZE 0xd14 -#define MV64340_PCI_1_DEVCS_BOOT_BANK_SIZE 0xd94 -#define MV64340_PCI_0_P2P_MEM0_BAR_SIZE 0xd1c -#define MV64340_PCI_1_P2P_MEM0_BAR_SIZE 0xd9c -#define MV64340_PCI_0_P2P_MEM1_BAR_SIZE 0xd20 -#define MV64340_PCI_1_P2P_MEM1_BAR_SIZE 0xda0 -#define MV64340_PCI_0_P2P_I_O_BAR_SIZE 0xd24 -#define MV64340_PCI_1_P2P_I_O_BAR_SIZE 0xda4 -#define MV64340_PCI_0_CPU_BAR_SIZE 0xd28 -#define MV64340_PCI_1_CPU_BAR_SIZE 0xda8 -#define MV64340_PCI_0_INTERNAL_SRAM_BAR_SIZE 0xe00 -#define MV64340_PCI_1_INTERNAL_SRAM_BAR_SIZE 0xe80 -#define MV64340_PCI_0_EXPANSION_ROM_BAR_SIZE 0xd2c -#define MV64340_PCI_1_EXPANSION_ROM_BAR_SIZE 0xd9c -#define MV64340_PCI_0_BASE_ADDR_REG_ENABLE 0xc3c -#define MV64340_PCI_1_BASE_ADDR_REG_ENABLE 0xcbc -#define MV64340_PCI_0_CS_0_BASE_ADDR_REMAP 0xc48 -#define MV64340_PCI_1_CS_0_BASE_ADDR_REMAP 0xcc8 -#define MV64340_PCI_0_CS_1_BASE_ADDR_REMAP 0xd48 -#define MV64340_PCI_1_CS_1_BASE_ADDR_REMAP 0xdc8 -#define MV64340_PCI_0_CS_2_BASE_ADDR_REMAP 0xc4c -#define MV64340_PCI_1_CS_2_BASE_ADDR_REMAP 0xccc -#define MV64340_PCI_0_CS_3_BASE_ADDR_REMAP 0xd4c -#define MV64340_PCI_1_CS_3_BASE_ADDR_REMAP 0xdcc -#define MV64340_PCI_0_CS_0_BASE_HIGH_ADDR_REMAP 0xF04 -#define MV64340_PCI_1_CS_0_BASE_HIGH_ADDR_REMAP 0xF84 -#define MV64340_PCI_0_CS_1_BASE_HIGH_ADDR_REMAP 0xF08 -#define MV64340_PCI_1_CS_1_BASE_HIGH_ADDR_REMAP 0xF88 -#define MV64340_PCI_0_CS_2_BASE_HIGH_ADDR_REMAP 0xF0C -#define MV64340_PCI_1_CS_2_BASE_HIGH_ADDR_REMAP 0xF8C -#define MV64340_PCI_0_CS_3_BASE_HIGH_ADDR_REMAP 0xF10 -#define MV64340_PCI_1_CS_3_BASE_HIGH_ADDR_REMAP 0xF90 -#define MV64340_PCI_0_DEVCS_0_BASE_ADDR_REMAP 0xc50 -#define MV64340_PCI_1_DEVCS_0_BASE_ADDR_REMAP 0xcd0 -#define MV64340_PCI_0_DEVCS_1_BASE_ADDR_REMAP 0xd50 -#define MV64340_PCI_1_DEVCS_1_BASE_ADDR_REMAP 0xdd0 -#define MV64340_PCI_0_DEVCS_2_BASE_ADDR_REMAP 0xd58 -#define MV64340_PCI_1_DEVCS_2_BASE_ADDR_REMAP 0xdd8 -#define MV64340_PCI_0_DEVCS_3_BASE_ADDR_REMAP 0xc54 -#define MV64340_PCI_1_DEVCS_3_BASE_ADDR_REMAP 0xcd4 -#define MV64340_PCI_0_DEVCS_BOOTCS_BASE_ADDR_REMAP 0xd54 -#define MV64340_PCI_1_DEVCS_BOOTCS_BASE_ADDR_REMAP 0xdd4 -#define MV64340_PCI_0_P2P_MEM0_BASE_ADDR_REMAP_LOW 0xd5c -#define MV64340_PCI_1_P2P_MEM0_BASE_ADDR_REMAP_LOW 0xddc -#define MV64340_PCI_0_P2P_MEM0_BASE_ADDR_REMAP_HIGH 0xd60 -#define MV64340_PCI_1_P2P_MEM0_BASE_ADDR_REMAP_HIGH 0xde0 -#define MV64340_PCI_0_P2P_MEM1_BASE_ADDR_REMAP_LOW 0xd64 -#define MV64340_PCI_1_P2P_MEM1_BASE_ADDR_REMAP_LOW 0xde4 -#define MV64340_PCI_0_P2P_MEM1_BASE_ADDR_REMAP_HIGH 0xd68 -#define MV64340_PCI_1_P2P_MEM1_BASE_ADDR_REMAP_HIGH 0xde8 -#define MV64340_PCI_0_P2P_I_O_BASE_ADDR_REMAP 0xd6c -#define MV64340_PCI_1_P2P_I_O_BASE_ADDR_REMAP 0xdec -#define MV64340_PCI_0_CPU_BASE_ADDR_REMAP_LOW 0xd70 -#define MV64340_PCI_1_CPU_BASE_ADDR_REMAP_LOW 0xdf0 -#define MV64340_PCI_0_CPU_BASE_ADDR_REMAP_HIGH 0xd74 -#define MV64340_PCI_1_CPU_BASE_ADDR_REMAP_HIGH 0xdf4 -#define MV64340_PCI_0_INTEGRATED_SRAM_BASE_ADDR_REMAP 0xf00 -#define MV64340_PCI_1_INTEGRATED_SRAM_BASE_ADDR_REMAP 0xf80 -#define MV64340_PCI_0_EXPANSION_ROM_BASE_ADDR_REMAP 0xf38 -#define MV64340_PCI_1_EXPANSION_ROM_BASE_ADDR_REMAP 0xfb8 -#define MV64340_PCI_0_ADDR_DECODE_CONTROL 0xd3c -#define MV64340_PCI_1_ADDR_DECODE_CONTROL 0xdbc -#define MV64340_PCI_0_HEADERS_RETARGET_CONTROL 0xF40 -#define MV64340_PCI_1_HEADERS_RETARGET_CONTROL 0xFc0 -#define MV64340_PCI_0_HEADERS_RETARGET_BASE 0xF44 -#define MV64340_PCI_1_HEADERS_RETARGET_BASE 0xFc4 -#define MV64340_PCI_0_HEADERS_RETARGET_HIGH 0xF48 -#define MV64340_PCI_1_HEADERS_RETARGET_HIGH 0xFc8 - -/***********************************/ -/* PCI Control Register Map */ -/***********************************/ - -#define MV64340_PCI_0_DLL_STATUS_AND_COMMAND 0x1d20 -#define MV64340_PCI_1_DLL_STATUS_AND_COMMAND 0x1da0 -#define MV64340_PCI_0_MPP_PADS_DRIVE_CONTROL 0x1d1C -#define MV64340_PCI_1_MPP_PADS_DRIVE_CONTROL 0x1d9C -#define MV64340_PCI_0_COMMAND 0xc00 -#define MV64340_PCI_1_COMMAND 0xc80 -#define MV64340_PCI_0_MODE 0xd00 -#define MV64340_PCI_1_MODE 0xd80 -#define MV64340_PCI_0_RETRY 0xc04 -#define MV64340_PCI_1_RETRY 0xc84 -#define MV64340_PCI_0_READ_BUFFER_DISCARD_TIMER 0xd04 -#define MV64340_PCI_1_READ_BUFFER_DISCARD_TIMER 0xd84 -#define MV64340_PCI_0_MSI_TRIGGER_TIMER 0xc38 -#define MV64340_PCI_1_MSI_TRIGGER_TIMER 0xcb8 -#define MV64340_PCI_0_ARBITER_CONTROL 0x1d00 -#define MV64340_PCI_1_ARBITER_CONTROL 0x1d80 -#define MV64340_PCI_0_CROSS_BAR_CONTROL_LOW 0x1d08 -#define MV64340_PCI_1_CROSS_BAR_CONTROL_LOW 0x1d88 -#define MV64340_PCI_0_CROSS_BAR_CONTROL_HIGH 0x1d0c -#define MV64340_PCI_1_CROSS_BAR_CONTROL_HIGH 0x1d8c -#define MV64340_PCI_0_CROSS_BAR_TIMEOUT 0x1d04 -#define MV64340_PCI_1_CROSS_BAR_TIMEOUT 0x1d84 -#define MV64340_PCI_0_SYNC_BARRIER_TRIGGER_REG 0x1D18 -#define MV64340_PCI_1_SYNC_BARRIER_TRIGGER_REG 0x1D98 -#define MV64340_PCI_0_SYNC_BARRIER_VIRTUAL_REG 0x1d10 -#define MV64340_PCI_1_SYNC_BARRIER_VIRTUAL_REG 0x1d90 -#define MV64340_PCI_0_P2P_CONFIG 0x1d14 -#define MV64340_PCI_1_P2P_CONFIG 0x1d94 - -#define MV64340_PCI_0_ACCESS_CONTROL_BASE_0_LOW 0x1e00 -#define MV64340_PCI_0_ACCESS_CONTROL_BASE_0_HIGH 0x1e04 -#define MV64340_PCI_0_ACCESS_CONTROL_SIZE_0 0x1e08 -#define MV64340_PCI_0_ACCESS_CONTROL_BASE_1_LOW 0x1e10 -#define MV64340_PCI_0_ACCESS_CONTROL_BASE_1_HIGH 0x1e14 -#define MV64340_PCI_0_ACCESS_CONTROL_SIZE_1 0x1e18 -#define MV64340_PCI_0_ACCESS_CONTROL_BASE_2_LOW 0x1e20 -#define MV64340_PCI_0_ACCESS_CONTROL_BASE_2_HIGH 0x1e24 -#define MV64340_PCI_0_ACCESS_CONTROL_SIZE_2 0x1e28 -#define MV64340_PCI_0_ACCESS_CONTROL_BASE_3_LOW 0x1e30 -#define MV64340_PCI_0_ACCESS_CONTROL_BASE_3_HIGH 0x1e34 -#define MV64340_PCI_0_ACCESS_CONTROL_SIZE_3 0x1e38 -#define MV64340_PCI_0_ACCESS_CONTROL_BASE_4_LOW 0x1e40 -#define MV64340_PCI_0_ACCESS_CONTROL_BASE_4_HIGH 0x1e44 -#define MV64340_PCI_0_ACCESS_CONTROL_SIZE_4 0x1e48 -#define MV64340_PCI_0_ACCESS_CONTROL_BASE_5_LOW 0x1e50 -#define MV64340_PCI_0_ACCESS_CONTROL_BASE_5_HIGH 0x1e54 -#define MV64340_PCI_0_ACCESS_CONTROL_SIZE_5 0x1e58 - -#define MV64340_PCI_1_ACCESS_CONTROL_BASE_0_LOW 0x1e80 -#define MV64340_PCI_1_ACCESS_CONTROL_BASE_0_HIGH 0x1e84 -#define MV64340_PCI_1_ACCESS_CONTROL_SIZE_0 0x1e88 -#define MV64340_PCI_1_ACCESS_CONTROL_BASE_1_LOW 0x1e90 -#define MV64340_PCI_1_ACCESS_CONTROL_BASE_1_HIGH 0x1e94 -#define MV64340_PCI_1_ACCESS_CONTROL_SIZE_1 0x1e98 -#define MV64340_PCI_1_ACCESS_CONTROL_BASE_2_LOW 0x1ea0 -#define MV64340_PCI_1_ACCESS_CONTROL_BASE_2_HIGH 0x1ea4 -#define MV64340_PCI_1_ACCESS_CONTROL_SIZE_2 0x1ea8 -#define MV64340_PCI_1_ACCESS_CONTROL_BASE_3_LOW 0x1eb0 -#define MV64340_PCI_1_ACCESS_CONTROL_BASE_3_HIGH 0x1eb4 -#define MV64340_PCI_1_ACCESS_CONTROL_SIZE_3 0x1eb8 -#define MV64340_PCI_1_ACCESS_CONTROL_BASE_4_LOW 0x1ec0 -#define MV64340_PCI_1_ACCESS_CONTROL_BASE_4_HIGH 0x1ec4 -#define MV64340_PCI_1_ACCESS_CONTROL_SIZE_4 0x1ec8 -#define MV64340_PCI_1_ACCESS_CONTROL_BASE_5_LOW 0x1ed0 -#define MV64340_PCI_1_ACCESS_CONTROL_BASE_5_HIGH 0x1ed4 -#define MV64340_PCI_1_ACCESS_CONTROL_SIZE_5 0x1ed8 - -/****************************************/ -/* PCI Configuration Access Registers */ -/****************************************/ - -#define MV64340_PCI_0_CONFIG_ADDR 0xcf8 -#define MV64340_PCI_0_CONFIG_DATA_VIRTUAL_REG 0xcfc -#define MV64340_PCI_1_CONFIG_ADDR 0xc78 -#define MV64340_PCI_1_CONFIG_DATA_VIRTUAL_REG 0xc7c -#define MV64340_PCI_0_INTERRUPT_ACKNOWLEDGE_VIRTUAL_REG 0xc34 -#define MV64340_PCI_1_INTERRUPT_ACKNOWLEDGE_VIRTUAL_REG 0xcb4 - -/****************************************/ -/* PCI Error Report Registers */ -/****************************************/ - -#define MV64340_PCI_0_SERR_MASK 0xc28 -#define MV64340_PCI_1_SERR_MASK 0xca8 -#define MV64340_PCI_0_ERROR_ADDR_LOW 0x1d40 -#define MV64340_PCI_1_ERROR_ADDR_LOW 0x1dc0 -#define MV64340_PCI_0_ERROR_ADDR_HIGH 0x1d44 -#define MV64340_PCI_1_ERROR_ADDR_HIGH 0x1dc4 -#define MV64340_PCI_0_ERROR_ATTRIBUTE 0x1d48 -#define MV64340_PCI_1_ERROR_ATTRIBUTE 0x1dc8 -#define MV64340_PCI_0_ERROR_COMMAND 0x1d50 -#define MV64340_PCI_1_ERROR_COMMAND 0x1dd0 -#define MV64340_PCI_0_ERROR_CAUSE 0x1d58 -#define MV64340_PCI_1_ERROR_CAUSE 0x1dd8 -#define MV64340_PCI_0_ERROR_MASK 0x1d5c -#define MV64340_PCI_1_ERROR_MASK 0x1ddc - -/****************************************/ -/* PCI Debug Registers */ -/****************************************/ - -#define MV64340_PCI_0_MMASK 0X1D24 -#define MV64340_PCI_1_MMASK 0X1DA4 - -/*********************************************/ -/* PCI Configuration, Function 0, Registers */ -/*********************************************/ - -#define MV64340_PCI_DEVICE_AND_VENDOR_ID 0x000 -#define MV64340_PCI_STATUS_AND_COMMAND 0x004 -#define MV64340_PCI_CLASS_CODE_AND_REVISION_ID 0x008 -#define MV64340_PCI_BIST_HEADER_TYPE_LATENCY_TIMER_CACHE_LINE 0x00C - -#define MV64340_PCI_SCS_0_BASE_ADDR_LOW 0x010 -#define MV64340_PCI_SCS_0_BASE_ADDR_HIGH 0x014 -#define MV64340_PCI_SCS_1_BASE_ADDR_LOW 0x018 -#define MV64340_PCI_SCS_1_BASE_ADDR_HIGH 0x01C -#define MV64340_PCI_INTERNAL_REG_MEM_MAPPED_BASE_ADDR_LOW 0x020 -#define MV64340_PCI_INTERNAL_REG_MEM_MAPPED_BASE_ADDR_HIGH 0x024 -#define MV64340_PCI_SUBSYSTEM_ID_AND_SUBSYSTEM_VENDOR_ID 0x02c -#define MV64340_PCI_EXPANSION_ROM_BASE_ADDR_REG 0x030 -#define MV64340_PCI_CAPABILTY_LIST_POINTER 0x034 -#define MV64340_PCI_INTERRUPT_PIN_AND_LINE 0x03C - /* capability list */ -#define MV64340_PCI_POWER_MANAGEMENT_CAPABILITY 0x040 -#define MV64340_PCI_POWER_MANAGEMENT_STATUS_AND_CONTROL 0x044 -#define MV64340_PCI_VPD_ADDR 0x048 -#define MV64340_PCI_VPD_DATA 0x04c -#define MV64340_PCI_MSI_MESSAGE_CONTROL 0x050 -#define MV64340_PCI_MSI_MESSAGE_ADDR 0x054 -#define MV64340_PCI_MSI_MESSAGE_UPPER_ADDR 0x058 -#define MV64340_PCI_MSI_MESSAGE_DATA 0x05c -#define MV64340_PCI_X_COMMAND 0x060 -#define MV64340_PCI_X_STATUS 0x064 -#define MV64340_PCI_COMPACT_PCI_HOT_SWAP 0x068 - -/***********************************************/ -/* PCI Configuration, Function 1, Registers */ -/***********************************************/ - -#define MV64340_PCI_SCS_2_BASE_ADDR_LOW 0x110 -#define MV64340_PCI_SCS_2_BASE_ADDR_HIGH 0x114 -#define MV64340_PCI_SCS_3_BASE_ADDR_LOW 0x118 -#define MV64340_PCI_SCS_3_BASE_ADDR_HIGH 0x11c -#define MV64340_PCI_INTERNAL_SRAM_BASE_ADDR_LOW 0x120 -#define MV64340_PCI_INTERNAL_SRAM_BASE_ADDR_HIGH 0x124 - -/***********************************************/ -/* PCI Configuration, Function 2, Registers */ -/***********************************************/ - -#define MV64340_PCI_DEVCS_0_BASE_ADDR_LOW 0x210 -#define MV64340_PCI_DEVCS_0_BASE_ADDR_HIGH 0x214 -#define MV64340_PCI_DEVCS_1_BASE_ADDR_LOW 0x218 -#define MV64340_PCI_DEVCS_1_BASE_ADDR_HIGH 0x21c -#define MV64340_PCI_DEVCS_2_BASE_ADDR_LOW 0x220 -#define MV64340_PCI_DEVCS_2_BASE_ADDR_HIGH 0x224 - -/***********************************************/ -/* PCI Configuration, Function 3, Registers */ -/***********************************************/ - -#define MV64340_PCI_DEVCS_3_BASE_ADDR_LOW 0x310 -#define MV64340_PCI_DEVCS_3_BASE_ADDR_HIGH 0x314 -#define MV64340_PCI_BOOT_CS_BASE_ADDR_LOW 0x318 -#define MV64340_PCI_BOOT_CS_BASE_ADDR_HIGH 0x31c -#define MV64340_PCI_CPU_BASE_ADDR_LOW 0x220 -#define MV64340_PCI_CPU_BASE_ADDR_HIGH 0x224 - -/***********************************************/ -/* PCI Configuration, Function 4, Registers */ -/***********************************************/ - -#define MV64340_PCI_P2P_MEM0_BASE_ADDR_LOW 0x410 -#define MV64340_PCI_P2P_MEM0_BASE_ADDR_HIGH 0x414 -#define MV64340_PCI_P2P_MEM1_BASE_ADDR_LOW 0x418 -#define MV64340_PCI_P2P_MEM1_BASE_ADDR_HIGH 0x41c -#define MV64340_PCI_P2P_I_O_BASE_ADDR 0x420 -#define MV64340_PCI_INTERNAL_REGS_I_O_MAPPED_BASE_ADDR 0x424 - -/****************************************/ -/* Messaging Unit Registers (I20) */ -/****************************************/ - -#define MV64340_I2O_INBOUND_MESSAGE_REG0_PCI_0_SIDE 0x010 -#define MV64340_I2O_INBOUND_MESSAGE_REG1_PCI_0_SIDE 0x014 -#define MV64340_I2O_OUTBOUND_MESSAGE_REG0_PCI_0_SIDE 0x018 -#define MV64340_I2O_OUTBOUND_MESSAGE_REG1_PCI_0_SIDE 0x01C -#define MV64340_I2O_INBOUND_DOORBELL_REG_PCI_0_SIDE 0x020 -#define MV64340_I2O_INBOUND_INTERRUPT_CAUSE_REG_PCI_0_SIDE 0x024 -#define MV64340_I2O_INBOUND_INTERRUPT_MASK_REG_PCI_0_SIDE 0x028 -#define MV64340_I2O_OUTBOUND_DOORBELL_REG_PCI_0_SIDE 0x02C -#define MV64340_I2O_OUTBOUND_INTERRUPT_CAUSE_REG_PCI_0_SIDE 0x030 -#define MV64340_I2O_OUTBOUND_INTERRUPT_MASK_REG_PCI_0_SIDE 0x034 -#define MV64340_I2O_INBOUND_QUEUE_PORT_VIRTUAL_REG_PCI_0_SIDE 0x040 -#define MV64340_I2O_OUTBOUND_QUEUE_PORT_VIRTUAL_REG_PCI_0_SIDE 0x044 -#define MV64340_I2O_QUEUE_CONTROL_REG_PCI_0_SIDE 0x050 -#define MV64340_I2O_QUEUE_BASE_ADDR_REG_PCI_0_SIDE 0x054 -#define MV64340_I2O_INBOUND_FREE_HEAD_POINTER_REG_PCI_0_SIDE 0x060 -#define MV64340_I2O_INBOUND_FREE_TAIL_POINTER_REG_PCI_0_SIDE 0x064 -#define MV64340_I2O_INBOUND_POST_HEAD_POINTER_REG_PCI_0_SIDE 0x068 -#define MV64340_I2O_INBOUND_POST_TAIL_POINTER_REG_PCI_0_SIDE 0x06C -#define MV64340_I2O_OUTBOUND_FREE_HEAD_POINTER_REG_PCI_0_SIDE 0x070 -#define MV64340_I2O_OUTBOUND_FREE_TAIL_POINTER_REG_PCI_0_SIDE 0x074 -#define MV64340_I2O_OUTBOUND_POST_HEAD_POINTER_REG_PCI_0_SIDE 0x0F8 -#define MV64340_I2O_OUTBOUND_POST_TAIL_POINTER_REG_PCI_0_SIDE 0x0FC - -#define MV64340_I2O_INBOUND_MESSAGE_REG0_PCI_1_SIDE 0x090 -#define MV64340_I2O_INBOUND_MESSAGE_REG1_PCI_1_SIDE 0x094 -#define MV64340_I2O_OUTBOUND_MESSAGE_REG0_PCI_1_SIDE 0x098 -#define MV64340_I2O_OUTBOUND_MESSAGE_REG1_PCI_1_SIDE 0x09C -#define MV64340_I2O_INBOUND_DOORBELL_REG_PCI_1_SIDE 0x0A0 -#define MV64340_I2O_INBOUND_INTERRUPT_CAUSE_REG_PCI_1_SIDE 0x0A4 -#define MV64340_I2O_INBOUND_INTERRUPT_MASK_REG_PCI_1_SIDE 0x0A8 -#define MV64340_I2O_OUTBOUND_DOORBELL_REG_PCI_1_SIDE 0x0AC -#define MV64340_I2O_OUTBOUND_INTERRUPT_CAUSE_REG_PCI_1_SIDE 0x0B0 -#define MV64340_I2O_OUTBOUND_INTERRUPT_MASK_REG_PCI_1_SIDE 0x0B4 -#define MV64340_I2O_INBOUND_QUEUE_PORT_VIRTUAL_REG_PCI_1_SIDE 0x0C0 -#define MV64340_I2O_OUTBOUND_QUEUE_PORT_VIRTUAL_REG_PCI_1_SIDE 0x0C4 -#define MV64340_I2O_QUEUE_CONTROL_REG_PCI_1_SIDE 0x0D0 -#define MV64340_I2O_QUEUE_BASE_ADDR_REG_PCI_1_SIDE 0x0D4 -#define MV64340_I2O_INBOUND_FREE_HEAD_POINTER_REG_PCI_1_SIDE 0x0E0 -#define MV64340_I2O_INBOUND_FREE_TAIL_POINTER_REG_PCI_1_SIDE 0x0E4 -#define MV64340_I2O_INBOUND_POST_HEAD_POINTER_REG_PCI_1_SIDE 0x0E8 -#define MV64340_I2O_INBOUND_POST_TAIL_POINTER_REG_PCI_1_SIDE 0x0EC -#define MV64340_I2O_OUTBOUND_FREE_HEAD_POINTER_REG_PCI_1_SIDE 0x0F0 -#define MV64340_I2O_OUTBOUND_FREE_TAIL_POINTER_REG_PCI_1_SIDE 0x0F4 -#define MV64340_I2O_OUTBOUND_POST_HEAD_POINTER_REG_PCI_1_SIDE 0x078 -#define MV64340_I2O_OUTBOUND_POST_TAIL_POINTER_REG_PCI_1_SIDE 0x07C - -#define MV64340_I2O_INBOUND_MESSAGE_REG0_CPU0_SIDE 0x1C10 -#define MV64340_I2O_INBOUND_MESSAGE_REG1_CPU0_SIDE 0x1C14 -#define MV64340_I2O_OUTBOUND_MESSAGE_REG0_CPU0_SIDE 0x1C18 -#define MV64340_I2O_OUTBOUND_MESSAGE_REG1_CPU0_SIDE 0x1C1C -#define MV64340_I2O_INBOUND_DOORBELL_REG_CPU0_SIDE 0x1C20 -#define MV64340_I2O_INBOUND_INTERRUPT_CAUSE_REG_CPU0_SIDE 0x1C24 -#define MV64340_I2O_INBOUND_INTERRUPT_MASK_REG_CPU0_SIDE 0x1C28 -#define MV64340_I2O_OUTBOUND_DOORBELL_REG_CPU0_SIDE 0x1C2C -#define MV64340_I2O_OUTBOUND_INTERRUPT_CAUSE_REG_CPU0_SIDE 0x1C30 -#define MV64340_I2O_OUTBOUND_INTERRUPT_MASK_REG_CPU0_SIDE 0x1C34 -#define MV64340_I2O_INBOUND_QUEUE_PORT_VIRTUAL_REG_CPU0_SIDE 0x1C40 -#define MV64340_I2O_OUTBOUND_QUEUE_PORT_VIRTUAL_REG_CPU0_SIDE 0x1C44 -#define MV64340_I2O_QUEUE_CONTROL_REG_CPU0_SIDE 0x1C50 -#define MV64340_I2O_QUEUE_BASE_ADDR_REG_CPU0_SIDE 0x1C54 -#define MV64340_I2O_INBOUND_FREE_HEAD_POINTER_REG_CPU0_SIDE 0x1C60 -#define MV64340_I2O_INBOUND_FREE_TAIL_POINTER_REG_CPU0_SIDE 0x1C64 -#define MV64340_I2O_INBOUND_POST_HEAD_POINTER_REG_CPU0_SIDE 0x1C68 -#define MV64340_I2O_INBOUND_POST_TAIL_POINTER_REG_CPU0_SIDE 0x1C6C -#define MV64340_I2O_OUTBOUND_FREE_HEAD_POINTER_REG_CPU0_SIDE 0x1C70 -#define MV64340_I2O_OUTBOUND_FREE_TAIL_POINTER_REG_CPU0_SIDE 0x1C74 -#define MV64340_I2O_OUTBOUND_POST_HEAD_POINTER_REG_CPU0_SIDE 0x1CF8 -#define MV64340_I2O_OUTBOUND_POST_TAIL_POINTER_REG_CPU0_SIDE 0x1CFC -#define MV64340_I2O_INBOUND_MESSAGE_REG0_CPU1_SIDE 0x1C90 -#define MV64340_I2O_INBOUND_MESSAGE_REG1_CPU1_SIDE 0x1C94 -#define MV64340_I2O_OUTBOUND_MESSAGE_REG0_CPU1_SIDE 0x1C98 -#define MV64340_I2O_OUTBOUND_MESSAGE_REG1_CPU1_SIDE 0x1C9C -#define MV64340_I2O_INBOUND_DOORBELL_REG_CPU1_SIDE 0x1CA0 -#define MV64340_I2O_INBOUND_INTERRUPT_CAUSE_REG_CPU1_SIDE 0x1CA4 -#define MV64340_I2O_INBOUND_INTERRUPT_MASK_REG_CPU1_SIDE 0x1CA8 -#define MV64340_I2O_OUTBOUND_DOORBELL_REG_CPU1_SIDE 0x1CAC -#define MV64340_I2O_OUTBOUND_INTERRUPT_CAUSE_REG_CPU1_SIDE 0x1CB0 -#define MV64340_I2O_OUTBOUND_INTERRUPT_MASK_REG_CPU1_SIDE 0x1CB4 -#define MV64340_I2O_INBOUND_QUEUE_PORT_VIRTUAL_REG_CPU1_SIDE 0x1CC0 -#define MV64340_I2O_OUTBOUND_QUEUE_PORT_VIRTUAL_REG_CPU1_SIDE 0x1CC4 -#define MV64340_I2O_QUEUE_CONTROL_REG_CPU1_SIDE 0x1CD0 -#define MV64340_I2O_QUEUE_BASE_ADDR_REG_CPU1_SIDE 0x1CD4 -#define MV64340_I2O_INBOUND_FREE_HEAD_POINTER_REG_CPU1_SIDE 0x1CE0 -#define MV64340_I2O_INBOUND_FREE_TAIL_POINTER_REG_CPU1_SIDE 0x1CE4 -#define MV64340_I2O_INBOUND_POST_HEAD_POINTER_REG_CPU1_SIDE 0x1CE8 -#define MV64340_I2O_INBOUND_POST_TAIL_POINTER_REG_CPU1_SIDE 0x1CEC -#define MV64340_I2O_OUTBOUND_FREE_HEAD_POINTER_REG_CPU1_SIDE 0x1CF0 -#define MV64340_I2O_OUTBOUND_FREE_TAIL_POINTER_REG_CPU1_SIDE 0x1CF4 -#define MV64340_I2O_OUTBOUND_POST_HEAD_POINTER_REG_CPU1_SIDE 0x1C78 -#define MV64340_I2O_OUTBOUND_POST_TAIL_POINTER_REG_CPU1_SIDE 0x1C7C - -/****************************************/ -/* Ethernet Unit Registers */ -/****************************************/ - -/*******************************************/ -/* CUNIT Registers */ -/*******************************************/ - - /* Address Decoding Register Map */ - -#define MV64340_CUNIT_BASE_ADDR_REG0 0xf200 -#define MV64340_CUNIT_BASE_ADDR_REG1 0xf208 -#define MV64340_CUNIT_BASE_ADDR_REG2 0xf210 -#define MV64340_CUNIT_BASE_ADDR_REG3 0xf218 -#define MV64340_CUNIT_SIZE0 0xf204 -#define MV64340_CUNIT_SIZE1 0xf20c -#define MV64340_CUNIT_SIZE2 0xf214 -#define MV64340_CUNIT_SIZE3 0xf21c -#define MV64340_CUNIT_HIGH_ADDR_REMAP_REG0 0xf240 -#define MV64340_CUNIT_HIGH_ADDR_REMAP_REG1 0xf244 -#define MV64340_CUNIT_BASE_ADDR_ENABLE_REG 0xf250 -#define MV64340_MPSC0_ACCESS_PROTECTION_REG 0xf254 -#define MV64340_MPSC1_ACCESS_PROTECTION_REG 0xf258 -#define MV64340_CUNIT_INTERNAL_SPACE_BASE_ADDR_REG 0xf25C - - /* Error Report Registers */ - -#define MV64340_CUNIT_INTERRUPT_CAUSE_REG 0xf310 -#define MV64340_CUNIT_INTERRUPT_MASK_REG 0xf314 -#define MV64340_CUNIT_ERROR_ADDR 0xf318 - - /* Cunit Control Registers */ - -#define MV64340_CUNIT_ARBITER_CONTROL_REG 0xf300 -#define MV64340_CUNIT_CONFIG_REG 0xb40c -#define MV64340_CUNIT_CRROSBAR_TIMEOUT_REG 0xf304 - - /* Cunit Debug Registers */ - -#define MV64340_CUNIT_DEBUG_LOW 0xf340 -#define MV64340_CUNIT_DEBUG_HIGH 0xf344 -#define MV64340_CUNIT_MMASK 0xf380 - - /* MPSCs Clocks Routing Registers */ - -#define MV64340_MPSC_ROUTING_REG 0xb400 -#define MV64340_MPSC_RX_CLOCK_ROUTING_REG 0xb404 -#define MV64340_MPSC_TX_CLOCK_ROUTING_REG 0xb408 - - /* MPSCs Interrupts Registers */ - -#define MV64340_MPSC_CAUSE_REG(port) (0xb804 + (port<<3)) -#define MV64340_MPSC_MASK_REG(port) (0xb884 + (port<<3)) - -#define MV64340_MPSC_MAIN_CONFIG_LOW(port) (0x8000 + (port<<12)) -#define MV64340_MPSC_MAIN_CONFIG_HIGH(port) (0x8004 + (port<<12)) -#define MV64340_MPSC_PROTOCOL_CONFIG(port) (0x8008 + (port<<12)) -#define MV64340_MPSC_CHANNEL_REG1(port) (0x800c + (port<<12)) -#define MV64340_MPSC_CHANNEL_REG2(port) (0x8010 + (port<<12)) -#define MV64340_MPSC_CHANNEL_REG3(port) (0x8014 + (port<<12)) -#define MV64340_MPSC_CHANNEL_REG4(port) (0x8018 + (port<<12)) -#define MV64340_MPSC_CHANNEL_REG5(port) (0x801c + (port<<12)) -#define MV64340_MPSC_CHANNEL_REG6(port) (0x8020 + (port<<12)) -#define MV64340_MPSC_CHANNEL_REG7(port) (0x8024 + (port<<12)) -#define MV64340_MPSC_CHANNEL_REG8(port) (0x8028 + (port<<12)) -#define MV64340_MPSC_CHANNEL_REG9(port) (0x802c + (port<<12)) -#define MV64340_MPSC_CHANNEL_REG10(port) (0x8030 + (port<<12)) - - /* MPSC0 Registers */ - - -/***************************************/ -/* SDMA Registers */ -/***************************************/ - -#define MV64340_SDMA_CONFIG_REG(channel) (0x4000 + (channel<<13)) -#define MV64340_SDMA_COMMAND_REG(channel) (0x4008 + (channel<<13)) -#define MV64340_SDMA_CURRENT_RX_DESCRIPTOR_POINTER(channel) (0x4810 + (channel<<13)) -#define MV64340_SDMA_CURRENT_TX_DESCRIPTOR_POINTER(channel) (0x4c10 + (channel<<13)) -#define MV64340_SDMA_FIRST_TX_DESCRIPTOR_POINTER(channel) (0x4c14 + (channel<<13)) - -#define MV64340_SDMA_CAUSE_REG 0xb800 -#define MV64340_SDMA_MASK_REG 0xb880 - -/* BRG Interrupts */ - -#define MV64340_BRG_CONFIG_REG(brg) (0xb200 + (brg<<3)) -#define MV64340_BRG_BAUDE_TUNING_REG(brg) (0xb208 + (brg<<3)) -#define MV64340_BRG_CAUSE_REG 0xb834 -#define MV64340_BRG_MASK_REG 0xb8b4 - -/****************************************/ -/* DMA Channel Control */ -/****************************************/ - -#define MV64340_DMA_CHANNEL0_CONTROL 0x840 -#define MV64340_DMA_CHANNEL0_CONTROL_HIGH 0x880 -#define MV64340_DMA_CHANNEL1_CONTROL 0x844 -#define MV64340_DMA_CHANNEL1_CONTROL_HIGH 0x884 -#define MV64340_DMA_CHANNEL2_CONTROL 0x848 -#define MV64340_DMA_CHANNEL2_CONTROL_HIGH 0x888 -#define MV64340_DMA_CHANNEL3_CONTROL 0x84C -#define MV64340_DMA_CHANNEL3_CONTROL_HIGH 0x88C - - -/****************************************/ -/* IDMA Registers */ -/****************************************/ - -#define MV64340_DMA_CHANNEL0_BYTE_COUNT 0x800 -#define MV64340_DMA_CHANNEL1_BYTE_COUNT 0x804 -#define MV64340_DMA_CHANNEL2_BYTE_COUNT 0x808 -#define MV64340_DMA_CHANNEL3_BYTE_COUNT 0x80C -#define MV64340_DMA_CHANNEL0_SOURCE_ADDR 0x810 -#define MV64340_DMA_CHANNEL1_SOURCE_ADDR 0x814 -#define MV64340_DMA_CHANNEL2_SOURCE_ADDR 0x818 -#define MV64340_DMA_CHANNEL3_SOURCE_ADDR 0x81c -#define MV64340_DMA_CHANNEL0_DESTINATION_ADDR 0x820 -#define MV64340_DMA_CHANNEL1_DESTINATION_ADDR 0x824 -#define MV64340_DMA_CHANNEL2_DESTINATION_ADDR 0x828 -#define MV64340_DMA_CHANNEL3_DESTINATION_ADDR 0x82C -#define MV64340_DMA_CHANNEL0_NEXT_DESCRIPTOR_POINTER 0x830 -#define MV64340_DMA_CHANNEL1_NEXT_DESCRIPTOR_POINTER 0x834 -#define MV64340_DMA_CHANNEL2_NEXT_DESCRIPTOR_POINTER 0x838 -#define MV64340_DMA_CHANNEL3_NEXT_DESCRIPTOR_POINTER 0x83C -#define MV64340_DMA_CHANNEL0_CURRENT_DESCRIPTOR_POINTER 0x870 -#define MV64340_DMA_CHANNEL1_CURRENT_DESCRIPTOR_POINTER 0x874 -#define MV64340_DMA_CHANNEL2_CURRENT_DESCRIPTOR_POINTER 0x878 -#define MV64340_DMA_CHANNEL3_CURRENT_DESCRIPTOR_POINTER 0x87C - - /* IDMA Address Decoding Base Address Registers */ - -#define MV64340_DMA_BASE_ADDR_REG0 0xa00 -#define MV64340_DMA_BASE_ADDR_REG1 0xa08 -#define MV64340_DMA_BASE_ADDR_REG2 0xa10 -#define MV64340_DMA_BASE_ADDR_REG3 0xa18 -#define MV64340_DMA_BASE_ADDR_REG4 0xa20 -#define MV64340_DMA_BASE_ADDR_REG5 0xa28 -#define MV64340_DMA_BASE_ADDR_REG6 0xa30 -#define MV64340_DMA_BASE_ADDR_REG7 0xa38 - - /* IDMA Address Decoding Size Address Register */ - -#define MV64340_DMA_SIZE_REG0 0xa04 -#define MV64340_DMA_SIZE_REG1 0xa0c -#define MV64340_DMA_SIZE_REG2 0xa14 -#define MV64340_DMA_SIZE_REG3 0xa1c -#define MV64340_DMA_SIZE_REG4 0xa24 -#define MV64340_DMA_SIZE_REG5 0xa2c -#define MV64340_DMA_SIZE_REG6 0xa34 -#define MV64340_DMA_SIZE_REG7 0xa3C - - /* IDMA Address Decoding High Address Remap and Access - Protection Registers */ - -#define MV64340_DMA_HIGH_ADDR_REMAP_REG0 0xa60 -#define MV64340_DMA_HIGH_ADDR_REMAP_REG1 0xa64 -#define MV64340_DMA_HIGH_ADDR_REMAP_REG2 0xa68 -#define MV64340_DMA_HIGH_ADDR_REMAP_REG3 0xa6C -#define MV64340_DMA_BASE_ADDR_ENABLE_REG 0xa80 -#define MV64340_DMA_CHANNEL0_ACCESS_PROTECTION_REG 0xa70 -#define MV64340_DMA_CHANNEL1_ACCESS_PROTECTION_REG 0xa74 -#define MV64340_DMA_CHANNEL2_ACCESS_PROTECTION_REG 0xa78 -#define MV64340_DMA_CHANNEL3_ACCESS_PROTECTION_REG 0xa7c -#define MV64340_DMA_ARBITER_CONTROL 0x860 -#define MV64340_DMA_CROSS_BAR_TIMEOUT 0x8d0 - - /* IDMA Headers Retarget Registers */ - -#define MV64340_DMA_HEADERS_RETARGET_CONTROL 0xa84 -#define MV64340_DMA_HEADERS_RETARGET_BASE 0xa88 - - /* IDMA Interrupt Register */ - -#define MV64340_DMA_INTERRUPT_CAUSE_REG 0x8c0 -#define MV64340_DMA_INTERRUPT_CAUSE_MASK 0x8c4 -#define MV64340_DMA_ERROR_ADDR 0x8c8 -#define MV64340_DMA_ERROR_SELECT 0x8cc - - /* IDMA Debug Register ( for internal use ) */ - -#define MV64340_DMA_DEBUG_LOW 0x8e0 -#define MV64340_DMA_DEBUG_HIGH 0x8e4 -#define MV64340_DMA_SPARE 0xA8C - -/****************************************/ -/* Timer_Counter */ -/****************************************/ - -#define MV64340_TIMER_COUNTER0 0x850 -#define MV64340_TIMER_COUNTER1 0x854 -#define MV64340_TIMER_COUNTER2 0x858 -#define MV64340_TIMER_COUNTER3 0x85C -#define MV64340_TIMER_COUNTER_0_3_CONTROL 0x864 -#define MV64340_TIMER_COUNTER_0_3_INTERRUPT_CAUSE 0x868 -#define MV64340_TIMER_COUNTER_0_3_INTERRUPT_MASK 0x86c - -/****************************************/ -/* Watchdog registers */ -/****************************************/ - -#define MV64340_WATCHDOG_CONFIG_REG 0xb410 -#define MV64340_WATCHDOG_VALUE_REG 0xb414 - -/****************************************/ -/* I2C Registers */ -/****************************************/ - -#define MV64XXX_I2C_OFFSET 0xc000 -#define MV64XXX_I2C_REG_BLOCK_SIZE 0x0020 - -/****************************************/ -/* GPP Interface Registers */ -/****************************************/ - -#define MV64340_GPP_IO_CONTROL 0xf100 -#define MV64340_GPP_LEVEL_CONTROL 0xf110 -#define MV64340_GPP_VALUE 0xf104 -#define MV64340_GPP_INTERRUPT_CAUSE 0xf108 -#define MV64340_GPP_INTERRUPT_MASK0 0xf10c -#define MV64340_GPP_INTERRUPT_MASK1 0xf114 -#define MV64340_GPP_VALUE_SET 0xf118 -#define MV64340_GPP_VALUE_CLEAR 0xf11c - -/****************************************/ -/* Interrupt Controller Registers */ -/****************************************/ - -/****************************************/ -/* Interrupts */ -/****************************************/ - -#define MV64340_MAIN_INTERRUPT_CAUSE_LOW 0x004 -#define MV64340_MAIN_INTERRUPT_CAUSE_HIGH 0x00c -#define MV64340_CPU_INTERRUPT0_MASK_LOW 0x014 -#define MV64340_CPU_INTERRUPT0_MASK_HIGH 0x01c -#define MV64340_CPU_INTERRUPT0_SELECT_CAUSE 0x024 -#define MV64340_CPU_INTERRUPT1_MASK_LOW 0x034 -#define MV64340_CPU_INTERRUPT1_MASK_HIGH 0x03c -#define MV64340_CPU_INTERRUPT1_SELECT_CAUSE 0x044 -#define MV64340_INTERRUPT0_MASK_0_LOW 0x054 -#define MV64340_INTERRUPT0_MASK_0_HIGH 0x05c -#define MV64340_INTERRUPT0_SELECT_CAUSE 0x064 -#define MV64340_INTERRUPT1_MASK_0_LOW 0x074 -#define MV64340_INTERRUPT1_MASK_0_HIGH 0x07c -#define MV64340_INTERRUPT1_SELECT_CAUSE 0x084 - -/****************************************/ -/* MPP Interface Registers */ -/****************************************/ - -#define MV64340_MPP_CONTROL0 0xf000 -#define MV64340_MPP_CONTROL1 0xf004 -#define MV64340_MPP_CONTROL2 0xf008 -#define MV64340_MPP_CONTROL3 0xf00c - -/****************************************/ -/* Serial Initialization registers */ -/****************************************/ - -#define MV64340_SERIAL_INIT_LAST_DATA 0xf324 -#define MV64340_SERIAL_INIT_CONTROL 0xf328 -#define MV64340_SERIAL_INIT_STATUS 0xf32c - -extern void mv64340_irq_init(unsigned int base); - -#endif /* __ASM_MV643XX_H */ -- cgit v1.2.3 From 4208c562a27899212e8046080555e0f204e0579a Mon Sep 17 00:00:00 2001 From: Kanchan Joshi Date: Tue, 17 Sep 2024 10:24:57 +0530 Subject: block: remove bogus union The union around bi_integrity field is pointless. Remove it. Signed-off-by: Kanchan Joshi Link: https://lore.kernel.org/r/20240917045457.429698-1-joshi.k@samsung.com Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 36ed96133217..6d3a0fff2a1d 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -248,11 +248,9 @@ struct bio { struct bio_crypt_ctx *bi_crypt_context; #endif - union { #if defined(CONFIG_BLK_DEV_INTEGRITY) - struct bio_integrity_payload *bi_integrity; /* data integrity */ + struct bio_integrity_payload *bi_integrity; /* data integrity */ #endif - }; unsigned short bi_vcnt; /* how many bio_vec's */ -- cgit v1.2.3 From 6857be5fecaebd9773ff27b6d29b6fff3b1abbce Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Mon, 26 Aug 2024 16:43:35 -0400 Subject: mm: introduce ARCH_SUPPORTS_HUGE_PFNMAP and special bits to pmd/pud Patch series "mm: Support huge pfnmaps", v2. Overview ======== This series implements huge pfnmaps support for mm in general. Huge pfnmap allows e.g. VM_PFNMAP vmas to map in either PMD or PUD levels, similar to what we do with dax / thp / hugetlb so far to benefit from TLB hits. Now we extend that idea to PFN mappings, e.g. PCI MMIO bars where it can grow as large as 8GB or even bigger. Currently, only x86_64 (1G+2M) and arm64 (2M) are supported. The last patch (from Alex Williamson) will be the first user of huge pfnmap, so as to enable vfio-pci driver to fault in huge pfn mappings. Implementation ============== In reality, it's relatively simple to add such support comparing to many other types of mappings, because of PFNMAP's specialties when there's no vmemmap backing it, so that most of the kernel routines on huge mappings should simply already fail for them, like GUPs or old-school follow_page() (which is recently rewritten to be folio_walk* APIs by David). One trick here is that we're still unmature on PUDs in generic paths here and there, as DAX is so far the only user. This patchset will add the 2nd user of it. Hugetlb can be a 3rd user if the hugetlb unification work can go on smoothly, but to be discussed later. The other trick is how to allow gup-fast working for such huge mappings even if there's no direct sign of knowing whether it's a normal page or MMIO mapping. This series chose to keep the pte_special solution, so that it reuses similar idea on setting a special bit to pfnmap PMDs/PUDs so that gup-fast will be able to identify them and fail properly. Along the way, we'll also notice that the major pgtable pfn walker, aka, follow_pte(), will need to retire soon due to the fact that it only works with ptes. A new set of simple API is introduced (follow_pfnmap* API) to be able to do whatever follow_pte() can already do, plus that it can also process huge pfnmaps now. Half of this series is about that and converting all existing pfnmap walkers to use the new API properly. Hopefully the new API also looks better to avoid exposing e.g. pgtable lock details into the callers, so that it can be used in an even more straightforward way. Here, three more options will be introduced and involved in huge pfnmap: - ARCH_SUPPORTS_HUGE_PFNMAP Arch developers will need to select this option when huge pfnmap is supported in arch's Kconfig. After this patchset applied, both x86_64 and arm64 will start to enable it by default. - ARCH_SUPPORTS_PMD_PFNMAP / ARCH_SUPPORTS_PUD_PFNMAP These options are for driver developers to identify whether current arch / config supports huge pfnmaps, making decision on whether it can use the huge pfnmap APIs to inject them. One can refer to the last vfio-pci patch from Alex on the use of them properly in a device driver. So after the whole set applied, and if one would enable some dynamic debug lines in vfio-pci core files, we should observe things like: vfio-pci 0000:00:06.0: vfio_pci_mmap_huge_fault(,order = 9) BAR 0 page offset 0x0: 0x100 vfio-pci 0000:00:06.0: vfio_pci_mmap_huge_fault(,order = 9) BAR 0 page offset 0x200: 0x100 vfio-pci 0000:00:06.0: vfio_pci_mmap_huge_fault(,order = 9) BAR 0 page offset 0x400: 0x100 In this specific case, it says that vfio-pci faults in PMDs properly for a few BAR0 offsets. Patch Layout ============ Patch 1: Introduce the new options mentioned above for huge PFNMAPs Patch 2: A tiny cleanup Patch 3-8: Preparation patches for huge pfnmap (include introduce special bit for pmd/pud) Patch 9-16: Introduce follow_pfnmap*() API, use it everywhere, and then drop follow_pte() API Patch 17: Add huge pfnmap support for x86_64 Patch 18: Add huge pfnmap support for arm64 Patch 19: Add vfio-pci support for all kinds of huge pfnmaps (Alex) TODO ==== More architectures / More page sizes ------------------------------------ Currently only x86_64 (2M+1G) and arm64 (2M) are supported. There seems to have plan to support arm64 1G later on top of this series [2]. Any arch will need to first support THP / THP_1G, then provide a special bit in pmds/puds to support huge pfnmaps. remap_pfn_range() support ------------------------- Currently, remap_pfn_range() still only maps PTEs. With the new option, remap_pfn_range() can logically start to inject either PMDs or PUDs when the alignment requirements match on the VAs. When the support is there, it should be able to silently benefit all drivers that is using remap_pfn_range() in its mmap() handler on better TLB hit rate and overall faster MMIO accesses similar to processor on hugepages. More driver support ------------------- VFIO is so far the only consumer for the huge pfnmaps after this series applied. Besides above remap_pfn_range() generic optimization, device driver can also try to optimize its mmap() on a better VA alignment for either PMD/PUD sizes. This may, iiuc, normally require userspace changes, as the driver doesn't normally decide the VA to map a bar. But I don't think I know all the drivers to know the full picture. Credits all go to Alex on help testing the GPU/NIC use cases above. [0] https://lore.kernel.org/r/73ad9540-3fb8-4154-9a4f-30a0a2b03d41@lucifer.local [1] https://lore.kernel.org/r/20240807194812.819412-1-peterx@redhat.com [2] https://lore.kernel.org/r/498e0731-81a4-4f75-95b4-a8ad0bcc7665@huawei.com This patch (of 19): This patch introduces the option to introduce special pte bit into pmd/puds. Archs can start to define pmd_special / pud_special when supported by selecting the new option. Per-arch support will be added later. Before that, create fallbacks for these helpers so that they are always available. Link: https://lkml.kernel.org/r/20240826204353.2228736-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20240826204353.2228736-2-peterx@redhat.com Signed-off-by: Peter Xu Cc: Alexander Gordeev Cc: Alex Williamson Cc: Aneesh Kumar K.V Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Dave Hansen Cc: David Hildenbrand Cc: Gavin Shan Cc: Gerald Schaefer Cc: Heiko Carstens Cc: Ingo Molnar Cc: Jason Gunthorpe Cc: Matthew Wilcox Cc: Niklas Schnelle Cc: Paolo Bonzini Cc: Ryan Roberts Cc: Sean Christopherson Cc: Sven Schnelle Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Will Deacon Cc: Zi Yan Signed-off-by: Andrew Morton --- include/linux/mm.h | 24 ++++++++++++++++++++++++ mm/Kconfig | 13 +++++++++++++ 2 files changed, 37 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 39f6faace590..c2307a2d275d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2643,6 +2643,30 @@ static inline pte_t pte_mkspecial(pte_t pte) } #endif +#ifndef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP +static inline bool pmd_special(pmd_t pmd) +{ + return false; +} + +static inline pmd_t pmd_mkspecial(pmd_t pmd) +{ + return pmd; +} +#endif /* CONFIG_ARCH_SUPPORTS_PMD_PFNMAP */ + +#ifndef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP +static inline bool pud_special(pud_t pud) +{ + return false; +} + +static inline pud_t pud_mkspecial(pud_t pud) +{ + return pud; +} +#endif /* CONFIG_ARCH_SUPPORTS_PUD_PFNMAP */ + #ifndef CONFIG_ARCH_HAS_PTE_DEVMAP static inline int pte_devmap(pte_t pte) { diff --git a/mm/Kconfig b/mm/Kconfig index 7c23e8a889d0..1aa282e35dc7 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -875,6 +875,19 @@ endif # TRANSPARENT_HUGEPAGE config PGTABLE_HAS_HUGE_LEAVES def_bool TRANSPARENT_HUGEPAGE || HUGETLB_PAGE +# TODO: Allow to be enabled without THP +config ARCH_SUPPORTS_HUGE_PFNMAP + def_bool n + depends on TRANSPARENT_HUGEPAGE + +config ARCH_SUPPORTS_PMD_PFNMAP + def_bool y + depends on ARCH_SUPPORTS_HUGE_PFNMAP && HAVE_ARCH_TRANSPARENT_HUGEPAGE + +config ARCH_SUPPORTS_PUD_PFNMAP + def_bool y + depends on ARCH_SUPPORTS_HUGE_PFNMAP && HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD + # # UP and nommu archs use km based percpu allocator # -- cgit v1.2.3 From ef713ec3a566d3e5e011c5d6201eb661ebf94c1f Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Mon, 26 Aug 2024 16:43:36 -0400 Subject: mm: drop is_huge_zero_pud() It constantly returns false since 2017. One assertion is added in 2019 but it should never have triggered, IOW it means what is checked should be asserted instead. If it didn't exist for 7 years maybe it's good idea to remove it and only add it when it comes. Link: https://lkml.kernel.org/r/20240826204353.2228736-3-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Jason Gunthorpe Acked-by: David Hildenbrand Cc: Matthew Wilcox Cc: Aneesh Kumar K.V Cc: Alexander Gordeev Cc: Alex Williamson Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Dave Hansen Cc: Gavin Shan Cc: Gerald Schaefer Cc: Heiko Carstens Cc: Ingo Molnar Cc: Niklas Schnelle Cc: Paolo Bonzini Cc: Ryan Roberts Cc: Sean Christopherson Cc: Sven Schnelle Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Will Deacon Cc: Zi Yan Signed-off-by: Andrew Morton --- include/linux/huge_mm.h | 10 ---------- mm/huge_memory.c | 13 +------------ 2 files changed, 1 insertion(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index e3896ebf0f94..ffca706bac81 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -433,11 +433,6 @@ static inline bool is_huge_zero_pmd(pmd_t pmd) return pmd_present(pmd) && READ_ONCE(huge_zero_pfn) == pmd_pfn(pmd); } -static inline bool is_huge_zero_pud(pud_t pud) -{ - return false; -} - struct folio *mm_get_huge_zero_folio(struct mm_struct *mm); void mm_put_huge_zero_folio(struct mm_struct *mm); @@ -578,11 +573,6 @@ static inline bool is_huge_zero_pmd(pmd_t pmd) return false; } -static inline bool is_huge_zero_pud(pud_t pud) -{ - return false; -} - static inline void mm_put_huge_zero_folio(struct mm_struct *mm) { return; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index cc2872f12030..a4a14b81e013 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1453,10 +1453,8 @@ static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr, ptl = pud_lock(mm, pud); if (!pud_none(*pud)) { if (write) { - if (pud_pfn(*pud) != pfn_t_to_pfn(pfn)) { - WARN_ON_ONCE(!is_huge_zero_pud(*pud)); + if (WARN_ON_ONCE(pud_pfn(*pud) != pfn_t_to_pfn(pfn))) goto out_unlock; - } entry = pud_mkyoung(*pud); entry = maybe_pud_mkwrite(pud_mkdirty(entry), vma); if (pudp_set_access_flags(vma, addr, pud, entry, 1)) @@ -1704,15 +1702,6 @@ int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (unlikely(!pud_trans_huge(pud) && !pud_devmap(pud))) goto out_unlock; - /* - * When page table lock is held, the huge zero pud should not be - * under splitting since we don't split the page itself, only pud to - * a page table. - */ - if (is_huge_zero_pud(pud)) { - /* No huge zero pud yet */ - } - /* * TODO: once we support anonymous pages, use * folio_try_dup_anon_rmap_*() and split if duplicating fails. -- cgit v1.2.3 From 5dd40721f147e83733ad34848330913cb633046e Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Mon, 26 Aug 2024 16:43:38 -0400 Subject: mm: allow THP orders for PFNMAPs This enables PFNMAPs to be mapped at either pmd/pud layers. Generalize the dax case into vma_is_special_huge() so as to cover both. Meanwhile, rename the macro to THP_ORDERS_ALL_SPECIAL. Link: https://lkml.kernel.org/r/20240826204353.2228736-5-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Jason Gunthorpe Acked-by: David Hildenbrand Cc: Matthew Wilcox Cc: Gavin Shan Cc: Ryan Roberts Cc: Zi Yan Cc: Alexander Gordeev Cc: Alex Williamson Cc: Aneesh Kumar K.V Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Dave Hansen Cc: Gerald Schaefer Cc: Heiko Carstens Cc: Ingo Molnar Cc: Niklas Schnelle Cc: Paolo Bonzini Cc: Sean Christopherson Cc: Sven Schnelle Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/huge_mm.h | 6 +++--- mm/huge_memory.c | 4 ++-- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index ffca706bac81..0b0539f4ee1a 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -76,9 +76,9 @@ extern struct kobj_attribute thpsize_shmem_enabled_attr; /* * Mask of all large folio orders supported for file THP. Folios in a DAX * file is never split and the MAX_PAGECACHE_ORDER limit does not apply to - * it. + * it. Same to PFNMAPs where there's neither page* nor pagecache. */ -#define THP_ORDERS_ALL_FILE_DAX \ +#define THP_ORDERS_ALL_SPECIAL \ (BIT(PMD_ORDER) | BIT(PUD_ORDER)) #define THP_ORDERS_ALL_FILE_DEFAULT \ ((BIT(MAX_PAGECACHE_ORDER + 1) - 1) & ~BIT(0)) @@ -87,7 +87,7 @@ extern struct kobj_attribute thpsize_shmem_enabled_attr; * Mask of all large folio orders supported for THP. */ #define THP_ORDERS_ALL \ - (THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE_DAX | THP_ORDERS_ALL_FILE_DEFAULT) + (THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_SPECIAL | THP_ORDERS_ALL_FILE_DEFAULT) #define TVA_SMAPS (1 << 0) /* Will be used for procfs */ #define TVA_IN_PF (1 << 1) /* Page fault handler */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index f0983b17621c..7ab9a171e3d0 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -97,8 +97,8 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, /* Check the intersection of requested and supported orders. */ if (vma_is_anonymous(vma)) supported_orders = THP_ORDERS_ALL_ANON; - else if (vma_is_dax(vma)) - supported_orders = THP_ORDERS_ALL_FILE_DAX; + else if (vma_is_special_huge(vma)) + supported_orders = THP_ORDERS_ALL_SPECIAL; else supported_orders = THP_ORDERS_ALL_FILE_DEFAULT; -- cgit v1.2.3 From 0515e022e167cfacf1fee092eb93aa9514e23c0a Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Mon, 26 Aug 2024 16:43:42 -0400 Subject: mm: always define pxx_pgprot() There're: - 8 archs (arc, arm64, include, mips, powerpc, s390, sh, x86) that support pte_pgprot(). - 2 archs (x86, sparc) that support pmd_pgprot(). - 1 arch (x86) that support pud_pgprot(). Always define them to be used in generic code, and then we don't need to fiddle with "#ifdef"s when doing so. Link: https://lkml.kernel.org/r/20240826204353.2228736-9-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Jason Gunthorpe Cc: Alexander Gordeev Cc: Alex Williamson Cc: Aneesh Kumar K.V Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Dave Hansen Cc: David Hildenbrand Cc: Gavin Shan Cc: Gerald Schaefer Cc: Heiko Carstens Cc: Ingo Molnar Cc: Matthew Wilcox Cc: Niklas Schnelle Cc: Paolo Bonzini Cc: Ryan Roberts Cc: Sean Christopherson Cc: Sven Schnelle Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Will Deacon Cc: Zi Yan Signed-off-by: Andrew Morton --- arch/arm64/include/asm/pgtable.h | 1 + arch/powerpc/include/asm/pgtable.h | 1 + arch/s390/include/asm/pgtable.h | 1 + arch/sparc/include/asm/pgtable_64.h | 1 + include/linux/pgtable.h | 12 ++++++++++++ 5 files changed, 16 insertions(+) (limited to 'include/linux') diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 7a4f5604be3f..b78cc4a6758b 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -384,6 +384,7 @@ static inline void __sync_cache_and_tags(pte_t pte, unsigned int nr_pages) /* * Select all bits except the pfn */ +#define pte_pgprot pte_pgprot static inline pgprot_t pte_pgprot(pte_t pte) { unsigned long pfn = pte_pfn(pte); diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index 264a6c09517a..2f72ad885332 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -65,6 +65,7 @@ static inline unsigned long pte_pfn(pte_t pte) /* * Select all bits except the pfn */ +#define pte_pgprot pte_pgprot static inline pgprot_t pte_pgprot(pte_t pte) { unsigned long pte_flags; diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 3fa280d0672a..0ffbaf741955 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -955,6 +955,7 @@ static inline int pte_unused(pte_t pte) * young/old accounting is not supported, i.e _PAGE_PROTECT and _PAGE_INVALID * must not be set. */ +#define pte_pgprot pte_pgprot static inline pgprot_t pte_pgprot(pte_t pte) { unsigned long pte_flags = pte_val(pte) & _PAGE_CHG_MASK; diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 3fe429d73a65..2b7f358762c1 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -783,6 +783,7 @@ static inline pmd_t pmd_mkwrite_novma(pmd_t pmd) return __pmd(pte_val(pte)); } +#define pmd_pgprot pmd_pgprot static inline pgprot_t pmd_pgprot(pmd_t entry) { unsigned long val = pmd_val(entry); diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 780f3b439d98..e8b2ac6bd2ae 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1956,6 +1956,18 @@ typedef unsigned int pgtbl_mod_mask; #define MAX_PTRS_PER_P4D PTRS_PER_P4D #endif +#ifndef pte_pgprot +#define pte_pgprot(x) ((pgprot_t) {0}) +#endif + +#ifndef pmd_pgprot +#define pmd_pgprot(x) ((pgprot_t) {0}) +#endif + +#ifndef pud_pgprot +#define pud_pgprot(x) ((pgprot_t) {0}) +#endif + /* description of effects of mapping type and prot in current implementation. * this is due to the limited x86 page protection hardware. The expected * behavior is in parens: -- cgit v1.2.3 From 6da8e9634bb7e3fdad9ae0e4db873a05036c4343 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Mon, 26 Aug 2024 16:43:43 -0400 Subject: mm: new follow_pfnmap API Introduce a pair of APIs to follow pfn mappings to get entry information. It's very similar to what follow_pte() does before, but different in that it recognizes huge pfn mappings. Link: https://lkml.kernel.org/r/20240826204353.2228736-10-peterx@redhat.com Signed-off-by: Peter Xu Cc: Alexander Gordeev Cc: Alex Williamson Cc: Aneesh Kumar K.V Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Dave Hansen Cc: David Hildenbrand Cc: Gavin Shan Cc: Gerald Schaefer Cc: Heiko Carstens Cc: Ingo Molnar Cc: Jason Gunthorpe Cc: Matthew Wilcox Cc: Niklas Schnelle Cc: Paolo Bonzini Cc: Ryan Roberts Cc: Sean Christopherson Cc: Sven Schnelle Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Will Deacon Cc: Zi Yan Signed-off-by: Andrew Morton --- include/linux/mm.h | 31 +++++++++++ mm/memory.c | 150 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 181 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index c2307a2d275d..62bd89414897 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2373,6 +2373,37 @@ int follow_pte(struct vm_area_struct *vma, unsigned long address, int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write); +struct follow_pfnmap_args { + /** + * Inputs: + * @vma: Pointer to @vm_area_struct struct + * @address: the virtual address to walk + */ + struct vm_area_struct *vma; + unsigned long address; + /** + * Internals: + * + * The caller shouldn't touch any of these. + */ + spinlock_t *lock; + pte_t *ptep; + /** + * Outputs: + * + * @pfn: the PFN of the address + * @pgprot: the pgprot_t of the mapping + * @writable: whether the mapping is writable + * @special: whether the mapping is a special mapping (real PFN maps) + */ + unsigned long pfn; + pgprot_t pgprot; + bool writable; + bool special; +}; +int follow_pfnmap_start(struct follow_pfnmap_args *args); +void follow_pfnmap_end(struct follow_pfnmap_args *args); + extern void truncate_pagecache(struct inode *inode, loff_t new); extern void truncate_setsize(struct inode *inode, loff_t newsize); void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to); diff --git a/mm/memory.c b/mm/memory.c index 9a540e231625..3878bf69bc14 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -6172,6 +6172,156 @@ out: } EXPORT_SYMBOL_GPL(follow_pte); +static inline void pfnmap_args_setup(struct follow_pfnmap_args *args, + spinlock_t *lock, pte_t *ptep, + pgprot_t pgprot, unsigned long pfn_base, + unsigned long addr_mask, bool writable, + bool special) +{ + args->lock = lock; + args->ptep = ptep; + args->pfn = pfn_base + ((args->address & ~addr_mask) >> PAGE_SHIFT); + args->pgprot = pgprot; + args->writable = writable; + args->special = special; +} + +static inline void pfnmap_lockdep_assert(struct vm_area_struct *vma) +{ +#ifdef CONFIG_LOCKDEP + struct address_space *mapping = vma->vm_file->f_mapping; + + if (mapping) + lockdep_assert(lockdep_is_held(&vma->vm_file->f_mapping->i_mmap_rwsem) || + lockdep_is_held(&vma->vm_mm->mmap_lock)); + else + lockdep_assert(lockdep_is_held(&vma->vm_mm->mmap_lock)); +#endif +} + +/** + * follow_pfnmap_start() - Look up a pfn mapping at a user virtual address + * @args: Pointer to struct @follow_pfnmap_args + * + * The caller needs to setup args->vma and args->address to point to the + * virtual address as the target of such lookup. On a successful return, + * the results will be put into other output fields. + * + * After the caller finished using the fields, the caller must invoke + * another follow_pfnmap_end() to proper releases the locks and resources + * of such look up request. + * + * During the start() and end() calls, the results in @args will be valid + * as proper locks will be held. After the end() is called, all the fields + * in @follow_pfnmap_args will be invalid to be further accessed. Further + * use of such information after end() may require proper synchronizations + * by the caller with page table updates, otherwise it can create a + * security bug. + * + * If the PTE maps a refcounted page, callers are responsible to protect + * against invalidation with MMU notifiers; otherwise access to the PFN at + * a later point in time can trigger use-after-free. + * + * Only IO mappings and raw PFN mappings are allowed. The mmap semaphore + * should be taken for read, and the mmap semaphore cannot be released + * before the end() is invoked. + * + * This function must not be used to modify PTE content. + * + * Return: zero on success, negative otherwise. + */ +int follow_pfnmap_start(struct follow_pfnmap_args *args) +{ + struct vm_area_struct *vma = args->vma; + unsigned long address = args->address; + struct mm_struct *mm = vma->vm_mm; + spinlock_t *lock; + pgd_t *pgdp; + p4d_t *p4dp, p4d; + pud_t *pudp, pud; + pmd_t *pmdp, pmd; + pte_t *ptep, pte; + + pfnmap_lockdep_assert(vma); + + if (unlikely(address < vma->vm_start || address >= vma->vm_end)) + goto out; + + if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) + goto out; +retry: + pgdp = pgd_offset(mm, address); + if (pgd_none(*pgdp) || unlikely(pgd_bad(*pgdp))) + goto out; + + p4dp = p4d_offset(pgdp, address); + p4d = READ_ONCE(*p4dp); + if (p4d_none(p4d) || unlikely(p4d_bad(p4d))) + goto out; + + pudp = pud_offset(p4dp, address); + pud = READ_ONCE(*pudp); + if (pud_none(pud)) + goto out; + if (pud_leaf(pud)) { + lock = pud_lock(mm, pudp); + if (!unlikely(pud_leaf(pud))) { + spin_unlock(lock); + goto retry; + } + pfnmap_args_setup(args, lock, NULL, pud_pgprot(pud), + pud_pfn(pud), PUD_MASK, pud_write(pud), + pud_special(pud)); + return 0; + } + + pmdp = pmd_offset(pudp, address); + pmd = pmdp_get_lockless(pmdp); + if (pmd_leaf(pmd)) { + lock = pmd_lock(mm, pmdp); + if (!unlikely(pmd_leaf(pmd))) { + spin_unlock(lock); + goto retry; + } + pfnmap_args_setup(args, lock, NULL, pmd_pgprot(pmd), + pmd_pfn(pmd), PMD_MASK, pmd_write(pmd), + pmd_special(pmd)); + return 0; + } + + ptep = pte_offset_map_lock(mm, pmdp, address, &lock); + if (!ptep) + goto out; + pte = ptep_get(ptep); + if (!pte_present(pte)) + goto unlock; + pfnmap_args_setup(args, lock, ptep, pte_pgprot(pte), + pte_pfn(pte), PAGE_MASK, pte_write(pte), + pte_special(pte)); + return 0; +unlock: + pte_unmap_unlock(ptep, lock); +out: + return -EINVAL; +} +EXPORT_SYMBOL_GPL(follow_pfnmap_start); + +/** + * follow_pfnmap_end(): End a follow_pfnmap_start() process + * @args: Pointer to struct @follow_pfnmap_args + * + * Must be used in pair of follow_pfnmap_start(). See the start() function + * above for more information. + */ +void follow_pfnmap_end(struct follow_pfnmap_args *args) +{ + if (args->lock) + spin_unlock(args->lock); + if (args->ptep) + pte_unmap(args->ptep); +} +EXPORT_SYMBOL_GPL(follow_pfnmap_end); + #ifdef CONFIG_HAVE_IOREMAP_PROT /** * generic_access_phys - generic implementation for iomem mmap access -- cgit v1.2.3 From b0a1c0d0edcd75a0f8ec5fd19dbd64b8d097f534 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Mon, 26 Aug 2024 16:43:50 -0400 Subject: mm: remove follow_pte() follow_pte() users have been converted to follow_pfnmap*(). Remove the API. Link: https://lkml.kernel.org/r/20240826204353.2228736-17-peterx@redhat.com Signed-off-by: Peter Xu Cc: Alexander Gordeev Cc: Alex Williamson Cc: Aneesh Kumar K.V Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Dave Hansen Cc: David Hildenbrand Cc: Gavin Shan Cc: Gerald Schaefer Cc: Heiko Carstens Cc: Ingo Molnar Cc: Jason Gunthorpe Cc: Matthew Wilcox Cc: Niklas Schnelle Cc: Paolo Bonzini Cc: Ryan Roberts Cc: Sean Christopherson Cc: Sven Schnelle Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Will Deacon Cc: Zi Yan Signed-off-by: Andrew Morton --- include/linux/mm.h | 2 -- mm/memory.c | 73 ------------------------------------------------------ 2 files changed, 75 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 62bd89414897..d750be768121 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2368,8 +2368,6 @@ void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); int copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma); -int follow_pte(struct vm_area_struct *vma, unsigned long address, - pte_t **ptepp, spinlock_t **ptlp); int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write); diff --git a/mm/memory.c b/mm/memory.c index cfc278691466..42674c0748cb 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -6099,79 +6099,6 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) } #endif /* __PAGETABLE_PMD_FOLDED */ -/** - * follow_pte - look up PTE at a user virtual address - * @vma: the memory mapping - * @address: user virtual address - * @ptepp: location to store found PTE - * @ptlp: location to store the lock for the PTE - * - * On a successful return, the pointer to the PTE is stored in @ptepp; - * the corresponding lock is taken and its location is stored in @ptlp. - * - * The contents of the PTE are only stable until @ptlp is released using - * pte_unmap_unlock(). This function will fail if the PTE is non-present. - * Present PTEs may include PTEs that map refcounted pages, such as - * anonymous folios in COW mappings. - * - * Callers must be careful when relying on PTE content after - * pte_unmap_unlock(). Especially if the PTE maps a refcounted page, - * callers must protect against invalidation with MMU notifiers; otherwise - * access to the PFN at a later point in time can trigger use-after-free. - * - * Only IO mappings and raw PFN mappings are allowed. The mmap semaphore - * should be taken for read. - * - * This function must not be used to modify PTE content. - * - * Return: zero on success, -ve otherwise. - */ -int follow_pte(struct vm_area_struct *vma, unsigned long address, - pte_t **ptepp, spinlock_t **ptlp) -{ - struct mm_struct *mm = vma->vm_mm; - pgd_t *pgd; - p4d_t *p4d; - pud_t *pud; - pmd_t *pmd; - pte_t *ptep; - - mmap_assert_locked(mm); - if (unlikely(address < vma->vm_start || address >= vma->vm_end)) - goto out; - - if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) - goto out; - - pgd = pgd_offset(mm, address); - if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) - goto out; - - p4d = p4d_offset(pgd, address); - if (p4d_none(*p4d) || unlikely(p4d_bad(*p4d))) - goto out; - - pud = pud_offset(p4d, address); - if (pud_none(*pud) || unlikely(pud_bad(*pud))) - goto out; - - pmd = pmd_offset(pud, address); - VM_BUG_ON(pmd_trans_huge(*pmd)); - - ptep = pte_offset_map_lock(mm, pmd, address, ptlp); - if (!ptep) - goto out; - if (!pte_present(ptep_get(ptep))) - goto unlock; - *ptepp = ptep; - return 0; -unlock: - pte_unmap_unlock(ptep, *ptlp); -out: - return -EINVAL; -} -EXPORT_SYMBOL_GPL(follow_pte); - static inline void pfnmap_args_setup(struct follow_pfnmap_args *args, spinlock_t *lock, pte_t *ptep, pgprot_t pgprot, unsigned long pfn_base, -- cgit v1.2.3 From 82ce8e2f31a1eb05b1527c3d807bea40031df913 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 7 Sep 2024 17:40:42 +0200 Subject: set_memory: add __must_check to generic stubs Following query shows that architectures that don't provide asm/set_memory.h don't use set_memory_...() functions. $ git grep set_memory_ alpha arc csky hexagon loongarch m68k microblaze mips nios2 openrisc parisc sh sparc um xtensa Following query shows that all core users of set_memory_...() functions always take returned value into account: $ git grep -w -e set_memory_ro -e set_memory_rw -e set_memory_x -e set_memory_nx -e set_memory_rox `find . -maxdepth 1 -type d | grep -v arch | grep /` set_memory_...() functions can fail, leaving the memory attributes unchanged. Make sure all callers check the returned code. Link: https://github.com/KSPP/linux/issues/7 Link: https://lkml.kernel.org/r/6a89ffc69666de84721216947c6b6c7dcca39d7d.1725723347.git.christophe.leroy@csgroup.eu Signed-off-by: Christophe Leroy Cc: Arnd Bergmann Cc: Kees Cook Signed-off-by: Andrew Morton --- include/linux/set_memory.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h index 95ac8398ee72..e7aec20fb44f 100644 --- a/include/linux/set_memory.h +++ b/include/linux/set_memory.h @@ -8,10 +8,10 @@ #ifdef CONFIG_ARCH_HAS_SET_MEMORY #include #else -static inline int set_memory_ro(unsigned long addr, int numpages) { return 0; } -static inline int set_memory_rw(unsigned long addr, int numpages) { return 0; } -static inline int set_memory_x(unsigned long addr, int numpages) { return 0; } -static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; } +static inline int __must_check set_memory_ro(unsigned long addr, int numpages) { return 0; } +static inline int __must_check set_memory_rw(unsigned long addr, int numpages) { return 0; } +static inline int __must_check set_memory_x(unsigned long addr, int numpages) { return 0; } +static inline int __must_check set_memory_nx(unsigned long addr, int numpages) { return 0; } #endif #ifndef set_memory_rox -- cgit v1.2.3 From 325efb16da2c840e165d9b620fec8049d4d664cc Mon Sep 17 00:00:00 2001 From: Barry Song Date: Mon, 9 Sep 2024 11:21:18 +1200 Subject: mm: add nr argument in mem_cgroup_swapin_uncharge_swap() helper to support large folios With large folios swap-in, we might need to uncharge multiple entries all together, add nr argument in mem_cgroup_swapin_uncharge_swap(). For the existing two users, just pass nr=1. Link: https://lkml.kernel.org/r/20240908232119.2157-3-21cnbao@gmail.com Signed-off-by: Barry Song Acked-by: Chris Li Reviewed-by: Yosry Ahmed Cc: Shakeel Butt Cc: Baolin Wang Cc: Christoph Hellwig Cc: David Hildenbrand Cc: Gao Xiang Cc: "Huang, Ying" Cc: Hugh Dickins Cc: Johannes Weiner Cc: Kairui Song Cc: Kairui Song Cc: Kalesh Singh Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Minchan Kim Cc: Nhat Pham Cc: Ryan Roberts Cc: Sergey Senozhatsky Cc: Suren Baghdasaryan Cc: Yang Shi Cc: Chuanhua Han Cc: Kanchana P Sridhar Cc: Usama Arif Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 5 +++-- mm/memcontrol.c | 7 ++++--- mm/memory.c | 2 +- mm/swap_state.c | 2 +- 4 files changed, 9 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 2ef94c74847d..34d2da05f2f1 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -699,7 +699,8 @@ int mem_cgroup_hugetlb_try_charge(struct mem_cgroup *memcg, gfp_t gfp, int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm, gfp_t gfp, swp_entry_t entry); -void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry); + +void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry, unsigned int nr_pages); void __mem_cgroup_uncharge(struct folio *folio); @@ -1206,7 +1207,7 @@ static inline int mem_cgroup_swapin_charge_folio(struct folio *folio, return 0; } -static inline void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry) +static inline void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry, unsigned int nr) { } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index d632650c6a2b..ae9a9d7968cb 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4559,14 +4559,15 @@ int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm, /* * mem_cgroup_swapin_uncharge_swap - uncharge swap slot - * @entry: swap entry for which the page is charged + * @entry: the first swap entry for which the pages are charged + * @nr_pages: number of pages which will be uncharged * * Call this function after successfully adding the charged page to swapcache. * * Note: This function assumes the page for which swap slot is being uncharged * is order 0 page. */ -void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry) +void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry, unsigned int nr_pages) { /* * Cgroup1's unified memory+swap counter has been charged with the @@ -4586,7 +4587,7 @@ void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry) * let's not wait for it. The page already received a * memory+swap charge, drop the swap entry duplicate. */ - mem_cgroup_uncharge_swap(entry, 1); + mem_cgroup_uncharge_swap(entry, nr_pages); } } diff --git a/mm/memory.c b/mm/memory.c index cca3d2907439..9bcc440dd56e 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4104,7 +4104,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) ret = VM_FAULT_OOM; goto out_page; } - mem_cgroup_swapin_uncharge_swap(entry); + mem_cgroup_swapin_uncharge_swap(entry, 1); shadow = get_shadow_from_swap_cache(entry); if (shadow) diff --git a/mm/swap_state.c b/mm/swap_state.c index a042720554a7..4669f29cf555 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -522,7 +522,7 @@ struct folio *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, if (add_to_swap_cache(new_folio, entry, gfp_mask & GFP_RECLAIM_MASK, &shadow)) goto fail_unlock; - mem_cgroup_swapin_uncharge_swap(entry); + mem_cgroup_swapin_uncharge_swap(entry, 1); if (shadow) workingset_refault(new_folio, shadow); -- cgit v1.2.3 From ed8d5b0ce1d738e13c60d6b1a901a56d832e5070 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 11 Sep 2024 15:13:20 +0200 Subject: Revert "uprobes: use vm_special_mapping close() functionality" This reverts commit 08e28de1160a712724268fd33d77b32f1bc84d1c. A malicious application can munmap() its "[uprobes]" vma and in this case xol_mapping.close == uprobe_clear_state() will free the memory which can be used by another thread, or the same thread when it hits the uprobe bp afterwards. Link: https://lkml.kernel.org/r/20240911131320.GA3448@redhat.com Signed-off-by: Oleg Nesterov Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andrii Nakryiko Cc: Arnaldo Carvalho de Melo Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Linus Torvalds Cc: Mark Rutland Cc: Masami Hiramatsu Cc: Michael Ellerman Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Sven Schnelle Signed-off-by: Andrew Morton --- include/linux/uprobes.h | 1 + kernel/events/uprobes.c | 36 +++++++++++++++++++----------------- kernel/fork.c | 1 + 3 files changed, 21 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index 493dc95d912c..b503fafb7fb3 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -126,6 +126,7 @@ extern int uprobe_pre_sstep_notifier(struct pt_regs *regs); extern void uprobe_notify_resume(struct pt_regs *regs); extern bool uprobe_deny_signal(void); extern bool arch_uprobe_skip_sstep(struct arch_uprobe *aup, struct pt_regs *regs); +extern void uprobe_clear_state(struct mm_struct *mm); extern int arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long addr); extern int arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs); extern int arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs); diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index c2d6b2d64de2..73cc47708679 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1482,22 +1482,6 @@ void * __weak arch_uprobe_trampoline(unsigned long *psize) return &insn; } -/* - * uprobe_clear_state - Free the area allocated for slots. - */ -static void uprobe_clear_state(const struct vm_special_mapping *sm, struct vm_area_struct *vma) -{ - struct xol_area *area = container_of(vma->vm_private_data, struct xol_area, xol_mapping); - - mutex_lock(&delayed_uprobe_lock); - delayed_uprobe_remove(NULL, vma->vm_mm); - mutex_unlock(&delayed_uprobe_lock); - - put_page(area->pages[0]); - kfree(area->bitmap); - kfree(area); -} - static struct xol_area *__create_xol_area(unsigned long vaddr) { struct mm_struct *mm = current->mm; @@ -1516,7 +1500,6 @@ static struct xol_area *__create_xol_area(unsigned long vaddr) area->xol_mapping.name = "[uprobes]"; area->xol_mapping.fault = NULL; - area->xol_mapping.close = uprobe_clear_state; area->xol_mapping.pages = area->pages; area->pages[0] = alloc_page(GFP_HIGHUSER); if (!area->pages[0]) @@ -1562,6 +1545,25 @@ static struct xol_area *get_xol_area(void) return area; } +/* + * uprobe_clear_state - Free the area allocated for slots. + */ +void uprobe_clear_state(struct mm_struct *mm) +{ + struct xol_area *area = mm->uprobes_state.xol_area; + + mutex_lock(&delayed_uprobe_lock); + delayed_uprobe_remove(NULL, mm); + mutex_unlock(&delayed_uprobe_lock); + + if (!area) + return; + + put_page(area->pages[0]); + kfree(area->bitmap); + kfree(area); +} + void uprobe_start_dup_mmap(void) { percpu_down_read(&dup_mmap_sem); diff --git a/kernel/fork.c b/kernel/fork.c index 61070248a7d3..3d590e51ce84 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1338,6 +1338,7 @@ static inline void __mmput(struct mm_struct *mm) { VM_BUG_ON(atomic_read(&mm->mm_users)); + uprobe_clear_state(mm); exit_aio(mm); ksm_exit(mm); khugepaged_exit(mm); /* must run before exit_mmap */ -- cgit v1.2.3 From aef79e189ba2b32f78bd35daf2c0b41f3868a321 Mon Sep 17 00:00:00 2001 From: Carlos Song Date: Tue, 10 Sep 2024 13:16:25 +0800 Subject: i3c: master: support to adjust first broadcast address speed According to I3C spec 6.2 Timing Specification, the Open Drain High Period of SCL Clock timing for first broadcast address should be adjusted to 200ns at least. I3C device working as i2c device will see the broadcast to close its Spike Filter then change to work at I3C mode. After that I3C open drain SCL high level should be adjusted back. Signed-off-by: Carlos Song Reviewed-by: Miquel Raynal Reviewed-by: Frank Li Link: https://lore.kernel.org/r/20240910051626.4052552-1-carlos.song@nxp.com Signed-off-by: Alexandre Belloni --- drivers/i3c/master.c | 12 ++++++++++++ include/linux/i3c/master.h | 16 ++++++++++++++++ 2 files changed, 28 insertions(+) (limited to 'include/linux') diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c index 7028f03c2c42..6f3eb710a75d 100644 --- a/drivers/i3c/master.c +++ b/drivers/i3c/master.c @@ -1868,6 +1868,12 @@ static int i3c_master_bus_init(struct i3c_master_controller *master) goto err_bus_cleanup; } + if (master->ops->set_speed) { + ret = master->ops->set_speed(master, I3C_OPEN_DRAIN_SLOW_SPEED); + if (ret) + goto err_bus_cleanup; + } + /* * Reset all dynamic address that may have been assigned before * (assigned by the bootloader for example). @@ -1876,6 +1882,12 @@ static int i3c_master_bus_init(struct i3c_master_controller *master) if (ret && ret != I3C_ERROR_M2) goto err_bus_cleanup; + if (master->ops->set_speed) { + master->ops->set_speed(master, I3C_OPEN_DRAIN_NORMAL_SPEED); + if (ret) + goto err_bus_cleanup; + } + /* Disable all slave events before starting DAA. */ ret = i3c_master_disec_locked(master, I3C_BROADCAST_ADDR, I3C_CCC_EVENT_SIR | I3C_CCC_EVENT_MR | diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h index 074f632868d9..2a1ed05d5782 100644 --- a/include/linux/i3c/master.h +++ b/include/linux/i3c/master.h @@ -277,6 +277,20 @@ enum i3c_bus_mode { I3C_BUS_MODE_MIXED_SLOW, }; +/** + * enum i3c_open_drain_speed - I3C open-drain speed + * @I3C_OPEN_DRAIN_SLOW_SPEED: Slow open-drain speed for sending the first + * broadcast address. The first broadcast address at this speed + * will be visible to all devices on the I3C bus. I3C devices + * working in I2C mode will turn off their spike filter when + * switching into I3C mode. + * @I3C_OPEN_DRAIN_NORMAL_SPEED: Normal open-drain speed in I3C bus mode. + */ +enum i3c_open_drain_speed { + I3C_OPEN_DRAIN_SLOW_SPEED, + I3C_OPEN_DRAIN_NORMAL_SPEED, +}; + /** * enum i3c_addr_slot_status - I3C address slot status * @I3C_ADDR_SLOT_FREE: address is free @@ -436,6 +450,7 @@ struct i3c_bus { * NULL. * @enable_hotjoin: enable hot join event detect. * @disable_hotjoin: disable hot join event detect. + * @set_speed: adjust I3C open drain mode timing. */ struct i3c_master_controller_ops { int (*bus_init)(struct i3c_master_controller *master); @@ -464,6 +479,7 @@ struct i3c_master_controller_ops { struct i3c_ibi_slot *slot); int (*enable_hotjoin)(struct i3c_master_controller *master); int (*disable_hotjoin)(struct i3c_master_controller *master); + int (*set_speed)(struct i3c_master_controller *master, enum i3c_open_drain_speed speed); }; /** -- cgit v1.2.3 From 9ba5dcc722de4390a1d3211b2ee3c864f84f5461 Mon Sep 17 00:00:00 2001 From: "Dr. David Alan Gilbert" Date: Fri, 20 Sep 2024 01:48:17 +0100 Subject: block: Remove unused blk_limits_io_{min,opt} blk_limits_io_min and blk_limits_io_opt are unused since the recent commit 0a94a469a4f0 ("dm: stop using blk_limits_io_{min,opt}") Remove them. Signed-off-by: Dr. David Alan Gilbert Link: https://lore.kernel.org/r/20240920004817.676216-1-linux@treblig.org Signed-off-by: Jens Axboe --- block/blk-settings.c | 42 ------------------------------------------ include/linux/blkdev.h | 2 -- 2 files changed, 44 deletions(-) (limited to 'include/linux') diff --git a/block/blk-settings.c b/block/blk-settings.c index cd8a8eabc9a5..a446654ddee5 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -437,48 +437,6 @@ int queue_limits_set(struct request_queue *q, struct queue_limits *lim) } EXPORT_SYMBOL_GPL(queue_limits_set); -/** - * blk_limits_io_min - set minimum request size for a device - * @limits: the queue limits - * @min: smallest I/O size in bytes - * - * Description: - * Some devices have an internal block size bigger than the reported - * hardware sector size. This function can be used to signal the - * smallest I/O the device can perform without incurring a performance - * penalty. - */ -void blk_limits_io_min(struct queue_limits *limits, unsigned int min) -{ - limits->io_min = min; - - if (limits->io_min < limits->logical_block_size) - limits->io_min = limits->logical_block_size; - - if (limits->io_min < limits->physical_block_size) - limits->io_min = limits->physical_block_size; -} -EXPORT_SYMBOL(blk_limits_io_min); - -/** - * blk_limits_io_opt - set optimal request size for a device - * @limits: the queue limits - * @opt: smallest I/O size in bytes - * - * Description: - * Storage devices may report an optimal I/O size, which is the - * device's preferred unit for sustained I/O. This is rarely reported - * for disk drives. For RAID arrays it is usually the stripe width or - * the internal track size. A properly aligned multiple of - * optimal_io_size is the preferred request size for workloads where - * sustained throughput is desired. - */ -void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt) -{ - limits->io_opt = opt; -} -EXPORT_SYMBOL(blk_limits_io_opt); - static int queue_limit_alignment_offset(const struct queue_limits *lim, sector_t sector) { diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 643c9020a35a..50c3b959da28 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -968,8 +968,6 @@ static inline void blk_queue_disable_write_zeroes(struct request_queue *q) /* * Access functions for manipulating queue properties */ -extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min); -extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt); extern void blk_set_queue_depth(struct request_queue *q, unsigned int depth); extern void blk_set_stacking_limits(struct queue_limits *lim); extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, -- cgit v1.2.3 From 65f666c6203600053478ce8e34a1db269a8701c9 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 19 Sep 2024 10:17:09 +0800 Subject: lib/sbitmap: define swap_lock as raw_spinlock_t When called from sbitmap_queue_get(), sbitmap_deferred_clear() may be run with preempt disabled. In RT kernel, spin_lock() can sleep, then warning of "BUG: sleeping function called from invalid context" can be triggered. Fix it by replacing it with raw_spin_lock. Cc: Yang Yang Fixes: 72d04bdcf3f7 ("sbitmap: fix io hung due to race on sbitmap_word::cleared") Signed-off-by: Ming Lei Reviewed-by: Yang Yang Link: https://lore.kernel.org/r/20240919021709.511329-1-ming.lei@redhat.com Signed-off-by: Jens Axboe --- include/linux/sbitmap.h | 2 +- lib/sbitmap.