summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Kconfig.preempt2
-rw-r--r--kernel/Makefile2
-rw-r--r--kernel/audit.c7
-rw-r--r--kernel/audit_tree.c19
-rw-r--r--kernel/audit_watch.c41
-rw-r--r--kernel/auditfilter.c17
-rw-r--r--kernel/auditsc.c27
-rw-r--r--kernel/bpf/Makefile4
-rw-r--r--kernel/bpf/arraymap.c28
-rw-r--r--kernel/bpf/btf.c30
-rw-r--r--kernel/bpf/cgroup.c162
-rw-r--r--kernel/bpf/core.c79
-rw-r--r--kernel/bpf/cpumap.c18
-rw-r--r--kernel/bpf/devmap.c16
-rw-r--r--kernel/bpf/hashtab.c26
-rw-r--r--kernel/bpf/helpers.c20
-rw-r--r--kernel/bpf/inode.c11
-rw-r--r--kernel/bpf/local_storage.c379
-rw-r--r--kernel/bpf/lpm_trie.c12
-rw-r--r--kernel/bpf/map_in_map.c3
-rw-r--r--kernel/bpf/offload.c223
-rw-r--r--kernel/bpf/reuseport_array.c363
-rw-r--r--kernel/bpf/sockmap.c134
-rw-r--r--kernel/bpf/stackmap.c1
-rw-r--r--kernel/bpf/syscall.c107
-rw-r--r--kernel/bpf/verifier.c76
-rw-r--r--kernel/bpf/xskmap.c4
-rw-r--r--kernel/cgroup/cgroup.c4
-rw-r--r--kernel/compat.c29
-rw-r--r--kernel/cpu.c297
-rw-r--r--kernel/crash_core.c8
-rw-r--r--kernel/dma/contiguous.c6
-rw-r--r--kernel/dma/direct.c9
-rw-r--r--kernel/dma/noncoherent.c8
-rw-r--r--kernel/dma/swiotlb.c18
-rw-r--r--kernel/events/core.c36
-rw-r--r--kernel/events/hw_breakpoint.c92
-rw-r--r--kernel/events/uprobes.c82
-rw-r--r--kernel/exit.c12
-rw-r--r--kernel/fail_function.c3
-rw-r--r--kernel/fork.c105
-rw-r--r--kernel/freezer.c4
-rw-r--r--kernel/hung_task.c15
-rw-r--r--kernel/irq/Kconfig1
-rw-r--r--kernel/irq/irqdesc.c13
-rw-r--r--kernel/irq/manage.c56
-rw-r--r--kernel/irq/proc.c22
-rw-r--r--kernel/kexec.c8
-rw-r--r--kernel/kprobes.c167
-rw-r--r--kernel/kthread.c14
-rw-r--r--kernel/livepatch/core.c6
-rw-r--r--kernel/livepatch/transition.c7
-rw-r--r--kernel/locking/lockdep.c35
-rw-r--r--kernel/locking/locktorture.c7
-rw-r--r--kernel/locking/mutex.c345
-rw-r--r--kernel/locking/rtmutex.c29
-rw-r--r--kernel/locking/test-ww_mutex.c2
-rw-r--r--kernel/memremap.c32
-rw-r--r--kernel/module-internal.h25
-rw-r--r--kernel/module.c177
-rw-r--r--kernel/module_signing.c12
-rw-r--r--kernel/pid.c42
-rw-r--r--kernel/power/Kconfig1
-rw-r--r--kernel/power/hibernate.c16
-rw-r--r--kernel/power/main.c12
-rw-r--r--kernel/power/suspend.c8
-rw-r--r--kernel/power/swap.c4
-rw-r--r--kernel/power/user.c4
-rw-r--r--kernel/printk/internal.h9
-rw-r--r--kernel/printk/printk.c198
-rw-r--r--kernel/printk/printk_safe.c58
-rw-r--r--kernel/rcu/rcu.h104
-rw-r--r--kernel/rcu/rcuperf.c57
-rw-r--r--kernel/rcu/rcutorture.c462
-rw-r--r--kernel/rcu/srcutiny.c4
-rw-r--r--kernel/rcu/srcutree.c39
-rw-r--r--kernel/rcu/tiny.c4
-rw-r--r--kernel/rcu/tree.c1027
-rw-r--r--kernel/rcu/tree.h71
-rw-r--r--kernel/rcu/tree_exp.h18
-rw-r--r--kernel/rcu/tree_plugin.h188
-rw-r--r--kernel/rcu/update.c45
-rw-r--r--kernel/reboot.c6
-rw-r--r--kernel/sched/Makefile2
-rw-r--r--kernel/sched/clock.c57
-rw-r--r--kernel/sched/completion.c8
-rw-r--r--kernel/sched/core.c178
-rw-r--r--kernel/sched/cpufreq_schedutil.c103
-rw-r--r--kernel/sched/deadline.c16
-rw-r--r--kernel/sched/debug.c37
-rw-r--r--kernel/sched/fair.c664
-rw-r--r--kernel/sched/idle.c2
-rw-r--r--kernel/sched/pelt.c399
-rw-r--r--kernel/sched/pelt.h72
-rw-r--r--kernel/sched/rt.c17
-rw-r--r--kernel/sched/sched.h87
-rw-r--r--kernel/sched/swait.c32
-rw-r--r--kernel/sched/topology.c2
-rw-r--r--kernel/sched/wait.c57
-rw-r--r--kernel/signal.c268
-rw-r--r--kernel/smp.c2
-rw-r--r--kernel/smpboot.c54
-rw-r--r--kernel/softirq.c2
-rw-r--r--kernel/stop_machine.c35
-rw-r--r--kernel/sys.c4
-rw-r--r--kernel/sysctl.c27
-rw-r--r--kernel/test_kprobes.c94
-rw-r--r--kernel/time/alarmtimer.c7
-rw-r--r--kernel/time/clockevents.c6
-rw-r--r--kernel/time/clocksource.c149
-rw-r--r--kernel/time/hrtimer.c7
-rw-r--r--kernel/time/itimer.c5
-rw-r--r--kernel/time/ntp.c23
-rw-r--r--kernel/time/ntp_internal.h4
-rw-r--r--kernel/time/posix-cpu-timers.c4
-rw-r--r--kernel/time/posix-stubs.c2
-rw-r--r--kernel/time/posix-timers.c89
-rw-r--r--kernel/time/posix-timers.h2
-rw-r--r--kernel/time/sched_clock.c2
-rw-r--r--kernel/time/tick-broadcast-hrtimer.c2
-rw-r--r--kernel/time/tick-sched.c2
-rw-r--r--kernel/time/time.c31
-rw-r--r--kernel/time/timekeeping.c183
-rw-r--r--kernel/time/timekeeping_debug.c2
-rw-r--r--kernel/time/timekeeping_internal.h2
-rw-r--r--kernel/time/timer.c31
-rw-r--r--kernel/torture.c15
-rw-r--r--kernel/trace/Kconfig66
-rw-r--r--kernel/trace/Makefile8
-rw-r--r--kernel/trace/blktrace.c14
-rw-r--r--kernel/trace/bpf_trace.c5
-rw-r--r--kernel/trace/ftrace.c44
-rw-r--r--kernel/trace/preemptirq_delay_test.c72
-rw-r--r--kernel/trace/ring_buffer.c19
-rw-r--r--kernel/trace/ring_buffer_benchmark.c1
-rw-r--r--kernel/trace/trace.c17
-rw-r--r--kernel/trace/trace.h23
-rw-r--r--kernel/trace/trace_benchmark.h2
-rw-r--r--kernel/trace/trace_clock.c1
-rw-r--r--kernel/trace/trace_entries.h2
-rw-r--r--kernel/trace/trace_event_perf.c1
-rw-r--r--kernel/trace/trace_events.c13
-rw-r--r--kernel/trace/trace_events_filter.c30
-rw-r--r--kernel/trace/trace_events_filter_test.h2
-rw-r--r--kernel/trace/trace_events_hist.c13
-rw-r--r--kernel/trace/trace_events_trigger.c45
-rw-r--r--kernel/trace/trace_hwlat.c7
-rw-r--r--kernel/trace/trace_irqsoff.c270
-rw-r--r--kernel/trace/trace_kprobe.c120
-rw-r--r--kernel/trace/trace_kprobe_selftest.c10
-rw-r--r--kernel/trace/trace_kprobe_selftest.h7
-rw-r--r--kernel/trace/trace_output.c1
-rw-r--r--kernel/trace/trace_output.h2
-rw-r--r--kernel/trace/trace_preemptirq.c89
-rw-r--r--kernel/trace/trace_printk.c1
-rw-r--r--kernel/trace/trace_probe.c14
-rw-r--r--kernel/trace/trace_probe.h14
-rw-r--r--kernel/trace/trace_seq.c1
-rw-r--r--kernel/trace/trace_stat.h2
-rw-r--r--kernel/trace/trace_uprobe.c16
-rw-r--r--kernel/trace/tracing_map.c11
-rw-r--r--kernel/trace/tracing_map.h2
-rw-r--r--kernel/tracepoint.c97
-rw-r--r--kernel/user.c11
-rw-r--r--kernel/watchdog.c147
-rw-r--r--kernel/watchdog_hld.c4
166 files changed, 6196 insertions, 3669 deletions
diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index 3f9c97419f02..cd1655122ec0 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -18,6 +18,7 @@ config PREEMPT_NONE
config PREEMPT_VOLUNTARY
bool "Voluntary Kernel Preemption (Desktop)"
+ depends on !ARCH_NO_PREEMPT
help
This option reduces the latency of the kernel by adding more
"explicit preemption points" to the kernel code. These new
@@ -35,6 +36,7 @@ config PREEMPT_VOLUNTARY
config PREEMPT
bool "Preemptible Kernel (Low-Latency Desktop)"
+ depends on !ARCH_NO_PREEMPT
select PREEMPT_COUNT
select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK
help
diff --git a/kernel/Makefile b/kernel/Makefile
index 04bc07c2b42a..7a63d567fdb5 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -123,7 +123,7 @@ targets += config_data.gz
$(obj)/config_data.gz: $(KCONFIG_CONFIG) FORCE
$(call if_changed,gzip)
- filechk_ikconfiggz = (echo "static const char kernel_config_data[] __used = MAGIC_START"; cat $< | scripts/basic/bin2c; echo "MAGIC_END;")
+ filechk_ikconfiggz = (echo "static const char kernel_config_data[] __used = MAGIC_START"; cat $< | scripts/bin2c; echo "MAGIC_END;")
targets += config_data.h
$(obj)/config_data.h: $(obj)/config_data.gz FORCE
$(call filechk,ikconfiggz)
diff --git a/kernel/audit.c b/kernel/audit.c
index e7478cb58079..2a8058764aa6 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -83,9 +83,6 @@
#define AUDIT_INITIALIZED 1
static int audit_initialized;
-#define AUDIT_OFF 0
-#define AUDIT_ON 1
-#define AUDIT_LOCKED 2
u32 audit_enabled = AUDIT_OFF;
bool audit_ever_enabled = !!AUDIT_OFF;
@@ -1724,7 +1721,7 @@ static inline void audit_get_stamp(struct audit_context *ctx,
struct timespec64 *t, unsigned int *serial)
{
if (!ctx || !auditsc_get_stamp(ctx, t, serial)) {
- *t = current_kernel_time64();
+ ktime_get_coarse_real_ts64(t);
*serial = audit_serial();
}
}
@@ -1754,7 +1751,7 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
if (audit_initialized != AUDIT_INITIALIZED)
return NULL;
- if (unlikely(!audit_filter(type, AUDIT_FILTER_TYPE)))
+ if (unlikely(!audit_filter(type, AUDIT_FILTER_EXCLUDE)))
return NULL;
/* NOTE: don't ever fail/sleep on these two conditions:
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index c99ebaae5abc..ea43181cde4a 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -168,7 +168,8 @@ static __cacheline_aligned_in_smp DEFINE_SPINLOCK(hash_lock);
/* Function to return search key in our hash from inode. */
static unsigned long inode_to_key(const struct inode *inode)
{
- return (unsigned long)inode;
+ /* Use address pointed to by connector->obj as the key */
+ return (unsigned long)&inode->i_fsnotify_marks;
}
/*
@@ -183,7 +184,7 @@ static unsigned long chunk_to_key(struct audit_chunk *chunk)
*/
if (WARN_ON_ONCE(!chunk->mark.connector))
return 0;
- return (unsigned long)chunk->mark.connector->inode;
+ return (unsigned long)chunk->mark.connector->obj;
}
static inline struct list_head *chunk_hash(unsigned long key)
@@ -258,7 +259,7 @@ static void untag_chunk(struct node *p)
spin_lock(&entry->lock);
/*
* mark_mutex protects mark from getting detached and thus also from
- * mark->connector->inode getting NULL.
+ * mark->connector->obj getting NULL.
*/
if (chunk->dead || !(entry->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) {
spin_unlock(&entry->lock);
@@ -288,8 +289,8 @@ static void untag_chunk(struct node *p)
if (!new)
goto Fallback;
- if (fsnotify_add_inode_mark_locked(&new->mark, entry->connector->inode,
- 1)) {
+ if (fsnotify_add_mark_locked(&new->mark, entry->connector->obj,
+ FSNOTIFY_OBJ_TYPE_INODE, 1)) {
fsnotify_put_mark(&new->mark);
goto Fallback;
}
@@ -423,7 +424,7 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree)
spin_lock(&old_entry->lock);
/*
* mark_mutex protects mark from getting detached and thus also from
- * mark->connector->inode getting NULL.
+ * mark->connector->obj getting NULL.
*/
if (!(old_entry->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) {
/* old_entry is being shot, lets just lie */
@@ -434,8 +435,8 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree)
return -ENOENT;
}
- if (fsnotify_add_inode_mark_locked(chunk_entry,
- old_entry->connector->inode, 1)) {
+ if (fsnotify_add_mark_locked(chunk_entry, old_entry->connector->obj,
+ FSNOTIFY_OBJ_TYPE_INODE, 1)) {
spin_unlock(&old_entry->lock);
mutex_unlock(&old_entry->group->mark_mutex);
fsnotify_put_mark(chunk_entry);
@@ -497,6 +498,8 @@ static void audit_tree_log_remove_rule(struct audit_krule *rule)
{
struct audit_buffer *ab;
+ if (!audit_enabled)
+ return;
ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE);
if (unlikely(!ab))
return;
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index c17c0c268436..787c7afdf829 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -238,20 +238,21 @@ out:
static void audit_watch_log_rule_change(struct audit_krule *r, struct audit_watch *w, char *op)
{
- if (audit_enabled) {
- struct audit_buffer *ab;
- ab = audit_log_start(NULL, GFP_NOFS, AUDIT_CONFIG_CHANGE);
- if (unlikely(!ab))
- return;
- audit_log_format(ab, "auid=%u ses=%u op=%s",
- from_kuid(&init_user_ns, audit_get_loginuid(current)),
- audit_get_sessionid(current), op);
- audit_log_format(ab, " path=");
- audit_log_untrustedstring(ab, w->path);
- audit_log_key(ab, r->filterkey);
- audit_log_format(ab, " list=%d res=1", r->listnr);
- audit_log_end(ab);
- }
+ struct audit_buffer *ab;
+
+ if (!audit_enabled)
+ return;
+ ab = audit_log_start(NULL, GFP_NOFS, AUDIT_CONFIG_CHANGE);
+ if (!ab)
+ return;
+ audit_log_format(ab, "auid=%u ses=%u op=%s",
+ from_kuid(&init_user_ns, audit_get_loginuid(current)),
+ audit_get_sessionid(current), op);
+ audit_log_format(ab, " path=");
+ audit_log_untrustedstring(ab, w->path);
+ audit_log_key(ab, r->filterkey);
+ audit_log_format(ab, " list=%d res=1", r->listnr);
+ audit_log_end(ab);
}
/* Update inode info in audit rules based on filesystem event. */
@@ -419,6 +420,13 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list)
struct path parent_path;
int h, ret = 0;
+ /*
+ * When we will be calling audit_add_to_parent, krule->watch might have
+ * been updated and watch might have been freed.
+ * So we need to keep a reference of watch.
+ */
+ audit_get_watch(watch);
+
mutex_unlock(&audit_filter_mutex);
/* Avoid calling path_lookup under audit_filter_mutex. */
@@ -427,8 +435,10 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list)
/* caller expects mutex locked */
mutex_lock(&audit_filter_mutex);
- if (ret)
+ if (ret) {
+ audit_put_watch(watch);
return ret;
+ }
/* either find an old parent or attach a new one */
parent = audit_find_parent(d_backing_inode(parent_path.dentry));
@@ -446,6 +456,7 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list)
*list = &audit_inode_hash[h];
error:
path_put(&parent_path);
+ audit_put_watch(watch);
return ret;
}
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index eaa320148d97..bf309f2592c4 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -264,7 +264,7 @@ static inline struct audit_entry *audit_to_entry_common(struct audit_rule_data *
case AUDIT_FILTER_TASK:
#endif
case AUDIT_FILTER_USER:
- case AUDIT_FILTER_TYPE:
+ case AUDIT_FILTER_EXCLUDE:
case AUDIT_FILTER_FS:
;
}
@@ -337,7 +337,7 @@ static int audit_field_valid(struct audit_entry *entry, struct audit_field *f)
{
switch(f->type) {
case AUDIT_MSGTYPE:
- if (entry->rule.listnr != AUDIT_FILTER_TYPE &&
+ if (entry->rule.listnr != AUDIT_FILTER_EXCLUDE &&
entry->rule.listnr != AUDIT_FILTER_USER)
return -EINVAL;
break;
@@ -428,8 +428,6 @@ static int audit_field_valid(struct audit_entry *entry, struct audit_field *f)
case AUDIT_EXE:
if (f->op != Audit_not_equal && f->op != Audit_equal)
return -EINVAL;
- if (entry->rule.listnr != AUDIT_FILTER_EXIT)
- return -EINVAL;
break;
}
return 0;
@@ -931,7 +929,7 @@ static inline int audit_add_rule(struct audit_entry *entry)
/* If any of these, don't count towards total */
switch(entry->rule.listnr) {
case AUDIT_FILTER_USER:
- case AUDIT_FILTER_TYPE:
+ case AUDIT_FILTER_EXCLUDE:
case AUDIT_FILTER_FS:
dont_count = 1;
}
@@ -1013,7 +1011,7 @@ int audit_del_rule(struct audit_entry *entry)
/* If any of these, don't count towards total */
switch(entry->rule.listnr) {
case AUDIT_FILTER_USER:
- case AUDIT_FILTER_TYPE:
+ case AUDIT_FILTER_EXCLUDE:
case AUDIT_FILTER_FS:
dont_count = 1;
}
@@ -1360,6 +1358,11 @@ int audit_filter(int msgtype, unsigned int listtype)
f->type, f->op, f->lsm_rule, NULL);
}
break;
+ case AUDIT_EXE:
+ result = audit_exe_compare(current, e->rule.exe);
+ if (f->op == Audit_not_equal)
+ result = !result;
+ break;
default:
goto unlock_and_return;
}
@@ -1369,7 +1372,7 @@ int audit_filter(int msgtype, unsigned int listtype)
break;
}
if (result > 0) {
- if (e->rule.action == AUDIT_NEVER || listtype == AUDIT_FILTER_TYPE)
+ if (e->rule.action == AUDIT_NEVER || listtype == AUDIT_FILTER_EXCLUDE)
ret = 0;
break;
}
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index ceb1c4596c51..b2d1f043f17f 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -494,20 +494,20 @@ static int audit_filter_rules(struct task_struct *tsk,
result = audit_gid_comparator(cred->gid, f->op, f->gid);
if (f->op == Audit_equal) {
if (!result)
- result = in_group_p(f->gid);
+ result = groups_search(cred->group_info, f->gid);
} else if (f->op == Audit_not_equal) {
if (result)
- result = !in_group_p(f->gid);
+ result = !groups_search(cred->group_info, f->gid);
}
break;
case AUDIT_EGID:
result = audit_gid_comparator(cred->egid, f->op, f->gid);
if (f->op == Audit_equal) {
if (!result)
- result = in_egroup_p(f->gid);
+ result = groups_search(cred->group_info, f->gid);
} else if (f->op == Audit_not_equal) {
if (result)
- result = !in_egroup_p(f->gid);
+ result = !groups_search(cred->group_info, f->gid);
}
break;
case AUDIT_SGID:
@@ -1279,8 +1279,12 @@ static void show_special(struct audit_context *context, int *call_panic)
break;
case AUDIT_KERN_MODULE:
audit_log_format(ab, "name=");
- audit_log_untrustedstring(ab, context->module.name);
- kfree(context->module.name);
+ if (context->module.name) {
+ audit_log_untrustedstring(ab, context->module.name);
+ kfree(context->module.name);
+ } else
+ audit_log_format(ab, "(null)");
+
break;
}
audit_log_end(ab);
@@ -1540,10 +1544,10 @@ void __audit_syscall_entry(int major, unsigned long a1, unsigned long a2,
context->argv[2] = a3;
context->argv[3] = a4;
context->serial = 0;
- context->ctime = current_kernel_time64();
context->in_syscall = 1;
context->current_state = state;
context->ppid = 0;
+ ktime_get_coarse_real_ts64(&context->ctime);
}
/**
@@ -2411,8 +2415,9 @@ void __audit_log_kern_module(char *name)
{
struct audit_context *context = audit_context();
- context->module.name = kmalloc(strlen(name) + 1, GFP_KERNEL);
- strcpy(context->module.name, name);
+ context->module.name = kstrdup(name, GFP_KERNEL);
+ if (!context->module.name)
+ audit_log_lost("out of memory in __audit_log_kern_module");
context->type = AUDIT_KERN_MODULE;
}
@@ -2461,7 +2466,7 @@ void audit_core_dumps(long signr)
if (signr == SIGQUIT) /* don't care for those */
return;
- ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_ANOM_ABEND);
+ ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_ANOM_ABEND);
if (unlikely(!ab))
return;
audit_log_task(ab);
@@ -2485,7 +2490,7 @@ void audit_seccomp(unsigned long syscall, long signr, int code)
{
struct audit_buffer *ab;
- ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_SECCOMP);
+ ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_SECCOMP);
if (unlikely(!ab))
return;
audit_log_task(ab);
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index f27f5496d6fe..0488b8258321 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -3,6 +3,7 @@ obj-y := core.o
obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o
obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
+obj-$(CONFIG_BPF_SYSCALL) += local_storage.o
obj-$(CONFIG_BPF_SYSCALL) += disasm.o
obj-$(CONFIG_BPF_SYSCALL) += btf.o
ifeq ($(CONFIG_NET),y)
@@ -22,3 +23,6 @@ ifeq ($(CONFIG_PERF_EVENTS),y)
obj-$(CONFIG_BPF_SYSCALL) += stackmap.o
endif
obj-$(CONFIG_CGROUP_BPF) += cgroup.o
+ifeq ($(CONFIG_INET),y)
+obj-$(CONFIG_BPF_SYSCALL) += reuseport_array.o
+endif
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 544e58f5f642..0c17aab3ce5f 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -54,7 +54,7 @@ static int bpf_array_alloc_percpu(struct bpf_array *array)
}
/* Called from syscall */
-static int array_map_alloc_check(union bpf_attr *attr)
+int array_map_alloc_check(union bpf_attr *attr)
{
bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
int numa_node = bpf_map_attr_numa_node(attr);
@@ -358,27 +358,20 @@ static void array_map_seq_show_elem(struct bpf_map *map, void *key,
rcu_read_unlock();
}
-static int array_map_check_btf(const struct bpf_map *map, const struct btf *btf,
- u32 btf_key_id, u32 btf_value_id)
+static int array_map_check_btf(const struct bpf_map *map,
+ const struct btf_type *key_type,
+ const struct btf_type *value_type)
{
- const struct btf_type *key_type, *value_type;
- u32 key_size, value_size;
u32 int_data;
- key_type = btf_type_id_size(btf, &btf_key_id, &key_size);
- if (!key_type || BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
+ if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
return -EINVAL;
int_data = *(u32 *)(key_type + 1);
- /* bpf array can only take a u32 key. This check makes
- * sure that the btf matches the attr used during map_create.
+ /* bpf array can only take a u32 key. This check makes sure
+ * that the btf matches the attr used during map_create.
*/
- if (BTF_INT_BITS(int_data) != 32 || key_size != 4 ||
- BTF_INT_OFFSET(int_data))
- return -EINVAL;
-
- value_type = btf_type_id_size(btf, &btf_value_id, &value_size);
- if (!value_type || value_size > map->value_size)
+ if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data))
return -EINVAL;
return 0;
@@ -405,6 +398,7 @@ const struct bpf_map_ops percpu_array_map_ops = {
.map_lookup_elem = percpu_array_map_lookup_elem,
.map_update_elem = array_map_update_elem,
.map_delete_elem = array_map_delete_elem,
+ .map_check_btf = array_map_check_btf,
};
static int fd_array_map_alloc_check(union bpf_attr *attr)
@@ -546,6 +540,7 @@ const struct bpf_map_ops prog_array_map_ops = {
.map_fd_put_ptr = prog_fd_array_put_ptr,
.map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem,
.map_release_uref = bpf_fd_array_map_clear,
+ .map_check_btf = map_check_no_btf,
};
static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file,
@@ -634,6 +629,7 @@ const struct bpf_map_ops perf_event_array_map_ops = {
.map_fd_get_ptr = perf_event_fd_array_get_ptr,
.map_fd_put_ptr = perf_event_fd_array_put_ptr,
.map_release = perf_event_fd_array_release,
+ .map_check_btf = map_check_no_btf,
};
#ifdef CONFIG_CGROUPS
@@ -665,6 +661,7 @@ const struct bpf_map_ops cgroup_array_map_ops = {
.map_delete_elem = fd_array_map_delete_elem,
.map_fd_get_ptr = cgroup_fd_array_get_ptr,
.map_fd_put_ptr = cgroup_fd_array_put_ptr,
+ .map_check_btf = map_check_no_btf,
};
#endif
@@ -749,4 +746,5 @@ const struct bpf_map_ops array_of_maps_map_ops = {
.map_fd_put_ptr = bpf_map_fd_put_ptr,
.map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem,
.map_gen_lookup = array_of_map_gen_lookup,
+ .map_check_btf = map_check_no_btf,
};
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index e016ac3afa24..2590700237c1 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -450,7 +450,7 @@ static const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id)
*/
static bool btf_type_int_is_regular(const struct btf_type *t)
{
- u16 nr_bits, nr_bytes;
+ u8 nr_bits, nr_bytes;
u32 int_data;
int_data = btf_type_int(t);
@@ -993,12 +993,16 @@ static void btf_int_bits_seq_show(const struct btf *btf,
{
u16 left_shift_bits, right_shift_bits;
u32 int_data = btf_type_int(t);
- u16 nr_bits = BTF_INT_BITS(int_data);
- u16 total_bits_offset;
- u16 nr_copy_bytes;
- u16 nr_copy_bits;
+ u8 nr_bits = BTF_INT_BITS(int_data);
+ u8 total_bits_offset;
+ u8 nr_copy_bytes;
+ u8 nr_copy_bits;
u64 print_num;
+ /*
+ * bits_offset is at most 7.
+ * BTF_INT_OFFSET() cannot exceed 64 bits.
+ */
total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data);
data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset);
@@ -1028,7 +1032,7 @@ static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t,
u32 int_data = btf_type_int(t);
u8 encoding = BTF_INT_ENCODING(int_data);
bool sign = encoding & BTF_INT_SIGNED;
- u32 nr_bits = BTF_INT_BITS(int_data);
+ u8 nr_bits = BTF_INT_BITS(int_data);
if (bits_offset || BTF_INT_OFFSET(int_data) ||
BITS_PER_BYTE_MASKED(nr_bits)) {
@@ -1515,9 +1519,9 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
{
bool is_union = BTF_INFO_KIND(t->info) == BTF_KIND_UNION;
const struct btf_member *member;
+ u32 meta_needed, last_offset;
struct btf *btf = env->btf;
u32 struct_size = t->size;
- u32 meta_needed;
u16 i;
meta_needed = btf_type_vlen(t) * sizeof(*member);
@@ -1530,6 +1534,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
btf_verifier_log_type(env, t, NULL);
+ last_offset = 0;
for_each_member(i, t, member) {
if (!btf_name_offset_valid(btf, member->name_off)) {
btf_verifier_log_member(env, t, member,
@@ -1551,6 +1556,16 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
return -EINVAL;
}
+ /*
+ * ">" instead of ">=" because the last member could be
+ * "char a[0];"
+ */
+ if (last_offset > member->offset) {
+ btf_verifier_log_member(env, t, member,
+ "Invalid member bits_offset");
+ return -EINVAL;
+ }
+
if (BITS_ROUNDUP_BYTES(member->offset) > struct_size) {
btf_verifier_log_member(env, t, member,
"Memmber bits_offset exceeds its struct size");
@@ -1558,6 +1573,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
}
btf_verifier_log_member(env, t, member, NULL);
+ last_offset = member->offset;
}
return meta_needed;
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 3d83ee7df381..6a7d931bbc55 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -34,6 +34,8 @@ void cgroup_bpf_put(struct cgroup *cgrp)
list_for_each_entry_safe(pl, tmp, progs, node) {
list_del(&pl->node);
bpf_prog_put(pl->prog);
+ bpf_cgroup_storage_unlink(pl->storage);
+ bpf_cgroup_storage_free(pl->storage);
kfree(pl);
static_branch_dec(&cgroup_bpf_enabled_key);
}
@@ -95,7 +97,7 @@ static int compute_effective_progs(struct cgroup *cgrp,
enum bpf_attach_type type,
struct bpf_prog_array __rcu **array)
{
- struct bpf_prog_array __rcu *progs;
+ struct bpf_prog_array *progs;
struct bpf_prog_list *pl;
struct cgroup *p = cgrp;
int cnt = 0;
@@ -115,18 +117,20 @@ static int compute_effective_progs(struct cgroup *cgrp,
cnt = 0;
p = cgrp;
do {
- if (cnt == 0 || (p->bpf.flags[type] & BPF_F_ALLOW_MULTI))
- list_for_each_entry(pl,
- &p->bpf.progs[type], node) {
- if (!pl->prog)
- continue;
- rcu_dereference_protected(progs, 1)->
- progs[cnt++] = pl->prog;
- }
- p = cgroup_parent(p);
- } while (p);
+ if (cnt > 0 && !(p->bpf.flags[type] & BPF_F_ALLOW_MULTI))
+ continue;
+
+ list_for_each_entry(pl, &p->bpf.progs[type], node) {
+ if (!pl->prog)
+ continue;
- *array = progs;
+ progs->items[cnt].prog = pl->prog;
+ progs->items[cnt].cgroup_storage = pl->storage;
+ cnt++;
+ }
+ } while ((p = cgroup_parent(p)));
+
+ rcu_assign_pointer(*array, progs);
return 0;
}
@@ -173,6 +177,45 @@ cleanup:
return -ENOMEM;
}
+static int update_effective_progs(struct cgroup *cgrp,
+ enum bpf_attach_type type)
+{
+ struct cgroup_subsys_state *css;
+ int err;
+
+ /* allocate and recompute effective prog arrays */
+ css_for_each_descendant_pre(css, &cgrp->self) {
+ struct cgroup *desc = container_of(css, struct cgroup, self);
+
+ err = compute_effective_progs(desc, type, &desc->bpf.inactive);
+ if (err)
+ goto cleanup;
+ }
+
+ /* all allocations were successful. Activate all prog arrays */
+ css_for_each_descendant_pre(css, &cgrp->self) {
+ struct cgroup *desc = container_of(css, struct cgroup, self);
+
+ activate_effective_progs(desc, type, desc->bpf.inactive);
+ desc->bpf.inactive = NULL;
+ }
+
+ return 0;
+
+cleanup:
+ /* oom while computing effective. Free all computed effective arrays
+ * since they were not activated
+ */
+ css_for_each_descendant_pre(css, &cgrp->self) {
+ struct cgroup *desc = container_of(css, struct cgroup, self);
+
+ bpf_prog_array_free(desc->bpf.inactive);
+ desc->bpf.inactive = NULL;
+ }
+
+ return err;
+}
+
#define BPF_CGROUP_MAX_PROGS 64
/**
@@ -189,7 +232,7 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
{
struct list_head *progs = &cgrp->bpf.progs[type];
struct bpf_prog *old_prog = NULL;
- struct cgroup_subsys_state *css;
+ struct bpf_cgroup_storage *storage, *old_storage = NULL;
struct bpf_prog_list *pl;
bool pl_was_allocated;
int err;
@@ -211,72 +254,71 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS)
return -E2BIG;
+ storage = bpf_cgroup_storage_alloc(prog);
+ if (IS_ERR(storage))
+ return -ENOMEM;
+
if (flags & BPF_F_ALLOW_MULTI) {
- list_for_each_entry(pl, progs, node)
- if (pl->prog == prog)
+ list_for_each_entry(pl, progs, node) {
+ if (pl->prog == prog) {
/* disallow attaching the same prog twice */
+ bpf_cgroup_storage_free(storage);
return -EINVAL;
+ }
+ }
pl = kmalloc(sizeof(*pl), GFP_KERNEL);
- if (!pl)
+ if (!pl) {
+ bpf_cgroup_storage_free(storage);
return -ENOMEM;
+ }
+
pl_was_allocated = true;
pl->prog = prog;
+ pl->storage = storage;
list_add_tail(&pl->node, progs);
} else {
if (list_empty(progs)) {
pl = kmalloc(sizeof(*pl), GFP_KERNEL);
- if (!pl)
+ if (!pl) {
+ bpf_cgroup_storage_free(storage);
return -ENOMEM;
+ }
pl_was_allocated = true;
list_add_tail(&pl->node, progs);
} else {
pl = list_first_entry(progs, typeof(*pl), node);
old_prog = pl->prog;
+ old_storage = pl->storage;
+ bpf_cgroup_storage_unlink(old_storage);
pl_was_allocated = false;
}
pl->prog = prog;
+ pl->storage = storage;
}
cgrp->bpf.flags[type] = flags;
- /* allocate and recompute effective prog arrays */
- css_for_each_descendant_pre(css, &cgrp->self) {
- struct cgroup *desc = container_of(css, struct cgroup, self);
-
- err = compute_effective_progs(desc, type, &desc->bpf.inactive);
- if (err)
- goto cleanup;
- }
-
- /* all allocations were successful. Activate all prog arrays */
- css_for_each_descendant_pre(css, &cgrp->self) {
- struct cgroup *desc = container_of(css, struct cgroup, self);
-
- activate_effective_progs(desc, type, desc->bpf.inactive);
- desc->bpf.inactive = NULL;
- }
+ err = update_effective_progs(cgrp, type);
+ if (err)
+ goto cleanup;
static_branch_inc(&cgroup_bpf_enabled_key);
+ if (old_storage)
+ bpf_cgroup_storage_free(old_storage);
if (old_prog) {
bpf_prog_put(old_prog);
static_branch_dec(&cgroup_bpf_enabled_key);
}
+ bpf_cgroup_storage_link(storage, cgrp, type);
return 0;
cleanup:
- /* oom while computing effective. Free all computed effective arrays
- * since they were not activated
- */
- css_for_each_descendant_pre(css, &cgrp->self) {
- struct cgroup *desc = container_of(css, struct cgroup, self);
-
- bpf_prog_array_free(desc->bpf.inactive);
- desc->bpf.inactive = NULL;
- }
-
/* and cleanup the prog list */
pl->prog = old_prog;
+ bpf_cgroup_storage_free(pl->storage);
+ pl->storage = old_storage;
+ bpf_cgroup_storage_link(old_storage, cgrp, type);
if (pl_was_allocated) {
list_del(&pl->node);
kfree(pl);
@@ -299,7 +341,6 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
struct list_head *progs = &cgrp->bpf.progs[type];
u32 flags = cgrp->bpf.flags[type];
struct bpf_prog *old_prog = NULL;
- struct cgroup_subsys_state *css;
struct bpf_prog_list *pl;
int err;
@@ -338,25 +379,14 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
pl->prog = NULL;
}
- /* allocate and recompute effective prog arrays */
- css_for_each_descendant_pre(css, &cgrp->self) {
- struct cgroup *desc = container_of(css, struct cgroup, self);
-
- err = compute_effective_progs(desc, type, &desc->bpf.inactive);
- if (err)
- goto cleanup;
- }
-
- /* all allocations were successful. Activate all prog arrays */
- css_for_each_descendant_pre(css, &cgrp->self) {
- struct cgroup *desc = container_of(css, struct cgroup, self);
-
- activate_effective_progs(desc, type, desc->bpf.inactive);
- desc->bpf.inactive = NULL;
- }
+ err = update_effective_progs(cgrp, type);
+ if (err)
+ goto cleanup;
/* now can actually delete it from this cgroup list */
list_del(&pl->node);
+ bpf_cgroup_storage_unlink(pl->storage);
+ bpf_cgroup_storage_free(pl->storage);
kfree(pl);
if (list_empty(progs))
/* last program was detached, reset flags to zero */
@@ -367,16 +397,6 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
return 0;
cleanup:
- /* oom while computing effective. Free all computed effective arrays
- * since they were not activated
- */
- css_for_each_descendant_pre(css, &cgrp->self) {
- struct cgroup *desc = container_of(css, struct cgroup, self);
-
- bpf_prog_array_free(desc->bpf.inactive);
- desc->bpf.inactive = NULL;
- }
-
/* and restore back old_prog */
pl->prog = old_prog;
return err;
@@ -655,6 +675,8 @@ cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_map_delete_elem_proto;
case BPF_FUNC_get_current_uid_gid:
return &bpf_get_current_uid_gid_proto;
+ case BPF_FUNC_get_local_storage:
+ return &bpf_get_local_storage_proto;
case BPF_FUNC_trace_printk:
if (capable(CAP_SYS_ADMIN))
return bpf_get_trace_printk_proto();
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 1e5625d46414..3f5bf1af0826 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1538,11 +1538,12 @@ static struct {
.null_prog = NULL,
};
-struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags)
+struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags)
{
if (prog_cnt)
return kzalloc(sizeof(struct bpf_prog_array) +
- sizeof(struct bpf_prog *) * (prog_cnt + 1),
+ sizeof(struct bpf_prog_array_item) *
+ (prog_cnt + 1),
flags);
return &empty_prog_array.hdr;
@@ -1556,43 +1557,45 @@ void bpf_prog_array_free(struct bpf_prog_array __rcu *progs)
kfree_rcu(progs, rcu);
}
-int bpf_prog_array_length(struct bpf_prog_array __rcu *progs)
+int bpf_prog_array_length(struct bpf_prog_array __rcu *array)
{
- struct bpf_prog **prog;
+ struct bpf_prog_array_item *item;
u32 cnt = 0;
rcu_read_lock();
- prog = rcu_dereference(progs)->progs;
- for (; *prog; prog++)
- if (*prog != &dummy_bpf_prog.prog)
+ item = rcu_dereference(array)->items;
+ for (; item->prog; item++)
+ if (item->prog != &dummy_bpf_prog.prog)
cnt++;
rcu_read_unlock();
return cnt;
}
-static bool bpf_prog_array_copy_core(struct bpf_prog **prog,
+
+static bool bpf_prog_array_copy_core(struct bpf_prog_array __rcu *array,
u32 *prog_ids,
u32 request_cnt)
{
+ struct bpf_prog_array_item *item;
int i = 0;
- for (; *prog; prog++) {
- if (*prog == &dummy_bpf_prog.prog)
+ item = rcu_dereference_check(array, 1)->items;
+ for (; item->prog; item++) {
+ if (item->prog == &dummy_bpf_prog.prog)
continue;
- prog_ids[i] = (*prog)->aux->id;
+ prog_ids[i] = item->prog->aux->id;
if (++i == request_cnt) {
- prog++;
+ item++;
break;
}
}
- return !!(*prog);
+ return !!(item->prog);
}
-int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
+int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *array,
__u32 __user *prog_ids, u32 cnt)
{
- struct bpf_prog **prog;
unsigned long err = 0;
bool nospc;
u32 *ids;
@@ -1611,8 +1614,7 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
if (!ids)
return -ENOMEM;
rcu_read_lock();
- prog = rcu_dereference(progs)->progs;
- nospc = bpf_prog_array_copy_core(prog, ids, cnt);
+ nospc = bpf_prog_array_copy_core(array, ids, cnt);
rcu_read_unlock();
err = copy_to_user(prog_ids, ids, cnt * sizeof(u32));
kfree(ids);
@@ -1623,14 +1625,14 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
return 0;
}
-void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *progs,
+void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *array,
struct bpf_prog *old_prog)
{
- struct bpf_prog **prog = progs->progs;
+ struct bpf_prog_array_item *item = array->items;
- for (; *prog; prog++)
- if (*prog == old_prog) {
- WRITE_ONCE(*prog, &dummy_bpf_prog.prog);
+ for (; item->prog; item++)
+ if (item->prog == old_prog) {
+ WRITE_ONCE(item->prog, &dummy_bpf_prog.prog);
break;
}
}
@@ -1641,7 +1643,7 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
struct bpf_prog_array **new_array)
{
int new_prog_cnt, carry_prog_cnt = 0;
- struct bpf_prog **existing_prog;
+ struct bpf_prog_array_item *existing;
struct bpf_prog_array *array;
bool found_exclude = false;
int new_prog_idx = 0;
@@ -1650,15 +1652,15 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
* the new array.
*/
if (old_array) {
- existing_prog = old_array->progs;
- for (; *existing_prog; existing_prog++) {
- if (*existing_prog == exclude_prog) {
+ existing = old_array->items;
+ for (; existing->prog; existing++) {
+ if (existing->prog == exclude_prog) {
found_exclude = true;
continue;
}
- if (*existing_prog != &dummy_bpf_prog.prog)
+ if (existing->prog != &dummy_bpf_prog.prog)
carry_prog_cnt++;
- if (*existing_prog == include_prog)
+ if (existing->prog == include_prog)
return -EEXIST;
}
}
@@ -1684,15 +1686,17 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
/* Fill in the new prog array */
if (carry_prog_cnt) {
- existing_prog = old_array->progs;
- for (; *existing_prog; existing_prog++)
- if (*existing_prog != exclude_prog &&
- *existing_prog != &dummy_bpf_prog.prog)
- array->progs[new_prog_idx++] = *existing_prog;
+ existing = old_array->items;
+ for (; existing->prog; existing++)
+ if (existing->prog != exclude_prog &&
+ existing->prog != &dummy_bpf_prog.prog) {
+ array->items[new_prog_idx++].prog =
+ existing->prog;
+ }
}
if (include_prog)
- array->progs[new_prog_idx++] = include_prog;
- array->progs[new_prog_idx] = NULL;
+ array->items[new_prog_idx++].prog = include_prog;
+ array->items[new_prog_idx].prog = NULL;
*new_array = array;
return 0;
}
@@ -1701,7 +1705,6 @@ int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array,
u32 *prog_ids, u32 request_cnt,
u32 *prog_cnt)
{
- struct bpf_prog **prog;
u32 cnt = 0;
if (array)
@@ -1714,8 +1717,7 @@ int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array,
return 0;
/* this function is called under trace/bpf_trace.c: bpf_event_mutex */
- prog = rcu_dereference_check(array, 1)->progs;
- return bpf_prog_array_copy_core(prog, prog_ids, request_cnt) ? -ENOSPC
+ return bpf_prog_array_copy_core(array, prog_ids, request_cnt) ? -ENOSPC
: 0;
}
@@ -1793,6 +1795,7 @@ const struct bpf_func_proto bpf_get_current_comm_proto __weak;
const struct bpf_func_proto bpf_sock_map_update_proto __weak;
const struct bpf_func_proto bpf_sock_hash_update_proto __weak;
const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak;
+const struct bpf_func_proto bpf_get_local_storage_proto __weak;
const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
{
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index e0918d180f08..24aac0d0f412 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -69,7 +69,7 @@ struct bpf_cpu_map {
};
static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
- struct xdp_bulk_queue *bq);
+ struct xdp_bulk_queue *bq, bool in_napi_ctx);
static u64 cpu_map_bitmap_size(const union bpf_attr *attr)
{
@@ -375,7 +375,7 @@ static void __cpu_map_entry_free(struct rcu_head *rcu)
struct xdp_bulk_queue *bq = per_cpu_ptr(rcpu->bulkq, cpu);
/* No concurrent bq_enqueue can run at this point */
- bq_flush_to_queue(rcpu, bq);
+ bq_flush_to_queue(rcpu, bq, false);
}
free_percpu(rcpu->bulkq);
/* Cannot kthread_stop() here, last put free rcpu resources */
@@ -479,6 +479,8 @@ static void cpu_map_free(struct bpf_map *map)
* It does __not__ ensure pending flush operations (if any) are
* complete.
*/
+
+ bpf_clear_redirect_map(map);
synchronize_rcu();
/* To ensure all pending flush operations have completed wait for flush
@@ -555,10 +557,11 @@ const struct bpf_map_ops cpu_map_ops = {
.map_update_elem = cpu_map_update_elem,
.map_lookup_elem = cpu_map_lookup_elem,
.map_get_next_key = cpu_map_get_next_key,
+ .map_check_btf = map_check_no_btf,
};
static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
- struct xdp_bulk_queue *bq)
+ struct xdp_bulk_queue *bq, bool in_napi_ctx)
{
unsigned int processed = 0, drops = 0;
const int to_cpu = rcpu->cpu;
@@ -578,7 +581,10 @@ static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
err = __ptr_ring_produce(q, xdpf);
if (err) {
drops++;
- xdp_return_frame_rx_napi(xdpf);
+ if (likely(in_napi_ctx))
+ xdp_return_frame_rx_napi(xdpf);
+ else
+ xdp_return_frame(xdpf);
}
processed++;
}
@@ -598,7 +604,7 @@ static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf)
struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq);
if (unlikely(bq->count == CPU_MAP_BULK_SIZE))
- bq_flush_to_queue(rcpu, bq);
+ bq_flush_to_queue(rcpu, bq, true);
/* Notice, xdp_buff/page MUST be queued here, long enough for
* driver to code invoking us to finished, due to driver
@@ -661,7 +667,7 @@ void __cpu_map_flush(struct bpf_map *map)
/* Flush all frames in bulkq to real queue */
bq = this_cpu_ptr(rcpu->bulkq);
- bq_flush_to_queue(rcpu, bq);
+ bq_flush_to_queue(rcpu, bq, true);
/* If already running, costs spin_lock_irqsave + smb_mb */
wake_up_process(rcpu->kthread);
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index d361fc1e3bf3..141710b82a6c 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -161,6 +161,7 @@ static void dev_map_free(struct bpf_map *map)
list_del_rcu(&dtab->list);
spin_unlock(&dev_map_lock);
+ bpf_clear_redirect_map(map);
synchronize_rcu();
/* To ensure all pending flush operations have completed wait for flush
@@ -217,7 +218,8 @@ void __dev_map_insert_ctx(struct bpf_map *map, u32 bit)
}
static int bq_xmit_all(struct bpf_dtab_netdev *obj,
- struct xdp_bulk_queue *bq, u32 flags)
+ struct xdp_bulk_queue *bq, u32 flags,
+ bool in_napi_ctx)
{
struct net_device *dev = obj->dev;
int sent = 0, drops = 0, err = 0;
@@ -254,7 +256,10 @@ error:
struct xdp_frame *xdpf = bq->q[i];
/* RX path under NAPI protection, can return frames faster */
- xdp_return_frame_rx_napi(xdpf);
+ if (likely(in_napi_ctx))
+ xdp_return_frame_rx_napi(xdpf);
+ else
+ xdp_return_frame(xdpf);
drops++;
}
goto out;
@@ -286,7 +291,7 @@ void __dev_map_flush(struct bpf_map *map)
__clear_bit(bit, bitmap);
bq = this_cpu_ptr(dev->bulkq);
- bq_xmit_all(dev, bq, XDP_XMIT_FLUSH);
+ bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, true);
}
}
@@ -316,7 +321,7 @@ static int bq_enqueue(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf,
struct xdp_bulk_queue *bq = this_cpu_ptr(obj->bulkq);
if (unlikely(bq->count == DEV_MAP_BULK_SIZE))
- bq_xmit_all(obj, bq, 0);
+ bq_xmit_all(obj, bq, 0, true);
/* Ingress dev_rx will be the same for all xdp_frame's in
* bulk_queue, because bq stored per-CPU and must be flushed
@@ -385,7 +390,7 @@ static void dev_map_flush_old(struct bpf_dtab_netdev *dev)
__clear_bit(dev->bit, bitmap);
bq = per_cpu_ptr(dev->bulkq, cpu);
- bq_xmit_all(dev, bq, XDP_XMIT_FLUSH);
+ bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, false);
}
}
}
@@ -484,6 +489,7 @@ const struct bpf_map_ops dev_map_ops = {
.map_lookup_elem = dev_map_lookup_elem,
.map_update_elem = dev_map_update_elem,
.map_delete_elem = dev_map_delete_elem,
+ .map_check_btf = map_check_no_btf,
};
static int dev_map_notification(struct notifier_block *notifier,
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 513d9dfcf4ee..04b8eda94e7d 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -11,9 +11,11 @@
* General Public License for more details.
*/
#include <linux/bpf.h>
+#include <linux/btf.h>
#include <linux/jhash.h>
#include <linux/filter.h>
#include <linux/rculist_nulls.h>
+#include <uapi/linux/btf.h>
#include "percpu_freelist.h"
#include "bpf_lru_list.h"
#include "map_in_map.h"
@@ -1162,6 +1164,27 @@ static void htab_map_free(struct bpf_map *map)
kfree(htab);
}
+static void htab_map_seq_show_elem(struct bpf_map *map, void *key,
+ struct seq_file *m)
+{
+ void *value;
+
+ rcu_read_lock();
+
+ value = htab_map_lookup_elem(map, key);
+ if (!value) {
+ rcu_read_unlock();
+ return;
+ }
+
+ btf_type_seq_show(map->btf, map->btf_key_type_id, key, m);
+ seq_puts(m, ": ");
+ btf_type_seq_show(map->btf, map->btf_value_type_id, value, m);
+ seq_puts(m, "\n");
+
+ rcu_read_unlock();
+}
+
const struct bpf_map_ops htab_map_ops = {
.map_alloc_check = htab_map_alloc_check,
.map_alloc = htab_map_alloc,
@@ -1171,6 +1194,7 @@ const struct bpf_map_ops htab_map_ops = {
.map_update_elem = htab_map_update_elem,
.map_delete_elem = htab_map_delete_elem,
.map_gen_lookup = htab_map_gen_lookup,
+ .map_seq_show_elem = htab_map_seq_show_elem,
};
const struct bpf_map_ops htab_lru_map_ops = {
@@ -1182,6 +1206,7 @@ const struct bpf_map_ops htab_lru_map_ops = {
.map_update_elem = htab_lru_map_update_elem,
.map_delete_elem = htab_lru_map_delete_elem,
.map_gen_lookup = htab_lru_map_gen_lookup,
+ .map_seq_show_elem = htab_map_seq_show_elem,
};
/* Called from eBPF program */
@@ -1408,4 +1433,5 @@ const struct bpf_map_ops htab_of_maps_map_ops = {
.map_fd_put_ptr = bpf_map_fd_put_ptr,
.map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem,
.map_gen_lookup = htab_of_map_gen_lookup,
+ .map_check_btf = map_check_no_btf,
};
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 73065e2d23c2..1991466b8327 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -193,4 +193,24 @@ const struct bpf_func_proto bpf_get_current_cgroup_id_proto = {
.gpl_only = false,
.ret_type = RET_INTEGER,
};
+
+DECLARE_PER_CPU(void*, bpf_cgroup_storage);
+
+BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags)
+{
+ /* map and flags arguments are not used now,
+ * but provide an ability to extend the API
+ * for other types of local storages.
+ * verifier checks that their values are correct.
+ */
+ return (unsigned long) this_cpu_read(bpf_cgroup_storage);
+}
+
+const struct bpf_func_proto bpf_get_local_storage_proto = {
+ .func = bpf_get_local_storage,
+ .gpl_only = false,
+ .ret_type = RET_PTR_TO_MAP_VALUE,
+ .arg1_type = ARG_CONST_MAP_PTR,
+ .arg2_type = ARG_ANYTHING,
+};
#endif
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 76efe9a183f5..2ada5e21dfa6 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -196,19 +196,21 @@ static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos)
{
struct bpf_map *map = seq_file_to_map(m);
void *key = map_iter(m)->key;
+ void *prev_key;
if (map_iter(m)->done)
return NULL;
if (unlikely(v == SEQ_START_TOKEN))
- goto done;
+ prev_key = NULL;
+ else
+ prev_key = key;
- if (map->ops->map_get_next_key(map, key, key)) {
+ if (map->ops->map_get_next_key(map, prev_key, key)) {
map_iter(m)->done = true;
return NULL;
}
-done:
++(*pos);
return key;
}
@@ -332,7 +334,8 @@ static int bpf_mkmap(struct dentry *dentry, umode_t mode, void *arg)
struct bpf_map *map = arg;
return bpf_mkobj_ops(dentry, mode, arg, &bpf_map_iops,
- map->btf ? &bpffs_map_fops : &bpffs_obj_fops);
+ bpf_map_support_seq_show(map) ?
+ &bpffs_map_fops : &bpffs_obj_fops);
}
static struct dentry *
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
new file mode 100644
index 000000000000..22ad967d1e5f
--- /dev/null
+++ b/kernel/bpf/local_storage.c
@@ -0,0 +1,379 @@
+//SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf-cgroup.h>
+#include <linux/bpf.h>
+#include <linux/bug.h>
+#include <linux/filter.h>
+#include <linux/mm.h>
+#include <linux/rbtree.h>
+#include <linux/slab.h>
+
+DEFINE_PER_CPU(void*, bpf_cgroup_storage);
+
+#ifdef CONFIG_CGROUP_BPF
+
+#define LOCAL_STORAGE_CREATE_FLAG_MASK \
+ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+
+struct bpf_cgroup_storage_map {
+ struct bpf_map map;
+
+ spinlock_t lock;
+ struct bpf_prog *prog;
+ struct rb_root root;
+ struct list_head list;
+};
+
+static struct bpf_cgroup_storage_map *map_to_storage(struct bpf_map *map)
+{
+ return container_of(map, struct bpf_cgroup_storage_map, map);
+}
+
+static int bpf_cgroup_storage_key_cmp(
+ const struct bpf_cgroup_storage_key *key1,
+ const struct bpf_cgroup_storage_key *key2)
+{
+ if (key1->cgroup_inode_id < key2->cgroup_inode_id)
+ return -1;
+ else if (key1->cgroup_inode_id > key2->cgroup_inode_id)
+ return 1;
+ else if (key1->attach_type < key2->attach_type)
+ return -1;
+ else if (key1->attach_type > key2->attach_type)
+ return 1;
+ return 0;
+}
+
+static struct bpf_cgroup_storage *cgroup_storage_lookup(
+ struct bpf_cgroup_storage_map *map, struct bpf_cgroup_storage_key *key,
+ bool locked)
+{
+ struct rb_root *root = &map->root;
+ struct rb_node *node;
+
+ if (!locked)
+ spin_lock_bh(&map->lock);
+
+ node = root->rb_node;
+ while (node) {
+ struct bpf_cgroup_storage *storage;
+
+ storage = container_of(node, struct bpf_cgroup_storage, node);
+
+ switch (bpf_cgroup_storage_key_cmp(key, &storage->key)) {
+ case -1:
+ node = node->rb_left;
+ break;
+ case 1:
+ node = node->rb_right;
+ break;
+ default:
+ if (!locked)
+ spin_unlock_bh(&map->lock);
+ return storage;
+ }
+ }
+
+ if (!locked)
+ spin_unlock_bh(&map->lock);
+
+ return NULL;
+}
+
+static int cgroup_storage_insert(struct bpf_cgroup_storage_map *map,
+ struct bpf_cgroup_storage *storage)
+{
+ struct rb_root *root = &map->root;
+ struct rb_node **new = &(root->rb_node), *parent = NULL;
+
+ while (*new) {
+ struct bpf_cgroup_storage *this;
+
+ this = container_of(*new, struct bpf_cgroup_storage, node);
+
+ parent = *new;
+ switch (bpf_cgroup_storage_key_cmp(&storage->key, &this->key)) {
+ case -1:
+ new = &((*new)->rb_left);
+ break;
+ case 1:
+ new = &((*new)->rb_right);
+ break;
+ default:
+ return -EEXIST;
+ }
+ }
+
+ rb_link_node(&storage->node, parent, new);
+ rb_insert_color(&storage->node, root);
+
+ return 0;
+}
+
+static void *cgroup_storage_lookup_elem(struct bpf_map *_map, void *_key)
+{
+ struct bpf_cgroup_storage_map *map = map_to_storage(_map);
+ struct bpf_cgroup_storage_key *key = _key;
+ struct bpf_cgroup_storage *storage;
+
+ storage = cgroup_storage_lookup(map, key, false);
+ if (!storage)
+ return NULL;
+
+ return &READ_ONCE(storage->buf)->data[0];
+}
+
+static int cgroup_storage_update_elem(struct bpf_map *map, void *_key,
+ void *value, u64 flags)
+{
+ struct bpf_cgroup_storage_key *key = _key;
+ struct bpf_cgroup_storage *storage;
+ struct bpf_storage_buffer *new;
+
+ if (flags & BPF_NOEXIST)
+ return -EINVAL;
+
+ storage = cgroup_storage_lookup((struct bpf_cgroup_storage_map *)map,
+ key, false);
+ if (!storage)
+ return -ENOENT;
+
+ new = kmalloc_node(sizeof(struct bpf_storage_buffer) +
+ map->value_size, __GFP_ZERO | GFP_USER,
+ map->numa_node);
+ if (!new)
+ return -ENOMEM;
+
+ memcpy(&new->data[0], value, map->value_size);
+
+ new = xchg(&storage->buf, new);
+ kfree_rcu(new, rcu);
+
+ return 0;
+}
+
+static int cgroup_storage_get_next_key(struct bpf_map *_map, void *_key,
+ void *_next_key)
+{
+ struct bpf_cgroup_storage_map *map = map_to_storage(_map);
+ struct bpf_cgroup_storage_key *key = _key;
+ struct bpf_cgroup_storage_key *next = _next_key;
+ struct bpf_cgroup_storage *storage;
+
+ spin_lock_bh(&map->lock);
+
+ if (list_empty(&map->list))
+ goto enoent;
+
+ if (key) {
+ storage = cgroup_storage_lookup(map, key, true);
+ if (!storage)
+ goto enoent;
+
+ storage = list_next_entry(storage, list);
+ if (!storage)
+ goto enoent;
+ } else {
+ storage = list_first_entry(&map->list,
+ struct bpf_cgroup_storage, list);
+ }
+
+ spin_unlock_bh(&map->lock);
+ next->attach_type = storage->key.attach_type;
+ next->cgroup_inode_id = storage->key.cgroup_inode_id;
+ return 0;
+
+enoent:
+ spin_unlock_bh(&map->lock);
+ return -ENOENT;
+}
+
+static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr)
+{
+ int numa_node = bpf_map_attr_numa_node(attr);
+ struct bpf_cgroup_storage_map *map;
+
+ if (attr->key_size != sizeof(struct bpf_cgroup_storage_key))
+ return ERR_PTR(-EINVAL);
+
+ if (attr->value_size > PAGE_SIZE)
+ return ERR_PTR(-E2BIG);
+
+ if (attr->map_flags & ~LOCAL_STORAGE_CREATE_FLAG_MASK)
+ /* reserved bits should not be used */
+ return ERR_PTR(-EINVAL);
+
+ if (attr->max_entries)
+ /* max_entries is not used and enforced to be 0 */
+ return ERR_PTR(-EINVAL);
+
+ map = kmalloc_node(sizeof(struct bpf_cgroup_storage_map),
+ __GFP_ZERO | GFP_USER, numa_node);
+ if (!map)
+ return ERR_PTR(-ENOMEM);
+
+ map->map.pages = round_up(sizeof(struct bpf_cgroup_storage_map),
+ PAGE_SIZE) >> PAGE_SHIFT;
+
+ /* copy mandatory map attributes */
+ bpf_map_init_from_attr(&map->map, attr);
+
+ spin_lock_init(&map->lock);
+ map->root = RB_ROOT;
+ INIT_LIST_HEAD(&map->list);
+
+ return &map->map;
+}
+
+static void cgroup_storage_map_free(struct bpf_map *_map)
+{
+ struct bpf_cgroup_storage_map *map = map_to_storage(_map);
+
+ WARN_ON(!RB_EMPTY_ROOT(&map->root));
+ WARN_ON(!list_empty(&map->list));
+
+ kfree(map);
+}
+
+static int cgroup_storage_delete_elem(struct bpf_map *map, void *key)
+{
+ return -EINVAL;
+}
+
+const struct bpf_map_ops cgroup_storage_map_ops = {
+ .map_alloc = cgroup_storage_map_alloc,
+ .map_free = cgroup_storage_map_free,
+ .map_get_next_key = cgroup_storage_get_next_key,
+ .map_lookup_elem = cgroup_storage_lookup_elem,
+ .map_update_elem = cgroup_storage_update_elem,
+ .map_delete_elem = cgroup_storage_delete_elem,
+ .map_check_btf = map_check_no_btf,
+};
+
+int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map)
+{
+ struct bpf_cgroup_storage_map *map = map_to_storage(_map);
+ int ret = -EBUSY;
+
+ spin_lock_bh(&map->lock);
+
+ if (map->prog && map->prog != prog)
+ goto unlock;
+ if (prog->aux->cgroup_storage && prog->aux->cgroup_storage != _map)
+ goto unlock;
+
+ map->prog = prog;
+ prog->aux->cgroup_storage = _map;
+ ret = 0;
+unlock:
+ spin_unlock_bh(&map->lock);
+
+ return ret;
+}
+
+void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *_map)
+{
+ struct bpf_cgroup_storage_map *map = map_to_storage(_map);
+
+ spin_lock_bh(&map->lock);
+ if (map->prog == prog) {
+ WARN_ON(prog->aux->cgroup_storage != _map);
+ map->prog = NULL;
+ prog->aux->cgroup_storage = NULL;
+ }
+ spin_unlock_bh(&map->lock);
+}
+
+struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog)
+{
+ struct bpf_cgroup_storage *storage;
+ struct bpf_map *map;
+ u32 pages;
+
+ map = prog->aux->cgroup_storage;
+ if (!map)
+ return NULL;
+
+ pages = round_up(sizeof(struct bpf_cgroup_storage) +
+ sizeof(struct bpf_storage_buffer) +
+ map->value_size, PAGE_SIZE) >> PAGE_SHIFT;
+ if (bpf_map_charge_memlock(map, pages))
+ return ERR_PTR(-EPERM);
+
+ storage = kmalloc_node(sizeof(struct bpf_cgroup_storage),
+ __GFP_ZERO | GFP_USER, map->numa_node);
+ if (!storage) {
+ bpf_map_uncharge_memlock(map, pages);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ storage->buf = kmalloc_node(sizeof(struct bpf_storage_buffer) +
+ map->value_size, __GFP_ZERO | GFP_USER,
+ map->numa_node);
+ if (!storage->buf) {
+ bpf_map_uncharge_memlock(map, pages);
+ kfree(storage);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ storage->map = (struct bpf_cgroup_storage_map *)map;
+
+ return storage;
+}
+
+void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage)
+{
+ u32 pages;
+ struct bpf_map *map;
+
+ if (!storage)
+ return;
+
+ map = &storage->map->map;
+ pages = round_up(sizeof(struct bpf_cgroup_storage) +
+ sizeof(struct bpf_storage_buffer) +
+ map->value_size, PAGE_SIZE) >> PAGE_SHIFT;
+ bpf_map_uncharge_memlock(map, pages);
+
+ kfree_rcu(storage->buf, rcu);
+ kfree_rcu(storage, rcu);
+}
+
+void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage,
+ struct cgroup *cgroup,
+ enum bpf_attach_type type)
+{
+ struct bpf_cgroup_storage_map *map;
+
+ if (!storage)
+ return;
+
+ storage->key.attach_type = type;
+ storage->key.cgroup_inode_id = cgroup->kn->id.id;
+
+ map = storage->map;
+
+ spin_lock_bh(&map->lock);
+ WARN_ON(cgroup_storage_insert(map, storage));
+ list_add(&storage->list, &map->list);
+ spin_unlock_bh(&map->lock);
+}
+
+void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage)
+{
+ struct bpf_cgroup_storage_map *map;
+ struct rb_root *root;
+
+ if (!storage)
+ return;
+
+ map = storage->map;
+
+ spin_lock_bh(&map->lock);
+ root = &map->root;
+ rb_erase(&storage->node, root);
+
+ list_del(&storage->list);
+ spin_unlock_bh(&map->lock);
+}
+
+#endif
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 1603492c9cc7..9058317ba9de 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -10,11 +10,13 @@
*/
#include <linux/bpf.h>
+#include <linux/btf.h>
#include <linux/err.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/vmalloc.h>
#include <net/ipv6.h>
+#include <uapi/linux/btf.h>
/* Intermediate node */
#define LPM_TREE_NODE_FLAG_IM BIT(0)
@@ -686,6 +688,15 @@ free_stack:
return err;
}
+static int trie_check_btf(const struct bpf_map *map,
+ const struct btf_type *key_type,
+ const struct btf_type *value_type)
+{
+ /* Keys must have struct bpf_lpm_trie_key embedded. */
+ return BTF_INFO_KIND(key_type->info) != BTF_KIND_STRUCT ?
+ -EINVAL : 0;
+}
+
const struct bpf_map_ops trie_map_ops = {
.map_alloc = trie_alloc,
.map_free = trie_free,
@@ -693,4 +704,5 @@ const struct bpf_map_ops trie_map_ops = {
.map_lookup_elem = trie_lookup_elem,
.map_update_elem = trie_update_elem,
.map_delete_elem = trie_delete_elem,
+ .map_check_btf = trie_check_btf,
};
diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c
index 1da574612bea..3bfbf4464416 100644
--- a/kernel/bpf/map_in_map.c
+++ b/kernel/bpf/map_in_map.c
@@ -23,7 +23,8 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
* is a runtime binding. Doing static check alone
* in the verifier is not enough.
*/
- if (inner_map->map_type == BPF_MAP_TYPE_PROG_ARRAY) {
+ if (inner_map->map_type == BPF_MAP_TYPE_PROG_ARRAY ||
+ inner_map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE) {
fdput(f);
return ERR_PTR(-ENOTSUPP);
}
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index ac747d5cf7c6..177a52436394 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -18,19 +18,43 @@
#include <linux/bug.h>
#include <linux/kdev_t.h>
#include <linux/list.h>
+#include <linux/lockdep.h>
#include <linux/netdevice.h>
#include <linux/printk.h>
#include <linux/proc_ns.h>
+#include <linux/rhashtable.h>
#include <linux/rtnetlink.h>
#include <linux/rwsem.h>
-/* Protects bpf_prog_offload_devs, bpf_map_offload_devs and offload members
+/* Protects offdevs, members of bpf_offload_netdev and offload members
* of all progs.
* RTNL lock cannot be taken when holding this lock.
*/
static DECLARE_RWSEM(bpf_devs_lock);
-static LIST_HEAD(bpf_prog_offload_devs);
-static LIST_HEAD(bpf_map_offload_devs);
+
+struct bpf_offload_dev {
+ struct list_head netdevs;
+};
+
+struct bpf_offload_netdev {
+ struct rhash_head l;
+ struct net_device *netdev;
+ struct bpf_offload_dev *offdev;
+ struct list_head progs;
+ struct list_head maps;
+ struct list_head offdev_netdevs;
+};
+
+static const struct rhashtable_params offdevs_params = {
+ .nelem_hint = 4,
+ .key_len = sizeof(struct net_device *),
+ .key_offset = offsetof(struct bpf_offload_netdev, netdev),
+ .head_offset = offsetof(struct bpf_offload_netdev, l),
+ .automatic_shrinking = true,
+};
+
+static struct rhashtable offdevs;
+static bool offdevs_inited;
static int bpf_dev_offload_check(struct net_device *netdev)
{
@@ -41,8 +65,19 @@ static int bpf_dev_offload_check(struct net_device *netdev)
return 0;
}
+static struct bpf_offload_netdev *
+bpf_offload_find_netdev(struct net_device *netdev)
+{
+ lockdep_assert_held(&bpf_devs_lock);
+
+ if (!offdevs_inited)
+ return NULL;
+ return rhashtable_lookup_fast(&offdevs, &netdev, offdevs_params);
+}
+
int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr)
{
+ struct bpf_offload_netdev *ondev;
struct bpf_prog_offload *offload;
int err;
@@ -66,12 +101,13 @@ int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr)
goto err_maybe_put;
down_write(&bpf_devs_lock);
- if (offload->netdev->reg_state != NETREG_REGISTERED) {
+ ondev = bpf_offload_find_netdev(offload->netdev);
+ if (!ondev) {
err = -EINVAL;
goto err_unlock;
}
prog->aux->offload = offload;
- list_add_tail(&offload->offloads, &bpf_prog_offload_devs);
+ list_add_tail(&offload->offloads, &ondev->progs);
dev_put(offload->netdev);
up_write(&bpf_devs_lock);
@@ -294,6 +330,7 @@ static int bpf_map_offload_ndo(struct bpf_offloaded_map *offmap,
struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr)
{
struct net *net = current->nsproxy->net_ns;
+ struct bpf_offload_netdev *ondev;
struct bpf_offloaded_map *offmap;
int err;
@@ -316,11 +353,17 @@ struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr)
if (err)
goto err_unlock;
+ ondev = bpf_offload_find_netdev(offmap->netdev);
+ if (!ondev) {
+ err = -EINVAL;
+ goto err_unlock;
+ }
+
err = bpf_map_offload_ndo(offmap, BPF_OFFLOAD_MAP_ALLOC);
if (err)
goto err_unlock;
- list_add_tail(&offmap->offloads, &bpf_map_offload_devs);
+ list_add_tail(&offmap->offloads, &ondev->maps);
up_write(&bpf_devs_lock);
rtnl_unlock();
@@ -468,77 +511,159 @@ int bpf_map_offload_info_fill(struct bpf_map_info *info, struct bpf_map *map)
return 0;
}
-bool bpf_offload_dev_match(struct bpf_prog *prog, struct bpf_map *map)
+static bool __bpf_offload_dev_match(struct bpf_prog *prog,
+ struct net_device *netdev)
{
- struct bpf_offloaded_map *offmap;
+ struct bpf_offload_netdev *ondev1, *ondev2;
struct bpf_prog_offload *offload;
- bool ret;
if (!bpf_prog_is_dev_bound(prog->aux))
return false;
- if (!bpf_map_is_dev_bound(map))
- return bpf_map_offload_neutral(map);
- down_read(&bpf_devs_lock);
offload = prog->aux->offload;
- offmap = map_to_offmap(map);
+ if (!offload)
+ return false;
+ if (offload->netdev == netdev)
+ return true;
- ret = offload && offload->netdev == offmap->netdev;
+ ondev1 = bpf_offload_find_netdev(offload->netdev);
+ ondev2 = bpf_offload_find_netdev(netdev);
+
+ return ondev1 && ondev2 && ondev1->offdev == ondev2->offdev;
+}
+
+bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev)
+{
+ bool ret;
+
+ down_read(&bpf_devs_lock);
+ ret = __bpf_offload_dev_match(prog, netdev);
up_read(&bpf_devs_lock);
return ret;
}
+EXPORT_SYMBOL_GPL(bpf_offload_dev_match);
-static void bpf_offload_orphan_all_progs(struct net_device *netdev)
+bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map)
{
- struct bpf_prog_offload *offload, *tmp;
+ struct bpf_offloaded_map *offmap;
+ bool ret;
- list_for_each_entry_safe(offload, tmp, &bpf_prog_offload_devs, offloads)
- if (offload->netdev == netdev)
- __bpf_prog_offload_destroy(offload->prog);
+ if (!bpf_map_is_dev_bound(map))
+ return bpf_map_offload_neutral(map);
+ offmap = map_to_offmap(map);
+
+ down_read(&bpf_devs_lock);
+ ret = __bpf_offload_dev_match(prog, offmap->netdev);
+ up_read(&bpf_devs_lock);
+
+ return ret;
}
-static void bpf_offload_orphan_all_maps(struct net_device *netdev)
+int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev,
+ struct net_device *netdev)
{
- struct bpf_offloaded_map *offmap, *tmp;
+ struct bpf_offload_netdev *ondev;
+ int err;
- list_for_each_entry_safe(offmap, tmp, &bpf_map_offload_devs, offloads)
- if (offmap->netdev == netdev)
- __bpf_map_offload_destroy(offmap);
+ ondev = kzalloc(sizeof(*ondev), GFP_KERNEL);
+ if (!ondev)
+ return -ENOMEM;
+
+ ondev->netdev = netdev;
+ ondev->offdev = offdev;
+ INIT_LIST_HEAD(&ondev->progs);
+ INIT_LIST_HEAD(&ondev->maps);
+
+ down_write(&bpf_devs_lock);
+ err = rhashtable_insert_fast(&offdevs, &ondev->l, offdevs_params);
+ if (err) {
+ netdev_warn(netdev, "failed to register for BPF offload\n");
+ goto err_unlock_free;
+ }
+
+ list_add(&ondev->offdev_netdevs, &offdev->netdevs);
+ up_write(&bpf_devs_lock);
+ return 0;
+
+err_unlock_free:
+ up_write(&bpf_devs_lock);
+ kfree(ondev);
+ return err;
}
+EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_register);
-static int bpf_offload_notification(struct notifier_block *notifier,
- ulong event, void *ptr)
+void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev,
+ struct net_device *netdev)
{
- struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+ struct bpf_offload_netdev *ondev, *altdev;
+ struct bpf_offloaded_map *offmap, *mtmp;
+ struct bpf_prog_offload *offload, *ptmp;
ASSERT_RTNL();
- switch (event) {
- case NETDEV_UNREGISTER:
- /* ignore namespace changes */
- if (netdev->reg_state != NETREG_UNREGISTERING)
- break;
-
- down_write(&bpf_devs_lock);
- bpf_offload_orphan_all_progs(netdev);
- bpf_offload_orphan_all_maps(netdev);
- up_write(&bpf_devs_lock);
- break;
- default:
- break;
+ down_write(&bpf_devs_lock);
+ ondev = rhashtable_lookup_fast(&offdevs, &netdev, offdevs_params);
+ if (WARN_ON(!ondev))
+ goto unlock;
+
+ WARN_ON(rhashtable_remove_fast(&offdevs, &ondev->l, offdevs_params));
+ list_del(&ondev->offdev_netdevs);
+
+ /* Try to move the objects to another netdev of the device */
+ altdev = list_first_entry_or_null(&offdev->netdevs,
+ struct bpf_offload_netdev,
+ offdev_netdevs);
+ if (altdev) {
+ list_for_each_entry(offload, &ondev->progs, offloads)
+ offload->netdev = altdev->netdev;
+ list_splice_init(&ondev->progs, &altdev->progs);
+
+ list_for_each_entry(offmap, &ondev->maps, offloads)
+ offmap->netdev = altdev->netdev;
+ list_splice_init(&ondev->maps, &altdev->maps);
+ } else {
+ list_for_each_entry_safe(offload, ptmp, &ondev->progs, offloads)
+ __bpf_prog_offload_destroy(offload->prog);
+ list_for_each_entry_safe(offmap, mtmp, &ondev->maps, offloads)
+ __bpf_map_offload_destroy(offmap);
}
- return NOTIFY_OK;
-}
-static struct notifier_block bpf_offload_notifier = {
- .notifier_call = bpf_offload_notification,
-};
+ WARN_ON(!list_empty(&ondev->progs));
+ WARN_ON(!list_empty(&ondev->maps));
+ kfree(ondev);
+unlock:
+ up_write(&bpf_devs_lock);
+}
+EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_unregister);
-static int __init bpf_offload_init(void)
+struct bpf_offload_dev *bpf_offload_dev_create(void)
{
- register_netdevice_notifier(&bpf_offload_notifier);
- return 0;
+ struct bpf_offload_dev *offdev;
+ int err;
+
+ down_write(&bpf_devs_lock);
+ if (!offdevs_inited) {
+ err = rhashtable_init(&offdevs, &offdevs_params);
+ if (err)
+ return ERR_PTR(err);
+ offdevs_inited = true;
+ }
+ up_write(&bpf_devs_lock);
+
+ offdev = kzalloc(sizeof(*offdev), GFP_KERNEL);
+ if (!offdev)
+ return ERR_PTR(-ENOMEM);
+
+ INIT_LIST_HEAD(&offdev->netdevs);
+
+ return offdev;
}
+EXPORT_SYMBOL_GPL(bpf_offload_dev_create);
-subsys_initcall(bpf_offload_init);
+void bpf_offload_dev_destroy(struct bpf_offload_dev *offdev)
+{
+ WARN_ON(!list_empty(&offdev->netdevs));
+ kfree(offdev);
+}
+EXPORT_SYMBOL_GPL(bpf_offload_dev_destroy);
diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c
new file mode 100644
index 000000000000..18e225de80ff
--- /dev/null
+++ b/kernel/bpf/reuseport_array.c
@@ -0,0 +1,363 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018 Facebook
+ */
+#include <linux/bpf.h>
+#include <linux/err.h>
+#include <linux/sock_diag.h>
+#include <net/sock_reuseport.h>
+
+struct reuseport_array {
+ struct bpf_map map;
+ struct sock __rcu *ptrs[];
+};
+
+static struct reuseport_array *reuseport_array(struct bpf_map *map)
+{
+ return (struct reuseport_array *)map;
+}
+
+/* The caller must hold the reuseport_lock */
+void bpf_sk_reuseport_detach(struct sock *sk)
+{
+ struct sock __rcu **socks;
+
+ write_lock_bh(&sk->sk_callback_lock);
+ socks = sk->sk_user_data;
+ if (socks) {
+ WRITE_ONCE(sk->sk_user_data, NULL);
+ /*
+ * Do not move this NULL assignment outside of
+ * sk->sk_callback_lock because there is
+ * a race with reuseport_array_free()
+ * which does not hold the reuseport_lock.
+ */
+ RCU_INIT_POINTER(*socks, NULL);
+ }
+ write_unlock_bh(&sk->sk_callback_lock);
+}
+
+static int reuseport_array_alloc_check(union bpf_attr *attr)
+{
+ if (attr->value_size != sizeof(u32) &&
+ attr->value_size != sizeof(u64))
+ return -EINVAL;
+
+ return array_map_alloc_check(attr);
+}
+
+static void *reuseport_array_lookup_elem(struct bpf_map *map, void *key)
+{
+ struct reuseport_array *array = reuseport_array(map);
+ u32 index = *(u32 *)key;
+
+ if (unlikely(index >= array->map.max_entries))
+ return NULL;
+
+ return rcu_dereference(array->ptrs[index]);
+}
+
+/* Called from syscall only */
+static int reuseport_array_delete_elem(struct bpf_map *map, void *key)
+{
+ struct reuseport_array *array = reuseport_array(map);
+ u32 index = *(u32 *)key;
+ struct sock *sk;
+ int err;
+
+ if (index >= map->max_entries)
+ return -E2BIG;
+
+ if (!rcu_access_pointer(array->ptrs[index]))
+ return -ENOENT;
+
+ spin_lock_bh(&reuseport_lock);
+
+ sk = rcu_dereference_protected(array->ptrs[index],
+ lockdep_is_held(&reuseport_lock));
+ if (sk) {
+ write_lock_bh(&sk->sk_callback_lock);
+ WRITE_ONCE(sk->sk_user_data, NULL);
+ RCU_INIT_POINTER(array->ptrs[index], NULL);
+ write_unlock_bh(&sk->sk_callback_lock);
+ err = 0;
+ } else {
+ err = -ENOENT;
+ }
+
+ spin_unlock_bh(&reuseport_lock);
+
+ return err;
+}
+
+static void reuseport_array_free(struct bpf_map *map)
+{
+ struct reuseport_array *array = reuseport_array(map);
+ struct sock *sk;
+ u32 i;
+
+ synchronize_rcu();
+
+ /*
+ * ops->map_*_elem() will not be able to access this
+ * array now. Hence, this function only races with
+ * bpf_sk_reuseport_detach() which was triggerred by
+ * close() or disconnect().
+ *
+ * This function and bpf_sk_reuseport_detach() are
+ * both removing sk from "array". Who removes it
+ * first does not matter.
+ *
+ * The only concern here is bpf_sk_reuseport_detach()
+ * may access "array" which is being freed here.
+ * bpf_sk_reuseport_detach() access this "array"
+ * through sk->sk_user_data _and_ with sk->sk_callback_lock
+ * held which is enough because this "array" is not freed
+ * until all sk->sk_user_data has stopped referencing this "array".
+ *
+ * Hence, due to the above, taking "reuseport_lock" is not
+ * needed here.
+ */
+
+ /*
+ * Since reuseport_lock is not taken, sk is accessed under
+ * rcu_read_lock()
+ */
+ rcu_read_lock();
+ for (i = 0; i < map->max_entries; i++) {
+ sk = rcu_dereference(array->ptrs[i]);
+ if (sk) {
+ write_lock_bh(&sk->sk_callback_lock);
+ /*
+ * No need for WRITE_ONCE(). At this point,
+ * no one is reading it without taking the
+ * sk->sk_callback_lock.
+ */
+ sk->sk_user_data = NULL;
+ write_unlock_bh(&sk->sk_callback_lock);
+ RCU_INIT_POINTER(array->ptrs[i], NULL);
+ }
+ }
+ rcu_read_unlock();
+
+ /*
+ * Once reaching here, all sk->sk_user_data is not
+ * referenceing this "array". "array" can be freed now.
