diff options
Diffstat (limited to 'kernel')
89 files changed, 6861 insertions, 1901 deletions
diff --git a/kernel/acct.c b/kernel/acct.c index b4c667d22e79..33738ef972f3 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -472,7 +472,6 @@ static void do_acct_process(struct bsd_acct_struct *acct) acct_t ac; unsigned long flim; const struct cred *orig_cred; - struct pid_namespace *ns = acct->ns; struct file *file = acct->file; /* @@ -500,10 +499,15 @@ static void do_acct_process(struct bsd_acct_struct *acct) ac.ac_gid16 = ac.ac_gid; #endif #if ACCT_VERSION == 3 - ac.ac_pid = task_tgid_nr_ns(current, ns); - rcu_read_lock(); - ac.ac_ppid = task_tgid_nr_ns(rcu_dereference(current->real_parent), ns); - rcu_read_unlock(); + { + struct pid_namespace *ns = acct->ns; + + ac.ac_pid = task_tgid_nr_ns(current, ns); + rcu_read_lock(); + ac.ac_ppid = task_tgid_nr_ns(rcu_dereference(current->real_parent), + ns); + rcu_read_unlock(); + } #endif /* * Get freeze protection. If the fs is frozen, just skip the write diff --git a/kernel/async.c b/kernel/async.c index 61f023ce0228..4c3773c0bf63 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -115,7 +115,7 @@ static void async_run_entry_fn(struct work_struct *work) /* 1) run (and print duration) */ if (initcall_debug && system_state == SYSTEM_BOOTING) { - printk(KERN_DEBUG "calling %lli_%pF @ %i\n", + pr_debug("calling %lli_%pF @ %i\n", (long long)entry->cookie, entry->func, task_pid_nr(current)); calltime = ktime_get(); @@ -124,7 +124,7 @@ static void async_run_entry_fn(struct work_struct *work) if (initcall_debug && system_state == SYSTEM_BOOTING) { rettime = ktime_get(); delta = ktime_sub(rettime, calltime); - printk(KERN_DEBUG "initcall %lli_%pF returned 0 after %lld usecs\n", + pr_debug("initcall %lli_%pF returned 0 after %lld usecs\n", (long long)entry->cookie, entry->func, (long long)ktime_to_ns(delta) >> 10); @@ -285,7 +285,7 @@ void async_synchronize_cookie_domain(async_cookie_t cookie, struct async_domain ktime_t uninitialized_var(starttime), delta, endtime; if (initcall_debug && system_state == SYSTEM_BOOTING) { - printk(KERN_DEBUG "async_waiting @ %i\n", task_pid_nr(current)); + pr_debug("async_waiting @ %i\n", task_pid_nr(current)); starttime = ktime_get(); } @@ -295,7 +295,7 @@ void async_synchronize_cookie_domain(async_cookie_t cookie, struct async_domain endtime = ktime_get(); delta = ktime_sub(endtime, starttime); - printk(KERN_DEBUG "async_continuing @ %i after %lli usec\n", + pr_debug("async_continuing @ %i after %lli usec\n", task_pid_nr(current), (long long)ktime_to_ns(delta) >> 10); } diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 21eae3c05ec0..7208c1df248d 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -2406,7 +2406,7 @@ int __audit_log_bprm_fcaps(struct linux_binprm *bprm, * @new: the new credentials * @old: the old (current) credentials * - * Record the aguments userspace sent to sys_capset for later printing by the + * Record the arguments userspace sent to sys_capset for later printing by the * audit system if applicable */ void __audit_log_capset(const struct cred *new, const struct cred *old) diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 6a71145e2769..45427239f375 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -1 +1,5 @@ -obj-y := core.o +obj-y := core.o syscall.o verifier.o + +ifdef CONFIG_TEST_BPF +obj-y += test_stub.o +endif diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 7f0dbcbb34af..f0c30c59b317 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -20,9 +20,14 @@ * Andi Kleen - Fix a few bad bugs and races. * Kris Katterjohn - Added many additional checks in bpf_check_classic() */ + #include <linux/filter.h> #include <linux/skbuff.h> +#include <linux/vmalloc.h> +#include <linux/random.h> +#include <linux/moduleloader.h> #include <asm/unaligned.h> +#include <linux/bpf.h> /* Registers */ #define BPF_R0 regs[BPF_REG_0] @@ -63,6 +68,105 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns return NULL; } +struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags) +{ + gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO | + gfp_extra_flags; + struct bpf_prog_aux *aux; + struct bpf_prog *fp; + + size = round_up(size, PAGE_SIZE); + fp = __vmalloc(size, gfp_flags, PAGE_KERNEL); + if (fp == NULL) + return NULL; + + aux = kzalloc(sizeof(*aux), GFP_KERNEL | gfp_extra_flags); + if (aux == NULL) { + vfree(fp); + return NULL; + } + + fp->pages = size / PAGE_SIZE; + fp->aux = aux; + + return fp; +} +EXPORT_SYMBOL_GPL(bpf_prog_alloc); + +struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, + gfp_t gfp_extra_flags) +{ + gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO | + gfp_extra_flags; + struct bpf_prog *fp; + + BUG_ON(fp_old == NULL); + + size = round_up(size, PAGE_SIZE); + if (size <= fp_old->pages * PAGE_SIZE) + return fp_old; + + fp = __vmalloc(size, gfp_flags, PAGE_KERNEL); + if (fp != NULL) { + memcpy(fp, fp_old, fp_old->pages * PAGE_SIZE); + fp->pages = size / PAGE_SIZE; + + /* We keep fp->aux from fp_old around in the new + * reallocated structure. + */ + fp_old->aux = NULL; + __bpf_prog_free(fp_old); + } + + return fp; +} +EXPORT_SYMBOL_GPL(bpf_prog_realloc); + +void __bpf_prog_free(struct bpf_prog *fp) +{ + kfree(fp->aux); + vfree(fp); +} +EXPORT_SYMBOL_GPL(__bpf_prog_free); + +#ifdef CONFIG_BPF_JIT +struct bpf_binary_header * +bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, + unsigned int alignment, + bpf_jit_fill_hole_t bpf_fill_ill_insns) +{ + struct bpf_binary_header *hdr; + unsigned int size, hole, start; + + /* Most of BPF filters are really small, but if some of them + * fill a page, allow at least 128 extra bytes to insert a + * random section of illegal instructions. + */ + size = round_up(proglen + sizeof(*hdr) + 128, PAGE_SIZE); + hdr = module_alloc(size); + if (hdr == NULL) + return NULL; + + /* Fill space with illegal/arch-dep instructions. */ + bpf_fill_ill_insns(hdr, size); + + hdr->pages = size / PAGE_SIZE; + hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)), + PAGE_SIZE - sizeof(*hdr)); + start = (prandom_u32() % hole) & ~(alignment - 1); + + /* Leave a random number of instructions before BPF code. */ + *image_ptr = &hdr->image[start]; + + return hdr; +} + +void bpf_jit_binary_free(struct bpf_binary_header *hdr) +{ + module_free(NULL, hdr); +} +#endif /* CONFIG_BPF_JIT */ + /* Base function for offset calculation. Needs to go into .text section, * therefore keeping it non-static as well; will also be used by JITs * anyway later on, so do not let the compiler omit it. @@ -180,6 +284,7 @@ static unsigned int __bpf_prog_run(void *ctx, const struct bpf_insn *insn) [BPF_LD | BPF_IND | BPF_W] = &&LD_IND_W, [BPF_LD | BPF_IND | BPF_H] = &&LD_IND_H, [BPF_LD | BPF_IND | BPF_B] = &&LD_IND_B, + [BPF_LD | BPF_IMM | BPF_DW] = &&LD_IMM_DW, }; void *ptr; int off; @@ -239,6 +344,10 @@ select_insn: ALU64_MOV_K: DST = IMM; CONT; + LD_IMM_DW: + DST = (u64) (u32) insn[0].imm | ((u64) (u32) insn[1].imm) << 32; + insn++; + CONT; ALU64_ARSH_X: (*(s64 *) &DST) >>= SRC; CONT; @@ -523,12 +632,26 @@ void bpf_prog_select_runtime(struct bpf_prog *fp) /* Probe if internal BPF can be JITed */ bpf_int_jit_compile(fp); + /* Lock whole bpf_prog as read-only */ + bpf_prog_lock_ro(fp); } EXPORT_SYMBOL_GPL(bpf_prog_select_runtime); -/* free internal BPF program */ +static void bpf_prog_free_deferred(struct work_struct *work) +{ + struct bpf_prog_aux *aux; + + aux = container_of(work, struct bpf_prog_aux, work); + bpf_jit_free(aux->prog); +} + +/* Free internal BPF program */ void bpf_prog_free(struct bpf_prog *fp) { - bpf_jit_free(fp); + struct bpf_prog_aux *aux = fp->aux; + + INIT_WORK(&aux->work, bpf_prog_free_deferred); + aux->prog = fp; + schedule_work(&aux->work); } EXPORT_SYMBOL_GPL(bpf_prog_free); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c new file mode 100644 index 000000000000..ba61c8c16032 --- /dev/null +++ b/kernel/bpf/syscall.c @@ -0,0 +1,606 @@ +/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com + * + * 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. + * + * 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. + */ +#include <linux/bpf.h> +#include <linux/syscalls.h> +#include <linux/slab.h> +#include <linux/anon_inodes.h> +#include <linux/file.h> +#include <linux/license.h> +#include <linux/filter.h> + +static LIST_HEAD(bpf_map_types); + +static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) +{ + struct bpf_map_type_list *tl; + struct bpf_map *map; + + list_for_each_entry(tl, &bpf_map_types, list_node) { + if (tl->type == attr->map_type) { + map = tl->ops->map_alloc(attr); + if (IS_ERR(map)) + return map; + map->ops = tl->ops; + map->map_type = attr->map_type; + return map; + } + } + return ERR_PTR(-EINVAL); +} + +/* boot time registration of different map implementations */ +void bpf_register_map_type(struct bpf_map_type_list *tl) +{ + list_add(&tl->list_node, &bpf_map_types); +} + +/* called from workqueue */ +static void bpf_map_free_deferred(struct work_struct *work) +{ + struct bpf_map *map = container_of(work, struct bpf_map, work); + + /* implementation dependent freeing */ + map->ops->map_free(map); +} + +/* decrement map refcnt and schedule it for freeing via workqueue + * (unrelying map implementation ops->map_free() might sleep) + */ +void bpf_map_put(struct bpf_map *map) +{ + if (atomic_dec_and_test(&map->refcnt)) { + INIT_WORK(&map->work, bpf_map_free_deferred); + schedule_work(&map->work); + } +} + +static int bpf_map_release(struct inode *inode, struct file *filp) +{ + struct bpf_map *map = filp->private_data; + + bpf_map_put(map); + return 0; +} + +static const struct file_operations bpf_map_fops = { + .release = bpf_map_release, +}; + +/* helper macro to check that unused fields 'union bpf_attr' are zero */ +#define CHECK_ATTR(CMD) \ + memchr_inv((void *) &attr->CMD##_LAST_FIELD + \ + sizeof(attr->CMD##_LAST_FIELD), 0, \ + sizeof(*attr) - \ + offsetof(union bpf_attr, CMD##_LAST_FIELD) - \ + sizeof(attr->CMD##_LAST_FIELD)) != NULL + +#define BPF_MAP_CREATE_LAST_FIELD max_entries +/* called via syscall */ +static int map_create(union bpf_attr *attr) +{ + struct bpf_map *map; + int err; + + err = CHECK_ATTR(BPF_MAP_CREATE); + if (err) + return -EINVAL; + + /* find map type and init map: hashtable vs rbtree vs bloom vs ... */ + map = find_and_alloc_map(attr); + if (IS_ERR(map)) + return PTR_ERR(map); + + atomic_set(&map->refcnt, 1); + + err = anon_inode_getfd("bpf-map", &bpf_map_fops, map, O_RDWR | O_CLOEXEC); + + if (err < 0) + /* failed to allocate fd */ + goto free_map; + + return err; + +free_map: + map->ops->map_free(map); + return err; +} + +/* if error is returned, fd is released. + * On success caller should complete fd access with matching fdput() + */ +struct bpf_map *bpf_map_get(struct fd f) +{ + struct bpf_map *map; + + if (!f.file) + return ERR_PTR(-EBADF); + + if (f.file->f_op != &bpf_map_fops) { + fdput(f); + return ERR_PTR(-EINVAL); + } + + map = f.file->private_data; + + return map; +} + +/* helper to convert user pointers passed inside __aligned_u64 fields */ +static void __user *u64_to_ptr(__u64 val) +{ + return (void __user *) (unsigned long) val; +} + +/* last field in 'union bpf_attr' used by this command */ +#define BPF_MAP_LOOKUP_ELEM_LAST_FIELD value + +static int map_lookup_elem(union bpf_attr *attr) +{ + void __user *ukey = u64_to_ptr(attr->key); + void __user *uvalue = u64_to_ptr(attr->value); + int ufd = attr->map_fd; + struct fd f = fdget(ufd); + struct bpf_map *map; + void *key, *value; + int err; + + if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM)) + return -EINVAL; + + map = bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + + err = -ENOMEM; + key = kmalloc(map->key_size, GFP_USER); + if (!key) + goto err_put; + + err = -EFAULT; + if (copy_from_user(key, ukey, map->key_size) != 0) + goto free_key; + + err = -ESRCH; + rcu_read_lock(); + value = map->ops->map_lookup_elem(map, key); + if (!value) + goto err_unlock; + + err = -EFAULT; + if (copy_to_user(uvalue, value, map->value_size) != 0) + goto err_unlock; + + err = 0; + +err_unlock: + rcu_read_unlock(); +free_key: + kfree(key); +err_put: + fdput(f); + return err; +} + +#define BPF_MAP_UPDATE_ELEM_LAST_FIELD value + +static int map_update_elem(union bpf_attr *attr) +{ + void __user *ukey = u64_to_ptr(attr->key); + void __user *uvalue = u64_to_ptr(attr->value); + int ufd = attr->map_fd; + struct fd f = fdget(ufd); + struct bpf_map *map; + void *key, *value; + int err; + + if (CHECK_ATTR(BPF_MAP_UPDATE_ELEM)) + return -EINVAL; + + map = bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + + err = -ENOMEM; + key = kmalloc(map->key_size, GFP_USER); + if (!key) + goto err_put; + + err = -EFAULT; + if (copy_from_user(key, ukey, map->key_size) != 0) + goto free_key; + + err = -ENOMEM; + value = kmalloc(map->value_size, GFP_USER); + if (!value) + goto free_key; + + err = -EFAULT; + if (copy_from_user(value, uvalue, map->value_size) != 0) + goto free_value; + + /* eBPF program that use maps are running under rcu_read_lock(), + * therefore all map accessors rely on this fact, so do the same here + */ + rcu_read_lock(); + err = map->ops->map_update_elem(map, key, value); + rcu_read_unlock(); + +free_value: + kfree(value); +free_key: + kfree(key); +err_put: + fdput(f); + return err; +} + +#define BPF_MAP_DELETE_ELEM_LAST_FIELD key + +static int map_delete_elem(union bpf_attr *attr) +{ + void __user *ukey = u64_to_ptr(attr->key); + int ufd = attr->map_fd; + struct fd f = fdget(ufd); + struct bpf_map *map; + void *key; + int err; + + if (CHECK_ATTR(BPF_MAP_DELETE_ELEM)) + return -EINVAL; + + map = bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + + err = -ENOMEM; + key = kmalloc(map->key_size, GFP_USER); + if (!key) + goto err_put; + + err = -EFAULT; + if (copy_from_user(key, ukey, map->key_size) != 0) + goto free_key; + + rcu_read_lock(); + err = map->ops->map_delete_elem(map, key); + rcu_read_unlock(); + +free_key: + kfree(key); +err_put: + fdput(f); + return err; +} + +/* last field in 'union bpf_attr' used by this command */ +#define BPF_MAP_GET_NEXT_KEY_LAST_FIELD next_key + +static int map_get_next_key(union bpf_attr *attr) +{ + void __user *ukey = u64_to_ptr(attr->key); + void __user *unext_key = u64_to_ptr(attr->next_key); + int ufd = attr->map_fd; + struct fd f = fdget(ufd); + struct bpf_map *map; + void *key, *next_key; + int err; + + if (CHECK_ATTR(BPF_MAP_GET_NEXT_KEY)) + return -EINVAL; + + map = bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + + err = -ENOMEM; + key = kmalloc(map->key_size, GFP_USER); + if (!key) + goto err_put; + + err = -EFAULT; + if (copy_from_user(key, ukey, map->key_size) != 0) + goto free_key; + + err = -ENOMEM; + next_key = kmalloc(map->key_size, GFP_USER); + if (!next_key) + goto free_key; + + rcu_read_lock(); + err = map->ops->map_get_next_key(map, key, next_key); + rcu_read_unlock(); + if (err) + goto free_next_key; + + err = -EFAULT; + if (copy_to_user(unext_key, next_key, map->key_size) != 0) + goto free_next_key; + + err = 0; + +free_next_key: + kfree(next_key); +free_key: + kfree(key); +err_put: + fdput(f); + return err; +} + +static LIST_HEAD(bpf_prog_types); + +static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog) +{ + struct bpf_prog_type_list *tl; + + list_for_each_entry(tl, &bpf_prog_types, list_node) { + if (tl->type == type) { + prog->aux->ops = tl->ops; + prog->aux->prog_type = type; + return 0; + } + } + return -EINVAL; +} + +void bpf_register_prog_type(struct bpf_prog_type_list *tl) +{ + list_add(&tl->list_node, &bpf_prog_types); +} + +/* fixup insn->imm field of bpf_call instructions: + * if (insn->imm == BPF_FUNC_map_lookup_elem) + * insn->imm = bpf_map_lookup_elem - __bpf_call_base; + * else if (insn->imm == BPF_FUNC_map_update_elem) + * insn->imm = bpf_map_update_elem - __bpf_call_base; + * else ... + * + * this function is called after eBPF program passed verification + */ +static void fixup_bpf_calls(struct bpf_prog *prog) +{ + const struct bpf_func_proto *fn; + int i; + + for (i = 0; i < prog->len; i++) { + struct bpf_insn *insn = &prog->insnsi[i]; + + if (insn->code == (BPF_JMP | BPF_CALL)) { + /* we reach here when program has bpf_call instructions + * and it passed bpf_check(), means that + * ops->get_func_proto must have been supplied, check it + */ + BUG_ON(!prog->aux->ops->get_func_proto); + + fn = prog->aux->ops->get_func_proto(insn->imm); + /* all functions that have prototype and verifier allowed + * programs to call them, must be real in-kernel functions + */ + BUG_ON(!fn->func); + insn->imm = fn->func - __bpf_call_base; + } + } +} + +/* drop refcnt on maps used by eBPF program and free auxilary data */ +static void free_used_maps(struct bpf_prog_aux *aux) +{ + int i; + + for (i = 0; i < aux->used_map_cnt; i++) + bpf_map_put(aux->used_maps[i]); + + kfree(aux->used_maps); +} + +void bpf_prog_put(struct bpf_prog *prog) +{ + if (atomic_dec_and_test(&prog->aux->refcnt)) { + free_used_maps(prog->aux); + bpf_prog_free(prog); + } +} + +static int bpf_prog_release(struct inode *inode, struct file *filp) +{ + struct bpf_prog *prog = filp->private_data; + + bpf_prog_put(prog); + return 0; +} + +static const struct file_operations bpf_prog_fops = { + .release = bpf_prog_release, +}; + +static struct bpf_prog *get_prog(struct fd f) +{ + struct bpf_prog *prog; + + if (!f.file) + return ERR_PTR(-EBADF); + + if (f.file->f_op != &bpf_prog_fops) { + fdput(f); + return ERR_PTR(-EINVAL); + } + + prog = f.file->private_data; + + return prog; +} + +/* called by sockets/tracing/seccomp before attaching program to an event + * pairs with bpf_prog_put() + */ +struct bpf_prog *bpf_prog_get(u32 ufd) +{ + struct fd f = fdget(ufd); + struct bpf_prog *prog; + + prog = get_prog(f); + + if (IS_ERR(prog)) + return prog; + + atomic_inc(&prog->aux->refcnt); + fdput(f); + return prog; +} + +/* last field in 'union bpf_attr' used by this command */ +#define BPF_PROG_LOAD_LAST_FIELD log_buf + +static int bpf_prog_load(union bpf_attr *attr) +{ + enum bpf_prog_type type = attr->prog_type; + struct bpf_prog *prog; + int err; + char license[128]; + bool is_gpl; + + if (CHECK_ATTR(BPF_PROG_LOAD)) + return -EINVAL; + + /* copy eBPF program license from user space */ + if (strncpy_from_user(license, u64_to_ptr(attr->license), + sizeof(license) - 1) < 0) + return -EFAULT; + license[sizeof(license) - 1] = 0; + + /* eBPF programs must be GPL compatible to use GPL-ed functions */ + is_gpl = license_is_gpl_compatible(license); + + if (attr->insn_cnt >= BPF_MAXINSNS) + return -EINVAL; + + /* plain bpf_prog allocation */ + prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER); + if (!prog) + return -ENOMEM; + + prog->len = attr->insn_cnt; + + err = -EFAULT; + if (copy_from_user(prog->insns, u64_to_ptr(attr->insns), + prog->len * sizeof(struct bpf_insn)) != 0) + goto free_prog; + + prog->orig_prog = NULL; + prog->jited = false; + + atomic_set(&prog->aux->refcnt, 1); + prog->aux->is_gpl_compatible = is_gpl; + + /* find program type: socket_filter vs tracing_filter */ + err = find_prog_type(type, prog); + if (err < 0) + goto free_prog; + + /* run eBPF verifier */ + err = bpf_check(prog, attr); + + if (err < 0) + goto free_used_maps; + + /* fixup BPF_CALL->imm field */ + fixup_bpf_calls(prog); + + /* eBPF program is ready to be JITed */ + bpf_prog_select_runtime(prog); + + err = anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog, O_RDWR | O_CLOEXEC); + + if (err < 0) + /* failed to allocate fd */ + goto free_used_maps; + + return err; + +free_used_maps: + free_used_maps(prog->aux); +free_prog: + bpf_prog_free(prog); + return err; +} + +SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) +{ + union bpf_attr attr = {}; + int err; + + /* the syscall is limited to root temporarily. This restriction will be + * lifted when security audit is clean. Note that eBPF+tracing must have + * this restriction, since it may pass kernel data to user space + */ + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (!access_ok(VERIFY_READ, uattr, 1)) + return -EFAULT; + + if (size > PAGE_SIZE) /* silly large */ + return -E2BIG; + + /* If we're handed a bigger struct than we know of, + * ensure all the unknown bits are 0 - i.e. new + * user-space does not rely on any kernel feature + * extensions we dont know about yet. + */ + if (size > sizeof(attr)) { + unsigned char __user *addr; + unsigned char __user *end; + unsigned char val; + + addr = (void __user *)uattr + sizeof(attr); + end = (void __user *)uattr + size; + + for (; addr < end; addr++) { + err = get_user(val, addr); + if (err) + return err; + if (val) + return -E2BIG; + } + size = sizeof(attr); + } + + /* copy attributes from user space, may be less than sizeof(bpf_attr) */ + if (copy_from_user(&attr, uattr, size) != 0) + return -EFAULT; + + switch (cmd) { + case BPF_MAP_CREATE: + err = map_create(&attr); + break; + case BPF_MAP_LOOKUP_ELEM: + err = map_lookup_elem(&attr); + break; + case BPF_MAP_UPDATE_ELEM: + err = map_update_elem(&attr); + break; + case BPF_MAP_DELETE_ELEM: + err = map_delete_elem(&attr); + break; + case BPF_MAP_GET_NEXT_KEY: + err = map_get_next_key(&attr); + break; + case BPF_PROG_LOAD: + err = bpf_prog_load(&attr); + break; + default: + err = -EINVAL; + break; + } + + return err; +} diff --git a/kernel/bpf/test_stub.c b/kernel/bpf/test_stub.c new file mode 100644 index 000000000000..fcaddff4003e --- /dev/null +++ b/kernel/bpf/test_stub.c @@ -0,0 +1,116 @@ +/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com + * + * 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> +#include <linux/slab.h> +#include <linux/err.h> +#include <linux/bpf.h> + +/* test stubs for BPF_MAP_TYPE_UNSPEC and for BPF_PROG_TYPE_UNSPEC + * to be used by user space verifier testsuite + */ +struct bpf_context { + u64 arg1; + u64 arg2; +}; + +static u64 test_func(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + return 0; +} + +static struct bpf_func_proto test_funcs[] = { + [BPF_FUNC_unspec] = { + .func = test_func, + .gpl_only = true, + .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_MAP_KEY, + }, +}; + +static const struct bpf_func_proto *test_func_proto(enum bpf_func_id func_id) +{ + if (func_id < 0 || func_id >= ARRAY_SIZE(test_funcs)) + return NULL; + return &test_funcs[func_id]; +} + +static const struct bpf_context_access { + int size; + enum bpf_access_type type; +} test_ctx_access[] = { + [offsetof(struct bpf_context, arg1)] = { + FIELD_SIZEOF(struct bpf_context, arg1), + BPF_READ + }, + [offsetof(struct bpf_context, arg2)] = { + FIELD_SIZEOF(struct bpf_context, arg2), + BPF_READ + }, +}; + +static bool test_is_valid_access(int off, int size, enum bpf_access_type type) +{ + const struct bpf_context_access *access; + + if (off < 0 || off >= ARRAY_SIZE(test_ctx_access)) + return false; + + access = &test_ctx_access[off]; + if (access->size == size && (access->type & type)) + return true; + + return false; +} + +static struct bpf_verifier_ops test_ops = { + .get_func_proto = test_func_proto, + .is_valid_access = test_is_valid_access, +}; + +static struct bpf_prog_type_list tl_prog = { + .ops = &test_ops, + .type = BPF_PROG_TYPE_UNSPEC, +}; + +static struct bpf_map *test_map_alloc(union bpf_attr *attr) +{ + struct bpf_map *map; + + map = kzalloc(sizeof(*map), GFP_USER); + if (!map) + return ERR_PTR(-ENOMEM); + + map->key_size = attr->key_size; + map->value_size = attr->value_size; + map->max_entries = attr->max_entries; + return map; +} + +static void test_map_free(struct bpf_map *map) +{ + kfree(map); +} + +static struct bpf_map_ops test_map_ops = { + .map_alloc = test_map_alloc, + .map_free = test_map_free, +}; + +static struct bpf_map_type_list tl_map = { + .ops = &test_map_ops, + .type = BPF_MAP_TYPE_UNSPEC, +}; + +static int __init register_test_ops(void) +{ + bpf_register_map_type(&tl_map); + bpf_register_prog_type(&tl_prog); + return 0; +} +late_initcall(register_test_ops); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c new file mode 100644 index 000000000000..801f5f3b9307 --- /dev/null +++ b/kernel/bpf/verifier.c @@ -0,0 +1,1923 @@ +/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com + * + * 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. + * + * 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. + */ +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/bpf.h> +#include <linux/filter.h> +#include <net/netlink.h> +#include <linux/file.h> +#include <linux/vmalloc.h> + +/* bpf_check() is a static code analyzer that walks eBPF program + * instruction by instruction and updates register/stack state. + * All paths of conditional branches are analyzed until 'bpf_exit' insn. + * + * The first pass is depth-first-search to check that the program is a DAG. + * It rejects the following programs: + * - larger than BPF_MAXINSNS insns + * - if loop is present (detected via back-edge) + * - unreachable insns exist (shouldn't be a forest. program = one function) + * - out of bounds or malformed jumps + * The second pass is all possible path descent from the 1st insn. + * Since it's analyzing all pathes through the program, the length of the + * analysis is limited to 32k insn, which may be hit even if total number of + * insn is less then 4K, but there are too many branches that change stack/regs. + * Number of 'branches to be analyzed' is limited to 1k + * + * On entry to each instruction, each register has a type, and the instruction + * changes the types of the registers depending on instruction semantics. + * If instruction is BPF_MOV64_REG(BPF_REG_1, BPF_REG_5), then type of R5 is + * copied to R1. + * + * All registers are 64-bit. + * R0 - return register + * R1-R5 argument passing registers + * R6-R9 callee saved registers + * R10 - frame pointer read-only + * + * At the start of BPF program the register R1 contains a pointer to bpf_context + * and has type PTR_TO_CTX. + * + * Verifier tracks arithmetic operations on pointers in case: + * BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + * BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -20), + * 1st insn copies R10 (which has FRAME_PTR) type into R1 + * and 2nd arithmetic instruction is pattern matched to recognize + * that it wants to construct a pointer to some element within stack. + * So after 2nd insn, the register R1 has type PTR_TO_STACK + * (and -20 constant is saved for further stack bounds checking). + * Meaning that this reg is a pointer to stack plus known immediate constant. + * + * Most of the time the registers have UNKNOWN_VALUE type, which + * means the register has some value, but it's not a valid pointer. + * (like pointer plus pointer becomes UNKNOWN_VALUE type) + * + * When verifier sees load or store instructions the type of base register + * can be: PTR_TO_MAP_VALUE, PTR_TO_CTX, FRAME_PTR. These are three pointer + * types recognized by check_mem_access() function. + * + * PTR_TO_MAP_VALUE means that this register is pointing to 'map element value' + * and the range of [ptr, ptr + map's value_size) is accessible. + * + * registers used to pass values to function calls are checked against + * function argument constraints. + * + * ARG_PTR_TO_MAP_KEY is one of such argument constraints. + * It means that the register type passed to this function must be + * PTR_TO_STACK and it will be used inside the function as + * 'pointer to map element key' + * + * For example the argument constraints for bpf_map_lookup_elem(): + * .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, + * .arg1_type = ARG_CONST_MAP_PTR, + * .arg2_type = ARG_PTR_TO_MAP_KEY, + * + * ret_type says that this function returns 'pointer to map elem value or null' + * function expects 1st argument to be a const pointer to 'struct bpf_map' and + * 2nd argument should be a pointer to stack, which will be used inside + * the helper function as a pointer to map element key. + * + * On the kernel side the helper function looks like: + * u64 bpf_map_lookup_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) + * { + * struct bpf_map *map = (struct bpf_map *) (unsigned long) r1; + * void *key = (void *) (unsigned long) r2; + * void *value; + * + * here kernel can access 'key' and 'map' pointers safely, knowing that + * [key, key + map->key_size) bytes are valid and were initialized on + * the stack of eBPF program. + * } + * + * Corresponding eBPF program may look like: + * BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), // after this insn R2 type is FRAME_PTR + * BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), // after this insn R2 type is PTR_TO_STACK + * BPF_LD_MAP_FD(BPF_REG_1, map_fd), // after this insn R1 type is CONST_PTR_TO_MAP + * BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + * here verifier looks at prototype of map_lookup_elem() and sees: + * .arg1_type == ARG_CONST_MAP_PTR and R1->type == CONST_PTR_TO_MAP, which is ok, + * Now verifier knows that this map has key of R1->map_ptr->key_size bytes + * + * Then .arg2_type == ARG_PTR_TO_MAP_KEY and R2->type == PTR_TO_STACK, ok so far, + * Now verifier checks that [R2, R2 + map's key_size) are within stack limits + * and were initialized prior to this call. + * If it's ok, then verifier allows this BPF_CALL insn and looks at + * .ret_type which is RET_PTR_TO_MAP_VALUE_OR_NULL, so it sets + * R0->type = PTR_TO_MAP_VALUE_OR_NULL which means bpf_map_lookup_elem() function + * returns ether pointer to map value or NULL. + * + * When type PTR_TO_MAP_VALUE_OR_NULL passes through 'if (reg != 0) goto +off' + * insn, the register holding that pointer in the true branch changes state to + * PTR_TO_MAP_VALUE and the same register changes state to CONST_IMM in the false + * branch. See check_cond_jmp_op(). + * + * After the call R0 is set to return type of the function and registers R1-R5 + * are set to NOT_INIT to indicate that they are no longer readable. + */ + +/* types of values stored in eBPF registers */ +enum bpf_reg_type { + NOT_INIT = 0, /* nothing was written into register */ + UNKNOWN_VALUE, /* reg doesn't contain a valid pointer */ + PTR_TO_CTX, /* reg points to bpf_context */ + CONST_PTR_TO_MAP, /* reg points to struct bpf_map */ + PTR_TO_MAP_VALUE, /* reg points to map element value */ + PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */ + FRAME_PTR, /* reg == frame_pointer */ + PTR_TO_STACK, /* reg == frame_pointer + imm */ + CONST_IMM, /* constant integer value */ +}; + +struct reg_state { + enum bpf_reg_type type; + union { + /* valid when type == CONST_IMM | PTR_TO_STACK */ + int imm; + + /* valid when type == CONST_PTR_TO_MAP | PTR_TO_MAP_VALUE | + * PTR_TO_MAP_VALUE_OR_NULL + */ + struct bpf_map *map_ptr; + }; +}; + +enum bpf_stack_slot_type { + STACK_INVALID, /* nothing was stored in this stack slot */ + STACK_SPILL, /* 1st byte of register spilled into stack */ + STACK_SPILL_PART, /* other 7 bytes of register spill */ + STACK_MISC /* BPF program wrote some data into this slot */ +}; + +struct bpf_stack_slot { + enum bpf_stack_slot_type stype; + struct reg_state reg_st; +}; + +/* state of the program: + * type of all registers and stack info + */ +struct verifier_state { + struct reg_state regs[MAX_BPF_REG]; + struct bpf_stack_slot stack[MAX_BPF_STACK]; +}; + +/* linked list of verifier states used to prune search */ +struct verifier_state_list { + struct verifier_state state; + struct verifier_state_list *next; +}; + +/* verifier_state + insn_idx are pushed to stack when branch is encountered */ +struct verifier_stack_elem { + /* verifer state is 'st' + * before processing instruction 'insn_idx' + * and after processing instruction 'prev_insn_idx' + */ + struct verifier_state st; + int insn_idx; + int prev_insn_idx; + struct verifier_stack_elem *next; +}; + +#define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ + +/* single container for all structs + * one verifier_env per bpf_check() call + */ +struct verifier_env { + struct bpf_prog *prog; /* eBPF program being verified */ + struct verifier_stack_elem *head; /* stack of verifier states to be processed */ + int stack_size; /* number of states to be processed */ + struct verifier_state cur_state; /* current verifier state */ + struct verifier_state_list **explored_states; /* search pruning optimization */ + struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */ + u32 used_map_cnt; /* number of used maps */ +}; + +/* verbose verifier prints what it's seeing + * bpf_check() is called under lock, so no race to access these global vars + */ +static u32 log_level, log_size, log_len; +static char *log_buf; + +static DEFINE_MUTEX(bpf_verifier_lock); + +/* log_level controls verbosity level of eBPF verifier. + * verbose() is used to dump the verification trace to the log, so the user + * can figure out what's wrong with the program + */ +static void verbose(const char *fmt, ...) +{ + va_list args; + + if (log_level == 0 || log_len >= log_size - 1) + return; + + va_start(args, fmt); + log_len += vscnprintf(log_buf + log_len, log_size - log_len, fmt, args); + va_end(args); +} + +/* string representation of 'enum bpf_reg_type' */ +static const char * const reg_type_str[] = { + [NOT_INIT] = "?", + [UNKNOWN_VALUE] = "inv", + [PTR_TO_CTX] = "ctx", + [CONST_PTR_TO_MAP] = "map_ptr", + [PTR_TO_MAP_VALUE] = "map_value", + [PTR_TO_MAP_VALUE_OR_NULL] = "map_value_or_null", + [FRAME_PTR] = "fp", + [PTR_TO_STACK] = "fp", + [CONST_IMM] = "imm", +}; + +static void print_verifier_state(struct verifier_env *env) +{ + enum bpf_reg_type t; + int i; + + for (i = 0; i < MAX_BPF_REG; i++) { + t = env->cur_state.regs[i].type; + if (t == NOT_INIT) + continue; + verbose(" R%d=%s", i, reg_type_str[t]); + if (t == CONST_IMM || t == PTR_TO_STACK) + verbose("%d", env->cur_state.regs[i].imm); + else if (t == CONST_PTR_TO_MAP || t == PTR_TO_MAP_VALUE || + t == PTR_TO_MAP_VALUE_OR_NULL) + verbose("(ks=%d,vs=%d)", + env->cur_state.regs[i].map_ptr->key_size, + env->cur_state.regs[i].map_ptr->value_size); + } + for (i = 0; i < MAX_BPF_STACK; i++) { + if (env->cur_state.stack[i].stype == STACK_SPILL) + verbose(" fp%d=%s", -MAX_BPF_STACK + i, + reg_type_str[env->cur_state.stack[i].reg_st.type]); + } + verbose("\n"); +} + +static const char *const bpf_class_string[] = { + [BPF_LD] = "ld", + [BPF_LDX] = "ldx", + [BPF_ST] = "st", + [BPF_STX] = "stx", + [BPF_ALU] = "alu", + [BPF_JMP] = "jmp", + [BPF_RET] = "BUG", + [BPF_ALU64] = "alu64", +}; + +static const char *const bpf_alu_string[] = { + [BPF_ADD >> 4] = "+=", + [BPF_SUB >> 4] = "-=", + [BPF_MUL >> 4] = "*=", + [BPF_DIV >> 4] = "/=", + [BPF_OR >> 4] = "|=", + [BPF_AND >> 4] = "&=", + [BPF_LSH >> 4] = "<<=", + [BPF_RSH >> 4] = ">>=", + [BPF_NEG >> 4] = "neg", + [BPF_MOD >> 4] = "%=", + [BPF_XOR >> 4] = "^=", + [BPF_MOV >> 4] = "=", + [BPF_ARSH >> 4] = "s>>=", + [BPF_END >> 4] = "endian", +}; + +static const char *const bpf_ldst_string[] = { + [BPF_W >> 3] = "u32", + [BPF_H >> 3] = "u16", + [BPF_B >> 3] = "u8", + [BPF_DW >> 3] = "u64", +}; + +static const char *const bpf_jmp_string[] = { + [BPF_JA >> 4] = "jmp", + [BPF_JEQ >> 4] = "==", + [BPF_JGT >> 4] = ">", + [BPF_JGE >> 4] = ">=", + [BPF_JSET >> 4] = "&", + [BPF_JNE >> 4] = "!=", + [BPF_JSGT >> 4] = "s>", + [BPF_JSGE >> 4] = "s>=", + [BPF_CALL >> 4] = "call", + [BPF_EXIT >> 4] = "exit", +}; + +static void print_bpf_insn(struct bpf_insn *insn) +{ + u8 class = BPF_CLASS(insn->code); + + if (class == BPF_ALU || class == BPF_ALU64) { + if (BPF_SRC(insn->code) == BPF_X) + verbose("(%02x) %sr%d %s %sr%d\n", + insn->code, class == BPF_ALU ? "(u32) " : "", + insn->dst_reg, + bpf_alu_string[BPF_OP(insn->code) >> 4], + class == BPF_ALU ? "(u32) " : "", + insn->src_reg); + else + verbose("(%02x) %sr%d %s %s%d\n", + insn->code, class == BPF_ALU ? "(u32) " : "", + insn->dst_reg, + bpf_alu_string[BPF_OP(insn->code) >> 4], + class == BPF_ALU ? "(u32) " : "", + insn->imm); + } else if (class == BPF_STX) { + if (BPF_MODE(insn->code) == BPF_MEM) + verbose("(%02x) *(%s *)(r%d %+d) = r%d\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, + insn->off, insn->src_reg); + else if (BPF_MODE(insn->code) == BPF_XADD) + verbose("(%02x) lock *(%s *)(r%d %+d) += r%d\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, insn->off, + insn->src_reg); + else + verbose("BUG_%02x\n", insn->code); + } else if (class == BPF_ST) { + if (BPF_MODE(insn->code) != BPF_MEM) { + verbose("BUG_st_%02x\n", insn->code); + return; + } + verbose("(%02x) *(%s *)(r%d %+d) = %d\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, + insn->off, insn->imm); + } else if (class == BPF_LDX) { + if (BPF_MODE(insn->code) != BPF_MEM) { + verbose("BUG_ldx_%02x\n", insn->code); + return; + } + verbose("(%02x) r%d = *(%s *)(r%d %+d)\n", + insn->code, insn->dst_reg, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->src_reg, insn->off); + } else if (class == BPF_LD) { + if (BPF_MODE(insn->code) == BPF_ABS) { + verbose("(%02x) r0 = *(%s *)skb[%d]\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->imm); + } else if (BPF_MODE(insn->code) == BPF_IND) { + verbose("(%02x) r0 = *(%s *)skb[r%d + %d]\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->src_reg, insn->imm); + } else if (BPF_MODE(insn->code) == BPF_IMM) { + verbose("(%02x) r%d = 0x%x\n", + insn->code, insn->dst_reg, insn->imm); + } else { + verbose("BUG_ld_%02x\n", insn->code); + return; + } + } else if (class == BPF_JMP) { + u8 opcode = BPF_OP(insn->code); + + if (opcode == BPF_CALL) { + verbose("(%02x) call %d\n", insn->code, insn->imm); + } else if (insn->code == (BPF_JMP | BPF_JA)) { + verbose("(%02x) goto pc%+d\n", + insn->code, insn->off); + } else if (insn->code == (BPF_JMP | BPF_EXIT)) { + verbose("(%02x) exit\n", insn->code); + } else if (BPF_SRC(insn->code) == BPF_X) { + verbose("(%02x) if r%d %s r%d goto pc%+d\n", + insn->code, insn->dst_reg, + bpf_jmp_string[BPF_OP(insn->code) >> 4], + insn->src_reg, insn->off); + } else { + verbose("(%02x) if r%d %s 0x%x goto pc%+d\n", + insn->code, insn->dst_reg, + bpf_jmp_string[BPF_OP(insn->code) >> 4], + insn->imm, insn->off); + } + } else { + verbose("(%02x) %s\n", insn->code, bpf_class_string[class]); + } +} + +static int pop_stack(struct verifier_env *env, int *prev_insn_idx) +{ + struct verifier_stack_elem *elem; + int insn_idx; + + if (env->head == NULL) + return -1; + + memcpy(&env->cur_state, &env->head->st, sizeof(env->cur_state)); + insn_idx = env->head->insn_idx; + if (prev_insn_idx) + *prev_insn_idx = env->head->prev_insn_idx; + elem = env->head->next; + kfree(env->head); + env->head = elem; + env->stack_size--; + return insn_idx; +} + +static struct verifier_state *push_stack(struct verifier_env *env, int insn_idx, + int prev_insn_idx) +{ + struct verifier_stack_elem *elem; + + elem = kmalloc(sizeof(struct verifier_stack_elem), GFP_KERNEL); + if (!elem) + goto err; + + memcpy(&elem->st, &env->cur_state, sizeof(env->cur_state)); + elem->insn_idx = insn_idx; + elem->prev_insn_idx = prev_insn_idx; + elem->next = env->head; + env->head = elem; + env->stack_size++; + if (env->stack_size > 1024) { + verbose("BPF program is too complex\n"); + goto err; + } + return &elem->st; +err: + /* pop all elements and return */ + while (pop_stack(env, NULL) >= 0); + return NULL; +} + +#define CALLER_SAVED_REGS 6 +static const int caller_saved[CALLER_SAVED_REGS] = { + BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5 +}; + +static void init_reg_state(struct reg_state *regs) +{ + int i; + + for (i = 0; i < MAX_BPF_REG; i++) { + regs[i].type = NOT_INIT; + regs[i].imm = 0; + regs[i].map_ptr = NULL; + } + + /* frame pointer */ + regs[BPF_REG_FP].type = FRAME_PTR; + + /* 1st arg to a function */ + regs[BPF_REG_1].type = PTR_TO_CTX; +} + +static void mark_reg_unknown_value(struct reg_state *regs, u32 regno) +{ + BUG_ON(regno >= MAX_BPF_REG); + regs[regno].type = UNKNOWN_VALUE; + regs[regno].imm = 0; + regs[regno].map_ptr = NULL; +} + +enum reg_arg_type { + SRC_OP, /* register is used as source operand */ + DST_OP, /* register is used as destination operand */ + DST_OP_NO_MARK /* same as above, check only, don't mark */ +}; + +static int check_reg_arg(struct reg_state *regs, u32 regno, + enum reg_arg_type t) +{ + if (regno >= MAX_BPF_REG) { + verbose("R%d is invalid\n", regno); + return -EINVAL; + } + + if (t == SRC_OP) { + /* check whether register used as source operand can be read */ + if (regs[regno].type == NOT_INIT) { + verbose("R%d !read_ok\n", regno); + return -EACCES; + } + } else { + /* check whether register used as dest operand can be written to */ + if (regno == BPF_REG_FP) { + verbose("frame pointer is read only\n"); + return -EACCES; + } + if (t == DST_OP) + mark_reg_unknown_value(regs, regno); + } + return 0; +} + +static int bpf_size_to_bytes(int bpf_size) +{ + if (bpf_size == BPF_W) + return 4; + else if (bpf_size == BPF_H) + return 2; + else if (bpf_size == BPF_B) + return 1; + else if (bpf_size == BPF_DW) + return 8; + else + return -EINVAL; +} + +/* check_stack_read/write functions track spill/fill of registers, + * stack boundary and alignment are checked in check_mem_access() + */ +static int check_stack_write(struct verifier_state *state, int off, int size, + int value_regno) +{ + struct bpf_stack_slot *slot; + int i; + + if (value_regno >= 0 && + (state->regs[value_regno].type == PTR_TO_MAP_VALUE || + state->regs[value_regno].type == PTR_TO_STACK || + state->regs[value_regno].type == PTR_TO_CTX)) { + + /* register containing pointer is being spilled into stack */ + if (size != 8) { + verbose("invalid size of register spill\n"); + return -EACCES; + } + + slot = &state->stack[MAX_BPF_STACK + off]; + slot->stype = STACK_SPILL; + /* save register state */ + slot->reg_st = state->regs[value_regno]; + for (i = 1; i < 8; i++) { + slot = &state->stack[MAX_BPF_STACK + off + i]; + slot->stype = STACK_SPILL_PART; + slot->reg_st.type = UNKNOWN_VALUE; + slot->reg_st.map_ptr = NULL; + } + } else { + + /* regular write of data into stack */ + for (i = 0; i < size; i++) { + slot = &state->stack[MAX_BPF_STACK + off + i]; + slot->stype = STACK_MISC; + slot->reg_st.type = UNKNOWN_VALUE; + slot->reg_st.map_ptr = NULL; + } + } + return 0; +} + +static int check_stack_read(struct verifier_state *state, int off, int size, + int value_regno) +{ + int i; + struct bpf_stack_slot *slot; + + slot = &state->stack[MAX_BPF_STACK + off]; + + if (slot->stype == STACK_SPILL) { + if (size != 8) { + verbose("invalid size of register spill\n"); + return -EACCES; + } + for (i = 1; i < 8; i++) { + if (state->stack[MAX_BPF_STACK + off + i].stype != + STACK_SPILL_PART) { + verbose("corrupted spill memory\n"); + return -EACCES; + } + } + + if (value_regno >= 0) + /* restore register state from stack */ + state->regs[value_regno] = slot->reg_st; + return 0; + } else { + for (i = 0; i < size; i++) { + if (state->stack[MAX_BPF_STACK + off + i].stype != + STACK_MISC) { + verbose("invalid read from stack off %d+%d size %d\n", + off, i, size); + return -EACCES; + } + } + if (value_regno >= 0) + /* have read misc data from the stack */ + mark_reg_unknown_value(state->regs, value_regno); + return 0; + } +} + +/* check read/write into map element returned by bpf_map_lookup_elem() */ +static int check_map_access(struct verifier_env *env, u32 regno, int off, + int size) +{ + struct bpf_map *map = env->cur_state.regs[regno].map_ptr; + + if (off < 0 || off + size > map->value_size) { + verbose("invalid access to map value, value_size=%d off=%d size=%d\n", + map->value_size, off, size); + return -EACCES; + } + return 0; +} + +/* check access to 'struct bpf_context' fields */ +static int check_ctx_access(struct verifier_env *env, int off, int size, + enum bpf_access_type t) +{ + if (env->prog->aux->ops->is_valid_access && + env->prog->aux->ops->is_valid_access(off, size, t)) + return 0; + + verbose("invalid bpf_context access off=%d size=%d\n", off, size); + return -EACCES; +} + +/* check whether memory at (regno + off) is accessible for t = (read | write) + * if t==write, value_regno is a register which value is stored into memory + * if t==read, value_regno is a register which will receive the value from memory + * if t==write && value_regno==-1, some unknown value is stored into memory + * if t==read && value_regno==-1, don't care what we read from memory + */ +static int check_mem_access(struct verifier_env *env, u32 regno, int off, + int bpf_size, enum bpf_access_type t, + int value_regno) +{ + struct verifier_state *state = &env->cur_state; + int size, err = 0; + + size = bpf_size_to_bytes(bpf_size); + if (size < 0) + return size; + + if (off % size != 0) { + verbose("misaligned access off %d size %d\n", off, size); + return -EACCES; + } + + if (state->regs[regno].type == PTR_TO_MAP_VALUE) { + err = check_map_access(env, regno, off, size); + if (!err && t == BPF_READ && value_regno >= 0) + mark_reg_unknown_value(state->regs, value_regno); + + } else if (state->regs[regno].type == PTR_TO_CTX) { + err = check_ctx_access(env, off, size, t); + if (!err && t == BPF_READ && value_regno >= 0) + mark_reg_unknown_value(state->regs, value_regno); + + } else if (state->regs[regno].type == FRAME_PTR) { + if (off >= 0 || off < -MAX_BPF_STACK) { + verbose("invalid stack off=%d size=%d\n", off, size); + return -EACCES; + } + if (t == BPF_WRITE) + err = check_stack_write(state, off, size, value_regno); + else + err = check_stack_read(state, off, size, value_regno); + } else { + verbose("R%d invalid mem access '%s'\n", + regno, reg_type_str[state->regs[regno].type]); + return -EACCES; + } + return err; +} + +static int check_xadd(struct verifier_env *env, struct bpf_insn *insn) +{ + struct reg_state *regs = env->cur_state.regs; + int err; + + if ((BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) || + insn->imm != 0) { + verbose("BPF_XADD uses reserved fields\n"); + return -EINVAL; + } + + /* check src1 operand */ + err = check_reg_arg(regs, insn->src_reg, SRC_OP); + if (err) + return err; + + /* check src2 operand */ + err = check_reg_arg(regs, insn->dst_reg, SRC_OP); + if (err) + return err; + + /* check whether atomic_add can read the memory */ + err = check_mem_access(env, insn->dst_reg, insn->off, + BPF_SIZE(insn->code), BPF_READ, -1); + if (err) + return err; + + /* check whether atomic_add can write into the same memory */ + return check_mem_access(env, insn->dst_reg, insn->off, + BPF_SIZE(insn->code), BPF_WRITE, -1); +} + +/* when register 'regno' is passed into function that will read 'access_size' + * bytes from that pointer, make sure that it's within stack boundary + * and all elements of stack are initialized + */ +static int check_stack_boundary(struct verifier_env *env, + int regno, int access_size) +{ + struct verifier_state *state = &env->cur_state; + struct reg_state *regs = state->regs; + int off, i; + + if (regs[regno].type != PTR_TO_STACK) + return -EACCES; + + off = regs[regno].imm; + if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 || + access_size <= 0) { + verbose("invalid stack type R%d off=%d access_size=%d\n", + regno, off, access_size); + return -EACCES; + } + + for (i = 0; i < access_size; i++) { + if (state->stack[MAX_BPF_STACK + off + i].stype != STACK_MISC) { + verbose("invalid indirect read from stack off %d+%d size %d\n", + off, i, access_size); + return -EACCES; + } + } + return 0; +} + +static int check_func_arg(struct verifier_env *env, u32 regno, + enum bpf_arg_type arg_type, struct bpf_map **mapp) +{ + struct reg_state *reg = env->cur_state.regs + regno; + enum bpf_reg_type expected_type; + int err = 0; + + if (arg_type == ARG_ANYTHING) + return 0; + + if (reg->type == NOT_INIT) { + verbose("R%d !read_ok\n", regno); + return -EACCES; + } + + if (arg_type == ARG_PTR_TO_STACK || arg_type == ARG_PTR_TO_MAP_KEY || + arg_type == ARG_PTR_TO_MAP_VALUE) { + expected_type = PTR_TO_STACK; + } else if (arg_type == ARG_CONST_STACK_SIZE) { + expected_type = CONST_IMM; + } else if (arg_type == ARG_CONST_MAP_PTR) { + expected_type = CONST_PTR_TO_MAP; + } else { + verbose("unsupported arg_type %d\n", arg_type); + return -EFAULT; + } + + if (reg->type != expected_type) { + verbose("R%d type=%s expected=%s\n", regno, + reg_type_str[reg->type], reg_type_str[expected_type]); + return -EACCES; + } + + if (arg_type == ARG_CONST_MAP_PTR) { + /* bpf_map_xxx(map_ptr) call: remember that map_ptr */ + *mapp = reg->map_ptr; + + } else if (arg_type == ARG_PTR_TO_MAP_KEY) { + /* bpf_map_xxx(..., map_ptr, ..., key) call: + * check that [key, key + map->key_size) are within + * stack limits and initialized + */ + if (!