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index c09cdcc99471..189140bf11fc 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -40,7 +40,7 @@ struct sbitmap_word { /** * @swap_lock: serializes simultaneous updates of ->word and ->cleared */ - spinlock_t swap_lock; + raw_spinlock_t swap_lock; } ____cacheline_aligned_in_smp; /** diff --git a/lib/sbitmap.c b/lib/sbitmap.c index 5e2e93307f0d..d3412984170c 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -65,7 +65,7 @@ static inline bool sbitmap_deferred_clear(struct sbitmap_word *map, { unsigned long mask, word_mask; - guard(spinlock_irqsave)(&map->swap_lock); + guard(raw_spinlock_irqsave)(&map->swap_lock); if (!map->cleared) { if (depth == 0) @@ -136,7 +136,7 @@ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift, } for (i = 0; i < sb->map_nr; i++) - spin_lock_init(&sb->map[i].swap_lock); + raw_spin_lock_init(&sb->map[i].swap_lock); return 0; } -- cgit v1.2.3 From 652bfcb76fe689f4d85b6f3688025a87fb94f9a1 Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Wed, 31 Jul 2024 15:43:13 +0800 Subject: KEYS: Remove unused declarations These declarations are never implemented, remove it. Signed-off-by: Yue Haibing Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen --- include/keys/dns_resolver-type.h | 4 ---- include/linux/key.h | 3 --- 2 files changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/keys/dns_resolver-type.h b/include/keys/dns_resolver-type.h index 218ca22fb056..1b89088a2837 100644 --- a/include/keys/dns_resolver-type.h +++ b/include/keys/dns_resolver-type.h @@ -12,8 +12,4 @@ extern struct key_type key_type_dns_resolver; -extern int request_dns_resolver_key(const char *description, - const char *callout_info, - char **data); - #endif /* _KEYS_DNS_RESOLVER_TYPE_H */ diff --git a/include/linux/key.h b/include/linux/key.h index 943a432da3ae..074dca3222b9 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -436,9 +436,6 @@ extern key_ref_t keyring_search(key_ref_t keyring, const char *description, bool recurse); -extern int keyring_add_key(struct key *keyring, - struct key *key); - extern int keyring_restrict(key_ref_t keyring, const char *type, const char *restriction); -- cgit v1.2.3 From 60749cbe3d8ae572a6c7dda675de3e8b25797a18 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 15 Jul 2024 17:14:18 +1000 Subject: sunrpc: change sp_nrthreads from atomic_t to unsigned int. sp_nrthreads is only ever accessed under the service mutex nlmsvc_mutex nfs_callback_mutex nfsd_mutex so these is no need for it to be an atomic_t. The fact that all code using it is single-threaded means that we can simplify svc_pool_victim and remove the temporary elevation of sp_nrthreads. Signed-off-by: NeilBrown Signed-off-by: Chuck Lever --- fs/nfsd/nfsctl.c | 2 +- fs/nfsd/nfssvc.c | 2 +- include/linux/sunrpc/svc.h | 4 ++-- net/sunrpc/svc.c | 31 +++++++++++-------------------- 4 files changed, 15 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 965519995aeb..1c9e5b4bcb0a 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1769,7 +1769,7 @@ int nfsd_nl_threads_get_doit(struct sk_buff *skb, struct genl_info *info) struct svc_pool *sp = &nn->nfsd_serv->sv_pools[i]; err = nla_put_u32(skb, NFSD_A_SERVER_THREADS, - atomic_read(&sp->sp_nrthreads)); + sp->sp_nrthreads); if (err) goto err_unlock; } diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 5bc4dc60ea4c..b1dc3404173b 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -641,7 +641,7 @@ int nfsd_get_nrthreads(int n, int *nthreads, struct net *net) if (serv) for (i = 0; i < serv->sv_nrpools && i < n; i++) - nthreads[i] = atomic_read(&serv->sv_pools[i].sp_nrthreads); + nthreads[i] = serv->sv_pools[i].sp_nrthreads; return 0; } diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index e4fa25fafa97..99e9345d829e 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -33,9 +33,9 @@ * node traffic on multi-node NUMA NFS servers. */ struct svc_pool { - unsigned int sp_id; /* pool id; also node id on NUMA */ + unsigned int sp_id; /* pool id; also node id on NUMA */ struct lwq sp_xprts; /* pending transports */ - atomic_t sp_nrthreads; /* # of threads in pool */ + unsigned int sp_nrthreads; /* # of threads in pool */ struct list_head sp_all_threads; /* all server threads */ struct llist_head sp_idle_threads; /* idle server threads */ diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 2e148137376d..9442ebf38bbd 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -725,7 +725,7 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node) serv->sv_nrthreads += 1; spin_unlock_bh(&serv->sv_lock); - atomic_inc(&pool->sp_nrthreads); + pool->sp_nrthreads += 1; /* Protected by whatever lock the service uses when calling * svc_set_num_threads() @@ -780,31 +780,22 @@ svc_pool_victim(struct svc_serv *serv, struct svc_pool *target_pool, struct svc_pool *pool; unsigned int i; -retry: pool = target_pool; - if (pool != NULL) { - if (atomic_inc_not_zero(&pool->sp_nrthreads)) - goto found_pool; - return NULL; - } else { + if (!pool) { for (i = 0; i < serv->sv_nrpools; i++) { pool = &serv->sv_pools[--(*state) % serv->sv_nrpools]; - if (atomic_inc_not_zero(&pool->sp_nrthreads)) - goto found_pool; + if (pool->sp_nrthreads) + break; } - return NULL; } -found_pool: - set_bit(SP_VICTIM_REMAINS, &pool->sp_flags); - set_bit(SP_NEED_VICTIM, &pool->sp_flags); - if (!atomic_dec_and_test(&pool->sp_nrthreads)) + if (pool && pool->sp_nrthreads) { + set_bit(SP_VICTIM_REMAINS, &pool->sp_flags); + set_bit(SP_NEED_VICTIM, &pool->sp_flags); return pool; - /* Nothing left in this pool any more */ - clear_bit(SP_NEED_VICTIM, &pool->sp_flags); - clear_bit(SP_VICTIM_REMAINS, &pool->sp_flags); - goto retry; + } + return NULL; } static int @@ -883,7 +874,7 @@ svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) if (!pool) nrservs -= serv->sv_nrthreads; else - nrservs -= atomic_read(&pool->sp_nrthreads); + nrservs -= pool->sp_nrthreads; if (nrservs > 0) return svc_start_kthreads(serv, pool, nrservs); @@ -967,7 +958,7 @@ svc_exit_thread(struct svc_rqst *rqstp) list_del_rcu(&rqstp->rq_all); - atomic_dec(&pool->sp_nrthreads); + pool->sp_nrthreads -= 1; spin_lock_bh(&serv->sv_lock); serv->sv_nrthreads -= 1; -- cgit v1.2.3 From 3391fc92db8e761f1a2df5612fcb999dac6bc00a Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 16 Sep 2024 09:45:40 +1000 Subject: sunrpc: allow svc threads to fail initialisation cleanly If an svc thread needs to perform some initialisation that might fail, it has no good way to handle the failure. Before the thread can exit it must call svc_exit_thread(), but that requires the service mutex to be held. The thread cannot simply take the mutex as that could deadlock if there is a concurrent attempt to shut down all threads (which is unlikely, but not impossible). nfsd currently call svc_exit_thread() unprotected in the unlikely event that unshare_fs_struct() fails. We can clean this up by introducing svc_thread_init_status() by which an svc thread can report whether initialisation has succeeded. If it has, it continues normally into the action loop. If it has not, svc_thread_init_status() immediately aborts the thread. svc_start_kthread() waits for either of these to happen, and calls svc_exit_thread() (under the mutex) if the thread aborted. Signed-off-by: NeilBrown Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/lockd/svc.c | 2 ++ fs/nfs/callback.c | 2 ++ fs/nfsd/nfssvc.c | 9 +++------ include/linux/sunrpc/svc.h | 31 +++++++++++++++++++++++++++++++ net/sunrpc/svc.c | 10 ++++++++++ 5 files changed, 48 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 71713309967d..4ec22c2f2ea3 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -124,6 +124,8 @@ lockd(void *vrqstp) struct net *net = &init_net; struct lockd_net *ln = net_generic(net, lockd_net_id); + svc_thread_init_status(rqstp, 0); + /* try_to_freeze() is called from svc_recv() */ set_freezable(); diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 8adfcd4c8c1a..6cf92498a5ac 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -76,6 +76,8 @@ nfs4_callback_svc(void *vrqstp) { struct svc_rqst *rqstp = vrqstp; + svc_thread_init_status(rqstp, 0); + set_freezable(); while (!svc_thread_should_stop(rqstp)) diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index b1dc3404173b..3fb6c8c9a2f0 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -873,11 +873,9 @@ nfsd(void *vrqstp) /* At this point, the thread shares current->fs * with the init process. We need to create files with the - * umask as defined by the client instead of init's umask. */ - if (unshare_fs_struct() < 0) { - printk("Unable to start nfsd thread: out of memory\n"); - goto out; - } + * umask as defined by the client instead of init's umask. + */ + svc_thread_init_status(rqstp, unshare_fs_struct()); current->fs->umask = 0; @@ -899,7 +897,6 @@ nfsd(void *vrqstp) atomic_dec(&nfsd_th_cnt); -out: /* Release the thread */ svc_exit_thread(rqstp); return 0; diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 99e9345d829e..c419a61f60e5 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -21,6 +21,7 @@ #include #include #include +#include /* * @@ -232,6 +233,11 @@ struct svc_rqst { struct net *rq_bc_net; /* pointer to backchannel's * net namespace */ + + int rq_err; /* Thread sets this to inidicate + * initialisation success. + */ + unsigned long bc_to_initval; unsigned int bc_to_retries; void ** rq_lease_breaker; /* The v4 client breaking a lease */ @@ -305,6 +311,31 @@ static inline bool svc_thread_should_stop(struct svc_rqst *rqstp) return test_bit(RQ_VICTIM, &rqstp->rq_flags); } +/** + * svc_thread_init_status - report whether thread has initialised successfully + * @rqstp: the thread in question + * @err: errno code + * + * After performing any initialisation that could fail, and before starting + * normal work, each sunrpc svc_thread must call svc_thread_init_status() + * with an appropriate error, or zero. + * + * If zero is passed, the thread is ready and must continue until + * svc_thread_should_stop() returns true. If a non-zero error is passed + * the call will not return - the thread will exit. + */ +static inline void svc_thread_init_status(struct svc_rqst *rqstp, int err) +{ + rqstp->rq_err = err; + /* memory barrier ensures assignment to error above is visible before + * waitqueue_active() test below completes. + */ + smp_mb(); + wake_up_var(&rqstp->rq_err); + if (err) + kthread_exit(1); +} + struct svc_deferred_req { u32 prot; /* protocol (UDP or TCP) */ struct svc_xprt *xprt; diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 17f0f59c068f..9aff845196ce 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -706,6 +706,8 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node) if (!svc_init_buffer(rqstp, serv->sv_max_mesg, node)) goto out_enomem; + rqstp->rq_err = -EAGAIN; /* No error yet */ + serv->sv_nrthreads += 1; pool->sp_nrthreads += 1; @@ -792,6 +794,7 @@ svc_start_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) struct svc_pool *chosen_pool; unsigned int state = serv->sv_nrthreads-1; int node; + int err; do { nrservs--; @@ -814,6 +817,13 @@ svc_start_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) svc_sock_update_bufs(serv); wake_up_process(task); + + wait_var_event(&rqstp->rq_err, rqstp->rq_err != -EAGAIN); + err = rqstp->rq_err; + if (err) { + svc_exit_thread(rqstp); + return err; + } } while (nrservs > 0); return 0; -- cgit v1.2.3 From 36ffa3d0de54c1cf516ea32a5ec556f5c9874795 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 29 Jul 2024 11:47:23 +1000 Subject: nfsd: be more systematic about selecting error codes for internal use. Rather than using ad hoc values for internal errors (30000, 11000, ...) use 'enum' to sequentially allocate numbers starting from the first known available number - now visible as NFS4ERR_FIRST_FREE. The goal is values that are distinct from all be32 error codes. To get those we must first select integers that are not already used, then convert them with cpu_to_be32(). Signed-off-by: NeilBrown Reviewed-by: Jeff Layton Reviewed-by: Christoph Hellwig Signed-off-by: Chuck Lever --- fs/nfsd/nfsd.h | 24 +++++++++++++++++++----- include/linux/nfs4.h | 17 ++++++++++------- 2 files changed, 29 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 8750ade0a7ee..11825cbe4360 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -330,17 +330,31 @@ void nfsd_lockd_shutdown(void); #define nfserr_xattr2big cpu_to_be32(NFS4ERR_XATTR2BIG) #define nfserr_noxattr cpu_to_be32(NFS4ERR_NOXATTR) -/* error codes for internal use */ +/* + * Error codes for internal use. We use enum to choose numbers that are + * not already assigned, then covert to be32 resulting in a number that + * cannot conflict with any existing be32 nfserr value. + */ +enum { + NFSERR_DROPIT = NFS4ERR_FIRST_FREE, /* if a request fails due to kmalloc failure, it gets dropped. * Client should resend eventually */ -#define nfserr_dropit cpu_to_be32(30000) +#define nfserr_dropit cpu_to_be32(NFSERR_DROPIT) + /* end-of-file indicator in readdir */ -#define nfserr_eof cpu_to_be32(30001) + NFSERR_EOF, +#define nfserr_eof cpu_to_be32(NFSERR_EOF) + /* replay detected */ -#define nfserr_replay_me cpu_to_be32(11001) + NFSERR_REPLAY_ME, +#define nfserr_replay_me cpu_to_be32(NFSERR_REPLAY_ME) + /* nfs41 replay detected */ -#define nfserr_replay_cache cpu_to_be32(11002) + NFSERR_REPLAY_CACHE, +#define nfserr_replay_cache cpu_to_be32(NFSERR_REPLAY_CACHE) + +}; /* Check for dir entries '.' and '..' */ #define isdotent(n, l) (l < 3 && n[0] == '.' && (l == 1 || n[1] == '.')) diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index f9df88091c6d..8d7430d9f218 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -281,15 +281,18 @@ enum nfsstat4 { /* nfs42 */ NFS4ERR_PARTNER_NOTSUPP = 10088, NFS4ERR_PARTNER_NO_AUTH = 10089, - NFS4ERR_UNION_NOTSUPP = 10090, - NFS4ERR_OFFLOAD_DENIED = 10091, - NFS4ERR_WRONG_LFS = 10092, - NFS4ERR_BADLABEL = 10093, - NFS4ERR_OFFLOAD_NO_REQS = 10094, + NFS4ERR_UNION_NOTSUPP = 10090, + NFS4ERR_OFFLOAD_DENIED = 10091, + NFS4ERR_WRONG_LFS = 10092, + NFS4ERR_BADLABEL = 10093, + NFS4ERR_OFFLOAD_NO_REQS = 10094, /* xattr (RFC8276) */ - NFS4ERR_NOXATTR = 10095, - NFS4ERR_XATTR2BIG = 10096, + NFS4ERR_NOXATTR = 10095, + NFS4ERR_XATTR2BIG = 10096, + + /* can be used for internal errors */ + NFS4ERR_FIRST_FREE }; /* error codes for internal client use */ -- cgit v1.2.3 From c4de97f7c45434985e5dbf2d6ccc9eca676e37fe Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 29 Jul 2024 16:52:32 -0400 Subject: svcrdma: Handle device removal outside of the CM event handler Synchronously wait for all disconnects to complete to ensure the transports have divested all hardware resources before the underlying RDMA device can safely be removed. Reviewed-by: Sagi Grimberg Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc_rdma.h | 2 ++ include/trace/events/rpcrdma.h | 23 +++++++++++++++++++++++ net/sunrpc/xprtrdma/svc_rdma_transport.c | 16 +++++++++++++++- 3 files changed, 40 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index d33bab33099a..619fc0bd837a 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -48,6 +48,7 @@ #include #include #include +#include #include #include @@ -76,6 +77,7 @@ struct svcxprt_rdma { struct svc_xprt sc_xprt; /* SVC transport structure */ struct rdma_cm_id *sc_cm_id; /* RDMA connection id */ struct list_head sc_accept_q; /* Conn. waiting accept */ + struct rpcrdma_notification sc_rn; /* removal notification */ int sc_ord; /* RDMA read limit */ int sc_max_send_sges; bool sc_snd_w_inv; /* OK to use Send With Invalidate */ diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index a96a985c49b3..e6a72646c507 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -2172,6 +2172,29 @@ TRACE_EVENT(svcrdma_qp_error, ) ); +TRACE_EVENT(svcrdma_device_removal, + TP_PROTO( + const struct rdma_cm_id *id + ), + + TP_ARGS(id), + + TP_STRUCT__entry( + __string(name, id->device->name) + __array(unsigned char, addr, sizeof(struct sockaddr_in6)) + ), + + TP_fast_assign( + __assign_str(name); + memcpy(__entry->addr, &id->route.addr.dst_addr, + sizeof(struct sockaddr_in6)); + ), + + TP_printk("device %s to be removed, disconnecting %pISpc\n", + __get_str(name), __entry->addr + ) +); + DECLARE_EVENT_CLASS(svcrdma_sendqueue_class, TP_PROTO( const struct svcxprt_rdma *rdma, diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index f15750cacacf..581cc5ed7c0c 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -339,7 +339,6 @@ static int svc_rdma_cma_handler(struct rdma_cm_id *cma_id, svc_xprt_enqueue(xprt); break; case RDMA_CM_EVENT_DISCONNECTED: - case RDMA_CM_EVENT_DEVICE_REMOVAL: svc_xprt_deferred_close(xprt); break; default: @@ -384,6 +383,16 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv, return &cma_xprt->sc_xprt; } +static void svc_rdma_xprt_done(struct rpcrdma_notification *rn) +{ + struct svcxprt_rdma *rdma = container_of(rn, struct svcxprt_rdma, + sc_rn); + struct rdma_cm_id *id = rdma->sc_cm_id; + + trace_svcrdma_device_removal(id); + svc_xprt_close(&rdma->sc_xprt); +} + /* * This is the xpo_recvfrom function for listening endpoints. Its * purpose is to accept incoming connections. The CMA callback handler @@ -425,6 +434,9 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) dev = newxprt->sc_cm_id->device; newxprt->sc_port_num = newxprt->sc_cm_id->port_num; + if (rpcrdma_rn_register(dev, &newxprt->sc_rn, svc_rdma_xprt_done)) + goto errout; + newxprt->sc_max_req_size = svcrdma_max_req_size; newxprt->sc_max_requests = svcrdma_max_requests; newxprt->sc_max_bc_requests = svcrdma_max_bc_requests; @@ -580,6 +592,7 @@ static void __svc_rdma_free(struct work_struct *work) { struct svcxprt_rdma *rdma = container_of(work, struct svcxprt_rdma, sc_work); + struct ib_device *device = rdma->sc_cm_id->device; /* This blocks until the Completion Queues are empty */ if (rdma->sc_qp && !IS_ERR(rdma->sc_qp)) @@ -608,6 +621,7 @@ static void __svc_rdma_free(struct work_struct *work) /* Destroy the CM ID */ rdma_destroy_id(rdma->sc_cm_id); + rpcrdma_rn_unregister(device, &rdma->sc_rn); kfree(rdma); } -- cgit v1.2.3 From 4b132aacb0768ac1e652cf517097ea6f237214b9 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 13 Sep 2024 14:08:13 -0400 Subject: tools: Add xdrgen Add a Python-based tool for translating XDR specifications into XDR encoder and decoder functions written in the Linux kernel's C coding style. The generator attempts to match the usual C coding style of the Linux kernel's SunRPC consumers. This approach is similar to the netlink code generator in tools/net/ynl . The maintainability benefits of machine-generated XDR code include: - Stronger type checking - Reduces the number of bugs introduced by human error - Makes the XDR code easier to audit and analyze - Enables rapid prototyping of new RPC-based protocols - Hardens the layering between protocol logic and marshaling - Makes it easier to add observability on demand - Unit tests might be built for both the tool and (automatically) for the generated code In addition, converting the XDR layer to use memory-safe languages such as Rust will be easier if much of the code can be converted automatically. Tested-by: Jeff Layton Signed-off-by: Chuck Lever --- include/linux/sunrpc/xdrgen/_builtins.h | 243 ++++++++++ include/linux/sunrpc/xdrgen/_defs.h | 26 ++ tools/net/sunrpc/xdrgen/.gitignore | 2 + tools/net/sunrpc/xdrgen/README | 244 ++++++++++ tools/net/sunrpc/xdrgen/__init__.py | 2 + tools/net/sunrpc/xdrgen/generators/__init__.py | 113 +++++ tools/net/sunrpc/xdrgen/generators/constant.py | 20 + tools/net/sunrpc/xdrgen/generators/enum.py | 44 ++ .../net/sunrpc/xdrgen/generators/header_bottom.py | 33 ++ tools/net/sunrpc/xdrgen/generators/header_top.py | 45 ++ tools/net/sunrpc/xdrgen/generators/pointer.py | 272 +++++++++++ tools/net/sunrpc/xdrgen/generators/program.py | 168 +++++++ tools/net/sunrpc/xdrgen/generators/source_top.py | 32 ++ tools/net/sunrpc/xdrgen/generators/struct.py | 272 +++++++++++ tools/net/sunrpc/xdrgen/generators/typedef.py | 255 +++++++++++ tools/net/sunrpc/xdrgen/generators/union.py | 243 ++++++++++ tools/net/sunrpc/xdrgen/grammars/xdr.lark | 119 +++++ tools/net/sunrpc/xdrgen/subcmds/__init__.py | 2 + tools/net/sunrpc/xdrgen/subcmds/declarations.py | 76 +++ tools/net/sunrpc/xdrgen/subcmds/definitions.py | 78 ++++ tools/net/sunrpc/xdrgen/subcmds/lint.py | 33 ++ tools/net/sunrpc/xdrgen/subcmds/source.py | 118 +++++ .../xdrgen/templates/C/constants/definition.j2 | 3 + .../xdrgen/templates/C/enum/declaration/close.j2 | 4 + .../sunrpc/xdrgen/templates/C/enum/decoder/enum.j2 | 19 + .../xdrgen/templates/C/enum/definition/close.j2 | 2 + .../templates/C/enum/definition/enumerator.j2 | 2 + .../xdrgen/templates/C/enum/definition/open.j2 | 3 + .../sunrpc/xdrgen/templates/C/enum/encoder/enum.j2 | 14 + .../C/header_bottom/declaration/header.j2 | 3 + .../templates/C/header_bottom/definition/header.j2 | 3 + .../templates/C/header_top/declaration/header.j2 | 14 + .../templates/C/header_top/definition/header.j2 | 10 + .../templates/C/pointer/declaration/close.j2 | 4 + .../xdrgen/templates/C/pointer/decoder/basic.j2 | 6 + .../xdrgen/templates/C/pointer/decoder/close.j2 | 3 + .../C/pointer/decoder/fixed_length_array.j2 | 8 + .../C/pointer/decoder/fixed_length_opaque.j2 | 6 + .../xdrgen/templates/C/pointer/decoder/open.j2 | 22 + .../templates/C/pointer/decoder/optional_data.j2 | 6 + .../C/pointer/decoder/variable_length_array.j2 | 13 + .../C/pointer/decoder/variable_length_opaque.j2 | 6 + .../C/pointer/decoder/variable_length_string.j2 | 6 + .../xdrgen/templates/C/pointer/definition/basic.j2 | 5 + .../xdrgen/templates/C/pointer/definition/close.j2 | 2 + .../C/pointer/definition/fixed_length_array.j2 | 5 + .../C/pointer/definition/fixed_length_opaque.j2 | 5 + .../xdrgen/templates/C/pointer/definition/open.j2 | 6 + .../C/pointer/definition/optional_data.j2 | 5 + .../C/pointer/definition/variable_length_array.j2 | 8 + .../C/pointer/definition/variable_length_opaque.j2 | 5 + .../C/pointer/definition/variable_length_string.j2 | 5 + .../xdrgen/templates/C/pointer/encoder/basic.j2 | 10 + .../xdrgen/templates/C/pointer/encoder/close.j2 | 3 + .../C/pointer/encoder/fixed_length_array.j2 | 12 + .../C/pointer/encoder/fixed_length_opaque.j2 | 6 + .../xdrgen/templates/C/pointer/encoder/open.j2 | 20 + .../templates/C/pointer/encoder/optional_data.j2 | 6 + .../C/pointer/encoder/variable_length_array.j2 | 15 + .../C/pointer/encoder/variable_length_opaque.j2 | 8 + .../C/pointer/encoder/variable_length_string.j2 | 8 + .../templates/C/program/declaration/argument.j2 | 2 + .../templates/C/program/declaration/result.j2 | 2 + .../xdrgen/templates/C/program/decoder/argument.j2 | 21 + .../xdrgen/templates/C/program/decoder/result.j2 | 22 + .../xdrgen/templates/C/program/definition/close.j2 | 2 + .../xdrgen/templates/C/program/definition/open.j2 | 6 + .../templates/C/program/definition/procedure.j2 | 2 + .../xdrgen/templates/C/program/encoder/argument.j2 | 16 + .../xdrgen/templates/C/program/encoder/result.j2 | 21 + .../sunrpc/xdrgen/templates/C/source_top/client.j2 | 8 + .../sunrpc/xdrgen/templates/C/source_top/server.j2 | 8 + .../xdrgen/templates/C/struct/declaration/close.j2 | 4 + .../xdrgen/templates/C/struct/decoder/basic.j2 | 6 + .../xdrgen/templates/C/struct/decoder/close.j2 | 3 + .../C/struct/decoder/fixed_length_array.j2 | 8 + .../C/struct/decoder/fixed_length_opaque.j2 | 6 + .../xdrgen/templates/C/struct/decoder/open.j2 | 12 + .../templates/C/struct/decoder/optional_data.j2 | 6 + .../C/struct/decoder/variable_length_array.j2 | 13 + .../C/struct/decoder/variable_length_opaque.j2 | 6 + .../C/struct/decoder/variable_length_string.j2 | 6 + .../xdrgen/templates/C/struct/definition/basic.j2 | 5 + .../xdrgen/templates/C/struct/definition/close.j2 | 2 + .../C/struct/definition/fixed_length_array.j2 | 5 + .../C/struct/definition/fixed_length_opaque.j2 | 5 + .../xdrgen/templates/C/struct/definition/open.j2 | 6 + .../templates/C/struct/definition/optional_data.j2 | 5 + .../C/struct/definition/variable_length_array.j2 | 8 + .../C/struct/definition/variable_length_opaque.j2 | 5 + .../C/struct/definition/variable_length_string.j2 | 5 + .../xdrgen/templates/C/struct/encoder/basic.j2 | 10 + .../xdrgen/templates/C/struct/encoder/close.j2 | 3 + .../C/struct/encoder/fixed_length_array.j2 | 12 + .../C/struct/encoder/fixed_length_opaque.j2 | 6 + .../xdrgen/templates/C/struct/encoder/open.j2 | 12 + .../templates/C/struct/encoder/optional_data.j2 | 6 + .../C/struct/encoder/variable_length_array.j2 | 15 + .../C/struct/encoder/variable_length_opaque.j2 | 8 + .../C/struct/encoder/variable_length_string.j2 | 8 + .../templates/C/typedef/declaration/basic.j2 | 8 + .../C/typedef/declaration/fixed_length_array.j2 | 4 + .../C/typedef/declaration/fixed_length_opaque.j2 | 4 + .../C/typedef/declaration/variable_length_array.j2 | 4 + .../typedef/declaration/variable_length_opaque.j2 | 4 + .../typedef/declaration/variable_length_string.j2 | 4 + .../xdrgen/templates/C/typedef/decoder/basic.j2 | 17 + .../C/typedef/decoder/fixed_length_array.j2 | 25 + .../C/typedef/decoder/fixed_length_opaque.j2 | 17 + .../C/typedef/decoder/variable_length_array.j2 | 26 ++ .../C/typedef/decoder/variable_length_opaque.j2 | 17 + .../C/typedef/decoder/variable_length_string.j2 | 17 + .../xdrgen/templates/C/typedef/definition/basic.j2 | 6 + .../C/typedef/definition/fixed_length_array.j2 | 6 + .../C/typedef/definition/fixed_length_opaque.j2 | 6 + .../C/typedef/definition/variable_length_array.j2 | 9 + .../C/typedef/definition/variable_length_opaque.j2 | 6 + .../C/typedef/definition/variable_length_string.j2 | 6 + .../xdrgen/templates/C/typedef/encoder/basic.j2 | 21 + .../C/typedef/encoder/fixed_length_array.j2 | 25 + .../C/typedef/encoder/fixed_length_opaque.j2 | 17 + .../C/typedef/encoder/variable_length_array.j2 | 30 ++ .../C/typedef/encoder/variable_length_opaque.j2 | 17 + .../C/typedef/encoder/variable_length_string.j2 | 17 + .../xdrgen/templates/C/union/decoder/basic.j2 | 6 + .../xdrgen/templates/C/union/decoder/break.j2 | 2 + .../xdrgen/templates/C/union/decoder/case_spec.j2 | 2 + .../xdrgen/templates/C/union/decoder/close.j2 | 4 + .../templates/C/union/decoder/default_spec.j2 | 2 + .../xdrgen/templates/C/union/decoder/open.j2 | 12 + .../templates/C/union/decoder/optional_data.j2 | 6 + .../templates/C/union/decoder/switch_spec.j2 | 7 + .../C/union/decoder/variable_length_array.j2 | 13 + .../C/union/decoder/variable_length_opaque.j2 | 6 + .../C/union/decoder/variable_length_string.j2 | 6 + .../xdrgen/templates/C/union/decoder/void.j2 | 3 + .../templates/C/union/definition/case_spec.j2 | 2 + .../xdrgen/templates/C/union/definition/close.j2 | 8 + .../templates/C/union/definition/default_spec.j2 | 2 + .../xdrgen/templates/C/union/definition/open.j2 | 6 + .../templates/C/union/definition/switch_spec.j2 | 3 + .../xdrgen/templates/C/union/encoder/basic.j2 | 10 + .../xdrgen/templates/C/union/encoder/break.j2 | 2 + .../xdrgen/templates/C/union/encoder/case_spec.j2 | 2 + .../xdrgen/templates/C/union/encoder/close.j2 | 4 + .../templates/C/union/encoder/default_spec.j2 | 2 + .../xdrgen/templates/C/union/encoder/open.j2 | 12 + .../templates/C/union/encoder/switch_spec.j2 | 7 + .../xdrgen/templates/C/union/encoder/void.j2 | 3 + tools/net/sunrpc/xdrgen/tests/test.x | 36 ++ tools/net/sunrpc/xdrgen/xdr_ast.py | 510 +++++++++++++++++++++ tools/net/sunrpc/xdrgen/xdr_parse.py | 36 ++ tools/net/sunrpc/xdrgen/xdrgen | 132 ++++++ 153 files changed, 4196 insertions(+) create mode 100644 include/linux/sunrpc/xdrgen/_builtins.h create mode 100644 include/linux/sunrpc/xdrgen/_defs.h create mode 100644 tools/net/sunrpc/xdrgen/.gitignore create mode 100644 tools/net/sunrpc/xdrgen/README create mode 100644 tools/net/sunrpc/xdrgen/__init__.py create mode 100644 tools/net/sunrpc/xdrgen/generators/__init__.py create mode 100644 tools/net/sunrpc/xdrgen/generators/constant.py create mode 100644 tools/net/sunrpc/xdrgen/generators/enum.py create mode 100644 tools/net/sunrpc/xdrgen/generators/header_bottom.py create mode 100644 tools/net/sunrpc/xdrgen/generators/header_top.py create mode 100644 tools/net/sunrpc/xdrgen/generators/pointer.py create mode 100644 tools/net/sunrpc/xdrgen/generators/program.py create mode 100644 tools/net/sunrpc/xdrgen/generators/source_top.py create mode 100644 tools/net/sunrpc/xdrgen/generators/struct.py create mode 100644 tools/net/sunrpc/xdrgen/generators/typedef.py create mode 100644 tools/net/sunrpc/xdrgen/generators/union.py create mode 100644 tools/net/sunrpc/xdrgen/grammars/xdr.lark create mode 100644 tools/net/sunrpc/xdrgen/subcmds/__init__.py create mode 100644 tools/net/sunrpc/xdrgen/subcmds/declarations.py create mode 100644 tools/net/sunrpc/xdrgen/subcmds/definitions.py create mode 100644 tools/net/sunrpc/xdrgen/subcmds/lint.py create mode 100644 tools/net/sunrpc/xdrgen/subcmds/source.py create mode 100644 tools/net/sunrpc/xdrgen/templates/C/constants/definition.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/enum/declaration/close.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/enum/decoder/enum.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/enum/definition/close.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/enum/definition/enumerator.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/enum/definition/open.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/enum/encoder/enum.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/header_bottom/declaration/header.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/header_bottom/definition/header.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/header_top/declaration/header.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/header_top/definition/header.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/pointer/declaration/close.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/basic.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/close.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/fixed_length_array.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/fixed_length_opaque.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/open.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/optional_data.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/variable_length_array.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/variable_length_opaque.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/variable_length_string.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/pointer/definition/basic.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/pointer/definition/close.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/pointer/definition/fixed_length_array.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/pointer/definition/fixed_length_opaque.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/pointer/definition/open.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/pointer/definition/optional_data.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/pointer/definition/variable_length_array.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/pointer/definition/variable_length_opaque.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/pointer/definition/variable_length_string.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/basic.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/close.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/fixed_length_array.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/fixed_length_opaque.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/open.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/optional_data.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/variable_length_array.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/variable_length_opaque.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/variable_length_string.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/program/declaration/argument.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/program/declaration/result.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/program/decoder/argument.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/program/decoder/result.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/program/definition/close.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/program/definition/open.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/program/definition/procedure.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/program/encoder/argument.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/program/encoder/result.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/source_top/client.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/source_top/server.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/struct/declaration/close.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/struct/decoder/basic.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/struct/decoder/close.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/struct/decoder/fixed_length_array.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/struct/decoder/fixed_length_opaque.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/struct/decoder/open.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/struct/decoder/optional_data.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/struct/decoder/variable_length_array.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/struct/decoder/variable_length_opaque.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/struct/decoder/variable_length_string.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/struct/definition/basic.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/struct/definition/close.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/struct/definition/fixed_length_array.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/struct/definition/fixed_length_opaque.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/struct/definition/open.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/struct/definition/optional_data.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/struct/definition/variable_length_array.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/struct/definition/variable_length_opaque.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/struct/definition/variable_length_string.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/struct/encoder/basic.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/struct/encoder/close.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/struct/encoder/fixed_length_array.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/struct/encoder/fixed_length_opaque.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/struct/encoder/open.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/struct/encoder/optional_data.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/struct/encoder/variable_length_array.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/struct/encoder/variable_length_opaque.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/struct/encoder/variable_length_string.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/typedef/declaration/basic.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/typedef/declaration/fixed_length_array.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/typedef/declaration/fixed_length_opaque.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/typedef/declaration/variable_length_array.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/typedef/declaration/variable_length_opaque.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/typedef/declaration/variable_length_string.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/typedef/decoder/basic.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/typedef/decoder/fixed_length_array.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/typedef/decoder/fixed_length_opaque.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/typedef/decoder/variable_length_array.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/typedef/decoder/variable_length_opaque.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/typedef/decoder/variable_length_string.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/typedef/definition/basic.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/typedef/definition/fixed_length_array.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/typedef/definition/fixed_length_opaque.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/typedef/definition/variable_length_array.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/typedef/definition/variable_length_opaque.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/typedef/definition/variable_length_string.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/typedef/encoder/basic.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/typedef/encoder/fixed_length_array.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/typedef/encoder/fixed_length_opaque.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/typedef/encoder/variable_length_array.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/typedef/encoder/variable_length_opaque.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/typedef/encoder/variable_length_string.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/union/decoder/basic.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/union/decoder/break.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/union/decoder/case_spec.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/union/decoder/close.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/union/decoder/default_spec.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/union/decoder/open.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/union/decoder/optional_data.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/union/decoder/switch_spec.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/union/decoder/variable_length_array.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/union/decoder/variable_length_opaque.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/union/decoder/variable_length_string.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/union/decoder/void.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/union/definition/case_spec.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/union/definition/close.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/union/definition/default_spec.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/union/definition/open.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/union/definition/switch_spec.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/union/encoder/basic.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/union/encoder/break.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/union/encoder/case_spec.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/union/encoder/close.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/union/encoder/default_spec.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/union/encoder/open.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/union/encoder/switch_spec.j2 create mode 100644 tools/net/sunrpc/xdrgen/templates/C/union/encoder/void.j2 create mode 100644 tools/net/sunrpc/xdrgen/tests/test.x create mode 100644 tools/net/sunrpc/xdrgen/xdr_ast.py create mode 100644 tools/net/sunrpc/xdrgen/xdr_parse.py create mode 100755 tools/net/sunrpc/xdrgen/xdrgen (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdrgen/_builtins.h b/include/linux/sunrpc/xdrgen/_builtins.h new file mode 100644 index 000000000000..68746c59fc9a --- /dev/null +++ b/include/linux/sunrpc/xdrgen/_builtins.h @@ -0,0 +1,243 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Oracle and/or its affiliates. + * + * This header defines XDR data type primitives specified in + * Section 4 of RFC 4506, used by RPC programs implemented + * in the Linux kernel. + */ + +#ifndef _SUNRPC_XDRGEN__BUILTINS_H_ +#define _SUNRPC_XDRGEN__BUILTINS_H_ + +#include + +static inline bool +xdrgen_decode_void(struct xdr_stream *xdr) +{ + return true; +} + +static inline bool +xdrgen_encode_void(struct xdr_stream *xdr) +{ + return true; +} + +static inline bool +xdrgen_decode_bool(struct xdr_stream *xdr, bool *ptr) +{ + __be32 *p = xdr_inline_decode(xdr, XDR_UNIT); + + if (unlikely(!p)) + return false; + *ptr = (*p != xdr_zero); + return true; +} + +static inline bool +xdrgen_encode_bool(struct xdr_stream *xdr, bool val) +{ + __be32 *p = xdr_reserve_space(xdr, XDR_UNIT); + + if (unlikely(!p)) + return false; + *p = val ? xdr_one : xdr_zero; + return true; +} + +static inline bool +xdrgen_decode_int(struct xdr_stream *xdr, s32 *ptr) +{ + __be32 *p = xdr_inline_decode(xdr, XDR_UNIT); + + if (unlikely(!p)) + return false; + *ptr = be32_to_cpup(p); + return true; +} + +static inline bool +xdrgen_encode_int(struct xdr_stream *xdr, s32 val) +{ + __be32 *p = xdr_reserve_space(xdr, XDR_UNIT); + + if (unlikely(!p)) + return false; + *p = cpu_to_be32(val); + return true; +} + +static inline bool +xdrgen_decode_unsigned_int(struct xdr_stream *xdr, u32 *ptr) +{ + __be32 *p = xdr_inline_decode(xdr, XDR_UNIT); + + if (unlikely(!p)) + return false; + *ptr = be32_to_cpup(p); + return true; +} + +static inline bool +xdrgen_encode_unsigned_int(struct xdr_stream *xdr, u32 val) +{ + __be32 *p = xdr_reserve_space(xdr, XDR_UNIT); + + if (unlikely(!p)) + return false; + *p = cpu_to_be32(val); + return true; +} + +static inline bool +xdrgen_decode_long(struct xdr_stream *xdr, s32 *ptr) +{ + __be32 *p = xdr_inline_decode(xdr, XDR_UNIT); + + if (unlikely(!p)) + return false; + *ptr = be32_to_cpup(p); + return true; +} + +static inline bool +xdrgen_encode_long(struct xdr_stream *xdr, s32 val) +{ + __be32 *p = xdr_reserve_space(xdr, XDR_UNIT); + + if (unlikely(!p)) + return false; + *p = cpu_to_be32(val); + return true; +} + +static inline bool +xdrgen_decode_unsigned_long(struct xdr_stream *xdr, u32 *ptr) +{ + __be32 *p = xdr_inline_decode(xdr, XDR_UNIT); + + if (unlikely(!p)) + return false; + *ptr = be32_to_cpup(p); + return true; +} + +static inline bool +xdrgen_encode_unsigned_long(struct xdr_stream *xdr, u32 val) +{ + __be32 *p = xdr_reserve_space(xdr, XDR_UNIT); + + if (unlikely(!p)) + return false; + *p = cpu_to_be32(val); + return true; +} + +static inline bool +xdrgen_decode_hyper(struct xdr_stream *xdr, s64 *ptr) +{ + __be32 *p = xdr_inline_decode(xdr, XDR_UNIT * 2); + + if (unlikely(!p)) + return false; + *ptr = get_unaligned_be64(p); + return true; +} + +static inline bool +xdrgen_encode_hyper(struct xdr_stream *xdr, s64 val) +{ + __be32 *p = xdr_reserve_space(xdr, XDR_UNIT * 2); + + if (unlikely(!p)) + return false; + put_unaligned_be64(val, p); + return true; +} + +static inline bool +xdrgen_decode_unsigned_hyper(struct xdr_stream *xdr, u64 *ptr) +{ + __be32 *p = xdr_inline_decode(xdr, XDR_UNIT * 2); + + if (unlikely(!p)) + return false; + *ptr = get_unaligned_be64(p); + return true; +} + +static inline bool +xdrgen_encode_unsigned_hyper(struct xdr_stream *xdr, u64 val) +{ + __be32 *p = xdr_reserve_space(xdr, XDR_UNIT * 2); + + if (unlikely(!p)) + return false; + put_unaligned_be64(val, p); + return true; +} + +static inline bool +xdrgen_decode_string(struct xdr_stream *xdr, string *ptr, u32 maxlen) +{ + __be32 *p; + u32 len; + + if (unlikely(xdr_stream_decode_u32(xdr, &len) != XDR_UNIT)) + return false; + if (unlikely(maxlen && len > maxlen)) + return false; + if (len != 0) { + p = xdr_inline_decode(xdr, len); + if (unlikely(!p)) + return false; + ptr->data = (unsigned char *)p; + } + ptr->len = len; + return true; +} + +static inline bool +xdrgen_encode_string(struct xdr_stream *xdr, string val, u32 maxlen) +{ + __be32 *p = xdr_reserve_space(xdr, XDR_UNIT + xdr_align_size(val.len)); + + if (unlikely(!p)) + return false; + xdr_encode_opaque(p, val.data, val.len); + return true; +} + +static inline bool +xdrgen_decode_opaque(struct xdr_stream *xdr, opaque *ptr, u32 maxlen) +{ + __be32 *p; + u32 len; + + if (unlikely(xdr_stream_decode_u32(xdr, &len) != XDR_UNIT)) + return false; + if (unlikely(maxlen && len > maxlen)) + return false; + if (len != 0) { + p = xdr_inline_decode(xdr, len); + if (unlikely(!p)) + return false; + ptr->data = (u8 *)p; + } + ptr->len = len; + return true; +} + +static inline bool +xdrgen_encode_opaque(struct xdr_stream *xdr, opaque val) +{ + __be32 *p = xdr_reserve_space(xdr, XDR_UNIT + xdr_align_size(val.len)); + + if (unlikely(!p)) + return false; + xdr_encode_opaque(p, val.data, val.len); + return true; +} + +#endif /* _SUNRPC_XDRGEN__BUILTINS_H_ */ diff --git a/include/linux/sunrpc/xdrgen/_defs.h b/include/linux/sunrpc/xdrgen/_defs.h new file mode 100644 index 000000000000..be9e62371758 --- /dev/null +++ b/include/linux/sunrpc/xdrgen/_defs.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Oracle and/or its affiliates. + * + * This header defines XDR data type primitives specified in + * Section 4 of RFC 4506, used by RPC programs implemented + * in the Linux kernel. + */ + +#ifndef _SUNRPC_XDRGEN__DEFS_H_ +#define _SUNRPC_XDRGEN__DEFS_H_ + +#define TRUE (true) +#define FALSE (false) + +typedef struct { + u32 len; + unsigned char *data; +} string; + +typedef struct { + u32 len; + u8 *data; +} opaque; + +#endif /* _SUNRPC_XDRGEN__DEFS_H_ */ diff --git a/tools/net/sunrpc/xdrgen/.gitignore b/tools/net/sunrpc/xdrgen/.gitignore new file mode 100644 index 000000000000..d7366c2f9be8 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/.gitignore @@ -0,0 +1,2 @@ +__pycache__ +generators/__pycache__ diff --git a/tools/net/sunrpc/xdrgen/README b/tools/net/sunrpc/xdrgen/README new file mode 100644 index 000000000000..92f7738ad50c --- /dev/null +++ b/tools/net/sunrpc/xdrgen/README @@ -0,0 +1,244 @@ +xdrgen - Linux Kernel XDR code generator + +Introduction +------------ + +SunRPC programs are typically specified using a language defined by +RFC 4506. In fact, all IETF-published NFS specifications provide a +description of the specified protocol using this language. + +Since the 1990's, user space consumers of SunRPC have had access to +a tool that could read such XDR specifications and then generate C +code that implements the RPC portions of that protocol. This tool is +called rpcgen. + +This RPC-level code is code that handles input directly from the +network, and thus a high degree of memory safety and sanity checking +is needed to help ensure proper levels of security. Bugs in this +code can have significant impact on security and performance. + +However, it is code that is repetitive and tedious to write by hand. + +The C code generated by rpcgen makes extensive use of the facilities +of the user space TI-RPC library and libc. Furthermore, the dialect +of the generated code is very traditional K&R C. + +The Linux kernel's implementation of SunRPC-based protocols hand-roll +their XDR implementation. There are two main reasons for this: + +1. libtirpc (and its predecessors) operate only in user space. The + kernel's RPC implementation and its API are significantly + different than libtirpc. + +2. rpcgen-generated code is believed to be less efficient than code + that is hand-written. + +These days, gcc and its kin are capable of optimizing code better +than human authors. There are only a few instances where writing +XDR code by hand will make a measurable performance different. + +In addition, the current hand-written code in the Linux kernel is +difficult to audit and prove that it implements exactly what is in +the protocol specification. + +In order to accrue the benefits of machine-generated XDR code in the +kernel, a tool is needed that will output C code that works against +the kernel's SunRPC implementation rather than libtirpc. + +Enter xdrgen. + + +Dependencies +------------ + +These dependencies are typically packaged by Linux distributions: + +- python3 +- python3-lark +- python3-jinja2 + +These dependencies are available via PyPi: + +- pip install 'lark[interegular]' + + +XDR Specifications +------------------ + +When adding a new protocol implementation to the kernel, the XDR +specification can be derived by feeding a .txt copy of the RFC to +the script located in tools/net/sunrpc/extract.sh. + + $ extract.sh < rfc0001.txt > new2.x + + +Operation +--------- + +Once a .x file is available, use xdrgen to generate source and +header files containing an implementation of XDR encoding and +decoding functions for the specified protocol. + + $ ./xdrgen definitions new2.x > include/linux/sunrpc/xdrgen/new2.h + $ ./xdrgen declarations new2.x > new2xdr_gen.h + +and + + $ ./xdrgen source new2.x > new2xdr_gen.c + +The files are ready to use for a server-side protocol implementation, +or may be used as a guide for implementing these routines by hand. + +By default, the only comments added to this code are kdoc comments +that appear directly in front of the public per-procedure APIs. For +deeper introspection, specifying the "--annotate" flag will insert +additional comments in the generated code to help readers match the +generated code to specific parts of the XDR specification. + +Because the generated code is targeted for the Linux kernel, it +is tagged with a GPLv2-only license. + +The xdrgen tool can also provide lexical and syntax checking of +an XDR specification: + + $ ./xdrgen lint xdr/new.x + + +How It Works +------------ + +xdrgen does not use machine learning to generate source code. The +translation is entirely deterministic. + +RFC 4506 Section 6 contains a BNF grammar of the XDR specification +language. The grammar has been adapted for use by the Python Lark +module. + +The xdr.ebnf file in this directory contains the grammar used to +parse XDR specifications. xdrgen configures Lark using the grammar +in xdr.ebnf. Lark parses the target XDR specification using this +grammar, creating a parse tree. + +xdrgen then transforms the parse tree into an abstract syntax tree. +This tree is passed to a series of code generators. + +The generators are implemented as Python classes residing in the +generators/ directory. Each generator emits code created from Jinja2 +templates stored in the templates/ directory. + +The source code is generated in the same order in which they appear +in the specification to ensure the generated code compiles. This +conforms with the behavior of rpcgen. + +xdrgen assumes that the generated source code is further compiled by +a compiler that can optimize in a number of ways, including: + + - Unused functions are discarded (ie, not added to the executable) + + - Aggressive function inlining removes unnecessary stack frames + + - Single-arm switch statements are replaced by a single conditional + branch + +And so on. + + +Pragmas +------- + +Pragma directives specify exceptions to the normal generation of +encoding and decoding functions. Currently one directive is +implemented: "public". + +Pragma exclude +------ ------- + + pragma exclude ; + +In some cases, a procedure encoder or decoder function might need +special processing that cannot be automatically generated. The +automatically-generated functions might conflict or interfere with +the hand-rolled function. To avoid editing the generated source code +by hand, a pragma can specify that the procedure's encoder and +decoder functions are not included in the generated header and +source. + +For example: + + pragma exclude NFSPROC3_READDIRPLUS; + +Excludes the decoder function for the READDIRPLUS argument and the +encoder function for the READDIRPLUS result. + +Note that because data item encoder and decoder functions are +defined "static __maybe_unused", subsequent compilation +automatically excludes data item encoder and decoder functions that +are used only by excluded procedure. + +Pragma header +------ ------ + + pragma header ; + +Provide a name to use for the header file. For example: + + pragma header nlm4; + +Adds + + #include "nlm4xdr_gen.h" + +to the generated source file. + +Pragma public +------ ------ + + pragma public ; + +Normally XDR encoder and decoder functions are "static". In case an +implementer wants to call these functions from other source code, +s/he can add a public pragma in the input .x file to indicate a set +of functions that should get a prototype in the generated header, +and the function definitions will not be declared static. + +For example: + + pragma public nfsstat3; + +Adds these prototypes in the generated header: + + bool xdrgen_decode_nfsstat3(struct xdr_stream *xdr, enum nfsstat3 *ptr); + bool xdrgen_encode_nfsstat3(struct xdr_stream *xdr, enum nfsstat3 value); + +And, in the generated source code, both of these functions appear +without the "static __maybe_unused" modifiers. + + +Future Work +----------- + +Finish implementing XDR pointer and list types. + +Generate client-side procedure functions + +Expand the README into a user guide similar to rpcgen(1) + +Add more pragma directives: + + * @pages -- use xdr_read/write_pages() for the specified opaque + field + * @skip -- do not decode, but rather skip, the specified argument + field + +Enable something like a #include to dynamically insert the content +of other specification files + +Properly support line-by-line pass-through via the "%" decorator + +Build a unit test suite for verifying translation of XDR language +into compilable code + +Add a command-line option to insert trace_printk call sites in the +generated source code, for improved (temporary) observability + +Generate kernel Rust code as well as C code diff --git a/tools/net/sunrpc/xdrgen/__init__.py b/tools/net/sunrpc/xdrgen/__init__.py new file mode 100644 index 000000000000..c940e9275252 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/__init__.py @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +# Just to make sphinx-apidoc document this directory diff --git a/tools/net/sunrpc/xdrgen/generators/__init__.py b/tools/net/sunrpc/xdrgen/generators/__init__.py new file mode 100644 index 000000000000..fd2457461274 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/generators/__init__.py @@ -0,0 +1,113 @@ +# SPDX-License-Identifier: GPL-2.0 + +"""Define a base code generator class""" + +import sys +from jinja2 import Environment, FileSystemLoader, Template + +from xdr_ast import _XdrAst, Specification, _RpcProgram, _XdrTypeSpecifier +from xdr_ast import public_apis, pass_by_reference, get_header_name +from xdr_parse import get_xdr_annotate + + +def create_jinja2_environment(language: str, xdr_type: str) -> Environment: + """Open a set of templates based on output language""" + match language: + case "C": + environment = Environment( + loader=FileSystemLoader(sys.path[0] + "/templates/C/" + xdr_type + "/"), + trim_blocks=True, + lstrip_blocks=True, + ) + environment.globals["annotate"] = get_xdr_annotate() + environment.globals["public_apis"] = public_apis + environment.globals["pass_by_reference"] = pass_by_reference + return environment + case _: + raise NotImplementedError("Language not supported") + + +def get_jinja2_template( + environment: Environment, template_type: str, template_name: str +) -> Template: + """Retrieve a Jinja2 template for emitting source code""" + return environment.get_template(template_type + "/" + template_name + ".j2") + + +def find_xdr_program_name(root: Specification) -> str: + """Retrieve the RPC program name from an abstract syntax tree""" + raw_name = get_header_name() + if raw_name != "none": + return raw_name.lower() + for definition in root.definitions: + if isinstance(definition.value, _RpcProgram): + raw_name = definition.value.name + return raw_name.lower().removesuffix("_program").removesuffix("_prog") + return "noprog" + + +def header_guard_infix(filename: str) -> str: + """Extract the header guard infix from the specification filename""" + basename = filename.split("/")[-1] + program = basename.replace(".x", "") + return program.upper() + + +def kernel_c_type(spec: _XdrTypeSpecifier) -> str: + """Return name of C type""" + builtin_native_c_type = { + "bool": "bool", + "int": "s32", + "unsigned_int": "u32", + "long": "s32", + "unsigned_long": "u32", + "hyper": "s64", + "unsigned_hyper": "u64", + } + if spec.type_name in builtin_native_c_type: + return builtin_native_c_type[spec.type_name] + return spec.type_name + + +class Boilerplate: + """Base class to generate boilerplate for source files""" + + def __init__(self, language: str, peer: str): + """Initialize an instance of this class""" + raise NotImplementedError("No language support defined") + + def emit_declaration(self, filename: str, root: Specification) -> None: + """Emit declaration header boilerplate""" + raise NotImplementedError("Header boilerplate generation not supported") + + def emit_definition(self, filename: str, root: Specification) -> None: + """Emit definition header boilerplate""" + raise NotImplementedError("Header boilerplate generation not supported") + + def emit_source(self, filename: str, root: Specification) -> None: + """Emit generic source code for this XDR type""" + raise NotImplementedError("Source boilerplate generation not supported") + + +class SourceGenerator: + """Base class to generate header and source code for XDR types""" + + def __init__(self, language: str, peer: str): + """Initialize an instance of this class""" + raise NotImplementedError("No language support defined") + + def emit_declaration(self, node: _XdrAst) -> None: + """Emit one function declaration for this XDR type""" + raise NotImplementedError("Declaration generation not supported") + + def emit_decoder(self, node: _XdrAst) -> None: + """Emit one decoder function for this XDR type""" + raise NotImplementedError("Decoder generation not supported") + + def emit_definition(self, node: _XdrAst) -> None: + """Emit one definition for this XDR type""" + raise NotImplementedError("Definition generation not supported") + + def emit_encoder(self, node: _XdrAst) -> None: + """Emit one encoder function for this XDR type""" + raise NotImplementedError("Encoder generation not supported") diff --git a/tools/net/sunrpc/xdrgen/generators/constant.py b/tools/net/sunrpc/xdrgen/generators/constant.py new file mode 100644 index 000000000000..f2339caf0953 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/generators/constant.py @@ -0,0 +1,20 @@ +#!/usr/bin/env python3 +# ex: set filetype=python: + +"""Generate code to handle XDR constants""" + +from generators import SourceGenerator, create_jinja2_environment +from xdr_ast import _XdrConstant + +class XdrConstantGenerator(SourceGenerator): + """Generate source code for XDR constants""" + + def __init__(self, language: str, peer: str): + """Initialize an instance of this class""" + self.environment = create_jinja2_environment(language, "constants") + self.peer = peer + + def emit_definition(self, node: _XdrConstant) -> None: + """Emit one definition for a constant""" + template = self.environment.get_template("definition.j2") + print(template.render(name=node.name, value=node.value)) diff --git a/tools/net/sunrpc/xdrgen/generators/enum.py b/tools/net/sunrpc/xdrgen/generators/enum.py new file mode 100644 index 000000000000..855e43f4ae38 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/generators/enum.py @@ -0,0 +1,44 @@ +#!/usr/bin/env python3 +# ex: set filetype=python: + +"""Generate code to handle XDR enum types""" + +from generators import SourceGenerator, create_jinja2_environment +from xdr_ast import _XdrEnum, public_apis + + +class XdrEnumGenerator(SourceGenerator): + """Generate source code for XDR enum types""" + + def __init__(self, language: str, peer: str): + """Initialize an instance of this class""" + self.environment = create_jinja2_environment(language, "enum") + self.peer = peer + + def emit_declaration(self, node: _XdrEnum) -> None: + """Emit one declaration pair for an XDR enum type""" + if node.name in public_apis: + template = self.environment.get_template("declaration/close.j2") + print(template.render(name=node.name)) + + def emit_definition(self, node: _XdrEnum) -> None: + """Emit one definition for an XDR enum type""" + template = self.environment.get_template("definition/open.j2") + print(template.render(name=node.name)) + + template = self.environment.get_template("definition/enumerator.j2") + for enumerator in node.enumerators: + print(template.render(name=enumerator.name, value=enumerator.value)) + + template = self.environment.get_template("definition/close.j2") + print(template.render(name=node.name)) + + def emit_decoder(self, node: _XdrEnum) -> None: + """Emit one decoder function for an XDR enum type""" + template = self.environment.get_template("decoder/enum.j2") + print(template.render(name=node.name)) + + def emit_encoder(self, node: _XdrEnum) -> None: + """Emit one encoder function for an XDR enum type""" + template = self.environment.get_template("encoder/enum.j2") + print(template.render(name=node.name)) diff --git a/tools/net/sunrpc/xdrgen/generators/header_bottom.py b/tools/net/sunrpc/xdrgen/generators/header_bottom.py new file mode 100644 index 000000000000..4b55b282dfc0 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/generators/header_bottom.py @@ -0,0 +1,33 @@ +#!/usr/bin/env python3 +# ex: set filetype=python: + +"""Generate header bottom boilerplate""" + +import os.path +import time + +from generators import Boilerplate, header_guard_infix +from generators import create_jinja2_environment, get_jinja2_template +from xdr_ast import Specification + + +class XdrHeaderBottomGenerator(Boilerplate): + """Generate header boilerplate""" + + def __init__(self, language: str, peer: str): + """Initialize an instance of this class""" + self.environment = create_jinja2_environment(language, "header_bottom") + self.peer = peer + + def emit_declaration(self, filename: str, root: Specification) -> None: + """Emit the bottom header guard""" + template = get_jinja2_template(self.environment, "declaration", "header") + print(template.render(infix=header_guard_infix(filename))) + + def emit_definition(self, filename: str, root: Specification) -> None: + """Emit the bottom header guard""" + template = get_jinja2_template(self.environment, "definition", "header") + print(template.render(infix=header_guard_infix(filename))) + + def emit_source(self, filename: str, root: Specification) -> None: + pass diff --git a/tools/net/sunrpc/xdrgen/generators/header_top.py b/tools/net/sunrpc/xdrgen/generators/header_top.py new file mode 100644 index 000000000000..c6bc21c71f19 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/generators/header_top.py @@ -0,0 +1,45 @@ +#!/usr/bin/env python3 +# ex: set filetype=python: + +"""Generate header top boilerplate""" + +import os.path +import time + +from generators import Boilerplate, header_guard_infix +from generators import create_jinja2_environment, get_jinja2_template +from xdr_ast import Specification + + +class XdrHeaderTopGenerator(Boilerplate): + """Generate header boilerplate""" + + def __init__(self, language: str, peer: str): + """Initialize an instance of this class""" + self.environment = create_jinja2_environment(language, "header_top") + self.peer = peer + + def emit_declaration(self, filename: str, root: Specification) -> None: + """Emit the top header guard""" + template = get_jinja2_template(self.environment, "declaration", "header") + print( + template.render( + infix=header_guard_infix(filename), + filename=filename, + mtime=time.ctime(os.path.getmtime(filename)), + ) + ) + + def emit_definition(self, filename: str, root: Specification) -> None: + """Emit the top header guard""" + template = get_jinja2_template(self.environment, "definition", "header") + print( + template.render( + infix=header_guard_infix(filename), + filename=filename, + mtime=time.ctime(os.path.getmtime(filename)), + ) + ) + + def emit_source(self, filename: str, root: Specification) -> None: + pass diff --git a/tools/net/sunrpc/xdrgen/generators/pointer.py b/tools/net/sunrpc/xdrgen/generators/pointer.py new file mode 100644 index 000000000000..b0b27f1819c8 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/generators/pointer.py @@ -0,0 +1,272 @@ +#!/usr/bin/env python3 +# ex: set filetype=python: + +"""Generate code to handle XDR pointer types""" + +from jinja2 import Environment + +from generators import SourceGenerator, kernel_c_type +from generators import create_jinja2_environment, get_jinja2_template + +from xdr_ast import _XdrBasic, _XdrVariableLengthString +from xdr_ast import _XdrFixedLengthOpaque, _XdrVariableLengthOpaque +from xdr_ast import _XdrFixedLengthArray, _XdrVariableLengthArray +from xdr_ast import _XdrOptionalData, _XdrPointer, _XdrDeclaration +from xdr_ast import public_apis + + +def emit_pointer_declaration(environment: Environment, node: _XdrPointer) -> None: + """Emit a declaration pair for an XDR pointer type""" + if node.name in public_apis: + template = get_jinja2_template(environment, "declaration", "close") + print(template.render(name=node.name)) + + +def emit_pointer_member_definition( + environment: Environment, field: _XdrDeclaration +) -> None: + """Emit a definition for one field in an XDR struct""" + if isinstance(field, _XdrBasic): + template = get_jinja2_template(environment, "definition", field.template) + print( + template.render( + name=field.name, + type=kernel_c_type(field.spec), + classifier=field.spec.c_classifier, + ) + ) + elif isinstance(field, _XdrFixedLengthOpaque): + template = get_jinja2_template(environment, "definition", field.template) + print( + template.render( + name=field.name, + size=field.size, + ) + ) + elif isinstance(field, _XdrVariableLengthOpaque): + template = get_jinja2_template(environment, "definition", field.template) + print(template.render(name=field.name)) + elif isinstance(field, _XdrVariableLengthString): + template = get_jinja2_template(environment, "definition", field.template) + print(template.render(name=field.name)) + elif isinstance(field, _XdrFixedLengthArray): + template = get_jinja2_template(environment, "definition", field.template) + print( + template.render( + name=field.name, + type=kernel_c_type(field.spec), + size=field.size, + ) + ) + elif isinstance(field, _XdrVariableLengthArray): + template = get_jinja2_template(environment, "definition", field.template) + print( + template.render( + name=field.name, + type=kernel_c_type(field.spec), + classifier=field.spec.c_classifier, + ) + ) + elif isinstance(field, _XdrOptionalData): + template = get_jinja2_template(environment, "definition", field.template) + print( + template.render( + name=field.name, + type=kernel_c_type(field.spec), + classifier=field.spec.c_classifier, + ) + ) + + +def emit_pointer_definition(environment: Environment, node: _XdrPointer) -> None: + """Emit a definition for an XDR pointer type""" + template = get_jinja2_template(environment, "definition", "open") + print(template.render(name=node.name)) + + for field in node.fields[0:-1]: + emit_pointer_member_definition(environment, field) + + template = get_jinja2_template(environment, "definition", "close") + print(template.render(name=node.name)) + + +def emit_pointer_member_decoder( + environment: Environment, field: _XdrDeclaration +) -> None: + """Emit a decoder for one field in an XDR pointer""" + if isinstance(field, _XdrBasic): + template = get_jinja2_template(environment, "decoder", field.template) + print( + template.render( + name=field.name, + type=field.spec.type_name, + classifier=field.spec.c_classifier, + ) + ) + elif isinstance(field, _XdrFixedLengthOpaque): + template = get_jinja2_template(environment, "decoder", field.template) + print( + template.render( + name=field.name, + size=field.size, + ) + ) + elif isinstance(field, _XdrVariableLengthOpaque): + template = get_jinja2_template(environment, "decoder", field.template) + print( + template.render( + name=field.name, + maxsize=field.maxsize, + ) + ) + elif isinstance(field, _XdrVariableLengthString): + template = get_jinja2_template(environment, "decoder", field.template) + print( + template.render( + name=field.name, + maxsize=field.maxsize, + ) + ) + elif isinstance(field, _XdrFixedLengthArray): + template = get_jinja2_template(environment, "decoder", field.template) + print( + template.render( + name=field.name, + type=field.spec.type_name, + size=field.size, + classifier=field.spec.c_classifier, + ) + ) + elif isinstance(field, _XdrVariableLengthArray): + template = get_jinja2_template(environment, "decoder", field.template) + print( + template.render( + name=field.name, + type=field.spec.type_name, + maxsize=field.maxsize, + classifier=field.spec.c_classifier, + ) + ) + elif isinstance(field, _XdrOptionalData): + template = get_jinja2_template(environment, "decoder", field.template) + print( + template.render( + name=field.name, + type=field.spec.type_name, + classifier=field.spec.c_classifier, + ) + ) + + +def emit_pointer_decoder(environment: Environment, node: _XdrPointer) -> None: + """Emit one decoder function for an XDR pointer type""" + template = get_jinja2_template(environment, "decoder", "open") + print(template.render(name=node.name)) + + for field in node.fields[0:-1]: + emit_pointer_member_decoder(environment, field) + + template = get_jinja2_template(environment, "decoder", "close") + print(template.render()) + + +def emit_pointer_member_encoder( + environment: Environment, field: _XdrDeclaration +) -> None: + """Emit an encoder for one field in a XDR pointer""" + if isinstance(field, _XdrBasic): + template = get_jinja2_template(environment, "encoder", field.template) + print( + template.render( + name=field.name, + type=field.spec.type_name, + ) + ) + elif isinstance(field, _XdrFixedLengthOpaque): + template = get_jinja2_template(environment, "encoder", field.template) + print( + template.render( + name=field.name, + size=field.size, + ) + ) + elif isinstance(field, _XdrVariableLengthOpaque): + template = get_jinja2_template(environment, "encoder", field.template) + print( + template.render( + name=field.name, + maxsize=field.maxsize, + ) + ) + elif isinstance(field, _XdrVariableLengthString): + template = get_jinja2_template(environment, "encoder", field.template) + print( + template.render( + name=field.name, + maxsize=field.maxsize, + ) + ) + elif isinstance(field, _XdrFixedLengthArray): + template = get_jinja2_template(environment, "encoder", field.template) + print( + template.render( + name=field.name, + type=field.spec.type_name, + size=field.size, + ) + ) + elif isinstance(field, _XdrVariableLengthArray): + template = get_jinja2_template(environment, "encoder", field.template) + print( + template.render( + name=field.name, + type=field.spec.type_name, + maxsize=field.maxsize, + ) + ) + elif isinstance(field, _XdrOptionalData): + template = get_jinja2_template(environment, "encoder", field.template) + print( + template.render( + name=field.name, + type=field.spec.type_name, + classifier=field.spec.c_classifier, + ) + ) + + +def emit_pointer_encoder(environment: Environment, node: _XdrPointer) -> None: + """Emit one encoder function for an XDR pointer type""" + template = get_jinja2_template(environment, "encoder", "open") + print(template.render(name=node.name)) + + for field in node.fields[0:-1]: + emit_pointer_member_encoder(environment, field) + + template = get_jinja2_template(environment, "encoder", "close") + print(template.render()) + + +class XdrPointerGenerator(SourceGenerator): + """Generate source code for XDR pointer""" + + def __init__(self, language: str, peer: str): + """Initialize an instance of this class""" + self.environment = create_jinja2_environment(language, "pointer") + self.peer = peer + + def emit_declaration(self, node: _XdrPointer) -> None: + """Emit one declaration pair for an XDR pointer type""" + emit_pointer_declaration(self.environment, node) + + def emit_definition(self, node: _XdrPointer) -> None: + """Emit one declaration for an XDR pointer type""" + emit_pointer_definition(self.environment, node) + + def emit_decoder(self, node: _XdrPointer) -> None: + """Emit one decoder function for an XDR pointer type""" + emit_pointer_decoder(self.environment, node) + + def emit_encoder(self, node: _XdrPointer) -> None: + """Emit one encoder function for an XDR pointer type""" + emit_pointer_encoder(self.environment, node) diff --git a/tools/net/sunrpc/xdrgen/generators/program.py b/tools/net/sunrpc/xdrgen/generators/program.py new file mode 100644 index 000000000000..83b0ecbae86f --- /dev/null +++ b/tools/net/sunrpc/xdrgen/generators/program.py @@ -0,0 +1,168 @@ +#!