+ */
+ bpf_map_area_free(array);
+}
+
+static struct bpf_map *reuseport_array_alloc(union bpf_attr *attr)
+{
+ int err, numa_node = bpf_map_attr_numa_node(attr);
+ struct reuseport_array *array;
+ u64 cost, array_size;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return ERR_PTR(-EPERM);
+
+ array_size = sizeof(*array);
+ array_size += (u64)attr->max_entries * sizeof(struct sock *);
+
+ /* make sure there is no u32 overflow later in round_up() */
+ cost = array_size;
+ if (cost >= U32_MAX - PAGE_SIZE)
+ return ERR_PTR(-ENOMEM);
+ cost = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+
+ err = bpf_map_precharge_memlock(cost);
+ if (err)
+ return ERR_PTR(err);
+
+ /* allocate all map elements and zero-initialize them */
+ array = bpf_map_area_alloc(array_size, numa_node);
+ if (!array)
+ return ERR_PTR(-ENOMEM);
+
+ /* copy mandatory map attributes */
+ bpf_map_init_from_attr(&array->map, attr);
+ array->map.pages = cost;
+
+ return &array->map;
+}
+
+int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key,
+ void *value)
+{
+ struct sock *sk;
+ int err;
+
+ if (map->value_size != sizeof(u64))
+ return -ENOSPC;
+
+ rcu_read_lock();
+ sk = reuseport_array_lookup_elem(map, key);
+ if (sk) {
+ *(u64 *)value = sock_gen_cookie(sk);
+ err = 0;
+ } else {
+ err = -ENOENT;
+ }
+ rcu_read_unlock();
+
+ return err;
+}
+
+static int
+reuseport_array_update_check(const struct reuseport_array *array,
+ const struct sock *nsk,
+ const struct sock *osk,
+ const struct sock_reuseport *nsk_reuse,
+ u32 map_flags)
+{
+ if (osk && map_flags == BPF_NOEXIST)
+ return -EEXIST;
+
+ if (!osk && map_flags == BPF_EXIST)
+ return -ENOENT;
+
+ if (nsk->sk_protocol != IPPROTO_UDP && nsk->sk_protocol != IPPROTO_TCP)
+ return -ENOTSUPP;
+
+ if (nsk->sk_family != AF_INET && nsk->sk_family != AF_INET6)
+ return -ENOTSUPP;
+
+ if (nsk->sk_type != SOCK_STREAM && nsk->sk_type != SOCK_DGRAM)
+ return -ENOTSUPP;
+
+ /*
+ * sk must be hashed (i.e. listening in the TCP case or binded
+ * in the UDP case) and
+ * it must also be a SO_REUSEPORT sk (i.e. reuse cannot be NULL).
+ *
+ * Also, sk will be used in bpf helper that is protected by
+ * rcu_read_lock().
+ */
+ if (!sock_flag(nsk, SOCK_RCU_FREE) || !sk_hashed(nsk) || !nsk_reuse)
+ return -EINVAL;
+
+ /* READ_ONCE because the sk->sk_callback_lock may not be held here */
+ if (READ_ONCE(nsk->sk_user_data))
+ return -EBUSY;
+
+ return 0;
+}
+
+/*
+ * Called from syscall only.
+ * The "nsk" in the fd refcnt.
+ * The "osk" and "reuse" are protected by reuseport_lock.
+ */
+int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key,
+ void *value, u64 map_flags)
+{
+ struct reuseport_array *array = reuseport_array(map);
+ struct sock *free_osk = NULL, *osk, *nsk;
+ struct sock_reuseport *reuse;
+ u32 index = *(u32 *)key;
+ struct socket *socket;
+ int err, fd;
+
+ if (map_flags > BPF_EXIST)
+ return -EINVAL;
+
+ if (index >= map->max_entries)
+ return -E2BIG;
+
+ if (map->value_size == sizeof(u64)) {
+ u64 fd64 = *(u64 *)value;
+
+ if (fd64 > S32_MAX)
+ return -EINVAL;
+ fd = fd64;
+ } else {
+ fd = *(int *)value;
+ }
+
+ socket = sockfd_lookup(fd, &err);
+ if (!socket)
+ return err;
+
+ nsk = socket->sk;
+ if (!nsk) {
+ err = -EINVAL;
+ goto put_file;
+ }
+
+ /* Quick checks before taking reuseport_lock */
+ err = reuseport_array_update_check(array, nsk,
+ rcu_access_pointer(array->ptrs[index]),
+ rcu_access_pointer(nsk->sk_reuseport_cb),
+ map_flags);
+ if (err)
+ goto put_file;
+
+ spin_lock_bh(&reuseport_lock);
+ /*
+ * Some of the checks only need reuseport_lock
+ * but it is done under sk_callback_lock also
+ * for simplicity reason.
+ */
+ write_lock_bh(&nsk->sk_callback_lock);
+
+ osk = rcu_dereference_protected(array->ptrs[index],
+ lockdep_is_held(&reuseport_lock));
+ reuse = rcu_dereference_protected(nsk->sk_reuseport_cb,
+ lockdep_is_held(&reuseport_lock));
+ err = reuseport_array_update_check(array, nsk, osk, reuse, map_flags);
+ if (err)
+ goto put_file_unlock;
+
+ /* Ensure reuse->reuseport_id is set */
+ err = reuseport_get_id(reuse);
+ if (err < 0)
+ goto put_file_unlock;
+
+ WRITE_ONCE(nsk->sk_user_data, &array->ptrs[index]);
+ rcu_assign_pointer(array->ptrs[index], nsk);
+ free_osk = osk;
+ err = 0;
+
+put_file_unlock:
+ write_unlock_bh(&nsk->sk_callback_lock);
+
+ if (free_osk) {
+ write_lock_bh(&free_osk->sk_callback_lock);
+ WRITE_ONCE(free_osk->sk_user_data, NULL);
+ write_unlock_bh(&free_osk->sk_callback_lock);
+ }
+
+ spin_unlock_bh(&reuseport_lock);
+put_file:
+ fput(socket->file);
+ return err;
+}
+
+/* Called from syscall */
+static int reuseport_array_get_next_key(struct bpf_map *map, void *key,
+ void *next_key)
+{
+ struct reuseport_array *array = reuseport_array(map);
+ u32 index = key ? *(u32 *)key : U32_MAX;
+ u32 *next = (u32 *)next_key;
+
+ if (index >= array->map.max_entries) {
+ *next = 0;
+ return 0;
+ }
+
+ if (index == array->map.max_entries - 1)
+ return -ENOENT;
+
+ *next = index + 1;
+ return 0;
+}
+
+const struct bpf_map_ops reuseport_array_ops = {
+ .map_alloc_check = reuseport_array_alloc_check,
+ .map_alloc = reuseport_array_alloc,
+ .map_free = reuseport_array_free,
+ .map_lookup_elem = reuseport_array_lookup_elem,
+ .map_get_next_key = reuseport_array_get_next_key,
+ .map_delete_elem = reuseport_array_delete_elem,
+};
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index 98fb7938beea..98e621a29e8e 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -58,6 +58,7 @@ struct bpf_stab {
struct bpf_map map;
struct sock **sock_map;
struct bpf_sock_progs progs;
+ raw_spinlock_t lock;
};
struct bucket {
@@ -89,9 +90,9 @@ enum smap_psock_state {
struct smap_psock_map_entry {
struct list_head list;
+ struct bpf_map *map;
struct sock **entry;
struct htab_elem __rcu *hash_link;
- struct bpf_htab __rcu *htab;
};
struct smap_psock {
@@ -343,13 +344,18 @@ static void bpf_tcp_close(struct sock *sk, long timeout)
e = psock_map_pop(sk, psock);
while (e) {
if (e->entry) {
- osk = cmpxchg(e->entry, sk, NULL);
+ struct bpf_stab *stab = container_of(e->map, struct bpf_stab, map);
+
+ raw_spin_lock_bh(&stab->lock);
+ osk = *e->entry;
if (osk == sk) {
+ *e->entry = NULL;
smap_release_sock(psock, sk);
}
+ raw_spin_unlock_bh(&stab->lock);
} else {
struct htab_elem *link = rcu_dereference(e->hash_link);
- struct bpf_htab *htab = rcu_dereference(e->htab);
+ struct bpf_htab *htab = container_of(e->map, struct bpf_htab, map);
struct hlist_head *head;
struct htab_elem *l;
struct bucket *b;
@@ -370,6 +376,7 @@ static void bpf_tcp_close(struct sock *sk, long timeout)
}
raw_spin_unlock_bh(&b->lock);
}
+ kfree(e);
e = psock_map_pop(sk, psock);
}
rcu_read_unlock();
@@ -725,11 +732,8 @@ static int bpf_tcp_sendmsg_do_redirect(struct sock *sk, int send,
{
bool ingress = !!(md->flags & BPF_F_INGRESS);
struct smap_psock *psock;
- struct scatterlist *sg;
int err = 0;
- sg = md->sg_data;
-
rcu_read_lock();
psock = smap_psock_sk(sk);
if (unlikely(!psock))
@@ -1048,12 +1052,12 @@ static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
while (msg_data_left(msg)) {
- struct sk_msg_buff *m;
+ struct sk_msg_buff *m = NULL;
bool enospc = false;
int copy;
if (sk->sk_err) {
- err = sk->sk_err;
+ err = -sk->sk_err;
goto out_err;
}
@@ -1116,8 +1120,11 @@ wait_for_sndbuf:
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
wait_for_memory:
err = sk_stream_wait_memory(sk, &timeo);
- if (err)
+ if (err) {
+ if (m && m != psock->cork)
+ free_start_sg(sk, m);
goto out_err;
+ }
}
out_err:
if (err < 0)
@@ -1641,6 +1648,7 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
return ERR_PTR(-ENOMEM);
bpf_map_init_from_attr(&stab->map, attr);
+ raw_spin_lock_init(&stab->lock);
/* make sure page count doesn't overflow */
cost = (u64) stab->map.max_entries * sizeof(struct sock *);
@@ -1675,8 +1683,10 @@ static void smap_list_map_remove(struct smap_psock *psock,
spin_lock_bh(&psock->maps_lock);
list_for_each_entry_safe(e, tmp, &psock->maps, list) {
- if (e->entry == entry)
+ if (e->entry == entry) {
list_del(&e->list);
+ kfree(e);
+ }
}
spin_unlock_bh(&psock->maps_lock);
}
@@ -1690,8 +1700,10 @@ static void smap_list_hash_remove(struct smap_psock *psock,
list_for_each_entry_safe(e, tmp, &psock->maps, list) {
struct htab_elem *c = rcu_dereference(e->hash_link);
- if (c == hash_link)
+ if (c == hash_link) {
list_del(&e->list);
+ kfree(e);
+ }
}
spin_unlock_bh(&psock->maps_lock);
}
@@ -1711,14 +1723,15 @@ static void sock_map_free(struct bpf_map *map)
* and a grace period expire to ensure psock is really safe to remove.
*/
rcu_read_lock();
+ raw_spin_lock_bh(&stab->lock);
for (i = 0; i < stab->map.max_entries; i++) {
struct smap_psock *psock;
struct sock *sock;
- sock = xchg(&stab->sock_map[i], NULL);
+ sock = stab->sock_map[i];
if (!sock)
continue;
-
+ stab->sock_map[i] = NULL;
psock = smap_psock_sk(sock);
/* This check handles a racing sock event that can get the
* sk_callback_lock before this case but after xchg happens
@@ -1730,6 +1743,7 @@ static void sock_map_free(struct bpf_map *map)
smap_release_sock(psock, sock);
}
}
+ raw_spin_unlock_bh(&stab->lock);
rcu_read_unlock();
sock_map_remove_complete(stab);
@@ -1773,19 +1787,23 @@ static int sock_map_delete_elem(struct bpf_map *map, void *key)
if (k >= map->max_entries)
return -EINVAL;
- sock = xchg(&stab->sock_map[k], NULL);
+ raw_spin_lock_bh(&stab->lock);
+ sock = stab->sock_map[k];
+ stab->sock_map[k] = NULL;
+ raw_spin_unlock_bh(&stab->lock);
if (!sock)
return -EINVAL;
psock = smap_psock_sk(sock);
if (!psock)
- goto out;
-
- if (psock->bpf_parse)
+ return 0;
+ if (psock->bpf_parse) {
+ write_lock_bh(&sock->sk_callback_lock);
smap_stop_sock(psock, sock);
+ write_unlock_bh(&sock->sk_callback_lock);
+ }
smap_list_map_remove(psock, &stab->sock_map[k]);
smap_release_sock(psock, sock);
-out:
return 0;
}
@@ -1821,11 +1839,9 @@ out:
static int __sock_map_ctx_update_elem(struct bpf_map *map,
struct bpf_sock_progs *progs,
struct sock *sock,
- struct sock **map_link,
void *key)
{
struct bpf_prog *verdict, *parse, *tx_msg;
- struct smap_psock_map_entry *e = NULL;
struct smap_psock *psock;
bool new = false;
int err = 0;
@@ -1898,14 +1914,6 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map,
new = true;
}
- if (map_link) {
- e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN);
- if (!e) {
- err = -ENOMEM;
- goto out_free;
- }
- }
-
/* 3. At this point we have a reference to a valid psock that is
* running. Attach any BPF programs needed.
*/
@@ -1927,17 +1935,6 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map,
write_unlock_bh(&sock->sk_callback_lock);
}
- /* 4. Place psock in sockmap for use and stop any programs on
- * the old sock assuming its not the same sock we are replacing
- * it with. Because we can only have a single set of programs if
- * old_sock has a strp we can stop it.
- */
- if (map_link) {
- e->entry = map_link;
- spin_lock_bh(&psock->maps_lock);
- list_add_tail(&e->list, &psock->maps);
- spin_unlock_bh(&psock->maps_lock);
- }
return err;
out_free:
smap_release_sock(psock, sock);
@@ -1948,7 +1945,6 @@ out_progs:
}
if (tx_msg)
bpf_prog_put(tx_msg);
- kfree(e);
return err;
}
@@ -1958,36 +1954,57 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
{
struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
struct bpf_sock_progs *progs = &stab->progs;
- struct sock *osock, *sock;
+ struct sock *osock, *sock = skops->sk;
+ struct smap_psock_map_entry *e;
+ struct smap_psock *psock;
u32 i = *(u32 *)key;
int err;
if (unlikely(flags > BPF_EXIST))
return -EINVAL;
-
if (unlikely(i >= stab->map.max_entries))
return -E2BIG;
- sock = READ_ONCE(stab->sock_map[i]);
- if (flags == BPF_EXIST && !sock)
- return -ENOENT;
- else if (flags == BPF_NOEXIST && sock)
- return -EEXIST;
+ e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN);
+ if (!e)
+ return -ENOMEM;
- sock = skops->sk;
- err = __sock_map_ctx_update_elem(map, progs, sock, &stab->sock_map[i],
- key);
+ err = __sock_map_ctx_update_elem(map, progs, sock, key);
if (err)
goto out;
- osock = xchg(&stab->sock_map[i], sock);
- if (osock) {
- struct smap_psock *opsock = smap_psock_sk(osock);
+ /* psock guaranteed to be present. */
+ psock = smap_psock_sk(sock);
+ raw_spin_lock_bh(&stab->lock);
+ osock = stab->sock_map[i];
+ if (osock && flags == BPF_NOEXIST) {
+ err = -EEXIST;
+ goto out_unlock;
+ }
+ if (!osock && flags == BPF_EXIST) {
+ err = -ENOENT;
+ goto out_unlock;
+ }
+
+ e->entry = &stab->sock_map[i];
+ e->map = map;
+ spin_lock_bh(&psock->maps_lock);
+ list_add_tail(&e->list, &psock->maps);
+ spin_unlock_bh(&psock->maps_lock);
- smap_list_map_remove(opsock, &stab->sock_map[i]);
- smap_release_sock(opsock, osock);
+ stab->sock_map[i] = sock;
+ if (osock) {
+ psock = smap_psock_sk(osock);
+ smap_list_map_remove(psock, &stab->sock_map[i]);
+ smap_release_sock(psock, osock);
}
+ raw_spin_unlock_bh(&stab->lock);
+ return 0;
+out_unlock:
+ smap_release_sock(psock, sock);
+ raw_spin_unlock_bh(&stab->lock);
out:
+ kfree(e);
return err;
}
@@ -2350,7 +2367,7 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops,
b = __select_bucket(htab, hash);
head = &b->head;
- err = __sock_map_ctx_update_elem(map, progs, sock, NULL, key);
+ err = __sock_map_ctx_update_elem(map, progs, sock, key);
if (err)
goto err;
@@ -2376,8 +2393,7 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops,
}
rcu_assign_pointer(e->hash_link, l_new);
- rcu_assign_pointer(e->htab,
- container_of(map, struct bpf_htab, map));
+ e->map = map;
spin_lock_bh(&psock->maps_lock);
list_add_tail(&e->list, &psock->maps);
spin_unlock_bh(&psock->maps_lock);
@@ -2498,6 +2514,7 @@ const struct bpf_map_ops sock_map_ops = {
.map_update_elem = sock_map_update_elem,
.map_delete_elem = sock_map_delete_elem,
.map_release_uref = sock_map_release,
+ .map_check_btf = map_check_no_btf,
};
const struct bpf_map_ops sock_hash_ops = {
@@ -2508,6 +2525,7 @@ const struct bpf_map_ops sock_hash_ops = {
.map_update_elem = sock_hash_update_elem,
.map_delete_elem = sock_hash_delete_elem,
.map_release_uref = sock_map_release,
+ .map_check_btf = map_check_no_btf,
};
BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock,
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index b675a3f3d141..8061a439ef18 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -607,6 +607,7 @@ const struct bpf_map_ops stack_map_ops = {
.map_lookup_elem = stack_map_lookup_elem,
.map_update_elem = stack_map_update_elem,
.map_delete_elem = stack_map_delete_elem,
+ .map_check_btf = map_check_no_btf,
};
static int __init stack_map_init(void)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index a31a1ba0f8ea..8339d81cba1d 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -103,6 +103,7 @@ int bpf_check_uarg_tail_zero(void __user *uaddr,
const struct bpf_map_ops bpf_map_offload_ops = {
.map_alloc = bpf_map_offload_map_alloc,
.map_free = bpf_map_offload_map_free,
+ .map_check_btf = map_check_no_btf,
};
static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
@@ -181,32 +182,60 @@ int bpf_map_precharge_memlock(u32 pages)
return 0;
}
-static int bpf_map_charge_memlock(struct bpf_map *map)
+static int bpf_charge_memlock(struct user_struct *user, u32 pages)
{
- struct user_struct *user = get_current_user();
- unsigned long memlock_limit;
+ unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
- memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+ if (atomic_long_add_return(pages, &user->locked_vm) > memlock_limit) {
+ atomic_long_sub(pages, &user->locked_vm);
+ return -EPERM;
+ }
+ return 0;
+}
- atomic_long_add(map->pages, &user->locked_vm);
+static void bpf_uncharge_memlock(struct user_struct *user, u32 pages)
+{
+ atomic_long_sub(pages, &user->locked_vm);
+}
- if (atomic_long_read(&user->locked_vm) > memlock_limit) {
- atomic_long_sub(map->pages, &user->locked_vm);
+static int bpf_map_init_memlock(struct bpf_map *map)
+{
+ struct user_struct *user = get_current_user();
+ int ret;
+
+ ret = bpf_charge_memlock(user, map->pages);
+ if (ret) {
free_uid(user);
- return -EPERM;
+ return ret;
}
map->user = user;
- return 0;
+ return ret;
}
-static void bpf_map_uncharge_memlock(struct bpf_map *map)
+static void bpf_map_release_memlock(struct bpf_map *map)
{
struct user_struct *user = map->user;
-
- atomic_long_sub(map->pages, &user->locked_vm);
+ bpf_uncharge_memlock(user, map->pages);
free_uid(user);
}
+int bpf_map_charge_memlock(struct bpf_map *map, u32 pages)
+{
+ int ret;
+
+ ret = bpf_charge_memlock(map->user, pages);
+ if (ret)
+ return ret;
+ map->pages += pages;
+ return ret;
+}
+
+void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages)
+{
+ bpf_uncharge_memlock(map->user, pages);
+ map->pages -= pages;
+}
+
static int bpf_map_alloc_id(struct bpf_map *map)
{
int id;
@@ -256,7 +285,7 @@ static void bpf_map_free_deferred(struct work_struct *work)
{
struct bpf_map *map = container_of(work, struct bpf_map, work);
- bpf_map_uncharge_memlock(map);
+ bpf_map_release_memlock(map);
security_bpf_map_free(map);
/* implementation dependent freeing */
map->ops->map_free(map);
@@ -427,6 +456,34 @@ static int bpf_obj_name_cpy(char *dst, const char *src)
return 0;
}
+int map_check_no_btf(const struct bpf_map *map,
+ const struct btf_type *key_type,
+ const struct btf_type *value_type)
+{
+ return -ENOTSUPP;
+}
+
+static int map_check_btf(const struct bpf_map *map, const struct btf *btf,
+ u32 btf_key_id, u32 btf_value_id)
+{
+ const struct btf_type *key_type, *value_type;
+ u32 key_size, value_size;
+ int ret = 0;
+
+ key_type = btf_type_id_size(btf, &btf_key_id, &key_size);
+ if (!key_type || key_size != map->key_size)
+ return -EINVAL;
+
+ value_type = btf_type_id_size(btf, &btf_value_id, &value_size);
+ if (!value_type || value_size != map->value_size)
+ return -EINVAL;
+
+ if (map->ops->map_check_btf)
+ ret = map->ops->map_check_btf(map, key_type, value_type);
+
+ return ret;
+}
+
#define BPF_MAP_CREATE_LAST_FIELD btf_value_type_id
/* called via syscall */
static int map_create(union bpf_attr *attr)
@@ -461,8 +518,7 @@ static int map_create(union bpf_attr *attr)
atomic_set(&map->refcnt, 1);
atomic_set(&map->usercnt, 1);
- if (bpf_map_support_seq_show(map) &&
- (attr->btf_key_type_id || attr->btf_value_type_id)) {
+ if (attr->btf_key_type_id || attr->btf_value_type_id) {
struct btf *btf;
if (!attr->btf_key_type_id || !attr->btf_value_type_id) {
@@ -476,8 +532,8 @@ static int map_create(union bpf_attr *attr)
goto free_map_nouncharge;
}
- err = map->ops->map_check_btf(map, btf, attr->btf_key_type_id,
- attr->btf_value_type_id);
+ err = map_check_btf(map, btf, attr->btf_key_type_id,
+ attr->btf_value_type_id);
if (err) {
btf_put(btf);
goto free_map_nouncharge;
@@ -492,7 +548,7 @@ static int map_create(union bpf_attr *attr)
if (err)
goto free_map_nouncharge;
- err = bpf_map_charge_memlock(map);
+ err = bpf_map_init_memlock(map);
if (err)
goto free_map_sec;
@@ -515,7 +571,7 @@ static int map_create(union bpf_attr *attr)
return err;
free_map:
- bpf_map_uncharge_memlock(map);
+ bpf_map_release_memlock(map);
free_map_sec:
security_bpf_map_free(map);
free_map_nouncharge:
@@ -575,7 +631,7 @@ static struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map,
{
int refold;
- refold = __atomic_add_unless(&map->refcnt, 1, 0);
+ refold = atomic_fetch_add_unless(&map->refcnt, 1, 0);
if (refold >= BPF_MAX_REFCNT) {
__bpf_map_put(map, false);
@@ -656,6 +712,8 @@ static int map_lookup_elem(union bpf_attr *attr)
err = bpf_fd_array_map_lookup_elem(map, key, value);
} else if (IS_FD_HASH(map)) {
err = bpf_fd_htab_map_lookup_elem(map, key, value);
+ } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) {
+ err = bpf_fd_reuseport_array_lookup_elem(map, key, value);
} else {
rcu_read_lock();
ptr = map->ops->map_lookup_elem(map, key);
@@ -762,6 +820,10 @@ static int map_update_elem(union bpf_attr *attr)
err = bpf_fd_htab_map_update_elem(map, f.file, key, value,
attr->flags);
rcu_read_unlock();
+ } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) {
+ /* rcu_read_lock() is not needed */
+ err = bpf_fd_reuseport_array_update_elem(map, key, value,
+ attr->flags);
} else {
rcu_read_lock();
err = map->ops->map_update_elem(map, key, value, attr->flags);
@@ -929,6 +991,9 @@ static void free_used_maps(struct bpf_prog_aux *aux)
{
int i;
+ if (aux->cgroup_storage)
+ bpf_cgroup_storage_release(aux->prog, aux->cgroup_storage);
+
for (i = 0; i < aux->used_map_cnt; i++)
bpf_map_put(aux->used_maps[i]);
@@ -1144,7 +1209,7 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog)
{
int refold;
- refold = __atomic_add_unless(&prog->aux->refcnt, 1, 0);
+ refold = atomic_fetch_add_unless(&prog->aux->refcnt, 1, 0);
if (refold >= BPF_MAX_REFCNT) {
__bpf_prog_put(prog, false);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 63aaac52a265..92246117d2b0 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1310,6 +1310,7 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
case BPF_PROG_TYPE_LWT_IN:
case BPF_PROG_TYPE_LWT_OUT:
case BPF_PROG_TYPE_LWT_SEG6LOCAL:
+ case BPF_PROG_TYPE_SK_REUSEPORT:
/* dst_input() and dst_output() can't write for now */
if (t == BPF_WRITE)
return false;
@@ -2127,6 +2128,10 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
func_id != BPF_FUNC_current_task_under_cgroup)
goto error;
break;
+ case BPF_MAP_TYPE_CGROUP_STORAGE:
+ if (func_id != BPF_FUNC_get_local_storage)
+ goto error;
+ break;
/* devmap returns a pointer to a live net_device ifindex that we cannot
* allow to be modified from bpf side. So do not allow lookup elements
* for now.
@@ -2162,6 +2167,10 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
func_id != BPF_FUNC_msg_redirect_hash)
goto error;
break;
+ case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY:
+ if (func_id != BPF_FUNC_sk_select_reuseport)
+ goto error;
+ break;
default:
break;
}
@@ -2209,6 +2218,14 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
if (map->map_type != BPF_MAP_TYPE_SOCKHASH)
goto error;
break;
+ case BPF_FUNC_get_local_storage:
+ if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE)
+ goto error;
+ break;
+ case BPF_FUNC_sk_select_reuseport:
+ if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY)
+ goto error;
+ break;
default:
break;
}
@@ -2533,6 +2550,16 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
}
regs = cur_regs(env);
+
+ /* check that flags argument in get_local_storage(map, flags) is 0,
+ * this is required because get_local_storage() can't return an error.
+ */
+ if (func_id == BPF_FUNC_get_local_storage &&
+ !register_is_null(&regs[BPF_REG_2])) {
+ verbose(env, "get_local_storage() doesn't support non-zero flags\n");
+ return -EINVAL;
+ }
+
/* reset caller saved regs */
for (i = 0; i < CALLER_SAVED_REGS; i++) {
mark_reg_not_init(env, regs, caller_saved[i]);
@@ -2545,8 +2572,12 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
mark_reg_unknown(env, regs, BPF_REG_0);
} else if (fn->ret_type == RET_VOID) {
regs[BPF_REG_0].type = NOT_INIT;
- } else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL) {
- regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
+ } else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL ||
+ fn->ret_type == RET_PTR_TO_MAP_VALUE) {
+ if (fn->ret_type == RET_PTR_TO_MAP_VALUE)
+ regs[BPF_REG_0].type = PTR_TO_MAP_VALUE;
+ else
+ regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
/* There is no offset yet applied, variable or fixed */
mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].off = 0;
@@ -3238,8 +3269,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
}
}
- /* check dest operand */
- err = check_reg_arg(env, insn->dst_reg, DST_OP);
+ /* check dest operand, mark as required later */
+ err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK);
if (err)
return err;
@@ -3265,6 +3296,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
/* case: R = imm
* remember the value we stored into this reg
*/
+ /* clear any state __mark_reg_known doesn't set */
+ mark_reg_unknown(env, regs, insn->dst_reg);
regs[insn->dst_reg].type = SCALAR_VALUE;
if (BPF_CLASS(insn->code) == BPF_ALU64) {
__mark_reg_known(regs + insn->dst_reg,
@@ -5054,7 +5087,7 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
}
if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) &&
- !bpf_offload_dev_match(prog, map)) {
+ !bpf_offload_prog_map_match(prog, map)) {
verbose(env, "offload device mismatch between prog and map\n");
return -EINVAL;
}
@@ -5152,6 +5185,14 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
}
env->used_maps[env->used_map_cnt++] = map;
+ if (map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE &&
+ bpf_cgroup_storage_assign(env->prog, map)) {
+ verbose(env,
+ "only one cgroup storage is allowed\n");
+ fdput(f);
+ return -EBUSY;
+ }
+
fdput(f);
next_insn:
insn++;
@@ -5178,6 +5219,10 @@ static void release_maps(struct bpf_verifier_env *env)
{
int i;
+ if (env->prog->aux->cgroup_storage)
+ bpf_cgroup_storage_release(env->prog,
+ env->prog->aux->cgroup_storage);
+
for (i = 0; i < env->used_map_cnt; i++)
bpf_map_put(env->used_maps[i]);
}
@@ -5799,27 +5844,6 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
goto patch_call_imm;
}
- if (insn->imm == BPF_FUNC_redirect_map) {
- /* Note, we cannot use prog directly as imm as subsequent
- * rewrites would still change the prog pointer. The only
- * stable address we can use is aux, which also works with
- * prog clones during blinding.
- */
- u64 addr = (unsigned long)prog->aux;
- struct bpf_insn r4_ld[] = {
- BPF_LD_IMM64(BPF_REG_4, addr),
- *insn,
- };
- cnt = ARRAY_SIZE(r4_ld);
-
- new_prog = bpf_patch_insn_data(env, i + delta, r4_ld, cnt);
- if (!new_prog)
- return -ENOMEM;
-
- delta += cnt - 1;
- env->prog = prog = new_prog;
- insn = new_prog->insnsi + i + delta;
- }
patch_call_imm:
fn = env->ops->get_func_proto(insn->imm, env->prog);
/* all functions that have prototype and verifier allowed
diff --git a/kernel/bpf/xskmap.c b/kernel/bpf/xskmap.c
index b3c557476a8d..9f8463afda9c 100644
--- a/kernel/bpf/xskmap.c
+++ b/kernel/bpf/xskmap.c
@@ -75,6 +75,7 @@ static void xsk_map_free(struct bpf_map *map)
struct xsk_map *m = container_of(map, struct xsk_map, map);
int i;
+ bpf_clear_redirect_map(map);
synchronize_net();
for (i = 0; i < map->max_entries; i++) {
@@ -227,6 +228,5 @@ const struct bpf_map_ops xsk_map_ops = {
.map_lookup_elem = xsk_map_lookup_elem,
.map_update_elem = xsk_map_update_elem,
.map_delete_elem = xsk_map_delete_elem,
+ .map_check_btf = map_check_no_btf,
};
-
-
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 077370bf8964..35cf3d71f8aa 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -3557,7 +3557,9 @@ static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp,
key = &cft->lockdep_key;
#endif
kn = __kernfs_create_file(cgrp->kn, cgroup_file_name(cgrp, cft, name),
- cgroup_file_mode(cft), 0, cft->kf_ops, cft,
+ cgroup_file_mode(cft),
+ GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
+ 0, cft->kf_ops, cft,
NULL, key);
if (IS_ERR(kn))
return PTR_ERR(kn);
diff --git a/kernel/compat.c b/kernel/compat.c
index 702aa846ddac..8e40efc2928a 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -324,35 +324,6 @@ COMPAT_SYSCALL_DEFINE3(sched_getaffinity, compat_pid_t, pid, unsigned int, len,
return ret;
}
-/* Todo: Delete these extern declarations when get/put_compat_itimerspec64()
- * are moved to kernel/time/time.c .
- */
-extern int __compat_get_timespec64(struct timespec64 *ts64,
- const struct compat_timespec __user *cts);
-extern int __compat_put_timespec64(const struct timespec64 *ts64,
- struct compat_timespec __user *cts);
-
-int get_compat_itimerspec64(struct itimerspec64 *its,
- const struct compat_itimerspec __user *uits)
-{
-
- if (__compat_get_timespec64(&its->it_interval, &uits->it_interval) ||
- __compat_get_timespec64(&its->it_value, &uits->it_value))
- return -EFAULT;
- return 0;
-}
-EXPORT_SYMBOL_GPL(get_compat_itimerspec64);
-
-int put_compat_itimerspec64(const struct itimerspec64 *its,
- struct compat_itimerspec __user *uits)
-{
- if (__compat_put_timespec64(&its->it_interval, &uits->it_interval) ||
- __compat_put_timespec64(&its->it_value, &uits->it_value))
- return -EFAULT;
- return 0;
-}
-EXPORT_SYMBOL_GPL(put_compat_itimerspec64);
-
/*
* We currently only need the following fields from the sigevent
* structure: sigev_value, sigev_signo, sig_notify and (sometimes
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 0db8938fbb23..ed44d7d34c2d 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -60,6 +60,7 @@ struct cpuhp_cpu_state {
bool rollback;
bool single;
bool bringup;
+ bool booted_once;
struct hlist_node *node;
struct hlist_node *last;
enum cpuhp_state cb_state;
@@ -290,6 +291,12 @@ void cpus_read_lock(void)
}
EXPORT_SYMBOL_GPL(cpus_read_lock);
+int cpus_read_trylock(void)
+{
+ return percpu_down_read_trylock(&cpu_hotplug_lock);
+}
+EXPORT_SYMBOL_GPL(cpus_read_trylock);
+
void cpus_read_unlock(void)
{
percpu_up_read(&cpu_hotplug_lock);
@@ -342,6 +349,85 @@ void cpu_hotplug_enable(void)
EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
#endif /* CONFIG_HOTPLUG_CPU */
+#ifdef CONFIG_HOTPLUG_SMT
+enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED;
+EXPORT_SYMBOL_GPL(cpu_smt_control);
+
+static bool cpu_smt_available __read_mostly;
+
+void __init cpu_smt_disable(bool force)
+{
+ if (cpu_smt_control == CPU_SMT_FORCE_DISABLED ||
+ cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
+ return;
+
+ if (force) {
+ pr_info("SMT: Force disabled\n");
+ cpu_smt_control = CPU_SMT_FORCE_DISABLED;
+ } else {
+ cpu_smt_control = CPU_SMT_DISABLED;
+ }
+}
+
+/*
+ * The decision whether SMT is supported can only be done after the full
+ * CPU identification. Called from architecture code before non boot CPUs
+ * are brought up.
+ */
+void __init cpu_smt_check_topology_early(void)
+{
+ if (!topology_smt_supported())
+ cpu_smt_control = CPU_SMT_NOT_SUPPORTED;
+}
+
+/*
+ * If SMT was disabled by BIOS, detect it here, after the CPUs have been
+ * brought online. This ensures the smt/l1tf sysfs entries are consistent
+ * with reality. cpu_smt_available is set to true during the bringup of non
+ * boot CPUs when a SMT sibling is detected. Note, this may overwrite
+ * cpu_smt_control's previous setting.
+ */
+void __init cpu_smt_check_topology(void)
+{
+ if (!cpu_smt_available)
+ cpu_smt_control = CPU_SMT_NOT_SUPPORTED;
+}
+
+static int __init smt_cmdline_disable(char *str)
+{
+ cpu_smt_disable(str && !strcmp(str, "force"));
+ return 0;
+}
+early_param("nosmt", smt_cmdline_disable);
+
+static inline bool cpu_smt_allowed(unsigned int cpu)
+{
+ if (topology_is_primary_thread(cpu))
+ return true;
+
+ /*
+ * If the CPU is not a 'primary' thread and the booted_once bit is
+ * set then the processor has SMT support. Store this information
+ * for the late check of SMT support in cpu_smt_check_topology().
+ */
+ if (per_cpu(cpuhp_state, cpu).booted_once)
+ cpu_smt_available = true;
+
+ if (cpu_smt_control == CPU_SMT_ENABLED)
+ return true;
+
+ /*
+ * On x86 it's required to boot all logical CPUs at least once so
+ * that the init code can get a chance to set CR4.MCE on each
+ * CPU. Otherwise, a broadacasted MCE observing CR4.MCE=0b on any
+ * core will shutdown the machine.
+ */
+ return !per_cpu(cpuhp_state, cpu).booted_once;
+}
+#else
+static inline bool cpu_smt_allowed(unsigned int cpu) { return true; }
+#endif
+
static inline enum cpuhp_state
cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target)
{
@@ -422,6 +508,16 @@ static int bringup_wait_for_ap(unsigned int cpu)
stop_machine_unpark(cpu);
kthread_unpark(st->thread);
+ /*
+ * SMT soft disabling on X86 requires to bring the CPU out of the
+ * BIOS 'wait for SIPI' state in order to set the CR4.MCE bit. The
+ * CPU marked itself as booted_once in cpu_notify_starting() so the
+ * cpu_smt_allowed() check will now return false if this is not the
+ * primary sibling.
+ */
+ if (!cpu_smt_allowed(cpu))
+ return -ECANCELED;
+
if (st->target <= CPUHP_AP_ONLINE_IDLE)
return 0;
@@ -754,7 +850,6 @@ static int takedown_cpu(unsigned int cpu)
/* Park the smpboot threads */
kthread_park(per_cpu_ptr(&cpuhp_state, cpu)->thread);
- smpboot_park_threads(cpu);
/*
* Prevent irq alloc/free while the dying cpu reorganizes the
@@ -907,20 +1002,19 @@ out:
return ret;
}
+static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target)
+{
+ if (cpu_hotplug_disabled)
+ return -EBUSY;
+ return _cpu_down(cpu, 0, target);
+}
+
static int do_cpu_down(unsigned int cpu, enum cpuhp_state target)
{
int err;
cpu_maps_update_begin();
-
- if (cpu_hotplug_disabled) {
- err = -EBUSY;
- goto out;
- }
-
- err = _cpu_down(cpu, 0, target);
-
-out:
+ err = cpu_down_maps_locked(cpu, target);
cpu_maps_update_done();
return err;
}
@@ -949,6 +1043,7 @@ void notify_cpu_starting(unsigned int cpu)
int ret;
rcu_cpu_starting(cpu); /* Enables RCU usage on this CPU. */
+ st->booted_once = true;
while (st->state < target) {
st->state++;
ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL);
@@ -1058,6 +1153,10 @@ static int do_cpu_up(unsigned int cpu, enum cpuhp_state target)
err = -EBUSY;
goto out;
}
+ if (!cpu_smt_allowed(cpu)) {
+ err = -EPERM;
+ goto out;
+ }
err = _cpu_up(cpu, 0, target);
out:
@@ -1274,7 +1373,7 @@ static struct cpuhp_step cpuhp_hp_states[] = {
* otherwise a RCU stall occurs.
*/
[CPUHP_TIMERS_PREPARE] = {
- .name = "timers:dead",
+ .name = "timers:prepare",
.startup.single = timers_prepare_cpu,
.teardown.single = timers_dead_cpu,
},
@@ -1332,7 +1431,7 @@ static struct cpuhp_step cpuhp_hp_states[] = {
[CPUHP_AP_SMPBOOT_THREADS] = {
.name = "smpboot/threads:online",
.startup.single = smpboot_unpark_threads,
- .teardown.single = NULL,
+ .teardown.single = smpboot_park_threads,
},
[CPUHP_AP_IRQ_AFFINITY_ONLINE] = {
.name = "irq/affinity:online",
@@ -1344,6 +1443,11 @@ static struct cpuhp_step cpuhp_hp_states[] = {
.startup.single = perf_event_init_cpu,
.teardown.single = perf_event_exit_cpu,
},
+ [CPUHP_AP_WATCHDOG_ONLINE] = {
+ .name = "lockup_detector:online",
+ .startup.single = lockup_detector_online_cpu,
+ .teardown.single = lockup_detector_offline_cpu,
+ },
[CPUHP_AP_WORKQUEUE_ONLINE] = {
.name = "workqueue:online",
.startup.single = workqueue_online_cpu,
@@ -1906,10 +2010,172 @@ static const struct attribute_group cpuhp_cpu_root_attr_group = {
NULL
};
+#ifdef CONFIG_HOTPLUG_SMT
+
+static const char *smt_states[] = {
+ [CPU_SMT_ENABLED] = "on",
+ [CPU_SMT_DISABLED] = "off",
+ [CPU_SMT_FORCE_DISABLED] = "forceoff",
+ [CPU_SMT_NOT_SUPPORTED] = "notsupported",
+};
+
+static ssize_t
+show_smt_control(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ return snprintf(buf, PAGE_SIZE - 2, "%s\n", smt_states[cpu_smt_control]);
+}
+
+static void cpuhp_offline_cpu_device(unsigned int cpu)
+{
+ struct device *dev = get_cpu_device(cpu);
+
+ dev->offline = true;
+ /* Tell user space about the state change */
+ kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
+}
+
+static void cpuhp_online_cpu_device(unsigned int cpu)
+{
+ struct device *dev = get_cpu_device(cpu);
+
+ dev->offline = false;
+ /* Tell user space about the state change */
+ kobject_uevent(&dev->kobj, KOBJ_ONLINE);
+}
+
+static int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
+{
+ int cpu, ret = 0;
+
+ cpu_maps_update_begin();
+ for_each_online_cpu(cpu) {
+ if (topology_is_primary_thread(cpu))
+ continue;
+ ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE);
+ if (ret)
+ break;
+ /*
+ * As this needs to hold the cpu maps lock it's impossible
+ * to call device_offline() because that ends up calling
+ * cpu_down() which takes cpu maps lock. cpu maps lock
+ * needs to be held as this might race against in kernel
+ * abusers of the hotplug machinery (thermal management).
+ *
+ * So nothing would update device:offline state. That would
+ * leave the sysfs entry stale and prevent onlining after
+ * smt control has been changed to 'off' again. This is
+ * called under the sysfs hotplug lock, so it is properly
+ * serialized against the regular offline usage.
+ */
+ cpuhp_offline_cpu_device(cpu);
+ }
+ if (!ret)
+ cpu_smt_control = ctrlval;
+ cpu_maps_update_done();
+ return ret;
+}
+
+static int cpuhp_smt_enable(void)
+{
+ int cpu, ret = 0;
+
+ cpu_maps_update_begin();
+ cpu_smt_control = CPU_SMT_ENABLED;
+ for_each_present_cpu(cpu) {
+ /* Skip online CPUs and CPUs on offline nodes */
+ if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
+ continue;
+ ret = _cpu_up(cpu, 0, CPUHP_ONLINE);
+ if (ret)
+ break;
+ /* See comment in cpuhp_smt_disable() */
+ cpuhp_online_cpu_device(cpu);
+ }
+ cpu_maps_update_done();
+ return ret;
+}
+
+static ssize_t
+store_smt_control(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ int ctrlval, ret;
+
+ if (sysfs_streq(buf, "on"))
+ ctrlval = CPU_SMT_ENABLED;
+ else if (sysfs_streq(buf, "off"))
+ ctrlval = CPU_SMT_DISABLED;
+ else if (sysfs_streq(buf, "forceoff"))
+ ctrlval = CPU_SMT_FORCE_DISABLED;
+ else
+ return -EINVAL;
+
+ if (cpu_smt_control == CPU_SMT_FORCE_DISABLED)
+ return -EPERM;
+
+ if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
+ return -ENODEV;
+
+ ret = lock_device_hotplug_sysfs();
+ if (ret)
+ return ret;
+
+ if (ctrlval != cpu_smt_control) {
+ switch (ctrlval) {
+ case CPU_SMT_ENABLED:
+ ret = cpuhp_smt_enable();
+ break;
+ case CPU_SMT_DISABLED:
+ case CPU_SMT_FORCE_DISABLED:
+ ret = cpuhp_smt_disable(ctrlval);
+ break;
+ }
+ }
+
+ unlock_device_hotplug();
+ return ret ? ret : count;
+}
+static DEVICE_ATTR(control, 0644, show_smt_control, store_smt_control);
+
+static ssize_t
+show_smt_active(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ bool active = topology_max_smt_threads() > 1;
+
+ return snprintf(buf, PAGE_SIZE - 2, "%d\n", active);
+}
+static DEVICE_ATTR(active, 0444, show_smt_active, NULL);
+
+static struct attribute *cpuhp_smt_attrs[] = {
+ &dev_attr_control.attr,
+ &dev_attr_active.attr,
+ NULL
+};
+
+static const struct attribute_group cpuhp_smt_attr_group = {
+ .attrs = cpuhp_smt_attrs,
+ .name = "smt",
+ NULL
+};
+
+static int __init cpu_smt_state_init(void)
+{
+ return sysfs_create_group(&cpu_subsys.dev_root->kobj,
+ &cpuhp_smt_attr_group);
+}
+
+#else
+static inline int cpu_smt_state_init(void) { return 0; }
+#endif
+
static int __init cpuhp_sysfs_init(void)
{
int cpu, ret;
+ ret = cpu_smt_state_init();
+ if (ret)
+ return ret;
+
ret = sysfs_create_group(&cpu_subsys.dev_root->kobj,
&cpuhp_cpu_root_attr_group);
if (ret)
@@ -2010,7 +2276,10 @@ void __init boot_cpu_init(void)
/*
* Must be called _AFTER_ setting up the per_cpu areas
*/
-void __init boot_cpu_state_init(void)
+void __init boot_cpu_hotplug_init(void)
{
- per_cpu_ptr(&cpuhp_state, smp_processor_id())->state = CPUHP_ONLINE;
+#ifdef CONFIG_SMP
+ this_cpu_write(cpuhp_state.booted_once, true);
+#endif
+ this_cpu_write(cpuhp_state.state, CPUHP_ONLINE);
}
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index b66aced5e8c2..933cb3e45b98 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -14,8 +14,8 @@
#include <asm/sections.h>
/* vmcoreinfo stuff */
-static unsigned char *vmcoreinfo_data;
-static size_t vmcoreinfo_size;
+unsigned char *vmcoreinfo_data;
+size_t vmcoreinfo_size;
u32 *vmcoreinfo_note;
/* trusted vmcoreinfo, e.g. we can make a copy in the crash memory */
@@ -344,7 +344,7 @@ void crash_save_vmcoreinfo(void)
if (vmcoreinfo_data_safecopy)
vmcoreinfo_data = vmcoreinfo_data_safecopy;
- vmcoreinfo_append_str("CRASHTIME=%ld\n", get_seconds());
+ vmcoreinfo_append_str("CRASHTIME=%lld\n", ktime_get_real_seconds());
update_vmcoreinfo_note();
}
@@ -401,7 +401,7 @@ static int __init crash_save_vmcoreinfo_init(void)
VMCOREINFO_SYMBOL(init_uts_ns);
VMCOREINFO_SYMBOL(node_online_map);
#ifdef CONFIG_MMU
- VMCOREINFO_SYMBOL(swapper_pg_dir);
+ VMCOREINFO_SYMBOL_ARRAY(swapper_pg_dir);
#endif
VMCOREINFO_SYMBOL(_stext);
VMCOREINFO_SYMBOL(vmap_area_list);
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index d987dcd1bd56..286d82329eb0 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -178,7 +178,7 @@ int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
* @dev: Pointer to device for which the allocation is performed.
* @count: Requested number of pages.
* @align: Requested alignment of pages (in PAGE_SIZE order).
- * @gfp_mask: GFP flags to use for this allocation.
+ * @no_warn: Avoid printing message about failed allocation.
*
* This function allocates memory buffer for specified device. It uses
* device specific contiguous memory area if available or the default
@@ -186,12 +186,12 @@ int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
* function.
*/
struct page *dma_alloc_from_contiguous(struct device *dev, size_t count,
- unsigned int align, gfp_t gfp_mask)
+ unsigned int align, bool no_warn)
{
if (align > CONFIG_CMA_ALIGNMENT)
align = CONFIG_CMA_ALIGNMENT;
- return cma_alloc(dev_get_cma_area(dev), count, align, gfp_mask);
+ return cma_alloc(dev_get_cma_area(dev), count, align, no_warn);
}
/**
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 8be8106270c2..1c35b7b945d0 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -78,7 +78,8 @@ void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
again:
/* CMA can be used only in the context which permits sleeping */
if (gfpflags_allow_blocking(gfp)) {
- page = dma_alloc_from_contiguous(dev, count, page_order, gfp);
+ page = dma_alloc_from_contiguous(dev, count, page_order,
+ gfp & __GFP_NOWARN);
if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
dma_release_from_contiguous(dev, page, count);
page = NULL;
@@ -180,10 +181,10 @@ int dma_direct_supported(struct device *dev, u64 mask)
return 0;
#endif
/*
- * Various PCI/PCIe bridges have broken support for > 32bit DMA even
- * if the device itself might support it.
+ * Upstream PCI/PCIe bridges or SoC interconnects may not carry
+ * as many DMA address bits as the device itself supports.
*/
- if (dev->dma_32bit_limit && mask > DMA_BIT_MASK(32))
+ if (dev->bus_dma_mask && mask > dev->bus_dma_mask)
return 0;
return 1;
}
diff --git a/kernel/dma/noncoherent.c b/kernel/dma/noncoherent.c
index 79e9a757387f..031fe235d958 100644
--- a/kernel/dma/noncoherent.c
+++ b/kernel/dma/noncoherent.c
@@ -49,11 +49,13 @@ static int dma_noncoherent_map_sg(struct device *dev, struct scatterlist *sgl,
return nents;
}
-#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
+ defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL)
static void dma_noncoherent_sync_single_for_cpu(struct device *dev,
dma_addr_t addr, size_t size, enum dma_data_direction dir)
{
arch_sync_dma_for_cpu(dev, dma_to_phys(dev, addr), size, dir);
+ arch_sync_dma_for_cpu_all(dev);
}
static void dma_noncoherent_sync_sg_for_cpu(struct device *dev,
@@ -64,6 +66,7 @@ static void dma_noncoherent_sync_sg_for_cpu(struct device *dev,
for_each_sg(sgl, sg, nents, i)
arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
+ arch_sync_dma_for_cpu_all(dev);
}
static void dma_noncoherent_unmap_page(struct device *dev, dma_addr_t addr,
@@ -89,7 +92,8 @@ const struct dma_map_ops dma_noncoherent_ops = {
.sync_sg_for_device = dma_noncoherent_sync_sg_for_device,
.map_page = dma_noncoherent_map_page,
.map_sg = dma_noncoherent_map_sg,
-#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
+ defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL)
.sync_single_for_cpu = dma_noncoherent_sync_single_for_cpu,
.sync_sg_for_cpu = dma_noncoherent_sync_sg_for_cpu,
.unmap_page = dma_noncoherent_unmap_page,
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 904541055792..4f8a6dbf0b60 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -17,6 +17,8 @@
* 08/12/11 beckyb Add highmem support
*/
+#define pr_fmt(fmt) "software IO TLB: " fmt
+
#include <linux/cache.h>
#include <linux/dma-direct.h>
#include <linux/mm.h>
@@ -162,20 +164,16 @@ static bool no_iotlb_memory;
void swiotlb_print_info(void)
{
unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT;
- unsigned char *vstart, *vend;
if (no_iotlb_memory) {
- pr_warn("software IO TLB: No low mem\n");
+ pr_warn("No low mem\n");
return;
}
- vstart = phys_to_virt(io_tlb_start);
- vend = phys_to_virt(io_tlb_end);
-
- printk(KERN_INFO "software IO TLB [mem %#010llx-%#010llx] (%luMB) mapped at [%p-%p]\n",
+ pr_info("mapped [mem %#010llx-%#010llx] (%luMB)\n",
(unsigned long long)io_tlb_start,
(unsigned long long)io_tlb_end,
- bytes >> 20, vstart, vend - 1);
+ bytes >> 20);
}
/*
@@ -275,7 +273,7 @@ swiotlb_init(int verbose)
if (io_tlb_start)
memblock_free_early(io_tlb_start,
PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
- pr_warn("Cannot allocate SWIOTLB buffer");
+ pr_warn("Cannot allocate buffer");
no_iotlb_memory = true;
}
@@ -317,8 +315,8 @@ swiotlb_late_init_with_default_size(size_t default_size)
return -ENOMEM;
}
if (order != get_order(bytes)) {
- printk(KERN_WARNING "Warning: only able to allocate %ld MB "
- "for software IO TLB\n", (PAGE_SIZE << order) >> 20);
+ pr_warn("only able to allocate %ld MB\n",
+ (PAGE_SIZE << order) >> 20);
io_tlb_nslabs = SLABS_PER_PAGE << order;
}
rc = swiotlb_late_init_with_tbl(vstart, io_tlb_nslabs);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 8f0434a9951a..2a62b96600ad 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1334,7 +1334,7 @@ static u32 perf_event_pid_type(struct perf_event *event, struct task_struct *p,
static u32 perf_event_pid(struct perf_event *event, struct task_struct *p)
{
- return perf_event_pid_type(event, p, __PIDTYPE_TGID);
+ return perf_event_pid_type(event, p, PIDTYPE_TGID);
}
static u32 perf_event_tid(struct perf_event *event, struct task_struct *p)
@@ -1656,7 +1656,7 @@ perf_event_groups_next(struct perf_event *event)
typeof(*event), group_node))
/*
- * Add a event from the lists for its context.
+ * Add an event from the lists for its context.
* Must be called with ctx->mutex and ctx->lock held.
*/
static void
@@ -1844,7 +1844,7 @@ static void perf_group_attach(struct perf_event *event)
}
/*
- * Remove a event from the lists for its context.
+ * Remove an event from the lists for its context.
* Must be called with ctx->mutex and ctx->lock held.
*/
static void
@@ -2148,7 +2148,7 @@ static void __perf_event_disable(struct perf_event *event,
}
/*
- * Disable a event.
+ * Disable an event.
*
* If event->ctx is a cloned context, callers must make sure that
* every task struct that event->ctx->task could possibly point to
@@ -2677,7 +2677,7 @@ static void __perf_event_enable(struct perf_event *event,
}
/*
- * Enable a event.
+ * Enable an event.
*
* If event->ctx is a cloned context, callers must make sure that
* every task struct that event->ctx->task could possibly point to
@@ -2755,7 +2755,7 @@ static int __perf_event_stop(void *info)
* events will refuse to restart because of rb::aux_mmap_count==0,
* see comments in perf_aux_output_begin().
*
- * Since this is happening on a event-local CPU, no trace is lost
+ * Since this is happening on an event-local CPU, no trace is lost
* while restarting.
*/
if (sd->restart)
@@ -4827,7 +4827,7 @@ __perf_read(struct perf_event *event, char __user *buf, size_t count)
int ret;
/*
- * Return end-of-file for a read on a event that is in
+ * Return end-of-file for a read on an event that is in
* error state (i.e. because it was pinned but it couldn't be
* scheduled on to the CPU at some point).
*/
@@ -5246,8 +5246,8 @@ void perf_event_update_userpage(struct perf_event *event)
userpg = rb->user_page;
/*
- * Disable preemption so as to not let the corresponding user-space
- * spin too long if we get preempted.
+ * Disable preemption to guarantee consistent time stamps are stored to
+ * the user page.
*/
preempt_disable();
++userpg->lock;
@@ -5273,11 +5273,11 @@ unlock:
}
EXPORT_SYMBOL_GPL(perf_event_update_userpage);
-static int perf_mmap_fault(struct vm_fault *vmf)
+static vm_fault_t perf_mmap_fault(struct vm_fault *vmf)
{
struct perf_event *event = vmf->vma->vm_file->private_data;
struct ring_buffer *rb;
- int ret = VM_FAULT_SIGBUS;
+ vm_fault_t ret = VM_FAULT_SIGBUS;
if (vmf->flags & FAULT_FLAG_MKWRITE) {
if (vmf->pgoff == 0)
@@ -6343,7 +6343,7 @@ static u64 perf_virt_to_phys(u64 virt)
static struct perf_callchain_entry __empty_callchain = { .nr = 0, };
-static struct perf_callchain_entry *
+struct perf_callchain_entry *
perf_callchain(struct perf_event *event, struct pt_regs *regs)
{
bool kernel = !event->attr.exclude_callchain_kernel;
@@ -6382,7 +6382,9 @@ void perf_prepare_sample(struct perf_event_header *header,
if (sample_type & PERF_SAMPLE_CALLCHAIN) {
int size = 1;
- data->callchain = perf_callchain(event, regs);
+ if (!(sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY))
+ data->callchain = perf_callchain(event, regs);
+
size += data->callchain->nr;
header->size += size * sizeof(u64);
@@ -7335,6 +7337,10 @@ static bool perf_addr_filter_match(struct perf_addr_filter *filter,
struct file *file, unsigned long offset,
unsigned long size)
{
+ /* d_inode(NULL) won't be equal to any mapped user-space file */
+ if (!filter->path.dentry)
+ return false;
+
if (d_inode(filter->path.dentry) != file_inode(file))
return false;
@@ -9898,7 +9904,7 @@ enabled:
}
/*
- * Allocate and initialize a event structure
+ * Allocate and initialize an event structure
*/
static struct perf_event *
perf_event_alloc(struct perf_event_attr *attr, int cpu,
@@ -11229,7 +11235,7 @@ const struct perf_event_attr *perf_event_attrs(struct perf_event *event)
}
/*
- * Inherit a event from parent task to child task.
+ * Inherit an event from parent task to child task.
*
* Returns:
* - valid pointer on success
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index 6e28d2866be5..b3814fce5ecb 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -345,13 +345,13 @@ void release_bp_slot(struct perf_event *bp)
mutex_unlock(&nr_bp_mutex);
}
-static int __modify_bp_slot(struct perf_event *bp, u64 old_type)
+static int __modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type)
{
int err;
__release_bp_slot(bp, old_type);
- err = __reserve_bp_slot(bp, bp->attr.bp_type);
+ err = __reserve_bp_slot(bp, new_type);
if (err) {
/*
* Reserve the old_type slot back in case
@@ -367,12 +367,12 @@ static int __modify_bp_slot(struct perf_event *bp, u64 old_type)
return err;
}
-static int modify_bp_slot(struct perf_event *bp, u64 old_type)
+static int modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type)
{
int ret;
mutex_lock(&nr_bp_mutex);
- ret = __modify_bp_slot(bp, old_type);
+ ret = __modify_bp_slot(bp, old_type, new_type);
mutex_unlock(&nr_bp_mutex);
return ret;
}
@@ -400,16 +400,18 @@ int dbg_release_bp_slot(struct perf_event *bp)
return 0;
}
-static int validate_hw_breakpoint(struct perf_event *bp)
+static int hw_breakpoint_parse(struct perf_event *bp,
+ const struct perf_event_attr *attr,
+ struct arch_hw_breakpoint *hw)
{
- int ret;
+ int err;
- ret = arch_validate_hwbkpt_settings(bp);
- if (ret)
- return ret;
+ err = hw_breakpoint_arch_parse(bp, attr, hw);
+ if (err)
+ return err;
- if (arch_check_bp_in_kernelspace(bp)) {
- if (bp->attr.exclude_kernel)
+ if (arch_check_bp_in_kernelspace(hw)) {
+ if (attr->exclude_kernel)
return -EINVAL;
/*
* Don't let unprivileged users set a breakpoint in the trap
@@ -424,19 +426,22 @@ static int validate_hw_breakpoint(struct perf_event *bp)
int register_perf_hw_breakpoint(struct perf_event *bp)
{
- int ret;
-
- ret = reserve_bp_slot(bp);
- if (ret)
- return ret;
+ struct arch_hw_breakpoint hw;
+ int err;
- ret = validate_hw_breakpoint(bp);
+ err = reserve_bp_slot(bp);
+ if (err)
+ return err;
- /* if arch_validate_hwbkpt_settings() fails then release bp slot */
- if (ret)
+ err = hw_breakpoint_parse(bp, &bp->attr, &hw);
+ if (err) {
release_bp_slot(bp);
+ return err;
+ }
- return ret;
+ bp->hw.info = hw;
+
+ return 0;
}
/**
@@ -456,35 +461,44 @@ register_user_hw_breakpoint(struct perf_event_attr *attr,
}
EXPORT_SYMBOL_GPL(register_user_hw_breakpoint);
+static void hw_breakpoint_copy_attr(struct perf_event_attr *to,
+ struct perf_event_attr *from)
+{
+ to->bp_addr = from->bp_addr;
+ to->bp_type = from->bp_type;
+ to->bp_len = from->bp_len;
+ to->disabled = from->disabled;
+}
+
int
modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *attr,
bool check)
{
- u64 old_addr = bp->attr.bp_addr;
- u64 old_len = bp->attr.bp_len;
- int old_type = bp->attr.bp_type;
- bool modify = attr->bp_type != old_type;
- int err = 0;
+ struct arch_hw_breakpoint hw;
+ int err;
- bp->attr.bp_addr = attr->bp_addr;
- bp->attr.bp_type = attr->bp_type;
- bp->attr.bp_len = attr->bp_len;
+ err = hw_breakpoint_parse(bp, attr, &hw);
+ if (err)
+ return err;
- if (check && memcmp(&bp->attr, attr, sizeof(*attr)))
- return -EINVAL;
+ if (check) {
+ struct perf_event_attr old_attr;
- err = validate_hw_breakpoint(bp);
- if (!err && modify)
- err = modify_bp_slot(bp, old_type);
+ old_attr = bp->attr;
+ hw_breakpoint_copy_attr(&old_attr, attr);
+ if (memcmp(&old_attr, attr, sizeof(*attr)))
+ return -EINVAL;
+ }
- if (err) {
- bp->attr.bp_addr = old_addr;
- bp->attr.bp_type = old_type;
- bp->attr.bp_len = old_len;
- return err;
+ if (bp->attr.bp_type != attr->bp_type) {
+ err = modify_bp_slot(bp, bp->attr.bp_type, attr->bp_type);
+ if (err)
+ return err;
}
- bp->attr.disabled = attr->disabled;
+ hw_breakpoint_copy_attr(&bp->attr, attr);
+ bp->hw.info = hw;
+
return 0;
}
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index ccc579a7d32e..3207a4d26849 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -299,8 +299,8 @@ static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t
* Called with mm->mmap_sem held for write.
* Return 0 (success) or a negative errno.
*/
-int uprobe_write_opcode(struct mm_struct *mm, unsigned long vaddr,
- uprobe_opcode_t opcode)
+int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
+ unsigned long vaddr, uprobe_opcode_t opcode)
{
struct page *old_page, *new_page;
struct vm_area_struct *vma;
@@ -351,7 +351,7 @@ put_old:
*/
int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
{
- return uprobe_write_opcode(mm, vaddr, UPROBE_SWBP_INSN);
+ return uprobe_write_opcode(auprobe, mm, vaddr, UPROBE_SWBP_INSN);
}
/**
@@ -366,7 +366,8 @@ int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned
int __weak
set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
{
- return uprobe_write_opcode(mm, vaddr, *(uprobe_opcode_t *)&auprobe->insn);
+ return uprobe_write_opcode(auprobe, mm, vaddr,
+ *(uprobe_opcode_t *)&auprobe->insn);
}
static struct uprobe *get_uprobe(struct uprobe *uprobe)
@@ -840,13 +841,8 @@ register_for_each_vma(struct uprobe *uprobe, struct uprobe_consumer *new)
return err;
}
-static int __uprobe_register(struct uprobe *uprobe, struct uprobe_consumer *uc)
-{
- consumer_add(uprobe, uc);
- return register_for_each_vma(uprobe, uc);
-}
-
-static void __uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc)
+static void
+__uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc)
{
int err;
@@ -860,24 +856,46 @@ static void __uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *u
}
/*
- * uprobe_register - register a probe
+ * 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.
+ * @uc: identify which probe if multiple probes are colocated.
+ */
+void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc)
+{
+ struct uprobe *uprobe;
+
+ uprobe = find_uprobe(inode, offset);
+ if (WARN_ON(!uprobe))
+ return;
+
+ down_write(&uprobe->register_rwsem);
+ __uprobe_unregister(uprobe, uc);
+ up_write(&uprobe->register_rwsem);
+ put_uprobe(uprobe);
+}
+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.
* @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)
*/
-int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc)
+static int __uprobe_register(struct inode *inode, loff_t offset,
+ struct uprobe_consumer *uc)
{
struct uprobe *uprobe;
int ret;
@@ -904,7 +922,8 @@ int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *
down_write(&uprobe->register_rwsem);
ret = -EAGAIN;
if (likely(uprobe_is_active(uprobe))) {
- ret = __uprobe_register(uprobe, uc);
+ consumer_add(uprobe, uc);
+ ret = register_for_each_vma(uprobe, uc);
if (ret)
__uprobe_unregister(uprobe, uc);
}
@@ -915,10 +934,16 @@ int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *
goto retry;
return ret;
}
+
+int uprobe_register(struct inode *inode, loff_t offset,
+ struct uprobe_consumer *uc)
+{
+ return __uprobe_register(inode, offset, uc);
+}
EXPORT_SYMBOL_GPL(uprobe_register);
/*
- * uprobe_apply - unregister a already registered probe.
+ * 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.
* @uc: consumer which wants to add more or remove some breakpoints
@@ -946,27 +971,6 @@ int uprobe_apply(struct inode *inode, loff_t offset,
return ret;
}
-/*
- * uprobe_unregister - unregister a already registered probe.
- * @inode: the file in which the probe has to be removed.
- * @offset: offset from the start of the file.
- * @uc: identify which probe if multiple probes are colocated.
- */
-void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc)
-{
- struct uprobe *uprobe;
-
- uprobe = find_uprobe(inode, offset);
- if (WARN_ON(!uprobe))
- return;
-
- down_write(&uprobe->register_rwsem);
- __uprobe_unregister(uprobe, uc);
- up_write(&uprobe->register_rwsem);
- put_uprobe(uprobe);
-}
-EXPORT_SYMBOL_GPL(uprobe_unregister);
-
static int unapply_uprobe(struct uprobe *uprobe, struct mm_struct *mm)
{
struct vm_area_struct *vma;
@@ -1403,7 +1407,7 @@ static struct return_instance *free_ret_instance(struct return_instance *ri)
/*
* Called with no locks held.
- * Called in context of a exiting or a exec-ing thread.
+ * Called in context of an exiting or an exec-ing thread.
*/
void uprobe_free_utask(struct task_struct *t)
{
diff --git a/kernel/exit.c b/kernel/exit.c
index c3c7ac560114..0e21e6d21f35 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -73,6 +73,7 @@ static void __unhash_process(struct task_struct *p, bool group_dead)
nr_threads--;
detach_pid(p, PIDTYPE_PID);
if (group_dead) {
+ detach_pid(p, PIDTYPE_TGID);
detach_pid(p, PIDTYPE_PGID);
detach_pid(p, PIDTYPE_SID);
@@ -680,7 +681,8 @@ static void forget_original_parent(struct task_struct *father,
t->parent = t->real_parent;
if (t->pdeath_signal)
group_send_sig_info(t->pdeath_signal,
- SEND_SIG_NOINFO, t);
+ SEND_SIG_NOINFO, t,
+ PIDTYPE_TGID);
}
/*
* If this is a threaded reparent there is no need to
@@ -1001,14 +1003,6 @@ struct wait_opts {
int notask_error;
};
-static inline
-struct pid *task_pid_type(struct task_struct *task, enum pid_type type)
-{
- if (type != PIDTYPE_PID)
- task = task->group_leader;
- return task->pids[type].pid;
-}
-
static int eligible_pid(struct wait_opts *wo, struct task_struct *p)
{
return wo->wo_type == PIDTYPE_MAX ||
diff --git a/kernel/fail_function.c b/kernel/fail_function.c
index 5349c91c2298..bc80a4e268c0 100644
--- a/kernel/fail_function.c
+++ b/kernel/fail_function.c
@@ -184,9 +184,6 @@ static int fei_kprobe_handler(struct kprobe *kp, struct pt_regs *regs)
if (should_fail(&fei_fault_attr, 1)) {
regs_set_return_value(regs, attr->retval);
override_function_with_return(regs);
- /* Kprobe specific fixup */
- reset_current_kprobe();
- preempt_enable_no_resched();
return 1;
}
diff --git a/kernel/fork.c b/kernel/fork.c
index f40c82b5c5a3..d896e9ca38b0 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -310,12 +310,11 @@ static struct kmem_cache *mm_cachep;
struct vm_area_struct *vm_area_alloc(struct mm_struct *mm)
{
- struct vm_area_struct *vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+ struct vm_area_struct *vma;
- if (vma) {
- vma->vm_mm = mm;
- INIT_LIST_HEAD(&vma->anon_vma_chain);
- }
+ vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+ if (vma)
+ vma_init(vma, mm);
return vma;
}
@@ -873,6 +872,9 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
tsk->use_memdelay = 0;
#endif
+#ifdef CONFIG_MEMCG
+ tsk->active_memcg = NULL;
+#endif
return tsk;
free_stack:
@@ -1300,6 +1302,7 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
tsk->nvcsw = tsk->nivcsw = 0;
#ifdef CONFIG_DETECT_HUNG_TASK
tsk->last_switch_count = tsk->nvcsw + tsk->nivcsw;
+ tsk->last_switch_time = 0;
#endif
tsk->mm = NULL;
@@ -1424,7 +1427,9 @@ static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk)
return -ENOMEM;
atomic_set(&sig->count, 1);
+ spin_lock_irq(&current->sighand->siglock);
memcpy(sig->action, current->sighand->action, sizeof(sig->action));
+ spin_unlock_irq(&current->sighand->siglock);
return 0;
}
@@ -1486,6 +1491,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
init_waitqueue_head(&sig->wait_chldexit);
sig->curr_target = tsk;
init_sigpending(&sig->shared_pending);
+ INIT_HLIST_HEAD(&sig->multiprocess);
seqlock_init(&sig->stats_lock);
prev_cputime_init(&sig->prev_cputime);
@@ -1579,10 +1585,22 @@ static void posix_cpu_timers_init(struct task_struct *tsk)
static inline void posix_cpu_timers_init(struct task_struct *tsk) { }
#endif
+static inline void init_task_pid_links(struct task_struct *task)
+{
+ enum pid_type type;
+
+ for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) {
+ INIT_HLIST_NODE(&task->pid_links[type]);
+ }
+}
+
static inline void
init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid)
{
- task->pids[type].pid = pid;
+ if (type == PIDTYPE_PID)
+ task->thread_pid = pid;
+ else
+ task->signal->pids[type] = pid;
}
static inline void rcu_copy_process(struct task_struct *p)
@@ -1620,6 +1638,7 @@ static __latent_entropy struct task_struct *copy_process(
{
int retval;
struct task_struct *p;
+ struct multiprocess_signals delayed;
/*
* Don't allow sharing the root directory with processes in a different
@@ -1667,6 +1686,24 @@ static __latent_entropy struct task_struct *copy_process(
return ERR_PTR(-EINVAL);
}
+ /*
+ * Force any signals received before this point to be delivered
+ * before the fork happens. Collect up signals sent to multiple
+ * processes that happen during the fork and delay them so that
+ * they appear to happen after the fork.
+ */
+ sigemptyset(&delayed.signal);
+ INIT_HLIST_NODE(&delayed.node);
+
+ spin_lock_irq(&current->sighand->siglock);
+ if (!(clone_flags & CLONE_THREAD))
+ hlist_add_head(&delayed.node, &current->signal->multiprocess);
+ recalc_sigpending();
+ spin_unlock_irq(&current->sighand->siglock);
+ retval = -ERESTARTNOINTR;
+ if (signal_pending(current))
+ goto fork_out;
+
retval = -ENOMEM;
p = dup_task_struct(current, node);
if (!p)
@@ -1940,29 +1977,26 @@ static __latent_entropy struct task_struct *copy_process(
rseq_fork(p, clone_flags);
- /*
- * Process group and session signals need to be delivered to just the
- * parent before the fork or both the parent and the child after the
- * fork. Restart if a signal comes in before we add the new process to
- * it's process group.
- * A fatal signal pending means that current will exit, so the new
- * thread can't slip out of an OOM kill (or normal SIGKILL).
- */
- recalc_sigpending();
- if (signal_pending(current)) {
- retval = -ERESTARTNOINTR;
- goto bad_fork_cancel_cgroup;
- }
+ /* 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;
}
+ /* Let kill terminate clone/fork in the middle */
+ if (fatal_signal_pending(current)) {
+ retval = -EINTR;
+ goto bad_fork_cancel_cgroup;
+ }
+
+
+ init_task_pid_links(p);
if (likely(p->pid)) {
ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace);
init_task_pid(p, PIDTYPE_PID, pid);
if (thread_group_leader(p)) {
+ init_task_pid(p, PIDTYPE_TGID, pid);
init_task_pid(p, PIDTYPE_PGID, task_pgrp(current));
init_task_pid(p, PIDTYPE_SID, task_session(current));
@@ -1970,8 +2004,7 @@ static __latent_entropy struct task_struct *copy_process(
ns_of_pid(pid)->child_reaper = p;
p->signal->flags |= SIGNAL_UNKILLABLE;
}
-
- p->signal->leader_pid = pid;
+ p->signal->shared_pending.signal = delayed.signal;
p->signal->tty = tty_kref_get(current->signal->tty);
/*
* Inherit has_child_subreaper flag under the same
@@ -1982,6 +2015,7 @@ static __latent_entropy struct task_struct *copy_process(
p->real_parent->signal->is_child_subreaper;
list_add_tail(&p->sibling, &p->real_parent->children);
list_add_tail_rcu(&p->tasks, &init_task.tasks);
+ attach_pid(p, PIDTYPE_TGID);
attach_pid(p, PIDTYPE_PGID);
attach_pid(p, PIDTYPE_SID);
__this_cpu_inc(process_counts);
@@ -1989,6 +2023,7 @@ static __latent_entropy struct task_struct *copy_process(
current->signal->nr_threads++;
atomic_inc(&current->signal->live);
atomic_inc(&current->signal->sigcnt);
+ task_join_group_stop(p);
list_add_tail_rcu(&p->thread_group,
&p->group_leader->thread_group);
list_add_tail_rcu(&p->thread_node,
@@ -1997,8 +2032,8 @@ static __latent_entropy struct task_struct *copy_process(
attach_pid(p, PIDTYPE_PID);
nr_threads++;
}
-
total_forks++;
+ hlist_del_init(&delayed.node);
spin_unlock(&current->sighand->siglock);
syscall_tracepoint_update(p);
write_unlock_irq(&tasklist_lock);
@@ -2063,16 +2098,19 @@ bad_fork_free:
put_task_stack(p);
free_task(p);
fork_out:
+ spin_lock_irq(&current->sighand->siglock);
+ hlist_del_init(&delayed.node);
+ spin_unlock_irq(&current->sighand->siglock);
return ERR_PTR(retval);
}
-static inline void init_idle_pids(struct pid_link *links)
+static inline void init_idle_pids(struct task_struct *idle)
{
enum pid_type type;
for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) {
- INIT_HLIST_NODE(&links[type].node); /* not really needed */
- links[type].pid = &init_struct_pid;
+ INIT_HLIST_NODE(&idle->pid_links[type]); /* not really needed */
+ init_task_pid(idle, type, &init_struct_pid);
}
}
@@ -2082,7 +2120,7 @@ struct task_struct *fork_idle(int cpu)
task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0,
cpu_to_node(cpu));
if (!IS_ERR(task)) {
- init_idle_pids(task->pids);
+ init_idle_pids(task);
init_idle(task, cpu);
}
@@ -2283,6 +2321,8 @@ static void sighand_ctor(void *data)
void __init proc_caches_init(void)
{
+ unsigned int mm_size;
+
sighand_cachep = kmem_cache_create("sighand_cache",
sizeof(struct sighand_struct), 0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU|
@@ -2299,15 +2339,16 @@ void __init proc_caches_init(void)
sizeof(struct fs_struct), 0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,
NULL);
+
/*
- * FIXME! The "sizeof(struct mm_struct)" currently includes the
- * whole struct cpumask for the OFFSTACK case. We could change
- * this to *only* allocate as much of it as required by the
- * maximum number of CPU's we can ever have. The cpumask_allocation
- * is at the end of the structure, exactly for that reason.
+ * The mm_cpumask is located at the end of mm_struct, and is
+ * dynamically sized based on the maximum CPU number this system
+ * can have, taking hotplug into account (nr_cpu_ids).
*/
+ mm_size = sizeof(struct mm_struct) + cpumask_size();
+
mm_cachep = kmem_cache_create_usercopy("mm_struct",
- sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN,
+ mm_size, ARCH_MIN_MMSTRUCT_ALIGN,
SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,
offsetof(struct mm_struct, saved_auxv),
sizeof_field(struct mm_struct, saved_auxv),
diff --git a/kernel/freezer.c b/kernel/freezer.c
index 6f56a9e219fa..b162b74611e4 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -15,7 +15,9 @@
atomic_t system_freezing_cnt = ATOMIC_INIT(0);
EXPORT_SYMBOL(system_freezing_cnt);
-/* indicate whether PM freezing is in effect, protected by pm_mutex */
+/* indicate whether PM freezing is in effect, protected by
+ * system_transition_mutex
+ */
bool pm_freezing;
bool pm_nosig_freezing;
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 32b479468e4d..b9132d1269ef 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -40,6 +40,11 @@ int __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT;
*/
unsigned long __read_mostly sysctl_hung_task_timeout_secs = CONFIG_DEFAULT_HUNG_TASK_TIMEOUT;
+/*
+ * Zero (default value) means use sysctl_hung_task_timeout_secs:
+ */
+unsigned long __read_mostly sysctl_hung_task_check_interval_secs;
+
int __read_mostly sysctl_hung_task_warnings = 10;
static int __read_mostly did_panic;
@@ -98,8 +103,11 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
if (switch_count != t->last_switch_count) {
t->last_switch_count = switch_count;
+ t->last_switch_time = jiffies;
return;
}
+ if (time_is_after_jiffies(t->last_switch_time + timeout * HZ))
+ return;
trace_sched_process_hang(t);
@@ -245,8 +253,13 @@ static int watchdog(void *dummy)
for ( ; ; ) {
unsigned long timeout = sysctl_hung_task_timeout_secs;
- long t = hung_timeout_jiffies(hung_last_checked, timeout);
+ unsigned long interval = sysctl_hung_task_check_interval_secs;
+ long t;
+ if (interval == 0)
+ interval = timeout;
+ interval = min_t(unsigned long, interval, timeout);
+ t = hung_timeout_jiffies(hung_last_checked, interval);
if (t <= 0) {
if (!atomic_xchg(&reset_hung_task, 0))
check_hung_uninterruptible_tasks(timeout);
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index c6766f326072..5f3e2baefca9 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -134,7 +134,6 @@ config GENERIC_IRQ_DEBUGFS
endmenu
config GENERIC_IRQ_MULTI_HANDLER
- depends on !MULTI_IRQ_HANDLER
bool
help
Allow to specify the low level IRQ handler at run time.
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index afc7f902d74a..578d0e5f1b5b 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -443,6 +443,7 @@ static void free_desc(unsigned int irq)
* We free the descriptor, masks and stat fields via RCU. That
* allows demultiplex interrupts to do rcu based management of
* the child interrupts.
+ * This also allows us to use rcu in kstat_irqs_usr().
*/
call_rcu(&desc->rcu, delayed_free_desc);
}
@@ -928,17 +929,17 @@ unsigned int kstat_irqs(unsigned int irq)
* kstat_irqs_usr - Get the statistics for an interrupt
* @irq: The interrupt number
*
- * Returns the sum of interrupt counts on all cpus since boot for
- * @irq. Contrary to kstat_irqs() this can be called from any
- * preemptible context. It's protected against concurrent removal of
- * an interrupt descriptor when sparse irqs are enabled.
+ * Returns the sum of interrupt counts on all cpus since boot for @irq.
+ * Contrary to kstat_irqs() this can be called from any context.
+ * It uses rcu since a concurrent removal of an interrupt descriptor is
+ * observing an rcu grace period before delayed_free_desc()/irq_kobj_release().
*/
unsigned int kstat_irqs_usr(unsigned int irq)
{
unsigned int sum;
- irq_lock_sparse();
+ rcu_read_lock();
sum = kstat_irqs(irq);
- irq_unlock_sparse();
+ rcu_read_unlock();
return sum;
}
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index daeabd791d58..fb86146037a7 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -790,9 +790,19 @@ static irqreturn_t irq_forced_secondary_handler(int irq, void *dev_id)
static int irq_wait_for_interrupt(struct irqaction *action)
{
- set_current_state(TASK_INTERRUPTIBLE);
+ for (;;) {
+ set_current_state(TASK_INTERRUPTIBLE);
- while (!kthread_should_stop()) {
+ if (kthread_should_stop()) {
+ /* may need to run one last time */
+ if (test_and_clear_bit(IRQTF_RUNTHREAD,
+ &action->thread_flags)) {
+ __set_current_state(TASK_RUNNING);
+ return 0;
+ }
+ __set_current_state(TASK_RUNNING);
+ return -1;
+ }
if (test_and_clear_bit(IRQTF_RUNTHREAD,
&action->thread_flags)) {
@@ -800,10 +810,7 @@ static int irq_wait_for_interrupt(struct irqaction *action)
return 0;
}
schedule();
- set_current_state(TASK_INTERRUPTIBLE);
}
- __set_current_state(TASK_RUNNING);
- return -1;
}
/*
@@ -1024,11 +1031,8 @@ static int irq_thread(void *data)
/*
* This is the regular exit path. __free_irq() is stopping the
* thread via kthread_stop() after calling
- * synchronize_irq(). So neither IRQTF_RUNTHREAD nor the
- * oneshot mask bit can be set. We cannot verify that as we
- * cannot touch the oneshot mask at this point anymore as
- * __setup_irq() might have given out currents thread_mask
- * again.
+ * synchronize_hardirq(). So neither IRQTF_RUNTHREAD nor the
+ * oneshot mask bit can be set.
*/
task_work_cancel(current, irq_thread_dtor);
return 0;
@@ -1068,6 +1072,13 @@ static int irq_setup_forced_threading(struct irqaction *new)
if (new->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT))
return 0;
+ /*
+ * No further action required for interrupts which are requested as
+ * threaded interrupts already
+ */
+ if (new->handler == irq_default_primary_handler)
+ return 0;
+
new->flags |= IRQF_ONESHOT;
/*
@@ -1075,7 +1086,7 @@ static int irq_setup_forced_threading(struct irqaction *new)
* thread handler. We force thread them as well by creating a
* secondary action.
*/
- if (new->handler != irq_default_primary_handler && new->thread_fn) {
+ if (new->handler && new->thread_fn) {
/* Allocate the secondary action */
new->secondary = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
if (!new->secondary)
@@ -1244,8 +1255,10 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
/*
* Protects against a concurrent __free_irq() call which might wait
- * for synchronize_irq() to complete without holding the optional
- * chip bus lock and desc->lock.
+ * for synchronize_hardirq() to complete without holding the optional
+ * chip bus lock and desc->lock. Also protects against handing out
+ * a recycled oneshot thread_mask bit while it's still in use by
+ * its previous owner.
*/
mutex_lock(&desc->request_mutex);
@@ -1564,9 +1577,6 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq);
- if (!desc)
- return NULL;
-
mutex_lock(&desc->request_mutex);
chip_bus_lock(desc);
raw_spin_lock_irqsave(&desc->lock, flags);
@@ -1613,11 +1623,11 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
/*
* Drop bus_lock here so the changes which were done in the chip
* callbacks above are synced out to the irq chips which hang
- * behind a slow bus (I2C, SPI) before calling synchronize_irq().
+ * behind a slow bus (I2C, SPI) before calling synchronize_hardirq().
*
* Aside of that the bus_lock can also be taken from the threaded
* handler in irq_finalize_oneshot() which results in a deadlock
- * because synchronize_irq() would wait forever for the thread to
+ * because kthread_stop() would wait forever for the thread to
* complete, which is blocked on the bus lock.