*mapp) { + /* in function declaration map_ptr must come before + * map_key, so that it's verified and known before + * we have to check map_key here. Otherwise it means + * that kernel subsystem misconfigured verifier + */ + verbose("invalid map_ptr to access map->key\n"); + return -EACCES; + } + err = check_stack_boundary(env, regno, (*mapp)->key_size); + + } else if (arg_type == ARG_PTR_TO_MAP_VALUE) { + /* bpf_map_xxx(..., map_ptr, ..., value) call: + * check [value, value + map->value_size) validity + */ + if (!*mapp) { + /* kernel subsystem misconfigured verifier */ + verbose("invalid map_ptr to access map->value\n"); + return -EACCES; + } + err = check_stack_boundary(env, regno, (*mapp)->value_size); + + } else if (arg_type == ARG_CONST_STACK_SIZE) { + /* bpf_xxx(..., buf, len) call will access 'len' bytes + * from stack pointer 'buf'. Check it + * note: regno == len, regno - 1 == buf + */ + if (regno == 0) { + /* kernel subsystem misconfigured verifier */ + verbose("ARG_CONST_STACK_SIZE cannot be first argument\n"); + return -EACCES; + } + err = check_stack_boundary(env, regno - 1, reg->imm); + } + + return err; +} + +static int check_call(struct verifier_env *env, int func_id) +{ + struct verifier_state *state = &env->cur_state; + const struct bpf_func_proto *fn = NULL; + struct reg_state *regs = state->regs; + struct bpf_map *map = NULL; + struct reg_state *reg; + int i, err; + + /* find function prototype */ + if (func_id < 0 || func_id >= __BPF_FUNC_MAX_ID) { + verbose("invalid func %d\n", func_id); + return -EINVAL; + } + + if (env->prog->aux->ops->get_func_proto) + fn = env->prog->aux->ops->get_func_proto(func_id); + + if (!fn) { + verbose("unknown func %d\n", func_id); + return -EINVAL; + } + + /* eBPF programs must be GPL compatible to use GPL-ed functions */ + if (!env->prog->aux->is_gpl_compatible && fn->gpl_only) { + verbose("cannot call GPL only function from proprietary program\n"); + return -EINVAL; + } + + /* check args */ + err = check_func_arg(env, BPF_REG_1, fn->arg1_type, &map); + if (err) + return err; + err = check_func_arg(env, BPF_REG_2, fn->arg2_type, &map); + if (err) + return err; + err = check_func_arg(env, BPF_REG_3, fn->arg3_type, &map); + if (err) + return err; + err = check_func_arg(env, BPF_REG_4, fn->arg4_type, &map); + if (err) + return err; + err = check_func_arg(env, BPF_REG_5, fn->arg5_type, &map); + if (err) + return err; + + /* reset caller saved regs */ + for (i = 0; i < CALLER_SAVED_REGS; i++) { + reg = regs + caller_saved[i]; + reg->type = NOT_INIT; + reg->imm = 0; + } + + /* update return register */ + if (fn->ret_type == RET_INTEGER) { + regs[BPF_REG_0].type = UNKNOWN_VALUE; + } 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; + /* remember map_ptr, so that check_map_access() + * can check 'value_size' boundary of memory access + * to map element returned from bpf_map_lookup_elem() + */ + if (map == NULL) { + verbose("kernel subsystem misconfigured verifier\n"); + return -EINVAL; + } + regs[BPF_REG_0].map_ptr = map; + } else { + verbose("unknown return type %d of func %d\n", + fn->ret_type, func_id); + return -EINVAL; + } + return 0; +} + +/* check validity of 32-bit and 64-bit arithmetic operations */ +static int check_alu_op(struct reg_state *regs, struct bpf_insn *insn) +{ + u8 opcode = BPF_OP(insn->code); + int err; + + if (opcode == BPF_END || opcode == BPF_NEG) { + if (opcode == BPF_NEG) { + if (BPF_SRC(insn->code) != 0 || + insn->src_reg != BPF_REG_0 || + insn->off != 0 || insn->imm != 0) { + verbose("BPF_NEG uses reserved fields\n"); + return -EINVAL; + } + } else { + if (insn->src_reg != BPF_REG_0 || insn->off != 0 || + (insn->imm != 16 && insn->imm != 32 && insn->imm != 64)) { + verbose("BPF_END uses reserved fields\n"); + return -EINVAL; + } + } + + /* check src operand */ + err = check_reg_arg(regs, insn->dst_reg, SRC_OP); + if (err) + return err; + + /* check dest operand */ + err = check_reg_arg(regs, insn->dst_reg, DST_OP); + if (err) + return err; + + } else if (opcode == BPF_MOV) { + + if (BPF_SRC(insn->code) == BPF_X) { + if (insn->imm != 0 || insn->off != 0) { + verbose("BPF_MOV uses reserved fields\n"); + return -EINVAL; + } + + /* check src operand */ + err = check_reg_arg(regs, insn->src_reg, SRC_OP); + if (err) + return err; + } else { + if (insn->src_reg != BPF_REG_0 || insn->off != 0) { + verbose("BPF_MOV uses reserved fields\n"); + return -EINVAL; + } + } + + /* check dest operand */ + err = check_reg_arg(regs, insn->dst_reg, DST_OP); + if (err) + return err; + + if (BPF_SRC(insn->code) == BPF_X) { + if (BPF_CLASS(insn->code) == BPF_ALU64) { + /* case: R1 = R2 + * copy register state to dest reg + */ + regs[insn->dst_reg] = regs[insn->src_reg]; + } else { + regs[insn->dst_reg].type = UNKNOWN_VALUE; + regs[insn->dst_reg].map_ptr = NULL; + } + } else { + /* case: R = imm + * remember the value we stored into this reg + */ + regs[insn->dst_reg].type = CONST_IMM; + regs[insn->dst_reg].imm = insn->imm; + } + + } else if (opcode > BPF_END) { + verbose("invalid BPF_ALU opcode %x\n", opcode); + return -EINVAL; + + } else { /* all other ALU ops: and, sub, xor, add, ... */ + + bool stack_relative = false; + + if (BPF_SRC(insn->code) == BPF_X) { + if (insn->imm != 0 || insn->off != 0) { + verbose("BPF_ALU uses reserved fields\n"); + return -EINVAL; + } + /* check src1 operand */ + err = check_reg_arg(regs, insn->src_reg, SRC_OP); + if (err) + return err; + } else { + if (insn->src_reg != BPF_REG_0 || insn->off != 0) { + verbose("BPF_ALU uses reserved fields\n"); + return -EINVAL; + } + } + + /* check src2 operand */ + err = check_reg_arg(regs, insn->dst_reg, SRC_OP); + if (err) + return err; + + if ((opcode == BPF_MOD || opcode == BPF_DIV) && + BPF_SRC(insn->code) == BPF_K && insn->imm == 0) { + verbose("div by zero\n"); + return -EINVAL; + } + + /* pattern match 'bpf_add Rx, imm' instruction */ + if (opcode == BPF_ADD && BPF_CLASS(insn->code) == BPF_ALU64 && + regs[insn->dst_reg].type == FRAME_PTR && + BPF_SRC(insn->code) == BPF_K) + stack_relative = true; + + /* check dest operand */ + err = check_reg_arg(regs, insn->dst_reg, DST_OP); + if (err) + return err; + + if (stack_relative) { + regs[insn->dst_reg].type = PTR_TO_STACK; + regs[insn->dst_reg].imm = insn->imm; + } + } + + return 0; +} + +static int check_cond_jmp_op(struct verifier_env *env, + struct bpf_insn *insn, int *insn_idx) +{ + struct reg_state *regs = env->cur_state.regs; + struct verifier_state *other_branch; + u8 opcode = BPF_OP(insn->code); + int err; + + if (opcode > BPF_EXIT) { + verbose("invalid BPF_JMP opcode %x\n", opcode); + return -EINVAL; + } + + if (BPF_SRC(insn->code) == BPF_X) { + if (insn->imm != 0) { + verbose("BPF_JMP uses reserved fields\n"); + return -EINVAL; + } + + /* check src1 operand */ + err = check_reg_arg(regs, insn->src_reg, SRC_OP); + if (err) + return err; + } else { + if (insn->src_reg != BPF_REG_0) { + verbose("BPF_JMP uses reserved fields\n"); + return -EINVAL; + } + } + + /* check src2 operand */ + err = check_reg_arg(regs, insn->dst_reg, SRC_OP); + if (err) + return err; + + /* detect if R == 0 where R was initialized to zero earlier */ + if (BPF_SRC(insn->code) == BPF_K && + (opcode == BPF_JEQ || opcode == BPF_JNE) && + regs[insn->dst_reg].type == CONST_IMM && + regs[insn->dst_reg].imm == insn->imm) { + if (opcode == BPF_JEQ) { + /* if (imm == imm) goto pc+off; + * only follow the goto, ignore fall-through + */ + *insn_idx += insn->off; + return 0; + } else { + /* if (imm != imm) goto pc+off; + * only follow fall-through branch, since + * that's where the program will go + */ + return 0; + } + } + + other_branch = push_stack(env, *insn_idx + insn->off + 1, *insn_idx); + if (!other_branch) + return -EFAULT; + + /* detect if R == 0 where R is returned value from bpf_map_lookup_elem() */ + if (BPF_SRC(insn->code) == BPF_K && + insn->imm == 0 && (opcode == BPF_JEQ || + opcode == BPF_JNE) && + regs[insn->dst_reg].type == PTR_TO_MAP_VALUE_OR_NULL) { + if (opcode == BPF_JEQ) { + /* next fallthrough insn can access memory via + * this register + */ + regs[insn->dst_reg].type = PTR_TO_MAP_VALUE; + /* branch targer cannot access it, since reg == 0 */ + other_branch->regs[insn->dst_reg].type = CONST_IMM; + other_branch->regs[insn->dst_reg].imm = 0; + } else { + other_branch->regs[insn->dst_reg].type = PTR_TO_MAP_VALUE; + regs[insn->dst_reg].type = CONST_IMM; + regs[insn->dst_reg].imm = 0; + } + } else if (BPF_SRC(insn->code) == BPF_K && + (opcode == BPF_JEQ || opcode == BPF_JNE)) { + + if (opcode == BPF_JEQ) { + /* detect if (R == imm) goto + * and in the target state recognize that R = imm + */ + other_branch->regs[insn->dst_reg].type = CONST_IMM; + other_branch->regs[insn->dst_reg].imm = insn->imm; + } else { + /* detect if (R != imm) goto + * and in the fall-through state recognize that R = imm + */ + regs[insn->dst_reg].type = CONST_IMM; + regs[insn->dst_reg].imm = insn->imm; + } + } + if (log_level) + print_verifier_state(env); + return 0; +} + +/* return the map pointer stored inside BPF_LD_IMM64 instruction */ +static struct bpf_map *ld_imm64_to_map_ptr(struct bpf_insn *insn) +{ + u64 imm64 = ((u64) (u32) insn[0].imm) | ((u64) (u32) insn[1].imm) << 32; + + return (struct bpf_map *) (unsigned long) imm64; +} + +/* verify BPF_LD_IMM64 instruction */ +static int check_ld_imm(struct verifier_env *env, struct bpf_insn *insn) +{ + struct reg_state *regs = env->cur_state.regs; + int err; + + if (BPF_SIZE(insn->code) != BPF_DW) { + verbose("invalid BPF_LD_IMM insn\n"); + return -EINVAL; + } + if (insn->off != 0) { + verbose("BPF_LD_IMM64 uses reserved fields\n"); + return -EINVAL; + } + + err = check_reg_arg(regs, insn->dst_reg, DST_OP); + if (err) + return err; + + if (insn->src_reg == 0) + /* generic move 64-bit immediate into a register */ + return 0; + + /* replace_map_fd_with_map_ptr() should have caught bad ld_imm64 */ + BUG_ON(insn->src_reg != BPF_PSEUDO_MAP_FD); + + regs[insn->dst_reg].type = CONST_PTR_TO_MAP; + regs[insn->dst_reg].map_ptr = ld_imm64_to_map_ptr(insn); + return 0; +} + +/* non-recursive DFS pseudo code + * 1 procedure DFS-iterative(G,v): + * 2 label v as discovered + * 3 let S be a stack + * 4 S.push(v) + * 5 while S is not empty + * 6 t <- S.pop() + * 7 if t is what we're looking for: + * 8 return t + * 9 for all edges e in G.adjacentEdges(t) do + * 10 if edge e is already labelled + * 11 continue with the next edge + * 12 w <- G.adjacentVertex(t,e) + * 13 if vertex w is not discovered and not explored + * 14 label e as tree-edge + * 15 label w as discovered + * 16 S.push(w) + * 17 continue at 5 + * 18 else if vertex w is discovered + * 19 label e as back-edge + * 20 else + * 21 // vertex w is explored + * 22 label e as forward- or cross-edge + * 23 label t as explored + * 24 S.pop() + * + * convention: + * 0x10 - discovered + * 0x11 - discovered and fall-through edge labelled + * 0x12 - discovered and fall-through and branch edges labelled + * 0x20 - explored + */ + +enum { + DISCOVERED = 0x10, + EXPLORED = 0x20, + FALLTHROUGH = 1, + BRANCH = 2, +}; + +#define STATE_LIST_MARK ((struct verifier_state_list *) -1L) + +static int *insn_stack; /* stack of insns to process */ +static int cur_stack; /* current stack index */ +static int *insn_state; + +/* t, w, e - match pseudo-code above: + * t - index of current instruction + * w - next instruction + * e - edge + */ +static int push_insn(int t, int w, int e, struct verifier_env *env) +{ + if (e == FALLTHROUGH && insn_state[t] >= (DISCOVERED | FALLTHROUGH)) + return 0; + + if (e == BRANCH && insn_state[t] >= (DISCOVERED | BRANCH)) + return 0; + + if (w < 0 || w >= env->prog->len) { + verbose("jump out of range from insn %d to %d\n", t, w); + return -EINVAL; + } + + if (e == BRANCH) + /* mark branch target for state pruning */ + env->explored_states[w] = STATE_LIST_MARK; + + if (insn_state[w] == 0) { + /* tree-edge */ + insn_state[t] = DISCOVERED | e; + insn_state[w] = DISCOVERED; + if (cur_stack >= env->prog->len) + return -E2BIG; + insn_stack[cur_stack++] = w; + return 1; + } else if ((insn_state[w] & 0xF0) == DISCOVERED) { + verbose("back-edge from insn %d to %d\n", t, w); + return -EINVAL; + } else if (insn_state[w] == EXPLORED) { + /* forward- or cross-edge */ + insn_state[t] = DISCOVERED | e; + } else { + verbose("insn state internal bug\n"); + return -EFAULT; + } + return 0; +} + +/* non-recursive depth-first-search to detect loops in BPF program + * loop == back-edge in directed graph + */ +static int check_cfg(struct verifier_env *env) +{ + struct bpf_insn *insns = env->prog->insnsi; + int insn_cnt = env->prog->len; + int ret = 0; + int i, t; + + insn_state = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL); + if (!insn_state) + return -ENOMEM; + + insn_stack = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL); + if (!insn_stack) { + kfree(insn_state); + return -ENOMEM; + } + + insn_state[0] = DISCOVERED; /* mark 1st insn as discovered */ + insn_stack[0] = 0; /* 0 is the first instruction */ + cur_stack = 1; + +peek_stack: + if (cur_stack == 0) + goto check_state; + t = insn_stack[cur_stack - 1]; + + if (BPF_CLASS(insns[t].code) == BPF_JMP) { + u8 opcode = BPF_OP(insns[t].code); + + if (opcode == BPF_EXIT) { + goto mark_explored; + } else if (opcode == BPF_CALL) { + ret = push_insn(t, t + 1, FALLTHROUGH, env); + if (ret == 1) + goto peek_stack; + else if (ret < 0) + goto err_free; + } else if (opcode == BPF_JA) { + if (BPF_SRC(insns[t].code) != BPF_K) { + ret = -EINVAL; + goto err_free; + } + /* unconditional jump with single edge */ + ret = push_insn(t, t + insns[t].off + 1, + FALLTHROUGH, env); + if (ret == 1) + goto peek_stack; + else if (ret < 0) + goto err_free; + /* tell verifier to check for equivalent states + * after every call and jump + */ + env->explored_states[t + 1] = STATE_LIST_MARK; + } else { + /* conditional jump with two edges */ + ret = push_insn(t, t + 1, FALLTHROUGH, env); + if (ret == 1) + goto peek_stack; + else if (ret < 0) + goto err_free; + + ret = push_insn(t, t + insns[t].off + 1, BRANCH, env); + if (ret == 1) + goto peek_stack; + else if (ret < 0) + goto err_free; + } + } else { + /* all other non-branch instructions with single + * fall-through edge + */ + ret = push_insn(t, t + 1, FALLTHROUGH, env); + if (ret == 1) + goto peek_stack; + else if (ret < 0) + goto err_free; + } + +mark_explored: + insn_state[t] = EXPLORED; + if (cur_stack-- <= 0) { + verbose("pop stack internal bug\n"); + ret = -EFAULT; + goto err_free; + } + goto peek_stack; + +check_state: + for (i = 0; i < insn_cnt; i++) { + if (insn_state[i] != EXPLORED) { + verbose("unreachable insn %d\n", i); + ret = -EINVAL; + goto err_free; + } + } + ret = 0; /* cfg looks good */ + +err_free: + kfree(insn_state); + kfree(insn_stack); + return ret; +} + +/* compare two verifier states + * + * all states stored in state_list are known to be valid, since + * verifier reached 'bpf_exit' instruction through them + * + * this function is called when verifier exploring different branches of + * execution popped from the state stack. If it sees an old state that has + * more strict register state and more strict stack state then this execution + * branch doesn't need to be explored further, since verifier already + * concluded that more strict state leads to valid finish. + * + * Therefore two states are equivalent if register state is more conservative + * and explored stack state is more conservative than the current one. + * Example: + * explored current + * (slot1=INV slot2=MISC) == (slot1=MISC slot2=MISC) + * (slot1=MISC slot2=MISC) != (slot1=INV slot2=MISC) + * + * In other words if current stack state (one being explored) has more + * valid slots than old one that already passed validation, it means + * the verifier can stop exploring and conclude that current state is valid too + * + * Similarly with registers. If explored state has register type as invalid + * whereas register type in current state is meaningful, it means that + * the current state will reach 'bpf_exit' instruction safely + */ +static bool states_equal(struct verifier_state *old, struct verifier_state *cur) +{ + int i; + + for (i = 0; i < MAX_BPF_REG; i++) { + if (memcmp(&old->regs[i], &cur->regs[i], + sizeof(old->regs[0])) != 0) { + if (old->regs[i].type == NOT_INIT || + old->regs[i].type == UNKNOWN_VALUE) + continue; + return false; + } + } + + for (i = 0; i < MAX_BPF_STACK; i++) { + if (memcmp(&old->stack[i], &cur->stack[i], + sizeof(old->stack[0])) != 0) { + if (old->stack[i].stype == STACK_INVALID) + continue; + return false; + } + } + return true; +} + +static int is_state_visited(struct verifier_env *env, int insn_idx) +{ + struct verifier_state_list *new_sl; + struct verifier_state_list *sl; + + sl = env->explored_states[insn_idx]; + if (!sl) + /* this 'insn_idx' instruction wasn't marked, so we will not + * be doing state search here + */ + return 0; + + while (sl != STATE_LIST_MARK) { + if (states_equal(&sl->state, &env->cur_state)) + /* reached equivalent register/stack state, + * prune the search + */ + return 1; + sl = sl->next; + } + + /* there were no equivalent states, remember current one. + * technically the current state is not proven to be safe yet, + * but it will either reach bpf_exit (which means it's safe) or + * it will be rejected. Since there are no loops, we won't be + * seeing this 'insn_idx' instruction again on the way to bpf_exit + */ + new_sl = kmalloc(sizeof(struct verifier_state_list), GFP_USER); + if (!new_sl) + return -ENOMEM; + + /* add new state to the head of linked list */ + memcpy(&new_sl->state, &env->cur_state, sizeof(env->cur_state)); + new_sl->next = env->explored_states[insn_idx]; + env->explored_states[insn_idx] = new_sl; + return 0; +} + +static int do_check(struct verifier_env *env) +{ + struct verifier_state *state = &env->cur_state; + struct bpf_insn *insns = env->prog->insnsi; + struct reg_state *regs = state->regs; + int insn_cnt = env->prog->len; + int insn_idx, prev_insn_idx = 0; + int insn_processed = 0; + bool do_print_state = false; + + init_reg_state(regs); + insn_idx = 0; + for (;;) { + struct bpf_insn *insn; + u8 class; + int err; + + if (insn_idx >= insn_cnt) { + verbose("invalid insn idx %d insn_cnt %d\n", + insn_idx, insn_cnt); + return -EFAULT; + } + + insn = &insns[insn_idx]; + class = BPF_CLASS(insn->code); + + if (++insn_processed > 32768) { + verbose("BPF program is too large. Proccessed %d insn\n", + insn_processed); + return -E2BIG; + } + + err = is_state_visited(env, insn_idx); + if (err < 0) + return err; + if (err == 1) { + /* found equivalent state, can prune the search */ + if (log_level) { + if (do_print_state) + verbose("\nfrom %d to %d: safe\n", + prev_insn_idx, insn_idx); + else + verbose("%d: safe\n", insn_idx); + } + goto process_bpf_exit; + } + + if (log_level && do_print_state) { + verbose("\nfrom %d to %d:", prev_insn_idx, insn_idx); + print_verifier_state(env); + do_print_state = false; + } + + if (log_level) { + verbose("%d: ", insn_idx); + print_bpf_insn(insn); + } + + if (class == BPF_ALU || class == BPF_ALU64) { + err = check_alu_op(regs, insn); + if (err) + return err; + + } else if (class == BPF_LDX) { + if (BPF_MODE(insn->code) != BPF_MEM || + insn->imm != 0) { + verbose("BPF_LDX uses reserved fields\n"); + return -EINVAL; + } + /* check src operand */ + err = check_reg_arg(regs, insn->src_reg, SRC_OP); + if (err) + return err; + + err = check_reg_arg(regs, insn->dst_reg, DST_OP_NO_MARK); + if (err) + return err; + + /* check that memory (src_reg + off) is readable, + * the state of dst_reg will be updated by this func + */ + err = check_mem_access(env, insn->src_reg, insn->off, + BPF_SIZE(insn->code), BPF_READ, + insn->dst_reg); + if (err) + return err; + + } else if (class == BPF_STX) { + if (BPF_MODE(insn->code) == BPF_XADD) { + err = check_xadd(env, insn); + if (err) + return err; + insn_idx++; + continue; + } + + if (BPF_MODE(insn->code) != BPF_MEM || + insn->imm != 0) { + verbose("BPF_STX uses reserved fields\n"); + return -EINVAL; + } + /* check src1 operand */ + err = check_reg_arg(regs, insn->src_reg, SRC_OP); + if (err) + return err; + /* check src2 operand */ + err = check_reg_arg(regs, insn->dst_reg, SRC_OP); + if (err) + return err; + + /* check that memory (dst_reg + off) is writeable */ + err = check_mem_access(env, insn->dst_reg, insn->off, + BPF_SIZE(insn->code), BPF_WRITE, + insn->src_reg); + if (err) + return err; + + } else if (class == BPF_ST) { + if (BPF_MODE(insn->code) != BPF_MEM || + insn->src_reg != BPF_REG_0) { + verbose("BPF_ST uses reserved fields\n"); + return -EINVAL; + } + /* check src operand */ + err = check_reg_arg(regs, insn->dst_reg, SRC_OP); + if (err) + return err; + + /* check that memory (dst_reg + off) is writeable */ + err = check_mem_access(env, insn->dst_reg, insn->off, + BPF_SIZE(insn->code), BPF_WRITE, + -1); + if (err) + return err; + + } else if (class == BPF_JMP) { + u8 opcode = BPF_OP(insn->code); + + if (opcode == BPF_CALL) { + if (BPF_SRC(insn->code) != BPF_K || + insn->off != 0 || + insn->src_reg != BPF_REG_0 || + insn->dst_reg != BPF_REG_0) { + verbose("BPF_CALL uses reserved fields\n"); + return -EINVAL; + } + + err = check_call(env, insn->imm); + if (err) + return err; + + } else if (opcode == BPF_JA) { + if (BPF_SRC(insn->code) != BPF_K || + insn->imm != 0 || + insn->src_reg != BPF_REG_0 || + insn->dst_reg != BPF_REG_0) { + verbose("BPF_JA uses reserved fields\n"); + return -EINVAL; + } + + insn_idx += insn->off + 1; + continue; + + } else if (opcode == BPF_EXIT) { + if (BPF_SRC(insn->code) != BPF_K || + insn->imm != 0 || + insn->src_reg != BPF_REG_0 || + insn->dst_reg != BPF_REG_0) { + verbose("BPF_EXIT uses reserved fields\n"); + return -EINVAL; + } + + /* eBPF calling convetion is such that R0 is used + * to return the value from eBPF program. + * Make sure that it's readable at this time + * of bpf_exit, which means that program wrote + * something into it earlier + */ + err = check_reg_arg(regs, BPF_REG_0, SRC_OP); + if (err) + return err; + +process_bpf_exit: + insn_idx = pop_stack(env, &prev_insn_idx); + if (insn_idx < 0) { + break; + } else { + do_print_state = true; + continue; + } + } else { + err = check_cond_jmp_op(env, insn, &insn_idx); + if (err) + return err; + } + } else if (class == BPF_LD) { + u8 mode = BPF_MODE(insn->code); + + if (mode == BPF_ABS || mode == BPF_IND) { + verbose("LD_ABS is not supported yet\n"); + return -EINVAL; + } else if (mode == BPF_IMM) { + err = check_ld_imm(env, insn); + if (err) + return err; + + insn_idx++; + } else { + verbose("invalid BPF_LD mode\n"); + return -EINVAL; + } + } else { + verbose("unknown insn class %d\n", class); + return -EINVAL; + } + + insn_idx++; + } + + return 0; +} + +/* look for pseudo eBPF instructions that access map FDs and + * replace them with actual map pointers + */ +static int replace_map_fd_with_map_ptr(struct verifier_env *env) +{ + struct bpf_insn *insn = env->prog->insnsi; + int insn_cnt = env->prog->len; + int i, j; + + for (i = 0; i < insn_cnt; i++, insn++) { + if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW)) { + struct bpf_map *map; + struct fd f; + + if (i == insn_cnt - 1 || insn[1].code != 0 || + insn[1].dst_reg != 0 || insn[1].src_reg != 0 || + insn[1].off != 0) { + verbose("invalid bpf_ld_imm64 insn\n"); + return -EINVAL; + } + + if (insn->src_reg == 0) + /* valid generic load 64-bit imm */ + goto next_insn; + + if (insn->src_reg != BPF_PSEUDO_MAP_FD) { + verbose("unrecognized bpf_ld_imm64 insn\n"); + return -EINVAL; + } + + f = fdget(insn->imm); + + map = bpf_map_get(f); + if (IS_ERR(map)) { + verbose("fd %d is not pointing to valid bpf_map\n", + insn->imm); + fdput(f); + return PTR_ERR(map); + } + + /* store map pointer inside BPF_LD_IMM64 instruction */ + insn[0].imm = (u32) (unsigned long) map; + insn[1].imm = ((u64) (unsigned long) map) >> 32; + + /* check whether we recorded this map already */ + for (j = 0; j < env->used_map_cnt; j++) + if (env->used_maps[j] == map) { + fdput(f); + goto next_insn; + } + + if (env->used_map_cnt >= MAX_USED_MAPS) { + fdput(f); + return -E2BIG; + } + + /* remember this map */ + env->used_maps[env->used_map_cnt++] = map; + + /* hold the map. If the program is rejected by verifier, + * the map will be released by release_maps() or it + * will be used by the valid program until it's unloaded + * and all maps are released in free_bpf_prog_info() + */ + atomic_inc(&map->refcnt); + + fdput(f); +next_insn: + insn++; + i++; + } + } + + /* now all pseudo BPF_LD_IMM64 instructions load valid + * 'struct bpf_map *' into a register instead of user map_fd. + * These pointers will be used later by verifier to validate map access. + */ + return 0; +} + +/* drop refcnt of maps used by the rejected program */ +static void release_maps(struct verifier_env *env) +{ + int i; + + for (i = 0; i < env->used_map_cnt; i++) + bpf_map_put(env->used_maps[i]); +} + +/* convert pseudo BPF_LD_IMM64 into generic BPF_LD_IMM64 */ +static void convert_pseudo_ld_imm64(struct verifier_env *env) +{ + struct bpf_insn *insn = env->prog->insnsi; + int insn_cnt = env->prog->len; + int i; + + for (i = 0; i < insn_cnt; i++, insn++) + if (insn->code == (BPF_LD | BPF_IMM | BPF_DW)) + insn->src_reg = 0; +} + +static void free_states(struct verifier_env *env) +{ + struct verifier_state_list *sl, *sln; + int i; + + if (!env->explored_states) + return; + + for (i = 0; i < env->prog->len; i++) { + sl = env->explored_states[i]; + + if (sl) + while (sl != STATE_LIST_MARK) { + sln = sl->next; + kfree(sl); + sl = sln; + } + } + + kfree(env->explored_states); +} + +int bpf_check(struct bpf_prog *prog, union bpf_attr *attr) +{ + char __user *log_ubuf = NULL; + struct verifier_env *env; + int ret = -EINVAL; + + if (prog->len <= 0 || prog->len > BPF_MAXINSNS) + return -E2BIG; + + /* 'struct verifier_env' can be global, but since it's not small, + * allocate/free it every time bpf_check() is called + */ + env = kzalloc(sizeof(struct verifier_env), GFP_KERNEL); + if (!env) + return -ENOMEM; + + env->prog = prog; + + /* grab the mutex to protect few globals used by verifier */ + mutex_lock(&bpf_verifier_lock); + + if (attr->log_level || attr->log_buf || attr->log_size) { + /* user requested verbose verifier output + * and supplied buffer to store the verification trace + */ + log_level = attr->log_level; + log_ubuf = (char __user *) (unsigned long) attr->log_buf; + log_size = attr->log_size; + log_len = 0; + + ret = -EINVAL; + /* log_* values have to be sane */ + if (log_size < 128 || log_size > UINT_MAX >> 8 || + log_level == 0 || log_ubuf == NULL) + goto free_env; + + ret = -ENOMEM; + log_buf = vmalloc(log_size); + if (!log_buf) + goto free_env; + } else { + log_level = 0; + } + + ret = replace_map_fd_with_map_ptr(env); + if (ret < 0) + goto skip_full_check; + + env->explored_states = kcalloc(prog->len, + sizeof(struct verifier_state_list *), + GFP_USER); + ret = -ENOMEM; + if (!env->explored_states) + goto skip_full_check; + + ret = check_cfg(env); + if (ret < 0) + goto skip_full_check; + + ret = do_check(env); + +skip_full_check: + while (pop_stack(env, NULL) >= 0); + free_states(env); + + if (log_level && log_len >= log_size - 1) { + BUG_ON(log_len >= log_size); + /* verifier log exceeded user supplied buffer */ + ret = -ENOSPC; + /* fall through to return what was recorded */ + } + + /* copy verifier log back to user space including trailing zero */ + if (log_level && copy_to_user(log_ubuf, log_buf, log_len + 1) != 0) { + ret = -EFAULT; + goto free_log_buf; + } + + if (ret == 0 && env->used_map_cnt) { + /* if program passed verifier, update used_maps in bpf_prog_info */ + prog->aux->used_maps = kmalloc_array(env->used_map_cnt, + sizeof(env->used_maps[0]), + GFP_KERNEL); + + if (!prog->aux->used_maps) { + ret = -ENOMEM; + goto free_log_buf; + } + + memcpy(prog->aux->used_maps, env->used_maps, + sizeof(env->used_maps[0]) * env->used_map_cnt); + prog->aux->used_map_cnt = env->used_map_cnt; + + /* program is valid. Convert pseudo bpf_ld_imm64 into generic + * bpf_ld_imm64 instructions + */ + convert_pseudo_ld_imm64(env); + } + +free_log_buf: + if (log_level) + vfree(log_buf); +free_env: + if (!prog->aux->used_maps) + /* if we didn't copy map pointers into bpf_prog_info, release + * them now. Otherwise free_bpf_prog_info() will release them. + */ + release_maps(env); + kfree(env); + mutex_unlock(&bpf_verifier_lock); + return ret; +} diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 940aced4ed00..136eceadeed1 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -185,7 +185,6 @@ static int need_forkexit_callback __read_mostly; static struct cftype cgroup_dfl_base_files[]; static struct cftype cgroup_legacy_base_files[]; -static void cgroup_put(struct cgroup *cgrp); static int rebind_subsystems(struct cgroup_root *dst_root, unsigned int ss_mask); static int cgroup_destroy_locked(struct cgroup *cgrp); @@ -195,7 +194,6 @@ static void css_release(struct percpu_ref *ref); static void kill_css(struct cgroup_subsys_state *css); static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[], bool is_add); -static void cgroup_pidlist_destroy_all(struct cgroup *cgrp); /* IDR wrappers which synchronize using cgroup_idr_lock */ static int cgroup_idr_alloc(struct idr *idr, void *ptr, int start, int end, @@ -331,14 +329,6 @@ bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor) return false; } -static int cgroup_is_releasable(const struct cgroup *cgrp) -{ - const int bits = - (1 << CGRP_RELEASABLE) | - (1 << CGRP_NOTIFY_ON_RELEASE); - return (cgrp->flags & bits) == bits; -} - static int notify_on_release(const struct cgroup *cgrp) { return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); @@ -394,12 +384,7 @@ static int notify_on_release(const struct cgroup *cgrp) ; \ else -/* the list of cgroups eligible for automatic release. Protected by - * release_list_lock */ -static LIST_HEAD(release_list); -static DEFINE_RAW_SPINLOCK(release_list_lock); static void cgroup_release_agent(struct work_struct *work); -static DECLARE_WORK(release_agent_work, cgroup_release_agent); static void check_for_release(struct cgroup *cgrp); /* @@ -498,7 +483,7 @@ static unsigned long css_set_hash(struct cgroup_subsys_state *css[]) return key; } -static void put_css_set_locked(struct css_set *cset, bool taskexit) +static void put_css_set_locked(struct css_set *cset) { struct cgrp_cset_link *link, *tmp_link; struct cgroup_subsys *ss; @@ -524,11 +509,7 @@ static void put_css_set_locked(struct css_set *cset, bool taskexit) /* @cgrp can't go away while we're holding css_set_rwsem */ if (list_empty(&cgrp->cset_links)) { cgroup_update_populated(cgrp, false); - if (notify_on_release(cgrp)) { - if (taskexit) - set_bit(CGRP_RELEASABLE, &cgrp->flags); - check_for_release(cgrp); - } + check_for_release(cgrp); } kfree(link); @@ -537,7 +518,7 @@ static void put_css_set_locked(struct css_set *cset, bool taskexit) kfree_rcu(cset, rcu_head); } -static void put_css_set(struct css_set *cset, bool taskexit) +static void put_css_set(struct css_set *cset) { /* * Ensure that the refcount doesn't hit zero while any readers @@ -548,7 +529,7 @@ static void put_css_set(struct css_set *cset, bool taskexit) return; down_write(&css_set_rwsem); - put_css_set_locked(cset, taskexit); + put_css_set_locked(cset); up_write(&css_set_rwsem); } @@ -969,14 +950,6 @@ static struct cgroup *task_cgroup_from_root(struct task_struct *task, * knows that the cgroup won't be removed, as cgroup_rmdir() * needs that mutex. * - * The fork and exit callbacks cgroup_fork() and cgroup_exit(), don't - * (usually) take cgroup_mutex. These are the two most performance - * critical pieces of code here. The exception occurs on cgroup_exit(), - * when a task in a notify_on_release cgroup exits. Then cgroup_mutex - * is taken, and if the cgroup count is zero, a usermode call made - * to the release agent with the name of the cgroup (path relative to - * the root of cgroup file system) as the argument. - * * A cgroup can only be deleted if both its 'count' of using tasks * is zero, and its list of 'children' cgroups is empty. Since all * tasks in the system use _some_ cgroup, and since there is always at @@ -1587,7 +1560,6 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp) INIT_LIST_HEAD(&cgrp->self.sibling); INIT_LIST_HEAD(&cgrp->self.children); INIT_LIST_HEAD(&cgrp->cset_links); - INIT_LIST_HEAD(&cgrp->release_list); INIT_LIST_HEAD(&cgrp->pidlists); mutex_init(&cgrp->pidlist_mutex); cgrp->self.cgroup = cgrp; @@ -1597,6 +1569,7 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp) INIT_LIST_HEAD(&cgrp->e_csets[ssid]); init_waitqueue_head(&cgrp->offline_waitq); + INIT_WORK(&cgrp->release_agent_work, cgroup_release_agent); } static void init_cgroup_root(struct cgroup_root *root, @@ -1634,7 +1607,8 @@ static int cgroup_setup_root(struct cgroup_root *root, unsigned int ss_mask) goto out; root_cgrp->id = ret; - ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release); + ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release, 0, + GFP_KERNEL); if (ret) goto out; @@ -2052,8 +2026,7 @@ static void cgroup_task_migrate(struct cgroup *old_cgrp, * task. As trading it for new_cset is protected by cgroup_mutex, * we're safe to drop it here; it will be freed under RCU. */ - set_bit(CGRP_RELEASABLE, &old_cgrp->flags); - put_css_set_locked(old_cset, false); + put_css_set_locked(old_cset); } /** @@ -2074,7 +2047,7 @@ static void cgroup_migrate_finish(struct list_head *preloaded_csets) cset->mg_src_cgrp = NULL; cset->mg_dst_cset = NULL; list_del_init(&cset->mg_preload_node); - put_css_set_locked(cset, false); + put_css_set_locked(cset); } up_write(&css_set_rwsem); } @@ -2168,8 +2141,8 @@ static int cgroup_migrate_prepare_dst(struct cgroup *dst_cgrp, if (src_cset == dst_cset) { src_cset->mg_src_cgrp = NULL; list_del_init(&src_cset->mg_preload_node); - put_css_set(src_cset, false); - put_css_set(dst_cset, false); + put_css_set(src_cset); + put_css_set(dst_cset); continue; } @@ -2178,7 +2151,7 @@ static int cgroup_migrate_prepare_dst(struct cgroup *dst_cgrp, if (list_empty(&dst_cset->mg_preload_node)) list_add(&dst_cset->mg_preload_node, &csets); else - put_css_set(dst_cset, false); + put_css_set(dst_cset); } list_splice_tail(&csets, preloaded_csets); @@ -3985,7 +3958,6 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, l = cgroup_pidlist_find_create(cgrp, type); if (!l) { - mutex_unlock(&cgrp->pidlist_mutex); pidlist_free(array); return -ENOMEM; } @@ -4174,7 +4146,6 @@ static u64 cgroup_read_notify_on_release(struct cgroup_subsys_state *css, static int cgroup_write_notify_on_release(struct cgroup_subsys_state *css, struct cftype *cft, u64 val) { - clear_bit(CGRP_RELEASABLE, &css->cgroup->flags); if (val) set_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags); else @@ -4352,6 +4323,7 @@ static void css_free_work_fn(struct work_struct *work) /* cgroup free path */ atomic_dec(&cgrp->root->nr_cgrps); cgroup_pidlist_destroy_all(cgrp); + cancel_work_sync(&cgrp->release_agent_work); if (cgroup_parent(cgrp)) { /* @@ -4511,7 +4483,7 @@ static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss, init_and_link_css(css, ss, cgrp); - err = percpu_ref_init(&css->refcnt, css_release); + err = percpu_ref_init(&css->refcnt, css_release, 0, GFP_KERNEL); if (err) goto err_free_css; @@ -4584,7 +4556,7 @@ static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, goto out_unlock; } - ret = percpu_ref_init(&cgrp->self.refcnt, css_release); + ret = percpu_ref_init(&cgrp->self.refcnt, css_release, 0, GFP_KERNEL); if (ret) goto out_free_cgrp; @@ -4814,19 +4786,12 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) for_each_css(css, ssid, cgrp) kill_css(css); - /* CSS_ONLINE is clear, remove from ->release_list for the last time */ - raw_spin_lock(&release_list_lock); - if (!list_empty(&cgrp->release_list)) - list_del_init(&cgrp->release_list); - raw_spin_unlock(&release_list_lock); - /* * Remove @cgrp directory along with the base files. @cgrp has an * extra ref on its kn. */ kernfs_remove(cgrp->kn); - set_bit(CGRP_RELEASABLE, &cgroup_parent(cgrp)->flags); check_for_release(cgroup_parent(cgrp)); /* put the base reference */ @@ -4843,13 +4808,10 @@ static int cgroup_rmdir(struct kernfs_node *kn) cgrp = cgroup_kn_lock_live(kn); if (!cgrp) return 0; - cgroup_get(cgrp); /* for @kn->priv clearing */ ret = cgroup_destroy_locked(cgrp); cgroup_kn_unlock(kn); - - cgroup_put(cgrp); return ret; } @@ -5053,12 +5015,9 @@ core_initcall(cgroup_wq_init); * - Print task's cgroup paths into seq_file, one line for each hierarchy * - Used for /proc/<pid>/cgroup. */ - -/* TODO: Use a proper seq_file iterator */ -int proc_cgroup_show(struct seq_file *m, void *v) +int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *tsk) { - struct pid *pid; - struct task_struct *tsk; char *buf, *path; int retval; struct cgroup_root *root; @@ -5068,14 +5027,6 @@ int proc_cgroup_show(struct seq_file *m, void *v) if (!buf) goto out; - retval = -ESRCH; - pid = m->private; - tsk = get_pid_task(pid, PIDTYPE_PID); - if (!tsk) - goto out_free; - - retval = 0; - mutex_lock(&cgroup_mutex); down_read(&css_set_rwsem); @@ -5105,11 +5056,10 @@ int proc_cgroup_show(struct seq_file *m, void *v) seq_putc(m, '\n'); } + retval = 0; out_unlock: up_read(&css_set_rwsem); mutex_unlock(&cgroup_mutex); - put_task_struct(tsk); -out_free: kfree(buf); out: return retval; @@ -5180,7 +5130,7 @@ void cgroup_post_fork(struct task_struct *child) int i; /* - * This may race against cgroup_enable_task_cg_links(). As that + * This may race against cgroup_enable_task_cg_lists(). As that * function sets use_task_css_set_links before grabbing * tasklist_lock and we just went through tasklist_lock to add * @child, it's guaranteed that either we see the set @@ -5195,7 +5145,7 @@ void cgroup_post_fork(struct task_struct *child) * when implementing operations which need to migrate all tasks of * a cgroup to another. * - * Note that if we lose to cgroup_enable_task_cg_links(), @child + * Note that if we lose to cgroup_enable_task_cg_lists(), @child * will remain in init_css_set. This is safe because all tasks are * in the init_css_set before cg_links is enabled and there's no * operation which transfers all tasks out of init_css_set. @@ -5279,30 +5229,14 @@ void cgroup_exit(struct task_struct *tsk) } if (put_cset) - put_css_set(cset, true); + put_css_set(cset); } static void check_for_release(struct cgroup *cgrp) { - if (cgroup_is_releasable(cgrp) && list_empty(&cgrp->cset_links) && - !css_has_online_children(&cgrp->self)) { - /* - * Control Group is currently removeable. If it's not - * already queued for a userspace notification, queue - * it now - */ - int need_schedule_work = 0; - - raw_spin_lock(&release_list_lock); - if (!cgroup_is_dead(cgrp) && - list_empty(&cgrp->release_list)) { - list_add(&cgrp->release_list, &release_list); - need_schedule_work = 1; - } - raw_spin_unlock(&release_list_lock); - if (need_schedule_work) - schedule_work(&release_agent_work); - } + if (notify_on_release(cgrp) && !cgroup_has_tasks(cgrp) && + !css_has_online_children(&cgrp->self) && !cgroup_is_dead(cgrp)) + schedule_work(&cgrp->release_agent_work); } /* @@ -5330,52 +5264,39 @@ static void check_for_release(struct cgroup *cgrp) */ static void cgroup_release_agent(struct work_struct *work) { - BUG_ON(work != &release_agent_work); + struct cgroup *cgrp = + container_of(work, struct cgroup, release_agent_work); + char *pathbuf = NULL, *agentbuf = NULL, *path; + char *argv[3], *envp[3]; + mutex_lock(&cgroup_mutex); - raw_spin_lock(&release_list_lock); - while (!list_empty(&release_list)) { - char *argv[3], *envp[3]; - int i; - char *pathbuf = NULL, *agentbuf = NULL, *path; - struct cgroup *cgrp = list_entry(release_list.next, - struct cgroup, - release_list); - list_del_init(&cgrp->release_list); - raw_spin_unlock(&release_list_lock); - pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); - if (!pathbuf) - goto continue_free; - path = cgroup_path(cgrp, pathbuf, PATH_MAX); - if (!path) - goto continue_free; - agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL); - if (!agentbuf) - goto continue_free; - - i = 0; - argv[i++] = agentbuf; - argv[i++] = path; - argv[i] = NULL; - - i = 0; - /* minimal command environment */ - envp[i++] = "HOME=/"; - envp[i++] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin"; - envp[i] = NULL; - - /* Drop the lock while we invoke the usermode helper, - * since the exec could involve hitting disk and hence - * be a slow process */ - mutex_unlock(&cgroup_mutex); - call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC); - mutex_lock(&cgroup_mutex); - continue_free: - kfree(pathbuf); - kfree(agentbuf); - raw_spin_lock(&release_list_lock); - } - raw_spin_unlock(&release_list_lock); + + pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); + agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL); + if (!pathbuf || !agentbuf) + goto out; + + path = cgroup_path(cgrp, pathbuf, PATH_MAX); + if (!path) + goto out; + + argv[0] = agentbuf; + argv[1] = path; + argv[2] = NULL; + + /* minimal command environment */ + envp[0] = "HOME=/"; + envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin"; + envp[2] = NULL; + + mutex_unlock(&cgroup_mutex); + call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC); + goto out_free; +out: mutex_unlock(&cgroup_mutex); +out_free: + kfree(agentbuf); + kfree(pathbuf); } static int __init cgroup_disable(char *str) @@ -5563,7 +5484,8 @@ static int cgroup_css_links_read(struct seq_file *seq, void *v) static u64 releasable_read(struct cgroup_subsys_state *css, struct cftype *cft) { - return test_bit(CGRP_RELEASABLE, &css->cgroup->flags); + return (!cgroup_has_tasks(css->cgroup) && + !css_has_online_children(&css->cgroup->self)); } static struct cftype debug_files[] = { diff --git a/kernel/configs/tiny.config b/kernel/configs/tiny.config new file mode 100644 index 000000000000..c2de56ab0fce --- /dev/null +++ b/kernel/configs/tiny.config @@ -0,0 +1,4 @@ +CONFIG_CC_OPTIMIZE_FOR_SIZE=y +CONFIG_KERNEL_XZ=y +CONFIG_OPTIMIZE_INLINING=y +CONFIG_SLOB=y diff --git a/kernel/cpu.c b/kernel/cpu.c index 81e2a388a0f6..356450f09c1f 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -79,6 +79,8 @@ static struct { /* Lockdep annotations for get/put_online_cpus() and cpu_hotplug_begin/end() */ #define cpuhp_lock_acquire_read() lock_map_acquire_read(&cpu_hotplug.dep_map) +#define cpuhp_lock_acquire_tryread() \ + lock_map_acquire_tryread(&cpu_hotplug.dep_map) #define cpuhp_lock_acquire() lock_map_acquire(&cpu_hotplug.dep_map) #define cpuhp_lock_release() lock_map_release(&cpu_hotplug.dep_map) @@ -91,10 +93,22 @@ void get_online_cpus(void) mutex_lock(&cpu_hotplug.lock); cpu_hotplug.refcount++; mutex_unlock(&cpu_hotplug.lock); - } EXPORT_SYMBOL_GPL(get_online_cpus); +bool try_get_online_cpus(void) +{ + if (cpu_hotplug.active_writer == current) + return true; + if (!mutex_trylock(&cpu_hotplug.lock)) + return false; + cpuhp_lock_acquire_tryread(); + cpu_hotplug.refcount++; + mutex_unlock(&cpu_hotplug.lock); + return true; +} +EXPORT_SYMBOL_GPL(try_get_online_cpus); + void put_online_cpus(void) { if (cpu_hotplug.active_writer == current) diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 22874d7cf2c0..1f107c74087b 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -365,13 +365,14 @@ static void cpuset_update_task_spread_flag(struct cpuset *cs, struct task_struct *tsk) { if (is_spread_page(cs)) - tsk->flags |= PF_SPREAD_PAGE; + task_set_spread_page(tsk); else - tsk->flags &= ~PF_SPREAD_PAGE; + task_clear_spread_page(tsk); + if (is_spread_slab(cs)) - tsk->flags |= PF_SPREAD_SLAB; + task_set_spread_slab(tsk); else - tsk->flags &= ~PF_SPREAD_SLAB; + task_clear_spread_slab(tsk); } /* @@ -2729,10 +2730,9 @@ void __cpuset_memory_pressure_bump(void) * and we take cpuset_mutex, keeping cpuset_attach() from changing it * anyway. */ -int proc_cpuset_show(struct seq_file *m, void *unused_v) +int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *tsk) { - struct pid *pid; - struct task_struct *tsk; char *buf, *p; struct cgroup_subsys_state *css; int retval; @@ -2742,24 +2742,16 @@ int proc_cpuset_show(struct seq_file *m, void *unused_v) if (!buf) goto out; - retval = -ESRCH; - pid = m->private; - tsk = get_pid_task(pid, PIDTYPE_PID); - if (!tsk) - goto out_free; - retval = -ENAMETOOLONG; rcu_read_lock(); css = task_css(tsk, cpuset_cgrp_id); p = cgroup_path(css->cgroup, buf, PATH_MAX); rcu_read_unlock(); if (!p) - goto out_put_task; + goto out_free; seq_puts(m, p); seq_putc(m, '\n'); retval = 0; -out_put_task: - put_task_struct(tsk); out_free: kfree(buf); out: diff --git a/kernel/crash_dump.c b/kernel/crash_dump.c index c766ee54c0b1..b64e238b553b 100644 --- a/kernel/crash_dump.c +++ b/kernel/crash_dump.c @@ -18,6 +18,7 @@ unsigned long saved_max_pfn; * it under CONFIG_CRASH_DUMP and not CONFIG_PROC_VMCORE. */ unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX; +EXPORT_SYMBOL_GPL(elfcorehdr_addr); /* * stores the size of elf header of crash image diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c index 97b67df8fbfe..f2a88de87a49 100644 --- a/kernel/events/callchain.c +++ b/kernel/events/callchain.c @@ -52,7 +52,7 @@ static void release_callchain_buffers(void) struct callchain_cpus_entries *entries; entries = callchain_cpus_entries; - rcu_assign_pointer(callchain_cpus_entries, NULL); + RCU_INIT_POINTER(callchain_cpus_entries, NULL); call_rcu(&entries->rcu_head, release_callchain_buffers_rcu); } diff --git a/kernel/events/core.c b/kernel/events/core.c index f9c1ed002dbc..094df8c0742d 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -47,6 +47,8 @@ #include <asm/irq_regs.h> +static struct workqueue_struct *perf_wq; + struct remote_function_call { struct task_struct *p; int (*func)(void *info); @@ -120,6 +122,13 @@ static int cpu_function_call(int cpu, int (*func) (void *info), void *info) return data.ret; } +#define EVENT_OWNER_KERNEL ((void *) -1) + +static bool is_kernel_event(struct perf_event *event) +{ + return event->owner == EVENT_OWNER_KERNEL; +} + #define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\ PERF_FLAG_FD_OUTPUT |\ PERF_FLAG_PID_CGROUP |\ @@ -392,14 +401,9 @@ perf_cgroup_match(struct perf_event *event) event->cgrp->css.cgroup); } -static inline void perf_put_cgroup(struct perf_event *event) -{ - css_put(&event->cgrp->css); -} - static inline void perf_detach_cgroup(struct perf_event *event) { - perf_put_cgroup(event); + css_put(&event->cgrp->css); event->cgrp = NULL; } @@ -902,13 +906,23 @@ static void put_ctx(struct perf_event_context *ctx) } } -static void unclone_ctx(struct perf_event_context *ctx) +/* + * This must be done under the ctx->lock, such as to serialize against + * context_equiv(), therefore we cannot call put_ctx() since that might end up + * calling scheduler related locks and ctx->lock nests inside those. + */ +static __must_check struct perf_event_context * +unclone_ctx(struct perf_event_context *ctx) { - if (ctx->parent_ctx) { - put_ctx(ctx->parent_ctx); + struct perf_event_context *parent_ctx = ctx->parent_ctx; + + lockdep_assert_held(&ctx->lock); + + if (parent_ctx) ctx->parent_ctx = NULL; - } ctx->generation++; + + return parent_ctx; } static u32 perf_event_pid(struct perf_event *event, struct task_struct *p) @@ -1375,6 +1389,45 @@ out: perf_event__header_size(tmp); } +/* + * User event without the task. + */ +static bool is_orphaned_event(struct perf_event *event) +{ + return event && !is_kernel_event(event) && !event->owner; +} + +/* + * Event has a parent but parent's task finished and it's + * alive only because of children holding refference. + */ +static bool is_orphaned_child(struct perf_event *event) +{ + return is_orphaned_event(event->parent); +} + +static void orphans_remove_work(struct work_struct *work); + +static void schedule_orphans_remove(struct perf_event_context *ctx) +{ + if (!ctx->task || ctx->orphans_remove_sched || !perf_wq) + return; + + if (queue_delayed_work(perf_wq, &ctx->orphans_remove, 1)) { + get_ctx(ctx); + ctx->orphans_remove_sched = true; + } +} + +static int __init perf_workqueue_init(void) +{ + perf_wq = create_singlethread_workqueue("perf"); + WARN(!perf_wq, "failed to create perf workqueue\n"); + return perf_wq ? 0 : -1; +} + +core_initcall(perf_workqueue_init); + static inline int event_filter_match(struct perf_event *event) { @@ -1424,6 +1477,9 @@ event_sched_out(struct perf_event *event, if (event->attr.exclusive || !cpuctx->active_oncpu) cpuctx->exclusive = 0; + if (is_orphaned_child(event)) + schedule_orphans_remove(ctx); + perf_pmu_enable(event->pmu); } @@ -1524,6 +1580,11 @@ retry: */ if (ctx->is_active) { raw_spin_unlock_irq(&ctx->lock); + /* + * Reload the task pointer, it might have been changed by + * a concurrent perf_event_context_sched_out(). + */ + task = ctx->task; goto retry; } @@ -1726,6 +1787,9 @@ event_sched_in(struct perf_event *event, if (event->attr.exclusive) cpuctx->exclusive = 1; + if (is_orphaned_child(event)) + schedule_orphans_remove(ctx); + out: perf_pmu_enable(event->pmu); @@ -1967,6 +2031,11 @@ retry: */ if (ctx->is_active) { raw_spin_unlock_irq(&ctx->lock); + /* + * Reload the task pointer, it might have been changed by + * a concurrent perf_event_context_sched_out(). + */ + task = ctx->task; goto retry; } @@ -2200,6 +2269,9 @@ static void ctx_sched_out(struct perf_event_context *ctx, static int context_equiv(struct perf_event_context *ctx1, struct perf_event_context *ctx2) { + lockdep_assert_held(&ctx1->lock); + lockdep_assert_held(&ctx2->lock); + /* Pinning disables the swap optimization */ if (ctx1->pin_count || ctx2->pin_count) return 0; @@ -2321,7 +2393,7 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn, next_parent = rcu_dereference(next_ctx->parent_ctx); /* If neither context have a parent context; they cannot be clones. */ - if (!parent || !next_parent) + if (!parent && !next_parent) goto unlock; if (next_parent == ctx || next_ctx == parent || next_parent == parent) { @@ -2933,6 +3005,7 @@ static int event_enable_on_exec(struct perf_event *event, */ static void perf_event_enable_on_exec(struct perf_event_context *ctx) { + struct perf_event_context *clone_ctx = NULL; struct perf_event *event; unsigned long flags; int enabled = 0; @@ -2964,7 +3037,7 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx) * Unclone this context if we enabled any event. */ if (enabled) - unclone_ctx(ctx); + clone_ctx = unclone_ctx(ctx); raw_spin_unlock(&ctx->lock); @@ -2974,6 +3047,9 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx) perf_event_context_sched_in(ctx, ctx->task); out: local_irq_restore(flags); + + if (clone_ctx) + put_ctx(clone_ctx); } void perf_event_exec(void) @@ -3068,6 +3144,7 @@ static void __perf_event_init_context(struct perf_event_context *ctx) INIT_LIST_HEAD(&ctx->flexible_groups); INIT_LIST_HEAD(&ctx->event_list); atomic_set(&ctx->refcount, 1); + INIT_DELAYED_WORK(&ctx->orphans_remove, orphans_remove_work); } static struct perf_event_context * @@ -3125,7 +3202,7 @@ errout: static struct perf_event_context * find_get_context(struct pmu *pmu, struct task_struct *task, int cpu) { - struct perf_event_context *ctx; + struct perf_event_context *ctx, *clone_ctx = NULL; struct perf_cpu_context *cpuctx; unsigned long flags; int ctxn, err; @@ -3159,9 +3236,12 @@ find_get_context(struct pmu *pmu, struct task_struct *task, int cpu) retry: ctx = perf_lock_task_context(task, ctxn, &flags); if (ctx) { - unclone_ctx(ctx); + clone_ctx = unclone_ctx(ctx); ++ctx->pin_count; raw_spin_unlock_irqrestore(&ctx->lock, flags); + + if (clone_ctx) + put_ctx(clone_ctx); } else { ctx = alloc_perf_context(pmu, task); err = -ENOMEM; @@ -3313,16 +3393,12 @@ static void free_event(struct perf_event *event) } /* - * Called when the last reference to the file is gone. + * Remove user event from the owner task. */ -static void put_event(struct perf_event *event) +static void perf_remove_from_owner(struct perf_event *event) { - struct perf_event_context *ctx = event->ctx; struct task_struct *owner; - if (!atomic_long_dec_and_test(&event->refcount)) - return; - rcu_read_lock(); owner = ACCESS_ONCE(event->owner); /* @@ -3355,6 +3431,20 @@ static void put_event(struct perf_event *event) mutex_unlock(&owner->perf_event_mutex); put_task_struct(owner); } +} + +/* + * Called when the last reference to the file is gone. + */ +static void put_event(struct perf_event *event) +{ + struct perf_event_context *ctx = event->ctx; + + if (!atomic_long_dec_and_test(&event->refcount)) + return; + + if (!is_kernel_event(event)) + perf_remove_from_owner(event); WARN_ON_ONCE(ctx->parent_ctx); /* @@ -3389,6 +3479,42 @@ static int perf_release(struct inode *inode, struct file *file) return 0; } +/* + * Remove all orphanes events from the context. + */ +static void orphans_remove_work(struct work_struct *work) +{ + struct perf_event_context *ctx; + struct perf_event *event, *tmp; + + ctx = container_of(work, struct perf_event_context, + orphans_remove.work); + + mutex_lock(&ctx->mutex); + list_for_each_entry_safe(event, tmp, &ctx->event_list, event_entry) { + struct perf_event *parent_event = event->parent; + + if (!is_orphaned_child(event)) + continue; + + perf_remove_from_context(event, true); + + mutex_lock(&parent_event->child_mutex); + list_del_init(&event->child_list); + mutex_unlock(&parent_event->child_mutex); + + free_event(event); + put_event(parent_event); + } + + raw_spin_lock_irq(&ctx->lock); + ctx->orphans_remove_sched = false; + raw_spin_unlock_irq(&ctx->lock); + mutex_unlock(&ctx->mutex); + + put_ctx(ctx); +} + u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running) { struct perf_event *child; @@ -3486,6 +3612,19 @@ static int perf_event_read_one(struct perf_event *event, return n * sizeof(u64); } +static bool is_event_hup(struct perf_event *event) +{ + bool no_children; + + if (event->state != PERF_EVENT_STATE_EXIT) + return false; + + mutex_lock(&event->child_mutex); + no_children = list_empty(&event->child_list); + mutex_unlock(&event->child_mutex); + return no_children; +} + /* * Read the performance event - simple non blocking version for now */ @@ -3527,7 +3666,12 @@ static unsigned int perf_poll(struct file *file, poll_table *wait) { struct perf_event *event = file->private_data; struct ring_buffer *rb; - unsigned int events = POLL_HUP; + unsigned int events = POLLHUP; + + poll_wait(file, &event->waitq, wait); + + if (is_event_hup(event)) + return events; /* * Pin the event->rb by taking event->mmap_mutex; otherwise @@ -3538,9 +3682,6 @@ static unsigned int perf_poll(struct file *file, poll_table *wait) if (rb) events = atomic_xchg(&rb->poll, 0); mutex_unlock(&event->mmap_mutex); - - poll_wait(file, &event->waitq, wait); - return events; } @@ -5804,7 +5945,7 @@ static void swevent_hlist_release(struct swevent_htable *swhash) if (!hlist) return; - rcu_assign_pointer(swhash->swevent_hlist, NULL); + RCU_INIT_POINTER(swhash->swevent_hlist, NULL); kfree_rcu(hlist, rcu_head); } @@ -7387,6 +7528,9 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, goto err; } + /* Mark owner so we could distinguish it from user events. */ + event->owner = EVENT_OWNER_KERNEL; + account_event(event); ctx = find_get_context(event->pmu, task, cpu); @@ -7474,6 +7618,12 @@ static void sync_child_event(struct perf_event *child_event, mutex_unlock(&parent_event->child_mutex); /* + * Make sure user/parent get notified, that we just + * lost one event. + */ + perf_event_wakeup(parent_event); + + /* * Release the parent event, if this was the last * reference to it. */ @@ -7507,13 +7657,16 @@ __perf_event_exit_task(struct perf_event *child_event, if (child_event->parent) { sync_child_event(child_event, child); free_event(child_event); + } else { + child_event->state = PERF_EVENT_STATE_EXIT; + perf_event_wakeup(child_event); } } static void perf_event_exit_task_context(struct task_struct *child, int ctxn) { struct perf_event *child_event, *next; - struct perf_event_context *child_ctx, *parent_ctx; + struct perf_event_context *child_ctx, *clone_ctx = NULL; unsigned long flags; if (likely(!child->perf_event_ctxp[ctxn])) { @@ -7540,28 +7693,16 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn) child->perf_event_ctxp[ctxn] = NULL; /* - * In order to avoid freeing: child_ctx->parent_ctx->task - * under perf_event_context::lock, grab another reference. - */ - parent_ctx = child_ctx->parent_ctx; - if (parent_ctx) - get_ctx(parent_ctx); - - /* * If this context is a clone; unclone it so it can't get * swapped to another process while we're removing all * the events from it. */ - unclone_ctx(child_ctx); + clone_ctx = unclone_ctx(child_ctx); update_context_time(child_ctx); raw_spin_unlock_irqrestore(&child_ctx->lock, flags); - /* - * Now that we no longer hold perf_event_context::lock, drop - * our extra child_ctx->parent_ctx reference. - */ - if (parent_ctx) - put_ctx(parent_ctx); + if (clone_ctx) + put_ctx(clone_ctx); /* * Report the task dead after unscheduling the events so that we @@ -7690,6 +7831,7 @@ inherit_event(struct perf_event *parent_event, struct perf_event *group_leader, struct perf_event_context *child_ctx) { + enum perf_event_active_state parent_state = parent_event->state; struct perf_event *child_event; unsigned long flags; @@ -7710,7 +7852,8 @@ inherit_event(struct perf_event *parent_event, if (IS_ERR(child_event)) return child_event; - if (!atomic_long_inc_not_zero(&parent_event->refcount)) { + if (is_orphaned_event(parent_event) || + !atomic_long_inc_not_zero(&parent_event->refcount)) { free_event(child_event); return NULL; } @@ -7722,7 +7865,7 @@ inherit_event(struct perf_event *parent_event, * not its attr.disabled bit. We hold the parent's mutex, * so we won't race with perf_event_{en, dis}able_family. */ - if (parent_event->state >= PERF_EVENT_STATE_INACTIVE) + if (parent_state >= PERF_EVENT_STATE_INACTIVE) child_event->state = PERF_EVENT_STATE_INACTIVE; else child_event->state = PERF_EVENT_STATE_OFF; @@ -7938,8 +8081,10 @@ int perf_event_init_task(struct task_struct *child) for_each_task_context_nr(ctxn) { ret = perf_event_init_context(child, ctxn); - if (ret) + if (ret) { + perf_event_free_task(child); return ret; + } } return 0; diff --git a/kernel/exit.c b/kernel/exit.c index 32c58f7433a3..5d30019ff953 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -115,32 +115,33 @@ static void __exit_signal(struct task_struct *tsk) if (tsk == sig->curr_target) sig->curr_target = next_thread(tsk); - /* - * Accumulate here the counters for all threads but the - * group leader as they die, so they can be added into - * the process-wide totals when those are taken. - * The group leader stays around as a zombie as long - * as there are other threads. When it gets reaped, - * the exit.c code will add its counts into these totals. - * We won't ever get here for the group leader, since it - * will have been the last reference on the signal_struct. - */ - task_cputime(tsk, &utime, &stime); - sig->utime += utime; - sig->stime += stime; - sig->gtime += task_gtime(tsk); - sig->min_flt += tsk->min_flt; - sig->maj_flt += tsk->maj_flt; - sig->nvcsw += tsk->nvcsw; - sig->nivcsw += tsk->nivcsw; - sig->inblock += task_io_get_inblock(tsk); - sig->oublock += task_io_get_oublock(tsk); - task_io_accounting_add(&sig->ioac, &tsk->ioac); - sig->sum_sched_runtime += tsk->se.sum_exec_runtime; } + /* + * Accumulate here the counters for all threads but the group leader + * as they die, so they can be added into the process-wide totals + * when those are taken. The group leader stays around as a zombie as + * long as there are other threads. When it gets reaped, the exit.c + * code will add its counts into these totals. We won't ever get here + * for the group leader, since it will have been the last reference on + * the signal_struct. + */ + task_cputime(tsk, &utime, &stime); + write_seqlock(&sig->stats_lock); + sig->utime += utime; + sig->stime += stime; + sig->gtime += task_gtime(tsk); + sig->min_flt += tsk->min_flt; + sig->maj_flt += tsk->maj_flt; + sig->nvcsw += tsk->nvcsw; + sig->nivcsw += tsk->nivcsw; + sig->inblock += task_io_get_inblock(tsk); + sig->oublock += task_io_get_oublock(tsk); + task_io_accounting_add(&sig->ioac, &tsk->ioac); + sig->sum_sched_runtime += tsk->se.sum_exec_runtime; sig->nr_threads--; __unhash_process(tsk, group_dead); + write_sequnlock(&sig->stats_lock); /* * Do this under ->siglock, we can race with another thread @@ -667,6 +668,7 @@ void do_exit(long code) { struct task_struct *tsk = current; int group_dead; + TASKS_RCU(int tasks_rcu_i); profile_task_exit(tsk); @@ -775,6 +777,7 @@ void do_exit(long code) */ flush_ptrace_hw_breakpoint(tsk); + TASKS_RCU(tasks_rcu_i = __srcu_read_lock(&tasks_rcu_exit_srcu)); exit_notify(tsk, group_dead); proc_exit_connector(tsk); #ifdef CONFIG_NUMA @@ -814,6 +817,7 @@ void do_exit(long code) if (tsk->nr_dirtied) __this_cpu_add(dirty_throttle_leaks, tsk->nr_dirtied); exit_rcu(); + TASKS_RCU(__srcu_read_unlock(&tasks_rcu_exit_srcu, tasks_rcu_i)); /* * The setting of TASK_RUNNING by try_to_wake_up() may be delayed @@ -1043,6 +1047,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) spin_lock_irq(&p->real_parent->sighand->siglock); psig = p->real_parent->signal; sig = p->signal; + write_seqlock(&psig->stats_lock); psig->cutime += tgutime + sig->cutime; psig->cstime += tgstime + sig->cstime; psig->cgtime += task_gtime(p) + sig->gtime + sig->cgtime; @@ -1065,6 +1070,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) psig->cmaxrss = maxrss; task_io_accounting_add(&psig->ioac, &p->ioac); task_io_accounting_add(&psig->ioac, &sig->ioac); + write_sequnlock(&psig->stats_lock); spin_unlock_irq(&p->real_parent->sighand->siglock); } diff --git a/kernel/fork.c b/kernel/fork.c index 0cf9cdb6e491..9b7d746d6d62 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -294,11 +294,18 @@ int __weak arch_dup_task_struct(struct task_struct *dst, return 0; } +void set_task_stack_end_magic(struct task_struct *tsk) +{ + unsigned long *stackend; + + stackend = end_of_stack(tsk); + *stackend = STACK_END_MAGIC; /* for overflow detection */ +} + static struct task_struct *dup_task_struct(struct task_struct *orig) { struct task_struct *tsk; struct thread_info *ti; - unsigned long *stackend; int node = tsk_fork_get_node(orig); int err; @@ -328,8 +335,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) setup_thread_stack(tsk, orig); clear_user_return_notifier(tsk); clear_tsk_need_resched(tsk); - stackend = end_of_stack(tsk); - *stackend = STACK_END_MAGIC; /* for overflow detection */ + set_task_stack_end_magic(tsk); #ifdef CONFIG_CC_STACKPROTECTOR tsk->stack_canary = get_random_int(); @@ -601,9 +607,8 @@ static void check_mm(struct mm_struct *mm) printk(KERN_ALERT "BUG: Bad rss-counter state " "mm:%p idx:%d val:%ld\n", mm, i, x); } - #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS - VM_BUG_ON(mm->pmd_huge_pte); + VM_BUG_ON_MM(mm->pmd_huge_pte, mm); #endif } @@ -1068,6 +1073,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->curr_target = tsk; init_sigpending(&sig->shared_pending); INIT_LIST_HEAD(&sig->posix_timers); + seqlock_init(&sig->stats_lock); hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); sig->real_timer.function = it_real_fn; @@ -1360,7 +1366,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, goto bad_fork_cleanup_policy; retval = audit_alloc(p); if (retval) - goto bad_fork_cleanup_policy; + goto bad_fork_cleanup_perf; /* copy all the process information */ shm_init_task(p); retval = copy_semundo(clone_flags, p); @@ -1566,8 +1572,9 @@ bad_fork_cleanup_semundo: exit_sem(p); bad_fork_cleanup_audit: audit_free(p); -bad_fork_cleanup_policy: +bad_fork_cleanup_perf: perf_event_free_task(p); +bad_fork_cleanup_policy: #ifdef CONFIG_NUMA mpol_put(p->mempolicy); bad_fork_cleanup_threadgroup_lock: diff --git a/kernel/futex.c b/kernel/futex.c index d3a9d946d0b7..815d7af2ffe8 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -2592,6 +2592,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, * shared futexes. We need to compare the keys: */ if (match_futex(&q.key, &key2)) { + queue_unlock(hb); ret = -EINVAL; goto out_put_keys; } diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig index d04ce8ac4399..cf66c5c8458e 100644 --- a/kernel/gcov/Kconfig +++ b/kernel/gcov/Kconfig @@ -35,7 +35,7 @@ config GCOV_KERNEL config GCOV_PROFILE_ALL bool "Profile entire Kernel" depends on GCOV_KERNEL - depends on SUPERH || S390 || X86 || PPC || MICROBLAZE + depends on SUPERH || S390 || X86 || PPC || MICROBLAZE || ARM default n ---help--- This options activates profiling for the entire kernel. diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index d269cecdfbf0..225086b2652e 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -55,6 +55,9 @@ config GENERIC_IRQ_CHIP config IRQ_DOMAIN bool +config HANDLE_DOMAIN_IRQ + bool + config IRQ_DOMAIN_DEBUG bool "Expose hardware/virtual IRQ mapping via debugfs" depends on IRQ_DOMAIN && DEBUG_FS diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 6223fab9a9d2..8fb52e9bddc1 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -342,6 +342,31 @@ static bool irq_check_poll(struct irq_desc *desc) return irq_wait_for_poll(desc); } +static bool irq_may_run(struct irq_desc *desc) +{ + unsigned int mask = IRQD_IRQ_INPROGRESS | IRQD_WAKEUP_ARMED; + + /* + * If the interrupt is not in progress and is not an armed + * wakeup interrupt, proceed. + */ + if (!irqd_has_set(&desc->irq_data, mask)) + return true; + + /* + * If the interrupt is an armed wakeup source, mark it pending + * and suspended, disable it and notify the pm core about the + * event. + */ + if (irq_pm_check_wakeup(desc)) + return false; + + /* + * Handle a potential concurrent poll on a different core. + */ + return irq_check_poll(desc); +} + /** * handle_simple_irq - Simple and software-decoded IRQs. * @irq: the interrupt number @@ -359,9 +384,8 @@ handle_simple_irq(unsigned int irq, struct irq_desc *desc) { raw_spin_lock(&desc->lock); - if (unlikely(irqd_irq_inprogress(&desc->irq_data))) - if (!irq_check_poll(desc)) - goto out_unlock; + if (!irq_may_run(desc)) + goto out_unlock; desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING); kstat_incr_irqs_this_cpu(irq, desc); @@ -412,9 +436,8 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc) raw_spin_lock(&desc->lock); mask_ack_irq(desc); - if (unlikely(irqd_irq_inprogress(&desc->irq_data))) - if (!irq_check_poll(desc)) - goto out_unlock; + if (!irq_may_run(desc)) + goto out_unlock; desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING); kstat_incr_irqs_this_cpu(irq, desc); @@ -485,9 +508,8 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc) raw_spin_lock(&desc->lock); - if (unlikely(irqd_irq_inprogress(&desc->irq_data))) - if (!irq_check_poll(desc)) - goto out; + if (!irq_may_run(desc)) + goto out; desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING); kstat_incr_irqs_this_cpu(irq, desc); @@ -541,19 +563,23 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc) raw_spin_lock(&desc->lock); desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING); + + if (!irq_may_run(desc)) { + desc->istate |= IRQS_PENDING; + mask_ack_irq(desc); + goto out_unlock; + } + /* - * If we're currently running this IRQ, or its disabled, - * we shouldn't process the IRQ. Mark it pending, handle - * the necessary masking and go out + * If its disabled or no action available then mask it and get + * out of here. */ - if (unlikely(irqd_irq_disabled(&desc->irq_data) || - irqd_irq_inprogress(&desc->irq_data) || !desc->action)) { - if (!irq_check_poll(desc)) { - desc->istate |= IRQS_PENDING; - mask_ack_irq(desc); - goto out_unlock; - } + if (irqd_irq_disabled(&desc->irq_data) || !desc->action) { + desc->istate |= IRQS_PENDING; + mask_ack_irq(desc); + goto out_unlock; } + kstat_incr_irqs_this_cpu(irq, desc); /* Start handling the irq */ @@ -602,18 +628,21 @@ void handle_edge_eoi_irq(unsigned int irq, struct irq_desc *desc) raw_spin_lock(&desc->lock); desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING); + + if (!irq_may_run(desc)) { + desc->istate |= IRQS_PENDING; + goto out_eoi; + } + /* - * If we're currently running this IRQ, or its disabled, - * we shouldn't process the IRQ. Mark it pending, handle - * the necessary masking and go out + * If its disabled or no action available then mask it and get + * out of here. */ - if (unlikely(irqd_irq_disabled(&desc->irq_data) || - irqd_irq_inprogress(&desc->irq_data) || !desc->action)) { - if (!irq_check_poll(desc)) { - desc->istate |= IRQS_PENDING; - goto out_eoi; - } + if (irqd_irq_disabled(&desc->irq_data) || !desc->action) { + desc->istate |= IRQS_PENDING; + goto out_eoi; } + kstat_incr_irqs_this_cpu(irq, desc); do { diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c index 1ef0606797c9..d5d0f7345c54 100644 --- a/kernel/irq/devres.c +++ b/kernel/irq/devres.c @@ -38,7 +38,7 @@ static int devm_irq_match(struct device *dev, void *res, void *data) * * Except for the extra @dev argument, this function takes the * same arguments and performs the same function as - * request_irq(). IRQs requested with this function will be + * request_threaded_irq(). IRQs requested with this function will be * automatically freed on driver detach. * * If an IRQ allocated with this function needs to be freed diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 099ea2e0eb88..4332d766619d 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -63,8 +63,8 @@ enum { extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq, unsigned long flags); -extern void __disable_irq(struct irq_desc *desc, unsigned int irq, bool susp); -extern void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume); +extern void __disable_irq(struct irq_desc *desc, unsigned int irq); +extern void __enable_irq(struct irq_desc *desc, unsigned int irq); extern int irq_startup(struct irq_desc *desc, bool resend); extern void irq_shutdown(struct irq_desc *desc); @@ -194,3 +194,15 @@ static inline void kstat_incr_irqs_this_cpu(unsigned int irq, struct irq_desc *d __this_cpu_inc(*desc->kstat_irqs); __this_cpu_inc(kstat.irqs_sum); } + +#ifdef CONFIG_PM_SLEEP +bool irq_pm_check_wakeup(struct irq_desc *desc); +void irq_pm_install_action(struct irq_desc *desc, struct irqaction *action); +void irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action); +#else +static inline bool irq_pm_check_wakeup(struct irq_desc *desc) { return false; } +static inline void +irq_pm_install_action(struct irq_desc *desc, struct irqaction *action) { } +static inline void +irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action) { } +#endif diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 1487a123db5c..a1782f88f0af 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -14,6 +14,7 @@ #include <linux/kernel_stat.h> #include <linux/radix-tree.h> #include <linux/bitmap.h> +#include <linux/irqdomain.h> #include "internals.h" @@ -336,6 +337,47 @@ int generic_handle_irq(unsigned int irq) } EXPORT_SYMBOL_GPL(generic_handle_irq); +#ifdef CONFIG_HANDLE_DOMAIN_IRQ +/** + * __handle_domain_irq - Invoke the handler for a HW irq belonging to a domain + * @domain: The domain where to perform the lookup + * @hwirq: The HW irq number to convert to a logical one + * @lookup: Whether to perform the domain lookup or not + * @regs: Register file coming from the low-level handling code + * + * Returns: 0 on success, or -EINVAL if conversion has failed + */ +int __handle_domain_irq(struct irq_domain *domain, unsigned int hwirq, + bool lookup, struct pt_regs *regs) +{ + struct pt_regs *old_regs = set_irq_regs(regs); + unsigned int irq = hwirq; + int ret = 0; + + irq_enter(); + +#ifdef CONFIG_IRQ_DOMAIN + if (lookup) + irq = irq_find_mapping(domain, hwirq); +#endif + + /* + * Some hardware gives randomly wrong interrupts. Rather + * than crashing, do something sensible. + */ + if (unlikely(!irq || irq >= nr_irqs)) { + ack_bad_irq(irq); + ret = -EINVAL; + } else { + generic_handle_irq(irq); + } + + irq_exit(); + set_irq_regs(old_regs); + return ret; +} +#endif + /* Dynamic interrupt handling */ /** diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 3dc6a61bf06a..0a9104b4608b 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -382,14 +382,8 @@ setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask) } #endif -void __disable_irq(struct irq_desc *desc, unsigned int irq, bool suspend) +void __disable_irq(struct irq_desc *desc, unsigned int irq) { - if (suspend) { - if (!desc->action || (desc->action->flags & IRQF_NO_SUSPEND)) - return; - desc->istate |= IRQS_SUSPENDED; - } - if (!desc->depth++) irq_disable(desc); } @@ -401,7 +395,7 @@ static int __disable_irq_nosync(unsigned int irq) if (!desc) return -EINVAL; - __disable_irq(desc, irq, false); + __disable_irq(desc, irq); irq_put_desc_busunlock(desc, flags); return 0; } @@ -442,20 +436,8 @@ void disable_irq(unsigned int irq) } EXPORT_SYMBOL(disable_irq); -void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume) +void __enable_irq(struct irq_desc *desc, unsigned int irq) { - if (resume) { - if (!(desc->istate & IRQS_SUSPENDED)) { - if (!desc->action) - return; - if (!(desc->action->flags & IRQF_FORCE_RESUME)) - return; - /* Pretend that it got disabled ! */ - desc->depth++; - } - desc->istate &= ~IRQS_SUSPENDED; - } - switch (desc->depth) { case 0: err_out: @@ -497,7 +479,7 @@ void enable_irq(unsigned int irq) KERN_ERR "enable_irq before setup/request_irq: irq %u\n", irq)) goto out; - __enable_irq(desc, irq, false); + __enable_irq(desc, irq); out: irq_put_desc_busunlock(desc, flags); } @@ -1218,6 +1200,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) new->irq = irq; *old_ptr = new; + irq_pm_install_action(desc, new); + /* Reset broken irq detection when installing new handler */ desc->irq_count = 0; desc->irqs_unhandled = 0; @@ -1228,7 +1212,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) */ if (shared && (desc->istate & IRQS_SPURIOUS_DISABLED)) { desc->istate &= ~IRQS_SPURIOUS_DISABLED; - __enable_irq(desc, irq, false); + __enable_irq(desc, irq); } raw_spin_unlock_irqrestore(&desc->lock, flags); @@ -1336,6 +1320,8 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) /* Found it - now remove it from the list of entries: */ *action_ptr = action->next; + irq_pm_remove_action(desc, action); + /* If this was the last handler, shut down the IRQ line: */ if (!desc->action) { irq_shutdown(desc); diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c index abcd6ca86cb7..3ca532592704 100644 --- a/kernel/irq/pm.c +++ b/kernel/irq/pm.c @@ -9,17 +9,105 @@ #include <linux/irq.h> #include <linux/module.h> #include <linux/interrupt.h> +#include <linux/suspend.h> #include <linux/syscore_ops.h> #include "internals.h" +bool irq_pm_check_wakeup(struct irq_desc *desc) +{ + if (irqd_is_wakeup_armed(&desc->irq_data)) { + irqd_clear(&desc->irq_data, IRQD_WAKEUP_ARMED); + desc->istate |= IRQS_SUSPENDED | IRQS_PENDING; + desc->depth++; + irq_disable(desc); + pm_system_wakeup(); + return true; + } + return false; +} + +/* + * Called from __setup_irq() with desc->lock held after @action has + * been installed in the action chain. + */ +void irq_pm_install_action(struct irq_desc *desc, struct irqaction *action) +{ + desc->nr_actions++; + + if (action->flags & IRQF_FORCE_RESUME) + desc->force_resume_depth++; + + WARN_ON_ONCE(desc->force_resume_depth && + desc->force_resume_depth != desc->nr_actions); + + if (action->flags & IRQF_NO_SUSPEND) + desc->no_suspend_depth++; + + WARN_ON_ONCE(desc->no_suspend_depth && + desc->no_suspend_depth != desc->nr_actions); +} + +/* + * Called from __free_irq() with desc->lock held after @action has + * been removed from the action chain. + */ +void irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action) +{ + desc->nr_actions--; + + if (action->flags & IRQF_FORCE_RESUME) + desc->force_resume_depth--; + + if (action->flags & IRQF_NO_SUSPEND) + desc->no_suspend_depth--; +} + +static bool suspend_device_irq(struct irq_desc *desc, int irq) +{ + if (!desc->action || desc->no_suspend_depth) + return false; + + if (irqd_is_wakeup_set(&desc->irq_data)) { + irqd_set(&desc->irq_data, IRQD_WAKEUP_ARMED); + /* + * We return true here to force the caller to issue + * synchronize_irq(). We need to make sure that the + * IRQD_WAKEUP_ARMED is visible before we return from + * suspend_device_irqs(). + */ + return true; + } + + desc->istate |= IRQS_SUSPENDED; + __disable_irq(desc, irq); + + /* + * Hardware which has no wakeup source configuration facility + * requires that the non wakeup interrupts are masked at the + * chip level. The chip implementation indicates that with + * IRQCHIP_MASK_ON_SUSPEND. + */ + if (irq_desc_get_chip(desc)->flags & IRQCHIP_MASK_ON_SUSPEND) + mask_irq(desc); + return true; +} + /** * suspend_device_irqs - disable all currently enabled interrupt lines * - * During system-wide suspend or hibernation device drivers need to be prevented - * from receiving interrupts and this function is provided for this purpose. - * It marks all interrupt lines in use, except for the timer ones, as disabled - * and sets the IRQS_SUSPENDED flag for each of them. + * During system-wide suspend or hibernation device drivers need to be + * prevented from receiving interrupts and this function is provided + * for this purpose. + * + * So we disable all interrupts and mark them IRQS_SUSPENDED except + * for those which are unused, those which are marked as not + * suspendable via an interrupt request with the flag IRQF_NO_SUSPEND + * set and those which are marked as active wakeup sources. + * + * The active wakeup sources are handled by the flow handler entry + * code which checks for the IRQD_WAKEUP_ARMED flag, suspends the + * interrupt and notifies the pm core about the wakeup. */ void suspend_device_irqs(void) { @@ -28,18 +116,36 @@ void suspend_device_irqs(void) for_each_irq_desc(irq, desc) { unsigned long flags; + bool sync; raw_spin_lock_irqsave(&desc->lock, flags); - __disable_irq(desc, irq, true); + sync = suspend_device_irq(desc, irq); raw_spin_unlock_irqrestore(&desc->lock, flags); - } - for_each_irq_desc(irq, desc) - if (desc->istate & IRQS_SUSPENDED) + if (sync) synchronize_irq(irq); + } } EXPORT_SYMBOL_GPL(suspend_device_irqs); +static void resume_irq(struct irq_desc *desc, int irq) +{ + irqd_clear(&desc->irq_data, IRQD_WAKEUP_ARMED); + + if (desc->istate & IRQS_SUSPENDED) + goto resume; + + /* Force resume the interrupt? */ + if (!desc->force_resume_depth) + return; + + /* Pretend that it got disabled ! */ + desc->depth++; +resume: + desc->istate &= ~IRQS_SUSPENDED; + __enable_irq(desc, irq); +} + static void resume_irqs(bool want_early) { struct irq_desc *desc; @@ -54,7 +160,7 @@ static void resume_irqs(bool want_early) continue; raw_spin_lock_irqsave(&desc->lock, flags); - __enable_irq(desc, irq, true); + resume_irq(desc, irq); raw_spin_unlock_irqrestore(&desc->lock, flags); } } @@ -93,38 +199,3 @@ void resume_device_irqs(void) resume_irqs(false); } EXPORT_SYMBOL_GPL(resume_device_irqs); - -/** - * check_wakeup_irqs - check if any wake-up interrupts are pending - */ -int check_wakeup_irqs(void) -{ - struct irq_desc *desc; - int irq; - - for_each_irq_desc(irq, desc) { - /* - * Only interrupts which are marked as wakeup source - * and have not been disabled before the suspend check - * can abort suspend. - */ - if (irqd_is_wakeup_set(&desc->irq_data)) { - if (desc->depth == 1 && desc->istate & IRQS_PENDING) - return -EBUSY; - continue; - } - /* - * Check the non wakeup interrupts whether they need - * to be masked before finally going into suspend - * state. That's for hardware which has no wakeup - * source configuration facility. The chip - * implementation indicates that with - * IRQCHIP_MASK_ON_SUSPEND. - */ - if (desc->istate & IRQS_SUSPENDED && - irq_desc_get_chip(desc)->flags & IRQCHIP_MASK_ON_SUSPEND) - mask_irq(desc); - } - - return 0; -} diff --git a/kernel/irq_work.c b/kernel/irq_work.c index e6bcbe756663..385b85aded19 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -115,8 +115,10 @@ bool irq_work_needs_cpu(void) raised = &__get_cpu_var(raised_list); lazy = &__get_cpu_var(lazy_list); - if (llist_empty(raised) && llist_empty(lazy)) - return false; + + if (llist_empty(raised) || arch_irq_work_has_interrupt()) + if (llist_empty(lazy)) + return false; /* All work should have been flushed before going offline */ WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); @@ -171,6 +173,15 @@ void irq_work_run(void) } EXPORT_SYMBOL_GPL(irq_work_run); +void irq_work_tick(void) +{ + struct llist_head *raised = &__get_cpu_var(raised_list); + + if (!llist_empty(raised) && !arch_irq_work_has_interrupt()) + irq_work_run_list(raised); + irq_work_run_list(&__get_cpu_var(lazy_list)); +} + /* * Synchronize against the irq_work @entry, ensures the entry is not * currently in use. diff --git a/kernel/kcmp.c b/kernel/kcmp.c index e30ac0fe61c3..0aa69ea1d8fd 100644 --- a/kernel/kcmp.c +++ b/kernel/kcmp.c @@ -44,11 +44,12 @@ static long kptr_obfuscate(long v, int type) */ static int kcmp_ptr(void *v1, void *v2, enum kcmp_type type) { - long ret; + long t1, t2; - ret = kptr_obfuscate((long)v1, type) - kptr_obfuscate((long)v2, type); + t1 = kptr_obfuscate((long)v1, type); + t2 = kptr_obfuscate((long)v2, type); - return (ret < 0) | ((ret > 0) << 1); + return (t1 < t2) | ((t1 > t2) << 1); } /* The caller must have pinned the task */ diff --git a/kernel/kthread.c b/kernel/kthread.c index ef483220e855..10e489c448fe 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -369,7 +369,7 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), { struct task_struct *p; - p = kthread_create_on_node(threadfn, data, cpu_to_mem(cpu), namefmt, + p = kthread_create_on_node(threadfn, data, cpu_to_node(cpu), namefmt, cpu); if (IS_ERR(p)) return p; diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index 0955b885d0dc..ec8cce259779 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -20,30 +20,20 @@ * Author: Paul E. McKenney <paulmck@us.ibm.com> * Based on kernel/rcu/torture.c. */ -#include <linux/types.h> #include <linux/kernel.h> -#include <linux/init.h> #include <linux/module.h> #include <linux/kthread.h> -#include <linux/err.h> #include <linux/spinlock.h> +#include <linux/rwlock.h> +#include <linux/mutex.h> +#include <linux/rwsem.h> #include <linux/smp.h> #include <linux/interrupt.h> #include <linux/sched.h> #include <linux/atomic.h> -#include <linux/bitops.h> -#include <linux/completion.h> #include <linux/moduleparam.h> -#include <linux/percpu.h> -#include <linux/notifier.h> -#include <linux/reboot.h> -#include <linux/freezer.h> -#include <linux/cpu.h> #include <linux/delay.h> -#include <linux/stat.h> #include <linux/slab.h> -#include <linux/trace_clock.h> -#include <asm/byteorder.h> #include <linux/torture.h> MODULE_LICENSE("GPL"); @@ -51,6 +41,8 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com>"); torture_param(int, nwriters_stress, -1, "Number of write-locking stress-test threads"); +torture_param(int, nreaders_stress, -1, + "Number of read-locking stress-test threads"); 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"); @@ -66,30 +58,28 @@ torture_param(bool, verbose, true, static char *torture_type = "spin_lock"; module_param(torture_type, charp, 0444); MODULE_PARM_DESC(torture_type, - "Type of lock to torture (spin_lock, spin_lock_irq, ...)"); - -static atomic_t n_lock_torture_errors; + "Type of lock to torture (spin_lock, spin_lock_irq, mutex_lock, ...)"); static struct task_struct *stats_task; static struct task_struct **writer_tasks; +static struct task_struct **reader_tasks; -static int nrealwriters_stress; static bool lock_is_write_held; +static bool lock_is_read_held; -struct lock_writer_stress_stats { - long n_write_lock_fail; - long n_write_lock_acquired; +struct lock_stress_stats { + long n_lock_fail; + long n_lock_acquired; }; -static struct lock_writer_stress_stats *lwsa; #if defined(MODULE) #define LOCKTORTURE_RUNNABLE_INIT 1 #else #define LOCKTORTURE_RUNNABLE_INIT 0 #endif -int locktorture_runnable = LOCKTORTURE_RUNNABLE_INIT; -module_param(locktorture_runnable, int, 0444); -MODULE_PARM_DESC(locktorture_runnable, "Start locktorture at module init"); +int torture_runnable = LOCKTORTURE_RUNNABLE_INIT; +module_param(torture_runnable, int, 0444); +MODULE_PARM_DESC(torture_runnable, "Start locktorture at module init"); /* Forward reference. */ static void lock_torture_cleanup(void); @@ -102,12 +92,25 @@ struct lock_torture_ops { int (*writelock)(void); void (*write_delay)(struct torture_random_state *trsp); void (*writeunlock)(void); + int (*readlock)(void); + void (*read_delay)(struct torture_random_state *trsp); + void (*readunlock)(void); unsigned long flags; const char *name; }; -static struct lock_torture_ops *cur_ops; - +struct lock_torture_cxt { + int nrealwriters_stress; + int nrealreaders_stress; + bool debug_lock; + atomic_t n_lock_torture_errors; + struct lock_torture_ops *cur_ops; + struct lock_stress_stats *lwsa; /* writer statistics */ + struct lock_stress_stats *lrsa; /* reader statistics */ +}; +static struct lock_torture_cxt cxt = { 0, 0, false, + ATOMIC_INIT(0), + NULL, NULL}; /* * Definitions for lock torture testing. */ @@ -123,10 +126,10 @@ static void torture_lock_busted_write_delay(struct torture_random_state *trsp) /* We want a long delay occasionally to force massive contention. */ if (!