/usr/bin/env python3 +# ex: set filetype=python: + +"""Generate code for an RPC program's procedures""" + +from jinja2 import Environment + +from generators import SourceGenerator, create_jinja2_environment +from xdr_ast import _RpcProgram, _RpcVersion, excluded_apis + + +def emit_version_definitions( + environment: Environment, program: str, version: _RpcVersion +) -> None: + """Emit procedure numbers for each RPC version's procedures""" + template = environment.get_template("definition/open.j2") + print(template.render(program=program.upper())) + + template = environment.get_template("definition/procedure.j2") + for procedure in version.procedures: + if procedure.name not in excluded_apis: + print( + template.render( + name=procedure.name, + value=procedure.number, + ) + ) + + template = environment.get_template("definition/close.j2") + print(template.render()) + + +def emit_version_declarations( + environment: Environment, program: str, version: _RpcVersion +) -> None: + """Emit declarations for each RPC version's procedures""" + arguments = set() + for procedure in version.procedures: + if procedure.name not in excluded_apis: + arguments.add(procedure.argument.type_name) + if len(arguments) > 0: + print("") + template = environment.get_template("declaration/argument.j2") + for argument in arguments: + print(template.render(program=program, argument=argument)) + + results = set() + for procedure in version.procedures: + if procedure.name not in excluded_apis: + results.add(procedure.result.type_name) + if len(results) > 0: + print("") + template = environment.get_template("declaration/result.j2") + for result in results: + print(template.render(program=program, result=result)) + + +def emit_version_argument_decoders( + environment: Environment, program: str, version: _RpcVersion +) -> None: + """Emit server argument decoders for each RPC version's procedures""" + arguments = set() + for procedure in version.procedures: + if procedure.name not in excluded_apis: + arguments.add(procedure.argument.type_name) + + template = environment.get_template("decoder/argument.j2") + for argument in arguments: + print(template.render(program=program, argument=argument)) + + +def emit_version_result_decoders( + environment: Environment, program: str, version: _RpcVersion +) -> None: + """Emit client result decoders for each RPC version's procedures""" + results = set() + for procedure in version.procedures: + if procedure.name not in excluded_apis: + results.add(procedure.result.type_name) + + template = environment.get_template("decoder/result.j2") + for result in results: + print(template.render(program=program, result=result)) + + +def emit_version_argument_encoders( + environment: Environment, program: str, version: _RpcVersion +) -> None: + """Emit client argument encoders for each RPC version's procedures""" + arguments = set() + for procedure in version.procedures: + if procedure.name not in excluded_apis: + arguments.add(procedure.argument.type_name) + + template = environment.get_template("encoder/argument.j2") + for argument in arguments: + print(template.render(program=program, argument=argument)) + + +def emit_version_result_encoders( + environment: Environment, program: str, version: _RpcVersion +) -> None: + """Emit server result encoders for each RPC version's procedures""" + results = set() + for procedure in version.procedures: + if procedure.name not in excluded_apis: + results.add(procedure.result.type_name) + + template = environment.get_template("encoder/result.j2") + for result in results: + print(template.render(program=program, result=result)) + + +class XdrProgramGenerator(SourceGenerator): + """Generate source code for an RPC program's procedures""" + + def __init__(self, language: str, peer: str): + """Initialize an instance of this class""" + self.environment = create_jinja2_environment(language, "program") + self.peer = peer + + def emit_definition(self, node: _RpcProgram) -> None: + """Emit procedure numbers for each of an RPC programs's procedures""" + raw_name = node.name + program = raw_name.lower().removesuffix("_program").removesuffix("_prog") + + for version in node.versions: + emit_version_definitions(self.environment, program, version) + + def emit_declaration(self, node: _RpcProgram) -> None: + """Emit a declaration pair for each of an RPC programs's procedures""" + raw_name = node.name + program = raw_name.lower().removesuffix("_program").removesuffix("_prog") + + for version in node.versions: + emit_version_declarations(self.environment, program, version) + + def emit_decoder(self, node: _RpcProgram) -> None: + """Emit all decoder functions for an RPC program's procedures""" + raw_name = node.name + program = raw_name.lower().removesuffix("_program").removesuffix("_prog") + match self.peer: + case "server": + for version in node.versions: + emit_version_argument_decoders( + self.environment, program, version, + ) + case "client": + for version in node.versions: + emit_version_result_decoders( + self.environment, program, version, + ) + + def emit_encoder(self, node: _RpcProgram) -> None: + """Emit all encoder functions for an RPC program's procedures""" + raw_name = node.name + program = raw_name.lower().removesuffix("_program").removesuffix("_prog") + match self.peer: + case "server": + for version in node.versions: + emit_version_result_encoders( + self.environment, program, version, + ) + case "client": + for version in node.versions: + emit_version_argument_encoders( + self.environment, program, version, + ) diff --git a/tools/net/sunrpc/xdrgen/generators/source_top.py b/tools/net/sunrpc/xdrgen/generators/source_top.py new file mode 100644 index 000000000000..bcf47d93d6f1 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/generators/source_top.py @@ -0,0 +1,32 @@ +#!/usr/bin/env python3 +# ex: set filetype=python: + +"""Generate source code boilerplate""" + +import os.path +import time + +from generators import Boilerplate +from generators import find_xdr_program_name, create_jinja2_environment +from xdr_ast import _RpcProgram, Specification, get_header_name + + +class XdrSourceTopGenerator(Boilerplate): + """Generate source code boilerplate""" + + def __init__(self, language: str, peer: str): + """Initialize an instance of this class""" + self.environment = create_jinja2_environment(language, "source_top") + self.peer = peer + + def emit_source(self, filename: str, root: Specification) -> None: + """Emit the top source boilerplate""" + name = find_xdr_program_name(root) + template = self.environment.get_template(self.peer + ".j2") + print( + template.render( + program=name, + filename=filename, + mtime=time.ctime(os.path.getmtime(filename)), + ) + ) diff --git a/tools/net/sunrpc/xdrgen/generators/struct.py b/tools/net/sunrpc/xdrgen/generators/struct.py new file mode 100644 index 000000000000..b694cd470829 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/generators/struct.py @@ -0,0 +1,272 @@ +#!/usr/bin/env python3 +# ex: set filetype=python: + +"""Generate code to handle XDR struct types""" + +from jinja2 import Environment + +from generators import SourceGenerator, kernel_c_type +from generators import create_jinja2_environment, get_jinja2_template + +from xdr_ast import _XdrBasic, _XdrVariableLengthString +from xdr_ast import _XdrFixedLengthOpaque, _XdrVariableLengthOpaque +from xdr_ast import _XdrFixedLengthArray, _XdrVariableLengthArray +from xdr_ast import _XdrOptionalData, _XdrStruct, _XdrDeclaration +from xdr_ast import public_apis + + +def emit_struct_declaration(environment: Environment, node: _XdrStruct) -> None: + """Emit one declaration pair for an XDR struct type""" + if node.name in public_apis: + template = get_jinja2_template(environment, "declaration", "close") + print(template.render(name=node.name)) + + +def emit_struct_member_definition( + environment: Environment, field: _XdrDeclaration +) -> None: + """Emit a definition for one field in an XDR struct""" + if isinstance(field, _XdrBasic): + template = get_jinja2_template(environment, "definition", field.template) + print( + template.render( + name=field.name, + type=kernel_c_type(field.spec), + classifier=field.spec.c_classifier, + ) + ) + elif isinstance(field, _XdrFixedLengthOpaque): + template = get_jinja2_template(environment, "definition", field.template) + print( + template.render( + name=field.name, + size=field.size, + ) + ) + elif isinstance(field, _XdrVariableLengthOpaque): + template = get_jinja2_template(environment, "definition", field.template) + print(template.render(name=field.name)) + elif isinstance(field, _XdrVariableLengthString): + template = get_jinja2_template(environment, "definition", field.template) + print(template.render(name=field.name)) + elif isinstance(field, _XdrFixedLengthArray): + template = get_jinja2_template(environment, "definition", field.template) + print( + template.render( + name=field.name, + type=kernel_c_type(field.spec), + size=field.size, + ) + ) + elif isinstance(field, _XdrVariableLengthArray): + template = get_jinja2_template(environment, "definition", field.template) + print( + template.render( + name=field.name, + type=kernel_c_type(field.spec), + classifier=field.spec.c_classifier, + ) + ) + elif isinstance(field, _XdrOptionalData): + template = get_jinja2_template(environment, "definition", field.template) + print( + template.render( + name=field.name, + type=kernel_c_type(field.spec), + classifier=field.spec.c_classifier, + ) + ) + + +def emit_struct_definition(environment: Environment, node: _XdrStruct) -> None: + """Emit one definition for an XDR struct type""" + template = get_jinja2_template(environment, "definition", "open") + print(template.render(name=node.name)) + + for field in node.fields: + emit_struct_member_definition(environment, field) + + template = get_jinja2_template(environment, "definition", "close") + print(template.render(name=node.name)) + + +def emit_struct_member_decoder( + environment: Environment, field: _XdrDeclaration +) -> None: + """Emit a decoder for one field in an XDR struct""" + if isinstance(field, _XdrBasic): + template = get_jinja2_template(environment, "decoder", field.template) + print( + template.render( + name=field.name, + type=field.spec.type_name, + classifier=field.spec.c_classifier, + ) + ) + elif isinstance(field, _XdrFixedLengthOpaque): + template = get_jinja2_template(environment, "decoder", field.template) + print( + template.render( + name=field.name, + size=field.size, + ) + ) + elif isinstance(field, _XdrVariableLengthOpaque): + template = get_jinja2_template(environment, "decoder", field.template) + print( + template.render( + name=field.name, + maxsize=field.maxsize, + ) + ) + elif isinstance(field, _XdrVariableLengthString): + template = get_jinja2_template(environment, "decoder", field.template) + print( + template.render( + name=field.name, + maxsize=field.maxsize, + ) + ) + elif isinstance(field, _XdrFixedLengthArray): + template = get_jinja2_template(environment, "decoder", field.template) + print( + template.render( + name=field.name, + type=field.spec.type_name, + size=field.size, + classifier=field.spec.c_classifier, + ) + ) + elif isinstance(field, _XdrVariableLengthArray): + template = get_jinja2_template(environment, "decoder", field.template) + print( + template.render( + name=field.name, + type=field.spec.type_name, + maxsize=field.maxsize, + classifier=field.spec.c_classifier, + ) + ) + elif isinstance(field, _XdrOptionalData): + template = get_jinja2_template(environment, "decoder", field.template) + print( + template.render( + name=field.name, + type=field.spec.type_name, + classifier=field.spec.c_classifier, + ) + ) + + +def emit_struct_decoder(environment: Environment, node: _XdrStruct) -> None: + """Emit one decoder function for an XDR struct type""" + template = get_jinja2_template(environment, "decoder", "open") + print(template.render(name=node.name)) + + for field in node.fields: + emit_struct_member_decoder(environment, field) + + template = get_jinja2_template(environment, "decoder", "close") + print(template.render()) + + +def emit_struct_member_encoder( + environment: Environment, field: _XdrDeclaration +) -> None: + """Emit an encoder for one field in an XDR struct""" + if isinstance(field, _XdrBasic): + template = get_jinja2_template(environment, "encoder", field.template) + print( + template.render( + name=field.name, + type=field.spec.type_name, + ) + ) + elif isinstance(field, _XdrFixedLengthOpaque): + template = get_jinja2_template(environment, "encoder", field.template) + print( + template.render( + name=field.name, + size=field.size, + ) + ) + elif isinstance(field, _XdrVariableLengthOpaque): + template = get_jinja2_template(environment, "encoder", field.template) + print( + template.render( + name=field.name, + maxsize=field.maxsize, + ) + ) + elif isinstance(field, _XdrVariableLengthString): + template = get_jinja2_template(environment, "encoder", field.template) + print( + template.render( + name=field.name, + maxsize=field.maxsize, + ) + ) + elif isinstance(field, _XdrFixedLengthArray): + template = get_jinja2_template(environment, "encoder", field.template) + print( + template.render( + name=field.name, + type=field.spec.type_name, + size=field.size, + ) + ) + elif isinstance(field, _XdrVariableLengthArray): + template = get_jinja2_template(environment, "encoder", field.template) + print( + template.render( + name=field.name, + type=field.spec.type_name, + maxsize=field.maxsize, + ) + ) + elif isinstance(field, _XdrOptionalData): + template = get_jinja2_template(environment, "encoder", field.template) + print( + template.render( + name=field.name, + type=field.spec.type_name, + classifier=field.spec.c_classifier, + ) + ) + + +def emit_struct_encoder(environment: Environment, node: _XdrStruct) -> None: + """Emit one encoder function for an XDR struct type""" + template = get_jinja2_template(environment, "encoder", "open") + print(template.render(name=node.name)) + + for field in node.fields: + emit_struct_member_encoder(environment, field) + + template = get_jinja2_template(environment, "encoder", "close") + print(template.render()) + + +class XdrStructGenerator(SourceGenerator): + """Generate source code for XDR structs""" + + def __init__(self, language: str, peer: str): + """Initialize an instance of this class""" + self.environment = create_jinja2_environment(language, "struct") + self.peer = peer + + def emit_declaration(self, node: _XdrStruct) -> None: + """Emit one declaration pair for an XDR struct type""" + emit_struct_declaration(self.environment, node) + + def emit_definition(self, node: _XdrStruct) -> None: + """Emit one definition for an XDR struct type""" + emit_struct_definition(self.environment, node) + + def emit_decoder(self, node: _XdrStruct) -> None: + """Emit one decoder function for an XDR struct type""" + emit_struct_decoder(self.environment, node) + + def emit_encoder(self, node: _XdrStruct) -> None: + """Emit one encoder function for an XDR struct type""" + emit_struct_encoder(self.environment, node) diff --git a/tools/net/sunrpc/xdrgen/generators/typedef.py b/tools/net/sunrpc/xdrgen/generators/typedef.py new file mode 100644 index 000000000000..85a1b2303333 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/generators/typedef.py @@ -0,0 +1,255 @@ +#!/usr/bin/env python3 +# ex: set filetype=python: + +"""Generate code to handle XDR typedefs""" + +from jinja2 import Environment + +from generators import SourceGenerator, kernel_c_type +from generators import create_jinja2_environment, get_jinja2_template + +from xdr_ast import _XdrBasic, _XdrTypedef, _XdrVariableLengthString +from xdr_ast import _XdrFixedLengthOpaque, _XdrVariableLengthOpaque +from xdr_ast import _XdrFixedLengthArray, _XdrVariableLengthArray +from xdr_ast import _XdrOptionalData, _XdrVoid, _XdrDeclaration +from xdr_ast import public_apis + + +def emit_typedef_declaration(environment: Environment, node: _XdrDeclaration) -> None: + """Emit a declaration pair for one XDR typedef""" + if node.name not in public_apis: + return + if isinstance(node, _XdrBasic): + template = get_jinja2_template(environment, "declaration", node.template) + print( + template.render( + name=node.name, + type=kernel_c_type(node.spec), + classifier=node.spec.c_classifier, + ) + ) + elif isinstance(node, _XdrVariableLengthString): + template = get_jinja2_template(environment, "declaration", node.template) + print(template.render(name=node.name)) + elif isinstance(node, _XdrFixedLengthOpaque): + template = get_jinja2_template(environment, "declaration", node.template) + print(template.render(name=node.name, size=node.size)) + elif isinstance(node, _XdrVariableLengthOpaque): + template = get_jinja2_template(environment, "declaration", node.template) + print(template.render(name=node.name)) + elif isinstance(node, _XdrFixedLengthArray): + template = get_jinja2_template(environment, "declaration", node.template) + print( + template.render( + name=node.name, + type=node.spec.type_name, + size=node.size, + ) + ) + elif isinstance(node, _XdrVariableLengthArray): + template = get_jinja2_template(environment, "declaration", node.template) + print( + template.render( + name=node.name, + type=node.spec.type_name, + classifier=node.spec.c_classifier, + ) + ) + elif isinstance(node, _XdrOptionalData): + raise NotImplementedError(" typedef not yet implemented") + elif isinstance(node, _XdrVoid): + raise NotImplementedError(" typedef not yet implemented") + else: + raise NotImplementedError("typedef: type not recognized") + + +def emit_type_definition(environment: Environment, node: _XdrDeclaration) -> None: + """Emit a definition for one XDR typedef""" + if isinstance(node, _XdrBasic): + template = get_jinja2_template(environment, "definition", node.template) + print( + template.render( + name=node.name, + type=kernel_c_type(node.spec), + classifier=node.spec.c_classifier, + ) + ) + elif isinstance(node, _XdrVariableLengthString): + template = get_jinja2_template(environment, "definition", node.template) + print(template.render(name=node.name)) + elif isinstance(node, _XdrFixedLengthOpaque): + template = get_jinja2_template(environment, "definition", node.template) + print(template.render(name=node.name, size=node.size)) + elif isinstance(node, _XdrVariableLengthOpaque): + template = get_jinja2_template(environment, "definition", node.template) + print(template.render(name=node.name)) + elif isinstance(node, _XdrFixedLengthArray): + template = get_jinja2_template(environment, "definition", node.template) + print( + template.render( + name=node.name, + type=node.spec.type_name, + size=node.size, + ) + ) + elif isinstance(node, _XdrVariableLengthArray): + template = get_jinja2_template(environment, "definition", node.template) + print( + template.render( + name=node.name, + type=node.spec.type_name, + classifier=node.spec.c_classifier, + ) + ) + elif isinstance(node, _XdrOptionalData): + raise NotImplementedError(" typedef not yet implemented") + elif isinstance(node, _XdrVoid): + raise NotImplementedError(" typedef not yet implemented") + else: + raise NotImplementedError("typedef: type not recognized") + + +def emit_typedef_decoder(environment: Environment, node: _XdrDeclaration) -> None: + """Emit a decoder function for one XDR typedef""" + if isinstance(node, _XdrBasic): + template = get_jinja2_template(environment, "decoder", node.template) + print( + template.render( + name=node.name, + type=node.spec.type_name, + ) + ) + elif isinstance(node, _XdrVariableLengthString): + template = get_jinja2_template(environment, "decoder", node.template) + print( + template.render( + name=node.name, + maxsize=node.maxsize, + ) + ) + elif isinstance(node, _XdrFixedLengthOpaque): + template = get_jinja2_template(environment, "decoder", node.template) + print( + template.render( + name=node.name, + size=node.size, + ) + ) + elif isinstance(node, _XdrVariableLengthOpaque): + template = get_jinja2_template(environment, "decoder", node.template) + print( + template.render( + name=node.name, + maxsize=node.maxsize, + ) + ) + elif isinstance(node, _XdrFixedLengthArray): + template = get_jinja2_template(environment, "decoder", node.template) + print( + template.render( + name=node.name, + type=node.spec.type_name, + size=node.size, + classifier=node.spec.c_classifier, + ) + ) + elif isinstance(node, _XdrVariableLengthArray): + template = get_jinja2_template(environment, "decoder", node.template) + print( + template.render( + name=node.name, + type=node.spec.type_name, + maxsize=node.maxsize, + ) + ) + elif isinstance(node, _XdrOptionalData): + raise NotImplementedError(" typedef not yet implemented") + elif isinstance(node, _XdrVoid): + raise NotImplementedError(" typedef not yet implemented") + else: + raise NotImplementedError("typedef: type not recognized") + + +def emit_typedef_encoder(environment: Environment, node: _XdrDeclaration) -> None: + """Emit an encoder function for one XDR typedef""" + if isinstance(node, _XdrBasic): + template = get_jinja2_template(environment, "encoder", node.template) + print( + template.render( + name=node.name, + type=node.spec.type_name, + ) + ) + elif isinstance(node, _XdrVariableLengthString): + template = get_jinja2_template(environment, "encoder", node.template) + print( + template.render( + name=node.name, + maxsize=node.maxsize, + ) + ) + elif isinstance(node, _XdrFixedLengthOpaque): + template = get_jinja2_template(environment, "encoder", node.template) + print( + template.render( + name=node.name, + size=node.size, + ) + ) + elif isinstance(node, _XdrVariableLengthOpaque): + template = get_jinja2_template(environment, "encoder", node.template) + print( + template.render( + name=node.name, + maxsize=node.maxsize, + ) + ) + elif isinstance(node, _XdrFixedLengthArray): + template = get_jinja2_template(environment, "encoder", node.template) + print( + template.render( + name=node.name, + type=node.spec.type_name, + size=node.size, + ) + ) + elif isinstance(node, _XdrVariableLengthArray): + template = get_jinja2_template(environment, "encoder", node.template) + print( + template.render( + name=node.name, + type=node.spec.type_name, + maxsize=node.maxsize, + ) + ) + elif isinstance(node, _XdrOptionalData): + raise NotImplementedError(" typedef not yet implemented") + elif isinstance(node, _XdrVoid): + raise NotImplementedError(" typedef not yet implemented") + else: + raise NotImplementedError("typedef: type not recognized") + + +class XdrTypedefGenerator(SourceGenerator): + """Generate source code for XDR typedefs""" + + def __init__(self, language: str, peer: str): + """Initialize an instance of this class""" + self.environment = create_jinja2_environment(language, "typedef") + self.peer = peer + + def emit_declaration(self, node: _XdrTypedef) -> None: + """Emit one declaration pair for an XDR enum type""" + emit_typedef_declaration(self.environment, node.declaration) + + def emit_definition(self, node: _XdrTypedef) -> None: + """Emit one definition for an XDR typedef""" + emit_type_definition(self.environment, node.declaration) + + def emit_decoder(self, node: _XdrTypedef) -> None: + """Emit one decoder function for an XDR typedef""" + emit_typedef_decoder(self.environment, node.declaration) + + def emit_encoder(self, node: _XdrTypedef) -> None: + """Emit one encoder function for an XDR typedef""" + emit_typedef_encoder(self.environment, node.declaration) diff --git a/tools/net/sunrpc/xdrgen/generators/union.py b/tools/net/sunrpc/xdrgen/generators/union.py new file mode 100644 index 000000000000..7974967bbb9f --- /dev/null +++ b/tools/net/sunrpc/xdrgen/generators/union.py @@ -0,0 +1,243 @@ +#!/usr/bin/env python3 +# ex: set filetype=python: + +"""Generate code to handle XDR unions""" + +from jinja2 import Environment + +from generators import SourceGenerator +from generators import create_jinja2_environment, get_jinja2_template + +from xdr_ast import _XdrBasic, _XdrUnion, _XdrVoid +from xdr_ast import _XdrDeclaration, _XdrCaseSpec, public_apis + + +def emit_union_declaration(environment: Environment, node: _XdrUnion) -> None: + """Emit one declaration pair for an XDR union type""" + if node.name in public_apis: + template = get_jinja2_template(environment, "declaration", "close") + print(template.render(name=node.name)) + + +def emit_union_switch_spec_definition( + environment: Environment, node: _XdrDeclaration +) -> None: + """Emit a definition for an XDR union's discriminant""" + assert isinstance(node, _XdrBasic) + template = get_jinja2_template(environment, "definition", "switch_spec") + print( + template.render( + name=node.name, + type=node.spec.type_name, + classifier=node.spec.c_classifier, + ) + ) + + +def emit_union_case_spec_definition( + environment: Environment, node: _XdrDeclaration +) -> None: + """Emit a definition for an XDR union's case arm""" + if isinstance(node.arm, _XdrVoid): + return + assert isinstance(node.arm, _XdrBasic) + template = get_jinja2_template(environment, "definition", "case_spec") + print( + template.render( + name=node.arm.name, + type=node.arm.spec.type_name, + classifier=node.arm.spec.c_classifier, + ) + ) + + +def emit_union_definition(environment: Environment, node: _XdrUnion) -> None: + """Emit one XDR union definition""" + template = get_jinja2_template(environment, "definition", "open") + print(template.render(name=node.name)) + + emit_union_switch_spec_definition(environment, node.discriminant) + + for case in node.cases: + emit_union_case_spec_definition(environment, case) + + if node.default is not None: + emit_union_case_spec_definition(environment, node.default) + + template = get_jinja2_template(environment, "definition", "close") + print(template.render(name=node.name)) + + +def emit_union_switch_spec_decoder( + environment: Environment, node: _XdrDeclaration +) -> None: + """Emit a decoder for an XDR union's discriminant""" + assert isinstance(node, _XdrBasic) + template = get_jinja2_template(environment, "decoder", "switch_spec") + print(template.render(name=node.name, type=node.spec.type_name)) + + +def emit_union_case_spec_decoder(environment: Environment, node: _XdrCaseSpec) -> None: + """Emit decoder functions for an XDR union's case arm""" + + if isinstance(node.arm, _XdrVoid): + return + + template = get_jinja2_template(environment, "decoder", "case_spec") + for case in node.values: + print(template.render(case=case)) + + assert isinstance(node.arm, _XdrBasic) + template = get_jinja2_template(environment, "decoder", node.arm.template) + print( + template.render( + name=node.arm.name, + type=node.arm.spec.type_name, + classifier=node.arm.spec.c_classifier, + ) + ) + + template = get_jinja2_template(environment, "decoder", "break") + print(template.render()) + + +def emit_union_default_spec_decoder(environment: Environment, node: _XdrUnion) -> None: + """Emit a decoder function for an XDR union's default arm""" + default_case = node.default + + # Avoid a gcc warning about a default case with boolean discriminant + if default_case is None and node.discriminant.spec.type_name == "bool": + return + + template = get_jinja2_template(environment, "decoder", "default_spec") + print(template.render()) + + if default_case is None or isinstance(default_case.arm, _XdrVoid): + template = get_jinja2_template(environment, "decoder", "break") + print(template.render()) + return + + assert isinstance(default_case.arm, _XdrBasic) + template = get_jinja2_template(environment, "decoder", default_case.arm.template) + print( + template.render( + name=default_case.arm.name, + type=default_case.arm.spec.type_name, + classifier=default_case.arm.spec.c_classifier, + ) + ) + + +def emit_union_decoder(environment: Environment, node: _XdrUnion) -> None: + """Emit one XDR union decoder""" + template = get_jinja2_template(environment, "decoder", "open") + print(template.render(name=node.name)) + + emit_union_switch_spec_decoder(environment, node.discriminant) + + for case in node.cases: + emit_union_case_spec_decoder(environment, case) + + emit_union_default_spec_decoder(environment, node) + + template = get_jinja2_template(environment, "decoder", "close") + print(template.render()) + + +def emit_union_switch_spec_encoder( + environment: Environment, node: _XdrDeclaration +) -> None: + """Emit an encoder for an XDR union's discriminant""" + assert isinstance(node, _XdrBasic) + template = get_jinja2_template(environment, "encoder", "switch_spec") + print(template.render(name=node.name, type=node.spec.type_name)) + + +def emit_union_case_spec_encoder(environment: Environment, node: _XdrCaseSpec) -> None: + """Emit encoder functions for an XDR union's case arm""" + + if isinstance(node.arm, _XdrVoid): + return + + template = get_jinja2_template(environment, "encoder", "case_spec") + for case in node.values: + print(template.render(case=case)) + + assert isinstance(node.arm, _XdrBasic) + template = get_jinja2_template(environment, "encoder", node.arm.template) + print( + template.render( + name=node.arm.name, + type=node.arm.spec.type_name, + ) + ) + + template = get_jinja2_template(environment, "encoder", "break") + print(template.render()) + + +def emit_union_default_spec_encoder(environment: Environment, node: _XdrUnion) -> None: + """Emit an encoder function for an XDR union's default arm""" + default_case = node.default + + # Avoid a gcc warning about a default case with boolean discriminant + if default_case is None and node.discriminant.spec.type_name == "bool": + return + + template = get_jinja2_template(environment, "encoder", "default_spec") + print(template.render()) + + if default_case is None or isinstance(default_case.arm, _XdrVoid): + template = get_jinja2_template(environment, "encoder", "break") + print(template.render()) + return + + assert isinstance(default_case.arm, _XdrBasic) + template = get_jinja2_template(environment, "encoder", default_case.arm.template) + print( + template.render( + name=default_case.arm.name, + type=default_case.arm.spec.type_name, + ) + ) + + +def emit_union_encoder(environment, node: _XdrUnion) -> None: + """Emit one XDR union encoder""" + template = get_jinja2_template(environment, "encoder", "open") + print(template.render(name=node.name)) + + emit_union_switch_spec_encoder(environment, node.discriminant) + + for case in node.cases: + emit_union_case_spec_encoder(environment, case) + + emit_union_default_spec_encoder(environment, node) + + template = get_jinja2_template(environment, "encoder", "close") + print(template.render()) + + +class XdrUnionGenerator(SourceGenerator): + """Generate source code for XDR unions""" + + def __init__(self, language: str, peer: str): + """Initialize an instance of this class""" + self.environment = create_jinja2_environment(language, "union") + self.peer = peer + + def emit_declaration(self, node: _XdrUnion) -> None: + """Emit one declaration pair for an XDR union""" + emit_union_declaration(self.environment, node) + + def emit_definition(self, node: _XdrUnion) -> None: + """Emit one definition for an XDR union""" + emit_union_definition(self.environment, node) + + def emit_decoder(self, node: _XdrUnion) -> None: + """Emit one decoder function for an XDR union""" + emit_union_decoder(self.environment, node) + + def emit_encoder(self, node: _XdrUnion) -> None: + """Emit one encoder function for an XDR union""" + emit_union_encoder(self.environment, node) diff --git a/tools/net/sunrpc/xdrgen/grammars/xdr.lark b/tools/net/sunrpc/xdrgen/grammars/xdr.lark new file mode 100644 index 000000000000..f3c4552e548d --- /dev/null +++ b/tools/net/sunrpc/xdrgen/grammars/xdr.lark @@ -0,0 +1,119 @@ +// A Lark grammar for the XDR specification language based on +// https://tools.ietf.org/html/rfc4506 Section 6.3 + +declaration : "opaque" identifier "[" value "]" -> fixed_length_opaque + | "opaque" identifier "<" [ value ] ">" -> variable_length_opaque + | "string" identifier "<" [ value ] ">" -> variable_length_string + | type_specifier identifier "[" value "]" -> fixed_length_array + | type_specifier identifier "<" [ value ] ">" -> variable_length_array + | type_specifier "*" identifier -> optional_data + | type_specifier identifier -> basic + | "void" -> void + +value : decimal_constant + | hexadecimal_constant + | octal_constant + | identifier + +constant : decimal_constant | hexadecimal_constant | octal_constant + +type_specifier : unsigned_hyper + | unsigned_long + | unsigned_int + | hyper + | long + | int + | float + | double + | quadruple + | bool + | enum_type_spec + | struct_type_spec + | union_type_spec + | identifier + +unsigned_hyper : "unsigned" "hyper" +unsigned_long : "unsigned" "long" +unsigned_int : "unsigned" "int" +hyper : "hyper" +long : "long" +int : "int" +float : "float" +double : "double" +quadruple : "quadruple" +bool : "bool" + +enum_type_spec : "enum" enum_body + +enum_body : "{" ( identifier "=" value ) ( "," identifier "=" value )* "}" + +struct_type_spec : "struct" struct_body + +struct_body : "{" ( declaration ";" )+ "}" + +union_type_spec : "union" union_body + +union_body : switch_spec "{" case_spec+ [ default_spec ] "}" + +switch_spec : "switch" "(" declaration ")" + +case_spec : ( "case" value ":" )+ declaration ";" + +default_spec : "default" ":" declaration ";" + +constant_def : "const" identifier "=" value ";" + +type_def : "typedef" declaration ";" -> typedef + | "enum" identifier enum_body ";" -> enum + | "struct" identifier struct_body ";" -> struct + | "union" identifier union_body ";" -> union + +specification : definition* + +definition : constant_def + | type_def + | program_def + | pragma_def + +// +// RPC program definitions not specified in RFC 4506 +// + +program_def : "program" identifier "{" version_def+ "}" "=" constant ";" + +version_def : "version" identifier "{" procedure_def+ "}" "=" constant ";" + +procedure_def : type_specifier identifier "(" type_specifier ")" "=" constant ";" + +pragma_def : "pragma" directive identifier [ identifier ] ";" + +directive : exclude_directive + | header_directive + | pages_directive + | public_directive + | skip_directive + +exclude_directive : "exclude" +header_directive : "header" +pages_directive : "pages" +public_directive : "public" +skip_directive : "skip" + +// +// XDR language primitives +// + +identifier : /([a-z]|[A-Z])(_|[a-z]|[A-Z]|[0-9])*/ + +decimal_constant : /[\+-]?(0|[1-9][0-9]*)/ +hexadecimal_constant : /0x([a-f]|[A-F]|[0-9])+/ +octal_constant : /0[0-7]+/ + +PASSTHRU : "%" | "%" /.+/ +%ignore PASSTHRU + +%import common.C_COMMENT +%ignore C_COMMENT + +%import common.WS +%ignore WS diff --git a/tools/net/sunrpc/xdrgen/subcmds/__init__.py b/tools/net/sunrpc/xdrgen/subcmds/__init__.py new file mode 100644 index 000000000000..c940e9275252 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/subcmds/__init__.py @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +# Just to make sphinx-apidoc document this directory diff --git a/tools/net/sunrpc/xdrgen/subcmds/declarations.py b/tools/net/sunrpc/xdrgen/subcmds/declarations.py new file mode 100644 index 000000000000..c5e8d79986ef --- /dev/null +++ b/tools/net/sunrpc/xdrgen/subcmds/declarations.py @@ -0,0 +1,76 @@ +#!/usr/bin/env python3 +# ex: set filetype=python: + +"""Translate an XDR specification into executable code that +can be compiled for the Linux kernel.""" + +import logging + +from argparse import Namespace +from lark import logger +from lark.exceptions import UnexpectedInput + +from generators.constant import XdrConstantGenerator +from generators.enum import XdrEnumGenerator +from generators.header_bottom import XdrHeaderBottomGenerator +from generators.header_top import XdrHeaderTopGenerator +from generators.pointer import XdrPointerGenerator +from generators.program import XdrProgramGenerator +from generators.typedef import XdrTypedefGenerator +from generators.struct import XdrStructGenerator +from generators.union import XdrUnionGenerator + +from xdr_ast import transform_parse_tree, _RpcProgram, Specification +from xdr_ast import _XdrConstant, _XdrEnum, _XdrPointer +from xdr_ast import _XdrTypedef, _XdrStruct, _XdrUnion +from xdr_parse import xdr_parser, set_xdr_annotate + +logger.setLevel(logging.INFO) + + +def emit_header_declarations( + root: Specification, language: str, peer: str +) -> None: + """Emit header declarations""" + for definition in root.definitions: + if isinstance(definition.value, _XdrEnum): + gen = XdrEnumGenerator(language, peer) + elif isinstance(definition.value, _XdrPointer): + gen = XdrPointerGenerator(language, peer) + elif isinstance(definition.value, _XdrTypedef): + gen = XdrTypedefGenerator(language, peer) + elif isinstance(definition.value, _XdrStruct): + gen = XdrStructGenerator(language, peer) + elif isinstance(definition.value, _XdrUnion): + gen = XdrUnionGenerator(language, peer) + elif isinstance(definition.value, _RpcProgram): + gen = XdrProgramGenerator(language, peer) + else: + continue + gen.emit_declaration(definition.value) + + +def handle_parse_error(e: UnexpectedInput) -> bool: + """Simple parse error reporting, no recovery attempted""" + print(e) + return True + + +def subcmd(args: Namespace) -> int: + """Generate definitions and declarations""" + + set_xdr_annotate(args.annotate) + parser = xdr_parser() + with open(args.filename, encoding="utf-8") as f: + parse_tree = parser.parse(f.read(), on_error=handle_parse_error) + ast = transform_parse_tree(parse_tree) + + gen = XdrHeaderTopGenerator(args.language, args.peer) + gen.emit_declaration(args.filename, ast) + + emit_header_declarations(ast, args.language, args.peer) + + gen = XdrHeaderBottomGenerator(args.language, args.peer) + gen.emit_declaration(args.filename, ast) + + return 0 diff --git a/tools/net/sunrpc/xdrgen/subcmds/definitions.py b/tools/net/sunrpc/xdrgen/subcmds/definitions.py new file mode 100644 index 000000000000..5cd13d53221f --- /dev/null +++ b/tools/net/sunrpc/xdrgen/subcmds/definitions.py @@ -0,0 +1,78 @@ +#!/usr/bin/env python3 +# ex: set filetype=python: + +"""Translate an XDR specification into executable code that +can be compiled for the Linux kernel.""" + +import logging + +from argparse import Namespace +from lark import logger +from lark.exceptions import UnexpectedInput + +from generators.constant import XdrConstantGenerator +from generators.enum import XdrEnumGenerator +from generators.header_bottom import XdrHeaderBottomGenerator +from generators.header_top import XdrHeaderTopGenerator +from generators.pointer import XdrPointerGenerator +from generators.program import XdrProgramGenerator +from generators.typedef import XdrTypedefGenerator +from generators.struct import XdrStructGenerator +from generators.union import XdrUnionGenerator + +from xdr_ast import transform_parse_tree, Specification +from xdr_ast import _RpcProgram, _XdrConstant, _XdrEnum, _XdrPointer +from xdr_ast import _XdrTypedef, _XdrStruct, _XdrUnion +from xdr_parse import xdr_parser, set_xdr_annotate + +logger.setLevel(logging.INFO) + + +def emit_header_definitions( + root: Specification, language: str, peer: str +) -> None: + """Emit header definitions""" + for definition in root.definitions: + if isinstance(definition.value, _XdrConstant): + gen = XdrConstantGenerator(language, peer) + elif isinstance(definition.value, _XdrEnum): + gen = XdrEnumGenerator(language, peer) + elif isinstance(definition.value, _XdrPointer): + gen = XdrPointerGenerator(language, peer) + elif isinstance(definition.value, _RpcProgram): + gen = XdrProgramGenerator(language, peer) + elif isinstance(definition.value, _XdrTypedef): + gen = XdrTypedefGenerator(language, peer) + elif isinstance(definition.value, _XdrStruct): + gen = XdrStructGenerator(language, peer) + elif isinstance(definition.value, _XdrUnion): + gen = XdrUnionGenerator(language, peer) + else: + continue + gen.emit_definition(definition.value) + + +def handle_parse_error(e: UnexpectedInput) -> bool: + """Simple parse error reporting, no recovery attempted""" + print(e) + return True + + +def subcmd(args: Namespace) -> int: + """Generate definitions""" + + set_xdr_annotate(args.annotate) + parser = xdr_parser() + with open(args.filename, encoding="utf-8") as f: + parse_tree = parser.parse(f.read(), on_error=handle_parse_error) + ast = transform_parse_tree(parse_tree) + + gen = XdrHeaderTopGenerator(args.language, args.peer) + gen.emit_definition(args.filename, ast) + + emit_header_definitions(ast, args.language, args.peer) + + gen = XdrHeaderBottomGenerator(args.language, args.peer) + gen.emit_definition(args.filename, ast) + + return 0 diff --git a/tools/net/sunrpc/xdrgen/subcmds/lint.py b/tools/net/sunrpc/xdrgen/subcmds/lint.py new file mode 100644 index 000000000000..36cc43717d30 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/subcmds/lint.py @@ -0,0 +1,33 @@ +#!/usr/bin/env python3 +# ex: set filetype=python: + +"""Translate an XDR specification into executable code that +can be compiled for the Linux kernel.""" + +import logging + +from argparse import Namespace +from lark import logger +from lark.exceptions import UnexpectedInput + +from xdr_parse import xdr_parser +from xdr_ast import transform_parse_tree + +logger.setLevel(logging.DEBUG) + + +def handle_parse_error(e: UnexpectedInput) -> bool: + """Simple parse error reporting, no recovery attempted""" + print(e) + return True + + +def subcmd(args: Namespace) -> int: + """Lexical and syntax check of an XDR specification""" + + parser = xdr_parser() + with open(args.filename, encoding="utf-8") as f: + parse_tree = parser.parse(f.read(), on_error=handle_parse_error) + transform_parse_tree(parse_tree) + + return 0 diff --git a/tools/net/sunrpc/xdrgen/subcmds/source.py b/tools/net/sunrpc/xdrgen/subcmds/source.py new file mode 100644 index 000000000000..00c04ad15b89 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/subcmds/source.py @@ -0,0 +1,118 @@ +#!/usr/bin/env python3 +# ex: set filetype=python: + +"""Translate an XDR specification into executable code that +can be compiled for the Linux kernel.""" + +import logging + +from argparse import Namespace +from lark import logger +from lark.exceptions import UnexpectedInput + +from generators.source_top import XdrSourceTopGenerator +from generators.enum import XdrEnumGenerator +from generators.pointer import XdrPointerGenerator +from generators.program import XdrProgramGenerator +from generators.typedef import XdrTypedefGenerator +from generators.struct import XdrStructGenerator +from generators.union import XdrUnionGenerator + +from xdr_ast import transform_parse_tree, _RpcProgram, Specification +from xdr_ast import _XdrAst, _XdrEnum, _XdrPointer +from xdr_ast import _XdrStruct, _XdrTypedef, _XdrUnion + +from xdr_parse import xdr_parser, set_xdr_annotate + +logger.setLevel(logging.INFO) + + +def emit_source_decoder(node: _XdrAst, language: str, peer: str) -> None: + """Emit one XDR decoder function for a source file""" + if isinstance(node, _XdrEnum): + gen = XdrEnumGenerator(language, peer) + elif isinstance(node, _XdrPointer): + gen = XdrPointerGenerator(language, peer) + elif isinstance(node, _XdrTypedef): + gen = XdrTypedefGenerator(language, peer) + elif isinstance(node, _XdrStruct): + gen = XdrStructGenerator(language, peer) + elif isinstance(node, _XdrUnion): + gen = XdrUnionGenerator(language, peer) + elif isinstance(node, _RpcProgram): + gen = XdrProgramGenerator(language, peer) + else: + return + gen.emit_decoder(node) + + +def emit_source_encoder(node: _XdrAst, language: str, peer: str) -> None: + """Emit one XDR encoder function for a source file""" + if isinstance(node, _XdrEnum): + gen = XdrEnumGenerator(language, peer) + elif isinstance(node, _XdrPointer): + gen = XdrPointerGenerator(language, peer) + elif isinstance(node, _XdrTypedef): + gen = XdrTypedefGenerator(language, peer) + elif isinstance(node, _XdrStruct): + gen = XdrStructGenerator(language, peer) + elif isinstance(node, _XdrUnion): + gen = XdrUnionGenerator(language, peer) + elif isinstance(node, _RpcProgram): + gen = XdrProgramGenerator(language, peer) + else: + return + gen.emit_encoder(node) + + +def generate_server_source(filename: str, root: Specification, language: str) -> None: + """Generate server-side source code""" + + gen = XdrSourceTopGenerator(language, "server") + gen.emit_source(filename, root) + + for definition in root.definitions: + emit_source_decoder(definition.value, language, "server") + for definition in root.definitions: + emit_source_encoder(definition.value, language, "server") + + +def generate_client_source(filename: str, root: Specification, language: str) -> None: + """Generate server-side source code""" + + gen = XdrSourceTopGenerator(language, "client") + gen.emit_source(filename, root) + + # cel: todo: client needs XDR size macros + + for definition in root.definitions: + emit_source_encoder(definition.value, language, "client") + for definition in root.definitions: + emit_source_decoder(definition.value, language, "client") + + # cel: todo: client needs PROC macros + + +def handle_parse_error(e: UnexpectedInput) -> bool: + """Simple parse error reporting, no recovery attempted""" + print(e) + return True + + +def subcmd(args: Namespace) -> int: + """Generate encoder and decoder functions""" + + set_xdr_annotate(args.annotate) + parser = xdr_parser() + with open(args.filename, encoding="utf-8") as f: + parse_tree = parser.parse(f.read(), on_error=handle_parse_error) + ast = transform_parse_tree(parse_tree) + match args.peer: + case "server": + generate_server_source(args.filename, ast, args.language) + case "client": + generate_client_source(args.filename, ast, args.language) + case _: + print("Code generation for", args.peer, "is not yet supported") + + return 0 diff --git a/tools/net/sunrpc/xdrgen/templates/C/constants/definition.j2 b/tools/net/sunrpc/xdrgen/templates/C/constants/definition.j2 new file mode 100644 index 000000000000..d648ca4193f8 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/constants/definition.j2 @@ -0,0 +1,3 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +enum { {{ name }} = {{ value }} }; diff --git a/tools/net/sunrpc/xdrgen/templates/C/enum/declaration/close.j2 b/tools/net/sunrpc/xdrgen/templates/C/enum/declaration/close.j2 new file mode 100644 index 000000000000..ab1e576c9531 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/enum/declaration/close.j2 @@ -0,0 +1,4 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +bool xdrgen_decode_{{ name }}(struct xdr_stream *xdr, enum {{ name }} *ptr); +bool xdrgen_encode_{{ name }}(struct xdr_stream *xdr, enum {{ name }} value); diff --git a/tools/net/sunrpc/xdrgen/templates/C/enum/decoder/enum.j2 b/tools/net/sunrpc/xdrgen/templates/C/enum/decoder/enum.j2 new file mode 100644 index 000000000000..341d829afeda --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/enum/decoder/enum.j2 @@ -0,0 +1,19 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* enum {{ name }} */ +{% endif %} +{% if name in public_apis %} +bool +{% else %} +static bool __maybe_unused +{% endif %} +xdrgen_decode_{{ name }}(struct xdr_stream *xdr, enum {{ name }} *ptr) +{ + u32 val; + + if (xdr_stream_decode_u32(xdr, &val) < 0) + return false; + *ptr = val; + return true; +} diff --git a/tools/net/sunrpc/xdrgen/templates/C/enum/definition/close.j2 b/tools/net/sunrpc/xdrgen/templates/C/enum/definition/close.j2 new file mode 100644 index 000000000000..9e62344a976a --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/enum/definition/close.j2 @@ -0,0 +1,2 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/enum/definition/enumerator.j2 b/tools/net/sunrpc/xdrgen/templates/C/enum/definition/enumerator.j2 new file mode 100644 index 000000000000..ff0b893b8b14 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/enum/definition/enumerator.j2 @@ -0,0 +1,2 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + {{ name }} = {{ value }}, diff --git a/tools/net/sunrpc/xdrgen/templates/C/enum/definition/open.j2 b/tools/net/sunrpc/xdrgen/templates/C/enum/definition/open.j2 new file mode 100644 index 000000000000..b25335221d48 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/enum/definition/open.j2 @@ -0,0 +1,3 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +enum {{ name }} { diff --git a/tools/net/sunrpc/xdrgen/templates/C/enum/encoder/enum.j2 b/tools/net/sunrpc/xdrgen/templates/C/enum/encoder/enum.j2 new file mode 100644 index 000000000000..bd0a770e50f2 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/enum/encoder/enum.j2 @@ -0,0 +1,14 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* enum {{ name }} */ +{% endif %} +{% if name in public_apis %} +bool +{% else %} +static bool __maybe_unused +{% endif %} +xdrgen_encode_{{ name }}(struct xdr_stream *xdr, enum {{ name }} value) +{ + return xdr_stream_encode_u32(xdr, value) == XDR_UNIT; +} diff --git a/tools/net/sunrpc/xdrgen/templates/C/header_bottom/declaration/header.j2 b/tools/net/sunrpc/xdrgen/templates/C/header_bottom/declaration/header.j2 new file mode 100644 index 000000000000..0bb8c6fc0c20 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/header_bottom/declaration/header.j2 @@ -0,0 +1,3 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +#endif /* _LINUX_XDRGEN_{{ infix }}_DECL_H */ diff --git a/tools/net/sunrpc/xdrgen/templates/C/header_bottom/definition/header.j2 b/tools/net/sunrpc/xdrgen/templates/C/header_bottom/definition/header.j2 new file mode 100644 index 000000000000..69069d08dc91 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/header_bottom/definition/header.j2 @@ -0,0 +1,3 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +#endif /* _LINUX_XDRGEN_{{ infix }}_DEF_H */ diff --git a/tools/net/sunrpc/xdrgen/templates/C/header_top/declaration/header.j2 b/tools/net/sunrpc/xdrgen/templates/C/header_top/declaration/header.j2 new file mode 100644 index 000000000000..ebb4e1d32f85 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/header_top/declaration/header.j2 @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Generated by xdrgen. Manual edits will be lost. */ +/* XDR specification file: {{ filename }} */ +/* XDR specification modification time: {{ mtime }} */ + +#ifndef _LINUX_XDRGEN_{{ infix }}_DECL_H +#define _LINUX_XDRGEN_{{ infix }}_DECL_H + +#include + +#include +#include +#include +#include diff --git a/tools/net/sunrpc/xdrgen/templates/C/header_top/definition/header.j2 b/tools/net/sunrpc/xdrgen/templates/C/header_top/definition/header.j2 new file mode 100644 index 000000000000..92f1fd4ba024 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/header_top/definition/header.j2 @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Generated by xdrgen. Manual edits will be lost. */ +/* XDR specification file: {{ filename }} */ +/* XDR specification modification time: {{ mtime }} */ + +#ifndef _LINUX_XDRGEN_{{ infix }}_DEF_H +#define _LINUX_XDRGEN_{{ infix }}_DEF_H + +#include +#include diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/declaration/close.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/declaration/close.j2 new file mode 100644 index 000000000000..816291184e8c --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/declaration/close.j2 @@ -0,0 +1,4 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +bool xdrgen_decode_{{ name }}(struct xdr_stream *xdr, struct {{ name }} *ptr); +bool xdrgen_encode_{{ name }}(struct xdr_stream *xdr, const struct {{ name }} *value); diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/basic.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/basic.j2 new file mode 100644 index 000000000000..cde4ab53f4be --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/basic.j2 @@ -0,0 +1,6 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (basic) */ +{% endif %} + if (!xdrgen_decode_{{ type }}(xdr, &ptr->{{ name }})) + return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/close.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/close.j2 new file mode 100644 index 000000000000..5bf010665f84 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/close.j2 @@ -0,0 +1,3 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + return true; +}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/fixed_length_array.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/fixed_length_array.j2 new file mode 100644 index 000000000000..cfd64217ad82 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/fixed_length_array.j2 @@ -0,0 +1,8 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (fixed-length array) */ +{% endif %} + for (u32 i = 0; i < {{ size }}; i++) { + if (xdrgen_decode_{{ type }}(xdr, &ptr->{{ name }}.items[i]) < 0) + return false; + } diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/fixed_length_opaque.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/fixed_length_opaque.j2 new file mode 100644 index 000000000000..b4695ece1884 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/fixed_length_opaque.j2 @@ -0,0 +1,6 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (fixed-length opaque) */ +{% endif %} + if (xdr_stream_decode_opaque_fixed(xdr, ptr->{{ name }}, {{ size }}) < 0) + return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/open.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/open.j2 new file mode 100644 index 000000000000..c093d9e3c9ad --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/open.j2 @@ -0,0 +1,22 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* pointer {{ name }} */ +{% endif %} +{% if name in public_apis %} +bool +{% else %} +static bool __maybe_unused +{% endif %} +xdrgen_decode_{{ name }}(struct xdr_stream *xdr, struct {{ name }} *ptr) +{ + bool opted; + +{% if annotate %} + /* opted */ +{% endif %} + if (!xdrgen_decode_bool(xdr, &opted)) + return false; + if (!opted) + return true; + diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/optional_data.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/optional_data.j2 new file mode 100644 index 000000000000..b6834299a04b --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/optional_data.j2 @@ -0,0 +1,6 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (optional data) */ +{% endif %} + if (!xdrgen_decode_{{ type }}(xdr, ptr->{{ name }})) + return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/variable_length_array.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/variable_length_array.j2 new file mode 100644 index 000000000000..f54ccd136762 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/variable_length_array.j2 @@ -0,0 +1,13 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (variable-length array) */ +{% endif %} + if (xdr_stream_decode_u32(xdr, &ptr->{{ name }}.count) != XDR_UNIT) + return false; +{% if maxsize != "0" %} + if (ptr->{{ name }}.count > {{ maxsize }}) + return false; +{% endif %} + for (u32 i = 0; i < ptr->{{ name }}.count; i++) + if (!xdrgen_decode_{{ type }}(xdr, &ptr->{{ name }}.element[i])) + return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/variable_length_opaque.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/variable_length_opaque.j2 new file mode 100644 index 000000000000..9a814de54ae8 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/variable_length_opaque.j2 @@ -0,0 +1,6 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (variable-length opaque) */ +{% endif %} + if (!xdrgen_decode_opaque(xdr, (opaque *)ptr, {{ maxsize }})) + return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/variable_length_string.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/variable_length_string.j2 new file mode 100644 index 000000000000..12d20b143b43 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/variable_length_string.j2 @@ -0,0 +1,6 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (variable-length string) */ +{% endif %} + if (!xdrgen_decode_string(xdr, (string *)ptr, {{ maxsize }})) + return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/definition/basic.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/definition/basic.j2 new file mode 100644 index 000000000000..b3430895f311 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/definition/basic.j2 @@ -0,0 +1,5 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* (basic) */ +{% endif %} + {{ classifier }}{{ type }} {{ name }}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/definition/close.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/definition/close.j2 new file mode 100644 index 000000000000..9e62344a976a --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/definition/close.j2 @@ -0,0 +1,2 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/definition/fixed_length_array.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/definition/fixed_length_array.j2 new file mode 100644 index 000000000000..66be836826a0 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/definition/fixed_length_array.j2 @@ -0,0 +1,5 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* (fixed-length array) */ +{% endif %} + {{ type }} {{ name }}[{{ size }}]; diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/definition/fixed_length_opaque.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/definition/fixed_length_opaque.j2 new file mode 100644 index 000000000000..0daba19aa0f0 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/definition/fixed_length_opaque.j2 @@ -0,0 +1,5 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* (fixed-length opaque) */ +{% endif %} + u8 {{ name }}[{{ size }}]; diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/definition/open.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/definition/open.j2 new file mode 100644 index 000000000000..bc886b818d85 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/definition/open.j2 @@ -0,0 +1,6 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* pointer {{ name }} */ +{% endif %} +struct {{ name }} { diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/definition/optional_data.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/definition/optional_data.j2 new file mode 100644 index 000000000000..a33341f45e8f --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/definition/optional_data.j2 @@ -0,0 +1,5 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* (optional data) */ +{% endif %} + {{ classifier }}{{ type }} *{{ name }}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/definition/variable_length_array.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/definition/variable_length_array.j2 new file mode 100644 index 000000000000..5d767f9b3674 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/definition/variable_length_array.j2 @@ -0,0 +1,8 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* (variable-length array) */ +{% endif %} + struct { + u32 count; + {{ classifier }}{{ type }} *element; + } {{ name }}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/definition/variable_length_opaque.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/definition/variable_length_opaque.j2 new file mode 100644 index 000000000000..4d0cd84be3db --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/definition/variable_length_opaque.j2 @@ -0,0 +1,5 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* (variable-length opaque) */ +{% endif %} + opaque {{ name }}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/definition/variable_length_string.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/definition/variable_length_string.j2 new file mode 100644 index 000000000000..2de2feec77db --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/definition/variable_length_string.j2 @@ -0,0 +1,5 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* (variable-length string) */ +{% endif %} + string {{ name }}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/basic.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/basic.j2 new file mode 100644 index 000000000000..a7d3695c5a6a --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/basic.j2 @@ -0,0 +1,10 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (basic) */ +{% endif %} +{% if type in pass_by_reference %} + if (!xdrgen_encode_{{ type }}(xdr, &value->{{ name }})) +{% else %} + if (!xdrgen_encode_{{ type }}(xdr, value->{{ name }})) +{% endif %} + return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/close.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/close.j2 new file mode 100644 index 000000000000..5bf010665f84 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/close.j2 @@ -0,0 +1,3 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + return true; +}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/fixed_length_array.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/fixed_length_array.j2 new file mode 100644 index 000000000000..b01833a2c7a1 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/fixed_length_array.j2 @@ -0,0 +1,12 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (fixed-length array) */ +{% endif %} + for (u32 i = 0; i < {{ size }}; i++) { +{% if type in pass_by_reference %} + if (xdrgen_encode_{{ type }}(xdr, &value->items[i]) < 0) +{% else %} + if (xdrgen_encode_{{ type }}(xdr, value->items[i]) < 0) +{% endif %} + return false; + } diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/fixed_length_opaque.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/fixed_length_opaque.j2 new file mode 100644 index 000000000000..07bc91919898 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/fixed_length_opaque.j2 @@ -0,0 +1,6 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (fixed-length opaque) */ +{% endif %} + if (xdr_stream_encode_opaque_fixed(xdr, value->{{ name }}, {{ size }}) < 0) + return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/open.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/open.j2 new file mode 100644 index 000000000000..d67fae200261 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/open.j2 @@ -0,0 +1,20 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* pointer {{ name }} */ +{% endif %} +{% if name in public_apis %} +bool +{% else %} +static bool __maybe_unused +{% endif %} +xdrgen_encode_{{ name }}(struct xdr_stream *xdr, const struct {{ name }} *value) +{ +{% if annotate %} + /* opted */ +{% endif %} + if (!xdrgen_encode_bool(xdr, value != NULL)) + return false; + if (!value) + return true; + diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/optional_data.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/optional_data.j2 new file mode 100644 index 000000000000..16fb3e09bba1 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/optional_data.j2 @@ -0,0 +1,6 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (optional data) */ +{% endif %} + if (!xdrgen_encode_{{ type }}(xdr, value->{{ name }})) + return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/variable_length_array.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/variable_length_array.j2 new file mode 100644 index 000000000000..0ec8660d621a --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/variable_length_array.j2 @@ -0,0 +1,15 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (variable-length array) */ +{% endif %} + if (value->{{ name }}.count > {{ maxsize }}) + return false; + if (xdr_stream_encode_u32(xdr, value->{{ name }}.count) != XDR_UNIT) + return false; + for (u32 i = 0; i < value->{{ name }}.count; i++) +{% if type in pass_by_reference %} + if (!xdrgen_encode_{{ type }}(xdr, &value->{{ name }}.element[i])) +{% else %} + if (!xdrgen_encode_{{ type }}(xdr, value->{{ name }}.element[i])) +{% endif %} + return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/variable_length_opaque.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/variable_length_opaque.j2 new file mode 100644 index 000000000000..1d477c2d197a --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/variable_length_opaque.j2 @@ -0,0 +1,8 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (variable-length opaque) */ +{% endif %} + if (value->{{ name }}.len > {{ maxsize }}) + return false; + if (xdr_stream_encode_opaque(xdr, value->{{ name }}.data, value->{{ name }}.len) < 0) + return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/variable_length_string.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/variable_length_string.j2 new file mode 100644 index 000000000000..cf65b71eaef3 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/variable_length_string.j2 @@ -0,0 +1,8 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (variable-length string) */ +{% endif %} + if (value->{{ name }}.len > {{ maxsize }}) + return false; + if (xdr_stream_encode_opaque(xdr, value->{{ name }}.data, value->{{ name }}.len) < 0) + return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/program/declaration/argument.j2 b/tools/net/sunrpc/xdrgen/templates/C/program/declaration/argument.j2 new file mode 100644 index 000000000000..4364fed19162 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/program/declaration/argument.j2 @@ -0,0 +1,2 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +bool {{ program }}_svc_decode_{{ argument }}(struct svc_rqst *rqstp, struct xdr_stream *xdr); diff --git a/tools/net/sunrpc/xdrgen/templates/C/program/declaration/result.j2 b/tools/net/sunrpc/xdrgen/templates/C/program/declaration/result.j2 new file mode 100644 index 000000000000..e0ea1e849910 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/program/declaration/result.j2 @@ -0,0 +1,2 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +bool {{ program }}_svc_encode_{{ result }}(struct svc_rqst *rqstp, struct xdr_stream *xdr); diff --git a/tools/net/sunrpc/xdrgen/templates/C/program/decoder/argument.j2 b/tools/net/sunrpc/xdrgen/templates/C/program/decoder/argument.j2 new file mode 100644 index 000000000000..0b1709cca0d4 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/program/decoder/argument.j2 @@ -0,0 +1,21 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +/** + * {{ program }}_svc_decode_{{ argument }} - Decode a {{ argument }} argument + * @rqstp: RPC transaction context + * @xdr: source XDR data stream + * + * Return values: + * %true: procedure arguments decoded successfully + * %false: decode failed + */ +bool {{ program }}_svc_decode_{{ argument }}(struct svc_rqst *rqstp, struct xdr_stream *xdr) +{ +{% if argument == 'void' %} + return xdrgen_decode_void(xdr); +{% else %} + struct {{ argument }} *argp = rqstp->rq_argp; + + return xdrgen_decode_{{ argument }}(xdr, argp); +{% endif %} +} diff --git a/tools/net/sunrpc/xdrgen/templates/C/program/decoder/result.j2 b/tools/net/sunrpc/xdrgen/templates/C/program/decoder/result.j2 new file mode 100644 index 000000000000..d304eccb5c40 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/program/decoder/result.j2 @@ -0,0 +1,22 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* Decode {{ result }} results */ +{% endif %} +static int {{ program }}_xdr_dec_{{ result }}(struct rpc_rqst *req, + struct xdr_stream *xdr, void *data) +{ +{% if result == 'void' %} + xdrgen_decode_void(xdr); +{% else %} + struct {{ result }} *result = data; + + if (!xdrgen_decode_{{ result }}(xdr, result)) + return -EIO; + if (result->stat != nfs_ok) { + trace_nfs_xdr_status(xdr, (int)result->stat); + return {{ program }}_stat_to_errno(result->stat); + } +{% endif %} + return 0; +} diff --git a/tools/net/sunrpc/xdrgen/templates/C/program/definition/close.j2 b/tools/net/sunrpc/xdrgen/templates/C/program/definition/close.j2 new file mode 100644 index 000000000000..9e62344a976a --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/program/definition/close.j2 @@ -0,0 +1,2 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/program/definition/open.j2 b/tools/net/sunrpc/xdrgen/templates/C/program/definition/open.j2 new file mode 100644 index 000000000000..f9a6d439f156 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/program/definition/open.j2 @@ -0,0 +1,6 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* procedure numbers for {{ program }} */ +{% endif %} +enum { diff --git a/tools/net/sunrpc/xdrgen/templates/C/program/definition/procedure.j2 b/tools/net/sunrpc/xdrgen/templates/C/program/definition/procedure.j2 new file mode 100644 index 000000000000..ff0b893b8b14 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/program/definition/procedure.j2 @@ -0,0 +1,2 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + {{ name }} = {{ value }}, diff --git a/tools/net/sunrpc/xdrgen/templates/C/program/encoder/argument.j2 b/tools/net/sunrpc/xdrgen/templates/C/program/encoder/argument.j2 new file mode 100644 index 000000000000..2fbb5bd13aec --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/program/encoder/argument.j2 @@ -0,0 +1,16 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{%if annotate %} +/* Encode {{ argument }} arguments */ +{% endif %} +static void {{ program }}_xdr_enc_{{ argument }}(struct rpc_rqst *req, + struct xdr_stream *xdr, const void *data) +{ +{% if argument == 'void' %} + xdrgen_encode_void(xdr); +{% else %} + const struct {{ argument }} *args = data; + + xdrgen_encode_{{ argument }}(xdr, args); +{% endif %} +} diff --git a/tools/net/sunrpc/xdrgen/templates/C/program/encoder/result.j2 b/tools/net/sunrpc/xdrgen/templates/C/program/encoder/result.j2 new file mode 100644 index 000000000000..6fc61a5d47b7 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/program/encoder/result.j2 @@ -0,0 +1,21 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +/** + * {{ program }}_svc_encode_{{ result }} - Encode a {{ result }} result + * @rqstp: RPC transaction context + * @xdr: target XDR data stream + * + * Return values: + * %true: procedure results encoded successfully + * %false: encode failed + */ +bool {{ program }}_svc_encode_{{ result }}(struct svc_rqst *rqstp, struct xdr_stream *xdr) +{ +{% if result == 'void' %} + return xdrgen_encode_void(xdr); +{% else %} + struct {{ result }} *resp = rqstp->rq_resp; + + return xdrgen_encode_{{ result }}(xdr, resp); +{% endif %} +} diff --git a/tools/net/sunrpc/xdrgen/templates/C/source_top/client.j2 b/tools/net/sunrpc/xdrgen/templates/C/source_top/client.j2 new file mode 100644 index 000000000000..e3a802cbc4d7 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/source_top/client.j2 @@ -0,0 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 +// Generated by xdrgen. Manual edits will be lost. +// XDR specification file: {{ filename }} +// XDR specification modification time: {{ mtime }} + +#include + +#include "{{ program }}xdr_gen.h" diff --git a/tools/net/sunrpc/xdrgen/templates/C/source_top/server.j2 b/tools/net/sunrpc/xdrgen/templates/C/source_top/server.j2 new file mode 100644 index 000000000000..974e1d971e5d --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/source_top/server.j2 @@ -0,0 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 +// Generated by xdrgen. Manual edits will be lost. +// XDR specification file: {{ filename }} +// XDR specification modification time: {{ mtime }} + +#include + +#include "{{ program }}xdr_gen.h" diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/declaration/close.