*
* The still held desc->request_mutex() protects against a
@@ -1629,7 +1639,7 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
unregister_handler_proc(irq, action);
/* Make sure it's not being used on another CPU: */
- synchronize_irq(irq);
+ synchronize_hardirq(irq);
#ifdef CONFIG_DEBUG_SHIRQ
/*
@@ -1638,7 +1648,7 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
* is so by doing an extra call to the handler ....
*
* ( We do this after actually deregistering it, to make sure that a
- * 'real' IRQ doesn't run in * parallel with our fake. )
+ * 'real' IRQ doesn't run in parallel with our fake. )
*/
if (action->flags & IRQF_SHARED) {
local_irq_save(flags);
@@ -1647,6 +1657,12 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
}
#endif
+ /*
+ * The action has already been removed above, but the thread writes
+ * its oneshot mask bit when it completes. Though request_mutex is
+ * held across this which prevents __setup_irq() from handing out
+ * the same bit to a newly requested action.
+ */
if (action->thread) {
kthread_stop(action->thread);
put_task_struct(action->thread);
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 37eda10f5c36..da9addb8d655 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -475,22 +475,24 @@ int show_interrupts(struct seq_file *p, void *v)
seq_putc(p, '\n');
}
- irq_lock_sparse();
+ rcu_read_lock();
desc = irq_to_desc(i);
if (!desc)
goto outsparse;
- raw_spin_lock_irqsave(&desc->lock, flags);
- for_each_online_cpu(j)
- any_count |= kstat_irqs_cpu(i, j);
- action = desc->action;
- if ((!action || irq_desc_is_chained(desc)) && !any_count)
- goto out;
+ if (desc->kstat_irqs)
+ for_each_online_cpu(j)
+ any_count |= *per_cpu_ptr(desc->kstat_irqs, j);
+
+ if ((!desc->action || irq_desc_is_chained(desc)) && !any_count)
+ goto outsparse;
seq_printf(p, "%*d: ", prec, i);
for_each_online_cpu(j)
- seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
+ seq_printf(p, "%10u ", desc->kstat_irqs ?
+ *per_cpu_ptr(desc->kstat_irqs, j) : 0);
+ raw_spin_lock_irqsave(&desc->lock, flags);
if (desc->irq_data.chip) {
if (desc->irq_data.chip->irq_print_chip)
desc->irq_data.chip->irq_print_chip(&desc->irq_data, p);
@@ -511,6 +513,7 @@ int show_interrupts(struct seq_file *p, void *v)
if (desc->name)
seq_printf(p, "-%-8s", desc->name);
+ action = desc->action;
if (action) {
seq_printf(p, " %s", action->name);
while ((action = action->next) != NULL)
@@ -518,10 +521,9 @@ int show_interrupts(struct seq_file *p, void *v)
}
seq_putc(p, '\n');
-out:
raw_spin_unlock_irqrestore(&desc->lock, flags);
outsparse:
- irq_unlock_sparse();
+ rcu_read_unlock();
return 0;
}
#endif
diff --git a/kernel/kexec.c b/kernel/kexec.c
index aed8fb2564b3..68559808fdfa 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -11,6 +11,7 @@
#include <linux/capability.h>
#include <linux/mm.h>
#include <linux/file.h>
+#include <linux/security.h>
#include <linux/kexec.h>
#include <linux/mutex.h>
#include <linux/list.h>
@@ -195,10 +196,17 @@ out:
static inline int kexec_load_check(unsigned long nr_segments,
unsigned long flags)
{
+ int result;
+
/* We only trust the superuser with rebooting the system. */
if (!capable(CAP_SYS_BOOT) || kexec_load_disabled)
return -EPERM;
+ /* Permit LSMs and IMA to fail the kexec */
+ result = security_kernel_load_data(LOADING_KEXEC_IMAGE);
+ if (result < 0)
+ return result;
+
/*
* Verify we have a legal set of flags
* This leaves us room for future extensions.
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index ea619021d901..ab257be4d924 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -627,8 +627,8 @@ static void optimize_kprobe(struct kprobe *p)
(kprobe_disabled(p) || kprobes_all_disarmed))
return;
- /* Both of break_handler and post_handler are not supported. */
- if (p->break_handler || p->post_handler)
+ /* kprobes with post_handler can not be optimized */
+ if (p->post_handler)
return;
op = container_of(p, struct optimized_kprobe, kp);
@@ -710,9 +710,7 @@ static void reuse_unused_kprobe(struct kprobe *ap)
* there is still a relative jump) and disabled.
*/
op = container_of(ap, struct optimized_kprobe, kp);
- if (unlikely(list_empty(&op->list)))
- printk(KERN_WARNING "Warning: found a stray unused "
- "aggrprobe@%p\n", ap->addr);
+ WARN_ON_ONCE(list_empty(&op->list));
/* Enable the probe again */
ap->flags &= ~KPROBE_FLAG_DISABLED;
/* Optimize it again (remove from op->list) */
@@ -985,7 +983,8 @@ static int arm_kprobe_ftrace(struct kprobe *p)
ret = ftrace_set_filter_ip(&kprobe_ftrace_ops,
(unsigned long)p->addr, 0, 0);
if (ret) {
- pr_debug("Failed to arm kprobe-ftrace at %p (%d)\n", p->addr, ret);
+ pr_debug("Failed to arm kprobe-ftrace at %pS (%d)\n",
+ p->addr, ret);
return ret;
}
@@ -1025,7 +1024,8 @@ static int disarm_kprobe_ftrace(struct kprobe *p)
ret = ftrace_set_filter_ip(&kprobe_ftrace_ops,
(unsigned long)p->addr, 1, 0);
- WARN(ret < 0, "Failed to disarm kprobe-ftrace at %p (%d)\n", p->addr, ret);
+ WARN_ONCE(ret < 0, "Failed to disarm kprobe-ftrace at %pS (%d)\n",
+ p->addr, ret);
return ret;
}
#else /* !CONFIG_KPROBES_ON_FTRACE */
@@ -1116,20 +1116,6 @@ static int aggr_fault_handler(struct kprobe *p, struct pt_regs *regs,
}
NOKPROBE_SYMBOL(aggr_fault_handler);
-static int aggr_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
- struct kprobe *cur = __this_cpu_read(kprobe_instance);
- int ret = 0;
-
- if (cur && cur->break_handler) {
- if (cur->break_handler(cur, regs))
- ret = 1;
- }
- reset_kprobe_instance();
- return ret;
-}
-NOKPROBE_SYMBOL(aggr_break_handler);
-
/* Walks the list and increments nmissed count for multiprobe case */
void kprobes_inc_nmissed_count(struct kprobe *p)
{
@@ -1270,24 +1256,15 @@ static void cleanup_rp_inst(struct kretprobe *rp)
}
NOKPROBE_SYMBOL(cleanup_rp_inst);
-/*
-* Add the new probe to ap->list. Fail if this is the
-* second jprobe at the address - two jprobes can't coexist
-*/
+/* Add the new probe to ap->list */
static int add_new_kprobe(struct kprobe *ap, struct kprobe *p)
{
BUG_ON(kprobe_gone(ap) || kprobe_gone(p));
- if (p->break_handler || p->post_handler)
+ if (p->post_handler)
unoptimize_kprobe(ap, true); /* Fall back to normal kprobe */
- if (p->break_handler) {
- if (ap->break_handler)
- return -EEXIST;
- list_add_tail_rcu(&p->list, &ap->list);
- ap->break_handler = aggr_break_handler;
- } else
- list_add_rcu(&p->list, &ap->list);
+ list_add_rcu(&p->list, &ap->list);
if (p->post_handler && !ap->post_handler)
ap->post_handler = aggr_post_handler;
@@ -1310,8 +1287,6 @@ static void init_aggr_kprobe(struct kprobe *ap, struct kprobe *p)
/* We don't care the kprobe which has gone. */
if (p->post_handler && !kprobe_gone(p))
ap->post_handler = aggr_post_handler;
- if (p->break_handler && !kprobe_gone(p))
- ap->break_handler = aggr_break_handler;
INIT_LIST_HEAD(&ap->list);
INIT_HLIST_NODE(&ap->hlist);
@@ -1706,8 +1681,6 @@ static int __unregister_kprobe_top(struct kprobe *p)
goto disarmed;
else {
/* If disabling probe has special handlers, update aggrprobe */
- if (p->break_handler && !kprobe_gone(p))
- ap->break_handler = NULL;
if (p->post_handler && !kprobe_gone(p)) {
list_for_each_entry_rcu(list_p, &ap->list, list) {
if ((list_p != p) && (list_p->post_handler))
@@ -1812,77 +1785,6 @@ unsigned long __weak arch_deref_entry_point(void *entry)
return (unsigned long)entry;
}
-#if 0
-int register_jprobes(struct jprobe **jps, int num)
-{
- int ret = 0, i;
-
- if (num <= 0)
- return -EINVAL;
-
- for (i = 0; i < num; i++) {
- ret = register_jprobe(jps[i]);
-
- if (ret < 0) {
- if (i > 0)
- unregister_jprobes(jps, i);
- break;
- }
- }
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(register_jprobes);
-
-int register_jprobe(struct jprobe *jp)
-{
- unsigned long addr, offset;
- struct kprobe *kp = &jp->kp;
-
- /*
- * Verify probepoint as well as the jprobe handler are
- * valid function entry points.
- */
- addr = arch_deref_entry_point(jp->entry);
-
- if (kallsyms_lookup_size_offset(addr, NULL, &offset) && offset == 0 &&
- kprobe_on_func_entry(kp->addr, kp->symbol_name, kp->offset)) {
- kp->pre_handler = setjmp_pre_handler;
- kp->break_handler = longjmp_break_handler;
- return register_kprobe(kp);
- }
-
- return -EINVAL;
-}
-EXPORT_SYMBOL_GPL(register_jprobe);
-
-void unregister_jprobe(struct jprobe *jp)
-{
- unregister_jprobes(&jp, 1);
-}
-EXPORT_SYMBOL_GPL(unregister_jprobe);
-
-void unregister_jprobes(struct jprobe **jps, int num)
-{
- int i;
-
- if (num <= 0)
- return;
- mutex_lock(&kprobe_mutex);
- for (i = 0; i < num; i++)
- if (__unregister_kprobe_top(&jps[i]->kp) < 0)
- jps[i]->kp.addr = NULL;
- mutex_unlock(&kprobe_mutex);
-
- synchronize_sched();
- for (i = 0; i < num; i++) {
- if (jps[i]->kp.addr)
- __unregister_kprobe_bottom(&jps[i]->kp);
- }
-}
-EXPORT_SYMBOL_GPL(unregister_jprobes);
-#endif
-
#ifdef CONFIG_KRETPROBES
/*
* This kprobe pre_handler is registered with every kretprobe. When probe
@@ -1982,7 +1884,6 @@ int register_kretprobe(struct kretprobe *rp)
rp->kp.pre_handler = pre_handler_kretprobe;
rp->kp.post_handler = NULL;
rp->kp.fault_handler = NULL;
- rp->kp.break_handler = NULL;
/* Pre-allocate memory for max kretprobe instances */
if (rp->maxactive <= 0) {
@@ -2105,7 +2006,6 @@ static void kill_kprobe(struct kprobe *p)
list_for_each_entry_rcu(kp, &p->list, list)
kp->flags |= KPROBE_FLAG_GONE;
p->post_handler = NULL;
- p->break_handler = NULL;
kill_optimized_kprobe(p);
}
/*
@@ -2169,11 +2069,12 @@ out:
}
EXPORT_SYMBOL_GPL(enable_kprobe);
+/* Caller must NOT call this in usual path. This is only for critical case */
void dump_kprobe(struct kprobe *kp)
{
- printk(KERN_WARNING "Dumping kprobe:\n");
- printk(KERN_WARNING "Name: %s\nAddress: %p\nOffset: %x\n",
- kp->symbol_name, kp->addr, kp->offset);
+ pr_err("Dumping kprobe:\n");
+ pr_err("Name: %s\nOffset: %x\nAddress: %pS\n",
+ kp->symbol_name, kp->offset, kp->addr);
}
NOKPROBE_SYMBOL(dump_kprobe);
@@ -2196,11 +2097,8 @@ static int __init populate_kprobe_blacklist(unsigned long *start,
entry = arch_deref_entry_point((void *)*iter);
if (!kernel_text_address(entry) ||
- !kallsyms_lookup_size_offset(entry, &size, &offset)) {
- pr_err("Failed to find blacklist at %p\n",
- (void *)entry);
+ !kallsyms_lookup_size_offset(entry, &size, &offset))
continue;
- }
ent = kmalloc(sizeof(*ent), GFP_KERNEL);
if (!ent)
@@ -2326,21 +2224,23 @@ static void report_probe(struct seq_file *pi, struct kprobe *p,
const char *sym, int offset, char *modname, struct kprobe *pp)
{
char *kprobe_type;
+ void *addr = p->addr;
if (p->pre_handler == pre_handler_kretprobe)
kprobe_type = "r";
- else if (p->pre_handler == setjmp_pre_handler)
- kprobe_type = "j";
else
kprobe_type = "k";
+ if (!kallsyms_show_value())
+ addr = NULL;
+
if (sym)
- seq_printf(pi, "%p %s %s+0x%x %s ",
- p->addr, kprobe_type, sym, offset,
+ seq_printf(pi, "%px %s %s+0x%x %s ",
+ addr, kprobe_type, sym, offset,
(modname ? modname : " "));
- else
- seq_printf(pi, "%p %s %p ",
- p->addr, kprobe_type, p->addr);
+ else /* try to use %pS */
+ seq_printf(pi, "%px %s %pS ",
+ addr, kprobe_type, p->addr);
if (!pp)
pp = p;
@@ -2428,8 +2328,16 @@ static int kprobe_blacklist_seq_show(struct seq_file *m, void *v)
struct kprobe_blacklist_entry *ent =
list_entry(v, struct kprobe_blacklist_entry, list);
- seq_printf(m, "0x%px-0x%px\t%ps\n", (void *)ent->start_addr,
- (void *)ent->end_addr, (void *)ent->start_addr);
+ /*
+ * If /proc/kallsyms is not showing kernel address, we won't
+ * show them here either.
+ */
+ if (!kallsyms_show_value())
+ seq_printf(m, "0x%px-0x%px\t%ps\n", NULL, NULL,
+ (void *)ent->start_addr);
+ else
+ seq_printf(m, "0x%px-0x%px\t%ps\n", (void *)ent->start_addr,
+ (void *)ent->end_addr, (void *)ent->start_addr);
return 0;
}
@@ -2611,7 +2519,7 @@ static int __init debugfs_kprobe_init(void)
if (!dir)
return -ENOMEM;
- file = debugfs_create_file("list", 0444, dir, NULL,
+ file = debugfs_create_file("list", 0400, dir, NULL,
&debugfs_kprobes_operations);
if (!file)
goto error;
@@ -2621,7 +2529,7 @@ static int __init debugfs_kprobe_init(void)
if (!file)
goto error;
- file = debugfs_create_file("blacklist", 0444, dir, NULL,
+ file = debugfs_create_file("blacklist", 0400, dir, NULL,
&debugfs_kprobe_blacklist_ops);
if (!file)
goto error;
@@ -2637,6 +2545,3 @@ late_initcall(debugfs_kprobe_init);
#endif /* CONFIG_DEBUG_FS */
module_init(init_kprobes);
-
-/* defined in arch/.../kernel/kprobes.c */
-EXPORT_SYMBOL_GPL(jprobe_return);
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 750cb8082694..087d18d771b5 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -190,7 +190,7 @@ static void __kthread_parkme(struct kthread *self)
if (!test_bit(KTHREAD_SHOULD_PARK, &self->flags))
break;
- complete_all(&self->parked);
+ complete(&self->parked);
schedule();
}
__set_current_state(TASK_RUNNING);
@@ -325,8 +325,14 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data),
task = create->result;
if (!IS_ERR(task)) {
static const struct sched_param param = { .sched_priority = 0 };
+ char name[TASK_COMM_LEN];
- vsnprintf(task->comm, sizeof(task->comm), namefmt, args);
+ /*
+ * task is already visible to other tasks, so updating
+ * COMM must be protected.
+ */
+ vsnprintf(name, sizeof(name), namefmt, args);
+ set_task_comm(task, name);
/*
* root may have changed our (kthreadd's) priority or CPU mask.
* The kernel thread should not inherit these properties.
@@ -465,7 +471,6 @@ void kthread_unpark(struct task_struct *k)
if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
__kthread_bind(k, kthread->cpu, TASK_PARKED);
- reinit_completion(&kthread->parked);
clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
/*
* __kthread_parkme() will either see !SHOULD_PARK or get the wakeup.
@@ -493,6 +498,9 @@ int kthread_park(struct task_struct *k)
if (WARN_ON(k->flags & PF_EXITING))
return -ENOSYS;
+ if (WARN_ON_ONCE(test_bit(KTHREAD_SHOULD_PARK, &kthread->flags)))
+ return -EBUSY;
+
set_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
if (k != current) {
wake_up_process(k);
diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c
index 3a4656fb7047..5b77a7314e01 100644
--- a/kernel/livepatch/core.c
+++ b/kernel/livepatch/core.c
@@ -678,6 +678,9 @@ static int klp_init_func(struct klp_object *obj, struct klp_func *func)
if (!func->old_name || !func->new_func)
return -EINVAL;
+ if (strlen(func->old_name) >= KSYM_NAME_LEN)
+ return -EINVAL;
+
INIT_LIST_HEAD(&func->stack_node);
func->patched = false;
func->transition = false;
@@ -751,6 +754,9 @@ static int klp_init_object(struct klp_patch *patch, struct klp_object *obj)
if (!obj->funcs)
return -EINVAL;
+ if (klp_is_module(obj) && strlen(obj->name) >= MODULE_NAME_LEN)
+ return -EINVAL;
+
obj->patched = false;
obj->mod = NULL;
diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c
index 7c6631e693bc..5bc349805e03 100644
--- a/kernel/livepatch/transition.c
+++ b/kernel/livepatch/transition.c
@@ -310,13 +310,6 @@ static bool klp_try_switch_task(struct task_struct *task)
return true;
/*
- * For arches which don't have reliable stack traces, we have to rely
- * on other methods (e.g., switching tasks at kernel exit).
- */
- if (!klp_have_reliable_stack())
- return false;
-
- /*
* Now try to check the stack for any to-be-patched or to-be-unpatched
* functions. If all goes well, switch the task to the target patch
* state.
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 5fa4d3138bf1..e406c5fdb41e 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -55,6 +55,7 @@
#include "lockdep_internals.h"
+#include <trace/events/preemptirq.h>
#define CREATE_TRACE_POINTS
#include <trace/events/lock.h>
@@ -248,12 +249,7 @@ void clear_lock_stats(struct lock_class *class)
static struct lock_class_stats *get_lock_stats(struct lock_class *class)
{
- return &get_cpu_var(cpu_lock_stats)[class - lock_classes];
-}
-
-static void put_lock_stats(struct lock_class_stats *stats)
-{
- put_cpu_var(cpu_lock_stats);
+ return &this_cpu_ptr(cpu_lock_stats)[class - lock_classes];
}
static void lock_release_holdtime(struct held_lock *hlock)
@@ -271,7 +267,6 @@ static void lock_release_holdtime(struct held_lock *hlock)
lock_time_inc(&stats->read_holdtime, holdtime);
else
lock_time_inc(&stats->write_holdtime, holdtime);
- put_lock_stats(stats);
}
#else
static inline void lock_release_holdtime(struct held_lock *hlock)
@@ -2845,10 +2840,8 @@ static void __trace_hardirqs_on_caller(unsigned long ip)
debug_atomic_inc(hardirqs_on_events);
}
-__visible void trace_hardirqs_on_caller(unsigned long ip)
+void lockdep_hardirqs_on(unsigned long ip)
{
- time_hardirqs_on(CALLER_ADDR0, ip);
-
if (unlikely(!debug_locks || current->lockdep_recursion))
return;
@@ -2887,23 +2880,14 @@ __visible void trace_hardirqs_on_caller(unsigned long ip)
__trace_hardirqs_on_caller(ip);
current->lockdep_recursion = 0;
}
-EXPORT_SYMBOL(trace_hardirqs_on_caller);
-
-void trace_hardirqs_on(void)
-{
- trace_hardirqs_on_caller(CALLER_ADDR0);
-}
-EXPORT_SYMBOL(trace_hardirqs_on);
/*
* Hardirqs were disabled:
*/
-__visible void trace_hardirqs_off_caller(unsigned long ip)
+void lockdep_hardirqs_off(unsigned long ip)
{
struct task_struct *curr = current;
- time_hardirqs_off(CALLER_ADDR0, ip);
-
if (unlikely(!debug_locks || current->lockdep_recursion))
return;
@@ -2925,13 +2909,6 @@ __visible void trace_hardirqs_off_caller(unsigned long ip)
} else
debug_atomic_inc(redundant_hardirqs_off);
}
-EXPORT_SYMBOL(trace_hardirqs_off_caller);
-
-void trace_hardirqs_off(void)
-{
- trace_hardirqs_off_caller(CALLER_ADDR0);
-}
-EXPORT_SYMBOL(trace_hardirqs_off);
/*
* Softirqs will be enabled:
@@ -4090,7 +4067,6 @@ __lock_contended(struct lockdep_map *lock, unsigned long ip)
stats->contending_point[contending_point]++;
if (lock->cpu != smp_processor_id())
stats->bounces[bounce_contended + !!hlock->read]++;
- put_lock_stats(stats);
}
static void
@@ -4138,7 +4114,6 @@ __lock_acquired(struct lockdep_map *lock, unsigned long ip)
}
if (lock->cpu != cpu)
stats->bounces[bounce_acquired + !!hlock->read]++;
- put_lock_stats(stats);
lock->cpu = cpu;
lock->ip = ip;
@@ -4338,7 +4313,7 @@ out_restore:
raw_local_irq_restore(flags);
}
-void __init lockdep_info(void)
+void __init lockdep_init(void)
{
printk("Lock dependency validator: Copyright (c) 2006 Red Hat, Inc., Ingo Molnar\n");
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index 8402b3349dca..7d0b0ed74404 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -21,6 +21,9 @@
* Davidlohr Bueso <dave@stgolabs.net>
* Based on kernel/rcu/torture.c.
*/
+
+#define pr_fmt(fmt) fmt
+
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/kthread.h>
@@ -57,7 +60,7 @@ torture_param(int, shutdown_secs, 0, "Shutdown time (j), <= zero to disable.");
torture_param(int, stat_interval, 60,
"Number of seconds between stats printk()s");
torture_param(int, stutter, 5, "Number of jiffies to run/halt test, 0=disable");
-torture_param(bool, verbose, true,
+torture_param(int, verbose, 1,
"Enable verbose debugging printk()s");
static char *torture_type = "spin_lock";
@@ -365,7 +368,7 @@ static struct lock_torture_ops mutex_lock_ops = {
};
#include <linux/ww_mutex.h>
-static DEFINE_WW_CLASS(torture_ww_class);
+static DEFINE_WD_CLASS(torture_ww_class);
static DEFINE_WW_MUTEX(torture_ww_mutex_0, &torture_ww_class);
static DEFINE_WW_MUTEX(torture_ww_mutex_1, &torture_ww_class);
static DEFINE_WW_MUTEX(torture_ww_mutex_2, &torture_ww_class);
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index f44f658ae629..1a81a1257b3f 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -174,6 +174,21 @@ static inline bool __mutex_waiter_is_first(struct mutex *lock, struct mutex_wait
}
/*
+ * Add @waiter to a given location in the lock wait_list and set the
+ * FLAG_WAITERS flag if it's the first waiter.
+ */
+static void __sched
+__mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter,
+ struct list_head *list)
+{
+ debug_mutex_add_waiter(lock, waiter, current);
+
+ list_add_tail(&waiter->list, list);
+ if (__mutex_waiter_is_first(lock, waiter))
+ __mutex_set_flag(lock, MUTEX_FLAG_WAITERS);
+}
+
+/*
* Give up ownership to a specific task, when @task = NULL, this is equivalent
* to a regular unlock. Sets PICKUP on a handoff, clears HANDOF, preserves
* WAITERS. Provides RELEASE semantics like a regular unlock, the
@@ -244,6 +259,22 @@ void __sched mutex_lock(struct mutex *lock)
EXPORT_SYMBOL(mutex_lock);
#endif
+/*
+ * Wait-Die:
+ * The newer transactions are killed when:
+ * It (the new transaction) makes a request for a lock being held
+ * by an older transaction.
+ *
+ * Wound-Wait:
+ * The newer transactions are wounded when:
+ * An older transaction makes a request for a lock being held by
+ * the newer transaction.
+ */
+
+/*
+ * Associate the ww_mutex @ww with the context @ww_ctx under which we acquired
+ * it.
+ */
static __always_inline void
ww_mutex_lock_acquired(struct ww_mutex *ww, struct ww_acquire_ctx *ww_ctx)
{
@@ -282,26 +313,108 @@ ww_mutex_lock_acquired(struct ww_mutex *ww, struct ww_acquire_ctx *ww_ctx)
DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class);
#endif
ww_ctx->acquired++;
+ ww->ctx = ww_ctx;
}
+/*
+ * Determine if context @a is 'after' context @b. IOW, @a is a younger
+ * transaction than @b and depending on algorithm either needs to wait for
+ * @b or die.
+ */
static inline bool __sched
__ww_ctx_stamp_after(struct ww_acquire_ctx *a, struct ww_acquire_ctx *b)
{
- return a->stamp - b->stamp <= LONG_MAX &&
- (a->stamp != b->stamp || a > b);
+
+ return (signed long)(a->stamp - b->stamp) > 0;
+}
+
+/*
+ * Wait-Die; wake a younger waiter context (when locks held) such that it can
+ * die.
+ *
+ * Among waiters with context, only the first one can have other locks acquired
+ * already (ctx->acquired > 0), because __ww_mutex_add_waiter() and
+ * __ww_mutex_check_kill() wake any but the earliest context.
+ */
+static bool __sched
+__ww_mutex_die(struct mutex *lock, struct mutex_waiter *waiter,
+ struct ww_acquire_ctx *ww_ctx)
+{
+ if (!ww_ctx->is_wait_die)
+ return false;
+
+ if (waiter->ww_ctx->acquired > 0 &&
+ __ww_ctx_stamp_after(waiter->ww_ctx, ww_ctx)) {
+ debug_mutex_wake_waiter(lock, waiter);
+ wake_up_process(waiter->task);
+ }
+
+ return true;
+}
+
+/*
+ * Wound-Wait; wound a younger @hold_ctx if it holds the lock.
+ *
+ * Wound the lock holder if there are waiters with older transactions than
+ * the lock holders. Even if multiple waiters may wound the lock holder,
+ * it's sufficient that only one does.
+ */
+static bool __ww_mutex_wound(struct mutex *lock,
+ struct ww_acquire_ctx *ww_ctx,
+ struct ww_acquire_ctx *hold_ctx)
+{
+ struct task_struct *owner = __mutex_owner(lock);
+
+ lockdep_assert_held(&lock->wait_lock);
+
+ /*
+ * Possible through __ww_mutex_add_waiter() when we race with
+ * ww_mutex_set_context_fastpath(). In that case we'll get here again
+ * through __ww_mutex_check_waiters().
+ */
+ if (!hold_ctx)
+ return false;
+
+ /*
+ * Can have !owner because of __mutex_unlock_slowpath(), but if owner,
+ * it cannot go away because we'll have FLAG_WAITERS set and hold
+ * wait_lock.
+ */
+ if (!owner)
+ return false;
+
+ if (ww_ctx->acquired > 0 && __ww_ctx_stamp_after(hold_ctx, ww_ctx)) {
+ hold_ctx->wounded = 1;
+
+ /*
+ * wake_up_process() paired with set_current_state()
+ * inserts sufficient barriers to make sure @owner either sees
+ * it's wounded in __ww_mutex_lock_check_stamp() or has a
+ * wakeup pending to re-read the wounded state.
+ */
+ if (owner != current)
+ wake_up_process(owner);
+
+ return true;
+ }
+
+ return false;
}
/*
- * Wake up any waiters that may have to back off when the lock is held by the
- * given context.
+ * We just acquired @lock under @ww_ctx, if there are later contexts waiting
+ * behind us on the wait-list, check if they need to die, or wound us.
*
- * Due to the invariants on the wait list, this can only affect the first
- * waiter with a context.
+ * See __ww_mutex_add_waiter() for the list-order construction; basically the
+ * list is ordered by stamp, smallest (oldest) first.
+ *
+ * This relies on never mixing wait-die/wound-wait on the same wait-list;
+ * which is currently ensured by that being a ww_class property.
*
* The current task must not be on the wait list.
*/
static void __sched
-__ww_mutex_wakeup_for_backoff(struct mutex *lock, struct ww_acquire_ctx *ww_ctx)
+__ww_mutex_check_waiters(struct mutex *lock, struct ww_acquire_ctx *ww_ctx)
{
struct mutex_waiter *cur;
@@ -311,66 +424,51 @@ __ww_mutex_wakeup_for_backoff(struct mutex *lock, struct ww_acquire_ctx *ww_ctx)
if (!cur->ww_ctx)
continue;
- if (cur->ww_ctx->acquired > 0 &&
- __ww_ctx_stamp_after(cur->ww_ctx, ww_ctx)) {
- debug_mutex_wake_waiter(lock, cur);
- wake_up_process(cur->task);
- }
-
- break;
+ if (__ww_mutex_die(lock, cur, ww_ctx) ||
+ __ww_mutex_wound(lock, cur->ww_ctx, ww_ctx))
+ break;
}
}
/*
- * After acquiring lock with fastpath or when we lost out in contested
- * slowpath, set ctx and wake up any waiters so they can recheck.
+ * After acquiring lock with fastpath, where we do not hold wait_lock, set ctx
+ * and wake up any waiters so they can recheck.
*/
static __always_inline void
ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
{
ww_mutex_lock_acquired(lock, ctx);
- lock->ctx = ctx;
-
/*
* The lock->ctx update should be visible on all cores before
- * the atomic read is done, otherwise contended waiters might be
+ * the WAITERS check is done, otherwise contended waiters might be
* missed. The contended waiters will either see ww_ctx == NULL
* and keep spinning, or it will acquire wait_lock, add itself
* to waiter list and sleep.
*/
- smp_mb(); /* ^^^ */
+ smp_mb(); /* See comments above and below. */
/*
- * Check if lock is contended, if not there is nobody to wake up
+ * [W] ww->ctx = ctx [W] MUTEX_FLAG_WAITERS
+ * MB MB
+ * [R] MUTEX_FLAG_WAITERS [R] ww->ctx
+ *
+ * The memory barrier above pairs with the memory barrier in
+ * __ww_mutex_add_waiter() and makes sure we either observe ww->ctx
+ * and/or !empty list.
*/
if (likely(!(atomic_long_read(&lock->base.owner) & MUTEX_FLAG_WAITERS)))
return;
/*
- * Uh oh, we raced in fastpath, wake up everyone in this case,
- * so they can see the new lock->ctx.
+ * Uh oh, we raced in fastpath, check if any of the waiters need to
+ * die or wound us.
*/
spin_lock(&lock->base.wait_lock);
- __ww_mutex_wakeup_for_backoff(&lock->base, ctx);
+ __ww_mutex_check_waiters(&lock->base, ctx);
spin_unlock(&lock->base.wait_lock);
}
-/*
- * After acquiring lock in the slowpath set ctx.
- *
- * Unlike for the fast path, the caller ensures that waiters are woken up where
- * necessary.
- *
- * Callers must hold the mutex wait_lock.
- */
-static __always_inline void
-ww_mutex_set_context_slowpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
-{
- ww_mutex_lock_acquired(lock, ctx);
- lock->ctx = ctx;
-}
-
#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
static inline
@@ -646,37 +744,83 @@ void __sched ww_mutex_unlock(struct ww_mutex *lock)
}
EXPORT_SYMBOL(ww_mutex_unlock);
+
+static __always_inline int __sched
+__ww_mutex_kill(struct mutex *lock, struct ww_acquire_ctx *ww_ctx)
+{
+ if (ww_ctx->acquired > 0) {
+#ifdef CONFIG_DEBUG_MUTEXES
+ struct ww_mutex *ww;
+
+ ww = container_of(lock, struct ww_mutex, base);
+ DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock);
+ ww_ctx->contending_lock = ww;
+#endif
+ return -EDEADLK;
+ }
+
+ return 0;
+}
+
+
+/*
+ * Check the wound condition for the current lock acquire.
+ *
+ * Wound-Wait: If we're wounded, kill ourself.
+ *
+ * Wait-Die: If we're trying to acquire a lock already held by an older
+ * context, kill ourselves.
+ *
+ * Since __ww_mutex_add_waiter() orders the wait-list on stamp, we only have to
+ * look at waiters before us in the wait-list.
+ */
static inline int __sched
-__ww_mutex_lock_check_stamp(struct mutex *lock, struct mutex_waiter *waiter,
- struct ww_acquire_ctx *ctx)
+__ww_mutex_check_kill(struct mutex *lock, struct mutex_waiter *waiter,
+ struct ww_acquire_ctx *ctx)
{
struct ww_mutex *ww = container_of(lock, struct ww_mutex, base);
struct ww_acquire_ctx *hold_ctx = READ_ONCE(ww->ctx);
struct mutex_waiter *cur;
+ if (ctx->acquired == 0)
+ return 0;
+
+ if (!ctx->is_wait_die) {
+ if (ctx->wounded)
+ return __ww_mutex_kill(lock, ctx);
+
+ return 0;
+ }
+
if (hold_ctx && __ww_ctx_stamp_after(ctx, hold_ctx))
- goto deadlock;
+ return __ww_mutex_kill(lock, ctx);
/*
* If there is a waiter in front of us that has a context, then its
- * stamp is earlier than ours and we must back off.
+ * stamp is earlier than ours and we must kill ourself.
*/
cur = waiter;
list_for_each_entry_continue_reverse(cur, &lock->wait_list, list) {
- if (cur->ww_ctx)
- goto deadlock;
+ if (!cur->ww_ctx)
+ continue;
+
+ return __ww_mutex_kill(lock, ctx);
}
return 0;
-
-deadlock:
-#ifdef CONFIG_DEBUG_MUTEXES
- DEBUG_LOCKS_WARN_ON(ctx->contending_lock);
- ctx->contending_lock = ww;
-#endif
- return -EDEADLK;
}
+/*
+ * Add @waiter to the wait-list, keep the wait-list ordered by stamp, smallest
+ * first. Such that older contexts are preferred to acquire the lock over
+ * younger contexts.
+ *
+ * Waiters without context are interspersed in FIFO order.
+ *
+ * Furthermore, for Wait-Die kill ourself immediately when possible (there are
+ * older contexts already waiting) to avoid unnecessary waiting and for
+ * Wound-Wait ensure we wound the owning context when it is younger.
+ */
static inline int __sched
__ww_mutex_add_waiter(struct mutex_waiter *waiter,
struct mutex *lock,
@@ -684,16 +828,21 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter,
{
struct mutex_waiter *cur;
struct list_head *pos;
+ bool is_wait_die;
if (!ww_ctx) {
- list_add_tail(&waiter->list, &lock->wait_list);
+ __mutex_add_waiter(lock, waiter, &lock->wait_list);
return 0;
}
+ is_wait_die = ww_ctx->is_wait_die;
+
/*
* Add the waiter before the first waiter with a higher stamp.
* Waiters without a context are skipped to avoid starving
- * them.
+ * them. Wait-Die waiters may die here. Wound-Wait waiters
+ * never die here, but they are sorted in stamp order and
+ * may wound the lock holder.
*/
pos = &lock->wait_list;
list_for_each_entry_reverse(cur, &lock->wait_list, list) {
@@ -701,16 +850,16 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter,
continue;
if (__ww_ctx_stamp_after(ww_ctx, cur->ww_ctx)) {
- /* Back off immediately if necessary. */
- if (ww_ctx->acquired > 0) {
-#ifdef CONFIG_DEBUG_MUTEXES
- struct ww_mutex *ww;
-
- ww = container_of(lock, struct ww_mutex, base);
- DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock);
- ww_ctx->contending_lock = ww;
-#endif
- return -EDEADLK;
+ /*
+ * Wait-Die: if we find an older context waiting, there
+ * is no point in queueing behind it, as we'd have to
+ * die the moment it would acquire the lock.
+ */
+ if (is_wait_die) {
+ int ret = __ww_mutex_kill(lock, ww_ctx);
+
+ if (ret)
+ return ret;
}
break;
@@ -718,17 +867,28 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter,
pos = &cur->list;
+ /* Wait-Die: ensure younger waiters die. */
+ __ww_mutex_die(lock, cur, ww_ctx);
+ }
+
+ __mutex_add_waiter(lock, waiter, pos);
+
+ /*
+ * Wound-Wait: if we're blocking on a mutex owned by a younger context,
+ * wound that such that we might proceed.
+ */
+ if (!is_wait_die) {
+ struct ww_mutex *ww = container_of(lock, struct ww_mutex, base);
+
/*
- * Wake up the waiter so that it gets a chance to back
- * off.
+ * See ww_mutex_set_context_fastpath(). Orders setting
+ * MUTEX_FLAG_WAITERS vs the ww->ctx load,
+ * such that either we or the fastpath will wound @ww->ctx.
*/
- if (cur->ww_ctx->acquired > 0) {
- debug_mutex_wake_waiter(lock, cur);
- wake_up_process(cur->task);
- }
+ smp_mb();
+ __ww_mutex_wound(lock, ww_ctx, ww->ctx);
}
- list_add_tail(&waiter->list, pos);
return 0;
}
@@ -751,6 +911,14 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
if (use_ww_ctx && ww_ctx) {
if (unlikely(ww_ctx == READ_ONCE(ww->ctx)))
return -EALREADY;
+
+ /*
+ * Reset the wounded flag after a kill. No other process can
+ * race and wound us here since they can't have a valid owner
+ * pointer if we don't have any locks held.
+ */
+ if (ww_ctx->acquired == 0)
+ ww_ctx->wounded = 0;
}
preempt_disable();
@@ -772,7 +940,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
*/
if (__mutex_trylock(lock)) {
if (use_ww_ctx && ww_ctx)
- __ww_mutex_wakeup_for_backoff(lock, ww_ctx);
+ __ww_mutex_check_waiters(lock, ww_ctx);
goto skip_wait;
}
@@ -784,25 +952,26 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
if (!use_ww_ctx) {
/* add waiting tasks to the end of the waitqueue (FIFO): */
- list_add_tail(&waiter.list, &lock->wait_list);
+ __mutex_add_waiter(lock, &waiter, &lock->wait_list);
+
#ifdef CONFIG_DEBUG_MUTEXES
waiter.ww_ctx = MUTEX_POISON_WW_CTX;
#endif
} else {
- /* Add in stamp order, waking up waiters that must back off. */
+ /*
+ * Add in stamp order, waking up waiters that must kill
+ * themselves.
+ */
ret = __ww_mutex_add_waiter(&waiter, lock, ww_ctx);
if (ret)
- goto err_early_backoff;
+ goto err_early_kill;
waiter.ww_ctx = ww_ctx;
}
waiter.task = current;
- if (__mutex_waiter_is_first(lock, &waiter))
- __mutex_set_flag(lock, MUTEX_FLAG_WAITERS);
-
set_current_state(state);
for (;;) {
/*
@@ -815,7 +984,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
goto acquired;
/*
- * Check for signals and wound conditions while holding
+ * Check for signals and kill conditions while holding
* wait_lock. This ensures the lock cancellation is ordered
* against mutex_unlock() and wake-ups do not go missing.
*/
@@ -824,8 +993,8 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
goto err;
}
- if (use_ww_ctx && ww_ctx && ww_ctx->acquired > 0) {
- ret = __ww_mutex_lock_check_stamp(lock, &waiter, ww_ctx);
+ if (use_ww_ctx && ww_ctx) {
+ ret = __ww_mutex_check_kill(lock, &waiter, ww_ctx);
if (ret)
goto err;
}
@@ -859,6 +1028,16 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
acquired:
__set_current_state(TASK_RUNNING);
+ if (use_ww_ctx && ww_ctx) {
+ /*
+ * Wound-Wait; we stole the lock (!first_waiter), check the
+ * waiters as anyone might want to wound us.
+ */
+ if (!ww_ctx->is_wait_die &&
+ !__mutex_waiter_is_first(lock, &waiter))
+ __ww_mutex_check_waiters(lock, ww_ctx);
+ }
+
mutex_remove_waiter(lock, &waiter, current);
if (likely(list_empty(&lock->wait_list)))
__mutex_clear_flag(lock, MUTEX_FLAGS);
@@ -870,7 +1049,7 @@ skip_wait:
lock_acquired(&lock->dep_map, ip);
if (use_ww_ctx && ww_ctx)
- ww_mutex_set_context_slowpath(ww, ww_ctx);
+ ww_mutex_lock_acquired(ww, ww_ctx);
spin_unlock(&lock->wait_lock);
preempt_enable();
@@ -879,7 +1058,7 @@ skip_wait:
err:
__set_current_state(TASK_RUNNING);
mutex_remove_waiter(lock, &waiter, current);
-err_early_backoff:
+err_early_kill:
spin_unlock(&lock->wait_lock);
debug_mutex_free_waiter(&waiter);
mutex_release(&lock->dep_map, 1, ip);
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 4f014be7a4b8..2823d4163a37 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1465,6 +1465,29 @@ rt_mutex_fastunlock(struct rt_mutex *lock,
rt_mutex_postunlock(&wake_q);
}
+static inline void __rt_mutex_lock(struct rt_mutex *lock, unsigned int subclass)
+{
+ might_sleep();
+
+ mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
+ rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock);
+}
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+/**
+ * rt_mutex_lock_nested - lock a rt_mutex
+ *
+ * @lock: the rt_mutex to be locked
+ * @subclass: the lockdep subclass
+ */
+void __sched rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass)
+{
+ __rt_mutex_lock(lock, subclass);
+}
+EXPORT_SYMBOL_GPL(rt_mutex_lock_nested);
+#endif
+
+#ifndef CONFIG_DEBUG_LOCK_ALLOC
/**
* rt_mutex_lock - lock a rt_mutex
*
@@ -1472,12 +1495,10 @@ rt_mutex_fastunlock(struct rt_mutex *lock,
*/
void __sched rt_mutex_lock(struct rt_mutex *lock)
{
- might_sleep();
-
- mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_);
- rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock);
+ __rt_mutex_lock(lock, 0);
}
EXPORT_SYMBOL_GPL(rt_mutex_lock);
+#endif
/**
* rt_mutex_lock_interruptible - lock a rt_mutex interruptible
diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c
index 0e4cd64ad2c0..5b915b370d5a 100644
--- a/kernel/locking/test-ww_mutex.c
+++ b/kernel/locking/test-ww_mutex.c
@@ -26,7 +26,7 @@
#include <linux/slab.h>
#include <linux/ww_mutex.h>
-static DEFINE_WW_CLASS(ww_class);
+static DEFINE_WD_CLASS(ww_class);
struct workqueue_struct *wq;
struct test_mutex {
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 5857267a4af5..1f87ea6b6545 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -5,6 +5,7 @@
#include <linux/types.h>
#include <linux/pfn_t.h>
#include <linux/io.h>
+#include <linux/kasan.h>
#include <linux/mm.h>
#include <linux/memory_hotplug.h>
#include <linux/swap.h>
@@ -137,6 +138,7 @@ static void devm_memremap_pages_release(void *data)
mem_hotplug_begin();
arch_remove_memory(align_start, align_size, pgmap->altmap_valid ?
&pgmap->altmap : NULL);
+ kasan_remove_zero_shadow(__va(align_start), align_size);
mem_hotplug_done();
untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
@@ -176,10 +178,27 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
unsigned long pfn, pgoff, order;
pgprot_t pgprot = PAGE_KERNEL;
int error, nid, is_ram;
+ struct dev_pagemap *conflict_pgmap;
align_start = res->start & ~(SECTION_SIZE - 1);
align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
- align_start;
+ align_end = align_start + align_size - 1;
+
+ conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_start), NULL);
+ if (conflict_pgmap) {
+ dev_WARN(dev, "Conflicting mapping in same section\n");
+ put_dev_pagemap(conflict_pgmap);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_end), NULL);
+ if (conflict_pgmap) {
+ dev_WARN(dev, "Conflicting mapping in same section\n");
+ put_dev_pagemap(conflict_pgmap);
+ return ERR_PTR(-ENOMEM);
+ }
+
is_ram = region_intersects(align_start, align_size,
IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
@@ -199,7 +218,6 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
mutex_lock(&pgmap_lock);
error = 0;
- align_end = align_start + align_size - 1;
foreach_order_pgoff(res, order, pgoff) {
error = __radix_tree_insert(&pgmap_radix,
@@ -223,6 +241,12 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
goto err_pfn_remap;
mem_hotplug_begin();
+ error = kasan_add_zero_shadow(__va(align_start), align_size);
+ if (error) {
+ mem_hotplug_done();
+ goto err_kasan;
+ }
+
error = arch_add_memory(nid, align_start, align_size, altmap, false);
if (!error)
move_pfn_range_to_zone(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
@@ -251,6 +275,8 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
return __va(res->start);
err_add_memory:
+ kasan_remove_zero_shadow(__va(align_start), align_size);
+ err_kasan:
untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
err_pfn_remap:
err_radix:
@@ -305,7 +331,7 @@ EXPORT_SYMBOL_GPL(get_dev_pagemap);
#ifdef CONFIG_DEV_PAGEMAP_OPS
DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
-EXPORT_SYMBOL_GPL(devmap_managed_key);
+EXPORT_SYMBOL(devmap_managed_key);
static atomic_t devmap_enable;
/*
@@ -346,5 +372,5 @@ void __put_devmap_managed_page(struct page *page)
} else if (!count)
__put_page(page);
}
-EXPORT_SYMBOL_GPL(__put_devmap_managed_page);
+EXPORT_SYMBOL(__put_devmap_managed_page);
#endif /* CONFIG_DEV_PAGEMAP_OPS */
diff --git a/kernel/module-internal.h b/kernel/module-internal.h
index 915e123a430f..79c9be2dbbe9 100644
--- a/kernel/module-internal.h
+++ b/kernel/module-internal.h
@@ -9,4 +9,27 @@
* 2 of the Licence, or (at your option) any later version.
*/
-extern int mod_verify_sig(const void *mod, unsigned long *_modlen);
+#include <linux/elf.h>
+#include <asm/module.h>
+
+struct load_info {
+ const char *name;
+ /* pointer to module in temporary copy, freed at end of load_module() */
+ struct module *mod;
+ Elf_Ehdr *hdr;
+ unsigned long len;
+ Elf_Shdr *sechdrs;
+ char *secstrings, *strtab;
+ unsigned long symoffs, stroffs;
+ struct _ddebug *debug;
+ unsigned int num_debug;
+ bool sig_ok;
+#ifdef CONFIG_KALLSYMS
+ unsigned long mod_kallsyms_init_off;
+#endif
+ struct {
+ unsigned int sym, str, mod, vers, info, pcpu;
+ } index;
+};
+
+extern int mod_verify_sig(const void *mod, struct load_info *info);
diff --git a/kernel/module.c b/kernel/module.c
index f475f30eed8c..6746c85511fe 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -307,24 +307,6 @@ int unregister_module_notifier(struct notifier_block *nb)
}
EXPORT_SYMBOL(unregister_module_notifier);
-struct load_info {
- const char *name;
- Elf_Ehdr *hdr;
- unsigned long len;
- Elf_Shdr *sechdrs;
- char *secstrings, *strtab;
- unsigned long symoffs, stroffs;
- struct _ddebug *debug;
- unsigned int num_debug;
- bool sig_ok;
-#ifdef CONFIG_KALLSYMS
- unsigned long mod_kallsyms_init_off;
-#endif
- struct {
- unsigned int sym, str, mod, vers, info, pcpu;
- } index;
-};
-
/*
* We require a truly strong try_module_get(): 0 means success.
* Otherwise an error is returned due to ongoing or failed
@@ -547,12 +529,30 @@ static bool check_symbol(const struct symsearch *syms,
return true;
}
+static unsigned long kernel_symbol_value(const struct kernel_symbol *sym)
+{
+#ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS
+ return (unsigned long)offset_to_ptr(&sym->value_offset);
+#else
+ return sym->value;
+#endif
+}
+
+static const char *kernel_symbol_name(const struct kernel_symbol *sym)
+{
+#ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS
+ return offset_to_ptr(&sym->name_offset);
+#else
+ return sym->name;
+#endif
+}
+
static int cmp_name(const void *va, const void *vb)
{
const char *a;
const struct kernel_symbol *b;
a = va; b = vb;
- return strcmp(a, b->name);
+ return strcmp(a, kernel_symbol_name(b));
}
static bool find_symbol_in_section(const struct symsearch *syms,
@@ -1339,14 +1339,12 @@ static inline int check_modstruct_version(const struct load_info *info,
* locking is necessary -- use preempt_disable() to placate lockdep.
*/
preempt_disable();
- if (!find_symbol(VMLINUX_SYMBOL_STR(module_layout), NULL,
- &crc, true, false)) {
+ if (!find_symbol("module_layout", NULL, &crc, true, false)) {
preempt_enable();
BUG();
}
preempt_enable();
- return check_version(info, VMLINUX_SYMBOL_STR(module_layout),
- mod, crc);
+ return check_version(info, "module_layout", mod, crc);
}
/* First part is kernel version, which we ignore if module has crcs. */
@@ -2059,21 +2057,19 @@ static int copy_module_elf(struct module *mod, struct load_info *info)
/* Elf section header table */
size = sizeof(*info->sechdrs) * info->hdr->e_shnum;
- mod->klp_info->sechdrs = kmalloc(size, GFP_KERNEL);
+ mod->klp_info->sechdrs = kmemdup(info->sechdrs, size, GFP_KERNEL);
if (mod->klp_info->sechdrs == NULL) {
ret = -ENOMEM;
goto free_info;
}
- memcpy(mod->klp_info->sechdrs, info->sechdrs, size);
/* Elf section name string table */
size = info->sechdrs[info->hdr->e_shstrndx].sh_size;
- mod->klp_info->secstrings = kmalloc(size, GFP_KERNEL);
+ mod->klp_info->secstrings = kmemdup(info->secstrings, size, GFP_KERNEL);
if (mod->klp_info->secstrings == NULL) {
ret = -ENOMEM;
goto free_sechdrs;
}
- memcpy(mod->klp_info->secstrings, info->secstrings, size);
/* Elf symbol section index */
symndx = info->index.sym;
@@ -2192,7 +2188,7 @@ void *__symbol_get(const char *symbol)
sym = NULL;
preempt_enable();
- return sym ? (void *)sym->value : NULL;
+ return sym ? (void *)kernel_symbol_value(sym) : NULL;
}
EXPORT_SYMBOL_GPL(__symbol_get);
@@ -2222,10 +2218,12 @@ static int verify_export_symbols(struct module *mod)
for (i = 0; i < ARRAY_SIZE(arr); i++) {
for (s = arr[i].sym; s < arr[i].sym + arr[i].num; s++) {
- if (find_symbol(s->name, &owner, NULL, true, false)) {
+ if (find_symbol(kernel_symbol_name(s), &owner, NULL,
+ true, false)) {
pr_err("%s: exports duplicate symbol %s"
" (owned by %s)\n",
- mod->name, s->name, module_name(owner));
+ mod->name, kernel_symbol_name(s),
+ module_name(owner));
return -ENOEXEC;
}
}
@@ -2274,7 +2272,7 @@ static int simplify_symbols(struct module *mod, const struct load_info *info)
ksym = resolve_symbol_wait(mod, info, name);
/* Ok if resolved. */
if (ksym && !IS_ERR(ksym)) {
- sym[i].st_value = ksym->value;
+ sym[i].st_value = kernel_symbol_value(ksym);
break;
}
@@ -2282,9 +2280,9 @@ static int simplify_symbols(struct module *mod, const struct load_info *info)
if (!ksym && ELF_ST_BIND(sym[i].st_info) == STB_WEAK)
break;
- pr_warn("%s: Unknown symbol %s (err %li)\n",
- mod->name, name, PTR_ERR(ksym));
ret = PTR_ERR(ksym) ?: -ENOENT;
+ pr_warn("%s: Unknown symbol %s (err %d)\n",
+ mod->name, name, ret);
break;
default:
@@ -2486,7 +2484,11 @@ static char *get_modinfo(struct load_info *info, const char *tag)
Elf_Shdr *infosec = &info->sechdrs[info->index.info];
unsigned long size = infosec->sh_size;
- for (p = (char *)infosec->sh_addr; p; p = next_string(p, &size)) {
+ /*
+ * get_modinfo() calls made before rewrite_section_headers()
+ * must use sh_offset, as sh_addr isn't set!
+ */
+ for (p = (char *)info->hdr + infosec->sh_offset; p; p = next_string(p, &size)) {
if (strncmp(p, tag, taglen) == 0 && p[taglen] == '=')
return p + taglen + 1;
}
@@ -2534,7 +2536,7 @@ static int is_exported(const char *name, unsigned long value,
ks = lookup_symbol(name, __start___ksymtab, __stop___ksymtab);
else
ks = lookup_symbol(name, mod->syms, mod->syms + mod->num_syms);
- return ks != NULL && ks->value == value;
+ return ks != NULL && kernel_symbol_value(ks) == value;
}
/* As per nm */
@@ -2774,7 +2776,7 @@ static int module_sig_check(struct load_info *info, int flags)
memcmp(mod + info->len - markerlen, MODULE_SIG_STRING, markerlen) == 0) {
/* We truncate the module to discard the signature */
info->len -= markerlen;
- err = mod_verify_sig(mod, &info->len);
+ err = mod_verify_sig(mod, info);
}
if (!err) {
@@ -2876,7 +2878,7 @@ static int copy_module_from_user(const void __user *umod, unsigned long len,
if (info->len < sizeof(*(info->hdr)))
return -ENOEXEC;
- err = security_kernel_read_file(NULL, READING_MODULE);
+ err = security_kernel_load_data(LOADING_MODULE);
if (err)
return err;
@@ -2926,17 +2928,7 @@ static int rewrite_section_headers(struct load_info *info, int flags)
}
/* Track but don't keep modinfo and version sections. */
- if (flags & MODULE_INIT_IGNORE_MODVERSIONS)
- info->index.vers = 0; /* Pretend no __versions section! */
- else
- info->index.vers = find_sec(info, "__versions");
info->sechdrs[info->index.vers].sh_flags &= ~(unsigned long)SHF_ALLOC;
-
- info->index.info = find_sec(info, ".modinfo");
- if (!info->index.info)
- info->name = "(missing .modinfo section)";
- else
- info->name = get_modinfo(info, "name");
info->sechdrs[info->index.info].sh_flags &= ~(unsigned long)SHF_ALLOC;
return 0;
@@ -2947,23 +2939,24 @@ static int rewrite_section_headers(struct load_info *info, int flags)
* search for module section index etc), and do some basic section
* verification.
*
- * Return the temporary module pointer (we'll replace it with the final
- * one when we move the module sections around).
+ * Set info->mod to the temporary copy of the module in info->hdr. The final one
+ * will be allocated in move_module().
*/
-static struct module *setup_load_info(struct load_info *info, int flags)
+static int setup_load_info(struct load_info *info, int flags)
{
unsigned int i;
- int err;
- struct module *mod;
/* Set up the convenience variables */
info->sechdrs = (void *)info->hdr + info->hdr->e_shoff;
info->secstrings = (void *)info->hdr
+ info->sechdrs[info->hdr->e_shstrndx].sh_offset;
- err = rewrite_section_headers(info, flags);
- if (err)
- return ERR_PTR(err);
+ /* Try to find a name early so we can log errors with a module name */
+ info->index.info = find_sec(info, ".modinfo");
+ if (!info->index.info)
+ info->name = "(missing .modinfo section)";
+ else
+ info->name = get_modinfo(info, "name");
/* Find internal symbols and strings. */
for (i = 1; i < info->hdr->e_shnum; i++) {
@@ -2976,34 +2969,35 @@ static struct module *setup_load_info(struct load_info *info, int flags)
}
}
+ if (info->index.sym == 0) {
+ pr_warn("%s: module has no symbols (stripped?)\n", info->name);
+ return -ENOEXEC;
+ }
+
info->index.mod = find_sec(info, ".gnu.linkonce.this_module");
if (!info->index.mod) {
pr_warn("%s: No module found in object\n",
info->name ?: "(missing .modinfo name field)");
- return ERR_PTR(-ENOEXEC);
+ return -ENOEXEC;
}
/* This is temporary: point mod into copy of data. */
- mod = (void *)info->sechdrs[info->index.mod].sh_addr;
+ info->mod = (void *)info->hdr + info->sechdrs[info->index.mod].sh_offset;
/*
- * If we didn't load the .modinfo 'name' field, fall back to
+ * If we didn't load the .modinfo 'name' field earlier, fall back to
* on-disk struct mod 'name' field.
*/
if (!info->name)
- info->name = mod->name;
+ info->name = info->mod->name;
- if (info->index.sym == 0) {
- pr_warn("%s: module has no symbols (stripped?)\n", info->name);
- return ERR_PTR(-ENOEXEC);
- }
+ if (flags & MODULE_INIT_IGNORE_MODVERSIONS)
+ info->index.vers = 0; /* Pretend no __versions section! */
+ else
+ info->index.vers = find_sec(info, "__versions");
info->index.pcpu = find_pcpusec(info);
- /* Check module struct version now, before we try to use module. */
- if (!check_modstruct_version(info, mod))
- return ERR_PTR(-ENOEXEC);
-
- return mod;
+ return 0;
}
static int check_modinfo(struct module *mod, struct load_info *info, int flags)
@@ -3298,25 +3292,17 @@ core_param(module_blacklist, module_blacklist, charp, 0400);
static struct module *layout_and_allocate(struct load_info *info, int flags)
{
- /* Module within temporary copy. */
struct module *mod;
unsigned int ndx;
int err;
- mod = setup_load_info(info, flags);
- if (IS_ERR(mod))
- return mod;
-
- if (blacklisted(info->name))
- return ERR_PTR(-EPERM);
-
- err = check_modinfo(mod, info, flags);
+ err = check_modinfo(info->mod, info, flags);
if (err)
return ERR_PTR(err);
/* Allow arches to frob section contents and sizes. */
err = module_frob_arch_sections(info->hdr, info->sechdrs,
- info->secstrings, mod);
+ info->secstrings, info->mod);
if (err < 0)
return ERR_PTR(err);
@@ -3335,11 +3321,11 @@ static struct module *layout_and_allocate(struct load_info *info, int flags)
/* Determine total sizes, and put offsets in sh_entsize. For now
this is done generically; there doesn't appear to be any
special cases for the architectures. */
- layout_sections(mod, info);
- layout_symtab(mod, info);
+ layout_sections(info->mod, info);
+ layout_symtab(info->mod, info);
/* Allocate and move to the final place */
- err = move_module(mod, info);
+ err = move_module(info->mod, info);
if (err)
return ERR_PTR(err);
@@ -3657,17 +3643,36 @@ static int load_module(struct load_info *info, const char __user *uargs,
int flags)
{
struct module *mod;
- long err;
+ long err = 0;
char *after_dashes;
+ err = elf_header_check(info);
+ if (err)
+ goto free_copy;
+
+ err = setup_load_info(info, flags);
+ if (err)
+ goto free_copy;
+
+ if (blacklisted(info->name)) {
+ err = -EPERM;
+ goto free_copy;
+ }
+
err = module_sig_check(info, flags);
if (err)
goto free_copy;
- err = elf_header_check(info);
+ err = rewrite_section_headers(info, flags);
if (err)
goto free_copy;
+ /* Check module struct version now, before we try to use module. */
+ if (!check_modstruct_version(info, info->mod)) {
+ err = -ENOEXEC;
+ goto free_copy;
+ }
+
/* Figure out module layout, and allocate all the memory. */
mod = layout_and_allocate(info, flags);
if (IS_ERR(mod)) {
@@ -4067,7 +4072,7 @@ static unsigned long mod_find_symname(struct module *mod, const char *name)
for (i = 0; i < kallsyms->num_symtab; i++)
if (strcmp(name, symname(kallsyms, i)) == 0 &&
- kallsyms->symtab[i].st_info != 'U')
+ kallsyms->symtab[i].st_shndx != SHN_UNDEF)
return kallsyms->symtab[i].st_value;
return 0;
}
@@ -4113,6 +4118,10 @@ int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *,
if (mod->state == MODULE_STATE_UNFORMED)
continue;
for (i = 0; i < kallsyms->num_symtab; i++) {
+
+ if (kallsyms->symtab[i].st_shndx == SHN_UNDEF)
+ continue;
+
ret = fn(data, symname(kallsyms, i),
mod, kallsyms->symtab[i].st_value);
if (ret != 0)
diff --git a/kernel/module_signing.c b/kernel/module_signing.c
index 937c844bee4a..f2075ce8e4b3 100644
--- a/kernel/module_signing.c
+++ b/kernel/module_signing.c
@@ -45,10 +45,10 @@ struct module_signature {
/*
* Verify the signature on a module.
*/
-int mod_verify_sig(const void *mod, unsigned long *_modlen)
+int mod_verify_sig(const void *mod, struct load_info *info)
{
struct module_signature ms;
- size_t modlen = *_modlen, sig_len;
+ size_t sig_len, modlen = info->len;
pr_devel("==>%s(,%zu)\n", __func__, modlen);
@@ -62,10 +62,11 @@ int mod_verify_sig(const void *mod, unsigned long *_modlen)
if (sig_len >= modlen)
return -EBADMSG;
modlen -= sig_len;
- *_modlen = modlen;
+ info->len = modlen;
if (ms.id_type != PKEY_ID_PKCS7) {
- pr_err("Module is not signed with expected PKCS#7 message\n");
+ pr_err("%s: Module is not signed with expected PKCS#7 message\n",
+ info->name);
return -ENOPKG;
}
@@ -76,7 +77,8 @@ int mod_verify_sig(const void *mod, unsigned long *_modlen)
ms.__pad[0] != 0 ||
ms.__pad[1] != 0 ||
ms.__pad[2] != 0) {
- pr_err("PKCS#7 signature info has unexpected non-zero params\n");
+ pr_err("%s: PKCS#7 signature info has unexpected non-zero params\n",
+ info->name);
return -EBADMSG;
}
diff --git a/kernel/pid.c b/kernel/pid.c
index 157fe4b19971..de1cfc4f75a2 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -265,27 +265,33 @@ struct pid *find_vpid(int nr)
}
EXPORT_SYMBOL_GPL(find_vpid);
+static struct pid **task_pid_ptr(struct task_struct *task, enum pid_type type)
+{
+ return (type == PIDTYPE_PID) ?
+ &task->thread_pid :
+ &task->signal->pids[type];
+}
+
/*
* attach_pid() must be called with the tasklist_lock write-held.
*/
void attach_pid(struct task_struct *task, enum pid_type type)
{
- struct pid_link *link = &task->pids[type];
- hlist_add_head_rcu(&link->node, &link->pid->tasks[type]);
+ struct pid *pid = *task_pid_ptr(task, type);
+ hlist_add_head_rcu(&task->pid_links[type], &pid->tasks[type]);
}
static void __change_pid(struct task_struct *task, enum pid_type type,
struct pid *new)
{
- struct pid_link *link;
+ struct pid **pid_ptr = task_pid_ptr(task, type);
struct pid *pid;
int tmp;
- link = &task->pids[type];
- pid = link->pid;
+ pid = *pid_ptr;
- hlist_del_rcu(&link->node);
- link->pid = new;
+ hlist_del_rcu(&task->pid_links[type]);
+ *pid_ptr = new;
for (tmp = PIDTYPE_MAX; --tmp >= 0; )
if (!hlist_empty(&pid->tasks[tmp]))
@@ -310,8 +316,9 @@ void change_pid(struct task_struct *task, enum pid_type type,
void transfer_pid(struct task_struct *old, struct task_struct *new,
enum pid_type type)
{
- new->pids[type].pid = old->pids[type].pid;
- hlist_replace_rcu(&old->pids[type].node, &new->pids[type].node);
+ if (type == PIDTYPE_PID)
+ new->thread_pid = old->thread_pid;
+ hlist_replace_rcu(&old->pid_links[type], &new->pid_links[type]);
}
struct task_struct *pid_task(struct pid *pid, enum pid_type type)
@@ -322,7 +329,7 @@ struct task_struct *pid_task(struct pid *pid, enum pid_type type)
first = rcu_dereference_check(hlist_first_rcu(&pid->tasks[type]),
lockdep_tasklist_lock_is_held());
if (first)
- result = hlist_entry(first, struct task_struct, pids[(type)].node);
+ result = hlist_entry(first, struct task_struct, pid_links[(type)]);
}
return result;
}
@@ -360,9 +367,7 @@ struct pid *get_task_pid(struct task_struct *task, enum pid_type type)
{
struct pid *pid;
rcu_read_lock();
- if (type != PIDTYPE_PID)
- task = task->group_leader;
- pid = get_pid(rcu_dereference(task->pids[type].pid));
+ pid = get_pid(rcu_dereference(*task_pid_ptr(task, type)));
rcu_read_unlock();
return pid;
}
@@ -420,15 +425,8 @@ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
rcu_read_lock();
if (!ns)
ns = task_active_pid_ns(current);
- if (likely(pid_alive(task))) {
- if (type != PIDTYPE_PID) {
- if (type == __PIDTYPE_TGID)
- type = PIDTYPE_PID;
-
- task = task->group_leader;
- }
- nr = pid_nr_ns(rcu_dereference(task->pids[type].pid), ns);
- }
+ if (likely(pid_alive(task)))
+ nr = pid_nr_ns(rcu_dereference(*task_pid_ptr(task, type)), ns);
rcu_read_unlock();
return nr;
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index e880ca22c5a5..3a6c2f87699e 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -105,6 +105,7 @@ config PM_SLEEP
def_bool y
depends on SUSPEND || HIBERNATE_CALLBACKS
select PM
+ select SRCU
config PM_SLEEP_SMP
def_bool y
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 9c85c7822383..abef759de7c8 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -338,7 +338,7 @@ static int create_image(int platform_mode)
* hibernation_snapshot - Quiesce devices and create a hibernation image.
* @platform_mode: If set, use platform driver to prepare for the transition.
*
- * This routine must be called with pm_mutex held.
+ * This routine must be called with system_transition_mutex held.
*/
int hibernation_snapshot(int platform_mode)
{
@@ -500,8 +500,9 @@ static int resume_target_kernel(bool platform_mode)
* hibernation_restore - Quiesce devices and restore from a hibernation image.
* @platform_mode: If set, use platform driver to prepare for the transition.
*
- * This routine must be called with pm_mutex held. If it is successful, control
- * reappears in the restored target kernel in hibernation_snapshot().
+ * This routine must be called with system_transition_mutex held. If it is
+ * successful, control reappears in the restored target kernel in
+ * hibernation_snapshot().
*/
int hibernation_restore(int platform_mode)
{
@@ -638,6 +639,7 @@ static void power_down(void)
break;
case HIBERNATION_PLATFORM:
hibernation_platform_enter();
+ /* Fall through */
case HIBERNATION_SHUTDOWN:
if (pm_power_off)
kernel_power_off();
@@ -805,13 +807,13 @@ static int software_resume(void)
* name_to_dev_t() below takes a sysfs buffer mutex when sysfs
* is configured into the kernel. Since the regular hibernate
* trigger path is via sysfs which takes a buffer mutex before
- * calling hibernate functions (which take pm_mutex) this can
- * cause lockdep to complain about a possible ABBA deadlock
+ * calling hibernate functions (which take system_transition_mutex)
+ * this can cause lockdep to complain about a possible ABBA deadlock
* which cannot happen since we're in the boot code here and
* sysfs can't be invoked yet. Therefore, we use a subclass
* here to avoid lockdep complaining.
*/
- mutex_lock_nested(&pm_mutex, SINGLE_DEPTH_NESTING);
+ mutex_lock_nested(&system_transition_mutex, SINGLE_DEPTH_NESTING);
if (swsusp_resume_device)
goto Check_image;
@@ -899,7 +901,7 @@ static int software_resume(void)
atomic_inc(&snapshot_device_available);
/* For success case, the suspend path will release the lock */
Unlock:
- mutex_unlock(&pm_mutex);
+ mutex_unlock(&system_transition_mutex);
pm_pr_dbg("Hibernation image not present or could not be loaded.\n");
return error;
Close_Finish:
diff --git a/kernel/power/main.c b/kernel/power/main.c
index d9706da10930..35b50823d83b 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -15,17 +15,16 @@
#include <linux/workqueue.h>
#include <linux/debugfs.h>
#include <linux/seq_file.h>
+#include <linux/suspend.h>
#include "power.h"
-DEFINE_MUTEX(pm_mutex);
-
#ifdef CONFIG_PM_SLEEP
void lock_system_sleep(void)
{
current->flags |= PF_FREEZER_SKIP;
- mutex_lock(&pm_mutex);
+ mutex_lock(&system_transition_mutex);
}
EXPORT_SYMBOL_GPL(lock_system_sleep);
@@ -37,8 +36,9 @@ void unlock_system_sleep(void)
*
* Reason:
* Fundamentally, we just don't need it, because freezing condition
- * doesn't come into effect until we release the pm_mutex lock,
- * since the freezer always works with pm_mutex held.
+ * doesn't come into effect until we release the
+ * system_transition_mutex lock, since the freezer always works with
+ * system_transition_mutex held.
*
* More importantly, in the case of hibernation,
* unlock_system_sleep() gets called in snapshot_read() and
@@ -47,7 +47,7 @@ void unlock_system_sleep(void)
* enter the refrigerator, thus causing hibernation to lockup.
*/
current->flags &= ~PF_FREEZER_SKIP;
- mutex_unlock(&pm_mutex);
+ mutex_unlock(&system_transition_mutex);
}
EXPORT_SYMBOL_GPL(unlock_system_sleep);
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 87331565e505..5342f6fc022e 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -92,7 +92,7 @@ static void s2idle_enter(void)
/* Push all the CPUs into the idle loop. */
wake_up_all_idle_cpus();
/* Make the current CPU wait so it can enter the idle loop too. */
- swait_event(s2idle_wait_head,
+ swait_event_exclusive(s2idle_wait_head,
s2idle_state == S2IDLE_STATE_WAKE);
cpuidle_pause();
@@ -160,7 +160,7 @@ void s2idle_wake(void)
raw_spin_lock_irqsave(&s2idle_lock, flags);
if (s2idle_state > S2IDLE_STATE_NONE) {
s2idle_state = S2IDLE_STATE_WAKE;
- swake_up(&s2idle_wait_head);
+ swake_up_one(&s2idle_wait_head);
}
raw_spin_unlock_irqrestore(&s2idle_lock, flags);
}
@@ -556,7 +556,7 @@ static int enter_state(suspend_state_t state)
} else if (!valid_state(state)) {
return -EINVAL;
}
- if (!mutex_trylock(&pm_mutex))
+ if (!mutex_trylock(&system_transition_mutex))
return -EBUSY;
if (state == PM_SUSPEND_TO_IDLE)
@@ -590,7 +590,7 @@ static int enter_state(suspend_state_t state)
pm_pr_dbg("Finishing wakeup.\n");
suspend_finish();
Unlock:
- mutex_unlock(&pm_mutex);
+ mutex_unlock(&system_transition_mutex);
return error;
}
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index c2bcf97d24c8..d7f6c1a288d3 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -923,7 +923,7 @@ int swsusp_write(unsigned int flags)
}
memset(&snapshot, 0, sizeof(struct snapshot_handle));
error = snapshot_read_next(&snapshot);
- if (error < PAGE_SIZE) {
+ if (error < (int)PAGE_SIZE) {
if (error >= 0)
error = -EFAULT;
@@ -1483,7 +1483,7 @@ int swsusp_read(unsigned int *flags_p)
memset(&snapshot, 0, sizeof(struct snapshot_handle));
error = snapshot_write_next(&snapshot);
- if (error < PAGE_SIZE)
+ if (error < (int)PAGE_SIZE)
return error < 0 ? error : -EFAULT;
header = (struct swsusp_info *)data_of(snapshot);
error = get_swap_reader(&handle, flags_p);
diff --git a/kernel/power/user.c b/kernel/power/user.c
index abd225550271..2d8b60a3c86b 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -216,7 +216,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- if (!mutex_trylock(&pm_mutex))
+ if (!mutex_trylock(&system_transition_mutex))
return -EBUSY;
lock_device_hotplug();
@@ -394,7 +394,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
}
unlock_device_hotplug();
- mutex_unlock(&pm_mutex);
+ mutex_unlock(&system_transition_mutex);
return error;
}
diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h
index 2a7d04049af4..0f1898820cba 100644
--- a/kernel/printk/internal.h
+++ b/kernel/printk/internal.h
@@ -19,11 +19,16 @@
#ifdef CONFIG_PRINTK
#define PRINTK_SAFE_CONTEXT_MASK 0x3fffffff
-#define PRINTK_NMI_DEFERRED_CONTEXT_MASK 0x40000000
+#define PRINTK_NMI_DIRECT_CONTEXT_MASK 0x40000000
#define PRINTK_NMI_CONTEXT_MASK 0x80000000
extern raw_spinlock_t logbuf_lock;
+__printf(5, 0)
+int vprintk_store(int facility, int level,
+ const char *dict, size_t dictlen,
+ const char *fmt, va_list args);
+
__printf(1, 0) int vprintk_default(const char *fmt, va_list args);
__printf(1, 0) int vprintk_deferred(const char *fmt, va_list args);
__printf(1, 0) int vprintk_func(const char *fmt, va_list args);
@@ -54,6 +59,8 @@ void __printk_safe_exit(void);
local_irq_enable(); \
} while (0)
+void defer_console_output(void);
+
#else
__printf(1, 0) int vprintk_func(const char *fmt, va_list args) { return 0; }
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 247808333ba4..918f386b2f6e 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -349,7 +349,7 @@ static int console_msg_format = MSG_FORMAT_DEFAULT;
*/
enum log_flags {
- LOG_NOCONS = 1, /* already flushed, do not print to console */
+ LOG_NOCONS = 1, /* suppress print, do not print to console */
LOG_NEWLINE = 2, /* text ended with a newline */
LOG_PREFIX = 4, /* text started with a prefix */
LOG_CONT = 8, /* text is a fragment of a continuation line */
@@ -1352,71 +1352,68 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
{
char *text;
int len = 0;
+ u64 next_seq;
+ u64 seq;
+ u32 idx;
text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL);
if (!text)
return -ENOMEM;
logbuf_lock_irq();
- if (buf) {
- u64 next_seq;
- u64 seq;
- u32 idx;
+ /*
+ * Find first record that fits, including all following records,
+ * into the user-provided buffer for this dump.
+ */
+ seq = clear_seq;
+ idx = clear_idx;
+ while (seq < log_next_seq) {
+ struct printk_log *msg = log_from_idx(idx);
- /*
- * Find first record that fits, including all following records,
- * into the user-provided buffer for this dump.
- */
- seq = clear_seq;
- idx = clear_idx;
- while (seq < log_next_seq) {
- struct printk_log *msg = log_from_idx(idx);
-
- len += msg_print_text(msg, true, NULL, 0);
- idx = log_next(idx);
- seq++;
- }
+ len += msg_print_text(msg, true, NULL, 0);
+ idx = log_next(idx);
+ seq++;
+ }
- /* move first record forward until length fits into the buffer */
- seq = clear_seq;
- idx = clear_idx;
- while (len > size && seq < log_next_seq) {
- struct printk_log *msg = log_from_idx(idx);
+ /* move first record forward until length fits into the buffer */
+ seq = clear_seq;
+ idx = clear_idx;
+ while (len > size && seq < log_next_seq) {
+ struct printk_log *msg = log_from_idx(idx);
- len -= msg_print_text(msg, true, NULL, 0);
- idx = log_next(idx);
- seq++;
- }
+ len -= msg_print_text(msg, true, NULL, 0);
+ idx = log_next(idx);
+ seq++;
+ }
- /* last message fitting into this dump */
- next_seq = log_next_seq;
+ /* last message fitting into this dump */
+ next_seq = log_next_seq;
- len = 0;
- while (len >= 0 && seq < next_seq) {
- struct printk_log *msg = log_from_idx(idx);
- int textlen;
+ len = 0;
+ while (len >= 0 && seq < next_seq) {
+ struct printk_log *msg = log_from_idx(idx);
+ int textlen;
- textlen = msg_print_text(msg, true, text,
- LOG_LINE_MAX + PREFIX_MAX);
- if (textlen < 0) {
- len = textlen;
- break;
- }
- idx = log_next(idx);
- seq++;
+ textlen = msg_print_text(msg, true, text,
+ LOG_LINE_MAX + PREFIX_MAX);
+ if (textlen < 0) {
+ len = textlen;
+ break;
+ }
+ idx = log_next(idx);
+ seq++;
- logbuf_unlock_irq();
- if (copy_to_user(buf + len, text, textlen))
- len = -EFAULT;
- else
- len += textlen;
- logbuf_lock_irq();
-
- if (seq < log_first_seq) {
- /* messages are gone, move to next one */
- seq = log_first_seq;
- idx = log_first_idx;
- }
+ logbuf_unlock_irq();
+ if (copy_to_user(buf + len, text, textlen))
+ len = -EFAULT;
+ else
+ len += textlen;
+ logbuf_lock_irq();
+
+ if (seq < log_first_seq) {
+ /* messages are gone, move to next one */
+ seq = log_first_seq;
+ idx = log_first_idx;
}
}
@@ -1430,6 +1427,14 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
return len;
}
+static void syslog_clear(void)
+{
+ logbuf_lock_irq();
+ clear_seq = log_next_seq;
+ clear_idx = log_next_idx;
+ logbuf_unlock_irq();
+}
+
int do_syslog(int type, char __user *buf, int len, int source)
{
bool clear = false;
@@ -1474,7 +1479,7 @@ int do_syslog(int type, char __user *buf, int len, int source)
break;
/* Clear ring buffer */
case SYSLOG_ACTION_CLEAR:
- syslog_print_all(NULL, 0, true);
+ syslog_clear();
break;
/* Disable logging to console */
case SYSLOG_ACTION_CONSOLE_OFF:
@@ -1824,28 +1829,16 @@ static size_t log_output(int facility, int level, enum log_flags lflags, const c
return log_store(facility, level, lflags, 0, dict, dictlen, text, text_len);
}
-asmlinkage int vprintk_emit(int facility, int level,
- const char *dict, size_t dictlen,
- const char *fmt, va_list args)
+/* Must be called under logbuf_lock. */
+int vprintk_store(int facility, int level,
+ const char *dict, size_t dictlen,
+ const char *fmt, va_list args)
{
static char textbuf[LOG_LINE_MAX];
char *text = textbuf;
size_t text_len;
enum log_flags lflags = 0;
- unsigned long flags;
- int printed_len;
- bool in_sched = false;
- if (level == LOGLEVEL_SCHED) {
- level = LOGLEVEL_DEFAULT;
- in_sched = true;
- }
-
- boot_delay_msec(level);
- printk_delay();
-
- /* This stops the holder of console_sem just where we want him */
- logbuf_lock_irqsave(flags);
/*
* The printf needs to come first; we need the syslog
* prefix which might be passed-in as a parameter.
@@ -1886,8 +1879,32 @@ asmlinkage int vprintk_emit(int facility, int level,
if (dict)
lflags |= LOG_PREFIX|LOG_NEWLINE;
- printed_len = log_output(facility, level, lflags, dict, dictlen, text, text_len);
+ if (suppress_message_printing(level))
+ lflags |= LOG_NOCONS;
+
+ return log_output(facility, level, lflags,
+ dict, dictlen, text, text_len);
+}
+
+asmlinkage int vprintk_emit(int facility, int level,
+ const char *dict, size_t dictlen,
+ const char *fmt, va_list args)
+{
+ int printed_len;
+ bool in_sched = false;
+ unsigned long flags;
+
+ if (level == LOGLEVEL_SCHED) {
+ level = LOGLEVEL_DEFAULT;
+ in_sched = true;
+ }
+ boot_delay_msec(level);
+ printk_delay();
+
+ /* This stops the holder of console_sem just where we want him */
+ logbuf_lock_irqsave(flags);
+ printed_len = vprintk_store(facility, level, dict, dictlen, fmt, args);
logbuf_unlock_irqrestore(flags);
/* If called from the scheduler, we can not call up(). */
@@ -2013,7 +2030,6 @@ static void call_console_drivers(const char *ext_text, size_t ext_len,
const char *text, size_t len) {}
static size_t msg_print_text(const struct printk_log *msg,
bool syslog, char *buf, size_t size) { return 0; }
-static bool suppress_message_printing(int level) { return false; }
#endif /* CONFIG_PRINTK */
@@ -2243,6 +2259,7 @@ int is_console_locked(void)
{
return console_locked;
}
+EXPORT_SYMBOL(is_console_locked);
/*
* Check if we have any console that is capable of printing while cpu is
@@ -2349,11 +2366,10 @@ skip:
break;
msg = log_from_idx(console_idx);
- if (suppress_message_printing(msg->level)) {
+ if (msg->flags & LOG_NOCONS) {
/*
- * Skip record we have buffered and already printed
- * directly to the console when we received it, and
- * record that has level above the console loglevel.
+ * Skip record if !ignore_loglevel, and
+ * record has level above the console loglevel.
*/
console_idx = log_next(console_idx);
console_seq++;
@@ -2772,7 +2788,8 @@ EXPORT_SYMBOL(unregister_console);
void __init console_init(void)
{
int ret;
- initcall_t *call;
+ initcall_t call;
+ initcall_entry_t *ce;
/* Setup the default TTY line discipline. */
n_tty_init();
@@ -2781,13 +2798,14 @@ void __init console_init(void)
* set up the console device so that later boot sequences can
* inform about problems etc..