(torture_random(trsp) % - (nrealwriters_stress * 2000 * longdelay_us))) + (cxt.nrealwriters_stress * 2000 * longdelay_us))) mdelay(longdelay_us); #ifdef CONFIG_PREEMPT - if (!(torture_random(trsp) % (nrealwriters_stress * 20000))) + if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000))) preempt_schedule(); /* Allow test to be preempted. */ #endif } @@ -140,6 +143,9 @@ static struct lock_torture_ops lock_busted_ops = { .writelock = torture_lock_busted_write_lock, .write_delay = torture_lock_busted_write_delay, .writeunlock = torture_lock_busted_write_unlock, + .readlock = NULL, + .read_delay = NULL, + .readunlock = NULL, .name = "lock_busted" }; @@ -160,13 +166,13 @@ static void torture_spin_lock_write_delay(struct torture_random_state *trsp) * we want a long delay occasionally to force massive contention. */ if (!(torture_random(trsp) % - (nrealwriters_stress * 2000 * longdelay_us))) + (cxt.nrealwriters_stress * 2000 * longdelay_us))) mdelay(longdelay_us); if (!(torture_random(trsp) % - (nrealwriters_stress * 2 * shortdelay_us))) + (cxt.nrealwriters_stress * 2 * shortdelay_us))) udelay(shortdelay_us); #ifdef CONFIG_PREEMPT - if (!(torture_random(trsp) % (nrealwriters_stress * 20000))) + if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000))) preempt_schedule(); /* Allow test to be preempted. */ #endif } @@ -180,39 +186,253 @@ static struct lock_torture_ops spin_lock_ops = { .writelock = torture_spin_lock_write_lock, .write_delay = torture_spin_lock_write_delay, .writeunlock = torture_spin_lock_write_unlock, + .readlock = NULL, + .read_delay = NULL, + .readunlock = NULL, .name = "spin_lock" }; static int torture_spin_lock_write_lock_irq(void) -__acquires(torture_spinlock_irq) +__acquires(torture_spinlock) { unsigned long flags; spin_lock_irqsave(&torture_spinlock, flags); - cur_ops->flags = flags; + cxt.cur_ops->flags = flags; return 0; } static void torture_lock_spin_write_unlock_irq(void) __releases(torture_spinlock) { - spin_unlock_irqrestore(&torture_spinlock, cur_ops->flags); + spin_unlock_irqrestore(&torture_spinlock, cxt.cur_ops->flags); } static struct lock_torture_ops spin_lock_irq_ops = { .writelock = torture_spin_lock_write_lock_irq, .write_delay = torture_spin_lock_write_delay, .writeunlock = torture_lock_spin_write_unlock_irq, + .readlock = NULL, + .read_delay = NULL, + .readunlock = NULL, .name = "spin_lock_irq" }; +static DEFINE_RWLOCK(torture_rwlock); + +static int torture_rwlock_write_lock(void) __acquires(torture_rwlock) +{ + write_lock(&torture_rwlock); + return 0; +} + +static void torture_rwlock_write_delay(struct torture_random_state *trsp) +{ + const unsigned long shortdelay_us = 2; + const unsigned long longdelay_ms = 100; + + /* We want a short delay mostly to emulate likely code, and + * we want a long delay occasionally to force massive contention. + */ + if (!(torture_random(trsp) % + (cxt.nrealwriters_stress * 2000 * longdelay_ms))) + mdelay(longdelay_ms); + else + udelay(shortdelay_us); +} + +static void torture_rwlock_write_unlock(void) __releases(torture_rwlock) +{ + write_unlock(&torture_rwlock); +} + +static int torture_rwlock_read_lock(void) __acquires(torture_rwlock) +{ + read_lock(&torture_rwlock); + return 0; +} + +static void torture_rwlock_read_delay(struct torture_random_state *trsp) +{ + const unsigned long shortdelay_us = 10; + const unsigned long longdelay_ms = 100; + + /* We want a short delay mostly to emulate likely code, and + * we want a long delay occasionally to force massive contention. + */ + if (!(torture_random(trsp) % + (cxt.nrealreaders_stress * 2000 * longdelay_ms))) + mdelay(longdelay_ms); + else + udelay(shortdelay_us); +} + +static void torture_rwlock_read_unlock(void) __releases(torture_rwlock) +{ + read_unlock(&torture_rwlock); +} + +static struct lock_torture_ops rw_lock_ops = { + .writelock = torture_rwlock_write_lock, + .write_delay = torture_rwlock_write_delay, + .writeunlock = torture_rwlock_write_unlock, + .readlock = torture_rwlock_read_lock, + .read_delay = torture_rwlock_read_delay, + .readunlock = torture_rwlock_read_unlock, + .name = "rw_lock" +}; + +static int torture_rwlock_write_lock_irq(void) __acquires(torture_rwlock) +{ + unsigned long flags; + + write_lock_irqsave(&torture_rwlock, flags); + cxt.cur_ops->flags = flags; + return 0; +} + +static void torture_rwlock_write_unlock_irq(void) +__releases(torture_rwlock) +{ + write_unlock_irqrestore(&torture_rwlock, cxt.cur_ops->flags); +} + +static int torture_rwlock_read_lock_irq(void) __acquires(torture_rwlock) +{ + unsigned long flags; + + read_lock_irqsave(&torture_rwlock, flags); + cxt.cur_ops->flags = flags; + return 0; +} + +static void torture_rwlock_read_unlock_irq(void) +__releases(torture_rwlock) +{ + write_unlock_irqrestore(&torture_rwlock, cxt.cur_ops->flags); +} + +static struct lock_torture_ops rw_lock_irq_ops = { + .writelock = torture_rwlock_write_lock_irq, + .write_delay = torture_rwlock_write_delay, + .writeunlock = torture_rwlock_write_unlock_irq, + .readlock = torture_rwlock_read_lock_irq, + .read_delay = torture_rwlock_read_delay, + .readunlock = torture_rwlock_read_unlock_irq, + .name = "rw_lock_irq" +}; + +static DEFINE_MUTEX(torture_mutex); + +static int torture_mutex_lock(void) __acquires(torture_mutex) +{ + mutex_lock(&torture_mutex); + return 0; +} + +static void torture_mutex_delay(struct torture_random_state *trsp) +{ + const unsigned long longdelay_ms = 100; + + /* We want a long delay occasionally to force massive contention. */ + if (!(torture_random(trsp) % + (cxt.nrealwriters_stress * 2000 * longdelay_ms))) + mdelay(longdelay_ms * 5); + else + mdelay(longdelay_ms / 5); +#ifdef CONFIG_PREEMPT + if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000))) + preempt_schedule(); /* Allow test to be preempted. */ +#endif +} + +static void torture_mutex_unlock(void) __releases(torture_mutex) +{ + mutex_unlock(&torture_mutex); +} + +static struct lock_torture_ops mutex_lock_ops = { + .writelock = torture_mutex_lock, + .write_delay = torture_mutex_delay, + .writeunlock = torture_mutex_unlock, + .readlock = NULL, + .read_delay = NULL, + .readunlock = NULL, + .name = "mutex_lock" +}; + +static DECLARE_RWSEM(torture_rwsem); +static int torture_rwsem_down_write(void) __acquires(torture_rwsem) +{ + down_write(&torture_rwsem); + return 0; +} + +static void torture_rwsem_write_delay(struct torture_random_state *trsp) +{ + const unsigned long longdelay_ms = 100; + + /* We want a long delay occasionally to force massive contention. */ + if (!(torture_random(trsp) % + (cxt.nrealwriters_stress * 2000 * longdelay_ms))) + mdelay(longdelay_ms * 10); + else + mdelay(longdelay_ms / 10); +#ifdef CONFIG_PREEMPT + if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000))) + preempt_schedule(); /* Allow test to be preempted. */ +#endif +} + +static void torture_rwsem_up_write(void) __releases(torture_rwsem) +{ + up_write(&torture_rwsem); +} + +static int torture_rwsem_down_read(void) __acquires(torture_rwsem) +{ + down_read(&torture_rwsem); + return 0; +} + +static void torture_rwsem_read_delay(struct torture_random_state *trsp) +{ + const unsigned long longdelay_ms = 100; + + /* We want a long delay occasionally to force massive contention. */ + if (!(torture_random(trsp) % + (cxt.nrealwriters_stress * 2000 * longdelay_ms))) + mdelay(longdelay_ms * 2); + else + mdelay(longdelay_ms / 2); +#ifdef CONFIG_PREEMPT + if (!(torture_random(trsp) % (cxt.nrealreaders_stress * 20000))) + preempt_schedule(); /* Allow test to be preempted. */ +#endif +} + +static void torture_rwsem_up_read(void) __releases(torture_rwsem) +{ + up_read(&torture_rwsem); +} + +static struct lock_torture_ops rwsem_lock_ops = { + .writelock = torture_rwsem_down_write, + .write_delay = torture_rwsem_write_delay, + .writeunlock = torture_rwsem_up_write, + .readlock = torture_rwsem_down_read, + .read_delay = torture_rwsem_read_delay, + .readunlock = torture_rwsem_up_read, + .name = "rwsem_lock" +}; + /* * Lock torture writer kthread. Repeatedly acquires and releases * the lock, checking for duplicate acquisitions. */ static int lock_torture_writer(void *arg) { - struct lock_writer_stress_stats *lwsp = arg; + struct lock_stress_stats *lwsp = arg; static DEFINE_TORTURE_RANDOM(rand); VERBOSE_TOROUT_STRING("lock_torture_writer task started"); @@ -221,14 +441,19 @@ static int lock_torture_writer(void *arg) do { if ((torture_random(&rand) & 0xfffff) == 0) schedule_timeout_uninterruptible(1); - cur_ops->writelock(); + + cxt.cur_ops->writelock(); if (WARN_ON_ONCE(lock_is_write_held)) - lwsp->n_write_lock_fail++; + lwsp->n_lock_fail++; lock_is_write_held = 1; - lwsp->n_write_lock_acquired++; - cur_ops->write_delay(&rand); + if (WARN_ON_ONCE(lock_is_read_held)) + lwsp->n_lock_fail++; /* rare, but... */ + + lwsp->n_lock_acquired++; + cxt.cur_ops->write_delay(&rand); lock_is_write_held = 0; - cur_ops->writeunlock(); + cxt.cur_ops->writeunlock(); + stutter_wait("lock_torture_writer"); } while (!torture_must_stop()); torture_kthread_stopping("lock_torture_writer"); @@ -236,32 +461,66 @@ static int lock_torture_writer(void *arg) } /* + * Lock torture reader kthread. Repeatedly acquires and releases + * the reader lock. + */ +static int lock_torture_reader(void *arg) +{ + struct lock_stress_stats *lrsp = arg; + static DEFINE_TORTURE_RANDOM(rand); + + VERBOSE_TOROUT_STRING("lock_torture_reader task started"); + set_user_nice(current, MAX_NICE); + + do { + if ((torture_random(&rand) & 0xfffff) == 0) + schedule_timeout_uninterruptible(1); + + cxt.cur_ops->readlock(); + lock_is_read_held = 1; + if (WARN_ON_ONCE(lock_is_write_held)) + lrsp->n_lock_fail++; /* rare, but... */ + + lrsp->n_lock_acquired++; + cxt.cur_ops->read_delay(&rand); + lock_is_read_held = 0; + cxt.cur_ops->readunlock(); + + stutter_wait("lock_torture_reader"); + } while (!torture_must_stop()); + torture_kthread_stopping("lock_torture_reader"); + return 0; +} + +/* * Create an lock-torture-statistics message in the specified buffer. */ -static void lock_torture_printk(char *page) +static void __torture_print_stats(char *page, + struct lock_stress_stats *statp, bool write) { bool fail = 0; - int i; + int i, n_stress; long max = 0; - long min = lwsa[0].n_write_lock_acquired; + long min = statp[0].n_lock_acquired; long long sum = 0; - for (i = 0; i < nrealwriters_stress; i++) { - if (lwsa[i].n_write_lock_fail) + n_stress = write ? cxt.nrealwriters_stress : cxt.nrealreaders_stress; + for (i = 0; i < n_stress; i++) { + if (statp[i].n_lock_fail) fail = true; - sum += lwsa[i].n_write_lock_acquired; - if (max < lwsa[i].n_write_lock_fail) - max = lwsa[i].n_write_lock_fail; - if (min > lwsa[i].n_write_lock_fail) - min = lwsa[i].n_write_lock_fail; + sum += statp[i].n_lock_acquired; + if (max < statp[i].n_lock_fail) + max = statp[i].n_lock_fail; + if (min > statp[i].n_lock_fail) + min = statp[i].n_lock_fail; } - page += sprintf(page, "%s%s ", torture_type, TORTURE_FLAG); page += sprintf(page, - "Writes: Total: %lld Max/Min: %ld/%ld %s Fail: %d %s\n", + "%s: Total: %lld Max/Min: %ld/%ld %s Fail: %d %s\n", + write ? "Writes" : "Reads ", sum, max, min, max / 2 > min ? "???" : "", fail, fail ? "!!!" : ""); if (fail) - atomic_inc(&n_lock_torture_errors); + atomic_inc(&cxt.n_lock_torture_errors); } /* @@ -274,18 +533,35 @@ static void lock_torture_printk(char *page) */ static void lock_torture_stats_print(void) { - int size = nrealwriters_stress * 200 + 8192; + int size = cxt.nrealwriters_stress * 200 + 8192; char *buf; + if (cxt.cur_ops->readlock) + size += cxt.nrealreaders_stress * 200 + 8192; + buf = kmalloc(size, GFP_KERNEL); if (!buf) { pr_err("lock_torture_stats_print: Out of memory, need: %d", size); return; } - lock_torture_printk(buf); + + __torture_print_stats(buf, cxt.lwsa, true); pr_alert("%s", buf); kfree(buf); + + if (cxt.cur_ops->readlock) { + buf = kmalloc(size, GFP_KERNEL); + if (!buf) { + pr_err("lock_torture_stats_print: Out of memory, need: %d", + size); + return; + } + + __torture_print_stats(buf, cxt.lrsa, false); + pr_alert("%s", buf); + kfree(buf); + } } /* @@ -312,9 +588,10 @@ lock_torture_print_module_parms(struct lock_torture_ops *cur_ops, const char *tag) { pr_alert("%s" TORTURE_FLAG - "--- %s: nwriters_stress=%d stat_interval=%d verbose=%d shuffle_interval=%d stutter=%d shutdown_secs=%d onoff_interval=%d onoff_holdoff=%d\n", - torture_type, tag, nrealwriters_stress, stat_interval, verbose, - shuffle_interval, stutter, shutdown_secs, + "--- %s%s: nwriters_stress=%d nreaders_stress=%d stat_interval=%d verbose=%d shuffle_interval=%d stutter=%d shutdown_secs=%d onoff_interval=%d onoff_holdoff=%d\n", + torture_type, tag, cxt.debug_lock ? " [debug]": "", + cxt.nrealwriters_stress, cxt.nrealreaders_stress, stat_interval, + verbose, shuffle_interval, stutter, shutdown_secs, onoff_interval, onoff_holdoff); } @@ -322,46 +599,59 @@ static void lock_torture_cleanup(void) { int i; - if (torture_cleanup()) + if (torture_cleanup_begin()) return; if (writer_tasks) { - for (i = 0; i < nrealwriters_stress; i++) + for (i = 0; i < cxt.nrealwriters_stress; i++) torture_stop_kthread(lock_torture_writer, writer_tasks[i]); kfree(writer_tasks); writer_tasks = NULL; } + if (reader_tasks) { + for (i = 0; i < cxt.nrealreaders_stress; i++) + torture_stop_kthread(lock_torture_reader, + reader_tasks[i]); + kfree(reader_tasks); + reader_tasks = NULL; + } + torture_stop_kthread(lock_torture_stats, stats_task); lock_torture_stats_print(); /* -After- the stats thread is stopped! */ - if (atomic_read(&n_lock_torture_errors)) - lock_torture_print_module_parms(cur_ops, + if (atomic_read(&cxt.n_lock_torture_errors)) + lock_torture_print_module_parms(cxt.cur_ops, "End of test: FAILURE"); else if (torture_onoff_failures()) - lock_torture_print_module_parms(cur_ops, + lock_torture_print_module_parms(cxt.cur_ops, "End of test: LOCK_HOTPLUG"); else - lock_torture_print_module_parms(cur_ops, + lock_torture_print_module_parms(cxt.cur_ops, "End of test: SUCCESS"); + torture_cleanup_end(); } static int __init lock_torture_init(void) { - int i; + int i, j; int firsterr = 0; static struct lock_torture_ops *torture_ops[] = { - &lock_busted_ops, &spin_lock_ops, &spin_lock_irq_ops, + &lock_busted_ops, + &spin_lock_ops, &spin_lock_irq_ops, + &rw_lock_ops, &rw_lock_irq_ops, + &mutex_lock_ops, + &rwsem_lock_ops, }; - if (!torture_init_begin(torture_type, verbose, &locktorture_runnable)) + if (!torture_init_begin(torture_type, verbose, &torture_runnable)) return -EBUSY; /* Process args and tell the world that the torturer is on the job. */ for (i = 0; i < ARRAY_SIZE(torture_ops); i++) { - cur_ops = torture_ops[i]; - if (strcmp(torture_type, cur_ops->name) == 0) + cxt.cur_ops = torture_ops[i]; + if (strcmp(torture_type, cxt.cur_ops->name) == 0) break; } if (i == ARRAY_SIZE(torture_ops)) { @@ -374,31 +664,69 @@ static int __init lock_torture_init(void) torture_init_end(); return -EINVAL; } - if (cur_ops->init) - cur_ops->init(); /* no "goto unwind" prior to this point!!! */ + if (cxt.cur_ops->init) + cxt.cur_ops->init(); /* no "goto unwind" prior to this point!!! */ if (nwriters_stress >= 0) - nrealwriters_stress = nwriters_stress; + cxt.nrealwriters_stress = nwriters_stress; else - nrealwriters_stress = 2 * num_online_cpus(); - lock_torture_print_module_parms(cur_ops, "Start of test"); + cxt.nrealwriters_stress = 2 * num_online_cpus(); + +#ifdef CONFIG_DEBUG_MUTEXES + if (strncmp(torture_type, "mutex", 5) == 0) + cxt.debug_lock = true; +#endif +#ifdef CONFIG_DEBUG_SPINLOCK + if ((strncmp(torture_type, "spin", 4) == 0) || + (strncmp(torture_type, "rw_lock", 7) == 0)) + cxt.debug_lock = true; +#endif /* Initialize the statistics so that each run gets its own numbers. */ lock_is_write_held = 0; - lwsa = kmalloc(sizeof(*lwsa) * nrealwriters_stress, GFP_KERNEL); - if (lwsa == NULL) { - VERBOSE_TOROUT_STRING("lwsa: Out of memory"); + cxt.lwsa = kmalloc(sizeof(*cxt.lwsa) * cxt.nrealwriters_stress, GFP_KERNEL); + if (cxt.lwsa == NULL) { + VERBOSE_TOROUT_STRING("cxt.lwsa: Out of memory"); firsterr = -ENOMEM; goto unwind; } - for (i = 0; i < nrealwriters_stress; i++) { - lwsa[i].n_write_lock_fail = 0; - lwsa[i].n_write_lock_acquired = 0; + for (i = 0; i < cxt.nrealwriters_stress; i++) { + cxt.lwsa[i].n_lock_fail = 0; + cxt.lwsa[i].n_lock_acquired = 0; } - /* Start up the kthreads. */ + if (cxt.cur_ops->readlock) { + if (nreaders_stress >= 0) + cxt.nrealreaders_stress = nreaders_stress; + else { + /* + * By default distribute evenly the number of + * readers and writers. We still run the same number + * of threads as the writer-only locks default. + */ + if (nwriters_stress < 0) /* user doesn't care */ + cxt.nrealwriters_stress = num_online_cpus(); + cxt.nrealreaders_stress = cxt.nrealwriters_stress; + } + + lock_is_read_held = 0; + cxt.lrsa = kmalloc(sizeof(*cxt.lrsa) * cxt.nrealreaders_stress, GFP_KERNEL); + if (cxt.lrsa == NULL) { + VERBOSE_TOROUT_STRING("cxt.lrsa: Out of memory"); + firsterr = -ENOMEM; + kfree(cxt.lwsa); + goto unwind; + } + + for (i = 0; i < cxt.nrealreaders_stress; i++) { + cxt.lrsa[i].n_lock_fail = 0; + cxt.lrsa[i].n_lock_acquired = 0; + } + } + lock_torture_print_module_parms(cxt.cur_ops, "Start of test"); + /* Prepare torture context. */ if (onoff_interval > 0) { firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval * HZ); @@ -422,18 +750,51 @@ static int __init lock_torture_init(void) goto unwind; } - writer_tasks = kzalloc(nrealwriters_stress * sizeof(writer_tasks[0]), + writer_tasks = kzalloc(cxt.nrealwriters_stress * sizeof(writer_tasks[0]), GFP_KERNEL); if (writer_tasks == NULL) { VERBOSE_TOROUT_ERRSTRING("writer_tasks: Out of memory"); firsterr = -ENOMEM; goto unwind; } - for (i = 0; i < nrealwriters_stress; i++) { - firsterr = torture_create_kthread(lock_torture_writer, &lwsa[i], + + if (cxt.cur_ops->readlock) { + reader_tasks = kzalloc(cxt.nrealreaders_stress * sizeof(reader_tasks[0]), + GFP_KERNEL); + if (reader_tasks == NULL) { + VERBOSE_TOROUT_ERRSTRING("reader_tasks: Out of memory"); + firsterr = -ENOMEM; + goto unwind; + } + } + + /* + * Create the kthreads and start torturing (oh, those poor little locks). + * + * TODO: Note that we interleave writers with readers, giving writers a + * slight advantage, by creating its kthread first. This can be modified + * for very specific needs, or even let the user choose the policy, if + * ever wanted. + */ + for (i = 0, j = 0; i < cxt.nrealwriters_stress || + j < cxt.nrealreaders_stress; i++, j++) { + if (i >= cxt.nrealwriters_stress) + goto create_reader; + + /* Create writer. */ + firsterr = torture_create_kthread(lock_torture_writer, &cxt.lwsa[i], writer_tasks[i]); if (firsterr) goto unwind; + + create_reader: + if (cxt.cur_ops->readlock == NULL || (j >= cxt.nrealreaders_stress)) + continue; + /* Create reader. */ + firsterr = torture_create_kthread(lock_torture_reader, &cxt.lrsa[j], + reader_tasks[j]); + if (firsterr) + goto unwind; } if (stat_interval > 0) { firsterr = torture_create_kthread(lock_torture_stats, NULL, diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h index 23e89c5930e9..4d60986fcbee 100644 --- a/kernel/locking/mcs_spinlock.h +++ b/kernel/locking/mcs_spinlock.h @@ -56,9 +56,6 @@ do { \ * If the lock has already been acquired, then this will proceed to spin * on this node->locked until the previous lock holder sets the node->locked * in mcs_spin_unlock(). - * - * We don't inline mcs_spin_lock() so that perf can correctly account for the - * time spent in this lock function. */ static inline void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node) diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index ae712b25e492..dadbf88c22c4 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -15,7 +15,7 @@ * by Steven Rostedt, based on work by Gregory Haskins, Peter Morreale * and Sven Dietrich. * - * Also see Documentation/mutex-design.txt. + * Also see Documentation/locking/mutex-design.txt. */ #include <linux/mutex.h> #include <linux/ww_mutex.h> @@ -106,6 +106,92 @@ void __sched mutex_lock(struct mutex *lock) EXPORT_SYMBOL(mutex_lock); #endif +static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww, + struct ww_acquire_ctx *ww_ctx) +{ +#ifdef CONFIG_DEBUG_MUTEXES + /* + * If this WARN_ON triggers, you used ww_mutex_lock to acquire, + * but released with a normal mutex_unlock in this call. + * + * This should never happen, always use ww_mutex_unlock. + */ + DEBUG_LOCKS_WARN_ON(ww->ctx); + + /* + * Not quite done after calling ww_acquire_done() ? + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->done_acquire); + + if (ww_ctx->contending_lock) { + /* + * After -EDEADLK you tried to + * acquire a different ww_mutex? Bad! + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock != ww); + + /* + * You called ww_mutex_lock after receiving -EDEADLK, + * but 'forgot' to unlock everything else first? + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->acquired > 0); + ww_ctx->contending_lock = NULL; + } + + /* + * Naughty, using a different class will lead to undefined behavior! + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class); +#endif + ww_ctx->acquired++; +} + +/* + * after acquiring lock with fastpath or when we lost out in contested + * slowpath, set ctx and wake up any waiters so they can recheck. + * + * This function is never called when CONFIG_DEBUG_LOCK_ALLOC is set, + * as the fastpath and opportunistic spinning are disabled in that case. + */ +static __always_inline void +ww_mutex_set_context_fastpath(struct ww_mutex *lock, + struct ww_acquire_ctx *ctx) +{ + unsigned long flags; + struct mutex_waiter *cur; + + 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 + * 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(); /* ^^^ */ + + /* + * Check if lock is contended, if not there is nobody to wake up + */ + if (likely(atomic_read(&lock->base.count) == 0)) + return; + + /* + * Uh oh, we raced in fastpath, wake up everyone in this case, + * so they can see the new lock->ctx. + */ + spin_lock_mutex(&lock->base.wait_lock, flags); + list_for_each_entry(cur, &lock->base.wait_list, list) { + debug_mutex_wake_waiter(&lock->base, cur); + wake_up_process(cur->task); + } + spin_unlock_mutex(&lock->base.wait_lock, flags); +} + + #ifdef CONFIG_MUTEX_SPIN_ON_OWNER /* * In order to avoid a stampede of mutex spinners from acquiring the mutex @@ -180,6 +266,129 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock) */ return retval; } + +/* + * Atomically try to take the lock when it is available + */ +static inline bool mutex_try_to_acquire(struct mutex *lock) +{ + return !mutex_is_locked(lock) && + (atomic_cmpxchg(&lock->count, 1, 0) == 1); +} + +/* + * Optimistic spinning. + * + * We try to spin for acquisition when we find that the lock owner + * is currently running on a (different) CPU and while we don't + * need to reschedule. The rationale is that if the lock owner is + * running, it is likely to release the lock soon. + * + * Since this needs the lock owner, and this mutex implementation + * doesn't track the owner atomically in the lock field, we need to + * track it non-atomically. + * + * We can't do this for DEBUG_MUTEXES because that relies on wait_lock + * to serialize everything. + * + * The mutex spinners are queued up using MCS lock so that only one + * spinner can compete for the mutex. However, if mutex spinning isn't + * going to happen, there is no point in going through the lock/unlock + * overhead. + * + * Returns true when the lock was taken, otherwise false, indicating + * that we need to jump to the slowpath and sleep. + */ +static bool mutex_optimistic_spin(struct mutex *lock, + struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx) +{ + struct task_struct *task = current; + + if (!mutex_can_spin_on_owner(lock)) + goto done; + + if (!osq_lock(&lock->osq)) + goto done; + + while (true) { + struct task_struct *owner; + + if (use_ww_ctx && ww_ctx->acquired > 0) { + struct ww_mutex *ww; + + ww = container_of(lock, struct ww_mutex, base); + /* + * If ww->ctx is set the contents are undefined, only + * by acquiring wait_lock there is a guarantee that + * they are not invalid when reading. + * + * As such, when deadlock detection needs to be + * performed the optimistic spinning cannot be done. + */ + if (ACCESS_ONCE(ww->ctx)) + break; + } + + /* + * If there's an owner, wait for it to either + * release the lock or go to sleep. + */ + owner = ACCESS_ONCE(lock->owner); + if (owner && !mutex_spin_on_owner(lock, owner)) + break; + + /* Try to acquire the mutex if it is unlocked. */ + if (mutex_try_to_acquire(lock)) { + lock_acquired(&lock->dep_map, ip); + + if (use_ww_ctx) { + struct ww_mutex *ww; + ww = container_of(lock, struct ww_mutex, base); + + ww_mutex_set_context_fastpath(ww, ww_ctx); + } + + mutex_set_owner(lock); + osq_unlock(&lock->osq); + return true; + } + + /* + * When there's no owner, we might have preempted between the + * owner acquiring the lock and setting the owner field. If + * we're an RT task that will live-lock because we won't let + * the owner complete. + */ + if (!owner && (need_resched() || rt_task(task))) + break; + + /* + * The cpu_relax() call is a compiler barrier which forces + * everything in this loop to be re-loaded. We don't need + * memory barriers as we'll eventually observe the right + * values at the cost of a few extra spins. + */ + cpu_relax_lowlatency(); + } + + osq_unlock(&lock->osq); +done: + /* + * If we fell out of the spin path because of need_resched(), + * reschedule now, before we try-lock the mutex. This avoids getting + * scheduled out right after we obtained the mutex. + */ + if (need_resched()) + schedule_preempt_disabled(); + + return false; +} +#else +static bool mutex_optimistic_spin(struct mutex *lock, + struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx) +{ + return false; +} #endif __visible __used noinline @@ -277,91 +486,6 @@ __mutex_lock_check_stamp(struct mutex *lock, struct ww_acquire_ctx *ctx) return 0; } -static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww, - struct ww_acquire_ctx *ww_ctx) -{ -#ifdef CONFIG_DEBUG_MUTEXES - /* - * If this WARN_ON triggers, you used ww_mutex_lock to acquire, - * but released with a normal mutex_unlock in this call. - * - * This should never happen, always use ww_mutex_unlock. - */ - DEBUG_LOCKS_WARN_ON(ww->ctx); - - /* - * Not quite done after calling ww_acquire_done() ? - */ - DEBUG_LOCKS_WARN_ON(ww_ctx->done_acquire); - - if (ww_ctx->contending_lock) { - /* - * After -EDEADLK you tried to - * acquire a different ww_mutex? Bad! - */ - DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock != ww); - - /* - * You called ww_mutex_lock after receiving -EDEADLK, - * but 'forgot' to unlock everything else first? - */ - DEBUG_LOCKS_WARN_ON(ww_ctx->acquired > 0); - ww_ctx->contending_lock = NULL; - } - - /* - * Naughty, using a different class will lead to undefined behavior! - */ - DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class); -#endif - ww_ctx->acquired++; -} - -/* - * after acquiring lock with fastpath or when we lost out in contested - * slowpath, set ctx and wake up any waiters so they can recheck. - * - * This function is never called when CONFIG_DEBUG_LOCK_ALLOC is set, - * as the fastpath and opportunistic spinning are disabled in that case. - */ -static __always_inline void -ww_mutex_set_context_fastpath(struct ww_mutex *lock, - struct ww_acquire_ctx *ctx) -{ - unsigned long flags; - struct mutex_waiter *cur; - - 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 - * 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(); /* ^^^ */ - - /* - * Check if lock is contended, if not there is nobody to wake up - */ - if (likely(atomic_read(&lock->base.count) == 0)) - return; - - /* - * Uh oh, we raced in fastpath, wake up everyone in this case, - * so they can see the new lock->ctx. - */ - spin_lock_mutex(&lock->base.wait_lock, flags); - list_for_each_entry(cur, &lock->base.wait_list, list) { - debug_mutex_wake_waiter(&lock->base, cur); - wake_up_process(cur->task); - } - spin_unlock_mutex(&lock->base.wait_lock, flags); -} - /* * Lock a mutex (possibly interruptible), slowpath: */ @@ -378,104 +502,12 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, preempt_disable(); mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip); -#ifdef CONFIG_MUTEX_SPIN_ON_OWNER - /* - * Optimistic spinning. - * - * We try to spin for acquisition when we find that the lock owner - * is currently running on a (different) CPU and while we don't - * need to reschedule. The rationale is that if the lock owner is - * running, it is likely to release the lock soon. - * - * Since this needs the lock owner, and this mutex implementation - * doesn't track the owner atomically in the lock field, we need to - * track it non-atomically. - * - * We can't do this for DEBUG_MUTEXES because that relies on wait_lock - * to serialize everything. - * - * The mutex spinners are queued up using MCS lock so that only one - * spinner can compete for the mutex. However, if mutex spinning isn't - * going to happen, there is no point in going through the lock/unlock - * overhead. - */ - if (!mutex_can_spin_on_owner(lock)) - goto slowpath; - - if (!osq_lock(&lock->osq)) - goto slowpath; - - for (;;) { - struct task_struct *owner; - - if (use_ww_ctx && ww_ctx->acquired > 0) { - struct ww_mutex *ww; - - ww = container_of(lock, struct ww_mutex, base); - /* - * If ww->ctx is set the contents are undefined, only - * by acquiring wait_lock there is a guarantee that - * they are not invalid when reading. - * - * As such, when deadlock detection needs to be - * performed the optimistic spinning cannot be done. - */ - if (ACCESS_ONCE(ww->ctx)) - break; - } - - /* - * If there's an owner, wait for it to either - * release the lock or go to sleep. - */ - owner = ACCESS_ONCE(lock->owner); - if (owner && !mutex_spin_on_owner(lock, owner)) - break; - - /* Try to acquire the mutex if it is unlocked. */ - if (!mutex_is_locked(lock) && - (atomic_cmpxchg(&lock->count, 1, 0) == 1)) { - lock_acquired(&lock->dep_map, ip); - if (use_ww_ctx) { - struct ww_mutex *ww; - ww = container_of(lock, struct ww_mutex, base); - - ww_mutex_set_context_fastpath(ww, ww_ctx); - } - - mutex_set_owner(lock); - osq_unlock(&lock->osq); - preempt_enable(); - return 0; - } - - /* - * When there's no owner, we might have preempted between the - * owner acquiring the lock and setting the owner field. If - * we're an RT task that will live-lock because we won't let - * the owner complete. - */ - if (!owner && (need_resched() || rt_task(task))) - break; - - /* - * The cpu_relax() call is a compiler barrier which forces - * everything in this loop to be re-loaded. We don't need - * memory barriers as we'll eventually observe the right - * values at the cost of a few extra spins. - */ - cpu_relax_lowlatency(); + if (mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx)) { + /* got the lock, yay! */ + preempt_enable(); + return 0; } - osq_unlock(&lock->osq); -slowpath: - /* - * If we fell out of the spin path because of need_resched(), - * reschedule now, before we try-lock the mutex. This avoids getting - * scheduled out right after we obtained the mutex. - */ - if (need_resched()) - schedule_preempt_disabled(); -#endif + spin_lock_mutex(&lock->wait_lock, flags); /* @@ -679,15 +711,21 @@ EXPORT_SYMBOL_GPL(__ww_mutex_lock_interruptible); * Release the lock, slowpath: */ static inline void -__mutex_unlock_common_slowpath(atomic_t *lock_count, int nested) +__mutex_unlock_common_slowpath(struct mutex *lock, int nested) { - struct mutex *lock = container_of(lock_count, struct mutex, count); unsigned long flags; /* - * some architectures leave the lock unlocked in the fastpath failure + * As a performance measurement, release the lock before doing other + * wakeup related duties to follow. This allows other tasks to acquire + * the lock sooner, while still handling cleanups in past unlock calls. + * This can be done as we do not enforce strict equivalence between the + * mutex counter and wait_list. + * + * + * Some architectures leave the lock unlocked in the fastpath failure * case, others need to leave it locked. In the later case we have to - * unlock it here + * unlock it here - as the lock counter is currently 0 or negative. */ if (__mutex_slowpath_needs_to_unlock()) atomic_set(&lock->count, 1); @@ -716,7 +754,9 @@ __mutex_unlock_common_slowpath(atomic_t *lock_count, int nested) __visible void __mutex_unlock_slowpath(atomic_t *lock_count) { - __mutex_unlock_common_slowpath(lock_count, 1); + struct mutex *lock = container_of(lock_count, struct mutex, count); + + __mutex_unlock_common_slowpath(lock, 1); } #ifndef CONFIG_DEBUG_LOCK_ALLOC diff --git a/kernel/locking/mutex.h b/kernel/locking/mutex.h index 4115fbf83b12..5cda397607f2 100644 --- a/kernel/locking/mutex.h +++ b/kernel/locking/mutex.h @@ -16,7 +16,7 @@ #define mutex_remove_waiter(lock, waiter, ti) \ __list_del((waiter)->list.prev, (waiter)->list.next) -#ifdef CONFIG_SMP +#ifdef CONFIG_MUTEX_SPIN_ON_OWNER static inline void mutex_set_owner(struct mutex *lock) { lock->owner = current; diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index a0ea2a141b3b..7c98873a3077 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -8,7 +8,7 @@ * Copyright (C) 2005 Kihon Technologies Inc., Steven Rostedt * Copyright (C) 2006 Esben Nielsen * - * See Documentation/rt-mutex-design.txt for details. + * See Documentation/locking/rt-mutex-design.txt for details. */ #include <linux/spinlock.h> #include <linux/export.h> diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index d6203faf2eb1..7628c3fc37ca 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -246,19 +246,22 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem) return sem; } +EXPORT_SYMBOL(rwsem_down_read_failed); static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem) { - if (!(count & RWSEM_ACTIVE_MASK)) { - /* try acquiring the write lock */ - if (sem->count == RWSEM_WAITING_BIAS && - cmpxchg(&sem->count, RWSEM_WAITING_BIAS, - RWSEM_ACTIVE_WRITE_BIAS) == RWSEM_WAITING_BIAS) { - if (!list_is_singular(&sem->wait_list)) - rwsem_atomic_update(RWSEM_WAITING_BIAS, sem); - return true; - } + /* + * Try acquiring the write lock. Check count first in order + * to reduce unnecessary expensive cmpxchg() operations. + */ + if (count == RWSEM_WAITING_BIAS && + cmpxchg(&sem->count, RWSEM_WAITING_BIAS, + RWSEM_ACTIVE_WRITE_BIAS) == RWSEM_WAITING_BIAS) { + if (!list_is_singular(&sem->wait_list)) + rwsem_atomic_update(RWSEM_WAITING_BIAS, sem); + return true; } + return false; } @@ -465,6 +468,7 @@ struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem) return sem; } +EXPORT_SYMBOL(rwsem_down_write_failed); /* * handle waking up a waiter on the semaphore @@ -485,6 +489,7 @@ struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem) return sem; } +EXPORT_SYMBOL(rwsem_wake); /* * downgrade a write lock into a read lock @@ -506,8 +511,4 @@ struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem) return sem; } - -EXPORT_SYMBOL(rwsem_down_read_failed); -EXPORT_SYMBOL(rwsem_down_write_failed); -EXPORT_SYMBOL(rwsem_wake); EXPORT_SYMBOL(rwsem_downgrade_wake); diff --git a/kernel/locking/semaphore.c b/kernel/locking/semaphore.c index 6815171a4fff..b8120abe594b 100644 --- a/kernel/locking/semaphore.c +++ b/kernel/locking/semaphore.c @@ -36,7 +36,7 @@ static noinline void __down(struct semaphore *sem); static noinline int __down_interruptible(struct semaphore *sem); static noinline int __down_killable(struct semaphore *sem); -static noinline int __down_timeout(struct semaphore *sem, long jiffies); +static noinline int __down_timeout(struct semaphore *sem, long timeout); static noinline void __up(struct semaphore *sem); /** @@ -145,14 +145,14 @@ EXPORT_SYMBOL(down_trylock); /** * down_timeout - acquire the semaphore within a specified time * @sem: the semaphore to be acquired - * @jiffies: how long to wait before failing + * @timeout: how long to wait before failing * * Attempts to acquire the semaphore. If no more tasks are allowed to * acquire the semaphore, calling this function will put the task to sleep. * If the semaphore is not released within the specified number of jiffies, * this function returns -ETIME. It returns 0 if the semaphore was acquired. */ -int down_timeout(struct semaphore *sem, long jiffies) +int down_timeout(struct semaphore *sem, long timeout) { unsigned long flags; int result = 0; @@ -161,7 +161,7 @@ int down_timeout(struct semaphore *sem, long jiffies) if (likely(sem->count > 0)) sem->count--; else - result = __down_timeout(sem, jiffies); + result = __down_timeout(sem, timeout); raw_spin_unlock_irqrestore(&sem->lock, flags); return result; @@ -248,9 +248,9 @@ static noinline int __sched __down_killable(struct semaphore *sem) return __down_common(sem, TASK_KILLABLE, MAX_SCHEDULE_TIMEOUT); } -static noinline int __sched __down_timeout(struct semaphore *sem, long jiffies) +static noinline int __sched __down_timeout(struct semaphore *sem, long timeout) { - return __down_common(sem, TASK_UNINTERRUPTIBLE, jiffies); + return __down_common(sem, TASK_UNINTERRUPTIBLE, timeout); } static noinline void __sched __up(struct semaphore *sem) diff --git a/kernel/module.c b/kernel/module.c index 03214bd288e9..65586ffa0c98 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -135,7 +135,7 @@ static int param_set_bool_enable_only(const char *val, } static const struct kernel_param_ops param_ops_bool_enable_only = { - .flags = KERNEL_PARAM_FL_NOARG, + .flags = KERNEL_PARAM_OPS_FL_NOARG, .set = param_set_bool_enable_only, .get = param_get_bool, }; @@ -3388,7 +3388,7 @@ static inline int is_arm_mapping_symbol(const char *str) { if (str[0] == '.' && str[1] == 'L') return true; - return str[0] == '$' && strchr("atd", str[1]) + return str[0] == '$' && strchr("axtd", str[1]) && (str[2] == '\0' || str[2] == '.'); } diff --git a/kernel/params.c b/kernel/params.c index 34f527023794..041b5899d5e2 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -83,6 +83,15 @@ bool parameq(const char *a, const char *b) return parameqn(a, b, strlen(a)+1); } +static void param_check_unsafe(const struct kernel_param *kp) +{ + if (kp->flags & KERNEL_PARAM_FL_UNSAFE) { + pr_warn("Setting dangerous option %s - tainting kernel\n", + kp->name); + add_taint(TAINT_USER, LOCKDEP_STILL_OK); + } +} + static int parse_one(char *param, char *val, const char *doing, @@ -104,11 +113,12 @@ static int parse_one(char *param, return 0; /* No one handled NULL, so do it here. */ if (!val && - !(params[i].ops->flags & KERNEL_PARAM_FL_NOARG)) + !