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/declaration/close.j2 new file mode 100644 index 000000000000..816291184e8c --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/struct/declaration/close.j2 @@ -0,0 +1,4 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +bool xdrgen_decode_{{ name }}(struct xdr_stream *xdr, struct {{ name }} *ptr); +bool xdrgen_encode_{{ name }}(struct xdr_stream *xdr, const struct {{ name }} *value); diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/basic.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/basic.j2 new file mode 100644 index 000000000000..cde4ab53f4be --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/basic.j2 @@ -0,0 +1,6 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (basic) */ +{% endif %} + if (!xdrgen_decode_{{ type }}(xdr, &ptr->{{ name }})) + return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/close.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/close.j2 new file mode 100644 index 000000000000..5bf010665f84 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/close.j2 @@ -0,0 +1,3 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + return true; +}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/fixed_length_array.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/fixed_length_array.j2 new file mode 100644 index 000000000000..cfd64217ad82 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/fixed_length_array.j2 @@ -0,0 +1,8 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (fixed-length array) */ +{% endif %} + for (u32 i = 0; i < {{ size }}; i++) { + if (xdrgen_decode_{{ type }}(xdr, &ptr->{{ name }}.items[i]) < 0) + return false; + } diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/fixed_length_opaque.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/fixed_length_opaque.j2 new file mode 100644 index 000000000000..b4695ece1884 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/fixed_length_opaque.j2 @@ -0,0 +1,6 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (fixed-length opaque) */ +{% endif %} + if (xdr_stream_decode_opaque_fixed(xdr, ptr->{{ name }}, {{ size }}) < 0) + return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/open.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/open.j2 new file mode 100644 index 000000000000..289e67259f55 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/open.j2 @@ -0,0 +1,12 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* struct {{ name }} */ +{% endif %} +{% if name in public_apis %} +bool +{% else %} +static bool __maybe_unused +{% endif %} +xdrgen_decode_{{ name }}(struct xdr_stream *xdr, struct {{ name }} *ptr) +{ diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/optional_data.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/optional_data.j2 new file mode 100644 index 000000000000..b6834299a04b --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/optional_data.j2 @@ -0,0 +1,6 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (optional data) */ +{% endif %} + if (!xdrgen_decode_{{ type }}(xdr, ptr->{{ name }})) + return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/variable_length_array.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/variable_length_array.j2 new file mode 100644 index 000000000000..f54ccd136762 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/variable_length_array.j2 @@ -0,0 +1,13 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (variable-length array) */ +{% endif %} + if (xdr_stream_decode_u32(xdr, &ptr->{{ name }}.count) != XDR_UNIT) + return false; +{% if maxsize != "0" %} + if (ptr->{{ name }}.count > {{ maxsize }}) + return false; +{% endif %} + for (u32 i = 0; i < ptr->{{ name }}.count; i++) + if (!xdrgen_decode_{{ type }}(xdr, &ptr->{{ name }}.element[i])) + return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/variable_length_opaque.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/variable_length_opaque.j2 new file mode 100644 index 000000000000..9a814de54ae8 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/variable_length_opaque.j2 @@ -0,0 +1,6 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (variable-length opaque) */ +{% endif %} + if (!xdrgen_decode_opaque(xdr, (opaque *)ptr, {{ maxsize }})) + return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/variable_length_string.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/variable_length_string.j2 new file mode 100644 index 000000000000..12d20b143b43 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/variable_length_string.j2 @@ -0,0 +1,6 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (variable-length string) */ +{% endif %} + if (!xdrgen_decode_string(xdr, (string *)ptr, {{ maxsize }})) + return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/definition/basic.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/definition/basic.j2 new file mode 100644 index 000000000000..b3430895f311 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/struct/definition/basic.j2 @@ -0,0 +1,5 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* (basic) */ +{% endif %} + {{ classifier }}{{ type }} {{ name }}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/definition/close.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/definition/close.j2 new file mode 100644 index 000000000000..9e62344a976a --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/struct/definition/close.j2 @@ -0,0 +1,2 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/definition/fixed_length_array.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/definition/fixed_length_array.j2 new file mode 100644 index 000000000000..66be836826a0 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/struct/definition/fixed_length_array.j2 @@ -0,0 +1,5 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* (fixed-length array) */ +{% endif %} + {{ type }} {{ name }}[{{ size }}]; diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/definition/fixed_length_opaque.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/definition/fixed_length_opaque.j2 new file mode 100644 index 000000000000..0daba19aa0f0 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/struct/definition/fixed_length_opaque.j2 @@ -0,0 +1,5 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* (fixed-length opaque) */ +{% endif %} + u8 {{ name }}[{{ size }}]; diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/definition/open.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/definition/open.j2 new file mode 100644 index 000000000000..07cbf5424546 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/struct/definition/open.j2 @@ -0,0 +1,6 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* struct {{ name }} */ +{% endif %} +struct {{ name }} { diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/definition/optional_data.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/definition/optional_data.j2 new file mode 100644 index 000000000000..a33341f45e8f --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/struct/definition/optional_data.j2 @@ -0,0 +1,5 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* (optional data) */ +{% endif %} + {{ classifier }}{{ type }} *{{ name }}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/definition/variable_length_array.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/definition/variable_length_array.j2 new file mode 100644 index 000000000000..5d767f9b3674 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/struct/definition/variable_length_array.j2 @@ -0,0 +1,8 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* (variable-length array) */ +{% endif %} + struct { + u32 count; + {{ classifier }}{{ type }} *element; + } {{ name }}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/definition/variable_length_opaque.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/definition/variable_length_opaque.j2 new file mode 100644 index 000000000000..4d0cd84be3db --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/struct/definition/variable_length_opaque.j2 @@ -0,0 +1,5 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* (variable-length opaque) */ +{% endif %} + opaque {{ name }}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/definition/variable_length_string.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/definition/variable_length_string.j2 new file mode 100644 index 000000000000..2de2feec77db --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/struct/definition/variable_length_string.j2 @@ -0,0 +1,5 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* (variable-length string) */ +{% endif %} + string {{ name }}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/basic.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/basic.j2 new file mode 100644 index 000000000000..a7d3695c5a6a --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/basic.j2 @@ -0,0 +1,10 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (basic) */ +{% endif %} +{% if type in pass_by_reference %} + if (!xdrgen_encode_{{ type }}(xdr, &value->{{ name }})) +{% else %} + if (!xdrgen_encode_{{ type }}(xdr, value->{{ name }})) +{% endif %} + return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/close.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/close.j2 new file mode 100644 index 000000000000..5bf010665f84 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/close.j2 @@ -0,0 +1,3 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + return true; +}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/fixed_length_array.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/fixed_length_array.j2 new file mode 100644 index 000000000000..b01833a2c7a1 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/fixed_length_array.j2 @@ -0,0 +1,12 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (fixed-length array) */ +{% endif %} + for (u32 i = 0; i < {{ size }}; i++) { +{% if type in pass_by_reference %} + if (xdrgen_encode_{{ type }}(xdr, &value->items[i]) < 0) +{% else %} + if (xdrgen_encode_{{ type }}(xdr, value->items[i]) < 0) +{% endif %} + return false; + } diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/fixed_length_opaque.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/fixed_length_opaque.j2 new file mode 100644 index 000000000000..07bc91919898 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/fixed_length_opaque.j2 @@ -0,0 +1,6 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (fixed-length opaque) */ +{% endif %} + if (xdr_stream_encode_opaque_fixed(xdr, value->{{ name }}, {{ size }}) < 0) + return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/open.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/open.j2 new file mode 100644 index 000000000000..2286a3adf82a --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/open.j2 @@ -0,0 +1,12 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* struct {{ name }} */ +{% endif %} +{% if name in public_apis %} +bool +{% else %} +static bool __maybe_unused +{% endif %} +xdrgen_encode_{{ name }}(struct xdr_stream *xdr, const struct {{ name }} *value) +{ diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/optional_data.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/optional_data.j2 new file mode 100644 index 000000000000..16fb3e09bba1 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/optional_data.j2 @@ -0,0 +1,6 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (optional data) */ +{% endif %} + if (!xdrgen_encode_{{ type }}(xdr, value->{{ name }})) + return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/variable_length_array.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/variable_length_array.j2 new file mode 100644 index 000000000000..0ec8660d621a --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/variable_length_array.j2 @@ -0,0 +1,15 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (variable-length array) */ +{% endif %} + if (value->{{ name }}.count > {{ maxsize }}) + return false; + if (xdr_stream_encode_u32(xdr, value->{{ name }}.count) != XDR_UNIT) + return false; + for (u32 i = 0; i < value->{{ name }}.count; i++) +{% if type in pass_by_reference %} + if (!xdrgen_encode_{{ type }}(xdr, &value->{{ name }}.element[i])) +{% else %} + if (!xdrgen_encode_{{ type }}(xdr, value->{{ name }}.element[i])) +{% endif %} + return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/variable_length_opaque.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/variable_length_opaque.j2 new file mode 100644 index 000000000000..1d477c2d197a --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/variable_length_opaque.j2 @@ -0,0 +1,8 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (variable-length opaque) */ +{% endif %} + if (value->{{ name }}.len > {{ maxsize }}) + return false; + if (xdr_stream_encode_opaque(xdr, value->{{ name }}.data, value->{{ name }}.len) < 0) + return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/variable_length_string.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/variable_length_string.j2 new file mode 100644 index 000000000000..cf65b71eaef3 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/variable_length_string.j2 @@ -0,0 +1,8 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (variable-length string) */ +{% endif %} + if (value->{{ name }}.len > {{ maxsize }}) + return false; + if (xdr_stream_encode_opaque(xdr, value->{{ name }}.data, value->{{ name }}.len) < 0) + return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/declaration/basic.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/declaration/basic.j2 new file mode 100644 index 000000000000..455b10bd90ec --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/typedef/declaration/basic.j2 @@ -0,0 +1,8 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +bool xdrgen_decode_{{ name }}(struct xdr_stream *xdr, {{ name }} *ptr); +{% if name in pass_by_reference %} +bool xdrgen_encode_{{ name }}(struct xdr_stream *xdr, const {{ name }} *value); +{%- else -%} +bool xdrgen_encode_{{ name }}(struct xdr_stream *xdr, const {{ name }} value); +{% endif %} diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/declaration/fixed_length_array.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/declaration/fixed_length_array.j2 new file mode 100644 index 000000000000..3fe3ddd9f359 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/typedef/declaration/fixed_length_array.j2 @@ -0,0 +1,4 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +bool xdrgen_decode_{{ name }}(struct xdr_stream *xdr, {{ classifier }}{{ name }} *ptr); +bool xdrgen_encode_{{ name }}(struct xdr_stream *xdr, const {{ classifier }}{{ name }} value); diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/declaration/fixed_length_opaque.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/declaration/fixed_length_opaque.j2 new file mode 100644 index 000000000000..3fe3ddd9f359 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/typedef/declaration/fixed_length_opaque.j2 @@ -0,0 +1,4 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +bool xdrgen_decode_{{ name }}(struct xdr_stream *xdr, {{ classifier }}{{ name }} *ptr); +bool xdrgen_encode_{{ name }}(struct xdr_stream *xdr, const {{ classifier }}{{ name }} value); diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/declaration/variable_length_array.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/declaration/variable_length_array.j2 new file mode 100644 index 000000000000..3fe3ddd9f359 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/typedef/declaration/variable_length_array.j2 @@ -0,0 +1,4 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +bool xdrgen_decode_{{ name }}(struct xdr_stream *xdr, {{ classifier }}{{ name }} *ptr); +bool xdrgen_encode_{{ name }}(struct xdr_stream *xdr, const {{ classifier }}{{ name }} value); diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/declaration/variable_length_opaque.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/declaration/variable_length_opaque.j2 new file mode 100644 index 000000000000..3fe3ddd9f359 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/typedef/declaration/variable_length_opaque.j2 @@ -0,0 +1,4 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +bool xdrgen_decode_{{ name }}(struct xdr_stream *xdr, {{ classifier }}{{ name }} *ptr); +bool xdrgen_encode_{{ name }}(struct xdr_stream *xdr, const {{ classifier }}{{ name }} value); diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/declaration/variable_length_string.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/declaration/variable_length_string.j2 new file mode 100644 index 000000000000..3fe3ddd9f359 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/typedef/declaration/variable_length_string.j2 @@ -0,0 +1,4 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +bool xdrgen_decode_{{ name }}(struct xdr_stream *xdr, {{ classifier }}{{ name }} *ptr); +bool xdrgen_encode_{{ name }}(struct xdr_stream *xdr, const {{ classifier }}{{ name }} value); diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/decoder/basic.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/decoder/basic.j2 new file mode 100644 index 000000000000..da4709403dc9 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/typedef/decoder/basic.j2 @@ -0,0 +1,17 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* typedef {{ name }} */ +{% endif %} +{% if name in public_apis %} +bool +{% else %} +static bool __maybe_unused +{% endif %} +xdrgen_decode_{{ name }}(struct xdr_stream *xdr, {{ name }} *ptr) +{ +{% if annotate %} + /* (basic) */ +{% endif %} + return xdrgen_decode_{{ type }}(xdr, ptr); +}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/decoder/fixed_length_array.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/decoder/fixed_length_array.j2 new file mode 100644 index 000000000000..d7c80e472fe3 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/typedef/decoder/fixed_length_array.j2 @@ -0,0 +1,25 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* typedef {{ name }} */ +{% endif %} +{% if name in public_apis %} +bool +{% else %} +static bool __maybe_unused +{% endif %} +xdrgen_decode_{{ name }}(struct xdr_stream *xdr, {{ classifier }}{{ name }} *ptr) +{ +{% if annotate %} + /* (fixed-length array) */ +{% endif %} + for (u32 i = 0; i < {{ size }}; i++) { +{%- if classifier == '' %} + if (xdrgen_decode_{{ type }}(xdr, ptr->items[i]) < 0) +{% else %} + if (xdrgen_decode_{{ type }}(xdr, &ptr->items[i]) < 0) +{% endif %} + return false; + } + return true; +}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/decoder/fixed_length_opaque.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/decoder/fixed_length_opaque.j2 new file mode 100644 index 000000000000..8b4ff08c49e5 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/typedef/decoder/fixed_length_opaque.j2 @@ -0,0 +1,17 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* typedef {{ name }} */ +{% endif %} +{% if name in public_apis %} +bool +{% else %} +static bool __maybe_unused +{% endif %} +xdrgen_decode_{{ name }}(struct xdr_stream *xdr, {{ classifier }}{{ name }} *ptr) +{ +{% if annotate %} + /* (fixed-length opaque) */ +{% endif %} + return xdr_stream_decode_opaque_fixed(xdr, ptr, {{ size }}) >= 0; +}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/decoder/variable_length_array.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/decoder/variable_length_array.j2 new file mode 100644 index 000000000000..e74ffdd98463 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/typedef/decoder/variable_length_array.j2 @@ -0,0 +1,26 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* typedef {{ name }} */ +{% endif %} +{% if name in public_apis %} +bool +{% else %} +static bool __maybe_unused +{% endif %} +xdrgen_decode_{{ name }}(struct xdr_stream *xdr, {{ classifier }}{{ name }} *ptr) +{ +{% if annotate %} + /* (variable-length array) */ +{% endif %} + if (xdr_stream_decode_u32(xdr, &ptr->count) < 0) + return false; +{% if maxsize != "0" %} + if (ptr->count > {{ maxsize }}) + return false; +{% endif %} + for (u32 i = 0; i < ptr->count; i++) + if (!xdrgen_decode_{{ type }}(xdr, &ptr->element[i])) + return false; + return true; +}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/decoder/variable_length_opaque.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/decoder/variable_length_opaque.j2 new file mode 100644 index 000000000000..c1b7ad84f99c --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/typedef/decoder/variable_length_opaque.j2 @@ -0,0 +1,17 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* typedef {{ name }} */ +{% endif %} +{% if name in public_apis %} +bool +{% else %} +static bool __maybe_unused +{% endif %} +xdrgen_decode_{{ name }}(struct xdr_stream *xdr, {{ classifier }}{{ name }} *ptr) +{ +{% if annotate %} + /* (variable-length opaque) */ +{% endif %} + return xdr_stream_decode_opaque(xdr, ptr->data, ptr->len) >= 0; +}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/decoder/variable_length_string.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/decoder/variable_length_string.j2 new file mode 100644 index 000000000000..937286d76688 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/typedef/decoder/variable_length_string.j2 @@ -0,0 +1,17 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* typedef {{ name }} */ +{% endif %} +{% if name in public_apis %} +bool +{% else %} +static bool __maybe_unused +{% endif %} +xdrgen_decode_{{ name }}(struct xdr_stream *xdr, {{ classifier }}{{ name }} *ptr) +{ +{% if annotate %} + /* (variable-length string) */ +{% endif %} + return xdr_stream_decode_opaque(xdr, ptr->data, ptr->len) >= 0; +}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/definition/basic.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/definition/basic.j2 new file mode 100644 index 000000000000..1c5f28135eec --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/typedef/definition/basic.j2 @@ -0,0 +1,6 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* typedef {{ name }} (basic) */ +{% endif %} +typedef {{ classifier }}{{ type }} {{ name }}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/definition/fixed_length_array.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/definition/fixed_length_array.j2 new file mode 100644 index 000000000000..c3a67c952e77 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/typedef/definition/fixed_length_array.j2 @@ -0,0 +1,6 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* typedef {{ name }} (fixed-length array) */ +{% endif %} +typedef {{ type }}{{ name }}[{{ size }}]; diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/definition/fixed_length_opaque.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/definition/fixed_length_opaque.j2 new file mode 100644 index 000000000000..8788b02fe4f5 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/typedef/definition/fixed_length_opaque.j2 @@ -0,0 +1,6 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* typedef {{ name }} (fixed-length opaque) */ +{% endif %} +typedef u8 {{ name }}[{{ size }}]; diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/definition/variable_length_array.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/definition/variable_length_array.j2 new file mode 100644 index 000000000000..f03393760545 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/typedef/definition/variable_length_array.j2 @@ -0,0 +1,9 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* typedef {{ name }} (variable-length array) */ +{% endif %} +typedef struct { + u32 count; + {{ classifier }}{{ type }} *element; +} {{ name }}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/definition/variable_length_opaque.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/definition/variable_length_opaque.j2 new file mode 100644 index 000000000000..162f2610af34 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/typedef/definition/variable_length_opaque.j2 @@ -0,0 +1,6 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* typedef {{ name }} (variable-length opaque) */ +{% endif %} +typedef opaque {{ name }}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/definition/variable_length_string.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/definition/variable_length_string.j2 new file mode 100644 index 000000000000..c03c2df8e625 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/typedef/definition/variable_length_string.j2 @@ -0,0 +1,6 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* typedef {{ name }} (variable-length string) */ +{% endif %} +typedef string {{ name }}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/encoder/basic.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/encoder/basic.j2 new file mode 100644 index 000000000000..35effe67e4ef --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/typedef/encoder/basic.j2 @@ -0,0 +1,21 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* typedef {{ name }} */ +{% endif %} +{% if name in public_apis %} +bool +{% else %} +static bool __maybe_unused +{% endif %} +{% if name in pass_by_reference %} +xdrgen_encode_{{ name }}(struct xdr_stream *xdr, const {{ classifier }}{{ name }} *value) +{% else %} +xdrgen_encode_{{ name }}(struct xdr_stream *xdr, const {{ classifier }}{{ name }} value) +{% endif %} +{ +{% if annotate %} + /* (basic) */ +{% endif %} + return xdrgen_encode_{{ type }}(xdr, value); +}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/encoder/fixed_length_array.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/encoder/fixed_length_array.j2 new file mode 100644 index 000000000000..95202ad5ad2d --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/typedef/encoder/fixed_length_array.j2 @@ -0,0 +1,25 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* typedef {{ name }} */ +{% endif %} +{% if name in public_apis %} +bool +{% else %} +static bool __maybe_unused +{% endif %} +xdrgen_encode_{{ name }}(struct xdr_stream *xdr, const {{ classifier }}{{ name }} value) +{ +{% if annotate %} + /* (fixed-length array) */ +{% endif %} + for (u32 i = 0; i < {{ size }}; i++) { +{% if type in pass_by_reference %} + if (xdrgen_encode_{{ type }}(xdr, &value->items[i]) < 0) +{% else %} + if (xdrgen_encode_{{ type }}(xdr, value->items[i]) < 0) +{% endif %} + return false; + } + return true; +}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/encoder/fixed_length_opaque.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/encoder/fixed_length_opaque.j2 new file mode 100644 index 000000000000..9c66a11b9912 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/typedef/encoder/fixed_length_opaque.j2 @@ -0,0 +1,17 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* typedef {{ name }} */ +{% endif %} +{% if name in public_apis %} +bool +{% else %} +static bool __maybe_unused +{% endif %} +xdrgen_encode_{{ name }}(struct xdr_stream *xdr, const {{ classifier }}{{ name }} value) +{ +{% if annotate %} + /* (fixed-length opaque) */ +{% endif %} + return xdr_stream_encode_opaque_fixed(xdr, value, {{ size }}) >= 0; +}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/encoder/variable_length_array.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/encoder/variable_length_array.j2 new file mode 100644 index 000000000000..2d2384f64918 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/typedef/encoder/variable_length_array.j2 @@ -0,0 +1,30 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* typedef {{ name }} */ +{% endif %} +{% if name in public_apis %} +bool +{% else %} +static bool __maybe_unused +{% endif %} +xdrgen_encode_{{ name }}(struct xdr_stream *xdr, const {{ classifier }}{{ name }} value) +{ +{% if annotate %} + /* (variable-length array) */ +{% endif %} +{% if maxsize != "0" %} + if (unlikely(value.count > {{ maxsize }})) + return false; +{% endif %} + if (xdr_stream_encode_u32(xdr, value.count) != XDR_UNIT) + return false; + for (u32 i = 0; i < value.count; i++) +{% if type in pass_by_reference %} + if (!xdrgen_encode_{{ type }}(xdr, &value.element[i])) +{% else %} + if (!xdrgen_encode_{{ type }}(xdr, value.element[i])) +{% endif %} + return false; + return true; +}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/encoder/variable_length_opaque.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/encoder/variable_length_opaque.j2 new file mode 100644 index 000000000000..8508f13c95b9 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/typedef/encoder/variable_length_opaque.j2 @@ -0,0 +1,17 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* typedef {{ name }} */ +{% endif %} +{% if name in public_apis %} +bool +{% else %} +static bool __maybe_unused +{% endif %} +xdrgen_encode_{{ name }}(struct xdr_stream *xdr, const {{ classifier }}{{ name }} value) +{ +{% if annotate %} + /* (variable-length opaque) */ +{% endif %} + return xdr_stream_encode_opaque(xdr, value.data, value.len) >= 0; +}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/typedef/encoder/variable_length_string.j2 b/tools/net/sunrpc/xdrgen/templates/C/typedef/encoder/variable_length_string.j2 new file mode 100644 index 000000000000..3d490ff180d0 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/typedef/encoder/variable_length_string.j2 @@ -0,0 +1,17 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* typedef {{ name }} */ +{% endif %} +{% if name in public_apis %} +bool +{% else %} +static bool __maybe_unused +{% endif %} +xdrgen_encode_{{ name }}(struct xdr_stream *xdr, const {{ classifier }}{{ name }} value) +{ +{% if annotate %} + /* (variable-length string) */ +{% endif %} + return xdr_stream_encode_opaque(xdr, value.data, value.len) >= 0; +}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/decoder/basic.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/basic.j2 new file mode 100644 index 000000000000..4d97cc5395eb --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/basic.j2 @@ -0,0 +1,6 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (basic) */ +{% endif %} + if (!xdrgen_decode_{{ type }}(xdr, &ptr->u.{{ name }})) + return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/decoder/break.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/break.j2 new file mode 100644 index 000000000000..b286d1407029 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/break.j2 @@ -0,0 +1,2 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + break; diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/decoder/case_spec.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/case_spec.j2 new file mode 100644 index 000000000000..5fa2163f0a74 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/case_spec.j2 @@ -0,0 +1,2 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + case {{ case }}: diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/decoder/close.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/close.j2 new file mode 100644 index 000000000000..fdc2dfd1843b --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/close.j2 @@ -0,0 +1,4 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + } + return true; +}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/decoder/default_spec.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/default_spec.j2 new file mode 100644 index 000000000000..044a002d0589 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/default_spec.j2 @@ -0,0 +1,2 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + default: diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/decoder/open.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/open.j2 new file mode 100644 index 000000000000..eb9941376e49 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/open.j2 @@ -0,0 +1,12 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* union {{ name }} */ +{% endif %} +{% if name in public_apis %} +bool +{% else %} +static bool __maybe_unused +{% endif %} +xdrgen_decode_{{ name }}(struct xdr_stream *xdr, struct {{ name }} *ptr) +{ diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/decoder/optional_data.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/optional_data.j2 new file mode 100644 index 000000000000..e4476f5fd8d3 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/optional_data.j2 @@ -0,0 +1,6 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (optional data) */ +{% endif %} + if (!xdrgen_decode_{{ type }}(xdr, &ptr->u.{{ name }})) + return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/decoder/switch_spec.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/switch_spec.j2 new file mode 100644 index 000000000000..99b3067ef617 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/switch_spec.j2 @@ -0,0 +1,7 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* discriminant {{ name }} */ +{% endif %} + if (!xdrgen_decode_{{ type }}(xdr, &ptr->{{ name }})) + return false; + switch (ptr->{{ name }}) { diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/decoder/variable_length_array.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/variable_length_array.j2 new file mode 100644 index 000000000000..eee2b9a68e27 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/variable_length_array.j2 @@ -0,0 +1,13 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (variable-length array) */ +{% endif %} + if (xdr_stream_decode_u32(xdr, &count) != XDR_UNIT) + return false; + if (count > {{ maxsize }}) + return false; + for (u32 i = 0; i < count; i++) { + if (xdrgen_decode_{{ type }}(xdr, &ptr->{{ name }}.items[i]) < 0) + return false; + } + ptr->{{ name }}.len = count; diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/decoder/variable_length_opaque.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/variable_length_opaque.j2 new file mode 100644 index 000000000000..c9d88ed29c78 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/variable_length_opaque.j2 @@ -0,0 +1,6 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (variable-length opaque) */ +{% endif %} + if (!xdrgen_decode_opaque(xdr, (struct opaque *)ptr->u.{{ name }}, {{ maxsize }})) + return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/decoder/variable_length_string.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/variable_length_string.j2 new file mode 100644 index 000000000000..83b6e5a14e7f --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/variable_length_string.j2 @@ -0,0 +1,6 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (variable-length string) */ +{% endif %} + if (!xdrgen_decode_string(xdr, (struct string *)ptr->u.{{ name }}, {{ maxsize }})) + return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/decoder/void.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/void.j2 new file mode 100644 index 000000000000..65205ce37b36 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/void.j2 @@ -0,0 +1,3 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + if (!xdrgen_decode_void(xdr)) + return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/definition/case_spec.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/definition/case_spec.j2 new file mode 100644 index 000000000000..52f8d131b805 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/union/definition/case_spec.j2 @@ -0,0 +1,2 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + {{ classifier }}{{ type }} {{ name }}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/definition/close.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/definition/close.j2 new file mode 100644 index 000000000000..01d716d0099e --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/union/definition/close.j2 @@ -0,0 +1,8 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + } u; +}; +{%- if name in public_apis %} + +bool xdrgen_decode_{{ name }}(struct xdr_stream *xdr, struct {{ name }} *ptr); +bool xdrgen_encode_{{ name }}(struct xdr_stream *xdr, const struct {{ name }} *ptr); +{%- endif -%} diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/definition/default_spec.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/definition/default_spec.j2 new file mode 100644 index 000000000000..52f8d131b805 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/union/definition/default_spec.j2 @@ -0,0 +1,2 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + {{ classifier }}{{ type }} {{ name }}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/definition/open.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/definition/open.j2 new file mode 100644 index 000000000000..20fcfd1fc4e5 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/union/definition/open.j2 @@ -0,0 +1,6 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* union {{ name }} */ +{% endif %} +struct {{ name }} { diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/definition/switch_spec.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/definition/switch_spec.j2 new file mode 100644 index 000000000000..3e552732502c --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/union/definition/switch_spec.j2 @@ -0,0 +1,3 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + {{ classifier }}{{ type }} {{ name }}; + union { diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/encoder/basic.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/encoder/basic.j2 new file mode 100644 index 000000000000..6452d75c6f9a --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/union/encoder/basic.j2 @@ -0,0 +1,10 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* member {{ name }} (basic) */ +{% endif %} +{% if type in pass_by_reference %} + if (!xdrgen_encode_{{ type }}(xdr, &ptr->u.{{ name }})) +{% else %} + if (!xdrgen_encode_{{ type }}(xdr, ptr->u.{{ name }})) +{% endif %} + return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/encoder/break.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/encoder/break.j2 new file mode 100644 index 000000000000..b286d1407029 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/union/encoder/break.j2 @@ -0,0 +1,2 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + break; diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/encoder/case_spec.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/encoder/case_spec.j2 new file mode 100644 index 000000000000..5fa2163f0a74 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/union/encoder/case_spec.j2 @@ -0,0 +1,2 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + case {{ case }}: diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/encoder/close.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/encoder/close.j2 new file mode 100644 index 000000000000..fdc2dfd1843b --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/union/encoder/close.j2 @@ -0,0 +1,4 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + } + return true; +}; diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/encoder/default_spec.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/encoder/default_spec.j2 new file mode 100644 index 000000000000..044a002d0589 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/union/encoder/default_spec.j2 @@ -0,0 +1,2 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + default: diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/encoder/open.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/encoder/open.j2 new file mode 100644 index 000000000000..e5a206df10c6 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/union/encoder/open.j2 @@ -0,0 +1,12 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + +{% if annotate %} +/* union {{ name }} */ +{% endif %} +{% if name in public_apis %} +bool +{% else %} +static bool __maybe_unused +{% endif %} +xdrgen_encode_{{ name }}(struct xdr_stream *xdr, const struct {{ name }} *ptr) +{ diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/encoder/switch_spec.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/encoder/switch_spec.j2 new file mode 100644 index 000000000000..c8c3ecbe038b --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/union/encoder/switch_spec.j2 @@ -0,0 +1,7 @@ +{# SPDX-License-Identifier: GPL-2.0 #} +{% if annotate %} + /* discriminant {{ name }} */ +{% endif %} + if (!xdrgen_encode_{{ type }}(xdr, ptr->{{ name }})) + return false; + switch (ptr->{{ name }}) { diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/encoder/void.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/encoder/void.j2 new file mode 100644 index 000000000000..84e7c2127d75 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/templates/C/union/encoder/void.j2 @@ -0,0 +1,3 @@ +{# SPDX-License-Identifier: GPL-2.0 #} + if (!xdrgen_encode_void(xdr)) + return false; diff --git a/tools/net/sunrpc/xdrgen/tests/test.x b/tools/net/sunrpc/xdrgen/tests/test.x new file mode 100644 index 000000000000..90c8587f6fe5 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/tests/test.x @@ -0,0 +1,36 @@ +/* Sample XDR specification from RFC 1832 Section 5.5 */ + +const MAXUSERNAME = 32; /* max length of a user name */ +const MAXFILELEN = 65535; /* max length of a file */ +const MAXNAMELEN = 255; /* max length of a file name */ + +/* + * Types of files: + */ +enum filekind { + TEXT = 0, /* ascii data */ + DATA = 1, /* raw data */ + EXEC = 2 /* executable */ +}; + +/* + * File information, per kind of file: + */ +union filetype switch (filekind kind) { +case TEXT: + void; /* no extra information */ +case DATA: + string creator; /* data creator */ +case EXEC: + string interpretor; /* program interpretor */ +}; + +/* + * A complete file: + */ +struct file { + string filename; /* name of file */ + filetype type; /* info about file */ + string owner; /* owner of file */ + opaque data; /* file data */ +}; diff --git a/tools/net/sunrpc/xdrgen/xdr_ast.py b/tools/net/sunrpc/xdrgen/xdr_ast.py new file mode 100644 index 000000000000..dbd3fcf9c957 --- /dev/null +++ b/tools/net/sunrpc/xdrgen/xdr_ast.py @@ -0,0 +1,510 @@ +#!/usr/bin/env python3 +# ex: set filetype=python: + +"""Define and implement the Abstract Syntax Tree for the XDR language.""" + +import sys +from typing import List +from dataclasses import dataclass + +from lark import ast_utils, Transformer +from lark.tree import Meta + +this_module = sys.modules[__name__] + +excluded_apis = [] +header_name = "none" +public_apis = [] +enums = set() +structs = set() +pass_by_reference = set() + + +@dataclass +class _XdrAst(ast_utils.Ast): + """Base class for the XDR abstract syntax tree""" + + +@dataclass +class _XdrIdentifier(_XdrAst): + """Corresponds to 'identifier' in the XDR language grammar""" + + symbol: str + + +@dataclass +class _XdrValue(_XdrAst): + """Corresponds to 'value' in the XDR language grammar""" + + value: str + + +@dataclass +class _XdrConstantValue(_XdrAst): + """Corresponds to 'constant' in the XDR language grammar""" + + value: int + + +@dataclass +class _XdrTypeSpecifier(_XdrAst): + """Corresponds to 'type_specifier' in the XDR language grammar""" + + type_name: str + c_classifier: str + + +@dataclass +class _XdrDefinedType(_XdrTypeSpecifier): + """Corresponds to a type defined by the input specification""" + + +@dataclass +class _XdrBuiltInType(_XdrTypeSpecifier): + """Corresponds to a built-in XDR type""" + + +@dataclass +class _XdrDeclaration(_XdrAst): + """Base class of XDR type declarations""" + + +@dataclass +class _XdrFixedLengthOpaque(_XdrDeclaration): + """A fixed-length opaque declaration""" + + name: str + size: str + template: str = "fixed_length_opaque" + + +@dataclass +class _XdrVariableLengthOpaque(_XdrDeclaration): + """A variable-length opaque declaration""" + + name: str + maxsize: str + template: str = "variable_length_opaque" + + +@dataclass +class _XdrVariableLengthString(_XdrDeclaration): + """A (NUL-terminated) variable-length string declaration""" + + name: str + maxsize: str + template: str = "variable_length_string" + + +@dataclass +class _XdrFixedLengthArray(_XdrDeclaration): + """A fixed-length array declaration""" + + name: str + spec: _XdrTypeSpecifier + size: str + template: str = "fixed_length_array" + + +@dataclass +class _XdrVariableLengthArray(_XdrDeclaration): + """A variable-length array declaration""" + + name: str + spec: _XdrTypeSpecifier + maxsize: str + template: str = "variable_length_array" + + +@dataclass +class _XdrOptionalData(_XdrDeclaration): + """An 'optional_data' declaration""" + + name: str + spec: _XdrTypeSpecifier + template: str = "optional_data" + + +@dataclass +class _XdrBasic(_XdrDeclaration): + """A 'basic' declaration""" + + name: str + spec: _XdrTypeSpecifier + template: str = "basic" + + +@dataclass +class _XdrVoid(_XdrDeclaration): + """A void declaration""" + + template: str = "void" + + +@dataclass +class _XdrConstant(_XdrAst): + """Corresponds to 'constant_def' in the grammar""" + + name: str + value: str + + +@dataclass +class _XdrEnumerator(_XdrAst): + """An 'identifier = value' enumerator""" + + name: str + value: str + + +@dataclass +class _XdrEnum(_XdrAst): + """An XDR enum definition""" + + name: str + minimum: int + maximum: int + enumerators: List[_XdrEnumerator] + + +@dataclass +class _XdrStruct(_XdrAst): + """An XDR struct definition""" + + name: str + fields: List[_XdrDeclaration] + + +@dataclass +class _XdrPointer(_XdrAst): + """An XDR pointer definition""" + + name: str + fields: List[_XdrDeclaration] + + +@dataclass +class _XdrTypedef(_XdrAst): + """An XDR typedef""" + + declaration: _XdrDeclaration + + +@dataclass +class _XdrCaseSpec(_XdrAst): + """One case in an XDR union""" + + values: List[str] + arm: _XdrDeclaration + template: str = "case_spec" + + +@dataclass +class _XdrDefaultSpec(_XdrAst): + """Default case in an XDR union""" + + arm: _XdrDeclaration + template: str = "default_spec" + + +@dataclass +class _XdrUnion(_XdrAst): + """An XDR union""" + + name: str + discriminant: _XdrDeclaration + cases: List[_XdrCaseSpec] + default: _XdrDeclaration + + +@dataclass +class _RpcProcedure(_XdrAst): + """RPC procedure definition""" + + name: str + number: str + argument: _XdrTypeSpecifier + result: _XdrTypeSpecifier + + +@dataclass +class _RpcVersion(_XdrAst): + """RPC version definition""" + + name: str + number: str + procedures: List[_RpcProcedure] + + +@dataclass +class _RpcProgram(_XdrAst): + """RPC program definition""" + + name: str + number: str + versions: List[_RpcVersion] + + +@dataclass +class _Pragma(_XdrAst): + """Empty class for pragma directives""" + + +@dataclass +class Definition(_XdrAst, ast_utils.WithMeta): + """Corresponds to 'definition' in the grammar""" + + meta: Meta + value: _XdrAst + + +@dataclass +class Specification(_XdrAst, ast_utils.AsList): + """Corresponds to 'specification' in the grammar""" + + definitions: List[Definition] + + +class ParseToAst(Transformer): + """Functions that transform productions into AST nodes""" + + def identifier(self, children): + """Instantiate one _XdrIdentifier object""" + return _XdrIdentifier(children[0].value) + + def value(self, children): + """Instantiate one _XdrValue object""" + if isinstance(children[0], _XdrIdentifier): + return _XdrValue(children[0].symbol) + return _XdrValue(children[0].children[0].value) + + def constant(self, children): + """Instantiate one _XdrConstantValue object""" + match children[0].data: + case "decimal_constant": + value = int(children[0].children[0].value, base=10) + case "hexadecimal_constant": + value = int(children[0].children[0].value, base=16) + case "octal_constant": + value = int(children[0].children[0].value, base=8) + return _XdrConstantValue(value) + + def type_specifier(self, children): + """Instantiate one type_specifier object""" + c_classifier = "" + if isinstance(children[0], _XdrIdentifier): + name = children[0].symbol + if name in enums: + c_classifier = "enum " + if name in structs: + c_classifier = "struct " + return _XdrDefinedType( + type_name=name, + c_classifier=c_classifier, + ) + + token = children[0].data + return _XdrBuiltInType( + type_name=token.value, + c_classifier=c_classifier, + ) + + def constant_def(self, children): + """Instantiate one _XdrConstant object""" + name = children[0].symbol + value = children[1].value + return _XdrConstant(name, value) + + # cel: Python can compute a min() and max() for the enumerator values + # so that the generated code can perform proper range checking. + def enum(self, children): + """Instantiate one _XdrEnum object""" + enum_name = children[0].symbol + enums.add(enum_name) + + i = 0 + enumerators = [] + body = children[1] + while i < len(body.children): + name = body.children[i].symbol + value = body.children[i + 1].value + enumerators.append(_XdrEnumerator(name, value)) + i = i + 2 + + return _XdrEnum(enum_name, 0, 0, enumerators) + + def fixed_length_opaque(self, children): + """Instantiate one _XdrFixedLengthOpaque declaration object""" + name = children[0].symbol + size = children[1].value + + return _XdrFixedLengthOpaque(name, size) + + def variable_length_opaque(self, children): + """Instantiate one _XdrVariableLengthOpaque declaration object""" + name = children[0].symbol + if children[1] is not None: + maxsize = children[1].value + else: + maxsize = "0" + + return _XdrVariableLengthOpaque(name, maxsize) + + def variable_length_string(self, children): + """Instantiate one _XdrVariableLengthString declaration object""" + name = children[0].symbol + if children[1] is not None: + maxsize = children[1].value + else: + maxsize = "0" + + return _XdrVariableLengthString(name, maxsize) + + def fixed_length_array(self, children): + """Instantiate one _XdrFixedLengthArray declaration object""" + spec = children[0] + name = children[1].symbol + size = children[2].value + + return _XdrFixedLengthArray(name, spec, size) + + def variable_length_array(self, children): + """Instantiate one _XdrVariableLengthArray declaration object""" + spec = children[0] + name = children[1].symbol + if children[2] is not None: + maxsize = children[2].value + else: + maxsize = "0" + + return _XdrVariableLengthArray(name, spec, maxsize) + + def optional_data(self, children): + """Instantiate one _XdrOptionalData declaration object""" + spec = children[0] + name = children[1].symbol + structs.add(name) + pass_by_reference.add(name) + + return _XdrOptionalData(name, spec) + + def basic(self, children): + """Instantiate one _XdrBasic object""" + spec = children[0] + name = children[1].symbol + + return _XdrBasic(name, spec) + + def void(self, children): + """Instantiate one _XdrVoid declaration object""" + + return _XdrVoid() + + def struct(self, children): + """Instantiate one _XdrStruct object""" + name = children[0].symbol + structs.add(name) + pass_by_reference.add(name) + fields = children[1].children + + last_field = fields[-1] + if ( + isinstance(last_field, _XdrOptionalData) + and name == last_field.spec.type_name + ): + return _XdrPointer(name, fields) + + return _XdrStruct(name, fields) + + def typedef(self, children): + """Instantiate one _XdrTypedef object""" + new_type = children[0] + if isinstance(new_type, _XdrBasic) and isinstance( + new_type.spec, _XdrDefinedType + ): + if new_type.spec.type_name in pass_by_reference: + pass_by_reference.add(new_type.name) + + return _XdrTypedef(new_type) + + def case_spec(self, children): + """Instantiate one _XdrCaseSpec object""" + values = [] + for item in children[0:-1]: + values.append(item.value) + arm = children[-1] + + return _XdrCaseSpec(values, arm) + + def default_spec(self, children): + """Instantiate one _XdrDefaultSpec object""" + arm = children[0] + + return _XdrDefaultSpec(arm) + + def union(self, children): + """Instantiate one _XdrUnion object""" + name = children[0].symbol + structs.add(name) + pass_by_reference.add(name) + + body = children[1] + discriminant = body.children[0].children[0] + cases = body.children[1:-1] + default = body.children[-1] + + return _XdrUnion(name, discriminant, cases, default) + + def procedure_def(self, children): + """Instantiate one _RpcProcedure object""" + result = children[0] + name = children[1].symbol + argument = children[2] + number = children[3].value + + return _RpcProcedure(name, number, argument, result) + + def version_def(self, children): + """Instantiate one _RpcVersion object""" + name = children[0].symbol + number = children[-1].value + procedures = children[1:-1] + + return _RpcVersion(name, number, procedures) + + def program_def(self, children): + """Instantiate one _RpcProgram object""" + name = children[0].symbol + number = children[-1].value + versions = children[1:-1] + + return _RpcProgram(name, number, versions) + + def pragma_def(self, children): + """Instantiate one _Pragma object""" + directive = children[0].children[0].data + match directive: + case "exclude_directive": + excluded_apis.append(children[1].symbol) + case "header_directive": + global header_name + header_name = children[1].symbol + case "public_directive": + public_apis.append(children[1].symbol) + case _: + raise NotImplementedError("Directive not supported") + return _Pragma() + + +transformer = ast_utils.create_transformer(this_module, ParseToAst()) + + +def transform_parse_tree(parse_tree): + """Transform productions into an abstract syntax tree""" + + return transformer.transform(parse_tree) + + +def get_header_name() -> str: + """Return header name set by pragma header directive""" + return header_name diff --git a/tools/net/sunrpc/xdrgen/xdr_parse.py b/tools/net/sunrpc/xdrgen/xdr_parse.py new file mode 100644 index 000000000000..964b44e675df --- /dev/null +++ b/tools/net/sunrpc/xdrgen/xdr_parse.py @@ -0,0 +1,36 @@ +#!/usr/bin/env python3 +# ex: set filetype=python: + +"""Common parsing code for xdrgen""" + +from lark import Lark + + +# Set to True to emit annotation comments in generated source +annotate = False + + +def set_xdr_annotate(set_it: bool) -> None: + """Set 'annotate' if --annotate was specified on the command line""" + global annotate + annotate = set_it + + +def get_xdr_annotate() -> bool: + """Return True if --annotate was specified on the command line""" + return annotate + + +def xdr_parser() -> Lark: + """Return a Lark parser instance configured with the XDR language grammar""" + + return Lark.open( + "grammars/xdr.lark", + rel_to=__file__, + start="specification", + debug=True, + strict=True, + propagate_positions=True, + parser="lalr", + lexer="contextual", + ) diff --git a/tools/net/sunrpc/xdrgen/xdrgen b/tools/net/sunrpc/xdrgen/xdrgen new file mode 100755 index 000000000000..95f303b2861b --- /dev/null +++ b/tools/net/sunrpc/xdrgen/xdrgen @@ -0,0 +1,132 @@ +#!/usr/bin/env python3 +# ex: set filetype=python: + +"""Translate an XDR specification into executable code that +can be compiled for the Linux kernel.""" + +__author__ = "Chuck Lever" +__copyright__ = "Copyright (c) 2024 Oracle and/or its affiliates." +__license__ = "GPL-2.0 only" +__version__ = "0.2" + +import sys +import argparse + +from subcmds import definitions +from subcmds import declarations +from subcmds import lint +from subcmds import source + + +sys.path.insert(1, "@pythondir@") + + +def main() -> int: + """Parse command-line options""" + parser = argparse.ArgumentParser( + formatter_class=argparse.RawDescriptionHelpFormatter, + description="Convert an XDR specification to Linux kernel source code", + epilog="""\ +Copyright (c) 2024 Oracle and/or its affiliates. + +License GPLv2: +This is free software. You are free to change and redistribute it. +There is NO WARRANTY, to the extent permitted by law.""", + ) + parser.add_argument( + "--version", + help="Display the version of this tool", + action="version", + version=__version__, + ) + + subcommands = parser.add_subparsers(title="Subcommands", required=True) + + definitions_parser = subcommands.add_parser( + "definitions", help="Generate XDR definitions" + ) + definitions_parser.add_argument( + "--annotate", + action="store_true", + default=False, + help="Add annotation comments", + ) + definitions_parser.add_argument( + "--language", + action="store_true", + default="C", + help="Output language", + ) + definitions_parser.add_argument( + "--peer", + choices=["server", "client",], + default="server", + help="Generate header code for client or server side", + type=str, + ) + definitions_parser.add_argument("filename", help="File containing an XDR specification") + definitions_parser.set_defaults(func=definitions.subcmd) + + declarations_parser = subcommands.add_parser( + "declarations", help="Generate function declarations" + ) + declarations_parser.add_argument( + "--annotate", + action="store_true", + default=False, + help="Add annotation comments", + ) + declarations_parser.add_argument( + "--language", + action="store_true", + default="C", + help="Output language", + ) + declarations_parser.add_argument( + "--peer", + choices=["server", "client",], + default="server", + help="Generate code for client or server side", + type=str, + ) + declarations_parser.add_argument("filename", help="File containing an XDR specification") + declarations_parser.set_defaults(func=declarations.subcmd) + + linter_parser = subcommands.add_parser("lint", help="Check an XDR specification") + linter_parser.add_argument("filename", help="File containing an XDR specification") + linter_parser.set_defaults(func=lint.subcmd) + + source_parser = subcommands.add_parser( + "source", help="Generate XDR encoder and decoder source code" + ) + source_parser.add_argument( + "--annotate", + action="store_true", + default=False, + help="Add annotation comments", + ) + source_parser.add_argument( + "--language", + action="store_true", + default="C", + help="Output language", + ) + source_parser.add_argument( + "--peer", + choices=["server", "client",], + default="server", + help="Generate code for client or server side", + type=str, + ) + source_parser.add_argument("filename", help="File containing an XDR specification") + source_parser.set_defaults(func=source.subcmd) + + args = parser.parse_args() + return args.func(args) + + +try: + if __name__ == "__main__": + sys.exit(main()) +except (SystemExit, KeyboardInterrupt, BrokenPipeError): + sys.exit(1) -- cgit v1.2.3 From 663ad8b1df8724cd5e01df66ea67ce0424fbcdf6 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 10 Sep 2024 15:31:19 -0400 Subject: xdrgen: Fix return code checking in built-in XDR decoders xdr_stream_encode_u32() returns XDR_UNIT on success. xdr_stream_decode_u32() returns zero or -EMSGSIZE, but never XDR_UNIT. Signed-off-by: Chuck Lever --- include/linux/sunrpc/xdrgen/_builtins.h | 4 ++-- .../xdrgen/templates/C/pointer/decoder/variable_length_array.j2 | 2 +- .../sunrpc/xdrgen/templates/C/struct/decoder/variable_length_array.j2 | 2 +- .../sunrpc/xdrgen/templates/C/union/decoder/variable_length_array.j2 | 2 +- 4 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdrgen/_builtins.h b/include/linux/sunrpc/xdrgen/_builtins.h index 68746c59fc9a..66ca3ece951a 100644 --- a/include/linux/sunrpc/xdrgen/_builtins.h +++ b/include/linux/sunrpc/xdrgen/_builtins.h @@ -184,7 +184,7 @@ xdrgen_decode_string(struct xdr_stream *xdr, string *ptr, u32 maxlen) __be32 *p; u32 len; - if (unlikely(xdr_stream_decode_u32(xdr, &len) != XDR_UNIT)) + if (unlikely(xdr_stream_decode_u32(xdr, &len) < 0)) return false; if (unlikely(maxlen && len > maxlen)) return false; @@ -215,7 +215,7 @@ xdrgen_decode_opaque(struct xdr_stream *xdr, opaque *ptr, u32 maxlen) __be32 *p; u32 len; - if (unlikely(xdr_stream_decode_u32(xdr, &len) != XDR_UNIT)) + if (unlikely(xdr_stream_decode_u32(xdr, &len) < 0)) return false; if (unlikely(maxlen && len > maxlen)) return false; diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/variable_length_array.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/variable_length_array.j2 index f54ccd136762..2f943909cdf7 100644 --- a/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/variable_length_array.j2 +++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/decoder/variable_length_array.j2 @@ -2,7 +2,7 @@ {% if annotate %} /* member {{ name }} (variable-length array) */ {% endif %} - if (xdr_stream_decode_u32(xdr, &ptr->{{ name }}.count) != XDR_UNIT) + if (xdr_stream_decode_u32(xdr, &ptr->{{ name }}.count) < 0) return false; {% if maxsize != "0" %} if (ptr->{{ name }}.count > {{ maxsize }}) diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/variable_length_array.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/variable_length_array.j2 index f54ccd136762..2f943909cdf7 100644 --- a/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/variable_length_array.j2 +++ b/tools/net/sunrpc/xdrgen/templates/C/struct/decoder/variable_length_array.j2 @@ -2,7 +2,7 @@ {% if annotate %} /* member {{ name }} (variable-length array) */ {% endif %} - if (xdr_stream_decode_u32(xdr, &ptr->{{ name }}.count) != XDR_UNIT) + if (xdr_stream_decode_u32(xdr, &ptr->{{ name }}.count) < 0) return false; {% if maxsize != "0" %} if (ptr->{{ name }}.count > {{ maxsize }}) diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/decoder/variable_length_array.