*/
- call = __con_initcall_start;
+ ce = __con_initcall_start;
trace_initcall_level("console");
- while (call < __con_initcall_end) {
- trace_initcall_start((*call));
- ret = (*call)();
- trace_initcall_finish((*call), ret);
- call++;
+ while (ce < __con_initcall_end) {
+ call = initcall_from_entry(ce);
+ trace_initcall_start(call);
+ ret = call();
+ trace_initcall_finish(call, ret);
+ ce++;
}
}
@@ -2878,16 +2896,20 @@ void wake_up_klogd(void)
preempt_enable();
}
-int vprintk_deferred(const char *fmt, va_list args)
+void defer_console_output(void)
{
- int r;
-
- r = vprintk_emit(0, LOGLEVEL_SCHED, NULL, 0, fmt, args);
-
preempt_disable();
__this_cpu_or(printk_pending, PRINTK_PENDING_OUTPUT);
irq_work_queue(this_cpu_ptr(&wake_up_klogd_work));
preempt_enable();
+}
+
+int vprintk_deferred(const char *fmt, va_list args)
+{
+ int r;
+
+ r = vprintk_emit(0, LOGLEVEL_SCHED, NULL, 0, fmt, args);
+ defer_console_output();
return r;
}
diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c
index d7d091309054..a0a74c533e4b 100644
--- a/kernel/printk/printk_safe.c
+++ b/kernel/printk/printk_safe.c
@@ -308,24 +308,33 @@ static __printf(1, 0) int vprintk_nmi(const char *fmt, va_list args)
void printk_nmi_enter(void)
{
- /*
- * The size of the extra per-CPU buffer is limited. Use it only when
- * the main one is locked. If this CPU is not in the safe context,
- * the lock must be taken on another CPU and we could wait for it.
- */
- if ((this_cpu_read(printk_context) & PRINTK_SAFE_CONTEXT_MASK) &&
- raw_spin_is_locked(&logbuf_lock)) {
- this_cpu_or(printk_context, PRINTK_NMI_CONTEXT_MASK);
- } else {
- this_cpu_or(printk_context, PRINTK_NMI_DEFERRED_CONTEXT_MASK);
- }
+ this_cpu_or(printk_context, PRINTK_NMI_CONTEXT_MASK);
}
void printk_nmi_exit(void)
{
- this_cpu_and(printk_context,
- ~(PRINTK_NMI_CONTEXT_MASK |
- PRINTK_NMI_DEFERRED_CONTEXT_MASK));
+ this_cpu_and(printk_context, ~PRINTK_NMI_CONTEXT_MASK);
+}
+
+/*
+ * Marks a code that might produce many messages in NMI context
+ * and the risk of losing them is more critical than eventual
+ * reordering.
+ *
+ * It has effect only when called in NMI context. Then printk()
+ * will try to store the messages into the main logbuf directly
+ * and use the per-CPU buffers only as a fallback when the lock
+ * is not available.
+ */
+void printk_nmi_direct_enter(void)
+{
+ if (this_cpu_read(printk_context) & PRINTK_NMI_CONTEXT_MASK)
+ this_cpu_or(printk_context, PRINTK_NMI_DIRECT_CONTEXT_MASK);
+}
+
+void printk_nmi_direct_exit(void)
+{
+ this_cpu_and(printk_context, ~PRINTK_NMI_DIRECT_CONTEXT_MASK);
}
#else
@@ -363,6 +372,20 @@ void __printk_safe_exit(void)
__printf(1, 0) int vprintk_func(const char *fmt, va_list args)
{
+ /*
+ * Try to use the main logbuf even in NMI. But avoid calling console
+ * drivers that might have their own locks.
+ */
+ if ((this_cpu_read(printk_context) & PRINTK_NMI_DIRECT_CONTEXT_MASK) &&
+ raw_spin_trylock(&logbuf_lock)) {
+ int len;
+
+ len = vprintk_store(0, LOGLEVEL_DEFAULT, NULL, 0, fmt, args);
+ raw_spin_unlock(&logbuf_lock);
+ defer_console_output();
+ return len;
+ }
+
/* Use extra buffer in NMI when logbuf_lock is taken or in safe mode. */
if (this_cpu_read(printk_context) & PRINTK_NMI_CONTEXT_MASK)
return vprintk_nmi(fmt, args);
@@ -371,13 +394,6 @@ __printf(1, 0) int vprintk_func(const char *fmt, va_list args)
if (this_cpu_read(printk_context) & PRINTK_SAFE_CONTEXT_MASK)
return vprintk_safe(fmt, args);
- /*
- * Use the main logbuf when logbuf_lock is available in NMI.
- * But avoid calling console drivers that might have their own locks.
- */
- if (this_cpu_read(printk_context) & PRINTK_NMI_DEFERRED_CONTEXT_MASK)
- return vprintk_deferred(fmt, args);
-
/* No obstacles. */
return vprintk_default(fmt, args);
}
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 40cea6735c2d..4d04683c31b2 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -91,7 +91,17 @@ static inline void rcu_seq_end(unsigned long *sp)
WRITE_ONCE(*sp, rcu_seq_endval(sp));
}
-/* Take a snapshot of the update side's sequence number. */
+/*
+ * rcu_seq_snap - Take a snapshot of the update side's sequence number.
+ *
+ * This function returns the earliest value of the grace-period sequence number
+ * that will indicate that a full grace period has elapsed since the current
+ * time. Once the grace-period sequence number has reached this value, it will
+ * be safe to invoke all callbacks that have been registered prior to the
+ * current time. This value is the current grace-period number plus two to the
+ * power of the number of low-order bits reserved for state, then rounded up to
+ * the next value in which the state bits are all zero.
+ */
static inline unsigned long rcu_seq_snap(unsigned long *sp)
{
unsigned long s;
@@ -108,6 +118,15 @@ static inline unsigned long rcu_seq_current(unsigned long *sp)
}
/*
+ * Given a snapshot from rcu_seq_snap(), determine whether or not the
+ * corresponding update-side operation has started.
+ */
+static inline bool rcu_seq_started(unsigned long *sp, unsigned long s)
+{
+ return ULONG_CMP_LT((s - 1) & ~RCU_SEQ_STATE_MASK, READ_ONCE(*sp));
+}
+
+/*
* Given a snapshot from rcu_seq_snap(), determine whether or not a
* full update-side operation has occurred.
*/
@@ -117,6 +136,45 @@ static inline bool rcu_seq_done(unsigned long *sp, unsigned long s)
}
/*
+ * Has a grace period completed since the time the old gp_seq was collected?
+ */
+static inline bool rcu_seq_completed_gp(unsigned long old, unsigned long new)
+{
+ return ULONG_CMP_LT(old, new & ~RCU_SEQ_STATE_MASK);
+}
+
+/*
+ * Has a grace period started since the time the old gp_seq was collected?
+ */
+static inline bool rcu_seq_new_gp(unsigned long old, unsigned long new)
+{
+ return ULONG_CMP_LT((old + RCU_SEQ_STATE_MASK) & ~RCU_SEQ_STATE_MASK,
+ new);
+}
+
+/*
+ * Roughly how many full grace periods have elapsed between the collection
+ * of the two specified grace periods?
+ */
+static inline unsigned long rcu_seq_diff(unsigned long new, unsigned long old)
+{
+ unsigned long rnd_diff;
+
+ if (old == new)
+ return 0;
+ /*
+ * Compute the number of grace periods (still shifted up), plus
+ * one if either of new and old is not an exact grace period.
+ */
+ rnd_diff = (new & ~RCU_SEQ_STATE_MASK) -
+ ((old + RCU_SEQ_STATE_MASK) & ~RCU_SEQ_STATE_MASK) +
+ ((new & RCU_SEQ_STATE_MASK) || (old & RCU_SEQ_STATE_MASK));
+ if (ULONG_CMP_GE(RCU_SEQ_STATE_MASK, rnd_diff))
+ return 1; /* Definitely no grace period has elapsed. */
+ return ((rnd_diff - RCU_SEQ_STATE_MASK - 1) >> RCU_SEQ_CTR_SHIFT) + 2;
+}
+
+/*
* debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally
* by call_rcu() and rcu callback execution, and are therefore not part of the
* RCU API. Leaving in rcupdate.h because they are used by all RCU flavors.
@@ -276,6 +334,9 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt)
/* Is this rcu_node a leaf? */
#define rcu_is_leaf_node(rnp) ((rnp)->level == rcu_num_lvls - 1)
+/* Is this rcu_node the last leaf? */
+#define rcu_is_last_leaf_node(rsp, rnp) ((rnp) == &(rsp)->node[rcu_num_nodes - 1])
+
/*
* Do a full breadth-first scan of the rcu_node structures for the
* specified rcu_state structure.
@@ -405,8 +466,7 @@ enum rcutorture_type {
#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU)
void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
- unsigned long *gpnum, unsigned long *completed);
-void rcutorture_record_test_transition(void);
+ unsigned long *gp_seq);
void rcutorture_record_progress(unsigned long vernum);
void do_trace_rcu_torture_read(const char *rcutorturename,
struct rcu_head *rhp,
@@ -415,15 +475,11 @@ void do_trace_rcu_torture_read(const char *rcutorturename,
unsigned long c);
#else
static inline void rcutorture_get_gp_data(enum rcutorture_type test_type,
- int *flags,
- unsigned long *gpnum,
- unsigned long *completed)
+ int *flags, unsigned long *gp_seq)
{
*flags = 0;
- *gpnum = 0;
- *completed = 0;
+ *gp_seq = 0;
}
-static inline void rcutorture_record_test_transition(void) { }
static inline void rcutorture_record_progress(unsigned long vernum) { }
#ifdef CONFIG_RCU_TRACE
void do_trace_rcu_torture_read(const char *rcutorturename,
@@ -441,31 +497,26 @@ void do_trace_rcu_torture_read(const char *rcutorturename,
static inline void srcutorture_get_gp_data(enum rcutorture_type test_type,
struct srcu_struct *sp, int *flags,
- unsigned long *gpnum,
- unsigned long *completed)
+ unsigned long *gp_seq)
{
if (test_type != SRCU_FLAVOR)
return;
*flags = 0;
- *completed = sp->srcu_idx;
- *gpnum = *completed;
+ *gp_seq = sp->srcu_idx;
}
#elif defined(CONFIG_TREE_SRCU)
void srcutorture_get_gp_data(enum rcutorture_type test_type,
struct srcu_struct *sp, int *flags,
- unsigned long *gpnum, unsigned long *completed);
+ unsigned long *gp_seq);
#endif
#ifdef CONFIG_TINY_RCU
-static inline unsigned long rcu_batches_started(void) { return 0; }
-static inline unsigned long rcu_batches_started_bh(void) { return 0; }
-static inline unsigned long rcu_batches_started_sched(void) { return 0; }
-static inline unsigned long rcu_batches_completed(void) { return 0; }
-static inline unsigned long rcu_batches_completed_bh(void) { return 0; }
-static inline unsigned long rcu_batches_completed_sched(void) { return 0; }
+static inline unsigned long rcu_get_gp_seq(void) { return 0; }
+static inline unsigned long rcu_bh_get_gp_seq(void) { return 0; }
+static inline unsigned long rcu_sched_get_gp_seq(void) { return 0; }
static inline unsigned long rcu_exp_batches_completed(void) { return 0; }
static inline unsigned long rcu_exp_batches_completed_sched(void) { return 0; }
static inline unsigned long
@@ -474,19 +525,16 @@ static inline void rcu_force_quiescent_state(void) { }
static inline void rcu_bh_force_quiescent_state(void) { }
static inline void rcu_sched_force_quiescent_state(void) { }
static inline void show_rcu_gp_kthreads(void) { }
+static inline int rcu_get_gp_kthreads_prio(void) { return 0; }
#else /* #ifdef CONFIG_TINY_RCU */
-extern unsigned long rcutorture_testseq;
-extern unsigned long rcutorture_vernum;
-unsigned long rcu_batches_started(void);
-unsigned long rcu_batches_started_bh(void);
-unsigned long rcu_batches_started_sched(void);
-unsigned long rcu_batches_completed(void);
-unsigned long rcu_batches_completed_bh(void);
-unsigned long rcu_batches_completed_sched(void);
+unsigned long rcu_get_gp_seq(void);
+unsigned long rcu_bh_get_gp_seq(void);
+unsigned long rcu_sched_get_gp_seq(void);
unsigned long rcu_exp_batches_completed(void);
unsigned long rcu_exp_batches_completed_sched(void);
unsigned long srcu_batches_completed(struct srcu_struct *sp);
void show_rcu_gp_kthreads(void);
+int rcu_get_gp_kthreads_prio(void);
void rcu_force_quiescent_state(void);
void rcu_bh_force_quiescent_state(void);
void rcu_sched_force_quiescent_state(void);
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index e232846516b3..34244523550e 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -19,6 +19,9 @@
*
* Authors: Paul E. McKenney <paulmck@us.ibm.com>
*/
+
+#define pr_fmt(fmt) fmt
+
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/init.h>
@@ -88,7 +91,7 @@ torture_param(int, nreaders, -1, "Number of RCU reader threads");
torture_param(int, nwriters, -1, "Number of RCU updater threads");
torture_param(bool, shutdown, !IS_ENABLED(MODULE),
"Shutdown at end of performance tests.");
-torture_param(bool, verbose, true, "Enable verbose debugging printk()s");
+torture_param(int, verbose, 1, "Enable verbose debugging printk()s");
torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable");
static char *perf_type = "rcu";
@@ -135,8 +138,8 @@ struct rcu_perf_ops {
void (*cleanup)(void);
int (*readlock)(void);
void (*readunlock)(int idx);
- unsigned long (*started)(void);
- unsigned long (*completed)(void);
+ unsigned long (*get_gp_seq)(void);
+ unsigned long (*gp_diff)(unsigned long new, unsigned long old);
unsigned long (*exp_completed)(void);
void (*async)(struct rcu_head *head, rcu_callback_t func);
void (*gp_barrier)(void);
@@ -176,8 +179,8 @@ static struct rcu_perf_ops rcu_ops = {
.init = rcu_sync_perf_init,
.readlock = rcu_perf_read_lock,
.readunlock = rcu_perf_read_unlock,
- .started = rcu_batches_started,
- .completed = rcu_batches_completed,
+ .get_gp_seq = rcu_get_gp_seq,
+ .gp_diff = rcu_seq_diff,
.exp_completed = rcu_exp_batches_completed,
.async = call_rcu,
.gp_barrier = rcu_barrier,
@@ -206,8 +209,8 @@ static struct rcu_perf_ops rcu_bh_ops = {
.init = rcu_sync_perf_init,
.readlock = rcu_bh_perf_read_lock,
.readunlock = rcu_bh_perf_read_unlock,
- .started = rcu_batches_started_bh,
- .completed = rcu_batches_completed_bh,
+ .get_gp_seq = rcu_bh_get_gp_seq,
+ .gp_diff = rcu_seq_diff,
.exp_completed = rcu_exp_batches_completed_sched,
.async = call_rcu_bh,
.gp_barrier = rcu_barrier_bh,
@@ -263,8 +266,8 @@ static struct rcu_perf_ops srcu_ops = {
.init = rcu_sync_perf_init,
.readlock = srcu_perf_read_lock,
.readunlock = srcu_perf_read_unlock,
- .started = NULL,
- .completed = srcu_perf_completed,
+ .get_gp_seq = srcu_perf_completed,
+ .gp_diff = rcu_seq_diff,
.exp_completed = srcu_perf_completed,
.async = srcu_call_rcu,
.gp_barrier = srcu_rcu_barrier,
@@ -292,8 +295,8 @@ static struct rcu_perf_ops srcud_ops = {
.cleanup = srcu_sync_perf_cleanup,
.readlock = srcu_perf_read_lock,
.readunlock = srcu_perf_read_unlock,
- .started = NULL,
- .completed = srcu_perf_completed,
+ .get_gp_seq = srcu_perf_completed,
+ .gp_diff = rcu_seq_diff,
.exp_completed = srcu_perf_completed,
.async = srcu_call_rcu,
.gp_barrier = srcu_rcu_barrier,
@@ -322,8 +325,8 @@ static struct rcu_perf_ops sched_ops = {
.init = rcu_sync_perf_init,
.readlock = sched_perf_read_lock,
.readunlock = sched_perf_read_unlock,
- .started = rcu_batches_started_sched,
- .completed = rcu_batches_completed_sched,
+ .get_gp_seq = rcu_sched_get_gp_seq,
+ .gp_diff = rcu_seq_diff,
.exp_completed = rcu_exp_batches_completed_sched,
.async = call_rcu_sched,
.gp_barrier = rcu_barrier_sched,
@@ -350,8 +353,8 @@ static struct rcu_perf_ops tasks_ops = {
.init = rcu_sync_perf_init,
.readlock = tasks_perf_read_lock,
.readunlock = tasks_perf_read_unlock,
- .started = rcu_no_completed,
- .completed = rcu_no_completed,
+ .get_gp_seq = rcu_no_completed,
+ .gp_diff = rcu_seq_diff,
.async = call_rcu_tasks,
.gp_barrier = rcu_barrier_tasks,
.sync = synchronize_rcu_tasks,
@@ -359,9 +362,11 @@ static struct rcu_perf_ops tasks_ops = {
.name = "tasks"
};
-static bool __maybe_unused torturing_tasks(void)
+static unsigned long rcuperf_seq_diff(unsigned long new, unsigned long old)
{
- return cur_ops == &tasks_ops;
+ if (!cur_ops->gp_diff)
+ return new - old;
+ return cur_ops->gp_diff(new, old);
}
/*
@@ -444,8 +449,7 @@ rcu_perf_writer(void *arg)
b_rcu_perf_writer_started =
cur_ops->exp_completed() / 2;
} else {
- b_rcu_perf_writer_started =
- cur_ops->completed();
+ b_rcu_perf_writer_started = cur_ops->get_gp_seq();
}
}
@@ -502,7 +506,7 @@ retry:
cur_ops->exp_completed() / 2;
} else {
b_rcu_perf_writer_finished =
- cur_ops->completed();
+ cur_ops->get_gp_seq();
}
if (shutdown) {
smp_mb(); /* Assign before wake. */
@@ -527,7 +531,7 @@ retry:
return 0;
}
-static inline void
+static void
rcu_perf_print_module_parms(struct rcu_perf_ops *cur_ops, const char *tag)
{
pr_alert("%s" PERF_FLAG
@@ -582,8 +586,8 @@ rcu_perf_cleanup(void)
t_rcu_perf_writer_finished -
t_rcu_perf_writer_started,
ngps,
- b_rcu_perf_writer_finished -
- b_rcu_perf_writer_started);
+ rcuperf_seq_diff(b_rcu_perf_writer_finished,
+ b_rcu_perf_writer_started));
for (i = 0; i < nrealwriters; i++) {
if (!writer_durations)
break;
@@ -671,12 +675,11 @@ rcu_perf_init(void)
break;
}
if (i == ARRAY_SIZE(perf_ops)) {
- pr_alert("rcu-perf: invalid perf type: \"%s\"\n",
- perf_type);
+ pr_alert("rcu-perf: invalid perf type: \"%s\"\n", perf_type);
pr_alert("rcu-perf types:");
for (i = 0; i < ARRAY_SIZE(perf_ops); i++)
- pr_alert(" %s", perf_ops[i]->name);
- pr_alert("\n");
+ pr_cont(" %s", perf_ops[i]->name);
+ pr_cont("\n");
firsterr = -EINVAL;
goto unwind;
}
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 42fcb7f05fac..c596c6f1e457 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -22,6 +22,9 @@
*
* See also: Documentation/RCU/torture.txt
*/
+
+#define pr_fmt(fmt) fmt
+
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/init.h>
@@ -52,6 +55,7 @@
#include <linux/torture.h>
#include <linux/vmalloc.h>
#include <linux/sched/debug.h>
+#include <linux/sched/sysctl.h>
#include "rcu.h"
@@ -59,6 +63,19 @@ MODULE_LICENSE("GPL");
MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@joshtriplett.org>");
+/* Bits for ->extendables field, extendables param, and related definitions. */
+#define RCUTORTURE_RDR_SHIFT 8 /* Put SRCU index in upper bits. */
+#define RCUTORTURE_RDR_MASK ((1 << RCUTORTURE_RDR_SHIFT) - 1)
+#define RCUTORTURE_RDR_BH 0x1 /* Extend readers by disabling bh. */
+#define RCUTORTURE_RDR_IRQ 0x2 /* ... disabling interrupts. */
+#define RCUTORTURE_RDR_PREEMPT 0x4 /* ... disabling preemption. */
+#define RCUTORTURE_RDR_RCU 0x8 /* ... entering another RCU reader. */
+#define RCUTORTURE_RDR_NBITS 4 /* Number of bits defined above. */
+#define RCUTORTURE_MAX_EXTEND (RCUTORTURE_RDR_BH | RCUTORTURE_RDR_IRQ | \
+ RCUTORTURE_RDR_PREEMPT)
+#define RCUTORTURE_RDR_MAX_LOOPS 0x7 /* Maximum reader extensions. */
+ /* Must be power of two minus one. */
+
torture_param(int, cbflood_inter_holdoff, HZ,
"Holdoff between floods (jiffies)");
torture_param(int, cbflood_intra_holdoff, 1,
@@ -66,6 +83,8 @@ torture_param(int, cbflood_intra_holdoff, 1,
torture_param(int, cbflood_n_burst, 3, "# bursts in flood, zero to disable");
torture_param(int, cbflood_n_per_burst, 20000,
"# callbacks per burst in flood");
+torture_param(int, extendables, RCUTORTURE_MAX_EXTEND,
+ "Extend readers by disabling bh (1), irqs (2), or preempt (4)");
torture_param(int, fqs_duration, 0,
"Duration of fqs bursts (us), 0 to disable");
torture_param(int, fqs_holdoff, 0, "Holdoff time within fqs bursts (us)");
@@ -84,7 +103,7 @@ torture_param(int, object_debug, 0,
"Enable debug-object double call_rcu() testing");
torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)");
torture_param(int, onoff_interval, 0,
- "Time between CPU hotplugs (s), 0=disable");
+ "Time between CPU hotplugs (jiffies), 0=disable");
torture_param(int, shuffle_interval, 3, "Number of seconds between shuffles");
torture_param(int, shutdown_secs, 0, "Shutdown time (s), <= zero to disable.");
torture_param(int, stall_cpu, 0, "Stall duration (s), zero to disable.");
@@ -101,7 +120,7 @@ torture_param(int, test_boost_interval, 7,
"Interval between boost tests, seconds.");
torture_param(bool, test_no_idle_hz, true,
"Test support for tickless idle CPUs");
-torture_param(bool, verbose, true,
+torture_param(int, verbose, 1,
"Enable verbose debugging printk()s");
static char *torture_type = "rcu";
@@ -148,9 +167,9 @@ static long n_rcu_torture_boost_ktrerror;
static long n_rcu_torture_boost_rterror;
static long n_rcu_torture_boost_failure;
static long n_rcu_torture_boosts;
-static long n_rcu_torture_timers;
+static atomic_long_t n_rcu_torture_timers;
static long n_barrier_attempts;
-static long n_barrier_successes;
+static long n_barrier_successes; /* did rcu_barrier test succeed? */
static atomic_long_t n_cbfloods;
static struct list_head rcu_torture_removed;
@@ -261,8 +280,8 @@ struct rcu_torture_ops {
int (*readlock)(void);
void (*read_delay)(struct torture_random_state *rrsp);
void (*readunlock)(int idx);
- unsigned long (*started)(void);
- unsigned long (*completed)(void);
+ unsigned long (*get_gp_seq)(void);
+ unsigned long (*gp_diff)(unsigned long new, unsigned long old);
void (*deferred_free)(struct rcu_torture *p);
void (*sync)(void);
void (*exp_sync)(void);
@@ -274,6 +293,8 @@ struct rcu_torture_ops {
void (*stats)(void);
int irq_capable;
int can_boost;
+ int extendables;
+ int ext_irq_conflict;
const char *name;
};
@@ -302,10 +323,10 @@ static void rcu_read_delay(struct torture_random_state *rrsp)
* force_quiescent_state. */
if (!(torture_random(rrsp) % (nrealreaders * 2000 * longdelay_ms))) {
- started = cur_ops->completed();
+ started = cur_ops->get_gp_seq();
ts = rcu_trace_clock_local();
mdelay(longdelay_ms);
- completed = cur_ops->completed();
+ completed = cur_ops->get_gp_seq();
do_trace_rcu_torture_read(cur_ops->name, NULL, ts,
started, completed);
}
@@ -397,8 +418,8 @@ static struct rcu_torture_ops rcu_ops = {
.readlock = rcu_torture_read_lock,
.read_delay = rcu_read_delay,
.readunlock = rcu_torture_read_unlock,
- .started = rcu_batches_started,
- .completed = rcu_batches_completed,
+ .get_gp_seq = rcu_get_gp_seq,
+ .gp_diff = rcu_seq_diff,
.deferred_free = rcu_torture_deferred_free,
.sync = synchronize_rcu,
.exp_sync = synchronize_rcu_expedited,
@@ -439,8 +460,8 @@ static struct rcu_torture_ops rcu_bh_ops = {
.readlock = rcu_bh_torture_read_lock,
.read_delay = rcu_read_delay, /* just reuse rcu's version. */
.readunlock = rcu_bh_torture_read_unlock,
- .started = rcu_batches_started_bh,
- .completed = rcu_batches_completed_bh,
+ .get_gp_seq = rcu_bh_get_gp_seq,
+ .gp_diff = rcu_seq_diff,
.deferred_free = rcu_bh_torture_deferred_free,
.sync = synchronize_rcu_bh,
.exp_sync = synchronize_rcu_bh_expedited,
@@ -449,6 +470,8 @@ static struct rcu_torture_ops rcu_bh_ops = {
.fqs = rcu_bh_force_quiescent_state,
.stats = NULL,
.irq_capable = 1,
+ .extendables = (RCUTORTURE_RDR_BH | RCUTORTURE_RDR_IRQ),
+ .ext_irq_conflict = RCUTORTURE_RDR_RCU,
.name = "rcu_bh"
};
@@ -483,8 +506,7 @@ static struct rcu_torture_ops rcu_busted_ops = {
.readlock = rcu_torture_read_lock,
.read_delay = rcu_read_delay, /* just reuse rcu's version. */
.readunlock = rcu_torture_read_unlock,
- .started = rcu_no_completed,
- .completed = rcu_no_completed,
+ .get_gp_seq = rcu_no_completed,
.deferred_free = rcu_busted_torture_deferred_free,
.sync = synchronize_rcu_busted,
.exp_sync = synchronize_rcu_busted,
@@ -572,8 +594,7 @@ static struct rcu_torture_ops srcu_ops = {
.readlock = srcu_torture_read_lock,
.read_delay = srcu_read_delay,
.readunlock = srcu_torture_read_unlock,
- .started = NULL,
- .completed = srcu_torture_completed,
+ .get_gp_seq = srcu_torture_completed,
.deferred_free = srcu_torture_deferred_free,
.sync = srcu_torture_synchronize,
.exp_sync = srcu_torture_synchronize_expedited,
@@ -610,8 +631,7 @@ static struct rcu_torture_ops srcud_ops = {
.readlock = srcu_torture_read_lock,
.read_delay = srcu_read_delay,
.readunlock = srcu_torture_read_unlock,
- .started = NULL,
- .completed = srcu_torture_completed,
+ .get_gp_seq = srcu_torture_completed,
.deferred_free = srcu_torture_deferred_free,
.sync = srcu_torture_synchronize,
.exp_sync = srcu_torture_synchronize_expedited,
@@ -622,6 +642,26 @@ static struct rcu_torture_ops srcud_ops = {
.name = "srcud"
};
+/* As above, but broken due to inappropriate reader extension. */
+static struct rcu_torture_ops busted_srcud_ops = {
+ .ttype = SRCU_FLAVOR,
+ .init = srcu_torture_init,
+ .cleanup = srcu_torture_cleanup,
+ .readlock = srcu_torture_read_lock,
+ .read_delay = rcu_read_delay,
+ .readunlock = srcu_torture_read_unlock,
+ .get_gp_seq = srcu_torture_completed,
+ .deferred_free = srcu_torture_deferred_free,
+ .sync = srcu_torture_synchronize,
+ .exp_sync = srcu_torture_synchronize_expedited,
+ .call = srcu_torture_call,
+ .cb_barrier = srcu_torture_barrier,
+ .stats = srcu_torture_stats,
+ .irq_capable = 1,
+ .extendables = RCUTORTURE_MAX_EXTEND,
+ .name = "busted_srcud"
+};
+
/*
* Definitions for sched torture testing.
*/
@@ -648,8 +688,8 @@ static struct rcu_torture_ops sched_ops = {
.readlock = sched_torture_read_lock,
.read_delay = rcu_read_delay, /* just reuse rcu's version. */
.readunlock = sched_torture_read_unlock,
- .started = rcu_batches_started_sched,
- .completed = rcu_batches_completed_sched,
+ .get_gp_seq = rcu_sched_get_gp_seq,
+ .gp_diff = rcu_seq_diff,
.deferred_free = rcu_sched_torture_deferred_free,
.sync = synchronize_sched,
.exp_sync = synchronize_sched_expedited,
@@ -660,6 +700,7 @@ static struct rcu_torture_ops sched_ops = {
.fqs = rcu_sched_force_quiescent_state,
.stats = NULL,
.irq_capable = 1,
+ .extendables = RCUTORTURE_MAX_EXTEND,
.name = "sched"
};
@@ -687,8 +728,7 @@ static struct rcu_torture_ops tasks_ops = {
.readlock = tasks_torture_read_lock,
.read_delay = rcu_read_delay, /* just reuse rcu's version. */
.readunlock = tasks_torture_read_unlock,
- .started = rcu_no_completed,
- .completed = rcu_no_completed,
+ .get_gp_seq = rcu_no_completed,
.deferred_free = rcu_tasks_torture_deferred_free,
.sync = synchronize_rcu_tasks,
.exp_sync = synchronize_rcu_tasks,
@@ -700,6 +740,13 @@ static struct rcu_torture_ops tasks_ops = {
.name = "tasks"
};
+static unsigned long rcutorture_seq_diff(unsigned long new, unsigned long old)
+{
+ if (!cur_ops->gp_diff)
+ return new - old;
+ return cur_ops->gp_diff(new, old);
+}
+
static bool __maybe_unused torturing_tasks(void)
{
return cur_ops == &tasks_ops;
@@ -726,6 +773,44 @@ static void rcu_torture_boost_cb(struct rcu_head *head)
smp_store_release(&rbip->inflight, 0);
}
+static int old_rt_runtime = -1;
+
+static void rcu_torture_disable_rt_throttle(void)
+{
+ /*
+ * Disable RT throttling so that rcutorture's boost threads don't get
+ * throttled. Only possible if rcutorture is built-in otherwise the
+ * user should manually do this by setting the sched_rt_period_us and
+ * sched_rt_runtime sysctls.
+ */
+ if (!IS_BUILTIN(CONFIG_RCU_TORTURE_TEST) || old_rt_runtime != -1)
+ return;
+
+ old_rt_runtime = sysctl_sched_rt_runtime;
+ sysctl_sched_rt_runtime = -1;
+}
+
+static void rcu_torture_enable_rt_throttle(void)
+{
+ if (!IS_BUILTIN(CONFIG_RCU_TORTURE_TEST) || old_rt_runtime == -1)
+ return;
+
+ sysctl_sched_rt_runtime = old_rt_runtime;
+ old_rt_runtime = -1;
+}
+
+static bool rcu_torture_boost_failed(unsigned long start, unsigned long end)
+{
+ if (end - start > test_boost_duration * HZ - HZ / 2) {
+ VERBOSE_TOROUT_STRING("rcu_torture_boost boosting failed");
+ n_rcu_torture_boost_failure++;
+
+ return true; /* failed */
+ }
+
+ return false; /* passed */
+}
+
static int rcu_torture_boost(void *arg)
{
unsigned long call_rcu_time;
@@ -746,6 +831,21 @@ static int rcu_torture_boost(void *arg)
init_rcu_head_on_stack(&rbi.rcu);
/* Each pass through the following loop does one boost-test cycle. */
do {
+ /* Track if the test failed already in this test interval? */
+ bool failed = false;
+
+ /* Increment n_rcu_torture_boosts once per boost-test */
+ while (!kthread_should_stop()) {
+ if (mutex_trylock(&boost_mutex)) {
+ n_rcu_torture_boosts++;
+ mutex_unlock(&boost_mutex);
+ break;
+ }
+ schedule_timeout_uninterruptible(1);
+ }
+ if (kthread_should_stop())
+ goto checkwait;
+
/* Wait for the next test interval. */
oldstarttime = boost_starttime;
while (ULONG_CMP_LT(jiffies, oldstarttime)) {
@@ -764,11 +864,10 @@ static int rcu_torture_boost(void *arg)
/* RCU core before ->inflight = 1. */
smp_store_release(&rbi.inflight, 1);
call_rcu(&rbi.rcu, rcu_torture_boost_cb);
- if (jiffies - call_rcu_time >
- test_boost_duration * HZ - HZ / 2) {
- VERBOSE_TOROUT_STRING("rcu_torture_boost boosting failed");
- n_rcu_torture_boost_failure++;
- }
+ /* Check if the boost test failed */
+ failed = failed ||
+ rcu_torture_boost_failed(call_rcu_time,
+ jiffies);
call_rcu_time = jiffies;
}
stutter_wait("rcu_torture_boost");
@@ -777,6 +876,14 @@ static int rcu_torture_boost(void *arg)
}
/*
+ * If boost never happened, then inflight will always be 1, in
+ * this case the boost check would never happen in the above
+ * loop so do another one here.
+ */
+ if (!failed && smp_load_acquire(&rbi.inflight))
+ rcu_torture_boost_failed(call_rcu_time, jiffies);
+
+ /*
* Set the start time of the next test interval.
* Yes, this is vulnerable to long delays, but such
* delays simply cause a false negative for the next
@@ -788,7 +895,6 @@ static int rcu_torture_boost(void *arg)
if (mutex_trylock(&boost_mutex)) {
boost_starttime = jiffies +
test_boost_interval * HZ;
- n_rcu_torture_boosts++;
mutex_unlock(&boost_mutex);
break;
}
@@ -1010,7 +1116,7 @@ rcu_torture_writer(void *arg)
break;
}
}
- rcutorture_record_progress(++rcu_torture_current_version);
+ rcu_torture_current_version++;
/* Cycle through nesting levels of rcu_expedite_gp() calls. */
if (can_expedite &&
!(torture_random(&rand) & 0xff & (!!expediting - 1))) {
@@ -1084,27 +1190,133 @@ static void rcu_torture_timer_cb(struct rcu_head *rhp)
}
/*
- * RCU torture reader from timer handler. Dereferences rcu_torture_current,
- * incrementing the corresponding element of the pipeline array. The
- * counter in the element should never be greater than 1, otherwise, the
- * RCU implementation is broken.
+ * Do one extension of an RCU read-side critical section using the
+ * current reader state in readstate (set to zero for initial entry
+ * to extended critical section), set the new state as specified by
+ * newstate (set to zero for final exit from extended critical section),
+ * and random-number-generator state in trsp. If this is neither the
+ * beginning or end of the critical section and if there was actually a
+ * change, do a ->read_delay().
*/
-static void rcu_torture_timer(struct timer_list *unused)
+static void rcutorture_one_extend(int *readstate, int newstate,
+ struct torture_random_state *trsp)
+{
+ int idxnew = -1;
+ int idxold = *readstate;
+ int statesnew = ~*readstate & newstate;
+ int statesold = *readstate & ~newstate;
+
+ WARN_ON_ONCE(idxold < 0);
+ WARN_ON_ONCE((idxold >> RCUTORTURE_RDR_SHIFT) > 1);
+
+ /* First, put new protection in place to avoid critical-section gap. */
+ if (statesnew & RCUTORTURE_RDR_BH)
+ local_bh_disable();
+ if (statesnew & RCUTORTURE_RDR_IRQ)
+ local_irq_disable();
+ if (statesnew & RCUTORTURE_RDR_PREEMPT)
+ preempt_disable();
+ if (statesnew & RCUTORTURE_RDR_RCU)
+ idxnew = cur_ops->readlock() << RCUTORTURE_RDR_SHIFT;
+
+ /* Next, remove old protection, irq first due to bh conflict. */
+ if (statesold & RCUTORTURE_RDR_IRQ)
+ local_irq_enable();
+ if (statesold & RCUTORTURE_RDR_BH)
+ local_bh_enable();
+ if (statesold & RCUTORTURE_RDR_PREEMPT)
+ preempt_enable();
+ if (statesold & RCUTORTURE_RDR_RCU)
+ cur_ops->readunlock(idxold >> RCUTORTURE_RDR_SHIFT);
+
+ /* Delay if neither beginning nor end and there was a change. */
+ if ((statesnew || statesold) && *readstate && newstate)
+ cur_ops->read_delay(trsp);
+
+ /* Update the reader state. */
+ if (idxnew == -1)
+ idxnew = idxold & ~RCUTORTURE_RDR_MASK;
+ WARN_ON_ONCE(idxnew < 0);
+ WARN_ON_ONCE((idxnew >> RCUTORTURE_RDR_SHIFT) > 1);
+ *readstate = idxnew | newstate;
+ WARN_ON_ONCE((*readstate >> RCUTORTURE_RDR_SHIFT) < 0);
+ WARN_ON_ONCE((*readstate >> RCUTORTURE_RDR_SHIFT) > 1);
+}
+
+/* Return the biggest extendables mask given current RCU and boot parameters. */
+static int rcutorture_extend_mask_max(void)
+{
+ int mask;
+
+ WARN_ON_ONCE(extendables & ~RCUTORTURE_MAX_EXTEND);
+ mask = extendables & RCUTORTURE_MAX_EXTEND & cur_ops->extendables;
+ mask = mask | RCUTORTURE_RDR_RCU;
+ return mask;
+}
+
+/* Return a random protection state mask, but with at least one bit set. */
+static int
+rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp)
+{
+ int mask = rcutorture_extend_mask_max();
+ unsigned long randmask1 = torture_random(trsp) >> 8;
+ unsigned long randmask2 = randmask1 >> 1;
+
+ WARN_ON_ONCE(mask >> RCUTORTURE_RDR_SHIFT);
+ /* Half the time lots of bits, half the time only one bit. */
+ if (randmask1 & 0x1)
+ mask = mask & randmask2;
+ else
+ mask = mask & (1 << (randmask2 % RCUTORTURE_RDR_NBITS));
+ if ((mask & RCUTORTURE_RDR_IRQ) &&
+ !(mask & RCUTORTURE_RDR_BH) &&
+ (oldmask & RCUTORTURE_RDR_BH))
+ mask |= RCUTORTURE_RDR_BH; /* Can't enable bh w/irq disabled. */
+ if ((mask & RCUTORTURE_RDR_IRQ) &&
+ !(mask & cur_ops->ext_irq_conflict) &&
+ (oldmask & cur_ops->ext_irq_conflict))
+ mask |= cur_ops->ext_irq_conflict; /* Or if readers object. */
+ return mask ?: RCUTORTURE_RDR_RCU;
+}
+
+/*
+ * Do a randomly selected number of extensions of an existing RCU read-side
+ * critical section.
+ */
+static void rcutorture_loop_extend(int *readstate,
+ struct torture_random_state *trsp)
+{
+ int i;
+ int mask = rcutorture_extend_mask_max();
+
+ WARN_ON_ONCE(!*readstate); /* -Existing- RCU read-side critsect! */
+ if (!((mask - 1) & mask))
+ return; /* Current RCU flavor not extendable. */
+ i = (torture_random(trsp) >> 3) & RCUTORTURE_RDR_MAX_LOOPS;
+ while (i--) {
+ mask = rcutorture_extend_mask(*readstate, trsp);
+ rcutorture_one_extend(readstate, mask, trsp);
+ }
+}
+
+/*
+ * Do one read-side critical section, returning false if there was
+ * no data to read. Can be invoked both from process context and
+ * from a timer handler.
+ */
+static bool rcu_torture_one_read(struct torture_random_state *trsp)
{
- int idx;
unsigned long started;
unsigned long completed;
- static DEFINE_TORTURE_RANDOM(rand);
- static DEFINE_SPINLOCK(rand_lock);
+ int newstate;
struct rcu_torture *p;
int pipe_count;
+ int readstate = 0;
unsigned long long ts;
- idx = cur_ops->readlock();
- if (cur_ops->started)
- started = cur_ops->started();
- else
- started = cur_ops->completed();
+ newstate = rcutorture_extend_mask(readstate, trsp);
+ rcutorture_one_extend(&readstate, newstate, trsp);
+ started = cur_ops->get_gp_seq();
ts = rcu_trace_clock_local();
p = rcu_dereference_check(rcu_torture_current,
rcu_read_lock_bh_held() ||
@@ -1112,39 +1324,50 @@ static void rcu_torture_timer(struct timer_list *unused)
srcu_read_lock_held(srcu_ctlp) ||
torturing_tasks());
if (p == NULL) {
- /* Leave because rcu_torture_writer is not yet underway */
- cur_ops->readunlock(idx);
- return;
+ /* Wait for rcu_torture_writer to get underway */
+ rcutorture_one_extend(&readstate, 0, trsp);
+ return false;
}
if (p->rtort_mbtest == 0)
atomic_inc(&n_rcu_torture_mberror);
- spin_lock(&rand_lock);
- cur_ops->read_delay(&rand);
- n_rcu_torture_timers++;
- spin_unlock(&rand_lock);
+ rcutorture_loop_extend(&readstate, trsp);
preempt_disable();
pipe_count = p->rtort_pipe_count;
if (pipe_count > RCU_TORTURE_PIPE_LEN) {
/* Should not happen, but... */
pipe_count = RCU_TORTURE_PIPE_LEN;
}
- completed = cur_ops->completed();
+ completed = cur_ops->get_gp_seq();
if (pipe_count > 1) {
- do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, ts,
- started, completed);
+ do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu,
+ ts, started, completed);
rcu_ftrace_dump(DUMP_ALL);
}
__this_cpu_inc(rcu_torture_count[pipe_count]);
- completed = completed - started;
- if (cur_ops->started)
- completed++;
+ completed = rcutorture_seq_diff(completed, started);
if (completed > RCU_TORTURE_PIPE_LEN) {
/* Should not happen, but... */
completed = RCU_TORTURE_PIPE_LEN;
}
__this_cpu_inc(rcu_torture_batch[completed]);
preempt_enable();
- cur_ops->readunlock(idx);
+ rcutorture_one_extend(&readstate, 0, trsp);
+ WARN_ON_ONCE(readstate & RCUTORTURE_RDR_MASK);
+ return true;
+}
+
+static DEFINE_TORTURE_RANDOM_PERCPU(rcu_torture_timer_rand);
+
+/*
+ * RCU torture reader from timer handler. Dereferences rcu_torture_current,
+ * incrementing the corresponding element of the pipeline array. The
+ * counter in the element should never be greater than 1, otherwise, the
+ * RCU implementation is broken.
+ */
+static void rcu_torture_timer(struct timer_list *unused)
+{
+ atomic_long_inc(&n_rcu_torture_timers);
+ (void)rcu_torture_one_read(this_cpu_ptr(&rcu_torture_timer_rand));
/* Test call_rcu() invocation from interrupt handler. */
if (cur_ops->call) {
@@ -1164,14 +1387,8 @@ static void rcu_torture_timer(struct timer_list *unused)
static int
rcu_torture_reader(void *arg)
{
- unsigned long started;
- unsigned long completed;
- int idx;
DEFINE_TORTURE_RANDOM(rand);
- struct rcu_torture *p;
- int pipe_count;
struct timer_list t;
- unsigned long long ts;
VERBOSE_TOROUT_STRING("rcu_torture_reader task started");
set_user_nice(current, MAX_NICE);
@@ -1183,49 +1400,8 @@ rcu_torture_reader(void *arg)
if (!timer_pending(&t))
mod_timer(&t, jiffies + 1);
}
- idx = cur_ops->readlock();
- if (cur_ops->started)
- started = cur_ops->started();
- else
- started = cur_ops->completed();
- ts = rcu_trace_clock_local();
- p = rcu_dereference_check(rcu_torture_current,
- rcu_read_lock_bh_held() ||
- rcu_read_lock_sched_held() ||
- srcu_read_lock_held(srcu_ctlp) ||
- torturing_tasks());
- if (p == NULL) {
- /* Wait for rcu_torture_writer to get underway */
- cur_ops->readunlock(idx);
+ if (!rcu_torture_one_read(&rand))
schedule_timeout_interruptible(HZ);
- continue;
- }
- if (p->rtort_mbtest == 0)
- atomic_inc(&n_rcu_torture_mberror);
- cur_ops->read_delay(&rand);
- preempt_disable();
- pipe_count = p->rtort_pipe_count;
- if (pipe_count > RCU_TORTURE_PIPE_LEN) {
- /* Should not happen, but... */
- pipe_count = RCU_TORTURE_PIPE_LEN;
- }
- completed = cur_ops->completed();
- if (pipe_count > 1) {
- do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu,
- ts, started, completed);
- rcu_ftrace_dump(DUMP_ALL);
- }
- __this_cpu_inc(rcu_torture_count[pipe_count]);
- completed = completed - started;
- if (cur_ops->started)
- completed++;
- if (completed > RCU_TORTURE_PIPE_LEN) {
- /* Should not happen, but... */
- completed = RCU_TORTURE_PIPE_LEN;
- }
- __this_cpu_inc(rcu_torture_batch[completed]);
- preempt_enable();
- cur_ops->readunlock(idx);
stutter_wait("rcu_torture_reader");
} while (!torture_must_stop());
if (irqreader && cur_ops->irq_capable) {
@@ -1282,7 +1458,7 @@ rcu_torture_stats_print(void)
pr_cont("rtbf: %ld rtb: %ld nt: %ld ",
n_rcu_torture_boost_failure,
n_rcu_torture_boosts,
- n_rcu_torture_timers);
+ atomic_long_read(&n_rcu_torture_timers));
torture_onoff_stats();
pr_cont("barrier: %ld/%ld:%ld ",
n_barrier_successes,
@@ -1324,18 +1500,16 @@ rcu_torture_stats_print(void)
if (rtcv_snap == rcu_torture_current_version &&
rcu_torture_current != NULL) {
int __maybe_unused flags = 0;
- unsigned long __maybe_unused gpnum = 0;
- unsigned long __maybe_unused completed = 0;
+ unsigned long __maybe_unused gp_seq = 0;
rcutorture_get_gp_data(cur_ops->ttype,
- &flags, &gpnum, &completed);
+ &flags, &gp_seq);
srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp,
- &flags, &gpnum, &completed);
+ &flags, &gp_seq);
wtp = READ_ONCE(writer_task);
- pr_alert("??? Writer stall state %s(%d) g%lu c%lu f%#x ->state %#lx cpu %d\n",
+ pr_alert("??? Writer stall state %s(%d) g%lu f%#x ->state %#lx cpu %d\n",
rcu_torture_writer_state_getname(),
- rcu_torture_writer_state,
- gpnum, completed, flags,
+ rcu_torture_writer_state, gp_seq, flags,
wtp == NULL ? ~0UL : wtp->state,
wtp == NULL ? -1 : (int)task_cpu(wtp));
if (!splatted && wtp) {
@@ -1365,7 +1539,7 @@ rcu_torture_stats(void *arg)
return 0;
}
-static inline void
+static void
rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag)
{
pr_alert("%s" TORTURE_FLAG
@@ -1397,6 +1571,7 @@ static int rcutorture_booster_cleanup(unsigned int cpu)
mutex_lock(&boost_mutex);
t = boost_tasks[cpu];
boost_tasks[cpu] = NULL;
+ rcu_torture_enable_rt_throttle();
mutex_unlock(&boost_mutex);
/* This must be outside of the mutex, otherwise deadlock! */
@@ -1413,6 +1588,7 @@ static int rcutorture_booster_init(unsigned int cpu)
/* Don't allow time recalculation while creating a new task. */
mutex_lock(&boost_mutex);
+ rcu_torture_disable_rt_throttle();
VERBOSE_TOROUT_STRING("Creating rcu_torture_boost task");
boost_tasks[cpu] = kthread_create_on_node(rcu_torture_boost, NULL,
cpu_to_node(cpu),
@@ -1446,7 +1622,7 @@ static int rcu_torture_stall(void *args)
VERBOSE_TOROUT_STRING("rcu_torture_stall end holdoff");
}
if (!kthread_should_stop()) {
- stop_at = get_seconds() + stall_cpu;
+ stop_at = ktime_get_seconds() + stall_cpu;
/* RCU CPU stall is expected behavior in following code. */
rcu_read_lock();
if (stall_cpu_irqsoff)
@@ -1455,7 +1631,8 @@ static int rcu_torture_stall(void *args)
preempt_disable();
pr_alert("rcu_torture_stall start on CPU %d.\n",
smp_processor_id());
- while (ULONG_CMP_LT(get_seconds(), stop_at))
+ while (ULONG_CMP_LT((unsigned long)ktime_get_seconds(),
+ stop_at))
continue; /* Induce RCU CPU stall warning. */
if (stall_cpu_irqsoff)
local_irq_enable();
@@ -1546,8 +1723,9 @@ static int rcu_torture_barrier(void *arg)
atomic_read(&barrier_cbs_invoked),
n_barrier_cbs);
WARN_ON_ONCE(1);
+ } else {
+ n_barrier_successes++;
}
- n_barrier_successes++;
schedule_timeout_interruptible(HZ / 10);
} while (!torture_must_stop());
torture_kthread_stopping("rcu_torture_barrier");
@@ -1610,17 +1788,39 @@ static void rcu_torture_barrier_cleanup(void)
}
}
+static bool rcu_torture_can_boost(void)
+{
+ static int boost_warn_once;
+ int prio;
+
+ if (!(test_boost == 1 && cur_ops->can_boost) && test_boost != 2)
+ return false;
+
+ prio = rcu_get_gp_kthreads_prio();
+ if (!prio)
+ return false;
+
+ if (prio < 2) {
+ if (boost_warn_once == 1)
+ return false;
+
+ pr_alert("%s: WARN: RCU kthread priority too low to test boosting. Skipping RCU boost test. Try passing rcutree.kthread_prio > 1 on the kernel command line.\n", KBUILD_MODNAME);
+ boost_warn_once = 1;
+ return false;
+ }
+
+ return true;
+}
+
static enum cpuhp_state rcutor_hp;
static void
rcu_torture_cleanup(void)
{
int flags = 0;
- unsigned long gpnum = 0;
- unsigned long completed = 0;
+ unsigned long gp_seq = 0;
int i;
- rcutorture_record_test_transition();
if (torture_cleanup_begin()) {
if (cur_ops->cb_barrier != NULL)
cur_ops->cb_barrier();
@@ -1648,17 +1848,15 @@ rcu_torture_cleanup(void)
fakewriter_tasks = NULL;
}
- rcutorture_get_gp_data(cur_ops->ttype, &flags, &gpnum, &completed);
- srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp,
- &flags, &gpnum, &completed);
- pr_alert("%s: End-test grace-period state: g%lu c%lu f%#x\n",
- cur_ops->name, gpnum, completed, flags);
+ rcutorture_get_gp_data(cur_ops->ttype, &flags, &gp_seq);
+ srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp, &flags, &gp_seq);
+ pr_alert("%s: End-test grace-period state: g%lu f%#x\n",
+ cur_ops->name, gp_seq, flags);
torture_stop_kthread(rcu_torture_stats, stats_task);
torture_stop_kthread(rcu_torture_fqs, fqs_task);
for (i = 0; i < ncbflooders; i++)
torture_stop_kthread(rcu_torture_cbflood, cbflood_task[i]);
- if ((test_boost == 1 && cur_ops->can_boost) ||
- test_boost == 2)
+ if (rcu_torture_can_boost())
cpuhp_remove_state(rcutor_hp);
/*
@@ -1746,7 +1944,7 @@ rcu_torture_init(void)
int firsterr = 0;
static struct rcu_torture_ops *torture_ops[] = {
&rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &srcud_ops,
- &sched_ops, &tasks_ops,
+ &busted_srcud_ops, &sched_ops, &tasks_ops,
};
if (!torture_init_begin(torture_type, verbose))
@@ -1763,8 +1961,8 @@ rcu_torture_init(void)
torture_type);
pr_alert("rcu-torture types:");
for (i = 0; i < ARRAY_SIZE(torture_ops); i++)
- pr_alert(" %s", torture_ops[i]->name);
- pr_alert("\n");
+ pr_cont(" %s", torture_ops[i]->name);
+ pr_cont("\n");
firsterr = -EINVAL;
goto unwind;
}
@@ -1882,8 +2080,7 @@ rcu_torture_init(void)
test_boost_interval = 1;
if (test_boost_duration < 2)
test_boost_duration = 2;
- if ((test_boost == 1 && cur_ops->can_boost) ||
- test_boost == 2) {
+ if (rcu_torture_can_boost()) {
boost_starttime = jiffies + test_boost_interval * HZ;
@@ -1897,7 +2094,7 @@ rcu_torture_init(void)
firsterr = torture_shutdown_init(shutdown_secs, rcu_torture_cleanup);
if (firsterr)
goto unwind;
- firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval * HZ);
+ firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval);
if (firsterr)
goto unwind;
firsterr = rcu_torture_stall_init();
@@ -1926,7 +2123,6 @@ rcu_torture_init(void)
goto unwind;
}
}
- rcutorture_record_test_transition();
torture_init_end();
return 0;
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index 622792abe41a..04fc2ed71af8 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -110,7 +110,7 @@ void __srcu_read_unlock(struct srcu_struct *sp, int idx)
WRITE_ONCE(sp->srcu_lock_nesting[idx], newval);
if (!newval && READ_ONCE(sp->srcu_gp_waiting))
- swake_up(&sp->srcu_wq);
+ swake_up_one(&sp->srcu_wq);
}
EXPORT_SYMBOL_GPL(__srcu_read_unlock);
@@ -140,7 +140,7 @@ void srcu_drive_gp(struct work_struct *wp)
idx = sp->srcu_idx;
WRITE_ONCE(sp->srcu_idx, !sp->srcu_idx);
WRITE_ONCE(sp->srcu_gp_waiting, true); /* srcu_read_unlock() wakes! */
- swait_event(sp->srcu_wq, !READ_ONCE(sp->srcu_lock_nesting[idx]));
+ swait_event_exclusive(sp->srcu_wq, !READ_ONCE(sp->srcu_lock_nesting[idx]));
WRITE_ONCE(sp->srcu_gp_waiting, false); /* srcu_read_unlock() cheap. */
/* Invoke the callbacks we removed above. */
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index b4123d7a2cec..6c9866a854b1 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -26,6 +26,8 @@
*
*/
+#define pr_fmt(fmt) "rcu: " fmt
+
#include <linux/export.h>
#include <linux/mutex.h>
#include <linux/percpu.h>
@@ -390,7 +392,8 @@ void _cleanup_srcu_struct(struct srcu_struct *sp, bool quiesced)
}
if (WARN_ON(rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) != SRCU_STATE_IDLE) ||
WARN_ON(srcu_readers_active(sp))) {
- pr_info("%s: Active srcu_struct %p state: %d\n", __func__, sp, rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)));
+ pr_info("%s: Active srcu_struct %p state: %d\n",
+ __func__, sp, rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)));
return; /* Caller forgot to stop doing call_srcu()? */
}
free_percpu(sp->sda);
@@ -641,6 +644,9 @@ static void srcu_funnel_exp_start(struct srcu_struct *sp, struct srcu_node *snp,
* period s. Losers must either ensure that their desired grace-period
* number is recorded on at least their leaf srcu_node structure, or they
* must take steps to invoke their own callbacks.
+ *
+ * Note that this function also does the work of srcu_funnel_exp_start(),
+ * in some cases by directly invoking it.
*/
static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp,
unsigned long s, bool do_norm)
@@ -823,17 +829,17 @@ static void srcu_leak_callback(struct rcu_head *rhp)
* more than one CPU, this means that when "func()" is invoked, each CPU
* is guaranteed to have executed a full memory barrier since the end of
* its last corresponding SRCU read-side critical section whose beginning
- * preceded the call to call_rcu(). It also means that each CPU executing
+ * preceded the call to call_srcu(). It also means that each CPU executing
* an SRCU read-side critical section that continues beyond the start of
- * "func()" must have executed a memory barrier after the call_rcu()
+ * "func()" must have executed a memory barrier after the call_srcu()
* but before the beginning of that SRCU read-side critical section.
* Note that these guarantees include CPUs that are offline, idle, or
* executing in user mode, as well as CPUs that are executing in the kernel.
*
- * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the
+ * Furthermore, if CPU A invoked call_srcu() and CPU B invoked the
* resulting SRCU callback function "func()", then both CPU A and CPU
* B are guaranteed to execute a full memory barrier during the time
- * interval between the call to call_rcu() and the invocation of "func()".
+ * interval between the call to call_srcu() and the invocation of "func()".
* This guarantee applies even if CPU A and CPU B are the same CPU (but
* again only if the system has more than one CPU).
*
@@ -1246,13 +1252,12 @@ static void process_srcu(struct work_struct *work)
void srcutorture_get_gp_data(enum rcutorture_type test_type,
struct srcu_struct *sp, int *flags,
- unsigned long *gpnum, unsigned long *completed)
+ unsigned long *gp_seq)
{
if (test_type != SRCU_FLAVOR)
return;
*flags = 0;
- *completed = rcu_seq_ctr(sp->srcu_gp_seq);
- *gpnum = rcu_seq_ctr(sp->srcu_gp_seq_needed);
+ *gp_seq = rcu_seq_current(&sp->srcu_gp_seq);
}
EXPORT_SYMBOL_GPL(srcutorture_get_gp_data);
@@ -1263,16 +1268,17 @@ void srcu_torture_stats_print(struct srcu_struct *sp, char *tt, char *tf)
unsigned long s0 = 0, s1 = 0;
idx = sp->srcu_idx & 0x1;
- pr_alert("%s%s Tree SRCU per-CPU(idx=%d):", tt, tf, idx);
+ pr_alert("%s%s Tree SRCU g%ld per-CPU(idx=%d):",
+ tt, tf, rcu_seq_current(&sp->srcu_gp_seq), idx);
for_each_possible_cpu(cpu) {
unsigned long l0, l1;
unsigned long u0, u1;
long c0, c1;
- struct srcu_data *counts;
+ struct srcu_data *sdp;
- counts = per_cpu_ptr(sp->sda, cpu);
- u0 = counts->srcu_unlock_count[!idx];
- u1 = counts->srcu_unlock_count[idx];
+ sdp = per_cpu_ptr(sp->sda, cpu);
+ u0 = sdp->srcu_unlock_count[!idx];
+ u1 = sdp->srcu_unlock_count[idx];
/*
* Make sure that a lock is always counted if the corresponding
@@ -1280,12 +1286,13 @@ void srcu_torture_stats_print(struct srcu_struct *sp, char *tt, char *tf)
*/
smp_rmb();
- l0 = counts->srcu_lock_count[!idx];
- l1 = counts->srcu_lock_count[idx];
+ l0 = sdp->srcu_lock_count[!idx];
+ l1 = sdp->srcu_lock_count[idx];
c0 = l0 - u0;
c1 = l1 - u1;
- pr_cont(" %d(%ld,%ld)", cpu, c0, c1);
+ pr_cont(" %d(%ld,%ld %1p)",
+ cpu, c0, c1, rcu_segcblist_head(&sdp->srcu_cblist));
s0 += c0;
s1 += c1;
}
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index a64eee0db39e..befc9321a89c 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -122,10 +122,8 @@ void rcu_check_callbacks(int user)
{
if (user)
rcu_sched_qs();
- else if (!in_softirq())
+ if (user || !in_softirq())
rcu_bh_qs();
- if (user)
- rcu_note_voluntary_context_switch(current);
}
/*
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index aa7cade1b9f3..0b760c1369f7 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -27,6 +27,9 @@
* For detailed explanation of Read-Copy Update mechanism see -
* Documentation/RCU
*/
+
+#define pr_fmt(fmt) "rcu: " fmt
+
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/init.h>
@@ -95,13 +98,13 @@ struct rcu_state sname##_state = { \
.rda = &sname##_data, \
.call = cr, \
.gp_state = RCU_GP_IDLE, \
- .gpnum = 0UL - 300UL, \
- .completed = 0UL - 300UL, \
+ .gp_seq = (0UL - 300UL) << RCU_SEQ_CTR_SHIFT, \
.barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \
.name = RCU_STATE_NAME(sname), \
.abbr = sabbr, \
.exp_mutex = __MUTEX_INITIALIZER(sname##_state.exp_mutex), \
.exp_wake_mutex = __MUTEX_INITIALIZER(sname##_state.exp_wake_mutex), \
+ .ofl_lock = __SPIN_LOCK_UNLOCKED(sname##_state.ofl_lock), \
}
RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched);
@@ -155,6 +158,9 @@ EXPORT_SYMBOL_GPL(rcu_scheduler_active);
*/
static int rcu_scheduler_fully_active __read_mostly;
+static void
+rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
+ struct rcu_node *rnp, unsigned long gps, unsigned long flags);
static void rcu_init_new_rnp(struct rcu_node *rnp_leaf);
static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf);
static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu);
@@ -177,6 +183,13 @@ module_param(gp_init_delay, int, 0444);
static int gp_cleanup_delay;
module_param(gp_cleanup_delay, int, 0444);
+/* Retreive RCU kthreads priority for rcutorture */
+int rcu_get_gp_kthreads_prio(void)
+{
+ return kthread_prio;
+}
+EXPORT_SYMBOL_GPL(rcu_get_gp_kthreads_prio);
+
/*
* Number of grace periods between delays, normalized by the duration of
* the delay. The longer the delay, the more the grace periods between
@@ -189,18 +202,6 @@ module_param(gp_cleanup_delay, int, 0444);
#define PER_RCU_NODE_PERIOD 3 /* Number of grace periods between delays. */
/*
- * Track the rcutorture test sequence number and the update version
- * number within a given test. The rcutorture_testseq is incremented
- * on every rcutorture module load and unload, so has an odd value
- * when a test is running. The rcutorture_vernum is set to zero
- * when rcutorture starts and is incremented on each rcutorture update.
- * These variables enable correlating rcutorture output with the
- * RCU tracing information.
- */
-unsigned long rcutorture_testseq;
-unsigned long rcutorture_vernum;
-
-/*
* Compute the mask of online CPUs for the specified rcu_node structure.
* This will not be stable unless the rcu_node structure's ->lock is
* held, but the bit corresponding to the current CPU will be stable
@@ -218,7 +219,7 @@ unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp)
*/
static int rcu_gp_in_progress(struct rcu_state *rsp)
{
- return READ_ONCE(rsp->completed) != READ_ONCE(rsp->gpnum);
+ return rcu_seq_state(rcu_seq_current(&rsp->gp_seq));
}
/*
@@ -233,7 +234,7 @@ void rcu_sched_qs(void)
if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.s))
return;
trace_rcu_grace_period(TPS("rcu_sched"),
- __this_cpu_read(rcu_sched_data.gpnum),
+ __this_cpu_read(rcu_sched_data.gp_seq),
TPS("cpuqs"));
__this_cpu_write(rcu_sched_data.cpu_no_qs.b.norm, false);
if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp))
@@ -248,7 +249,7 @@ void rcu_bh_qs(void)
RCU_LOCKDEP_WARN(preemptible(), "rcu_bh_qs() invoked with preemption enabled!!!");
if (__this_cpu_read(rcu_bh_data.cpu_no_qs.s)) {
trace_rcu_grace_period(TPS("rcu_bh"),
- __this_cpu_read(rcu_bh_data.gpnum),
+ __this_cpu_read(rcu_bh_data.gp_seq),
TPS("cpuqs"));
__this_cpu_write(rcu_bh_data.cpu_no_qs.b.norm, false);
}
@@ -380,20 +381,6 @@ static bool rcu_dynticks_in_eqs_since(struct rcu_dynticks *rdtp, int snap)
}
/*
- * Do a double-increment of the ->dynticks counter to emulate a
- * momentary idle-CPU quiescent state.
- */
-static void rcu_dynticks_momentary_idle(void)
-{
- struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
- int special = atomic_add_return(2 * RCU_DYNTICK_CTRL_CTR,
- &rdtp->dynticks);
-
- /* It is illegal to call this from idle state. */
- WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR));
-}
-
-/*
* Set the special (bottom) bit of the specified CPU so that it
* will take special action (such as flushing its TLB) on the
* next exit from an extended quiescent state. Returns true if
@@ -424,12 +411,17 @@ bool rcu_eqs_special_set(int cpu)
*
* We inform the RCU core by emulating a zero-duration dyntick-idle period.
*
- * The caller must have disabled interrupts.
+ * The caller must have disabled interrupts and must not be idle.
*/
static void rcu_momentary_dyntick_idle(void)
{
+ struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+ int special;
+
raw_cpu_write(rcu_dynticks.rcu_need_heavy_qs, false);
- rcu_dynticks_momentary_idle();
+ special = atomic_add_return(2 * RCU_DYNTICK_CTRL_CTR, &rdtp->dynticks);
+ /* It is illegal to call this from idle state. */
+ WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR));
}
/*
@@ -451,7 +443,7 @@ void rcu_note_context_switch(bool preempt)
rcu_momentary_dyntick_idle();
this_cpu_inc(rcu_dynticks.rcu_qs_ctr);
if (!preempt)
- rcu_note_voluntary_context_switch_lite(current);
+ rcu_tasks_qs(current);
out:
trace_rcu_utilization(TPS("End context switch"));
barrier(); /* Avoid RCU read-side critical sections leaking up. */
@@ -513,8 +505,38 @@ static ulong jiffies_till_first_fqs = ULONG_MAX;
static ulong jiffies_till_next_fqs = ULONG_MAX;
static bool rcu_kick_kthreads;
-module_param(jiffies_till_first_fqs, ulong, 0644);
-module_param(jiffies_till_next_fqs, ulong, 0644);
+static int param_set_first_fqs_jiffies(const char *val, const struct kernel_param *kp)
+{
+ ulong j;
+ int ret = kstrtoul(val, 0, &j);
+
+ if (!ret)
+ WRITE_ONCE(*(ulong *)kp->arg, (j > HZ) ? HZ : j);
+ return ret;
+}
+
+static int param_set_next_fqs_jiffies(const char *val, const struct kernel_param *kp)
+{
+ ulong j;
+ int ret = kstrtoul(val, 0, &j);
+
+ if (!ret)
+ WRITE_ONCE(*(ulong *)kp->arg, (j > HZ) ? HZ : (j ?: 1));
+ return ret;
+}
+
+static struct kernel_param_ops first_fqs_jiffies_ops = {
+ .set = param_set_first_fqs_jiffies,
+ .get = param_get_ulong,
+};
+
+static struct kernel_param_ops next_fqs_jiffies_ops = {
+ .set = param_set_next_fqs_jiffies,
+ .get = param_get_ulong,
+};
+
+module_param_cb(jiffies_till_first_fqs, &first_fqs_jiffies_ops, &jiffies_till_first_fqs, 0644);
+module_param_cb(jiffies_till_next_fqs, &next_fqs_jiffies_ops, &jiffies_till_next_fqs, 0644);
module_param(rcu_kick_kthreads, bool, 0644);
/*
@@ -529,58 +551,31 @@ static void force_quiescent_state(struct rcu_state *rsp);
static int rcu_pending(void);
/*
- * Return the number of RCU batches started thus far for debug & stats.
+ * Return the number of RCU GPs completed thus far for debug & stats.
*/
-unsigned long rcu_batches_started(void)
+unsigned long rcu_get_gp_seq(void)
{
- return rcu_state_p->gpnum;
+ return READ_ONCE(rcu_state_p->gp_seq);
}
-EXPORT_SYMBOL_GPL(rcu_batches_started);
+EXPORT_SYMBOL_GPL(rcu_get_gp_seq);
/*
- * Return the number of RCU-sched batches started thus far for debug & stats.
+ * Return the number of RCU-sched GPs completed thus far for debug & stats.
*/
-unsigned long rcu_batches_started_sched(void)
+unsigned long rcu_sched_get_gp_seq(void)
{
- return rcu_sched_state.gpnum;
+ return READ_ONCE(rcu_sched_state.gp_seq);
}
-EXPORT_SYMBOL_GPL(rcu_batches_started_sched);
+EXPORT_SYMBOL_GPL(rcu_sched_get_gp_seq);
/*
- * Return the number of RCU BH batches started thus far for debug & stats.
+ * Return the number of RCU-bh GPs completed thus far for debug & stats.
*/
-unsigned long rcu_batches_started_bh(void)
+unsigned long rcu_bh_get_gp_seq(void)
{
- return rcu_bh_state.gpnum;
+ return READ_ONCE(rcu_bh_state.gp_seq);
}
-EXPORT_SYMBOL_GPL(rcu_batches_started_bh);
-
-/*
- * Return the number of RCU batches completed thus far for debug & stats.
- */
-unsigned long rcu_batches_completed(void)
-{
- return rcu_state_p->completed;
-}
-EXPORT_SYMBOL_GPL(rcu_batches_completed);
-
-/*
- * Return the number of RCU-sched batches completed thus far for debug & stats.
- */
-unsigned long rcu_batches_completed_sched(void)
-{
- return rcu_sched_state.completed;
-}
-EXPORT_SYMBOL_GPL(rcu_batches_completed_sched);
-
-/*
- * Return the number of RCU BH batches completed thus far for debug & stats.
- */
-unsigned long rcu_batches_completed_bh(void)
-{
- return rcu_bh_state.completed;
-}
-EXPORT_SYMBOL_GPL(rcu_batches_completed_bh);
+EXPORT_SYMBOL_GPL(rcu_bh_get_gp_seq);
/*
* Return the number of RCU expedited batches completed thus far for
@@ -636,35 +631,42 @@ EXPORT_SYMBOL_GPL(rcu_sched_force_quiescent_state);
*/
void show_rcu_gp_kthreads(void)
{
+ int cpu;
+ struct rcu_data *rdp;
+ struct rcu_node *rnp;
struct rcu_state *rsp;
for_each_rcu_flavor(rsp) {
pr_info("%s: wait state: %d ->state: %#lx\n",
rsp->name, rsp->gp_state, rsp->gp_kthread->state);
+ rcu_for_each_node_breadth_first(rsp, rnp) {
+ if (ULONG_CMP_GE(rsp->gp_seq, rnp->gp_seq_needed))
+ continue;
+ pr_info("\trcu_node %d:%d ->gp_seq %lu ->gp_seq_needed %lu\n",
+ rnp->grplo, rnp->grphi, rnp->gp_seq,
+ rnp->gp_seq_needed);
+ if (!rcu_is_leaf_node(rnp))
+ continue;
+ for_each_leaf_node_possible_cpu(rnp, cpu) {
+ rdp = per_cpu_ptr(rsp->rda, cpu);
+ if (rdp->gpwrap ||
+ ULONG_CMP_GE(rsp->gp_seq,
+ rdp->gp_seq_needed))
+ continue;
+ pr_info("\tcpu %d ->gp_seq_needed %lu\n",
+ cpu, rdp->gp_seq_needed);
+ }
+ }
/* sched_show_task(rsp->gp_kthread); */
}
}
EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads);
/*
- * Record the number of times rcutorture tests have been initiated and
- * terminated. This information allows the debugfs tracing stats to be
- * correlated to the rcutorture messages, even when the rcutorture module
- * is being repeatedly loaded and unloaded. In other words, we cannot
- * store this state in rcutorture itself.
- */
-void rcutorture_record_test_transition(void)
-{
- rcutorture_testseq++;
- rcutorture_vernum = 0;
-}
-EXPORT_SYMBOL_GPL(rcutorture_record_test_transition);
-
-/*
* Send along grace-period-related data for rcutorture diagnostics.
*/
void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
- unsigned long *gpnum, unsigned long *completed)
+ unsigned long *gp_seq)
{
struct rcu_state *rsp = NULL;
@@ -684,23 +686,11 @@ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
if (rsp == NULL)
return;
*flags = READ_ONCE(rsp->gp_flags);
- *gpnum = READ_ONCE(rsp->gpnum);
- *completed = READ_ONCE(rsp->completed);
+ *gp_seq = rcu_seq_current(&rsp->gp_seq);
}
EXPORT_SYMBOL_GPL(rcutorture_get_gp_data);
/*
- * Record the number of writer passes through the current rcutorture test.
- * This is also used to correlate debugfs tracing stats with the rcutorture
- * messages.
- */
-void rcutorture_record_progress(unsigned long vernum)
-{
- rcutorture_vernum++;
-}
-EXPORT_SYMBOL_GPL(rcutorture_record_progress);
-
-/*
* Return the root node of the specified rcu_state structure.
*/
static struct rcu_node *rcu_get_root(struct rcu_state *rsp)
@@ -1059,41 +1049,41 @@ void rcu_request_urgent_qs_task(struct task_struct *t)
#if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU)
/*
- * Is the current CPU online? Disable preemption to avoid false positives
- * that could otherwise happen due to the current CPU number being sampled,
- * this task being preempted, its old CPU being taken offline, resuming
- * on some other CPU, then determining that its old CPU is now offline.
- * It is OK to use RCU on an offline processor during initial boot, hence
- * the check for rcu_scheduler_fully_active. Note also that it is OK
- * for a CPU coming online to use RCU for one jiffy prior to marking itself
- * online in the cpu_online_mask. Similarly, it is OK for a CPU going
- * offline to continue to use RCU for one jiffy after marking itself
- * offline in the cpu_online_mask. This leniency is necessary given the
- * non-atomic nature of the online and offline processing, for example,
- * the fact that a CPU enters the scheduler after completing the teardown
- * of the CPU.
+ * Is the current CPU online as far as RCU is concerned?
*
- * This is also why RCU internally marks CPUs online during in the
- * preparation phase and offline after the CPU has been taken down.
+ * Disable preemption to avoid false positives that could otherwise
+ * happen due to the current CPU number being sampled, this task being
+ * preempted, its old CPU being taken offline, resuming on some other CPU,
+ * then determining that its old CPU is now offline. Because there are
+ * multiple flavors of RCU, and because this function can be called in the
+ * midst of updating the flavors while a given CPU coming online or going
+ * offline, it is necessary to check all flavors. If any of the flavors
+ * believe that given CPU is online, it is considered to be online.
*
- * Disable checking if in an NMI handler because we cannot safely report
- * errors from NMI handlers anyway.
+ * Disable checking if in an NMI handler because we cannot safely
+ * report errors from NMI handlers anyway. In addition, it is OK to use
+ * RCU on an offline processor during initial boot, hence the check for
+ * rcu_scheduler_fully_active.
*/
bool rcu_lockdep_current_cpu_online(void)
{
struct rcu_data *rdp;
struct rcu_node *rnp;
- bool ret;
+ struct rcu_state *rsp;
- if (in_nmi())
+ if (in_nmi() || !rcu_scheduler_fully_active)
return true;
preempt_disable();
- rdp = this_cpu_ptr(&rcu_sched_data);
- rnp = rdp->mynode;
- ret = (rdp->grpmask & rcu_rnp_online_cpus(rnp)) ||
- !rcu_scheduler_fully_active;
+ for_each_rcu_flavor(rsp) {
+ rdp = this_cpu_ptr(rsp->rda);
+ rnp = rdp->mynode;
+ if (rdp->grpmask & rcu_rnp_online_cpus(rnp)) {
+ preempt_enable();
+ return true;
+ }
+ }
preempt_enable();
- return ret;
+ return false;
}
EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online);
@@ -1115,17 +1105,18 @@ static int rcu_is_cpu_rrupt_from_idle(void)
/*
* We are reporting a quiescent state on behalf of some other CPU, so
* it is our responsibility to check for and handle potential overflow
- * of the rcu_node ->gpnum counter with respect to the rcu_data counters.
+ * of the rcu_node ->gp_seq counter with respect to the rcu_data counters.
* After all, the CPU might be in deep idle state, and thus executing no
* code whatsoever.
*/
static void rcu_gpnum_ovf(struct rcu_node *rnp, struct rcu_data *rdp)
{
raw_lockdep_assert_held_rcu_node(rnp);
- if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4, rnp->gpnum))
+ if (ULONG_CMP_LT(rcu_seq_current(&rdp->gp_seq) + ULONG_MAX / 4,
+ rnp->gp_seq))
WRITE_ONCE(rdp->gpwrap, true);
- if (ULONG_CMP_LT(rdp->rcu_iw_gpnum + ULONG_MAX / 4, rnp->gpnum))
- rdp->rcu_iw_gpnum = rnp->gpnum + ULONG_MAX / 4;
+ if (ULONG_CMP_LT(rdp->rcu_iw_gp_seq + ULONG_MAX / 4, rnp->gp_seq))
+ rdp->rcu_iw_gp_seq = rnp->gp_seq + ULONG_MAX / 4;
}
/*
@@ -1137,7 +1128,7 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp)
{
rdp->dynticks_snap = rcu_dynticks_snap(rdp->dynticks);
if (rcu_dynticks_in_eqs(rdp->dynticks_snap)) {
- trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti"));
+ trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("dti"));
rcu_gpnum_ovf(rdp->mynode, rdp);
return 1;
}
@@ -1159,7 +1150,7 @@ static void rcu_iw_handler(struct irq_work *iwp)
rnp = rdp->mynode;
raw_spin_lock_rcu_node(rnp);
if (!WARN_ON_ONCE(!rdp->rcu_iw_pending)) {
- rdp->rcu_iw_gpnum = rnp->gpnum;
+ rdp->rcu_iw_gp_seq = rnp->gp_seq;
rdp->rcu_iw_pending = false;
}
raw_spin_unlock_rcu_node(rnp);
@@ -1187,7 +1178,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
* of the current RCU grace period.
*/
if (rcu_dynticks_in_eqs_since(rdp->dynticks, rdp->dynticks_snap)) {
- trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti"));
+ trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("dti"));
rdp->dynticks_fqs++;
rcu_gpnum_ovf(rnp, rdp);
return 1;
@@ -1203,8 +1194,8 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
ruqp = per_cpu_ptr(&rcu_dynticks.rcu_urgent_qs, rdp->cpu);
if (time_after(jiffies, rdp->rsp->gp_start + jtsq) &&
READ_ONCE(rdp->rcu_qs_ctr_snap) != per_cpu(rcu_dynticks.rcu_qs_ctr, rdp->cpu) &&
- READ_ONCE(rdp->gpnum) == rnp->gpnum && !rdp->gpwrap) {
- trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("rqc"));
+ rcu_seq_current(&rdp->gp_seq) == rnp->gp_seq && !rdp->gpwrap) {
+ trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("rqc"));
rcu_gpnum_ovf(rnp, rdp);
return 1;
} else if (time_after(jiffies, rdp->rsp->gp_start + jtsq)) {
@@ -1212,12 +1203,25 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
smp_store_release(ruqp, true);
}
- /* Check for the CPU being offline. */
- if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp))) {
- trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("ofl"));
- rdp->offline_fqs++;
- rcu_gpnum_ovf(rnp, rdp);
- return 1;
+ /* If waiting too long on an offline CPU, complain. */
+ if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp)) &&
+ time_after(jiffies, rdp->rsp->gp_start + HZ)) {
+ bool onl;
+ struct rcu_node *rnp1;
+
+ WARN_ON(1); /* Offline CPUs are supposed to report QS! */
+ pr_info("%s: grp: %d-%d level: %d ->gp_seq %ld ->completedqs %ld\n",
+ __func__, rnp->grplo, rnp->grphi, rnp->level,
+ (long)rnp->gp_seq, (long)rnp->completedqs);
+ for (rnp1 = rnp; rnp1; rnp1 = rnp1->parent)
+ pr_info("%s: %d:%d ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx ->rcu_gp_init_mask %#lx\n",
+ __func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext, rnp1->rcu_gp_init_mask);
+ onl = !!(rdp->grpmask & rcu_rnp_online_cpus(rnp));
+ pr_info("%s %d: %c online: %ld(%d) offline: %ld(%d)\n",
+ __func__, rdp->cpu, ".o"[onl],
+ (long)rdp->rcu_onl_gp_seq, rdp->rcu_onl_gp_flags,
+ (long)rdp->rcu_ofl_gp_seq, rdp->rcu_ofl_gp_flags);
+ return 1; /* Break things loose after complaining. */
}
/*
@@ -1256,11 +1260,11 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
if (jiffies - rdp->rsp->gp_start > rcu_jiffies_till_stall_check() / 2) {
resched_cpu(rdp->cpu);
if (IS_ENABLED(CONFIG_IRQ_WORK) &&
- !rdp->rcu_iw_pending && rdp->rcu_iw_gpnum != rnp->gpnum &&
+ !rdp->rcu_iw_pending && rdp->rcu_iw_gp_seq != rnp->gp_seq &&
(rnp->ffmask & rdp->grpmask)) {
init_irq_work(&rdp->rcu_iw, rcu_iw_handler);
rdp->rcu_iw_pending = true;
- rdp->rcu_iw_gpnum = rnp->gpnum;
+ rdp->rcu_iw_gp_seq = rnp->gp_seq;
irq_work_queue_on(&rdp->rcu_iw, rdp->cpu);
}
}
@@ -1274,9 +1278,9 @@ static void record_gp_stall_check_time(struct rcu_state *rsp)
unsigned long j1;
rsp->gp_start = j;
- smp_wmb(); /* Record start time before stall time. */
j1 = rcu_jiffies_till_stall_check();
- WRITE_ONCE(rsp->jiffies_stall, j + j1);
+ /* Record ->gp_start before ->jiffies_stall. */
+ smp_store_release(&rsp->jiffies_stall, j + j1); /* ^^^ */
rsp->jiffies_resched = j + j1 / 2;
rsp->n_force_qs_gpstart = READ_ONCE(rsp->n_force_qs);
}
@@ -1302,9 +1306,9 @@ static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp)
j = jiffies;
gpa = READ_ONCE(rsp->gp_activity);
if (j - gpa > 2 * HZ) {
- pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x %s(%d) ->state=%#lx ->cpu=%d\n",
+ pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx ->cpu=%d\n",
rsp->name, j - gpa,
- rsp->gpnum, rsp->completed,
+ (long)rcu_seq_current(&rsp->gp_seq),
rsp->gp_flags,
gp_state_getname(rsp->gp_state), rsp->gp_state,
rsp->gp_kthread ? rsp->gp_kthread->state : ~0,
@@ -1359,16 +1363,15 @@ static void rcu_stall_kick_kthreads(struct rcu_state *rsp)
}
}
-static inline void panic_on_rcu_stall(void)
+static void panic_on_rcu_stall(void)
{
if (sysctl_panic_on_rcu_stall)
panic("RCU Stall\n");
}
-static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
+static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gp_seq)
{
int cpu;
- long delta;
unsigned long flags;
unsigned long gpa;
unsigned long j;
@@ -1381,25 +1384,12 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
if (rcu_cpu_stall_suppress)
return;
- /* Only let one CPU complain about others per time interval. */
-
- raw_spin_lock_irqsave_rcu_node(rnp, flags);
- delta = jiffies - READ_ONCE(rsp->jiffies_stall);
- if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) {
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
- return;
- }
- WRITE_ONCE(rsp->jiffies_stall,
- jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-
/*
* OK, time to rat on our buddy...
* See Documentation/RCU/stallwarn.txt for info on how to debug
* RCU CPU stall warnings.