(params[i].ops->flags & KERNEL_PARAM_OPS_FL_NOARG)) return -EINVAL; pr_debug("handling %s with %p\n", param, params[i].ops->set); mutex_lock(¶m_lock); + param_check_unsafe(¶ms[i]); err = params[i].ops->set(val, ¶ms[i]); mutex_unlock(¶m_lock); return err; @@ -318,7 +328,7 @@ int param_get_bool(char *buffer, const struct kernel_param *kp) EXPORT_SYMBOL(param_get_bool); struct kernel_param_ops param_ops_bool = { - .flags = KERNEL_PARAM_FL_NOARG, + .flags = KERNEL_PARAM_OPS_FL_NOARG, .set = param_set_bool, .get = param_get_bool, }; @@ -369,7 +379,7 @@ int param_set_bint(const char *val, const struct kernel_param *kp) EXPORT_SYMBOL(param_set_bint); struct kernel_param_ops param_ops_bint = { - .flags = KERNEL_PARAM_FL_NOARG, + .flags = KERNEL_PARAM_OPS_FL_NOARG, .set = param_set_bint, .get = param_get_int, }; @@ -552,6 +562,7 @@ static ssize_t param_attr_store(struct module_attribute *mattr, return -EPERM; mutex_lock(¶m_lock); + param_check_unsafe(attribute->param); err = attribute->param->ops->set(buf, attribute->param); mutex_unlock(¶m_lock); if (!err) diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index e4e4121fa327..bbef57f5bdfd 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -302,6 +302,10 @@ config PM_GENERIC_DOMAINS_RUNTIME def_bool y depends on PM_RUNTIME && PM_GENERIC_DOMAINS +config PM_GENERIC_DOMAINS_OF + def_bool y + depends on PM_GENERIC_DOMAINS && OF + config CPU_PM bool depends on SUSPEND || CPU_IDLE diff --git a/kernel/power/process.c b/kernel/power/process.c index 4ee194eb524b..7b323221b9ee 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -129,6 +129,7 @@ int freeze_processes(void) if (!pm_freezing) atomic_inc(&system_freezing_cnt); + pm_wakeup_clear(); printk("Freezing user space processes ... "); pm_freezing = true; error = try_to_freeze_tasks(true); diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index c4b8093c80b3..791a61892bb5 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1343,6 +1343,9 @@ void swsusp_free(void) { unsigned long fb_pfn, fr_pfn; + if (!forbidden_pages_map || !free_pages_map) + goto out; + memory_bm_position_reset(forbidden_pages_map); memory_bm_position_reset(free_pages_map); @@ -1370,6 +1373,7 @@ loop: goto loop; } +out: nr_copy_pages = 0; nr_meta_pages = 0; restore_pblist = NULL; diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 18c62195660f..4ca9a33ff620 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -146,17 +146,29 @@ static int platform_suspend_prepare(suspend_state_t state) static int platform_suspend_prepare_late(suspend_state_t state) { + return state == PM_SUSPEND_FREEZE && freeze_ops->prepare ? + freeze_ops->prepare() : 0; +} + +static int platform_suspend_prepare_noirq(suspend_state_t state) +{ return state != PM_SUSPEND_FREEZE && suspend_ops->prepare_late ? suspend_ops->prepare_late() : 0; } -static void platform_suspend_wake(suspend_state_t state) +static void platform_resume_noirq(suspend_state_t state) { if (state != PM_SUSPEND_FREEZE && suspend_ops->wake) suspend_ops->wake(); } -static void platform_suspend_finish(suspend_state_t state) +static void platform_resume_early(suspend_state_t state) +{ + if (state == PM_SUSPEND_FREEZE && freeze_ops->restore) + freeze_ops->restore(); +} + +static void platform_resume_finish(suspend_state_t state) { if (state != PM_SUSPEND_FREEZE && suspend_ops->finish) suspend_ops->finish(); @@ -172,7 +184,7 @@ static int platform_suspend_begin(suspend_state_t state) return 0; } -static void platform_suspend_end(suspend_state_t state) +static void platform_resume_end(suspend_state_t state) { if (state == PM_SUSPEND_FREEZE && freeze_ops && freeze_ops->end) freeze_ops->end(); @@ -180,7 +192,7 @@ static void platform_suspend_end(suspend_state_t state) suspend_ops->end(); } -static void platform_suspend_recover(suspend_state_t state) +static void platform_recover(suspend_state_t state) { if (state != PM_SUSPEND_FREEZE && suspend_ops->recover) suspend_ops->recover(); @@ -265,13 +277,22 @@ static int suspend_enter(suspend_state_t state, bool *wakeup) if (error) goto Platform_finish; - error = dpm_suspend_end(PMSG_SUSPEND); + error = dpm_suspend_late(PMSG_SUSPEND); if (error) { - printk(KERN_ERR "PM: Some devices failed to power down\n"); + printk(KERN_ERR "PM: late suspend of devices failed\n"); goto Platform_finish; } error = platform_suspend_prepare_late(state); if (error) + goto Devices_early_resume; + + error = dpm_suspend_noirq(PMSG_SUSPEND); + if (error) { + printk(KERN_ERR "PM: noirq suspend of devices failed\n"); + goto Platform_early_resume; + } + error = platform_suspend_prepare_noirq(state); + if (error) goto Platform_wake; if (suspend_test(TEST_PLATFORM)) @@ -318,11 +339,17 @@ static int suspend_enter(suspend_state_t state, bool *wakeup) enable_nonboot_cpus(); Platform_wake: - platform_suspend_wake(state); - dpm_resume_start(PMSG_RESUME); + platform_resume_noirq(state); + dpm_resume_noirq(PMSG_RESUME); + + Platform_early_resume: + platform_resume_early(state); + + Devices_early_resume: + dpm_resume_early(PMSG_RESUME); Platform_finish: - platform_suspend_finish(state); + platform_resume_finish(state); return error; } @@ -361,14 +388,16 @@ int suspend_devices_and_enter(suspend_state_t state) suspend_test_start(); dpm_resume_end(PMSG_RESUME); suspend_test_finish("resume devices"); + trace_suspend_resume(TPS("resume_console"), state, true); resume_console(); + trace_suspend_resume(TPS("resume_console"), state, false); Close: - platform_suspend_end(state); + platform_resume_end(state); return error; Recover_platform: - platform_suspend_recover(state); + platform_recover(state); goto Resume_devices; } diff --git a/kernel/power/suspend_test.c b/kernel/power/suspend_test.c index bd91bc177c93..084452e34a12 100644 --- a/kernel/power/suspend_test.c +++ b/kernel/power/suspend_test.c @@ -22,6 +22,8 @@ #define TEST_SUSPEND_SECONDS 10 static unsigned long suspend_test_start_time; +static u32 test_repeat_count_max = 1; +static u32 test_repeat_count_current; void suspend_test_start(void) { @@ -74,6 +76,7 @@ static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state) int status; /* this may fail if the RTC hasn't been initialized */ +repeat: status = rtc_read_time(rtc, &alm.time); if (status < 0) { printk(err_readtime, dev_name(&rtc->dev), status); @@ -100,10 +103,21 @@ static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state) if (state == PM_SUSPEND_STANDBY) { printk(info_test, pm_states[state]); status = pm_suspend(state); + if (status < 0) + state = PM_SUSPEND_FREEZE; } + if (state == PM_SUSPEND_FREEZE) { + printk(info_test, pm_states[state]); + status = pm_suspend(state); + } + if (status < 0) printk(err_suspend, status); + test_repeat_count_current++; + if (test_repeat_count_current < test_repeat_count_max) + goto repeat; + /* Some platforms can't detect that the alarm triggered the * wakeup, or (accordingly) disable it after it afterwards. * It's supposed to give oneshot behavior; cope. @@ -137,16 +151,28 @@ static char warn_bad_state[] __initdata = static int __init setup_test_suspend(char *value) { int i; + char *repeat; + char *suspend_type; - /* "=mem" ==> "mem" */ + /* example : "=mem[,N]" ==> "mem[,N]" */ value++; + suspend_type = strsep(&value, ","); + if (!suspend_type) + return 0; + + repeat = strsep(&value, ","); + if (repeat) { + if (kstrtou32(repeat, 0, &test_repeat_count_max)) + return 0; + } + for (i = 0; pm_labels[i]; i++) - if (!strcmp(pm_labels[i], value)) { + if (!strcmp(pm_labels[i], suspend_type)) { test_state_label = pm_labels[i]; return 0; } - printk(warn_bad_state, value); + printk(warn_bad_state, suspend_type); return 0; } __setup("test_suspend", setup_test_suspend); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index e04c455a0e38..7a6e69441f75 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -519,14 +519,13 @@ struct devkmsg_user { char buf[8192]; }; -static ssize_t devkmsg_writev(struct kiocb *iocb, const struct iovec *iv, - unsigned long count, loff_t pos) +static ssize_t devkmsg_write(struct kiocb *iocb, struct iov_iter *from) { char *buf, *line; int i; int level = default_message_loglevel; int facility = 1; /* LOG_USER */ - size_t len = iov_length(iv, count); + size_t len = iocb->ki_nbytes; ssize_t ret = len; if (len > LOG_LINE_MAX) @@ -535,13 +534,10 @@ static ssize_t devkmsg_writev(struct kiocb *iocb, const struct iovec *iv, if (buf == NULL) return -ENOMEM; - line = buf; - for (i = 0; i < count; i++) { - if (copy_from_user(line, iv[i].iov_base, iv[i].iov_len)) { - ret = -EFAULT; - goto out; - } - line += iv[i].iov_len; + buf[len] = '\0'; + if (copy_from_iter(buf, len, from) != len) { + kfree(buf); + return -EFAULT; } /* @@ -567,10 +563,8 @@ static ssize_t devkmsg_writev(struct kiocb *iocb, const struct iovec *iv, line = endp; } } - line[len] = '\0'; printk_emit(facility, level, NULL, 0, "%s", line); -out: kfree(buf); return ret; } @@ -802,7 +796,7 @@ static int devkmsg_release(struct inode *inode, struct file *file) const struct file_operations kmsg_fops = { .open = devkmsg_open, .read = devkmsg_read, - .aio_write = devkmsg_writev, + .write_iter = devkmsg_write, .llseek = devkmsg_llseek, .poll = devkmsg_poll, .release = devkmsg_release, @@ -1665,15 +1659,15 @@ asmlinkage int vprintk_emit(int facility, int level, raw_spin_lock(&logbuf_lock); logbuf_cpu = this_cpu; - if (recursion_bug) { + if (unlikely(recursion_bug)) { static const char recursion_msg[] = "BUG: recent printk recursion!"; recursion_bug = 0; - text_len = strlen(recursion_msg); /* emit KERN_CRIT message */ printed_len += log_store(0, 2, LOG_PREFIX|LOG_NEWLINE, 0, - NULL, 0, recursion_msg, text_len); + NULL, 0, recursion_msg, + strlen(recursion_msg)); } /* diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 948a7693748e..240fa9094f83 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -49,11 +49,19 @@ #include <linux/trace_clock.h> #include <asm/byteorder.h> #include <linux/torture.h> +#include <linux/vmalloc.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@joshtriplett.org>"); +torture_param(int, cbflood_inter_holdoff, HZ, + "Holdoff between floods (jiffies)"); +torture_param(int, cbflood_intra_holdoff, 1, + "Holdoff between bursts (jiffies)"); +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, fqs_duration, 0, "Duration of fqs bursts (us), 0 to disable"); torture_param(int, fqs_holdoff, 0, "Holdoff time within fqs bursts (us)"); @@ -96,10 +104,12 @@ module_param(torture_type, charp, 0444); MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh, ...)"); static int nrealreaders; +static int ncbflooders; static struct task_struct *writer_task; static struct task_struct **fakewriter_tasks; static struct task_struct **reader_tasks; static struct task_struct *stats_task; +static struct task_struct **cbflood_task; static struct task_struct *fqs_task; static struct task_struct *boost_tasks[NR_CPUS]; static struct task_struct *stall_task; @@ -138,6 +148,7 @@ static long n_rcu_torture_boosts; static long n_rcu_torture_timers; static long n_barrier_attempts; static long n_barrier_successes; +static atomic_long_t n_cbfloods; static struct list_head rcu_torture_removed; static int rcu_torture_writer_state; @@ -157,9 +168,9 @@ static int rcu_torture_writer_state; #else #define RCUTORTURE_RUNNABLE_INIT 0 #endif -int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT; -module_param(rcutorture_runnable, int, 0444); -MODULE_PARM_DESC(rcutorture_runnable, "Start rcutorture at boot"); +static int torture_runnable = RCUTORTURE_RUNNABLE_INIT; +module_param(torture_runnable, int, 0444); +MODULE_PARM_DESC(torture_runnable, "Start rcutorture at boot"); #if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU) #define rcu_can_boost() 1 @@ -182,7 +193,7 @@ static u64 notrace rcu_trace_clock_local(void) #endif /* #else #ifdef CONFIG_RCU_TRACE */ static unsigned long boost_starttime; /* jiffies of next boost test start. */ -DEFINE_MUTEX(boost_mutex); /* protect setting boost_starttime */ +static DEFINE_MUTEX(boost_mutex); /* protect setting boost_starttime */ /* and boost task create/destroy. */ static atomic_t barrier_cbs_count; /* Barrier callbacks registered. */ static bool barrier_phase; /* Test phase. */ @@ -242,7 +253,7 @@ struct rcu_torture_ops { void (*call)(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); void (*cb_barrier)(void); void (*fqs)(void); - void (*stats)(char *page); + void (*stats)(void); int irq_capable; int can_boost; const char *name; @@ -525,21 +536,21 @@ static void srcu_torture_barrier(void) srcu_barrier(&srcu_ctl); } -static void srcu_torture_stats(char *page) +static void srcu_torture_stats(void) { int cpu; int idx = srcu_ctl.completed & 0x1; - page += sprintf(page, "%s%s per-CPU(idx=%d):", - torture_type, TORTURE_FLAG, idx); + pr_alert("%s%s per-CPU(idx=%d):", + torture_type, TORTURE_FLAG, idx); for_each_possible_cpu(cpu) { long c0, c1; c0 = (long)per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[!idx]; c1 = (long)per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[idx]; - page += sprintf(page, " %d(%ld,%ld)", cpu, c0, c1); + pr_cont(" %d(%ld,%ld)", cpu, c0, c1); } - sprintf(page, "\n"); + pr_cont("\n"); } static void srcu_torture_synchronize_expedited(void) @@ -601,6 +612,52 @@ static struct rcu_torture_ops sched_ops = { .name = "sched" }; +#ifdef CONFIG_TASKS_RCU + +/* + * Definitions for RCU-tasks torture testing. + */ + +static int tasks_torture_read_lock(void) +{ + return 0; +} + +static void tasks_torture_read_unlock(int idx) +{ +} + +static void rcu_tasks_torture_deferred_free(struct rcu_torture *p) +{ + call_rcu_tasks(&p->rtort_rcu, rcu_torture_cb); +} + +static struct rcu_torture_ops tasks_ops = { + .ttype = RCU_TASKS_FLAVOR, + .init = rcu_sync_torture_init, + .readlock = tasks_torture_read_lock, + .read_delay = rcu_read_delay, /* just reuse rcu's version. */ + .readunlock = tasks_torture_read_unlock, + .completed = rcu_no_completed, + .deferred_free = rcu_tasks_torture_deferred_free, + .sync = synchronize_rcu_tasks, + .exp_sync = synchronize_rcu_tasks, + .call = call_rcu_tasks, + .cb_barrier = rcu_barrier_tasks, + .fqs = NULL, + .stats = NULL, + .irq_capable = 1, + .name = "tasks" +}; + +#define RCUTORTURE_TASKS_OPS &tasks_ops, + +#else /* #ifdef CONFIG_TASKS_RCU */ + +#define RCUTORTURE_TASKS_OPS + +#endif /* #else #ifdef CONFIG_TASKS_RCU */ + /* * RCU torture priority-boost testing. Runs one real-time thread per * CPU for moderate bursts, repeatedly registering RCU callbacks and @@ -667,7 +724,7 @@ static int rcu_torture_boost(void *arg) } call_rcu_time = jiffies; } - cond_resched(); + cond_resched_rcu_qs(); stutter_wait("rcu_torture_boost"); if (torture_must_stop()) goto checkwait; @@ -707,6 +764,58 @@ checkwait: stutter_wait("rcu_torture_boost"); return 0; } +static void rcu_torture_cbflood_cb(struct rcu_head *rhp) +{ +} + +/* + * RCU torture callback-flood kthread. Repeatedly induces bursts of calls + * to call_rcu() or analogous, increasing the probability of occurrence + * of callback-overflow corner cases. + */ +static int +rcu_torture_cbflood(void *arg) +{ + int err = 1; + int i; + int j; + struct rcu_head *rhp; + + if (cbflood_n_per_burst > 0 && + cbflood_inter_holdoff > 0 && + cbflood_intra_holdoff > 0 && + cur_ops->call && + cur_ops->cb_barrier) { + rhp = vmalloc(sizeof(*rhp) * + cbflood_n_burst * cbflood_n_per_burst); + err = !rhp; + } + if (err) { + VERBOSE_TOROUT_STRING("rcu_torture_cbflood disabled: Bad args or OOM"); + while (!torture_must_stop()) + schedule_timeout_interruptible(HZ); + return 0; + } + VERBOSE_TOROUT_STRING("rcu_torture_cbflood task started"); + do { + schedule_timeout_interruptible(cbflood_inter_holdoff); + atomic_long_inc(&n_cbfloods); + WARN_ON(signal_pending(current)); + for (i = 0; i < cbflood_n_burst; i++) { + for (j = 0; j < cbflood_n_per_burst; j++) { + cur_ops->call(&rhp[i * cbflood_n_per_burst + j], + rcu_torture_cbflood_cb); + } + schedule_timeout_interruptible(cbflood_intra_holdoff); + WARN_ON(signal_pending(current)); + } + cur_ops->cb_barrier(); + stutter_wait("rcu_torture_cbflood"); + } while (!torture_must_stop()); + torture_kthread_stopping("rcu_torture_cbflood"); + return 0; +} + /* * RCU torture force-quiescent-state kthread. Repeatedly induces * bursts of calls to force_quiescent_state(), increasing the probability @@ -1019,7 +1128,7 @@ rcu_torture_reader(void *arg) __this_cpu_inc(rcu_torture_batch[completed]); preempt_enable(); cur_ops->readunlock(idx); - cond_resched(); + cond_resched_rcu_qs(); stutter_wait("rcu_torture_reader"); } while (!torture_must_stop()); if (irqreader && cur_ops->irq_capable) { @@ -1031,10 +1140,15 @@ rcu_torture_reader(void *arg) } /* - * Create an RCU-torture statistics message in the specified buffer. + * Print torture statistics. Caller must ensure that there is only + * one call to this function at a given time!!! This is normally + * accomplished by relying on the module system to only have one copy + * of the module loaded, and then by giving the rcu_torture_stats + * kthread full control (or the init/cleanup functions when rcu_torture_stats + * thread is not running). */ static void -rcu_torture_printk(char *page) +rcu_torture_stats_print(void) { int cpu; int i; @@ -1052,55 +1166,61 @@ rcu_torture_printk(char *page) if (pipesummary[i] != 0) break; } - page += sprintf(page, "%s%s ", torture_type, TORTURE_FLAG); - page += sprintf(page, - "rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d ", - rcu_torture_current, - rcu_torture_current_version, - list_empty(&rcu_torture_freelist), - atomic_read(&n_rcu_torture_alloc), - atomic_read(&n_rcu_torture_alloc_fail), - atomic_read(&n_rcu_torture_free)); - page += sprintf(page, "rtmbe: %d rtbke: %ld rtbre: %ld ", - atomic_read(&n_rcu_torture_mberror), - n_rcu_torture_boost_ktrerror, - n_rcu_torture_boost_rterror); - page += sprintf(page, "rtbf: %ld rtb: %ld nt: %ld ", - n_rcu_torture_boost_failure, - n_rcu_torture_boosts, - n_rcu_torture_timers); - page = torture_onoff_stats(page); - page += sprintf(page, "barrier: %ld/%ld:%ld", - n_barrier_successes, - n_barrier_attempts, - n_rcu_torture_barrier_error); - page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG); + + pr_alert("%s%s ", torture_type, TORTURE_FLAG); + pr_cont("rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d ", + rcu_torture_current, + rcu_torture_current_version, + list_empty(&rcu_torture_freelist), + atomic_read(&n_rcu_torture_alloc), + atomic_read(&n_rcu_torture_alloc_fail), + atomic_read(&n_rcu_torture_free)); + pr_cont("rtmbe: %d rtbke: %ld rtbre: %ld ", + atomic_read(&n_rcu_torture_mberror), + n_rcu_torture_boost_ktrerror, + n_rcu_torture_boost_rterror); + pr_cont("rtbf: %ld rtb: %ld nt: %ld ", + n_rcu_torture_boost_failure, + n_rcu_torture_boosts, + n_rcu_torture_timers); + torture_onoff_stats(); + pr_cont("barrier: %ld/%ld:%ld ", + n_barrier_successes, + n_barrier_attempts, + n_rcu_torture_barrier_error); + pr_cont("cbflood: %ld\n", atomic_long_read(&n_cbfloods)); + + pr_alert("%s%s ", torture_type, TORTURE_FLAG); if (atomic_read(&n_rcu_torture_mberror) != 0 || n_rcu_torture_barrier_error != 0 || n_rcu_torture_boost_ktrerror != 0 || n_rcu_torture_boost_rterror != 0 || n_rcu_torture_boost_failure != 0 || i > 1) { - page += sprintf(page, "!!! "); + pr_cont("%s", "!!! "); atomic_inc(&n_rcu_torture_error); WARN_ON_ONCE(1); } - page += sprintf(page, "Reader Pipe: "); + pr_cont("Reader Pipe: "); for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) - page += sprintf(page, " %ld", pipesummary[i]); - page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG); - page += sprintf(page, "Reader Batch: "); + pr_cont(" %ld", pipesummary[i]); + pr_cont("\n"); + + pr_alert("%s%s ", torture_type, TORTURE_FLAG); + pr_cont("Reader Batch: "); for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) - page += sprintf(page, " %ld", batchsummary[i]); - page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG); - page += sprintf(page, "Free-Block Circulation: "); + pr_cont(" %ld", batchsummary[i]); + pr_cont("\n"); + + pr_alert("%s%s ", torture_type, TORTURE_FLAG); + pr_cont("Free-Block Circulation: "); for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) { - page += sprintf(page, " %d", - atomic_read(&rcu_torture_wcount[i])); + pr_cont(" %d", atomic_read(&rcu_torture_wcount[i])); } - page += sprintf(page, "\n"); + pr_cont("\n"); + if (cur_ops->stats) - cur_ops->stats(page); + cur_ops->stats(); if (rtcv_snap == rcu_torture_current_version && rcu_torture_current != NULL) { int __maybe_unused flags; @@ -1109,10 +1229,9 @@ rcu_torture_printk(char *page) rcutorture_get_gp_data(cur_ops->ttype, &flags, &gpnum, &completed); - page += sprintf(page, - "??? Writer stall state %d g%lu c%lu f%#x\n", - rcu_torture_writer_state, - gpnum, completed, flags); + pr_alert("??? Writer stall state %d g%lu c%lu f%#x\n", + rcu_torture_writer_state, + gpnum, completed, flags); show_rcu_gp_kthreads(); rcutorture_trace_dump(); } @@ -1120,30 +1239,6 @@ rcu_torture_printk(char *page) } /* - * Print torture statistics. Caller must ensure that there is only - * one call to this function at a given time!!! This is normally - * accomplished by relying on the module system to only have one copy - * of the module loaded, and then by giving the rcu_torture_stats - * kthread full control (or the init/cleanup functions when rcu_torture_stats - * thread is not running). - */ -static void -rcu_torture_stats_print(void) -{ - int size = nr_cpu_ids * 200 + 8192; - char *buf; - - buf = kmalloc(size, GFP_KERNEL); - if (!buf) { - pr_err("rcu-torture: Out of memory, need: %d", size); - return; - } - rcu_torture_printk(buf); - pr_alert("%s", buf); - kfree(buf); -} - -/* * Periodically prints torture statistics, if periodic statistics printing * was specified via the stat_interval module parameter. */ @@ -1295,7 +1390,8 @@ static int rcu_torture_barrier_cbs(void *arg) if (atomic_dec_and_test(&barrier_cbs_count)) wake_up(&barrier_wq); } while (!torture_must_stop()); - cur_ops->cb_barrier(); + if (cur_ops->cb_barrier != NULL) + cur_ops->cb_barrier(); destroy_rcu_head_on_stack(&rcu); torture_kthread_stopping("rcu_torture_barrier_cbs"); return 0; @@ -1418,7 +1514,7 @@ rcu_torture_cleanup(void) int i; rcutorture_record_test_transition(); - if (torture_cleanup()) { + if (torture_cleanup_begin()) { if (cur_ops->cb_barrier != NULL) cur_ops->cb_barrier(); return; @@ -1447,6 +1543,8 @@ rcu_torture_cleanup(void) 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) { unregister_cpu_notifier(&rcutorture_cpu_nb); @@ -1468,6 +1566,7 @@ rcu_torture_cleanup(void) "End of test: RCU_HOTPLUG"); else rcu_torture_print_module_parms(cur_ops, "End of test: SUCCESS"); + torture_cleanup_end(); } #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD @@ -1534,9 +1633,10 @@ rcu_torture_init(void) int firsterr = 0; static struct rcu_torture_ops *torture_ops[] = { &rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &sched_ops, + RCUTORTURE_TASKS_OPS }; - if (!torture_init_begin(torture_type, verbose, &rcutorture_runnable)) + if (!torture_init_begin(torture_type, verbose, &torture_runnable)) return -EBUSY; /* Process args and tell the world that the torturer is on the job. */ @@ -1693,6 +1793,24 @@ rcu_torture_init(void) goto unwind; if (object_debug) rcu_test_debug_objects(); + if (cbflood_n_burst > 0) { + /* Create the cbflood threads */ + ncbflooders = (num_online_cpus() + 3) / 4; + cbflood_task = kcalloc(ncbflooders, sizeof(*cbflood_task), + GFP_KERNEL); + if (!cbflood_task) { + VERBOSE_TOROUT_ERRSTRING("out of memory"); + firsterr = -ENOMEM; + goto unwind; + } + for (i = 0; i < ncbflooders; i++) { + firsterr = torture_create_kthread(rcu_torture_cbflood, + NULL, + cbflood_task[i]); + if (firsterr) + goto unwind; + } + } rcutorture_record_test_transition(); torture_init_end(); return 0; diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index d9efcc13008c..c0623fc47125 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -51,7 +51,7 @@ static long long rcu_dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; #include "tiny_plugin.h" -/* Common code for rcu_idle_enter() and rcu_irq_exit(), see kernel/rcutree.c. */ +/* Common code for rcu_idle_enter() and rcu_irq_exit(), see kernel/rcu/tree.c. */ static void rcu_idle_enter_common(long long newval) { if (newval) { @@ -62,7 +62,7 @@ static void rcu_idle_enter_common(long long newval) } RCU_TRACE(trace_rcu_dyntick(TPS("Start"), rcu_dynticks_nesting, newval)); - if (!is_idle_task(current)) { + if (IS_ENABLED(CONFIG_RCU_TRACE) && !is_idle_task(current)) { struct task_struct *idle __maybe_unused = idle_task(smp_processor_id()); RCU_TRACE(trace_rcu_dyntick(TPS("Entry error: not idle task"), @@ -72,7 +72,7 @@ static void rcu_idle_enter_common(long long newval) current->pid, current->comm, idle->pid, idle->comm); /* must be idle task! */ } - rcu_sched_qs(0); /* implies rcu_bh_qsctr_inc(0) */ + rcu_sched_qs(); /* implies rcu_bh_inc() */ barrier(); rcu_dynticks_nesting = newval; } @@ -114,7 +114,7 @@ void rcu_irq_exit(void) } EXPORT_SYMBOL_GPL(rcu_irq_exit); -/* Common code for rcu_idle_exit() and rcu_irq_enter(), see kernel/rcutree.c. */ +/* Common code for rcu_idle_exit() and rcu_irq_enter(), see kernel/rcu/tree.c. */ static void rcu_idle_exit_common(long long oldval) { if (oldval) { @@ -123,7 +123,7 @@ static void rcu_idle_exit_common(long long oldval) return; } RCU_TRACE(trace_rcu_dyntick(TPS("End"), oldval, rcu_dynticks_nesting)); - if (!is_idle_task(current)) { + if (IS_ENABLED(CONFIG_RCU_TRACE) && !is_idle_task(current)) { struct task_struct *idle __maybe_unused = idle_task(smp_processor_id()); RCU_TRACE(trace_rcu_dyntick(TPS("Exit error: not idle task"), @@ -217,7 +217,7 @@ static int rcu_qsctr_help(struct rcu_ctrlblk *rcp) * are at it, given that any rcu quiescent state is also an rcu_bh * quiescent state. Use "+" instead of "||" to defeat short circuiting. */ -void rcu_sched_qs(int cpu) +void rcu_sched_qs(void) { unsigned long flags; @@ -231,7 +231,7 @@ void rcu_sched_qs(int cpu) /* * Record an rcu_bh quiescent state. */ -void rcu_bh_qs(int cpu) +void rcu_bh_qs(void) { unsigned long flags; @@ -251,9 +251,11 @@ void rcu_check_callbacks(int cpu, int user) { RCU_TRACE(check_cpu_stalls()); if (user || rcu_is_cpu_rrupt_from_idle()) - rcu_sched_qs(cpu); + rcu_sched_qs(); else if (!in_softirq()) - rcu_bh_qs(cpu); + rcu_bh_qs(); + if (user) + rcu_note_voluntary_context_switch(current); } /* diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 1b70cb6fbe3c..133e47223095 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -79,9 +79,18 @@ static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS]; * the tracing userspace tools to be able to decipher the string * address to the matching string. */ -#define RCU_STATE_INITIALIZER(sname, sabbr, cr) \ +#ifdef CONFIG_TRACING +# define DEFINE_RCU_TPS(sname) \ static char sname##_varname[] = #sname; \ -static const char *tp_##sname##_varname __used __tracepoint_string = sname##_varname; \ +static const char *tp_##sname##_varname __used __tracepoint_string = sname##_varname; +# define RCU_STATE_NAME(sname) sname##_varname +#else +# define DEFINE_RCU_TPS(sname) +# define RCU_STATE_NAME(sname) __stringify(sname) +#endif + +#define RCU_STATE_INITIALIZER(sname, sabbr, cr) \ +DEFINE_RCU_TPS(sname) \ struct rcu_state sname##_state = { \ .level = { &sname##_state.node[0] }, \ .call = cr, \ @@ -93,7 +102,7 @@ struct rcu_state sname##_state = { \ .orphan_donetail = &sname##_state.orphan_donelist, \ .barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \ .onoff_mutex = __MUTEX_INITIALIZER(sname##_state.onoff_mutex), \ - .name = sname##_varname, \ + .name = RCU_STATE_NAME(sname), \ .abbr = sabbr, \ }; \ DEFINE_PER_CPU(struct rcu_data, sname##_data) @@ -188,22 +197,24 @@ static int rcu_gp_in_progress(struct rcu_state *rsp) * one since the start of the grace period, this just sets a flag. * The caller must have disabled preemption. */ -void rcu_sched_qs(int cpu) +void rcu_sched_qs(void) { - struct rcu_data *rdp = &per_cpu(rcu_sched_data, cpu); - - if (rdp->passed_quiesce == 0) - trace_rcu_grace_period(TPS("rcu_sched"), rdp->gpnum, TPS("cpuqs")); - rdp->passed_quiesce = 1; + if (!__this_cpu_read(rcu_sched_data.passed_quiesce)) { + trace_rcu_grace_period(TPS("rcu_sched"), + __this_cpu_read(rcu_sched_data.gpnum), + TPS("cpuqs")); + __this_cpu_write(rcu_sched_data.passed_quiesce, 1); + } } -void rcu_bh_qs(int cpu) +void rcu_bh_qs(void) { - struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu); - - if (rdp->passed_quiesce == 0) - trace_rcu_grace_period(TPS("rcu_bh"), rdp->gpnum, TPS("cpuqs")); - rdp->passed_quiesce = 1; + if (!__this_cpu_read(rcu_bh_data.passed_quiesce)) { + trace_rcu_grace_period(TPS("rcu_bh"), + __this_cpu_read(rcu_bh_data.gpnum), + TPS("cpuqs")); + __this_cpu_write(rcu_bh_data.passed_quiesce, 1); + } } static DEFINE_PER_CPU(int, rcu_sched_qs_mask); @@ -278,7 +289,7 @@ static void rcu_momentary_dyntick_idle(void) void rcu_note_context_switch(int cpu) { trace_rcu_utilization(TPS("Start context switch")); - rcu_sched_qs(cpu); + rcu_sched_qs(); rcu_preempt_note_context_switch(cpu); if (unlikely(raw_cpu_read(rcu_sched_qs_mask))) rcu_momentary_dyntick_idle(); @@ -526,6 +537,7 @@ static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval, atomic_inc(&rdtp->dynticks); smp_mb__after_atomic(); /* Force ordering with next sojourn. */ WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1); + rcu_dynticks_task_enter(); /* * It is illegal to enter an extended quiescent state while @@ -642,6 +654,7 @@ void rcu_irq_exit(void) static void rcu_eqs_exit_common(struct rcu_dynticks *rdtp, long long oldval, int user) { + rcu_dynticks_task_exit(); smp_mb__before_atomic(); /* Force ordering w/previous sojourn. */ atomic_inc(&rdtp->dynticks); /* CPUs seeing atomic_inc() must see later RCU read-side crit sects */ @@ -819,7 +832,7 @@ bool notrace __rcu_is_watching(void) */ bool notrace rcu_is_watching(void) { - int ret; + bool ret; preempt_disable(); ret = __rcu_is_watching(); @@ -1647,7 +1660,7 @@ static int rcu_gp_init(struct rcu_state *rsp) rnp->level, rnp->grplo, rnp->grphi, rnp->qsmask); raw_spin_unlock_irq(&rnp->lock); - cond_resched(); + cond_resched_rcu_qs(); } mutex_unlock(&rsp->onoff_mutex); @@ -1668,7 +1681,7 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in) if (fqs_state == RCU_SAVE_DYNTICK) { /* Collect dyntick-idle snapshots. */ if (is_sysidle_rcu_state(rsp)) { - isidle = 1; + isidle = true; maxj = jiffies - ULONG_MAX / 4; } force_qs_rnp(rsp, dyntick_save_progress_counter, @@ -1677,14 +1690,15 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in) fqs_state = RCU_FORCE_QS; } else { /* Handle dyntick-idle and offline CPUs. */ - isidle = 0; + isidle = false; force_qs_rnp(rsp, rcu_implicit_dynticks_qs, &isidle, &maxj); } /* Clear flag to prevent immediate re-entry. */ if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) { raw_spin_lock_irq(&rnp->lock); smp_mb__after_unlock_lock(); - ACCESS_ONCE(rsp->gp_flags) &= ~RCU_GP_FLAG_FQS; + ACCESS_ONCE(rsp->gp_flags) = + ACCESS_ONCE(rsp->gp_flags) & ~RCU_GP_FLAG_FQS; raw_spin_unlock_irq(&rnp->lock); } return fqs_state; @@ -1736,7 +1750,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) /* smp_mb() provided by prior unlock-lock pair. */ nocb += rcu_future_gp_cleanup(rsp, rnp); raw_spin_unlock_irq(&rnp->lock); - cond_resched(); + cond_resched_rcu_qs(); } rnp = rcu_get_root(rsp); raw_spin_lock_irq(&rnp->lock); @@ -1785,8 +1799,8 @@ static int __noreturn rcu_gp_kthread(void *arg) /* Locking provides needed memory barrier. */ if (rcu_gp_init(rsp)) break; - cond_resched(); - flush_signals(current); + cond_resched_rcu_qs(); + WARN_ON(signal_pending(current)); trace_rcu_grace_period(rsp->name, ACCESS_ONCE(rsp->gpnum), TPS("reqwaitsig")); @@ -1828,11 +1842,11 @@ static int __noreturn rcu_gp_kthread(void *arg) trace_rcu_grace_period(rsp->name, ACCESS_ONCE(rsp->gpnum), TPS("fqsend")); - cond_resched(); + cond_resched_rcu_qs(); } else { /* Deal with stray signal. */ - cond_resched(); - flush_signals(current); + cond_resched_rcu_qs(); + WARN_ON(signal_pending(current)); trace_rcu_grace_period(rsp->name, ACCESS_ONCE(rsp->gpnum), TPS("fqswaitsig")); @@ -1928,7 +1942,7 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) { WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags); - wake_up(&rsp->gp_wq); /* Memory barrier implied by wake_up() path. */ + rcu_gp_kthread_wake(rsp); } /* @@ -2210,8 +2224,6 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) /* Adjust any no-longer-needed kthreads. */ rcu_boost_kthread_setaffinity(rnp, -1); - /* Remove the dead CPU from the bitmasks in the rcu_node hierarchy. */ - /* Exclude any attempts to start a new grace period. */ mutex_lock(&rsp->onoff_mutex); raw_spin_lock_irqsave(&rsp->orphan_lock, flags); @@ -2393,8 +2405,8 @@ void rcu_check_callbacks(int cpu, int user) * at least not while the corresponding CPU is online. */ - rcu_sched_qs(cpu); - rcu_bh_qs(cpu); + rcu_sched_qs(); + rcu_bh_qs(); } else if (!in_softirq()) { @@ -2405,11 +2417,13 @@ void rcu_check_callbacks(int cpu, int user) * critical section, so note it. */ - rcu_bh_qs(cpu); + rcu_bh_qs(); } rcu_preempt_check_callbacks(cpu); if (rcu_pending(cpu)) invoke_rcu_core(); + if (user) + rcu_note_voluntary_context_switch(current); trace_rcu_utilization(TPS("End scheduler-tick")); } @@ -2432,7 +2446,7 @@ static void force_qs_rnp(struct rcu_state *rsp, struct rcu_node *rnp; rcu_for_each_leaf_node(rsp, rnp) { - cond_resched(); + cond_resched_rcu_qs(); mask = 0; raw_spin_lock_irqsave(&rnp->lock, flags); smp_mb__after_unlock_lock(); @@ -2449,7 +2463,7 @@ static void force_qs_rnp(struct rcu_state *rsp, for (; cpu <= rnp->grphi; cpu++, bit <<= 1) { if ((rnp->qsmask & bit) != 0) { if ((rnp->qsmaskinit & bit) != 0) - *isidle = 0; + *isidle = false; if (f(per_cpu_ptr(rsp->rda, cpu), isidle, maxj)) mask |= bit; } @@ -2505,9 +2519,10 @@ static void force_quiescent_state(struct rcu_state *rsp) raw_spin_unlock_irqrestore(&rnp_old->lock, flags); return; /* Someone beat us to it. */ } - ACCESS_ONCE(rsp->gp_flags) |= RCU_GP_FLAG_FQS; + ACCESS_ONCE(rsp->gp_flags) = + ACCESS_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS; raw_spin_unlock_irqrestore(&rnp_old->lock, flags); - wake_up(&rsp->gp_wq); /* Memory barrier implied by wake_up() path. */ + rcu_gp_kthread_wake(rsp); } /* @@ -2925,11 +2940,6 @@ static int synchronize_sched_expedited_cpu_stop(void *data) * restructure your code to batch your updates, and then use a single * synchronize_sched() instead. * - * Note that it is illegal to call this function while holding any lock - * that is acquired by a CPU-hotplug notifier. And yes, it is also illegal - * to call this function from a CPU-hotplug notifier. Failing to observe - * these restriction will result in deadlock. - * * This implementation can be thought of as an application of ticket * locking to RCU, with sync_sched_expedited_started and * sync_sched_expedited_done taking on the roles of the halves @@ -2979,7 +2989,12 @@ void synchronize_sched_expedited(void) */ snap = atomic_long_inc_return(&rsp->expedited_start); firstsnap = snap; - get_online_cpus(); + if (!try_get_online_cpus()) { + /* CPU hotplug operation in flight, fall back to normal GP. */ + wait_rcu_gp(call_rcu_sched); + atomic_long_inc(&rsp->expedited_normal); + return; + } WARN_ON_ONCE(cpu_is_offline(raw_smp_processor_id())); /* @@ -3026,7 +3041,12 @@ void synchronize_sched_expedited(void) * and they started after our first try, so their grace * period works for us. */ - get_online_cpus(); + if (!try_get_online_cpus()) { + /* CPU hotplug operation in flight, use normal GP. */ + wait_rcu_gp(call_rcu_sched); + atomic_long_inc(&rsp->expedited_normal); + return; + } snap = atomic_long_read(&rsp->expedited_start); smp_mb(); /* ensure read is before try_stop_cpus(). */ } @@ -3442,6 +3462,7 @@ static int rcu_cpu_notify(struct notifier_block *self, case CPU_UP_PREPARE_FROZEN: rcu_prepare_cpu(cpu); rcu_prepare_kthreads(cpu); + rcu_spawn_all_nocb_kthreads(cpu); break; case CPU_ONLINE: case CPU_DOWN_FAILED: @@ -3489,7 +3510,7 @@ static int rcu_pm_notify(struct notifier_block *self, } /* - * Spawn the kthread that handles this RCU flavor's grace periods. + * Spawn the kthreads that handle each RCU flavor's grace periods. */ static int __init rcu_spawn_gp_kthread(void) { @@ -3498,6 +3519,7 @@ static int __init rcu_spawn_gp_kthread(void) struct rcu_state *rsp; struct task_struct *t; + rcu_scheduler_fully_active = 1; for_each_rcu_flavor(rsp) { t = kthread_run(rcu_gp_kthread, rsp, "%s", rsp->name); BUG_ON(IS_ERR(t)); @@ -3505,8 +3527,9 @@ static int __init rcu_spawn_gp_kthread(void) raw_spin_lock_irqsave(&rnp->lock, flags); rsp->gp_kthread = t; raw_spin_unlock_irqrestore(&rnp->lock, flags); - rcu_spawn_nocb_kthreads(rsp); } + rcu_spawn_nocb_kthreads(); + rcu_spawn_boost_kthreads(); return 0; } early_initcall(rcu_spawn_gp_kthread); diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 6a86eb7bac45..d03764652d91 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -350,7 +350,7 @@ struct rcu_data { int nocb_p_count_lazy; /* (approximate). */ wait_queue_head_t nocb_wq; /* For nocb kthreads to sleep on. */ struct task_struct *nocb_kthread; - bool nocb_defer_wakeup; /* Defer wakeup of nocb_kthread. */ + int nocb_defer_wakeup; /* Defer wakeup of nocb_kthread. */ /* The following fields are used by the leader, hence own cacheline. */ struct rcu_head *nocb_gp_head ____cacheline_internodealigned_in_smp; @@ -383,6 +383,11 @@ struct rcu_data { #define RCU_FORCE_QS 3 /* Need to force quiescent state. */ #define RCU_SIGNAL_INIT RCU_SAVE_DYNTICK +/* Values for nocb_defer_wakeup field in struct rcu_data. */ +#define RCU_NOGP_WAKE_NOT 0 +#define RCU_NOGP_WAKE 1 +#define RCU_NOGP_WAKE_FORCE 2 + #define RCU_JIFFIES_TILL_FORCE_QS (1 + (HZ > 250) + (HZ > 500)) /* For jiffies_till_first_fqs and */ /* and jiffies_till_next_fqs. */ @@ -572,6 +577,7 @@ static void rcu_preempt_do_callbacks(void); static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp, struct rcu_node *rnp); #endif /* #ifdef CONFIG_RCU_BOOST */ +static void __init rcu_spawn_boost_kthreads(void); static void rcu_prepare_kthreads(int cpu); static void rcu_cleanup_after_idle(int cpu); static void rcu_prepare_for_idle(int cpu); @@ -589,10 +595,14 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp, static bool rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp, struct rcu_data *rdp, unsigned long flags); -static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp); +static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp); static void do_nocb_deferred_wakeup(struct rcu_data *rdp); static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp); -static void rcu_spawn_nocb_kthreads(struct rcu_state *rsp); +static void rcu_spawn_all_nocb_kthreads(int cpu); +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_sysidle_enter(struct rcu_dynticks *rdtp, int irq); @@ -605,6 +615,8 @@ static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle, static void rcu_bind_gp_kthread(void); static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp); static bool rcu_nohz_full_cpu(struct rcu_state *rsp); +static void rcu_dynticks_task_enter(void); +static void rcu_dynticks_task_exit(void); #endif /* #ifndef RCU_TREE_NONCORE */ diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index a7997e272564..387dd4599344 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -85,33 +85,6 @@ static void __init rcu_bootup_announce_oddness(void) 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=%d.\n", NR_CPUS, nr_cpu_ids); -#ifdef CONFIG_RCU_NOCB_CPU -#ifndef CONFIG_RCU_NOCB_CPU_NONE - if (!have_rcu_nocb_mask) { - zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL); - have_rcu_nocb_mask = true; - } -#ifdef CONFIG_RCU_NOCB_CPU_ZERO - pr_info("\tOffload RCU callbacks from CPU 0\n"); - cpumask_set_cpu(0, rcu_nocb_mask); -#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ZERO */ -#ifdef CONFIG_RCU_NOCB_CPU_ALL - pr_info("\tOffload RCU callbacks from all CPUs\n"); - cpumask_copy(rcu_nocb_mask, cpu_possible_mask); -#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ALL */ -#endif /* #ifndef CONFIG_RCU_NOCB_CPU_NONE */ - if (have_rcu_nocb_mask) { - if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) { - pr_info("\tNote: kernel parameter 'rcu_nocbs=' contains nonexistent CPUs.\n"); - cpumask_and(rcu_nocb_mask, cpu_possible_mask, - rcu_nocb_mask); - } - cpulist_scnprintf(nocb_buf, sizeof(nocb_buf), rcu_nocb_mask); - pr_info("\tOffload RCU callbacks from CPUs: %s.\n", nocb_buf); - if (rcu_nocb_poll) - pr_info("\tPoll for callbacks from no-CBs CPUs.\n"); - } -#endif /* #ifdef CONFIG_RCU_NOCB_CPU */ } #ifdef CONFIG_TREE_PREEMPT_RCU @@ -134,7 +107,7 @@ static void __init rcu_bootup_announce(void) * Return the number of RCU-preempt batches processed thus far * for debug and statistics. */ -long rcu_batches_completed_preempt(void) +static long rcu_batches_completed_preempt(void) { return rcu_preempt_state.completed; } @@ -155,18 +128,19 @@ EXPORT_SYMBOL_GPL(rcu_batches_completed); * not in a quiescent state. There might be any number of tasks blocked * while in an RCU read-side critical section. * - * Unlike the other rcu_*_qs() functions, callers to this function - * must disable irqs in order to protect the assignment to - * ->rcu_read_unlock_special. - */ -static void rcu_preempt_qs(int cpu) -{ - struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu); - - if (rdp->passed_quiesce == 0) - trace_rcu_grace_period(TPS("rcu_preempt"), rdp->gpnum, TPS("cpuqs")); - rdp->passed_quiesce = 1; - current->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS; + * As with the other rcu_*_qs() functions, callers to this function + * must disable preemption. + */ +static void rcu_preempt_qs(void) +{ + if (!