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/variable_length_array.j2 index eee2b9a68e27..51ad736d2530 100644 --- a/tools/net/sunrpc/xdrgen/templates/C/union/decoder/variable_length_array.j2 +++ b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/variable_length_array.j2 @@ -2,7 +2,7 @@ {% if annotate %} /* member {{ name }} (variable-length array) */ {% endif %} - if (xdr_stream_decode_u32(xdr, &count) != XDR_UNIT) + if (xdr_stream_decode_u32(xdr, &count) < 0) return false; if (count > {{ maxsize }}) return false; -- cgit v1.2.3 From bb0e391975f8da826305cbaa3e3d34b03c47e2a6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 22 Sep 2024 09:10:17 +0200 Subject: dma-mapping: fix vmap and mmap of noncontiougs allocations Commit b5c58b2fdc42 ("dma-mapping: direct calls for dma-iommu") switched to use direct calls to dma-iommu, but missed the dma_vmap_noncontiguous, dma_vunmap_noncontiguous and dma_mmap_noncontiguous behavior keyed off the presence of the alloc_noncontiguous method. Fix this by removing the now unused alloc_noncontiguous and free_noncontiguous methods and moving the vmapping and mmaping of the noncontiguous allocations into the iommu code, as it is the only provider of actually noncontiguous allocations. Fixes: b5c58b2fdc42 ("dma-mapping: direct calls for dma-iommu") Reported-by: Xi Ruoyao Signed-off-by: Christoph Hellwig Reviewed-by: Leon Romanovsky Tested-by: Xi Ruoyao --- drivers/iommu/dma-iommu.c | 33 +++++++++++++++++++++++++++++++++ include/linux/dma-map-ops.h | 19 ------------------- include/linux/iommu-dma.h | 6 ++++++ kernel/dma/mapping.c | 37 ++++++++++--------------------------- 4 files changed, 49 insertions(+), 46 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 3672d619bcb6..2a9fa0c8cc00 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -1038,6 +1038,21 @@ out_unmap: return NULL; } +/* + * This is the actual return value from the iommu_dma_alloc_noncontiguous. + * + * The users of the DMA API should only care about the sg_table, but to make + * the DMA-API internal vmaping and freeing easier we stash away the page + * array as well (except for the fallback case). This can go away any time, + * e.g. when a vmap-variant that takes a scatterlist comes along. + */ +struct dma_sgt_handle { + struct sg_table sgt; + struct page **pages; +}; +#define sgt_handle(sgt) \ + container_of((sgt), struct dma_sgt_handle, sgt) + struct sg_table *iommu_dma_alloc_noncontiguous(struct device *dev, size_t size, enum dma_data_direction dir, gfp_t gfp, unsigned long attrs) { @@ -1066,6 +1081,24 @@ void iommu_dma_free_noncontiguous(struct device *dev, size_t size, kfree(sh); } +void *iommu_dma_vmap_noncontiguous(struct device *dev, size_t size, + struct sg_table *sgt) +{ + unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; + + return vmap(sgt_handle(sgt)->pages, count, VM_MAP, PAGE_KERNEL); +} + +int iommu_dma_mmap_noncontiguous(struct device *dev, struct vm_area_struct *vma, + size_t size, struct sg_table *sgt) +{ + unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; + + if (vma->vm_pgoff >= count || vma_pages(vma) > count - vma->vm_pgoff) + return -ENXIO; + return vm_map_pages(vma, sgt_handle(sgt)->pages, count); +} + void iommu_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction dir) { diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 9668ddf3696e..b7773201414c 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -24,11 +24,6 @@ struct dma_map_ops { gfp_t gfp); void (*free_pages)(struct device *dev, size_t size, struct page *vaddr, dma_addr_t dma_handle, enum dma_data_direction dir); - struct sg_table *(*alloc_noncontiguous)(struct device *dev, size_t size, - enum dma_data_direction dir, gfp_t gfp, - unsigned long attrs); - void (*free_noncontiguous)(struct device *dev, size_t size, - struct sg_table *sgt, enum dma_data_direction dir); int (*mmap)(struct device *, struct vm_area_struct *, void *, dma_addr_t, size_t, unsigned long attrs); @@ -206,20 +201,6 @@ static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma, } #endif /* CONFIG_DMA_GLOBAL_POOL */ -/* - * This is the actual return value from the ->alloc_noncontiguous method. - * The users of the DMA API should only care about the sg_table, but to make - * the DMA-API internal vmaping and freeing easier we stash away the page - * array as well (except for the fallback case). This can go away any time, - * e.g. when a vmap-variant that takes a scatterlist comes along. - */ -struct dma_sgt_handle { - struct sg_table sgt; - struct page **pages; -}; -#define sgt_handle(sgt) \ - container_of((sgt), struct dma_sgt_handle, sgt) - int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs); diff --git a/include/linux/iommu-dma.h b/include/linux/iommu-dma.h index 1bb55ca1ab79..7bf145a52d6a 100644 --- a/include/linux/iommu-dma.h +++ b/include/linux/iommu-dma.h @@ -44,6 +44,12 @@ struct sg_table *iommu_dma_alloc_noncontiguous(struct device *dev, size_t size, enum dma_data_direction dir, gfp_t gfp, unsigned long attrs); void iommu_dma_free_noncontiguous(struct device *dev, size_t size, struct sg_table *sgt, enum dma_data_direction dir); +void *iommu_dma_vmap_noncontiguous(struct device *dev, size_t size, + struct sg_table *sgt); +#define iommu_dma_vunmap_noncontiguous(dev, vaddr) \ + vunmap(vaddr); +int iommu_dma_mmap_noncontiguous(struct device *dev, struct vm_area_struct *vma, + size_t size, struct sg_table *sgt); void iommu_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction dir); void iommu_dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index b839683da0ba..7911c754d9f4 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -750,7 +750,6 @@ out_free_sgt: struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size, enum dma_data_direction dir, gfp_t gfp, unsigned long attrs) { - const struct dma_map_ops *ops = get_dma_ops(dev); struct sg_table *sgt; if (WARN_ON_ONCE(attrs & ~DMA_ATTR_ALLOC_SINGLE_PAGES)) @@ -758,9 +757,7 @@ struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size, if (WARN_ON_ONCE(gfp & __GFP_COMP)) return NULL; - if (ops && ops->alloc_noncontiguous) - sgt = ops->alloc_noncontiguous(dev, size, dir, gfp, attrs); - else if (use_dma_iommu(dev)) + if (use_dma_iommu(dev)) sgt = iommu_dma_alloc_noncontiguous(dev, size, dir, gfp, attrs); else sgt = alloc_single_sgt(dev, size, dir, gfp); @@ -786,13 +783,10 @@ static void free_single_sgt(struct device *dev, size_t size, void dma_free_noncontiguous(struct device *dev, size_t size, struct sg_table *sgt, enum dma_data_direction dir) { - const struct dma_map_ops *ops = get_dma_ops(dev); - trace_dma_unmap_sg(dev, sgt->sgl, sgt->orig_nents, dir, 0); debug_dma_unmap_sg(dev, sgt->sgl, sgt->orig_nents, dir); - if (ops && ops->free_noncontiguous) - ops->free_noncontiguous(dev, size, sgt, dir); - else if (use_dma_iommu(dev)) + + if (use_dma_iommu(dev)) iommu_dma_free_noncontiguous(dev, size, sgt, dir); else free_single_sgt(dev, size, sgt, dir); @@ -802,37 +796,26 @@ EXPORT_SYMBOL_GPL(dma_free_noncontiguous); void *dma_vmap_noncontiguous(struct device *dev, size_t size, struct sg_table *sgt) { - const struct dma_map_ops *ops = get_dma_ops(dev); - unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; - if (ops && ops->alloc_noncontiguous) - return vmap(sgt_handle(sgt)->pages, count, VM_MAP, PAGE_KERNEL); + if (use_dma_iommu(dev)) + return iommu_dma_vmap_noncontiguous(dev, size, sgt); + return page_address(sg_page(sgt->sgl)); } EXPORT_SYMBOL_GPL(dma_vmap_noncontiguous); void dma_vunmap_noncontiguous(struct device *dev, void *vaddr) { - const struct dma_map_ops *ops = get_dma_ops(dev); - - if (ops && ops->alloc_noncontiguous) - vunmap(vaddr); + if (use_dma_iommu(dev)) + iommu_dma_vunmap_noncontiguous(dev, vaddr); } EXPORT_SYMBOL_GPL(dma_vunmap_noncontiguous); int dma_mmap_noncontiguous(struct device *dev, struct vm_area_struct *vma, size_t size, struct sg_table *sgt) { - const struct dma_map_ops *ops = get_dma_ops(dev); - - if (ops && ops->alloc_noncontiguous) { - unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; - - if (vma->vm_pgoff >= count || - vma_pages(vma) > count - vma->vm_pgoff) - return -ENXIO; - return vm_map_pages(vma, sgt_handle(sgt)->pages, count); - } + if (use_dma_iommu(dev)) + return iommu_dma_mmap_noncontiguous(dev, vma, size, sgt); return dma_mmap_pages(dev, vma, size, sg_page(sgt->sgl)); } EXPORT_SYMBOL_GPL(dma_mmap_noncontiguous); -- cgit v1.2.3 From 3d09ff45469eb2912ce2227c47efac297230d6d6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 22 Sep 2024 09:21:10 +0200 Subject: iommu/dma: remove most stubs in iommu-dma.h The direct calls from mapping.c all guarded by use_dma_iommu(), so don't bother to provide stubs, but instead just expose the prototypes unconditionally. Signed-off-by: Christoph Hellwig Reviewed-by: Leon Romanovsky --- include/linux/iommu-dma.h | 108 ++++------------------------------------------ 1 file changed, 8 insertions(+), 100 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu-dma.h b/include/linux/iommu-dma.h index 7bf145a52d6a..508beaa44c39 100644 --- a/include/linux/iommu-dma.h +++ b/include/linux/iommu-dma.h @@ -14,6 +14,13 @@ static inline bool use_dma_iommu(struct device *dev) { return dev->dma_iommu; } +#else +static inline bool use_dma_iommu(struct device *dev) +{ + return false; +} +#endif /* CONFIG_IOMMU_DMA */ + dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, unsigned long attrs); @@ -58,104 +65,5 @@ void iommu_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sgl, int nelems, enum dma_data_direction dir); void iommu_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sgl, int nelems, enum dma_data_direction dir); -#else -static inline bool use_dma_iommu(struct device *dev) -{ - return false; -} -static inline dma_addr_t iommu_dma_map_page(struct device *dev, - struct page *page, unsigned long offset, size_t size, - enum dma_data_direction dir, unsigned long attrs) -{ - return DMA_MAPPING_ERROR; -} -static inline void iommu_dma_unmap_page(struct device *dev, - dma_addr_t dma_handle, size_t size, enum dma_data_direction dir, - unsigned long attrs) -{ -} -static inline int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir, unsigned long attrs) -{ - return -EINVAL; -} -static inline void iommu_dma_unmap_sg(struct device *dev, - struct scatterlist *sg, int nents, enum dma_data_direction dir, - unsigned long attrs) -{ -} -static inline void *iommu_dma_alloc(struct device *dev, size_t size, - dma_addr_t *handle, gfp_t gfp, unsigned long attrs) -{ - return NULL; -} -static inline int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size, - unsigned long attrs) -{ - return -EINVAL; -} -static inline int iommu_dma_get_sgtable(struct device *dev, - struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, - size_t size, unsigned long attrs) -{ - return -EINVAL; -} -static inline unsigned long iommu_dma_get_merge_boundary(struct device *dev) -{ - return 0; -} -static inline size_t iommu_dma_opt_mapping_size(void) -{ - return 0; -} -static inline size_t iommu_dma_max_mapping_size(struct device *dev) -{ - return 0; -} -static inline void iommu_dma_free(struct device *dev, size_t size, - void *cpu_addr, dma_addr_t handle, unsigned long attrs) -{ -} -static inline dma_addr_t iommu_dma_map_resource(struct device *dev, - phys_addr_t phys, size_t size, enum dma_data_direction dir, - unsigned long attrs) -{ - return DMA_MAPPING_ERROR; -} -static inline void iommu_dma_unmap_resource(struct device *dev, - dma_addr_t handle, size_t size, enum dma_data_direction dir, - unsigned long attrs) -{ -} -static inline struct sg_table * -iommu_dma_alloc_noncontiguous(struct device *dev, size_t size, - enum dma_data_direction dir, gfp_t gfp, unsigned long attrs) -{ - return NULL; -} -static inline void iommu_dma_free_noncontiguous(struct device *dev, size_t size, - struct sg_table *sgt, enum dma_data_direction dir) -{ -} -static inline void iommu_dma_sync_single_for_cpu(struct device *dev, - dma_addr_t dma_handle, size_t size, - enum dma_data_direction dir) -{ -} -static inline void iommu_dma_sync_single_for_device(struct device *dev, - dma_addr_t dma_handle, size_t size, enum dma_data_direction dir) -{ -} -static inline void iommu_dma_sync_sg_for_cpu(struct device *dev, - struct scatterlist *sgl, int nelems, - enum dma_data_direction dir) -{ -} -static inline void iommu_dma_sync_sg_for_device(struct device *dev, - struct scatterlist *sgl, int nelems, - enum dma_data_direction dir) -{ -} -#endif /* CONFIG_IOMMU_DMA */ + #endif /* _LINUX_IOMMU_DMA_H */ -- cgit v1.2.3 From d0dd066a0fa26d55c19ace9e89dedd9504c5bcba Mon Sep 17 00:00:00 2001 From: "Christoph Lameter (Ampere)" Date: Wed, 12 Jun 2024 09:49:56 -0700 Subject: seqcount: replace smp_rmb() in read_seqcount() with load acquire Many architectures support load acquire which can replace a memory barrier and save some cycles. A typical sequence do { seq = read_seqcount_begin(&s); } while (read_seqcount_retry(&s, seq); requires 13 cycles on an N1 Neoverse arm64 core (Ampere Altra, to be specific) for an empty loop. Two read memory barriers are needed. One for each of the seqcount_* functions. We can replace the first read barrier with a load acquire of the seqcount which saves us one barrier. On the Altra doing so reduces the cycle count from 13 to 8. According to ARM, this is a general improvement for the ARM64 architecture and not specific to a certain processor. See https://developer.arm.com/documentation/102336/0100/Load-Acquire-and-Store-Release-instructions "Weaker ordering requirements that are imposed by Load-Acquire and Store-Release instructions allow for micro-architectural optimizations, which could reduce some of the performance impacts that are otherwise imposed by an explicit memory barrier. If the ordering requirement is satisfied using either a Load-Acquire or Store-Release, then it would be preferable to use these instructions instead of a DMB" [ NOTE! This is my original minimal patch that unconditionally switches over to using smp_load_acquire(), instead of the much more involved and subtle patch that Christoph Lameter wrote that made it conditional. But Christoph gets authorship credit because I had initially thought that we needed the more complex model, and Christoph ran with it it and did the work. Only after looking at code generation for all the relevant architectures, did I come to the conclusion that nobody actually really needs the old "smp_rmb()" model. Even architectures without load-acquire support generally do as well or better with smp_load_acquire(). So credit to Christoph, but if this then causes issues on other architectures, put the blame solidly on me. Also note as part of the ruthless simplification, this gets rid of the overly subtle optimization where some code uses a non-barrier version of the sequence count (see the __read_seqcount_begin() users in fs/namei.c). They then play games with their own barriers and/or with nested sequence counts. Those optimizations are literally meaningless on x86, and questionable elsewhere. If somebody can show that they matter, we need to re-do them more cleanly than "use an internal helper". - Linus ] Signed-off-by: Christoph Lameter (Ampere) Link: https://lore.kernel.org/all/20240912-seq_optimize-v3-1-8ee25e04dffa@gentwo.org/ Signed-off-by: Linus Torvalds --- include/linux/seqlock.h | 25 +++++-------------------- 1 file changed, 5 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index d90d8ee29d81..fffeb754880f 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -157,7 +157,7 @@ __seqprop_##lockname##_const_ptr(const seqcount_##lockname##_t *s) \ static __always_inline unsigned \ __seqprop_##lockname##_sequence(const seqcount_##lockname##_t *s) \ { \ - unsigned seq = READ_ONCE(s->seqcount.sequence); \ + unsigned seq = smp_load_acquire(&s->seqcount.sequence); \ \ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \ return seq; \ @@ -170,7 +170,7 @@ __seqprop_##lockname##_sequence(const seqcount_##lockname##_t *s) \ * Re-read the sequence counter since the (possibly \ * preempted) writer made progress. \ */ \ - seq = READ_ONCE(s->seqcount.sequence); \ + seq = smp_load_acquire(&s->seqcount.sequence); \ } \ \ return seq; \ @@ -208,7 +208,7 @@ static inline const seqcount_t *__seqprop_const_ptr(const seqcount_t *s) static inline unsigned __seqprop_sequence(const seqcount_t *s) { - return READ_ONCE(s->sequence); + return smp_load_acquire(&s->sequence); } static inline bool __seqprop_preemptible(const seqcount_t *s) @@ -263,17 +263,9 @@ SEQCOUNT_LOCKNAME(mutex, struct mutex, true, mutex) #define seqprop_assert(s) __seqprop(s, assert)(s) /** - * __read_seqcount_begin() - begin a seqcount_t read section w/o barrier + * __read_seqcount_begin() - begin a seqcount_t read section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * - * __read_seqcount_begin is like read_seqcount_begin, but has no smp_rmb() - * barrier. Callers should ensure that smp_rmb() or equivalent ordering is - * provided before actually loading any of the variables that are to be - * protected in this critical section. - * - * Use carefully, only in critical code, and comment how the barrier is - * provided. - * * Return: count to be passed to read_seqcount_retry() */ #define __read_seqcount_begin(s) \ @@ -293,13 +285,7 @@ SEQCOUNT_LOCKNAME(mutex, struct mutex, true, mutex) * * Return: count to be passed to read_seqcount_retry() */ -#define raw_read_seqcount_begin(s) \ -({ \ - unsigned _seq = __read_seqcount_begin(s); \ - \ - smp_rmb(); \ - _seq; \ -}) +#define raw_read_seqcount_begin(s) __read_seqcount_begin(s) /** * read_seqcount_begin() - begin a seqcount_t read critical section @@ -328,7 +314,6 @@ SEQCOUNT_LOCKNAME(mutex, struct mutex, true, mutex) ({ \ unsigned __seq = seqprop_sequence(s); \ \ - smp_rmb(); \ kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); \ __seq; \ }) -- cgit v1.2.3 From ffcdc4c628e1a30489da10dd78358e89c823b341 Mon Sep 17 00:00:00 2001 From: Alexander Mikhalitsyn Date: Fri, 6 Sep 2024 16:34:52 +0200 Subject: fs/mnt_idmapping: introduce an invalid_mnt_idmap Link: https://lore.kernel.org/linux-fsdevel/20240904-baugrube-erhoben-b3c1c49a2645@brauner/ Suggested-by: Christian Brauner Signed-off-by: Alexander Mikhalitsyn Reviewed-by: Christian Brauner Signed-off-by: Miklos Szeredi --- fs/mnt_idmapping.c | 22 ++++++++++++++++++++-- include/linux/mnt_idmapping.h | 1 + 2 files changed, 21 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/mnt_idmapping.c b/fs/mnt_idmapping.c index 3c60f1eaca61..cbca6500848e 100644 --- a/fs/mnt_idmapping.c +++ b/fs/mnt_idmapping.c @@ -32,6 +32,15 @@ struct mnt_idmap nop_mnt_idmap = { }; EXPORT_SYMBOL_GPL(nop_mnt_idmap); +/* + * Carries the invalid idmapping of a full 0-4294967295 {g,u}id range. + * This means that all {g,u}ids are mapped to INVALID_VFS{G,U}ID. + */ +struct mnt_idmap invalid_mnt_idmap = { + .count = REFCOUNT_INIT(1), +}; +EXPORT_SYMBOL_GPL(invalid_mnt_idmap); + /** * initial_idmapping - check whether this is the initial mapping * @ns: idmapping to check @@ -75,6 +84,8 @@ vfsuid_t make_vfsuid(struct mnt_idmap *idmap, if (idmap == &nop_mnt_idmap) return VFSUIDT_INIT(kuid); + if (idmap == &invalid_mnt_idmap) + return INVALID_VFSUID; if (initial_idmapping(fs_userns)) uid = __kuid_val(kuid); else @@ -112,6 +123,8 @@ vfsgid_t make_vfsgid(struct mnt_idmap *idmap, if (idmap == &nop_mnt_idmap) return VFSGIDT_INIT(kgid); + if (idmap == &invalid_mnt_idmap) + return INVALID_VFSGID; if (initial_idmapping(fs_userns)) gid = __kgid_val(kgid); else @@ -140,6 +153,8 @@ kuid_t from_vfsuid(struct mnt_idmap *idmap, if (idmap == &nop_mnt_idmap) return AS_KUIDT(vfsuid); + if (idmap == &invalid_mnt_idmap) + return INVALID_UID; uid = map_id_up(&idmap->uid_map, __vfsuid_val(vfsuid)); if (uid == (uid_t)-1) return INVALID_UID; @@ -167,6 +182,8 @@ kgid_t from_vfsgid(struct mnt_idmap *idmap, if (idmap == &nop_mnt_idmap) return AS_KGIDT(vfsgid); + if (idmap == &invalid_mnt_idmap) + return INVALID_GID; gid = map_id_up(&idmap->gid_map, __vfsgid_val(vfsgid)); if (gid == (gid_t)-1) return INVALID_GID; @@ -296,7 +313,7 @@ struct mnt_idmap *alloc_mnt_idmap(struct user_namespace *mnt_userns) */ struct mnt_idmap *mnt_idmap_get(struct mnt_idmap *idmap) { - if (idmap != &nop_mnt_idmap) + if (idmap != &nop_mnt_idmap && idmap != &invalid_mnt_idmap) refcount_inc(&idmap->count); return idmap; @@ -312,7 +329,8 @@ EXPORT_SYMBOL_GPL(mnt_idmap_get); */ void mnt_idmap_put(struct mnt_idmap *idmap) { - if (idmap != &nop_mnt_idmap && refcount_dec_and_test(&idmap->count)) + if (idmap != &nop_mnt_idmap && idmap != &invalid_mnt_idmap && + refcount_dec_and_test(&idmap->count)) free_mnt_idmap(idmap); } EXPORT_SYMBOL_GPL(mnt_idmap_put); diff --git a/include/linux/mnt_idmapping.h b/include/linux/mnt_idmapping.h index cd4d5c8781f5..b1b219bc3422 100644 --- a/include/linux/mnt_idmapping.h +++ b/include/linux/mnt_idmapping.h @@ -9,6 +9,7 @@ struct mnt_idmap; struct user_namespace; extern struct mnt_idmap nop_mnt_idmap; +extern struct mnt_idmap invalid_mnt_idmap; extern struct user_namespace init_user_ns; typedef struct { -- cgit v1.2.3 From f8eb5bd9a818cc5f2a1e50b22b0091830b28cc36 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 23 Sep 2024 08:58:31 -0700 Subject: mm: fix build on 32-bit targets without MAX_PHYSMEM_BITS MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The merge resolution to deal with the conflict between commits ea72ce5da228 ("x86/kaslr: Expose and use the end of the physical memory address space") and 99185c10d5d9 ("resource, kunit: add test case for region_intersects()") ended up being broken in configurations didn't define a MAX_PHYSMEM_BITS and that had a 32-bit 'phys_addr_t'. The fallback to using all bits set (ie "(-1ULL)") ended up causing a build error: kernel/resource.c: In function ‘gfr_start’: include/linux/minmax.h:93:30: error: conversion from ‘long long unsigned int’ to ‘resource_size_t’ {aka ‘unsigned int’} changes value from ‘18446744073709551615’ to ‘4294967295’ [-Werror=overflow] this was reported by Geert for m68k, but he points out that it happens on other 32-bit architectures too, eg mips, xtensa, parisc, and powerpc. Limiting 'PHYSMEM_END' to a 'phys_addr_t' (which is the same as 'resource_size_t') fixes the build, but Geert points out that it will then cause a silent overflow in mm/sparse.c: unsigned long max_sparsemem_pfn = (PHYSMEM_END + 1) >> PAGE_SHIFT; so we actually do want PHYSMEM_END to be defined a 64-bit type - just not all ones, and not larger than 'phys_addr_t'. The proper fix is probably to not have some kind of default fallback at all, but just make sure every architecture has a valid MAX_PHYSMEM_BITS. But in the meantime, this just applies the rule that PHYSMEM_END is the largest value that fits in a 'phys_addr_t', but does not have the high bit set in 64 bits. Ugly, ugly. Reported-by: Geert Uytterhoeven Cc: Andrew Morton Cc: Huang Ying Cc: Thomas Gleixner Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index b62437447077..ecf63d2b0582 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -101,7 +101,7 @@ extern int mmap_rnd_compat_bits __read_mostly; # ifdef MAX_PHYSMEM_BITS # define PHYSMEM_END ((1ULL << MAX_PHYSMEM_BITS) - 1) # else -# define PHYSMEM_END (-1ULL) +# define PHYSMEM_END (((phys_addr_t)-1)&~(1ULL<<63)) # endif #endif -- cgit v1.2.3 From d98f72272500f505cd7e152ffa456e64ee3855f0 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 6 Sep 2024 12:32:03 +1000 Subject: nfs: simplify and guarantee owner uniqueness. I have evidence of an Linux NFS client getting NFS4ERR_BAD_SEQID to a v4.0 LOCK request to a Linux server (which had fixed the problem with RELEASE_LOCKOWNER bug fixed). The LOCK request presented a "new" lock owner so there are two seq ids in the request: that for the open file, and that for the new lock. Given the context I am confident that the new lock owner was reported to have the wrong seqid. As lock owner identifiers are reused, the server must still have a lock owner active which the client thinks is no longer active. I wasn't able to determine a root-cause but the simplest fix seems to be to ensure lock owners are always unique much as open owners are (thanks to a time stamp). The easiest way to ensure uniqueness is with a 64bit counter for each server. That will never cycle (if updated once a nanosecond the last 584 years. A single NFS server would not handle open/lock requests nearly that fast, and a Linux node is unlikely to have an uptime approaching that). This patch removes the 2 ida and instead uses a per-server atomic64_t to provide uniqueness. Note that the lock owner already encodes the id as 64 bits even though it is a 32bit value. So changing to a 64bit value does not change the encoding of the lock owner. The open owner encoding is now 4 bytes larger. Signed-off-by: NeilBrown Signed-off-by: Anna Schumaker --- fs/nfs/client.c | 6 ++---- fs/nfs/nfs4_fs.h | 2 +- fs/nfs/nfs4state.c | 15 ++------------- fs/nfs/nfs4xdr.c | 6 +++--- include/linux/nfs_fs_sb.h | 3 +-- include/linux/nfs_xdr.h | 2 +- 6 files changed, 10 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 8286edd6062d..3fea7aa1366f 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -997,8 +997,8 @@ struct nfs_server *nfs_alloc_server(void) init_waitqueue_head(&server->write_congestion_wait); atomic_long_set(&server->writeback, 0); - ida_init(&server->openowner_id); - ida_init(&server->lockowner_id); + atomic64_set(&server->owner_ctr, 0); + pnfs_init_server(server); rpc_init_wait_queue(&server->uoc_rpcwaitq, "NFS UOC"); @@ -1037,8 +1037,6 @@ void nfs_free_server(struct nfs_server *server) } ida_free(&s_sysfs_ids, server->s_sysfs_id); - ida_destroy(&server->lockowner_id); - ida_destroy(&server->openowner_id); put_cred(server->cred); nfs_release_automount_timer(); call_rcu(&server->rcu, delayed_free); diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index c2045a2a9d0f..7d383d29a995 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -83,7 +83,7 @@ struct nfs4_minor_version_ops { #define NFS_SEQID_CONFIRMED 1 struct nfs_seqid_counter { ktime_t create_time; - int owner_id; + u64 owner_id; int flags; u32 counter; spinlock_t lock; /* Protects the list */ diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 30aba1dedaba..2ef656ca6371 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -501,11 +501,7 @@ nfs4_alloc_state_owner(struct nfs_server *server, sp = kzalloc(sizeof(*sp), gfp_flags); if (!sp) return NULL; - sp->so_seqid.owner_id = ida_alloc(&server->openowner_id, gfp_flags); - if (sp->so_seqid.owner_id < 0) { - kfree(sp); - return NULL; - } + sp->so_seqid.owner_id = atomic64_inc_return(&server->owner_ctr); sp->so_server = server; sp->so_cred = get_cred(cred); spin_lock_init(&sp->so_lock); @@ -536,7 +532,6 @@ static void nfs4_free_state_owner(struct nfs4_state_owner *sp) { nfs4_destroy_seqid_counter(&sp->so_seqid); put_cred(sp->so_cred); - ida_free(&sp->so_server->openowner_id, sp->so_seqid.owner_id); kfree(sp); } @@ -879,19 +874,13 @@ static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, f refcount_set(&lsp->ls_count, 1); lsp->ls_state = state; lsp->ls_owner = owner; - lsp->ls_seqid.owner_id = ida_alloc(&server->lockowner_id, GFP_KERNEL_ACCOUNT); - if (lsp->ls_seqid.owner_id < 0) - goto out_free; + lsp->ls_seqid.owner_id = atomic64_inc_return(&server->owner_ctr); INIT_LIST_HEAD(&lsp->ls_locks); return lsp; -out_free: - kfree(lsp); - return NULL; } void nfs4_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp) { - ida_free(&server->lockowner_id, lsp->ls_seqid.owner_id); nfs4_destroy_seqid_counter(&lsp->ls_seqid); kfree(lsp); } diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 7704a4509676..88bcbcba1381 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -1424,12 +1424,12 @@ static inline void encode_openhdr(struct xdr_stream *xdr, const struct nfs_opena */ encode_nfs4_seqid(xdr, arg->seqid); encode_share_access(xdr, arg->share_access); - p = reserve_space(xdr, 36); + p = reserve_space(xdr, 40); p = xdr_encode_hyper(p, arg->clientid); - *p++ = cpu_to_be32(24); + *p++ = cpu_to_be32(28); p = xdr_encode_opaque_fixed(p, "open id:", 8); *p++ = cpu_to_be32(arg->server->s_dev); - *p++ = cpu_to_be32(arg->id.uniquifier); + p = xdr_encode_hyper(p, arg->id.uniquifier); xdr_encode_hyper(p, arg->id.create_time); } diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 1df86ab98c77..e1e47ebd83ef 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -234,8 +234,7 @@ struct nfs_server { /* the following fields are protected by nfs_client->cl_lock */ struct rb_root state_owners; #endif - struct ida openowner_id; - struct ida lockowner_id; + atomic64_t owner_ctr; struct list_head state_owners_lru; struct list_head layouts; struct list_head delegations; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 45623af3e7b8..96ba04ab24f3 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -446,7 +446,7 @@ struct nfs42_clone_res { struct stateowner_id { __u64 create_time; - __u32 uniquifier; + __u64 uniquifier; }; struct nfs4_open_delegation { -- cgit v1.2.3 From 0b108e83795c9c23101f584ef7e3ab4f1f120ef0 Mon Sep 17 00:00:00 2001 From: Stephen Brennan Date: Mon, 19 Aug 2024 08:58:59 -0700 Subject: SUNRPC: convert RPC_TASK_* constants to enum The RPC_TASK_* constants are defined as macros, which means that most kernel builds will not contain their definitions in the debuginfo. However, it's quite useful for debuggers to be able to view the task state constant and interpret it correctly. Conversion to an enum will ensure the constants are present in debuginfo and can be interpreted by debuggers without needing to hard-code them and track their changes. Signed-off-by: Stephen Brennan Signed-off-by: Anna Schumaker --- include/linux/sunrpc/sched.h | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 0c77ba488bba..fec1e8a1570c 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -151,13 +151,15 @@ struct rpc_task_setup { #define RPC_WAS_SENT(t) ((t)->tk_flags & RPC_TASK_SENT) #define RPC_IS_MOVEABLE(t) ((t)->tk_flags & RPC_TASK_MOVEABLE) -#define RPC_TASK_RUNNING 0 -#define RPC_TASK_QUEUED 1 -#define RPC_TASK_ACTIVE 2 -#define RPC_TASK_NEED_XMIT 3 -#define RPC_TASK_NEED_RECV 4 -#define RPC_TASK_MSG_PIN_WAIT 5 -#define RPC_TASK_SIGNALLED 6 +enum { + RPC_TASK_RUNNING, + RPC_TASK_QUEUED, + RPC_TASK_ACTIVE, + RPC_TASK_NEED_XMIT, + RPC_TASK_NEED_RECV, + RPC_TASK_MSG_PIN_WAIT, + RPC_TASK_SIGNALLED, +}; #define rpc_test_and_set_running(t) \ test_and_set_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) -- cgit v1.2.3 From dfb07e990a0d019d7ae9b78dd4260620ce32e79a Mon Sep 17 00:00:00 2001 From: Dan Aloni Date: Wed, 24 Jul 2024 14:07:12 +0300 Subject: nfs: add 'noalignwrite' option for lock-less 'lost writes' prevention There are some applications that write to predefined non-overlapping file offsets from multiple clients and therefore don't need to rely on file locking. However, if these applications want non-aligned offsets and sizes they need to either use locks or risk data corruption, as the NFS client defaults to extending writes to whole pages. This commit adds a new mount option `noalignwrite`, which allows to turn that off and avoid the need of locking, as long as these applications don't overlap on offsets. Signed-off-by: Dan Aloni Reviewed-by: Jeff Layton Reviewed-by: Sagi Grimberg Reviewed-by: Christoph Hellwig Signed-off-by: Anna Schumaker --- fs/nfs/fs_context.c | 8 ++++++++ fs/nfs/super.c | 3 +++ fs/nfs/write.c | 3 +++ include/linux/nfs_fs_sb.h | 1 + 4 files changed, 15 insertions(+) (limited to 'include/linux') diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c index 6c9f3f6645dd..7e000d782e28 100644 --- a/fs/nfs/fs_context.c +++ b/fs/nfs/fs_context.c @@ -49,6 +49,7 @@ enum nfs_param { Opt_bsize, Opt_clientaddr, Opt_cto, + Opt_alignwrite, Opt_fg, Opt_fscache, Opt_fscache_flag, @@ -149,6 +150,7 @@ static const struct fs_parameter_spec nfs_fs_parameters[] = { fsparam_u32 ("bsize", Opt_bsize), fsparam_string("clientaddr", Opt_clientaddr), fsparam_flag_no("cto", Opt_cto), + fsparam_flag_no("alignwrite", Opt_alignwrite), fsparam_flag ("fg", Opt_fg), fsparam_flag_no("fsc", Opt_fscache_flag), fsparam_string("fsc", Opt_fscache), @@ -592,6 +594,12 @@ static int nfs_fs_context_parse_param(struct fs_context *fc, else ctx->flags |= NFS_MOUNT_TRUNK_DISCOVERY; break; + case Opt_alignwrite: + if (result.negated) + ctx->flags |= NFS_MOUNT_NO_ALIGNWRITE; + else + ctx->flags &= ~NFS_MOUNT_NO_ALIGNWRITE; + break; case Opt_ac: if (result.negated) ctx->flags |= NFS_MOUNT_NOAC; diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 97b386032b71..9723b6c53397 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -551,6 +551,9 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss, else seq_puts(m, ",local_lock=posix"); + if (nfss->flags & NFS_MOUNT_NO_ALIGNWRITE) + seq_puts(m, ",noalignwrite"); + if (nfss->flags & NFS_MOUNT_WRITE_EAGER) { if (nfss->flags & NFS_MOUNT_WRITE_WAIT) seq_puts(m, ",write=wait"); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 80c6ded5f74c..61b580bcb356 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1295,7 +1295,10 @@ static int nfs_can_extend_write(struct file *file, struct folio *folio, struct file_lock_context *flctx = locks_inode_context(inode); struct file_lock *fl; int ret; + unsigned int mntflags = NFS_SERVER(inode)->flags; + if (mntflags & NFS_MOUNT_NO_ALIGNWRITE) + return 0; if (file->f_flags & O_DSYNC) return 0; if (!nfs_folio_write_uptodate(folio, pagelen)) diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index e1e47ebd83ef..c49bfdded5c1 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -158,6 +158,7 @@ struct nfs_server { #define NFS_MOUNT_WRITE_WAIT 0x02000000 #define NFS_MOUNT_TRUNK_DISCOVERY 0x04000000 #define NFS_MOUNT_SHUTDOWN 0x08000000 +#define NFS_MOUNT_NO_ALIGNWRITE 0x10000000 unsigned int fattr_valid; /* Valid attributes */ unsigned int caps; /* server capabilities */ -- cgit v1.2.3 From 4806ded4c14c5e8fdc6ce885d83221a78c06a428 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 5 Sep 2024 15:09:35 -0400 Subject: nfs_common: factor out nfs_errtbl and nfs_stat_to_errno Common nfs_stat_to_errno() is used by both fs/nfs/nfs2xdr.c and fs/nfs/nfs3xdr.c Will also be used by fs/nfsd/localio.c Signed-off-by: Mike Snitzer Reviewed-by: Jeff Layton Reviewed-by: NeilBrown Signed-off-by: Anna Schumaker --- fs/nfs/Kconfig | 1 + fs/nfs/nfs2xdr.c | 70 +---------------------------- fs/nfs/nfs3xdr.c | 108 +++++++++------------------------------------ fs/nfs/nfs4xdr.c | 4 +- fs/nfs_common/Makefile | 2 + fs/nfs_common/common.c | 67 ++++++++++++++++++++++++++++ fs/nfsd/Kconfig | 1 + include/linux/nfs_common.h | 16 +++++++ 8 files changed, 109 insertions(+), 160 deletions(-) create mode 100644 fs/nfs_common/common.c create mode 100644 include/linux/nfs_common.h (limited to 'include/linux') diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 57249f040dfc..0eb20012792f 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -4,6 +4,7 @@ config NFS_FS depends on INET && FILE_LOCKING && MULTIUSER select LOCKD select SUNRPC + select NFS_COMMON select NFS_ACL_SUPPORT if NFS_V3_ACL help Choose Y here if you want to access files residing on other diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index c19093814296..6e75c6c2d234 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -22,14 +22,12 @@ #include #include #include +#include #include "nfstrace.h" #include "internal.h" #define NFSDBG_FACILITY NFSDBG_XDR -/* Mapping from NFS error code to "errno" error code. */ -#define errno_NFSERR_IO EIO - /* * Declare the space requirements for NFS arguments and replies as * number of 32bit-words @@ -64,8 +62,6 @@ #define NFS_readdirres_sz (1+NFS_pagepad_sz) #define NFS_statfsres_sz (1+NFS_info_sz) -static int nfs_stat_to_errno(enum nfs_stat); - /* * Encode/decode NFSv2 basic data types * @@ -1054,70 +1050,6 @@ out_default: return nfs_stat_to_errno(status); } - -/* - * We need to translate between nfs status return values and - * the local errno values which may not be the same. - */ -static const struct { - int stat; - int errno; -} nfs_errtbl[] = { - { NFS_OK, 0 }, - { NFSERR_PERM, -EPERM }, - { NFSERR_NOENT, -ENOENT }, - { NFSERR_IO, -errno_NFSERR_IO}, - { NFSERR_NXIO, -ENXIO }, -/* { NFSERR_EAGAIN, -EAGAIN }, */ - { NFSERR_ACCES, -EACCES }, - { NFSERR_EXIST, -EEXIST }, - { NFSERR_XDEV, -EXDEV }, - { NFSERR_NODEV, -ENODEV }, - { NFSERR_NOTDIR, -ENOTDIR }, - { NFSERR_ISDIR, -EISDIR }, - { NFSERR_INVAL, -EINVAL }, - { NFSERR_FBIG, -EFBIG }, - { NFSERR_NOSPC, -ENOSPC }, - { NFSERR_ROFS, -EROFS }, - { NFSERR_MLINK, -EMLINK }, - { NFSERR_NAMETOOLONG, -ENAMETOOLONG }, - { NFSERR_NOTEMPTY, -ENOTEMPTY }, - { NFSERR_DQUOT, -EDQUOT }, - { NFSERR_STALE, -ESTALE }, - { NFSERR_REMOTE, -EREMOTE }, -#ifdef EWFLUSH - { NFSERR_WFLUSH, -EWFLUSH }, -#endif - { NFSERR_BADHANDLE, -EBADHANDLE }, - { NFSERR_NOT_SYNC, -ENOTSYNC }, - { NFSERR_BAD_COOKIE, -EBADCOOKIE }, - { NFSERR_NOTSUPP, -ENOTSUPP }, - { NFSERR_TOOSMALL, -ETOOSMALL }, - { NFSERR_SERVERFAULT, -EREMOTEIO }, - { NFSERR_BADTYPE, -EBADTYPE }, - { NFSERR_JUKEBOX, -EJUKEBOX }, - { -1, -EIO } -}; - -/** - * nfs_stat_to_errno - convert an NFS status code to a local errno - * @status: NFS status code to convert - * - * Returns a local errno value, or -EIO if the NFS status code is - * not recognized. This function is used jointly by NFSv2 and NFSv3. - */ -static int nfs_stat_to_errno(enum nfs_stat status) -{ - int i; - - for (i = 0; nfs_errtbl[i].stat != -1; i++) { - if (nfs_errtbl[i].stat == (int)status) - return nfs_errtbl[i].errno; - } - dprintk("NFS: Unrecognized nfs status value: %u\n", status); - return nfs_errtbl[i].errno; -} - #define PROC(proc, argtype, restype, timer) \ [NFSPROC_##proc] = { \ .p_proc = NFSPROC_##proc, \ diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 60f032be805a..4ae01c10b7e2 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -21,14 +21,13 @@ #include #include #include +#include + #include "nfstrace.h" #include "internal.h" #define NFSDBG_FACILITY NFSDBG_XDR -/* Mapping from NFS error code to "errno" error code. */ -#define errno_NFSERR_IO EIO - /* * Declare the space requirements for NFS arguments and replies as * number of 32bit-words @@ -91,8 +90,6 @@ NFS3_pagepad_sz) #define ACL3_setaclres_sz (1+NFS3_post_op_attr_sz) -static int nfs3_stat_to_errno(enum nfs_stat); - /* * Map file type to S_IFMT bits */ @@ -1406,7 +1403,7 @@ static int nfs3_xdr_dec_getattr3res(struct rpc_rqst *req, out: return error; out_default: - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } /* @@ -1445,7 +1442,7 @@ static int nfs3_xdr_dec_setattr3res(struct rpc_rqst *req, out: return error; out_status: - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } /* @@ -1495,7 +1492,7 @@ out_default: error = decode_post_op_attr(xdr, result->dir_attr, userns); if (unlikely(error)) goto out; - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } /* @@ -1537,7 +1534,7 @@ static int nfs3_xdr_dec_access3res(struct rpc_rqst *req, out: return error; out_default: - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } /* @@ -1578,7 +1575,7 @@ static int nfs3_xdr_dec_readlink3res(struct rpc_rqst *req, out: return error; out_default: - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } /* @@ -1658,7 +1655,7 @@ static int nfs3_xdr_dec_read3res(struct rpc_rqst *req, struct xdr_stream *xdr, out: return error; out_status: - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } /* @@ -1728,7 +1725,7 @@ static int nfs3_xdr_dec_write3res(struct rpc_rqst *req, struct xdr_stream *xdr, out: return error; out_status: - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } /* @@ -1795,7 +1792,7 @@ out_default: error = decode_wcc_data(xdr, result->dir_attr, userns); if (unlikely(error)) goto out; - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } /* @@ -1835,7 +1832,7 @@ static int nfs3_xdr_dec_remove3res(struct rpc_rqst *req, out: return error; out_status: - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } /* @@ -1881,7 +1878,7 @@ static int nfs3_xdr_dec_rename3res(struct rpc_rqst *req, out: return error; out_status: - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } /* @@ -1926,7 +1923,7 @@ static int nfs3_xdr_dec_link3res(struct rpc_rqst *req, struct xdr_stream *xdr, out: return error; out_status: - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } /** @@ -2101,7 +2098,7 @@ out_default: error = decode_post_op_attr(xdr, result->dir_attr, rpc_rqst_userns(req)); if (unlikely(error)) goto out; - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } /* @@ -2167,7 +2164,7 @@ static int nfs3_xdr_dec_fsstat3res(struct rpc_rqst *req, out: return error; out_status: - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } /* @@ -2243,7 +2240,7 @@ static int nfs3_xdr_dec_fsinfo3res(struct rpc_rqst *req, out: return error; out_status: - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } /* @@ -2304,7 +2301,7 @@ static int nfs3_xdr_dec_pathconf3res(struct rpc_rqst *req, out: return error; out_status: - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } /* @@ -2350,7 +2347,7 @@ static int nfs3_xdr_dec_commit3res(struct rpc_rqst *req, out: return error; out_status: - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } #ifdef CONFIG_NFS_V3_ACL @@ -2416,7 +2413,7 @@ static int nfs3_xdr_dec_getacl3res(struct rpc_rqst *req, out: return error; out_default: - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } static int nfs3_xdr_dec_setacl3res(struct rpc_rqst *req, @@ -2435,76 +2432,11 @@ static int nfs3_xdr_dec_setacl3res(struct rpc_rqst *req, out: return error; out_default: - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } #endif /* CONFIG_NFS_V3_ACL */ - -/* - * We need to translate between nfs status return values and - * the local errno values which may not be the same. - */ -static const struct { - int stat; - int errno; -} nfs_errtbl[] = { - { NFS_OK, 0 }, - { NFSERR_PERM, -EPERM }, - { NFSERR_NOENT, -ENOENT }, - { NFSERR_IO, -errno_NFSERR_IO}, - { NFSERR_NXIO, -ENXIO }, -/* { NFSERR_EAGAIN, -EAGAIN }, */ - { NFSERR_ACCES, -EACCES }, - { NFSERR_EXIST, -EEXIST }, - { NFSERR_XDEV, -EXDEV }, - { NFSERR_NODEV, -ENODEV }, - { NFSERR_NOTDIR, -ENOTDIR }, - { NFSERR_ISDIR, -EISDIR }, - { NFSERR_INVAL, -EINVAL }, - { NFSERR_FBIG, -EFBIG }, - { NFSERR_NOSPC, -ENOSPC }, - { NFSERR_ROFS, -EROFS }, - { NFSERR_MLINK, -EMLINK }, - { NFSERR_NAMETOOLONG, -ENAMETOOLONG }, - { NFSERR_NOTEMPTY, -ENOTEMPTY }, - { NFSERR_DQUOT, -EDQUOT }, - { NFSERR_STALE, -ESTALE }, - { NFSERR_REMOTE, -EREMOTE }, -#ifdef EWFLUSH - { NFSERR_WFLUSH, -EWFLUSH }, -#endif - { NFSERR_BADHANDLE, -EBADHANDLE }, - { NFSERR_NOT_SYNC, -ENOTSYNC }, - { NFSERR_BAD_COOKIE, -EBADCOOKIE }, - { NFSERR_NOTSUPP, -ENOTSUPP }, - { NFSERR_TOOSMALL, -ETOOSMALL }, - { NFSERR_SERVERFAULT, -EREMOTEIO }, - { NFSERR_BADTYPE, -EBADTYPE }, - { NFSERR_JUKEBOX, -EJUKEBOX }, - { -1, -EIO } -}; - -/** - * nfs3_stat_to_errno - convert an NFS status code to a local errno - * @status: NFS status code to convert - * - * Returns a local errno value, or -EIO if the NFS status code is - * not recognized. This function is used jointly by NFSv2 and NFSv3. - */ -static int nfs3_stat_to_errno(enum nfs_stat status) -{ - int i; - - for (i = 0; nfs_errtbl[i].stat != -1; i++) { - if (nfs_errtbl[i].stat == (int)status) - return nfs_errtbl[i].errno; - } - dprintk("NFS: Unrecognized nfs status value: %u\n", status); - return nfs_errtbl[i].errno; -} - - #define PROC(proc, argtype, restype, timer) \ [NFS3PROC_##proc] = { \ .p_proc = NFS3PROC_##proc, \ diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 88bcbcba1381..b61ffe6b9851 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -52,6 +52,7 @@ #include #include #include +#include #include "nfs4_fs.h" #include "nfs4trace.h" @@ -63,9 +64,6 @@ #define NFSDBG_FACILITY NFSDBG_XDR -/* Mapping from NFS error code to "errno" error code. */ -#define errno_NFSERR_IO EIO - struct compound_hdr; static int nfs4_stat_to_errno(int); static void encode_layoutget(struct xdr_stream *xdr, diff --git a/fs/nfs_common/Makefile b/fs/nfs_common/Makefile index 119c75ab9fd0..e58b01bb8dda 100644 --- a/fs/nfs_common/Makefile +++ b/fs/nfs_common/Makefile @@ -8,3 +8,5 @@ nfs_acl-objs := nfsacl.o obj-$(CONFIG_GRACE_PERIOD) += grace.o obj-$(CONFIG_NFS_V4_2_SSC_HELPER) += nfs_ssc.o + +obj-$(CONFIG_NFS_COMMON) += common.o diff --git a/fs/nfs_common/common.c b/fs/nfs_common/common.c new file mode 100644 index 000000000000..a4ee95da2174 --- /dev/null +++ b/fs/nfs_common/common.c @@ -0,0 +1,67 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include + +/* + * We need to translate between nfs status return values and + * the local errno values which may not be the same. + */ +static const struct { + int stat; + int errno; +} nfs_errtbl[] = { + { NFS_OK, 0 }, + { NFSERR_PERM, -EPERM }, + { NFSERR_NOENT, -ENOENT }, + { NFSERR_IO, -errno_NFSERR_IO}, + { NFSERR_NXIO, -ENXIO }, +/* { NFSERR_EAGAIN, -EAGAIN }, */ + { NFSERR_ACCES, -EACCES }, + { NFSERR_EXIST, -EEXIST }, + { NFSERR_XDEV, -EXDEV }, + { NFSERR_NODEV, -ENODEV }, + { NFSERR_NOTDIR, -ENOTDIR }, + { NFSERR_ISDIR, -EISDIR }, + { NFSERR_INVAL, -EINVAL }, + { NFSERR_FBIG, -EFBIG }, + { NFSERR_NOSPC, -ENOSPC }, + { NFSERR_ROFS, -EROFS }, + { NFSERR_MLINK, -EMLINK }, + { NFSERR_NAMETOOLONG, -ENAMETOOLONG }, + { NFSERR_NOTEMPTY, -ENOTEMPTY }, + { NFSERR_DQUOT, -EDQUOT }, + { NFSERR_STALE, -ESTALE }, + { NFSERR_REMOTE, -EREMOTE }, +#ifdef EWFLUSH + { NFSERR_WFLUSH, -EWFLUSH }, +#endif + { NFSERR_BADHANDLE, -EBADHANDLE }, + { NFSERR_NOT_SYNC, -ENOTSYNC }, + { NFSERR_BAD_COOKIE, -EBADCOOKIE }, + { NFSERR_NOTSUPP, -ENOTSUPP }, + { NFSERR_TOOSMALL, -ETOOSMALL }, + { NFSERR_SERVERFAULT, -EREMOTEIO }, + { NFSERR_BADTYPE, -EBADTYPE }, + { NFSERR_JUKEBOX, -EJUKEBOX }, + { -1, -EIO } +}; + +/** + * nfs_stat_to_errno - convert an NFS status code to a local errno + * @status: NFS status code to convert + * + * Returns a local errno value, or -EIO if the NFS status code is + * not recognized. This function is used jointly by NFSv2 and NFSv3. + */ +int nfs_stat_to_errno(enum nfs_stat status) +{ + int i; + + for (i = 0; nfs_errtbl[i].stat != -1; i++) { + if (nfs_errtbl[i].stat == (int)status) + return nfs_errtbl[i].errno; + } + return nfs_errtbl[i].errno; +} +EXPORT_SYMBOL_GPL(nfs_stat_to_errno); diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig index ec2ab6429e00..c0bd1509ccd4 100644 --- a/fs/nfsd/Kconfig +++ b/fs/nfsd/Kconfig @@ -7,6 +7,7 @@ config NFSD select LOCKD select SUNRPC select EXPORTFS + select NFS_COMMON select NFS_ACL_SUPPORT if NFSD_V2_ACL select NFS_ACL_SUPPORT if NFSD_V3_ACL depends on MULTIUSER diff --git a/include/linux/nfs_common.h b/include/linux/nfs_common.h new file mode 100644 index 000000000000..3395c4a4d372 --- /dev/null +++ b/include/linux/nfs_common.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * This file contains constants and methods used by both NFS client and server. + */ +#ifndef _LINUX_NFS_COMMON_H +#define _LINUX_NFS_COMMON_H + +#include +#include + +/* Mapping from NFS error code to "errno" error code. */ +#define errno_NFSERR_IO EIO + +int nfs_stat_to_errno(enum nfs_stat status); + +#endif /* _LINUX_NFS_COMMON_H */ -- cgit v1.2.3 From 1fcb16674e37e434efe68ec3e142229f35b6b9e1 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 5 Sep 2024 15:09:36 -0400 Subject: nfs_common: factor out nfs4_errtbl and nfs4_stat_to_errno Common nfs4_stat_to_errno() is used by fs/nfs/nfs4xdr.c and will be used by fs/nfs/localio.c Signed-off-by: Mike Snitzer Reviewed-by: Jeff Layton Reviewed-by: NeilBrown Signed-off-by: Anna Schumaker --- fs/nfs/nfs4xdr.c | 67 ---------------------------------------------- fs/nfs_common/common.c | 67 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/nfs_common.h | 1 + 3 files changed, 68 insertions(+), 67 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index b61ffe6b9851..18d268029b1c 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -65,7 +65,6 @@ #define NFSDBG_FACILITY NFSDBG_XDR struct compound_hdr; -static int nfs4_stat_to_errno(int); static void encode_layoutget(struct xdr_stream *xdr, const struct nfs4_layoutget_args *args, struct compound_hdr *hdr); @@ -7619,72 +7618,6 @@ int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, return 0; } -/* - * We need to translate between nfs status return values and - * the local errno values which may not be the same. - */ -static struct { - int stat; - int errno; -} nfs_errtbl[] = { - { NFS4_OK, 0 }, - { NFS4ERR_PERM, -EPERM }, - { NFS4ERR_NOENT, -ENOENT }, - { NFS4ERR_IO, -errno_NFSERR_IO}, - { NFS4ERR_NXIO, -ENXIO }, - { NFS4ERR_ACCESS, -EACCES }, - { NFS4ERR_EXIST, -EEXIST }, - { NFS4ERR_XDEV, -EXDEV }, - { NFS4ERR_NOTDIR, -ENOTDIR }, - { NFS4ERR_ISDIR, -EISDIR }, - { NFS4ERR_INVAL, -EINVAL }, - { NFS4ERR_FBIG, -EFBIG }, - { NFS4ERR_NOSPC, -ENOSPC }, - { NFS4ERR_ROFS, -EROFS }, - { NFS4ERR_MLINK, -EMLINK }, - { NFS4ERR_NAMETOOLONG, -ENAMETOOLONG }, - { NFS4ERR_NOTEMPTY, -ENOTEMPTY }, - { NFS4ERR_DQUOT, -EDQUOT }, - { NFS4ERR_STALE, -ESTALE }, - { NFS4ERR_BADHANDLE, -EBADHANDLE }, - { NFS4ERR_BAD_COOKIE, -EBADCOOKIE }, - { NFS4ERR_NOTSUPP, -ENOTSUPP }, - { NFS4ERR_TOOSMALL, -ETOOSMALL }, - { NFS4ERR_SERVERFAULT, -EREMOTEIO }, - { NFS4ERR_BADTYPE, -EBADTYPE }, - { NFS4ERR_LOCKED, -EAGAIN }, - { NFS4ERR_SYMLINK, -ELOOP }, - { NFS4ERR_OP_ILLEGAL, -EOPNOTSUPP }, - { NFS4ERR_DEADLOCK, -EDEADLK }, - { NFS4ERR_NOXATTR, -ENODATA }, - { NFS4ERR_XATTR2BIG, -E2BIG }, - { -1, -EIO } -}; - -/* - * Convert an NFS error code to a local one. - * This one is used jointly by NFSv2 and NFSv3. - */ -static int -nfs4_stat_to_errno(int stat) -{ - int i; - for (i = 0; nfs_errtbl[i].stat != -1; i++) { - if (nfs_errtbl[i].stat == stat) - return nfs_errtbl[i].errno; - } - if (stat <= 10000 || stat > 10100) { - /* The server is looney tunes. */ - return -EREMOTEIO; - } - /* If we cannot translate the error, the recovery routines should - * handle it. - * Note: remaining NFSv4 error codes have values > 10000, so should - * not conflict with native Linux error codes. - */ - return -stat; -} - #ifdef CONFIG_NFS_V4_2 #include "nfs42xdr.c" #endif /* CONFIG_NFS_V4_2 */ diff --git a/fs/nfs_common/common.c b/fs/nfs_common/common.c index a4ee95da2174..34a115176f97 100644 --- a/fs/nfs_common/common.c +++ b/fs/nfs_common/common.c @@ -2,6 +2,7 @@ #include #include +#include /* * We need to translate between nfs status return values and @@ -65,3 +66,69 @@ int nfs_stat_to_errno(enum nfs_stat status) return nfs_errtbl[i].errno; } EXPORT_SYMBOL_GPL(nfs_stat_to_errno); + +/* + * We need to translate between nfs v4 status return values and + * the local errno values which may not be the same. + */ +static const struct { + int stat; + int errno; +} nfs4_errtbl[] = { + { NFS4_OK, 0 }, + { NFS4ERR_PERM, -EPERM }, + { NFS4ERR_NOENT, -ENOENT }, + { NFS4ERR_IO, -errno_NFSERR_IO}, + { NFS4ERR_NXIO, -ENXIO }, + { NFS4ERR_ACCESS, -EACCES }, + { NFS4ERR_EXIST, -EEXIST }, + { NFS4ERR_XDEV, -EXDEV }, + { NFS4ERR_NOTDIR, -ENOTDIR }, + { NFS4ERR_ISDIR, -EISDIR }, + { NFS4ERR_INVAL, -EINVAL }, + { NFS4ERR_FBIG, -EFBIG }, + { NFS4ERR_NOSPC, -ENOSPC }, + { NFS4ERR_ROFS, -EROFS }, + { NFS4ERR_MLINK, -EMLINK }, + { NFS4ERR_NAMETOOLONG, -ENAMETOOLONG }, + { NFS4ERR_NOTEMPTY, -ENOTEMPTY }, + { NFS4ERR_DQUOT, -EDQUOT }, + { NFS4ERR_STALE, -ESTALE }, + { NFS4ERR_BADHANDLE, -EBADHANDLE }, + { NFS4ERR_BAD_COOKIE, -EBADCOOKIE }, + { NFS4ERR_NOTSUPP, -ENOTSUPP }, + { NFS4ERR_TOOSMALL, -ETOOSMALL }, + { NFS4ERR_SERVERFAULT, -EREMOTEIO }, + { NFS4ERR_BADTYPE, -EBADTYPE }, + { NFS4ERR_LOCKED, -EAGAIN }, + { NFS4ERR_SYMLINK, -ELOOP }, + { NFS4ERR_OP_ILLEGAL, -EOPNOTSUPP }, + { NFS4ERR_DEADLOCK, -EDEADLK }, + { NFS4ERR_NOXATTR, -ENODATA }, + { NFS4ERR_XATTR2BIG, -E2BIG }, + { -1, -EIO } +}; + +/* + * Convert an NFS error code to a local one. + * This one is used by NFSv4. + */ +int nfs4_stat_to_errno(int stat) +{ + int i; + for (i = 0; nfs4_errtbl[i].stat != -1; i++) { + if (nfs4_errtbl[i].stat == stat) + return nfs4_errtbl[i].errno; + } + if (stat <= 10000 || stat > 10100) { + /* The server is looney tunes. */ + return -EREMOTEIO; + } + /* If we cannot translate the error, the recovery routines should + * handle it. + * Note: remaining NFSv4 error codes have values > 10000, so should + * not conflict with native Linux error codes. + */ + return -stat; +} +EXPORT_SYMBOL_GPL(nfs4_stat_to_errno); diff --git a/include/linux/nfs_common.h b/include/linux/nfs_common.h index 3395c4a4d372..5fc02df88252 100644 --- a/include/linux/nfs_common.h +++ b/include/linux/nfs_common.h @@ -12,5 +12,6 @@ #define errno_NFSERR_IO EIO int nfs_stat_to_errno(enum nfs_stat status); +int nfs4_stat_to_errno(int stat); #endif /* _LINUX_NFS_COMMON_H */ -- cgit v1.2.3 From 1545e488b1f908b10f6dff0c278c6b7a37122de8 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 5 Sep 2024 15:09:37 -0400 Subject: nfs: factor out {encode,decode}_opaque_fixed to nfs_xdr.h Eliminates duplicate functions in various files to allow for additional callers. Signed-off-by: Mike Snitzer Reviewed-by: NeilBrown Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- fs/nfs/flexfilelayout/flexfilelayout.c | 6 ------ fs/nfs/nfs4xdr.c | 13 ------------- include/linux/nfs_xdr.h | 20 +++++++++++++++++++- 3 files changed, 19 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 39ba9f4208aa..d4d551ffea7b 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -2086,12 +2086,6 @@ static int ff_layout_encode_ioerr(struct xdr_stream *xdr, return ff_layout_encode_ds_ioerr(xdr, &ff_args->errors); } -static void -encode_opaque_fixed(struct xdr_stream *xdr, const void *buf, size_t len) -{ - WARN_ON_ONCE(xdr_stream_encode_opaque_fixed(xdr, buf, len) < 0); -} - static void ff_layout_encode_ff_iostat_head(struct xdr_stream *xdr, const nfs4_stateid *stateid, diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 18d268029b1c..1a909408cf5a 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -972,11 +972,6 @@ static __be32 *reserve_space(struct xdr_stream *xdr, size_t nbytes) return p; } -static void encode_opaque_fixed(struct xdr_stream *xdr, const void *buf, size_t len) -{ - WARN_ON_ONCE(xdr_stream_encode_opaque_fixed(xdr, buf, len) < 0); -} - static void encode_string(struct xdr_stream *xdr, unsigned int len, const char *str) { WARN_ON_ONCE(xdr_stream_encode_opaque(xdr, str, len) < 0); @@ -4406,14 +4401,6 @@ static int decode_access(struct xdr_stream *xdr, u32 *supported, u32 *access) return 0; } -static int decode_opaque_fixed(struct xdr_stream *xdr, void *buf, size_t len) -{ - ssize_t ret = xdr_stream_decode_opaque_fixed(xdr, buf, len); - if (unlikely(ret < 0)) - return -EIO; - return 0; -} - static int decode_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid) { return decode_opaque_fixed(xdr, stateid, NFS4_STATEID_SIZE); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 96ba04ab24f3..12d8e47bc5a3 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1853,6 +1853,24 @@ struct nfs_rpc_ops { void (*disable_swap)(struct inode *inode); }; +/* + * Helper functions used by NFS client and/or server + */ +static inline void encode_opaque_fixed(struct xdr_stream *xdr, + const void *buf, size_t len) +{ + WARN_ON_ONCE(xdr_stream_encode_opaque_fixed(xdr, buf, len) < 0); +} + +static inline int decode_opaque_fixed(struct xdr_stream *xdr, + void *buf, size_t len) +{ + ssize_t ret = xdr_stream_decode_opaque_fixed(xdr, buf, len); + if (unlikely(ret < 0)) + return -EIO; + return 0; +} + /* * Function vectors etc. for the NFS client */ @@ -1866,4 +1884,4 @@ extern const struct rpc_version nfs_version4; extern const struct rpc_version nfsacl_version3; extern const struct rpc_program nfsacl_program; -#endif +#endif /* _LINUX_NFS_XDR_H */ -- cgit v1.2.3 From 199f2128741077087a2ab33889a6868830465033 Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Thu, 5 Sep 2024 15:09:46 -0400 Subject: SUNRPC: add svcauth_map_clnt_to_svc_cred_local Add new funtion svcauth_map_clnt_to_svc_cred_local which maps a generic cred to a svc_cred suitable for use in nfsd. This is needed by the localio code to map nfs client creds to nfs server credentials. Following from net/sunrpc/auth_unix.c:unx_marshal() it is clear that ->fsuid and ->fsgid must be used (rather than ->uid and ->gid). In addition, these uid and gid must be translated with from_kuid_munged() so local client uses correct uid and gid when acting as local server. Jeff Layton noted: This is where the magic happens. Since we're working in kuid_t/kgid_t, we don't need to worry about further idmapping. Suggested-by: NeilBrown # to approximate unx_marshal() Signed-off-by: Weston Andros Adamson Signed-off-by: Trond Myklebust Co-developed-by: Mike Snitzer Signed-off-by: Mike Snitzer Reviewed-by: Chuck Lever Reviewed-by: Jeff Layton Reviewed-by: NeilBrown Signed-off-by: Anna Schumaker --- include/linux/sunrpc/svcauth.h | 5 +++++ net/sunrpc/svcauth.c | 28 ++++++++++++++++++++++++++++ 2 files changed, 33 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h index 63cf6fb26dcc..2e111153f7cd 100644 --- a/include/linux/sunrpc/svcauth.h +++ b/include/linux/sunrpc/svcauth.h @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -157,6 +158,10 @@ extern enum svc_auth_status svc_set_client(struct svc_rqst *rqstp); extern int svc_auth_register(rpc_authflavor_t flavor, struct auth_ops *aops); extern void svc_auth_unregister(rpc_authflavor_t flavor); +extern void svcauth_map_clnt_to_svc_cred_local(struct rpc_clnt *clnt, + const struct cred *, + struct svc_cred *); + extern struct auth_domain *unix_domain_find(char *name); extern void auth_domain_put(struct auth_domain *item); extern struct auth_domain *auth_domain_lookup(char *name, struct auth_domain *new); diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c index 93d9e949e265..55b4d2874188 100644 --- a/net/sunrpc/svcauth.c +++ b/net/sunrpc/svcauth.c @@ -18,6 +18,7 @@ #include #include #include +#include #include @@ -175,6 +176,33 @@ rpc_authflavor_t svc_auth_flavor(struct svc_rqst *rqstp) } EXPORT_SYMBOL_GPL(svc_auth_flavor); +/** + * svcauth_map_clnt_to_svc_cred_local - maps a generic cred + * to a svc_cred suitable for use in nfsd. + * @clnt: rpc_clnt associated with nfs client + * @cred: generic cred associated with nfs client + * @svc: returned svc_cred that is suitable for use in nfsd + */ +void svcauth_map_clnt_to_svc_cred_local(struct rpc_clnt *clnt, + const struct cred *cred, + struct svc_cred *svc) +{ + struct user_namespace *userns = clnt->cl_cred ? + clnt->cl_cred->user_ns : &init_user_ns; + + memset(svc, 0, sizeof(struct svc_cred)); + + svc->cr_uid = KUIDT_INIT(from_kuid_munged(userns, cred->fsuid)); + svc->cr_gid = KGIDT_INIT(from_kgid_munged(userns, cred->fsgid)); + svc->cr_flavor = clnt->cl_auth->au_flavor; + if (cred->group_info) + svc->cr_group_info = get_group_info(cred->group_info); + /* These aren't relevant for local (network is bypassed) */ + svc->cr_principal = NULL; + svc->cr_gss_mech = NULL; +} +EXPORT_SYMBOL_GPL(svcauth_map_clnt_to_svc_cred_local); + /************************************************** * 'auth_domains' are stored in a hash table indexed by name. * When the last reference to an 'auth_domain' is dropped, -- cgit v1.2.3 From 86ab08beb3f07f6e51922a8b8f662a5ec7012d35 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 5 Sep 2024 15:09:47 -0400 Subject: SUNRPC: replace program list with program array A service created with svc_create_pooled() can be given a linked list of programs and all of these will be served. Using a linked list makes it cumbersome when there are several programs that can be optionally selected with CONFIG settings. After this patch is applied, API consumers must use only svc_create_pooled() when creating an RPC service that listens for more than one RPC program. Signed-off-by: NeilBrown Signed-off-by: Mike Snitzer Acked-by: Chuck Lever Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- fs/nfsd/nfsctl.c | 2 +- fs/nfsd/nfsd.h | 2 +- fs/nfsd/nfssvc.c | 38 +++++++++++++------------- include/linux/sunrpc/svc.h | 7 +++-- net/sunrpc/svc.c | 68 ++++++++++++++++++++++++++-------------------- net/sunrpc/svc_xprt.c | 2 +- net/sunrpc/svcauth_unix.c | 3 +- 7 files changed, 67 insertions(+), 55 deletions(-) (limited to 'include/linux') diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 1c9e5b4bcb0a..64c1b4d649bc 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -2246,7 +2246,7 @@ static __net_init int nfsd_net_init(struct net *net) if (retval) goto out_repcache_error; memset(&nn->nfsd_svcstats, 0, sizeof(nn->nfsd_svcstats)); - nn->nfsd_svcstats.program = &nfsd_program; + nn->nfsd_svcstats.program = &nfsd_programs[0]; for (i = 0; i < sizeof(nn->nfsd_versions); i++) nn->nfsd_versions[i] = nfsd_support_version(i); for (i = 0; i < sizeof(nn->nfsd4_minorversions); i++) diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 4ccbf014a2c7..b0d3e82d6dcd 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -85,7 +85,7 @@ struct nfsd_genl_rqstp { u32 rq_opnum[NFSD_MAX_OPS_PER_COMPOUND]; }; -extern struct svc_program nfsd_program; +extern struct svc_program nfsd_programs[]; extern const struct svc_version nfsd_version2, nfsd_version3, nfsd_version4; extern struct mutex nfsd_mutex; extern spinlock_t nfsd_drc_lock; diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 307e365798f5..fa34de5e59bd 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -35,7 +35,6 @@ #define NFSDDBG_FACILITY NFSDDBG_SVC atomic_t nfsd_th_cnt = ATOMIC_INIT(0); -extern struct svc_program nfsd_program; static int nfsd(void *vrqstp); #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) static int nfsd_acl_rpcbind_set(struct net *, @@ -90,20 +89,9 @@ static const struct svc_version *nfsd_acl_version[] = { # endif }; -#define NFSD_ACL_MINVERS 2 +#define NFSD_ACL_MINVERS 2 #define NFSD_ACL_NRVERS ARRAY_SIZE(nfsd_acl_version) -static struct svc_program nfsd_acl_program = { - .pg_prog = NFS_ACL_PROGRAM, - .pg_nvers = NFSD_ACL_NRVERS, - .pg_vers = nfsd_acl_version, - .pg_name = "nfsacl", - .pg_class = "nfsd", - .pg_authenticate = &svc_set_client, - .pg_init_request = nfsd_acl_init_request, - .pg_rpcbind_set = nfsd_acl_rpcbind_set, -}; - #endif /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */ static const struct svc_version *nfsd_version[NFSD_MAXVERS+1] = { @@ -116,18 +104,29 @@ static const struct svc_version *nfsd_version[NFSD_MAXVERS+1] = { #endif }; -struct svc_program nfsd_program = { -#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) - .pg_next = &nfsd_acl_program, -#endif +struct svc_program nfsd_programs[] = { + { .pg_prog = NFS_PROGRAM, /* program number */ .pg_nvers = NFSD_MAXVERS+1, /* nr of entries in nfsd_version */ .pg_vers = nfsd_version, /* version table */ .pg_name = "nfsd", /* program name */ .pg_class = "nfsd", /* authentication class */ - .pg_authenticate = &svc_set_client, /* export authentication */ + .pg_authenticate = svc_set_client, /* export authentication */ .pg_init_request = nfsd_init_request, .pg_rpcbind_set = nfsd_rpcbind_set, + }, +#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) + { + .pg_prog = NFS_ACL_PROGRAM, + .pg_nvers = NFSD_ACL_NRVERS, + .pg_vers = nfsd_acl_version, + .pg_name = "nfsacl", + .pg_class = "nfsd", + .pg_authenticate = svc_set_client, + .pg_init_request = nfsd_acl_init_request, + .pg_rpcbind_set = nfsd_acl_rpcbind_set, + }, +#endif /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */ }; bool nfsd_support_version(int vers) @@ -641,7 +640,8 @@ int nfsd_create_serv(struct net *net) if (nfsd_max_blksize == 0) nfsd_max_blksize = nfsd_get_default_max_blksize(); nfsd_reset_versions(nn); - serv = svc_create_pooled(&nfsd_program, &nn->nfsd_svcstats, + serv = svc_create_pooled(nfsd_programs, ARRAY_SIZE(nfsd_programs), + &nn->nfsd_svcstats, nfsd_max_blksize, nfsd); if (serv == NULL) return -ENOMEM; diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index c419a61f60e5..e68fecf6eab5 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -67,9 +67,10 @@ enum { * We currently do not support more than one RPC program per daemon. */ struct svc_serv { - struct svc_program * sv_program; /* RPC program */ + struct svc_program * sv_programs; /* RPC programs */ struct svc_stat * sv_stats; /* RPC statistics */ spinlock_t sv_lock; + unsigned int sv_nprogs; /* Number of sv_programs */ unsigned int sv_nrthreads; /* # of server threads */ unsigned int sv_maxconn; /* max connections allowed or * '0' causing max to be based @@ -360,10 +361,9 @@ struct svc_process_info { }; /* - * List of RPC programs on the same transport endpoint + * RPC program - an array of these can use the same transport endpoint */ struct svc_program { - struct svc_program * pg_next; /* other programs (same xprt) */ u32 pg_prog; /* program number */ unsigned int pg_lovers; /* lowest version */ unsigned int pg_hivers; /* highest version */ @@ -441,6 +441,7 @@ bool svc_rqst_replace_page(struct svc_rqst *rqstp, void svc_rqst_release_pages(struct svc_rqst *rqstp); void svc_exit_thread(struct svc_rqst *); struct svc_serv * svc_create_pooled(struct svc_program *prog, + unsigned int nprog, struct svc_stat *stats, unsigned int bufsize, int (*threadfn)(void *data)); diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 9aff845196ce..7e7f4e0390c7 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -440,10 +440,11 @@ EXPORT_SYMBOL_GPL(svc_rpcb_cleanup); static int svc_uses_rpcbind(struct svc_serv *serv) { - struct svc_program *progp; - unsigned int i; + unsigned int p, i; + + for (p = 0; p < serv->sv_nprogs; p++) { + struct svc_program *progp = &serv->sv_programs[p]; - for (progp = serv->sv_program; progp; progp = progp->pg_next) { for (i = 0; i < progp->pg_nvers; i++) { if (progp->pg_vers[i] == NULL) continue; @@ -480,7 +481,7 @@ __svc_init_bc(struct svc_serv *serv) * Create an RPC service */ static struct svc_serv * -__svc_create(struct svc_program *prog, struct svc_stat *stats, +__svc_create(struct svc_program *prog, int nprogs, struct svc_stat *stats, unsigned int bufsize, int npools, int (*threadfn)(void *data)) { struct svc_serv *serv; @@ -491,7 +492,8 @@ __svc_create(struct svc_program *prog, struct svc_stat *stats, if (!(serv = kzalloc(sizeof(*serv), GFP_KERNEL))) return NULL; serv->sv_name = prog->pg_name; - serv->sv_program = prog; + serv->sv_programs = prog; + serv->sv_nprogs = nprogs; serv->sv_stats = stats; if (bufsize > RPCSVC_MAXPAYLOAD) bufsize = RPCSVC_MAXPAYLOAD; @@ -499,17 +501,18 @@ __svc_create(struct svc_program *prog, struct svc_stat *stats, serv->sv_max_mesg = roundup(serv->sv_max_payload + PAGE_SIZE, PAGE_SIZE); serv->sv_threadfn = threadfn; xdrsize = 0; - while (prog) { - prog->pg_lovers = prog->pg_nvers-1; - for (vers=0; verspg_nvers ; vers++) - if (prog->pg_vers[vers]) { - prog->pg_hivers = vers; - if (prog->pg_lovers > vers) - prog->pg_lovers = vers; - if (prog->pg_vers[vers]->vs_xdrsize > xdrsize) - xdrsize = prog->pg_vers[vers]->vs_xdrsize; + for (i = 0; i < nprogs; i++) { + struct svc_program *progp = &prog[i]; + + progp->pg_lovers = progp->pg_nvers-1; + for (vers = 0; vers < progp->pg_nvers ; vers++) + if (progp->pg_vers[vers]) { + progp->pg_hivers = vers; + if (progp->pg_lovers > vers) + progp->pg_lovers = vers; + if (progp->pg_vers[vers]->vs_xdrsize > xdrsize) + xdrsize = progp->pg_vers[vers]->vs_xdrsize; } - prog = prog->pg_next; } serv->sv_xdrsize = xdrsize; INIT_LIST_HEAD(&serv->sv_tempsocks); @@ -558,13 +561,14 @@ __svc_create(struct svc_program *prog, struct svc_stat *stats, struct svc_serv *svc_create(struct svc_program *prog, unsigned int bufsize, int (*threadfn)(void *data)) { - return __svc_create(prog, NULL, bufsize, 1, threadfn); + return __svc_create(prog, 1, NULL, bufsize, 1, threadfn); } EXPORT_SYMBOL_GPL(svc_create); /** * svc_create_pooled - Create an RPC service with pooled threads - * @prog: the RPC program the new service will handle + * @prog: Array of RPC programs the new service will handle + * @nprogs: Number of programs in the array * @stats: the stats struct if desired * @bufsize: maximum message size for @prog * @threadfn: a function to service RPC requests for @prog @@ -572,6 +576,7 @@ EXPORT_SYMBOL_GPL(svc_create); * Returns an instantiated struct svc_serv object or NULL. */ struct svc_serv *svc_create_pooled(struct svc_program *prog, + unsigned int nprogs, struct svc_stat *stats, unsigned int bufsize, int (*threadfn)(void *data)) @@ -579,7 +584,7 @@ struct svc_serv *svc_create_pooled(struct svc_program *prog, struct svc_serv *serv; unsigned int npools = svc_pool_map_get(); - serv = __svc_create(prog, stats, bufsize, npools, threadfn); + serv = __svc_create(prog, nprogs, stats, bufsize, npools, threadfn); if (!serv) goto out_err; serv->sv_is_pooled = true; @@ -602,16 +607,16 @@ svc_destroy(struct svc_serv **servp) *servp = NULL; - dprintk("svc: svc_destroy(%s)\n", serv->sv_program->pg_name); + dprintk("svc: svc_destroy(%s)\n", serv->sv_programs->pg_name); timer_shutdown_sync(&serv->sv_temptimer); /* * Remaining transports at this point are not expected. */ WARN_ONCE(!list_empty(&serv->sv_permsocks), - "SVC: permsocks remain for %s\n", serv->sv_program->pg_name); + "SVC: permsocks remain for %s\n", serv->sv_programs->pg_name); WARN_ONCE(!list_empty(&serv->sv_tempsocks), - "SVC: tempsocks remain for %s\n", serv->sv_program->pg_name); + "SVC: tempsocks remain for %s\n", serv->sv_programs->pg_name); cache_clean_deferred(serv); @@ -1148,15 +1153,16 @@ int svc_register(const struct svc_serv *serv, struct net *net, const int family, const unsigned short proto, const unsigned short port) { - struct svc_program *progp; - unsigned int i; + unsigned int p, i; int error = 0; WARN_ON_ONCE(proto == 0 && port == 0); if (proto == 0 && port == 0) return -EINVAL; - for (progp = serv->sv_program; progp; progp = progp->pg_next) { + for (p = 0; p < serv->sv_nprogs; p++) { + struct svc_program *progp = &serv->sv_programs[p]; + for (i = 0; i < progp->pg_nvers; i++) { error = progp->pg_rpcbind_set(net, progp, i, @@ -1208,13 +1214,14 @@ static void __svc_unregister(struct net *net, const u32 program, const u32 versi static void svc_unregister(const struct svc_serv *serv, struct net *net) { struct sighand_struct *sighand; - struct svc_program *progp; unsigned long flags; - unsigned int i; + unsigned int p, i; clear_thread_flag(TIF_SIGPENDING); - for (progp = serv->sv_program; progp; progp = progp->pg_next) { + for (p = 0; p < serv->sv_nprogs; p++) { + struct svc_program *progp = &serv->sv_programs[p]; + for (i = 0; i < progp->pg_nvers; i++) { if (progp->pg_vers[i] == NULL) continue; @@ -1320,7 +1327,7 @@ svc_process_common(struct svc_rqst *rqstp) struct svc_process_info process; enum svc_auth_status auth_res; unsigned int aoffset; - int rc; + int pr, rc; __be32 *p; /* Will be turned off only when NFSv4 Sessions are used */ @@ -1344,9 +1351,12 @@ svc_process_common(struct svc_rqst *rqstp) rqstp->rq_vers = be32_to_cpup(p++); rqstp->rq_proc = be32_to_cpup(p); - for (progp = serv->sv_program; progp; progp = progp->pg_next) + for (pr = 0; pr < serv->sv_nprogs; pr++) { + progp = &serv->sv_programs[pr]; + if (rqstp->rq_prog == progp->pg_prog) break; + } /* * Decode auth data, and add verifier to reply buffer. diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 53ebc719ff5a..43c57124de52 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -268,7 +268,7 @@ static int _svc_xprt_create(struct svc_serv *serv, const char *xprt_name, spin_unlock(&svc_xprt_class_lock); newxprt = xcl->xcl_ops->xpo_create(serv, net, sap, len, flags); if (IS_ERR(newxprt)) { - trace_svc_xprt_create_err(serv->sv_program->pg_name, + trace_svc_xprt_create_err(serv->sv_programs->pg_name, xcl->xcl_name, sap, len, newxprt); module_put(xcl->xcl_owner); diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 04b45588ae6f..8ca98b146ec8 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -697,7 +697,8 @@ svcauth_unix_set_client(struct svc_rqst *rqstp) rqstp->rq_auth_stat = rpc_autherr_badcred; ipm = ip_map_cached_get(xprt); if (ipm == NULL) - ipm = __ip_map_lookup(sn->ip_map_cache, rqstp->rq_server->sv_program->pg_class, + ipm = __ip_map_lookup(sn->ip_map_cache, + rqstp->rq_server->sv_programs->pg_class, &sin6->sin6_addr); if (ipm == NULL) -- cgit v1.2.3 From 2a33a85be45178198245e1f656e6224c899895e4 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 5 Sep 2024 15:09:48 -0400 Subject: nfs_common: add NFS LOCALIO auxiliary protocol enablement fs/nfs_common/nfslocalio.c provides interfaces that enable an NFS client to generate a nonce (single-use UUID) and associated nfs_uuid_t struct, register it with nfs_common for subsequent lookup and verification by the NFS server and if matched the NFS server populates members in the nfs_uuid_t struct. nfs_common's nfs_uuids list is the basis for localio enablement, as such it has members that point to nfsd memory for direct use by the client (e.g. 'net' is the server's network namespace, through it the client can access nn->nfsd_serv). This commit also provides the base nfs_uuid_t interfaces to allow proper net namespace refcounting for the LOCALIO use case. CONFIG_NFS_LOCALIO controls the nfs_common, NFS server and NFS client enablement for LOCALIO. If both NFS_FS=m and NFSD=m then NFS_COMMON_LOCALIO_SUPPORT=m and nfs_localio.ko is built (and provides nfs_common's LOCALIO support). # lsmod | grep nfs_localio nfs_localio 12288 2 nfsd,nfs sunrpc 745472 35 nfs_localio,nfsd,auth_rpcgss,lockd,nfsv3,nfs Signed-off-by: Mike Snitzer Co-developed-by: NeilBrown Signed-off-by: NeilBrown Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- fs/Kconfig | 23 +++++++++ fs/nfs_common/Makefile | 3 ++ fs/nfs_common/nfslocalio.c | 116 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/nfslocalio.h | 36 ++++++++++++++ 4 files changed, 178 insertions(+) create mode 100644 fs/nfs_common/nfslocalio.c create mode 100644 include/linux/nfslocalio.h (limited to 'include/linux') diff --git a/fs/Kconfig b/fs/Kconfig index a46b0cbc4d8f..24d4e4b419d1 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -382,6 +382,29 @@ config NFS_COMMON depends on NFSD || NFS_FS || LOCKD default y +config NFS_COMMON_LOCALIO_SUPPORT + tristate + default n + default y if NFSD=y || NFS_FS=y + default m if NFSD=m && NFS_FS=m + select SUNRPC + +config NFS_LOCALIO + bool "NFS client and server support for LOCALIO auxiliary protocol" + depends on NFSD && NFS_FS + select NFS_COMMON_LOCALIO_SUPPORT + default n + help + Some NFS servers support an auxiliary NFS LOCALIO protocol + that is not an official part of the NFS protocol. + + This option enables support for the LOCALIO protocol in the + kernel's NFS server and client. Enable this to permit local + NFS clients to bypass the network when issuing reads and + writes to the local NFS server. + + If unsure, say N. + config NFS_V4_2_SSC_HELPER bool default y if NFS_V4_2 diff --git a/fs/nfs_common/Makefile b/fs/nfs_common/Makefile index e58b01bb8dda..a5e54809701e 100644 --- a/fs/nfs_common/Makefile +++ b/fs/nfs_common/Makefile @@ -6,6 +6,9 @@ obj-$(CONFIG_NFS_ACL_SUPPORT) += nfs_acl.o nfs_acl-objs := nfsacl.o +obj-$(CONFIG_NFS_COMMON_LOCALIO_SUPPORT) += nfs_localio.o +nfs_localio-objs := nfslocalio.o + obj-$(CONFIG_GRACE_PERIOD) += grace.o obj-$(CONFIG_NFS_V4_2_SSC_HELPER) += nfs_ssc.o diff --git a/fs/nfs_common/nfslocalio.c b/fs/nfs_common/nfslocalio.c new file mode 100644 index 000000000000..f0bff023bb5e --- /dev/null +++ b/fs/nfs_common/nfslocalio.c @@ -0,0 +1,116 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2024 Mike Snitzer + * Copyright (C) 2024 NeilBrown + */ + +#include +#include +#include +#include + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("NFS localio protocol bypass support"); + +static DEFINE_SPINLOCK(nfs_uuid_lock); + +/* + * Global list of nfs_uuid_t instances + * that is protected by nfs_uuid_lock. + */ +static LIST_HEAD(nfs_uuids); + +void nfs_uuid_begin(nfs_uuid_t *nfs_uuid) +{ + nfs_uuid->net = NULL; + nfs_uuid->dom = NULL; + uuid_gen(&nfs_uuid->uuid); + + spin_lock(&nfs_uuid_lock); + list_add_tail_rcu(&nfs_uuid->list, &nfs_uuids); + spin_unlock(&nfs_uuid_lock); +} +EXPORT_SYMBOL_GPL(nfs_uuid_begin); + +void nfs_uuid_end(nfs_uuid_t *nfs_uuid) +{ + if (nfs_uuid->net == NULL) { + spin_lock(&nfs_uuid_lock); + list_del_init(&nfs_uuid->list); + spin_unlock(&nfs_uuid_lock); + } +} +EXPORT_SYMBOL_GPL(nfs_uuid_end); + +static nfs_uuid_t * nfs_uuid_lookup_locked(const uuid_t *uuid) +{ + nfs_uuid_t *nfs_uuid; + + list_for_each_entry(nfs_uuid, &nfs_uuids, list) + if (uuid_equal(&nfs_uuid->uuid, uuid)) + return nfs_uuid; + + return NULL; +} + +static struct module *nfsd_mod; + +void nfs_uuid_is_local(const uuid_t *uuid, struct list_head *list, + struct net *net, struct auth_domain *dom, + struct module *mod) +{ + nfs_uuid_t *nfs_uuid; + + spin_lock(&nfs_uuid_lock); + nfs_uuid = nfs_uuid_lookup_locked(uuid); + if (nfs_uuid) { + kref_get(&dom->ref); + nfs_uuid->dom = dom; + /* + * We don't hold a ref on the net, but instead put + * ourselves on a list so the net pointer can be + * invalidated. + */ + list_move(&nfs_uuid->list, list); + nfs_uuid->net = net; + + __module_get(mod); + nfsd_mod = mod; + } + spin_unlock(&nfs_uuid_lock); +} +EXPORT_SYMBOL_GPL(nfs_uuid_is_local); + +static void nfs_uuid_put_locked(nfs_uuid_t *nfs_uuid) +{ + if (nfs_uuid->net) { + module_put(nfsd_mod); + nfs_uuid->net = NULL; + } + if (nfs_uuid->dom) { + auth_domain_put(nfs_uuid->dom); + nfs_uuid->dom = NULL; + } + list_del_init(&nfs_uuid->list); +} + +void nfs_uuid_invalidate_clients(struct list_head *list) +{ + nfs_uuid_t *nfs_uuid, *tmp; + + spin_lock(&nfs_uuid_lock); + list_for_each_entry_safe(nfs_uuid, tmp, list, list) + nfs_uuid_put_locked(nfs_uuid); + spin_unlock(&nfs_uuid_lock); +} +EXPORT_SYMBOL_GPL(nfs_uuid_invalidate_clients); + +void nfs_uuid_invalidate_one_client(nfs_uuid_t *nfs_uuid) +{ + if (nfs_uuid->net) { + spin_lock(&nfs_uuid_lock); + nfs_uuid_put_locked(nfs_uuid); + spin_unlock(&nfs_uuid_lock); + } +} +EXPORT_SYMBOL_GPL(nfs_uuid_invalidate_one_client); diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h new file mode 100644 index 000000000000..4165ff8390c1 --- /dev/null +++ b/include/linux/nfslocalio.