*/
- pr_err("INFO: %s detected stalls on CPUs/tasks:",
- rsp->name);
+ pr_err("INFO: %s detected stalls on CPUs/tasks:", rsp->name);
print_cpu_stall_info_begin();
rcu_for_each_leaf_node(rsp, rnp) {
raw_spin_lock_irqsave_rcu_node(rnp, flags);
@@ -1418,17 +1408,16 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
for_each_possible_cpu(cpu)
totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(rsp->rda,
cpu)->cblist);
- pr_cont("(detected by %d, t=%ld jiffies, g=%ld, c=%ld, q=%lu)\n",
+ pr_cont("(detected by %d, t=%ld jiffies, g=%ld, q=%lu)\n",
smp_processor_id(), (long)(jiffies - rsp->gp_start),
- (long)rsp->gpnum, (long)rsp->completed, totqlen);
+ (long)rcu_seq_current(&rsp->gp_seq), totqlen);
if (ndetected) {
rcu_dump_cpu_stacks(rsp);
/* Complain about tasks blocking the grace period. */
rcu_print_detail_task_stall(rsp);
} else {
- if (READ_ONCE(rsp->gpnum) != gpnum ||
- READ_ONCE(rsp->completed) == gpnum) {
+ if (rcu_seq_current(&rsp->gp_seq) != gp_seq) {
pr_err("INFO: Stall ended before state dump start\n");
} else {
j = jiffies;
@@ -1441,6 +1430,10 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
sched_show_task(current);
}
}
+ /* Rewrite if needed in case of slow consoles. */
+ if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall)))
+ WRITE_ONCE(rsp->jiffies_stall,
+ jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
rcu_check_gp_kthread_starvation(rsp);
@@ -1476,15 +1469,16 @@ static void print_cpu_stall(struct rcu_state *rsp)
for_each_possible_cpu(cpu)
totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(rsp->rda,
cpu)->cblist);
- pr_cont(" (t=%lu jiffies g=%ld c=%ld q=%lu)\n",
+ pr_cont(" (t=%lu jiffies g=%ld q=%lu)\n",
jiffies - rsp->gp_start,
- (long)rsp->gpnum, (long)rsp->completed, totqlen);
+ (long)rcu_seq_current(&rsp->gp_seq), totqlen);
rcu_check_gp_kthread_starvation(rsp);
rcu_dump_cpu_stacks(rsp);
raw_spin_lock_irqsave_rcu_node(rnp, flags);
+ /* Rewrite if needed in case of slow consoles. */
if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall)))
WRITE_ONCE(rsp->jiffies_stall,
jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
@@ -1504,10 +1498,11 @@ static void print_cpu_stall(struct rcu_state *rsp)
static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
{
- unsigned long completed;
- unsigned long gpnum;
+ unsigned long gs1;
+ unsigned long gs2;
unsigned long gps;
unsigned long j;
+ unsigned long jn;
unsigned long js;
struct rcu_node *rnp;
@@ -1520,43 +1515,46 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
/*
* Lots of memory barriers to reject false positives.
*
- * The idea is to pick up rsp->gpnum, then rsp->jiffies_stall,
- * then rsp->gp_start, and finally rsp->completed. These values
- * are updated in the opposite order with memory barriers (or
- * equivalent) during grace-period initialization and cleanup.
- * Now, a false positive can occur if we get an new value of
- * rsp->gp_start and a old value of rsp->jiffies_stall. But given
- * the memory barriers, the only way that this can happen is if one
- * grace period ends and another starts between these two fetches.
- * Detect this by comparing rsp->completed with the previous fetch
- * from rsp->gpnum.
+ * The idea is to pick up rsp->gp_seq, then rsp->jiffies_stall,
+ * then rsp->gp_start, and finally another copy of rsp->gp_seq.
+ * These values are updated in the opposite order with memory
+ * barriers (or equivalent) during grace-period initialization
+ * and cleanup. Now, a false positive can occur if we get an new
+ * value of rsp->gp_start and a old value of rsp->jiffies_stall.
+ * But given the memory barriers, the only way that this can happen
+ * is if one grace period ends and another starts between these
+ * two fetches. This is detected by comparing the second fetch
+ * of rsp->gp_seq with the previous fetch from rsp->gp_seq.
*
* Given this check, comparisons of jiffies, rsp->jiffies_stall,
* and rsp->gp_start suffice to forestall false positives.
*/
- gpnum = READ_ONCE(rsp->gpnum);
- smp_rmb(); /* Pick up ->gpnum first... */
+ gs1 = READ_ONCE(rsp->gp_seq);
+ smp_rmb(); /* Pick up ->gp_seq first... */
js = READ_ONCE(rsp->jiffies_stall);
smp_rmb(); /* ...then ->jiffies_stall before the rest... */
gps = READ_ONCE(rsp->gp_start);
- smp_rmb(); /* ...and finally ->gp_start before ->completed. */
- completed = READ_ONCE(rsp->completed);
- if (ULONG_CMP_GE(completed, gpnum) ||
+ smp_rmb(); /* ...and finally ->gp_start before ->gp_seq again. */
+ gs2 = READ_ONCE(rsp->gp_seq);
+ if (gs1 != gs2 ||
ULONG_CMP_LT(j, js) ||
ULONG_CMP_GE(gps, js))
return; /* No stall or GP completed since entering function. */
rnp = rdp->mynode;
+ jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
if (rcu_gp_in_progress(rsp) &&
- (READ_ONCE(rnp->qsmask) & rdp->grpmask)) {
+ (READ_ONCE(rnp->qsmask) & rdp->grpmask) &&
+ cmpxchg(&rsp->jiffies_stall, js, jn) == js) {
/* We haven't checked in, so go dump stack. */
print_cpu_stall(rsp);
} else if (rcu_gp_in_progress(rsp) &&
- ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY)) {
+ ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY) &&
+ cmpxchg(&rsp->jiffies_stall, js, jn) == js) {
/* They had a few time units to dump stack, so complain. */
- print_other_cpu_stall(rsp, gpnum);
+ print_other_cpu_stall(rsp, gs2);
}
}
@@ -1577,123 +1575,99 @@ void rcu_cpu_stall_reset(void)
WRITE_ONCE(rsp->jiffies_stall, jiffies + ULONG_MAX / 2);
}
-/*
- * Determine the value that ->completed will have at the end of the
- * next subsequent grace period. This is used to tag callbacks so that
- * a CPU can invoke callbacks in a timely fashion even if that CPU has
- * been dyntick-idle for an extended period with callbacks under the
- * influence of RCU_FAST_NO_HZ.
- *
- * The caller must hold rnp->lock with interrupts disabled.
- */
-static unsigned long rcu_cbs_completed(struct rcu_state *rsp,
- struct rcu_node *rnp)
-{
- raw_lockdep_assert_held_rcu_node(rnp);
-
- /*
- * If RCU is idle, we just wait for the next grace period.
- * But we can only be sure that RCU is idle if we are looking
- * at the root rcu_node structure -- otherwise, a new grace
- * period might have started, but just not yet gotten around
- * to initializing the current non-root rcu_node structure.
- */
- if (rcu_get_root(rsp) == rnp && rnp->gpnum == rnp->completed)
- return rnp->completed + 1;
-
- /*
- * If the current rcu_node structure believes that RCU is
- * idle, and if the rcu_state structure does not yet reflect
- * the start of a new grace period, then the next grace period
- * will suffice. The memory barrier is needed to accurately
- * sample the rsp->gpnum, and pairs with the second lock
- * acquisition in rcu_gp_init(), which is augmented with
- * smp_mb__after_unlock_lock() for this purpose.
- */
- if (rnp->gpnum == rnp->completed) {
- smp_mb(); /* See above block comment. */
- if (READ_ONCE(rsp->gpnum) == rnp->completed)
- return rnp->completed + 1;
- }
-
- /*
- * Otherwise, wait for a possible partial grace period and
- * then the subsequent full grace period.
- */
- return rnp->completed + 2;
-}
-
/* Trace-event wrapper function for trace_rcu_future_grace_period. */
static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
- unsigned long c, const char *s)
+ unsigned long gp_seq_req, const char *s)
{
- trace_rcu_future_grace_period(rdp->rsp->name, rnp->gpnum,
- rnp->completed, c, rnp->level,
- rnp->grplo, rnp->grphi, s);
+ trace_rcu_future_grace_period(rdp->rsp->name, rnp->gp_seq, gp_seq_req,
+ rnp->level, rnp->grplo, rnp->grphi, s);
}
/*
+ * rcu_start_this_gp - Request the start of a particular grace period
+ * @rnp_start: The leaf node of the CPU from which to start.
+ * @rdp: The rcu_data corresponding to the CPU from which to start.
+ * @gp_seq_req: The gp_seq of the grace period to start.
+ *
* Start the specified grace period, as needed to handle newly arrived
* callbacks. The required future grace periods are recorded in each
- * rcu_node structure's ->need_future_gp[] field. Returns true if there
+ * rcu_node structure's ->gp_seq_needed field. Returns true if there
* is reason to awaken the grace-period kthread.
*
* The caller must hold the specified rcu_node structure's ->lock, which
* is why the caller is responsible for waking the grace-period kthread.
+ *
+ * Returns true if the GP thread needs to be awakened else false.
*/
-static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
- unsigned long c)
+static bool rcu_start_this_gp(struct rcu_node *rnp_start, struct rcu_data *rdp,
+ unsigned long gp_seq_req)
{
bool ret = false;
struct rcu_state *rsp = rdp->rsp;
- struct rcu_node *rnp_root;
+ struct rcu_node *rnp;
/*
* Use funnel locking to either acquire the root rcu_node
* structure's lock or bail out if the need for this grace period
- * has already been recorded -- or has already started. If there
- * is already a grace period in progress in a non-leaf node, no
- * recording is needed because the end of the grace period will
- * scan the leaf rcu_node structures. Note that rnp->lock must
- * not be released.
+ * has already been recorded -- or if that grace period has in
+ * fact already started. If there is already a grace period in
+ * progress in a non-leaf node, no recording is needed because the
+ * end of the grace period will scan the leaf rcu_node structures.
+ * Note that rnp_start->lock must not be released.
*/
- raw_lockdep_assert_held_rcu_node(rnp);
- trace_rcu_this_gp(rnp, rdp, c, TPS("Startleaf"));
- for (rnp_root = rnp; 1; rnp_root = rnp_root->parent) {
- if (rnp_root != rnp)
- raw_spin_lock_rcu_node(rnp_root);
- WARN_ON_ONCE(ULONG_CMP_LT(rnp_root->gpnum +
- need_future_gp_mask(), c));
- if (need_future_gp_element(rnp_root, c) ||
- ULONG_CMP_GE(rnp_root->gpnum, c) ||
- (rnp != rnp_root &&
- rnp_root->gpnum != rnp_root->completed)) {
- trace_rcu_this_gp(rnp_root, rdp, c, TPS("Prestarted"));
+ raw_lockdep_assert_held_rcu_node(rnp_start);
+ trace_rcu_this_gp(rnp_start, rdp, gp_seq_req, TPS("Startleaf"));
+ for (rnp = rnp_start; 1; rnp = rnp->parent) {
+ if (rnp != rnp_start)
+ raw_spin_lock_rcu_node(rnp);
+ if (ULONG_CMP_GE(rnp->gp_seq_needed, gp_seq_req) ||
+ rcu_seq_started(&rnp->gp_seq, gp_seq_req) ||
+ (rnp != rnp_start &&
+ rcu_seq_state(rcu_seq_current(&rnp->gp_seq)))) {
+ trace_rcu_this_gp(rnp, rdp, gp_seq_req,
+ TPS("Prestarted"));
goto unlock_out;
}
- need_future_gp_element(rnp_root, c) = true;
- if (rnp_root != rnp && rnp_root->parent != NULL)
- raw_spin_unlock_rcu_node(rnp_root);
- if (!rnp_root->parent)
+ rnp->gp_seq_needed = gp_seq_req;
+ if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq))) {
+ /*
+ * We just marked the leaf or internal node, and a
+ * grace period is in progress, which means that
+ * rcu_gp_cleanup() will see the marking. Bail to
+ * reduce contention.
+ */
+ trace_rcu_this_gp(rnp_start, rdp, gp_seq_req,
+ TPS("Startedleaf"));
+ goto unlock_out;
+ }
+ if (rnp != rnp_start && rnp->parent != NULL)
+ raw_spin_unlock_rcu_node(rnp);
+ if (!rnp->parent)
break; /* At root, and perhaps also leaf. */
}
/* If GP already in progress, just leave, otherwise start one. */
- if (rnp_root->gpnum != rnp_root->completed) {
- trace_rcu_this_gp(rnp_root, rdp, c, TPS("Startedleafroot"));
+ if (rcu_gp_in_progress(rsp)) {
+ trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startedleafroot"));
goto unlock_out;
}
- trace_rcu_this_gp(rnp_root, rdp, c, TPS("Startedroot"));
+ trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startedroot"));
WRITE_ONCE(rsp->gp_flags, rsp->gp_flags | RCU_GP_FLAG_INIT);
+ rsp->gp_req_activity = jiffies;
if (!rsp->gp_kthread) {
- trace_rcu_this_gp(rnp_root, rdp, c, TPS("NoGPkthread"));
+ trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("NoGPkthread"));
goto unlock_out;
}
- trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum), TPS("newreq"));
+ trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gp_seq), TPS("newreq"));
ret = true; /* Caller must wake GP kthread. */
unlock_out:
- if (rnp != rnp_root)
- raw_spin_unlock_rcu_node(rnp_root);
+ /* Push furthest requested GP to leaf node and rcu_data structure. */
+ if (ULONG_CMP_LT(gp_seq_req, rnp->gp_seq_needed)) {
+ rnp_start->gp_seq_needed = rnp->gp_seq_needed;
+ rdp->gp_seq_needed = rnp->gp_seq_needed;
+ }
+ if (rnp != rnp_start)
+ raw_spin_unlock_rcu_node(rnp);
return ret;
}
@@ -1703,13 +1677,13 @@ unlock_out:
*/
static bool rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
{
- unsigned long c = rnp->completed;
bool needmore;
struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
- need_future_gp_element(rnp, c) = false;
- needmore = need_any_future_gp(rnp);
- trace_rcu_this_gp(rnp, rdp, c,
+ needmore = ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed);
+ if (!needmore)
+ rnp->gp_seq_needed = rnp->gp_seq; /* Avoid counter wrap. */
+ trace_rcu_this_gp(rnp, rdp, rnp->gp_seq,
needmore ? TPS("CleanupMore") : TPS("Cleanup"));
return needmore;
}
@@ -1727,25 +1701,25 @@ static void rcu_gp_kthread_wake(struct rcu_state *rsp)
!READ_ONCE(rsp->gp_flags) ||
!rsp->gp_kthread)
return;
- swake_up(&rsp->gp_wq);
+ swake_up_one(&rsp->gp_wq);
}
/*
- * If there is room, assign a ->completed number to any callbacks on
- * this CPU that have not already been assigned. Also accelerate any
- * callbacks that were previously assigned a ->completed number that has
- * since proven to be too conservative, which can happen if callbacks get
- * assigned a ->completed number while RCU is idle, but with reference to
- * a non-root rcu_node structure. This function is idempotent, so it does
- * not hurt to call it repeatedly. Returns an flag saying that we should
- * awaken the RCU grace-period kthread.
+ * If there is room, assign a ->gp_seq number to any callbacks on this
+ * CPU that have not already been assigned. Also accelerate any callbacks
+ * that were previously assigned a ->gp_seq number that has since proven
+ * to be too conservative, which can happen if callbacks get assigned a
+ * ->gp_seq number while RCU is idle, but with reference to a non-root
+ * rcu_node structure. This function is idempotent, so it does not hurt
+ * to call it repeatedly. Returns an flag saying that we should awaken
+ * the RCU grace-period kthread.
*
* The caller must hold rnp->lock with interrupts disabled.
*/
static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
struct rcu_data *rdp)
{
- unsigned long c;
+ unsigned long gp_seq_req;
bool ret = false;
raw_lockdep_assert_held_rcu_node(rnp);
@@ -1764,22 +1738,50 @@ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
* accelerating callback invocation to an earlier grace-period
* number.
*/
- c = rcu_cbs_completed(rsp, rnp);
- if (rcu_segcblist_accelerate(&rdp->cblist, c))
- ret = rcu_start_this_gp(rnp, rdp, c);
+ gp_seq_req = rcu_seq_snap(&rsp->gp_seq);
+ if (rcu_segcblist_accelerate(&rdp->cblist, gp_seq_req))
+ ret = rcu_start_this_gp(rnp, rdp, gp_seq_req);
/* Trace depending on how much we were able to accelerate. */
if (rcu_segcblist_restempty(&rdp->cblist, RCU_WAIT_TAIL))
- trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccWaitCB"));
+ trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("AccWaitCB"));
else
- trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccReadyCB"));
+ trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("AccReadyCB"));
return ret;
}
/*
+ * Similar to rcu_accelerate_cbs(), but does not require that the leaf
+ * rcu_node structure's ->lock be held. It consults the cached value
+ * of ->gp_seq_needed in the rcu_data structure, and if that indicates
+ * that a new grace-period request be made, invokes rcu_accelerate_cbs()
+ * while holding the leaf rcu_node structure's ->lock.
+ */
+static void rcu_accelerate_cbs_unlocked(struct rcu_state *rsp,
+ struct rcu_node *rnp,
+ struct rcu_data *rdp)
+{
+ unsigned long c;
+ bool needwake;
+
+ lockdep_assert_irqs_disabled();
+ c = rcu_seq_snap(&rsp->gp_seq);
+ if (!rdp->gpwrap && ULONG_CMP_GE(rdp->gp_seq_needed, c)) {
+ /* Old request still live, so mark recent callbacks. */
+ (void)rcu_segcblist_accelerate(&rdp->cblist, c);
+ return;
+ }
+ raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
+ needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
+ raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */
+ if (needwake)
+ rcu_gp_kthread_wake(rsp);
+}
+
+/*
* Move any callbacks whose grace period has completed to the
* RCU_DONE_TAIL sublist, then compact the remaining sublists and
- * assign ->completed numbers to any callbacks in the RCU_NEXT_TAIL
+ * assign ->gp_seq numbers to any callbacks in the RCU_NEXT_TAIL
* sublist. This function is idempotent, so it does not hurt to
* invoke it repeatedly. As long as it is not invoked -too- often...
* Returns true if the RCU grace-period kthread needs to be awakened.
@@ -1796,10 +1798,10 @@ static bool rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
return false;
/*
- * Find all callbacks whose ->completed numbers indicate that they
+ * Find all callbacks whose ->gp_seq numbers indicate that they
* are ready to invoke, and put them into the RCU_DONE_TAIL sublist.
*/
- rcu_segcblist_advance(&rdp->cblist, rnp->completed);
+ rcu_segcblist_advance(&rdp->cblist, rnp->gp_seq);
/* Classify any remaining callbacks. */
return rcu_accelerate_cbs(rsp, rnp, rdp);
@@ -1819,39 +1821,38 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp,
raw_lockdep_assert_held_rcu_node(rnp);
- /* Handle the ends of any preceding grace periods first. */
- if (rdp->completed == rnp->completed &&
- !unlikely(READ_ONCE(rdp->gpwrap))) {
-
- /* No grace period end, so just accelerate recent callbacks. */
- ret = rcu_accelerate_cbs(rsp, rnp, rdp);
+ if (rdp->gp_seq == rnp->gp_seq)
+ return false; /* Nothing to do. */
+ /* Handle the ends of any preceding grace periods first. */
+ if (rcu_seq_completed_gp(rdp->gp_seq, rnp->gp_seq) ||
+ unlikely(READ_ONCE(rdp->gpwrap))) {
+ ret = rcu_advance_cbs(rsp, rnp, rdp); /* Advance callbacks. */
+ trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("cpuend"));
} else {
-
- /* Advance callbacks. */
- ret = rcu_advance_cbs(rsp, rnp, rdp);
-
- /* Remember that we saw this grace-period completion. */
- rdp->completed = rnp->completed;
- trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuend"));
+ ret = rcu_accelerate_cbs(rsp, rnp, rdp); /* Recent callbacks. */
}
- if (rdp->gpnum != rnp->gpnum || unlikely(READ_ONCE(rdp->gpwrap))) {
+ /* Now handle the beginnings of any new-to-this-CPU grace periods. */
+ if (rcu_seq_new_gp(rdp->gp_seq, rnp->gp_seq) ||
+ unlikely(READ_ONCE(rdp->gpwrap))) {
/*
* If the current grace period is waiting for this CPU,
* set up to detect a quiescent state, otherwise don't
* go looking for one.
*/
- rdp->gpnum = rnp->gpnum;
- trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpustart"));
+ trace_rcu_grace_period(rsp->name, rnp->gp_seq, TPS("cpustart"));
need_gp = !!(rnp->qsmask & rdp->grpmask);
rdp->cpu_no_qs.b.norm = need_gp;
rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_dynticks.rcu_qs_ctr);
rdp->core_needs_qs = need_gp;
zero_cpu_stall_ticks(rdp);
- WRITE_ONCE(rdp->gpwrap, false);
- rcu_gpnum_ovf(rnp, rdp);
}
+ rdp->gp_seq = rnp->gp_seq; /* Remember new grace-period state. */
+ if (ULONG_CMP_GE(rnp->gp_seq_needed, rdp->gp_seq_needed) || rdp->gpwrap)
+ rdp->gp_seq_needed = rnp->gp_seq_needed;
+ WRITE_ONCE(rdp->gpwrap, false);
+ rcu_gpnum_ovf(rnp, rdp);
return ret;
}
@@ -1863,8 +1864,7 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
local_irq_save(flags);
rnp = rdp->mynode;
- if ((rdp->gpnum == READ_ONCE(rnp->gpnum) &&
- rdp->completed == READ_ONCE(rnp->completed) &&
+ if ((rdp->gp_seq == rcu_seq_current(&rnp->gp_seq) &&
!unlikely(READ_ONCE(rdp->gpwrap))) || /* w/out lock. */
!raw_spin_trylock_rcu_node(rnp)) { /* irqs already off, so later. */
local_irq_restore(flags);
@@ -1879,7 +1879,8 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
static void rcu_gp_slow(struct rcu_state *rsp, int delay)
{
if (delay > 0 &&
- !(rsp->gpnum % (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay)))
+ !(rcu_seq_ctr(rsp->gp_seq) %
+ (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay)))
schedule_timeout_uninterruptible(delay);
}
@@ -1888,7 +1889,9 @@ static void rcu_gp_slow(struct rcu_state *rsp, int delay)
*/
static bool rcu_gp_init(struct rcu_state *rsp)
{
+ unsigned long flags;
unsigned long oldmask;
+ unsigned long mask;
struct rcu_data *rdp;
struct rcu_node *rnp = rcu_get_root(rsp);
@@ -1912,9 +1915,9 @@ static bool rcu_gp_init(struct rcu_state *rsp)
/* Advance to a new grace period and initialize state. */
record_gp_stall_check_time(rsp);
- /* Record GP times before starting GP, hence smp_store_release(). */
- smp_store_release(&rsp->gpnum, rsp->gpnum + 1);
- trace_rcu_grace_period(rsp->name, rsp->gpnum, TPS("start"));
+ /* Record GP times before starting GP, hence rcu_seq_start(). */
+ rcu_seq_start(&rsp->gp_seq);
+ trace_rcu_grace_period(rsp->name, rsp->gp_seq, TPS("start"));
raw_spin_unlock_irq_rcu_node(rnp);
/*
@@ -1923,13 +1926,15 @@ static bool rcu_gp_init(struct rcu_state *rsp)
* for subsequent online CPUs, and that quiescent-state forcing
* will handle subsequent offline CPUs.
*/
+ rsp->gp_state = RCU_GP_ONOFF;
rcu_for_each_leaf_node(rsp, rnp) {
- rcu_gp_slow(rsp, gp_preinit_delay);
+ spin_lock(&rsp->ofl_lock);
raw_spin_lock_irq_rcu_node(rnp);
if (rnp->qsmaskinit == rnp->qsmaskinitnext &&
!rnp->wait_blkd_tasks) {
/* Nothing to do on this leaf rcu_node structure. */
raw_spin_unlock_irq_rcu_node(rnp);
+ spin_unlock(&rsp->ofl_lock);
continue;
}
@@ -1939,12 +1944,14 @@ static bool rcu_gp_init(struct rcu_state *rsp)
/* If zero-ness of ->qsmaskinit changed, propagate up tree. */
if (!oldmask != !rnp->qsmaskinit) {
- if (!oldmask) /* First online CPU for this rcu_node. */
- rcu_init_new_rnp(rnp);
- else if (rcu_preempt_has_tasks(rnp)) /* blocked tasks */
- rnp->wait_blkd_tasks = true;
- else /* Last offline CPU and can propagate. */
+ if (!oldmask) { /* First online CPU for rcu_node. */
+ if (!rnp->wait_blkd_tasks) /* Ever offline? */
+ rcu_init_new_rnp(rnp);
+ } else if (rcu_preempt_has_tasks(rnp)) {
+ rnp->wait_blkd_tasks = true; /* blocked tasks */
+ } else { /* Last offline CPU and can propagate. */
rcu_cleanup_dead_rnp(rnp);
+ }
}
/*
@@ -1953,18 +1960,19 @@ static bool rcu_gp_init(struct rcu_state *rsp)
* still offline, propagate up the rcu_node tree and
* clear ->wait_blkd_tasks. Otherwise, if one of this
* rcu_node structure's CPUs has since come back online,
- * simply clear ->wait_blkd_tasks (but rcu_cleanup_dead_rnp()
- * checks for this, so just call it unconditionally).
+ * simply clear ->wait_blkd_tasks.
*/
if (rnp->wait_blkd_tasks &&
- (!rcu_preempt_has_tasks(rnp) ||
- rnp->qsmaskinit)) {
+ (!rcu_preempt_has_tasks(rnp) || rnp->qsmaskinit)) {
rnp->wait_blkd_tasks = false;
- rcu_cleanup_dead_rnp(rnp);
+ if (!rnp->qsmaskinit)
+ rcu_cleanup_dead_rnp(rnp);
}
raw_spin_unlock_irq_rcu_node(rnp);
+ spin_unlock(&rsp->ofl_lock);
}
+ rcu_gp_slow(rsp, gp_preinit_delay); /* Races with CPU hotplug. */
/*
* Set the quiescent-state-needed bits in all the rcu_node
@@ -1978,22 +1986,27 @@ static bool rcu_gp_init(struct rcu_state *rsp)
* The grace period cannot complete until the initialization
* process finishes, because this kthread handles both.
*/
+ rsp->gp_state = RCU_GP_INIT;
rcu_for_each_node_breadth_first(rsp, rnp) {
rcu_gp_slow(rsp, gp_init_delay);
- raw_spin_lock_irq_rcu_node(rnp);
+ raw_spin_lock_irqsave_rcu_node(rnp, flags);
rdp = this_cpu_ptr(rsp->rda);
- rcu_preempt_check_blocked_tasks(rnp);
+ rcu_preempt_check_blocked_tasks(rsp, rnp);
rnp->qsmask = rnp->qsmaskinit;
- WRITE_ONCE(rnp->gpnum, rsp->gpnum);
- if (WARN_ON_ONCE(rnp->completed != rsp->completed))
- WRITE_ONCE(rnp->completed, rsp->completed);
+ WRITE_ONCE(rnp->gp_seq, rsp->gp_seq);
if (rnp == rdp->mynode)
(void)__note_gp_changes(rsp, rnp, rdp);
rcu_preempt_boost_start_gp(rnp);
- trace_rcu_grace_period_init(rsp->name, rnp->gpnum,
+ trace_rcu_grace_period_init(rsp->name, rnp->gp_seq,
rnp->level, rnp->grplo,
rnp->grphi, rnp->qsmask);
- raw_spin_unlock_irq_rcu_node(rnp);
+ /* Quiescent states for tasks on any now-offline CPUs. */
+ mask = rnp->qsmask & ~rnp->qsmaskinitnext;
+ rnp->rcu_gp_init_mask = mask;
+ if ((mask || rnp->wait_blkd_tasks) && rcu_is_leaf_node(rnp))
+ rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
+ else
+ raw_spin_unlock_irq_rcu_node(rnp);
cond_resched_tasks_rcu_qs();
WRITE_ONCE(rsp->gp_activity, jiffies);
}
@@ -2002,7 +2015,7 @@ static bool rcu_gp_init(struct rcu_state *rsp)
}
/*
- * Helper function for swait_event_idle() wakeup at force-quiescent-state
+ * Helper function for swait_event_idle_exclusive() wakeup at force-quiescent-state
* time.
*/
static bool rcu_gp_fqs_check_wake(struct rcu_state *rsp, int *gfp)
@@ -2053,6 +2066,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
{
unsigned long gp_duration;
bool needgp = false;
+ unsigned long new_gp_seq;
struct rcu_data *rdp;
struct rcu_node *rnp = rcu_get_root(rsp);
struct swait_queue_head *sq;
@@ -2074,19 +2088,22 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
raw_spin_unlock_irq_rcu_node(rnp);
/*
- * Propagate new ->completed value to rcu_node structures so
- * that other CPUs don't have to wait until the start of the next
- * grace period to process their callbacks. This also avoids
- * some nasty RCU grace-period initialization races by forcing
- * the end of the current grace period to be completely recorded in
- * all of the rcu_node structures before the beginning of the next
- * grace period is recorded in any of the rcu_node structures.
+ * Propagate new ->gp_seq value to rcu_node structures so that
+ * other CPUs don't have to wait until the start of the next grace
+ * period to process their callbacks. This also avoids some nasty
+ * RCU grace-period initialization races by forcing the end of
+ * the current grace period to be completely recorded in all of
+ * the rcu_node structures before the beginning of the next grace
+ * period is recorded in any of the rcu_node structures.
*/
+ new_gp_seq = rsp->gp_seq;
+ rcu_seq_end(&new_gp_seq);
rcu_for_each_node_breadth_first(rsp, rnp) {
raw_spin_lock_irq_rcu_node(rnp);
- WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp));
+ if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)))
+ dump_blkd_tasks(rsp, rnp, 10);
WARN_ON_ONCE(rnp->qsmask);
- WRITE_ONCE(rnp->completed, rsp->gpnum);
+ WRITE_ONCE(rnp->gp_seq, new_gp_seq);
rdp = this_cpu_ptr(rsp->rda);
if (rnp == rdp->mynode)
needgp = __note_gp_changes(rsp, rnp, rdp) || needgp;
@@ -2100,26 +2117,28 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
rcu_gp_slow(rsp, gp_cleanup_delay);
}
rnp = rcu_get_root(rsp);
- raw_spin_lock_irq_rcu_node(rnp); /* Order GP before ->completed update. */
+ raw_spin_lock_irq_rcu_node(rnp); /* GP before rsp->gp_seq update. */
/* Declare grace period done. */
- WRITE_ONCE(rsp->completed, rsp->gpnum);
- trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end"));
+ rcu_seq_end(&rsp->gp_seq);
+ trace_rcu_grace_period(rsp->name, rsp->gp_seq, TPS("end"));
rsp->gp_state = RCU_GP_IDLE;
/* Check for GP requests since above loop. */
rdp = this_cpu_ptr(rsp->rda);
- if (need_any_future_gp(rnp)) {
- trace_rcu_this_gp(rnp, rdp, rsp->completed - 1,
+ if (!needgp && ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed)) {
+ trace_rcu_this_gp(rnp, rdp, rnp->gp_seq_needed,
TPS("CleanupMore"));
needgp = true;
}
/* Advance CBs to reduce false positives below. */
if (!rcu_accelerate_cbs(rsp, rnp, rdp) && needgp) {
WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT);
- trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum),
+ rsp->gp_req_activity = jiffies;
+ trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gp_seq),
TPS("newreq"));
+ } else {
+ WRITE_ONCE(rsp->gp_flags, rsp->gp_flags & RCU_GP_FLAG_INIT);
}
- WRITE_ONCE(rsp->gp_flags, rsp->gp_flags & RCU_GP_FLAG_INIT);
raw_spin_unlock_irq_rcu_node(rnp);
}
@@ -2141,10 +2160,10 @@ static int __noreturn rcu_gp_kthread(void *arg)
/* Handle grace-period start. */
for (;;) {
trace_rcu_grace_period(rsp->name,
- READ_ONCE(rsp->gpnum),
+ READ_ONCE(rsp->gp_seq),
TPS("reqwait"));
rsp->gp_state = RCU_GP_WAIT_GPS;
- swait_event_idle(rsp->gp_wq, READ_ONCE(rsp->gp_flags) &
+ swait_event_idle_exclusive(rsp->gp_wq, READ_ONCE(rsp->gp_flags) &
RCU_GP_FLAG_INIT);
rsp->gp_state = RCU_GP_DONE_GPS;
/* Locking provides needed memory barrier. */
@@ -2154,17 +2173,13 @@ static int __noreturn rcu_gp_kthread(void *arg)
WRITE_ONCE(rsp->gp_activity, jiffies);
WARN_ON(signal_pending(current));
trace_rcu_grace_period(rsp->name,
- READ_ONCE(rsp->gpnum),
+ READ_ONCE(rsp->gp_seq),
TPS("reqwaitsig"));
}
/* Handle quiescent-state forcing. */
first_gp_fqs = true;
j = jiffies_till_first_fqs;
- if (j > HZ) {
- j = HZ;
- jiffies_till_first_fqs = HZ;
- }
ret = 0;
for (;;) {
if (!ret) {
@@ -2173,10 +2188,10 @@ static int __noreturn rcu_gp_kthread(void *arg)
jiffies + 3 * j);
}
trace_rcu_grace_period(rsp->name,
- READ_ONCE(rsp->gpnum),
+ READ_ONCE(rsp->gp_seq),
TPS("fqswait"));
rsp->gp_state = RCU_GP_WAIT_FQS;
- ret = swait_event_idle_timeout(rsp->gp_wq,
+ ret = swait_event_idle_timeout_exclusive(rsp->gp_wq,
rcu_gp_fqs_check_wake(rsp, &gf), j);
rsp->gp_state = RCU_GP_DOING_FQS;
/* Locking provides needed memory barriers. */
@@ -2188,31 +2203,24 @@ static int __noreturn rcu_gp_kthread(void *arg)
if (ULONG_CMP_GE(jiffies, rsp->jiffies_force_qs) ||
(gf & RCU_GP_FLAG_FQS)) {
trace_rcu_grace_period(rsp->name,
- READ_ONCE(rsp->gpnum),
+ READ_ONCE(rsp->gp_seq),
TPS("fqsstart"));
rcu_gp_fqs(rsp, first_gp_fqs);
first_gp_fqs = false;
trace_rcu_grace_period(rsp->name,
- READ_ONCE(rsp->gpnum),
+ READ_ONCE(rsp->gp_seq),
TPS("fqsend"));
cond_resched_tasks_rcu_qs();
WRITE_ONCE(rsp->gp_activity, jiffies);
ret = 0; /* Force full wait till next FQS. */
j = jiffies_till_next_fqs;
- if (j > HZ) {
- j = HZ;
- jiffies_till_next_fqs = HZ;
- } else if (j < 1) {
- j = 1;
- jiffies_till_next_fqs = 1;
- }
} else {
/* Deal with stray signal. */
cond_resched_tasks_rcu_qs();
WRITE_ONCE(rsp->gp_activity, jiffies);
WARN_ON(signal_pending(current));
trace_rcu_grace_period(rsp->name,
- READ_ONCE(rsp->gpnum),
+ READ_ONCE(rsp->gp_seq),
TPS("fqswaitsig"));
ret = 1; /* Keep old FQS timing. */
j = jiffies;
@@ -2256,8 +2264,12 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
* must be represented by the same rcu_node structure (which need not be a
* leaf rcu_node structure, though it often will be). The gps parameter
* is the grace-period snapshot, which means that the quiescent states
- * are valid only if rnp->gpnum is equal to gps. That structure's lock
+ * are valid only if rnp->gp_seq is equal to gps. That structure's lock
* must be held upon entry, and it is released before return.
+ *
+ * As a special case, if mask is zero, the bit-already-cleared check is
+ * disabled. This allows propagating quiescent state due to resumed tasks
+ * during grace-period initialization.
*/
static void
rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
@@ -2271,7 +2283,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
/* Walk up the rcu_node hierarchy. */
for (;;) {
- if (!(rnp->qsmask & mask) || rnp->gpnum != gps) {
+ if ((!(rnp->qsmask & mask) && mask) || rnp->gp_seq != gps) {
/*
* Our bit has already been cleared, or the
@@ -2284,7 +2296,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
WARN_ON_ONCE(!rcu_is_leaf_node(rnp) &&
rcu_preempt_blocked_readers_cgp(rnp));
rnp->qsmask &= ~mask;
- trace_rcu_quiescent_state_report(rsp->name, rnp->gpnum,
+ trace_rcu_quiescent_state_report(rsp->name, rnp->gp_seq,
mask, rnp->qsmask, rnp->level,
rnp->grplo, rnp->grphi,
!!rnp->gp_tasks);
@@ -2294,6 +2306,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return;
}
+ rnp->completedqs = rnp->gp_seq;
mask = rnp->grpmask;
if (rnp->parent == NULL) {
@@ -2323,8 +2336,9 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
* irqs disabled, and this lock is released upon return, but irqs remain
* disabled.
*/
-static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
- struct rcu_node *rnp, unsigned long flags)
+static void __maybe_unused
+rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
+ struct rcu_node *rnp, unsigned long flags)
__releases(rnp->lock)
{
unsigned long gps;
@@ -2332,12 +2346,15 @@ static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
struct rcu_node *rnp_p;
raw_lockdep_assert_held_rcu_node(rnp);
- if (rcu_state_p == &rcu_sched_state || rsp != rcu_state_p ||
- rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) {
+ if (WARN_ON_ONCE(rcu_state_p == &rcu_sched_state) ||
+ WARN_ON_ONCE(rsp != rcu_state_p) ||
+ WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)) ||
+ rnp->qsmask != 0) {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return; /* Still need more quiescent states! */
}
+ rnp->completedqs = rnp->gp_seq;
rnp_p = rnp->parent;
if (rnp_p == NULL) {
/*
@@ -2348,8 +2365,8 @@ static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
return;
}
- /* Report up the rest of the hierarchy, tracking current ->gpnum. */
- gps = rnp->gpnum;
+ /* Report up the rest of the hierarchy, tracking current ->gp_seq. */
+ gps = rnp->gp_seq;
mask = rnp->grpmask;
raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */
raw_spin_lock_rcu_node(rnp_p); /* irqs already disabled. */
@@ -2370,8 +2387,8 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
rnp = rdp->mynode;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
- if (rdp->cpu_no_qs.b.norm || rdp->gpnum != rnp->gpnum ||
- rnp->completed == rnp->gpnum || rdp->gpwrap) {
+ if (rdp->cpu_no_qs.b.norm || rdp->gp_seq != rnp->gp_seq ||
+ rdp->gpwrap) {
/*
* The grace period in which this quiescent state was
@@ -2396,7 +2413,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
*/
needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
- rcu_report_qs_rnp(mask, rsp, rnp, rnp->gpnum, flags);
+ rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
/* ^^^ Released rnp->lock */
if (needwake)
rcu_gp_kthread_wake(rsp);
@@ -2441,17 +2458,16 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
*/
static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
{
- RCU_TRACE(unsigned long mask;)
+ RCU_TRACE(bool blkd;)
RCU_TRACE(struct rcu_data *rdp = this_cpu_ptr(rsp->rda);)
RCU_TRACE(struct rcu_node *rnp = rdp->mynode;)
if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
return;
- RCU_TRACE(mask = rdp->grpmask;)
- trace_rcu_grace_period(rsp->name,
- rnp->gpnum + 1 - !!(rnp->qsmask & mask),
- TPS("cpuofl"));
+ RCU_TRACE(blkd = !!(rnp->qsmask & rdp->grpmask);)
+ trace_rcu_grace_period(rsp->name, rnp->gp_seq,
+ blkd ? TPS("cpuofl") : TPS("cpuofl-bgp"));
}
/*
@@ -2463,7 +2479,7 @@ static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
* This function therefore goes up the tree of rcu_node structures,
* clearing the corresponding bits in the ->qsmaskinit fields. Note that
* the leaf rcu_node structure's ->qsmaskinit field has already been
- * updated
+ * updated.
*
* This function does check that the specified rcu_node structure has
* all CPUs offline and no blocked tasks, so it is OK to invoke it
@@ -2476,9 +2492,10 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
long mask;
struct rcu_node *rnp = rnp_leaf;
- raw_lockdep_assert_held_rcu_node(rnp);
+ raw_lockdep_assert_held_rcu_node(rnp_leaf);
if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) ||
- rnp->qsmaskinit || rcu_preempt_has_tasks(rnp))
+ WARN_ON_ONCE(rnp_leaf->qsmaskinit) ||
+ WARN_ON_ONCE(rcu_preempt_has_tasks(rnp_leaf)))
return;
for (;;) {
mask = rnp->grpmask;
@@ -2487,7 +2504,8 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
break;
raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
rnp->qsmaskinit &= ~mask;
- rnp->qsmask &= ~mask;
+ /* Between grace periods, so better already be zero! */
+ WARN_ON_ONCE(rnp->qsmask);
if (rnp->qsmaskinit) {
raw_spin_unlock_rcu_node(rnp);
/* irqs remain disabled. */
@@ -2630,6 +2648,7 @@ void rcu_check_callbacks(int user)
rcu_sched_qs();
rcu_bh_qs();
+ rcu_note_voluntary_context_switch(current);
} else if (!in_softirq()) {
@@ -2645,8 +2664,7 @@ void rcu_check_callbacks(int user)
rcu_preempt_check_callbacks();
if (rcu_pending())
invoke_rcu_core();
- if (user)
- rcu_note_voluntary_context_switch(current);
+
trace_rcu_utilization(TPS("End scheduler-tick"));
}
@@ -2681,17 +2699,8 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp))
/* rcu_initiate_boost() releases rnp->lock */
continue;
}
- if (rnp->parent &&
- (rnp->parent->qsmask & rnp->grpmask)) {
- /*
- * Race between grace-period
- * initialization and task exiting RCU
- * read-side critical section: Report.
- */
- rcu_report_unblock_qs_rnp(rsp, rnp, flags);
- /* rcu_report_unblock_qs_rnp() rlses ->lock */
- continue;
- }
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ continue;
}
for_each_leaf_node_possible_cpu(rnp, cpu) {
unsigned long bit = leaf_node_cpu_bit(rnp, cpu);
@@ -2701,8 +2710,8 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp))
}
}
if (mask != 0) {
- /* Idle/offline CPUs, report (releases rnp->lock. */
- rcu_report_qs_rnp(mask, rsp, rnp, rnp->gpnum, flags);
+ /* Idle/offline CPUs, report (releases rnp->lock). */
+ rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
} else {
/* Nothing to do here, so just drop the lock. */
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
@@ -2747,6 +2756,65 @@ static void force_quiescent_state(struct rcu_state *rsp)
}
/*
+ * This function checks for grace-period requests that fail to motivate
+ * RCU to come out of its idle mode.
+ */
+static void
+rcu_check_gp_start_stall(struct rcu_state *rsp, struct rcu_node *rnp,
+ struct rcu_data *rdp)
+{
+ const unsigned long gpssdelay = rcu_jiffies_till_stall_check() * HZ;
+ unsigned long flags;
+ unsigned long j;
+ struct rcu_node *rnp_root = rcu_get_root(rsp);
+ static atomic_t warned = ATOMIC_INIT(0);
+
+ if (!IS_ENABLED(CONFIG_PROVE_RCU) || rcu_gp_in_progress(rsp) ||
+ ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed))
+ return;
+ j = jiffies; /* Expensive access, and in common case don't get here. */
+ if (time_before(j, READ_ONCE(rsp->gp_req_activity) + gpssdelay) ||
+ time_before(j, READ_ONCE(rsp->gp_activity) + gpssdelay) ||
+ atomic_read(&warned))
+ return;
+
+ raw_spin_lock_irqsave_rcu_node(rnp, flags);
+ j = jiffies;
+ if (rcu_gp_in_progress(rsp) ||
+ ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
+ time_before(j, READ_ONCE(rsp->gp_req_activity) + gpssdelay) ||
+ time_before(j, READ_ONCE(rsp->gp_activity) + gpssdelay) ||
+ atomic_read(&warned)) {
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ return;
+ }
+ /* Hold onto the leaf lock to make others see warned==1. */
+
+ if (rnp_root != rnp)
+ raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */
+ j = jiffies;
+ if (rcu_gp_in_progress(rsp) ||
+ ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
+ time_before(j, rsp->gp_req_activity + gpssdelay) ||
+ time_before(j, rsp->gp_activity + gpssdelay) ||
+ atomic_xchg(&warned, 1)) {
+ raw_spin_unlock_rcu_node(rnp_root); /* irqs remain disabled. */
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ return;
+ }
+ pr_alert("%s: g%ld->%ld gar:%lu ga:%lu f%#x gs:%d %s->state:%#lx\n",
+ __func__, (long)READ_ONCE(rsp->gp_seq),
+ (long)READ_ONCE(rnp_root->gp_seq_needed),
+ j - rsp->gp_req_activity, j - rsp->gp_activity,
+ rsp->gp_flags, rsp->gp_state, rsp->name,
+ rsp->gp_kthread ? rsp->gp_kthread->state : 0x1ffffL);
+ WARN_ON(1);
+ if (rnp_root != rnp)
+ raw_spin_unlock_rcu_node(rnp_root);
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+}
+
+/*
* This does the RCU core processing work for the specified rcu_state
* and rcu_data structures. This may be called only from the CPU to
* whom the rdp belongs.
@@ -2755,9 +2823,8 @@ static void
__rcu_process_callbacks(struct rcu_state *rsp)
{
unsigned long flags;
- bool needwake;
struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
- struct rcu_node *rnp;
+ struct rcu_node *rnp = rdp->mynode;
WARN_ON_ONCE(!rdp->beenonline);
@@ -2768,18 +2835,13 @@ __rcu_process_callbacks(struct rcu_state *rsp)
if (!rcu_gp_in_progress(rsp) &&
rcu_segcblist_is_enabled(&rdp->cblist)) {
local_irq_save(flags);
- if (rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) {
- local_irq_restore(flags);
- } else {
- rnp = rdp->mynode;
- raw_spin_lock_rcu_node(rnp); /* irqs disabled. */
- needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
- if (needwake)
- rcu_gp_kthread_wake(rsp);
- }
+ if (!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
+ rcu_accelerate_cbs_unlocked(rsp, rnp, rdp);
+ local_irq_restore(flags);
}
+ rcu_check_gp_start_stall(rsp, rnp, rdp);
+
/* If there are callbacks ready, invoke them. */
if (rcu_segcblist_ready_cbs(&rdp->cblist))
invoke_rcu_callbacks(rsp, rdp);
@@ -2833,8 +2895,6 @@ static void invoke_rcu_core(void)
static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
struct rcu_head *head, unsigned long flags)
{
- bool needwake;
-
/*
* If called from an extended quiescent state, invoke the RCU
* core in order to force a re-evaluation of RCU's idleness.
@@ -2861,13 +2921,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
/* Start a new grace period if one not already started. */
if (!rcu_gp_in_progress(rsp)) {
- struct rcu_node *rnp = rdp->mynode;
-
- raw_spin_lock_rcu_node(rnp);
- needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
- raw_spin_unlock_rcu_node(rnp);
- if (needwake)
- rcu_gp_kthread_wake(rsp);
+ rcu_accelerate_cbs_unlocked(rsp, rdp->mynode, rdp);
} else {
/* Give the grace period a kick. */
rdp->blimit = LONG_MAX;
@@ -3037,7 +3091,7 @@ EXPORT_SYMBOL_GPL(kfree_call_rcu);
* when there was in fact only one the whole time, as this just adds
* some overhead: RCU still operates correctly.
*/
-static inline int rcu_blocking_is_gp(void)
+static int rcu_blocking_is_gp(void)
{
int ret;
@@ -3136,16 +3190,10 @@ unsigned long get_state_synchronize_rcu(void)
{
/*
* Any prior manipulation of RCU-protected data must happen
- * before the load from ->gpnum.
+ * before the load from ->gp_seq.
*/
smp_mb(); /* ^^^ */
-
- /*
- * Make sure this load happens before the purportedly
- * time-consuming work between get_state_synchronize_rcu()
- * and cond_synchronize_rcu().
- */
- return smp_load_acquire(&rcu_state_p->gpnum);
+ return rcu_seq_snap(&rcu_state_p->gp_seq);
}
EXPORT_SYMBOL_GPL(get_state_synchronize_rcu);
@@ -3165,15 +3213,10 @@ EXPORT_SYMBOL_GPL(get_state_synchronize_rcu);
*/
void cond_synchronize_rcu(unsigned long oldstate)
{
- unsigned long newstate;
-
- /*
- * Ensure that this load happens before any RCU-destructive
- * actions the caller might carry out after we return.
- */
- newstate = smp_load_acquire(&rcu_state_p->completed);
- if (ULONG_CMP_GE(oldstate, newstate))
+ if (!rcu_seq_done(&rcu_state_p->gp_seq, oldstate))
synchronize_rcu();
+ else
+ smp_mb(); /* Ensure GP ends before subsequent accesses. */
}
EXPORT_SYMBOL_GPL(cond_synchronize_rcu);
@@ -3188,16 +3231,10 @@ unsigned long get_state_synchronize_sched(void)
{
/*
* Any prior manipulation of RCU-protected data must happen
- * before the load from ->gpnum.
+ * before the load from ->gp_seq.
*/
smp_mb(); /* ^^^ */
-
- /*
- * Make sure this load happens before the purportedly
- * time-consuming work between get_state_synchronize_sched()
- * and cond_synchronize_sched().
- */
- return smp_load_acquire(&rcu_sched_state.gpnum);
+ return rcu_seq_snap(&rcu_sched_state.gp_seq);
}
EXPORT_SYMBOL_GPL(get_state_synchronize_sched);
@@ -3217,15 +3254,10 @@ EXPORT_SYMBOL_GPL(get_state_synchronize_sched);
*/
void cond_synchronize_sched(unsigned long oldstate)
{
- unsigned long newstate;
-
- /*
- * Ensure that this load happens before any RCU-destructive
- * actions the caller might carry out after we return.
- */
- newstate = smp_load_acquire(&rcu_sched_state.completed);
- if (ULONG_CMP_GE(oldstate, newstate))
+ if (!rcu_seq_done(&rcu_sched_state.gp_seq, oldstate))
synchronize_sched();
+ else
+ smp_mb(); /* Ensure GP ends before subsequent accesses. */
}
EXPORT_SYMBOL_GPL(cond_synchronize_sched);
@@ -3261,12 +3293,8 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
return 1;
- /* Has another RCU grace period completed? */
- if (READ_ONCE(rnp->completed) != rdp->completed) /* outside lock */
- return 1;
-
- /* Has a new RCU grace period started? */
- if (READ_ONCE(rnp->gpnum) != rdp->gpnum ||
+ /* Have RCU grace period completed or started? */
+ if (rcu_seq_current(&rnp->gp_seq) != rdp->gp_seq ||
unlikely(READ_ONCE(rdp->gpwrap))) /* outside lock */
return 1;
@@ -3298,7 +3326,7 @@ static int rcu_pending(void)
* non-NULL, store an indication of whether all callbacks are lazy.
* (If there are no callbacks, all of them are deemed to be lazy.)
*/
-static bool __maybe_unused rcu_cpu_has_callbacks(bool *all_lazy)
+static bool rcu_cpu_has_callbacks(bool *all_lazy)
{
bool al = true;
bool hc = false;
@@ -3484,17 +3512,22 @@ EXPORT_SYMBOL_GPL(rcu_barrier_sched);
static void rcu_init_new_rnp(struct rcu_node *rnp_leaf)
{
long mask;
+ long oldmask;
struct rcu_node *rnp = rnp_leaf;
- raw_lockdep_assert_held_rcu_node(rnp);
+ raw_lockdep_assert_held_rcu_node(rnp_leaf);
+ WARN_ON_ONCE(rnp->wait_blkd_tasks);
for (;;) {
mask = rnp->grpmask;
rnp = rnp->parent;
if (rnp == NULL)
return;
raw_spin_lock_rcu_node(rnp); /* Interrupts already disabled. */
+ oldmask = rnp->qsmaskinit;
rnp->qsmaskinit |= mask;
raw_spin_unlock_rcu_node(rnp); /* Interrupts remain disabled. */
+ if (oldmask)
+ return;
}
}
@@ -3511,6 +3544,10 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != 1);
WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp->dynticks)));
+ rdp->rcu_ofl_gp_seq = rsp->gp_seq;
+ rdp->rcu_ofl_gp_flags = RCU_GP_CLEANED;
+ rdp->rcu_onl_gp_seq = rsp->gp_seq;
+ rdp->rcu_onl_gp_flags = RCU_GP_CLEANED;
rdp->cpu = cpu;
rdp->rsp = rsp;
rcu_boot_init_nocb_percpu_data(rdp);
@@ -3518,9 +3555,9 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
/*
* Initialize a CPU's per-CPU RCU data. Note that only one online or
- * offline event can be happening at a given time. Note also that we
- * can accept some slop in the rsp->completed access due to the fact
- * that this CPU cannot possibly have any RCU callbacks in flight yet.
+ * offline event can be happening at a given time. Note also that we can
+ * accept some slop in the rsp->gp_seq access due to the fact that this
+ * CPU cannot possibly have any RCU callbacks in flight yet.
*/
static void
rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
@@ -3549,14 +3586,14 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
rnp = rdp->mynode;
raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
rdp->beenonline = true; /* We have now been online. */
- rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */
- rdp->completed = rnp->completed;
+ rdp->gp_seq = rnp->gp_seq;
+ rdp->gp_seq_needed = rnp->gp_seq;
rdp->cpu_no_qs.b.norm = true;
rdp->rcu_qs_ctr_snap = per_cpu(rcu_dynticks.rcu_qs_ctr, cpu);
rdp->core_needs_qs = false;
rdp->rcu_iw_pending = false;
- rdp->rcu_iw_gpnum = rnp->gpnum - 1;
- trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl"));
+ rdp->rcu_iw_gp_seq = rnp->gp_seq - 1;
+ trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("cpuonl"));
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
@@ -3705,7 +3742,15 @@ void rcu_cpu_starting(unsigned int cpu)
nbits = bitmap_weight(&oldmask, BITS_PER_LONG);
/* Allow lockless access for expedited grace periods. */
smp_store_release(&rsp->ncpus, rsp->ncpus + nbits); /* ^^^ */
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ rcu_gpnum_ovf(rnp, rdp); /* Offline-induced counter wrap? */
+ rdp->rcu_onl_gp_seq = READ_ONCE(rsp->gp_seq);
+ rdp->rcu_onl_gp_flags = READ_ONCE(rsp->gp_flags);
+ if (rnp->qsmask & mask) { /* RCU waiting on incoming CPU? */
+ /* Report QS -after- changing ->qsmaskinitnext! */
+ rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
+ } else {
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ }
}
smp_mb(); /* Ensure RCU read-side usage follows above initialization. */
}
@@ -3713,7 +3758,7 @@ void rcu_cpu_starting(unsigned int cpu)
#ifdef CONFIG_HOTPLUG_CPU
/*
* The CPU is exiting the idle loop into the arch_cpu_idle_dead()
- * function. We now remove it from the rcu_node tree's ->qsmaskinit
+ * function. We now remove it from the rcu_node tree's ->qsmaskinitnext
* bit masks.
*/
static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
@@ -3725,9 +3770,18 @@ static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
mask = rdp->grpmask;
+ spin_lock(&rsp->ofl_lock);
raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */
+ rdp->rcu_ofl_gp_seq = READ_ONCE(rsp->gp_seq);
+ rdp->rcu_ofl_gp_flags = READ_ONCE(rsp->gp_flags);
+ if (rnp->qsmask & mask) { /* RCU waiting on outgoing CPU? */
+ /* Report quiescent state -before- changing ->qsmaskinitnext! */
+ rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
+ raw_spin_lock_irqsave_rcu_node(rnp, flags);
+ }
rnp->qsmaskinitnext &= ~mask;
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ spin_unlock(&rsp->ofl_lock);
}
/*
@@ -3839,12 +3893,16 @@ static int __init rcu_spawn_gp_kthread(void)
struct task_struct *t;
/* Force priority into range. */
- if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 1)
+ if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 2
+ && IS_BUILTIN(CONFIG_RCU_TORTURE_TEST))
+ kthread_prio = 2;
+ else if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 1)
kthread_prio = 1;
else if (kthread_prio < 0)
kthread_prio = 0;
else if (kthread_prio > 99)
kthread_prio = 99;
+
if (kthread_prio != kthread_prio_in)
pr_alert("rcu_spawn_gp_kthread(): Limited prio to %d from %d\n",
kthread_prio, kthread_prio_in);
@@ -3928,8 +3986,9 @@ static void __init rcu_init_one(struct rcu_state *rsp)
raw_spin_lock_init(&rnp->fqslock);
lockdep_set_class_and_name(&rnp->fqslock,
&rcu_fqs_class[i], fqs[i]);
- rnp->gpnum = rsp->gpnum;
- rnp->completed = rsp->completed;
+ rnp->gp_seq = rsp->gp_seq;
+ rnp->gp_seq_needed = rsp->gp_seq;
+ rnp->completedqs = rsp->gp_seq;
rnp->qsmask = 0;
rnp->qsmaskinit = 0;
rnp->grplo = j * cpustride;
@@ -3997,7 +4056,7 @@ static void __init rcu_init_geometry(void)
if (rcu_fanout_leaf == RCU_FANOUT_LEAF &&
nr_cpu_ids == NR_CPUS)
return;
- pr_info("RCU: Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%u\n",
+ pr_info("Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%u\n",
rcu_fanout_leaf, nr_cpu_ids);
/*
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 78e051dffc5b..4e74df768c57 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -81,18 +81,16 @@ struct rcu_node {
raw_spinlock_t __private lock; /* Root rcu_node's lock protects */
/* some rcu_state fields as well as */
/* following. */
- unsigned long gpnum; /* Current grace period for this node. */
- /* This will either be equal to or one */
- /* behind the root rcu_node's gpnum. */
- unsigned long completed; /* Last GP completed for this node. */
- /* This will either be equal to or one */
- /* behind the root rcu_node's gpnum. */
+ unsigned long gp_seq; /* Track rsp->rcu_gp_seq. */
+ unsigned long gp_seq_needed; /* Track rsp->rcu_gp_seq_needed. */
+ unsigned long completedqs; /* All QSes done for this node. */
unsigned long qsmask; /* CPUs or groups that need to switch in */
/* order for current grace period to proceed.*/
/* In leaf rcu_node, each bit corresponds to */
/* an rcu_data structure, otherwise, each */
/* bit corresponds to a child rcu_node */
/* structure. */
+ unsigned long rcu_gp_init_mask; /* Mask of offline CPUs at GP init. */
unsigned long qsmaskinit;
/* Per-GP initial value for qsmask. */
/* Initialized from ->qsmaskinitnext at the */
@@ -158,7 +156,6 @@ struct rcu_node {
struct swait_queue_head nocb_gp_wq[2];
/* Place for rcu_nocb_kthread() to wait GP. */
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
- u8 need_future_gp[4]; /* Counts of upcoming GP requests. */
raw_spinlock_t fqslock ____cacheline_internodealigned_in_smp;
spinlock_t exp_lock ____cacheline_internodealigned_in_smp;
@@ -168,22 +165,6 @@ struct rcu_node {
bool exp_need_flush; /* Need to flush workitem? */
} ____cacheline_internodealigned_in_smp;
-/* Accessors for ->need_future_gp[] array. */
-#define need_future_gp_mask() \
- (ARRAY_SIZE(((struct rcu_node *)NULL)->need_future_gp) - 1)
-#define need_future_gp_element(rnp, c) \
- ((rnp)->need_future_gp[(c) & need_future_gp_mask()])
-#define need_any_future_gp(rnp) \
-({ \
- int __i; \
- bool __nonzero = false; \
- \
- for (__i = 0; __i < ARRAY_SIZE((rnp)->need_future_gp); __i++) \
- __nonzero = __nonzero || \
- READ_ONCE((rnp)->need_future_gp[__i]); \
- __nonzero; \
-})
-
/*
* Bitmasks in an rcu_node cover the interval [grplo, grphi] of CPU IDs, and
* are indexed relative to this interval rather than the global CPU ID space.
@@ -206,16 +187,14 @@ union rcu_noqs {
/* Per-CPU data for read-copy update. */
struct rcu_data {
/* 1) quiescent-state and grace-period handling : */
- unsigned long completed; /* Track rsp->completed gp number */
- /* in order to detect GP end. */
- unsigned long gpnum; /* Highest gp number that this CPU */
- /* is aware of having started. */
+ unsigned long gp_seq; /* Track rsp->rcu_gp_seq counter. */
+ unsigned long gp_seq_needed; /* Track rsp->rcu_gp_seq_needed ctr. */
unsigned long rcu_qs_ctr_snap;/* Snapshot of rcu_qs_ctr to check */
/* for rcu_all_qs() invocations. */
union rcu_noqs cpu_no_qs; /* No QSes yet for this CPU. */
bool core_needs_qs; /* Core waits for quiesc state. */
bool beenonline; /* CPU online at least once. */
- bool gpwrap; /* Possible gpnum/completed wrap. */
+ bool gpwrap; /* Possible ->gp_seq wrap. */
struct rcu_node *mynode; /* This CPU's leaf of hierarchy */
unsigned long grpmask; /* Mask to apply to leaf qsmask. */
unsigned long ticks_this_gp; /* The number of scheduling-clock */
@@ -239,7 +218,6 @@ struct rcu_data {
/* 4) reasons this CPU needed to be kicked by force_quiescent_state */
unsigned long dynticks_fqs; /* Kicked due to dynticks idle. */
- unsigned long offline_fqs; /* Kicked due to being offline. */
unsigned long cond_resched_completed;
/* Grace period that needs help */
/* from cond_resched(). */
@@ -278,12 +256,16 @@ struct rcu_data {
/* Leader CPU takes GP-end wakeups. */
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
- /* 7) RCU CPU stall data. */
+ /* 7) Diagnostic data, including RCU CPU stall warnings. */
unsigned int softirq_snap; /* Snapshot of softirq activity. */
/* ->rcu_iw* fields protected by leaf rcu_node ->lock. */
struct irq_work rcu_iw; /* Check for non-irq activity. */
bool rcu_iw_pending; /* Is ->rcu_iw pending? */
- unsigned long rcu_iw_gpnum; /* ->gpnum associated with ->rcu_iw. */
+ unsigned long rcu_iw_gp_seq; /* ->gp_seq associated with ->rcu_iw. */
+ unsigned long rcu_ofl_gp_seq; /* ->gp_seq at last offline. */
+ short rcu_ofl_gp_flags; /* ->gp_flags at last offline. */
+ unsigned long rcu_onl_gp_seq; /* ->gp_seq at last online. */
+ short rcu_onl_gp_flags; /* ->gp_flags at last online. */
int cpu;
struct rcu_state *rsp;
@@ -340,8 +322,7 @@ struct rcu_state {
u8 boost ____cacheline_internodealigned_in_smp;
/* Subject to priority boost. */
- unsigned long gpnum; /* Current gp number. */
- unsigned long completed; /* # of last completed gp. */
+ unsigned long gp_seq; /* Grace-period sequence #. */
struct task_struct *gp_kthread; /* Task for grace periods. */
struct swait_queue_head gp_wq; /* Where GP task waits. */
short gp_flags; /* Commands for GP task. */
@@ -373,6 +354,8 @@ struct rcu_state {
/* but in jiffies. */
unsigned long gp_activity; /* Time of last GP kthread */
/* activity in jiffies. */
+ unsigned long gp_req_activity; /* Time of last GP request */
+ /* in jiffies. */
unsigned long jiffies_stall; /* Time at which to check */
/* for CPU stalls. */
unsigned long jiffies_resched; /* Time at which to resched */
@@ -384,6 +367,10 @@ struct rcu_state {
const char *name; /* Name of structure. */
char abbr; /* Abbreviated name. */
struct list_head flavors; /* List of RCU flavors. */
+
+ spinlock_t ofl_lock ____cacheline_internodealigned_in_smp;
+ /* Synchronize offline with */
+ /* GP pre-initialization. */
};
/* Values for rcu_state structure's gp_flags field. */
@@ -394,16 +381,20 @@ struct rcu_state {
#define RCU_GP_IDLE 0 /* Initial state and no GP in progress. */
#define RCU_GP_WAIT_GPS 1 /* Wait for grace-period start. */
#define RCU_GP_DONE_GPS 2 /* Wait done for grace-period start. */
-#define RCU_GP_WAIT_FQS 3 /* Wait for force-quiescent-state time. */
-#define RCU_GP_DOING_FQS 4 /* Wait done for force-quiescent-state time. */
-#define RCU_GP_CLEANUP 5 /* Grace-period cleanup started. */
-#define RCU_GP_CLEANED 6 /* Grace-period cleanup complete. */
+#define RCU_GP_ONOFF 3 /* Grace-period initialization hotplug. */
+#define RCU_GP_INIT 4 /* Grace-period initialization. */
+#define RCU_GP_WAIT_FQS 5 /* Wait for force-quiescent-state time. */
+#define RCU_GP_DOING_FQS 6 /* Wait done for force-quiescent-state time. */
+#define RCU_GP_CLEANUP 7 /* Grace-period cleanup started. */
+#define RCU_GP_CLEANED 8 /* Grace-period cleanup complete. */
#ifndef RCU_TREE_NONCORE
static const char * const gp_state_names[] = {
"RCU_GP_IDLE",
"RCU_GP_WAIT_GPS",
"RCU_GP_DONE_GPS",
+ "RCU_GP_ONOFF",
+ "RCU_GP_INIT",
"RCU_GP_WAIT_FQS",
"RCU_GP_DOING_FQS",
"RCU_GP_CLEANUP",
@@ -449,10 +440,13 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
static void rcu_print_detail_task_stall(struct rcu_state *rsp);
static int rcu_print_task_stall(struct rcu_node *rnp);
static int rcu_print_task_exp_stall(struct rcu_node *rnp);
-static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
+static void rcu_preempt_check_blocked_tasks(struct rcu_state *rsp,
+ struct rcu_node *rnp);
static void rcu_preempt_check_callbacks(void);
void call_rcu(struct rcu_head *head, rcu_callback_t func);
static void __init __rcu_init_preempt(void);
+static void dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp,
+ int ncheck);
static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
static void invoke_rcu_callbacks_kthread(void);
@@ -489,7 +483,6 @@ static void __init rcu_spawn_nocb_kthreads(void);
#ifdef CONFIG_RCU_NOCB_CPU
static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp);
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
-static void __maybe_unused rcu_kick_nohz_cpu(int cpu);
static bool init_nocb_callback_list(struct rcu_data *rdp);
static void rcu_bind_gp_kthread(void);
static bool rcu_nohz_full_cpu(struct rcu_state *rsp);
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index d40708e8c5d6..0b2c2ad69629 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -212,7 +212,7 @@ static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
if (wake) {
smp_mb(); /* EGP done before wake_up(). */
- swake_up(&rsp->expedited_wq);
+ swake_up_one(&rsp->expedited_wq);
}
break;
}
@@ -472,6 +472,7 @@ retry_ipi:
static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
smp_call_func_t func)
{
+ int cpu;
struct rcu_node *rnp;
trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("reset"));
@@ -486,13 +487,20 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
rnp->rew.rew_func = func;
rnp->rew.rew_rsp = rsp;
if (!READ_ONCE(rcu_par_gp_wq) ||
- rcu_scheduler_active != RCU_SCHEDULER_RUNNING) {
- /* No workqueues yet. */
+ rcu_scheduler_active != RCU_SCHEDULER_RUNNING ||
+ rcu_is_last_leaf_node(rsp, rnp)) {
+ /* No workqueues yet or last leaf, do direct call. */
sync_rcu_exp_select_node_cpus(&rnp->rew.rew_work);
continue;
}
INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus);
- queue_work_on(rnp->grplo, rcu_par_gp_wq, &rnp->rew.rew_work);
+ preempt_disable();
+ cpu = cpumask_next(rnp->grplo - 1, cpu_online_mask);
+ /* If all offline, queue the work on an unbound CPU. */
+ if (unlikely(cpu > rnp->grphi))
+ cpu = WORK_CPU_UNBOUND;
+ queue_work_on(cpu, rcu_par_gp_wq, &rnp->rew.rew_work);
+ preempt_enable();
rnp->exp_need_flush = true;
}
@@ -518,7 +526,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
jiffies_start = jiffies;
for (;;) {
- ret = swait_event_timeout(
+ ret = swait_event_timeout_exclusive(
rsp->expedited_wq,
sync_rcu_preempt_exp_done_unlocked(rnp_root),
jiffies_stall);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 7fd12039e512..a97c20ea9bce 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -74,8 +74,8 @@ static void __init rcu_bootup_announce_oddness(void)
pr_info("\tRCU event tracing is enabled.\n");
if ((IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 64) ||
(!IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 32))
- pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d\n",
- RCU_FANOUT);
+ pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d.\n",
+ RCU_FANOUT);
if (rcu_fanout_exact)
pr_info("\tHierarchical RCU autobalancing is disabled.\n");
if (IS_ENABLED(CONFIG_RCU_FAST_NO_HZ))
@@ -88,11 +88,13 @@ static void __init rcu_bootup_announce_oddness(void)
pr_info("\tBuild-time adjustment of leaf fanout to %d.\n",
RCU_FANOUT_LEAF);
if (rcu_fanout_leaf != RCU_FANOUT_LEAF)
- pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf);
+ pr_info("\tBoot-time adjustment of leaf fanout to %d.\n",
+ rcu_fanout_leaf);
if (nr_cpu_ids != NR_CPUS)
pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%u.\n", NR_CPUS, nr_cpu_ids);
#ifdef CONFIG_RCU_BOOST
- pr_info("\tRCU priority boosting: priority %d delay %d ms.\n", kthread_prio, CONFIG_RCU_BOOST_DELAY);
+ pr_info("\tRCU priority boosting: priority %d delay %d ms.\n",
+ kthread_prio, CONFIG_RCU_BOOST_DELAY);
#endif
if (blimit != DEFAULT_RCU_BLIMIT)
pr_info("\tBoot-time adjustment of callback invocation limit to %ld.\n", blimit);
@@ -127,6 +129,7 @@ static struct rcu_data __percpu *const rcu_data_p = &rcu_preempt_data;
static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
bool wake);
+static void rcu_read_unlock_special(struct task_struct *t);
/*
* Tell them what RCU they are running.
@@ -183,6 +186,9 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
raw_lockdep_assert_held_rcu_node(rnp);
WARN_ON_ONCE(rdp->mynode != rnp);
WARN_ON_ONCE(!rcu_is_leaf_node(rnp));
+ /* RCU better not be waiting on newly onlined CPUs! */
+ WARN_ON_ONCE(rnp->qsmaskinitnext & ~rnp->qsmaskinit & rnp->qsmask &
+ rdp->grpmask);
/*
* Decide where to queue the newly blocked task. In theory,
@@ -260,8 +266,10 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
* ->exp_tasks pointers, respectively, to reference the newly
* blocked tasks.
*/
- if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD))
+ if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD)) {
rnp->gp_tasks = &t->rcu_node_entry;
+ WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq);
+ }
if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD))
rnp->exp_tasks = &t->rcu_node_entry;
WARN_ON_ONCE(!(blkd_state & RCU_GP_BLKD) !=
@@ -286,20 +294,24 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
}
/*
- * Record a preemptible-RCU quiescent state for the specified CPU. Note
- * that this just means that the task currently running on the CPU is
- * not in a quiescent state. There might be any number of tasks blocked
- * while in an RCU read-side critical section.
+ * Record a preemptible-RCU quiescent state for the specified CPU.
+ * Note that this does not necessarily mean that the task currently running
+ * on the CPU is in a quiescent state: Instead, it means that the current
+ * grace period need not wait on any RCU read-side critical section that
+ * starts later on this CPU. It also means that if the current task is
+ * in an RCU read-side critical section, it has already added itself to
+ * some leaf rcu_node structure's ->blkd_tasks list. In addition to the
+ * current task, there might be any number of other tasks blocked while
+ * in an RCU read-side critical section.
*
- * As with the other rcu_*_qs() functions, callers to this function
- * must disable preemption.
+ * Callers to this function must disable preemption.
*/
static void rcu_preempt_qs(void)
{
RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_qs() invoked with preemption enabled!!!\n");
if (__this_cpu_read(rcu_data_p->cpu_no_qs.s)) {
trace_rcu_grace_period(TPS("rcu_preempt"),
- __this_cpu_read(rcu_data_p->gpnum),
+ __this_cpu_read(rcu_data_p->gp_seq),
TPS("cpuqs"));
__this_cpu_write(rcu_data_p->cpu_no_qs.b.norm, false);
barrier(); /* Coordinate with rcu_preempt_check_callbacks(). */
@@ -348,8 +360,8 @@ static void rcu_preempt_note_context_switch(bool preempt)
trace_rcu_preempt_task(rdp->rsp->name,
t->pid,
(rnp->qsmask & rdp->grpmask)
- ? rnp->gpnum
- : rnp->gpnum + 1);
+ ? rnp->gp_seq
+ : rcu_seq_snap(&rnp->gp_seq));
rcu_preempt_ctxt_queue(rnp, rdp);
} else if (t->rcu_read_lock_nesting < 0 &&
t->rcu_read_unlock_special.s) {
@@ -456,7 +468,7 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp)
* notify RCU core processing or task having blocked during the RCU
* read-side critical section.
*/
-void rcu_read_unlock_special(struct task_struct *t)
+static void rcu_read_unlock_special(struct task_struct *t)
{
bool empty_exp;
bool empty_norm;
@@ -535,13 +547,15 @@ void rcu_read_unlock_special(struct task_struct *t)
WARN_ON_ONCE(rnp != t->rcu_blocked_node);
WARN_ON_ONCE(!rcu_is_leaf_node(rnp));
empty_norm = !rcu_preempt_blocked_readers_cgp(rnp);
+ WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq &&
+ (!empty_norm || rnp->qsmask));
empty_exp = sync_rcu_preempt_exp_done(rnp);
smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
np = rcu_next_node_entry(t, rnp);
list_del_init(&t->rcu_node_entry);
t->rcu_blocked_node = NULL;
trace_rcu_unlock_preempted_task(TPS("rcu_preempt"),
- rnp->gpnum, t->pid);
+ rnp->gp_seq, t->pid);
if (&t->rcu_node_entry == rnp->gp_tasks)
rnp->gp_tasks = np;
if (&t->rcu_node_entry == rnp->exp_tasks)
@@ -562,7 +576,7 @@ void rcu_read_unlock_special(struct task_struct *t)
empty_exp_now = sync_rcu_preempt_exp_done(rnp);
if (!empty_norm && !rcu_preempt_blocked_readers_cgp(rnp)) {
trace_rcu_quiescent_state_report(TPS("preempt_rcu"),
- rnp->gpnum,
+ rnp->gp_seq,
0, rnp->qsmask,
rnp->level,
rnp->grplo,
@@ -686,24 +700,27 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp)
* Check that the list of blocked tasks for the newly completed grace
* period is in fact empty. It is a serious bug to complete a grace
* period that still has RCU readers blocked! This function must be
- * invoked -before- updating this rnp's ->gpnum, and the rnp's ->lock
+ * invoked -before- updating this rnp's ->gp_seq, and the rnp's ->lock
* must be held by the caller.
*
* Also, if there are blocked tasks on the list, they automatically
* block the newly created grace period, so set up ->gp_tasks accordingly.
*/
-static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
+static void
+rcu_preempt_check_blocked_tasks(struct rcu_state *rsp, struct rcu_node *rnp)
{
struct task_struct *t;
RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_check_blocked_tasks() invoked with preemption enabled!!!\n");
- WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp));
- if (rcu_preempt_has_tasks(rnp)) {
+ if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)))
+ dump_blkd_tasks(rsp, rnp, 10);
+ if (rcu_preempt_has_tasks(rnp) &&
+ (rnp->qsmaskinit || rnp->wait_blkd_tasks)) {
rnp->gp_tasks = rnp->blkd_tasks.next;
t = container_of(rnp->gp_tasks, struct task_struct,
rcu_node_entry);
trace_rcu_unlock_preempted_task(TPS("rcu_preempt-GPS"),
- rnp->gpnum, t->pid);
+ rnp->gp_seq, t->pid);
}
WARN_ON_ONCE(rnp->qsmask);
}
@@ -717,6 +734,7 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
*/
static void rcu_preempt_check_callbacks(void)
{
+ struct rcu_state *rsp = &rcu_preempt_state;
struct task_struct *t = current;
if (t->rcu_read_lock_nesting == 0) {
@@ -725,7 +743,9 @@ static void rcu_preempt_check_callbacks(void)
}
if (t->rcu_read_lock_nesting > 0 &&
__this_cpu_read(rcu_data_p->core_needs_qs) &&
- __this_cpu_read(rcu_data_p->cpu_no_qs.b.norm))
+ __this_cpu_read(rcu_data_p->cpu_no_qs.b.norm) &&
+ !t->rcu_read_unlock_special.b.need_qs &&
+ time_after(jiffies, rsp->gp_start + HZ))
t->rcu_read_unlock_special.b.need_qs = true;
}
@@ -841,6 +861,47 @@ void exit_rcu(void)
__rcu_read_unlock();
}
+/*
+ * Dump the blocked-tasks state, but limit the list dump to the
+ * specified number of elements.
+ */
+static void
+dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp, int ncheck)
+{
+ int cpu;
+ int i;
+ struct list_head *lhp;
+ bool onl;
+ struct rcu_data *rdp;
+ struct rcu_node *rnp1;
+
+ raw_lockdep_assert_held_rcu_node(rnp);
+ pr_info("%s: grp: %d-%d level: %d ->gp_seq %ld ->completedqs %ld\n",
+ __func__, rnp->grplo, rnp->grphi, rnp->level,
+ (long)rnp->gp_seq, (long)rnp->completedqs);
+ for (rnp1 = rnp; rnp1; rnp1 = rnp1->parent)
+ pr_info("%s: %d:%d ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx\n",
+ __func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext);
+ pr_info("%s: ->gp_tasks %p ->boost_tasks %p ->exp_tasks %p\n",
+ __func__, rnp->gp_tasks, rnp->boost_tasks, rnp->exp_tasks);
+ pr_info("%s: ->blkd_tasks", __func__);
+ i = 0;
+ list_for_each(lhp, &rnp->blkd_tasks) {
+ pr_cont(" %p", lhp);
+ if (++i >= 10)
+ break;
+ }
+ pr_cont("\n");
+ for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++) {
+ rdp = per_cpu_ptr(rsp->rda, cpu);
+ onl = !!(rdp->grpmask & rcu_rnp_online_cpus(rnp));
+ pr_info("\t%d: %c online: %ld(%d) offline: %ld(%d)\n",
+ cpu, ".o"[onl],
+ (long)rdp->rcu_onl_gp_seq, rdp->rcu_onl_gp_flags,
+ (long)rdp->rcu_ofl_gp_seq, rdp->rcu_ofl_gp_flags);
+ }
+}
+
#else /* #ifdef CONFIG_PREEMPT_RCU */
static struct rcu_state *const rcu_state_p = &rcu_sched_state;
@@ -911,7 +972,8 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp)
* so there is no need to check for blocked tasks. So check only for
* bogus qsmask values.
*/
-static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
+static void
+rcu_preempt_check_blocked_tasks(struct rcu_state *rsp, struct rcu_node *rnp)
{
WARN_ON_ONCE(rnp->qsmask);
}
@@ -949,6 +1011,15 @@ void exit_rcu(void)
{
}
+/*
+ * Dump the guaranteed-empty blocked-tasks state. Trust but verify.
+ */
+static void
+dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp, int ncheck)
+{
+ WARN_ON_ONCE(!list_empty(&rnp->blkd_tasks));
+}
+
#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
#ifdef CONFIG_RCU_BOOST
@@ -1433,7 +1504,8 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void)
* completed since we last checked and there are
* callbacks not yet ready to invoke.