__this_cpu_read(rcu_preempt_data.passed_quiesce)) { + trace_rcu_grace_period(TPS("rcu_preempt"), + __this_cpu_read(rcu_preempt_data.gpnum), + TPS("cpuqs")); + __this_cpu_write(rcu_preempt_data.passed_quiesce, 1); + barrier(); /* Coordinate with rcu_preempt_check_callbacks(). */ + current->rcu_read_unlock_special.b.need_qs = false; + } } /* @@ -190,14 +164,14 @@ static void rcu_preempt_note_context_switch(int cpu) struct rcu_node *rnp; if (t->rcu_read_lock_nesting > 0 && - (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) { + !t->rcu_read_unlock_special.b.blocked) { /* Possibly blocking in an RCU read-side critical section. */ rdp = per_cpu_ptr(rcu_preempt_state.rda, cpu); rnp = rdp->mynode; raw_spin_lock_irqsave(&rnp->lock, flags); smp_mb__after_unlock_lock(); - t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED; + t->rcu_read_unlock_special.b.blocked = true; t->rcu_blocked_node = rnp; /* @@ -239,7 +213,7 @@ static void rcu_preempt_note_context_switch(int cpu) : rnp->gpnum + 1); raw_spin_unlock_irqrestore(&rnp->lock, flags); } else if (t->rcu_read_lock_nesting < 0 && - t->rcu_read_unlock_special) { + t->rcu_read_unlock_special.s) { /* * Complete exit from RCU read-side critical section on @@ -257,9 +231,7 @@ static void rcu_preempt_note_context_switch(int cpu) * grace period, then the fact that the task has been enqueued * means that we continue to block the current grace period. */ - local_irq_save(flags); - rcu_preempt_qs(cpu); - local_irq_restore(flags); + rcu_preempt_qs(); } /* @@ -340,7 +312,7 @@ void rcu_read_unlock_special(struct task_struct *t) bool drop_boost_mutex = false; #endif /* #ifdef CONFIG_RCU_BOOST */ struct rcu_node *rnp; - int special; + union rcu_special special; /* NMI handlers cannot block and cannot safely manipulate state. */ if (in_nmi()) @@ -350,12 +322,13 @@ void rcu_read_unlock_special(struct task_struct *t) /* * If RCU core is waiting for this CPU to exit critical section, - * let it know that we have done so. + * let it know that we have done so. Because irqs are disabled, + * t->rcu_read_unlock_special cannot change. */ special = t->rcu_read_unlock_special; - if (special & RCU_READ_UNLOCK_NEED_QS) { - rcu_preempt_qs(smp_processor_id()); - if (!t->rcu_read_unlock_special) { + if (special.b.need_qs) { + rcu_preempt_qs(); + if (!t->rcu_read_unlock_special.s) { local_irq_restore(flags); return; } @@ -368,8 +341,8 @@ void rcu_read_unlock_special(struct task_struct *t) } /* Clean up if blocked during RCU read-side critical section. */ - if (special & RCU_READ_UNLOCK_BLOCKED) { - t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_BLOCKED; + if (special.b.blocked) { + t->rcu_read_unlock_special.b.blocked = false; /* * Remove this task from the list it blocked on. The @@ -653,12 +626,13 @@ static void rcu_preempt_check_callbacks(int cpu) struct task_struct *t = current; if (t->rcu_read_lock_nesting == 0) { - rcu_preempt_qs(cpu); + rcu_preempt_qs(); return; } if (t->rcu_read_lock_nesting > 0 && - per_cpu(rcu_preempt_data, cpu).qs_pending) - t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS; + per_cpu(rcu_preempt_data, cpu).qs_pending && + !per_cpu(rcu_preempt_data, cpu).passed_quiesce) + t->rcu_read_unlock_special.b.need_qs = true; } #ifdef CONFIG_RCU_BOOST @@ -819,11 +793,6 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp) * In fact, if you are using synchronize_rcu_expedited() in a loop, * please restructure your code to batch your updates, and then Use a * single synchronize_rcu() instead. - * - * Note that it is illegal to call this function while holding any lock - * that is acquired by a CPU-hotplug notifier. And yes, it is also illegal - * to call this function from a CPU-hotplug notifier. Failing to observe - * these restriction will result in deadlock. */ void synchronize_rcu_expedited(void) { @@ -845,7 +814,11 @@ void synchronize_rcu_expedited(void) * being boosted. This simplifies the process of moving tasks * from leaf to root rcu_node structures. */ - get_online_cpus(); + if (!try_get_online_cpus()) { + /* CPU-hotplug operation in flight, fall back to normal GP. */ + wait_rcu_gp(call_rcu); + return; + } /* * Acquire lock, falling back to synchronize_rcu() if too many @@ -897,7 +870,8 @@ void synchronize_rcu_expedited(void) /* Clean up and exit. */ smp_mb(); /* ensure expedited GP seen before counter increment. */ - ACCESS_ONCE(sync_rcu_preempt_exp_count)++; + ACCESS_ONCE(sync_rcu_preempt_exp_count) = + sync_rcu_preempt_exp_count + 1; unlock_mb_ret: mutex_unlock(&sync_rcu_preempt_exp_mutex); mb_ret: @@ -941,7 +915,7 @@ void exit_rcu(void) return; t->rcu_read_lock_nesting = 1; barrier(); - t->rcu_read_unlock_special = RCU_READ_UNLOCK_BLOCKED; + t->rcu_read_unlock_special.b.blocked = true; __rcu_read_unlock(); } @@ -1462,14 +1436,13 @@ static struct smp_hotplug_thread rcu_cpu_thread_spec = { }; /* - * Spawn all kthreads -- called as soon as the scheduler is running. + * Spawn boost kthreads -- called as soon as the scheduler is running. */ -static int __init rcu_spawn_kthreads(void) +static void __init rcu_spawn_boost_kthreads(void) { struct rcu_node *rnp; int cpu; - rcu_scheduler_fully_active = 1; for_each_possible_cpu(cpu) per_cpu(rcu_cpu_has_work, cpu) = 0; BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec)); @@ -1479,9 +1452,7 @@ static int __init rcu_spawn_kthreads(void) rcu_for_each_leaf_node(rcu_state_p, rnp) (void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp); } - return 0; } -early_initcall(rcu_spawn_kthreads); static void rcu_prepare_kthreads(int cpu) { @@ -1519,12 +1490,9 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) { } -static int __init rcu_scheduler_really_started(void) +static void __init rcu_spawn_boost_kthreads(void) { - rcu_scheduler_fully_active = 1; - return 0; } -early_initcall(rcu_scheduler_really_started); static void rcu_prepare_kthreads(int cpu) { @@ -1625,7 +1593,7 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void) /* Exit early if we advanced recently. */ if (jiffies == rdtp->last_advance_all) - return 0; + return false; rdtp->last_advance_all = jiffies; for_each_rcu_flavor(rsp) { @@ -1848,7 +1816,7 @@ static int rcu_oom_notify(struct notifier_block *self, get_online_cpus(); for_each_online_cpu(cpu) { smp_call_function_single(cpu, rcu_oom_notify_cpu, NULL, 1); - cond_resched(); + cond_resched_rcu_qs(); } put_online_cpus(); @@ -2075,7 +2043,7 @@ static void wake_nocb_leader(struct rcu_data *rdp, bool force) if (!ACCESS_ONCE(rdp_leader->nocb_kthread)) return; if (ACCESS_ONCE(rdp_leader->nocb_leader_sleep) || force) { - /* Prior xchg orders against prior callback enqueue. */ + /* Prior smp_mb__after_atomic() orders against prior enqueue. */ ACCESS_ONCE(rdp_leader->nocb_leader_sleep) = false; wake_up(&rdp_leader->nocb_wq); } @@ -2104,6 +2072,7 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp, ACCESS_ONCE(*old_rhpp) = rhp; atomic_long_add(rhcount, &rdp->nocb_q_count); atomic_long_add(rhcount_lazy, &rdp->nocb_q_count_lazy); + smp_mb__after_atomic(); /* Store *old_rhpp before _wake test. */ /* If we are not being polled and there is a kthread, awaken it ... */ t = ACCESS_ONCE(rdp->nocb_kthread); @@ -2120,16 +2089,23 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp, trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeEmpty")); } else { - rdp->nocb_defer_wakeup = true; + rdp->nocb_defer_wakeup = RCU_NOGP_WAKE; trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeEmptyIsDeferred")); } rdp->qlen_last_fqs_check = 0; } else if (len > rdp->qlen_last_fqs_check + qhimark) { /* ... or if many callbacks queued. */ - wake_nocb_leader(rdp, true); + if (!irqs_disabled_flags(flags)) { + wake_nocb_leader(rdp, true); + trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, + TPS("WakeOvf")); + } else { + rdp->nocb_defer_wakeup = RCU_NOGP_WAKE_FORCE; + trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, + TPS("WakeOvfIsDeferred")); + } rdp->qlen_last_fqs_check = LONG_MAX / 2; - trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeOvf")); } else { trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeNot")); } @@ -2150,7 +2126,7 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp, { if (!rcu_is_nocb_cpu(rdp->cpu)) - return 0; + return false; __call_rcu_nocb_enqueue(rdp, rhp, &rhp->next, 1, lazy, flags); if (__is_kfree_rcu_offset((unsigned long)rhp->func)) trace_rcu_kfree_callback(rdp->rsp->name, rhp, @@ -2161,7 +2137,18 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp, trace_rcu_callback(rdp->rsp->name, rhp, -atomic_long_read(&rdp->nocb_q_count_lazy), -atomic_long_read(&rdp->nocb_q_count)); - return 1; + + /* + * If called from an extended quiescent state with interrupts + * disabled, invoke the RCU core in order to allow the idle-entry + * deferred-wakeup check to function. + */ + if (irqs_disabled_flags(flags) && + !rcu_is_watching() && + cpu_online(smp_processor_id())) + invoke_rcu_core(); + + return true; } /* @@ -2177,7 +2164,7 @@ static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp, /* If this is not a no-CBs CPU, tell the caller to do it the old way. */ if (!rcu_is_nocb_cpu(smp_processor_id())) - return 0; + return false; rsp->qlen = 0; rsp->qlen_lazy = 0; @@ -2196,7 +2183,7 @@ static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp, rsp->orphan_nxtlist = NULL; rsp->orphan_nxttail = &rsp->orphan_nxtlist; } - return 1; + return true; } /* @@ -2229,7 +2216,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp) (d = ULONG_CMP_GE(ACCESS_ONCE(rnp->completed), c))); if (likely(d)) break; - flush_signals(current); + WARN_ON(signal_pending(current)); trace_rcu_future_gp(rnp, rdp, c, TPS("ResumeWait")); } trace_rcu_future_gp(rnp, rdp, c, TPS("EndWait")); @@ -2288,7 +2275,7 @@ wait_again: if (!rcu_nocb_poll) trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, "WokeEmpty"); - flush_signals(current); + WARN_ON(signal_pending(current)); schedule_timeout_interruptible(1); /* Rescan in case we were a victim of memory ordering. */ @@ -2327,6 +2314,7 @@ wait_again: atomic_long_add(rdp->nocb_gp_count, &rdp->nocb_follower_count); atomic_long_add(rdp->nocb_gp_count_lazy, &rdp->nocb_follower_count_lazy); + smp_mb__after_atomic(); /* Store *tail before wakeup. */ if (rdp != my_rdp && tail == &rdp->nocb_follower_head) { /* * List was empty, wake up the follower. @@ -2367,7 +2355,7 @@ static void nocb_follower_wait(struct rcu_data *rdp) if (!rcu_nocb_poll) trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, "WokeEmpty"); - flush_signals(current); + WARN_ON(signal_pending(current)); schedule_timeout_interruptible(1); } } @@ -2428,15 +2416,16 @@ static int rcu_nocb_kthread(void *arg) list = next; } trace_rcu_batch_end(rdp->rsp->name, c, !!list, 0, 0, 1); - ACCESS_ONCE(rdp->nocb_p_count) -= c; - ACCESS_ONCE(rdp->nocb_p_count_lazy) -= cl; + ACCESS_ONCE(rdp->nocb_p_count) = rdp->nocb_p_count - c; + ACCESS_ONCE(rdp->nocb_p_count_lazy) = + rdp->nocb_p_count_lazy - cl; rdp->n_nocbs_invoked += c; } return 0; } /* Is a deferred wakeup of rcu_nocb_kthread() required? */ -static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp) +static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp) { return ACCESS_ONCE(rdp->nocb_defer_wakeup); } @@ -2444,11 +2433,79 @@ static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp) /* Do a deferred wakeup of rcu_nocb_kthread(). */ static void do_nocb_deferred_wakeup(struct rcu_data *rdp) { + int ndw; + if (!rcu_nocb_need_deferred_wakeup(rdp)) return; - ACCESS_ONCE(rdp->nocb_defer_wakeup) = false; - wake_nocb_leader(rdp, false); - trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWakeEmpty")); + ndw = ACCESS_ONCE(rdp->nocb_defer_wakeup); + ACCESS_ONCE(rdp->nocb_defer_wakeup) = RCU_NOGP_WAKE_NOT; + wake_nocb_leader(rdp, ndw == RCU_NOGP_WAKE_FORCE); + trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWake")); +} + +void __init rcu_init_nohz(void) +{ + int cpu; + bool need_rcu_nocb_mask = true; + struct rcu_state *rsp; + +#ifdef CONFIG_RCU_NOCB_CPU_NONE + need_rcu_nocb_mask = false; +#endif /* #ifndef CONFIG_RCU_NOCB_CPU_NONE */ + +#if defined(CONFIG_NO_HZ_FULL) + if (tick_nohz_full_running && cpumask_weight(tick_nohz_full_mask)) + need_rcu_nocb_mask = true; +#endif /* #if defined(CONFIG_NO_HZ_FULL) */ + + if (!have_rcu_nocb_mask && need_rcu_nocb_mask) { + if (!zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL)) { + pr_info("rcu_nocb_mask allocation failed, callback offloading disabled.\n"); + return; + } + have_rcu_nocb_mask = true; + } + if (!have_rcu_nocb_mask) + return; + +#ifdef CONFIG_RCU_NOCB_CPU_ZERO + pr_info("\tOffload RCU callbacks from CPU 0\n"); + cpumask_set_cpu(0, rcu_nocb_mask); +#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ZERO */ +#ifdef CONFIG_RCU_NOCB_CPU_ALL + pr_info("\tOffload RCU callbacks from all CPUs\n"); + cpumask_copy(rcu_nocb_mask, cpu_possible_mask); +#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ALL */ +#if defined(CONFIG_NO_HZ_FULL) + if (tick_nohz_full_running) + cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask); +#endif /* #if defined(CONFIG_NO_HZ_FULL) */ + + if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) { + pr_info("\tNote: kernel parameter 'rcu_nocbs=' contains nonexistent CPUs.\n"); + cpumask_and(rcu_nocb_mask, cpu_possible_mask, + rcu_nocb_mask); + } + cpulist_scnprintf(nocb_buf, sizeof(nocb_buf), rcu_nocb_mask); + pr_info("\tOffload RCU callbacks from CPUs: %s.\n", nocb_buf); + if (rcu_nocb_poll) + pr_info("\tPoll for callbacks from no-CBs CPUs.\n"); + + for_each_rcu_flavor(rsp) { + for_each_cpu(cpu, rcu_nocb_mask) { + struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); + + /* + * If there are early callbacks, they will need + * to be moved to the nocb lists. + */ + WARN_ON_ONCE(rdp->nxttail[RCU_NEXT_TAIL] != + &rdp->nxtlist && + rdp->nxttail[RCU_NEXT_TAIL] != NULL); + init_nocb_callback_list(rdp); + } + rcu_organize_nocb_kthreads(rsp); + } } /* Initialize per-rcu_data variables for no-CBs CPUs. */ @@ -2459,15 +2516,85 @@ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) rdp->nocb_follower_tail = &rdp->nocb_follower_head; } +/* + * If the specified CPU is a no-CBs CPU that does not already have its + * rcuo kthread for the specified RCU flavor, spawn it. If the CPUs are + * brought online out of order, this can require re-organizing the + * leader-follower relationships. + */ +static void rcu_spawn_one_nocb_kthread(struct rcu_state *rsp, int cpu) +{ + struct rcu_data *rdp; + struct rcu_data *rdp_last; + struct rcu_data *rdp_old_leader; + struct rcu_data *rdp_spawn = per_cpu_ptr(rsp->rda, cpu); + struct task_struct *t; + + /* + * If this isn't a no-CBs CPU or if it already has an rcuo kthread, + * then nothing to do. + */ + if (!rcu_is_nocb_cpu(cpu) || rdp_spawn->nocb_kthread) + return; + + /* If we didn't spawn the leader first, reorganize! */ + rdp_old_leader = rdp_spawn->nocb_leader; + if (rdp_old_leader != rdp_spawn && !rdp_old_leader->nocb_kthread) { + rdp_last = NULL; + rdp = rdp_old_leader; + do { + rdp->nocb_leader = rdp_spawn; + if (rdp_last && rdp != rdp_spawn) + rdp_last->nocb_next_follower = rdp; + rdp_last = rdp; + rdp = rdp->nocb_next_follower; + rdp_last->nocb_next_follower = NULL; + } while (rdp); + rdp_spawn->nocb_next_follower = rdp_old_leader; + } + + /* Spawn the kthread for this CPU and RCU flavor. */ + t = kthread_run(rcu_nocb_kthread, rdp_spawn, + "rcuo%c/%d", rsp->abbr, cpu); + BUG_ON(IS_ERR(t)); + ACCESS_ONCE(rdp_spawn->nocb_kthread) = t; +} + +/* + * If the specified CPU is a no-CBs CPU that does not already have its + * rcuo kthreads, spawn them. + */ +static void rcu_spawn_all_nocb_kthreads(int cpu) +{ + struct rcu_state *rsp; + + if (rcu_scheduler_fully_active) + for_each_rcu_flavor(rsp) + rcu_spawn_one_nocb_kthread(rsp, cpu); +} + +/* + * Once the scheduler is running, spawn rcuo kthreads for all online + * no-CBs CPUs. This assumes that the early_initcall()s happen before + * non-boot CPUs come online -- if this changes, we will need to add + * some mutual exclusion. + */ +static void __init rcu_spawn_nocb_kthreads(void) +{ + int cpu; + + for_each_online_cpu(cpu) + rcu_spawn_all_nocb_kthreads(cpu); +} + /* How many follower CPU IDs per leader? Default of -1 for sqrt(nr_cpu_ids). */ static int rcu_nocb_leader_stride = -1; module_param(rcu_nocb_leader_stride, int, 0444); /* - * Create a kthread for each RCU flavor for each no-CBs CPU. - * Also initialize leader-follower relationships. + * Initialize leader-follower relationships for all no-CBs CPU. */ -static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp) +static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp) { int cpu; int ls = rcu_nocb_leader_stride; @@ -2475,14 +2602,9 @@ static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp) struct rcu_data *rdp; struct rcu_data *rdp_leader = NULL; /* Suppress misguided gcc warn. */ struct rcu_data *rdp_prev = NULL; - struct task_struct *t; - if (rcu_nocb_mask == NULL) + if (!have_rcu_nocb_mask) return; -#if defined(CONFIG_NO_HZ_FULL) && !defined(CONFIG_NO_HZ_FULL_ALL) - if (tick_nohz_full_running) - cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask); -#endif /* #if defined(CONFIG_NO_HZ_FULL) && !defined(CONFIG_NO_HZ_FULL_ALL) */ if (ls == -1) { ls = int_sqrt(nr_cpu_ids); rcu_nocb_leader_stride = ls; @@ -2505,21 +2627,15 @@ static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp) rdp_prev->nocb_next_follower = rdp; } rdp_prev = rdp; - - /* Spawn the kthread for this CPU. */ - t = kthread_run(rcu_nocb_kthread, rdp, - "rcuo%c/%d", rsp->abbr, cpu); - BUG_ON(IS_ERR(t)); - ACCESS_ONCE(rdp->nocb_kthread) = t; } } /* Prevent __call_rcu() from enqueuing callbacks on no-CBs CPUs */ static bool init_nocb_callback_list(struct rcu_data *rdp) { - if (rcu_nocb_mask == NULL || - !cpumask_test_cpu(rdp->cpu, rcu_nocb_mask)) + if (!rcu_is_nocb_cpu(rdp->cpu)) return false; + rdp->nxttail[RCU_NEXT_TAIL] = NULL; return true; } @@ -2541,21 +2657,21 @@ static void rcu_init_one_nocb(struct rcu_node *rnp) static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp, bool lazy, unsigned long flags) { - return 0; + return false; } static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp, struct rcu_data *rdp, unsigned long flags) { - return 0; + return false; } static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) { } -static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp) +static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp) { return false; } @@ -2564,7 +2680,11 @@ static void do_nocb_deferred_wakeup(struct rcu_data *rdp) { } -static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp) +static void rcu_spawn_all_nocb_kthreads(int cpu) +{ +} + +static void __init rcu_spawn_nocb_kthreads(void) { } @@ -2595,16 +2715,6 @@ static void __maybe_unused rcu_kick_nohz_cpu(int cpu) #ifdef CONFIG_NO_HZ_FULL_SYSIDLE -/* - * Define RCU flavor that holds sysidle state. This needs to be the - * most active flavor of RCU. - */ -#ifdef CONFIG_PREEMPT_RCU -static struct rcu_state *rcu_sysidle_state = &rcu_preempt_state; -#else /* #ifdef CONFIG_PREEMPT_RCU */ -static struct rcu_state *rcu_sysidle_state = &rcu_sched_state; -#endif /* #else #ifdef CONFIG_PREEMPT_RCU */ - static int full_sysidle_state; /* Current system-idle state. */ #define RCU_SYSIDLE_NOT 0 /* Some CPU is not idle. */ #define RCU_SYSIDLE_SHORT 1 /* All CPUs idle for brief period. */ @@ -2622,6 +2732,10 @@ static void rcu_sysidle_enter(struct rcu_dynticks *rdtp, int irq) { unsigned long j; + /* If there are no nohz_full= CPUs, no need to track this. */ + if (!tick_nohz_full_enabled()) + return; + /* Adjust nesting, check for fully idle. */ if (irq) { rdtp->dynticks_idle_nesting--; @@ -2687,6 +2801,10 @@ void rcu_sysidle_force_exit(void) */ static void rcu_sysidle_exit(struct rcu_dynticks *rdtp, int irq) { + /* If there are no nohz_full= CPUs, no need to track this. */ + if (!tick_nohz_full_enabled()) + return; + /* Adjust nesting, check for already non-idle. */ if (irq) { rdtp->dynticks_idle_nesting++; @@ -2741,12 +2859,16 @@ static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle, unsigned long j; struct rcu_dynticks *rdtp = rdp->dynticks; + /* If there are no nohz_full= CPUs, don't check system-wide idleness. */ + if (!tick_nohz_full_enabled()) + return; + /* * If some other CPU has already reported non-idle, if this is * not the flavor of RCU that tracks sysidle state, or if this * is an offline or the timekeeping CPU, nothing to do. */ - if (!*isidle || rdp->rsp != rcu_sysidle_state || + if (!*isidle || rdp->rsp != rcu_state_p || cpu_is_offline(rdp->cpu) || rdp->cpu == tick_do_timer_cpu) return; if (rcu_gp_in_progress(rdp->rsp)) @@ -2772,7 +2894,7 @@ static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle, */ static bool is_sysidle_rcu_state(struct rcu_state *rsp) { - return rsp == rcu_sysidle_state; + return rsp == rcu_state_p; } /* @@ -2850,7 +2972,7 @@ static void rcu_sysidle_cancel(void) static void rcu_sysidle_report(struct rcu_state *rsp, int isidle, unsigned long maxj, bool gpkt) { - if (rsp != rcu_sysidle_state) + if (rsp != rcu_state_p) return; /* Wrong flavor, ignore. */ if (gpkt && nr_cpu_ids <= CONFIG_NO_HZ_FULL_SYSIDLE_SMALL) return; /* Running state machine from timekeeping CPU. */ @@ -2867,6 +2989,10 @@ static void rcu_sysidle_report(struct rcu_state *rsp, int isidle, static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle, unsigned long maxj) { + /* If there are no nohz_full= CPUs, no need to track this. */ + if (!tick_nohz_full_enabled()) + return; + rcu_sysidle_report(rsp, isidle, maxj, true); } @@ -2893,7 +3019,8 @@ static void rcu_sysidle_cb(struct rcu_head *rhp) /* * Check to see if the system is fully idle, other than the timekeeping CPU. - * The caller must have disabled interrupts. + * The caller must have disabled interrupts. This is not intended to be + * called unless tick_nohz_full_enabled(). */ bool rcu_sys_is_idle(void) { @@ -2919,13 +3046,12 @@ bool rcu_sys_is_idle(void) /* Scan all the CPUs looking for nonidle CPUs. */ for_each_possible_cpu(cpu) { - rdp = per_cpu_ptr(rcu_sysidle_state->rda, cpu); + rdp = per_cpu_ptr(rcu_state_p->rda, cpu); rcu_sysidle_check_cpu(rdp, &isidle, &maxj); if (!isidle) break; } - rcu_sysidle_report(rcu_sysidle_state, - isidle, maxj, false); + rcu_sysidle_report(rcu_state_p, isidle, maxj, false); oldrss = rss; rss = ACCESS_ONCE(full_sysidle_state); } @@ -2952,7 +3078,7 @@ bool rcu_sys_is_idle(void) * provided by the memory allocator. */ if (nr_cpu_ids > CONFIG_NO_HZ_FULL_SYSIDLE_SMALL && - !rcu_gp_in_progress(rcu_sysidle_state) && + !rcu_gp_in_progress(rcu_state_p) && !rsh.inuse && xchg(&rsh.inuse, 1) == 0) call_rcu(&rsh.rh, rcu_sysidle_cb); return false; @@ -3036,3 +3162,19 @@ static void rcu_bind_gp_kthread(void) housekeeping_affine(current); #endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ } + +/* Record the current task on dyntick-idle entry. */ +static void rcu_dynticks_task_enter(void) +{ +#if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) + ACCESS_ONCE(current->rcu_tasks_idle_cpu) = smp_processor_id(); +#endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */ +} + +/* Record no current task on dyntick-idle exit. */ +static void rcu_dynticks_task_exit(void) +{ +#if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) + ACCESS_ONCE(current->rcu_tasks_idle_cpu) = -1; +#endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */ +} diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 4056d7992a6c..3ef8ba58694e 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -47,6 +47,8 @@ #include <linux/hardirq.h> #include <linux/delay.h> #include <linux/module.h> +#include <linux/kthread.h> +#include <linux/tick.h> #define CREATE_TRACE_POINTS @@ -91,7 +93,7 @@ void __rcu_read_unlock(void) barrier(); /* critical section before exit code. */ t->rcu_read_lock_nesting = INT_MIN; barrier(); /* assign before ->rcu_read_unlock_special load */ - if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special))) + if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special.s))) rcu_read_unlock_special(t); barrier(); /* ->rcu_read_unlock_special load before assign */ t->rcu_read_lock_nesting = 0; @@ -137,6 +139,38 @@ int notrace debug_lockdep_rcu_enabled(void) EXPORT_SYMBOL_GPL(debug_lockdep_rcu_enabled); /** + * rcu_read_lock_held() - might we be in RCU read-side critical section? + * + * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an RCU + * read-side critical section. In absence of CONFIG_DEBUG_LOCK_ALLOC, + * this assumes we are in an RCU read-side critical section unless it can + * prove otherwise. This is useful for debug checks in functions that + * require that they be called within an RCU read-side critical section. + * + * Checks debug_lockdep_rcu_enabled() to prevent false positives during boot + * and while lockdep is disabled. + * + * Note that rcu_read_lock() and the matching rcu_read_unlock() must + * occur in the same context, for example, it is illegal to invoke + * rcu_read_unlock() in process context if the matching rcu_read_lock() + * was invoked from within an irq handler. + * + * Note that rcu_read_lock() is disallowed if the CPU is either idle or + * offline from an RCU perspective, so check for those as well. + */ +int rcu_read_lock_held(void) +{ + if (!debug_lockdep_rcu_enabled()) + return 1; + if (!rcu_is_watching()) + return 0; + if (!rcu_lockdep_current_cpu_online()) + return 0; + return lock_is_held(&rcu_lock_map); +} +EXPORT_SYMBOL_GPL(rcu_read_lock_held); + +/** * rcu_read_lock_bh_held() - might we be in RCU-bh read-side critical section? * * Check for bottom half being disabled, which covers both the @@ -347,3 +381,312 @@ static int __init check_cpu_stall_init(void) early_initcall(check_cpu_stall_init); #endif /* #ifdef CONFIG_RCU_STALL_COMMON */ + +#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. + */ + +/* Global list of callbacks and associated lock. */ +static struct rcu_head *rcu_tasks_cbs_head; +static struct rcu_head **rcu_tasks_cbs_tail = &rcu_tasks_cbs_head; +static DECLARE_WAIT_QUEUE_HEAD(rcu_tasks_cbs_wq); +static DEFINE_RAW_SPINLOCK(rcu_tasks_cbs_lock); + +/* Track exiting tasks in order to allow them to be waited for. */ +DEFINE_SRCU(tasks_rcu_exit_srcu); + +/* Control stall timeouts. Disable with <= 0, otherwise jiffies till stall. */ +static int rcu_task_stall_timeout __read_mostly = HZ * 60 * 10; +module_param(rcu_task_stall_timeout, int, 0644); + +static void rcu_spawn_tasks_kthread(void); + +/* + * Post an RCU-tasks callback. First call must be from process context + * after the scheduler if fully operational. + */ +void call_rcu_tasks(struct rcu_head *rhp, void (*func)(struct rcu_head *rhp)) +{ + unsigned long flags; + bool needwake; + + rhp->next = NULL; + rhp->func = func; + raw_spin_lock_irqsave(&rcu_tasks_cbs_lock, flags); + needwake = !rcu_tasks_cbs_head; + *rcu_tasks_cbs_tail = rhp; + rcu_tasks_cbs_tail = &rhp->next; + raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags); + if (needwake) { + rcu_spawn_tasks_kthread(); + wake_up(&rcu_tasks_cbs_wq); + } +} +EXPORT_SYMBOL_GPL(call_rcu_tasks); + +/** + * synchronize_rcu_tasks - wait until an rcu-tasks grace period has elapsed. + * + * Control will return to the caller some time after a full rcu-tasks + * grace period has elapsed, in other words after all currently + * executing rcu-tasks read-side critical sections have elapsed. These + * read-side critical sections are delimited by calls to schedule(), + * cond_resched_rcu_qs(), idle execution, userspace execution, calls + * to synchronize_rcu_tasks(), and (in theory, anyway) cond_resched(). + * + * This is a very specialized primitive, intended only for a few uses in + * tracing and other situations requiring manipulation of function + * preambles and profiling hooks. The synchronize_rcu_tasks() function + * is not (yet) intended for heavy use from multiple CPUs. + * + * Note that this guarantee implies further memory-ordering guarantees. + * On systems with more than one CPU, when synchronize_rcu_tasks() returns, + * each CPU is guaranteed to have executed a full memory barrier since the + * end of its last RCU-tasks read-side critical section whose beginning + * preceded the call to synchronize_rcu_tasks(). In addition, each CPU + * having an RCU-tasks read-side critical section that extends beyond + * the return from synchronize_rcu_tasks() is guaranteed to have executed + * a full memory barrier after the beginning of synchronize_rcu_tasks() + * and before the beginning of that RCU-tasks 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 synchronize_rcu_tasks(), which returned + * to its caller on CPU B, then both CPU A and CPU B are guaranteed + * to have executed a full memory barrier during the execution of + * synchronize_rcu_tasks() -- even if CPU A and CPU B are the same CPU + * (but again only if the system has more than one CPU). + */ +void synchronize_rcu_tasks(void) +{ + /* Complain if the scheduler has not started. */ + rcu_lockdep_assert(!rcu_scheduler_active, + "synchronize_rcu_tasks called too soon"); + + /* Wait for the grace period. */ + wait_rcu_gp(call_rcu_tasks); +} +EXPORT_SYMBOL_GPL(synchronize_rcu_tasks); + +/** + * rcu_barrier_tasks - Wait for in-flight call_rcu_tasks() callbacks. + * + * Although the current implementation is guaranteed to wait, it is not + * obligated to, for example, if there are no pending callbacks. + */ +void rcu_barrier_tasks(void) +{ + /* There is only one callback queue, so this is easy. ;-) */ + synchronize_rcu_tasks(); +} +EXPORT_SYMBOL_GPL(rcu_barrier_tasks); + +/* See if tasks are still holding out, complain if so. */ +static void check_holdout_task(struct task_struct *t, + bool needreport, bool *firstreport) +{ + int cpu; + + if (!ACCESS_ONCE(t->rcu_tasks_holdout) || + t->rcu_tasks_nvcsw != ACCESS_ONCE(t->nvcsw) || + !ACCESS_ONCE(t->on_rq) || + (IS_ENABLED(CONFIG_NO_HZ_FULL) && + !is_idle_task(t) && t->rcu_tasks_idle_cpu >= 0)) { + ACCESS_ONCE(t->rcu_tasks_holdout) = false; + list_del_init(&t->rcu_tasks_holdout_list); + put_task_struct(t); + return; + } + if (!needreport) + return; + if (*firstreport) { + pr_err("INFO: rcu_tasks detected stalls on tasks:\n"); + *firstreport = false; + } + cpu = task_cpu(t); + pr_alert("%p: %c%c nvcsw: %lu/%lu holdout: %d idle_cpu: %d/%d\n", + t, ".I"[is_idle_task(t)], + "N."[cpu < 0 || !tick_nohz_full_cpu(cpu)], + t->rcu_tasks_nvcsw, t->nvcsw, t->rcu_tasks_holdout, + t->rcu_tasks_idle_cpu, cpu); + sched_show_task(t); +} + +/* RCU-tasks kthread that detects grace periods and invokes callbacks. */ +static int __noreturn rcu_tasks_kthread(void *arg) +{ + unsigned long flags; + struct task_struct *g, *t; + unsigned long lastreport; + struct rcu_head *list; + struct rcu_head *next; + LIST_HEAD(rcu_tasks_holdouts); + + /* FIXME: Add housekeeping affinity. */ + + /* + * Each pass through the following loop makes one check for + * newly arrived callbacks, and, if there are some, waits for + * one RCU-tasks grace period and then invokes the callbacks. + * This loop is terminated by the system going down. ;-) + */ + for (;;) { + + /* Pick up any new callbacks. */ + raw_spin_lock_irqsave(&rcu_tasks_cbs_lock, flags); + list = rcu_tasks_cbs_head; + rcu_tasks_cbs_head = NULL; + rcu_tasks_cbs_tail = &rcu_tasks_cbs_head; + raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags); + + /* If there were none, wait a bit and start over. */ + if (!list) { + wait_event_interruptible(rcu_tasks_cbs_wq, + rcu_tasks_cbs_head); + if (!rcu_tasks_cbs_head) { + WARN_ON(signal_pending(current)); + schedule_timeout_interruptible(HZ/10); + } + continue; + } + + /* + * Wait for all pre-existing t->on_rq and t->nvcsw + * transitions to complete. Invoking synchronize_sched() + * suffices because all these transitions occur with + * interrupts disabled. Without this synchronize_sched(), + * a read-side critical section that started before the + * grace period might be incorrectly seen as having started + * after the grace period. + * + * This synchronize_sched() also dispenses with the + * need for a memory barrier on the first store to + * ->rcu_tasks_holdout, as it forces the store to happen + * after the beginning of the grace period. + */ + synchronize_sched(); + + /* + * There were callbacks, so we need to wait for an + * RCU-tasks grace period. Start off by scanning + * the task list for tasks that are not already + * voluntarily blocked. Mark these tasks and make + * a list of them in rcu_tasks_holdouts. + */ + rcu_read_lock(); + for_each_process_thread(g, t) { + if (t != current && ACCESS_ONCE(t->on_rq) && + !is_idle_task(t)) { + get_task_struct(t); + t->rcu_tasks_nvcsw = ACCESS_ONCE(t->nvcsw); + ACCESS_ONCE(t->rcu_tasks_holdout) = true; + list_add(&t->rcu_tasks_holdout_list, + &rcu_tasks_holdouts); + } + } + rcu_read_unlock(); + + /* + * Wait for tasks that are in the process of exiting. + * This does only part of the job, ensuring that all + * tasks that were previously exiting reach the point + * where they have disabled preemption, allowing the + * later synchronize_sched() to finish the job. + */ + synchronize_srcu(&tasks_rcu_exit_srcu); + + /* + * Each pass through the following loop scans the list + * of holdout tasks, removing any that are no longer + * holdouts. When the list is empty, we are done. + */ + lastreport = jiffies; + while (!list_empty(&rcu_tasks_holdouts)) { + bool firstreport; + bool needreport; + int rtst; + struct task_struct *t1; + + schedule_timeout_interruptible(HZ); + rtst = ACCESS_ONCE(rcu_task_stall_timeout); + needreport = rtst > 0 && + time_after(jiffies, lastreport + rtst); + if (needreport) + lastreport = jiffies; + firstreport = true; + WARN_ON(signal_pending(current)); + list_for_each_entry_safe(t, t1, &rcu_tasks_holdouts, + rcu_tasks_holdout_list) { + check_holdout_task(t, needreport, &firstreport); + cond_resched(); + } + } + + /* + * Because ->on_rq and ->nvcsw are not guaranteed + * to have a full memory barriers prior to them in the + * schedule() path, memory reordering on other CPUs could + * cause their RCU-tasks read-side critical sections to + * extend past the end of the grace period. However, + * because these ->nvcsw updates are carried out with + * interrupts disabled, we can use synchronize_sched() + * to force the needed ordering on all such CPUs. + * + * This synchronize_sched() also confines all + * ->rcu_tasks_holdout accesses to be within the grace + * period, avoiding the need for memory barriers for + * ->rcu_tasks_holdout accesses. + * + * In addition, this synchronize_sched() waits for exiting + * tasks to complete their final preempt_disable() region + * of execution, cleaning up after the synchronize_srcu() + * above. + */ + synchronize_sched(); + + /* Invoke the callbacks. */ + while (list) { + next = list->next; + local_bh_disable(); + list->func(list); + local_bh_enable(); + list = next; + cond_resched(); + } + schedule_timeout_uninterruptible(HZ/10); + } +} + +/* Spawn rcu_tasks_kthread() at first call to call_rcu_tasks(). */ +static void rcu_spawn_tasks_kthread(void) +{ + static DEFINE_MUTEX(rcu_tasks_kthread_mutex); + static struct task_struct *rcu_tasks_kthread_ptr; + struct task_struct *t; + + if (ACCESS_ONCE(rcu_tasks_kthread_ptr)) { + smp_mb(); /* Ensure caller sees full kthread. */ + return; + } + mutex_lock(&rcu_tasks_kthread_mutex); + if (rcu_tasks_kthread_ptr) { + mutex_unlock(&rcu_tasks_kthread_mutex); + return; + } + t = kthread_run(rcu_tasks_kthread, NULL, "rcu_tasks_kthread"); + BUG_ON(IS_ERR(t)); + smp_mb(); /* Ensure others see full kthread. */ + ACCESS_ONCE(rcu_tasks_kthread_ptr) = t; + mutex_unlock(&rcu_tasks_kthread_mutex); +} + +#endif /* #ifdef CONFIG_TASKS_RCU */ diff --git a/kernel/reboot.c b/kernel/reboot.c index a3a9e240fcdb..5925f5ae8dff 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -104,6 +104,87 @@ int unregister_reboot_notifier(struct notifier_block *nb) } EXPORT_SYMBOL(unregister_reboot_notifier); +/* + * Notifier list for kernel code which wants to be called + * to restart the system. + */ +static ATOMIC_NOTIFIER_HEAD(restart_handler_list); + +/** + * register_restart_handler - Register function to be called to reset + * the system + * @nb: Info about handler function to be called + * @nb->priority: Handler priority. Handlers should follow the + * following guidelines for setting priorities. + * 0: Restart handler of last resort, + * with limited restart capabilities + * 128: Default restart handler; use if no other + * restart handler is expected to be available, + * and/or if restart functionality is + * sufficient to restart the entire system + * 255: Highest priority restart handler, will + * preempt all other restart handlers + * + * Registers a function with code to be called to restart the + * system. + * + * Registered functions will be called from machine_restart as last + * step of the restart sequence (if the architecture specific + * machine_restart function calls do_kernel_restart - see below + * for details). + * Registered functions are expected to restart the system immediately. + * If more than one function is registered, the restart handler priority + * selects which function will be called first. + * + * Restart handlers are expected to be registered from non-architecture + * code, typically from drivers. A typical use case would be a system + * where restart functionality is provided through a watchdog. Multiple + * restart handlers may exist; for example, one restart handler might + * restart the entire system, while another only restarts the CPU. + * In such cases, the restart handler which only restarts part of the + * hardware is expected to register with low priority to ensure that + * it only runs if no other means to restart the system is available. + * + * Currently always returns zero, as atomic_notifier_chain_register() + * always returns zero. + */ +int register_restart_handler(struct notifier_block *nb) +{ + return atomic_notifier_chain_register(&restart_handler_list, nb); +} +EXPORT_SYMBOL(register_restart_handler); + +/** + * unregister_restart_handler - Unregister previously registered + * restart handler + * @nb: Hook to be unregistered + * + * Unregisters a previously registered restart handler function. + * + * Returns zero on success, or %-ENOENT on failure. + */ +int unregister_restart_handler(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&restart_handler_list, nb); +} +EXPORT_SYMBOL(unregister_restart_handler); + +/** + * do_kernel_restart - Execute kernel restart handler call chain + * + * Calls functions registered with register_restart_handler. + * + * Expected to be called from machine_restart as last step of the restart + * sequence. + * + * Restarts the system immediately if a restart handler function has been + * registered. Otherwise does nothing. + */ +void do_kernel_restart(char *cmd) +{ + atomic_notifier_call_chain(&restart_handler_list, reboot_mode, cmd); +} + void migrate_to_reboot_cpu(void) { /* The boot cpu is always logical cpu 0 */ diff --git a/kernel/resource.c b/kernel/resource.c index 60c5a3856ab7..46322019ab7d 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -1245,6 +1245,76 @@ int release_mem_region_adjustable(struct resource *parent, /* * Managed region resource */ +static void devm_resource_release(struct device *dev, void *ptr) +{ + struct resource **r = ptr; + + release_resource(*r); +} + +/** + * devm_request_resource() - request and reserve an I/O or memory resource + * @dev: device for which to request the resource + * @root: root of the resource tree from which to request the resource + * @new: descriptor of the resource to request + * + * This is a device-managed version of request_resource(). There is usually + * no need to release resources requested by this function explicitly since + * that will be taken care of when the device is unbound from its driver. + * If for some reason the resource needs to be released explicitly, because + * of ordering issues for example, drivers must call devm_release_resource() + * rather than the regular release_resource(). + * + * When a conflict is detected between any existing resources and the newly + * requested resource, an error message will be printed. + * + * Returns 0 on success or a negative error code on failure. + */ +int devm_request_resource(struct device *dev, struct resource *root, + struct resource *new) +{ + struct resource *conflict, **ptr; + + ptr = devres_alloc(devm_resource_release, sizeof(*ptr), GFP_KERNEL); + if (!ptr) + return -ENOMEM; + + *ptr = new; + + conflict = request_resource_conflict(root, new); + if (conflict) { + dev_err(dev, "resource collision: %pR conflicts with %s %pR\n", + new, conflict->name, conflict); + devres_free(ptr); + return -EBUSY; + } + + devres_add(dev, ptr); + return 0; +} +EXPORT_SYMBOL(devm_request_resource); + +static int devm_resource_match(struct device *dev, void *res, void *data) +{ + struct resource **ptr = res; + + return *ptr == data; +} + +/** + * devm_release_resource() - release a previously requested resource + * @dev: device for which to release the resource + * @new: descriptor of the resource to release + * + * Releases a resource previously requested using devm_request_resource(). + */ +void devm_release_resource(struct device *dev, struct resource *new) +{ + WARN_ON(devres_release(dev, devm_resource_release, devm_resource_match, + new)); +} +EXPORT_SYMBOL(devm_release_resource); + struct region_devres { struct resource *parent; resource_size_t start; diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c index e73efba98301..8a2e230fb86a 100644 --- a/kernel/sched/auto_group.c +++ b/kernel/sched/auto_group.c @@ -148,11 +148,8 @@ autogroup_move_group(struct task_struct *p, struct autogroup *ag) if (!ACCESS_ONCE(sysctl_sched_autogroup_enabled)) goto out; - t = p; - do { + for_each_thread(p, t) sched_move_task(t); - } while_each_thread(p, t); - out: unlock_task_sighand(p, &flags); autogroup_kref_put(prev); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index ec1a286684a5..44999505e1bf 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -90,22 +90,6 @@ #define CREATE_TRACE_POINTS #include <trace/events/sched.h> -#ifdef smp_mb__before_atomic -void __smp_mb__before_atomic(void) -{ - smp_mb__before_atomic(); -} -EXPORT_SYMBOL(__smp_mb__before_atomic); -#endif - -#ifdef smp_mb__after_atomic -void __smp_mb__after_atomic(void) -{ - smp_mb__after_atomic(); -} -EXPORT_SYMBOL(__smp_mb__after_atomic); -#endif - void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period) { unsigned long delta; @@ -333,9 +317,12 @@ static inline struct rq *__task_rq_lock(struct task_struct *p) for (;;) { rq = task_rq(p); raw_spin_lock(&rq->lock); - if (likely(rq == task_rq(p))) + if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) return rq; raw_spin_unlock(&rq->lock); + + while (unlikely(task_on_rq_migrating(p))) + cpu_relax(); } } @@ -352,10 +339,13 @@ static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags) raw_spin_lock_irqsave(&p->pi_lock, *flags); rq = task_rq(p); raw_spin_lock(&rq->lock); - if (likely(rq == task_rq(p))) + if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) return rq; raw_spin_unlock(&rq->lock); raw_spin_unlock_irqrestore(&p->pi_lock, *flags); + + while (unlikely(task_on_rq_migrating(p))) + cpu_relax(); } } @@ -449,7 +439,15 @@ static void __hrtick_start(void *arg) void hrtick_start(struct rq *rq, u64 delay) { struct hrtimer *timer = &rq->hrtick_timer; - ktime_t time = ktime_add_ns(timer->base->get_time(), delay); + ktime_t time; + s64 delta; + + /* + * Don't schedule slices shorter than 10000ns, that just + * doesn't make sense and can cause timer DoS. + */ + delta = max_t(s64, delay, 10000LL); + time = ktime_add_ns(timer->base->get_time(), delta); hrtimer_set_expires(timer, time); @@ -1043,7 +1041,7 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) * A queue event has occurred, and we're going to schedule. In * this case, we can save a useless back to back clock update. */ - if (rq->curr->on_rq && test_tsk_need_resched(rq->curr)) + if (task_on_rq_queued(rq->curr) && test_tsk_need_resched(rq->curr)) rq->skip_clock_update = 1; } @@ -1088,7 +1086,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) static void __migrate_swap_task(struct task_struct *p, int cpu) { - if (p->on_rq) { + if (task_on_rq_queued(p)) { struct rq *src_rq, *dst_rq; src_rq = task_rq(p); @@ -1214,7 +1212,7 @@ static int migration_cpu_stop(void *data); unsigned long wait_task_inactive(struct task_struct *p, long match_state) { unsigned long flags; - int running, on_rq; + int running, queued; unsigned long ncsw; struct rq *rq; @@ -1252,7 +1250,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) rq = task_rq_lock(p, &flags); trace_sched_wait_task(p); running = task_running(rq, p); - on_rq = p->on_rq; + queued = task_on_rq_queued(p); ncsw = 0; if (!match_state || p->state == match_state) ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ @@ -1284,7 +1282,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) * running right now), it's preempted, and we should * yield - it could be a while. */ - if (unlikely(on_rq)) { + if (unlikely(queued)) { ktime_t to = ktime_set(0, NSEC_PER_SEC/HZ); set_current_state(TASK_UNINTERRUPTIBLE); @@ -1478,7 +1476,7 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags) static void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags) { activate_task(rq, p, en_flags); - p->on_rq = 1; + p->on_rq = TASK_ON_RQ_QUEUED; /* if a worker is waking up, notify workqueue */ if (p->flags & PF_WQ_WORKER) @@ -1537,7 +1535,7 @@ static int ttwu_remote(struct task_struct *p, int wake_flags) int ret = 0; rq = __task_rq_lock(p); - if (p->on_rq) { + if (task_on_rq_queued(p)) { /* check_preempt_curr() may use rq clock */ update_rq_clock(rq); ttwu_do_wakeup(rq, p, wake_flags); @@ -1620,6 +1618,25 @@ static void ttwu_queue_remote(struct task_struct *p, int cpu) } } +void wake_up_if_idle(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + + if (!is_idle_task(rq->curr)) + return; + + if (set_nr_if_polling(rq->idle)) { + trace_sched_wake_idle_without_ipi(cpu); + } else { + raw_spin_lock_irqsave(&rq->lock, flags); + if (is_idle_task(rq->curr)) + smp_send_reschedule(cpu); + /* Else cpu is not in idle, do nothing here */ + raw_spin_unlock_irqrestore(&rq->lock, flags); + } +} + bool cpus_share_cache(int this_cpu, int that_cpu) { return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu); @@ -1742,7 +1759,7 @@ static void try_to_wake_up_local(struct task_struct *p) if (!