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2024 Mike Snitzer + * Copyright (C) 2024 NeilBrown + */ +#ifndef __LINUX_NFSLOCALIO_H +#define __LINUX_NFSLOCALIO_H + +#include +#include +#include +#include +#include +#include + +/* + * Useful to allow a client to negotiate if localio + * possible with its server. + * + * See Documentation/filesystems/nfs/localio.rst for more detail. + */ +typedef struct { + uuid_t uuid; + struct list_head list; + struct net *net; /* nfsd's network namespace */ + struct auth_domain *dom; /* auth_domain for localio */ +} nfs_uuid_t; + +void nfs_uuid_begin(nfs_uuid_t *); +void nfs_uuid_end(nfs_uuid_t *); +void nfs_uuid_is_local(const uuid_t *, struct list_head *, + struct net *, struct auth_domain *, struct module *); +void nfs_uuid_invalidate_clients(struct list_head *list); +void nfs_uuid_invalidate_one_client(nfs_uuid_t *nfs_uuid); + +#endif /* __LINUX_NFSLOCALIO_H */ -- cgit v1.2.3 From a61e147e6be6e763d9c6dec8061d2893c0bb3423 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 5 Sep 2024 15:09:49 -0400 Subject: nfs_common: prepare for the NFS client to use nfsd_file for LOCALIO The next commit will introduce nfsd_open_local_fh() which returns an nfsd_file structure. This commit exposes LOCALIO's required NFSD symbols to the NFS client: - Make nfsd_open_local_fh() symbol and other required NFSD symbols available to NFS in a global 'nfs_to' nfsd_localio_operations struct (global access suggested by Trond, nfsd_localio_operations suggested by NeilBrown). The next commit will also introduce nfsd_localio_ops_init() that init_nfsd() will call to initialize 'nfs_to'. - Introduce nfsd_file_file() that provides access to nfsd_file's backing file. Keeps nfsd_file structure opaque to NFS client (as suggested by Jeff Layton). - Introduce nfsd_file_put_local() that will put the reference to the nfsd_file's associated nn->nfsd_serv and then put the reference to the nfsd_file (as suggested by NeilBrown). Suggested-by: Trond Myklebust # nfs_to Suggested-by: NeilBrown # nfsd_localio_operations Suggested-by: Jeff Layton # nfsd_file_file Signed-off-by: Mike Snitzer Reviewed-by: NeilBrown Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- fs/nfs_common/nfslocalio.c | 25 ++++++++++++++++++++++++- fs/nfsd/filecache.c | 28 ++++++++++++++++++++++++++++ fs/nfsd/filecache.h | 2 ++ fs/nfsd/nfssvc.c | 1 + include/linux/nfslocalio.h | 27 ++++++++++++++++++++++++++- 5 files changed, 81 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs_common/nfslocalio.c b/fs/nfs_common/nfslocalio.c index f0bff023bb5e..f61761ad19b1 100644 --- a/fs/nfs_common/nfslocalio.c +++ b/fs/nfs_common/nfslocalio.c @@ -72,7 +72,7 @@ void nfs_uuid_is_local(const uuid_t *uuid, struct list_head *list, * invalidated. */ list_move(&nfs_uuid->list, list); - nfs_uuid->net = net; + rcu_assign_pointer(nfs_uuid->net, net); __module_get(mod); nfsd_mod = mod; @@ -114,3 +114,26 @@ void nfs_uuid_invalidate_one_client(nfs_uuid_t *nfs_uuid) } } EXPORT_SYMBOL_GPL(nfs_uuid_invalidate_one_client); + +/* + * The NFS LOCALIO code needs to call into NFSD using various symbols, + * but cannot be statically linked, because that will make the NFS + * module always depend on the NFSD module. + * + * 'nfs_to' provides NFS access to NFSD functions needed for LOCALIO, + * its lifetime is tightly coupled to the NFSD module and will always + * be available to NFS LOCALIO because any successful client<->server + * LOCALIO handshake results in a reference on the NFSD module (above), + * so NFS implicitly holds a reference to the NFSD module and its + * functions in the 'nfs_to' nfsd_localio_operations cannot disappear. + * + * If the last NFS client using LOCALIO disconnects (and its reference + * on NFSD dropped) then NFSD could be unloaded, resulting in 'nfs_to' + * functions being invalid pointers. But if NFSD isn't loaded then NFS + * will not be able to handshake with NFSD and will have no cause to + * try to call 'nfs_to' function pointers. If/when NFSD is reloaded it + * will reinitialize the 'nfs_to' function pointers and make LOCALIO + * possible. + */ +const struct nfsd_localio_operations *nfs_to; +EXPORT_SYMBOL_GPL(nfs_to); diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index caeffc43ca4b..414b5bf738df 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -390,6 +390,34 @@ nfsd_file_put(struct nfsd_file *nf) nfsd_file_free(nf); } +/** + * nfsd_file_put_local - put the reference to nfsd_file and local nfsd_serv + * @nf: nfsd_file of which to put the references + * + * First put the reference of the nfsd_file and then put the + * reference to the associated nn->nfsd_serv. + */ +void +nfsd_file_put_local(struct nfsd_file *nf) +{ + struct net *net = nf->nf_net; + + nfsd_file_put(nf); + nfsd_serv_put(net); +} + +/** + * nfsd_file_file - get the backing file of an nfsd_file + * @nf: nfsd_file of which to access the backing file. + * + * Return backing file for @nf. + */ +struct file * +nfsd_file_file(struct nfsd_file *nf) +{ + return nf->nf_file; +} + static void nfsd_file_dispose_list(struct list_head *dispose) { diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h index 26ada78b8c1e..cadf3c2689c4 100644 --- a/fs/nfsd/filecache.h +++ b/fs/nfsd/filecache.h @@ -55,7 +55,9 @@ void nfsd_file_cache_shutdown(void); int nfsd_file_cache_start_net(struct net *net); void nfsd_file_cache_shutdown_net(struct net *net); void nfsd_file_put(struct nfsd_file *nf); +void nfsd_file_put_local(struct nfsd_file *nf); struct nfsd_file *nfsd_file_get(struct nfsd_file *nf); +struct file *nfsd_file_file(struct nfsd_file *nf); void nfsd_file_close_inode_sync(struct inode *inode); void nfsd_file_net_dispose(struct nfsd_net *nn); bool nfsd_file_is_cached(struct inode *inode); diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index fa34de5e59bd..f9a6d888ac9d 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h index 4165ff8390c1..1a39d7d727bd 100644 --- a/include/linux/nfslocalio.h +++ b/include/linux/nfslocalio.h @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -22,7 +23,7 @@ typedef struct { uuid_t uuid; struct list_head list; - struct net *net; /* nfsd's network namespace */ + struct net __rcu *net; /* nfsd's network namespace */ struct auth_domain *dom; /* auth_domain for localio */ } nfs_uuid_t; @@ -33,4 +34,28 @@ void nfs_uuid_is_local(const uuid_t *, struct list_head *, void nfs_uuid_invalidate_clients(struct list_head *list); void nfs_uuid_invalidate_one_client(nfs_uuid_t *nfs_uuid); +struct nfsd_file; + +/* localio needs to map filehandle -> struct nfsd_file */ +extern struct nfsd_file * +nfsd_open_local_fh(struct net *, struct auth_domain *, struct rpc_clnt *, + const struct cred *, const struct nfs_fh *, + const fmode_t) __must_hold(rcu); + +struct nfsd_localio_operations { + bool (*nfsd_serv_try_get)(struct net *); + void (*nfsd_serv_put)(struct net *); + struct nfsd_file *(*nfsd_open_local_fh)(struct net *, + struct auth_domain *, + struct rpc_clnt *, + const struct cred *, + const struct nfs_fh *, + const fmode_t); + void (*nfsd_file_put_local)(struct nfsd_file *); + struct file *(*nfsd_file_file)(struct nfsd_file *); +} ____cacheline_aligned; + +extern void nfsd_localio_ops_init(void); +extern const struct nfsd_localio_operations *nfs_to; + #endif /* __LINUX_NFSLOCALIO_H */ -- cgit v1.2.3 From fa4983862e506d395acc1b8d14dbebf63acc2e82 Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Thu, 5 Sep 2024 15:09:50 -0400 Subject: nfsd: add LOCALIO support Add server support for bypassing NFS for localhost reads, writes, and commits. This is only useful when both the client and server are running on the same host. If nfsd_open_local_fh() fails then the NFS client will both retry and fallback to normal network-based read, write and commit operations if localio is no longer supported. Care is taken to ensure the same NFS security mechanisms are used (authentication, etc) regardless of whether localio or regular NFS access is used. The auth_domain established as part of the traditional NFS client access to the NFS server is also used for localio. Store auth_domain for localio in nfsd_uuid_t and transfer it to the client if it is local to the server. Relative to containers, localio gives the client access to the network namespace the server has. This is required to allow the client to access the server's per-namespace nfsd_net struct. This commit also introduces the use of NFSD's percpu_ref to interlock nfsd_destroy_serv and nfsd_open_local_fh, to ensure nn->nfsd_serv is not destroyed while in use by nfsd_open_local_fh and other LOCALIO client code. CONFIG_NFS_LOCALIO enables NFS server support for LOCALIO. Signed-off-by: Weston Andros Adamson Signed-off-by: Trond Myklebust Co-developed-by: Mike Snitzer Signed-off-by: Mike Snitzer Co-developed-by: NeilBrown Signed-off-by: NeilBrown Reviewed-by: Jeff Layton Acked-by: Chuck Lever Signed-off-by: Anna Schumaker --- fs/nfsd/Makefile | 1 + fs/nfsd/filecache.c | 2 +- fs/nfsd/localio.c | 92 ++++++++++++++++++++++++++++++++++++++++++++++ fs/nfsd/netns.h | 4 ++ fs/nfsd/nfsctl.c | 25 ++++++++++++- fs/nfsd/trace.h | 3 +- fs/nfsd/vfs.h | 2 + include/linux/nfslocalio.h | 8 ++++ 8 files changed, 134 insertions(+), 3 deletions(-) create mode 100644 fs/nfsd/localio.c (limited to 'include/linux') diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile index b8736a82e57c..18cbd3fa7691 100644 --- a/fs/nfsd/Makefile +++ b/fs/nfsd/Makefile @@ -23,3 +23,4 @@ nfsd-$(CONFIG_NFSD_PNFS) += nfs4layouts.o nfsd-$(CONFIG_NFSD_BLOCKLAYOUT) += blocklayout.o blocklayoutxdr.o nfsd-$(CONFIG_NFSD_SCSILAYOUT) += blocklayout.o blocklayoutxdr.o nfsd-$(CONFIG_NFSD_FLEXFILELAYOUT) += flexfilelayout.o flexfilelayoutxdr.o +nfsd-$(CONFIG_NFS_LOCALIO) += localio.o diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 414b5bf738df..19bb88c7eebd 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -52,7 +52,7 @@ #define NFSD_FILE_CACHE_UP (0) /* We only care about NFSD_MAY_READ/WRITE for this cache */ -#define NFSD_FILE_MAY_MASK (NFSD_MAY_READ|NFSD_MAY_WRITE) +#define NFSD_FILE_MAY_MASK (NFSD_MAY_READ|NFSD_MAY_WRITE|NFSD_MAY_LOCALIO) static DEFINE_PER_CPU(unsigned long, nfsd_file_cache_hits); static DEFINE_PER_CPU(unsigned long, nfsd_file_acquisitions); diff --git a/fs/nfsd/localio.c b/fs/nfsd/localio.c new file mode 100644 index 000000000000..9fa10a80b2da --- /dev/null +++ b/fs/nfsd/localio.c @@ -0,0 +1,92 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * NFS server support for local clients to bypass network stack + * + * Copyright (C) 2014 Weston Andros Adamson + * Copyright (C) 2019 Trond Myklebust + * Copyright (C) 2024 Mike Snitzer + * Copyright (C) 2024 NeilBrown + */ + +#include +#include +#include +#include +#include +#include +#include + +#include "nfsd.h" +#include "vfs.h" +#include "netns.h" +#include "filecache.h" + +static const struct nfsd_localio_operations nfsd_localio_ops = { + .nfsd_serv_try_get = nfsd_serv_try_get, + .nfsd_serv_put = nfsd_serv_put, + .nfsd_open_local_fh = nfsd_open_local_fh, + .nfsd_file_put_local = nfsd_file_put_local, + .nfsd_file_file = nfsd_file_file, +}; + +void nfsd_localio_ops_init(void) +{ + nfs_to = &nfsd_localio_ops; +} + +/** + * nfsd_open_local_fh - lookup a local filehandle @nfs_fh and map to nfsd_file + * + * @net: 'struct net' to get the proper nfsd_net required for LOCALIO access + * @dom: 'struct auth_domain' required for LOCALIO access + * @rpc_clnt: rpc_clnt that the client established + * @cred: cred that the client established + * @nfs_fh: filehandle to lookup + * @fmode: fmode_t to use for open + * + * This function maps a local fh to a path on a local filesystem. + * This is useful when the nfs client has the local server mounted - it can + * avoid all the NFS overhead with reads, writes and commits. + * + * On successful return, returned nfsd_file will have its nf_net member + * set. Caller (NFS client) is responsible for calling nfsd_serv_put and + * nfsd_file_put (via nfs_to->nfsd_file_put_local). + */ +struct nfsd_file * +nfsd_open_local_fh(struct net *net, struct auth_domain *dom, + struct rpc_clnt *rpc_clnt, const struct cred *cred, + const struct nfs_fh *nfs_fh, const fmode_t fmode) +{ + int mayflags = NFSD_MAY_LOCALIO; + struct svc_cred rq_cred; + struct svc_fh fh; + struct nfsd_file *localio; + __be32 beres; + + if (nfs_fh->size > NFS4_FHSIZE) + return ERR_PTR(-EINVAL); + + /* nfs_fh -> svc_fh */ + fh_init(&fh, NFS4_FHSIZE); + fh.fh_handle.fh_size = nfs_fh->size; + memcpy(fh.fh_handle.fh_raw, nfs_fh->data, nfs_fh->size); + + if (fmode & FMODE_READ) + mayflags |= NFSD_MAY_READ; + if (fmode & FMODE_WRITE) + mayflags |= NFSD_MAY_WRITE; + + svcauth_map_clnt_to_svc_cred_local(rpc_clnt, cred, &rq_cred); + + beres = nfsd_file_acquire_local(net, &rq_cred, dom, + &fh, mayflags, &localio); + if (beres) + localio = ERR_PTR(nfs_stat_to_errno(be32_to_cpu(beres))); + + fh_put(&fh); + if (rq_cred.cr_group_info) + put_group_info(rq_cred.cr_group_info); + + return localio; +} +EXPORT_SYMBOL_GPL(nfsd_open_local_fh); diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index a228b9d6a6e1..26f7b34d1a03 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -217,6 +217,10 @@ struct nfsd_net { /* last time an admin-revoke happened for NFSv4.0 */ time64_t nfs40_last_revoke; +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + /* Local clients to be invalidated when net is shut down */ + struct list_head local_clients; +#endif }; /* Simple check to find out if a given net was properly initialized */ diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 64c1b4d649bc..3adbc05ebaac 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -18,6 +18,7 @@ #include #include #include +#include #include "idmap.h" #include "nfsd.h" @@ -2257,7 +2258,9 @@ static __net_init int nfsd_net_init(struct net *net) get_random_bytes(&nn->siphash_key, sizeof(nn->siphash_key)); seqlock_init(&nn->writeverf_lock); nfsd_proc_stat_init(net); - +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + INIT_LIST_HEAD(&nn->local_clients); +#endif return 0; out_repcache_error: @@ -2268,6 +2271,22 @@ out_export_error: return retval; } +#if IS_ENABLED(CONFIG_NFS_LOCALIO) +/** + * nfsd_net_pre_exit - Disconnect localio clients from net namespace + * @net: a network namespace that is about to be destroyed + * + * This invalidated ->net pointers held by localio clients + * while they can still safely access nn->counter. + */ +static __net_exit void nfsd_net_pre_exit(struct net *net) +{ + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + + nfs_uuid_invalidate_clients(&nn->local_clients); +} +#endif + /** * nfsd_net_exit - Release the nfsd_net portion of a net namespace * @net: a network namespace that is about to be destroyed @@ -2285,6 +2304,9 @@ static __net_exit void nfsd_net_exit(struct net *net) static struct pernet_operations nfsd_net_ops = { .init = nfsd_net_init, +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + .pre_exit = nfsd_net_pre_exit, +#endif .exit = nfsd_net_exit, .id = &nfsd_net_id, .size = sizeof(struct nfsd_net), @@ -2322,6 +2344,7 @@ static int __init init_nfsd(void) retval = genl_register_family(&nfsd_nl_family); if (retval) goto out_free_all; + nfsd_localio_ops_init(); return 0; out_free_all: diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index e339d04ff32f..c625966cfcf3 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -86,7 +86,8 @@ DEFINE_NFSD_XDR_ERR_EVENT(cant_encode); { NFSD_MAY_NOT_BREAK_LEASE, "NOT_BREAK_LEASE" }, \ { NFSD_MAY_BYPASS_GSS, "BYPASS_GSS" }, \ { NFSD_MAY_READ_IF_EXEC, "READ_IF_EXEC" }, \ - { NFSD_MAY_64BIT_COOKIE, "64BIT_COOKIE" }) + { NFSD_MAY_64BIT_COOKIE, "64BIT_COOKIE" }, \ + { NFSD_MAY_LOCALIO, "LOCALIO" }) TRACE_EVENT(nfsd_compound, TP_PROTO( diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index 01947561d375..3ff146522556 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -33,6 +33,8 @@ #define NFSD_MAY_64BIT_COOKIE 0x1000 /* 64 bit readdir cookies for >= NFSv3 */ +#define NFSD_MAY_LOCALIO 0x2000 /* for tracing, reflects when localio used */ + #define NFSD_MAY_CREATE (NFSD_MAY_EXEC|NFSD_MAY_WRITE) #define NFSD_MAY_REMOVE (NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC) diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h index 1a39d7d727bd..546f46b4e46f 100644 --- a/include/linux/nfslocalio.h +++ b/include/linux/nfslocalio.h @@ -6,6 +6,8 @@ #ifndef __LINUX_NFSLOCALIO_H #define __LINUX_NFSLOCALIO_H +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + #include #include #include @@ -58,4 +60,10 @@ struct nfsd_localio_operations { extern void nfsd_localio_ops_init(void); extern const struct nfsd_localio_operations *nfs_to; +#else /* CONFIG_NFS_LOCALIO */ +static inline void nfsd_localio_ops_init(void) +{ +} +#endif /* CONFIG_NFS_LOCALIO */ + #endif /* __LINUX_NFSLOCALIO_H */ -- cgit v1.2.3 From 946af9b3a0e7571c01447107d5e8968401e659ba Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 5 Sep 2024 15:09:51 -0400 Subject: nfsd: implement server support for NFS_LOCALIO_PROGRAM The LOCALIO auxiliary RPC protocol consists of a single "UUID_IS_LOCAL" RPC method that allows the Linux NFS client to verify the local Linux NFS server can see the nonce (single-use UUID) the client generated and made available in nfs_common. The server expects this protocol to use the same transport as NFS and NFSACL for its RPCs. This protocol isn't part of an IETF standard, nor does it need to be considering it is Linux-to-Linux auxiliary RPC protocol that amounts to an implementation detail. The UUID_IS_LOCAL method encodes the client generated uuid_t in terms of the fixed UUID_SIZE (16 bytes). The fixed size opaque encode and decode XDR methods are used instead of the less efficient variable sized methods. The RPC program number for the NFS_LOCALIO_PROGRAM is 400122 (as assigned by IANA, see https://www.iana.org/assignments/rpc-program-numbers/ ): Linux Kernel Organization 400122 nfslocalio Signed-off-by: Mike Snitzer [neilb: factored out and simplified single localio protocol] Co-developed-by: NeilBrown Signed-off-by: NeilBrown Acked-by: Chuck Lever Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- fs/nfsd/localio.c | 77 +++++++++++++++++++++++++++++++++++++++++++++++++++++ fs/nfsd/nfsd.h | 4 +++ fs/nfsd/nfssvc.c | 23 +++++++++++++++- include/linux/nfs.h | 7 +++++ 4 files changed, 110 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/nfsd/localio.c b/fs/nfsd/localio.c index 9fa10a80b2da..291e9c69cae4 100644 --- a/fs/nfsd/localio.c +++ b/fs/nfsd/localio.c @@ -14,12 +14,15 @@ #include #include #include +#include +#include #include #include "nfsd.h" #include "vfs.h" #include "netns.h" #include "filecache.h" +#include "cache.h" static const struct nfsd_localio_operations nfsd_localio_ops = { .nfsd_serv_try_get = nfsd_serv_try_get, @@ -90,3 +93,77 @@ nfsd_open_local_fh(struct net *net, struct auth_domain *dom, return localio; } EXPORT_SYMBOL_GPL(nfsd_open_local_fh); + +/* + * UUID_IS_LOCAL XDR functions + */ + +static __be32 localio_proc_null(struct svc_rqst *rqstp) +{ + return rpc_success; +} + +struct localio_uuidarg { + uuid_t uuid; +}; + +static __be32 localio_proc_uuid_is_local(struct svc_rqst *rqstp) +{ + struct localio_uuidarg *argp = rqstp->rq_argp; + struct net *net = SVC_NET(rqstp); + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + + nfs_uuid_is_local(&argp->uuid, &nn->local_clients, + net, rqstp->rq_client, THIS_MODULE); + + return rpc_success; +} + +static bool localio_decode_uuidarg(struct svc_rqst *rqstp, + struct xdr_stream *xdr) +{ + struct localio_uuidarg *argp = rqstp->rq_argp; + u8 uuid[UUID_SIZE]; + + if (decode_opaque_fixed(xdr, uuid, UUID_SIZE)) + return false; + import_uuid(&argp->uuid, uuid); + + return true; +} + +static const struct svc_procedure localio_procedures1[] = { + [LOCALIOPROC_NULL] = { + .pc_func = localio_proc_null, + .pc_decode = nfssvc_decode_voidarg, + .pc_encode = nfssvc_encode_voidres, + .pc_argsize = sizeof(struct nfsd_voidargs), + .pc_ressize = sizeof(struct nfsd_voidres), + .pc_cachetype = RC_NOCACHE, + .pc_xdrressize = 0, + .pc_name = "NULL", + }, + [LOCALIOPROC_UUID_IS_LOCAL] = { + .pc_func = localio_proc_uuid_is_local, + .pc_decode = localio_decode_uuidarg, + .pc_encode = nfssvc_encode_voidres, + .pc_argsize = sizeof(struct localio_uuidarg), + .pc_argzero = sizeof(struct localio_uuidarg), + .pc_ressize = sizeof(struct nfsd_voidres), + .pc_cachetype = RC_NOCACHE, + .pc_name = "UUID_IS_LOCAL", + }, +}; + +#define LOCALIO_NR_PROCEDURES ARRAY_SIZE(localio_procedures1) +static DEFINE_PER_CPU_ALIGNED(unsigned long, + localio_count[LOCALIO_NR_PROCEDURES]); +const struct svc_version localio_version1 = { + .vs_vers = 1, + .vs_nproc = LOCALIO_NR_PROCEDURES, + .vs_proc = localio_procedures1, + .vs_dispatch = nfsd_dispatch, + .vs_count = localio_count, + .vs_xdrsize = XDR_QUADLEN(UUID_SIZE), + .vs_hidden = true, +}; diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index b0d3e82d6dcd..4b56ba1e8e48 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -146,6 +146,10 @@ extern const struct svc_version nfsd_acl_version3; #endif #endif +#if IS_ENABLED(CONFIG_NFS_LOCALIO) +extern const struct svc_version localio_version1; +#endif + struct nfsd_net; enum vers_op {NFSD_SET, NFSD_CLEAR, NFSD_TEST, NFSD_AVAIL }; diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index f9a6d888ac9d..e236135ddc63 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -80,6 +80,15 @@ DEFINE_SPINLOCK(nfsd_drc_lock); unsigned long nfsd_drc_max_mem; unsigned long nfsd_drc_mem_used; +#if IS_ENABLED(CONFIG_NFS_LOCALIO) +static const struct svc_version *localio_versions[] = { + [1] = &localio_version1, +}; + +#define NFSD_LOCALIO_NRVERS ARRAY_SIZE(localio_versions) + +#endif /* CONFIG_NFS_LOCALIO */ + #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) static const struct svc_version *nfsd_acl_version[] = { # if defined(CONFIG_NFSD_V2_ACL) @@ -128,6 +137,18 @@ struct svc_program nfsd_programs[] = { .pg_rpcbind_set = nfsd_acl_rpcbind_set, }, #endif /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */ +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + { + .pg_prog = NFS_LOCALIO_PROGRAM, + .pg_nvers = NFSD_LOCALIO_NRVERS, + .pg_vers = localio_versions, + .pg_name = "nfslocalio", + .pg_class = "nfsd", + .pg_authenticate = svc_set_client, + .pg_init_request = svc_generic_init_request, + .pg_rpcbind_set = svc_generic_rpcbind_set, + } +#endif /* CONFIG_NFS_LOCALIO */ }; bool nfsd_support_version(int vers) @@ -949,7 +970,7 @@ nfsd(void *vrqstp) } /** - * nfsd_dispatch - Process an NFS or NFSACL Request + * nfsd_dispatch - Process an NFS or NFSACL or LOCALIO Request * @rqstp: incoming request * * This RPC dispatcher integrates the NFS server's duplicate reply cache. diff --git a/include/linux/nfs.h b/include/linux/nfs.h index ceb70a926b95..73da75908d95 100644 --- a/include/linux/nfs.h +++ b/include/linux/nfs.h @@ -13,6 +13,13 @@ #include #include +/* The LOCALIO program is entirely private to Linux and is + * NOT part of the uapi. + */ +#define NFS_LOCALIO_PROGRAM 400122 +#define LOCALIOPROC_NULL 0 +#define LOCALIOPROC_UUID_IS_LOCAL 1 + /* * This is the kernel NFS client file handle representation */ -- cgit v1.2.3 From df24c483e28f7f9a421afde15d0497e61bc2d3ea Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 5 Sep 2024 15:09:52 -0400 Subject: nfs: pass struct nfsd_file to nfs_init_pgio and nfs_init_commit The nfsd_file will be passed, in future commits, by callers that enable LOCALIO support (for both regular NFS and pNFS IO). [Derived from patch authored by Weston Andros Adamson, but switched from passing struct file to struct nfsd_file] Signed-off-by: Mike Snitzer Reviewed-by: NeilBrown Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- fs/nfs/filelayout/filelayout.c | 6 +++--- fs/nfs/flexfilelayout/flexfilelayout.c | 6 +++--- fs/nfs/internal.h | 7 +++++-- fs/nfs/pagelist.c | 6 ++++-- fs/nfs/pnfs_nfs.c | 2 +- fs/nfs/write.c | 5 +++-- include/linux/nfslocalio.h | 5 +++-- 7 files changed, 22 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index b6e9aeaf4ce2..d39a1f58e18d 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -488,7 +488,7 @@ filelayout_read_pagelist(struct nfs_pgio_header *hdr) /* Perform an asynchronous read to ds */ nfs_initiate_pgio(ds_clnt, hdr, hdr->cred, NFS_PROTO(hdr->inode), &filelayout_read_call_ops, - 0, RPC_TASK_SOFTCONN); + 0, RPC_TASK_SOFTCONN, NULL); return PNFS_ATTEMPTED; } @@ -530,7 +530,7 @@ filelayout_write_pagelist(struct nfs_pgio_header *hdr, int sync) /* Perform an asynchronous write */ nfs_initiate_pgio(ds_clnt, hdr, hdr->cred, NFS_PROTO(hdr->inode), &filelayout_write_call_ops, - sync, RPC_TASK_SOFTCONN); + sync, RPC_TASK_SOFTCONN, NULL); return PNFS_ATTEMPTED; } @@ -1011,7 +1011,7 @@ static int filelayout_initiate_commit(struct nfs_commit_data *data, int how) data->args.fh = fh; return nfs_initiate_commit(ds_clnt, data, NFS_PROTO(data->inode), &filelayout_commit_call_ops, how, - RPC_TASK_SOFTCONN); + RPC_TASK_SOFTCONN, NULL); out_err: pnfs_generic_prepare_to_resend_writes(data); pnfs_generic_commit_release(data); diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index d4d551ffea7b..01ee52551a63 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1806,7 +1806,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr) nfs_initiate_pgio(ds_clnt, hdr, ds_cred, ds->ds_clp->rpc_ops, vers == 3 ? &ff_layout_read_call_ops_v3 : &ff_layout_read_call_ops_v4, - 0, RPC_TASK_SOFTCONN); + 0, RPC_TASK_SOFTCONN, NULL); put_cred(ds_cred); return PNFS_ATTEMPTED; @@ -1874,7 +1874,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync) nfs_initiate_pgio(ds_clnt, hdr, ds_cred, ds->ds_clp->rpc_ops, vers == 3 ? &ff_layout_write_call_ops_v3 : &ff_layout_write_call_ops_v4, - sync, RPC_TASK_SOFTCONN); + sync, RPC_TASK_SOFTCONN, NULL); put_cred(ds_cred); return PNFS_ATTEMPTED; @@ -1949,7 +1949,7 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how) ret = nfs_initiate_commit(ds_clnt, data, ds->ds_clp->rpc_ops, vers == 3 ? &ff_layout_commit_call_ops_v3 : &ff_layout_commit_call_ops_v4, - how, RPC_TASK_SOFTCONN); + how, RPC_TASK_SOFTCONN, NULL); put_cred(ds_cred); return ret; out_err: diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index b3dc7c84eef9..f0af96a665d2 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -9,6 +9,7 @@ #include #include #include +#include #include #define NFS_SB_MASK (SB_RDONLY|SB_NOSUID|SB_NODEV|SB_NOEXEC|SB_SYNCHRONOUS) @@ -308,7 +309,8 @@ void nfs_pgio_header_free(struct nfs_pgio_header *); int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *); int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr, const struct cred *cred, const struct nfs_rpc_ops *rpc_ops, - const struct rpc_call_ops *call_ops, int how, int flags); + const struct rpc_call_ops *call_ops, int how, int flags, + struct nfsd_file *localio); void nfs_free_request(struct nfs_page *req); struct nfs_pgio_mirror * nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc); @@ -527,7 +529,8 @@ extern int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data, const struct nfs_rpc_ops *nfs_ops, const struct rpc_call_ops *call_ops, - int how, int flags); + int how, int flags, + struct nfsd_file *localio); extern void nfs_init_commit(struct nfs_commit_data *data, struct list_head *head, struct pnfs_layout_segment *lseg, diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 04124f226665..50f3d6c9ac2a 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -731,7 +731,8 @@ static void nfs_pgio_prepare(struct rpc_task *task, void *calldata) int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr, const struct cred *cred, const struct nfs_rpc_ops *rpc_ops, - const struct rpc_call_ops *call_ops, int how, int flags) + const struct rpc_call_ops *call_ops, int how, int flags, + struct nfsd_file *localio) { struct rpc_task *task; struct rpc_message msg = { @@ -961,7 +962,8 @@ static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc) NFS_PROTO(hdr->inode), desc->pg_rpc_callops, desc->pg_ioflags, - RPC_TASK_CRED_NOREF | task_flags); + RPC_TASK_CRED_NOREF | task_flags, + NULL); } return ret; } diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index a74ee69a2fa6..dbef837e871a 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -490,7 +490,7 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages, nfs_initiate_commit(NFS_CLIENT(inode), data, NFS_PROTO(data->inode), data->mds_ops, how, - RPC_TASK_CRED_NOREF); + RPC_TASK_CRED_NOREF, NULL); } else { nfs_init_commit(data, NULL, data->lseg, cinfo); initiate_commit(data, how); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 61b580bcb356..ef72922263bb 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1664,7 +1664,8 @@ EXPORT_SYMBOL_GPL(nfs_commitdata_release); int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data, const struct nfs_rpc_ops *nfs_ops, const struct rpc_call_ops *call_ops, - int how, int flags) + int how, int flags, + struct nfsd_file *localio) { struct rpc_task *task; int priority = flush_task_priority(how); @@ -1810,7 +1811,7 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how, task_flags = RPC_TASK_MOVEABLE; return nfs_initiate_commit(NFS_CLIENT(inode), data, NFS_PROTO(inode), data->mds_ops, how, - RPC_TASK_CRED_NOREF | task_flags); + RPC_TASK_CRED_NOREF | task_flags, NULL); } /* diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h index 546f46b4e46f..2c4e0fd9da6b 100644 --- a/include/linux/nfslocalio.h +++ b/include/linux/nfslocalio.h @@ -6,6 +6,9 @@ #ifndef __LINUX_NFSLOCALIO_H #define __LINUX_NFSLOCALIO_H +/* nfsd_file structure is purposely kept opaque to NFS client */ +struct nfsd_file; + #if IS_ENABLED(CONFIG_NFS_LOCALIO) #include @@ -36,8 +39,6 @@ void nfs_uuid_is_local(const uuid_t *, struct list_head *, void nfs_uuid_invalidate_clients(struct list_head *list); void nfs_uuid_invalidate_one_client(nfs_uuid_t *nfs_uuid); -struct nfsd_file; - /* localio needs to map filehandle -> struct nfsd_file */ extern struct nfsd_file * nfsd_open_local_fh(struct net *, struct auth_domain *, struct rpc_clnt *, -- cgit v1.2.3 From 70ba381e1a431245c137ed597ec6a05991c79bd9 Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Thu, 5 Sep 2024 15:09:53 -0400 Subject: nfs: add LOCALIO support Add client support for bypassing NFS for localhost reads, writes, and commits. This is only useful when the client and the server are running on the same host. nfs_local_probe() is stubbed out, later commits will enable client and server handshake via a Linux-only LOCALIO auxiliary RPC protocol. This has dynamic binding with the nfsd module (via nfs_localio module which is part of nfs_common). LOCALIO will only work if nfsd is already loaded. The "localio_enabled" nfs kernel module parameter can be used to disable and enable the ability to use LOCALIO support. CONFIG_NFS_LOCALIO enables NFS client support for LOCALIO. Lastly, LOCALIO uses an nfsd_file to initiate all IO. To make proper use of nfsd_file (and nfsd's filecache) its lifetime (duration before nfsd_file_put is called) must extend until after commit, read and write operations. So rather than immediately drop the nfsd_file reference in nfs_local_open_fh(), that doesn't happen until nfs_local_pgio_release() for read/write and not until nfs_local_release_commit_data() for commit. The same applies to the reference held on nfsd's nn->nfsd_serv. Both objects' lifetimes and associated references are managed through calls to nfs_to->nfsd_file_put_local(). Signed-off-by: Weston Andros Adamson Signed-off-by: Trond Myklebust Co-developed-by: Mike Snitzer Signed-off-by: Mike Snitzer Signed-off-by: NeilBrown # nfs_open_local_fh Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- fs/nfs/Makefile | 1 + fs/nfs/client.c | 11 + fs/nfs/internal.h | 45 ++++ fs/nfs/localio.c | 600 +++++++++++++++++++++++++++++++++++++++++++++ fs/nfs/nfstrace.h | 61 +++++ fs/nfs/pagelist.c | 4 + fs/nfs/write.c | 3 + fs/nfs_common/nfslocalio.c | 33 +++ include/linux/nfs.h | 2 + include/linux/nfs_fs_sb.h | 9 + include/linux/nfslocalio.h | 4 + 11 files changed, 773 insertions(+) create mode 100644 fs/nfs/localio.c (limited to 'include/linux') diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile index 5f6db37f461e..9fb2f2cac87e 100644 --- a/fs/nfs/Makefile +++ b/fs/nfs/Makefile @@ -13,6 +13,7 @@ nfs-y := client.o dir.o file.o getroot.o inode.o super.o \ nfs-$(CONFIG_ROOT_NFS) += nfsroot.o nfs-$(CONFIG_SYSCTL) += sysctl.o nfs-$(CONFIG_NFS_FSCACHE) += fscache.o +nfs-$(CONFIG_NFS_LOCALIO) += localio.o obj-$(CONFIG_NFS_V2) += nfsv2.o nfsv2-y := nfs2super.o proc.o nfs2xdr.o diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 3fea7aa1366f..c09ef6088451 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -178,6 +178,14 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init) clp->cl_max_connect = cl_init->max_connect ? cl_init->max_connect : 1; clp->cl_net = get_net(cl_init->net); +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + seqlock_init(&clp->cl_boot_lock); + ktime_get_real_ts64(&clp->cl_nfssvc_boot); + clp->cl_uuid.net = NULL; + clp->cl_uuid.dom = NULL; + spin_lock_init(&clp->cl_localio_lock); +#endif /* CONFIG_NFS_LOCALIO */ + clp->cl_principal = "*"; clp->cl_xprtsec = cl_init->xprtsec; return clp; @@ -233,6 +241,8 @@ static void pnfs_init_server(struct nfs_server *server) */ void nfs_free_client(struct nfs_client *clp) { + nfs_local_disable(clp); + /* -EIO all pending I/O */ if (!IS_ERR(clp->cl_rpcclient)) rpc_shutdown_client(clp->cl_rpcclient); @@ -424,6 +434,7 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *cl_init) list_add_tail(&new->cl_share_link, &nn->nfs_client_list); spin_unlock(&nn->nfs_client_lock); + nfs_local_probe(new); return rpc_ops->init_client(new, cl_init); } diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index f0af96a665d2..534c1ac16c57 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -451,6 +451,51 @@ extern void nfs_set_cache_invalid(struct inode *inode, unsigned long flags); extern bool nfs_check_cache_invalid(struct inode *, unsigned long); extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode); +#if IS_ENABLED(CONFIG_NFS_LOCALIO) +/* localio.c */ +extern void nfs_local_disable(struct nfs_client *); +extern void nfs_local_probe(struct nfs_client *); +extern struct nfsd_file *nfs_local_open_fh(struct nfs_client *, + const struct cred *, + struct nfs_fh *, + const fmode_t); +extern int nfs_local_doio(struct nfs_client *, + struct nfsd_file *, + struct nfs_pgio_header *, + const struct rpc_call_ops *); +extern int nfs_local_commit(struct nfsd_file *, + struct nfs_commit_data *, + const struct rpc_call_ops *, int); +extern bool nfs_server_is_local(const struct nfs_client *clp); + +#else /* CONFIG_NFS_LOCALIO */ +static inline void nfs_local_disable(struct nfs_client *clp) {} +static inline void nfs_local_probe(struct nfs_client *clp) {} +static inline struct nfsd_file * +nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred, + struct nfs_fh *fh, const fmode_t mode) +{ + return NULL; +} +static inline int nfs_local_doio(struct nfs_client *clp, + struct nfsd_file *localio, + struct nfs_pgio_header *hdr, + const struct rpc_call_ops *call_ops) +{ + return -EINVAL; +} +static inline int nfs_local_commit(struct nfsd_file *localio, + struct nfs_commit_data *data, + const struct rpc_call_ops *call_ops, int how) +{ + return -EINVAL; +} +static inline bool nfs_server_is_local(const struct nfs_client *clp) +{ + return false; +} +#endif /* CONFIG_NFS_LOCALIO */ + /* super.c */ extern const struct super_operations nfs_sops; bool nfs_auth_info_match(const struct nfs_auth_info *, rpc_authflavor_t); diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c new file mode 100644 index 000000000000..3cf4374de366 --- /dev/null +++ b/fs/nfs/localio.c @@ -0,0 +1,600 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * NFS client support for local clients to bypass network stack + * + * Copyright (C) 2014 Weston Andros Adamson + * Copyright (C) 2019 Trond Myklebust + * Copyright (C) 2024 Mike Snitzer + * Copyright (C) 2024 NeilBrown + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +#include "internal.h" +#include "pnfs.h" +#include "nfstrace.h" + +#define NFSDBG_FACILITY NFSDBG_VFS + +struct nfs_local_kiocb { + struct kiocb kiocb; + struct bio_vec *bvec; + struct nfs_pgio_header *hdr; + struct work_struct work; + struct nfsd_file *localio; +}; + +struct nfs_local_fsync_ctx { + struct nfsd_file *localio; + struct nfs_commit_data *data; + struct work_struct work; + struct kref kref; + struct completion *done; +}; +static void nfs_local_fsync_work(struct work_struct *work); + +static bool localio_enabled __read_mostly = true; +module_param(localio_enabled, bool, 0644); + +bool nfs_server_is_local(const struct nfs_client *clp) +{ + return test_bit(NFS_CS_LOCAL_IO, &clp->cl_flags) != 0 && + localio_enabled; +} +EXPORT_SYMBOL_GPL(nfs_server_is_local); + +/* + * nfs_local_enable - enable local i/o for an nfs_client + */ +static __maybe_unused void nfs_local_enable(struct nfs_client *clp) +{ + spin_lock(&clp->cl_localio_lock); + set_bit(NFS_CS_LOCAL_IO, &clp->cl_flags); + trace_nfs_local_enable(clp); + spin_unlock(&clp->cl_localio_lock); +} + +/* + * nfs_local_disable - disable local i/o for an nfs_client + */ +void nfs_local_disable(struct nfs_client *clp) +{ + spin_lock(&clp->cl_localio_lock); + if (test_and_clear_bit(NFS_CS_LOCAL_IO, &clp->cl_flags)) { + trace_nfs_local_disable(clp); + nfs_uuid_invalidate_one_client(&clp->cl_uuid); + } + spin_unlock(&clp->cl_localio_lock); +} + +/* + * nfs_local_probe - probe local i/o support for an nfs_server and nfs_client + */ +void nfs_local_probe(struct nfs_client *clp) +{ +} +EXPORT_SYMBOL_GPL(nfs_local_probe); + +/* + * nfs_local_open_fh - open a local filehandle in terms of nfsd_file + * + * Returns a pointer to a struct nfsd_file or NULL + */ +struct nfsd_file * +nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred, + struct nfs_fh *fh, const fmode_t mode) +{ + struct nfsd_file *localio; + int status; + + if (!nfs_server_is_local(clp)) + return NULL; + if (mode & ~(FMODE_READ | FMODE_WRITE)) + return NULL; + + localio = nfs_open_local_fh(&clp->cl_uuid, clp->cl_rpcclient, + cred, fh, mode); + if (IS_ERR(localio)) { + status = PTR_ERR(localio); + trace_nfs_local_open_fh(fh, mode, status); + switch (status) { + case -ENOMEM: + case -ENXIO: + case -ENOENT: + nfs_local_disable(clp); + } + return NULL; + } + return localio; +} +EXPORT_SYMBOL_GPL(nfs_local_open_fh); + +static struct bio_vec * +nfs_bvec_alloc_and_import_pagevec(struct page **pagevec, + unsigned int npages, gfp_t flags) +{ + struct bio_vec *bvec, *p; + + bvec = kmalloc_array(npages, sizeof(*bvec), flags); + if (bvec != NULL) { + for (p = bvec; npages > 0; p++, pagevec++, npages--) { + p->bv_page = *pagevec; + p->bv_len = PAGE_SIZE; + p->bv_offset = 0; + } + } + return bvec; +} + +static void +nfs_local_iocb_free(struct nfs_local_kiocb *iocb) +{ + kfree(iocb->bvec); + kfree(iocb); +} + +static struct nfs_local_kiocb * +nfs_local_iocb_alloc(struct nfs_pgio_header *hdr, + struct nfsd_file *localio, gfp_t flags) +{ + struct nfs_local_kiocb *iocb; + + iocb = kmalloc(sizeof(*iocb), flags); + if (iocb == NULL) + return NULL; + iocb->bvec = nfs_bvec_alloc_and_import_pagevec(hdr->page_array.pagevec, + hdr->page_array.npages, flags); + if (iocb->bvec == NULL) { + kfree(iocb); + return NULL; + } + init_sync_kiocb(&iocb->kiocb, nfs_to->nfsd_file_file(localio)); + iocb->kiocb.ki_pos = hdr->args.offset; + iocb->localio = localio; + iocb->hdr = hdr; + iocb->kiocb.ki_flags &= ~IOCB_APPEND; + return iocb; +} + +static void +nfs_local_iter_init(struct iov_iter *i, struct nfs_local_kiocb *iocb, int dir) +{ + struct nfs_pgio_header *hdr = iocb->hdr; + + iov_iter_bvec(i, dir, iocb->bvec, hdr->page_array.npages, + hdr->args.count + hdr->args.pgbase); + if (hdr->args.pgbase != 0) + iov_iter_advance(i, hdr->args.pgbase); +} + +static void +nfs_local_hdr_release(struct nfs_pgio_header *hdr, + const struct rpc_call_ops *call_ops) +{ + call_ops->rpc_call_done(&hdr->task, hdr); + call_ops->rpc_release(hdr); +} + +static void +nfs_local_pgio_init(struct nfs_pgio_header *hdr, + const struct rpc_call_ops *call_ops) +{ + hdr->task.tk_ops = call_ops; + if (!hdr->task.tk_start) + hdr->task.tk_start = ktime_get(); +} + +static void +nfs_local_pgio_done(struct nfs_pgio_header *hdr, long status) +{ + if (status >= 0) { + hdr->res.count = status; + hdr->res.op_status = NFS4_OK; + hdr->task.tk_status = 0; + } else { + hdr->res.op_status = nfs4_stat_to_errno(status); + hdr->task.tk_status = status; + } +} + +static void +nfs_local_pgio_release(struct nfs_local_kiocb *iocb) +{ + struct nfs_pgio_header *hdr = iocb->hdr; + + nfs_to->nfsd_file_put_local(iocb->localio); + nfs_local_iocb_free(iocb); + nfs_local_hdr_release(hdr, hdr->task.tk_ops); +} + +static void +nfs_local_read_done(struct nfs_local_kiocb *iocb, long status) +{ + struct nfs_pgio_header *hdr = iocb->hdr; + struct file *filp = iocb->kiocb.ki_filp; + + nfs_local_pgio_done(hdr, status); + + if (hdr->res.count != hdr->args.count || + hdr->args.offset + hdr->res.count >= i_size_read(file_inode(filp))) + hdr->res.eof = true; + + dprintk("%s: read %ld bytes eof %d.\n", __func__, + status > 0 ? status : 0, hdr->res.eof); +} + +static int +nfs_do_local_read(struct nfs_pgio_header *hdr, + struct nfsd_file *localio, + const struct rpc_call_ops *call_ops) +{ + struct file *filp = nfs_to->nfsd_file_file(localio); + struct nfs_local_kiocb *iocb; + struct iov_iter iter; + ssize_t status; + + dprintk("%s: vfs_read count=%u pos=%llu\n", + __func__, hdr->args.count, hdr->args.offset); + + iocb = nfs_local_iocb_alloc(hdr, localio, GFP_KERNEL); + if (iocb == NULL) + return -ENOMEM; + nfs_local_iter_init(&iter, iocb, READ); + + nfs_local_pgio_init(hdr, call_ops); + hdr->res.eof = false; + + status = filp->f_op->read_iter(&iocb->kiocb, &iter); + WARN_ON_ONCE(status == -EIOCBQUEUED); + + nfs_local_read_done(iocb, status); + nfs_local_pgio_release(iocb); + + return 0; +} + +static void +nfs_copy_boot_verifier(struct nfs_write_verifier *verifier, struct inode *inode) +{ + struct nfs_client *clp = NFS_SERVER(inode)->nfs_client; + u32 *verf = (u32 *)verifier->data; + int seq = 0; + + do { + read_seqbegin_or_lock(&clp->cl_boot_lock, &seq); + verf[0] = (u32)clp->cl_nfssvc_boot.tv_sec; + verf[1] = (u32)clp->cl_nfssvc_boot.tv_nsec; + } while (need_seqretry(&clp->cl_boot_lock, seq)); + done_seqretry(&clp->cl_boot_lock, seq); +} + +static void +nfs_reset_boot_verifier(struct inode *inode) +{ + struct nfs_client *clp = NFS_SERVER(inode)->nfs_client; + + write_seqlock(&clp->cl_boot_lock); + ktime_get_real_ts64(&clp->cl_nfssvc_boot); + write_sequnlock(&clp->cl_boot_lock); +} + +static void +nfs_set_local_verifier(struct inode *inode, + struct nfs_writeverf *verf, + enum nfs3_stable_how how) +{ + nfs_copy_boot_verifier(&verf->verifier, inode); + verf->committed = how; +} + +/* Factored out from fs/nfsd/vfs.h:fh_getattr() */ +static int __vfs_getattr(struct path *p, struct kstat *stat, int version) +{ + u32 request_mask = STATX_BASIC_STATS; + + if (version == 4) + request_mask |= (STATX_BTIME | STATX_CHANGE_COOKIE); + return vfs_getattr(p, stat, request_mask, AT_STATX_SYNC_AS_STAT); +} + +/* Copied from fs/nfsd/nfsfh.c:nfsd4_change_attribute() */ +static u64 __nfsd4_change_attribute(const struct kstat *stat, + const struct inode *inode) +{ + u64 chattr; + + if (stat->result_mask & STATX_CHANGE_COOKIE) { + chattr = stat->change_cookie; + if (S_ISREG(inode->i_mode) && + !(stat->attributes & STATX_ATTR_CHANGE_MONOTONIC)) { + chattr += (u64)stat->ctime.tv_sec << 30; + chattr += stat->ctime.tv_nsec; + } + } else { + chattr = time_to_chattr(&stat->ctime); + } + return chattr; +} + +static void nfs_local_vfs_getattr(struct nfs_local_kiocb *iocb) +{ + struct kstat stat; + struct file *filp = iocb->kiocb.ki_filp; + struct nfs_pgio_header *hdr = iocb->hdr; + struct nfs_fattr *fattr = hdr->res.fattr; + int version = NFS_PROTO(hdr->inode)->version; + + if (unlikely(!fattr) || __vfs_getattr(&filp->f_path, &stat, version)) + return; + + fattr->valid = (NFS_ATTR_FATTR_FILEID | + NFS_ATTR_FATTR_CHANGE | + NFS_ATTR_FATTR_SIZE | + NFS_ATTR_FATTR_ATIME | + NFS_ATTR_FATTR_MTIME | + NFS_ATTR_FATTR_CTIME | + NFS_ATTR_FATTR_SPACE_USED); + + fattr->fileid = stat.ino; + fattr->size = stat.size; + fattr->atime = stat.atime; + fattr->mtime = stat.mtime; + fattr->ctime = stat.ctime; + if (version == 4) { + fattr->change_attr = + __nfsd4_change_attribute(&stat, file_inode(filp)); + } else + fattr->change_attr = nfs_timespec_to_change_attr(&fattr->ctime); + fattr->du.nfs3.used = stat.blocks << 9; +} + +static void +nfs_local_write_done(struct nfs_local_kiocb *iocb, long status) +{ + struct nfs_pgio_header *hdr = iocb->hdr; + struct inode *inode = hdr->inode; + + dprintk("%s: wrote %ld bytes.\n", __func__, status > 0 ? status : 0); + + /* Handle short writes as if they are ENOSPC */ + if (status > 0 && status < hdr->args.count) { + hdr->mds_offset += status; + hdr->args.offset += status; + hdr->args.pgbase += status; + hdr->args.count -= status; + nfs_set_pgio_error(hdr, -ENOSPC, hdr->args.offset); + status = -ENOSPC; + } + if (status < 0) + nfs_reset_boot_verifier(inode); + else if (nfs_should_remove_suid(inode)) { + /* Deal with the suid/sgid bit corner case */ + spin_lock(&inode->i_lock); + nfs_set_cache_invalid(inode, NFS_INO_INVALID_MODE); + spin_unlock(&inode->i_lock); + } + nfs_local_pgio_done(hdr, status); +} + +static int +nfs_do_local_write(struct nfs_pgio_header *hdr, + struct nfsd_file *localio, + const struct rpc_call_ops *call_ops) +{ + struct file *filp = nfs_to->nfsd_file_file(localio); + struct nfs_local_kiocb *iocb; + struct iov_iter iter; + ssize_t status; + + dprintk("%s: vfs_write count=%u pos=%llu %s\n", + __func__, hdr->args.count, hdr->args.offset, + (hdr->args.stable == NFS_UNSTABLE) ? "unstable" : "stable"); + + iocb = nfs_local_iocb_alloc(hdr, localio, GFP_NOIO); + if (iocb == NULL) + return -ENOMEM; + nfs_local_iter_init(&iter, iocb, WRITE); + + switch (hdr->args.stable) { + default: + break; + case NFS_DATA_SYNC: + iocb->kiocb.ki_flags |= IOCB_DSYNC; + break; + case NFS_FILE_SYNC: + iocb->kiocb.ki_flags |= IOCB_DSYNC|IOCB_SYNC; + } + nfs_local_pgio_init(hdr, call_ops); + + nfs_set_local_verifier(hdr->inode, hdr->res.verf, hdr->args.stable); + + file_start_write(filp); + status = filp->f_op->write_iter(&iocb->kiocb, &iter); + file_end_write(filp); + WARN_ON_ONCE(status == -EIOCBQUEUED); + + nfs_local_write_done(iocb, status); + nfs_local_vfs_getattr(iocb); + nfs_local_pgio_release(iocb); + + return 0; +} + +int nfs_local_doio(struct nfs_client *clp, struct nfsd_file *localio, + struct nfs_pgio_header *hdr, + const struct rpc_call_ops *call_ops) +{ + int status = 0; + struct file *filp = nfs_to->nfsd_file_file(localio); + + if (!hdr->args.count) + return 0; + /* Don't support filesystems without read_iter/write_iter */ + if (!filp->f_op->read_iter || !filp->f_op->write_iter) { + nfs_local_disable(clp); + status = -EAGAIN; + goto out; + } + + switch (hdr->rw_mode) { + case FMODE_READ: + status = nfs_do_local_read(hdr, localio, call_ops); + break; + case FMODE_WRITE: + status = nfs_do_local_write(hdr, localio, call_ops); + break; + default: + dprintk("%s: invalid mode: %d\n", __func__, + hdr->rw_mode); + status = -EINVAL; + } +out: + if (status != 0) { + nfs_to->nfsd_file_put_local(localio); + hdr->task.tk_status = status; + nfs_local_hdr_release(hdr, call_ops); + } + return status; +} + +static void +nfs_local_init_commit(struct nfs_commit_data *data, + const struct rpc_call_ops *call_ops) +{ + data->task.tk_ops = call_ops; +} + +static int +nfs_local_run_commit(struct file *filp, struct nfs_commit_data *data) +{ + loff_t start = data->args.offset; + loff_t end = LLONG_MAX; + + if (data->args.count > 0) { + end = start + data->args.count - 1; + if (end < start) + end = LLONG_MAX; + } + + dprintk("%s: commit %llu - %llu\n", __func__, start, end); + return vfs_fsync_range(filp, start, end, 0); +} + +static void +nfs_local_commit_done(struct nfs_commit_data *data, int status) +{ + if (status >= 0) { + nfs_set_local_verifier(data->inode, + data->res.verf, + NFS_FILE_SYNC); + data->res.op_status = NFS4_OK; + data->task.tk_status = 0; + } else { + nfs_reset_boot_verifier(data->inode); + data->res.op_status = nfs4_stat_to_errno(status); + data->task.tk_status = status; + } +} + +static void +nfs_local_release_commit_data(struct nfsd_file *localio, + struct nfs_commit_data *data, + const struct rpc_call_ops *call_ops) +{ + nfs_to->nfsd_file_put_local(localio); + call_ops->rpc_call_done(&data->task, data); + call_ops->rpc_release(data); +} + +static struct nfs_local_fsync_ctx * +nfs_local_fsync_ctx_alloc(struct nfs_commit_data *data, + struct nfsd_file *localio, gfp_t flags) +{ + struct nfs_local_fsync_ctx *ctx = kmalloc(sizeof(*ctx), flags); + + if (ctx != NULL) { + ctx->localio = localio; + ctx->data = data; + INIT_WORK(&ctx->work, nfs_local_fsync_work); + kref_init(&ctx->kref); + ctx->done = NULL; + } + return ctx; +} + +static void +nfs_local_fsync_ctx_kref_free(struct kref *kref) +{ + kfree(container_of(kref, struct nfs_local_fsync_ctx, kref)); +} + +static void +nfs_local_fsync_ctx_put(struct nfs_local_fsync_ctx *ctx) +{ + kref_put(&ctx->kref, nfs_local_fsync_ctx_kref_free); +} + +static void +nfs_local_fsync_ctx_free(struct nfs_local_fsync_ctx *ctx) +{ + nfs_local_release_commit_data(ctx->localio, ctx->data, + ctx->data->task.tk_ops); + nfs_local_fsync_ctx_put(ctx); +} + +static void +nfs_local_fsync_work(struct work_struct *work) +{ + struct nfs_local_fsync_ctx *ctx; + int status; + + ctx = container_of(work, struct nfs_local_fsync_ctx, work); + + status = nfs_local_run_commit(nfs_to->nfsd_file_file(ctx->localio), + ctx->data); + nfs_local_commit_done(ctx->data, status); + if (ctx->done != NULL) + complete(ctx->done); + nfs_local_fsync_ctx_free(ctx); +} + +int nfs_local_commit(struct nfsd_file *localio, + struct nfs_commit_data *data, + const struct rpc_call_ops *call_ops, int how) +{ + struct nfs_local_fsync_ctx *ctx; + + ctx = nfs_local_fsync_ctx_alloc(data, localio, GFP_KERNEL); + if (!ctx) { + nfs_local_commit_done(data, -ENOMEM); + nfs_local_release_commit_data(localio, data, call_ops); + return -ENOMEM; + } + + nfs_local_init_commit(data, call_ops); + kref_get(&ctx->kref); + if (how & FLUSH_SYNC) { + DECLARE_COMPLETION_ONSTACK(done); + ctx->done = &done; + queue_work(nfsiod_workqueue, &ctx->work); + wait_for_completion(&done); + } else + queue_work(nfsiod_workqueue, &ctx->work); + nfs_local_fsync_ctx_put(ctx); + return 0; +} diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 352fdaed4075..1eab98c277fa 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -1685,6 +1685,67 @@ TRACE_EVENT(nfs_mount_path, TP_printk("path='%s'", __get_str(path)) ); +TRACE_EVENT(nfs_local_open_fh, + TP_PROTO( + const struct nfs_fh *fh, + fmode_t fmode, + int error + ), + + TP_ARGS(fh, fmode, error), + + TP_STRUCT__entry( + __field(int, error) + __field(u32, fhandle) + __field(unsigned int, fmode) + ), + + TP_fast_assign( + __entry->error = error; + __entry->fhandle = nfs_fhandle_hash(fh); + __entry->fmode = (__force unsigned int)fmode; + ), + + TP_printk( + "error=%d fhandle=0x%08x mode=%s", + __entry->error, + __entry->fhandle, + show_fs_fmode_flags(__entry->fmode) + ) +); + +DECLARE_EVENT_CLASS(nfs_local_client_event, + TP_PROTO( + const struct nfs_client *clp + ), + + TP_ARGS(clp), + + TP_STRUCT__entry( + __field(unsigned int, protocol) + __string(server, clp->cl_hostname) + ), + + TP_fast_assign( + __entry->protocol = clp->rpc_ops->version; + __assign_str(server); + ), + + TP_printk( + "server=%s NFSv%u", __get_str(server), __entry->protocol + ) +); + +#define DEFINE_NFS_LOCAL_CLIENT_EVENT(name) \ + DEFINE_EVENT(nfs_local_client_event, name, \ + TP_PROTO( \ + const struct nfs_client *clp \ + ), \ + TP_ARGS(clp)) + +DEFINE_NFS_LOCAL_CLIENT_EVENT(nfs_local_enable); +DEFINE_NFS_LOCAL_CLIENT_EVENT(nfs_local_disable); + DECLARE_EVENT_CLASS(nfs_xdr_event, TP_PROTO( const struct xdr_stream *xdr, diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 50f3d6c9ac2a..97d5524c379a 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -762,6 +762,10 @@ int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr, hdr->args.count, (unsigned long long)hdr->args.offset); + if (localio) + return nfs_local_doio(NFS_SERVER(hdr->inode)->nfs_client, + localio, hdr, call_ops); + task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return PTR_ERR(task); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index ef72922263bb..508e279da648 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1694,6 +1694,9 @@ int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data, dprintk("NFS: initiated commit call\n"); + if (localio) + return nfs_local_commit(localio, data, call_ops, how); + task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return PTR_ERR(task); diff --git a/fs/nfs_common/nfslocalio.c b/fs/nfs_common/nfslocalio.c index f61761ad19b1..42b479b9191f 100644 --- a/fs/nfs_common/nfslocalio.c +++ b/fs/nfs_common/nfslocalio.c @@ -115,6 +115,39 @@ void nfs_uuid_invalidate_one_client(nfs_uuid_t *nfs_uuid) } EXPORT_SYMBOL_GPL(nfs_uuid_invalidate_one_client); +struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *uuid, + struct rpc_clnt *rpc_clnt, const struct cred *cred, + const struct nfs_fh *nfs_fh, const fmode_t fmode) +{ + struct net *net; + struct nfsd_file *localio; + + /* + * Not running in nfsd context, so must safely get reference on nfsd_serv. + * But the server may already be shutting down, if so disallow new localio. + * uuid->net is NOT a counted reference, but rcu_read_lock() ensures that + * if uuid->net is not NULL, then calling nfsd_serv_try_get() is safe + * and if it succeeds we will have an implied reference to the net. + * + * Otherwise NFS may not have ref on NFSD and therefore cannot safely + * make 'nfs_to' calls. + */ + rcu_read_lock(); + net = rcu_dereference(uuid->net); + if (!net || !nfs_to->nfsd_serv_try_get(net)) { + rcu_read_unlock(); + return ERR_PTR(-ENXIO); + } + rcu_read_unlock(); + /* We have an implied reference to net thanks to nfsd_serv_try_get */ + localio = nfs_to->nfsd_open_local_fh(net, uuid->dom, rpc_clnt, + cred, nfs_fh, fmode); + if (IS_ERR(localio)) + nfs_to->nfsd_serv_put(net); + return localio; +} +EXPORT_SYMBOL_GPL(nfs_open_local_fh); + /* * The NFS LOCALIO code needs to call into NFSD using various symbols, * but cannot be statically linked, because that will make the NFS diff --git a/include/linux/nfs.h b/include/linux/nfs.h index 73da75908d95..9ad727ddfedb 100644 --- a/include/linux/nfs.h +++ b/include/linux/nfs.h @@ -8,6 +8,8 @@ #ifndef _LINUX_NFS_H #define _LINUX_NFS_H +#include +#include #include #include #include diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index c49bfdded5c1..853df3fcd4c2 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -8,6 +8,7 @@ #include #include #include +#include #include #include @@ -49,6 +50,7 @@ struct nfs_client { #define NFS_CS_DS 7 /* - Server is a DS */ #define NFS_CS_REUSEPORT 8 /* - reuse src port on reconnect */ #define NFS_CS_PNFS 9 /* - Server used for pnfs */ +#define NFS_CS_LOCAL_IO 10 /* - client is local */ struct sockaddr_storage cl_addr; /* server identifier */ size_t cl_addrlen; char * cl_hostname; /* hostname of server */ @@ -125,6 +127,13 @@ struct nfs_client { struct net *cl_net; struct list_head pending_cb_stateids; struct rcu_head rcu; + +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + struct timespec64 cl_nfssvc_boot; + seqlock_t cl_boot_lock; + nfs_uuid_t cl_uuid; + spinlock_t cl_localio_lock; +#endif /* CONFIG_NFS_LOCALIO */ }; /* diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h index 2c4e0fd9da6b..b353abe00357 100644 --- a/include/linux/nfslocalio.h +++ b/include/linux/nfslocalio.h @@ -61,6 +61,10 @@ struct nfsd_localio_operations { extern void nfsd_localio_ops_init(void); extern const struct nfsd_localio_operations *nfs_to; +struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *, + struct rpc_clnt *, const struct cred *, + const struct nfs_fh *, const fmode_t); + #else /* CONFIG_NFS_LOCALIO */ static inline void nfsd_localio_ops_init(void) { -- cgit v1.2.3 From b166b8ab4189743a717cb93f50d6fcca3a46770d Mon Sep 17 00:00:00 2001 From: Jiqian Chen Date: Tue, 24 Sep 2024 14:14:36 +0800 Subject: xen/pvh: Setup gsi for passthrough device In PVH dom0, the gsis don't get registered, but the gsi of a passthrough device must be configured for it to be able to be mapped into a domU. When assigning a device to passthrough, proactively setup the gsi of the device during that process. Signed-off-by: Jiqian Chen Signed-off-by: Huang Rui Signed-off-by: Jiqian Chen Reviewed-by: Stefano Stabellini Message-ID: <20240924061437.2636766-3-Jiqian.Chen@amd.com> Signed-off-by: Juergen Gross --- arch/x86/xen/enlighten_pvh.c | 23 ++++++++++++++++++ drivers/acpi/pci_irq.c | 2 +- drivers/xen/acpi.c | 50 ++++++++++++++++++++++++++++++++++++++ drivers/xen/xen-pciback/pci_stub.c | 20 +++++++++++++++ include/linux/acpi.h | 1 + include/xen/acpi.h | 18 ++++++++++++++ 6 files changed, 113 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index 728a4366ca85..bf68c329fc01 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -4,6 +4,7 @@ #include #include +#include #include #include @@ -28,6 +29,28 @@ bool __ro_after_init xen_pvh; EXPORT_SYMBOL_GPL(xen_pvh); +#ifdef CONFIG_XEN_DOM0 +int xen_pvh_setup_gsi(int gsi, int trigger, int polarity) +{ + int ret; + struct physdev_setup_gsi setup_gsi; + + setup_gsi.gsi = gsi; + setup_gsi.triggering = (trigger == ACPI_EDGE_SENSITIVE ? 0 : 1); + setup_gsi.polarity = (polarity == ACPI_ACTIVE_HIGH ? 0 : 1); + + ret = HYPERVISOR_physdev_op(PHYSDEVOP_setup_gsi, &setup_gsi); + if (ret == -EEXIST) { + xen_raw_printk("Already setup the GSI :%d\n", gsi); + ret = 0; + } else if (ret) + xen_raw_printk("Fail to setup GSI (%d)!\n", gsi); + + return ret; +} +EXPORT_SYMBOL_GPL(xen_pvh_setup_gsi); +#endif + /* * Reserve e820 UNUSABLE regions to inflate the memory balloon. * diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c index ff30ceca2203..630fe0a34bc6 100644 --- a/drivers/acpi/pci_irq.c +++ b/drivers/acpi/pci_irq.c @@ -288,7 +288,7 @@ static int acpi_reroute_boot_interrupt(struct pci_dev *dev, } #endif /* CONFIG_X86_IO_APIC */ -static struct acpi_prt_entry *acpi_pci_irq_lookup(struct pci_dev *dev, int pin) +struct acpi_prt_entry *acpi_pci_irq_lookup(struct pci_dev *dev, int pin) { struct acpi_prt_entry *entry = NULL; struct pci_dev *bridge; diff --git a/drivers/xen/acpi.c b/drivers/xen/acpi.c index 6893c79fd2a1..9e2096524fbc 100644 --- a/drivers/xen/acpi.c +++ b/drivers/xen/acpi.c @@ -30,6 +30,7 @@ * IN THE SOFTWARE. */ +#include #include #include #include @@ -75,3 +76,52 @@ int xen_acpi_notify_hypervisor_extended_sleep(u8 sleep_state, return xen_acpi_notify_hypervisor_state(sleep_state, val_a, val_b, true); } + +struct acpi_prt_entry { + struct acpi_pci_id id; + u8 pin; + acpi_handle link; + u32 index; +}; + +int xen_acpi_get_gsi_info(struct pci_dev *dev, + int *gsi_out, + int *trigger_out, + int *polarity_out) +{ + int gsi; + u8 pin; + struct acpi_prt_entry *entry; + int trigger = ACPI_LEVEL_SENSITIVE; + int polarity = acpi_irq_model == ACPI_IRQ_MODEL_GIC ? + ACPI_ACTIVE_HIGH : ACPI_ACTIVE_LOW; + + if (!dev || !gsi_out || !trigger_out || !polarity_out) + return -EINVAL; + + pin = dev->pin; + if (!pin) + return -EINVAL; + + entry = acpi_pci_irq_lookup(dev, pin); + if (entry) { + if (entry->link) + gsi = acpi_pci_link_allocate_irq(entry->link, + entry->index, + &trigger, &polarity, + NULL); + else + gsi = entry->index; + } else + gsi = -1; + + if (gsi < 0) + return -EINVAL; + + *gsi_out = gsi; + *trigger_out = trigger; + *polarity_out = polarity; + + return 0; +} +EXPORT_SYMBOL_GPL(xen_acpi_get_gsi_info); diff --git a/drivers/xen/xen-pciback/pci_stub.c b/drivers/xen/xen-pciback/pci_stub.c index 3e162c1753e2..8ce27333f54b 100644 --- a/drivers/xen/xen-pciback/pci_stub.c +++ b/drivers/xen/xen-pciback/pci_stub.c @@ -21,6 +21,9 @@ #include #include #include +#ifdef CONFIG_XEN_ACPI +#include +#endif #include #include #include "pciback.h" @@ -367,6 +370,9 @@ static int pcistub_match(struct pci_dev *dev) static int pcistub_init_device(struct pci_dev *dev) { struct xen_pcibk_dev_data *dev_data; +#ifdef CONFIG_XEN_ACPI + int gsi, trigger, polarity; +#endif int err = 0; dev_dbg(&dev->dev, "initializing...\n"); @@ -435,6 +441,20 @@ static int pcistub_init_device(struct pci_dev *dev) goto config_release; pci_restore_state(dev); } + +#ifdef CONFIG_XEN_ACPI + if (xen_initial_domain() && xen_pvh_domain()) { + err = xen_acpi_get_gsi_info(dev, &gsi, &trigger, &polarity); + if (err) { + dev_err(&dev->dev, "Fail to get gsi info!\n"); + goto config_release; + } + err = xen_pvh_setup_gsi(gsi, trigger, polarity); + if (err) + goto config_release; + } +#endif + /* Now disable the device (this also ensures some private device * data is setup before we export) */ diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 0687a442fec7..02ded9f53a6b 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -362,6 +362,7 @@ void acpi_unregister_gsi (u32 gsi); struct pci_dev; +struct acpi_prt_entry *acpi_pci_irq_lookup(struct pci_dev *dev, int pin); int acpi_pci_irq_enable (struct pci_dev *dev); void acpi_penalize_isa_irq(int irq, int active); bool acpi_isa_irq_available(int irq); diff --git a/include/xen/acpi.h b/include/xen/acpi.h index b1e11863144d..3bcfe82d9078 100644 --- a/include/xen/acpi.h +++ b/include/xen/acpi.h @@ -67,10 +67,28 @@ static inline void xen_acpi_sleep_register(void) acpi_suspend_lowlevel = xen_acpi_suspend_lowlevel; } } +int xen_pvh_setup_gsi(int gsi, int trigger, int polarity); +int xen_acpi_get_gsi_info(struct pci_dev *dev, + int *gsi_out, + int *trigger_out, + int *polarity_out); #else static inline void xen_acpi_sleep_register(void) { } + +static inline int xen_pvh_setup_gsi(int gsi, int trigger, int polarity) +{ + return -1; +} + +static inline int xen_acpi_get_gsi_info(struct pci_dev *dev, + int *gsi_out, + int *trigger_out, + int *polarity_out) +{ + return -1; +} #endif #endif /* _XEN_ACPI_H */ -- cgit v1.2.3 From 2efddb5575cd9f5f4d61ad417c92365a5f18d2f1 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 25 Sep 2024 10:57:00 +0200 Subject: Revert "driver core: shut down devices asynchronously" This reverts commit 8064952c65045f05ee2671fe437770e50c151776. The series is being reverted before -rc1 as there are still reports of lockups on shutdown, so it's not quite ready for "prime time." Reported-by: Andrey Skvortsov Link: https://lore.kernel.org/r/ZvMkkhyJrohaajuk@skv.local Cc: Christoph Hellwig Cc: David Jeffery Cc: Keith Busch Cc: Laurence Oberman Cc: Nathan Chancellor Cc: Sagi Grimberg Cc: Stuart Hayes Signed-off-by: Greg Kroah-Hartman --- drivers/base/base.h | 4 ---- drivers/base/core.c | 54 +------------------------------------------ include/linux/device/driver.h | 2 -- 3 files changed, 1 insertion(+), 59 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/base.h b/drivers/base/base.h index ea18aa70f151..8cf04a557bdb 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -10,7 +10,6 @@ * shared outside of the drivers/base/ directory. * */ -#include #include /** @@ -98,8 +97,6 @@ struct driver_private { * the device; typically because it depends on another driver getting * probed first. * @async_driver - pointer to device driver awaiting probe via async_probe - * @shutdown_after - used during device shutdown to ensure correct shutdown - * ordering. * @device - pointer back to the struct device that this structure is * associated with. * @dead - This device is currently either in the process of or has been @@ -117,7 +114,6 @@ struct device_private { struct list_head deferred_probe; const struct device_driver *async_driver; char *deferred_probe_reason; - async_cookie_t shutdown_after; struct device *device; u8 dead:1; }; diff --git a/drivers/base/core.c b/drivers/base/core.c index b69b82da8837..4482382fb947 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -9,7 +9,6 @@ */ #include -#include #include #include #include @@ -3525,7 +3524,6 @@ static int device_private_init(struct device *dev) klist_init(&dev->p->klist_children, klist_children_get, klist_children_put); INIT_LIST_HEAD(&dev->p->deferred_probe); - dev->p->shutdown_after = 0; return 0; } @@ -4781,8 +4779,6 @@ out: } EXPORT_SYMBOL_GPL(device_change_owner); -static ASYNC_DOMAIN(sd_domain); - static void shutdown_one_device(struct device *dev) { /* hold lock to avoid race with probe/release */ @@ -4818,34 +4814,12 @@ static void shutdown_one_device(struct device *dev) put_device(dev->parent); } -/** - * shutdown_one_device_async - * @data: the pointer to the struct device to be shutdown - * @cookie: not used - * - * Shuts down one device, after waiting for shutdown_after to complete. - * shutdown_after should be set to the cookie of the last child or consumer - * of this device to be shutdown (if any), or to the cookie of the previous - * device to be shut down for devices that don't enable asynchronous shutdown. - */ -static void shutdown_one_device_async(void *data, async_cookie_t cookie) -{ - struct device *dev = data; - - async_synchronize_cookie_domain(dev->p->shutdown_after + 1, &sd_domain); - - shutdown_one_device(dev); -} - /** * device_shutdown - call ->shutdown() on each device to shutdown. */ void device_shutdown(void) { struct device *dev, *parent; - async_cookie_t cookie = 0; - struct device_link *link; - int idx; wait_for_device_probe(); device_block_probing(); @@ -4876,37 +4850,11 @@ void device_shutdown(void) list_del_init(&dev->kobj.entry); spin_unlock(&devices_kset->list_lock); - - /* - * Set cookie for devices that will be shut down synchronously - */ - if (!dev->driver || !dev->driver->async_shutdown_enable) - dev->p->shutdown_after = cookie; - - get_device(dev); - get_device(parent); - - cookie = async_schedule_domain(shutdown_one_device_async, - dev, &sd_domain); - /* - * Ensure parent & suppliers wait for this device to shut down - */ - if (parent) { - parent->p->shutdown_after = cookie; - put_device(parent); - } - - idx = device_links_read_lock(); - list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, - device_links_read_lock_held()) - link->supplier->p->shutdown_after = cookie; - device_links_read_unlock(idx); - put_device(dev); + shutdown_one_device(dev); spin_lock(&devices_kset->list_lock); } spin_unlock(&devices_kset->list_lock); - async_synchronize_full_domain(&sd_domain); } /* diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h index 14c9211b82d6..5c04b8e3833b 100644 --- a/include/linux/device/driver.h +++ b/include/linux/device/driver.h @@ -56,7 +56,6 @@ enum probe_type { * @mod_name: Used for built-in modules. * @suppress_bind_attrs: Disables bind/unbind via sysfs. * @probe_type: Type of the probe (synchronous or asynchronous) to use. - * @async_shutdown_enable: Enables devices to be shutdown asynchronously. * @of_match_table: The open firmware table. * @acpi_match_table: The ACPI match table. * @probe: Called to query the existence of a specific device, @@ -103,7 +102,6 @@ struct device_driver { bool suppress_bind_attrs; /* disables bind/unbind via sysfs */ enum probe_type probe_type; - bool async_shutdown_enable; const struct of_device_id *of_match_table; const struct acpi_device_id *acpi_match_table; -- cgit v1.2.3 From ce4db753de21abfb7516ef64aff907813e8a8e3e Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Mon, 26 Aug 2024 11:25:52 +0800 Subject: kprobes: Remove obsoleted declaration for init_test_probes The init_test_probes() have been removed since commit e44e81c5b90f ("kprobes: convert tests to kunit"), and now it is useless, so remove it. Link: https://lore.kernel.org/all/20240826032552.4016314-1-cuigaosheng1@huawei.com/ Signed-off-by: Gaosheng Cui Signed-off-by: Masami Hiramatsu (Google) --- include/linux/kprobes.