*/
- if ((rdp->completed != rnp->completed ||
+ if ((rcu_seq_completed_gp(rdp->gp_seq,
+ rcu_seq_current(&rnp->gp_seq)) ||
unlikely(READ_ONCE(rdp->gpwrap))) &&
rcu_segcblist_pend_cbs(&rdp->cblist))
note_gp_changes(rsp, rdp);
@@ -1720,16 +1792,16 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu)
*/
touch_nmi_watchdog();
- if (rsp->gpnum == rdp->gpnum) {
+ ticks_value = rcu_seq_ctr(rsp->gp_seq - rdp->gp_seq);
+ if (ticks_value) {
+ ticks_title = "GPs behind";
+ } else {
ticks_title = "ticks this GP";
ticks_value = rdp->ticks_this_gp;
- } else {
- ticks_title = "GPs behind";
- ticks_value = rsp->gpnum - rdp->gpnum;
}
print_cpu_stall_fast_no_hz(fast_no_hz, cpu);
- delta = rdp->mynode->gpnum - rdp->rcu_iw_gpnum;
- pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%ld softirq=%u/%u fqs=%ld %s\n",
+ delta = rcu_seq_ctr(rdp->mynode->gp_seq - rdp->rcu_iw_gp_seq);
+ pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s\n",
cpu,
"O."[!!cpu_online(cpu)],
"o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)],
@@ -1817,7 +1889,7 @@ static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq)
static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp)
{
- return &rnp->nocb_gp_wq[rnp->completed & 0x1];
+ return &rnp->nocb_gp_wq[rcu_seq_ctr(rnp->gp_seq) & 0x1];
}
static void rcu_init_one_nocb(struct rcu_node *rnp)
@@ -1854,8 +1926,8 @@ static void __wake_nocb_leader(struct rcu_data *rdp, bool force,
WRITE_ONCE(rdp_leader->nocb_leader_sleep, false);
del_timer(&rdp->nocb_timer);
raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
- smp_mb(); /* ->nocb_leader_sleep before swake_up(). */
- swake_up(&rdp_leader->nocb_wq);
+ smp_mb(); /* ->nocb_leader_sleep before swake_up_one(). */
+ swake_up_one(&rdp_leader->nocb_wq);
} else {
raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
}
@@ -2069,12 +2141,17 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
bool needwake;
struct rcu_node *rnp = rdp->mynode;
- raw_spin_lock_irqsave_rcu_node(rnp, flags);
- c = rcu_cbs_completed(rdp->rsp, rnp);
- needwake = rcu_start_this_gp(rnp, rdp, c);
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
- if (needwake)
- rcu_gp_kthread_wake(rdp->rsp);
+ local_irq_save(flags);
+ c = rcu_seq_snap(&rdp->rsp->gp_seq);
+ if (!rdp->gpwrap && ULONG_CMP_GE(rdp->gp_seq_needed, c)) {
+ local_irq_restore(flags);
+ } else {
+ raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
+ needwake = rcu_start_this_gp(rnp, rdp, c);
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ if (needwake)
+ rcu_gp_kthread_wake(rdp->rsp);
+ }
/*
* Wait for the grace period. Do so interruptibly to avoid messing
@@ -2082,9 +2159,9 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
*/
trace_rcu_this_gp(rnp, rdp, c, TPS("StartWait"));
for (;;) {
- swait_event_interruptible(
- rnp->nocb_gp_wq[c & 0x1],
- (d = ULONG_CMP_GE(READ_ONCE(rnp->completed), c)));
+ swait_event_interruptible_exclusive(
+ rnp->nocb_gp_wq[rcu_seq_ctr(c) & 0x1],
+ (d = rcu_seq_done(&rnp->gp_seq, c)));
if (likely(d))
break;
WARN_ON(signal_pending(current));
@@ -2111,7 +2188,7 @@ wait_again:
/* Wait for callbacks to appear. */
if (!rcu_nocb_poll) {
trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, TPS("Sleep"));
- swait_event_interruptible(my_rdp->nocb_wq,
+ swait_event_interruptible_exclusive(my_rdp->nocb_wq,
!READ_ONCE(my_rdp->nocb_leader_sleep));
raw_spin_lock_irqsave(&my_rdp->nocb_lock, flags);
my_rdp->nocb_leader_sleep = true;
@@ -2176,7 +2253,7 @@ wait_again:
raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
if (rdp != my_rdp && tail == &rdp->nocb_follower_head) {
/* List was empty, so wake up the follower. */
- swake_up(&rdp->nocb_wq);
+ swake_up_one(&rdp->nocb_wq);
}
}
@@ -2193,7 +2270,7 @@ static void nocb_follower_wait(struct rcu_data *rdp)
{
for (;;) {
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("FollowerSleep"));
- swait_event_interruptible(rdp->nocb_wq,
+ swait_event_interruptible_exclusive(rdp->nocb_wq,
READ_ONCE(rdp->nocb_follower_head));
if (smp_load_acquire(&rdp->nocb_follower_head)) {
/* ^^^ Ensure CB invocation follows _head test. */
@@ -2569,23 +2646,6 @@ static bool init_nocb_callback_list(struct rcu_data *rdp)
#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
/*
- * An adaptive-ticks CPU can potentially execute in kernel mode for an
- * arbitrarily long period of time with the scheduling-clock tick turned
- * off. RCU will be paying attention to this CPU because it is in the
- * kernel, but the CPU cannot be guaranteed to be executing the RCU state
- * machine because the scheduling-clock tick has been disabled. Therefore,
- * if an adaptive-ticks CPU is failing to respond to the current grace
- * period and has not be idle from an RCU perspective, kick it.
- */
-static void __maybe_unused rcu_kick_nohz_cpu(int cpu)
-{
-#ifdef CONFIG_NO_HZ_FULL
- if (tick_nohz_full_cpu(cpu))
- smp_send_reschedule(cpu);
-#endif /* #ifdef CONFIG_NO_HZ_FULL */
-}
-
-/*
* Is this CPU a NO_HZ_FULL CPU that should ignore RCU so that the
* grace-period kthread will do force_quiescent_state() processing?
* The idea is to avoid waking up RCU core processing on such a
@@ -2610,8 +2670,6 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp)
*/
static void rcu_bind_gp_kthread(void)
{
- int __maybe_unused cpu;
-
if (!tick_nohz_full_enabled())
return;
housekeeping_affine(current, HK_FLAG_RCU);
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 4c230a60ece4..39cb23d22109 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -507,14 +507,15 @@ early_initcall(check_cpu_stall_init);
#ifdef CONFIG_TASKS_RCU
/*
- * Simple variant of RCU whose quiescent states are voluntary context switch,
- * user-space execution, and idle. As such, grace periods can take one good
- * long time. There are no read-side primitives similar to rcu_read_lock()
- * and rcu_read_unlock() because this implementation is intended to get
- * the system into a safe state for some of the manipulations involved in
- * tracing and the like. Finally, this implementation does not support
- * high call_rcu_tasks() rates from multiple CPUs. If this is required,
- * per-CPU callback lists will be needed.
+ * Simple variant of RCU whose quiescent states are voluntary context
+ * switch, cond_resched_rcu_qs(), user-space execution, and idle.
+ * As such, grace periods can take one good long time. There are no
+ * read-side primitives similar to rcu_read_lock() and rcu_read_unlock()
+ * because this implementation is intended to get the system into a safe
+ * state for some of the manipulations involved in tracing and the like.
+ * Finally, this implementation does not support high call_rcu_tasks()
+ * rates from multiple CPUs. If this is required, per-CPU callback lists
+ * will be needed.
*/
/* Global list of callbacks and associated lock. */
@@ -542,11 +543,11 @@ static struct task_struct *rcu_tasks_kthread_ptr;
* period elapses, in other words after all currently executing RCU
* read-side critical sections have completed. call_rcu_tasks() assumes
* that the read-side critical sections end at a voluntary context
- * switch (not a preemption!), entry into idle, or transition to usermode
- * execution. As such, there are no read-side primitives analogous to
- * rcu_read_lock() and rcu_read_unlock() because this primitive is intended
- * to determine that all tasks have passed through a safe state, not so
- * much for data-strcuture synchronization.
+ * switch (not a preemption!), cond_resched_rcu_qs(), entry into idle,
+ * or transition to usermode execution. As such, there are no read-side
+ * primitives analogous to rcu_read_lock() and rcu_read_unlock() because
+ * this primitive is intended to determine that all tasks have passed
+ * through a safe state, not so much for data-strcuture synchronization.
*
* See the description of call_rcu() for more detailed information on
* memory ordering guarantees.
@@ -667,6 +668,7 @@ static int __noreturn rcu_tasks_kthread(void *arg)
struct rcu_head *list;
struct rcu_head *next;
LIST_HEAD(rcu_tasks_holdouts);
+ int fract;
/* Run on housekeeping CPUs by default. Sysadm can move if desired. */
housekeeping_affine(current, HK_FLAG_RCU);
@@ -748,13 +750,25 @@ static int __noreturn rcu_tasks_kthread(void *arg)
* holdouts. When the list is empty, we are done.
*/
lastreport = jiffies;
- while (!list_empty(&rcu_tasks_holdouts)) {
+
+ /* Start off with HZ/10 wait and slowly back off to 1 HZ wait*/
+ fract = 10;
+
+ for (;;) {
bool firstreport;
bool needreport;
int rtst;
struct task_struct *t1;
- schedule_timeout_interruptible(HZ);
+ if (list_empty(&rcu_tasks_holdouts))
+ break;
+
+ /* Slowly back off waiting for holdouts */
+ schedule_timeout_interruptible(HZ/fract);
+
+ if (fract > 1)
+ fract--;
+
rtst = READ_ONCE(rcu_task_stall_timeout);
needreport = rtst > 0 &&
time_after(jiffies, lastreport + rtst);
@@ -800,6 +814,7 @@ static int __noreturn rcu_tasks_kthread(void *arg)
list = next;
cond_resched();
}
+ /* Paranoid sleep to keep this from entering a tight loop */
schedule_timeout_uninterruptible(HZ/10);
}
}
diff --git a/kernel/reboot.c b/kernel/reboot.c
index e4ced883d8de..8fb44dec9ad7 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -294,7 +294,7 @@ void kernel_power_off(void)
}
EXPORT_SYMBOL_GPL(kernel_power_off);
-static DEFINE_MUTEX(reboot_mutex);
+DEFINE_MUTEX(system_transition_mutex);
/*
* Reboot system call: for obvious reasons only root may call it,
@@ -338,7 +338,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !pm_power_off)
cmd = LINUX_REBOOT_CMD_HALT;
- mutex_lock(&reboot_mutex);
+ mutex_lock(&system_transition_mutex);
switch (cmd) {
case LINUX_REBOOT_CMD_RESTART:
kernel_restart(NULL);
@@ -389,7 +389,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
ret = -EINVAL;
break;
}
- mutex_unlock(&reboot_mutex);
+ mutex_unlock(&system_transition_mutex);
return ret;
}
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index d9a02b318108..7fe183404c38 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -20,7 +20,7 @@ obj-y += core.o loadavg.o clock.o cputime.o
obj-y += idle.o fair.o rt.o deadline.o
obj-y += wait.o wait_bit.o swait.o completion.o
-obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o
+obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o pelt.o
obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o
obj-$(CONFIG_SCHEDSTATS) += stats.o
obj-$(CONFIG_SCHED_DEBUG) += debug.o
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index 10c83e73837a..e3e3b979f9bd 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -53,6 +53,7 @@
*
*/
#include "sched.h"
+#include <linux/sched_clock.h>
/*
* Scheduler clock - returns current time in nanosec units.
@@ -66,12 +67,7 @@ unsigned long long __weak sched_clock(void)
}
EXPORT_SYMBOL_GPL(sched_clock);
-__read_mostly int sched_clock_running;
-
-void sched_clock_init(void)
-{
- sched_clock_running = 1;
-}
+static DEFINE_STATIC_KEY_FALSE(sched_clock_running);
#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
/*
@@ -195,17 +191,40 @@ void clear_sched_clock_stable(void)
smp_mb(); /* matches sched_clock_init_late() */
- if (sched_clock_running == 2)
+ if (static_key_count(&sched_clock_running.key) == 2)
__clear_sched_clock_stable();
}
+static void __sched_clock_gtod_offset(void)
+{
+ struct sched_clock_data *scd = this_scd();
+
+ __scd_stamp(scd);
+ __gtod_offset = (scd->tick_raw + __sched_clock_offset) - scd->tick_gtod;
+}
+
+void __init sched_clock_init(void)
+{
+ /*
+ * Set __gtod_offset such that once we mark sched_clock_running,
+ * sched_clock_tick() continues where sched_clock() left off.
+ *
+ * Even if TSC is buggered, we're still UP at this point so it
+ * can't really be out of sync.
+ */
+ local_irq_disable();
+ __sched_clock_gtod_offset();
+ local_irq_enable();
+
+ static_branch_inc(&sched_clock_running);
+}
/*
* We run this as late_initcall() such that it runs after all built-in drivers,
* notably: acpi_processor and intel_idle, which can mark the TSC as unstable.
*/
static int __init sched_clock_init_late(void)
{
- sched_clock_running = 2;
+ static_branch_inc(&sched_clock_running);
/*
* Ensure that it is impossible to not do a static_key update.
*
@@ -350,8 +369,8 @@ u64 sched_clock_cpu(int cpu)
if (sched_clock_stable())
return sched_clock() + __sched_clock_offset;
- if (unlikely(!sched_clock_running))
- return 0ull;
+ if (!static_branch_unlikely(&sched_clock_running))
+ return sched_clock();
preempt_disable_notrace();
scd = cpu_sdc(cpu);
@@ -373,7 +392,7 @@ void sched_clock_tick(void)
if (sched_clock_stable())
return;
- if (unlikely(!sched_clock_running))
+ if (!static_branch_unlikely(&sched_clock_running))
return;
lockdep_assert_irqs_disabled();
@@ -385,8 +404,6 @@ void sched_clock_tick(void)
void sched_clock_tick_stable(void)
{
- u64 gtod, clock;
-
if (!sched_clock_stable())
return;
@@ -398,9 +415,7 @@ void sched_clock_tick_stable(void)
* TSC to be unstable, any computation will be computing crap.
*/
local_irq_disable();
- gtod = ktime_get_ns();
- clock = sched_clock();
- __gtod_offset = (clock + __sched_clock_offset) - gtod;
+ __sched_clock_gtod_offset();
local_irq_enable();
}
@@ -434,9 +449,17 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
#else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
+void __init sched_clock_init(void)
+{
+ static_branch_inc(&sched_clock_running);
+ local_irq_disable();
+ generic_sched_clock_init();
+ local_irq_enable();
+}
+
u64 sched_clock_cpu(int cpu)
{
- if (unlikely(!sched_clock_running))
+ if (!static_branch_unlikely(&sched_clock_running))
return 0;
return sched_clock();
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index e426b0cb9ac6..a1ad5b7d5521 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -22,8 +22,8 @@
*
* See also complete_all(), wait_for_completion() and related routines.
*
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
*/
void complete(struct completion *x)
{
@@ -44,8 +44,8 @@ EXPORT_SYMBOL(complete);
*
* This will wake up all threads waiting on this particular completion event.
*
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
*
* Since complete_all() sets the completion of @x permanently to done
* to allow multiple waiters to finish, a call to reinit_completion()
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index fe365c9a08e9..625bc9897f62 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -17,6 +17,8 @@
#include "../workqueue_internal.h"
#include "../smpboot.h"
+#include "pelt.h"
+
#define CREATE_TRACE_POINTS
#include <trace/events/sched.h>
@@ -45,14 +47,6 @@ const_debug unsigned int sysctl_sched_features =
const_debug unsigned int sysctl_sched_nr_migrate = 32;
/*
- * period over which we average the RT time consumption, measured
- * in ms.
- *
- * default: 1s
- */
-const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC;
-
-/*
* period over which we measure -rt task CPU usage in us.
* default: 1s
*/
@@ -183,9 +177,9 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
rq->clock_task += delta;
-#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+#ifdef HAVE_SCHED_AVG_IRQ
if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY))
- sched_rt_avg_update(rq, irq_delta + steal);
+ update_irq_load_avg(rq, irq_delta + steal);
#endif
}
@@ -412,8 +406,8 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task)
* its already queued (either by us or someone else) and will get the
* wakeup due to that.
*
- * This cmpxchg() implies a full barrier, which pairs with the write
- * barrier implied by the wakeup in wake_up_q().
+ * This cmpxchg() executes a full barrier, which pairs with the full
+ * barrier executed by the wakeup in wake_up_q().
*/
if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL))
return;
@@ -441,8 +435,8 @@ void wake_up_q(struct wake_q_head *head)
task->wake_q.next = NULL;
/*
- * wake_up_process() implies a wmb() to pair with the queueing
- * in wake_q_add() so as not to miss wakeups.
+ * wake_up_process() executes a full barrier, which pairs with
+ * the queueing in wake_q_add() so as not to miss wakeups.
*/
wake_up_process(task);
put_task_struct(task);
@@ -649,23 +643,6 @@ bool sched_can_stop_tick(struct rq *rq)
return true;
}
#endif /* CONFIG_NO_HZ_FULL */
-
-void sched_avg_update(struct rq *rq)
-{
- s64 period = sched_avg_period();
-
- while ((s64)(rq_clock(rq) - rq->age_stamp) > period) {
- /*
- * Inline assembly required to prevent the compiler
- * optimising this loop into a divmod call.
- * See __iter_div_u64_rem() for another example of this.
- */
- asm("" : "+rm" (rq->age_stamp));
- rq->age_stamp += period;
- rq->rt_avg /= 2;
- }
-}
-
#endif /* CONFIG_SMP */
#if defined(CONFIG_RT_GROUP_SCHED) || (defined(CONFIG_FAIR_GROUP_SCHED) && \
@@ -1199,6 +1176,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
__set_task_cpu(p, new_cpu);
}
+#ifdef CONFIG_NUMA_BALANCING
static void __migrate_swap_task(struct task_struct *p, int cpu)
{
if (task_on_rq_queued(p)) {
@@ -1280,16 +1258,17 @@ unlock:
/*
* Cross migrate two tasks
*/
-int migrate_swap(struct task_struct *cur, struct task_struct *p)
+int migrate_swap(struct task_struct *cur, struct task_struct *p,
+ int target_cpu, int curr_cpu)
{
struct migration_swap_arg arg;
int ret = -EINVAL;
arg = (struct migration_swap_arg){
.src_task = cur,
- .src_cpu = task_cpu(cur),
+ .src_cpu = curr_cpu,
.dst_task = p,
- .dst_cpu = task_cpu(p),
+ .dst_cpu = target_cpu,
};
if (arg.src_cpu == arg.dst_cpu)
@@ -1314,6 +1293,7 @@ int migrate_swap(struct task_struct *cur, struct task_struct *p)
out:
return ret;
}
+#endif /* CONFIG_NUMA_BALANCING */
/*
* wait_task_inactive - wait for a thread to unschedule.
@@ -1879,8 +1859,7 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
* rq(c1)->lock (if not at the same time, then in that order).
* C) LOCK of the rq(c1)->lock scheduling in task
*
- * Transitivity guarantees that B happens after A and C after B.
- * Note: we only require RCpc transitivity.
+ * Release/acquire chaining guarantees that B happens after A and C after B.
* Note: the CPU doing B need not be c0 or c1
*
* Example:
@@ -1942,16 +1921,9 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
* UNLOCK rq(0)->lock
*
*
- * However; for wakeups there is a second guarantee we must provide, namely we
- * must observe the state that lead to our wakeup. That is, not only must our
- * task observe its own prior state, it must also observe the stores prior to
- * its wakeup.
- *
- * This means that any means of doing remote wakeups must order the CPU doing
- * the wakeup against the CPU the task is going to end up running on. This,
- * however, is already required for the regular Program-Order guarantee above,
- * since the waking CPU is the one issueing the ACQUIRE (smp_cond_load_acquire).
- *
+ * However, for wakeups there is a second guarantee we must provide, namely we
+ * must ensure that CONDITION=1 done by the caller can not be reordered with
+ * accesses to the task state; see try_to_wake_up() and set_current_state().
*/
/**
@@ -1967,6 +1939,9 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
* Atomic against schedule() which would dequeue a task, also see
* set_current_state().
*
+ * This function executes a full memory barrier before accessing the task
+ * state; see set_current_state().
+ *
* Return: %true if @p->state changes (an actual wakeup was done),
* %false otherwise.
*/
@@ -1998,21 +1973,20 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
* be possible to, falsely, observe p->on_rq == 0 and get stuck
* in smp_cond_load_acquire() below.
*
- * sched_ttwu_pending() try_to_wake_up()
- * [S] p->on_rq = 1; [L] P->state
- * UNLOCK rq->lock -----.
- * \
- * +--- RMB
- * schedule() /
- * LOCK rq->lock -----'
- * UNLOCK rq->lock
+ * sched_ttwu_pending() try_to_wake_up()
+ * STORE p->on_rq = 1 LOAD p->state
+ * UNLOCK rq->lock
+ *
+ * __schedule() (switch to task 'p')
+ * LOCK rq->lock smp_rmb();
+ * smp_mb__after_spinlock();
+ * UNLOCK rq->lock
*
* [task p]
- * [S] p->state = UNINTERRUPTIBLE [L] p->on_rq
+ * STORE p->state = UNINTERRUPTIBLE LOAD p->on_rq
*
- * Pairs with the UNLOCK+LOCK on rq->lock from the
- * last wakeup of our task and the schedule that got our task
- * current.
+ * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
+ * __schedule(). See the comment for smp_mb__after_spinlock().
*/
smp_rmb();
if (p->on_rq && ttwu_remote(p, wake_flags))
@@ -2026,15 +2000,17 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
* One must be running (->on_cpu == 1) in order to remove oneself
* from the runqueue.
*
- * [S] ->on_cpu = 1; [L] ->on_rq
- * UNLOCK rq->lock
- * RMB
- * LOCK rq->lock
- * [S] ->on_rq = 0; [L] ->on_cpu
+ * __schedule() (switch to task 'p') try_to_wake_up()
+ * STORE p->on_cpu = 1 LOAD p->on_rq
+ * UNLOCK rq->lock
*
- * Pairs with the full barrier implied in the UNLOCK+LOCK on rq->lock
- * from the consecutive calls to schedule(); the first switching to our
- * task, the second putting it to sleep.
+ * __schedule() (put 'p' to sleep)
+ * LOCK rq->lock smp_rmb();
+ * smp_mb__after_spinlock();
+ * STORE p->on_rq = 0 LOAD p->on_cpu
+ *
+ * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
+ * __schedule(). See the comment for smp_mb__after_spinlock().
*/
smp_rmb();
@@ -2140,8 +2116,7 @@ out:
*
* Return: 1 if the process was woken up, 0 if it was already running.
*
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * This function executes a full memory barrier before accessing the task state.
*/
int wake_up_process(struct task_struct *p)
{
@@ -2317,7 +2292,6 @@ static inline void init_schedstats(void) {}
int sched_fork(unsigned long clone_flags, struct task_struct *p)
{
unsigned long flags;
- int cpu = get_cpu();
__sched_fork(clone_flags, p);
/*
@@ -2353,14 +2327,12 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
p->sched_reset_on_fork = 0;
}
- if (dl_prio(p->prio)) {
- put_cpu();
+ if (dl_prio(p->prio))
return -EAGAIN;
- } else if (rt_prio(p->prio)) {
+ 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);
@@ -2376,7 +2348,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
* We're setting the CPU for the first time, we don't migrate,
* so use __set_task_cpu().
*/
- __set_task_cpu(p, cpu);
+ __set_task_cpu(p, smp_processor_id());
if (p->sched_class->task_fork)
p->sched_class->task_fork(p);
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
@@ -2393,8 +2365,6 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
plist_node_init(&p->pushable_tasks, MAX_PRIO);
RB_CLEAR_NODE(&p->pushable_dl_tasks);
#endif
-
- put_cpu();
return 0;
}
@@ -2804,6 +2774,8 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev)
if (current->set_child_tid)
put_user(task_pid_vnr(current), current->set_child_tid);
+
+ calculate_sigpending();
}
/*
@@ -3189,7 +3161,7 @@ static inline void sched_tick_stop(int cpu) { }
#endif
#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
- defined(CONFIG_PREEMPT_TRACER))
+ defined(CONFIG_TRACE_PREEMPT_TOGGLE))
/*
* If the value passed in is equal to the current preempt count
* then we just disabled preemption. Start timing the latency.
@@ -5714,13 +5686,6 @@ void set_rq_offline(struct rq *rq)
}
}
-static void set_cpu_rq_start_time(unsigned int cpu)
-{
- struct rq *rq = cpu_rq(cpu);
-
- rq->age_stamp = sched_clock_cpu(cpu);
-}
-
/*
* used to mark begin/end of suspend/resume:
*/
@@ -5774,6 +5739,18 @@ int sched_cpu_activate(unsigned int cpu)
struct rq *rq = cpu_rq(cpu);
struct rq_flags rf;
+#ifdef CONFIG_SCHED_SMT
+ /*
+ * The sched_smt_present static key needs to be evaluated on every
+ * hotplug event because at boot time SMT might be disabled when
+ * the number of booted CPUs is limited.
+ *
+ * If then later a sibling gets hotplugged, then the key would stay
+ * off and SMT scheduling would never be functional.
+ */
+ if (cpumask_weight(cpu_smt_mask(cpu)) > 1)
+ static_branch_enable_cpuslocked(&sched_smt_present);
+#endif
set_cpu_active(cpu, true);
if (sched_smp_initialized) {
@@ -5838,7 +5815,6 @@ static void sched_rq_cpu_starting(unsigned int cpu)
int sched_cpu_starting(unsigned int cpu)
{
- set_cpu_rq_start_time(cpu);
sched_rq_cpu_starting(cpu);
sched_tick_start(cpu);
return 0;
@@ -5871,22 +5847,6 @@ int sched_cpu_dying(unsigned int cpu)
}
#endif
-#ifdef CONFIG_SCHED_SMT
-DEFINE_STATIC_KEY_FALSE(sched_smt_present);
-
-static void sched_init_smt(void)
-{
- /*
- * We've enumerated all CPUs and will assume that if any CPU
- * has SMT siblings, CPU0 will too.
- */
- if (cpumask_weight(cpu_smt_mask(0)) > 1)
- static_branch_enable(&sched_smt_present);
-}
-#else
-static inline void sched_init_smt(void) { }
-#endif
-
void __init sched_init_smp(void)
{
sched_init_numa();
@@ -5908,8 +5868,6 @@ void __init sched_init_smp(void)
init_sched_rt_class();
init_sched_dl_class();
- sched_init_smt();
-
sched_smp_initialized = true;
}
@@ -5954,7 +5912,6 @@ void __init sched_init(void)
int i, j;
unsigned long alloc_size = 0, ptr;
- sched_clock_init();
wait_bit_init();
#ifdef CONFIG_FAIR_GROUP_SCHED
@@ -6106,7 +6063,6 @@ void __init sched_init(void)
#ifdef CONFIG_SMP
idle_thread_set_boot_cpu();
- set_cpu_rq_start_time(smp_processor_id());
#endif
init_sched_fair_class();
@@ -6785,6 +6741,16 @@ static int cpu_cfs_stat_show(struct seq_file *sf, void *v)
seq_printf(sf, "nr_throttled %d\n", cfs_b->nr_throttled);
seq_printf(sf, "throttled_time %llu\n", cfs_b->throttled_time);
+ if (schedstat_enabled() && tg != &root_task_group) {
+ u64 ws = 0;
+ int i;
+
+ for_each_possible_cpu(i)
+ ws += schedstat_val(tg->se[i]->statistics.wait_sum);
+
+ seq_printf(sf, "wait_sum %llu\n", ws);
+ }
+
return 0;
}
#endif /* CONFIG_CFS_BANDWIDTH */
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index c907fde01eaa..3fffad3bc8a8 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -53,9 +53,7 @@ struct sugov_cpu {
unsigned int iowait_boost_max;
u64 last_update;
- /* The fields below are only needed when sharing a policy: */
- unsigned long util_cfs;
- unsigned long util_dl;
+ unsigned long bw_dl;
unsigned long max;
/* The field below is for single-CPU policies only: */
@@ -179,33 +177,90 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
return cpufreq_driver_resolve_freq(policy, freq);
}
-static void sugov_get_util(struct sugov_cpu *sg_cpu)
+/*
+ * This function computes an effective utilization for the given CPU, to be
+ * used for frequency selection given the linear relation: f = u * f_max.
+ *
+ * The scheduler tracks the following metrics:
+ *
+ * cpu_util_{cfs,rt,dl,irq}()
+ * cpu_bw_dl()
+ *
+ * Where the cfs,rt and dl util numbers are tracked with the same metric and
+ * synchronized windows and are thus directly comparable.
+ *
+ * The cfs,rt,dl utilization are the running times measured with rq->clock_task
+ * which excludes things like IRQ and steal-time. These latter are then accrued
+ * in the irq utilization.
+ *
+ * The DL bandwidth number otoh is not a measured metric but a value computed
+ * based on the task model parameters and gives the minimal utilization
+ * required to meet deadlines.
+ */
+static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
{
struct rq *rq = cpu_rq(sg_cpu->cpu);
+ unsigned long util, irq, max;
- sg_cpu->max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu);
- sg_cpu->util_cfs = cpu_util_cfs(rq);
- sg_cpu->util_dl = cpu_util_dl(rq);
-}
-
-static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu)
-{
- struct rq *rq = cpu_rq(sg_cpu->cpu);
+ sg_cpu->max = max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu);
+ sg_cpu->bw_dl = cpu_bw_dl(rq);
if (rt_rq_is_runnable(&rq->rt))
- return sg_cpu->max;
+ return max;
+
+ /*
+ * Early check to see if IRQ/steal time saturates the CPU, can be
+ * because of inaccuracies in how we track these -- see
+ * update_irq_load_avg().
+ */
+ irq = cpu_util_irq(rq);
+ if (unlikely(irq >= max))
+ return max;
+
+ /*
+ * Because the time spend on RT/DL tasks is visible as 'lost' time to
+ * CFS tasks and we use the same metric to track the effective
+ * utilization (PELT windows are synchronized) we can directly add them
+ * to obtain the CPU's actual utilization.
+ */
+ util = cpu_util_cfs(rq);
+ util += cpu_util_rt(rq);
+
+ /*
+ * We do not make cpu_util_dl() a permanent part of this sum because we
+ * want to use cpu_bw_dl() later on, but we need to check if the
+ * CFS+RT+DL sum is saturated (ie. no idle time) such that we select
+ * f_max when there is no idle time.
+ *
+ * NOTE: numerical errors or stop class might cause us to not quite hit
+ * saturation when we should -- something for later.
+ */
+ if ((util + cpu_util_dl(rq)) >= max)
+ return max;
+
+ /*
+ * There is still idle time; further improve the number by using the
+ * irq metric. Because IRQ/steal time is hidden from the task clock we
+ * need to scale the task numbers:
+ *
+ * 1 - irq
+ * U' = irq + ------- * U
+ * max
+ */
+ util = scale_irq_capacity(util, irq, max);
+ util += irq;
/*
- * Utilization required by DEADLINE must always be granted while, for
- * FAIR, we use blocked utilization of IDLE CPUs as a mechanism to
- * gracefully reduce the frequency when no tasks show up for longer
+ * Bandwidth required by DEADLINE must always be granted while, for
+ * FAIR and RT, we use blocked utilization of IDLE CPUs as a mechanism
+ * to gracefully reduce the frequency when no tasks show up for longer
* periods of time.
*
- * Ideally we would like to set util_dl as min/guaranteed freq and
- * util_cfs + util_dl as requested freq. However, cpufreq is not yet
- * ready for such an interface. So, we only do the latter for now.
+ * Ideally we would like to set bw_dl as min/guaranteed freq and util +
+ * bw_dl as requested freq. However, cpufreq is not yet ready for such
+ * an interface. So, we only do the latter for now.
*/
- return min(sg_cpu->max, (sg_cpu->util_dl + sg_cpu->util_cfs));
+ return min(max, util + sg_cpu->bw_dl);
}
/**
@@ -360,7 +415,7 @@ static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; }
*/
static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu, struct sugov_policy *sg_policy)
{
- if (cpu_util_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->util_dl)
+ if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_dl)
sg_policy->need_freq_update = true;
}
@@ -383,9 +438,8 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
busy = sugov_cpu_is_busy(sg_cpu);
- sugov_get_util(sg_cpu);
+ util = sugov_get_util(sg_cpu);
max = sg_cpu->max;
- util = sugov_aggregate_util(sg_cpu);
sugov_iowait_apply(sg_cpu, time, &util, &max);
next_f = get_next_freq(sg_policy, util, max);
/*
@@ -424,9 +478,8 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j);
unsigned long j_util, j_max;
- sugov_get_util(j_sg_cpu);
+ j_util = sugov_get_util(j_sg_cpu);
j_max = j_sg_cpu->max;
- j_util = sugov_aggregate_util(j_sg_cpu);
sugov_iowait_apply(j_sg_cpu, time, &j_util, &j_max);
if (j_util * max > j_max * util) {
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 10c7b51c0d1f..997ea7b839fa 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -16,6 +16,7 @@
* Fabio Checconi <fchecconi@gmail.com>
*/
#include "sched.h"
+#include "pelt.h"
struct dl_bandwidth def_dl_bandwidth;
@@ -1179,8 +1180,6 @@ static void update_curr_dl(struct rq *rq)
curr->se.exec_start = now;
cgroup_account_cputime(curr, delta_exec);
- sched_rt_avg_update(rq, delta_exec);
-
if (dl_entity_is_special(dl_se))
return;
@@ -1761,6 +1760,9 @@ pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
deadline_queue_push_tasks(rq);
+ if (rq->curr->sched_class != &dl_sched_class)
+ update_dl_rq_load_avg(rq_clock_task(rq), rq, 0);
+
return p;
}
@@ -1768,6 +1770,7 @@ static void put_prev_task_dl(struct rq *rq, struct task_struct *p)
{
update_curr_dl(rq);
+ update_dl_rq_load_avg(rq_clock_task(rq), rq, 1);
if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1)
enqueue_pushable_dl_task(rq, p);
}
@@ -1784,6 +1787,7 @@ static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued)
{
update_curr_dl(rq);
+ update_dl_rq_load_avg(rq_clock_task(rq), rq, 1);
/*
* Even when we have runtime, update_curr_dl() might have resulted in us
* not being the leftmost task anymore. In that case NEED_RESCHED will
@@ -2090,8 +2094,14 @@ retry:
sub_rq_bw(&next_task->dl, &rq->dl);
set_task_cpu(next_task, later_rq->cpu);
add_rq_bw(&next_task->dl, &later_rq->dl);
+
+ /*
+ * Update the later_rq clock here, because the clock is used
+ * by the cpufreq_update_util() inside __add_running_bw().
+ */
+ update_rq_clock(later_rq);
add_running_bw(&next_task->dl, &later_rq->dl);
- activate_task(later_rq, next_task, 0);
+ activate_task(later_rq, next_task, ENQUEUE_NOCLOCK);
ret = 1;
resched_curr(later_rq);
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index e593b4118578..60caf1fb94e0 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -111,20 +111,19 @@ static int sched_feat_set(char *cmp)
cmp += 3;
}
- for (i = 0; i < __SCHED_FEAT_NR; i++) {
- if (strcmp(cmp, sched_feat_names[i]) == 0) {
- if (neg) {
- sysctl_sched_features &= ~(1UL << i);
- sched_feat_disable(i);
- } else {
- sysctl_sched_features |= (1UL << i);
- sched_feat_enable(i);
- }
- break;
- }
+ i = match_string(sched_feat_names, __SCHED_FEAT_NR, cmp);
+ if (i < 0)
+ return i;
+
+ if (neg) {
+ sysctl_sched_features &= ~(1UL << i);
+ sched_feat_disable(i);
+ } else {
+ sysctl_sched_features |= (1UL << i);
+ sched_feat_enable(i);
}
- return i;
+ return 0;
}
static ssize_t
@@ -133,7 +132,7 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
{
char buf[64];
char *cmp;
- int i;
+ int ret;
struct inode *inode;
if (cnt > 63)
@@ -148,10 +147,10 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
/* Ensure the static_key remains in a consistent state */
inode = file_inode(filp);
inode_lock(inode);
- i = sched_feat_set(cmp);
+ ret = sched_feat_set(cmp);
inode_unlock(inode);
- if (i == __SCHED_FEAT_NR)
- return -EINVAL;
+ if (ret < 0)
+ return ret;
*ppos += cnt;
@@ -623,8 +622,6 @@ void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq)
#undef PU
}
-extern __read_mostly int sched_clock_running;
-
static void print_cpu(struct seq_file *m, int cpu)
{
struct rq *rq = cpu_rq(cpu);
@@ -843,8 +840,8 @@ void print_numa_stats(struct seq_file *m, int node, unsigned long tsf,
unsigned long tpf, unsigned long gsf, unsigned long gpf)
{
SEQ_printf(m, "numa_faults node=%d ", node);
- SEQ_printf(m, "task_private=%lu task_shared=%lu ", tsf, tpf);
- SEQ_printf(m, "group_private=%lu group_shared=%lu\n", gsf, gpf);
+ SEQ_printf(m, "task_private=%lu task_shared=%lu ", tpf, tsf);
+ SEQ_printf(m, "group_private=%lu group_shared=%lu\n", gpf, gsf);
}
#endif
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 2f0a0be4d344..b39fb596f6c1 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -255,9 +255,6 @@ static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
return cfs_rq->rq;
}
-/* An entity is a task if it doesn't "own" a runqueue */
-#define entity_is_task(se) (!se->my_q)
-
static inline struct task_struct *task_of(struct sched_entity *se)
{
SCHED_WARN_ON(!entity_is_task(se));
@@ -419,7 +416,6 @@ static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
return container_of(cfs_rq, struct rq, cfs);
}
-#define entity_is_task(se) 1
#define for_each_sched_entity(se) \
for (; se; se = NULL)
@@ -692,7 +688,7 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
}
#ifdef CONFIG_SMP
-
+#include "pelt.h"
#include "sched-pelt.h"
static int select_idle_sibling(struct task_struct *p, int prev_cpu, int cpu);
@@ -735,11 +731,12 @@ static void attach_entity_cfs_rq(struct sched_entity *se);
* To solve this problem, we also cap the util_avg of successive tasks to
* only 1/2 of the left utilization budget:
*
- * util_avg_cap = (1024 - cfs_rq->avg.util_avg) / 2^n
+ * util_avg_cap = (cpu_scale - cfs_rq->avg.util_avg) / 2^n
*
- * where n denotes the nth task.
+ * where n denotes the nth task and cpu_scale the CPU capacity.
*
- * For example, a simplest series from the beginning would be like:
+ * For example, for a CPU with 1024 of capacity, a simplest series from
+ * the beginning would be like:
*
* task util_avg: 512, 256, 128, 64, 32, 16, 8, ...
* cfs_rq util_avg: 512, 768, 896, 960, 992, 1008, 1016, ...
@@ -751,7 +748,8 @@ void post_init_entity_util_avg(struct sched_entity *se)
{
struct cfs_rq *cfs_rq = cfs_rq_of(se);
struct sched_avg *sa = &se->avg;
- long cap = (long)(SCHED_CAPACITY_SCALE - cfs_rq->avg.util_avg) / 2;
+ long cpu_scale = arch_scale_cpu_capacity(NULL, cpu_of(rq_of(cfs_rq)));
+ long cap = (long)(cpu_scale - cfs_rq->avg.util_avg) / 2;
if (cap > 0) {
if (cfs_rq->avg.util_avg != 0) {
@@ -1314,7 +1312,7 @@ static unsigned long score_nearby_nodes(struct task_struct *p, int nid,
* of each group. Skip other nodes.
*/
if (sched_numa_topology_type == NUMA_BACKPLANE &&
- dist > maxdist)
+ dist >= maxdist)
continue;
/* Add up the faults from nearby nodes. */
@@ -1452,15 +1450,12 @@ static unsigned long capacity_of(int cpu);
/* Cached statistics for all CPUs within a node */
struct numa_stats {
- unsigned long nr_running;
unsigned long load;
/* Total compute capacity of CPUs on a node */
unsigned long compute_capacity;
- /* Approximate capacity in terms of runnable tasks on a node */
- unsigned long task_capacity;
- int has_free_capacity;
+ unsigned int nr_running;
};
/*
@@ -1487,8 +1482,7 @@ static void update_numa_stats(struct numa_stats *ns, int nid)
* the @ns structure is NULL'ed and task_numa_compare() will
* not find this node attractive.
*
- * We'll either bail at !has_free_capacity, or we'll detect a huge
- * imbalance and bail there.
+ * We'll detect a huge imbalance and bail there.
*/
if (!cpus)
return;
@@ -1497,9 +1491,8 @@ static void update_numa_stats(struct numa_stats *ns, int nid)
smt = DIV_ROUND_UP(SCHED_CAPACITY_SCALE * cpus, ns->compute_capacity);
capacity = cpus / smt; /* cores */
- ns->task_capacity = min_t(unsigned, capacity,
+ capacity = min_t(unsigned, capacity,
DIV_ROUND_CLOSEST(ns->compute_capacity, SCHED_CAPACITY_SCALE));
- ns->has_free_capacity = (ns->nr_running < ns->task_capacity);
}
struct task_numa_env {
@@ -1548,28 +1541,12 @@ static bool load_too_imbalanced(long src_load, long dst_load,
src_capacity = env->src_stats.compute_capacity;
dst_capacity = env->dst_stats.compute_capacity;
- /* We care about the slope of the imbalance, not the direction. */
- if (dst_load < src_load)
- swap(dst_load, src_load);
+ imb = abs(dst_load * src_capacity - src_load * dst_capacity);
- /* Is the difference below the threshold? */
- imb = dst_load * src_capacity * 100 -
- src_load * dst_capacity * env->imbalance_pct;
- if (imb <= 0)
- return false;
-
- /*
- * The imbalance is above the allowed threshold.
- * Compare it with the old imbalance.
- */
orig_src_load = env->src_stats.load;
orig_dst_load = env->dst_stats.load;
- if (orig_dst_load < orig_src_load)
- swap(orig_dst_load, orig_src_load);
-
- old_imb = orig_dst_load * src_capacity * 100 -
- orig_src_load * dst_capacity * env->imbalance_pct;
+ old_imb = abs(orig_dst_load * src_capacity - orig_src_load * dst_capacity);
/* Would this change make things worse? */
return (imb > old_imb);
@@ -1582,9 +1559,8 @@ static bool load_too_imbalanced(long src_load, long dst_load,
* be exchanged with the source task
*/
static void task_numa_compare(struct task_numa_env *env,
- long taskimp, long groupimp)
+ long taskimp, long groupimp, bool maymove)
{
- struct rq *src_rq = cpu_rq(env->src_cpu);
struct rq *dst_rq = cpu_rq(env->dst_cpu);
struct task_struct *cur;
long src_load, dst_load;
@@ -1605,97 +1581,73 @@ static void task_numa_compare(struct task_numa_env *env,
if (cur == env->p)
goto unlock;
+ if (!cur) {
+ if (maymove || imp > env->best_imp)
+ goto assign;
+ else
+ goto unlock;
+ }
+
/*
* "imp" is the fault differential for the source task between the
* source and destination node. Calculate the total differential for
* the source task and potential destination task. The more negative
- * the value is, the more rmeote accesses that would be expected to
+ * the value is, the more remote accesses that would be expected to
* be incurred if the tasks were swapped.
*/
- if (cur) {
- /* Skip this swap candidate if cannot move to the source CPU: */
- if (!cpumask_test_cpu(env->src_cpu, &cur->cpus_allowed))
- goto unlock;
+ /* Skip this swap candidate if cannot move to the source cpu */
+ if (!cpumask_test_cpu(env->src_cpu, &cur->cpus_allowed))
+ goto unlock;
+ /*
+ * If dst and source tasks are in the same NUMA group, or not
+ * in any group then look only at task weights.
+ */
+ if (cur->numa_group == env->p->numa_group) {
+ imp = taskimp + task_weight(cur, env->src_nid, dist) -
+ task_weight(cur, env->dst_nid, dist);
/*
- * If dst and source tasks are in the same NUMA group, or not
- * in any group then look only at task weights.
+ * Add some hysteresis to prevent swapping the
+ * tasks within a group over tiny differences.
*/
- if (cur->numa_group == env->p->numa_group) {
- imp = taskimp + task_weight(cur, env->src_nid, dist) -
- task_weight(cur, env->dst_nid, dist);
- /*
- * Add some hysteresis to prevent swapping the
- * tasks within a group over tiny differences.
- */
- if (cur->numa_group)
- imp -= imp/16;
- } else {
- /*
- * Compare the group weights. If a task is all by
- * itself (not part of a group), use the task weight
- * instead.
- */
- if (cur->numa_group)
- imp += group_weight(cur, env->src_nid, dist) -
- group_weight(cur, env->dst_nid, dist);
- else
- imp += task_weight(cur, env->src_nid, dist) -
- task_weight(cur, env->dst_nid, dist);
- }
+ if (cur->numa_group)
+ imp -= imp / 16;
+ } else {
+ /*
+ * Compare the group weights. If a task is all by itself
+ * (not part of a group), use the task weight instead.
+ */
+ if (cur->numa_group && env->p->numa_group)
+ imp += group_weight(cur, env->src_nid, dist) -
+ group_weight(cur, env->dst_nid, dist);
+ else
+ imp += task_weight(cur, env->src_nid, dist) -
+ task_weight(cur, env->dst_nid, dist);
}
- if (imp <= env->best_imp && moveimp <= env->best_imp)
+ if (imp <= env->best_imp)
goto unlock;
- if (!cur) {
- /* Is there capacity at our destination? */
- if (env->src_stats.nr_running <= env->src_stats.task_capacity &&
- !env->dst_stats.has_free_capacity)
- goto unlock;
-
- goto balance;
- }
-
- /* Balance doesn't matter much if we're running a task per CPU: */
- if (imp > env->best_imp && src_rq->nr_running == 1 &&
- dst_rq->nr_running == 1)
+ if (maymove && moveimp > imp && moveimp > env->best_imp) {
+ imp = moveimp - 1;
+ cur = NULL;
goto assign;
+ }
/*
* In the overloaded case, try and keep the load balanced.
*/
-balance:
- load = task_h_load(env->p);
+ load = task_h_load(env->p) - task_h_load(cur);
+ if (!load)
+ goto assign;
+
dst_load = env->dst_stats.load + load;
src_load = env->src_stats.load - load;
- if (moveimp > imp && moveimp > env->best_imp) {
- /*
- * If the improvement from just moving env->p direction is
- * better than swapping tasks around, check if a move is
- * possible. Store a slightly smaller score than moveimp,
- * so an actually idle CPU will win.
- */
- if (!load_too_imbalanced(src_load, dst_load, env)) {
- imp = moveimp - 1;
- cur = NULL;
- goto assign;
- }
- }
-
- if (imp <= env->best_imp)
- goto unlock;
-
- if (cur) {
- load = task_h_load(cur);
- dst_load -= load;
- src_load += load;
- }
-
if (load_too_imbalanced(src_load, dst_load, env))
goto unlock;
+assign:
/*
* One idle CPU per node is evaluated for a task numa move.
* Call select_idle_sibling to maybe find a better one.
@@ -1711,7 +1663,6 @@ balance:
local_irq_enable();
}
-assign:
task_numa_assign(env, cur, imp);
unlock:
rcu_read_unlock();
@@ -1720,43 +1671,30 @@ unlock:
static void task_numa_find_cpu(struct task_numa_env *env,
long taskimp, long groupimp)
{
+ long src_load, dst_load, load;
+ bool maymove = false;
int cpu;
+ load = task_h_load(env->p);
+ dst_load = env->dst_stats.load + load;
+ src_load = env->src_stats.load - load;
+
+ /*
+ * If the improvement from just moving env->p direction is better
+ * than swapping tasks around, check if a move is possible.
+ */
+ maymove = !load_too_imbalanced(src_load, dst_load, env);
+
for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) {
/* Skip this CPU if the source task cannot migrate */
if (!cpumask_test_cpu(cpu, &env->p->cpus_allowed))
continue;
env->dst_cpu = cpu;
- task_numa_compare(env, taskimp, groupimp);
+ task_numa_compare(env, taskimp, groupimp, maymove);
}
}
-/* Only move tasks to a NUMA node less busy than the current node. */
-static bool numa_has_capacity(struct task_numa_env *env)
-{
- struct numa_stats *src = &env->src_stats;
- struct numa_stats *dst = &env->dst_stats;
-
- if (src->has_free_capacity && !dst->has_free_capacity)
- return false;
-
- /*
- * Only consider a task move if the source has a higher load
- * than the destination, corrected for CPU capacity on each node.
- *
- * src->load dst->load
- * --------------------- vs ---------------------
- * src->compute_capacity dst->compute_capacity
- */
- if (src->load * dst->compute_capacity * env->imbalance_pct >
-
- dst->load * src->compute_capacity * 100)
- return true;
-
- return false;
-}
-
static int task_numa_migrate(struct task_struct *p)
{
struct task_numa_env env = {
@@ -1797,7 +1735,7 @@ static int task_numa_migrate(struct task_struct *p)
* elsewhere, so there is no point in (re)trying.
*/
if (unlikely(!sd)) {
- p->numa_preferred_nid = task_node(p);
+ sched_setnuma(p, task_node(p));
return -EINVAL;
}
@@ -1811,8 +1749,7 @@ static int task_numa_migrate(struct task_struct *p)
update_numa_stats(&env.dst_stats, env.dst_nid);
/* Try to find a spot on the preferred nid. */
- if (numa_has_capacity(&env))
- task_numa_find_cpu(&env, taskimp, groupimp);
+ task_numa_find_cpu(&env, taskimp, groupimp);
/*
* Look at other nodes in these cases:
@@ -1842,8 +1779,7 @@ static int task_numa_migrate(struct task_struct *p)
env.dist = dist;
env.dst_nid = nid;
update_numa_stats(&env.dst_stats, env.dst_nid);
- if (numa_has_capacity(&env))
- task_numa_find_cpu(&env, taskimp, groupimp);
+ task_numa_find_cpu(&env, taskimp, groupimp);
}
}
@@ -1856,15 +1792,13 @@ static int task_numa_migrate(struct task_struct *p)
* trying for a better one later. Do not set the preferred node here.
*/
if (p->numa_group) {
- struct numa_group *ng = p->numa_group;
-
if (env.best_cpu == -1)
nid = env.src_nid;
else
- nid = env.dst_nid;
+ nid = cpu_to_node(env.best_cpu);
- if (ng->active_nodes > 1 && numa_is_active_node(env.dst_nid, ng))
- sched_setnuma(p, env.dst_nid);
+ if (nid != p->numa_preferred_nid)
+ sched_setnuma(p, nid);
}
/* No better CPU than the current one was found. */
@@ -1884,7 +1818,8 @@ static int task_numa_migrate(struct task_struct *p)
return ret;
}
- ret = migrate_swap(p, env.best_task);
+ ret = migrate_swap(p, env.best_task, env.best_cpu, env.src_cpu);
+
if (ret != 0)
trace_sched_stick_numa(p, env.src_cpu, task_cpu(env.best_task));
put_task_struct(env.best_task);
@@ -2144,8 +2079,8 @@ static int preferred_group_nid(struct task_struct *p, int nid)
static void task_numa_placement(struct task_struct *p)
{
- int seq, nid, max_nid = -1, max_group_nid = -1;
- unsigned long max_faults = 0, max_group_faults = 0;
+ int seq, nid, max_nid = -1;
+ unsigned long max_faults = 0;
unsigned long fault_types[2] = { 0, 0 };
unsigned long total_faults;
u64 runtime, period;
@@ -2224,33 +2159,30 @@ static void task_numa_placement(struct task_struct *p)
}
}
- if (faults > max_faults) {
- max_faults = faults;
+ if (!p->numa_group) {
+ if (faults > max_faults) {
+ max_faults = faults;
+ max_nid = nid;
+ }
+ } else if (group_faults > max_faults) {
+ max_faults = group_faults;
max_nid = nid;
}
-
- if (group_faults > max_group_faults) {
- max_group_faults = group_faults;
- max_group_nid = nid;
- }
}
- update_task_scan_period(p, fault_types[0], fault_types[1]);
-
if (p->numa_group) {
numa_group_count_active_nodes(p->numa_group);
spin_unlock_irq(group_lock);
- max_nid = preferred_group_nid(p, max_group_nid);
+ max_nid = preferred_group_nid(p, max_nid);
}
if (max_faults) {
/* Set the new preferred node */
if (max_nid != p->numa_preferred_nid)
sched_setnuma(p, max_nid);
-
- if (task_node(p) != p->numa_preferred_nid)
- numa_migrate_preferred(p);
}
+
+ update_task_scan_period(p, fault_types[0], fault_types[1]);
}
static inline int get_numa_group(struct numa_group *grp)
@@ -2450,14 +2382,14 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
numa_is_active_node(mem_node, ng))
local = 1;
- task_numa_placement(p);
-
/*
* Retry task to preferred node migration periodically, in case it
* case it previously failed, or the scheduler moved us.
*/
- if (time_after(jiffies, p->numa_migrate_retry))
+ if (time_after(jiffies, p->numa_migrate_retry)) {
+ task_numa_placement(p);
numa_migrate_preferred(p);
+ }
if (migrated)
p->numa_pages_migrated += pages;
@@ -2749,19 +2681,6 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
} while (0)
#ifdef CONFIG_SMP
-/*
- * XXX we want to get rid of these helpers and use the full load resolution.
- */
-static inline long se_weight(struct sched_entity *se)
-{
- return scale_load_down(se->load.weight);
-}
-
-static inline long se_runnable(struct sched_entity *se)
-{
- return scale_load_down(se->runnable_weight);
-}
-
static inline void
enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
@@ -3062,314 +2981,6 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq, int flags)
}
#ifdef CONFIG_SMP
-/*
- * Approximate:
- * val * y^n, where y^32 ~= 0.5 (~1 scheduling period)
- */
-static u64 decay_load(u64 val, u64 n)
-{
- unsigned int local_n;
-
- if (unlikely(n > LOAD_AVG_PERIOD * 63))
- return 0;
-
- /* after bounds checking we can collapse to 32-bit */
- local_n = n;
-
- /*
- * As y^PERIOD = 1/2, we can combine
- * y^n = 1/2^(n/PERIOD) * y^(n%PERIOD)
- * With a look-up table which covers y^n (n<PERIOD)
- *
- * To achieve constant time decay_load.
- */
- if (unlikely(local_n >= LOAD_AVG_PERIOD)) {
- val >>= local_n / LOAD_AVG_PERIOD;
- local_n %= LOAD_AVG_PERIOD;
- }
-
- val = mul_u64_u32_shr(val, runnable_avg_yN_inv[local_n], 32);
- return val;
-}
-
-static u32 __accumulate_pelt_segments(u64 periods, u32 d1, u32 d3)
-{
- u32 c1, c2, c3 = d3; /* y^0 == 1 */
-
- /*
- * c1 = d1 y^p
- */
- c1 = decay_load((u64)d1, periods);
-
- /*
- * p-1
- * c2 = 1024 \Sum y^n
- * n=1
- *
- * inf inf
- * = 1024 ( \Sum y^n - \Sum y^n - y^0 )
- * n=0 n=p
- */
- c2 = LOAD_AVG_MAX - decay_load(LOAD_AVG_MAX, periods) - 1024;
-
- return c1 + c2 + c3;
-}
-
-/*
- * Accumulate the three separate parts of the sum; d1 the remainder
- * of the last (incomplete) period, d2 the span of full periods and d3
- * the remainder of the (incomplete) current period.
- *
- * d1 d2 d3
- * ^ ^ ^
- * | | |
- * |<->|<----------------->|<--->|
- * ... |---x---|------| ... |------|-----x (now)
- *
- * p-1
- * u' = (u + d1) y^p + 1024 \Sum y^n + d3 y^0
- * n=1
- *
- * = u y^p + (Step 1)
- *
- * p-1
- * d1 y^p + 1024 \Sum y^n + d3 y^0 (Step 2)
- * n=1
- */
-static __always_inline u32
-accumulate_sum(u64 delta, int cpu, struct sched_avg *sa,
- unsigned long load, unsigned long runnable, int running)
-{
- unsigned long scale_freq, scale_cpu;
- u32 contrib = (u32)delta; /* p == 0 -> delta < 1024 */
- u64 periods;
-
- scale_freq = arch_scale_freq_capacity(cpu);
- scale_cpu = arch_scale_cpu_capacity(NULL, cpu);
-
- delta += sa->period_contrib;
- periods = delta / 1024; /* A period is 1024us (~1ms) */
-
- /*
- * Step 1: decay old *_sum if we crossed period boundaries.
- */
- if (periods) {
- sa->load_sum = decay_load(sa->load_sum, periods);
- sa->runnable_load_sum =
- decay_load(sa->runnable_load_sum, periods);
- sa->util_sum = decay_load((u64)(sa->util_sum), periods);
-
- /*
- * Step 2
- */
- delta %= 1024;
- contrib = __accumulate_pelt_segments(periods,
- 1024 - sa->period_contrib, delta);
- }
- sa->period_contrib = delta;
-
- contrib = cap_scale(contrib, scale_freq);
- if (load)
- sa->load_sum += load * contrib;
- if (runnable)
- sa->runnable_load_sum += runnable * contrib;
- if (running)
- sa->util_sum += contrib * scale_cpu;
-
- return periods;
-}
-
-/*
- * We can represent the historical contribution to runnable average as the
- * coefficients of a geometric series. To do this we sub-divide our runnable
- * history into segments of approximately 1ms (1024us); label the segment that
- * occurred N-ms ago p_N, with p_0 corresponding to the current period, e.g.
- *
- * [<- 1024us ->|<- 1024us ->|<- 1024us ->| ...
- * p0 p1 p2
- * (now) (~1ms ago) (~2ms ago)
- *
- * Let u_i denote the fraction of p_i that the entity was runnable.
- *
- * We then designate the fractions u_i as our co-efficients, yielding the
- * following representation of historical load:
- * u_0 + u_1*y + u_2*y^2 + u_3*y^3 + ...
- *
- * We choose y based on the with of a reasonably scheduling period, fixing:
- * y^32 = 0.5
- *
- * This means that the contribution to load ~32ms ago (u_32) will be weighted
- * approximately half as much as the contribution to load within the last ms
- * (u_0).
- *
- * When a period "rolls over" and we have new u_0`, multiplying the previous
- * sum again by y is sufficient to update:
- * load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... )
- * = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}]
- */
-static __always_inline int
-___update_load_sum(u64 now, int cpu, struct sched_avg *sa,
- unsigned long load, unsigned long runnable, int running)
-{
- u64 delta;
-
- delta = now - sa->last_update_time;
- /*
- * This should only happen when time goes backwards, which it
- * unfortunately does during sched clock init when we swap over to TSC.
- */
- if ((s64)delta < 0) {
- sa->last_update_time = now;
- return 0;
- }
-
- /*
- * Use 1024ns as the unit of measurement since it's a reasonable
- * approximation of 1us and fast to compute.
- */
- delta >>= 10;
- if (!delta)
- return 0;
-
- sa->last_update_time += delta << 10;
-
- /*
- * running is a subset of runnable (weight) so running can't be set if
- * runnable is clear. But there are some corner cases where the current
- * se has been already dequeued but cfs_rq->curr still points to it.
- * This means that weight will be 0 but not running for a sched_entity
- * but also for a cfs_rq if the latter becomes idle. As an example,
- * this happens during idle_balance() which calls
- * update_blocked_averages()
- */
- if (!load)
- runnable = running = 0;
-
- /*
- * Now we know we crossed measurement unit boundaries. The *_avg
- * accrues by two steps:
- *
- * Step 1: accumulate *_sum since last_update_time. If we haven't
- * crossed period boundaries, finish.
- */
- if (!accumulate_sum(delta, cpu, sa, load, runnable, running))
- return 0;
-
- return 1;
-}
-
-static __always_inline void
-___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runnable)
-{
- u32 divider = LOAD_AVG_MAX - 1024 + sa->period_contrib;
-
- /*
- * Step 2: update *_avg.
- */
- sa->load_avg = div_u64(load * sa->load_sum, divider);
- sa->runnable_load_avg = div_u64(runnable * sa->runnable_load_sum, divider);
- sa->util_avg = sa->util_sum / divider;
-}
-
-/*
- * When a task is dequeued, its estimated utilization should not be update if
- * its util_avg has not been updated at least once.
- * This flag is used to synchronize util_avg updates with util_est updates.
- * We map this information into the LSB bit of the utilization saved at
- * dequeue time (i.e. util_est.dequeued).
- */
-#define UTIL_AVG_UNCHANGED 0x1
-
-static inline void cfs_se_util_change(struct sched_avg *avg)
-{
- unsigned int enqueued;
-
- if (!sched_feat(UTIL_EST))
- return;
-
- /* Avoid store if the flag has been already set */
- enqueued = avg->util_est.enqueued;
- if (!(enqueued & UTIL_AVG_UNCHANGED))
- return;
-
- /* Reset flag to report util_avg has been updated */
- enqueued &= ~UTIL_AVG_UNCHANGED;
- WRITE_ONCE(avg->util_est.enqueued, enqueued);
-}
-
-/*
- * sched_entity:
- *
- * task:
- * se_runnable() == se_weight()
- *
- * group: [ see update_cfs_group() ]
- * se_weight() = tg->weight * grq->load_avg / tg->load_avg
- * se_runnable() = se_weight(se) * grq->runnable_load_avg / grq->load_avg
- *
- * load_sum := runnable_sum
- * load_avg = se_weight(se) * runnable_avg
- *
- * runnable_load_sum := runnable_sum
- * runnable_load_avg = se_runnable(se) * runnable_avg
- *
- * XXX collapse load_sum and runnable_load_sum
- *
- * cfq_rs:
- *
- * load_sum = \Sum se_weight(se) * se->avg.load_sum
- * load_avg = \Sum se->avg.load_avg
- *
- * runnable_load_sum = \Sum se_runnable(se) * se->avg.runnable_load_sum
- * runnable_load_avg = \Sum se->avg.runable_load_avg
- */
-
-static int
-__update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se)
-{
- if (entity_is_task(se))
- se->runnable_weight = se->load.weight;
-
- if (___update_load_sum(now, cpu, &se->avg, 0, 0, 0)) {
- ___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
- return 1;
- }
-
- return 0;
-}
-
-static int
-__update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
- if (entity_is_task(se))
- se->runnable_weight = se->load.weight;
-
- if (___update_load_sum(now, cpu, &se->avg, !!se->on_rq, !!se->on_rq,
- cfs_rq->curr == se)) {
-
- ___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
- cfs_se_util_change(&se->avg);
- return 1;
- }
-
- return 0;
-}
-
-static int
-__update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq)
-{
- if (___update_load_sum(now, cpu, &cfs_rq->avg,
- scale_load_down(cfs_rq->load.weight),
- scale_load_down(cfs_rq->runnable_weight),
- cfs_rq->curr != NULL)) {
-
- ___update_load_avg(&cfs_rq->avg, 1, 1);
- return 1;
- }
-
- return 0;
-}
-
#ifdef CONFIG_FAIR_GROUP_SCHED
/**
* update_tg_load_avg - update the tg's load avg
@@ -4037,12 +3648,6 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep)
#else /* CONFIG_SMP */
-static inline int
-update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
-{
- return 0;
-}
-
#define UPDATE_TG 0x0
#define SKIP_AGE_LOAD 0x0
#define DO_ATTACH 0x0
@@ -4726,7 +4331,6 @@ static inline int throttled_lb_pair(struct task_group *tg,
throttled_hierarchy(dest_cfs_rq);
}
-/* updated child weight may affect parent so we have to do this bottom up */
static int tg_unthrottle_up(struct task_group *tg, void *data)
{
struct rq *rq = data;
@@ -5653,8 +5257,6 @@ static void cpu_load_update(struct rq *this_rq, unsigned long this_load,
this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i;
}
-
- sched_avg_update(this_rq);
}
/* Used instead of source_load when we know the type == 0 */
@@ -6237,6 +5839,7 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p
}
#ifdef CONFIG_SCHED_SMT
+DEFINE_STATIC_KEY_FALSE(sched_smt_present);
static inline void set_idle_cores(int cpu, int val)
{
@@ -7294,8 +6897,8 @@ static int task_hot(struct task_struct *p, struct lb_env *env)
static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
{
struct numa_group *numa_group = rcu_dereference(p->numa_group);
- unsigned long src_faults, dst_faults;
- int src_nid, dst_nid;
+ unsigned long src_weight, dst_weight;
+ int src_nid, dst_nid, dist;
if (!static_branch_likely(&sched_numa_balancing))
return -1;
@@ -7322,18 +6925,19 @@ static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
return 0;
/* Leaving a core idle is often worse than degrading locality. */
- if (env->idle != CPU_NOT_IDLE)
+ if (env->idle == CPU_IDLE)
return -1;
+ dist = node_distance(src_nid, dst_nid);
if (numa_group) {
- src_faults = group_faults(p, src_nid);
- dst_faults = group_faults(p, dst_nid);
+ src_weight = group_weight(p, src_nid, dist);
+ dst_weight = group_weight(p, dst_nid, dist);
} else {
- src_faults = task_faults(p, src_nid);
- dst_faults = task_faults(p, dst_nid);
+ src_weight = task_weight(p, src_nid, dist);
+ dst_weight = task_weight(p, dst_nid, dist);
}
- return dst_faults < src_faults;
+ return dst_weight < src_weight;
}
#else
@@ -7620,6 +7224,22 @@ static inline bool cfs_rq_has_blocked(struct cfs_rq *cfs_rq)
return false;
}
+static inline bool others_have_blocked(struct rq *rq)
+{
+ if (READ_ONCE(rq->avg_rt.util_avg))
+ return true;
+
+ if (READ_ONCE(rq->avg_dl.util_avg))
+ return true;
+
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+ if (READ_ONCE(rq->avg_irq.util_avg))
+ return true;
+#endif
+
+ return false;
+}
+
#ifdef CONFIG_FAIR_GROUP_SCHED
static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
@@ -7679,6 +7299,12 @@ static void update_blocked_averages(int cpu)
if (cfs_rq_has_blocked(cfs_rq))
done = false;
}
+ update_rt_rq_load_avg(rq_clock_task(rq), rq, 0);
+ update_dl_rq_load_avg(rq_clock_task(rq), rq, 0);
+ update_irq_load_avg(rq, 0);
+ /* Don't need periodic decay once load/util_avg are null */
+ if (others_have_blocked(rq))
+ done = false;
#ifdef CONFIG_NO_HZ_COMMON
rq->last_blocked_load_update_tick = jiffies;
@@ -7744,9 +7370,12 @@ static inline void update_blocked_averages(int cpu)
rq_lock_irqsave(rq, &rf);
update_rq_clock(rq);
update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq);
+ update_rt_rq_load_avg(rq_clock_task(rq), rq, 0);
+ update_dl_rq_load_avg(rq_clock_task(rq), rq, 0);
+ update_irq_load_avg(rq, 0);
#ifdef CONFIG_NO_HZ_COMMON
rq->last_blocked_load_update_tick = jiffies;
- if (!cfs_rq_has_blocked(cfs_rq))
+ if (!cfs_rq_has_blocked(cfs_rq) && !others_have_blocked(rq))
rq->has_blocked_load = 0;
#endif
rq_unlock_irqrestore(rq, &rf);
@@ -7856,39 +7485,32 @@ static inline int get_sd_load_idx(struct sched_domain *sd,
static unsigned long scale_rt_capacity(int cpu)
{
struct rq *rq = cpu_rq(cpu);
- u64 total, used, age_stamp, avg;
- s64 delta;
+ unsigned long max = arch_scale_cpu_capacity(NULL, cpu);
+ unsigned long used, free;
+ unsigned long irq;
- /*
- * Since we're reading these variables without serialization make sure
- * we read them once before doing sanity checks on them.
- */
- age_stamp = READ_ONCE(rq->age_stamp);
- avg = READ_ONCE(rq->rt_avg);
- delta = __rq_clock_broken(rq) - age_stamp;
+ irq = cpu_util_irq(rq);
- if (unlikely(delta < 0))
- delta = 0;
+ if (unlikely(irq >= max))
+ return 1;
- total = sched_avg_period() + delta;
+ used = READ_ONCE(rq->avg_rt.util_avg);
+ used += READ_ONCE(rq->avg_dl.util_avg);
- used = div_u64(avg, total);
+ if (unlikely(used >= max))
+ return 1;
- if (likely(used < SCHED_CAPACITY_SCALE))
- return SCHED_CAPACITY_SCALE - used;
+ free = max - used;
- return 1;
+ return scale_irq_capacity(free, irq, max);
}
static void update_cpu_capacity(struct sched_domain *sd, int cpu)
{
- unsigned long capacity = arch_scale_cpu_capacity(sd, cpu);
+ unsigned long capacity = scale_rt_capacity(cpu);
struct sched_group *sdg = sd->groups;
- cpu_rq(cpu)->cpu_capacity_orig = capacity;
-
- capacity *= scale_rt_capacity(cpu);
- capacity >>= SCHED_CAPACITY_SHIFT;
+ cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(sd, cpu);
if (!capacity)
capacity = 1;
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 1a3e9bddd17b..16f84142f2f4 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -190,7 +190,7 @@ static void cpuidle_idle_call(void)
*/
next_state = cpuidle_select(drv, dev, &stop_tick);
- if (stop_tick)
+ if (stop_tick || tick_nohz_tick_stopped())
tick_nohz_idle_stop_tick();
else
tick_nohz_idle_retain_tick();
diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
new file mode 100644
index 000000000000..35475c0c5419
--- /dev/null
+++ b/kernel/sched/pelt.c
@@ -0,0 +1,399 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Per Entity Load Tracking
+ *
+ * Copyright (C) 2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ *
+ * Interactivity improvements by Mike Galbraith
+ * (C) 2007 Mike Galbraith <efault@gmx.de>
+ *
+ * Various enhancements by Dmitry Adamushko.
+ * (C) 2007 Dmitry Adamushko <dmitry.adamushko@gmail.com>
+ *
+ * Group scheduling enhancements by Srivatsa Vaddagiri
+ * Copyright IBM Corporation, 2007
+ * Author: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
+ *
+ * Scaled math optimizations by Thomas Gleixner
+ * Copyright (C) 2007, Thomas Gleixner <tglx@linutronix.de>
+ *
+ * Adaptive scheduling granularity, math enhancements by Peter Zijlstra
+ * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
+ *
+ * Move PELT related code from fair.c into this pelt.c file
+ * Author: Vincent Guittot <vincent.guittot@linaro.org>
+ */
+
+#include <linux/sched.h>
+#include "sched.h"
+#include "sched-pelt.h"
+#include "pelt.h"
+
+/*
+ * Approximate:
+ * val * y^n, where y^32 ~= 0.5 (~1 scheduling period)
+ */
+static u64 decay_load(u64 val, u64 n)
+{
+ unsigned int local_n;
+
+ if (unlikely(n > LOAD_AVG_PERIOD * 63))
+ return 0;
+
+ /* after bounds checking we can collapse to 32-bit */
+ local_n = n;
+
+ /*
+ * As y^PERIOD = 1/2, we can combine
+ * y^n = 1/2^(n/PERIOD) * y^(n%PERIOD)
+ * With a look-up table which covers y^n (n<PERIOD)
+ *
+ * To achieve constant time decay_load.
+ */
+ if (unlikely(local_n >= LOAD_AVG_PERIOD)) {
+ val >>= local_n / LOAD_AVG_PERIOD;
+ local_n %= LOAD_AVG_PERIOD;
+ }
+
+ val = mul_u64_u32_shr(val, runnable_avg_yN_inv[local_n], 32);
+ return val;
+}
+
+static u32 __accumulate_pelt_segments(u64 periods, u32 d1, u32 d3)
+{
+ u32 c1, c2, c3 = d3; /* y^0 == 1 */
+
+ /*
+ * c1 = d1 y^p
+ */
+ c1 = decay_load((u64)d1, periods);
+
+ /*
+ * p-1
+ * c2 = 1024 \Sum y^n
+ * n=1
+ *
+ * inf inf
+ * = 1024 ( \Sum y^n - \Sum y^n - y^0 )
+ * n=0 n=p
+ */
+ c2 = LOAD_AVG_MAX - decay_load(LOAD_AVG_MAX, periods) - 1024;
+
+ return c1 + c2 + c3;
+}
+
+#define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
+
+/*
+ * Accumulate the three separate parts of the sum; d1 the remainder
+ * of the last (incomplete) period, d2 the span of full periods and d3
+ * the remainder of the (incomplete) current period.
+ *
+ * d1 d2 d3
+ * ^ ^ ^
+ * | | |
+ * |<->|<----------------->|<--->|
+ * ... |---x---|------| ... |------|-----x (now)
+ *
+ * p-1
+ * u' = (u + d1) y^p + 1024 \Sum y^n + d3 y^0
+ * n=1
+ *
+ * = u y^p + (Step 1)
+ *
+ * p-1
+ * d1 y^p + 1024 \Sum y^n + d3 y^0 (Step 2)
+ * n=1
+ */
+static __always_inline u32
+accumulate_sum(u64 delta, int cpu, struct sched_avg *sa,
+ unsigned long load, unsigned long runnable, int running)
+{
+ unsigned long scale_freq, scale_cpu;
+ u32 contrib = (u32)delta; /* p == 0 -> delta < 1024 */
+ u64 periods;
+
+ scale_freq = arch_scale_freq_capacity(cpu);
+ scale_cpu = arch_scale_cpu_capacity(NULL, cpu);
+
+ delta += sa->period_contrib;
+ periods = delta / 1024; /* A period is 1024us (~1ms) */
+
+ /*
+ * Step 1: decay old *_sum if we crossed period boundaries.
+ */
+ if (periods) {
+ sa->load_sum = decay_load(sa->load_sum, periods);
+ sa->runnable_load_sum =
+ decay_load(sa->runnable_load_sum, periods);
+ sa->util_sum = decay_load((u64)(sa->util_sum), periods);
+
+ /*
+ * Step 2
+ */
+ delta %= 1024;
+ contrib = __accumulate_pelt_segments(periods,
+ 1024 - sa->period_contrib, delta);
+ }
+ sa->period_contrib = delta;
+
+ contrib = cap_scale(contrib, scale_freq);
+ if (load)
+ sa->load_sum += load * contrib;
+ if (runnable)
+ sa->runnable_load_sum += runnable * contrib;
+ if (running)
+ sa->util_sum += contrib * scale_cpu;
+
+ return periods;
+}
+
+/*
+ * We can represent the historical contribution to runnable average as the
+ * coefficients of a geometric series. To do this we sub-divide our runnable
+ * history into segments of approximately 1ms (1024us); label the segment that
+ * occurred N-ms ago p_N, with p_0 corresponding to the current period, e.g.
+ *
+ * [<- 1024us ->|<- 1024us ->|<- 1024us ->| ...
+ * p0 p1 p2
+ * (now) (~1ms ago) (~2ms ago)
+ *
+ * Let u_i denote the fraction of p_i that the entity was runnable.
+ *
+ * We then designate the fractions u_i as our co-efficients, yielding the
+ * following representation of historical load:
+ * u_0 + u_1*y + u_2*y^2 + u_3*y^3 + ...
+ *
+ * We choose y based on the with of a reasonably scheduling period, fixing:
+ * y^32 = 0.5
+ *
+ * This means that the contribution to load ~32ms ago (u_32) will be weighted
+ * approximately half as much as the contribution to load within the last ms
+ * (u_0).
+ *
+ * When a period "rolls over" and we have new u_0`, multiplying the previous
+ * sum again by y is sufficient to update:
+ * load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... )
+ * = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}]
+ */
+static __always_inline int
+___update_load_sum(u64 now, int cpu, struct sched_avg *sa,
+ unsigned long load, unsigned long runnable, int running)
+{
+ u64 delta;
+
+ delta = now - sa->last_update_time;
+ /*
+ * This should only happen when time goes backwards, which it
+ * unfortunately does during sched clock init when we swap over to TSC.
+ */
+ if ((s64)delta < 0) {
+ sa->last_update_time = now;
+ return 0;
+ }
+
+ /*
+ * Use 1024ns as the unit of measurement since it's a reasonable
+ * approximation of 1us and fast to compute.
+ */
+ delta >>= 10;
+ if (!delta)
+ return 0;
+
+ sa->last_update_time += delta << 10;
+
+ /*
+ * running is a subset of runnable (weight) so running can't be set if
+ * runnable is clear. But there are some corner cases where the current
+ * se has been already dequeued but cfs_rq->curr still points to it.
+ * This means that weight will be 0 but not running for a sched_entity
+ * but also for a cfs_rq if the latter becomes idle. As an example,
+ * this happens during idle_balance() which calls
+ * update_blocked_averages()
+ */
+ if (!load)
+ runnable = running = 0;
+
+ /*
+ * Now we know we crossed measurement unit boundaries. The *_avg
+ * accrues by two steps:
+ *
+ * Step 1: accumulate *_sum since last_update_time. If we haven't
+ * crossed period boundaries, finish.
+ */
+ if (!accumulate_sum(delta, cpu, sa, load, runnable, running))
+ return 0;
+
+ return 1;
+}
+
+static __always_inline void
+___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runnable)
+{
+ u32 divider = LOAD_AVG_MAX - 1024 + sa->period_contrib;
+
+ /*
+ * Step 2: update *_avg.
+ */
+ sa->load_avg = div_u64(load * sa->load_sum, divider);
+ sa->runnable_load_avg = div_u64(runnable * sa->runnable_load_sum, divider);
+ WRITE_ONCE(sa->util_avg, sa->util_sum / divider);
+}
+
+/*
+ * sched_entity:
+ *
+ * task:
+ * se_runnable() == se_weight()
+ *
+ * group: [ see update_cfs_group() ]
+ * se_weight() = tg->weight * grq->load_avg / tg->load_avg
+ * se_runnable() = se_weight(se) * grq->runnable_load_avg / grq->load_avg
+ *
+ * load_sum := runnable_sum
+ * load_avg = se_weight(se) * runnable_avg
+ *
+ * runnable_load_sum := runnable_sum
+ * runnable_load_avg = se_runnable(se) * runnable_avg
+ *
+ * XXX collapse load_sum and runnable_load_sum
+ *
+ * cfq_rq:
+ *
+ * load_sum = \Sum se_weight(se) * se->avg.load_sum
+ * load_avg = \Sum se->avg.load_avg
+ *
+ * runnable_load_sum = \Sum se_runnable(se) * se->avg.runnable_load_sum
+ * runnable_load_avg = \Sum se->avg.runable_load_avg
+ */
+
+int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se)
+{
+ if (entity_is_task(se))
+ se->runnable_weight = se->load.weight;
+
+ if (___update_load_sum(now, cpu, &se->avg, 0, 0, 0)) {
+ ___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
+ return 1;
+ }
+
+ return 0;
+}
+
+int __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+ if (entity_is_task(se))
+ se->runnable_weight = se->load.weight;
+
+ if (___update_load_sum(now, cpu, &se->avg, !!se->on_rq, !!se->on_rq,
+ cfs_rq->curr == se)) {
+
+ ___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
+ cfs_se_util_change(&se->avg);
+ return 1;
+ }
+
+ return 0;
+}
+
+int __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq)
+{
+ if (___update_load_sum(now, cpu, &cfs_rq->avg,
+ scale_load_down(cfs_rq->load.weight),
+ scale_load_down(cfs_rq->runnable_weight),
+ cfs_rq->curr != NULL)) {
+
+ ___update_load_avg(&cfs_rq->avg, 1, 1);
+ return 1;
+ }
+
+ return 0;
+}
+
+/*
+ * rt_rq:
+ *
+ * util_sum = \Sum se->avg.util_sum but se->avg.util_sum is not tracked
+ * util_sum = cpu_scale * load_sum
+ * runnable_load_sum = load_sum
+ *
+ * load_avg and runnable_load_avg are not supported and meaningless.
+ *
+ */
+
+int update_rt_rq_load_avg(u64 now, struct rq *rq, int running)
+{
+ if (___update_load_sum(now, rq->cpu, &rq->avg_rt,
+ running,
+ running,
+ running)) {
+
+ ___update_load_avg(&rq->avg_rt, 1, 1);
+ return 1;
+ }
+
+ return 0;
+}
+
+/*
+ * dl_rq:
+ *
+ * util_sum = \Sum se->avg.util_sum but se->avg.util_sum is not tracked
+ * util_sum = cpu_scale * load_sum
+ * runnable_load_sum = load_sum
+ *
+ */
+
+int update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
+{
+ if (___update_load_sum(now, rq->cpu, &rq->avg_dl,
+ running,
+ running,
+ running)) {
+
+ ___update_load_avg(&rq->avg_dl, 1, 1);
+ return 1;
+ }
+
+ return 0;
+}
+
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+/*
+ * irq:
+ *
+ * util_sum = \Sum se->avg.util_sum but se->avg.util_sum is not tracked
+ * util_sum = cpu_scale * load_sum
+ * runnable_load_sum = load_sum
+ *
+ */
+
+int update_irq_load_avg(struct rq *rq, u64 running)
+{
+ int ret = 0;
+ /*
+ * We know the time that has been used by interrupt since last update
+ * but we don't when. Let be pessimistic and assume that interrupt has
+ * happened just before the update. This is not so far from reality
+ * because interrupt will most probably wake up task and trig an update
+ * of rq clock during which the metric si updated.
+ * We start to decay with normal context time and then we add the
+ * interrupt context time.
+ * We can safely remove running from rq->clock because
+ * rq->clock += delta with delta >= running
+ */
+ ret = ___update_load_sum(rq->clock - running, rq->cpu, &rq->avg_irq,
+ 0,
+ 0,
+ 0);
+ ret += ___update_load_sum(rq->clock, rq->cpu, &rq->avg_irq,
+ 1,
+ 1,
+ 1);
+
+ if (ret)
+ ___update_load_avg(&rq->avg_irq, 1, 1);
+
+ return ret;
+}
+#endif
diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h
new file mode 100644
index 000000000000..d2894db28955
--- /dev/null
+++ b/kernel/sched/pelt.h
@@ -0,0 +1,72 @@
+#ifdef CONFIG_SMP
+
+int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se);
+int __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se);
+int __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq);
+int update_rt_rq_load_avg(u64 now, struct rq *rq, int running);
+int update_dl_rq_load_avg(u64 now, struct rq *rq, int running);
+
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+int update_irq_load_avg(struct rq *rq, u64 running);
+#else
+static inline int
+update_irq_load_avg(struct rq *rq, u64 running)
+{
+ return 0;
+}
+#endif
+
+/*
+ * When a task is dequeued, its estimated utilization should not be update if
+ * its util_avg has not been updated at least once.
+ * This flag is used to synchronize util_avg updates with util_est updates.
+ * We map this information into the LSB bit of the utilization saved at
+ * dequeue time (i.e. util_est.dequeued).
+ */
+#define UTIL_AVG_UNCHANGED 0x1
+
+static inline void cfs_se_util_change(struct sched_avg *avg)
+{
+ unsigned int enqueued;
+
+ if (!sched_feat(UTIL_EST))
+ return;
+
+ /* Avoid store if the flag has been already set */
+ enqueued = avg->util_est.enqueued;
+ if (!(enqueued & UTIL_AVG_UNCHANGED))
+ return;
+
+ /* Reset flag to report util_avg has been updated */
+ enqueued &= ~UTIL_AVG_UNCHANGED;
+ WRITE_ONCE(avg->util_est.enqueued, enqueued);
+}
+
+#else
+
+static inline int
+update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
+{
+ return 0;
+}
+
+static inline int
+update_rt_rq_load_avg(u64 now, struct rq *rq, int running)
+{
+ return 0;
+}
+
+static inline int
+update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
+{
+ return 0;
+}
+
+static inline int
+update_irq_load_avg(struct rq *rq, u64 running)
+{
+ return 0;
+}
+#endif
+
+
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 572567078b60..2e2955a8cf8f 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -5,6 +5,8 @@
*/
#include "sched.h"
+#include "pelt.h"
+
int sched_rr_timeslice = RR_TIMESLICE;
int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE;
@@ -836,6 +838,8 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
* can be time-consuming. Try to avoid it when possible.