(p->state & TASK_NORMAL)) goto out; - if (!p->on_rq) + if (!task_on_rq_queued(p)) ttwu_activate(rq, p, ENQUEUE_WAKEUP); ttwu_do_wakeup(rq, p, 0); @@ -1776,6 +1793,20 @@ int wake_up_state(struct task_struct *p, unsigned int state) } /* + * This function clears the sched_dl_entity static params. + */ +void __dl_clear_params(struct task_struct *p) +{ + struct sched_dl_entity *dl_se = &p->dl; + + dl_se->dl_runtime = 0; + dl_se->dl_deadline = 0; + dl_se->dl_period = 0; + dl_se->flags = 0; + dl_se->dl_bw = 0; +} + +/* * Perform scheduler related setup for a newly forked process p. * p is forked by current. * @@ -1799,10 +1830,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) RB_CLEAR_NODE(&p->dl.rb_node); hrtimer_init(&p->dl.dl_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - p->dl.dl_runtime = p->dl.runtime = 0; - p->dl.dl_deadline = p->dl.deadline = 0; - p->dl.dl_period = 0; - p->dl.flags = 0; + __dl_clear_params(p); INIT_LIST_HEAD(&p->rt.run_list); @@ -1977,6 +2005,8 @@ unsigned long to_ratio(u64 period, u64 runtime) #ifdef CONFIG_SMP inline struct dl_bw *dl_bw_of(int i) { + rcu_lockdep_assert(rcu_read_lock_sched_held(), + "sched RCU must be held"); return &cpu_rq(i)->rd->dl_bw; } @@ -1985,6 +2015,8 @@ static inline int dl_bw_cpus(int i) struct root_domain *rd = cpu_rq(i)->rd; int cpus = 0; + rcu_lockdep_assert(rcu_read_lock_sched_held(), + "sched RCU must be held"); for_each_cpu_and(i, rd->span, cpu_active_mask) cpus++; @@ -2095,7 +2127,7 @@ void wake_up_new_task(struct task_struct *p) init_task_runnable_average(p); rq = __task_rq_lock(p); activate_task(rq, p, 0); - p->on_rq = 1; + p->on_rq = TASK_ON_RQ_QUEUED; trace_sched_wakeup_new(p, true); check_preempt_curr(rq, p, WF_FORK); #ifdef CONFIG_SMP @@ -2287,10 +2319,6 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev) */ post_schedule(rq); -#ifdef __ARCH_WANT_UNLOCKED_CTXSW - /* In this case, finish_task_switch does not reenable preemption */ - preempt_enable(); -#endif if (current->set_child_tid) put_user(task_pid_vnr(current), current->set_child_tid); } @@ -2333,9 +2361,7 @@ context_switch(struct rq *rq, struct task_struct *prev, * of the scheduler it's an obvious special-case), so we * do an early lockdep release here: */ -#ifndef __ARCH_WANT_UNLOCKED_CTXSW spin_release(&rq->lock.dep_map, 1, _THIS_IP_); -#endif context_tracking_task_switch(prev, next); /* Here we just switch the register state and the stack. */ @@ -2366,6 +2392,18 @@ unsigned long nr_running(void) return sum; } +/* + * Check if only the current task is running on the cpu. + */ +bool single_task_running(void) +{ + if (cpu_rq(smp_processor_id())->nr_running == 1) + return true; + else + return false; +} +EXPORT_SYMBOL(single_task_running); + unsigned long long nr_context_switches(void) { int i; @@ -2451,7 +2489,7 @@ static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq) * project cycles that may never be accounted to this * thread, breaking clock_gettime(). */ - if (task_current(rq, p) && p->on_rq) { + if (task_current(rq, p) && task_on_rq_queued(p)) { update_rq_clock(rq); ns = rq_clock_task(rq) - p->se.exec_start; if ((s64)ns < 0) @@ -2497,7 +2535,7 @@ unsigned long long task_sched_runtime(struct task_struct *p) * If we see ->on_cpu without ->on_rq, the task is leaving, and has * been accounted, so we're correct here as well. */ - if (!p->on_cpu || !p->on_rq) + if (!p->on_cpu || !task_on_rq_queued(p)) return p->se.sum_exec_runtime; #endif @@ -2660,6 +2698,9 @@ static noinline void __schedule_bug(struct task_struct *prev) */ static inline void schedule_debug(struct task_struct *prev) { +#ifdef CONFIG_SCHED_STACK_END_CHECK + BUG_ON(unlikely(task_stack_end_corrupted(prev))); +#endif /* * Test if we are atomic. Since do_exit() needs to call into * schedule() atomically, we ignore that path. Otherwise whine @@ -2801,7 +2842,7 @@ need_resched: switch_count = &prev->nvcsw; } - if (prev->on_rq || rq->skip_clock_update < 0) + if (task_on_rq_queued(prev) || rq->skip_clock_update < 0) update_rq_clock(rq); next = pick_next_task(rq, prev); @@ -2966,7 +3007,7 @@ EXPORT_SYMBOL(default_wake_function); */ void rt_mutex_setprio(struct task_struct *p, int prio) { - int oldprio, on_rq, running, enqueue_flag = 0; + int oldprio, queued, running, enqueue_flag = 0; struct rq *rq; const struct sched_class *prev_class; @@ -2995,12 +3036,12 @@ void rt_mutex_setprio(struct task_struct *p, int prio) trace_sched_pi_setprio(p, prio); oldprio = p->prio; prev_class = p->sched_class; - on_rq = p->on_rq; + queued = task_on_rq_queued(p); running = task_current(rq, p); - if (on_rq) + if (queued) dequeue_task(rq, p, 0); if (running) - p->sched_class->put_prev_task(rq, p); + put_prev_task(rq, p); /* * Boosting condition are: @@ -3037,7 +3078,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio) if (running) p->sched_class->set_curr_task(rq); - if (on_rq) + if (queued) enqueue_task(rq, p, enqueue_flag); check_class_changed(rq, p, prev_class, oldprio); @@ -3048,7 +3089,7 @@ out_unlock: void set_user_nice(struct task_struct *p, long nice) { - int old_prio, delta, on_rq; + int old_prio, delta, queued; unsigned long flags; struct rq *rq; @@ -3069,8 +3110,8 @@ void set_user_nice(struct task_struct *p, long nice) p->static_prio = NICE_TO_PRIO(nice); goto out_unlock; } - on_rq = p->on_rq; - if (on_rq) + queued = task_on_rq_queued(p); + if (queued) dequeue_task(rq, p, 0); p->static_prio = NICE_TO_PRIO(nice); @@ -3079,7 +3120,7 @@ void set_user_nice(struct task_struct *p, long nice) p->prio = effective_prio(p); delta = p->prio - old_prio; - if (on_rq) { + if (queued) { enqueue_task(rq, p, 0); /* * If the task increased its priority or is running and @@ -3351,7 +3392,7 @@ static int __sched_setscheduler(struct task_struct *p, { int newprio = dl_policy(attr->sched_policy) ? MAX_DL_PRIO - 1 : MAX_RT_PRIO - 1 - attr->sched_priority; - int retval, oldprio, oldpolicy = -1, on_rq, running; + int retval, oldprio, oldpolicy = -1, queued, running; int policy = attr->sched_policy; unsigned long flags; const struct sched_class *prev_class; @@ -3548,19 +3589,19 @@ change: return 0; } - on_rq = p->on_rq; + queued = task_on_rq_queued(p); running = task_current(rq, p); - if (on_rq) + if (queued) dequeue_task(rq, p, 0); if (running) - p->sched_class->put_prev_task(rq, p); + put_prev_task(rq, p); prev_class = p->sched_class; __setscheduler(rq, p, attr); if (running) p->sched_class->set_curr_task(rq); - if (on_rq) { + if (queued) { /* * We enqueue to tail when the priority of a task is * increased (user space view). @@ -3984,14 +4025,14 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) rcu_read_lock(); if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) { rcu_read_unlock(); - goto out_unlock; + goto out_free_new_mask; } rcu_read_unlock(); } retval = security_task_setscheduler(p); if (retval) - goto out_unlock; + goto out_free_new_mask; cpuset_cpus_allowed(p, cpus_allowed); @@ -4004,13 +4045,14 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) * root_domain. */ #ifdef CONFIG_SMP - if (task_has_dl_policy(p)) { - const struct cpumask *span = task_rq(p)->rd->span; - - if (dl_bandwidth_enabled() && !cpumask_subset(span, new_mask)) { + if (task_has_dl_policy(p) && dl_bandwidth_enabled()) { + rcu_read_lock(); + if (!cpumask_subset(task_rq(p)->rd->span, new_mask)) { retval = -EBUSY; - goto out_unlock; + rcu_read_unlock(); + goto out_free_new_mask; } + rcu_read_unlock(); } #endif again: @@ -4028,7 +4070,7 @@ again: goto again; } } -out_unlock: +out_free_new_mask: free_cpumask_var(new_mask); out_free_cpus_allowed: free_cpumask_var(cpus_allowed); @@ -4512,7 +4554,7 @@ void show_state_filter(unsigned long state_filter) " task PC stack pid father\n"); #endif rcu_read_lock(); - do_each_thread(g, p) { + for_each_process_thread(g, p) { /* * reset the NMI-timeout, listing all files on a slow * console might take a lot of time: @@ -4520,7 +4562,7 @@ void show_state_filter(unsigned long state_filter) touch_nmi_watchdog(); if (!state_filter || (p->state & state_filter)) sched_show_task(p); - } while_each_thread(g, p); + } touch_all_softlockup_watchdogs(); @@ -4575,7 +4617,7 @@ void init_idle(struct task_struct *idle, int cpu) rcu_read_unlock(); rq->curr = rq->idle = idle; - idle->on_rq = 1; + idle->on_rq = TASK_ON_RQ_QUEUED; #if defined(CONFIG_SMP) idle->on_cpu = 1; #endif @@ -4596,6 +4638,33 @@ void init_idle(struct task_struct *idle, int cpu) } #ifdef CONFIG_SMP +/* + * move_queued_task - move a queued task to new rq. + * + * Returns (locked) new rq. Old rq's lock is released. + */ +static struct rq *move_queued_task(struct task_struct *p, int new_cpu) +{ + struct rq *rq = task_rq(p); + + lockdep_assert_held(&rq->lock); + + dequeue_task(rq, p, 0); + p->on_rq = TASK_ON_RQ_MIGRATING; + set_task_cpu(p, new_cpu); + raw_spin_unlock(&rq->lock); + + rq = cpu_rq(new_cpu); + + raw_spin_lock(&rq->lock); + BUG_ON(task_cpu(p) != new_cpu); + p->on_rq = TASK_ON_RQ_QUEUED; + enqueue_task(rq, p, 0); + check_preempt_curr(rq, p, 0); + + return rq; +} + void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) { if (p->sched_class && p->sched_class->set_cpus_allowed) @@ -4652,14 +4721,15 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) goto out; dest_cpu = cpumask_any_and(cpu_active_mask, new_mask); - if (p->on_rq) { + if (task_running(rq, p) || p->state == TASK_WAKING) { struct migration_arg arg = { p, dest_cpu }; /* Need help from migration thread: drop lock and wait. */ task_rq_unlock(rq, p, &flags); stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); tlb_migrate_finish(p->mm); return 0; - } + } else if (task_on_rq_queued(p)) + rq = move_queued_task(p, dest_cpu); out: task_rq_unlock(rq, p, &flags); @@ -4680,20 +4750,20 @@ EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr); */ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu) { - struct rq *rq_dest, *rq_src; + struct rq *rq; int ret = 0; if (unlikely(!cpu_active(dest_cpu))) return ret; - rq_src = cpu_rq(src_cpu); - rq_dest = cpu_rq(dest_cpu); + rq = cpu_rq(src_cpu); raw_spin_lock(&p->pi_lock); - double_rq_lock(rq_src, rq_dest); + raw_spin_lock(&rq->lock); /* Already moved. */ if (task_cpu(p) != src_cpu) goto done; + /* Affinity changed (again). */ if (!cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p))) goto fail; @@ -4702,16 +4772,12 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu) * If we're not on a rq, the next wake-up will ensure we're * placed properly. */ - if (p->on_rq) { - dequeue_task(rq_src, p, 0); - set_task_cpu(p, dest_cpu); - enqueue_task(rq_dest, p, 0); - check_preempt_curr(rq_dest, p, 0); - } + if (task_on_rq_queued(p)) + rq = move_queued_task(p, dest_cpu); done: ret = 1; fail: - double_rq_unlock(rq_src, rq_dest); + raw_spin_unlock(&rq->lock); raw_spin_unlock(&p->pi_lock); return ret; } @@ -4743,22 +4809,22 @@ void sched_setnuma(struct task_struct *p, int nid) { struct rq *rq; unsigned long flags; - bool on_rq, running; + bool queued, running; rq = task_rq_lock(p, &flags); - on_rq = p->on_rq; + queued = task_on_rq_queued(p); running = task_current(rq, p); - if (on_rq) + if (queued) dequeue_task(rq, p, 0); if (running) - p->sched_class->put_prev_task(rq, p); + put_prev_task(rq, p); p->numa_preferred_nid = nid; if (running) p->sched_class->set_curr_task(rq); - if (on_rq) + if (queued) enqueue_task(rq, p, 0); task_rq_unlock(rq, p, &flags); } @@ -4778,6 +4844,12 @@ static int migration_cpu_stop(void *data) * be on another cpu but it doesn't matter. */ local_irq_disable(); + /* + * We need to explicitly wake pending tasks before running + * __migrate_task() such that we will not miss enforcing cpus_allowed + * during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test. + */ + sched_ttwu_pending(); __migrate_task(arg->task, raw_smp_processor_id(), arg->dest_cpu); local_irq_enable(); return 0; @@ -5188,6 +5260,7 @@ static int sched_cpu_inactive(struct notifier_block *nfb, { unsigned long flags; long cpu = (long)hcpu; + struct dl_bw *dl_b; switch (action & ~CPU_TASKS_FROZEN) { case CPU_DOWN_PREPARE: @@ -5195,15 +5268,19 @@ static int sched_cpu_inactive(struct notifier_block *nfb, /* explicitly allow suspend */ if (!(action & CPU_TASKS_FROZEN)) { - struct dl_bw *dl_b = dl_bw_of(cpu); bool overflow; int cpus; + rcu_read_lock_sched(); + dl_b = dl_bw_of(cpu); + raw_spin_lock_irqsave(&dl_b->lock, flags); cpus = dl_bw_cpus(cpu); overflow = __dl_overflow(dl_b, cpus, 0, 0); raw_spin_unlock_irqrestore(&dl_b->lock, flags); + rcu_read_unlock_sched(); + if (overflow) return notifier_from_errno(-EBUSY); } @@ -5746,7 +5823,7 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu) const struct cpumask *span = sched_domain_span(sd); struct cpumask *covered = sched_domains_tmpmask; struct sd_data *sdd = sd->private; - struct sched_domain *child; + struct sched_domain *sibling; int i; cpumask_clear(covered); @@ -5757,10 +5834,10 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu) if (cpumask_test_cpu(i, covered)) continue; - child = *per_cpu_ptr(sdd->sd, i); + sibling = *per_cpu_ptr(sdd->sd, i); /* See the comment near build_group_mask(). */ - if (!cpumask_test_cpu(i, sched_domain_span(child))) + if (!cpumask_test_cpu(i, sched_domain_span(sibling))) continue; sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(), @@ -5770,10 +5847,9 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu) goto fail; sg_span = sched_group_cpus(sg); - if (child->child) { - child = child->child; - cpumask_copy(sg_span, sched_domain_span(child)); - } else + if (sibling->child) + cpumask_copy(sg_span, sched_domain_span(sibling->child)); + else cpumask_set_cpu(i, sg_span); cpumask_or(covered, covered, sg_span); @@ -7124,13 +7200,13 @@ static void normalize_task(struct rq *rq, struct task_struct *p) .sched_policy = SCHED_NORMAL, }; int old_prio = p->prio; - int on_rq; + int queued; - on_rq = p->on_rq; - if (on_rq) + queued = task_on_rq_queued(p); + if (queued) dequeue_task(rq, p, 0); __setscheduler(rq, p, &attr); - if (on_rq) { + if (queued) { enqueue_task(rq, p, 0); resched_curr(rq); } @@ -7144,12 +7220,12 @@ void normalize_rt_tasks(void) unsigned long flags; struct rq *rq; - read_lock_irqsave(&tasklist_lock, flags); - do_each_thread(g, p) { + read_lock(&tasklist_lock); + for_each_process_thread(g, p) { /* * Only normalize user tasks: */ - if (!p->mm) + if (p->flags & PF_KTHREAD) continue; p->se.exec_start = 0; @@ -7164,21 +7240,16 @@ void normalize_rt_tasks(void) * Renice negative nice level userspace * tasks back to 0: */ - if (task_nice(p) < 0 && p->mm) + if (task_nice(p) < 0) set_user_nice(p, 0); continue; } - raw_spin_lock(&p->pi_lock); - rq = __task_rq_lock(p); - + rq = task_rq_lock(p, &flags); normalize_task(rq, p); - - __task_rq_unlock(rq); - raw_spin_unlock(&p->pi_lock); - } while_each_thread(g, p); - - read_unlock_irqrestore(&tasklist_lock, flags); + task_rq_unlock(rq, p, &flags); + } + read_unlock(&tasklist_lock); } #endif /* CONFIG_MAGIC_SYSRQ */ @@ -7318,19 +7389,19 @@ void sched_offline_group(struct task_group *tg) void sched_move_task(struct task_struct *tsk) { struct task_group *tg; - int on_rq, running; + int queued, running; unsigned long flags; struct rq *rq; rq = task_rq_lock(tsk, &flags); running = task_current(rq, tsk); - on_rq = tsk->on_rq; + queued = task_on_rq_queued(tsk); - if (on_rq) + if (queued) dequeue_task(rq, tsk, 0); if (unlikely(running)) - tsk->sched_class->put_prev_task(rq, tsk); + put_prev_task(rq, tsk); tg = container_of(task_css_check(tsk, cpu_cgrp_id, lockdep_is_held(&tsk->sighand->siglock)), @@ -7340,14 +7411,14 @@ void sched_move_task(struct task_struct *tsk) #ifdef CONFIG_FAIR_GROUP_SCHED if (tsk->sched_class->task_move_group) - tsk->sched_class->task_move_group(tsk, on_rq); + tsk->sched_class->task_move_group(tsk, queued); else #endif set_task_rq(tsk, task_cpu(tsk)); if (unlikely(running)) tsk->sched_class->set_curr_task(rq); - if (on_rq) + if (queued) enqueue_task(rq, tsk, 0); task_rq_unlock(rq, tsk, &flags); @@ -7365,10 +7436,10 @@ static inline int tg_has_rt_tasks(struct task_group *tg) { struct task_struct *g, *p; - do_each_thread(g, p) { - if (rt_task(p) && task_rq(p)->rt.tg == tg) + for_each_process_thread(g, p) { + if (rt_task(p) && task_group(p) == tg) return 1; - } while_each_thread(g, p); + } return 0; } @@ -7577,6 +7648,7 @@ static int sched_dl_global_constraints(void) u64 runtime = global_rt_runtime(); u64 period = global_rt_period(); u64 new_bw = to_ratio(period, runtime); + struct dl_bw *dl_b; int cpu, ret = 0; unsigned long flags; @@ -7590,13 +7662,16 @@ static int sched_dl_global_constraints(void) * solutions is welcome! */ for_each_possible_cpu(cpu) { - struct dl_bw *dl_b = dl_bw_of(cpu); + rcu_read_lock_sched(); + dl_b = dl_bw_of(cpu); raw_spin_lock_irqsave(&dl_b->lock, flags); if (new_bw < dl_b->total_bw) ret = -EBUSY; raw_spin_unlock_irqrestore(&dl_b->lock, flags); + rcu_read_unlock_sched(); + if (ret) break; } @@ -7607,6 +7682,7 @@ static int sched_dl_global_constraints(void) static void sched_dl_do_global(void) { u64 new_bw = -1; + struct dl_bw *dl_b; int cpu; unsigned long flags; @@ -7620,11 +7696,14 @@ static void sched_dl_do_global(void) * FIXME: As above... */ for_each_possible_cpu(cpu) { - struct dl_bw *dl_b = dl_bw_of(cpu); + rcu_read_lock_sched(); + dl_b = dl_bw_of(cpu); raw_spin_lock_irqsave(&dl_b->lock, flags); dl_b->bw = new_bw; raw_spin_unlock_irqrestore(&dl_b->lock, flags); + + rcu_read_unlock_sched(); } } @@ -8005,7 +8084,7 @@ static int tg_cfs_schedulable_down(struct task_group *tg, void *data) struct cfs_bandwidth *parent_b = &tg->parent->cfs_bandwidth; quota = normalize_cfs_quota(tg, d); - parent_quota = parent_b->hierarchal_quota; + parent_quota = parent_b->hierarchical_quota; /* * ensure max(child_quota) <= parent_quota, inherit when no @@ -8016,7 +8095,7 @@ static int tg_cfs_schedulable_down(struct task_group *tg, void *data) else if (parent_quota != RUNTIME_INF && quota > parent_quota) return -EINVAL; } - cfs_b->hierarchal_quota = quota; + cfs_b->hierarchical_quota = quota; return 0; } diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c index bd95963dae80..539ca3ce071b 100644 --- a/kernel/sched/cpudeadline.c +++ b/kernel/sched/cpudeadline.c @@ -107,9 +107,7 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p, int best_cpu = -1; const struct sched_dl_entity *dl_se = &p->dl; - if (later_mask && cpumask_and(later_mask, cp->free_cpus, - &p->cpus_allowed) && cpumask_and(later_mask, - later_mask, cpu_active_mask)) { + if (later_mask && cpumask_and(later_mask, later_mask, cp->free_cpus)) { best_cpu = cpumask_any(later_mask); goto out; } else if (cpumask_test_cpu(cpudl_maximum(cp), &p->cpus_allowed) && diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 72fdf06ef865..8394b1ee600c 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -288,24 +288,29 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times) struct signal_struct *sig = tsk->signal; cputime_t utime, stime; struct task_struct *t; - - times->utime = sig->utime; - times->stime = sig->stime; - times->sum_exec_runtime = sig->sum_sched_runtime; + unsigned int seq, nextseq; + unsigned long flags; rcu_read_lock(); - /* make sure we can trust tsk->thread_group list */ - if (!likely(pid_alive(tsk))) - goto out; - - t = tsk; + /* Attempt a lockless read on the first round. */ + nextseq = 0; do { - task_cputime(t, &utime, &stime); - times->utime += utime; - times->stime += stime; - times->sum_exec_runtime += task_sched_runtime(t); - } while_each_thread(tsk, t); -out: + seq = nextseq; + flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq); + times->utime = sig->utime; + times->stime = sig->stime; + times->sum_exec_runtime = sig->sum_sched_runtime; + + for_each_thread(tsk, t) { + task_cputime(t, &utime, &stime); + times->utime += utime; + times->stime += stime; + times->sum_exec_runtime += task_sched_runtime(t); + } + /* If lockless access failed, take the lock. */ + nextseq = 1; + } while (need_seqretry(&sig->stats_lock, seq)); + done_seqretry_irqrestore(&sig->stats_lock, seq, flags); rcu_read_unlock(); } @@ -550,6 +555,23 @@ drop_precision: } /* + * Atomically advance counter to the new value. Interrupts, vcpu + * scheduling, and scaling inaccuracies can cause cputime_advance + * to be occasionally called with a new value smaller than counter. + * Let's enforce atomicity. + * + * Normally a caller will only go through this loop once, or not + * at all in case a previous caller updated counter the same jiffy. + */ +static void cputime_advance(cputime_t *counter, cputime_t new) +{ + cputime_t old; + + while (new > (old = ACCESS_ONCE(*counter))) + cmpxchg_cputime(counter, old, new); +} + +/* * Adjust tick based cputime random precision against scheduler * runtime accounting. */ @@ -594,13 +616,8 @@ static void cputime_adjust(struct task_cputime *curr, utime = rtime - stime; } - /* - * If the tick based count grows faster than the scheduler one, - * the result of the scaling may go backward. - * Let's enforce monotonicity. - */ - prev->stime = max(prev->stime, stime); - prev->utime = max(prev->utime, utime); + cputime_advance(&prev->stime, stime); + cputime_advance(&prev->utime, utime); out: *ut = prev->utime; @@ -617,9 +634,6 @@ void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) cputime_adjust(&cputime, &p->prev_cputime, ut, st); } -/* - * Must be called with siglock held. - */ void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) { struct task_cputime cputime; diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 255ce138b652..abfaf3d9a29f 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -530,7 +530,7 @@ again: update_rq_clock(rq); dl_se->dl_throttled = 0; dl_se->dl_yielded = 0; - if (p->on_rq) { + if (task_on_rq_queued(p)) { enqueue_task_dl(rq, p, ENQUEUE_REPLENISH); if (task_has_dl_policy(rq->curr)) check_preempt_curr_dl(rq, p, 0); @@ -997,10 +997,7 @@ static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p, #ifdef CONFIG_SCHED_HRTICK static void start_hrtick_dl(struct rq *rq, struct task_struct *p) { - s64 delta = p->dl.dl_runtime - p->dl.runtime; - - if (delta > 10000) - hrtick_start(rq, p->dl.runtime); + hrtick_start(rq, p->dl.runtime); } #endif @@ -1030,7 +1027,7 @@ struct task_struct *pick_next_task_dl(struct rq *rq, struct task_struct *prev) * means a stop task can slip in, in which case we need to * re-start task selection. */ - if (rq->stop && rq->stop->on_rq) + if (rq->stop && task_on_rq_queued(rq->stop)) return RETRY_TASK; } @@ -1124,10 +1121,8 @@ static void set_curr_task_dl(struct rq *rq) static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu) { if (!task_running(rq, p) && - (cpu < 0 || cpumask_test_cpu(cpu, &p->cpus_allowed)) && - (p->nr_cpus_allowed > 1)) + cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) return 1; - return 0; } @@ -1169,6 +1164,13 @@ static int find_later_rq(struct task_struct *task) if (task->nr_cpus_allowed == 1) return -1; + /* + * We have to consider system topology and task affinity + * first, then we can look for a suitable cpu. + */ + cpumask_copy(later_mask, task_rq(task)->rd->span); + cpumask_and(later_mask, later_mask, cpu_active_mask); + cpumask_and(later_mask, later_mask, &task->cpus_allowed); best_cpu = cpudl_find(&task_rq(task)->rd->cpudl, task, later_mask); if (best_cpu == -1) @@ -1257,7 +1259,8 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq) if (unlikely(task_rq(task) != rq || !cpumask_test_cpu(later_rq->cpu, &task->cpus_allowed) || - task_running(rq, task) || !task->on_rq)) { + task_running(rq, task) || + !task_on_rq_queued(task))) { double_unlock_balance(rq, later_rq); later_rq = NULL; break; @@ -1296,7 +1299,7 @@ static struct task_struct *pick_next_pushable_dl_task(struct rq *rq) BUG_ON(task_current(rq, p)); BUG_ON(p->nr_cpus_allowed <= 1); - BUG_ON(!p->on_rq); + BUG_ON(!task_on_rq_queued(p)); BUG_ON(!dl_task(p)); return p; @@ -1443,7 +1446,7 @@ static int pull_dl_task(struct rq *this_rq) dl_time_before(p->dl.deadline, this_rq->dl.earliest_dl.curr))) { WARN_ON(p == src_rq->curr); - WARN_ON(!p->on_rq); + WARN_ON(!task_on_rq_queued(p)); /* * Then we pull iff p has actually an earlier @@ -1569,6 +1572,8 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p) if (hrtimer_active(&p->dl.dl_timer) && !dl_policy(p->policy)) hrtimer_try_to_cancel(&p->dl.dl_timer); + __dl_clear_params(p); + #ifdef CONFIG_SMP /* * Since this might be the only -deadline task on the rq, @@ -1596,7 +1601,7 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p) if (unlikely(p->dl.dl_throttled)) return; - if (p->on_rq && rq->curr != p) { + if (task_on_rq_queued(p) && rq->curr != p) { #ifdef CONFIG_SMP if (rq->dl.overloaded && push_dl_task(rq) && rq != task_rq(p)) /* Only reschedule if pushing failed */ @@ -1614,7 +1619,7 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p) static void prio_changed_dl(struct rq *rq, struct task_struct *p, int oldprio) { - if (p->on_rq || rq->curr == p) { + if (task_on_rq_queued(p) || rq->curr == p) { #ifdef CONFIG_SMP /* * This might be too much, but unfortunately diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 627b3c34b821..ce33780d8f20 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -150,7 +150,6 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu) { struct task_struct *g, *p; - unsigned long flags; SEQ_printf(m, "\nrunnable tasks:\n" @@ -159,16 +158,14 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu) "------------------------------------------------------" "----------------------------------------------------\n"); - read_lock_irqsave(&tasklist_lock, flags); - - do_each_thread(g, p) { + rcu_read_lock(); + for_each_process_thread(g, p) { if (task_cpu(p) != rq_cpu) continue; print_task(m, rq, p); - } while_each_thread(g, p); - - read_unlock_irqrestore(&tasklist_lock, flags); + } + rcu_read_unlock(); } void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) @@ -333,9 +330,7 @@ do { \ print_cfs_stats(m, cpu); print_rt_stats(m, cpu); - rcu_read_lock(); print_rq(m, rq, cpu); - rcu_read_unlock(); spin_unlock_irqrestore(&sched_debug_lock, flags); SEQ_printf(m, "\n"); } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index bfa3c86d0d68..b78280c59b46 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -23,6 +23,7 @@ #include <linux/latencytop.h> #include <linux/sched.h> #include <linux/cpumask.h> +#include <linux/cpuidle.h> #include <linux/slab.h> #include <linux/profile.h> #include <linux/interrupt.h> @@ -665,6 +666,7 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se) } #ifdef CONFIG_SMP +static int select_idle_sibling(struct task_struct *p, int cpu); static unsigned long task_h_load(struct task_struct *p); static inline void __update_task_entity_contrib(struct sched_entity *se); @@ -1038,7 +1040,8 @@ struct numa_stats { */ static void update_numa_stats(struct numa_stats *ns, int nid) { - int cpu, cpus = 0; + int smt, cpu, cpus = 0; + unsigned long capacity; memset(ns, 0, sizeof(*ns)); for_each_cpu(cpu, cpumask_of_node(nid)) { @@ -1062,8 +1065,12 @@ static void update_numa_stats(struct numa_stats *ns, int nid) if (!cpus) return; - ns->task_capacity = - DIV_ROUND_CLOSEST(ns->compute_capacity, SCHED_CAPACITY_SCALE); + /* smt := ceil(cpus / capacity), assumes: 1 < smt_power < 2 */ + smt = DIV_ROUND_UP(SCHED_CAPACITY_SCALE * cpus, ns->compute_capacity); + capacity = cpus / smt; /* cores */ + + ns->task_capacity = min_t(unsigned, capacity, + DIV_ROUND_CLOSEST(ns->compute_capacity, SCHED_CAPACITY_SCALE)); ns->has_free_capacity = (ns->nr_running < ns->task_capacity); } @@ -1206,7 +1213,7 @@ static void task_numa_compare(struct task_numa_env *env, if (!cur) { /* Is there capacity at our destination? */ - if (env->src_stats.has_free_capacity && + if (env->src_stats.nr_running <= env->src_stats.task_capacity && !env->dst_stats.has_free_capacity) goto unlock; @@ -1252,6 +1259,13 @@ balance: if (load_too_imbalanced(src_load, dst_load, env)) goto unlock; + /* + * One idle CPU per node is evaluated for a task numa move. + * Call select_idle_sibling to maybe find a better one. + */ + if (!cur) + env->dst_cpu = select_idle_sibling(env->p, env->dst_cpu); + assign: task_numa_assign(env, cur, imp); unlock: @@ -1775,7 +1789,7 @@ void task_numa_free(struct task_struct *p) list_del(&p->numa_entry); grp->nr_tasks--; spin_unlock_irqrestore(&grp->lock, flags); - rcu_assign_pointer(p->numa_group, NULL); + RCU_INIT_POINTER(p->numa_group, NULL); put_numa_group(grp); } @@ -1804,10 +1818,6 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) if (!p->mm) return; - /* Do not worry about placement if exiting */ - if (p->state == TASK_DEAD) - return; - /* Allocate buffer to track faults on a per-node basis */ if (unlikely(!p->numa_faults_memory)) { int size = sizeof(*p->numa_faults_memory) * @@ -1946,7 +1956,7 @@ void task_numa_work(struct callback_head *work) vma = mm->mmap; } for (; vma; vma = vma->vm_next) { - if (!vma_migratable(vma) || !vma_policy_mof(p, vma)) + if (!vma_migratable(vma) || !vma_policy_mof(vma)) continue; /* @@ -2211,8 +2221,8 @@ static __always_inline u64 decay_load(u64 val, u64 n) /* * As y^PERIOD = 1/2, we can combine - * y^n = 1/2^(n/PERIOD) * k^(n%PERIOD) - * With a look-up table which covers k^n (n<PERIOD) + * 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. */ @@ -2377,6 +2387,9 @@ static inline void __update_cfs_rq_tg_load_contrib(struct cfs_rq *cfs_rq, tg_contrib = cfs_rq->runnable_load_avg + cfs_rq->blocked_load_avg; tg_contrib -= cfs_rq->tg_load_contrib; + if (!tg_contrib) + return; + if (force_update || abs(tg_contrib) > cfs_rq->tg_load_contrib / 8) { atomic_long_add(tg_contrib, &tg->load_avg); cfs_rq->tg_load_contrib += tg_contrib; @@ -3892,14 +3905,6 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p) resched_curr(rq); return; } - - /* - * Don't schedule slices shorter than 10000ns, that just - * doesn't make sense. Rely on vruntime for fairness. - */ - if (rq->curr != p) - delta = max_t(s64, 10000LL, delta); - hrtick_start(rq, delta); } } @@ -4087,7 +4092,7 @@ static unsigned long capacity_of(int cpu) static unsigned long cpu_avg_load_per_task(int cpu) { struct rq *rq = cpu_rq(cpu); - unsigned long nr_running = ACCESS_ONCE(rq->nr_running); + unsigned long nr_running = ACCESS_ONCE(rq->cfs.h_nr_running); unsigned long load_avg = rq->cfs.runnable_load_avg; if (nr_running) @@ -4276,8 +4281,8 @@ static int wake_wide(struct task_struct *p) static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) { s64 this_load, load; + s64 this_eff_load, prev_eff_load; int idx, this_cpu, prev_cpu; - unsigned long tl_per_task; struct task_group *tg; unsigned long weight; int balanced; @@ -4320,47 +4325,30 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) * Otherwise check if either cpus are near enough in load to allow this * task to be woken on this_cpu. */ - if (this_load > 0) { - s64 this_eff_load, prev_eff_load; + this_eff_load = 100; + this_eff_load *= capacity_of(prev_cpu); - this_eff_load = 100; - this_eff_load *= capacity_of(prev_cpu); + prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2; + prev_eff_load *= capacity_of(this_cpu); + + if (this_load > 0) { this_eff_load *= this_load + effective_load(tg, this_cpu, weight, weight); - prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2; - prev_eff_load *= capacity_of(this_cpu); prev_eff_load *= load + effective_load(tg, prev_cpu, 0, weight); + } - balanced = this_eff_load <= prev_eff_load; - } else - balanced = true; - - /* - * If the currently running task will sleep within - * a reasonable amount of time then attract this newly - * woken task: - */ - if (sync && balanced) - return 1; + balanced = this_eff_load <= prev_eff_load; schedstat_inc(p, se.statistics.nr_wakeups_affine_attempts); - tl_per_task = cpu_avg_load_per_task(this_cpu); - if (balanced || - (this_load <= load && - this_load + target_load(prev_cpu, idx) <= tl_per_task)) { - /* - * This domain has SD_WAKE_AFFINE and - * p is cache cold in this domain, and - * there is no bad imbalance. - */ - schedstat_inc(sd, ttwu_move_affine); - schedstat_inc(p, se.statistics.nr_wakeups_affine); + if (!balanced) + return 0; - return 1; - } - return 0; + schedstat_inc(sd, ttwu_move_affine); + schedstat_inc(p, se.statistics.nr_wakeups_affine); + + return 1; } /* @@ -4428,20 +4416,46 @@ static int find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu) { unsigned long load, min_load = ULONG_MAX; - int idlest = -1; + unsigned int min_exit_latency = UINT_MAX; + u64 latest_idle_timestamp = 0; + int least_loaded_cpu = this_cpu; + int shallowest_idle_cpu = -1; int i; /* Traverse only the allowed CPUs */ for_each_cpu_and(i, sched_group_cpus(group), tsk_cpus_allowed(p)) { - load = weighted_cpuload(i); - - if (load < min_load || (load == min_load && i == this_cpu)) { - min_load = load; - idlest = i; + if (idle_cpu(i)) { + struct rq *rq = cpu_rq(i); + struct cpuidle_state *idle = idle_get_state(rq); + if (idle && idle->exit_latency < min_exit_latency) { + /* + * We give priority to a CPU whose idle state + * has the smallest exit latency irrespective + * of any idle timestamp. + */ + min_exit_latency = idle->exit_latency; + latest_idle_timestamp = rq->idle_stamp; + shallowest_idle_cpu = i; + } else if ((!idle || idle->exit_latency == min_exit_latency) && + rq->idle_stamp > latest_idle_timestamp) { + /* + * If equal or no active idle state, then + * the most recently idled CPU might have + * a warmer cache. + */ + latest_idle_timestamp = rq->idle_stamp; + shallowest_idle_cpu = i; + } + } else { + load = weighted_cpuload(i); + if (load < min_load || (load == min_load && i == this_cpu)) { + min_load = load; + least_loaded_cpu = i; + } } } - return idlest; + return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu; } /* @@ -4513,11 +4527,8 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f if (p->nr_cpus_allowed == 1) return prev_cpu; - if (sd_flag & SD_BALANCE_WAKE) { - if (cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) - want_affine = 1; - new_cpu = prev_cpu; - } + if (sd_flag & SD_BALANCE_WAKE) + want_affine = cpumask_test_cpu(cpu, tsk_cpus_allowed(p)); rcu_read_lock(); for_each_domain(cpu, tmp) { @@ -4704,7 +4715,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ return; /* - * This is possible from callers such as move_task(), in which we + * This is possible from callers such as attach_tasks(), in which we * unconditionally check_prempt_curr() after an enqueue (which may have * lead to a throttle). This both saves work and prevents false * next-buddy nomination below. @@ -5112,27 +5123,18 @@ struct lb_env { unsigned int loop_max; enum fbq_type fbq_type; + struct list_head tasks; }; /* - * move_task - move a task from one runqueue to another runqueue. - * Both runqueues must be locked. - */ -static void move_task(struct task_struct *p, struct lb_env *env) -{ - deactivate_task(env->src_rq, p, 0); - set_task_cpu(p, env->dst_cpu); - activate_task(env->dst_rq, p, 0); - check_preempt_curr(env->dst_rq, p, 0); -} - -/* * Is this task likely cache-hot: */ static int task_hot(struct task_struct *p, struct lb_env *env) { s64 delta; + lockdep_assert_held(&env->src_rq->lock); + if (p->sched_class != &fair_sched_class) return 0; @@ -5252,6 +5254,9 @@ static int can_migrate_task(struct task_struct *p, struct lb_env *env) { int tsk_cache_hot = 0; + + lockdep_assert_held(&env->src_rq->lock); + /* * We do not migrate tasks that are: * 1) throttled_lb_pair, or @@ -5310,24 +5315,12 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) if (!tsk_cache_hot) tsk_cache_hot = migrate_degrades_locality(p, env); - if (migrate_improves_locality(p, env)) { -#ifdef CONFIG_SCHEDSTATS + if (migrate_improves_locality(p, env) || !tsk_cache_hot || + env->sd->nr_balance_failed > env->sd->cache_nice_tries) { if (tsk_cache_hot) { schedstat_inc(env->sd, lb_hot_gained[env->idle]); schedstat_inc(p, se.statistics.nr_forced_migrations); } -#endif - return 1; - } - - if (!tsk_cache_hot || - env->sd->nr_balance_failed > env->sd->cache_nice_tries) { - - if (tsk_cache_hot) { - schedstat_inc(env->sd, lb_hot_gained[env->idle]); - schedstat_inc(p, se.statistics.nr_forced_migrations); - } - return 1; } @@ -5336,47 +5329,63 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) } /* - * move_one_task tries to move exactly one task from busiest to this_rq, as + * detach_task() -- detach the task for the migration specified in env + */ +static void detach_task(struct task_struct *p, struct lb_env *env) +{ + lockdep_assert_held(&env->src_rq->lock); + + deactivate_task(env->src_rq, p, 0); + p->on_rq = TASK_ON_RQ_MIGRATING; + set_task_cpu(p, env->dst_cpu); +} + +/* + * detach_one_task() -- tries to dequeue exactly one task from env->src_rq, as * part of active balancing operations within "domain". - * Returns 1 if successful and 0 otherwise. * - * Called with both runqueues locked. + * Returns a task if successful and NULL otherwise. */ -static int move_one_task(struct lb_env *env) +static struct task_struct *detach_one_task(struct lb_env *env) { struct task_struct *p, *n; + lockdep_assert_held(&env->src_rq->lock); + list_for_each_entry_safe(p, n, &env->src_rq->cfs_tasks, se.group_node) { if (!can_migrate_task(p, env)) continue; - move_task(p, env); + detach_task(p, env); + /* - * Right now, this is only the second place move_task() - * is called, so we can safely collect move_task() - * stats here rather than inside move_task(). + * Right now, this is only the second place where + * lb_gained[env->idle] is updated (other is detach_tasks) + * so we can safely collect stats here rather than + * inside detach_tasks(). */ schedstat_inc(env->sd, lb_gained[env->idle]); - return 1; + return p; } - return 0; + return NULL; } static const unsigned int sched_nr_migrate_break = 32; /* - * move_tasks tries to move up to imbalance weighted load from busiest to - * this_rq, as part of a balancing operation within domain "sd". - * Returns 1 if successful and 0 otherwise. + * detach_tasks() -- tries to detach up to imbalance weighted load from + * busiest_rq, as part of a balancing operation within domain "sd". * - * Called with both runqueues locked. + * Returns number of detached tasks if successful and 0 otherwise. */ -static int move_tasks(struct lb_env *env) +static int detach_tasks(struct lb_env *env) { struct list_head *tasks = &env->src_rq->cfs_tasks; struct task_struct *p; unsigned long load; - int pulled = 0; + int detached = 0; + + lockdep_assert_held(&env->src_rq->lock); if (env->imbalance <= 0) return 0; @@ -5407,14 +5416,16 @@ static int move_tasks(struct lb_env *env) if ((load / 2) > env->imbalance) goto next; - move_task(p, env); - pulled++; + detach_task(p, env); + list_add(&p->se.group_node, &env->tasks); + + detached++; env->imbalance -= load; #ifdef CONFIG_PREEMPT /* * NEWIDLE balancing is a source of latency, so preemptible - * kernels will stop after the first task is pulled to minimize + * kernels will stop after the first task is detached to minimize * the critical section. */ if (env->idle == CPU_NEWLY_IDLE) @@ -5434,13 +5445,58 @@ next: } /* - * Right now, this is one of only two places move_task() is called, - * so we can safely collect move_task() stats here rather than - * inside move_task(). + * Right now, this is one of only two places we collect this stat + * so we can safely collect detach_one_task() stats here rather + * than inside detach_one_task(). */ - schedstat_add(env->sd, lb_gained[env->idle], pulled); + schedstat_add(env->sd, lb_gained[env->idle], detached); + + return detached; +} + +/* + * attach_task() -- attach the task detached by detach_task() to its new rq. + */ +static void attach_task(struct rq *rq, struct task_struct *p) +{ + lockdep_assert_held(&rq->lock); + + BUG_ON(task_rq(p) != rq); + p->on_rq = TASK_ON_RQ_QUEUED; + activate_task(rq, p, 0); + check_preempt_curr(rq, p, 0); +} + +/* + * attach_one_task() -- attaches the task returned from detach_one_task() to + * its new rq. + */ +static void attach_one_task(struct rq *rq, struct task_struct *p) +{ + raw_spin_lock(&rq->lock); + attach_task(rq, p); + raw_spin_unlock(&rq->lock); +} + +/* + * attach_tasks() -- attaches all tasks detached by detach_tasks() to their + * new rq. + */ +static void attach_tasks(struct lb_env *env) +{ + struct list_head *tasks = &env->tasks; + struct task_struct *p; + + raw_spin_lock(&env->dst_rq->lock); + + while (!list_empty(tasks)) { + p = list_first_entry(tasks, struct task_struct, se.group_node); + list_del_init(&p->se.group_node); - return pulled; + attach_task(env->dst_rq, p); + } + + raw_spin_unlock(&env->dst_rq->lock); } #ifdef CONFIG_FAIR_GROUP_SCHED @@ -5559,6 +5615,13 @@ static unsigned long task_h_load(struct task_struct *p) #endif /********** Helpers for find_busiest_group ************************/ + +enum group_type { + group_other = 0, + group_imbalanced, + group_overloaded, +}; + /* * sg_lb_stats - stats of a sched_group required for load_balancing */ @@ -5572,7 +5635,7 @@ struct sg_lb_stats { unsigned int group_capacity_factor; unsigned int idle_cpus; unsigned int group_weight; - int group_imb; /* Is there an imbalance in the group ? */ + enum group_type group_type; int group_has_free_capacity; #ifdef CONFIG_NUMA_BALANCING unsigned int nr_numa_running; @@ -5610,6 +5673,8 @@ static inline void init_sd_lb_stats(struct sd_lb_stats *sds) .total_capacity = 0UL, .busiest_stat = { .avg_load = 0UL, + .sum_nr_running = 0, + .group_type = group_other, }, }; } @@ -5652,19 +5717,17 @@ unsigned long __weak arch_scale_freq_capacity(struct sched_domain *sd, int cpu) return default_scale_capacity(sd, cpu); } -static unsigned long default_scale_smt_capacity(struct sched_domain *sd, int cpu) +static unsigned long default_scale_cpu_capacity(struct sched_domain *sd, int cpu) { - unsigned long weight = sd->span_weight; - unsigned long smt_gain = sd->smt_gain; + if ((sd->flags & SD_SHARE_CPUCAPACITY) && (sd->span_weight > 1)) + return sd->smt_gain / sd->span_weight; - smt_gain /= weight; - - return smt_gain; + return SCHED_CAPACITY_SCALE; } -unsigned long __weak arch_scale_smt_capacity(struct sched_domain *sd, int cpu) +unsigned long __weak arch_scale_cpu_capacity(struct sched_domain *sd, int cpu) { - return default_scale_smt_capacity(sd, cpu); + return default_scale_cpu_capacity(sd, cpu); } static unsigned long scale_rt_capacity(int cpu) @@ -5703,18 +5766,15 @@ static unsigned long scale_rt_capacity(int cpu) static void update_cpu_capacity(struct sched_domain *sd, int cpu) { - unsigned long weight = sd->span_weight; unsigned long capacity = SCHED_CAPACITY_SCALE; struct sched_group *sdg = sd->groups; - if ((sd->flags & SD_SHARE_CPUCAPACITY) && weight > 1) { - if (sched_feat(ARCH_CAPACITY)) - capacity *= arch_scale_smt_capacity(sd, cpu); - else - capacity *= default_scale_smt_capacity(sd, cpu); + if (sched_feat(ARCH_CAPACITY)) + capacity *= arch_scale_cpu_capacity(sd, cpu); + else + capacity *= default_scale_cpu_capacity(sd, cpu); - capacity >>= SCHED_CAPACITY_SHIFT; - } + capacity >>= SCHED_CAPACITY_SHIFT; sdg->sgc->capacity_orig = capacity; @@ -5891,6 +5951,18 @@ static inline int sg_capacity_factor(struct lb_env *env, struct sched_group *gro return capacity_factor; } +static enum group_type +group_classify(struct sched_group *group, struct sg_lb_stats *sgs) +{ + if (sgs->sum_nr_running > sgs->group_capacity_factor) + return group_overloaded; + + if (sg_imbalanced(group)) + return group_imbalanced; + + return group_other; +} + /** * update_sg_lb_stats - Update sched_group's statistics for load balancing. * @env: The load balancing environment. @@ -5920,7 +5992,7 @@ static inline void update_sg_lb_stats(struct lb_env *env, load = source_load(i, load_idx); sgs->group_load += load; - sgs->sum_nr_running += rq->nr_running; + sgs->sum_nr_running += rq->cfs.h_nr_running; if (rq->nr_running > 1) *overload = true; @@ -5942,9 +6014,8 @@ static inline void update_sg_lb_stats(struct lb_env *env, sgs->load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running; sgs->group_weight = group->group_weight; - - sgs->group_imb = sg_imbalanced(group); sgs->group_capacity_factor = sg_capacity_factor(env, group); + sgs->group_type = group_classify(group, sgs); if (sgs->group_capacity_factor > sgs->sum_nr_running) sgs->group_has_free_capacity = 1; @@ -5968,13 +6039,19 @@ static bool update_sd_pick_busiest(struct lb_env *env, struct sched_group *sg, struct sg_lb_stats *sgs) { - if (sgs->avg_load <= sds->busiest_stat.avg_load) - return false; + struct sg_lb_stats *busiest = &sds->busiest_stat; - if (sgs->sum_nr_running > sgs->group_capacity_factor) + if (sgs->group_type > busiest->group_type) return true; - if (sgs->group_imb) + if (sgs->group_type < busiest->group_type) + return false; + + if (sgs->avg_load <= busiest->avg_load) + return false; + + /* This is the busiest node in its class. */ + if (!