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 5fcbc254d186..8c4f3bb24429 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -269,15 +269,6 @@ extern unsigned long __stop_kprobe_blacklist[]; extern struct kretprobe_blackpoint kretprobe_blacklist[]; -#ifdef CONFIG_KPROBES_SANITY_TEST -extern int init_test_probes(void); -#else /* !CONFIG_KPROBES_SANITY_TEST */ -static inline int init_test_probes(void) -{ - return 0; -} -#endif /* CONFIG_KPROBES_SANITY_TEST */ - extern int arch_prepare_kprobe(struct kprobe *p); extern void arch_arm_kprobe(struct kprobe *p); extern void arch_disarm_kprobe(struct kprobe *p); -- cgit v1.2.3 From d5dbf8b48a4620db771f399ed7fce32d447f04a6 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Sun, 18 Aug 2024 19:42:58 +0900 Subject: tracepoint: Support iterating over tracepoints on modules Add for_each_module_tracepoint() for iterating over tracepoints on modules. This is similar to the for_each_kernel_tracepoint() but only for the tracepoints on modules (not including kernel built-in tracepoints). Link: https://lore.kernel.org/all/172397777800.286558.14554748203446214056.stgit@devnote2/ Signed-off-by: Masami Hiramatsu (Google) --- include/linux/tracepoint.h | 7 +++++++ kernel/tracepoint.c | 21 +++++++++++++++++++++ 2 files changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 6be396bb4297..837fcf8ec0d5 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -64,6 +64,8 @@ struct tp_module { bool trace_module_has_bad_taint(struct module *mod); extern int register_tracepoint_module_notifier(struct notifier_block *nb); extern int unregister_tracepoint_module_notifier(struct notifier_block *nb); +void for_each_module_tracepoint(void (*fct)(struct tracepoint *, void *), + void *priv); #else static inline bool trace_module_has_bad_taint(struct module *mod) { @@ -79,6 +81,11 @@ int unregister_tracepoint_module_notifier(struct notifier_block *nb) { return 0; } +static inline +void for_each_module_tracepoint(void (*fct)(struct tracepoint *, void *), + void *priv) +{ +} #endif /* CONFIG_MODULES */ /* diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index 8d1507dd0724..bed4aad36d92 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -735,6 +735,27 @@ static __init int init_tracepoints(void) return ret; } __initcall(init_tracepoints); + +/** + * for_each_module_tracepoint - iteration on all tracepoints in all modules + * @fct: callback + * @priv: private data + */ +void for_each_module_tracepoint(void (*fct)(struct tracepoint *tp, void *priv), + void *priv) +{ + struct tp_module *tp_mod; + struct module *mod; + + mutex_lock(&tracepoint_module_list_mutex); + list_for_each_entry(tp_mod, &tracepoint_module_list, list) { + mod = tp_mod->mod; + for_each_tracepoint_range(mod->tracepoints_ptrs, + mod->tracepoints_ptrs + mod->num_tracepoints, + fct, priv); + } + mutex_unlock(&tracepoint_module_list_mutex); +} #endif /* CONFIG_MODULES */ /** -- cgit v1.2.3 From d4df54f338e43c790460674a3cc7db35b8395421 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Sun, 18 Aug 2024 19:43:07 +0900 Subject: tracepoint: Support iterating tracepoints in a loading module Add for_each_tracepoint_in_module() function to iterate tracepoints in a module. This API is needed for handling tracepoints in a loading module from tracepoint_module_notifier callback function. This also update for_each_module_tracepoint() to pass the module to callback function so that it can find module easily. Link: https://lore.kernel.org/all/172397778740.286558.15781131277732977643.stgit@devnote2/ Signed-off-by: Masami Hiramatsu (Google) --- include/linux/tracepoint.h | 17 +++++++++++++++-- kernel/tracepoint.c | 37 +++++++++++++++++++++++++++++-------- 2 files changed, 44 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 837fcf8ec0d5..93a9f3070b48 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -64,8 +64,13 @@ struct tp_module { bool trace_module_has_bad_taint(struct module *mod); extern int register_tracepoint_module_notifier(struct notifier_block *nb); extern int unregister_tracepoint_module_notifier(struct notifier_block *nb); -void for_each_module_tracepoint(void (*fct)(struct tracepoint *, void *), +void for_each_module_tracepoint(void (*fct)(struct tracepoint *, + struct module *, void *), void *priv); +void for_each_tracepoint_in_module(struct module *, + void (*fct)(struct tracepoint *, + struct module *, void *), + void *priv); #else static inline bool trace_module_has_bad_taint(struct module *mod) { @@ -82,10 +87,18 @@ int unregister_tracepoint_module_notifier(struct notifier_block *nb) return 0; } static inline -void for_each_module_tracepoint(void (*fct)(struct tracepoint *, void *), +void for_each_module_tracepoint(void (*fct)(struct tracepoint *, + struct module *, void *), void *priv) { } +static inline +void for_each_tracepoint_in_module(struct module *mod, + void (*fct)(struct tracepoint *, + struct module *, void *), + void *priv) +{ +} #endif /* CONFIG_MODULES */ /* diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index bed4aad36d92..8879da16ef4d 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -736,24 +736,45 @@ static __init int init_tracepoints(void) } __initcall(init_tracepoints); +/** + * for_each_tracepoint_in_module - iteration on all tracepoints in a module + * @mod: module + * @fct: callback + * @priv: private data + */ +void for_each_tracepoint_in_module(struct module *mod, + void (*fct)(struct tracepoint *tp, + struct module *mod, void *priv), + void *priv) +{ + tracepoint_ptr_t *begin, *end, *iter; + + lockdep_assert_held(&tracepoint_module_list_mutex); + + if (!mod) + return; + + begin = mod->tracepoints_ptrs; + end = mod->tracepoints_ptrs + mod->num_tracepoints; + + for (iter = begin; iter < end; iter++) + fct(tracepoint_ptr_deref(iter), mod, priv); +} + /** * for_each_module_tracepoint - iteration on all tracepoints in all modules * @fct: callback * @priv: private data */ -void for_each_module_tracepoint(void (*fct)(struct tracepoint *tp, void *priv), +void for_each_module_tracepoint(void (*fct)(struct tracepoint *tp, + struct module *mod, void *priv), void *priv) { struct tp_module *tp_mod; - struct module *mod; mutex_lock(&tracepoint_module_list_mutex); - list_for_each_entry(tp_mod, &tracepoint_module_list, list) { - mod = tp_mod->mod; - for_each_tracepoint_range(mod->tracepoints_ptrs, - mod->tracepoints_ptrs + mod->num_tracepoints, - fct, priv); - } + list_for_each_entry(tp_mod, &tracepoint_module_list, list) + for_each_tracepoint_in_module(tp_mod->mod, fct, priv); mutex_unlock(&tracepoint_module_list_mutex); } #endif /* CONFIG_MODULES */ -- cgit v1.2.3 From 04e906839a053f092ef53f4fb2d610983412b904 Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Thu, 19 Sep 2024 14:33:42 +0200 Subject: usbnet: fix cyclical race on disconnect with work queue The work can submit URBs and the URBs can schedule the work. This cycle needs to be broken, when a device is to be stopped. Use a flag to do so. This is a design issue as old as the driver. Signed-off-by: Oliver Neukum Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") CC: stable@vger.kernel.org Link: https://patch.msgid.link/20240919123525.688065-1-oneukum@suse.com Signed-off-by: Paolo Abeni --- drivers/net/usb/usbnet.c | 37 ++++++++++++++++++++++++++++--------- include/linux/usb/usbnet.h | 15 +++++++++++++++ 2 files changed, 43 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 18eb5ba436df..2506aa8c603e 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -464,10 +464,15 @@ static enum skb_state defer_bh(struct usbnet *dev, struct sk_buff *skb, void usbnet_defer_kevent (struct usbnet *dev, int work) { set_bit (work, &dev->flags); - if (!schedule_work (&dev->kevent)) - netdev_dbg(dev->net, "kevent %s may have been dropped\n", usbnet_event_names[work]); - else - netdev_dbg(dev->net, "kevent %s scheduled\n", usbnet_event_names[work]); + if (!usbnet_going_away(dev)) { + if (!schedule_work(&dev->kevent)) + netdev_dbg(dev->net, + "kevent %s may have been dropped\n", + usbnet_event_names[work]); + else + netdev_dbg(dev->net, + "kevent %s scheduled\n", usbnet_event_names[work]); + } } EXPORT_SYMBOL_GPL(usbnet_defer_kevent); @@ -535,7 +540,8 @@ static int rx_submit (struct usbnet *dev, struct urb *urb, gfp_t flags) tasklet_schedule (&dev->bh); break; case 0: - __usbnet_queue_skb(&dev->rxq, skb, rx_start); + if (!usbnet_going_away(dev)) + __usbnet_queue_skb(&dev->rxq, skb, rx_start); } } else { netif_dbg(dev, ifdown, dev->net, "rx: stopped\n"); @@ -843,9 +849,18 @@ int usbnet_stop (struct net_device *net) /* deferred work (timer, softirq, task) must also stop */ dev->flags = 0; - del_timer_sync (&dev->delay); - tasklet_kill (&dev->bh); + del_timer_sync(&dev->delay); + tasklet_kill(&dev->bh); cancel_work_sync(&dev->kevent); + + /* We have cyclic dependencies. Those calls are needed + * to break a cycle. We cannot fall into the gaps because + * we have a flag + */ + tasklet_kill(&dev->bh); + del_timer_sync(&dev->delay); + cancel_work_sync(&dev->kevent); + if (!pm) usb_autopm_put_interface(dev->intf); @@ -1171,7 +1186,8 @@ fail_halt: status); } else { clear_bit (EVENT_RX_HALT, &dev->flags); - tasklet_schedule (&dev->bh); + if (!usbnet_going_away(dev)) + tasklet_schedule(&dev->bh); } } @@ -1196,7 +1212,8 @@ fail_halt: usb_autopm_put_interface(dev->intf); fail_lowmem: if (resched) - tasklet_schedule (&dev->bh); + if (!usbnet_going_away(dev)) + tasklet_schedule(&dev->bh); } } @@ -1559,6 +1576,7 @@ static void usbnet_bh (struct timer_list *t) } else if (netif_running (dev->net) && netif_device_present (dev->net) && netif_carrier_ok(dev->net) && + !usbnet_going_away(dev) && !timer_pending(&dev->delay) && !test_bit(EVENT_RX_PAUSED, &dev->flags) && !test_bit(EVENT_RX_HALT, &dev->flags)) { @@ -1606,6 +1624,7 @@ void usbnet_disconnect (struct usb_interface *intf) usb_set_intfdata(intf, NULL); if (!dev) return; + usbnet_mark_going_away(dev); xdev = interface_to_usbdev (intf); diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index 9f08a584d707..0b9f1e598e3a 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -76,8 +76,23 @@ struct usbnet { # define EVENT_LINK_CHANGE 11 # define EVENT_SET_RX_MODE 12 # define EVENT_NO_IP_ALIGN 13 +/* This one is special, as it indicates that the device is going away + * there are cyclic dependencies between tasklet, timer and bh + * that must be broken + */ +# define EVENT_UNPLUG 31 }; +static inline bool usbnet_going_away(struct usbnet *ubn) +{ + return test_bit(EVENT_UNPLUG, &ubn->flags); +} + +static inline void usbnet_mark_going_away(struct usbnet *ubn) +{ + set_bit(EVENT_UNPLUG, &ubn->flags); +} + static inline struct usb_driver *driver_of(struct usb_interface *intf) { return to_usb_driver(intf->dev.driver); -- cgit v1.2.3 From 8af79d3edb5fd2dce35ea0a71595b6d4f9962350 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 18 Sep 2024 15:13:39 +0200 Subject: netfilter: nfnetlink_queue: remove old clash resolution logic For historical reasons there are two clash resolution spots in netfilter, one in nfnetlink_queue and one in conntrack core. nfnetlink_queue one was added first: If a colliding entry is found, NAT NAT transformation is reversed by calling nat engine again with altered tuple. See commit 368982cd7d1b ("netfilter: nfnetlink_queue: resolve clash for unconfirmed conntracks") for details. One problem is that nf_reroute() won't take an action if the queueing doesn't occur in the OUTPUT hook, i.e. when queueing in forward or postrouting, packet will be sent via the wrong path. Another problem is that the scenario addressed (2nd UDP packet sent with identical addresses while first packet is still being processed) can also occur without any nfqueue involvement due to threaded resolvers doing A and AAAA requests back-to-back. This lead us to add clash resolution logic to the conntrack core, see commit 6a757c07e51f ("netfilter: conntrack: allow insertion of clashing entries"). Instead of fixing the nfqueue based logic, lets remove it and let conntrack core handle this instead. Retain the ->update hook for sake of nfqueue based conntrack helpers. We could axe this hook completely but we'd have to split confirm and helper logic again, see commit ee04805ff54a ("netfilter: conntrack: make conntrack userspace helpers work again"). This SHOULD NOT be backported to kernels earlier than v5.6; they lack adequate clash resolution handling. Patch was originally written by Pablo Neira Ayuso. Reported-by: Antonio Ojea Closes: https://bugzilla.netfilter.org/show_bug.cgi?id=1766 Signed-off-by: Florian Westphal Tested-by: Antonio Ojea Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 4 -- net/netfilter/nf_conntrack_core.c | 85 --------------------------------------- net/netfilter/nf_nat_core.c | 1 - 3 files changed, 90 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 2683b2b77612..2b8aac2c70ad 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -376,15 +376,11 @@ int nf_route(struct net *net, struct dst_entry **dst, struct flowi *fl, struct nf_conn; enum nf_nat_manip_type; struct nlattr; -enum ip_conntrack_dir; struct nf_nat_hook { int (*parse_nat_setup)(struct nf_conn *ct, enum nf_nat_manip_type manip, const struct nlattr *attr); void (*decode_session)(struct sk_buff *skb, struct flowi *fl); - unsigned int (*manip_pkt)(struct sk_buff *skb, struct nf_conn *ct, - enum nf_nat_manip_type mtype, - enum ip_conntrack_dir dir); void (*remove_nat_bysrc)(struct nf_conn *ct); }; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 7c63fbfb8c1d..9db3e2b0b1c3 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -2197,80 +2197,6 @@ static void nf_conntrack_attach(struct sk_buff *nskb, const struct sk_buff *skb) nf_conntrack_get(skb_nfct(nskb)); } -static int __nf_conntrack_update(struct net *net, struct sk_buff *skb, - struct nf_conn *ct, - enum ip_conntrack_info ctinfo) -{ - const struct nf_nat_hook *nat_hook; - struct nf_conntrack_tuple_hash *h; - struct nf_conntrack_tuple tuple; - unsigned int status; - int dataoff; - u16 l3num; - u8 l4num; - - l3num = nf_ct_l3num(ct); - - dataoff = get_l4proto(skb, skb_network_offset(skb), l3num, &l4num); - if (dataoff <= 0) - return NF_DROP; - - if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, l3num, - l4num, net, &tuple)) - return NF_DROP; - - if (ct->status & IPS_SRC_NAT) { - memcpy(tuple.src.u3.all, - ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.all, - sizeof(tuple.src.u3.all)); - tuple.src.u.all = - ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.all; - } - - if (ct->status & IPS_DST_NAT) { - memcpy(tuple.dst.u3.all, - ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.all, - sizeof(tuple.dst.u3.all)); - tuple.dst.u.all = - ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u.all; - } - - h = nf_conntrack_find_get(net, nf_ct_zone(ct), &tuple); - if (!h) - return NF_ACCEPT; - - /* Store status bits of the conntrack that is clashing to re-do NAT - * mangling according to what it has been done already to this packet. - */ - status = ct->status; - - nf_ct_put(ct); - ct = nf_ct_tuplehash_to_ctrack(h); - nf_ct_set(skb, ct, ctinfo); - - nat_hook = rcu_dereference(nf_nat_hook); - if (!nat_hook) - return NF_ACCEPT; - - if (status & IPS_SRC_NAT) { - unsigned int verdict = nat_hook->manip_pkt(skb, ct, - NF_NAT_MANIP_SRC, - IP_CT_DIR_ORIGINAL); - if (verdict != NF_ACCEPT) - return verdict; - } - - if (status & IPS_DST_NAT) { - unsigned int verdict = nat_hook->manip_pkt(skb, ct, - NF_NAT_MANIP_DST, - IP_CT_DIR_ORIGINAL); - if (verdict != NF_ACCEPT) - return verdict; - } - - return NF_ACCEPT; -} - /* This packet is coming from userspace via nf_queue, complete the packet * processing after the helper invocation in nf_confirm(). */ @@ -2334,17 +2260,6 @@ static int nf_conntrack_update(struct net *net, struct sk_buff *skb) if (!ct) return NF_ACCEPT; - if (!nf_ct_is_confirmed(ct)) { - int ret = __nf_conntrack_update(net, skb, ct, ctinfo); - - if (ret != NF_ACCEPT) - return ret; - - ct = nf_ct_get(skb, &ctinfo); - if (!ct) - return NF_ACCEPT; - } - return nf_confirm_cthelper(skb, ct, ctinfo); } diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index d9ea2c26f309..4085c436e306 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -1324,7 +1324,6 @@ static const struct nf_nat_hook nat_hook = { #ifdef CONFIG_XFRM .decode_session = __nf_nat_decode_session, #endif - .manip_pkt = nf_nat_manip_pkt, .remove_nat_bysrc = nf_nat_cleanup_conntrack, }; -- cgit v1.2.3 From a78282e2c94f4ca80a2d7c56e4d1e9546be5596d Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 26 Sep 2024 11:39:02 -0700 Subject: Revert "binfmt_elf, coredump: Log the reason of the failed core dumps" This reverts commit fb97d2eb542faf19a8725afbd75cbc2518903210. The logging was questionable to begin with, but it seems to actively deadlock on the task lock. "On second thought, let's not log core dump failures. 'Tis a silly place" because if you can't tell your core dump is truncated, maybe you should just fix your debugger instead of adding bugs to the kernel. Reported-by: Vegard Nossum Link: https://lore.kernel.org/all/d122ece6-3606-49de-ae4d-8da88846bef2@oracle.com/ Signed-off-by: Linus Torvalds --- fs/binfmt_elf.c | 48 ++++++--------------- fs/coredump.c | 107 +++++++++-------------------------------------- include/linux/coredump.h | 8 +--- kernel/signal.c | 21 +--------- 4 files changed, 34 insertions(+), 150 deletions(-) (limited to 'include/linux') diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 34d0d1e43f36..06dc4a57ba78 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -2032,10 +2032,8 @@ static int elf_core_dump(struct coredump_params *cprm) * Collect all the non-memory information about the process for the * notes. This also sets up the file header. */ - if (!fill_note_info(&elf, e_phnum, &info, cprm)) { - coredump_report_failure("Error collecting note info"); + if (!fill_note_info(&elf, e_phnum, &info, cprm)) goto end_coredump; - } has_dumped = 1; @@ -2050,10 +2048,8 @@ static int elf_core_dump(struct coredump_params *cprm) sz += elf_coredump_extra_notes_size(); phdr4note = kmalloc(sizeof(*phdr4note), GFP_KERNEL); - if (!phdr4note) { - coredump_report_failure("Error allocating program headers note entry"); + if (!phdr4note) goto end_coredump; - } fill_elf_note_phdr(phdr4note, sz, offset); offset += sz; @@ -2067,24 +2063,18 @@ static int elf_core_dump(struct coredump_params *cprm) if (e_phnum == PN_XNUM) { shdr4extnum = kmalloc(sizeof(*shdr4extnum), GFP_KERNEL); - if (!shdr4extnum) { - coredump_report_failure("Error allocating extra program headers"); + if (!shdr4extnum) goto end_coredump; - } fill_extnum_info(&elf, shdr4extnum, e_shoff, segs); } offset = dataoff; - if (!dump_emit(cprm, &elf, sizeof(elf))) { - coredump_report_failure("Error emitting the ELF headers"); + if (!dump_emit(cprm, &elf, sizeof(elf))) goto end_coredump; - } - if (!dump_emit(cprm, phdr4note, sizeof(*phdr4note))) { - coredump_report_failure("Error emitting the program header for notes"); + if (!dump_emit(cprm, phdr4note, sizeof(*phdr4note))) goto end_coredump; - } /* Write program headers for segments dump */ for (i = 0; i < cprm->vma_count; i++) { @@ -2107,28 +2097,20 @@ static int elf_core_dump(struct coredump_params *cprm) phdr.p_flags |= PF_X; phdr.p_align = ELF_EXEC_PAGESIZE; - if (!dump_emit(cprm, &phdr, sizeof(phdr))) { - coredump_report_failure("Error emitting program headers"); + if (!dump_emit(cprm, &phdr, sizeof(phdr))) goto end_coredump; - } } - if (!elf_core_write_extra_phdrs(cprm, offset)) { - coredump_report_failure("Error writing out extra program headers"); + if (!elf_core_write_extra_phdrs(cprm, offset)) goto end_coredump; - } /* write out the notes section */ - if (!write_note_info(&info, cprm)) { - coredump_report_failure("Error writing out notes"); + if (!write_note_info(&info, cprm)) goto end_coredump; - } /* For cell spufs and x86 xstate */ - if (elf_coredump_extra_notes_write(cprm)) { - coredump_report_failure("Error writing out extra notes"); + if (elf_coredump_extra_notes_write(cprm)) goto end_coredump; - } /* Align to page */ dump_skip_to(cprm, dataoff); @@ -2136,22 +2118,16 @@ static int elf_core_dump(struct coredump_params *cprm) for (i = 0; i < cprm->vma_count; i++) { struct core_vma_metadata *meta = cprm->vma_meta + i; - if (!dump_user_range(cprm, meta->start, meta->dump_size)) { - coredump_report_failure("Error writing out the process memory"); + if (!dump_user_range(cprm, meta->start, meta->dump_size)) goto end_coredump; - } } - if (!elf_core_write_extra_data(cprm)) { - coredump_report_failure("Error writing out extra data"); + if (!elf_core_write_extra_data(cprm)) goto end_coredump; - } if (e_phnum == PN_XNUM) { - if (!dump_emit(cprm, shdr4extnum, sizeof(*shdr4extnum))) { - coredump_report_failure("Error emitting extra program headers"); + if (!dump_emit(cprm, shdr4extnum, sizeof(*shdr4extnum))) goto end_coredump; - } } end_coredump: diff --git a/fs/coredump.c b/fs/coredump.c index 53a78b6bbb5b..45737b43dda5 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -465,17 +465,7 @@ static bool dump_interrupted(void) * but then we need to teach dump_write() to restart and clear * TIF_SIGPENDING. */ - if (fatal_signal_pending(current)) { - coredump_report_failure("interrupted: fatal signal pending"); - return true; - } - - if (freezing(current)) { - coredump_report_failure("interrupted: freezing"); - return true; - } - - return false; + return fatal_signal_pending(current) || freezing(current); } static void wait_for_dump_helpers(struct file *file) @@ -530,7 +520,7 @@ static int umh_pipe_setup(struct subprocess_info *info, struct cred *new) return err; } -int do_coredump(const kernel_siginfo_t *siginfo) +void do_coredump(const kernel_siginfo_t *siginfo) { struct core_state core_state; struct core_name cn; @@ -538,7 +528,7 @@ int do_coredump(const kernel_siginfo_t *siginfo) struct linux_binfmt * binfmt; const struct cred *old_cred; struct cred *cred; - int retval; + int retval = 0; int ispipe; size_t *argv = NULL; int argc = 0; @@ -562,20 +552,14 @@ int do_coredump(const kernel_siginfo_t *siginfo) audit_core_dumps(siginfo->si_signo); binfmt = mm->binfmt; - if (!binfmt || !binfmt->core_dump) { - retval = -ENOEXEC; + if (!binfmt || !binfmt->core_dump) goto fail; - } - if (!__get_dumpable(cprm.mm_flags)) { - retval = -EACCES; + if (!__get_dumpable(cprm.mm_flags)) goto fail; - } cred = prepare_creds(); - if (!cred) { - retval = -EPERM; + if (!cred) goto fail; - } /* * We cannot trust fsuid as being the "true" uid of the process * nor do we know its entire history. We only know it was tainted @@ -604,7 +588,6 @@ int do_coredump(const kernel_siginfo_t *siginfo) if (ispipe < 0) { coredump_report_failure("format_corename failed, aborting core"); - retval = ispipe; goto fail_unlock; } @@ -625,7 +608,6 @@ int do_coredump(const kernel_siginfo_t *siginfo) * core_pattern process dies. */ coredump_report_failure("RLIMIT_CORE is set to 1, aborting core"); - retval = -EPERM; goto fail_unlock; } cprm.limit = RLIM_INFINITY; @@ -633,7 +615,6 @@ int do_coredump(const kernel_siginfo_t *siginfo) dump_count = atomic_inc_return(&core_dump_count); if (core_pipe_limit && (core_pipe_limit < dump_count)) { coredump_report_failure("over core_pipe_limit, skipping core dump"); - retval = -E2BIG; goto fail_dropcount; } @@ -641,7 +622,6 @@ int do_coredump(const kernel_siginfo_t *siginfo) GFP_KERNEL); if (!helper_argv) { coredump_report_failure("%s failed to allocate memory", __func__); - retval = -ENOMEM; goto fail_dropcount; } for (argi = 0; argi < argc; argi++) @@ -667,16 +647,12 @@ int do_coredump(const kernel_siginfo_t *siginfo) int open_flags = O_CREAT | O_WRONLY | O_NOFOLLOW | O_LARGEFILE | O_EXCL; - if (cprm.limit < binfmt->min_coredump) { - coredump_report_failure("over coredump resource limit, skipping core dump"); - retval = -E2BIG; + if (cprm.limit < binfmt->min_coredump) goto fail_unlock; - } if (need_suid_safe && cn.corename[0] != '/') { coredump_report_failure( "this process can only dump core to a fully qualified path, skipping core dump"); - retval = -EPERM; goto fail_unlock; } @@ -722,28 +698,20 @@ int do_coredump(const kernel_siginfo_t *siginfo) } else { cprm.file = filp_open(cn.corename, open_flags, 0600); } - if (IS_ERR(cprm.file)) { - retval = PTR_ERR(cprm.file); + if (IS_ERR(cprm.file)) goto fail_unlock; - } inode = file_inode(cprm.file); - if (inode->i_nlink > 1) { - retval = -EMLINK; + if (inode->i_nlink > 1) goto close_fail; - } - if (d_unhashed(cprm.file->f_path.dentry)) { - retval = -EEXIST; + if (d_unhashed(cprm.file->f_path.dentry)) goto close_fail; - } /* * AK: actually i see no reason to not allow this for named * pipes etc, but keep the previous behaviour for now. */ - if (!S_ISREG(inode->i_mode)) { - retval = -EISDIR; + if (!S_ISREG(inode->i_mode)) goto close_fail; - } /* * Don't dump core if the filesystem changed owner or mode * of the file during file creation. This is an issue when @@ -755,22 +723,17 @@ int do_coredump(const kernel_siginfo_t *siginfo) current_fsuid())) { coredump_report_failure("Core dump to %s aborted: " "cannot preserve file owner", cn.corename); - retval = -EPERM; goto close_fail; } if ((inode->i_mode & 0677) != 0600) { coredump_report_failure("Core dump to %s aborted: " "cannot preserve file permissions", cn.corename); - retval = -EPERM; goto close_fail; } - if (!(cprm.file->f_mode & FMODE_CAN_WRITE)) { - retval = -EACCES; + if (!(cprm.file->f_mode & FMODE_CAN_WRITE)) goto close_fail; - } - retval = do_truncate(idmap, cprm.file->f_path.dentry, - 0, 0, cprm.file); - if (retval) + if (do_truncate(idmap, cprm.file->f_path.dentry, + 0, 0, cprm.file)) goto close_fail; } @@ -786,15 +749,10 @@ int do_coredump(const kernel_siginfo_t *siginfo) */ if (!cprm.file) { coredump_report_failure("Core dump to |%s disabled", cn.corename); - retval = -EPERM; goto close_fail; } - if (!dump_vma_snapshot(&cprm)) { - coredump_report_failure("Can't get VMA snapshot for core dump |%s", - cn.corename); - retval = -EACCES; + if (!dump_vma_snapshot(&cprm)) goto close_fail; - } file_start_write(cprm.file); core_dumped = binfmt->core_dump(&cprm); @@ -810,21 +768,9 @@ int do_coredump(const kernel_siginfo_t *siginfo) } file_end_write(cprm.file); free_vma_snapshot(&cprm); - } else { - coredump_report_failure("Core dump to %s%s has been interrupted", - ispipe ? "|" : "", cn.corename); - retval = -EAGAIN; - goto fail; } - coredump_report( - "written to %s%s: VMAs: %d, size %zu; core: %lld bytes, pos %lld", - ispipe ? "|" : "", cn.corename, - cprm.vma_count, cprm.vma_data_size, cprm.written, cprm.pos); if (ispipe && core_pipe_limit) wait_for_dump_helpers(cprm.file); - - retval = 0; - close_fail: if (cprm.file) filp_close(cprm.file, NULL); @@ -839,7 +785,7 @@ fail_unlock: fail_creds: put_cred(cred); fail: - return retval; + return; } /* @@ -859,16 +805,8 @@ static int __dump_emit(struct coredump_params *cprm, const void *addr, int nr) if (dump_interrupted()) return 0; n = __kernel_write(file, addr, nr, &pos); - if (n != nr) { - if (n < 0) - coredump_report_failure("failed when writing out, error %zd", n); - else - coredump_report_failure( - "partially written out, only %zd(of %d) bytes written", - n, nr); - + if (n != nr) return 0; - } file->f_pos = pos; cprm->written += n; cprm->pos += n; @@ -881,16 +819,9 @@ static int __dump_skip(struct coredump_params *cprm, size_t nr) static char zeroes[PAGE_SIZE]; struct file *file = cprm->file; if (file->f_mode & FMODE_LSEEK) { - int ret; - - if (dump_interrupted()) + if (dump_interrupted() || + vfs_llseek(file, nr, SEEK_CUR) < 0) return 0; - - ret = vfs_llseek(file, nr, SEEK_CUR); - if (ret < 0) { - coredump_report_failure("failed when seeking, error %d", ret); - return 0; - } cprm->pos += nr; return 1; } else { diff --git a/include/linux/coredump.h b/include/linux/coredump.h index edeb8532ce0f..45e598fe3476 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -42,7 +42,7 @@ extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr); extern int dump_align(struct coredump_params *cprm, int align); int dump_user_range(struct coredump_params *cprm, unsigned long start, unsigned long len); -extern int do_coredump(const kernel_siginfo_t *siginfo); +extern void do_coredump(const kernel_siginfo_t *siginfo); /* * Logging for the coredump code, ratelimited. @@ -62,11 +62,7 @@ extern int do_coredump(const kernel_siginfo_t *siginfo); #define coredump_report_failure(fmt, ...) __COREDUMP_PRINTK(KERN_WARNING, fmt, ##__VA_ARGS__) #else -static inline int do_coredump(const kernel_siginfo_t *siginfo) -{ - /* Coredump support is not available, can't fail. */ - return 0; -} +static inline void do_coredump(const kernel_siginfo_t *siginfo) {} #define coredump_report(...) #define coredump_report_failure(...) diff --git a/kernel/signal.c b/kernel/signal.c index 6e57036f947f..4344860ffcac 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2888,8 +2888,6 @@ relock: current->flags |= PF_SIGNALED; if (sig_kernel_coredump(signr)) { - int ret; - if (print_fatal_signals) print_fatal_signal(signr); proc_coredump_connector(current); @@ -2901,24 +2899,7 @@ relock: * first and our do_group_exit call below will use * that value and ignore the one we pass it. */ - ret = do_coredump(&ksig->info); - if (ret) - coredump_report_failure("coredump has not been created, error %d", - ret); - else if (!IS_ENABLED(CONFIG_COREDUMP)) { - /* - * Coredumps are not available, can't fail collecting - * the coredump. - * - * Leave a note though that the coredump is going to be - * not created. This is not an error or a warning as disabling - * support in the kernel for coredumps isn't commonplace, and - * the user must've built the kernel with the custom config so - * let them know all works as desired. - */ - coredump_report("no coredump collected as " - "that is disabled in the kernel configuration"); - } + do_coredump(&ksig->info); } /* -- cgit v1.2.3 From 26a8ea80929c518bdec5e53a5776f95919b7c88e Mon Sep 17 00:00:00 2001 From: Steve Sistare Date: Tue, 3 Sep 2024 07:25:19 -0700 Subject: mm/hugetlb: fix memfd_pin_folios resv_huge_pages leak memfd_pin_folios followed by unpin_folios leaves resv_huge_pages elevated if the pages were not already faulted in. During a normal page fault, resv_huge_pages is consumed here: hugetlb_fault() alloc_hugetlb_folio() dequeue_hugetlb_folio_vma() dequeue_hugetlb_folio_nodemask() dequeue_hugetlb_folio_node_exact() free_huge_pages-- resv_huge_pages-- During memfd_pin_folios, the page is created by calling alloc_hugetlb_folio_nodemask instead of alloc_hugetlb_folio, and resv_huge_pages is not modified: memfd_alloc_folio() alloc_hugetlb_folio_nodemask() dequeue_hugetlb_folio_nodemask() dequeue_hugetlb_folio_node_exact() free_huge_pages-- alloc_hugetlb_folio_nodemask has other callers that must not modify resv_huge_pages. Therefore, to fix, define an alternate version of alloc_hugetlb_folio_nodemask for this call site that adjusts resv_huge_pages. Link: https://lkml.kernel.org/r/1725373521-451395-4-git-send-email-steven.sistare@oracle.com Fixes: 89c1905d9c14 ("mm/gup: introduce memfd_pin_folios() for pinning memfd folios") Signed-off-by: Steve Sistare Acked-by: Vivek Kasireddy Cc: David Hildenbrand Cc: Jason Gunthorpe Cc: Matthew Wilcox Cc: Muchun Song Cc: Peter Xu Cc: Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 10 ++++++++++ mm/hugetlb.c | 17 +++++++++++++++++ mm/memfd.c | 9 ++++----- 3 files changed, 31 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 98c47c394b89..e4697539b665 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -692,6 +692,9 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask, bool allow_alloc_fallback); +struct folio *alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid, + nodemask_t *nmask, gfp_t gfp_mask); + int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping, pgoff_t idx); void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, @@ -1059,6 +1062,13 @@ static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, return NULL; } +static inline struct folio * +alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid, + nodemask_t *nmask, gfp_t gfp_mask) +{ + return NULL; +} + static inline struct folio * alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask, diff --git a/mm/hugetlb.c b/mm/hugetlb.c index def84d8bcf2d..190fa05635f4 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2390,6 +2390,23 @@ struct folio *alloc_buddy_hugetlb_folio_with_mpol(struct hstate *h, return folio; } +struct folio *alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid, + nodemask_t *nmask, gfp_t gfp_mask) +{ + struct folio *folio; + + spin_lock_irq(&hugetlb_lock); + folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, preferred_nid, + nmask); + if (folio) { + VM_BUG_ON(!h->resv_huge_pages); + h->resv_huge_pages--; + } + + spin_unlock_irq(&hugetlb_lock); + return folio; +} + /* folio migration callback function */ struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask, bool allow_alloc_fallback) diff --git a/mm/memfd.c b/mm/memfd.c index e7b7c5294d59..bfe0e7189a37 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -82,11 +82,10 @@ struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx) gfp_mask = htlb_alloc_mask(hstate_file(memfd)); gfp_mask &= ~(__GFP_HIGHMEM | __GFP_MOVABLE); - folio = alloc_hugetlb_folio_nodemask(hstate_file(memfd), - numa_node_id(), - NULL, - gfp_mask, - false); + folio = alloc_hugetlb_folio_reserve(hstate_file(memfd), + numa_node_id(), + NULL, + gfp_mask); if (folio && folio_try_get(folio)) { err = hugetlb_add_to_page_cache(folio, memfd->f_mapping, -- cgit v1.2.3 From c5b1184decc819756ae549ba54c63b6790c4ddfd Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Tue, 24 Sep 2024 14:27:10 +0800 Subject: compiler.h: specify correct attribute for .rodata..c_jump_table Currently, there is an assembler message when generating kernel/bpf/core.o under CONFIG_OBJTOOL with LoongArch compiler toolchain: Warning: setting incorrect section attributes for .rodata..c_jump_table This is because the section ".rodata..c_jump_table" should be readonly, but there is a "W" (writable) part of the flags: $ readelf -S kernel/bpf/core.o | grep -A 1 "rodata..c" [34] .rodata..c_j[...] PROGBITS 0000000000000000 0000d2e0 0000000000000800 0000000000000000 WA 0 0 8 There is no above issue on x86 due to the generated section flag is only "A" (allocatable). In order to silence the warning on LoongArch, specify the attribute like ".rodata..c_jump_table,\"a\",@progbits #" explicitly, then the section attribute of ".rodata..c_jump_table" must be readonly in the kernel/bpf/core.o file. Before: $ objdump -h kernel/bpf/core.o | grep -A 1 "rodata..c" 21 .rodata..c_jump_table 00000800 0000000000000000 0000000000000000 0000d2e0 2**3 CONTENTS, ALLOC, LOAD, RELOC, DATA After: $ objdump -h kernel/bpf/core.o | grep -A 1 "rodata..c" 21 .rodata..c_jump_table 00000800 0000000000000000 0000000000000000 0000d2e0 2**3 CONTENTS, ALLOC, LOAD, RELOC, READONLY, DATA By the way, AFAICT, maybe the root cause is related with the different compiler behavior of various archs, so to some extent this change is a workaround for LoongArch, and also there is no effect for x86 which is the only port supported by objtool before LoongArch with this patch. Link: https://lkml.kernel.org/r/20240924062710.1243-1-yangtiezhu@loongson.cn Signed-off-by: Tiezhu Yang Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: [6.9+] Signed-off-by: Andrew Morton --- include/linux/compiler.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index ec55bcce4146..4d4e23b6e3e7 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -133,7 +133,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #define annotate_unreachable() __annotate_unreachable(__COUNTER__) /* Annotate a C jump table to allow objtool to follow the code flow */ -#define __annotate_jump_table __section(".rodata..c_jump_table") +#define __annotate_jump_table __section(".rodata..c_jump_table,\"a\",@progbits #") #else /* !CONFIG_OBJTOOL */ #define annotate_reachable() -- cgit v1.2.3 From cb787f4ac0c2e439ea8d7e6387b925f74576bdf8 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 27 Sep 2024 02:56:11 +0100 Subject: [tree-wide] finally take no_llseek out no_llseek had been defined to NULL two years ago, in commit 868941b14441 ("fs: remove no_llseek") To quote that commit, At -rc1 we'll need do a mechanical removal of no_llseek - git grep -l -w no_llseek | grep -v porting.rst | while read i; do sed -i '/\/d' $i done would do it. Unfortunately, that hadn't been done. Linus, could you do that now, so that we could finally put that thing to rest? All instances are of the form .llseek = no_llseek, so it's obviously safe. Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- Documentation/watchdog/convert_drivers_to_kernel_api.rst | 1 - arch/parisc/kernel/perf.c | 1 - arch/s390/hypfs/hypfs_dbfs.c | 1 - arch/s390/hypfs/inode.c | 1 - arch/s390/kernel/debug.c | 1 - arch/s390/kernel/perf_cpum_cf.c | 1 - arch/s390/kernel/sysinfo.c | 1 - arch/s390/pci/pci_clp.c | 1 - arch/um/drivers/harddog_kern.c | 1 - arch/um/drivers/hostaudio_kern.c | 2 -- arch/x86/kernel/cpu/mce/dev-mcelog.c | 1 - arch/x86/kernel/cpu/resctrl/pseudo_lock.c | 1 - drivers/acpi/apei/erst-dbg.c | 1 - drivers/auxdisplay/charlcd.c | 1 - drivers/block/mtip32xx/mtip32xx.c | 2 -- drivers/block/pktcdvd.c | 1 - drivers/block/ublk_drv.c | 1 - drivers/bluetooth/hci_vhci.c | 1 - drivers/bus/moxtet.c | 2 -- drivers/char/applicom.c | 1 - drivers/char/ds1620.c | 1 - drivers/char/dtlk.c | 1 - drivers/char/hpet.c | 1 - drivers/char/ipmi/ipmi_watchdog.c | 1 - drivers/char/pc8736x_gpio.c | 1 - drivers/char/ppdev.c | 1 - drivers/char/scx200_gpio.c | 1 - drivers/char/sonypi.c | 1 - drivers/char/tpm/tpm-dev.c | 1 - drivers/char/tpm/tpm_vtpm_proxy.c | 1 - drivers/char/tpm/tpmrm-dev.c | 1 - drivers/char/virtio_console.c | 1 - drivers/counter/counter-chrdev.c | 1 - drivers/firewire/core-cdev.c | 1 - drivers/firmware/arm_scmi/driver.c | 1 - drivers/firmware/arm_scmi/raw_mode.c | 5 ----- drivers/firmware/efi/capsule-loader.c | 1 - drivers/firmware/efi/test/efi_test.c | 1 - drivers/firmware/turris-mox-rwtm.c | 1 - drivers/gnss/core.c | 1 - drivers/gpio/gpio-mockup.c | 1 - drivers/gpio/gpio-sloppy-logic-analyzer.c | 1 - drivers/gpio/gpiolib-cdev.c | 1 - drivers/gpu/drm/drm_file.c | 1 - drivers/gpu/drm/i915/i915_perf.c | 1 - drivers/gpu/drm/msm/msm_perf.c | 1 - drivers/gpu/drm/msm/msm_rd.c | 1 - drivers/gpu/drm/xe/xe_oa.c | 1 - drivers/hid/uhid.c | 1 - drivers/hwmon/asus_atk0110.c | 1 - drivers/hwmon/fschmd.c | 1 - drivers/hwmon/w83793.c | 1 - drivers/hwtracing/coresight/coresight-etb10.c | 1 - drivers/hwtracing/coresight/coresight-tmc-core.c | 1 - drivers/hwtracing/coresight/ultrasoc-smb.c | 1 - drivers/hwtracing/intel_th/msu.c | 1 - drivers/hwtracing/stm/core.c | 1 - drivers/i2c/i2c-dev.c | 1 - drivers/infiniband/core/ucma.c | 1 - drivers/infiniband/core/user_mad.c | 2 -- drivers/infiniband/core/uverbs_main.c | 4 ---- drivers/infiniband/hw/hfi1/fault.c | 1 - drivers/infiniband/hw/mlx5/devx.c | 2 -- drivers/input/evdev.c | 1 - drivers/input/joydev.c | 1 - drivers/input/keyboard/applespi.c | 1 - drivers/input/misc/uinput.c | 1 - drivers/input/serio/userio.c | 1 - drivers/iommu/iommufd/fault.c | 1 - drivers/isdn/capi/capi.c | 1 - drivers/isdn/mISDN/timerdev.c | 1 - drivers/leds/uleds.c | 1 - drivers/macintosh/adb.c | 1 - drivers/macintosh/smu.c | 1 - drivers/media/cec/core/cec-api.c | 1 - drivers/media/mc/mc-devnode.c | 1 - drivers/media/rc/lirc_dev.c | 1 - drivers/media/usb/uvc/uvc_debugfs.c | 1 - drivers/media/v4l2-core/v4l2-dev.c | 1 - drivers/message/fusion/mptctl.c | 1 - drivers/misc/lis3lv02d/lis3lv02d.c | 1 - drivers/misc/mei/main.c | 1 - drivers/misc/ntsync.c | 2 -- drivers/misc/phantom.c | 1 - drivers/mmc/core/block.c | 1 - drivers/mtd/ubi/cdev.c | 2 -- drivers/mtd/ubi/debug.c | 1 - drivers/net/netdevsim/fib.c | 1 - drivers/net/tap.c | 1 - drivers/net/tun.c | 1 - drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c | 1 - drivers/net/wireless/intel/iwlwifi/mvm/d3.c | 1 - drivers/platform/chrome/cros_ec_debugfs.c | 1 - drivers/platform/chrome/wilco_ec/debugfs.c | 1 - drivers/platform/chrome/wilco_ec/event.c | 1 - drivers/platform/chrome/wilco_ec/telemetry.c | 1 - drivers/platform/surface/surface_aggregator_cdev.c | 1 - drivers/platform/surface/surface_dtx.c | 1 - drivers/pps/pps.c | 1 - drivers/rtc/dev.c | 1 - drivers/rtc/rtc-m41t80.c | 1 - drivers/s390/char/fs3270.c | 1 - drivers/s390/char/sclp_ctl.c | 1 - drivers/s390/char/tape_char.c | 1 - drivers/s390/char/uvdevice.c | 1 - drivers/s390/char/vmcp.c | 1 - drivers/s390/char/vmlogrdr.c | 1 - drivers/s390/char/zcore.c | 2 -- drivers/s390/cio/chsc_sch.c | 1 - drivers/s390/cio/css.c | 1 - drivers/s390/crypto/pkey_api.c | 1 - drivers/s390/crypto/zcrypt_api.c | 1 - drivers/sbus/char/openprom.c | 1 - drivers/sbus/char/uctrl.c | 1 - drivers/scsi/sg.c | 1 - drivers/spi/spidev.c | 1 - drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c | 1 - drivers/tty/tty_io.c | 3 --- drivers/usb/gadget/function/f_fs.c | 2 -- drivers/usb/gadget/legacy/inode.c | 2 -- drivers/usb/gadget/legacy/raw_gadget.c | 1 - drivers/usb/gadget/udc/atmel_usba_udc.c | 1 - drivers/usb/misc/ldusb.c | 1 - drivers/usb/mon/mon_bin.c | 1 - drivers/usb/mon/mon_stat.c | 1 - drivers/usb/mon/mon_text.c | 2 -- drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c | 2 -- drivers/vfio/pci/mlx5/main.c | 2 -- drivers/vfio/pci/pds/lm.c | 2 -- drivers/vfio/pci/qat/main.c | 2 -- drivers/virt/coco/tdx-guest/tdx-guest.c | 1 - drivers/watchdog/acquirewdt.c | 1 - drivers/watchdog/advantechwdt.c | 1 - drivers/watchdog/alim1535_wdt.c | 1 - drivers/watchdog/alim7101_wdt.c | 1 - drivers/watchdog/at91rm9200_wdt.c | 1 - drivers/watchdog/ath79_wdt.c | 1 - drivers/watchdog/cpu5wdt.c | 1 - drivers/watchdog/cpwd.c | 1 - drivers/watchdog/eurotechwdt.c | 1 - drivers/watchdog/gef_wdt.c | 1 - drivers/watchdog/geodewdt.c | 1 - drivers/watchdog/ib700wdt.c | 1 - drivers/watchdog/ibmasr.c | 1 - drivers/watchdog/indydog.c | 1 - drivers/watchdog/it8712f_wdt.c | 1 - drivers/watchdog/m54xx_wdt.c | 1 - drivers/watchdog/machzwd.c | 1 - drivers/watchdog/mixcomwd.c | 1 - drivers/watchdog/mtx-1_wdt.c | 1 - drivers/watchdog/nv_tco.c | 1 - drivers/watchdog/pc87413_wdt.c | 1 - drivers/watchdog/pcwd.c | 2 -- drivers/watchdog/pcwd_pci.c | 2 -- drivers/watchdog/pcwd_usb.c | 2 -- drivers/watchdog/pika_wdt.c | 1 - drivers/watchdog/rc32434_wdt.c | 1 - drivers/watchdog/rdc321x_wdt.c | 1 - drivers/watchdog/riowd.c | 1 - drivers/watchdog/sa1100_wdt.c | 1 - drivers/watchdog/sb_wdog.c | 1 - drivers/watchdog/sbc60xxwdt.c | 1 - drivers/watchdog/sbc7240_wdt.c | 1 - drivers/watchdog/sbc8360.c | 1 - drivers/watchdog/sbc_epx_c3.c | 1 - drivers/watchdog/sbc_fitpc2_wdt.c | 1 - drivers/watchdog/sc1200wdt.c | 1 - drivers/watchdog/sc520_wdt.c | 1 - drivers/watchdog/sch311x_wdt.c | 1 - drivers/watchdog/scx200_wdt.c | 1 - drivers/watchdog/smsc37b787_wdt.c | 1 - drivers/watchdog/w83877f_wdt.c | 1 - drivers/watchdog/w83977f_wdt.c | 1 - drivers/watchdog/wafer5823wdt.c | 1 - drivers/watchdog/wdrtas.c | 2 -- drivers/watchdog/wdt.c | 2 -- drivers/watchdog/wdt285.c | 1 - drivers/watchdog/wdt977.c | 1 - drivers/watchdog/wdt_pci.c | 2 -- drivers/xen/evtchn.c | 1 - drivers/xen/mcelog.c | 1 - drivers/xen/xenbus/xenbus_dev_frontend.c | 1 - fs/bcachefs/chardev.c | 1 - fs/bcachefs/thread_with_file.c | 2 -- fs/debugfs/file.c | 1 - fs/dlm/debug_fs.c | 1 - fs/efivarfs/file.c | 1 - fs/fsopen.c | 1 - fs/fuse/control.c | 4 ---- fs/fuse/dev.c | 1 - fs/nsfs.c | 1 - fs/pipe.c | 1 - fs/ubifs/debug.c | 2 -- include/linux/debugfs.h | 1 - include/linux/fs.h | 1 - kernel/bpf/bpf_iter.c | 1 - kernel/events/core.c | 1 - kernel/power/user.c | 1 - kernel/relay.c | 1 - kernel/time/posix-clock.c | 1 - kernel/trace/rv/rv.c | 3 --- kernel/trace/rv/rv_reactors.c | 1 - kernel/trace/trace.c | 3 --- mm/huge_memory.c | 1 - net/mac80211/rc80211_minstrel_ht_debugfs.c | 2 -- net/rfkill/core.c | 1 - net/socket.c | 1 - net/sunrpc/cache.c | 4 ---- net/sunrpc/rpc_pipe.c | 1 - samples/vfio-mdev/mtty.c | 2 -- scripts/coccinelle/api/stream_open.cocci | 1 - sound/core/control.c | 1 - sound/core/oss/mixer_oss.c | 1 - sound/core/oss/pcm_oss.c | 1 - sound/core/pcm_native.c | 2 -- sound/core/rawmidi.c | 1 - sound/core/seq/seq_clientmgr.c | 1 - sound/core/timer.c | 1 - sound/oss/dmasound/dmasound_core.c | 3 --- sound/soc/intel/avs/debugfs.c | 3 --- virt/kvm/kvm_main.c | 1 - 221 files changed, 270 deletions(-) (limited to 'include/linux') diff --git a/Documentation/watchdog/convert_drivers_to_kernel_api.rst b/Documentation/watchdog/convert_drivers_to_kernel_api.rst index a1c3f038ce0e..e83609a5d007 100644 --- a/Documentation/watchdog/convert_drivers_to_kernel_api.rst +++ b/Documentation/watchdog/convert_drivers_to_kernel_api.rst @@ -75,7 +75,6 @@ Example conversion:: -static const struct file_operations s3c2410wdt_fops = { - .owner = THIS_MODULE, - - .llseek = no_llseek, - .write = s3c2410wdt_write, - .unlocked_ioctl = s3c2410wdt_ioctl, - .open = s3c2410wdt_open, diff --git a/arch/parisc/kernel/perf.c b/arch/parisc/kernel/perf.c index b0f0816879df..5e8e37a722ef 100644 --- a/arch/parisc/kernel/perf.c +++ b/arch/parisc/kernel/perf.c @@ -466,7 +466,6 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg) } static const struct file_operations perf_fops = { - .llseek = no_llseek, .read = perf_read, .write = perf_write, .unlocked_ioctl = perf_ioctl, diff --git a/arch/s390/hypfs/hypfs_dbfs.c b/arch/s390/hypfs/hypfs_dbfs.c index 0e855c5e91c5..5d9effb0867c 100644 --- a/arch/s390/hypfs/hypfs_dbfs.c +++ b/arch/s390/hypfs/hypfs_dbfs.c @@ -76,7 +76,6 @@ static long dbfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg) static const struct file_operations dbfs_ops = { .read = dbfs_read, - .llseek = no_llseek, .unlocked_ioctl = dbfs_ioctl, }; diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index 858beaf4a8cb..d428635abf08 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -443,7 +443,6 @@ static const struct file_operations hypfs_file_ops = { .release = hypfs_release, .read_iter = hypfs_read_iter, .write_iter = hypfs_write_iter, - .llseek = no_llseek, }; static struct file_system_type hypfs_type = { diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index bce50ca75ea7..e62bea9ab21e 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -163,7 +163,6 @@ static const struct file_operations debug_file_ops = { .write = debug_input, .open = debug_open, .release = debug_close, - .llseek = no_llseek, }; static struct dentry *debug_debugfs_root_entry; diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index 18b0d025f3a2..e2e0aa463fbd 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -1698,7 +1698,6 @@ static const struct file_operations cfset_fops = { .release = cfset_release, .unlocked_ioctl = cfset_ioctl, .compat_ioctl = cfset_ioctl, - .llseek = no_llseek }; static struct miscdevice cfset_dev = { diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c index 2be30a96696a..88055f58fbda 100644 --- a/arch/s390/kernel/sysinfo.c +++ b/arch/s390/kernel/sysinfo.c @@ -498,7 +498,6 @@ static const struct file_operations stsi_##fc##_##s1##_##s2##_fs_ops = { \ .open = stsi_open_##fc##_##s1##_##s2, \ .release = stsi_release, \ .read = stsi_read, \ - .llseek = no_llseek, \ }; static int stsi_release(struct inode *inode, struct file *file) diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c index ee90a91ed888..6f55a59a0871 100644 --- a/arch/s390/pci/pci_clp.c +++ b/arch/s390/pci/pci_clp.c @@ -657,7 +657,6 @@ static const struct file_operations clp_misc_fops = { .release = clp_misc_release, .unlocked_ioctl = clp_misc_ioctl, .compat_ioctl = clp_misc_ioctl, - .llseek = no_llseek, }; static struct miscdevice clp_misc_device = { diff --git a/arch/um/drivers/harddog_kern.c b/arch/um/drivers/harddog_kern.c index 99a7144b229f..819aabb4ecdc 100644 --- a/arch/um/drivers/harddog_kern.c +++ b/arch/um/drivers/harddog_kern.c @@ -164,7 +164,6 @@ static const struct file_operations harddog_fops = { .compat_ioctl = compat_ptr_ioctl, .open = harddog_open, .release = harddog_release, - .llseek = no_llseek, }; static struct miscdevice harddog_miscdev = { diff --git a/arch/um/drivers/hostaudio_kern.c b/arch/um/drivers/hostaudio_kern.c index c42b793bce65..9d228878cea2 100644 --- a/arch/um/drivers/hostaudio_kern.c +++ b/arch/um/drivers/hostaudio_kern.c @@ -291,7 +291,6 @@ static int hostmixer_release(struct inode *inode, struct file *file) static const struct file_operations hostaudio_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = hostaudio_read, .write = hostaudio_write, .poll = hostaudio_poll, @@ -304,7 +303,6 @@ static const struct file_operations hostaudio_fops = { static const struct file_operations hostmixer_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .unlocked_ioctl = hostmixer_ioctl_mixdev, .open = hostmixer_open_mixdev, .release = hostmixer_release, diff --git a/arch/x86/kernel/cpu/mce/dev-mcelog.c b/arch/x86/kernel/cpu/mce/dev-mcelog.c index a3aa0199222e..af44fd5dbd7c 100644 --- a/arch/x86/kernel/cpu/mce/dev-mcelog.c +++ b/arch/x86/kernel/cpu/mce/dev-mcelog.c @@ -331,7 +331,6 @@ static const struct file_operations mce_chrdev_ops = { .poll = mce_chrdev_poll, .unlocked_ioctl = mce_chrdev_ioctl, .compat_ioctl = compat_ptr_ioctl, - .llseek = no_llseek, }; static struct miscdevice mce_chrdev_device = { diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c index e69489d48625..972e6b6b0481 100644 --- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c +++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c @@ -1567,7 +1567,6 @@ static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma) static const struct file_operations pseudo_lock_dev_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = NULL, .write = NULL, .open = pseudo_lock_dev_open, diff --git a/drivers/acpi/apei/erst-dbg.c b/drivers/acpi/apei/erst-dbg.c index 8bc71cdc2270..246076341e8c 100644 --- a/drivers/acpi/apei/erst-dbg.c +++ b/drivers/acpi/apei/erst-dbg.c @@ -199,7 +199,6 @@ static const struct file_operations erst_dbg_ops = { .read = erst_dbg_read, .write = erst_dbg_write, .unlocked_ioctl = erst_dbg_ioctl, - .llseek = no_llseek, }; static struct miscdevice erst_dbg_dev = { diff --git a/drivers/auxdisplay/charlcd.c b/drivers/auxdisplay/charlcd.c index bb9463814454..19b619376d48 100644 --- a/drivers/auxdisplay/charlcd.c +++ b/drivers/auxdisplay/charlcd.c @@ -526,7 +526,6 @@ static const struct file_operations charlcd_fops = { .write = charlcd_write, .open = charlcd_open, .release = charlcd_release, - .llseek = no_llseek, }; static struct miscdevice charlcd_dev = { diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 11901f2812ad..223faa9d5ffd 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -2259,14 +2259,12 @@ static const struct file_operations mtip_regs_fops = { .owner = THIS_MODULE, .open = simple_open, .read = mtip_hw_read_registers, - .llseek = no_llseek, }; static const struct file_operations mtip_flags_fops = { .owner = THIS_MODULE, .open = simple_open, .read = mtip_hw_read_flags, - .llseek = no_llseek, }; static void mtip_hw_debugfs_init(struct driver_data *dd) diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 3edb37a41312..499c110465e3 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -2835,7 +2835,6 @@ static const struct file_operations pkt_ctl_fops = { .compat_ioctl = pkt_ctl_compat_ioctl, #endif .owner = THIS_MODULE, - .llseek = no_llseek, }; static struct miscdevice pkt_misc = { diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index bca06bfb4bc3..a6c8e5cc6051 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -1983,7 +1983,6 @@ static const struct file_operations ublk_ch_fops = { .owner = THIS_MODULE, .open = ublk_ch_open, .release = ublk_ch_release, - .llseek = no_llseek, .read_iter = ublk_ch_read_iter, .write_iter = ublk_ch_write_iter, .uring_cmd = ublk_ch_uring_cmd, diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c index 43e9ac5a3324..aa6af351d02d 100644 --- a/drivers/bluetooth/hci_vhci.c +++ b/drivers/bluetooth/hci_vhci.c @@ -679,7 +679,6 @@ static const struct file_operations vhci_fops = { .poll = vhci_poll, .open = vhci_open, .release = vhci_release, - .llseek = no_llseek, }; static struct miscdevice vhci_miscdev = { diff --git a/drivers/bus/moxtet.c b/drivers/bus/moxtet.c index 8412406c4f1d..6276551d7968 100644 --- a/drivers/bus/moxtet.c +++ b/drivers/bus/moxtet.c @@ -484,7 +484,6 @@ static const struct file_operations input_fops = { .owner = THIS_MODULE, .open = moxtet_debug_open, .read = input_read, - .llseek = no_llseek, }; static ssize_t output_read(struct file *file, char __user *buf, size_t len, @@ -549,7 +548,6 @@ static const struct file_operations output_fops = { .open = moxtet_debug_open, .read = output_read, .write = output_write, - .llseek = no_llseek, }; static int moxtet_register_debugfs(struct moxtet *moxtet) diff --git a/drivers/char/applicom.c b/drivers/char/applicom.c index 69314532f38c..9fed9706d9cd 100644 --- a/drivers/char/applicom.c +++ b/drivers/char/applicom.c @@ -111,7 +111,6 @@ static irqreturn_t ac_interrupt(int, void *); static const struct file_operations ac_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = ac_read, .write = ac_write, .unlocked_ioctl = ac_ioctl, diff --git a/drivers/char/ds1620.c b/drivers/char/ds1620.c index a4f4291b4492..44a1cdbd4bfb 100644 --- a/drivers/char/ds1620.c +++ b/drivers/char/ds1620.c @@ -353,7 +353,6 @@ static const struct file_operations ds1620_fops = { .open = ds1620_open, .read = ds1620_read, .unlocked_ioctl = ds1620_unlocked_ioctl, - .llseek = no_llseek, }; static struct miscdevice ds1620_miscdev = { diff --git a/drivers/char/dtlk.c b/drivers/char/dtlk.c index 5a1a73310e97..27f5f9d19531 100644 --- a/drivers/char/dtlk.c +++ b/drivers/char/dtlk.c @@ -107,7 +107,6 @@ static const struct file_operations dtlk_fops = .unlocked_ioctl = dtlk_ioctl, .open = dtlk_open, .release = dtlk_release, - .llseek = no_llseek, }; /* local prototypes */ diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c index 3dadc4accee3..e904e476e49a 100644 --- a/drivers/char/hpet.c +++ b/drivers/char/hpet.c @@ -700,7 +700,6 @@ hpet_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) static const struct file_operations hpet_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = hpet_read, .poll = hpet_poll, .unlocked_ioctl = hpet_ioctl, diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c index 9a459257489f..335eea80054e 100644 --- a/drivers/char/ipmi/ipmi_watchdog.c +++ b/drivers/char/ipmi/ipmi_watchdog.c @@ -903,7 +903,6 @@ static const struct file_operations ipmi_wdog_fops = { .open = ipmi_open, .release = ipmi_close, .fasync = ipmi_fasync, - .llseek = no_llseek, }; static struct miscdevice ipmi_wdog_miscdev = { diff --git a/drivers/char/pc8736x_gpio.c b/drivers/char/pc8736x_gpio.c index c39a836ebd15..5f4696813cea 100644 --- a/drivers/char/pc8736x_gpio.c +++ b/drivers/char/pc8736x_gpio.c @@ -235,7 +235,6 @@ static const struct file_operations pc8736x_gpio_fileops = { .open = pc8736x_gpio_open, .write = nsc_gpio_write, .read = nsc_gpio_read, - .llseek = no_llseek, }; static void __init pc8736x_init_shadow(void) diff --git a/drivers/char/ppdev.c b/drivers/char/ppdev.c index eaff98dbaa8c..d1dfbd8d4d42 100644 --- a/drivers/char/ppdev.c +++ b/drivers/char/ppdev.c @@ -786,7 +786,6 @@ static const struct class ppdev_class = { static const struct file_operations pp_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = pp_read, .write = pp_write, .poll = pp_poll, diff --git a/drivers/char/scx200_gpio.c b/drivers/char/scx200_gpio.c index 9f701dcba95c..700e6affea6f 100644 --- a/drivers/char/scx200_gpio.c +++ b/drivers/char/scx200_gpio.c @@ -68,7 +68,6 @@ static const struct file_operations scx200_gpio_fileops = { .read = nsc_gpio_read, .open = scx200_gpio_open, .release = scx200_gpio_release, - .llseek = no_llseek, }; static struct cdev scx200_gpio_cdev; /* use 1 cdev for all pins */ diff --git a/drivers/char/sonypi.c b/drivers/char/sonypi.c index bb5115b1736a..0f8185e541ed 100644 --- a/drivers/char/sonypi.c +++ b/drivers/char/sonypi.c @@ -1054,7 +1054,6 @@ static const struct file_operations sonypi_misc_fops = { .release = sonypi_misc_release, .fasync = sonypi_misc_fasync, .unlocked_ioctl = sonypi_misc_ioctl, - .llseek = no_llseek, }; static struct miscdevice sonypi_misc_device = { diff --git a/drivers/char/tpm/tpm-dev.c b/drivers/char/tpm/tpm-dev.c index e2c0baa69fef..97c94b5e9340 100644 --- a/drivers/char/tpm/tpm-dev.c +++ b/drivers/char/tpm/tpm-dev.c @@ -59,7 +59,6 @@ static int tpm_release(struct inode *inode, struct file *file) const struct file_operations tpm_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .open = tpm_open, .read = tpm_common_read, .write = tpm_common_write, diff --git a/drivers/char/tpm/tpm_vtpm_proxy.c b/drivers/char/tpm/tpm_vtpm_proxy.c index 11c502039faf..8fe4a01eea12 100644 --- a/drivers/char/tpm/tpm_vtpm_proxy.c +++ b/drivers/char/tpm/tpm_vtpm_proxy.c @@ -243,7 +243,6 @@ static int vtpm_proxy_fops_release(struct inode *inode, struct file *filp) static const struct file_operations vtpm_proxy_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = vtpm_proxy_fops_read, .write = vtpm_proxy_fops_write, .poll = vtpm_proxy_fops_poll, diff --git a/drivers/char/tpm/tpmrm-dev.c b/drivers/char/tpm/tpmrm-dev.c index eef0fb06ea83..c25df7ea064e 100644 --- a/drivers/char/tpm/tpmrm-dev.c +++ b/drivers/char/tpm/tpmrm-dev.c @@ -46,7 +46,6 @@ static int tpmrm_release(struct inode *inode, struct file *file) const struct file_operations tpmrm_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .open = tpmrm_open, .read = tpm_common_read, .write = tpm_common_write, diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index de7d720d99fa..99a7f2441e70 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -1093,7 +1093,6 @@ static const struct file_operations port_fops = { .poll = port_fops_poll, .release = port_fops_release, .fasync = port_fops_fasync, - .llseek = no_llseek, }; /* diff --git a/drivers/counter/counter-chrdev.c b/drivers/counter/counter-chrdev.c index afc94d0062b1..3ee75e1a78cd 100644 --- a/drivers/counter/counter-chrdev.c +++ b/drivers/counter/counter-chrdev.c @@ -454,7 +454,6 @@ out_unlock: static const struct file_operations counter_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = counter_chrdev_read, .poll = counter_chrdev_poll, .unlocked_ioctl = counter_chrdev_ioctl, diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c index 518eaa073b2b..b360dca2c69e 100644 --- a/drivers/firewire/core-cdev.c +++ b/drivers/firewire/core-cdev.c @@ -1911,7 +1911,6 @@ static __poll_t fw_device_op_poll(struct file *file, poll_table * pt) const struct file_operations fw_device_ops = { .owner = THIS_MODULE, - .llseek = no_llseek, .open = fw_device_op_open, .read = fw_device_op_read, .unlocked_ioctl = fw_device_op_ioctl, diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index 69c15135371c..88c5c4ff4bb6 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -2886,7 +2886,6 @@ static ssize_t reset_all_on_write(struct file *filp, const char __user *buf, static const struct file_operations fops_reset_counts = { .owner = THIS_MODULE, .open = simple_open, - .llseek = no_llseek, .write = reset_all_on_write, }; diff --git a/drivers/firmware/arm_scmi/raw_mode.c b/drivers/firmware/arm_scmi/raw_mode.c index 130d13e9cd6b..9e89a6a763da 100644 --- a/drivers/firmware/arm_scmi/raw_mode.c +++ b/drivers/firmware/arm_scmi/raw_mode.c @@ -950,7 +950,6 @@ static const struct file_operations scmi_dbg_raw_mode_reset_fops = { .open = scmi_dbg_raw_mode_open, .release = scmi_dbg_raw_mode_release, .write = scmi_dbg_raw_mode_reset_write, - .llseek = no_llseek, .owner = THIS_MODULE, }; @@ -960,7 +959,6 @@ static const struct file_operations scmi_dbg_raw_mode_message_fops = { .read = scmi_dbg_raw_mode_message_read, .write = scmi_dbg_raw_mode_message_write, .poll = scmi_dbg_raw_mode_message_poll, - .llseek = no_llseek, .owner = THIS_MODULE, }; @@ -977,7 +975,6 @@ static const struct file_operations scmi_dbg_raw_mode_message_async_fops = { .read = scmi_dbg_raw_mode_message_read, .write = scmi_dbg_raw_mode_message_async_write, .poll = scmi_dbg_raw_mode_message_poll, - .llseek = no_llseek, .owner = THIS_MODULE, }; @@ -1001,7 +998,6 @@ static const struct file_operations scmi_dbg_raw_mode_notification_fops = { .release = scmi_dbg_raw_mode_release, .read = scmi_test_dbg_raw_mode_notif_read, .poll = scmi_test_dbg_raw_mode_notif_poll, - .llseek = no_llseek, .owner = THIS_MODULE, }; @@ -1025,7 +1021,6 @@ static const struct file_operations scmi_dbg_raw_mode_errors_fops = { .release = scmi_dbg_raw_mode_release, .read = scmi_test_dbg_raw_mode_errors_read, .poll = scmi_test_dbg_raw_mode_errors_poll, - .llseek = no_llseek, .owner = THIS_MODULE, }; diff --git a/drivers/firmware/efi/capsule-loader.c b/drivers/firmware/efi/capsule-loader.c index 97bafb5f7038..0c17bdd388e1 100644 --- a/drivers/firmware/efi/capsule-loader.c +++ b/drivers/firmware/efi/capsule-loader.c @@ -309,7 +309,6 @@ static const struct file_operations efi_capsule_fops = { .open = efi_capsule_open, .write = efi_capsule_write, .release = efi_capsule_release, - .llseek = no_llseek, }; static struct miscdevice efi_capsule_misc = { diff --git a/drivers/firmware/efi/test/efi_test.c b/drivers/firmware/efi/test/efi_test.c index 47d67bb0a516..9e2628728aad 100644 --- a/drivers/firmware/efi/test/efi_test.c +++ b/drivers/firmware/efi/test/efi_test.c @@ -750,7 +750,6 @@ static const struct file_operations efi_test_fops = { .unlocked_ioctl = efi_test_ioctl, .open = efi_test_open, .release = efi_test_close, - .llseek = no_llseek, }; static struct miscdevice efi_test_dev = { diff --git a/drivers/firmware/turris-mox-rwtm.c b/drivers/firmware/turris-mox-rwtm.c index 525ebdc7ded5..f3bc0d427825 100644 --- a/drivers/firmware/turris-mox-rwtm.c +++ b/drivers/firmware/turris-mox-rwtm.c @@ -386,7 +386,6 @@ static const struct file_operations do_sign_fops = { .open = rwtm_debug_open, .read = do_sign_read, .write = do_sign_write, - .llseek = no_llseek, }; static void rwtm_debugfs_release(void *root) diff --git a/drivers/gnss/core.c b/drivers/gnss/core.c index 48f2ee0f78c4..883ef86ad3fc 100644 --- a/drivers/gnss/core.c +++ b/drivers/gnss/core.c @@ -206,7 +206,6 @@ static const struct file_operations gnss_fops = { .read = gnss_read, .write = gnss_write, .poll = gnss_poll, - .llseek = no_llseek, }; static struct class *gnss_class; diff --git a/drivers/gpio/gpio-mockup.c b/drivers/gpio/gpio-mockup.c index 455eecf6380e..d39c6618bade 100644 --- a/drivers/gpio/gpio-mockup.c +++ b/drivers/gpio/gpio-mockup.c @@ -347,7 +347,6 @@ static const struct file_operations gpio_mockup_debugfs_ops = { .open = gpio_mockup_debugfs_open, .read = gpio_mockup_debugfs_read, .write = gpio_mockup_debugfs_write, - .llseek = no_llseek, .release = single_release, }; diff --git a/drivers/gpio/gpio-sloppy-logic-analyzer.c b/drivers/gpio/gpio-sloppy-logic-analyzer.c index aed6d1f6cfc3..07e0d7180579 100644 --- a/drivers/gpio/gpio-sloppy-logic-analyzer.c +++ b/drivers/gpio/gpio-sloppy-logic-analyzer.c @@ -217,7 +217,6 @@ static const struct file_operations fops_trigger = { .owner = THIS_MODULE, .open = trigger_open, .write = trigger_write, - .llseek = no_llseek, .release = single_release, }; diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c index 5aac59de0d76..78c9d9ed3d68 100644 --- a/drivers/gpio/gpiolib-cdev.c +++ b/drivers/gpio/gpiolib-cdev.c @@ -2842,7 +2842,6 @@ static const struct file_operations gpio_fileops = { .poll = lineinfo_watch_poll, .read = lineinfo_watch_read, .owner = THIS_MODULE, - .llseek = no_llseek, .unlocked_ioctl = gpio_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = gpio_ioctl_compat, diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c index 07e493d14d0c..ad1dc638c83b 100644 --- a/drivers/gpu/drm/drm_file.c +++ b/drivers/gpu/drm/drm_file.c @@ -103,7 +103,6 @@ bool drm_dev_needs_global_mutex(struct drm_device *dev) * .compat_ioctl = drm_compat_ioctl, // NULL if CONFIG_COMPAT=n * .poll = drm_poll, * .read = drm_read, - * .llseek = no_llseek, * .mmap = drm_gem_mmap, * }; * diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 025a79fe5920..2406cda75b7b 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -3751,7 +3751,6 @@ static int i915_perf_release(struct inode *inode, struct file *file) static const struct file_operations fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .release = i915_perf_release, .poll = i915_perf_poll, .read = i915_perf_read, diff --git a/drivers/gpu/drm/msm/msm_perf.c b/drivers/gpu/drm/msm/msm_perf.c index 3d3da79fec2a..d3c7889aaf26 100644 --- a/drivers/gpu/drm/msm/msm_perf.c +++ b/drivers/gpu/drm/msm/msm_perf.c @@ -192,7 +192,6 @@ static const struct file_operations perf_debugfs_fops = { .owner = THIS_MODULE, .open = perf_open, .read = perf_read, - .llseek = no_llseek, .release = perf_release, }; diff --git a/drivers/gpu/drm/msm/msm_rd.c b/drivers/gpu/drm/msm/msm_rd.c index ca44fd291c5b..39138e190cb9 100644 --- a/drivers/gpu/drm/msm/msm_rd.c +++ b/drivers/gpu/drm/msm/msm_rd.c @@ -227,7 +227,6 @@ static const struct file_operations rd_debugfs_fops = { .owner = THIS_MODULE, .open = rd_open, .read = rd_read, - .llseek = no_llseek, .release = rd_release, }; diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c index 0369cc016f6a..eae38a49ee8e 100644 --- a/drivers/gpu/drm/xe/xe_oa.c +++ b/drivers/gpu/drm/xe/xe_oa.c @@ -1263,7 +1263,6 @@ static int xe_oa_mmap(struct file *file, struct vm_area_struct *vma) static const struct file_operations xe_oa_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .release = xe_oa_release, .poll = xe_oa_poll, .read = xe_oa_read, diff --git a/drivers/hid/uhid.c b/drivers/hid/uhid.c index a54c7995b9be..21a70420151e 100644 --- a/drivers/hid/uhid.c +++ b/drivers/hid/uhid.c @@ -803,7 +803,6 @@ static const struct file_operations uhid_fops = { .read = uhid_char_read, .write = uhid_char_write, .poll = uhid_char_poll, - .llseek = no_llseek, }; static struct miscdevice uhid_misc = { diff --git a/drivers/hwmon/asus_atk0110.c b/drivers/hwmon/asus_atk0110.c index 3751c1e3eddd..1dc7e24fe4c5 100644 --- a/drivers/hwmon/asus_atk0110.c +++ b/drivers/hwmon/asus_atk0110.c @@ -783,7 +783,6 @@ static const struct file_operations atk_debugfs_ggrp_fops = { .read = atk_debugfs_ggrp_read, .open = atk_debugfs_ggrp_open, .release = atk_debugfs_ggrp_release, - .llseek = no_llseek, }; static void atk_debugfs_init(struct atk_data *data) diff --git a/drivers/hwmon/fschmd.c b/drivers/hwmon/fschmd.c index 1811f84d835e..a303959879ef 100644 --- a/drivers/hwmon/fschmd.c +++ b/drivers/hwmon/fschmd.c @@ -948,7 +948,6 @@ static long watchdog_ioctl(struct file *filp, unsigned int cmd, static const struct file_operations watchdog_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .open = watchdog_open, .release = watchdog_release, .write = watchdog_write, diff --git a/drivers/hwmon/w83793.c b/drivers/hwmon/w83793.c index 0acf6bd0227f..67728f60333f 100644 --- a/drivers/hwmon/w83793.c +++ b/drivers/hwmon/w83793.c @@ -1451,7 +1451,6 @@ static long watchdog_ioctl(struct file *filp, unsigned int cmd, static const struct file_operations watchdog_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .open = watchdog_open, .release = watchdog_close, .write = watchdog_write, diff --git a/drivers/hwtracing/coresight/coresight-etb10.c b/drivers/hwtracing/coresight/coresight-etb10.c index 7edd3f1d0d46..aea9ac9c4bd0 100644 --- a/drivers/hwtracing/coresight/coresight-etb10.c +++ b/drivers/hwtracing/coresight/coresight-etb10.c @@ -652,7 +652,6 @@ static const struct file_operations etb_fops = { .open = etb_open, .read = etb_read, .release = etb_release, - .llseek = no_llseek, }; static struct attribute *coresight_etb_mgmt_attrs[] = { diff --git a/drivers/hwtracing/coresight/coresight-tmc-core.c b/drivers/hwtracing/coresight/coresight-tmc-core.c index b54562f392f3..3a482fd2cb22 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-core.c +++ b/drivers/hwtracing/coresight/coresight-tmc-core.c @@ -220,7 +220,6 @@ static const struct file_operations tmc_fops = { .open = tmc_open, .read = tmc_read, .release = tmc_release, - .llseek = no_llseek, }; static enum tmc_mem_intf_width tmc_get_memwidth(u32 devid) diff --git a/drivers/hwtracing/coresight/ultrasoc-smb.c b/drivers/hwtracing/coresight/ultrasoc-smb.c index f9ebf20c91e6..ef7f560f0ffa 100644 --- a/drivers/hwtracing/coresight/ultrasoc-smb.c +++ b/drivers/hwtracing/coresight/ultrasoc-smb.c @@ -163,7 +163,6 @@ static const struct file_operations smb_fops = { .open = smb_open, .read = smb_read, .release = smb_release, - .llseek = no_llseek, }; static ssize_t buf_size_show(struct device *dev, struct device_attribute *attr, diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c index be63d5b8f193..66123d684ac9 100644 --- a/drivers/hwtracing/intel_th/msu.c +++ b/drivers/hwtracing/intel_th/msu.c @@ -1677,7 +1677,6 @@ static const struct file_operations intel_th_msc_fops = { .release = intel_th_msc_release, .read = intel_th_msc_read, .mmap = intel_th_msc_mmap, - .llseek = no_llseek, .owner = THIS_MODULE, }; diff --git a/drivers/hwtracing/stm/core.c b/drivers/hwtracing/stm/core.c index ccf39a80dc4f..cdba4e875b28 100644 --- a/drivers/hwtracing/stm/core.c +++ b/drivers/hwtracing/stm/core.c @@ -839,7 +839,6 @@ static const struct file_operations stm_fops = { .mmap = stm_char_mmap, .unlocked_ioctl = stm_char_ioctl, .compat_ioctl = compat_ptr_ioctl, - .llseek = no_llseek, }; static void stm_device_release(struct device *dev) diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c index f4fb212b7f39..61f7c4003d2f 100644 --- a/drivers/i2c/i2c-dev.c +++ b/drivers/i2c/i2c-dev.c @@ -637,7 +637,6 @@ static int i2cdev_release(struct inode *inode, struct file *file) static const struct file_operations i2cdev_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = i2cdev_read, .write = i2cdev_write, .unlocked_ioctl = i2cdev_ioctl, diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index dc57d07a1f45..5dbb248e9625 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -1817,7 +1817,6 @@ static const struct file_operations ucma_fops = { .release = ucma_close, .write = ucma_write, .poll = ucma_poll, - .llseek = no_llseek, }; static struct miscdevice ucma_misc = { diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c index f760dfffa188..fd67fc9fe85a 100644 --- a/drivers/infiniband/core/user_mad.c +++ b/drivers/infiniband/core/user_mad.c @@ -1082,7 +1082,6 @@ static const struct file_operations umad_fops = { #endif .open = ib_umad_open, .release = ib_umad_close, - .llseek = no_llseek, }; static int ib_umad_sm_open(struct inode *inode, struct file *filp) @@ -1150,7 +1149,6 @@ static const struct file_operations umad_sm_fops = { .owner = THIS_MODULE, .open = ib_umad_sm_open, .release = ib_umad_sm_close, - .llseek = no_llseek, }; static struct ib_umad_port *get_port(struct ib_device *ibdev, diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index bc099287de9a..94454186ed81 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -353,7 +353,6 @@ const struct file_operations uverbs_event_fops = { .poll = ib_uverbs_comp_event_poll, .release = uverbs_uobject_fd_release, .fasync = ib_uverbs_comp_event_fasync, - .llseek = no_llseek, }; const struct file_operations uverbs_async_event_fops = { @@ -362,7 +361,6 @@ const struct file_operations uverbs_async_event_fops = { .poll = ib_uverbs_async_event_poll, .release = uverbs_async_event_release, .fasync = ib_uverbs_async_event_fasync, - .llseek = no_llseek, }; void ib_uverbs_comp_handler(struct ib_cq *cq, void *cq_context) @@ -991,7 +989,6 @@ static const struct file_operations uverbs_fops = { .write = ib_uverbs_write, .open = ib_uverbs_open, .release = ib_uverbs_close, - .llseek = no_llseek, .unlocked_ioctl = ib_uverbs_ioctl, .compat_ioctl = compat_ptr_ioctl, }; @@ -1002,7 +999,6 @@ static const struct file_operations uverbs_mmap_fops = { .mmap = ib_uverbs_mmap, .open = ib_uverbs_open, .release = ib_uverbs_close, - .llseek = no_llseek, .unlocked_ioctl = ib_uverbs_ioctl, .compat_ioctl = compat_ptr_ioctl, }; diff --git a/drivers/infiniband/hw/hfi1/fault.c b/drivers/infiniband/hw/hfi1/fault.c index 35d2382ee618..ec9ee59fcf0c 100644 --- a/drivers/infiniband/hw/hfi1/fault.c +++ b/drivers/infiniband/hw/hfi1/fault.c @@ -203,7 +203,6 @@ static const struct file_operations __fault_opcodes_fops = { .open = fault_opcodes_open, .read = fault_opcodes_read, .write = fault_opcodes_write, - .llseek = no_llseek }; void hfi1_fault_exit_debugfs(struct hfi1_ibdev *ibd) diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index 253fea374a72..69999d8d24f3 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -2673,7 +2673,6 @@ static const struct file_operations devx_async_cmd_event_fops = { .read = devx_async_cmd_event_read, .poll = devx_async_cmd_event_poll, .release = uverbs_uobject_fd_release, - .llseek = no_llseek, }; static ssize_t devx_async_event_read(struct file *filp, char __user *buf, @@ -2788,7 +2787,6 @@ static const struct file_operations devx_async_event_fops = { .read = devx_async_event_read, .poll = devx_async_event_poll, .release = uverbs_uobject_fd_release, - .llseek = no_llseek, }; static void devx_async_cmd_event_destroy_uobj(struct ib_uobject *uobj, diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c index eb4906552ac8..b5cbb57ee5f6 100644 --- a/drivers/input/evdev.c +++ b/drivers/input/evdev.c @@ -1299,7 +1299,6 @@ static const struct file_operations evdev_fops = { .compat_ioctl = evdev_ioctl_compat, #endif .fasync = evdev_fasync, - .llseek = no_llseek, }; /* diff --git a/drivers/input/joydev.c b/drivers/input/joydev.c index 5824bca02e5a..ba2b17288bcd 100644 --- a/drivers/input/joydev.c +++ b/drivers/input/joydev.c @@ -718,7 +718,6 @@ static const struct file_operations joydev_fops = { .compat_ioctl = joydev_compat_ioctl, #endif .fasync = joydev_fasync, - .llseek = no_llseek, }; /* diff --git a/drivers/input/keyboard/applespi.c b/drivers/input/keyboard/applespi.c index cf25177b4830..707c5a8ae736 100644 --- a/drivers/input/keyboard/applespi.c +++ b/drivers/input/keyboard/applespi.c @@ -1007,7 +1007,6 @@ static const struct file_operations applespi_tp_dim_fops = { .owner = THIS_MODULE, .open = applespi_tp_dim_open, .read = applespi_tp_dim_read, - .llseek = no_llseek, }; static void report_finger_data(struct input_dev *input, int slot, diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c index 445856c9127a..2c51ea9d01d7 100644 --- a/drivers/input/misc/uinput.c +++ b/drivers/input/misc/uinput.c @@ -1132,7 +1132,6 @@ static const struct file_operations uinput_fops = { #ifdef CONFIG_COMPAT .compat_ioctl = uinput_compat_ioctl, #endif - .llseek = no_llseek, }; static struct miscdevice uinput_misc = { diff --git a/drivers/input/serio/userio.c b/drivers/input/serio/userio.c index a88e2eee55c3..1ab12b247f98 100644 --- a/drivers/input/serio/userio.c +++ b/drivers/input/serio/userio.c @@ -267,7 +267,6 @@ static const struct file_operations userio_fops = { .read = userio_char_read, .write = userio_char_write, .poll = userio_char_poll, - .llseek = no_llseek, }; static struct miscdevice userio_misc = { diff --git a/drivers/iommu/iommufd/fault.c b/drivers/iommu/iommufd/fault.c index 8c8226f0dffd..e590973ce5cf 100644 --- a/drivers/iommu/iommufd/fault.c +++ b/drivers/iommu/iommufd/fault.c @@ -360,7 +360,6 @@ static const struct file_operations iommufd_fault_fops = { .write = iommufd_fault_fops_write, .poll = iommufd_fault_fops_poll, .release = iommufd_fault_fops_release, - .llseek = no_llseek, }; int iommufd_fault_alloc(struct iommufd_ucmd *ucmd) diff --git a/drivers/isdn/capi/capi.c b/drivers/isdn/capi/capi.c index 3ed257334562..70dee9ad4bae 100644 --- a/drivers/isdn/capi/capi.c +++ b/drivers/isdn/capi/capi.c @@ -1024,7 +1024,6 @@ static int capi_release(struct inode *inode, struct file *file) static const struct file_operations capi_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = capi_read, .write = capi_write, .poll = capi_poll, diff --git a/drivers/isdn/mISDN/timerdev.c b/drivers/isdn/mISDN/timerdev.c index 83d6b484d3c6..7cfa8c61dba0 100644 --- a/drivers/isdn/mISDN/timerdev.c +++ b/drivers/isdn/mISDN/timerdev.c @@ -266,7 +266,6 @@ static const struct file_operations mISDN_fops = { .unlocked_ioctl = mISDN_ioctl, .open = mISDN_open, .release = mISDN_close, - .llseek = no_llseek, }; static struct miscdevice mISDNtimer = { diff --git a/drivers/leds/uleds.c b/drivers/leds/uleds.c index 3d361c920030..374a841f18c3 100644 --- a/drivers/leds/uleds.c +++ b/drivers/leds/uleds.c @@ -200,7 +200,6 @@ static const struct file_operations uleds_fops = { .read = uleds_read, .write = uleds_write, .poll = uleds_poll, - .llseek = no_llseek, }; static struct miscdevice uleds_misc = { diff --git a/drivers/macintosh/adb.c b/drivers/macintosh/adb.c index b0407c5fadb2..88adee42ba82 100644 --- a/drivers/macintosh/adb.c +++ b/drivers/macintosh/adb.c @@ -842,7 +842,6 @@ out: static const struct file_operations adb_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = adb_read, .write = adb_write, .open = adb_open, diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c index b2b78a53e532..a01bc5090cdf 100644 --- a/drivers/macintosh/smu.c +++ b/drivers/macintosh/smu.c @@ -1314,7 +1314,6 @@ static int smu_release(struct inode *inode, struct file *file) static const struct file_operations smu_device_fops = { - .llseek = no_llseek, .read = smu_read, .write = smu_write, .poll = smu_fpoll, diff --git a/drivers/media/cec/core/cec-api.c b/drivers/media/cec/core/cec-api.c index c75a4057f00e..c50299246fc4 100644 --- a/drivers/media/cec/core/cec-api.c +++ b/drivers/media/cec/core/cec-api.c @@ -698,5 +698,4 @@ const struct file_operations cec_devnode_fops = { .compat_ioctl = cec_ioctl, .release = cec_release, .poll = cec_poll, - .llseek = no_llseek, }; diff --git a/drivers/media/mc/mc-devnode.c b/drivers/media/mc/mc-devnode.c index 318e267e798e..56444edaf136 100644 --- a/drivers/media/mc/mc-devnode.c +++ b/drivers/media/mc/mc-devnode.c @@ -204,7 +204,6 @@ static const struct file_operations media_devnode_fops = { #endif /* CONFIG_COMPAT */ .release = media_release, .poll = media_poll, - .llseek = no_llseek, }; int __must_check media_devnode_register(struct media_device *mdev, diff --git a/drivers/media/rc/lirc_dev.c b/drivers/media/rc/lirc_dev.c index b8dfd530fab7..f042f3f14afa 100644 --- a/drivers/media/rc/lirc_dev.c +++ b/drivers/media/rc/lirc_dev.c @@ -706,7 +706,6 @@ static const struct file_operations lirc_fops = { .poll = lirc_poll, .open = lirc_open, .release = lirc_close, - .llseek = no_llseek, }; static void lirc_release_device(struct device *ld) diff --git a/drivers/media/usb/uvc/uvc_debugfs.c b/drivers/media/usb/uvc/uvc_debugfs.c index 1a1258d4ffca..14fa41cb8148 100644 --- a/drivers/media/usb/uvc/uvc_debugfs.c +++ b/drivers/media/usb/uvc/uvc_debugfs.c @@ -59,7 +59,6 @@ static int uvc_debugfs_stats_release(struct inode *inode, struct file *file) static const struct file_operations uvc_debugfs_stats_fops = { .owner = THIS_MODULE, .open = uvc_debugfs_stats_open, - .llseek = no_llseek, .read = uvc_debugfs_stats_read, .release = uvc_debugfs_stats_release, }; diff --git a/drivers/media/v4l2-core/v4l2-dev.c b/drivers/media/v4l2-core/v4l2-dev.c index 570ba00e00b3..3d7711cc42bc 100644 --- a/drivers/media/v4l2-core/v4l2-dev.c +++ b/drivers/media/v4l2-core/v4l2-dev.c @@ -483,7 +483,6 @@ static const struct file_operations v4l2_fops = { #endif .release = v4l2_release, .poll = v4l2_poll, - .llseek = no_llseek, }; /** diff --git a/drivers/message/fusion/mptctl.c b/drivers/message/fusion/mptctl.c index 9f3999750c23..4766d8518dc9 100644 --- a/drivers/message/fusion/mptctl.c +++ b/drivers/message/fusion/mptctl.c @@ -2691,7 +2691,6 @@ mptctl_hp_targetinfo(MPT_ADAPTER *ioc, unsigned long arg) static const struct file_operations mptctl_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .fasync = mptctl_fasync, .unlocked_ioctl = mptctl_ioctl, #ifdef CONFIG_COMPAT diff --git a/drivers/misc/lis3lv02d/lis3lv02d.c b/drivers/misc/lis3lv02d/lis3lv02d.c index 1fc635a27568..4233dc4cc7d6 100644 --- a/drivers/misc/lis3lv02d/lis3lv02d.c +++ b/drivers/misc/lis3lv02d/lis3lv02d.c @@ -669,7 +669,6 @@ static int lis3lv02d_misc_fasync(int fd, struct file *file, int on) static const struct file_operations lis3lv02d_misc_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = lis3lv02d_misc_read, .open = lis3lv02d_misc_open, .release = lis3lv02d_misc_release, diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c index 40c3fe26f76d..1f5aaf16e300 100644 --- a/drivers/misc/mei/main.c +++ b/drivers/misc/mei/main.c @@ -1176,7 +1176,6 @@ static const struct file_operations mei_fops = { .poll = mei_poll, .fsync = mei_fsync, .fasync = mei_fasync, - .llseek = no_llseek }; /** diff --git a/drivers/misc/ntsync.c b/drivers/misc/ntsync.c index 3c2f743c58b0..4954553b7baa 100644 --- a/drivers/misc/ntsync.c +++ b/drivers/misc/ntsync.c @@ -126,7 +126,6 @@ static const struct file_operations ntsync_obj_fops = { .release = ntsync_obj_release, .unlocked_ioctl = ntsync_obj_ioctl, .compat_ioctl = compat_ptr_ioctl, - .llseek = no_llseek, }; static struct ntsync_obj *ntsync_alloc_obj(struct ntsync_device *dev, @@ -233,7 +232,6 @@ static const struct file_operations ntsync_fops = { .release = ntsync_char_release, .unlocked_ioctl = ntsync_char_ioctl, .compat_ioctl = compat_ptr_ioctl, - .llseek = no_llseek, }; static struct miscdevice ntsync_misc = { diff --git a/drivers/misc/phantom.c b/drivers/misc/phantom.c index 30bd7c39c261..701db2c5859b 100644 --- a/drivers/misc/phantom.c +++ b/drivers/misc/phantom.c @@ -279,7 +279,6 @@ static const struct file_operations phantom_file_ops = { .unlocked_ioctl = phantom_ioctl, .compat_ioctl = phantom_compat_ioctl, .poll = phantom_poll, - .llseek = no_llseek, }; static irqreturn_t phantom_isr(int irq, void *data) diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index f58bea534004..ef06a4d5d65b 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -2734,7 +2734,6 @@ static const struct file_operations mmc_rpmb_fileops = { .release = mmc_rpmb_chrdev_release, .open = mmc_rpmb_chrdev_open, .owner = THIS_MODULE, - .llseek = no_llseek, .unlocked_ioctl = mmc_rpmb_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = mmc_rpmb_ioctl_compat, diff --git a/drivers/mtd/ubi/cdev.c b/drivers/mtd/ubi/cdev.c index 0d8f04cf03c5..6bb80d7714bc 100644 --- a/drivers/mtd/ubi/cdev.c +++ b/drivers/mtd/ubi/cdev.c @@ -1095,7 +1095,6 @@ const struct file_operations ubi_vol_cdev_operations = { /* UBI character device operations */ const struct file_operations ubi_cdev_operations = { .owner = THIS_MODULE, - .llseek = no_llseek, .unlocked_ioctl = ubi_cdev_ioctl, .compat_ioctl = compat_ptr_ioctl, }; @@ -1105,5 +1104,4 @@ const struct file_operations ubi_ctrl_cdev_operations = { .owner = THIS_MODULE, .unlocked_ioctl = ctrl_cdev_ioctl, .compat_ioctl = compat_ptr_ioctl, - .llseek = no_llseek, }; diff --git a/drivers/mtd/ubi/debug.c b/drivers/mtd/ubi/debug.c index 9ec3b8b6a0aa..d2a53961d8e2 100644 --- a/drivers/mtd/ubi/debug.c +++ b/drivers/mtd/ubi/debug.c @@ -470,7 +470,6 @@ static const struct file_operations dfs_fops = { .read = dfs_file_read, .write = dfs_file_write, .open = simple_open, - .llseek = no_llseek, .owner = THIS_MODULE, }; diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c index a1f91ff8ec56..41e80f78b316 100644 --- a/drivers/net/netdevsim/fib.c +++ b/drivers/net/netdevsim/fib.c @@ -1414,7 +1414,6 @@ out: static const struct file_operations nsim_nexthop_bucket_activity_fops = { .open = simple_open, .write = nsim_nexthop_bucket_activity_write, - .llseek = no_llseek, .owner = THIS_MODULE, }; diff --git a/drivers/net/tap.c b/drivers/net/tap.c index 77574f7a3bd4..5aa41d5f7765 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -1162,7 +1162,6 @@ static const struct file_operations tap_fops = { .read_iter = tap_read_iter, .write_iter = tap_write_iter, .poll = tap_poll, - .llseek = no_llseek, .unlocked_ioctl = tap_ioctl, .compat_ioctl = compat_ptr_ioctl, }; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 5f77faef0ff1..9a0f6eb32016 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -3543,7 +3543,6 @@ static void tun_chr_show_fdinfo(struct seq_file *m, struct file *file) static const struct file_operations tun_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read_iter = tun_chr_read_iter, .write_iter = tun_chr_write_iter, .poll = tun_chr_poll, diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c index df53dd1d7e74..da72fd2d541f 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c @@ -1184,7 +1184,6 @@ static ssize_t bus_reset_write(struct file *file, const char __user *user_buf, static const struct file_operations bus_reset_fops = { .open = simple_open, - .llseek = no_llseek, .write = bus_reset_write, }; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c index 99a541d442bb..49a6aff42376 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c @@ -3768,7 +3768,6 @@ static int iwl_mvm_d3_test_release(struct inode *inode, struct file *file) } const struct file_operations iwl_dbgfs_d3_test_ops = { - .llseek = no_llseek, .open = iwl_mvm_d3_test_open, .read = iwl_mvm_d3_test_read, .release = iwl_mvm_d3_test_release, diff --git a/drivers/platform/chrome/cros_ec_debugfs.c b/drivers/platform/chrome/cros_ec_debugfs.c index 4525ad1b59f4..839154c46e46 100644 --- a/drivers/platform/chrome/cros_ec_debugfs.c +++ b/drivers/platform/chrome/cros_ec_debugfs.c @@ -302,7 +302,6 @@ static const struct file_operations cros_ec_console_log_fops = { .owner = THIS_MODULE, .open = cros_ec_console_log_open, .read = cros_ec_console_log_read, - .llseek = no_llseek, .poll = cros_ec_console_log_poll, .release = cros_ec_console_log_release, }; diff --git a/drivers/platform/chrome/wilco_ec/debugfs.c b/drivers/platform/chrome/wilco_ec/debugfs.c index 983f2fa44ba5..99486086af6a 100644 --- a/drivers/platform/chrome/wilco_ec/debugfs.c +++ b/drivers/platform/chrome/wilco_ec/debugfs.c @@ -156,7 +156,6 @@ static const struct file_operations fops_raw = { .owner = THIS_MODULE, .read = raw_read, .write = raw_write, - .llseek = no_llseek, }; #define CMD_KB_CHROME 0x88 diff --git a/drivers/platform/chrome/wilco_ec/event.c b/drivers/platform/chrome/wilco_ec/event.c index bd1fb53ba028..196e46a1d489 100644 --- a/drivers/platform/chrome/wilco_ec/event.c +++ b/drivers/platform/chrome/wilco_ec/event.c @@ -403,7 +403,6 @@ static const struct file_operations event_fops = { .poll = event_poll, .read = event_read, .release = event_release, - .llseek = no_llseek, .owner = THIS_MODULE, }; diff --git a/drivers/platform/chrome/wilco_ec/telemetry.c b/drivers/platform/chrome/wilco_ec/telemetry.c index 21d4cbbb009a..a87877e4300a 100644 --- a/drivers/platform/chrome/wilco_ec/telemetry.c +++ b/drivers/platform/chrome/wilco_ec/telemetry.c @@ -330,7 +330,6 @@ static const struct file_operations telem_fops = { .write = telem_write, .read = telem_read, .release = telem_release, - .llseek = no_llseek, .owner = THIS_MODULE, }; diff --git a/drivers/platform/surface/surface_aggregator_cdev.c b/drivers/platform/surface/surface_aggregator_cdev.c index 07e065b9159f..165b1416230d 100644 --- a/drivers/platform/surface/surface_aggregator_cdev.c +++ b/drivers/platform/surface/surface_aggregator_cdev.c @@ -670,7 +670,6 @@ static const struct file_operations ssam_controller_fops = { .fasync = ssam_cdev_fasync, .unlocked_ioctl = ssam_cdev_device_ioctl, .compat_ioctl = ssam_cdev_device_ioctl, - .llseek = no_llseek, }; diff --git a/drivers/platform/surface/surface_dtx.c b/drivers/platform/surface/surface_dtx.c index 2de843b7ea70..89ca6b50e812 100644 --- a/drivers/platform/surface/surface_dtx.c +++ b/drivers/platform/surface/surface_dtx.c @@ -555,7 +555,6 @@ static const struct file_operations surface_dtx_fops = { .fasync = surface_dtx_fasync, .unlocked_ioctl = surface_dtx_ioctl, .compat_ioctl = surface_dtx_ioctl, - .llseek = no_llseek, }; diff --git a/drivers/pps/pps.c b/drivers/pps/pps.c index 5d19baae6a38..25d47907db17 100644 --- a/drivers/pps/pps.c +++ b/drivers/pps/pps.c @@ -319,7 +319,6 @@ static int pps_cdev_release(struct inode *inode, struct file *file) static const struct file_operations pps_cdev_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .poll = pps_cdev_poll, .fasync = pps_cdev_fasync, .compat_ioctl = pps_cdev_compat_ioctl, diff --git a/drivers/rtc/dev.c b/drivers/rtc/dev.c index 4aad9bb99868..c4a3ab53dcd4 100644 --- a/drivers/rtc/dev.c +++ b/drivers/rtc/dev.c @@ -523,7 +523,6 @@ static int rtc_dev_release(struct inode *inode, struct file *file) static const struct file_operations rtc_dev_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = rtc_dev_read, .poll = rtc_dev_poll, .unlocked_ioctl = rtc_dev_ioctl, diff --git a/drivers/rtc/rtc-m41t80.c b/drivers/rtc/rtc-m41t80.c index 0013bff0447d..1f58ae8b151e 100644 --- a/drivers/rtc/rtc-m41t80.c +++ b/drivers/rtc/rtc-m41t80.c @@ -850,7 +850,6 @@ static const struct file_operations wdt_fops = { .write = wdt_write, .open = wdt_open, .release = wdt_release, - .llseek = no_llseek, }; static struct miscdevice wdt_dev = { diff --git a/drivers/s390/char/fs3270.c b/drivers/s390/char/fs3270.c index 61515781c5dd..cfe7efd5b5da 100644 --- a/drivers/s390/char/fs3270.c +++ b/drivers/s390/char/fs3270.c @@ -515,7 +515,6 @@ static const struct file_operations fs3270_fops = { .compat_ioctl = fs3270_ioctl, /* ioctl */ .open = fs3270_open, /* open */ .release = fs3270_close, /* release */ - .llseek = no_llseek, }; static void fs3270_create_cb(int minor) diff --git a/drivers/s390/char/sclp_ctl.c b/drivers/s390/char/sclp_ctl.c index 248b5db3eaa8..dd6051602070 100644 --- a/drivers/s390/char/sclp_ctl.c +++ b/drivers/s390/char/sclp_ctl.c @@ -115,7 +115,6 @@ static const struct file_operations sclp_ctl_fops = { .open = nonseekable_open, .unlocked_ioctl = sclp_ctl_ioctl, .compat_ioctl = sclp_ctl_ioctl, - .llseek = no_llseek, }; /* diff --git a/drivers/s390/char/tape_char.c b/drivers/s390/char/tape_char.c index cc8237afeffa..89778d922d9f 100644 --- a/drivers/s390/char/tape_char.c +++ b/drivers/s390/char/tape_char.c @@ -52,7 +52,6 @@ static const struct file_operations tape_fops = #endif .open = tapechar_open, .release = tapechar_release, - .llseek = no_llseek, }; static int tapechar_major = TAPECHAR_MAJOR; diff --git a/drivers/s390/char/uvdevice.c b/drivers/s390/char/uvdevice.c index 42c9f77f8da0..f598edc5f251 100644 --- a/drivers/s390/char/uvdevice.c +++ b/drivers/s390/char/uvdevice.c @@ -448,7 +448,6 @@ static long uvio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) static const struct file_operations uvio_dev_fops = { .owner = THIS_MODULE, .unlocked_ioctl = uvio_ioctl, - .llseek = no_llseek, }; static struct miscdevice uvio_dev_miscdev = { diff --git a/drivers/s390/char/vmcp.c b/drivers/s390/char/vmcp.c index eb0520a9d4af..c6d58335beb4 100644 --- a/drivers/s390/char/vmcp.c +++ b/drivers/s390/char/vmcp.c @@ -242,7 +242,6 @@ static const struct file_operations vmcp_fops = { .write = vmcp_write, .unlocked_ioctl = vmcp_ioctl, .compat_ioctl = vmcp_ioctl, - .llseek = no_llseek, }; static struct miscdevice vmcp_dev = { diff --git a/drivers/s390/char/vmlogrdr.c b/drivers/s390/char/vmlogrdr.c index c09e1e09fb66..bd5cecc44123 100644 --- a/drivers/s390/char/vmlogrdr.c +++ b/drivers/s390/char/vmlogrdr.c @@ -96,7 +96,6 @@ static const struct file_operations vmlogrdr_fops = { .open = vmlogrdr_open, .release = vmlogrdr_release, .read = vmlogrdr_read, - .llseek = no_llseek, }; diff --git a/drivers/s390/char/zcore.c b/drivers/s390/char/zcore.c index 0969fa01df58..33cebb91b933 100644 --- a/drivers/s390/char/zcore.c +++ b/drivers/s390/char/zcore.c @@ -165,7 +165,6 @@ static const struct file_operations zcore_reipl_fops = { .write = zcore_reipl_write, .open = zcore_reipl_open, .release = zcore_reipl_release, - .llseek = no_llseek, }; static ssize_t zcore_hsa_read(struct file *filp, char __user *buf, @@ -200,7 +199,6 @@ static const struct file_operations zcore_hsa_fops = { .write = zcore_hsa_write, .read = zcore_hsa_read, .open = nonseekable_open, - .llseek = no_llseek, }; static int __init check_sdias(void) diff --git a/drivers/s390/cio/chsc_sch.c b/drivers/s390/cio/chsc_sch.c index e6c800653f98..1e58ee3cc87d 100644 --- a/drivers/s390/cio/chsc_sch.c +++ b/drivers/s390/cio/chsc_sch.c @@ -924,7 +924,6 @@ static const struct file_operations chsc_fops = { .release = chsc_release, .unlocked_ioctl = chsc_ioctl, .compat_ioctl = chsc_ioctl, - .llseek = no_llseek, }; static struct miscdevice chsc_misc_device = { diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c index 53b68f8c32f3..7b59d20bf785 100644 --- a/drivers/s390/cio/css.c +++ b/drivers/s390/cio/css.c @@ -1332,7 +1332,6 @@ static ssize_t cio_settle_write(struct file *file, const char __user *buf, static const struct proc_ops cio_settle_proc_ops = { .proc_open = nonseekable_open, .proc_write = cio_settle_write, - .proc_lseek = no_llseek, }; static int __init cio_settle_init(void) diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c index c20251e00cf9..3a39e167bdbf 100644 --- a/drivers/s390/crypto/pkey_api.c +++ b/drivers/s390/crypto/pkey_api.c @@ -776,7 +776,6 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, static const struct file_operations pkey_fops = { .owner = THIS_MODULE, .open = nonseekable_open, - .llseek = no_llseek, .unlocked_ioctl = pkey_unlocked_ioctl, }; diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index f9a47b54c51a..5020696f1379 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -1908,7 +1908,6 @@ static const struct file_operations zcrypt_fops = { #endif .open = zcrypt_open, .release = zcrypt_release, - .llseek = no_llseek, }; /* diff --git a/drivers/sbus/char/openprom.c b/drivers/sbus/char/openprom.c index cc178874c4a6..8643947fee8e 100644 --- a/drivers/sbus/char/openprom.c +++ b/drivers/sbus/char/openprom.c @@ -687,7 +687,6 @@ static int openprom_release(struct inode * inode, struct file * file) static const struct file_operations openprom_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .unlocked_ioctl = openprom_ioctl, .compat_ioctl = openprom_compat_ioctl, .open = openprom_open, diff --git a/drivers/sbus/char/uctrl.c b/drivers/sbus/char/uctrl.c index 3c88f29f4c47..8bbed7a7afb7 100644 --- a/drivers/sbus/char/uctrl.c +++ b/drivers/sbus/char/uctrl.c @@ -221,7 +221,6 @@ static irqreturn_t uctrl_interrupt(int irq, void *dev_id) static const struct file_operations uctrl_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .unlocked_ioctl = uctrl_ioctl, .open = uctrl_open, }; diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index baf870a03ecf..f86be197fedd 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1424,7 +1424,6 @@ static const struct file_operations sg_fops = { .mmap = sg_mmap, .release = sg_release, .fasync = sg_fasync, - .llseek = no_llseek, }; static const struct class sg_sysfs_class = { diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c index 5539c5d139d4..653f82984216 100644 --- a/drivers/spi/spidev.c +++ b/drivers/spi/spidev.c @@ -685,7 +685,6 @@ static const struct file_operations spidev_fops = { .compat_ioctl = spidev_compat_ioctl, .open = spidev_open, .release = spidev_release, - .llseek = no_llseek, }; /*-------------------------------------------------------------------------*/ diff --git a/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c b/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c index 4b4a4d63e61f..cb149bcdd7d5 100644 --- a/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c +++ b/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c @@ -564,7 +564,6 @@ static const struct file_operations acpi_thermal_rel_fops = { .open = acpi_thermal_rel_open, .release = acpi_thermal_rel_release, .unlocked_ioctl = acpi_thermal_rel_ioctl, - .llseek = no_llseek, }; static struct miscdevice acpi_thermal_rel_misc_device = { diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 6bd28a042dff..9771072da177 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -459,7 +459,6 @@ static void tty_show_fdinfo(struct seq_file *m, struct file *file) } static const struct file_operations tty_fops = { - .llseek = no_llseek, .read_iter = tty_read, .write_iter = tty_write, .splice_read = copy_splice_read, @@ -474,7 +473,6 @@ static const struct file_operations tty_fops = { }; static const struct file_operations console_fops = { - .llseek = no_llseek, .read_iter = tty_read, .write_iter = redirected_tty_write, .splice_read = copy_splice_read, @@ -488,7 +486,6 @@ static const struct file_operations console_fops = { }; static const struct file_operations hung_up_tty_fops = { - .llseek = no_llseek, .read_iter = hung_up_tty_read, .write_iter = hung_up_tty_write, .poll = hung_up_tty_poll, diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 05b52e61a66f..c626bb73ea59 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -722,7 +722,6 @@ static __poll_t ffs_ep0_poll(struct file *file, poll_table *wait) } static const struct file_operations ffs_ep0_operations = { - .llseek = no_llseek, .open = ffs_ep0_open, .write = ffs_ep0_write, @@ -1830,7 +1829,6 @@ static long ffs_epfile_ioctl(struct file *file, unsigned code, } static const struct file_operations ffs_epfile_operations = { - .llseek = no_llseek, .open = ffs_epfile_open, .write_iter = ffs_epfile_write_iter, diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index 03179b1880fd..9c7381661016 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -705,7 +705,6 @@ static const struct file_operations ep_io_operations = { .open = ep_open, .release = ep_release, - .llseek = no_llseek, .unlocked_ioctl = ep_ioctl, .read_iter = ep_read_iter, .write_iter = ep_write_iter, @@ -1939,7 +1938,6 @@ gadget_dev_open (struct inode *inode, struct file *fd) } static const struct file_operations ep0_operations = { - .llseek = no_llseek, .open = gadget_dev_open, .read = ep0_read, diff --git a/drivers/usb/gadget/legacy/raw_gadget.c b/drivers/usb/gadget/legacy/raw_gadget.c index 399fca32a8ac..112fd18d8c99 100644 --- a/drivers/usb/gadget/legacy/raw_gadget.c +++ b/drivers/usb/gadget/legacy/raw_gadget.c @@ -1364,7 +1364,6 @@ static const struct file_operations raw_fops = { .unlocked_ioctl = raw_ioctl, .compat_ioctl = raw_ioctl, .release = raw_release, - .llseek = no_llseek, }; static struct miscdevice raw_misc_device = { diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c index b76885d78e8a..4928eba19327 100644 --- a/drivers/usb/gadget/udc/atmel_usba_udc.c +++ b/drivers/usb/gadget/udc/atmel_usba_udc.c @@ -187,7 +187,6 @@ static int regs_dbg_release(struct inode *inode, struct file *file) static const struct file_operations queue_dbg_fops = { .owner = THIS_MODULE, .open = queue_dbg_open, - .llseek = no_llseek, .read = queue_dbg_read, .release = queue_dbg_release, }; diff --git a/drivers/usb/misc/ldusb.c b/drivers/usb/misc/ldusb.c index 7cbef74dfc9a..f392d6f84df9 100644 --- a/drivers/usb/misc/ldusb.c +++ b/drivers/usb/misc/ldusb.c @@ -627,7 +627,6 @@ static const struct file_operations ld_usb_fops = { .open = ld_usb_open, .release = ld_usb_release, .poll = ld_usb_poll, - .llseek = no_llseek, }; /* diff --git a/drivers/usb/mon/mon_bin.c b/drivers/usb/mon/mon_bin.c index 4e30de4db1c0..afb71c18415d 100644 --- a/drivers/usb/mon/mon_bin.c +++ b/drivers/usb/mon/mon_bin.c @@ -1289,7 +1289,6 @@ static int mon_bin_mmap(struct file *filp, struct vm_area_struct *vma) static const struct file_operations mon_fops_binary = { .owner = THIS_MODULE, .open = mon_bin_open, - .llseek = no_llseek, .read = mon_bin_read, /* .write = mon_text_write, */ .poll = mon_bin_poll, diff --git a/drivers/usb/mon/mon_stat.c b/drivers/usb/mon/mon_stat.c index 3c23805ab1a4..398e02af6a2b 100644 --- a/drivers/usb/mon/mon_stat.c +++ b/drivers/usb/mon/mon_stat.c @@ -62,7 +62,6 @@ static int mon_stat_release(struct inode *inode, struct file *file) const struct file_operations mon_fops_stat = { .owner = THIS_MODULE, .open = mon_stat_open, - .llseek = no_llseek, .read = mon_stat_read, /* .write = mon_stat_write, */ /* .poll = mon_stat_poll, */ diff --git a/drivers/usb/mon/mon_text.c b/drivers/usb/mon/mon_text.c index 2fe9b95bac1d..68b9b2b41189 100644 --- a/drivers/usb/mon/mon_text.c +++ b/drivers/usb/mon/mon_text.c @@ -685,7 +685,6 @@ static int mon_text_release(struct inode *inode, struct file *file) static const struct file_operations mon_fops_text_t = { .owner = THIS_MODULE, .open = mon_text_open, - .llseek = no_llseek, .read = mon_text_read_t, .release = mon_text_release, }; @@ -693,7 +692,6 @@ static const struct file_operations mon_fops_text_t = { static const struct file_operations mon_fops_text_u = { .owner = THIS_MODULE, .open = mon_text_open, - .llseek = no_llseek, .read = mon_text_read_u, .release = mon_text_release, }; diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c index 9a3e97108ace..0d632ba5d2a3 100644 --- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c +++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c @@ -723,7 +723,6 @@ static const struct file_operations hisi_acc_vf_resume_fops = { .owner = THIS_MODULE, .write = hisi_acc_vf_resume_write, .release = hisi_acc_vf_release_file, - .llseek = no_llseek, }; static struct hisi_acc_vf_migration_file * @@ -845,7 +844,6 @@ static const struct file_operations hisi_acc_vf_save_fops = { .unlocked_ioctl = hisi_acc_vf_precopy_ioctl, .compat_ioctl = compat_ptr_ioctl, .release = hisi_acc_vf_release_file, - .llseek = no_llseek, }; static struct hisi_acc_vf_migration_file * diff --git a/drivers/vfio/pci/mlx5/main.c b/drivers/vfio/pci/mlx5/main.c index 61d9b0f9146d..242c23eef452 100644 --- a/drivers/vfio/pci/mlx5/main.c +++ b/drivers/vfio/pci/mlx5/main.c @@ -587,7 +587,6 @@ static const struct file_operations mlx5vf_save_fops = { .unlocked_ioctl = mlx5vf_precopy_ioctl, .compat_ioctl = compat_ptr_ioctl, .release = mlx5vf_release_file, - .llseek = no_llseek, }; static int mlx5vf_pci_save_device_inc_data(struct mlx5vf_pci_core_device *mvdev) @@ -1000,7 +999,6 @@ static const struct file_operations mlx5vf_resume_fops = { .owner = THIS_MODULE, .write = mlx5vf_resume_write, .release = mlx5vf_release_file, - .llseek = no_llseek, }; static struct mlx5_vf_migration_file * diff --git a/drivers/vfio/pci/pds/lm.c b/drivers/vfio/pci/pds/lm.c index 6b94cc0bf45b..f2673d395236 100644 --- a/drivers/vfio/pci/pds/lm.c +++ b/drivers/vfio/pci/pds/lm.c @@ -235,7 +235,6 @@ static const struct file_operations pds_vfio_save_fops = { .owner = THIS_MODULE, .read = pds_vfio_save_read, .release = pds_vfio_release_file, - .llseek = no_llseek, }; static int pds_vfio_get_save_file(struct pds_vfio_pci_device *pds_vfio) @@ -334,7 +333,6 @@ static const struct file_operations pds_vfio_restore_fops = { .owner = THIS_MODULE, .write = pds_vfio_restore_write, .release = pds_vfio_release_file, - .llseek = no_llseek, }; static int pds_vfio_get_restore_file(struct pds_vfio_pci_device *pds_vfio) diff --git a/drivers/vfio/pci/qat/main.c b/drivers/vfio/pci/qat/main.c index e36740a282e7..be3644ced17b 100644 --- a/drivers/vfio/pci/qat/main.c +++ b/drivers/vfio/pci/qat/main.c @@ -220,7 +220,6 @@ static const struct file_operations qat_vf_save_fops = { .unlocked_ioctl = qat_vf_precopy_ioctl, .compat_ioctl = compat_ptr_ioctl, .release = qat_vf_release_file, - .llseek = no_llseek, }; static int qat_vf_save_state(struct qat_vf_core_device *qat_vdev, @@ -345,7 +344,6 @@ static const struct file_operations qat_vf_resume_fops = { .owner = THIS_MODULE, .write = qat_vf_resume_write, .release = qat_vf_release_file, - .llseek = no_llseek, }; static struct qat_vf_migration_file * diff --git a/drivers/virt/coco/tdx-guest/tdx-guest.c b/drivers/virt/coco/tdx-guest/tdx-guest.c index 2acba56ad42e..d7db6c824e13 100644 --- a/drivers/virt/coco/tdx-guest/tdx-guest.c +++ b/drivers/virt/coco/tdx-guest/tdx-guest.c @@ -285,7 +285,6 @@ static long tdx_guest_ioctl(struct file *file, unsigned int cmd, static const struct file_operations tdx_guest_fops = { .owner = THIS_MODULE, .unlocked_ioctl = tdx_guest_ioctl, - .llseek = no_llseek, }; static struct miscdevice tdx_misc_dev = { diff --git a/drivers/watchdog/acquirewdt.c b/drivers/watchdog/acquirewdt.c index 53b04abd55b0..08ca18e91124 100644 --- a/drivers/watchdog/acquirewdt.c +++ b/drivers/watchdog/acquirewdt.c @@ -218,7 +218,6 @@ static int acq_close(struct inode *inode, struct file *file) static const struct file_operations acq_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = acq_write, .unlocked_ioctl = acq_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/advantechwdt.c b/drivers/watchdog/advantechwdt.c index 7a0acbc3e4dd..e41cd3ba4e0e 100644 --- a/drivers/watchdog/advantechwdt.c +++ b/drivers/watchdog/advantechwdt.c @@ -217,7 +217,6 @@ static int advwdt_close(struct inode *inode, struct file *file) static const struct file_operations advwdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = advwdt_write, .unlocked_ioctl = advwdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/alim1535_wdt.c b/drivers/watchdog/alim1535_wdt.c index bfb9a91ca1df..1ecbd1ac5c3a 100644 --- a/drivers/watchdog/alim1535_wdt.c +++ b/drivers/watchdog/alim1535_wdt.c @@ -359,7 +359,6 @@ static int __init ali_find_watchdog(void) static const struct file_operations ali_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = ali_write, .unlocked_ioctl = ali_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/alim7101_wdt.c b/drivers/watchdog/alim7101_wdt.c index 4ff7f5afb7aa..9c7cf939ba3d 100644 --- a/drivers/watchdog/alim7101_wdt.c +++ b/drivers/watchdog/alim7101_wdt.c @@ -289,7 +289,6 @@ static long fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg) static const struct file_operations wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = fop_write, .open = fop_open, .release = fop_close, diff --git a/drivers/watchdog/at91rm9200_wdt.c b/drivers/watchdog/at91rm9200_wdt.c index 558015f08c7a..17382512a609 100644 --- a/drivers/watchdog/at91rm9200_wdt.c +++ b/drivers/watchdog/at91rm9200_wdt.c @@ -210,7 +210,6 @@ static ssize_t at91_wdt_write(struct file *file, const char *data, static const struct file_operations at91wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .unlocked_ioctl = at91_wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, .open = at91_wdt_open, diff --git a/drivers/watchdog/ath79_wdt.c b/drivers/watchdog/ath79_wdt.c index e5cc30622b12..d16b2c583fa4 100644 --- a/drivers/watchdog/ath79_wdt.c +++ b/drivers/watchdog/ath79_wdt.c @@ -231,7 +231,6 @@ static long ath79_wdt_ioctl(struct file *file, unsigned int cmd, static const struct file_operations ath79_wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = ath79_wdt_write, .unlocked_ioctl = ath79_wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/cpu5wdt.c b/drivers/watchdog/cpu5wdt.c index 9f279c0e13a6..f94b84048612 100644 --- a/drivers/watchdog/cpu5wdt.c +++ b/drivers/watchdog/cpu5wdt.c @@ -185,7 +185,6 @@ static ssize_t cpu5wdt_write(struct file *file, const char __user *buf, static const struct file_operations cpu5wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .unlocked_ioctl = cpu5wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, .open = cpu5wdt_open, diff --git a/drivers/watchdog/cpwd.c b/drivers/watchdog/cpwd.c index 901b94d456db..8ee81f018dda 100644 --- a/drivers/watchdog/cpwd.c +++ b/drivers/watchdog/cpwd.c @@ -507,7 +507,6 @@ static const struct file_operations cpwd_fops = { .write = cpwd_write, .read = cpwd_read, .release = cpwd_release, - .llseek = no_llseek, }; static int cpwd_probe(struct platform_device *op) diff --git a/drivers/watchdog/eurotechwdt.c b/drivers/watchdog/eurotechwdt.c index e26609ad4c17..10c647b1226a 100644 --- a/drivers/watchdog/eurotechwdt.c +++ b/drivers/watchdog/eurotechwdt.c @@ -368,7 +368,6 @@ static int eurwdt_notify_sys(struct notifier_block *this, unsigned long code, static const struct file_operations eurwdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = eurwdt_write, .unlocked_ioctl = eurwdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/gef_wdt.c b/drivers/watchdog/gef_wdt.c index 6a1db1c783fa..d854fcfbfa5b 100644 --- a/drivers/watchdog/gef_wdt.c +++ b/drivers/watchdog/gef_wdt.c @@ -245,7 +245,6 @@ static int gef_wdt_release(struct inode *inode, struct file *file) static const struct file_operations gef_wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = gef_wdt_write, .unlocked_ioctl = gef_wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/geodewdt.c b/drivers/watchdog/geodewdt.c index 5186c37ad451..4ed6d139320b 100644 --- a/drivers/watchdog/geodewdt.c +++ b/drivers/watchdog/geodewdt.c @@ -196,7 +196,6 @@ static long geodewdt_ioctl(struct file *file, unsigned int cmd, static const struct file_operations geodewdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = geodewdt_write, .unlocked_ioctl = geodewdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/ib700wdt.c b/drivers/watchdog/ib700wdt.c index 39ea97009abd..b041ad90a62c 100644 --- a/drivers/watchdog/ib700wdt.c +++ b/drivers/watchdog/ib700wdt.c @@ -256,7 +256,6 @@ static int ibwdt_close(struct inode *inode, struct file *file) static const struct file_operations ibwdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = ibwdt_write, .unlocked_ioctl = ibwdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/ibmasr.c b/drivers/watchdog/ibmasr.c index 6955c693b5fd..cf845f865945 100644 --- a/drivers/watchdog/ibmasr.c +++ b/drivers/watchdog/ibmasr.c @@ -340,7 +340,6 @@ static int asr_release(struct inode *inode, struct file *file) static const struct file_operations asr_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = asr_write, .unlocked_ioctl = asr_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/indydog.c b/drivers/watchdog/indydog.c index 9857bb74a723..d3092d261345 100644 --- a/drivers/watchdog/indydog.c +++ b/drivers/watchdog/indydog.c @@ -149,7 +149,6 @@ static int indydog_notify_sys(struct notifier_block *this, static const struct file_operations indydog_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = indydog_write, .unlocked_ioctl = indydog_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/it8712f_wdt.c b/drivers/watchdog/it8712f_wdt.c index 3ce6a58bd81e..b776e6766c9d 100644 --- a/drivers/watchdog/it8712f_wdt.c +++ b/drivers/watchdog/it8712f_wdt.c @@ -341,7 +341,6 @@ static int it8712f_wdt_release(struct inode *inode, struct file *file) static const struct file_operations it8712f_wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = it8712f_wdt_write, .unlocked_ioctl = it8712f_wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/m54xx_wdt.c b/drivers/watchdog/m54xx_wdt.c index 062ea3e6497e..26bd073bd375 100644 --- a/drivers/watchdog/m54xx_wdt.c +++ b/drivers/watchdog/m54xx_wdt.c @@ -179,7 +179,6 @@ static int m54xx_wdt_release(struct inode *inode, struct file *file) static const struct file_operations m54xx_wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = m54xx_wdt_write, .unlocked_ioctl = m54xx_wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/machzwd.c b/drivers/watchdog/machzwd.c index 73f2221f6222..73d641486909 100644 --- a/drivers/watchdog/machzwd.c +++ b/drivers/watchdog/machzwd.c @@ -359,7 +359,6 @@ static int zf_notify_sys(struct notifier_block *this, unsigned long code, static const struct file_operations zf_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = zf_write, .unlocked_ioctl = zf_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/mixcomwd.c b/drivers/watchdog/mixcomwd.c index d387bad377c4..70d9cf84c342 100644 --- a/drivers/watchdog/mixcomwd.c +++ b/drivers/watchdog/mixcomwd.c @@ -224,7 +224,6 @@ static long mixcomwd_ioctl(struct file *file, static const struct file_operations mixcomwd_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = mixcomwd_write, .unlocked_ioctl = mixcomwd_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/mtx-1_wdt.c b/drivers/watchdog/mtx-1_wdt.c index 06756135033d..11f05024a181 100644 --- a/drivers/watchdog/mtx-1_wdt.c +++ b/drivers/watchdog/mtx-1_wdt.c @@ -177,7 +177,6 @@ static ssize_t mtx1_wdt_write(struct file *file, const char *buf, static const struct file_operations mtx1_wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .unlocked_ioctl = mtx1_wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, .open = mtx1_wdt_open, diff --git a/drivers/watchdog/nv_tco.c b/drivers/watchdog/nv_tco.c index ac4a9c16341d..f8eb1f65a59e 100644 --- a/drivers/watchdog/nv_tco.c +++ b/drivers/watchdog/nv_tco.c @@ -264,7 +264,6 @@ static long nv_tco_ioctl(struct file *file, unsigned int cmd, static const struct file_operations nv_tco_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = nv_tco_write, .unlocked_ioctl = nv_tco_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/pc87413_wdt.c b/drivers/watchdog/pc87413_wdt.c index c7f745caf203..fbf835d112b8 100644 --- a/drivers/watchdog/pc87413_wdt.c +++ b/drivers/watchdog/pc87413_wdt.c @@ -470,7 +470,6 @@ static int pc87413_notify_sys(struct notifier_block *this, static const struct file_operations pc87413_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = pc87413_write, .unlocked_ioctl = pc87413_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/pcwd.c b/drivers/watchdog/pcwd.c index a793b03a785d..1a4282235aac 100644 --- a/drivers/watchdog/pcwd.c +++ b/drivers/watchdog/pcwd.c @@ -749,7 +749,6 @@ static int pcwd_temp_close(struct inode *inode, struct file *file) static const struct file_operations pcwd_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = pcwd_write, .unlocked_ioctl = pcwd_ioctl, .compat_ioctl = compat_ptr_ioctl, @@ -765,7 +764,6 @@ static struct miscdevice pcwd_miscdev = { static const struct file_operations pcwd_temp_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = pcwd_temp_read, .open = pcwd_temp_open, .release = pcwd_temp_close, diff --git a/drivers/watchdog/pcwd_pci.c b/drivers/watchdog/pcwd_pci.c index 54d86fcb1837..a489b426f2ba 100644 --- a/drivers/watchdog/pcwd_pci.c +++ b/drivers/watchdog/pcwd_pci.c @@ -643,7 +643,6 @@ static int pcipcwd_notify_sys(struct notifier_block *this, unsigned long code, static const struct file_operations pcipcwd_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = pcipcwd_write, .unlocked_ioctl = pcipcwd_ioctl, .compat_ioctl = compat_ptr_ioctl, @@ -659,7 +658,6 @@ static struct miscdevice pcipcwd_miscdev = { static const struct file_operations pcipcwd_temp_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = pcipcwd_temp_read, .open = pcipcwd_temp_open, .release = pcipcwd_temp_release, diff --git a/drivers/watchdog/pcwd_usb.c b/drivers/watchdog/pcwd_usb.c index 8202f0a6b093..132699e2f247 100644 --- a/drivers/watchdog/pcwd_usb.c +++ b/drivers/watchdog/pcwd_usb.c @@ -549,7 +549,6 @@ static int usb_pcwd_notify_sys(struct notifier_block *this, unsigned long code, static const struct file_operations usb_pcwd_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = usb_pcwd_write, .unlocked_ioctl = usb_pcwd_ioctl, .compat_ioctl = compat_ptr_ioctl, @@ -565,7 +564,6 @@ static struct miscdevice usb_pcwd_miscdev = { static const struct file_operations usb_pcwd_temperature_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = usb_pcwd_temperature_read, .open = usb_pcwd_temperature_open, .release = usb_pcwd_temperature_release, diff --git a/drivers/watchdog/pika_wdt.c b/drivers/watchdog/pika_wdt.c index 782b8c23d99c..393aa4b1bc13 100644 --- a/drivers/watchdog/pika_wdt.c +++ b/drivers/watchdog/pika_wdt.c @@ -209,7 +209,6 @@ static long pikawdt_ioctl(struct file *file, static const struct file_operations pikawdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .open = pikawdt_open, .release = pikawdt_release, .write = pikawdt_write, diff --git a/drivers/watchdog/rc32434_wdt.c b/drivers/watchdog/rc32434_wdt.c index 417f9b75679c..efadbb9d7ce7 100644 --- a/drivers/watchdog/rc32434_wdt.c +++ b/drivers/watchdog/rc32434_wdt.c @@ -242,7 +242,6 @@ static long rc32434_wdt_ioctl(struct file *file, unsigned int cmd, static const struct file_operations rc32434_wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = rc32434_wdt_write, .unlocked_ioctl = rc32434_wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/rdc321x_wdt.c b/drivers/watchdog/rdc321x_wdt.c index 6176f4343fc5..80490316a27f 100644 --- a/drivers/watchdog/rdc321x_wdt.c +++ b/drivers/watchdog/rdc321x_wdt.c @@ -197,7 +197,6 @@ static ssize_t rdc321x_wdt_write(struct file *file, const char __user *buf, static const struct file_operations rdc321x_wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .unlocked_ioctl = rdc321x_wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, .open = rdc321x_wdt_open, diff --git a/drivers/watchdog/riowd.c b/drivers/watchdog/riowd.c index b293792a292a..f47d90d01c19 100644 --- a/drivers/watchdog/riowd.c +++ b/drivers/watchdog/riowd.c @@ -160,7 +160,6 @@ static ssize_t riowd_write(struct file *file, const char __user *buf, static const struct file_operations riowd_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .unlocked_ioctl = riowd_ioctl, .compat_ioctl = compat_ptr_ioctl, .open = riowd_open, diff --git a/drivers/watchdog/sa1100_wdt.c b/drivers/watchdog/sa1100_wdt.c index 34a917221e31..6e91ee3fbfb5 100644 --- a/drivers/watchdog/sa1100_wdt.c +++ b/drivers/watchdog/sa1100_wdt.c @@ -164,7 +164,6 @@ static long sa1100dog_ioctl(struct file *file, unsigned int cmd, static const struct file_operations sa1100dog_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = sa1100dog_write, .unlocked_ioctl = sa1100dog_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/sb_wdog.c b/drivers/watchdog/sb_wdog.c index 504be461f992..eaa68b54cf56 100644 --- a/drivers/watchdog/sb_wdog.c +++ b/drivers/watchdog/sb_wdog.c @@ -234,7 +234,6 @@ static int sbwdog_notify_sys(struct notifier_block *this, unsigned long code, static const struct file_operations sbwdog_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = sbwdog_write, .unlocked_ioctl = sbwdog_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/sbc60xxwdt.c b/drivers/watchdog/sbc60xxwdt.c index 7b974802dfc7..e9bf12918ed8 100644 --- a/drivers/watchdog/sbc60xxwdt.c +++ b/drivers/watchdog/sbc60xxwdt.c @@ -275,7 +275,6 @@ static long fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg) static const struct file_operations wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = fop_write, .open = fop_open, .release = fop_close, diff --git a/drivers/watchdog/sbc7240_wdt.c b/drivers/watchdog/sbc7240_wdt.c index d640b26e18a6..21a1f0b32070 100644 --- a/drivers/watchdog/sbc7240_wdt.c +++ b/drivers/watchdog/sbc7240_wdt.c @@ -205,7 +205,6 @@ static long fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg) static const struct file_operations wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = fop_write, .open = fop_open, .release = fop_close, diff --git a/drivers/watchdog/sbc8360.c b/drivers/watchdog/sbc8360.c index 4f8b9912fc51..a9fd1615b4c3 100644 --- a/drivers/watchdog/sbc8360.c +++ b/drivers/watchdog/sbc8360.c @@ -301,7 +301,6 @@ static int sbc8360_notify_sys(struct notifier_block *this, unsigned long code, static const struct file_operations sbc8360_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = sbc8360_write, .open = sbc8360_open, .release = sbc8360_close, diff --git a/drivers/watchdog/sbc_epx_c3.c b/drivers/watchdog/sbc_epx_c3.c index 5e3a9ddb952e..1d291dc0a4a6 100644 --- a/drivers/watchdog/sbc_epx_c3.c +++ b/drivers/watchdog/sbc_epx_c3.c @@ -153,7 +153,6 @@ static int epx_c3_notify_sys(struct notifier_block *this, unsigned long code, static const struct file_operations epx_c3_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = epx_c3_write, .unlocked_ioctl = epx_c3_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/sbc_fitpc2_wdt.c b/drivers/watchdog/sbc_fitpc2_wdt.c index b8eb8d5ca1af..ff9e44825423 100644 --- a/drivers/watchdog/sbc_fitpc2_wdt.c +++ b/drivers/watchdog/sbc_fitpc2_wdt.c @@ -181,7 +181,6 @@ static int fitpc2_wdt_release(struct inode *inode, struct file *file) static const struct file_operations fitpc2_wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = fitpc2_wdt_write, .unlocked_ioctl = fitpc2_wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/sc1200wdt.c b/drivers/watchdog/sc1200wdt.c index f22ebe89fe13..76a58715f665 100644 --- a/drivers/watchdog/sc1200wdt.c +++ b/drivers/watchdog/sc1200wdt.c @@ -304,7 +304,6 @@ static struct notifier_block sc1200wdt_notifier = { static const struct file_operations sc1200wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = sc1200wdt_write, .unlocked_ioctl = sc1200wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/sc520_wdt.c b/drivers/watchdog/sc520_wdt.c index ca65468f4b9c..e849e1af267b 100644 --- a/drivers/watchdog/sc520_wdt.c +++ b/drivers/watchdog/sc520_wdt.c @@ -331,7 +331,6 @@ static long fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg) static const struct file_operations wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = fop_write, .open = fop_open, .release = fop_close, diff --git a/drivers/watchdog/sch311x_wdt.c b/drivers/watchdog/sch311x_wdt.c index 409d49880170..76053158d259 100644 --- a/drivers/watchdog/sch311x_wdt.c +++ b/drivers/watchdog/sch311x_wdt.c @@ -334,7 +334,6 @@ static int sch311x_wdt_close(struct inode *inode, struct file *file) static const struct file_operations sch311x_wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = sch311x_wdt_write, .unlocked_ioctl = sch311x_wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/scx200_wdt.c b/drivers/watchdog/scx200_wdt.c index 7b5e18323f3f..4dd8549e3674 100644 --- a/drivers/watchdog/scx200_wdt.c +++ b/drivers/watchdog/scx200_wdt.c @@ -198,7 +198,6 @@ static long scx200_wdt_ioctl(struct file *file, unsigned int cmd, static const struct file_operations scx200_wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = scx200_wdt_write, .unlocked_ioctl = scx200_wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/smsc37b787_wdt.c b/drivers/watchdog/smsc37b787_wdt.c index 7463df479d11..97ca500ec8a8 100644 --- a/drivers/watchdog/smsc37b787_wdt.c +++ b/drivers/watchdog/smsc37b787_wdt.c @@ -502,7 +502,6 @@ static int wb_smsc_wdt_notify_sys(struct notifier_block *this, static const struct file_operations wb_smsc_wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = wb_smsc_wdt_write, .unlocked_ioctl = wb_smsc_wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/w83877f_wdt.c b/drivers/watchdog/w83877f_wdt.c index f2650863fd02..1937084c182c 100644 --- a/drivers/watchdog/w83877f_wdt.c +++ b/drivers/watchdog/w83877f_wdt.c @@ -299,7 +299,6 @@ static long fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg) static const struct file_operations wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = fop_write, .open = fop_open, .release = fop_close, diff --git a/drivers/watchdog/w83977f_wdt.c b/drivers/watchdog/w83977f_wdt.c index 31bf21ceaf48..3776030fa7c6 100644 --- a/drivers/watchdog/w83977f_wdt.c +++ b/drivers/watchdog/w83977f_wdt.c @@ -443,7 +443,6 @@ static int wdt_notify_sys(struct notifier_block *this, unsigned long code, static const struct file_operations wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = wdt_write, .unlocked_ioctl = wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/wafer5823wdt.c b/drivers/watchdog/wafer5823wdt.c index a8a1ed215e1e..291109349e73 100644 --- a/drivers/watchdog/wafer5823wdt.c +++ b/drivers/watchdog/wafer5823wdt.c @@ -227,7 +227,6 @@ static int wafwdt_notify_sys(struct notifier_block *this, unsigned long code, static const struct file_operations wafwdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = wafwdt_write, .unlocked_ioctl = wafwdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/wdrtas.c b/drivers/watchdog/wdrtas.c index c00627825de8..d4fe0bc82211 100644 --- a/drivers/watchdog/wdrtas.c +++ b/drivers/watchdog/wdrtas.c @@ -469,7 +469,6 @@ static int wdrtas_reboot(struct notifier_block *this, static const struct file_operations wdrtas_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = wdrtas_write, .unlocked_ioctl = wdrtas_ioctl, .compat_ioctl = compat_ptr_ioctl, @@ -485,7 +484,6 @@ static struct miscdevice wdrtas_miscdev = { static const struct file_operations wdrtas_temp_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = wdrtas_temp_read, .open = wdrtas_temp_open, .release = wdrtas_temp_close, diff --git a/drivers/watchdog/wdt.c b/drivers/watchdog/wdt.c index 183876156243..3980d60bacd8 100644 --- a/drivers/watchdog/wdt.c +++ b/drivers/watchdog/wdt.c @@ -520,7 +520,6 @@ static int wdt_notify_sys(struct notifier_block *this, unsigned long code, static const struct file_operations wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = wdt_write, .unlocked_ioctl = wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, @@ -536,7 +535,6 @@ static struct miscdevice wdt_miscdev = { static const struct file_operations wdt_temp_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = wdt_temp_read, .open = wdt_temp_open, .release = wdt_temp_release, diff --git a/drivers/watchdog/wdt285.c b/drivers/watchdog/wdt285.c index 5b7be7a62d54..78681d9f7d53 100644 --- a/drivers/watchdog/wdt285.c +++ b/drivers/watchdog/wdt285.c @@ -178,7 +178,6 @@ static long watchdog_ioctl(struct file *file, unsigned int cmd, static const struct file_operations watchdog_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = watchdog_write, .unlocked_ioctl = watchdog_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/wdt977.c b/drivers/watchdog/wdt977.c index c9b8e863f70f..4f449ac4dda4 100644 --- a/drivers/watchdog/wdt977.c +++ b/drivers/watchdog/wdt977.c @@ -419,7 +419,6 @@ static int wdt977_notify_sys(struct notifier_block *this, unsigned long code, static const struct file_operations wdt977_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = wdt977_write, .unlocked_ioctl = wdt977_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/wdt_pci.c b/drivers/watchdog/wdt_pci.c index d5e56b601351..dc5f29560e9b 100644 --- a/drivers/watchdog/wdt_pci.c +++ b/drivers/watchdog/wdt_pci.c @@ -563,7 +563,6 @@ static int wdtpci_notify_sys(struct notifier_block *this, unsigned long code, static const struct file_operations wdtpci_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = wdtpci_write, .unlocked_ioctl = wdtpci_ioctl, .compat_ioctl = compat_ptr_ioctl, @@ -579,7 +578,6 @@ static struct miscdevice wdtpci_miscdev = { static const struct file_operations wdtpci_temp_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = wdtpci_temp_read, .open = wdtpci_temp_open, .release = wdtpci_temp_release, diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c index 9b7fcc7dbb38..7e4a13e632dc 100644 --- a/drivers/xen/evtchn.c +++ b/drivers/xen/evtchn.c @@ -694,7 +694,6 @@ static const struct file_operations evtchn_fops = { .fasync = evtchn_fasync, .open = evtchn_open, .release = evtchn_release, - .llseek = no_llseek, }; static struct miscdevice evtchn_miscdev = { diff --git a/drivers/xen/mcelog.c b/drivers/xen/mcelog.c index e9ac3b8c4167..4f65b641c054 100644 --- a/drivers/xen/mcelog.c +++ b/drivers/xen/mcelog.c @@ -182,7 +182,6 @@ static const struct file_operations xen_mce_chrdev_ops = { .read = xen_mce_chrdev_read, .poll = xen_mce_chrdev_poll, .unlocked_ioctl = xen_mce_chrdev_ioctl, - .llseek = no_llseek, }; static struct miscdevice xen_mce_chrdev_device = { diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index 6f56640092a9..46f8916597e5 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -700,7 +700,6 @@ const struct file_operations xen_xenbus_fops = { .open = xenbus_file_open, .release = xenbus_file_release, .poll = xenbus_file_poll, - .llseek = no_llseek, }; EXPORT_SYMBOL_GPL(xen_xenbus_fops); diff --git a/fs/bcachefs/chardev.c b/fs/bcachefs/chardev.c index ef1f74866e23..cbfd88f98472 100644 --- a/fs/bcachefs/chardev.c +++ b/fs/bcachefs/chardev.c @@ -471,7 +471,6 @@ static ssize_t bch2_data_job_read(struct file *file, char __user *buf, static const struct file_operations bcachefs_data_ops = { .release = bch2_data_job_release, .read = bch2_data_job_read, - .llseek = no_llseek, }; static long bch2_ioctl_data(struct bch_fs *c, diff --git a/fs/bcachefs/thread_with_file.c b/fs/bcachefs/thread_with_file.c index fb3442a7c67f..dea73bc1cb51 100644 --- a/fs/bcachefs/thread_with_file.c +++ b/fs/bcachefs/thread_with_file.c @@ -275,7 +275,6 @@ static long thread_with_stdio_ioctl(struct file *file, unsigned int cmd, unsigne } static const struct file_operations thread_with_stdio_fops = { - .llseek = no_llseek, .read = thread_with_stdio_read, .write = thread_with_stdio_write, .poll = thread_with_stdio_poll, @@ -285,7 +284,6 @@ static const struct file_operations thread_with_stdio_fops = { }; static const struct file_operations thread_with_stdout_fops = { - .llseek = no_llseek, .read = thread_with_stdio_read, .poll = thread_with_stdout_poll, .flush = thread_with_stdio_flush, diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index c6f4a9a98b85..67299e8b734e 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -1218,7 +1218,6 @@ static const struct file_operations u32_array_fops = { .open = u32_array_open, .release = u32_array_release, .read = u32_array_read, - .llseek = no_llseek, }; /** diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c index 7112958c2e5b..700a0cbb2f14 100644 --- a/fs/dlm/debug_fs.c +++ b/fs/dlm/debug_fs.c @@ -733,7 +733,6 @@ out: static const struct file_operations dlm_rawmsg_fops = { .open = simple_open, .write = dlm_rawmsg_write, - .llseek = no_llseek, }; void *dlm_create_debug_comms_file(int nodeid, void *data) diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c index 7e9961639802..23c51d62f902 100644 --- a/fs/efivarfs/file.c +++ b/fs/efivarfs/file.c @@ -110,5 +110,4 @@ const struct file_operations efivarfs_file_operations = { .open = simple_open, .read = efivarfs_file_read, .write = efivarfs_file_write, - .llseek = no_llseek, }; diff --git a/fs/fsopen.c b/fs/fsopen.c index ee92ca58429e..6cef3deccded 100644 --- a/fs/fsopen.c +++ b/fs/fsopen.c @@ -78,7 +78,6 @@ static int fscontext_release(struct inode *inode, struct file *file) const struct file_operations fscontext_fops = { .read = fscontext_read, .release = fscontext_release, - .llseek = no_llseek, }; /* diff --git a/fs/fuse/control.c b/fs/fuse/control.c index 97ac994ff78f..2a730d88cc3b 100644 --- a/fs/fuse/control.c +++ b/fs/fuse/control.c @@ -183,27 +183,23 @@ out: static const struct file_operations fuse_ctl_abort_ops = { .open = nonseekable_open, .write = fuse_conn_abort_write, - .llseek = no_llseek, }; static const struct file_operations fuse_ctl_waiting_ops = { .open = nonseekable_open, .read = fuse_conn_waiting_read, - .llseek = no_llseek, }; static const struct file_operations fuse_conn_max_background_ops = { .open = nonseekable_open, .read = fuse_conn_max_background_read, .write = fuse_conn_max_background_write, - .llseek = no_llseek, }; static const struct file_operations fuse_conn_congestion_threshold_ops = { .open = nonseekable_open, .read = fuse_conn_congestion_threshold_read, .write = fuse_conn_congestion_threshold_write, - .llseek = no_llseek, }; static struct dentry *fuse_ctl_add_dentry(struct dentry *parent, diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 46ed30a4e0fc..1f64ae6d7a69 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -2456,7 +2456,6 @@ static long fuse_dev_ioctl(struct file *file, unsigned int cmd, const struct file_operations fuse_dev_operations = { .owner = THIS_MODULE, .open = fuse_dev_open, - .llseek = no_llseek, .read_iter = fuse_dev_read, .splice_read = fuse_dev_splice_read, .write_iter = fuse_dev_write, diff --git a/fs/nsfs.c b/fs/nsfs.c index 67ee176b8824..c675fc40ce2d 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -22,7 +22,6 @@ static struct vfsmount *nsfs_mnt; static long ns_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); static const struct file_operations ns_file_operations = { - .llseek = no_llseek, .unlocked_ioctl = ns_ioctl, .compat_ioctl = compat_ptr_ioctl, }; diff --git a/fs/pipe.c b/fs/pipe.c index 4083ba492cb6..12b22c2723b7 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -1231,7 +1231,6 @@ err: const struct file_operations pipefifo_fops = { .open = fifo_open, - .llseek = no_llseek, .read_iter = pipe_read, .write_iter = pipe_write, .poll = pipe_poll, diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c index d91cec93d968..5cc69beaa62e 100644 --- a/fs/ubifs/debug.c +++ b/fs/ubifs/debug.c @@ -2807,7 +2807,6 @@ static const struct file_operations dfs_fops = { .read = dfs_file_read, .write = dfs_file_write, .owner = THIS_MODULE, - .llseek = no_llseek, }; /** @@ -2952,7 +2951,6 @@ static const struct file_operations dfs_global_fops = { .read = dfs_global_file_read, .write = dfs_global_file_write, .owner = THIS_MODULE, - .llseek = no_llseek, }; /** diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index c9c65b132c0f..0928a6c8ae1e 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -57,7 +57,6 @@ static const struct file_operations __fops = { \ .release = simple_attr_release, \ .read = debugfs_attr_read, \ .write = (__is_signed) ? debugfs_attr_write_signed : debugfs_attr_write, \ - .llseek = no_llseek, \ } #define DEFINE_DEBUGFS_ATTRIBUTE(__fops, __get, __set, __fmt) \ diff --git a/include/linux/fs.h b/include/linux/fs.h index eae5b67e4a15..e3c603d01337 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3234,7 +3234,6 @@ extern ssize_t iter_file_splice_write(struct pipe_inode_info *, extern void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping); extern loff_t noop_llseek(struct file *file, loff_t offset, int whence); -#define no_llseek NULL extern loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize); extern loff_t generic_file_llseek(struct file *file, loff_t offset, int whence); extern loff_t generic_file_llseek_size(struct file *file, loff_t offset, diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index 112581cf97e7..106735145948 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -283,7 +283,6 @@ static int iter_release(struct inode *inode, struct file *file) const struct file_operations bpf_iter_fops = { .open = iter_open, - .llseek = no_llseek, .read = bpf_seq_read, .release = iter_release, }; diff --git a/kernel/events/core.c b/kernel/events/core.c index 5a8071c45c80..e3589c4287cb 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6821,7 +6821,6 @@ static int perf_fasync(int fd, struct file *filp, int on) } static const struct file_operations perf_fops = { - .llseek = no_llseek, .release = perf_release, .read = perf_read, .poll = perf_poll, diff --git a/kernel/power/user.c b/kernel/power/user.c index 3aa41ba22129..3f9e3efb9f6e 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -447,7 +447,6 @@ static const struct file_operations snapshot_fops = { .release = snapshot_release, .read = snapshot_read, .write = snapshot_write, - .llseek = no_llseek, .unlocked_ioctl = snapshot_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = snapshot_compat_ioctl, diff --git a/kernel/relay.c b/kernel/relay.c index a8e90e98bf2c..a8ae436dc77e 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -1079,7 +1079,6 @@ const struct file_operations relay_file_operations = { .poll = relay_file_poll, .mmap = relay_file_mmap, .read = relay_file_read, - .llseek = no_llseek, .release = relay_file_release, }; EXPORT_SYMBOL_GPL(relay_file_operations); diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c index 4782edcbe7b9..c2f3d0c490d5 100644 --- a/kernel/time/posix-clock.c +++ b/kernel/time/posix-clock.c @@ -168,7 +168,6 @@ static int posix_clock_release(struct inode *inode, struct file *fp) static const struct file_operations posix_clock_file_operations = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = posix_clock_read, .poll = posix_clock_poll, .unlocked_ioctl = posix_clock_ioctl, diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c index df0745a42a3f..dc819aec43e8 100644 --- a/kernel/trace/rv/rv.c +++ b/kernel/trace/rv/rv.c @@ -306,7 +306,6 @@ static ssize_t monitor_enable_write_data(struct file *filp, const char __user *u static const struct file_operations interface_enable_fops = { .open = simple_open, - .llseek = no_llseek, .write = monitor_enable_write_data, .read = monitor_enable_read_data, }; @@ -329,7 +328,6 @@ static ssize_t monitor_desc_read_data(struct file *filp, char __user *user_buf, static const struct file_operations interface_desc_fops = { .open = simple_open, - .llseek = no_llseek, .read = monitor_desc_read_data, }; @@ -674,7 +672,6 @@ static ssize_t monitoring_on_write_data(struct file *filp, const char __user *us static const struct file_operations monitoring_on_fops = { .open = simple_open, - .llseek = no_llseek, .write = monitoring_on_write_data, .read = monitoring_on_read_data, }; diff --git a/kernel/trace/rv/rv_reactors.c b/kernel/trace/rv/rv_reactors.c index 6aae106695b6..7b49cbe388d4 100644 --- a/kernel/trace/rv/rv_reactors.c +++ b/kernel/trace/rv/rv_reactors.c @@ -426,7 +426,6 @@ static ssize_t reacting_on_write_data(struct file *filp, const char __user *user static const struct file_operations reacting_on_fops = { .open = simple_open, - .llseek = no_llseek, .write = reacting_on_write_data, .read = reacting_on_read_data, }; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index b4f348b4653f..c01375adc471 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -7557,7 +7557,6 @@ static const struct file_operations tracing_pipe_fops = { .read = tracing_read_pipe, .splice_read = tracing_splice_read_pipe, .release = tracing_release_pipe, - .llseek = no_llseek, }; static const struct file_operations tracing_entries_fops = { @@ -7636,7 +7635,6 @@ static const struct file_operations snapshot_raw_fops = { .read = tracing_buffers_read, .release = tracing_buffers_release, .splice_read = tracing_buffers_splice_read, - .llseek = no_llseek, }; #endif /* CONFIG_TRACER_SNAPSHOT */ @@ -8466,7 +8464,6 @@ static const struct file_operations tracing_buffers_fops = { .flush = tracing_buffers_flush, .splice_read = tracing_buffers_splice_read, .unlocked_ioctl = tracing_buffers_ioctl, - .llseek = no_llseek, .mmap = tracing_buffers_mmap, }; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 0580ac9e47b9..3ca89e0279a7 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -4115,7 +4115,6 @@ out: static const struct file_operations split_huge_pages_fops = { .owner = THIS_MODULE, .write = split_huge_pages_write, - .llseek = no_llseek, }; static int __init split_huge_pages_debugfs(void) diff --git a/net/mac80211/rc80211_minstrel_ht_debugfs.c b/net/mac80211/rc80211_minstrel_ht_debugfs.c index 25b8a67a63a4..85149c774505 100644 --- a/net/mac80211/rc80211_minstrel_ht_debugfs.c +++ b/net/mac80211/rc80211_minstrel_ht_debugfs.c @@ -187,7 +187,6 @@ static const struct file_operations minstrel_ht_stat_fops = { .open = minstrel_ht_stats_open, .read = minstrel_stats_read, .release = minstrel_stats_release, - .llseek = no_llseek, }; static char * @@ -323,7 +322,6 @@ static const struct file_operations minstrel_ht_stat_csv_fops = { .open = minstrel_ht_stats_csv_open, .read = minstrel_stats_read, .release = minstrel_stats_release, - .llseek = no_llseek, }; void diff --git a/net/rfkill/core.c b/net/rfkill/core.c index 13a5126bc36e..7d3e82e4c2fc 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -1394,7 +1394,6 @@ static const struct file_operations rfkill_fops = { .release = rfkill_fop_release, .unlocked_ioctl = rfkill_fop_ioctl, .compat_ioctl = compat_ptr_ioctl, - .llseek = no_llseek, }; #define RFKILL_NAME "rfkill" diff --git a/net/socket.c b/net/socket.c index 7b046dd3e9a7..601ad74930ef 100644 --- a/net/socket.c +++ b/net/socket.c @@ -153,7 +153,6 @@ static void sock_show_fdinfo(struct seq_file *m, struct file *f) static const struct file_operations socket_file_ops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read_iter = sock_read_iter, .write_iter = sock_write_iter, .poll = sock_poll, diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 4f31e73dc34d..1bd3e531b0e0 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -1592,7 +1592,6 @@ static int cache_release_procfs(struct inode *inode, struct file *filp) } static const struct proc_ops cache_channel_proc_ops = { - .proc_lseek = no_llseek, .proc_read = cache_read_procfs, .proc_write = cache_write_procfs, .proc_poll = cache_poll_procfs, @@ -1658,7 +1657,6 @@ static const struct proc_ops cache_flush_proc_ops = { .proc_read = read_flush_procfs, .proc_write = write_flush_procfs, .proc_release = release_flush_procfs, - .proc_lseek = no_llseek, }; static void remove_cache_proc_entries(struct cache_detail *cd) @@ -1811,7 +1809,6 @@ static int cache_release_pipefs(struct inode *inode, struct file *filp) const struct file_operations cache_file_operations_pipefs = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = cache_read_pipefs, .write = cache_write_pipefs, .poll = cache_poll_pipefs, @@ -1877,7 +1874,6 @@ const struct file_operations cache_flush_operations_pipefs = { .read = read_flush_pipefs, .write = write_flush_pipefs, .release = release_flush_pipefs, - .llseek = no_llseek, }; int sunrpc_cache_register_pipefs(struct dentry *parent, diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 910a5d850d04..7ce3721c06ca 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -385,7 +385,6 @@ rpc_pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) static const struct file_operations rpc_pipe_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = rpc_pipe_read, .write = rpc_pipe_write, .poll = rpc_pipe_poll, diff --git a/samples/vfio-mdev/mtty.c b/samples/vfio-mdev/mtty.c index b382c696c877..59eefe2fed10 100644 --- a/samples/vfio-mdev/mtty.c +++ b/samples/vfio-mdev/mtty.c @@ -927,7 +927,6 @@ static const struct file_operations mtty_save_fops = { .unlocked_ioctl = mtty_precopy_ioctl, .compat_ioctl = compat_ptr_ioctl, .release = mtty_release_migf, - .llseek = no_llseek, }; static void mtty_save_state(struct mdev_state *mdev_state) @@ -1082,7 +1081,6 @@ static const struct file_operations mtty_resume_fops = { .owner = THIS_MODULE, .write = mtty_resume_write, .release = mtty_release_migf, - .llseek = no_llseek, }; static struct mtty_migration_file * diff --git a/scripts/coccinelle/api/stream_open.cocci b/scripts/coccinelle/api/stream_open.cocci index df00d6619b06..50ab60c81f13 100644 --- a/scripts/coccinelle/api/stream_open.cocci +++ b/scripts/coccinelle/api/stream_open.cocci @@ -131,7 +131,6 @@ identifier llseek_f; identifier fops0.fops; @@ struct file_operations fops = { - .llseek = no_llseek, }; @ has_noop_llseek @ diff --git a/sound/core/control.c b/sound/core/control.c index 4f55f64c42e1..2f790a7b1e90 100644 --- a/sound/core/control.c +++ b/sound/core/control.c @@ -2267,7 +2267,6 @@ static const struct file_operations snd_ctl_f_ops = .read = snd_ctl_read, .open = snd_ctl_open, .release = snd_ctl_release, - .llseek = no_llseek, .poll = snd_ctl_poll, .unlocked_ioctl = snd_ctl_ioctl, .compat_ioctl = snd_ctl_ioctl_compat, diff --git a/sound/core/oss/mixer_oss.c b/sound/core/oss/mixer_oss.c index 33bf9a220ada..668604d0ec9d 100644 --- a/sound/core/oss/mixer_oss.c +++ b/sound/core/oss/mixer_oss.c @@ -412,7 +412,6 @@ static const struct file_operations snd_mixer_oss_f_ops = .owner = THIS_MODULE, .open = snd_mixer_oss_open, .release = snd_mixer_oss_release, - .llseek = no_llseek, .unlocked_ioctl = snd_mixer_oss_ioctl, .compat_ioctl = snd_mixer_oss_ioctl_compat, }; diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c index 7386982cf40e..4683b9139c56 100644 --- a/sound/core/oss/pcm_oss.c +++ b/sound/core/oss/pcm_oss.c @@ -3106,7 +3106,6 @@ static const struct file_operations snd_pcm_oss_f_reg = .write = snd_pcm_oss_write, .open = snd_pcm_oss_open, .release = snd_pcm_oss_release, - .llseek = no_llseek, .poll = snd_pcm_oss_poll, .unlocked_ioctl = snd_pcm_oss_ioctl, .compat_ioctl = snd_pcm_oss_ioctl_compat, diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 99e39b5359cc..5b9076829ade 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -4115,7 +4115,6 @@ const struct file_operations snd_pcm_f_ops[2] = { .write_iter = snd_pcm_writev, .open = snd_pcm_playback_open, .release = snd_pcm_release, - .llseek = no_llseek, .poll = snd_pcm_poll, .unlocked_ioctl = snd_pcm_ioctl, .compat_ioctl = snd_pcm_ioctl_compat, @@ -4129,7 +4128,6 @@ const struct file_operations snd_pcm_f_ops[2] = { .read_iter = snd_pcm_readv, .open = snd_pcm_capture_open, .release = snd_pcm_release, - .llseek = no_llseek, .poll = snd_pcm_poll, .unlocked_ioctl = snd_pcm_ioctl, .compat_ioctl = snd_pcm_ioctl_compat, diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index 7accf9a1ddf4..03306be5fa02 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -1784,7 +1784,6 @@ static const struct file_operations snd_rawmidi_f_ops = { .write = snd_rawmidi_write, .open = snd_rawmidi_open, .release = snd_rawmidi_release, - .llseek = no_llseek, .poll = snd_rawmidi_poll, .unlocked_ioctl = snd_rawmidi_ioctl, .compat_ioctl = snd_rawmidi_ioctl_compat, diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 6437193e42bf..3930e2f9082f 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -2722,7 +2722,6 @@ static const struct file_operations snd_seq_f_ops = .write = snd_seq_write, .open = snd_seq_open, .release = snd_seq_release, - .llseek = no_llseek, .poll = snd_seq_poll, .unlocked_ioctl = snd_seq_ioctl, .compat_ioctl = snd_seq_ioctl_compat, diff --git a/sound/core/timer.c b/sound/core/timer.c index 668c40bac318..fbada79380f9 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -2436,7 +2436,6 @@ static const struct file_operations snd_timer_f_ops = .read = snd_timer_user_read, .open = snd_timer_user_open, .release = snd_timer_user_release, - .llseek = no_llseek, .poll = snd_timer_user_poll, .unlocked_ioctl = snd_timer_user_ioctl, .compat_ioctl = snd_timer_user_ioctl_compat, diff --git a/sound/oss/dmasound/dmasound_core.c b/sound/oss/dmasound/dmasound_core.c index 4b1baf4dd50e..dea2d9b18fc9 100644 --- a/sound/oss/dmasound/dmasound_core.c +++ b/sound/oss/dmasound/dmasound_core.c @@ -381,7 +381,6 @@ static long mixer_unlocked_ioctl(struct file *file, u_int cmd, u_long arg) static const struct file_operations mixer_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .unlocked_ioctl = mixer_unlocked_ioctl, .compat_ioctl = compat_ptr_ioctl, .open = mixer_open, @@ -1155,7 +1154,6 @@ static long sq_unlocked_ioctl(struct file *file, u_int cmd, u_long arg) static const struct file_operations sq_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = sq_write, .poll = sq_poll, .unlocked_ioctl = sq_unlocked_ioctl, @@ -1351,7 +1349,6 @@ static ssize_t state_read(struct file *file, char __user *buf, size_t count, static const struct file_operations state_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = state_read, .open = state_open, .release = state_release, diff --git a/sound/soc/intel/avs/debugfs.c b/sound/soc/intel/avs/debugfs.c index 3fc2bbb63369..1767ded4d983 100644 --- a/sound/soc/intel/avs/debugfs.c +++ b/sound/soc/intel/avs/debugfs.c @@ -68,7 +68,6 @@ static ssize_t fw_regs_read(struct file *file, char __user *to, size_t count, lo static const struct file_operations fw_regs_fops = { .open = simple_open, .read = fw_regs_read, - .llseek = no_llseek, }; static ssize_t debug_window_read(struct file *file, char __user *to, size_t count, loff_t *ppos) @@ -93,7 +92,6 @@ static ssize_t debug_window_read(struct file *file, char __user *to, size_t coun static const struct file_operations debug_window_fops = { .open = simple_open, .read = debug_window_read, - .llseek = no_llseek, }; static ssize_t probe_points_read(struct file *file, char __user *to, size_t count, loff_t *ppos) @@ -170,7 +168,6 @@ static const struct file_operations probe_points_fops = { .open = simple_open, .read = probe_points_read, .write = probe_points_write, - .llseek = no_llseek, }; static ssize_t probe_points_disconnect_write(struct file *file, const char __user *from, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index f416d5e3f9c0..4f81366f8b61 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -6186,7 +6186,6 @@ static const struct file_operations stat_fops_per_vm = { .release = kvm_debugfs_release, .read = simple_attr_read, .write = simple_attr_write, - .llseek = no_llseek, }; static int vm_stat_get(void *_offset, u64 *val) -- cgit v1.2.3