*/
raw_spin_lock(&rt_rq->rt_runtime_lock);
+ if (!sched_feat(RT_RUNTIME_SHARE) && rt_rq->rt_runtime != RUNTIME_INF)
+ rt_rq->rt_runtime = rt_b->rt_runtime;
skip = !rt_rq->rt_time && !rt_rq->rt_nr_running;
raw_spin_unlock(&rt_rq->rt_runtime_lock);
if (skip)
@@ -971,8 +975,6 @@ static void update_curr_rt(struct rq *rq)
curr->se.exec_start = now;
cgroup_account_cputime(curr, delta_exec);
- sched_rt_avg_update(rq, delta_exec);
-
if (!rt_bandwidth_enabled())
return;
@@ -1576,6 +1578,14 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
rt_queue_push_tasks(rq);
+ /*
+ * If prev task was rt, put_prev_task() has already updated the
+ * utilization. We only care of the case where we start to schedule a
+ * rt task
+ */
+ if (rq->curr->sched_class != &rt_sched_class)
+ update_rt_rq_load_avg(rq_clock_task(rq), rq, 0);
+
return p;
}
@@ -1583,6 +1593,8 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
{
update_curr_rt(rq);
+ update_rt_rq_load_avg(rq_clock_task(rq), rq, 1);
+
/*
* The previous task needs to be made eligible for pushing
* if it is still active
@@ -2312,6 +2324,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
struct sched_rt_entity *rt_se = &p->rt;
update_curr_rt(rq);
+ update_rt_rq_load_avg(rq_clock_task(rq), rq, 1);
watchdog(rq, p);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c7742dcc136c..4a2e8cae63c4 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -594,6 +594,7 @@ struct rt_rq {
unsigned long rt_nr_total;
int overloaded;
struct plist_head pushable_tasks;
+
#endif /* CONFIG_SMP */
int rt_queued;
@@ -673,7 +674,26 @@ struct dl_rq {
u64 bw_ratio;
};
+#ifdef CONFIG_FAIR_GROUP_SCHED
+/* An entity is a task if it doesn't "own" a runqueue */
+#define entity_is_task(se) (!se->my_q)
+#else
+#define entity_is_task(se) 1
+#endif
+
#ifdef CONFIG_SMP
+/*
+ * XXX we want to get rid of these helpers and use the full load resolution.
+ */
+static inline long se_weight(struct sched_entity *se)
+{
+ return scale_load_down(se->load.weight);
+}
+
+static inline long se_runnable(struct sched_entity *se)
+{
+ return scale_load_down(se->runnable_weight);
+}
static inline bool sched_asym_prefer(int a, int b)
{
@@ -833,8 +853,12 @@ struct rq {
struct list_head cfs_tasks;
- u64 rt_avg;
- u64 age_stamp;
+ struct sched_avg avg_rt;
+ struct sched_avg avg_dl;
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+#define HAVE_SCHED_AVG_IRQ
+ struct sched_avg avg_irq;
+#endif
u64 idle_stamp;
u64 avg_idle;
@@ -1075,7 +1099,8 @@ enum numa_faults_stats {
};
extern void sched_setnuma(struct task_struct *p, int node);
extern int migrate_task_to(struct task_struct *p, int cpu);
-extern int migrate_swap(struct task_struct *, struct task_struct *);
+extern int migrate_swap(struct task_struct *p, struct task_struct *t,
+ int cpu, int scpu);
extern void init_numa_balancing(unsigned long clone_flags, struct task_struct *p);
#else
static inline void
@@ -1690,15 +1715,9 @@ extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags);
extern void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags);
-extern const_debug unsigned int sysctl_sched_time_avg;
extern const_debug unsigned int sysctl_sched_nr_migrate;
extern const_debug unsigned int sysctl_sched_migration_cost;
-static inline u64 sched_avg_period(void)
-{
- return (u64)sysctl_sched_time_avg * NSEC_PER_MSEC / 2;
-}
-
#ifdef CONFIG_SCHED_HRTICK
/*
@@ -1735,8 +1754,6 @@ unsigned long arch_scale_freq_capacity(int cpu)
#endif
#ifdef CONFIG_SMP
-extern void sched_avg_update(struct rq *rq);
-
#ifndef arch_scale_cpu_capacity
static __always_inline
unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
@@ -1747,12 +1764,6 @@ unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
return SCHED_CAPACITY_SCALE;
}
#endif
-
-static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
-{
- rq->rt_avg += rt_delta * arch_scale_freq_capacity(cpu_of(rq));
- sched_avg_update(rq);
-}
#else
#ifndef arch_scale_cpu_capacity
static __always_inline
@@ -1761,8 +1772,6 @@ unsigned long arch_scale_cpu_capacity(void __always_unused *sd, int cpu)
return SCHED_CAPACITY_SCALE;
}
#endif
-static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { }
-static inline void sched_avg_update(struct rq *rq) { }
#endif
struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
@@ -2177,11 +2186,16 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
#endif
#ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL
-static inline unsigned long cpu_util_dl(struct rq *rq)
+static inline unsigned long cpu_bw_dl(struct rq *rq)
{
return (rq->dl.running_bw * SCHED_CAPACITY_SCALE) >> BW_SHIFT;
}
+static inline unsigned long cpu_util_dl(struct rq *rq)
+{
+ return READ_ONCE(rq->avg_dl.util_avg);
+}
+
static inline unsigned long cpu_util_cfs(struct rq *rq)
{
unsigned long util = READ_ONCE(rq->cfs.avg.util_avg);
@@ -2193,4 +2207,37 @@ static inline unsigned long cpu_util_cfs(struct rq *rq)
return util;
}
+
+static inline unsigned long cpu_util_rt(struct rq *rq)
+{
+ return READ_ONCE(rq->avg_rt.util_avg);
+}
+#endif
+
+#ifdef HAVE_SCHED_AVG_IRQ
+static inline unsigned long cpu_util_irq(struct rq *rq)
+{
+ return rq->avg_irq.util_avg;
+}
+
+static inline
+unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned long max)
+{
+ util *= (max - irq);
+ util /= max;
+
+ return util;
+
+}
+#else
+static inline unsigned long cpu_util_irq(struct rq *rq)
+{
+ return 0;
+}
+
+static inline
+unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned long max)
+{
+ return util;
+}
#endif
diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c
index b6fb2c3b3ff7..66b59ac77c22 100644
--- a/kernel/sched/swait.c
+++ b/kernel/sched/swait.c
@@ -32,7 +32,7 @@ void swake_up_locked(struct swait_queue_head *q)
}
EXPORT_SYMBOL(swake_up_locked);
-void swake_up(struct swait_queue_head *q)
+void swake_up_one(struct swait_queue_head *q)
{
unsigned long flags;
@@ -40,7 +40,7 @@ void swake_up(struct swait_queue_head *q)
swake_up_locked(q);
raw_spin_unlock_irqrestore(&q->lock, flags);
}
-EXPORT_SYMBOL(swake_up);
+EXPORT_SYMBOL(swake_up_one);
/*
* Does not allow usage from IRQ disabled, since we must be able to
@@ -69,14 +69,14 @@ void swake_up_all(struct swait_queue_head *q)
}
EXPORT_SYMBOL(swake_up_all);
-void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait)
+static void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait)
{
wait->task = current;
if (list_empty(&wait->task_list))
- list_add(&wait->task_list, &q->task_list);
+ list_add_tail(&wait->task_list, &q->task_list);
}
-void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state)
+void prepare_to_swait_exclusive(struct swait_queue_head *q, struct swait_queue *wait, int state)
{
unsigned long flags;
@@ -85,16 +85,28 @@ void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int
set_current_state(state);
raw_spin_unlock_irqrestore(&q->lock, flags);
}
-EXPORT_SYMBOL(prepare_to_swait);
+EXPORT_SYMBOL(prepare_to_swait_exclusive);
long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state)
{
- if (signal_pending_state(state, current))
- return -ERESTARTSYS;
+ unsigned long flags;
+ long ret = 0;
- prepare_to_swait(q, wait, state);
+ raw_spin_lock_irqsave(&q->lock, flags);
+ if (unlikely(signal_pending_state(state, current))) {
+ /*
+ * See prepare_to_wait_event(). TL;DR, subsequent swake_up_one()
+ * must not see us.
+ */
+ list_del_init(&wait->task_list);
+ ret = -ERESTARTSYS;
+ } else {
+ __prepare_to_swait(q, wait);
+ set_current_state(state);
+ }
+ raw_spin_unlock_irqrestore(&q->lock, flags);
- return 0;
+ return ret;
}
EXPORT_SYMBOL(prepare_to_swait_event);
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 05a831427bc7..56a0fed30c0a 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -47,7 +47,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) {
printk(KERN_ERR "ERROR: domain->span does not contain CPU%d\n", cpu);
}
- if (!cpumask_test_cpu(cpu, sched_group_span(group))) {
+ if (group && !cpumask_test_cpu(cpu, sched_group_span(group))) {
printk(KERN_ERR "ERROR: domain->groups does not contain CPU%d\n", cpu);
}
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 928be527477e..5dd47f1103d1 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -69,6 +69,8 @@ static int __wake_up_common(struct wait_queue_head *wq_head, unsigned int mode,
wait_queue_entry_t *curr, *next;
int cnt = 0;
+ lockdep_assert_held(&wq_head->lock);
+
if (bookmark && (bookmark->flags & WQ_FLAG_BOOKMARK)) {
curr = list_next_entry(bookmark, entry);
@@ -134,8 +136,8 @@ static void __wake_up_common_lock(struct wait_queue_head *wq_head, unsigned int
* @nr_exclusive: how many wake-one or wake-many threads to wake up
* @key: is directly passed to the wakeup function
*
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
*/
void __wake_up(struct wait_queue_head *wq_head, unsigned int mode,
int nr_exclusive, void *key)
@@ -180,8 +182,8 @@ EXPORT_SYMBOL_GPL(__wake_up_locked_key_bookmark);
*
* On UP it can prevent extra preemption.
*
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
*/
void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode,
int nr_exclusive, void *key)
@@ -392,35 +394,36 @@ static inline bool is_kthread_should_stop(void)
* if (condition)
* break;
*
- * p->state = mode; condition = true;
- * smp_mb(); // A smp_wmb(); // C
- * if (!wq_entry->flags & WQ_FLAG_WOKEN) wq_entry->flags |= WQ_FLAG_WOKEN;
- * schedule() try_to_wake_up();
- * p->state = TASK_RUNNING; ~~~~~~~~~~~~~~~~~~
- * wq_entry->flags &= ~WQ_FLAG_WOKEN; condition = true;
- * smp_mb() // B smp_wmb(); // C
- * wq_entry->flags |= WQ_FLAG_WOKEN;
- * }
- * remove_wait_queue(&wq_head, &wait);
+ * // in wait_woken() // in woken_wake_function()
*
+ * p->state = mode; wq_entry->flags |= WQ_FLAG_WOKEN;
+ * smp_mb(); // A try_to_wake_up():
+ * if (!(wq_entry->flags & WQ_FLAG_WOKEN)) <full barrier>
+ * schedule() if (p->state & mode)
+ * p->state = TASK_RUNNING; p->state = TASK_RUNNING;
+ * wq_entry->flags &= ~WQ_FLAG_WOKEN; ~~~~~~~~~~~~~~~~~~
+ * smp_mb(); // B condition = true;
+ * } smp_mb(); // C
+ * remove_wait_queue(&wq_head, &wait); wq_entry->flags |= WQ_FLAG_WOKEN;
*/
long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout)
{
- set_current_state(mode); /* A */
/*
- * The above implies an smp_mb(), which matches with the smp_wmb() from
- * woken_wake_function() such that if we observe WQ_FLAG_WOKEN we must
- * also observe all state before the wakeup.
+ * The below executes an smp_mb(), which matches with the full barrier
+ * executed by the try_to_wake_up() in woken_wake_function() such that
+ * either we see the store to wq_entry->flags in woken_wake_function()
+ * or woken_wake_function() sees our store to current->state.
*/
+ set_current_state(mode); /* A */
if (!(wq_entry->flags & WQ_FLAG_WOKEN) && !is_kthread_should_stop())
timeout = schedule_timeout(timeout);
__set_current_state(TASK_RUNNING);
/*
- * The below implies an smp_mb(), it too pairs with the smp_wmb() from
- * woken_wake_function() such that we must either observe the wait
- * condition being true _OR_ WQ_FLAG_WOKEN such that we will not miss
- * an event.
+ * The below executes an smp_mb(), which matches with the smp_mb() (C)
+ * in woken_wake_function() such that either we see the wait condition
+ * being true or the store to wq_entry->flags in woken_wake_function()
+ * follows ours in the coherence order.
*/
smp_store_mb(wq_entry->flags, wq_entry->flags & ~WQ_FLAG_WOKEN); /* B */
@@ -430,14 +433,8 @@ EXPORT_SYMBOL(wait_woken);
int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key)
{
- /*
- * Although this function is called under waitqueue lock, LOCK
- * doesn't imply write barrier and the users expects write
- * barrier semantics on wakeup functions. The following
- * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up()
- * and is paired with smp_store_mb() in wait_woken().
- */
- smp_wmb(); /* C */
+ /* Pairs with the smp_store_mb() in wait_woken(). */
+ smp_mb(); /* C */
wq_entry->flags |= WQ_FLAG_WOKEN;
return default_wake_function(wq_entry, mode, sync, key);
diff --git a/kernel/signal.c b/kernel/signal.c
index 8d8a940422a8..5843c541fda9 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -65,14 +65,14 @@ static void __user *sig_handler(struct task_struct *t, int sig)
return t->sighand->action[sig - 1].sa.sa_handler;
}
-static int sig_handler_ignored(void __user *handler, int sig)
+static inline bool sig_handler_ignored(void __user *handler, int sig)
{
/* Is it explicitly or implicitly ignored? */
return handler == SIG_IGN ||
- (handler == SIG_DFL && sig_kernel_ignore(sig));
+ (handler == SIG_DFL && sig_kernel_ignore(sig));
}
-static int sig_task_ignored(struct task_struct *t, int sig, bool force)
+static bool sig_task_ignored(struct task_struct *t, int sig, bool force)
{
void __user *handler;
@@ -80,12 +80,12 @@ static int sig_task_ignored(struct task_struct *t, int sig, bool force)
if (unlikely(t->signal->flags & SIGNAL_UNKILLABLE) &&
handler == SIG_DFL && !(force && sig_kernel_only(sig)))
- return 1;
+ return true;
return sig_handler_ignored(handler, sig);
}
-static int sig_ignored(struct task_struct *t, int sig, bool force)
+static bool sig_ignored(struct task_struct *t, int sig, bool force)
{
/*
* Blocked signals are never ignored, since the
@@ -93,7 +93,7 @@ static int sig_ignored(struct task_struct *t, int sig, bool force)
* unblocked.
*/
if (sigismember(&t->blocked, sig) || sigismember(&t->real_blocked, sig))
- return 0;
+ return false;
/*
* Tracers may want to know about even ignored signal unless it
@@ -101,7 +101,7 @@ static int sig_ignored(struct task_struct *t, int sig, bool force)
* by SIGNAL_UNKILLABLE task.
*/
if (t->ptrace && sig != SIGKILL)
- return 0;
+ return false;
return sig_task_ignored(t, sig, force);
}
@@ -110,7 +110,7 @@ static int sig_ignored(struct task_struct *t, int sig, bool force)
* Re-calculate pending state from the set of locally pending
* signals, globally pending signals, and blocked signals.
*/
-static inline int has_pending_signals(sigset_t *signal, sigset_t *blocked)
+static inline bool has_pending_signals(sigset_t *signal, sigset_t *blocked)
{
unsigned long ready;
long i;
@@ -138,20 +138,21 @@ static inline int has_pending_signals(sigset_t *signal, sigset_t *blocked)
#define PENDING(p,b) has_pending_signals(&(p)->signal, (b))
-static int recalc_sigpending_tsk(struct task_struct *t)
+static bool recalc_sigpending_tsk(struct task_struct *t)
{
if ((t->jobctl & JOBCTL_PENDING_MASK) ||
PENDING(&t->pending, &t->blocked) ||
PENDING(&t->signal->shared_pending, &t->blocked)) {
set_tsk_thread_flag(t, TIF_SIGPENDING);
- return 1;
+ return true;
}
+
/*
* We must never clear the flag in another thread, or in current
* when it's possible the current syscall is returning -ERESTART*.
* So we don't clear it here, and only callers who know they should do.
*/
- return 0;
+ return false;
}
/*
@@ -172,6 +173,17 @@ void recalc_sigpending(void)
}
+void calculate_sigpending(void)
+{
+ /* Have any signals or users of TIF_SIGPENDING been delayed
+ * until after fork?
+ */
+ spin_lock_irq(&current->sighand->siglock);
+ set_tsk_thread_flag(current, TIF_SIGPENDING);
+ recalc_sigpending();
+ spin_unlock_irq(&current->sighand->siglock);
+}
+
/* Given the mask, find the first available signal that should be serviced. */
#define SYNCHRONOUS_MASK \
@@ -362,6 +374,20 @@ static bool task_participate_group_stop(struct task_struct *task)
return false;
}
+void task_join_group_stop(struct task_struct *task)
+{
+ /* Have the new thread join an on-going signal group stop */
+ unsigned long jobctl = current->jobctl;
+ if (jobctl & JOBCTL_STOP_PENDING) {
+ struct signal_struct *sig = current->signal;
+ unsigned long signr = jobctl & JOBCTL_STOP_SIGMASK;
+ unsigned long gstop = JOBCTL_STOP_PENDING | JOBCTL_STOP_CONSUME;
+ if (task_set_jobctl_pending(task, signr | gstop)) {
+ sig->group_stop_count++;
+ }
+ }
+}
+
/*
* allocate a new signal queue record
* - this may be called without locks if and only if t == current, otherwise an
@@ -504,13 +530,15 @@ flush_signal_handlers(struct task_struct *t, int force_default)
}
}
-int unhandled_signal(struct task_struct *tsk, int sig)
+bool unhandled_signal(struct task_struct *tsk, int sig)
{
void __user *handler = tsk->sighand->action[sig-1].sa.sa_handler;
if (is_global_init(tsk))
- return 1;
+ return true;
+
if (handler != SIG_IGN && handler != SIG_DFL)
- return 0;
+ return false;
+
/* if ptraced, let the tracer determine */
return !tsk->ptrace;
}
@@ -684,14 +712,14 @@ void signal_wake_up_state(struct task_struct *t, unsigned int state)
*
* All callers must be holding the siglock.
*/
-static int flush_sigqueue_mask(sigset_t *mask, struct sigpending *s)
+static void flush_sigqueue_mask(sigset_t *mask, struct sigpending *s)
{
struct sigqueue *q, *n;
sigset_t m;
sigandsets(&m, mask, &s->signal);
if (sigisemptyset(&m))
- return 0;
+ return;
sigandnsets(&s->signal, &s->signal, mask);
list_for_each_entry_safe(q, n, &s->list, list) {
@@ -700,7 +728,6 @@ static int flush_sigqueue_mask(sigset_t *mask, struct sigpending *s)
__sigqueue_free(q);
}
}
- return 1;
}
static inline int is_si_special(const struct siginfo *info)
@@ -717,21 +744,16 @@ static inline bool si_fromuser(const struct siginfo *info)
/*
* called with RCU read lock from check_kill_permission()
*/
-static int kill_ok_by_cred(struct task_struct *t)
+static bool kill_ok_by_cred(struct task_struct *t)
{
const struct cred *cred = current_cred();
const struct cred *tcred = __task_cred(t);
- if (uid_eq(cred->euid, tcred->suid) ||
- uid_eq(cred->euid, tcred->uid) ||
- uid_eq(cred->uid, tcred->suid) ||
- uid_eq(cred->uid, tcred->uid))
- return 1;
-
- if (ns_capable(tcred->user_ns, CAP_KILL))
- return 1;
-
- return 0;
+ return uid_eq(cred->euid, tcred->suid) ||
+ uid_eq(cred->euid, tcred->uid) ||
+ uid_eq(cred->uid, tcred->suid) ||
+ uid_eq(cred->uid, tcred->uid) ||
+ ns_capable(tcred->user_ns, CAP_KILL);
}
/*
@@ -882,20 +904,24 @@ static bool prepare_signal(int sig, struct task_struct *p, bool force)
* as soon as they're available, so putting the signal on the shared queue
* will be equivalent to sending it to one such thread.
*/
-static inline int wants_signal(int sig, struct task_struct *p)
+static inline bool wants_signal(int sig, struct task_struct *p)
{
if (sigismember(&p->blocked, sig))
- return 0;
+ return false;
+
if (p->flags & PF_EXITING)
- return 0;
+ return false;
+
if (sig == SIGKILL)
- return 1;
+ return true;
+
if (task_is_stopped_or_traced(p))
- return 0;
+ return false;
+
return task_curr(p) || !signal_pending(p);
}
-static void complete_signal(int sig, struct task_struct *p, int group)
+static void complete_signal(int sig, struct task_struct *p, enum pid_type type)
{
struct signal_struct *signal = p->signal;
struct task_struct *t;
@@ -908,7 +934,7 @@ static void complete_signal(int sig, struct task_struct *p, int group)
*/
if (wants_signal(sig, p))
t = p;
- else if (!group || thread_group_empty(p))
+ else if ((type == PIDTYPE_PID) || thread_group_empty(p))
/*
* There is just one thread and it does not need to be woken.
* It will dequeue unblocked signals before it runs again.
@@ -971,7 +997,7 @@ static void complete_signal(int sig, struct task_struct *p, int group)
return;
}
-static inline int legacy_queue(struct sigpending *signals, int sig)
+static inline bool legacy_queue(struct sigpending *signals, int sig)
{
return (sig < SIGRTMIN) && sigismember(&signals->signal, sig);
}
@@ -998,7 +1024,7 @@ static inline void userns_fixup_signal_uid(struct siginfo *info, struct task_str
#endif
static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
- int group, int from_ancestor_ns)
+ enum pid_type type, int from_ancestor_ns)
{
struct sigpending *pending;
struct sigqueue *q;
@@ -1012,7 +1038,7 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
from_ancestor_ns || (info == SEND_SIG_FORCED)))
goto ret;
- pending = group ? &t->signal->shared_pending : &t->pending;
+ pending = (type != PIDTYPE_PID) ? &t->signal->shared_pending : &t->pending;
/*
* Short-circuit ignored signals and support queuing
* exactly one non-rt signal, so that we can get more
@@ -1096,14 +1122,29 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
out_set:
signalfd_notify(t, sig);
sigaddset(&pending->signal, sig);
- complete_signal(sig, t, group);
+
+ /* Let multiprocess signals appear after on-going forks */
+ if (type > PIDTYPE_TGID) {
+ struct multiprocess_signals *delayed;
+ hlist_for_each_entry(delayed, &t->signal->multiprocess, node) {
+ sigset_t *signal = &delayed->signal;
+ /* Can't queue both a stop and a continue signal */
+ if (sig == SIGCONT)
+ sigdelsetmask(signal, SIG_KERNEL_STOP_MASK);
+ else if (sig_kernel_stop(sig))
+ sigdelset(signal, SIGCONT);
+ sigaddset(signal, sig);
+ }
+ }
+
+ complete_signal(sig, t, type);
ret:
- trace_signal_generate(sig, info, t, group, result);
+ trace_signal_generate(sig, info, t, type != PIDTYPE_PID, result);
return ret;
}
static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
- int group)
+ enum pid_type type)
{
int from_ancestor_ns = 0;
@@ -1112,7 +1153,7 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
!task_pid_nr_ns(current, task_active_pid_ns(t));
#endif
- return __send_signal(sig, info, t, group, from_ancestor_ns);
+ return __send_signal(sig, info, t, type, from_ancestor_ns);
}
static void print_fatal_signal(int signr)
@@ -1151,23 +1192,23 @@ __setup("print-fatal-signals=", setup_print_fatal_signals);
int
__group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
{
- return send_signal(sig, info, p, 1);
+ return send_signal(sig, info, p, PIDTYPE_TGID);
}
static int
specific_send_sig_info(int sig, struct siginfo *info, struct task_struct *t)
{
- return send_signal(sig, info, t, 0);
+ return send_signal(sig, info, t, PIDTYPE_PID);
}
int do_send_sig_info(int sig, struct siginfo *info, struct task_struct *p,
- bool group)
+ enum pid_type type)
{
unsigned long flags;
int ret = -ESRCH;
if (lock_task_sighand(p, &flags)) {
- ret = send_signal(sig, info, p, group);
+ ret = send_signal(sig, info, p, type);
unlock_task_sighand(p, &flags);
}
@@ -1274,7 +1315,8 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
/*
* send signal info to all the members of a group
*/
-int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
+int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p,
+ enum pid_type type)
{
int ret;
@@ -1283,7 +1325,7 @@ int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
rcu_read_unlock();
if (!ret && sig)
- ret = do_send_sig_info(sig, info, p, true);
+ ret = do_send_sig_info(sig, info, p, type);
return ret;
}
@@ -1301,7 +1343,7 @@ int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp)
success = 0;
retval = -ESRCH;
do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
- int err = group_send_sig_info(sig, info, p);
+ int err = group_send_sig_info(sig, info, p, PIDTYPE_PGID);
success |= !err;
retval = err;
} while_each_pid_task(pgrp, PIDTYPE_PGID, p);
@@ -1317,7 +1359,7 @@ int kill_pid_info(int sig, struct siginfo *info, struct pid *pid)
rcu_read_lock();
p = pid_task(pid, PIDTYPE_PID);
if (p)
- error = group_send_sig_info(sig, info, p);
+ error = group_send_sig_info(sig, info, p, PIDTYPE_TGID);
rcu_read_unlock();
if (likely(!p || error != -ESRCH))
return error;
@@ -1339,14 +1381,15 @@ static int kill_proc_info(int sig, struct siginfo *info, pid_t pid)
return error;
}
-static int kill_as_cred_perm(const struct cred *cred,
- struct task_struct *target)
+static inline bool kill_as_cred_perm(const struct cred *cred,
+ struct task_struct *target)
{
const struct cred *pcred = __task_cred(target);
- if (!uid_eq(cred->euid, pcred->suid) && !uid_eq(cred->euid, pcred->uid) &&
- !uid_eq(cred->uid, pcred->suid) && !uid_eq(cred->uid, pcred->uid))
- return 0;
- return 1;
+
+ return uid_eq(cred->euid, pcred->suid) ||
+ uid_eq(cred->euid, pcred->uid) ||
+ uid_eq(cred->uid, pcred->suid) ||
+ uid_eq(cred->uid, pcred->uid);
}
/* like kill_pid_info(), but doesn't use uid/euid of "current" */
@@ -1376,7 +1419,7 @@ int kill_pid_info_as_cred(int sig, struct siginfo *info, struct pid *pid,
if (sig) {
if (lock_task_sighand(p, &flags)) {
- ret = __send_signal(sig, info, p, 1, 0);
+ ret = __send_signal(sig, info, p, PIDTYPE_TGID, 0);
unlock_task_sighand(p, &flags);
} else
ret = -ESRCH;
@@ -1420,7 +1463,8 @@ static int kill_something_info(int sig, struct siginfo *info, pid_t pid)
for_each_process(p) {
if (task_pid_vnr(p) > 1 &&
!same_thread_group(p, current)) {
- int err = group_send_sig_info(sig, info, p);
+ int err = group_send_sig_info(sig, info, p,
+ PIDTYPE_MAX);
++count;
if (err != -EPERM)
retval = err;
@@ -1446,7 +1490,7 @@ int send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
if (!valid_signal(sig))
return -EINVAL;
- return do_send_sig_info(sig, info, p, false);
+ return do_send_sig_info(sig, info, p, PIDTYPE_PID);
}
#define __si_special(priv) \
@@ -1458,8 +1502,7 @@ send_sig(int sig, struct task_struct *p, int priv)
return send_sig_info(sig, __si_special(priv), p);
}
-void
-force_sig(int sig, struct task_struct *p)
+void force_sig(int sig, struct task_struct *p)
{
force_sig_info(sig, SEND_SIG_PRIV, p);
}
@@ -1470,8 +1513,7 @@ force_sig(int sig, struct task_struct *p)
* the problem was already a SIGSEGV, we'll want to
* make sure we don't even try to deliver the signal..
*/
-int
-force_sigsegv(int sig, struct task_struct *p)
+void force_sigsegv(int sig, struct task_struct *p)
{
if (sig == SIGSEGV) {
unsigned long flags;
@@ -1480,7 +1522,6 @@ force_sigsegv(int sig, struct task_struct *p)
spin_unlock_irqrestore(&p->sighand->siglock, flags);
}
force_sig(SIGSEGV, p);
- return 0;
}
int force_sig_fault(int sig, int code, void __user *addr
@@ -1664,17 +1705,20 @@ void sigqueue_free(struct sigqueue *q)
__sigqueue_free(q);
}
-int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group)
+int send_sigqueue(struct sigqueue *q, struct pid *pid, enum pid_type type)
{
int sig = q->info.si_signo;
struct sigpending *pending;
+ struct task_struct *t;
unsigned long flags;
int ret, result;
BUG_ON(!(q->flags & SIGQUEUE_PREALLOC));
ret = -1;
- if (!likely(lock_task_sighand(t, &flags)))
+ rcu_read_lock();
+ t = pid_task(pid, type);
+ if (!t || !likely(lock_task_sighand(t, &flags)))
goto ret;
ret = 1; /* the signal is ignored */
@@ -1696,15 +1740,16 @@ int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group)
q->info.si_overrun = 0;
signalfd_notify(t, sig);
- pending = group ? &t->signal->shared_pending : &t->pending;
+ pending = (type != PIDTYPE_PID) ? &t->signal->shared_pending : &t->pending;
list_add_tail(&q->list, &pending->list);
sigaddset(&pending->signal, sig);
- complete_signal(sig, t, group);
+ complete_signal(sig, t, type);
result = TRACE_SIGNAL_DELIVERED;
out:
- trace_signal_generate(sig, &q->info, t, group, result);
+ trace_signal_generate(sig, &q->info, t, type != PIDTYPE_PID, result);
unlock_task_sighand(t, &flags);
ret:
+ rcu_read_unlock();
return ret;
}
@@ -1877,10 +1922,10 @@ static void do_notify_parent_cldstop(struct task_struct *tsk,
spin_unlock_irqrestore(&sighand->siglock, flags);
}
-static inline int may_ptrace_stop(void)
+static inline bool may_ptrace_stop(void)
{
if (!likely(current->ptrace))
- return 0;
+ return false;
/*
* Are we in the middle of do_coredump?
* If so and our tracer is also part of the coredump stopping
@@ -1896,19 +1941,19 @@ static inline int may_ptrace_stop(void)
*/
if (unlikely(current->mm->core_state) &&
unlikely(current->mm == current->parent->mm))
- return 0;
+ return false;
- return 1;
+ return true;
}
/*
* Return non-zero if there is a SIGKILL that should be waking us up.
* Called with the siglock held.
*/
-static int sigkill_pending(struct task_struct *tsk)
+static bool sigkill_pending(struct task_struct *tsk)
{
- return sigismember(&tsk->pending.signal, SIGKILL) ||
- sigismember(&tsk->signal->shared_pending.signal, SIGKILL);
+ return sigismember(&tsk->pending.signal, SIGKILL) ||
+ sigismember(&tsk->signal->shared_pending.signal, SIGKILL);
}
/*
@@ -2288,7 +2333,7 @@ static int ptrace_signal(int signr, siginfo_t *info)
return signr;
}
-int get_signal(struct ksignal *ksig)
+bool get_signal(struct ksignal *ksig)
{
struct sighand_struct *sighand = current->sighand;
struct signal_struct *signal = current->signal;
@@ -2298,7 +2343,7 @@ int get_signal(struct ksignal *ksig)
task_work_run();
if (unlikely(uprobe_deny_signal()))
- return 0;
+ return false;
/*
* Do this once, we can't return to user-mode if freezing() == T.
@@ -2755,7 +2800,7 @@ COMPAT_SYSCALL_DEFINE4(rt_sigprocmask, int, how, compat_sigset_t __user *, nset,
}
#endif
-static int do_sigpending(sigset_t *set)
+static void do_sigpending(sigset_t *set)
{
spin_lock_irq(&current->sighand->siglock);
sigorsets(set, &current->pending.signal,
@@ -2764,7 +2809,6 @@ static int do_sigpending(sigset_t *set)
/* Outside the lock because only this thread touches it. */
sigandsets(set, &current->blocked, set);
- return 0;
}
/**
@@ -2776,15 +2820,16 @@ static int do_sigpending(sigset_t *set)
SYSCALL_DEFINE2(rt_sigpending, sigset_t __user *, uset, size_t, sigsetsize)
{
sigset_t set;
- int err;
if (sigsetsize > sizeof(*uset))
return -EINVAL;
- err = do_sigpending(&set);
- if (!err && copy_to_user(uset, &set, sigsetsize))
- err = -EFAULT;
- return err;
+ do_sigpending(&set);
+
+ if (copy_to_user(uset, &set, sigsetsize))
+ return -EFAULT;
+
+ return 0;
}
#ifdef CONFIG_COMPAT
@@ -2792,15 +2837,13 @@ COMPAT_SYSCALL_DEFINE2(rt_sigpending, compat_sigset_t __user *, uset,
compat_size_t, sigsetsize)
{
sigset_t set;
- int err;
if (sigsetsize > sizeof(*uset))
return -EINVAL;
- err = do_sigpending(&set);
- if (!err)
- err = put_compat_sigset(uset, &set, sigsetsize);
- return err;
+ do_sigpending(&set);
+
+ return put_compat_sigset(uset, &set, sigsetsize);
}
#endif
@@ -3193,7 +3236,7 @@ do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info)
* probe. No signal is actually delivered.
*/
if (!error && sig) {
- error = do_send_sig_info(sig, info, p, false);
+ error = do_send_sig_info(sig, info, p, PIDTYPE_PID);
/*
* If lock_task_sighand() failed we pretend the task
* dies after receiving the signal. The window is tiny,
@@ -3562,25 +3605,26 @@ int __compat_save_altstack(compat_stack_t __user *uss, unsigned long sp)
SYSCALL_DEFINE1(sigpending, old_sigset_t __user *, uset)
{
sigset_t set;
- int err;
if (sizeof(old_sigset_t) > sizeof(*uset))
return -EINVAL;
- err = do_sigpending(&set);
- if (!err && copy_to_user(uset, &set, sizeof(old_sigset_t)))
- err = -EFAULT;
- return err;
+ do_sigpending(&set);
+
+ if (copy_to_user(uset, &set, sizeof(old_sigset_t)))
+ return -EFAULT;
+
+ return 0;
}
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE1(sigpending, compat_old_sigset_t __user *, set32)
{
sigset_t set;
- int err = do_sigpending(&set);
- if (!err)
- err = put_user(set.sig[0], set32);
- return err;
+
+ do_sigpending(&set);
+
+ return put_user(set.sig[0], set32);
}
#endif
@@ -3651,25 +3695,23 @@ SYSCALL_DEFINE4(rt_sigaction, int, sig,
size_t, sigsetsize)
{
struct k_sigaction new_sa, old_sa;
- int ret = -EINVAL;
+ int ret;
/* XXX: Don't preclude handling different sized sigset_t's. */
if (sigsetsize != sizeof(sigset_t))
- goto out;
+ return -EINVAL;
- if (act) {
- if (copy_from_user(&new_sa.sa, act, sizeof(new_sa.sa)))
- return -EFAULT;
- }
+ if (act && copy_from_user(&new_sa.sa, act, sizeof(new_sa.sa)))
+ return -EFAULT;
ret = do_sigaction(sig, act ? &new_sa : NULL, oact ? &old_sa : NULL);
+ if (ret)
+ return ret;
- if (!ret && oact) {
- if (copy_to_user(oact, &old_sa.sa, sizeof(old_sa.sa)))
- return -EFAULT;
- }
-out:
- return ret;
+ if (oact && copy_to_user(oact, &old_sa.sa, sizeof(old_sa.sa)))
+ return -EFAULT;
+
+ return 0;
}
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE4(rt_sigaction, int, sig,
@@ -3960,7 +4002,7 @@ void kdb_send_sig(struct task_struct *t, int sig)
"the deadlock.\n");
return;
}
- ret = send_signal(sig, SEND_SIG_PRIV, t, false);
+ ret = send_signal(sig, SEND_SIG_PRIV, t, PIDTYPE_PID);
spin_unlock(&t->sighand->siglock);
if (ret)
kdb_printf("Fail to deliver Signal %d to process %d.\n",
diff --git a/kernel/smp.c b/kernel/smp.c
index 084c8b3a2681..d86eec5f51c1 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -584,6 +584,8 @@ void __init smp_init(void)
num_nodes, (num_nodes > 1 ? "s" : ""),
num_cpus, (num_cpus > 1 ? "s" : ""));
+ /* Final decision about SMT support */
+ cpu_smt_check_topology();
/* Any cleanup work */
smp_cpus_done(setup_max_cpus);
}
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index 5043e7433f4b..c230c2dd48e1 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -238,8 +238,7 @@ int smpboot_unpark_threads(unsigned int cpu)
mutex_lock(&smpboot_threads_lock);
list_for_each_entry(cur, &hotplug_threads, list)
- if (cpumask_test_cpu(cpu, cur->cpumask))
- smpboot_unpark_thread(cur, cpu);
+ smpboot_unpark_thread(cur, cpu);
mutex_unlock(&smpboot_threads_lock);
return 0;
}
@@ -280,34 +279,26 @@ static void smpboot_destroy_threads(struct smp_hotplug_thread *ht)
}
/**
- * smpboot_register_percpu_thread_cpumask - Register a per_cpu thread related
+ * smpboot_register_percpu_thread - Register a per_cpu thread related
* to hotplug
* @plug_thread: Hotplug thread descriptor
- * @cpumask: The cpumask where threads run
*
* Creates and starts the threads on all online cpus.
*/
-int smpboot_register_percpu_thread_cpumask(struct smp_hotplug_thread *plug_thread,
- const struct cpumask *cpumask)
+int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread)
{
unsigned int cpu;
int ret = 0;
- if (!alloc_cpumask_var(&plug_thread->cpumask, GFP_KERNEL))
- return -ENOMEM;
- cpumask_copy(plug_thread->cpumask, cpumask);
-
get_online_cpus();
mutex_lock(&smpboot_threads_lock);
for_each_online_cpu(cpu) {
ret = __smpboot_create_thread(plug_thread, cpu);
if (ret) {
smpboot_destroy_threads(plug_thread);
- free_cpumask_var(plug_thread->cpumask);
goto out;
}
- if (cpumask_test_cpu(cpu, cpumask))
- smpboot_unpark_thread(plug_thread, cpu);
+ smpboot_unpark_thread(plug_thread, cpu);
}
list_add(&plug_thread->list, &hotplug_threads);
out:
@@ -315,7 +306,7 @@ out:
put_online_cpus();
return ret;
}
-EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread_cpumask);
+EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread);
/**
* smpboot_unregister_percpu_thread - Unregister a per_cpu thread related to hotplug
@@ -331,44 +322,9 @@ void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread)
smpboot_destroy_threads(plug_thread);
mutex_unlock(&smpboot_threads_lock);
put_online_cpus();
- free_cpumask_var(plug_thread->cpumask);
}
EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread);
-/**
- * smpboot_update_cpumask_percpu_thread - Adjust which per_cpu hotplug threads stay parked
- * @plug_thread: Hotplug thread descriptor
- * @new: Revised mask to use
- *
- * The cpumask field in the smp_hotplug_thread must not be updated directly
- * by the client, but only by calling this function.
- * This function can only be called on a registered smp_hotplug_thread.
- */
-void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread,
- const struct cpumask *new)
-{
- struct cpumask *old = plug_thread->cpumask;
- static struct cpumask tmp;
- unsigned int cpu;
-
- lockdep_assert_cpus_held();
- mutex_lock(&smpboot_threads_lock);
-
- /* Park threads that were exclusively enabled on the old mask. */
- cpumask_andnot(&tmp, old, new);
- for_each_cpu_and(cpu, &tmp, cpu_online_mask)
- smpboot_park_thread(plug_thread, cpu);
-
- /* Unpark threads that are exclusively enabled on the new mask. */
- cpumask_andnot(&tmp, new, old);
- for_each_cpu_and(cpu, &tmp, cpu_online_mask)
- smpboot_unpark_thread(plug_thread, cpu);
-
- cpumask_copy(old, new);
-
- mutex_unlock(&smpboot_threads_lock);
-}
-
static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD);
/*
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 75ffc1d1a2e0..6f584861d329 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -390,7 +390,7 @@ static inline void tick_irq_exit(void)
/* Make sure that timer wheel updates are propagated */
if ((idle_cpu(cpu) && !need_resched()) || tick_nohz_full_cpu(cpu)) {
- if (!in_interrupt())
+ if (!in_irq())
tick_nohz_irq_exit();
}
#endif
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 1ff523dae6e2..067cb83f37ea 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -81,6 +81,7 @@ static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
unsigned long flags;
bool enabled;
+ preempt_disable();
raw_spin_lock_irqsave(&stopper->lock, flags);
enabled = stopper->enabled;
if (enabled)
@@ -90,6 +91,7 @@ static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
raw_spin_unlock_irqrestore(&stopper->lock, flags);
wake_up_q(&wakeq);
+ preempt_enable();
return enabled;
}
@@ -236,13 +238,24 @@ static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1,
struct cpu_stopper *stopper2 = per_cpu_ptr(&cpu_stopper, cpu2);
DEFINE_WAKE_Q(wakeq);
int err;
+
retry:
+ /*
+ * The waking up of stopper threads has to happen in the same
+ * scheduling context as the queueing. Otherwise, there is a
+ * possibility of one of the above stoppers being woken up by another
+ * CPU, and preempting us. This will cause us to not wake up the other
+ * stopper forever.
+ */
+ preempt_disable();
raw_spin_lock_irq(&stopper1->lock);
raw_spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING);
- err = -ENOENT;
- if (!stopper1->enabled || !stopper2->enabled)
+ if (!stopper1->enabled || !stopper2->enabled) {
+ err = -ENOENT;
goto unlock;
+ }
+
/*
* Ensure that if we race with __stop_cpus() the stoppers won't get
* queued up in reverse order leading to system deadlock.
@@ -253,28 +266,30 @@ retry:
* It can be falsely true but it is safe to spin until it is cleared,
* queue_stop_cpus_work() does everything under preempt_disable().
*/
- err = -EDEADLK;
- if (unlikely(stop_cpus_in_progress))
- goto unlock;
+ if (unlikely(stop_cpus_in_progress)) {
+ err = -EDEADLK;
+ goto unlock;
+ }
err = 0;
__cpu_stop_queue_work(stopper1, work1, &wakeq);
__cpu_stop_queue_work(stopper2, work2, &wakeq);
+
unlock:
raw_spin_unlock(&stopper2->lock);
raw_spin_unlock_irq(&stopper1->lock);
if (unlikely(err == -EDEADLK)) {
+ preempt_enable();
+
while (stop_cpus_in_progress)
cpu_relax();
+
goto retry;
}
- if (!err) {
- preempt_disable();
- wake_up_q(&wakeq);
- preempt_enable();
- }
+ wake_up_q(&wakeq);
+ preempt_enable();
return err;
}
diff --git a/kernel/sys.c b/kernel/sys.c
index 38509dc1f77b..e27b51d3facd 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2512,11 +2512,11 @@ static int do_sysinfo(struct sysinfo *info)
{
unsigned long mem_total, sav_total;
unsigned int mem_unit, bitcount;
- struct timespec tp;
+ struct timespec64 tp;
memset(info, 0, sizeof(struct sysinfo));
- get_monotonic_boottime(&tp);
+ ktime_get_boottime_ts64(&tp);
info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0);
get_avenrun(info->loads, 0, SI_LOAD_SHIFT - FSHIFT);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 2d9837c0aff4..71ceb6c13c1a 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -145,7 +145,10 @@ static int minolduid;
static int ngroups_max = NGROUPS_MAX;
static const int cap_last_cap = CAP_LAST_CAP;
-/*this is needed for proc_doulongvec_minmax of sysctl_hung_task_timeout_secs */
+/*
+ * This is needed for proc_doulongvec_minmax of sysctl_hung_task_timeout_secs
+ * and hung_task_check_interval_secs
+ */
#ifdef CONFIG_DETECT_HUNG_TASK
static unsigned long hung_task_timeout_max = (LONG_MAX/HZ);
#endif
@@ -222,7 +225,7 @@ static int proc_dopipe_max_size(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
#ifdef CONFIG_MAGIC_SYSRQ
-/* Note: sysrq code uses it's own private copy */
+/* Note: sysrq code uses its own private copy */
static int __sysrq_enabled = CONFIG_MAGIC_SYSRQ_DEFAULT_ENABLE;
static int sysrq_sysctl_handler(struct ctl_table *table, int write,
@@ -368,14 +371,6 @@ static struct ctl_table kern_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec,
},
- {
- .procname = "sched_time_avg_ms",
- .data = &sysctl_sched_time_avg,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = &one,
- },
#ifdef CONFIG_SCHEDSTATS
{
.procname = "sched_schedstats",
@@ -1099,6 +1094,14 @@ static struct ctl_table kern_table[] = {
.extra2 = &hung_task_timeout_max,
},
{
+ .procname = "hung_task_check_interval_secs",
+ .data = &sysctl_hung_task_check_interval_secs,
+ .maxlen = sizeof(unsigned long),
+ .mode = 0644,
+ .proc_handler = proc_dohung_task_timeout_secs,
+ .extra2 = &hung_task_timeout_max,
+ },
+ {
.procname = "hung_task_warnings",
.data = &sysctl_hung_task_warnings,
.maxlen = sizeof(int),
@@ -1973,13 +1976,13 @@ static void warn_sysctl_write(struct ctl_table *table)
}
/**
- * proc_first_pos_non_zero_ignore - check if firs position is allowed
+ * proc_first_pos_non_zero_ignore - check if first position is allowed
* @ppos: file position
* @table: the sysctl table
*
* Returns true if the first position is non-zero and the sysctl_writes_strict
* mode indicates this is not allowed for numeric input types. String proc
- * hadlers can ignore the return value.
+ * handlers can ignore the return value.
*/
static bool proc_first_pos_non_zero_ignore(loff_t *ppos,
struct ctl_table *table)
diff --git a/kernel/test_kprobes.c b/kernel/test_kprobes.c
index dd53e354f630..7bca480151b0 100644
--- a/kernel/test_kprobes.c
+++ b/kernel/test_kprobes.c
@@ -162,90 +162,6 @@ static int test_kprobes(void)
}
-#if 0
-static u32 jph_val;
-
-static u32 j_kprobe_target(u32 value)
-{
- if (preemptible()) {
- handler_errors++;
- pr_err("jprobe-handler is preemptible\n");
- }
- if (value != rand1) {
- handler_errors++;
- pr_err("incorrect value in jprobe handler\n");
- }
-
- jph_val = rand1;
- jprobe_return();
- return 0;
-}
-
-static struct jprobe jp = {
- .entry = j_kprobe_target,
- .kp.symbol_name = "kprobe_target"
-};
-
-static int test_jprobe(void)
-{
- int ret;
-
- ret = register_jprobe(&jp);
- if (ret < 0) {
- pr_err("register_jprobe returned %d\n", ret);
- return ret;
- }
-
- ret = target(rand1);
- unregister_jprobe(&jp);
- if (jph_val == 0) {
- pr_err("jprobe handler not called\n");
- handler_errors++;
- }
-
- return 0;
-}
-
-static struct jprobe jp2 = {
- .entry = j_kprobe_target,
- .kp.symbol_name = "kprobe_target2"
-};
-
-static int test_jprobes(void)
-{
- int ret;
- struct jprobe *jps[2] = {&jp, &jp2};
-
- /* addr and flags should be cleard for reusing kprobe. */
- jp.kp.addr = NULL;
- jp.kp.flags = 0;
- ret = register_jprobes(jps, 2);
- if (ret < 0) {
- pr_err("register_jprobes returned %d\n", ret);
- return ret;
- }
-
- jph_val = 0;
- ret = target(rand1);
- if (jph_val == 0) {
- pr_err("jprobe handler not called\n");
- handler_errors++;
- }
-
- jph_val = 0;
- ret = target2(rand1);
- if (jph_val == 0) {
- pr_err("jprobe handler2 not called\n");
- handler_errors++;
- }
- unregister_jprobes(jps, 2);
-
- return 0;
-}
-#else
-#define test_jprobe() (0)
-#define test_jprobes() (0)
-#endif
#ifdef CONFIG_KRETPROBES
static u32 krph_val;
@@ -383,16 +299,6 @@ int init_test_probes(void)
if (ret < 0)
errors++;
- num_tests++;
- ret = test_jprobe();
- if (ret < 0)
- errors++;
-
- num_tests++;
- ret = test_jprobes();
- if (ret < 0)
- errors++;
-
#ifdef CONFIG_KRETPROBES
num_tests++;
ret = test_kretprobe();
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 639321bf2e39..fa5de5e8de61 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -581,11 +581,11 @@ static void alarm_timer_rearm(struct k_itimer *timr)
* @timr: Pointer to the posixtimer data struct
* @now: Current time to forward the timer against
*/
-static int alarm_timer_forward(struct k_itimer *timr, ktime_t now)
+static s64 alarm_timer_forward(struct k_itimer *timr, ktime_t now)
{
struct alarm *alarm = &timr->it.alarm.alarmtimer;
- return (int) alarm_forward(alarm, timr->it_interval, now);
+ return alarm_forward(alarm, timr->it_interval, now);
}
/**
@@ -808,7 +808,8 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags,
/* Convert (if necessary) to absolute time */
if (flags != TIMER_ABSTIME) {
ktime_t now = alarm_bases[type].gettime();
- exp = ktime_add(now, exp);
+
+ exp = ktime_add_safe(now, exp);
}
ret = alarmtimer_do_nsleep(&alarm, exp, type);
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 16c027e9cc73..8c0e4092f661 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -463,6 +463,12 @@ void clockevents_register_device(struct clock_event_device *dev)
dev->cpumask = cpumask_of(smp_processor_id());
}
+ if (dev->cpumask == cpu_all_mask) {
+ WARN(1, "%s cpumask == cpu_all_mask, using cpu_possible_mask instead\n",
+ dev->name);
+ dev->cpumask = cpu_possible_mask;
+ }
+
raw_spin_lock_irqsave(&clockevents_lock, flags);
list_add(&dev->list, &clockevent_devices);
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index f89a78e2792b..f74fb00d8064 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -94,6 +94,8 @@ EXPORT_SYMBOL_GPL(clocks_calc_mult_shift);
/*[Clocksource internal variables]---------
* curr_clocksource:
* currently selected clocksource.
+ * suspend_clocksource:
+ * used to calculate the suspend time.
* clocksource_list:
* linked list with the registered clocksources
* clocksource_mutex:
@@ -102,10 +104,12 @@ EXPORT_SYMBOL_GPL(clocks_calc_mult_shift);
* Name of the user-specified clocksource.
*/
static struct clocksource *curr_clocksource;
+static struct clocksource *suspend_clocksource;
static LIST_HEAD(clocksource_list);
static DEFINE_MUTEX(clocksource_mutex);
static char override_name[CS_NAME_LEN];
static int finished_booting;
+static u64 suspend_start;
#ifdef CONFIG_CLOCKSOURCE_WATCHDOG
static void clocksource_watchdog_work(struct work_struct *work);
@@ -447,6 +451,140 @@ static inline void clocksource_watchdog_unlock(unsigned long *flags) { }
#endif /* CONFIG_CLOCKSOURCE_WATCHDOG */
+static bool clocksource_is_suspend(struct clocksource *cs)
+{
+ return cs == suspend_clocksource;
+}
+
+static void __clocksource_suspend_select(struct clocksource *cs)
+{
+ /*
+ * Skip the clocksource which will be stopped in suspend state.
+ */
+ if (!(cs->flags & CLOCK_SOURCE_SUSPEND_NONSTOP))
+ return;
+
+ /*
+ * The nonstop clocksource can be selected as the suspend clocksource to
+ * calculate the suspend time, so it should not supply suspend/resume
+ * interfaces to suspend the nonstop clocksource when system suspends.
+ */
+ if (cs->suspend || cs->resume) {
+ pr_warn("Nonstop clocksource %s should not supply suspend/resume interfaces\n",
+ cs->name);
+ }
+
+ /* Pick the best rating. */
+ if (!suspend_clocksource || cs->rating > suspend_clocksource->rating)
+ suspend_clocksource = cs;
+}
+
+/**
+ * clocksource_suspend_select - Select the best clocksource for suspend timing
+ * @fallback: if select a fallback clocksource
+ */
+static void clocksource_suspend_select(bool fallback)
+{
+ struct clocksource *cs, *old_suspend;
+
+ old_suspend = suspend_clocksource;
+ if (fallback)
+ suspend_clocksource = NULL;
+
+ list_for_each_entry(cs, &clocksource_list, list) {
+ /* Skip current if we were requested for a fallback. */
+ if (fallback && cs == old_suspend)
+ continue;
+
+ __clocksource_suspend_select(cs);
+ }
+}
+
+/**
+ * clocksource_start_suspend_timing - Start measuring the suspend timing
+ * @cs: current clocksource from timekeeping
+ * @start_cycles: current cycles from timekeeping
+ *
+ * This function will save the start cycle values of suspend timer to calculate
+ * the suspend time when resuming system.
+ *
+ * This function is called late in the suspend process from timekeeping_suspend(),
+ * that means processes are freezed, non-boot cpus and interrupts are disabled
+ * now. It is therefore possible to start the suspend timer without taking the
+ * clocksource mutex.
+ */
+void clocksource_start_suspend_timing(struct clocksource *cs, u64 start_cycles)
+{
+ if (!suspend_clocksource)
+ return;
+
+ /*
+ * If current clocksource is the suspend timer, we should use the
+ * tkr_mono.cycle_last value as suspend_start to avoid same reading
+ * from suspend timer.
+ */
+ if (clocksource_is_suspend(cs)) {
+ suspend_start = start_cycles;
+ return;
+ }
+
+ if (suspend_clocksource->enable &&
+ suspend_clocksource->enable(suspend_clocksource)) {
+ pr_warn_once("Failed to enable the non-suspend-able clocksource.\n");
+ return;
+ }
+
+ suspend_start = suspend_clocksource->read(suspend_clocksource);
+}
+
+/**
+ * clocksource_stop_suspend_timing - Stop measuring the suspend timing
+ * @cs: current clocksource from timekeeping
+ * @cycle_now: current cycles from timekeeping
+ *
+ * This function will calculate the suspend time from suspend timer.
+ *
+ * Returns nanoseconds since suspend started, 0 if no usable suspend clocksource.
+ *
+ * This function is called early in the resume process from timekeeping_resume(),
+ * that means there is only one cpu, no processes are running and the interrupts
+ * are disabled. It is therefore possible to stop the suspend timer without
+ * taking the clocksource mutex.
+ */
+u64 clocksource_stop_suspend_timing(struct clocksource *cs, u64 cycle_now)
+{
+ u64 now, delta, nsec = 0;
+
+ if (!suspend_clocksource)
+ return 0;
+
+ /*
+ * If current clocksource is the suspend timer, we should use the
+ * tkr_mono.cycle_last value from timekeeping as current cycle to
+ * avoid same reading from suspend timer.
+ */
+ if (clocksource_is_suspend(cs))
+ now = cycle_now;
+ else
+ now = suspend_clocksource->read(suspend_clocksource);
+
+ if (now > suspend_start) {
+ delta = clocksource_delta(now, suspend_start,
+ suspend_clocksource->mask);
+ nsec = mul_u64_u32_shr(delta, suspend_clocksource->mult,
+ suspend_clocksource->shift);
+ }
+
+ /*
+ * Disable the suspend timer to save power if current clocksource is
+ * not the suspend timer.
+ */
+ if (!clocksource_is_suspend(cs) && suspend_clocksource->disable)
+ suspend_clocksource->disable(suspend_clocksource);
+
+ return nsec;
+}
+
/**
* clocksource_suspend - suspend the clocksource(s)
*/
@@ -792,6 +930,7 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
clocksource_select();
clocksource_select_watchdog(false);
+ __clocksource_suspend_select(cs);
mutex_unlock(&clocksource_mutex);
return 0;
}
@@ -820,6 +959,7 @@ void clocksource_change_rating(struct clocksource *cs, int rating)
clocksource_select();
clocksource_select_watchdog(false);
+ clocksource_suspend_select(false);
mutex_unlock(&clocksource_mutex);
}
EXPORT_SYMBOL(clocksource_change_rating);
@@ -845,6 +985,15 @@ static int clocksource_unbind(struct clocksource *cs)
return -EBUSY;
}
+ if (clocksource_is_suspend(cs)) {
+ /*
+ * Select and try to install a replacement suspend clocksource.
+ * If no replacement suspend clocksource, we will just let the
+ * clocksource go and have no suspend clocksource.
+ */
+ clocksource_suspend_select(true);
+ }
+
clocksource_watchdog_lock(&flags);
clocksource_dequeue_watchdog(cs);
list_del_init(&cs->list);
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 3e93c54bd3a1..e1a549c9e399 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -718,8 +718,8 @@ static void hrtimer_switch_to_hres(void)
struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases);
if (tick_init_highres()) {
- printk(KERN_WARNING "Could not switch to high resolution "
- "mode on CPU %d\n", base->cpu);
+ pr_warn("Could not switch to high resolution mode on CPU %u\n",
+ base->cpu);
return;
}
base->hres_active = 1;
@@ -1573,8 +1573,7 @@ retry:
else
expires_next = ktime_add(now, delta);
tick_program_event(expires_next, 1);
- printk_once(KERN_WARNING "hrtimer: interrupt took %llu ns\n",
- ktime_to_ns(delta));
+ pr_warn_once("hrtimer: interrupt took %llu ns\n", ktime_to_ns(delta));
}
/* called with interrupts disabled */
diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c
index f26acef5d7b4..9a65713c8309 100644
--- a/kernel/time/itimer.c
+++ b/kernel/time/itimer.c
@@ -139,9 +139,10 @@ enum hrtimer_restart it_real_fn(struct hrtimer *timer)
{
struct signal_struct *sig =
container_of(timer, struct signal_struct, real_timer);
+ struct pid *leader_pid = sig->pids[PIDTYPE_TGID];
- trace_itimer_expire(ITIMER_REAL, sig->leader_pid, 0);
- kill_pid_info(SIGALRM, SEND_SIG_PRIV, sig->leader_pid);
+ trace_itimer_expire(ITIMER_REAL, leader_pid, 0);
+ kill_pid_info(SIGALRM, SEND_SIG_PRIV, leader_pid);
return HRTIMER_NORESTART;
}
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index a09ded765f6c..c5e0cba3b39c 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -502,7 +502,7 @@ static void sched_sync_hw_clock(struct timespec64 now,
{
struct timespec64 next;
- getnstimeofday64(&next);
+ ktime_get_real_ts64(&next);
if (!fail)
next.tv_sec = 659;
else {
@@ -537,7 +537,7 @@ static void sync_rtc_clock(void)
if (!IS_ENABLED(CONFIG_RTC_SYSTOHC))
return;
- getnstimeofday64(&now);
+ ktime_get_real_ts64(&now);
adjust = now;
if (persistent_clock_is_local)
@@ -591,7 +591,7 @@ static bool sync_cmos_clock(void)
* Architectures are strongly encouraged to use rtclib and not
* implement this legacy API.
*/
- getnstimeofday64(&now);
+ ktime_get_real_ts64(&now);
if (rtc_tv_nsec_ok(-1 * target_nsec, &adjust, &now)) {
if (persistent_clock_is_local)
adjust.tv_sec -= (sys_tz.tz_minuteswest * 60);
@@ -642,7 +642,7 @@ void ntp_notify_cmos_timer(void)
/*
* Propagate a new txc->status value into the NTP state:
*/
-static inline void process_adj_status(struct timex *txc, struct timespec64 *ts)
+static inline void process_adj_status(const struct timex *txc)
{
if ((time_status & STA_PLL) && !(txc->status & STA_PLL)) {
time_state = TIME_OK;
@@ -665,12 +665,10 @@ static inline void process_adj_status(struct timex *txc, struct timespec64 *ts)
}
-static inline void process_adjtimex_modes(struct timex *txc,
- struct timespec64 *ts,
- s32 *time_tai)
+static inline void process_adjtimex_modes(const struct timex *txc, s32 *time_tai)
{
if (txc->modes & ADJ_STATUS)
- process_adj_status(txc, ts);
+ process_adj_status(txc);
if (txc->modes & ADJ_NANO)
time_status |= STA_NANO;
@@ -718,7 +716,7 @@ static inline void process_adjtimex_modes(struct timex *txc,
* adjtimex mainly allows reading (and writing, if superuser) of
* kernel time-keeping variables. used by xntpd.
*/
-int __do_adjtimex(struct timex *txc, struct timespec64 *ts, s32 *time_tai)
+int __do_adjtimex(struct timex *txc, const struct timespec64 *ts, s32 *time_tai)
{
int result;
@@ -735,7 +733,7 @@ int __do_adjtimex(struct timex *txc, struct timespec64 *ts, s32 *time_tai)
/* If there are input parameters, then process them: */
if (txc->modes)
- process_adjtimex_modes(txc, ts, time_tai);
+ process_adjtimex_modes(txc, time_tai);
txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ,
NTP_SCALE_SHIFT);
@@ -1022,12 +1020,11 @@ void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_t
static int __init ntp_tick_adj_setup(char *str)
{
- int rc = kstrtol(str, 0, (long *)&ntp_tick_adj);
-
+ int rc = kstrtos64(str, 0, &ntp_tick_adj);
if (rc)
return rc;
- ntp_tick_adj <<= NTP_SCALE_SHIFT;
+ ntp_tick_adj <<= NTP_SCALE_SHIFT;
return 1;
}
diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h
index 909bd1f1bfb1..c24b0e13f011 100644
--- a/kernel/time/ntp_internal.h
+++ b/kernel/time/ntp_internal.h
@@ -8,6 +8,6 @@ extern void ntp_clear(void);
extern u64 ntp_tick_length(void);
extern ktime_t ntp_get_next_leap(void);
extern int second_overflow(time64_t secs);
-extern int __do_adjtimex(struct timex *, struct timespec64 *, s32 *);
-extern void __hardpps(const struct timespec64 *, const struct timespec64 *);
+extern int __do_adjtimex(struct timex *txc, const struct timespec64 *ts, s32 *time_tai);
+extern void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts);
#endif /* _LINUX_NTP_INTERNAL_H */
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 9cdf54b04ca8..ce32cf741b25 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -85,7 +85,7 @@ static void bump_cpu_timer(struct k_itimer *timer, u64 now)
continue;
timer->it.cpu.expires += incr;
- timer->it_overrun += 1 << i;
+ timer->it_overrun += 1LL << i;
delta -= incr;
}
}
@@ -894,7 +894,7 @@ static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it,
trace_itimer_expire(signo == SIGPROF ?
ITIMER_PROF : ITIMER_VIRTUAL,
- tsk->signal->leader_pid, cur_time);
+ task_tgid(tsk), cur_time);
__group_send_sig_info(signo, SEND_SIG_PRIV, tsk);
}
diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c
index 26aa9569e24a..2c6847d5d69b 100644
--- a/kernel/time/posix-stubs.c
+++ b/kernel/time/posix-stubs.c
@@ -81,7 +81,7 @@ int do_clock_gettime(clockid_t which_clock, struct timespec64 *tp)
ktime_get_ts64(tp);
break;
case CLOCK_BOOTTIME:
- get_monotonic_boottime64(tp);
+ ktime_get_boottime_ts64(tp);
break;
default:
return -EINVAL;
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index e08ce3f27447..4b9127e95430 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -86,15 +86,6 @@ static const struct k_clock clock_realtime, clock_monotonic;
#endif
/*
- * parisc wants ENOTSUP instead of EOPNOTSUPP
- */
-#ifndef ENOTSUP
-# define ENANOSLEEP_NOTSUP EOPNOTSUPP
-#else
-# define ENANOSLEEP_NOTSUP ENOTSUP
-#endif
-
-/*
* The timer ID is turned into a timer address by idr_find().
* Verifying a valid ID consists of:
*
@@ -228,21 +219,21 @@ static int posix_ktime_get_ts(clockid_t which_clock, struct timespec64 *tp)
*/
static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec64 *tp)
{
- getrawmonotonic64(tp);
+ ktime_get_raw_ts64(tp);
return 0;
}
static int posix_get_realtime_coarse(clockid_t which_clock, struct timespec64 *tp)
{
- *tp = current_kernel_time64();
+ ktime_get_coarse_real_ts64(tp);
return 0;
}
static int posix_get_monotonic_coarse(clockid_t which_clock,
struct timespec64 *tp)
{
- *tp = get_monotonic_coarse64();
+ ktime_get_coarse_ts64(tp);
return 0;
}
@@ -254,13 +245,13 @@ static int posix_get_coarse_res(const clockid_t which_clock, struct timespec64 *
static int posix_get_boottime(const clockid_t which_clock, struct timespec64 *tp)
{
- get_monotonic_boottime64(tp);
+ ktime_get_boottime_ts64(tp);
return 0;
}
static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp)
{
- timekeeping_clocktai64(tp);
+ ktime_get_clocktai_ts64(tp);
return 0;
}
@@ -283,6 +274,17 @@ static __init int init_posix_timers(void)
}
__initcall(init_posix_timers);
+/*
+ * The siginfo si_overrun field and the return value of timer_getoverrun(2)
+ * are of type int. Clamp the overrun value to INT_MAX
+ */
+static inline int timer_overrun_to_int(struct k_itimer *timr, int baseval)
+{
+ s64 sum = timr->it_overrun_last + (s64)baseval;
+
+ return sum > (s64)INT_MAX ? INT_MAX : (int)sum;
+}
+
static void common_hrtimer_rearm(struct k_itimer *timr)
{
struct hrtimer *timer = &timr->it.real.timer;
@@ -290,9 +292,8 @@ static void common_hrtimer_rearm(struct k_itimer *timr)
if (!timr->it_interval)
return;
- timr->it_overrun += (unsigned int) hrtimer_forward(timer,
- timer->base->get_time(),
- timr->it_interval);
+ timr->it_overrun += hrtimer_forward(timer, timer->base->get_time(),
+ timr->it_interval);
hrtimer_restart(timer);
}
@@ -321,10 +322,10 @@ void posixtimer_rearm(struct siginfo *info)
timr->it_active = 1;
timr->it_overrun_last = timr->it_overrun;
- timr->it_overrun = -1;
+ timr->it_overrun = -1LL;
++timr->it_requeue_pending;
- info->si_overrun += timr->it_overrun_last;
+ info->si_overrun = timer_overrun_to_int(timr, info->si_overrun);
}
unlock_timer(timr, flags);
@@ -332,8 +333,8 @@ void posixtimer_rearm(struct siginfo *info)
int posix_timer_event(struct k_itimer *timr, int si_private)
{
- struct task_struct *task;
- int shared, ret = -1;
+ enum pid_type type;
+ int ret = -1;
/*
* FIXME: if ->sigq is queued we can race with
* dequeue_signal()->posixtimer_rearm().
@@ -347,13 +348,8 @@ int posix_timer_event(struct k_itimer *timr, int si_private)
*/
timr->sigq->info.si_sys_private = si_private;
- rcu_read_lock();
- task = pid_task(timr->it_pid, PIDTYPE_PID);
- if (task) {
- shared = !(timr->it_sigev_notify & SIGEV_THREAD_ID);
- ret = send_sigqueue(timr->sigq, task, shared);
- }
- rcu_read_unlock();
+ type = !(timr->it_sigev_notify & SIGEV_THREAD_ID) ? PIDTYPE_TGID : PIDTYPE_PID;
+ ret = send_sigqueue(timr->sigq, timr->it_pid, type);
/* If we failed to send the signal the timer stops. */
return ret > 0;
}
@@ -418,9 +414,8 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer)
now = ktime_add(now, kj);
}
#endif
- timr->it_overrun += (unsigned int)
- hrtimer_forward(timer, now,
- timr->it_interval);
+ timr->it_overrun += hrtimer_forward(timer, now,
+ timr->it_interval);
ret = HRTIMER_RESTART;
++timr->it_requeue_pending;
timr->it_active = 1;
@@ -433,11 +428,13 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer)
static struct pid *good_sigevent(sigevent_t * event)
{
- struct task_struct *rtn = current->group_leader;
+ struct pid *pid = task_tgid(current);
+ struct task_struct *rtn;
switch (event->sigev_notify) {
case SIGEV_SIGNAL | SIGEV_THREAD_ID:
- rtn = find_task_by_vpid(event->sigev_notify_thread_id);
+ pid = find_vpid(event->sigev_notify_thread_id);
+ rtn = pid_task(pid, PIDTYPE_PID);
if (!rtn || !same_thread_group(rtn, current))
return NULL;
/* FALLTHRU */
@@ -447,7 +444,7 @@ static struct pid *good_sigevent(sigevent_t * event)
return NULL;
/* FALLTHRU */
case SIGEV_NONE:
- return task_pid(rtn);
+ return pid;
default:
return NULL;
}
@@ -524,7 +521,7 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event,
new_timer->it_id = (timer_t) new_timer_id;
new_timer->it_clock = which_clock;
new_timer->kclock = kc;
- new_timer->it_overrun = -1;
+ new_timer->it_overrun = -1LL;
if (event) {
rcu_read_lock();
@@ -645,11 +642,11 @@ static ktime_t common_hrtimer_remaining(struct k_itimer *timr, ktime_t now)
return __hrtimer_expires_remaining_adjusted(timer, now);
}
-static int common_hrtimer_forward(struct k_itimer *timr, ktime_t now)
+static s64 common_hrtimer_forward(struct k_itimer *timr, ktime_t now)
{
struct hrtimer *timer = &timr->it.real.timer;
- return (int)hrtimer_forward(timer, now, timr->it_interval);
+ return hrtimer_forward(timer, now, timr->it_interval);
}
/*
@@ -743,7 +740,7 @@ static int do_timer_gettime(timer_t timer_id, struct itimerspec64 *setting)
/* Get the time remaining on a POSIX.1b interval timer. */
SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
- struct itimerspec __user *, setting)
+ struct __kernel_itimerspec __user *, setting)
{
struct itimerspec64 cur_setting;
@@ -755,7 +752,8 @@ SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
return ret;
}
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_32BIT_TIME
+
COMPAT_SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
struct compat_itimerspec __user *, setting)
{
@@ -768,6 +766,7 @@ COMPAT_SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
}
return ret;
}
+
#endif
/*
@@ -789,7 +788,7 @@ SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id)
if (!timr)
return -EINVAL;
- overrun = timr->it_overrun_last;
+ overrun = timer_overrun_to_int(timr, 0);
unlock_timer(timr, flags);
return overrun;
@@ -906,8 +905,8 @@ retry:
/* Set a POSIX.1b interval timer */
SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
- const struct itimerspec __user *, new_setting,
- struct itimerspec __user *, old_setting)
+ const struct __kernel_itimerspec __user *, new_setting,
+ struct __kernel_itimerspec __user *, old_setting)
{
struct itimerspec64 new_spec, old_spec;
struct itimerspec64 *rtn = old_setting ? &old_spec : NULL;
@@ -927,7 +926,7 @@ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
return error;
}
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_32BIT_TIME
COMPAT_SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
struct compat_itimerspec __user *, new,
struct compat_itimerspec __user *, old)
@@ -1220,7 +1219,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
if (!kc)
return -EINVAL;
if (!kc->nsleep)
- return -ENANOSLEEP_NOTSUP;
+ return -EOPNOTSUPP;
if (get_timespec64(&t, rqtp))
return -EFAULT;
@@ -1247,7 +1246,7 @@ COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags,
if (!kc)
return -EINVAL;
if (!kc->nsleep)
- return -ENANOSLEEP_NOTSUP;
+ return -EOPNOTSUPP;
if (compat_get_timespec64(&t, rqtp))
return -EFAULT;
diff --git a/kernel/time/posix-timers.h b/kernel/time/posix-timers.h
index 151e28f5bf30..ddb21145211a 100644
--- a/kernel/time/posix-timers.h
+++ b/kernel/time/posix-timers.h
@@ -19,7 +19,7 @@ struct k_clock {
void (*timer_get)(struct k_itimer *timr,
struct itimerspec64 *cur_setting);
void (*timer_rearm)(struct k_itimer *timr);
- int (*timer_forward)(struct k_itimer *timr, ktime_t now);
+ s64 (*timer_forward)(struct k_itimer *timr, ktime_t now);
ktime_t (*timer_remaining)(struct k_itimer *timr, ktime_t now);
int (*timer_try_to_cancel)(struct k_itimer *timr);
void (*timer_arm)(struct k_itimer *timr, ktime_t expires,
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index 2d8f05aad442..cbc72c2c1fca 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -237,7 +237,7 @@ sched_clock_register(u64 (*read)(void), int bits, unsigned long rate)
pr_debug("Registered %pF as sched_clock source\n", read);
}
-void __init sched_clock_postinit(void)
+void __init generic_sched_clock_init(void)
{
/*
* If no sched_clock() function has been provided at that point,
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
index 58045eb976c3..a59641fb88b6 100644
--- a/kernel/time/tick-broadcast-hrtimer.c
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -90,7 +90,7 @@ static struct clock_event_device ce_broadcast_hrtimer = {
.max_delta_ticks = ULONG_MAX,
.mult = 1,
.shift = 0,
- .cpumask = cpu_all_mask,
+ .cpumask = cpu_possible_mask,
};
static enum hrtimer_restart bc_handler(struct hrtimer *t)
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index da9455a6b42b..5b33e2f5c0ed 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -642,7 +642,7 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
static inline bool local_timer_softirq_pending(void)
{
- return local_softirq_pending() & TIMER_SOFTIRQ;
+ return local_softirq_pending() & BIT(TIMER_SOFTIRQ);
}
static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
diff --git a/kernel/time/time.c b/kernel/time/time.c
index 2b41e8e2d31d..ccdb351277ee 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -64,7 +64,7 @@ EXPORT_SYMBOL(sys_tz);
*/
SYSCALL_DEFINE1(time, time_t __user *, tloc)
{
- time_t i = get_seconds();
+ time_t i = (time_t)ktime_get_real_seconds();
if (tloc) {
if (put_user(i,tloc))
@@ -107,11 +107,9 @@ SYSCALL_DEFINE1(stime, time_t __user *, tptr)
/* compat_time_t is a 32 bit "long" and needs to get converted. */
COMPAT_SYSCALL_DEFINE1(time, compat_time_t __user *, tloc)
{
- struct timeval tv;
compat_time_t i;
- do_gettimeofday(&tv);
- i = tv.tv_sec;
+ i = (compat_time_t)ktime_get_real_seconds();
if (tloc) {
if (put_user(i,tloc))
@@ -931,7 +929,7 @@ int compat_put_timespec64(const struct timespec64 *ts, void __user *uts)
EXPORT_SYMBOL_GPL(compat_put_timespec64);
int get_itimerspec64(struct itimerspec64 *it,
- const struct itimerspec __user *uit)
+ const struct __kernel_itimerspec __user *uit)
{
int ret;
@@ -946,7 +944,7 @@ int get_itimerspec64(struct itimerspec64 *it,
EXPORT_SYMBOL_GPL(get_itimerspec64);
int put_itimerspec64(const struct itimerspec64 *it,
- struct itimerspec __user *uit)
+ struct __kernel_itimerspec __user *uit)
{
int ret;
@@ -959,3 +957,24 @@ int put_itimerspec64(const struct itimerspec64 *it,
return ret;
}
EXPORT_SYMBOL_GPL(put_itimerspec64);
+
+int get_compat_itimerspec64(struct itimerspec64 *its,
+ const struct compat_itimerspec __user *uits)
+{
+
+ if (__compat_get_timespec64(&its->it_interval, &uits->it_interval) ||
+ __compat_get_timespec64(&its->it_value, &uits->it_value))
+ return -EFAULT;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(get_compat_itimerspec64);
+
+int put_compat_itimerspec64(const struct itimerspec64 *its,
+ struct compat_itimerspec __user *uits)
+{
+ if (__compat_put_timespec64(&its->it_interval, &uits->it_interval) ||
+ __compat_put_timespec64(&its->it_value, &uits->it_value))
+ return -EFAULT;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(put_compat_itimerspec64);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 4786df904c22..f3b22f456fac 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -17,6 +17,7 @@
#include <linux/nmi.h>
#include <linux/sched.h>
#include <linux/sched/loadavg.h>
+#include <linux/sched/clock.h>
#include <linux/syscore_ops.h>
#include <linux/clocksource.h>
#include <linux/jiffies.h>
@@ -34,6 +35,14 @@
#define TK_MIRROR (1 << 1)
#define TK_CLOCK_WAS_SET (1 << 2)
+enum timekeeping_adv_mode {
+ /* Update timekeeper when a tick has passed */
+ TK_ADV_TICK,
+
+ /* Update timekeeper on a direct frequency change */
+ TK_ADV_FREQ
+};
+
/*
* The most important data for readout fits into a single 64 byte
* cache line.
@@ -97,7 +106,7 @@ static inline void tk_normalize_xtime(struct timekeeper *tk)
}
}
-static inline struct timespec64 tk_xtime(struct timekeeper *tk)
+static inline struct timespec64 tk_xtime(const struct timekeeper *tk)
{
struct timespec64 ts;
@@ -154,7 +163,7 @@ static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta)
* a read of the fast-timekeeper tkrs (which is protected by its own locking
* and update logic).
*/
-static inline u64 tk_clock_read(struct tk_read_base *tkr)
+static inline u64 tk_clock_read(const struct tk_read_base *tkr)
{
struct clocksource *clock = READ_ONCE(tkr->clock);
@@ -203,7 +212,7 @@ static void timekeeping_check_update(struct timekeeper *tk, u64 offset)
}
}
-static inline u64 timekeeping_get_delta(struct tk_read_base *tkr)
+static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr)
{
struct timekeeper *tk = &tk_core.timekeeper;
u64 now, last, mask, max, delta;
@@ -247,7 +256,7 @@ static inline u64 timekeeping_get_delta(struct tk_read_base *tkr)
static inline void timekeeping_check_update(struct timekeeper *tk, u64 offset)
{
}
-static inline u64 timekeeping_get_delta(struct tk_read_base *tkr)
+static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr)
{
u64 cycle_now, delta;
@@ -344,7 +353,7 @@ u32 (*arch_gettimeoffset)(void) = default_arch_gettimeoffset;
static inline u32 arch_gettimeoffset(void) { return 0; }
#endif
-static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr, u64 delta)
+static inline u64 timekeeping_delta_to_ns(const struct tk_read_base *tkr, u64 delta)
{
u64 nsec;
@@ -355,7 +364,7 @@ static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr, u64 delta)
return nsec + arch_gettimeoffset();
}
-static inline u64 timekeeping_get_ns(struct tk_read_base *tkr)
+static inline u64 timekeeping_get_ns(const struct tk_read_base *tkr)
{
u64 delta;
@@ -363,7 +372,7 @@ static inline u64 timekeeping_get_ns(struct tk_read_base *tkr)
return timekeeping_delta_to_ns(tkr, delta);
}
-static inline u64 timekeeping_cycles_to_ns(struct tk_read_base *tkr, u64 cycles)
+static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles)
{
u64 delta;
@@ -386,7 +395,8 @@ static inline u64 timekeeping_cycles_to_ns(struct tk_read_base *tkr, u64 cycles)
* slightly wrong timestamp (a few nanoseconds). See
* @ktime_get_mono_fast_ns.
*/
-static void update_fast_timekeeper(struct tk_read_base *tkr, struct tk_fast *tkf)
+static void update_fast_timekeeper(const struct tk_read_base *tkr,
+ struct tk_fast *tkf)
{
struct tk_read_base *base = tkf->base;
@@ -541,10 +551,10 @@ EXPORT_SYMBOL_GPL(ktime_get_real_fast_ns);
* number of cycles every time until timekeeping is resumed at which time the
* proper readout base for the fast timekeeper will be restored automatically.
*/
-static void halt_fast_timekeeper(struct timekeeper *tk)
+static void halt_fast_timekeeper(const struct timekeeper *tk)
{
static struct tk_read_base tkr_dummy;
- struct tk_read_base *tkr = &tk->tkr_mono;
+ const struct tk_read_base *tkr = &tk->tkr_mono;
memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy));
cycles_at_suspend = tk_clock_read(tkr);
@@ -1269,7 +1279,7 @@ EXPORT_SYMBOL(do_settimeofday64);
*
* Adds or subtracts an offset value from the current time.
*/
-static int timekeeping_inject_offset(struct timespec64 *ts)
+static int timekeeping_inject_offset(const struct timespec64 *ts)
{
struct timekeeper *tk = &tk_core.timekeeper;
unsigned long flags;
@@ -1496,22 +1506,39 @@ void __weak read_persistent_clock64(struct timespec64 *ts64)
}
/**
- * read_boot_clock64 - Return time of the system start.
+ * read_persistent_wall_and_boot_offset - Read persistent clock, and also offset
+ * from the boot.
*
* Weak dummy function for arches that do not yet support it.
- * Function to read the exact time the system has been started.
- * Returns a timespec64 with tv_sec=0 and tv_nsec=0 if unsupported.
- *
- * XXX - Do be sure to remove it once all arches implement it.
+ * wall_time - current time as returned by persistent clock
+ * boot_offset - offset that is defined as wall_time - boot_time
+ * The default function calculates offset based on the current value of
+ * local_clock(). This way architectures that support sched_clock() but don't
+ * support dedicated boot time clock will provide the best estimate of the
+ * boot time.
*/
-void __weak read_boot_clock64(struct timespec64 *ts)
+void __weak __init
+read_persistent_wall_and_boot_offset(struct timespec64 *wall_time,
+ struct timespec64 *boot_offset)
{
- ts->tv_sec = 0;
- ts->tv_nsec = 0;
+ read_persistent_clock64(wall_time);
+ *boot_offset = ns_to_timespec64(local_clock());
}
-/* Flag for if timekeeping_resume() has injected sleeptime */
-static bool sleeptime_injected;
+/*
+ * Flag reflecting whether timekeeping_resume() has injected sleeptime.
+ *
+ * The flag starts of false and is only set when a suspend reaches
+ * timekeeping_suspend(), timekeeping_resume() sets it to false when the
+ * timekeeper clocksource is not stopping across suspend and has been
+ * used to update sleep time. If the timekeeper clocksource has stopped
+ * then the flag stays true and is used by the RTC resume code to decide
+ * whether sleeptime must be injected and if so the flag gets false then.
+ *
+ * If a suspend fails before reaching timekeeping_resume() then the flag
+ * stays false and prevents erroneous sleeptime injection.
+ */
+static bool suspend_timing_needed;
/* Flag for if there is a persistent clock on this platform */
static bool persistent_clock_exists;
@@ -1521,28 +1548,29 @@ static bool persistent_clock_exists;
*/
void __init timekeeping_init(void)
{
+ struct timespec64 wall_time, boot_offset, wall_to_mono;
struct timekeeper *tk = &tk_core.timekeeper;
struct clocksource *clock;
unsigned long flags;
- struct timespec64 now, boot, tmp;
-
- read_persistent_clock64(&now);
- if (!timespec64_valid_strict(&now)) {
- pr_warn("WARNING: Persistent clock returned invalid value!\n"
- " Check your CMOS/BIOS settings.\n");
- now.tv_sec = 0;
- now.tv_nsec = 0;
- } else if (now.tv_sec || now.tv_nsec)
- persistent_clock_exists = true;
- read_boot_clock64(&boot);
- if (!timespec64_valid_strict(&boot)) {
- pr_warn("WARNING: Boot clock returned invalid value!\n"
- " Check your CMOS/BIOS settings.\n");
- boot.tv_sec = 0;
- boot.tv_nsec = 0;
+ read_persistent_wall_and_boot_offset(&wall_time, &boot_offset);
+ if (timespec64_valid_strict(&wall_time) &&
+ timespec64_to_ns(&wall_time) > 0) {
+ persistent_clock_exists = true;
+ } else if (timespec64_to_ns(&wall_time) != 0) {
+ pr_warn("Persistent clock returned invalid value");
+ wall_time = (struct timespec64){0};
}
+ if (timespec64_compare(&wall_time, &boot_offset) < 0)
+ boot_offset = (struct timespec64){0};
+
+ /*
+ * We want set wall_to_mono, so the following is true:
+ * wall time + wall_to_mono = boot time
+ */
+ wall_to_mono = timespec64_sub(boot_offset, wall_time);
+
raw_spin_lock_irqsave(&timekeeper_lock, flags);
write_seqcount_begin(&tk_core.seq);
ntp_init();
@@ -1552,13 +1580,10 @@ void __init timekeeping_init(void)
clock->enable(clock);
tk_setup_internals(tk, clock);
- tk_set_xtime(tk, &now);
+ tk_set_xtime(tk, &wall_time);
tk->raw_sec = 0;
- if (boot.tv_sec == 0 && boot.tv_nsec == 0)
- boot = tk_xtime(tk);
- set_normalized_timespec64(&tmp, -boot.tv_sec, -boot.tv_nsec);
- tk_set_wall_to_mono(tk, tmp);
+ tk_set_wall_to_mono(tk, wall_to_mono);
timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
@@ -1577,7 +1602,7 @@ static struct timespec64 timekeeping_suspend_time;
* adds the sleep offset to the timekeeping variables.
*/
static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
- struct timespec64 *delta)
+ const struct timespec64 *delta)
{
if (!timespec64_valid_strict(delta)) {
printk_deferred(KERN_WARNING
@@ -1610,7 +1635,7 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
*/
bool timekeeping_rtc_skipresume(void)
{
- return sleeptime_injected;
+ return !suspend_timing_needed;
}
/**
@@ -1638,7 +1663,7 @@ bool timekeeping_rtc_skipsuspend(void)
* This function should only be called by rtc_resume(), and allows
* a suspend offset to be injected into the timekeeping values.
*/
-void timekeeping_inject_sleeptime64(struct timespec64 *delta)
+void timekeeping_inject_sleeptime64(const struct timespec64 *delta)
{
struct timekeeper *tk = &tk_core.timekeeper;
unsigned long flags;
@@ -1646,6 +1671,8 @@ void timekeeping_inject_sleeptime64(struct timespec64 *delta)
raw_spin_lock_irqsave(&timekeeper_lock, flags);
write_seqcount_begin(&tk_core.seq);
+ suspend_timing_needed = false;
+
timekeeping_forward_now(tk);
__timekeeping_inject_sleeptime(tk, delta);
@@ -1669,9 +1696,9 @@ void timekeeping_resume(void)
struct clocksource *clock = tk->tkr_mono.clock;
unsigned long flags;
struct timespec64 ts_new, ts_delta;
- u64 cycle_now;
+ u64 cycle_now, nsec;
+ bool inject_sleeptime = false;
- sleeptime_injected = false;
read_persistent_clock64(&ts_new);
clockevents_resume();
@@ -1693,22 +1720,19 @@ void timekeeping_resume(void)
* usable source. The rtc part is handled separately in rtc core code.
*/
cycle_now = tk_clock_read(&tk->tkr_mono);
- if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) &&
- cycle_now > tk->tkr_mono.cycle_last) {
- u64 nsec, cyc_delta;
-
- cyc_delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last,
- tk->tkr_mono.mask);
- nsec = mul_u64_u32_shr(cyc_delta, clock->mult, clock->shift);
+ nsec = clocksource_stop_suspend_timing(clock, cycle_now);
+ if (nsec > 0) {
ts_delta = ns_to_timespec64(nsec);
- sleeptime_injected = true;
+ inject_sleeptime = true;
} else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) {
ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time);
- sleeptime_injected = true;
+ inject_sleeptime = true;
}
- if (sleeptime_injected)
+ if (inject_sleeptime) {
+ suspend_timing_needed = false;
__timekeeping_inject_sleeptime(tk, &ts_delta);
+ }
/* Re-base the last cycle value */
tk->tkr_mono.cycle_last = cycle_now;
@@ -1732,6 +1756,8 @@ int timekeeping_suspend(void)
unsigned long flags;
struct timespec64 delta, delta_delta;
static struct timespec64 old_delta;
+ struct clocksource *curr_clock;
+ u64 cycle_now;
read_persistent_clock64(&timekeeping_suspend_time);
@@ -1743,11 +1769,22 @@ int timekeeping_suspend(void)
if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec)
persistent_clock_exists = true;
+ suspend_timing_needed = true;
+
raw_spin_lock_irqsave(&timekeeper_lock, flags);
write_seqcount_begin(&tk_core.seq);
timekeeping_forward_now(tk);
timekeeping_suspended = 1;
+ /*
+ * Since we've called forward_now, cycle_last stores the value
+ * just read from the current clocksource. Save this to potentially
+ * use in suspend timing.
+ */
+ curr_clock = tk->tkr_mono.clock;
+ cycle_now = tk->tkr_mono.cycle_last;
+ clocksource_start_suspend_timing(curr_clock, cycle_now);
+
if (persistent_clock_exists) {
/*
* To avoid drift caused by repeated suspend/resumes,
@@ -2021,11 +2058,11 @@ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset,
return offset;
}
-/**
- * update_wall_time - Uses the current clocksource to increment the wall time
- *
+/*
+ * timekeeping_advance - Updates the timekeeper to the current time and
+ * current NTP tick length
*/
-void update_wall_time(void)
+static void timekeeping_advance(enum timekeeping_adv_mode mode)
{
struct timekeeper *real_tk = &tk_core.timekeeper;
struct timekeeper *tk = &shadow_timekeeper;
@@ -2042,14 +2079,17 @@ void update_wall_time(void)
#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
offset = real_tk->cycle_interval;
+
+ if (mode != TK_ADV_TICK)
+ goto out;
#else
offset = clocksource_delta(tk_clock_read(&tk->tkr_mono),
tk->tkr_mono.cycle_last, tk->tkr_mono.mask);
-#endif
/* Check if there's really nothing to do */
- if (offset < real_tk->cycle_interval)
+ if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK)
goto out;
+#endif
/* Do some additional sanity checking */
timekeeping_check_update(tk, offset);
@@ -2106,6 +2146,15 @@ out:
}
/**
+ * update_wall_time - Uses the current clocksource to increment the wall time
+ *
+ */
+void update_wall_time(void)
+{
+ timekeeping_advance(TK_ADV_TICK);
+}
+
+/**
* getboottime64 - Return the real time of system boot.
* @ts: pointer to the timespec64 to be set
*
@@ -2220,7 +2269,7 @@ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real,
/**
* timekeeping_validate_timex - Ensures the timex is ok for use in do_adjtimex
*/
-static int timekeeping_validate_timex(struct timex *txc)
+static int timekeeping_validate_timex(const struct timex *txc)
{
if (txc->modes & ADJ_ADJTIME) {
/* singleshot must not be used with any other mode bits */
@@ -2310,7 +2359,7 @@ int do_adjtimex(struct timex *txc)
return ret;
}
- getnstimeofday64(&ts);
+ ktime_get_real_ts64(&ts);
raw_spin_lock_irqsave(&timekeeper_lock, flags);
write_seqcount_begin(&tk_core.seq);
@@ -2327,6 +2376,10 @@ int do_adjtimex(struct timex *txc)
write_seqcount_end(&tk_core.seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+ /* Update the multiplier immediately if frequency was set directly */
+ if (txc->modes & (ADJ_FREQUENCY | ADJ_TICK))
+ timekeeping_advance(TK_ADV_FREQ);
+
if (tai != orig_tai)
clock_was_set();
diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c
index 0754cadfa9e6..238e4be60229 100644
--- a/kernel/time/timekeeping_debug.c
+++ b/kernel/time/timekeeping_debug.c
@@ -70,7 +70,7 @@ static int __init tk_debug_sleep_time_init(void)
}
late_initcall(tk_debug_sleep_time_init);
-void tk_debug_account_sleep_time(struct timespec64 *t)
+void tk_debug_account_sleep_time(const struct timespec64 *t)
{
/* Cap bin index so we don't overflow the array */
int bin = min(fls(t->tv_sec), NUM_BINS-1);
diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h
index cf5c0828ee31..bcbb52db2256 100644
--- a/kernel/time/timekeeping_internal.h
+++ b/kernel/time/timekeeping_internal.h
@@ -8,7 +8,7 @@
#include <linux/time.h>
#ifdef CONFIG_DEBUG_FS
-extern void tk_debug_account_sleep_time(struct timespec64 *t);
+extern void tk_debug_account_sleep_time(const struct timespec64 *t);
#else
#define tk_debug_account_sleep_time(x)
#endif
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index cc2d23e6ff61..fa49cd753dea 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -581,7 +581,7 @@ trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer)
* wheel:
*/
base->next_expiry = timer->expires;
- wake_up_nohz_cpu(base->cpu);
+ wake_up_nohz_cpu(base->cpu);
}
static void
@@ -1657,6 +1657,22 @@ static inline void __run_timers(struct timer_base *base)
raw_spin_lock_irq(&base->lock);
+ /*
+ * timer_base::must_forward_clk must be cleared before running
+ * timers so that any timer functions that call mod_timer() will
+ * not try to forward the base. Idle tracking / clock forwarding
+ * logic is only used with BASE_STD timers.
+ *
+ * The must_forward_clk flag is cleared unconditionally also for
+ * the deferrable base. The deferrable base is not affected by idle
+ * tracking and never forwarded, so clearing the flag is a NOOP.
+ *
+ * The fact that the deferrable base is never forwarded can cause
+ * large variations in granularity for deferrable timers, but they
+ * can be deferred for long periods due to idle anyway.
+ */
+ base->must_forward_clk = false;
+
while (time_after_eq(jiffies, base->clk)) {
levels = collect_expired_timers(base, heads);
@@ -1676,19 +1692,6 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h)
{
struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
- /*
- * must_forward_clk must be cleared before running timers so that any
- * timer functions that call mod_timer will not try to forward the
- * base. idle trcking / clock forwarding logic is only used with
- * BASE_STD timers.
- *
- * The deferrable base does not do idle tracking at all, so we do
- * not forward it. This can result in very large variations in
- * granularity for deferrable timers, but they can be deferred for
- * long periods due to idle.
- */
- base->must_forward_clk = false;
-
__run_timers(base);
if (IS_ENABLED(CONFIG_NO_HZ_COMMON))
__run_timers(this_cpu_ptr(&timer_bases[BASE_DEF]));
diff --git a/kernel/torture.c b/kernel/torture.c
index 3de1efbecd6a..1ac24a826589 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -20,6 +20,9 @@
* Author: Paul E. McKenney <paulmck@us.ibm.com>
* Based on kernel/rcu/torture.c.
*/
+
+#define pr_fmt(fmt) fmt
+
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/init.h>
@@ -53,7 +56,7 @@ MODULE_LICENSE("GPL");
MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com>");
static char *torture_type;
-static bool verbose;
+static int verbose;
/* Mediate rmmod and system shutdown. Concurrent rmmod & shutdown illegal! */
#define FULLSTOP_DONTSTOP 0 /* Normal operation. */
@@ -98,7 +101,7 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes,
if (!cpu_online(cpu) || !cpu_is_hotpluggable(cpu))
return false;
- if (verbose)
+ if (verbose > 1)
pr_alert("%s" TORTURE_FLAG
"torture_onoff task: offlining %d\n",
torture_type, cpu);
@@ -111,7 +114,7 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes,
"torture_onoff task: offline %d failed: errno %d\n",
torture_type, cpu, ret);
} else {
- if (verbose)
+ if (verbose > 1)
pr_alert("%s" TORTURE_FLAG
"torture_onoff task: offlined %d\n",
torture_type, cpu);
@@ -147,7 +150,7 @@ bool torture_online(int cpu, long *n_onl_attempts, long *n_onl_successes,
if (cpu_online(cpu) || !cpu_is_hotpluggable(cpu))
return false;
- if (verbose)
+ if (verbose > 1)
pr_alert("%s" TORTURE_FLAG
"torture_onoff task: onlining %d\n",
torture_type, cpu);
@@ -160,7 +163,7 @@ bool torture_online(int cpu, long *n_onl_attempts, long *n_onl_successes,
"torture_onoff task: online %d failed: errno %d\n",
torture_type, cpu, ret);
} else {
- if (verbose)
+ if (verbose > 1)
pr_alert("%s" TORTURE_FLAG
"torture_onoff task: onlined %d\n",
torture_type, cpu);
@@ -647,7 +650,7 @@ static void torture_stutter_cleanup(void)
* The runnable parameter points to a flag that controls whether or not
* the test is currently runnable. If there is no such flag, pass in NULL.
*/
-bool torture_init_begin(char *ttype, bool v)
+bool torture_init_begin(char *ttype, int v)
{
mutex_lock(&fullstop_mutex);
if (torture_type != NULL) {
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index dcc0166d1997..c042a455afc6 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -47,6 +47,11 @@ config HAVE_FENTRY
help
Arch supports the gcc options -pg with -mfentry
+config HAVE_NOP_MCOUNT
+ bool
+ help
+ Arch supports the gcc options -pg with -mrecord-mcount and -nop-mcount
+
config HAVE_C_RECORDMCOUNT
bool
help
@@ -82,6 +87,15 @@ config RING_BUFFER_ALLOW_SWAP
Allow the use of ring_buffer_swap_cpu.
Adds a very slight overhead to tracing when enabled.
+config PREEMPTIRQ_TRACEPOINTS
+ bool
+ depends on TRACE_PREEMPT_TOGGLE || TRACE_IRQFLAGS
+ select TRACING
+ default y
+ help
+ Create preempt/irq toggle tracepoints if needed, so that other parts
+ of the kernel can use them to generate or add hooks to them.
+
# All tracer options should select GENERIC_TRACER. For those options that are
# enabled by all tracers (context switch and event tracer) they select TRACING.
# This allows those options to appear when no other tracer is selected. But the
@@ -155,18 +169,20 @@ config FUNCTION_GRAPH_TRACER
the return value. This is done by setting the current return
address on the current task structure into a stack of calls.
+config TRACE_PREEMPT_TOGGLE
+ bool
+ help
+ Enables hooks which will be called when preemption is first disabled,
+ and last enabled.
config PREEMPTIRQ_EVENTS
bool "Enable trace events for preempt and irq disable/enable"
select TRACE_IRQFLAGS
- depends on DEBUG_PREEMPT || !PROVE_LOCKING
- depends on TRACING
+ select TRACE_PREEMPT_TOGGLE if PREEMPT
+ select GENERIC_TRACER
default n
help
Enable tracing of disable and enable events for preemption and irqs.
- For tracing preempt disable/enable events, DEBUG_PREEMPT must be
- enabled. For tracing irq disable/enable events, PROVE_LOCKING must
- be disabled.
config IRQSOFF_TRACER
bool "Interrupts-off Latency Tracer"
@@ -203,6 +219,7 @@ config PREEMPT_TRACER
select RING_BUFFER_ALLOW_SWAP
select TRACER_SNAPSHOT
select TRACER_SNAPSHOT_PER_CPU_SWAP
+ select TRACE_PREEMPT_TOGGLE
help
This option measures the time spent in preemption-off critical
sections, with microsecond accuracy.
@@ -456,6 +473,26 @@ config KPROBE_EVENTS
This option is also required by perf-probe subcommand of perf tools.
If you want to use perf tools, this option is strongly recommended.
+config KPROBE_EVENTS_ON_NOTRACE
+ bool "Do NOT protect notrace function from kprobe events"
+ depends on KPROBE_EVENTS
+ depends on KPROBES_ON_FTRACE
+ default n
+ help
+ This is only for the developers who want to debug ftrace itself
+ using kprobe events.
+
+ If kprobes can use ftrace instead of breakpoint, ftrace related
+ functions are protected from kprobe-events to prevent an infinit
+ recursion or any unexpected execution path which leads to a kernel
+ crash.
+
+ This option disables such protection and allows you to put kprobe
+ events on ftrace functions for debugging ftrace by itself.
+ Note that this might let you shoot yourself in the foot.
+
+ If unsure, say N.
+
config UPROBE_EVENTS
bool "Enable uprobes-based dynamic events"
depends on ARCH_SUPPORTS_UPROBES
@@ -521,7 +558,7 @@ config FUNCTION_PROFILER
in debugfs called function_profile_enabled which defaults to zero.
When a 1 is echoed into this file profiling begins, and when a
zero is entered, profiling stops. A "functions" file is created in
- the trace_stats directory; this file shows the list of functions that
+ the trace_stat directory; this file shows the list of functions that
have been hit and their counters.
If in doubt, say N.
@@ -605,7 +642,7 @@ config HIST_TRIGGERS
Inter-event tracing of quantities such as latencies is also
supported using hist triggers under this option.
- See Documentation/trace/histogram.txt.
+ See Documentation/trace/histogram.rst.
If in doubt, say N.
config MMIOTRACE_TEST
@@ -687,6 +724,21 @@ config RING_BUFFER_STARTUP_TEST
If unsure, say N
+config PREEMPTIRQ_DELAY_TEST
+ tristate "Preempt / IRQ disable delay thread to test latency tracers"
+ depends on m
+ help
+ Select this option to build a test module that can help test latency
+ tracers by executing a preempt or irq disable section with a user
+ configurable delay. The module busy waits for the duration of the
+ critical section.
+
+ For example, the following invocation forces a one-time irq-disabled
+ critical section for 500us:
+ modprobe preemptirq_delay_test test_mode=irq delay=500000
+
+ If unsure, say N
+
config TRACE_EVAL_MAP_FILE
bool "Show eval mappings for trace events"
depends on TRACING
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index e2538c7638d4..98d53b39a8ee 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -13,6 +13,11 @@ obj-y += trace_selftest_dynamic.o
endif
endif
+ifdef CONFIG_FTRACE_STARTUP_TEST
+CFLAGS_trace_kprobe_selftest.o = $(CC_FLAGS_FTRACE)
+obj-$(CONFIG_KPROBE_EVENTS) += trace_kprobe_selftest.o
+endif
+
# If unlikely tracing is enabled, do not trace these files
ifdef CONFIG_TRACING_BRANCHES
KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
@@ -33,9 +38,10 @@ obj-$(CONFIG_TRACING) += trace_seq.o
obj-$(CONFIG_TRACING) += trace_stat.o
obj-$(CONFIG_TRACING) += trace_printk.o
obj-$(CONFIG_TRACING_MAP) += tracing_map.o
+obj-$(CONFIG_PREEMPTIRQ_DELAY_TEST) += preemptirq_delay_test.o
obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o
obj-$(CONFIG_FUNCTION_TRACER) += trace_functions.o
-obj-$(CONFIG_PREEMPTIRQ_EVENTS) += trace_irqsoff.o
+obj-$(CONFIG_PREEMPTIRQ_TRACEPOINTS) += trace_preemptirq.o
obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o
obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o
obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 96457ad8d720..2868d85f1fb1 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -1,19 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2006 Jens Axboe <axboe@kernel.dk>
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program 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 General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
*/
#include <linux/kernel.h>
#include <linux/blkdev.h>
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 0ae6829804bc..08fcfe440c63 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1,9 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2011-2015 PLUMgrid, http://plumgrid.com
* Copyright (c) 2016 Facebook
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
*/
#include <linux/kernel.h>
#include <linux/types.h>
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index caf9cbf35816..f536f601bd46 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Infrastructure for profiling code inserted by 'gcc -pg'.
*
@@ -157,30 +158,6 @@ static inline void ftrace_ops_init(struct ftrace_ops *ops)
#endif
}
-/**
- * ftrace_nr_registered_ops - return number of ops registered
- *
- * Returns the number of ftrace_ops registered and tracing functions
- */
-int ftrace_nr_registered_ops(void)
-{
- struct ftrace_ops *ops;
- int cnt = 0;
-
- mutex_lock(&ftrace_lock);
-
- for (ops = rcu_dereference_protected(ftrace_ops_list,
- lockdep_is_held(&ftrace_lock));
- ops != &ftrace_list_end;
- ops = rcu_dereference_protected(ops->next,
- lockdep_is_held(&ftrace_lock)))
- cnt++;
-
- mutex_unlock(&ftrace_lock);
-
- return cnt;
-}
-
static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct pt_regs *regs)
{
@@ -313,11 +290,6 @@ static void update_ftrace_function(void)
ftrace_trace_function = func;
}
-int using_ftrace_ops_list_func(void)
-{
- return ftrace_trace_function == ftrace_ops_list_func;
-}
-
static void add_ftrace_ops(struct ftrace_ops __rcu **list,
struct ftrace_ops *ops)
{
@@ -1049,8 +1021,6 @@ static __init void ftrace_profile_tracefs(struct dentry *d_tracer)
}
#endif /* CONFIG_FUNCTION_PROFILER */
-static struct pid * const ftrace_swapper_pid = &init_struct_pid;
-
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
static int ftrace_graph_active;
#else
@@ -2927,22 +2897,22 @@ ops_references_rec(struct ftrace_ops *ops, struct dyn_ftrace *rec)
{
/* If ops isn't enabled, ignore it */
if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
- return 0;
+ return false;
/* If ops traces all then it includes this function */
if (ops_traces_mod(ops))
- return 1;
+ return true;
/* The function must be in the filter */
if (!ftrace_hash_empty(ops->func_hash->filter_hash) &&
!__ftrace_lookup_ip(ops->func_hash->filter_hash, rec->ip))
- return 0;
+ return false;
/* If in notrace hash, we ignore it too */
if (ftrace_lookup_ip(ops->func_hash->notrace_hash, rec->ip))
- return 0;
+ return false;
- return 1;
+ return true;
}
static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs)
@@ -2981,12 +2951,14 @@ static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs)
p = &pg->records[i];
p->flags = rec_flags;
+#ifndef CC_USING_NOP_MCOUNT
/*
* Do the initial record conversion from mcount jump
* to the NOP instructions.
*/
if (!ftrace_code_disable(mod, p))
break;
+#endif
update_cnt++;
}
diff --git a/kernel/trace/preemptirq_delay_test.c b/kernel/trace/preemptirq_delay_test.c
new file mode 100644
index 000000000000..f704390db9fc
--- /dev/null
+++ b/kernel/trace/preemptirq_delay_test.c
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Preempt / IRQ disable delay thread to test latency tracers
+ *
+ * Copyright (C) 2018 Joel Fernandes (Google) <joel@joelfernandes.org>
+ */
+
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/kthread.h>
+#include <linux/ktime.h>
+#include <linux/module.h>
+#include <linux/printk.h>
+#include <linux/string.h>
+
+static ulong delay = 100;
+static char test_mode[10] = "irq";
+
+module_param_named(delay, delay, ulong, S_IRUGO);
+module_param_string(test_mode, test_mode, 10, S_IRUGO);
+MODULE_PARM_DESC(delay, "Period in microseconds (100 uS default)");
+MODULE_PARM_DESC(test_mode, "Mode of the test such as preempt or irq (default irq)");
+
+static void busy_wait(ulong time)
+{
+ ktime_t start, end;
+ start = ktime_get();
+ do {
+ end = ktime_get();
+ if (kthread_should_stop())
+ break;
+ } while (ktime_to_ns(ktime_sub(end, start)) < (time * 1000));
+}
+
+static int preemptirq_delay_run(void *data)
+{
+ unsigned long flags;
+
+ if (!strcmp(test_mode, "irq")) {
+ local_irq_save(flags);
+ busy_wait(delay);
+ local_irq_restore(flags);
+ } else if (!strcmp(test_mode, "preempt")) {
+ preempt_disable();
+ busy_wait(delay);
+ preempt_enable();
+ }
+
+ return 0;
+}
+
+static int __init preemptirq_delay_init(void)
+{
+ char task_name[50];
+ struct task_struct *test_task;
+
+ snprintf(task_name, sizeof(task_name), "%s_test", test_mode);
+
+ test_task = kthread_run(preemptirq_delay_run, NULL, task_name);
+ return PTR_ERR_OR_ZERO(test_task);
+}
+
+static void __exit preemptirq_delay_exit(void)
+{
+ return;
+}
+
+module_init(preemptirq_delay_init)
+module_exit(preemptirq_delay_exit)
+MODULE_LICENSE("GPL v2");
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 6a46af21765c..1d92d4a982fd 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Generic ring buffer
*
@@ -3221,12 +3222,28 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_on);
*
* Returns true if the ring buffer is in a state that it accepts writes.
*/
-int ring_buffer_record_is_on(struct ring_buffer *buffer)
+bool ring_buffer_record_is_on(struct ring_buffer *buffer)
{
return !atomic_read(&buffer->record_disabled);
}
/**
+ * ring_buffer_record_is_set_on - return true if the ring buffer is set writable
+ * @buffer: The ring buffer to see if write is set enabled
+ *
+ * Returns true if the ring buffer is set writable by ring_buffer_record_on().
+ * Note that this does NOT mean it is in a writable state.
+ *
+ * It may return true when the ring buffer has been disabled by
+ * ring_buffer_record_disable(), as that is a temporary disabling of
+ * the ring buffer.
+ */
+bool ring_buffer_record_is_set_on(struct ring_buffer *buffer)
+{
+ return !(atomic_read(&buffer->record_disabled) & RB_BUFFER_OFF);
+}
+
+/**
* ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer
* @buffer: The ring buffer to stop writes to.
* @cpu: The CPU buffer to stop
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index 68ee79afe31c..ffba6789c0e2 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* ring buffer tester and benchmark
*
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 87cf25171fb8..bf6f1d70484d 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* ring buffer based function tracer
*
@@ -1087,7 +1088,7 @@ void disable_trace_on_warning(void)
*
* Shows real state of the ring buffer if it is enabled or not.
*/
-int tracer_tracing_is_on(struct trace_array *tr)
+bool tracer_tracing_is_on(struct trace_array *tr)
{
if (tr->trace_buffer.buffer)
return ring_buffer_record_is_on(tr->trace_buffer.buffer);
@@ -1373,6 +1374,12 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
arch_spin_lock(&tr->max_lock);
+ /* Inherit the recordable setting from trace_buffer */
+ if (ring_buffer_record_is_set_on(tr->trace_buffer.buffer))
+ ring_buffer_record_on(tr->max_buffer.buffer);
+ else
+ ring_buffer_record_off(tr->max_buffer.buffer);
+
swap(tr->trace_buffer.buffer, tr->max_buffer.buffer);
__update_max_tr(tr, tsk, cpu);
@@ -7622,7 +7629,9 @@ rb_simple_write(struct file *filp, const char __user *ubuf,
if (buffer) {
mutex_lock(&trace_types_lock);
- if (val) {
+ if (!!val == tracer_tracing_is_on(tr)) {
+ val = 0; /* do nothing */
+ } else if (val) {
tracer_tracing_on(tr);
if (tr->current_trace->start)
tr->current_trace->start(tr);
@@ -8282,6 +8291,7 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
tracing_off();
local_irq_save(flags);
+ printk_nmi_direct_enter();
/* Simulate the iterator */
trace_init_global_iter(&iter);
@@ -8361,7 +8371,8 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
for_each_tracing_cpu(cpu) {
atomic_dec(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled);
}
- atomic_dec(&dump_running);
+ atomic_dec(&dump_running);
+ printk_nmi_direct_exit();
local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(ftrace_dump);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index f8f86231ad90..3b8c0e24ab30 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+// SPDX-License-Identifier: GPL-2.0
#ifndef _LINUX_KERNEL_TRACE_H
#define _LINUX_KERNEL_TRACE_H
@@ -594,7 +594,7 @@ void tracing_reset_current(int cpu);
void tracing_reset_all_online_cpus(void);
int tracing_open_generic(struct inode *inode, struct file *filp);
bool tracing_is_disabled(void);
-int tracer_tracing_is_on(struct trace_array *tr);
+bool tracer_tracing_is_on(struct trace_array *tr);
void tracer_tracing_on(struct trace_array *tr);
void tracer_tracing_off(struct trace_array *tr);
struct dentry *trace_create_file(const char *name,
@@ -937,7 +937,6 @@ void ftrace_destroy_function_files(struct trace_array *tr);
void ftrace_init_global_array_ops(struct trace_array *tr);
void ftrace_init_array_ops(struct trace_array *tr, ftrace_func_t func);
void ftrace_reset_array_ops(struct trace_array *tr);
-int using_ftrace_ops_list_func(void);
void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer);
void ftrace_init_tracefs_toplevel(struct trace_array *tr,
struct dentry *d_tracer);
@@ -1533,9 +1532,6 @@ extern int event_trigger_init(struct event_trigger_ops *ops,
extern int trace_event_trigger_enable_disable(struct trace_event_file *file,
int trigger_enable);
extern void update_cond_flag(struct trace_event_file *file);
-extern void unregister_trigger(char *glob, struct event_trigger_ops *ops,
- struct event_trigger_data *test,
- struct trace_event_file *file);
extern int set_trigger_filter(char *filter_str,
struct event_trigger_data *trigger_data,
struct trace_event_file *file);
@@ -1831,6 +1827,21 @@ static inline int tracing_alloc_snapshot_instance(struct trace_array *tr)
}
#endif
+#ifdef CONFIG_PREEMPT_TRACER
+void tracer_preempt_on(unsigned long a0, unsigned long a1);
+void tracer_preempt_off(unsigned long a0, unsigned long a1);
+#else
+static inline void tracer_preempt_on(unsigned long a0, unsigned long a1) { }
+static inline void tracer_preempt_off(unsigned long a0, unsigned long a1) { }
+#endif
+#ifdef CONFIG_IRQSOFF_TRACER
+void tracer_hardirqs_on(unsigned long a0, unsigned long a1);
+void tracer_hardirqs_off(unsigned long a0, unsigned long a1);
+#else
+static inline void tracer_hardirqs_on(unsigned long a0, unsigned long a1) { }
+static inline void tracer_hardirqs_off(unsigned long a0, unsigned long a1) { }
+#endif
+
extern struct trace_iterator *tracepoint_print_iter;
#endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_benchmark.h b/kernel/trace/trace_benchmark.h
index be1d86ff753d..79e6fbe5b365 100644
--- a/kernel/trace/trace_benchmark.h
+++ b/kernel/trace/trace_benchmark.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+// SPDX-License-Identifier: GPL-2.0
#undef TRACE_SYSTEM
#define TRACE_SYSTEM benchmark
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index d8a188e0418a..aaf6793ededa 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* tracing clocks
*
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index 1d67464ed95e..06bb2fd9a56c 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+// SPDX-License-Identifier: GPL-2.0
/*
* This file defines the trace event structures that go into the ring
* buffer directly. They are created via macros so that changes for them
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index c79193e598f5..69a3fe926e8c 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* trace event based perf event profiling/tracing
*
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 14ff4ff3caab..f94be0c2827b 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* event tracer
*
@@ -239,7 +240,7 @@ bool trace_event_ignore_this_pid(struct trace_event_file *trace_file)
struct trace_array_cpu *data;
struct trace_pid_list *pid_list;
- pid_list = rcu_dereference_sched(tr->filtered_pids);
+ pid_list = rcu_dereference_raw(tr->filtered_pids);
if (!pid_list)
return false;
@@ -512,7 +513,7 @@ event_filter_pid_sched_process_exit(void *data, struct task_struct *task)
struct trace_pid_list *pid_list;
struct trace_array *tr = data;
- pid_list = rcu_dereference_sched(tr->filtered_pids);
+ pid_list = rcu_dereference_raw(tr->filtered_pids);
trace_filter_add_remove_task(pid_list, NULL, task);
}
@@ -636,7 +637,7 @@ static void __ftrace_clear_event_pids(struct trace_array *tr)
rcu_assign_pointer(tr->filtered_pids, NULL);
/* Wait till all users are no longer using pid filtering */
- synchronize_sched();
+ tracepoint_synchronize_unregister();
trace_free_pid_list(pid_list);
}
@@ -1622,7 +1623,7 @@ ftrace_event_pid_write(struct file *filp, const char __user *ubuf,
}
if (filtered_pids) {
- synchronize_sched();
+ tracepoint_synchronize_unregister();
trace_free_pid_list(filtered_pids);
} else if (pid_list) {
/*
@@ -3036,8 +3037,8 @@ int event_trace_del_tracer(struct trace_array *tr)
/* Disable any running events */
__ftrace_set_clr_event_nolock(tr, NULL, NULL, NULL, 0);
- /* Access to events are within rcu_read_lock_sched() */
- synchronize_sched();
+ /* Make sure no more events are being executed */
+ tracepoint_synchronize_unregister();
down_write(&trace_event_sem);
__trace_remove_event_dirs(tr);
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 893a206bcba4..84a65173b1e9 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1,20 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* trace_events_filter - generic event filtering
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program 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 General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
* Copyright (C) 2009 Tom Zanussi <tzanussi@gmail.com>
*/
@@ -899,7 +886,8 @@ int filter_match_preds(struct event_filter *filter, void *rec)
if (!filter)
return 1;
- prog = rcu_dereference_sched(filter->prog);
+ /* Protected by either SRCU(tracepoint_srcu) or preempt_disable */
+ prog = rcu_dereference_raw(filter->prog);
if (!prog)
return 1;
@@ -1626,10 +1614,10 @@ static int process_system_preds(struct trace_subsystem_dir *dir,
/*
* The calls can still be using the old filters.
- * Do a synchronize_sched() to ensure all calls are
+ * Do a synchronize_sched() and to ensure all calls are
* done with them before we free them.
*/
- synchronize_sched();
+ tracepoint_synchronize_unregister();
list_for_each_entry_safe(filter_item, tmp, &filter_list, list) {
__free_filter(filter_item->filter);
list_del(&filter_item->list);
@@ -1648,7 +1636,7 @@ static int process_system_preds(struct trace_subsystem_dir *dir,
kfree(filter);
/* If any call succeeded, we still need to sync */
if (!fail)
- synchronize_sched();
+ tracepoint_synchronize_unregister();
list_for_each_entry_safe(filter_item, tmp, &filter_list, list) {
__free_filter(filter_item->filter);
list_del(&filter_item->list);
@@ -1790,7 +1778,7 @@ int apply_event_filter(struct trace_event_file *file, char *filter_string)
event_clear_filter(file);
/* Make sure the filter is not being used */
- synchronize_sched();
+ tracepoint_synchronize_unregister();
__free_filter(filter);
return 0;
@@ -1817,7 +1805,7 @@ int apply_event_filter(struct trace_event_file *file, char *filter_string)
if (tmp) {
/* Make sure the call is done with the filter */
- synchronize_sched();
+ tracepoint_synchronize_unregister();
__free_filter(tmp);
}
}
@@ -1847,7 +1835,7 @@ int apply_subsystem_event_filter(struct trace_subsystem_dir *dir,
filter = system->filter;
system->filter = NULL;
/* Ensure all filters are no longer used */
- synchronize_sched();
+ tracepoint_synchronize_unregister();
filter_free_subsystem_filters(dir, tr);
__free_filter(filter);
goto out_unlock;
diff --git a/kernel/trace/trace_events_filter_test.h b/kernel/trace/trace_events_filter_test.h
index 39d7ef4f57cb..e651dfbd345e 100644
--- a/kernel/trace/trace_events_filter_test.h
+++ b/kernel/trace/trace_events_filter_test.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+// SPDX-License-Identifier: GPL-2.0
#undef TRACE_SYSTEM
#define TRACE_SYSTEM test
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index aae18af94c94..85f6b01431c7 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -1,16 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* trace_events_hist - trace event hist triggers
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program 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 General Public License for more details.
- *
* Copyright (C) 2015 Tom Zanussi <tom.zanussi@linux.intel.com>
*/
@@ -5141,7 +5132,7 @@ static void hist_clear(struct event_trigger_data *data)
if (data->name)
pause_named_trigger(data);
- synchronize_sched();
+ tracepoint_synchronize_unregister();
tracing_map_clear(hist_data->map);
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index d18249683682..2152d1e530cb 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -1,20 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* trace_events_trigger - trace event triggers
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program 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 General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
* Copyright (C) 2013 Tom Zanussi <tom.zanussi@linux.intel.com>
*/
@@ -34,7 +21,9 @@ void trigger_data_free(struct event_trigger_data *data)
if (data->cmd_ops->set_filter)
data->cmd_ops->set_filter(NULL, data, NULL);
- synchronize_sched(); /* make sure current triggers exit before free */
+ /* make sure current triggers exit before free */
+ tracepoint_synchronize_unregister();
+
kfree(data);
}
@@ -579,9 +568,9 @@ out:
* Usually used directly as the @unreg method in event command
* implementations.
*/
-void unregister_trigger(char *glob, struct event_trigger_ops *ops,
- struct event_trigger_data *test,
- struct trace_event_file *file)
+static void unregister_trigger(char *glob, struct event_trigger_ops *ops,
+ struct event_trigger_data *test,
+ struct trace_event_file *file)
{
struct event_trigger_data *data;
bool unregistered = false;
@@ -679,6 +668,8 @@ event_trigger_callback(struct event_command *cmd_ops,
goto out_free;
out_reg:
+ /* Up the trigger_data count to make sure reg doesn't free it on failure */
+ event_trigger_init(trigger_ops, trigger_data);
ret = cmd_ops->reg(glob, trigger_ops, trigger_data, file);
/*
* The above returns on success the # of functions enabled,
@@ -686,11 +677,13 @@ event_trigger_callback(struct event_command *cmd_ops,
* Consider no functions a failure too.
*/
if (!ret) {
+ cmd_ops->unreg(glob, trigger_ops, trigger_data, file);
ret = -ENOENT;
- goto out_free;
- } else if (ret < 0)
- goto out_free;
- ret = 0;
+ } else if (ret > 0)
+ ret = 0;
+
+ /* Down the counter of trigger_data or free it if not used anymore */
+ event_trigger_free(trigger_ops, trigger_data);
out:
return ret;
@@ -748,7 +741,7 @@ int set_trigger_filter(char *filter_str,
if (tmp) {
/* Make sure the call is done with the filter */
- synchronize_sched();
+ tracepoint_synchronize_unregister();
free_event_filter(tmp);
}
@@ -1416,6 +1409,9 @@ int event_enable_trigger_func(struct event_command *cmd_ops,
goto out;
}
+ /* Up the trigger_data count to make sure nothing frees it on failure */
+ event_trigger_init(trigger_ops, trigger_data);
+
if (trigger) {
number = strsep(&trigger, ":");
@@ -1466,6 +1462,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops,
goto out_disable;
/* Just return zero, not the number of enabled functions */
ret = 0;
+ event_trigger_free(trigger_ops, trigger_data);
out:
return ret;
@@ -1476,7 +1473,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops,
out_free:
if (cmd_ops->set_filter)
cmd_ops->set_filter(NULL, trigger_data, NULL);
- kfree(trigger_data);
+ event_trigger_free(trigger_ops, trigger_data);
kfree(enable_data);
goto out;
}
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index d7c8e4ec3d9d..1e6db9cbe4dc 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* trace_hwlatdetect.c - A simple Hardware Latency detector.
*
@@ -35,9 +36,6 @@
*
* Includes useful feedback from Clark Williams <clark@redhat.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.
*/
#include <linux/kthread.h>
#include <linux/tracefs.h>
@@ -354,6 +352,9 @@ static int start_kthread(struct trace_array *tr)
struct task_struct *kthread;
int next_cpu;
+ if (WARN_ON(hwlat_kthread))
+ return 0;
+
/* Just pick the first CPU on first iteration */
current_mask = &save_cpumask;
get_online_cpus();
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 03ecb4465ee4..b7357f9f82a3 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* trace irqs off critical timings
*
@@ -16,7 +17,6 @@
#include "trace.h"
-#define CREATE_TRACE_POINTS
#include <trace/events/preemptirq.h>
#if defined(CONFIG_IRQSOFF_TRACER) || defined(CONFIG_PREEMPT_TRACER)
@@ -41,12 +41,12 @@ static int start_irqsoff_tracer(struct trace_array *tr, int graph);
#ifdef CONFIG_PREEMPT_TRACER
static inline int
-preempt_trace(void)
+preempt_trace(int pc)
{
- return ((trace_type & TRACER_PREEMPT_OFF) && preempt_count());
+ return ((trace_type & TRACER_PREEMPT_OFF) && pc);
}
#else
-# define preempt_trace() (0)
+# define preempt_trace(pc) (0)
#endif
#ifdef CONFIG_IRQSOFF_TRACER
@@ -367,7 +367,7 @@ out:
}
static inline void
-start_critical_timing(unsigned long ip, unsigned long parent_ip)
+start_critical_timing(unsigned long ip, unsigned long parent_ip, int pc)
{
int cpu;
struct trace_array *tr = irqsoff_trace;
@@ -395,7 +395,7 @@ start_critical_timing(unsigned long ip, unsigned long parent_ip)
local_save_flags(flags);
- __trace_function(tr, ip, parent_ip, flags, preempt_count());
+ __trace_function(tr, ip, parent_ip, flags, pc);
per_cpu(tracing_cpu, cpu) = 1;
@@ -403,7 +403,7 @@ start_critical_timing(unsigned long ip, unsigned long parent_ip)
}
static inline void
-stop_critical_timing(unsigned long ip, unsigned long parent_ip)
+stop_critical_timing(unsigned long ip, unsigned long parent_ip, int pc)
{
int cpu;
struct trace_array *tr = irqsoff_trace;
@@ -429,7 +429,7 @@ stop_critical_timing(unsigned long ip, unsigned long parent_ip)
atomic_inc(&data->disabled);
local_save_flags(flags);
- __trace_function(tr, ip, parent_ip, flags, preempt_count());
+ __trace_function(tr, ip, parent_ip, flags, pc);
check_critical_timing(tr, data, parent_ip ? : ip, cpu);
data->critical_start = 0;
atomic_dec(&data->disabled);
@@ -438,77 +438,21 @@ stop_critical_timing(unsigned long ip, unsigned long parent_ip)
/* start and stop critical timings used to for stoppage (in idle) */
void start_critical_timings(void)
{
- if (preempt_trace() || irq_trace())
- start_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
+ int pc = preempt_count();
+
+ if (preempt_trace(pc) || irq_trace())
+ start_critical_timing(CALLER_ADDR0, CALLER_ADDR1, pc);
}
EXPORT_SYMBOL_GPL(start_critical_timings);
void stop_critical_timings(void)
{
- if (preempt_trace() || irq_trace())
- stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
-}
-EXPORT_SYMBOL_GPL(stop_critical_timings);
-
-#ifdef CONFIG_IRQSOFF_TRACER
-#ifdef CONFIG_PROVE_LOCKING
-void time_hardirqs_on(unsigned long a0, unsigned long a1)
-{
- if (!preempt_trace() && irq_trace())
- stop_critical_timing(a0, a1);
-}
-
-void time_hardirqs_off(unsigned long a0, unsigned long a1)
-{
- if (!preempt_trace() && irq_trace())
- start_critical_timing(a0, a1);
-}
-
-#else /* !CONFIG_PROVE_LOCKING */
-
-/*
- * We are only interested in hardirq on/off events:
- */
-static inline void tracer_hardirqs_on(void)
-{
- if (!preempt_trace() && irq_trace())
- stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
-}
+ int pc = preempt_count();
-static inline void tracer_hardirqs_off(void)
-{
- if (!preempt_trace() && irq_trace())
- start_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
-}
-
-static inline void tracer_hardirqs_on_caller(unsigned long caller_addr)
-{
- if (!preempt_trace() && irq_trace())
- stop_critical_timing(CALLER_ADDR0, caller_addr);
-}
-
-static inline void tracer_hardirqs_off_caller(unsigned long caller_addr)
-{
- if (!preempt_trace() && irq_trace())
- start_critical_timing(CALLER_ADDR0, caller_addr);
-}
-
-#endif /* CONFIG_PROVE_LOCKING */
-#endif /* CONFIG_IRQSOFF_TRACER */
-
-#ifdef CONFIG_PREEMPT_TRACER
-static inline void tracer_preempt_on(unsigned long a0, unsigned long a1)
-{
- if (preempt_trace() && !irq_trace())
- stop_critical_timing(a0, a1);
-}
-
-static inline void tracer_preempt_off(unsigned long a0, unsigned long a1)
-{
- if (preempt_trace() && !irq_trace())
- start_critical_timing(a0, a1);
+ if (preempt_trace(pc) || irq_trace())
+ stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1, pc);
}
-#endif /* CONFIG_PREEMPT_TRACER */
+EXPORT_SYMBOL_GPL(stop_critical_timings);
#ifdef CONFIG_FUNCTION_TRACER
static bool function_enabled;
@@ -634,7 +578,7 @@ static int __irqsoff_tracer_init(struct trace_array *tr)
return 0;
}
-static void irqsoff_tracer_reset(struct trace_array *tr)
+static void __irqsoff_tracer_reset(struct trace_array *tr)
{
int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT;
int overwrite_flag = save_flags & TRACE_ITER_OVERWRITE;
@@ -659,12 +603,37 @@ static void irqsoff_tracer_stop(struct trace_array *tr)
}
#ifdef CONFIG_IRQSOFF_TRACER
+/*
+ * We are only interested in hardirq on/off events:
+ */
+void tracer_hardirqs_on(unsigned long a0, unsigned long a1)
+{
+ unsigned int pc = preempt_count();
+
+ if (!preempt_trace(pc) && irq_trace())
+ stop_critical_timing(a0, a1, pc);
+}
+
+void tracer_hardirqs_off(unsigned long a0, unsigned long a1)
+{
+ unsigned int pc = preempt_count();
+
+ if (!preempt_trace(pc) && irq_trace())
+ start_critical_timing(a0, a1, pc);
+}
+
static int irqsoff_tracer_init(struct trace_array *tr)
{
trace_type = TRACER_IRQS_OFF;
return __irqsoff_tracer_init(tr);
}
+
+static void irqsoff_tracer_reset(struct trace_array *tr)
+{
+ __irqsoff_tracer_reset(tr);
+}
+
static struct tracer irqsoff_tracer __read_mostly =
{
.name = "irqsoff",
@@ -684,12 +653,25 @@ static struct tracer irqsoff_tracer __read_mostly =
.allow_instances = true,
.use_max_tr = true,
};
-# define register_irqsoff(trace) register_tracer(&trace)
-#else
-# define register_irqsoff(trace) do { } while (0)
-#endif
+#endif /* CONFIG_IRQSOFF_TRACER */
#ifdef CONFIG_PREEMPT_TRACER
+void tracer_preempt_on(unsigned long a0, unsigned long a1)
+{
+ int pc = preempt_count();
+
+ if (preempt_trace(pc) && !irq_trace())
+ stop_critical_timing(a0, a1, pc);
+}
+
+void tracer_preempt_off(unsigned long a0, unsigned long a1)
+{
+ int pc = preempt_count();
+
+ if (preempt_trace(pc) && !irq_trace())
+ start_critical_timing(a0, a1, pc);
+}
+
static int preemptoff_tracer_init(struct trace_array *tr)
{
trace_type = TRACER_PREEMPT_OFF;
@@ -697,11 +679,16 @@ static int preemptoff_tracer_init(struct trace_array *tr)
return __irqsoff_tracer_init(tr);
}
+static void preemptoff_tracer_reset(struct trace_array *tr)
+{
+ __irqsoff_tracer_reset(tr);
+}
+
static struct tracer preemptoff_tracer __read_mostly =
{
.name = "preemptoff",
.init = preemptoff_tracer_init,
- .reset = irqsoff_tracer_reset,
+ .reset = preemptoff_tracer_reset,
.start = irqsoff_tracer_start,
.stop = irqsoff_tracer_stop,
.print_max = true,
@@ -716,13 +703,9 @@ static struct tracer preemptoff_tracer __read_mostly =
.allow_instances = true,
.use_max_tr = true,
};
-# define register_preemptoff(trace) register_tracer(&trace)
-#else
-# define register_preemptoff(trace) do { } while (0)
-#endif
+#endif /* CONFIG_PREEMPT_TRACER */
-#if defined(CONFIG_IRQSOFF_TRACER) && \
- defined(CONFIG_PREEMPT_TRACER)
+#if defined(CONFIG_IRQSOFF_TRACER) && defined(CONFIG_PREEMPT_TRACER)
static int preemptirqsoff_tracer_init(struct trace_array *tr)
{
@@ -731,11 +714,16 @@ static int preemptirqsoff_tracer_init(struct trace_array *tr)
return __irqsoff_tracer_init(tr);
}
+static void preemptirqsoff_tracer_reset(struct trace_array *tr)
+{
+ __irqsoff_tracer_reset(tr);
+}
+
static struct tracer preemptirqsoff_tracer __read_mostly =
{
.name = "preemptirqsoff",
.init = preemptirqsoff_tracer_init,
- .reset = irqsoff_tracer_reset,
+ .reset = preemptirqsoff_tracer_reset,
.start = irqsoff_tracer_start,
.stop = irqsoff_tracer_stop,
.print_max = true,
@@ -750,115 +738,21 @@ static struct tracer preemptirqsoff_tracer __read_mostly =
.allow_instances = true,
.use_max_tr = true,
};
-
-# define register_preemptirqsoff(trace) register_tracer(&trace)
-#else
-# define register_preemptirqsoff(trace) do { } while (0)
#endif
__init static int init_irqsoff_tracer(void)
{
- register_irqsoff(irqsoff_tracer);
- register_preemptoff(preemptoff_tracer);
- register_preemptirqsoff(preemptirqsoff_tracer);
-
- return 0;
-}
-core_initcall(init_irqsoff_tracer);
-#endif /* IRQSOFF_TRACER || PREEMPTOFF_TRACER */
-
-#ifndef CONFIG_IRQSOFF_TRACER
-static inline void tracer_hardirqs_on(void) { }
-static inline void tracer_hardirqs_off(void) { }
-static inline void tracer_hardirqs_on_caller(unsigned long caller_addr) { }
-static inline void tracer_hardirqs_off_caller(unsigned long caller_addr) { }
+#ifdef CONFIG_IRQSOFF_TRACER
+ register_tracer(&irqsoff_tracer);
#endif
-
-#ifndef CONFIG_PREEMPT_TRACER
-static inline void tracer_preempt_on(unsigned long a0, unsigned long a1) { }
-static inline void tracer_preempt_off(unsigned long a0, unsigned long a1) { }
+#ifdef CONFIG_PREEMPT_TRACER
+ register_tracer(&preemptoff_tracer);
#endif
-
-#if defined(CONFIG_TRACE_IRQFLAGS) && !defined(CONFIG_PROVE_LOCKING)
-/* Per-cpu variable to prevent redundant calls when IRQs already off */
-static DEFINE_PER_CPU(int, tracing_irq_cpu);
-
-void trace_hardirqs_on(void)
-{
- if (!this_cpu_read(tracing_irq_cpu))
- return;
-
- trace_irq_enable_rcuidle(CALLER_ADDR0, CALLER_ADDR1);
- tracer_hardirqs_on();
-
- this_cpu_write(tracing_irq_cpu, 0);
-}
-EXPORT_SYMBOL(trace_hardirqs_on);
-
-void trace_hardirqs_off(void)
-{
- if (this_cpu_read(tracing_irq_cpu))
- return;
-
- this_cpu_write(tracing_irq_cpu, 1);
-
- trace_irq_disable_rcuidle(CALLER_ADDR0, CALLER_ADDR1);
- tracer_hardirqs_off();
-}
-EXPORT_SYMBOL(trace_hardirqs_off);
-
-__visible void trace_hardirqs_on_caller(unsigned long caller_addr)
-{
- if (!this_cpu_read(tracing_irq_cpu))
- return;
-
- trace_irq_enable_rcuidle(CALLER_ADDR0, caller_addr);
- tracer_hardirqs_on_caller(caller_addr);
-
- this_cpu_write(tracing_irq_cpu, 0);
-}
-EXPORT_SYMBOL(trace_hardirqs_on_caller);
-
-__visible void trace_hardirqs_off_caller(unsigned long caller_addr)
-{
- if (this_cpu_read(tracing_irq_cpu))
- return;
-
- this_cpu_write(tracing_irq_cpu, 1);
-
- trace_irq_disable_rcuidle(CALLER_ADDR0, caller_addr);
- tracer_hardirqs_off_caller(caller_addr);
-}
-EXPORT_SYMBOL(trace_hardirqs_off_caller);
-
-/*
- * Stubs:
- */
-
-void trace_softirqs_on(unsigned long ip)
-{
-}
-
-void trace_softirqs_off(unsigned long ip)
-{
-}
-
-inline void print_irqtrace_events(struct task_struct *curr)
-{
-}
+#if defined(CONFIG_IRQSOFF_TRACER) && defined(CONFIG_PREEMPT_TRACER)
+ register_tracer(&preemptirqsoff_tracer);
#endif
-#if defined(CONFIG_PREEMPT_TRACER) || \
- (defined(CONFIG_DEBUG_PREEMPT) && defined(CONFIG_PREEMPTIRQ_EVENTS))
-void trace_preempt_on(unsigned long a0, unsigned long a1)
-{
- trace_preempt_enable_rcuidle(a0, a1);
- tracer_preempt_on(a0, a1);
-}
-
-void trace_preempt_off(unsigned long a0, unsigned long a1)
-{
- trace_preempt_disable_rcuidle(a0, a1);
- tracer_preempt_off(a0, a1);
+ return 0;
}
-#endif
+core_initcall(init_irqsoff_tracer);
+#endif /* IRQSOFF_TRACER || PREEMPTOFF_TRACER */
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 21f718472942..2bfb2bbeb3d2 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1,20 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Kprobes-based tracing events
*
* Created by Masami Hiramatsu <mhiramat@redhat.com>
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program 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 General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#define pr_fmt(fmt) "trace_kprobe: " fmt
@@ -23,6 +12,7 @@
#include <linux/rculist.h>
#include <linux/error-injection.h>
+#include "trace_kprobe_selftest.h"
#include "trace_probe.h"
#define KPROBE_EVENT_SYSTEM "kprobes"
@@ -87,6 +77,23 @@ static nokprobe_inline unsigned long trace_kprobe_nhit(struct trace_kprobe *tk)
return nhit;
}
+/* Return 0 if it fails to find the symbol address */
+static nokprobe_inline
+unsigned long trace_kprobe_address(struct trace_kprobe *tk)
+{
+ unsigned long addr;
+
+ if (tk->symbol) {
+ addr = (unsigned long)
+ kallsyms_lookup_name(trace_kprobe_symbol(tk));
+ if (addr)
+ addr += tk->rp.kp.offset;
+ } else {
+ addr = (unsigned long)tk->rp.kp.addr;
+ }
+ return addr;
+}
+
bool trace_kprobe_on_func_entry(struct trace_event_call *call)
{
struct trace_kprobe *tk = (struct trace_kprobe *)call->data;
@@ -99,16 +106,8 @@ bool trace_kprobe_on_func_entry(struct trace_event_call *call)
bool trace_kprobe_error_injectable(struct trace_event_call *call)
{
struct trace_kprobe *tk = (struct trace_kprobe *)call->data;
- unsigned long addr;
- if (tk->symbol) {
- addr = (unsigned long)
- kallsyms_lookup_name(trace_kprobe_symbol(tk));
- addr += tk->rp.kp.offset;
- } else {
- addr = (unsigned long)tk->rp.kp.addr;
- }
- return within_error_injection_list(addr);
+ return within_error_injection_list(trace_kprobe_address(tk));
}
static int register_kprobe_event(struct trace_kprobe *tk);
@@ -393,6 +392,20 @@ static struct trace_kprobe *find_trace_kprobe(const char *event,
return NULL;
}
+static inline int __enable_trace_kprobe(struct trace_kprobe *tk)
+{
+ int ret = 0;
+
+ if (trace_probe_is_registered(&tk->tp) && !trace_kprobe_has_gone(tk)) {
+ if (trace_kprobe_is_return(tk))
+ ret = enable_kretprobe(&tk->rp);
+ else
+ ret = enable_kprobe(&tk->rp.kp);
+ }
+
+ return ret;
+}
+
/*
* Enable trace_probe
* if the file is NULL, enable "perf" handler, or enable "trace" handler.
@@ -400,11 +413,10 @@ static struct trace_kprobe *find_trace_kprobe(const char *event,
static int
enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
{
+ struct event_file_link *link;
int ret = 0;
if (file) {
- struct event_file_link *link;
-
link = kmalloc(sizeof(*link), GFP_KERNEL);
if (!link) {
ret = -ENOMEM;
@@ -415,14 +427,18 @@ enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
list_add_tail_rcu(&link->list, &tk->tp.files);
tk->tp.flags |= TP_FLAG_TRACE;
- } else
- tk->tp.flags |= TP_FLAG_PROFILE;
+ ret = __enable_trace_kprobe(tk);
+ if (ret) {
+ list_del_rcu(&link->list);
+ kfree(link);
+ tk->tp.flags &= ~TP_FLAG_TRACE;
+ }
- if (trace_probe_is_registered(&tk->tp) && !trace_kprobe_has_gone(tk)) {
- if (trace_kprobe_is_return(tk))
- ret = enable_kretprobe(&tk->rp);
- else
- ret = enable_kprobe(&tk->rp.kp);
+ } else {
+ tk->tp.flags |= TP_FLAG_PROFILE;
+ ret = __enable_trace_kprobe(tk);
+ if (ret)
+ tk->tp.flags &= ~TP_FLAG_PROFILE;
}
out:
return ret;
@@ -487,6 +503,22 @@ disable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
return ret;
}
+#if defined(CONFIG_KPROBES_ON_FTRACE) && \
+ !defined(CONFIG_KPROBE_EVENTS_ON_NOTRACE)
+static bool within_notrace_func(struct trace_kprobe *tk)
+{
+ unsigned long offset, size, addr;
+
+ addr = trace_kprobe_address(tk);
+ if (!addr || !kallsyms_lookup_size_offset(addr, &size, &offset))
+ return false;
+
+ return !ftrace_location_range(addr - offset, addr - offset + size);
+}
+#else
+#define within_notrace_func(tk) (false)
+#endif
+
/* Internal register function - just handle k*probes and flags */
static int __register_trace_kprobe(struct trace_kprobe *tk)
{
@@ -495,6 +527,12 @@ static int __register_trace_kprobe(struct trace_kprobe *tk)
if (trace_probe_is_registered(&tk->tp))
return -EINVAL;
+ if (within_notrace_func(tk)) {
+ pr_warn("Could not probe notrace function %s\n",
+ trace_kprobe_symbol(tk));
+ return -EINVAL;
+ }
+
for (i = 0; i < tk->tp.nr_args; i++)
traceprobe_update_arg(&tk->tp.args[i]);
@@ -1217,16 +1255,11 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
/*
* We need to check and see if we modified the pc of the
- * pt_regs, and if so clear the kprobe and return 1 so that we
- * don't do the single stepping.
- * The ftrace kprobe handler leaves it up to us to re-enable
- * preemption here before returning if we've modified the ip.
+ * pt_regs, and if so return 1 so that we don't do the
+ * single stepping.
*/
- if (orig_ip != instruction_pointer(regs)) {
- reset_current_kprobe();
- preempt_enable_no_resched();
+ if (orig_ip != instruction_pointer(regs))
return 1;
- }
if (!ret)
return 0;
}
@@ -1541,17 +1574,6 @@ fs_initcall(init_kprobe_trace);
#ifdef CONFIG_FTRACE_STARTUP_TEST
-/*
- * The "__used" keeps gcc from removing the function symbol
- * from the kallsyms table. 'noinline' makes sure that there
- * isn't an inlined version used by the test method below
- */
-static __used __init noinline int
-kprobe_trace_selftest_target(int a1, int a2, int a3, int a4, int a5, int a6)
-{
- return a1 + a2 + a3 + a4 + a5 + a6;
-}
-
static __init struct trace_event_file *
find_trace_probe_file(struct trace_kprobe *tk, struct trace_array *tr)
{
diff --git a/kernel/trace/trace_kprobe_selftest.c b/kernel/trace/trace_kprobe_selftest.c
new file mode 100644
index 000000000000..16548ee4c8c6
--- /dev/null
+++ b/kernel/trace/trace_kprobe_selftest.c
@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Function used during the kprobe self test. This function is in a separate
+ * compile unit so it can be compile with CC_FLAGS_FTRACE to ensure that it
+ * can be probed by the selftests.
+ */
+int kprobe_trace_selftest_target(int a1, int a2, int a3, int a4, int a5, int a6)
+{
+ return a1 + a2 + a3 + a4 + a5 + a6;
+}
diff --git a/kernel/trace/trace_kprobe_selftest.h b/kernel/trace/trace_kprobe_selftest.h
new file mode 100644
index 000000000000..c4fc7268ba7c
--- /dev/null
+++ b/kernel/trace/trace_kprobe_selftest.h
@@ -0,0 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Function used during the kprobe self test. This function is in a separate
+ * compile unit so it can be compile with CC_FLAGS_FTRACE to ensure that it
+ * can be probed by the selftests.
+ */
+int kprobe_trace_selftest_target(int a1, int a2, int a3, int a4, int a5, int a6);
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 1c8e30fda46a..6e6cc64faa38 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* trace_output.c
*
diff --git a/kernel/trace/trace_output.h b/kernel/trace/trace_output.h
index dbba03ed96de..2f742b74e7e6 100644
--- a/kernel/trace/trace_output.h
+++ b/kernel/trace/trace_output.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+// SPDX-License-Identifier: GPL-2.0
#ifndef __TRACE_EVENTS_H
#define __TRACE_EVENTS_H
diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c
new file mode 100644
index 000000000000..71f553cceb3c
--- /dev/null
+++ b/kernel/trace/trace_preemptirq.c
@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * preemptoff and irqoff tracepoints
+ *
+ * Copyright (C) Joel Fernandes (Google) <joel@joelfernandes.org>
+ */
+
+#include <linux/kallsyms.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/ftrace.h>
+#include "trace.h"
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/preemptirq.h>
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+/* Per-cpu variable to prevent redundant calls when IRQs already off */
+static DEFINE_PER_CPU(int, tracing_irq_cpu);
+
+void trace_hardirqs_on(void)
+{
+ if (this_cpu_read(tracing_irq_cpu)) {
+ if (!in_nmi())
+ trace_irq_enable_rcuidle(CALLER_ADDR0, CALLER_ADDR1);
+ tracer_hardirqs_on(CALLER_ADDR0, CALLER_ADDR1);
+ this_cpu_write(tracing_irq_cpu, 0);
+ }
+
+ lockdep_hardirqs_on(CALLER_ADDR0);
+}
+EXPORT_SYMBOL(trace_hardirqs_on);
+
+void trace_hardirqs_off(void)
+{
+ if (!this_cpu_read(tracing_irq_cpu)) {
+ this_cpu_write(tracing_irq_cpu, 1);
+ tracer_hardirqs_off(CALLER_ADDR0, CALLER_ADDR1);
+ if (!in_nmi())
+ trace_irq_disable_rcuidle(CALLER_ADDR0, CALLER_ADDR1);
+ }
+
+ lockdep_hardirqs_off(CALLER_ADDR0);
+}
+EXPORT_SYMBOL(trace_hardirqs_off);
+
+__visible void trace_hardirqs_on_caller(unsigned long caller_addr)
+{
+ if (this_cpu_read(tracing_irq_cpu)) {
+ if (!in_nmi())
+ trace_irq_enable_rcuidle(CALLER_ADDR0, caller_addr);
+ tracer_hardirqs_on(CALLER_ADDR0, caller_addr);
+ this_cpu_write(tracing_irq_cpu, 0);
+ }
+
+ lockdep_hardirqs_on(CALLER_ADDR0);
+}
+EXPORT_SYMBOL(trace_hardirqs_on_caller);
+
+__visible void trace_hardirqs_off_caller(unsigned long caller_addr)
+{
+ if (!this_cpu_read(tracing_irq_cpu)) {
+ this_cpu_write(tracing_irq_cpu, 1);
+ tracer_hardirqs_off(CALLER_ADDR0, caller_addr);
+ if (!in_nmi())
+ trace_irq_disable_rcuidle(CALLER_ADDR0, caller_addr);
+ }
+
+ lockdep_hardirqs_off(CALLER_ADDR0);
+}
+EXPORT_SYMBOL(trace_hardirqs_off_caller);
+#endif /* CONFIG_TRACE_IRQFLAGS */
+
+#ifdef CONFIG_TRACE_PREEMPT_TOGGLE
+
+void trace_preempt_on(unsigned long a0, unsigned long a1)
+{
+ if (!in_nmi())
+ trace_preempt_enable_rcuidle(a0, a1);
+ tracer_preempt_on(a0, a1);
+}
+
+void trace_preempt_off(unsigned long a0, unsigned long a1)
+{
+ if (!in_nmi())
+ trace_preempt_disable_rcuidle(a0, a1);
+ tracer_preempt_off(a0, a1);
+}
+#endif
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index 50f44b7b2b32..b0875b327f5c 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* trace binary printk
*
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index daf54bda4dc8..e99c3ce7aa65 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -1,19 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Common code for probe-based Dynamic events.
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program 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 General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- *
* This code was copied from kernel/trace/trace_kprobe.c written by
* Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
*
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 75daff22ccea..5f52668e165d 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -1,19 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Common header file for probe-based Dynamic events.
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program 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 General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- *
* This code was copied from kernel/trace/trace_kprobe.h written by
* Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
*
diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c
index e694c9f9efa4..6b1c562ffdaf 100644
--- a/kernel/trace/trace_seq.c
+++ b/kernel/trace/trace_seq.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* trace_seq.c
*
diff --git a/kernel/trace/trace_stat.h b/kernel/trace/trace_stat.h
index 76d30b4ebe83..8786d17caf49 100644
--- a/kernel/trace/trace_stat.h
+++ b/kernel/trace/trace_stat.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+// SPDX-License-Identifier: GPL-2.0
#ifndef __TRACE_STAT_H
#define __TRACE_STAT_H
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index bf89a51e740d..e696667da29a 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1,19 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* uprobes-based tracing events
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program 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 General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- *
* Copyright (C) IBM Corporation, 2010-2012
* Author: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
*/
@@ -952,7 +940,7 @@ probe_event_disable(struct trace_uprobe *tu, struct trace_event_file *file)
list_del_rcu(&link->list);
/* synchronize with u{,ret}probe_trace_func */
- synchronize_sched();
+ synchronize_rcu();
kfree(link);
if (!list_empty(&tu->tp.files))
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index 752d8042bad4..9a1c22310323 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -1,16 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* tracing_map - lock-free map for tracing
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program 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 General Public License for more details.
- *
* Copyright (C) 2015 Tom Zanussi <tom.zanussi@linux.intel.com>
*
* tracing_map implementation inspired by lock-free map algorithms
diff --git a/kernel/trace/tracing_map.h b/kernel/trace/tracing_map.h
index 053eb92b2d31..a6de61fc22de 100644
--- a/kernel/trace/tracing_map.h
+++ b/kernel/trace/tracing_map.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+// SPDX-License-Identifier: GPL-2.0
#ifndef __TRACING_MAP_H
#define __TRACING_MAP_H
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 6dc6356c3327..bf2c06ef9afc 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -31,6 +31,9 @@
extern struct tracepoint * const __start___tracepoints_ptrs[];
extern struct tracepoint * const __stop___tracepoints_ptrs[];
+DEFINE_SRCU(tracepoint_srcu);
+EXPORT_SYMBOL_GPL(tracepoint_srcu);
+
/* Set to 1 to enable tracepoint debug output */
static const int tracepoint_debug;
@@ -50,6 +53,9 @@ static LIST_HEAD(tracepoint_module_list);
*/
static DEFINE_MUTEX(tracepoints_mutex);
+static struct rcu_head *early_probes;
+static bool ok_to_free_tracepoints;
+
/*
* Note about RCU :
* It is used to delay the free of multiple probes array until a quiescent
@@ -67,16 +73,56 @@ static inline void *allocate_probes(int count)
return p == NULL ? NULL : p->probes;
}
-static void rcu_free_old_probes(struct rcu_head *head)
+static void srcu_free_old_probes(struct rcu_head *head)
{
kfree(container_of(head, struct tp_probes, rcu));
}
+static void rcu_free_old_probes(struct rcu_head *head)
+{
+ call_srcu(&tracepoint_srcu, head, srcu_free_old_probes);
+}
+
+static __init int release_early_probes(void)
+{
+ struct rcu_head *tmp;
+
+ ok_to_free_tracepoints = true;
+
+ while (early_probes) {
+ tmp = early_probes;
+ early_probes = tmp->next;
+ call_rcu_sched(tmp, rcu_free_old_probes);
+ }
+
+ return 0;
+}
+
+/* SRCU is initialized at core_initcall */
+postcore_initcall(release_early_probes);
+
static inline void release_probes(struct tracepoint_func *old)
{
if (old) {
struct tp_probes *tp_probes = container_of(old,
struct tp_probes, probes[0]);
+
+ /*
+ * We can't free probes if SRCU is not initialized yet.
+ * Postpone the freeing till after SRCU is initialized.
+ */
+ if (unlikely(!ok_to_free_tracepoints)) {
+ tp_probes->rcu.next = early_probes;
+ early_probes = &tp_probes->rcu;
+ return;
+ }
+
+ /*
+ * Tracepoint probes are protected by both sched RCU and SRCU,
+ * by calling the SRCU callback in the sched RCU callback we
+ * cover both cases. So let us chain the SRCU and sched RCU
+ * callbacks to wait for both grace periods.
+ */
call_rcu_sched(&tp_probes->rcu, rcu_free_old_probes);
}
}
@@ -325,6 +371,27 @@ int tracepoint_probe_unregister(struct tracepoint *tp, void *probe, void *data)
}
EXPORT_SYMBOL_GPL(tracepoint_probe_unregister);
+static void for_each_tracepoint_range(struct tracepoint * const *begin,
+ struct tracepoint * const *end,
+ void (*fct)(struct tracepoint *tp, void *priv),
+ void *priv)
+{
+ if (!begin)
+ return;
+
+ if (IS_ENABLED(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS)) {
+ const int *iter;
+
+ for (iter = (const int *)begin; iter < (const int *)end; iter++)
+ fct(offset_to_ptr(iter), priv);
+ } else {
+ struct tracepoint * const *iter;
+
+ for (iter = begin; iter < end; iter++)
+ fct(*iter, priv);
+ }
+}
+
#ifdef CONFIG_MODULES
bool trace_module_has_bad_taint(struct module *mod)
{
@@ -389,15 +456,9 @@ EXPORT_SYMBOL_GPL(unregister_tracepoint_module_notifier);
* Ensure the tracer unregistered the module's probes before the module
* teardown is performed. Prevents leaks of probe and data pointers.
*/
-static void tp_module_going_check_quiescent(struct tracepoint * const *begin,
- struct tracepoint * const *end)
+static void tp_module_going_check_quiescent(struct tracepoint *tp, void *priv)
{
- struct tracepoint * const *iter;
-
- if (!begin)
- return;
- for (iter = begin; iter < end; iter++)
- WARN_ON_ONCE((*iter)->funcs);
+ WARN_ON_ONCE(tp->funcs);
}
static int tracepoint_module_coming(struct module *mod)
@@ -448,8 +509,9 @@ static void tracepoint_module_going(struct module *mod)
* Called the going notifier before checking for
* quiescence.
*/
- tp_module_going_check_quiescent(mod->tracepoints_ptrs,
- mod->tracepoints_ptrs + mod->num_tracepoints);
+ for_each_tracepoint_range(mod->tracepoints_ptrs,
+ mod->tracepoints_ptrs + mod->num_tracepoints,
+ tp_module_going_check_quiescent, NULL);
break;
}
}
@@ -501,19 +563,6 @@ static __init int init_tracepoints(void)
__initcall(init_tracepoints);
#endif /* CONFIG_MODULES */
-static void for_each_tracepoint_range(struct tracepoint * const *begin,
- struct tracepoint * const *end,
- void (*fct)(struct tracepoint *tp, void *priv),
- void *priv)
-{
- struct tracepoint * const *iter;
-
- if (!begin)
- return;
- for (iter = begin; iter < end; iter++)
- fct(*iter, priv);
-}
-
/**
* for_each_kernel_tracepoint - iteration on all kernel tracepoints
* @fct: callback
diff --git a/kernel/user.c b/kernel/user.c
index 36288d840675..0df9b1640b2a 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -96,7 +96,7 @@ static DEFINE_SPINLOCK(uidhash_lock);
/* root_user.__count is 1, for init task cred */
struct user_struct root_user = {
- .__count = ATOMIC_INIT(1),
+ .__count = REFCOUNT_INIT(1),
.processes = ATOMIC_INIT(1),
.sigpending = ATOMIC_INIT(0),
.locked_shm = 0,
@@ -123,7 +123,7 @@ static struct user_struct *uid_hash_find(kuid_t uid, struct hlist_head *hashent)
hlist_for_each_entry(user, hashent, uidhash_node) {
if (uid_eq(user->uid, uid)) {
- atomic_inc(&user->__count);
+ refcount_inc(&user->__count);
return user;
}
}
@@ -169,11 +169,8 @@ void free_uid(struct user_struct *up)
if (!up)
return;
- local_irq_save(flags);
- if (atomic_dec_and_lock(&up->__count, &uidhash_lock))
+ if (refcount_dec_and_lock_irqsave(&up->__count, &uidhash_lock, &flags))
free_user(up, flags);
- else
- local_irq_restore(flags);
}
struct user_struct *alloc_uid(kuid_t uid)
@@ -191,7 +188,7 @@ struct user_struct *alloc_uid(kuid_t uid)
goto out_unlock;
new->uid = uid;
- atomic_set(&new->__count, 1);
+ refcount_set(&new->__count, 1);
ratelimit_state_init(&new->ratelimit, HZ, 100);
ratelimit_set_flags(&new->ratelimit, RATELIMIT_MSG_ON_RELEASE);
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 576d18045811..5470dce212c0 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -18,18 +18,14 @@
#include <linux/init.h>
#include <linux/module.h>
#include <linux/sysctl.h>
-#include <linux/smpboot.h>
-#include <linux/sched/rt.h>
-#include <uapi/linux/sched/types.h>
#include <linux/tick.h>
-#include <linux/workqueue.h>
#include <linux/sched/clock.h>
#include <linux/sched/debug.h>
#include <linux/sched/isolation.h>
+#include <linux/stop_machine.h>
#include <asm/irq_regs.h>
#include <linux/kvm_para.h>
-#include <linux/kthread.h>
static DEFINE_MUTEX(watchdog_mutex);
@@ -169,11 +165,10 @@ static void lockup_detector_update_enable(void)
unsigned int __read_mostly softlockup_panic =
CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
-static bool softlockup_threads_initialized __read_mostly;
+static bool softlockup_initialized __read_mostly;
static u64 __read_mostly sample_period;
static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
-static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog);
static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer);
static DEFINE_PER_CPU(bool, softlockup_touch_sync);
static DEFINE_PER_CPU(bool, soft_watchdog_warn);
@@ -335,6 +330,27 @@ static void watchdog_interrupt_count(void)
__this_cpu_inc(hrtimer_interrupts);
}
+static DEFINE_PER_CPU(struct completion, softlockup_completion);
+static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work);
+
+/*
+ * The watchdog thread function - touches the timestamp.
+ *
+ * It only runs once every sample_period seconds (4 seconds by
+ * default) to reset the softlockup timestamp. If this gets delayed
+ * for more than 2*watchdog_thresh seconds then the debug-printout
+ * triggers in watchdog_timer_fn().
+ */
+static int softlockup_fn(void *data)
+{
+ __this_cpu_write(soft_lockup_hrtimer_cnt,
+ __this_cpu_read(hrtimer_interrupts));
+ __touch_watchdog();
+ complete(this_cpu_ptr(&softlockup_completion));
+
+ return 0;
+}
+
/* watchdog kicker functions */
static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
{
@@ -350,7 +366,12 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
watchdog_interrupt_count();
/* kick the softlockup detector */
- wake_up_process(__this_cpu_read(softlockup_watchdog));
+ if (completion_done(this_cpu_ptr(&softlockup_completion))) {
+ reinit_completion(this_cpu_ptr(&softlockup_completion));
+ stop_one_cpu_nowait(smp_processor_id(),
+ softlockup_fn, NULL,
+ this_cpu_ptr(&softlockup_stop_work));
+ }
/* .. and repeat */
hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period));
@@ -448,16 +469,15 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
return HRTIMER_RESTART;
}
-static void watchdog_set_prio(unsigned int policy, unsigned int prio)
-{
- struct sched_param param = { .sched_priority = prio };
-
- sched_setscheduler(current, policy, &param);
-}
-
static void watchdog_enable(unsigned int cpu)
{
struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer);
+ struct completion *done = this_cpu_ptr(&softlockup_completion);
+
+ WARN_ON_ONCE(cpu != smp_processor_id());
+
+ init_completion(done);
+ complete(done);
/*
* Start the timer first to prevent the NMI watchdog triggering
@@ -473,15 +493,14 @@ static void watchdog_enable(unsigned int cpu)
/* Enable the perf event */
if (watchdog_enabled & NMI_WATCHDOG_ENABLED)
watchdog_nmi_enable(cpu);
-
- watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1);
}
static void watchdog_disable(unsigned int cpu)
{
struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer);
- watchdog_set_prio(SCHED_NORMAL, 0);
+ WARN_ON_ONCE(cpu != smp_processor_id());
+
/*
* Disable the perf event first. That prevents that a large delay
* between disabling the timer and disabling the perf event causes
@@ -489,79 +508,66 @@ static void watchdog_disable(unsigned int cpu)
*/
watchdog_nmi_disable(cpu);
hrtimer_cancel(hrtimer);
+ wait_for_completion(this_cpu_ptr(&softlockup_completion));
}
-static void watchdog_cleanup(unsigned int cpu, bool online)
+static int softlockup_stop_fn(void *data)
{
- watchdog_disable(cpu);
+ watchdog_disable(smp_processor_id());
+ return 0;
}
-static int watchdog_should_run(unsigned int cpu)
+static void softlockup_stop_all(void)
{
- return __this_cpu_read(hrtimer_interrupts) !=
- __this_cpu_read(soft_lockup_hrtimer_cnt);
+ int cpu;
+
+ if (!softlockup_initialized)
+ return;
+
+ for_each_cpu(cpu, &watchdog_allowed_mask)
+ smp_call_on_cpu(cpu, softlockup_stop_fn, NULL, false);
+
+ cpumask_clear(&watchdog_allowed_mask);
}
-/*
- * The watchdog thread function - touches the timestamp.
- *
- * It only runs once every sample_period seconds (4 seconds by
- * default) to reset the softlockup timestamp. If this gets delayed
- * for more than 2*watchdog_thresh seconds then the debug-printout
- * triggers in watchdog_timer_fn().
- */
-static void watchdog(unsigned int cpu)
+static int softlockup_start_fn(void *data)
{
- __this_cpu_write(soft_lockup_hrtimer_cnt,
- __this_cpu_read(hrtimer_interrupts));
- __touch_watchdog();
+ watchdog_enable(smp_processor_id());
+ return 0;
}
-static struct smp_hotplug_thread watchdog_threads = {
- .store = &softlockup_watchdog,
- .thread_should_run = watchdog_should_run,
- .thread_fn = watchdog,
- .thread_comm = "watchdog/%u",
- .setup = watchdog_enable,
- .cleanup = watchdog_cleanup,
- .park = watchdog_disable,
- .unpark = watchdog_enable,
-};
-
-static void softlockup_update_smpboot_threads(void)
+static void softlockup_start_all(void)
{
- lockdep_assert_held(&watchdog_mutex);
-
- if (!softlockup_threads_initialized)
- return;
+ int cpu;
- smpboot_update_cpumask_percpu_thread(&watchdog_threads,
- &watchdog_allowed_mask);
+ cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask);
+ for_each_cpu(cpu, &watchdog_allowed_mask)
+ smp_call_on_cpu(cpu, softlockup_start_fn, NULL, false);
}
-/* Temporarily park all watchdog threads */
-static void softlockup_park_all_threads(void)
+int lockup_detector_online_cpu(unsigned int cpu)
{
- cpumask_clear(&watchdog_allowed_mask);
- softlockup_update_smpboot_threads();
+ watchdog_enable(cpu);
+ return 0;
}
-/* Unpark enabled threads */
-static void softlockup_unpark_threads(void)
+int lockup_detector_offline_cpu(unsigned int cpu)
{
- cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask);
- softlockup_update_smpboot_threads();
+ watchdog_disable(cpu);
+ return 0;
}
static void lockup_detector_reconfigure(void)
{
cpus_read_lock();
watchdog_nmi_stop();
- softlockup_park_all_threads();
+
+ softlockup_stop_all();
set_sample_period();
lockup_detector_update_enable();
if (watchdog_enabled && watchdog_thresh)
- softlockup_unpark_threads();
+ softlockup_start_all();
+
watchdog_nmi_start();
cpus_read_unlock();
/*
@@ -580,8 +586,6 @@ static void lockup_detector_reconfigure(void)
*/
static __init void lockup_detector_setup(void)
{
- int ret;
-
/*
* If sysctl is off and watchdog got disabled on the command line,
* nothing to do here.
@@ -592,24 +596,13 @@ static __init void lockup_detector_setup(void)
!(watchdog_enabled && watchdog_thresh))
return;
- ret = smpboot_register_percpu_thread_cpumask(&watchdog_threads,
- &watchdog_allowed_mask);
- if (ret) {
- pr_err("Failed to initialize soft lockup detector threads\n");
- return;
- }
-
mutex_lock(&watchdog_mutex);
- softlockup_threads_initialized = true;
lockup_detector_reconfigure();
+ softlockup_initialized = true;
mutex_unlock(&watchdog_mutex);
}
#else /* CONFIG_SOFTLOCKUP_DETECTOR */
-static inline int watchdog_park_threads(void) { return 0; }
-static inline void watchdog_unpark_threads(void) { }
-static inline int watchdog_enable_all_cpus(void) { return 0; }
-static inline void watchdog_disable_all_cpus(void) { }
static void lockup_detector_reconfigure(void)
{
cpus_read_lock();
diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
index e449a23e9d59..1f7020d65d0a 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -175,8 +175,8 @@ static int hardlockup_detector_event_create(void)
evt = perf_event_create_kernel_counter(wd_attr, cpu, NULL,
watchdog_overflow_callback, NULL);
if (IS_ERR(evt)) {
- pr_info("Perf event create on CPU %d failed with %ld\n", cpu,
- PTR_ERR(evt));
+ pr_debug("Perf event create on CPU %d failed with %ld\n", cpu,
+ PTR_ERR(evt));
return PTR_ERR(evt);
}
this_cpu_write(watchdog_ev, evt);