(env->sd->flags & SD_ASYM_PACKING)) return true; /* @@ -5982,8 +6059,7 @@ static bool update_sd_pick_busiest(struct lb_env *env, * numbered CPUs in the group, therefore mark all groups * higher than ourself as busy. */ - if ((env->sd->flags & SD_ASYM_PACKING) && sgs->sum_nr_running && - env->dst_cpu < group_first_cpu(sg)) { + if (sgs->sum_nr_running && env->dst_cpu < group_first_cpu(sg)) { if (!sds->busiest) return true; @@ -6228,7 +6304,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s local = &sds->local_stat; busiest = &sds->busiest_stat; - if (busiest->group_imb) { + if (busiest->group_type == group_imbalanced) { /* * In the group_imb case we cannot rely on group-wide averages * to ensure cpu-load equilibrium, look at wider averages. XXX @@ -6248,12 +6324,11 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s return fix_small_imbalance(env, sds); } - if (!busiest->group_imb) { - /* - * Don't want to pull so many tasks that a group would go idle. - * Except of course for the group_imb case, since then we might - * have to drop below capacity to reach cpu-load equilibrium. - */ + /* + * If there aren't any idle cpus, avoid creating some. + */ + if (busiest->group_type == group_overloaded && + local->group_type == group_overloaded) { load_above_capacity = (busiest->sum_nr_running - busiest->group_capacity_factor); @@ -6337,7 +6412,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env) * work because they assume all things are equal, which typically * isn't true due to cpus_allowed constraints and the like. */ - if (busiest->group_imb) + if (busiest->group_type == group_imbalanced) goto force_balance; /* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */ @@ -6346,7 +6421,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env) goto force_balance; /* - * If the local group is more busy than the selected busiest group + * If the local group is busier than the selected busiest group * don't try and pull any tasks. */ if (local->avg_load >= busiest->avg_load) @@ -6361,13 +6436,14 @@ static struct sched_group *find_busiest_group(struct lb_env *env) if (env->idle == CPU_IDLE) { /* - * This cpu is idle. If the busiest group load doesn't - * have more tasks than the number of available cpu's and - * there is no imbalance between this and busiest group - * wrt to idle cpu's, it is balanced. + * This cpu is idle. If the busiest group is not overloaded + * and there is no imbalance between this and busiest group + * wrt idle cpus, it is balanced. The imbalance becomes + * significant if the diff is greater than 1 otherwise we + * might end up to just move the imbalance on another group */ - if ((local->idle_cpus < busiest->idle_cpus) && - busiest->sum_nr_running <= busiest->group_weight) + if ((busiest->group_type != group_overloaded) && + (local->idle_cpus <= (busiest->idle_cpus + 1))) goto out_balanced; } else { /* @@ -6550,6 +6626,7 @@ static int load_balance(int this_cpu, struct rq *this_rq, .loop_break = sched_nr_migrate_break, .cpus = cpus, .fbq_type = all, + .tasks = LIST_HEAD_INIT(env.tasks), }; /* @@ -6599,23 +6676,30 @@ redo: env.loop_max = min(sysctl_sched_nr_migrate, busiest->nr_running); more_balance: - local_irq_save(flags); - double_rq_lock(env.dst_rq, busiest); + raw_spin_lock_irqsave(&busiest->lock, flags); /* * cur_ld_moved - load moved in current iteration * ld_moved - cumulative load moved across iterations */ - cur_ld_moved = move_tasks(&env); - ld_moved += cur_ld_moved; - double_rq_unlock(env.dst_rq, busiest); - local_irq_restore(flags); + cur_ld_moved = detach_tasks(&env); /* - * some other cpu did the load balance for us. + * We've detached some tasks from busiest_rq. Every + * task is masked "TASK_ON_RQ_MIGRATING", so we can safely + * unlock busiest->lock, and we are able to be sure + * that nobody can manipulate the tasks in parallel. + * See task_rq_lock() family for the details. */ - if (cur_ld_moved && env.dst_cpu != smp_processor_id()) - resched_cpu(env.dst_cpu); + + raw_spin_unlock(&busiest->lock); + + if (cur_ld_moved) { + attach_tasks(&env); + ld_moved += cur_ld_moved; + } + + local_irq_restore(flags); if (env.flags & LBF_NEED_BREAK) { env.flags &= ~LBF_NEED_BREAK; @@ -6665,10 +6749,8 @@ more_balance: if (sd_parent) { int *group_imbalance = &sd_parent->groups->sgc->imbalance; - if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0) { + if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0) *group_imbalance = 1; - } else if (*group_imbalance) - *group_imbalance = 0; } /* All tasks on this runqueue were pinned by CPU affinity */ @@ -6679,7 +6761,7 @@ more_balance: env.loop_break = sched_nr_migrate_break; goto redo; } - goto out_balanced; + goto out_all_pinned; } } @@ -6744,7 +6826,7 @@ more_balance: * If we've begun active balancing, start to back off. This * case may not be covered by the all_pinned logic if there * is only 1 task on the busy runqueue (because we don't call - * move_tasks). + * detach_tasks). */ if (sd->balance_interval < sd->max_interval) sd->balance_interval *= 2; @@ -6753,6 +6835,23 @@ more_balance: goto out; out_balanced: + /* + * We reach balance although we may have faced some affinity + * constraints. Clear the imbalance flag if it was set. + */ + if (sd_parent) { + int *group_imbalance = &sd_parent->groups->sgc->imbalance; + + if (*group_imbalance) + *group_imbalance = 0; + } + +out_all_pinned: + /* + * We reach balance because all tasks are pinned at this level so + * we can't migrate them. Let the imbalance flag set so parent level + * can try to migrate them. + */ schedstat_inc(sd, lb_balanced[idle]); sd->nr_balance_failed = 0; @@ -6914,6 +7013,7 @@ static int active_load_balance_cpu_stop(void *data) int target_cpu = busiest_rq->push_cpu; struct rq *target_rq = cpu_rq(target_cpu); struct sched_domain *sd; + struct task_struct *p = NULL; raw_spin_lock_irq(&busiest_rq->lock); @@ -6933,9 +7033,6 @@ static int active_load_balance_cpu_stop(void *data) */ BUG_ON(busiest_rq == target_rq); - /* move a task from busiest_rq to target_rq */ - double_lock_balance(busiest_rq, target_rq); - /* Search for an sd spanning us and the target CPU. */ rcu_read_lock(); for_each_domain(target_cpu, sd) { @@ -6956,16 +7053,22 @@ static int active_load_balance_cpu_stop(void *data) schedstat_inc(sd, alb_count); - if (move_one_task(&env)) + p = detach_one_task(&env); + if (p) schedstat_inc(sd, alb_pushed); else schedstat_inc(sd, alb_failed); } rcu_read_unlock(); - double_unlock_balance(busiest_rq, target_rq); out_unlock: busiest_rq->active_balance = 0; - raw_spin_unlock_irq(&busiest_rq->lock); + raw_spin_unlock(&busiest_rq->lock); + + if (p) + attach_one_task(target_rq, p); + + local_irq_enable(); + return 0; } @@ -7465,7 +7568,7 @@ static void task_fork_fair(struct task_struct *p) static void prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio) { - if (!p->se.on_rq) + if (!task_on_rq_queued(p)) return; /* @@ -7490,11 +7593,11 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p) * switched back to the fair class the enqueue_entity(.flags=0) will * do the right thing. * - * If it's on_rq, then the dequeue_entity(.flags=0) will already - * have normalized the vruntime, if it's !on_rq, then only when + * If it's queued, then the dequeue_entity(.flags=0) will already + * have normalized the vruntime, if it's !queued, then only when * the task is sleeping will it still have non-normalized vruntime. */ - if (!p->on_rq && p->state != TASK_RUNNING) { + if (!task_on_rq_queued(p) && p->state != TASK_RUNNING) { /* * Fix up our vruntime so that the current sleep doesn't * cause 'unlimited' sleep bonus. @@ -7521,15 +7624,15 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p) */ static void switched_to_fair(struct rq *rq, struct task_struct *p) { - struct sched_entity *se = &p->se; #ifdef CONFIG_FAIR_GROUP_SCHED + struct sched_entity *se = &p->se; /* * Since the real-depth could have been changed (only FAIR * class maintain depth value), reset depth properly. */ se->depth = se->parent ? se->parent->depth + 1 : 0; #endif - if (!se->on_rq) + if (!task_on_rq_queued(p)) return; /* @@ -7575,7 +7678,7 @@ void init_cfs_rq(struct cfs_rq *cfs_rq) } #ifdef CONFIG_FAIR_GROUP_SCHED -static void task_move_group_fair(struct task_struct *p, int on_rq) +static void task_move_group_fair(struct task_struct *p, int queued) { struct sched_entity *se = &p->se; struct cfs_rq *cfs_rq; @@ -7594,7 +7697,7 @@ static void task_move_group_fair(struct task_struct *p, int on_rq) * fair sleeper stuff for the first placement, but who cares. */ /* - * When !on_rq, vruntime of the task has usually NOT been normalized. + * When !queued, vruntime of the task has usually NOT been normalized. * But there are some cases where it has already been normalized: * * - Moving a forked child which is waiting for being woken up by @@ -7605,14 +7708,14 @@ static void task_move_group_fair(struct task_struct *p, int on_rq) * To prevent boost or penalty in the new cfs_rq caused by delta * min_vruntime between the two cfs_rqs, we skip vruntime adjustment. */ - if (!on_rq && (!se->sum_exec_runtime || p->state == TASK_WAKING)) - on_rq = 1; + if (!queued && (!se->sum_exec_runtime || p->state == TASK_WAKING)) + queued = 1; - if (!on_rq) + if (!queued) se->vruntime -= cfs_rq_of(se)->min_vruntime; set_task_rq(p, task_cpu(p)); se->depth = se->parent ? se->parent->depth + 1 : 0; - if (!on_rq) { + if (!queued) { cfs_rq = cfs_rq_of(se); se->vruntime += cfs_rq->min_vruntime; #ifdef CONFIG_SMP diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 11e7bc434f43..c47fce75e666 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -147,6 +147,9 @@ use_default: clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu)) goto use_default; + /* Take note of the planned idle state. */ + idle_set_state(this_rq(), &drv->states[next_state]); + /* * Enter the idle state previously returned by the governor decision. * This function will block until an interrupt occurs and will take @@ -154,6 +157,9 @@ use_default: */ entered_state = cpuidle_enter(drv, dev, next_state); + /* The cpu is no longer idle or about to enter idle. */ + idle_set_state(this_rq(), NULL); + if (broadcast) clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu); diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 5f6edca4fafd..87ea5bf1b87f 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1448,7 +1448,7 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev) * means a dl or stop task can slip in, in which case we need * to re-start task selection. */ - if (unlikely((rq->stop && rq->stop->on_rq) || + if (unlikely((rq->stop && task_on_rq_queued(rq->stop)) || rq->dl.dl_nr_running)) return RETRY_TASK; } @@ -1468,8 +1468,7 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev) p = _pick_next_task_rt(rq); /* The running task is never eligible for pushing */ - if (p) - dequeue_pushable_task(rq, p); + dequeue_pushable_task(rq, p); set_post_schedule(rq); @@ -1624,7 +1623,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) !cpumask_test_cpu(lowest_rq->cpu, tsk_cpus_allowed(task)) || task_running(rq, task) || - !task->on_rq)) { + !task_on_rq_queued(task))) { double_unlock_balance(rq, lowest_rq); lowest_rq = NULL; @@ -1658,7 +1657,7 @@ static struct task_struct *pick_next_pushable_task(struct rq *rq) BUG_ON(task_current(rq, p)); BUG_ON(p->nr_cpus_allowed <= 1); - BUG_ON(!p->on_rq); + BUG_ON(!task_on_rq_queued(p)); BUG_ON(!rt_task(p)); return p; @@ -1809,7 +1808,7 @@ static int pull_rt_task(struct rq *this_rq) */ if (p && (p->prio < this_rq->rt.highest_prio.curr)) { WARN_ON(p == src_rq->curr); - WARN_ON(!p->on_rq); + WARN_ON(!task_on_rq_queued(p)); /* * There's a chance that p is higher in priority @@ -1870,7 +1869,7 @@ static void set_cpus_allowed_rt(struct task_struct *p, BUG_ON(!rt_task(p)); - if (!p->on_rq) + if (!task_on_rq_queued(p)) return; weight = cpumask_weight(new_mask); @@ -1936,7 +1935,7 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p) * we may need to handle the pulling of RT tasks * now. */ - if (!p->on_rq || rq->rt.rt_nr_running) + if (!task_on_rq_queued(p) || rq->rt.rt_nr_running) return; if (pull_rt_task(rq)) @@ -1970,7 +1969,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p) * If that current running task is also an RT task * then see if we can move to another run queue. */ - if (p->on_rq && rq->curr != p) { + if (task_on_rq_queued(p) && rq->curr != p) { #ifdef CONFIG_SMP if (p->nr_cpus_allowed > 1 && rq->rt.overloaded && /* Don't resched if we changed runqueues */ @@ -1989,7 +1988,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p) static void prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio) { - if (!p->on_rq) + if (!task_on_rq_queued(p)) return; if (rq->curr == p) { @@ -2073,7 +2072,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued) for_each_sched_rt_entity(rt_se) { if (rt_se->run_list.prev != rt_se->run_list.next) { requeue_task_rt(rq, p, 0); - set_tsk_need_resched(p); + resched_curr(rq); return; } } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 579712f4e9d5..6130251de280 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -14,6 +14,11 @@ #include "cpuacct.h" struct rq; +struct cpuidle_state; + +/* task_struct::on_rq states: */ +#define TASK_ON_RQ_QUEUED 1 +#define TASK_ON_RQ_MIGRATING 2 extern __read_mostly int scheduler_running; @@ -126,6 +131,9 @@ struct rt_bandwidth { u64 rt_runtime; struct hrtimer rt_period_timer; }; + +void __dl_clear_params(struct task_struct *p); + /* * To keep the bandwidth of -deadline tasks and groups under control * we need some place where: @@ -184,7 +192,7 @@ struct cfs_bandwidth { raw_spinlock_t lock; ktime_t period; u64 quota, runtime; - s64 hierarchal_quota; + s64 hierarchical_quota; u64 runtime_expires; int idle, timer_active; @@ -636,6 +644,11 @@ struct rq { #ifdef CONFIG_SMP struct llist_head wake_list; #endif + +#ifdef CONFIG_CPU_IDLE + /* Must be inspected within a rcu lock section */ + struct cpuidle_state *idle_state; +#endif }; static inline int cpu_of(struct rq *rq) @@ -647,7 +660,7 @@ static inline int cpu_of(struct rq *rq) #endif } -DECLARE_PER_CPU(struct rq, runqueues); +DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); #define cpu_rq(cpu) (&per_cpu(runqueues, (cpu))) #define this_rq() (&__get_cpu_var(runqueues)) @@ -942,6 +955,15 @@ static inline int task_running(struct rq *rq, struct task_struct *p) #endif } +static inline int task_on_rq_queued(struct task_struct *p) +{ + return p->on_rq == TASK_ON_RQ_QUEUED; +} + +static inline int task_on_rq_migrating(struct task_struct *p) +{ + return p->on_rq == TASK_ON_RQ_MIGRATING; +} #ifndef prepare_arch_switch # define prepare_arch_switch(next) do { } while (0) @@ -953,7 +975,6 @@ static inline int task_running(struct rq *rq, struct task_struct *p) # define finish_arch_post_lock_switch() do { } while (0) #endif -#ifndef __ARCH_WANT_UNLOCKED_CTXSW static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) { #ifdef CONFIG_SMP @@ -991,35 +1012,6 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) raw_spin_unlock_irq(&rq->lock); } -#else /* __ARCH_WANT_UNLOCKED_CTXSW */ -static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) -{ -#ifdef CONFIG_SMP - /* - * We can optimise this out completely for !SMP, because the - * SMP rebalancing from interrupt is the only thing that cares - * here. - */ - next->on_cpu = 1; -#endif - raw_spin_unlock(&rq->lock); -} - -static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) -{ -#ifdef CONFIG_SMP - /* - * After ->on_cpu is cleared, the task can be moved to a different CPU. - * We must ensure this doesn't happen until the switch is completely - * finished. - */ - smp_wmb(); - prev->on_cpu = 0; -#endif - local_irq_enable(); -} -#endif /* __ARCH_WANT_UNLOCKED_CTXSW */ - /* * wake flags */ @@ -1180,6 +1172,30 @@ static inline void idle_exit_fair(struct rq *rq) { } #endif +#ifdef CONFIG_CPU_IDLE +static inline void idle_set_state(struct rq *rq, + struct cpuidle_state *idle_state) +{ + rq->idle_state = idle_state; +} + +static inline struct cpuidle_state *idle_get_state(struct rq *rq) +{ + WARN_ON(!rcu_read_lock_held()); + return rq->idle_state; +} +#else +static inline void idle_set_state(struct rq *rq, + struct cpuidle_state *idle_state) +{ +} + +static inline struct cpuidle_state *idle_get_state(struct rq *rq) +{ + return NULL; +} +#endif + extern void sysrq_sched_debug_show(void); extern void sched_init_granularity(void); extern void update_max_interval(void); diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c index bfe0edadbfbb..67426e529f59 100644 --- a/kernel/sched/stop_task.c +++ b/kernel/sched/stop_task.c @@ -28,7 +28,7 @@ pick_next_task_stop(struct rq *rq, struct task_struct *prev) { struct task_struct *stop = rq->stop; - if (!stop || !stop->on_rq) + if (!stop || !task_on_rq_queued(stop)) return NULL; put_prev_task(rq, prev); diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 15cab1a4f84e..5a62915f47a8 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -343,6 +343,18 @@ int __sched out_of_line_wait_on_bit(void *word, int bit, } EXPORT_SYMBOL(out_of_line_wait_on_bit); +int __sched out_of_line_wait_on_bit_timeout( + void *word, int bit, wait_bit_action_f *action, + unsigned mode, unsigned long timeout) +{ + wait_queue_head_t *wq = bit_waitqueue(word, bit); + DEFINE_WAIT_BIT(wait, word, bit); + + wait.key.timeout = jiffies + timeout; + return __wait_on_bit(wq, &wait, action, mode); +} +EXPORT_SYMBOL_GPL(out_of_line_wait_on_bit_timeout); + int __sched __wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q, wait_bit_action_f *action, unsigned mode) @@ -520,3 +532,27 @@ __sched int bit_wait_io(struct wait_bit_key *word) return 0; } EXPORT_SYMBOL(bit_wait_io); + +__sched int bit_wait_timeout(struct wait_bit_key *word) +{ + unsigned long now = ACCESS_ONCE(jiffies); + if (signal_pending_state(current->state, current)) + return 1; + if (time_after_eq(now, word->timeout)) + return -EAGAIN; + schedule_timeout(word->timeout - now); + return 0; +} +EXPORT_SYMBOL_GPL(bit_wait_timeout); + +__sched int bit_wait_io_timeout(struct wait_bit_key *word) +{ + unsigned long now = ACCESS_ONCE(jiffies); + if (signal_pending_state(current->state, current)) + return 1; + if (time_after_eq(now, word->timeout)) + return -EAGAIN; + io_schedule_timeout(word->timeout - now); + return 0; +} +EXPORT_SYMBOL_GPL(bit_wait_io_timeout); diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 44eb005c6695..4ef9687ac115 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -21,10 +21,11 @@ #include <linux/slab.h> #include <linux/syscalls.h> -/* #define SECCOMP_DEBUG 1 */ +#ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER +#include <asm/syscall.h> +#endif #ifdef CONFIG_SECCOMP_FILTER -#include <asm/syscall.h> #include <linux/filter.h> #include <linux/pid.h> #include <linux/ptrace.h> @@ -172,10 +173,10 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen) * * Returns valid seccomp BPF response codes. */ -static u32 seccomp_run_filters(int syscall) +static u32 seccomp_run_filters(struct seccomp_data *sd) { struct seccomp_filter *f = ACCESS_ONCE(current->seccomp.filter); - struct seccomp_data sd; + struct seccomp_data sd_local; u32 ret = SECCOMP_RET_ALLOW; /* Ensure unexpected behavior doesn't result in failing open. */ @@ -185,14 +186,17 @@ static u32 seccomp_run_filters(int syscall) /* Make sure cross-thread synced filter points somewhere sane. */ smp_read_barrier_depends(); - populate_seccomp_data(&sd); + if (!sd) { + populate_seccomp_data(&sd_local); + sd = &sd_local; + } /* * All filters in the list are evaluated and the lowest BPF return * value always takes priority (ignoring the DATA). */ for (; f; f = f->prev) { - u32 cur_ret = BPF_PROG_RUN(f->prog, (void *)&sd); + u32 cur_ret = BPF_PROG_RUN(f->prog, (void *)sd); if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION)) ret = cur_ret; @@ -395,16 +399,15 @@ static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog) if (!filter) goto free_prog; - filter->prog = kzalloc(bpf_prog_size(new_len), - GFP_KERNEL|__GFP_NOWARN); + filter->prog = bpf_prog_alloc(bpf_prog_size(new_len), __GFP_NOWARN); if (!filter->prog) goto free_filter; ret = bpf_convert_filter(fp, fprog->len, filter->prog->insnsi, &new_len); if (ret) goto free_filter_prog; - kfree(fp); + kfree(fp); atomic_set(&filter->usage, 1); filter->prog->len = new_len; @@ -413,7 +416,7 @@ static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog) return filter; free_filter_prog: - kfree(filter->prog); + __bpf_prog_free(filter->prog); free_filter: kfree(filter); free_prog: @@ -564,11 +567,55 @@ static int mode1_syscalls_32[] = { }; #endif -int __secure_computing(int this_syscall) +static void __secure_computing_strict(int this_syscall) +{ + int *syscall_whitelist = mode1_syscalls; +#ifdef CONFIG_COMPAT + if (is_compat_task()) + syscall_whitelist = mode1_syscalls_32; +#endif + do { + if (*syscall_whitelist == this_syscall) + return; + } while (*++syscall_whitelist); + +#ifdef SECCOMP_DEBUG + dump_stack(); +#endif + audit_seccomp(this_syscall, SIGKILL, SECCOMP_RET_KILL); + do_exit(SIGKILL); +} + +#ifndef CONFIG_HAVE_ARCH_SECCOMP_FILTER +void secure_computing_strict(int this_syscall) +{ + int mode = current->seccomp.mode; + + if (mode == 0) + return; + else if (mode == SECCOMP_MODE_STRICT) + __secure_computing_strict(this_syscall); + else + BUG(); +} +#else +int __secure_computing(void) +{ + u32 phase1_result = seccomp_phase1(NULL); + + if (likely(phase1_result == SECCOMP_PHASE1_OK)) + return 0; + else if (likely(phase1_result == SECCOMP_PHASE1_SKIP)) + return -1; + else + return seccomp_phase2(phase1_result); +} + +#ifdef CONFIG_SECCOMP_FILTER +static u32 __seccomp_phase1_filter(int this_syscall, struct seccomp_data *sd) { - int exit_sig = 0; - int *syscall; - u32 ret; + u32 filter_ret, action; + int data; /* * Make sure that any changes to mode from another thread have @@ -576,85 +623,127 @@ int __secure_computing(int this_syscall) */ rmb(); - switch (current->seccomp.mode) { - case SECCOMP_MODE_STRICT: - syscall = mode1_syscalls; -#ifdef CONFIG_COMPAT - if (is_compat_task()) - syscall = mode1_syscalls_32; + filter_ret = seccomp_run_filters(sd); + data = filter_ret & SECCOMP_RET_DATA; + action = filter_ret & SECCOMP_RET_ACTION; + + switch (action) { + case SECCOMP_RET_ERRNO: + /* Set the low-order 16-bits as a errno. */ + syscall_set_return_value(current, task_pt_regs(current), + -data, 0); + goto skip; + + case SECCOMP_RET_TRAP: + /* Show the handler the original registers. */ + syscall_rollback(current, task_pt_regs(current)); + /* Let the filter pass back 16 bits of data. */ + seccomp_send_sigsys(this_syscall, data); + goto skip; + + case SECCOMP_RET_TRACE: + return filter_ret; /* Save the rest for phase 2. */ + + case SECCOMP_RET_ALLOW: + return SECCOMP_PHASE1_OK; + + case SECCOMP_RET_KILL: + default: + audit_seccomp(this_syscall, SIGSYS, action); + do_exit(SIGSYS); + } + + unreachable(); + +skip: + audit_seccomp(this_syscall, 0, action); + return SECCOMP_PHASE1_SKIP; +} #endif - do { - if (*syscall == this_syscall) - return 0; - } while (*++syscall); - exit_sig = SIGKILL; - ret = SECCOMP_RET_KILL; - break; + +/** + * seccomp_phase1() - run fast path seccomp checks on the current syscall + * @arg sd: The seccomp_data or NULL + * + * This only reads pt_regs via the syscall_xyz helpers. The only change + * it will make to pt_regs is via syscall_set_return_value, and it will + * only do that if it returns SECCOMP_PHASE1_SKIP. + * + * If sd is provided, it will not read pt_regs at all. + * + * It may also call do_exit or force a signal; these actions must be + * safe. + * + * If it returns SECCOMP_PHASE1_OK, the syscall passes checks and should + * be processed normally. + * + * If it returns SECCOMP_PHASE1_SKIP, then the syscall should not be + * invoked. In this case, seccomp_phase1 will have set the return value + * using syscall_set_return_value. + * + * If it returns anything else, then the return value should be passed + * to seccomp_phase2 from a context in which ptrace hooks are safe. + */ +u32 seccomp_phase1(struct seccomp_data *sd) +{ + int mode = current->seccomp.mode; + int this_syscall = sd ? sd->nr : + syscall_get_nr(current, task_pt_regs(current)); + + switch (mode) { + case SECCOMP_MODE_STRICT: + __secure_computing_strict(this_syscall); /* may call do_exit */ + return SECCOMP_PHASE1_OK; #ifdef CONFIG_SECCOMP_FILTER - case SECCOMP_MODE_FILTER: { - int data; - struct pt_regs *regs = task_pt_regs(current); - ret = seccomp_run_filters(this_syscall); - data = ret & SECCOMP_RET_DATA; - ret &= SECCOMP_RET_ACTION; - switch (ret) { - case SECCOMP_RET_ERRNO: - /* Set the low-order 16-bits as a errno. */ - syscall_set_return_value(current, regs, - -data, 0); - goto skip; - case SECCOMP_RET_TRAP: - /* Show the handler the original registers. */ - syscall_rollback(current, regs); - /* Let the filter pass back 16 bits of data. */ - seccomp_send_sigsys(this_syscall, data); - goto skip; - case SECCOMP_RET_TRACE: - /* Skip these calls if there is no tracer. */ - if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) { - syscall_set_return_value(current, regs, - -ENOSYS, 0); - goto skip; - } - /* Allow the BPF to provide the event message */ - ptrace_event(PTRACE_EVENT_SECCOMP, data); - /* - * The delivery of a fatal signal during event - * notification may silently skip tracer notification. - * Terminating the task now avoids executing a system - * call that may not be intended. - */ - if (fatal_signal_pending(current)) - break; - if (syscall_get_nr(current, regs) < 0) - goto skip; /* Explicit request to skip. */ - - return 0; - case SECCOMP_RET_ALLOW: - return 0; - case SECCOMP_RET_KILL: - default: - break; - } - exit_sig = SIGSYS; - break; - } + case SECCOMP_MODE_FILTER: + return __seccomp_phase1_filter(this_syscall, sd); #endif default: BUG(); } +} -#ifdef SECCOMP_DEBUG - dump_stack(); -#endif - audit_seccomp(this_syscall, exit_sig, ret); - do_exit(exit_sig); -#ifdef CONFIG_SECCOMP_FILTER -skip: - audit_seccomp(this_syscall, exit_sig, ret); -#endif - return -1; +/** + * seccomp_phase2() - finish slow path seccomp work for the current syscall + * @phase1_result: The return value from seccomp_phase1() + * + * This must be called from a context in which ptrace hooks can be used. + * + * Returns 0 if the syscall should be processed or -1 to skip the syscall. + */ +int seccomp_phase2(u32 phase1_result) +{ + struct pt_regs *regs = task_pt_regs(current); + u32 action = phase1_result & SECCOMP_RET_ACTION; + int data = phase1_result & SECCOMP_RET_DATA; + + BUG_ON(action != SECCOMP_RET_TRACE); + + audit_seccomp(syscall_get_nr(current, regs), 0, action); + + /* Skip these calls if there is no tracer. */ + if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) { + syscall_set_return_value(current, regs, + -ENOSYS, 0); + return -1; + } + + /* Allow the BPF to provide the event message */ + ptrace_event(PTRACE_EVENT_SECCOMP, data); + /* + * The delivery of a fatal signal during event + * notification may silently skip tracer notification. + * Terminating the task now avoids executing a system + * call that may not be intended. + */ + if (fatal_signal_pending(current)) + do_exit(SIGSYS); + if (syscall_get_nr(current, regs) < 0) + return -1; /* Explicit request to skip. */ + + return 0; } +#endif /* CONFIG_HAVE_ARCH_SECCOMP_FILTER */ long prctl_get_seccomp(void) { diff --git a/kernel/smp.c b/kernel/smp.c index aff8aa14f547..9e0d0b289118 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -13,6 +13,7 @@ #include <linux/gfp.h> #include <linux/smp.h> #include <linux/cpu.h> +#include <linux/sched.h> #include "smpboot.h" @@ -699,3 +700,24 @@ void kick_all_cpus_sync(void) smp_call_function(do_nothing, NULL, 1); } EXPORT_SYMBOL_GPL(kick_all_cpus_sync); + +/** + * wake_up_all_idle_cpus - break all cpus out of idle + * wake_up_all_idle_cpus try to break all cpus which is in idle state even + * including idle polling cpus, for non-idle cpus, we will do nothing + * for them. + */ +void wake_up_all_idle_cpus(void) +{ + int cpu; + + preempt_disable(); + for_each_online_cpu(cpu) { + if (cpu == smp_processor_id()) + continue; + + wake_up_if_idle(cpu); + } + preempt_enable(); +} +EXPORT_SYMBOL_GPL(wake_up_all_idle_cpus); diff --git a/kernel/softirq.c b/kernel/softirq.c index 5918d227730f..348ec763b104 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -278,7 +278,7 @@ restart: pending >>= softirq_bit; } - rcu_bh_qs(smp_processor_id()); + rcu_bh_qs(); local_irq_disable(); pending = local_softirq_pending(); diff --git a/kernel/sys.c b/kernel/sys.c index ce8129192a26..1eaa2f0b0246 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -62,28 +62,28 @@ #include <asm/unistd.h> #ifndef SET_UNALIGN_CTL -# define SET_UNALIGN_CTL(a,b) (-EINVAL) +# define SET_UNALIGN_CTL(a, b) (-EINVAL) #endif #ifndef GET_UNALIGN_CTL -# define GET_UNALIGN_CTL(a,b) (-EINVAL) +# define GET_UNALIGN_CTL(a, b) (-EINVAL) #endif #ifndef SET_FPEMU_CTL -# define SET_FPEMU_CTL(a,b) (-EINVAL) +# define SET_FPEMU_CTL(a, b) (-EINVAL) #endif #ifndef GET_FPEMU_CTL -# define GET_FPEMU_CTL(a,b) (-EINVAL) +# define GET_FPEMU_CTL(a, b) (-EINVAL) #endif #ifndef SET_FPEXC_CTL -# define SET_FPEXC_CTL(a,b) (-EINVAL) +# define SET_FPEXC_CTL(a, b) (-EINVAL) #endif #ifndef GET_FPEXC_CTL -# define GET_FPEXC_CTL(a,b) (-EINVAL) +# define GET_FPEXC_CTL(a, b) (-EINVAL) #endif #ifndef GET_ENDIAN -# define GET_ENDIAN(a,b) (-EINVAL) +# define GET_ENDIAN(a, b) (-EINVAL) #endif #ifndef SET_ENDIAN -# define SET_ENDIAN(a,b) (-EINVAL) +# define SET_ENDIAN(a, b) (-EINVAL) #endif #ifndef GET_TSC_CTL # define GET_TSC_CTL(a) (-EINVAL) @@ -182,39 +182,40 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval) rcu_read_lock(); read_lock(&tasklist_lock); switch (which) { - case PRIO_PROCESS: - if (who) - p = find_task_by_vpid(who); - else - p = current; - if (p) - error = set_one_prio(p, niceval, error); - break; - case PRIO_PGRP: - if (who) - pgrp = find_vpid(who); - else - pgrp = task_pgrp(current); - do_each_pid_thread(pgrp, PIDTYPE_PGID, p) { - error = set_one_prio(p, niceval, error); - } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); - break; - case PRIO_USER: - uid = make_kuid(cred->user_ns, who); - user = cred->user; - if (!who) - uid = cred->uid; - else if (!uid_eq(uid, cred->uid) && - !(user = find_user(uid))) + case PRIO_PROCESS: + if (who) + p = find_task_by_vpid(who); + else + p = current; + if (p) + error = set_one_prio(p, niceval, error); + break; + case PRIO_PGRP: + if (who) + pgrp = find_vpid(who); + else + pgrp = task_pgrp(current); + do_each_pid_thread(pgrp, PIDTYPE_PGID, p) { + error = set_one_prio(p, niceval, error); + } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); + break; + case PRIO_USER: + uid = make_kuid(cred->user_ns, who); + user = cred->user; + if (!who) + uid = cred->uid; + else if (!uid_eq(uid, cred->uid)) { + user = find_user(uid); + if (!user) goto out_unlock; /* No processes for this user */ - - do_each_thread(g, p) { - if (uid_eq(task_uid(p), uid)) - error = set_one_prio(p, niceval, error); - } while_each_thread(g, p); - if (!uid_eq(uid, cred->uid)) - free_uid(user); /* For find_user() */ - break; + } + do_each_thread(g, p) { + if (uid_eq(task_uid(p), uid)) + error = set_one_prio(p, niceval, error); + } while_each_thread(g, p); + if (!uid_eq(uid, cred->uid)) + free_uid(user); /* For find_user() */ + break; } out_unlock: read_unlock(&tasklist_lock); @@ -244,47 +245,48 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who) rcu_read_lock(); read_lock(&tasklist_lock); switch (which) { - case PRIO_PROCESS: - if (who) - p = find_task_by_vpid(who); - else - p = current; - if (p) { + case PRIO_PROCESS: + if (who) + p = find_task_by_vpid(who); + else + p = current; + if (p) { + niceval = nice_to_rlimit(task_nice(p)); + if (niceval > retval) + retval = niceval; + } + break; + case PRIO_PGRP: + if (who) + pgrp = find_vpid(who); + else + pgrp = task_pgrp(current); + do_each_pid_thread(pgrp, PIDTYPE_PGID, p) { + niceval = nice_to_rlimit(task_nice(p)); + if (niceval > retval) + retval = niceval; + } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); + break; + case PRIO_USER: + uid = make_kuid(cred->user_ns, who); + user = cred->user; + if (!who) + uid = cred->uid; + else if (!uid_eq(uid, cred->uid)) { + user = find_user(uid); + if (!user) + goto out_unlock; /* No processes for this user */ + } + do_each_thread(g, p) { + if (uid_eq(task_uid(p), uid)) { niceval = nice_to_rlimit(task_nice(p)); if (niceval > retval) retval = niceval; } - break; - case PRIO_PGRP: - if (who) - pgrp = find_vpid(who); - else - pgrp = task_pgrp(current); - do_each_pid_thread(pgrp, PIDTYPE_PGID, p) { - niceval = nice_to_rlimit(task_nice(p)); - if (niceval > retval) - retval = niceval; - } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); - break; - case PRIO_USER: - uid = make_kuid(cred->user_ns, who); - user = cred->user; - if (!who) - uid = cred->uid; - else if (!uid_eq(uid, cred->uid) && - !(user = find_user(uid))) - goto out_unlock; /* No processes for this user */ - - do_each_thread(g, p) { - if (uid_eq(task_uid(p), uid)) { - niceval = nice_to_rlimit(task_nice(p)); - if (niceval > retval) - retval = niceval; - } - } while_each_thread(g, p); - if (!uid_eq(uid, cred->uid)) - free_uid(user); /* for find_user() */ - break; + } while_each_thread(g, p); + if (!uid_eq(uid, cred->uid)) + free_uid(user); /* for find_user() */ + break; } out_unlock: read_unlock(&tasklist_lock); @@ -306,7 +308,7 @@ out_unlock: * * The general idea is that a program which uses just setregid() will be * 100% compatible with BSD. A program which uses just setgid() will be - * 100% compatible with POSIX with saved IDs. + * 100% compatible with POSIX with saved IDs. * * SMP: There are not races, the GIDs are checked only by filesystem * operations (as far as semantic preservation is concerned). @@ -364,7 +366,7 @@ error: } /* - * setgid() is implemented like SysV w/ SAVED_IDS + * setgid() is implemented like SysV w/ SAVED_IDS * * SMP: Same implicit races as above. */ @@ -442,7 +444,7 @@ static int set_user(struct cred *new) * * The general idea is that a program which uses just setreuid() will be * 100% compatible with BSD. A program which uses just setuid() will be - * 100% compatible with POSIX with saved IDs. + * 100% compatible with POSIX with saved IDs. */ SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid) { @@ -503,17 +505,17 @@ error: abort_creds(new); return retval; } - + /* - * setuid() is implemented like SysV with SAVED_IDS - * + * setuid() is implemented like SysV with SAVED_IDS + * * Note that SAVED_ID's is deficient in that a setuid root program - * like sendmail, for example, cannot set its uid to be a normal + * like sendmail, for example, cannot set its uid to be a normal * user and then switch back, because if you're root, setuid() sets * the saved uid too. If you don't like this, blame the bright people * in the POSIX committee and/or USG. Note that the BSD-style setreuid() * will allow a root program to temporarily drop privileges and be able to - * regain them by swapping the real and effective uid. + * regain them by swapping the real and effective uid. */ SYSCALL_DEFINE1(setuid, uid_t, uid) { @@ -637,10 +639,12 @@ SYSCALL_DEFINE3(getresuid, uid_t __user *, ruidp, uid_t __user *, euidp, uid_t _ euid = from_kuid_munged(cred->user_ns, cred->euid); suid = from_kuid_munged(cred->user_ns, cred->suid); - if (!(retval = put_user(ruid, ruidp)) && - !(retval = put_user(euid, euidp))) - retval = put_user(suid, suidp); - + retval = put_user(ruid, ruidp); + if (!retval) { + retval = put_user(euid, euidp); + if (!retval) + return put_user(suid, suidp); + } return retval; } @@ -709,9 +713,12 @@ SYSCALL_DEFINE3(getresgid, gid_t __user *, rgidp, gid_t __user *, egidp, gid_t _ egid = from_kgid_munged(cred->user_ns, cred->egid); sgid = from_kgid_munged(cred->user_ns, cred->sgid); - if (!(retval = put_user(rgid, rgidp)) && - !(retval = put_user(egid, egidp))) - retval = put_user(sgid, sgidp); + retval = put_user(rgid, rgidp); + if (!retval) { + retval = put_user(egid, egidp); + if (!retval) + retval = put_user(sgid, sgidp); + } return retval; } @@ -862,11 +869,9 @@ void do_sys_times(struct tms *tms) { cputime_t tgutime, tgstime, cutime, cstime; - spin_lock_irq(¤t->sighand->siglock); thread_group_cputime_adjusted(current, &tgutime, &tgstime); cutime = current->signal->cutime; cstime = current->signal->cstime; - spin_unlock_irq(¤t->sighand->siglock); tms->tms_utime = cputime_to_clock_t(tgutime); tms->tms_stime = cputime_to_clock_t(tgstime); tms->tms_cutime = cputime_to_clock_t(cutime); @@ -1284,7 +1289,6 @@ SYSCALL_DEFINE2(getrlimit, unsigned int, resource, struct rlimit __user *, rlim) /* * Back compatibility for getrlimit. Needed for some apps. */ - SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource, struct rlimit __user *, rlim) { @@ -1299,7 +1303,7 @@ SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource, x.rlim_cur = 0x7FFFFFFF; if (x.rlim_max > 0x7FFFFFFF) x.rlim_max = 0x7FFFFFFF; - return copy_to_user(rlim, &x, sizeof(x))?-EFAULT:0; + return copy_to_user(rlim, &x, sizeof(x)) ? -EFAULT : 0; } #endif @@ -1527,7 +1531,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) cputime_t tgutime, tgstime, utime, stime; unsigned long maxrss = 0; - memset((char *) r, 0, sizeof *r); + memset((char *)r, 0, sizeof (*r)); utime = stime = 0; if (who == RUSAGE_THREAD) { @@ -1541,41 +1545,41 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) return; switch (who) { - case RUSAGE_BOTH: - case RUSAGE_CHILDREN: - utime = p->signal->cutime; - stime = p->signal->cstime; - r->ru_nvcsw = p->signal->cnvcsw; - r->ru_nivcsw = p->signal->cnivcsw; - r->ru_minflt = p->signal->cmin_flt; - r->ru_majflt = p->signal->cmaj_flt; - r->ru_inblock = p->signal->cinblock; - r->ru_oublock = p->signal->coublock; - maxrss = p->signal->cmaxrss; - - if (who == RUSAGE_CHILDREN) - break; - - case RUSAGE_SELF: - thread_group_cputime_adjusted(p, &tgutime, &tgstime); - utime += tgutime; - stime += tgstime; - r->ru_nvcsw += p->signal->nvcsw; - r->ru_nivcsw += p->signal->nivcsw; - r->ru_minflt += p->signal->min_flt; - r->ru_majflt += p->signal->maj_flt; - r->ru_inblock += p->signal->inblock; - r->ru_oublock += p->signal->oublock; - if (maxrss < p->signal->maxrss) - maxrss = p->signal->maxrss; - t = p; - do { - accumulate_thread_rusage(t, r); - } while_each_thread(p, t); + case RUSAGE_BOTH: + case RUSAGE_CHILDREN: + utime = p->signal->cutime; + stime = p->signal->cstime; + r->ru_nvcsw = p->signal->cnvcsw; + r->ru_nivcsw = p->signal->cnivcsw; + r->ru_minflt = p->signal->cmin_flt; + r->ru_majflt = p->signal->cmaj_flt; + r->ru_inblock = p->signal->cinblock; + r->ru_oublock = p->signal->coublock; + maxrss = p->signal->cmaxrss; + + if (who == RUSAGE_CHILDREN) break; - default: - BUG(); + case RUSAGE_SELF: + thread_group_cputime_adjusted(p, &tgutime, &tgstime); + utime += tgutime; + stime += tgstime; + r->ru_nvcsw += p->signal->nvcsw; + r->ru_nivcsw += p->signal->nivcsw; + r->ru_minflt += p->signal->min_flt; + r->ru_majflt += p->signal->maj_flt; + r->ru_inblock += p->signal->inblock; + r->ru_oublock += p->signal->oublock; + if (maxrss < p->signal->maxrss) + maxrss = p->signal->maxrss; + t = p; + do { + accumulate_thread_rusage(t, r); + } while_each_thread(p, t); + break; + + default: + BUG(); } unlock_task_sighand(p, &flags); @@ -1585,6 +1589,7 @@ out: if (who != RUSAGE_CHILDREN) { struct mm_struct *mm = get_task_mm(p); + if (mm) { setmax_mm_hiwater_rss(&maxrss, mm); mmput(mm); @@ -1596,6 +1601,7 @@ out: int getrusage(struct task_struct *p, int who, struct rusage __user *ru) { struct rusage r; + k_getrusage(p, who, &r); return copy_to_user(ru, &r, sizeof(r)) ? -EFAULT : 0; } @@ -1628,12 +1634,14 @@ SYSCALL_DEFINE1(umask, int, mask) return mask; } -static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd) +static int prctl_set_mm_exe_file_locked(struct mm_struct *mm, unsigned int fd) { struct fd exe; struct inode *inode; int err; + VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_sem), mm); + exe = fdget(fd); if (!exe.file) return -EBADF; @@ -1654,8 +1662,6 @@ static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd) if (err) goto exit; - down_write(&mm->mmap_sem); - /* * Forbid mm->exe_file change if old file still mapped. */ @@ -1667,7 +1673,7 @@ static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd) if (vma->vm_file && path_equal(&vma->vm_file->f_path, &mm->exe_file->f_path)) - goto exit_unlock; + goto exit; } /* @@ -1678,34 +1684,222 @@ static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd) */ err = -EPERM; if (test_and_set_bit(MMF_EXE_FILE_CHANGED, &mm->flags)) - goto exit_unlock; + goto exit; err = 0; set_mm_exe_file(mm, exe.file); /* this grabs a reference to exe.file */ -exit_unlock: - up_write(&mm->mmap_sem); - exit: fdput(exe); return err; } +#ifdef CONFIG_CHECKPOINT_RESTORE +/* + * WARNING: we don't require any capability here so be very careful + * in what is allowed for modification from userspace. + */ +static int validate_prctl_map(struct prctl_mm_map *prctl_map) +{ + unsigned long mmap_max_addr = TASK_SIZE; + struct mm_struct *mm = current->mm; + int error = -EINVAL, i; + + static const unsigned char offsets[] = { + offsetof(struct prctl_mm_map, start_code), + offsetof(struct prctl_mm_map, end_code), + offsetof(struct prctl_mm_map, start_data), + offsetof(struct prctl_mm_map, end_data), + offsetof(struct prctl_mm_map, start_brk), + offsetof(struct prctl_mm_map, brk), + offsetof(struct prctl_mm_map, start_stack), + offsetof(struct prctl_mm_map, arg_start), + offsetof(struct prctl_mm_map, arg_end), + offsetof(struct prctl_mm_map, env_start), + offsetof(struct prctl_mm_map, env_end), + }; + + /* + * Make sure the members are not somewhere outside + * of allowed address space. + */ + for (i = 0; i < ARRAY_SIZE(offsets); i++) { + u64 val = *(u64 *)((char *)prctl_map + offsets[i]); + + if ((unsigned long)val >= mmap_max_addr || + (unsigned long)val < mmap_min_addr) + goto out; + } + + /* + * Make sure the pairs are ordered. + */ +#define __prctl_check_order(__m1, __op, __m2) \ + ((unsigned long)prctl_map->__m1 __op \ + (unsigned long)prctl_map->__m2) ? 0 : -EINVAL + error = __prctl_check_order(start_code, <, end_code); + error |= __prctl_check_order(start_data, <, end_data); + error |= __prctl_check_order(start_brk, <=, brk); + error |= __prctl_check_order(arg_start, <=, arg_end); + error |= __prctl_check_order(env_start, <=, env_end); + if (error) + goto out; +#undef __prctl_check_order + + error = -EINVAL; + + /* + * @brk should be after @end_data in traditional maps. + */ + if (prctl_map->start_brk <= prctl_map->end_data || + prctl_map->brk <= prctl_map->end_data) + goto out; + + /* + * Neither we should allow to override limits if they set. + */ + if (check_data_rlimit(rlimit(RLIMIT_DATA), prctl_map->brk, + prctl_map->start_brk, prctl_map->end_data, + prctl_map->start_data)) + goto out; + + /* + * Someone is trying to cheat the auxv vector. + */ + if (prctl_map->auxv_size) { + if (!prctl_map->auxv || prctl_map->auxv_size > sizeof(mm->saved_auxv)) + goto out; + } + + /* + * Finally, make sure the caller has the rights to + * change /proc/pid/exe link: only local root should + * be allowed to. + */ + if (prctl_map->exe_fd != (u32)-1) { + struct user_namespace *ns = current_user_ns(); + const struct cred *cred = current_cred(); + + if (!uid_eq(cred->uid, make_kuid(ns, 0)) || + !gid_eq(cred->gid, make_kgid(ns, 0))) + goto out; + } + + error = 0; +out: + return error; +} + +static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data_size) +{ + struct prctl_mm_map prctl_map = { .exe_fd = (u32)-1, }; + unsigned long user_auxv[AT_VECTOR_SIZE]; + struct mm_struct *mm = current->mm; + int error; + + BUILD_BUG_ON(sizeof(user_auxv) != sizeof(mm->saved_auxv)); + BUILD_BUG_ON(sizeof(struct prctl_mm_map) > 256); + + if (opt == PR_SET_MM_MAP_SIZE) + return put_user((unsigned int)sizeof(prctl_map), + (unsigned int __user *)addr); + + if (data_size != sizeof(prctl_map)) + return -EINVAL; + + if (copy_from_user(&prctl_map, addr, sizeof(prctl_map))) + return -EFAULT; + + error = validate_prctl_map(&prctl_map); + if (error) + return error; + + if (prctl_map.auxv_size) { + memset(user_auxv, 0, sizeof(user_auxv)); + if (copy_from_user(user_auxv, + (const void __user *)prctl_map.auxv, + prctl_map.auxv_size)) + return -EFAULT; + + /* Last entry must be AT_NULL as specification requires */ + user_auxv[AT_VECTOR_SIZE - 2] = AT_NULL; + user_auxv[AT_VECTOR_SIZE - 1] = AT_NULL; + } + + down_write(&mm->mmap_sem); + if (prctl_map.exe_fd != (u32)-1) + error = prctl_set_mm_exe_file_locked(mm, prctl_map.exe_fd); + downgrade_write(&mm->mmap_sem); + if (error) + goto out; + + /* + * We don't validate if these members are pointing to + * real present VMAs because application may have correspond + * VMAs already unmapped and kernel uses these members for statistics + * output in procfs mostly, except + * + * - @start_brk/@brk which are used in do_brk but kernel lookups + * for VMAs when updating these memvers so anything wrong written + * here cause kernel to swear at userspace program but won't lead + * to any problem in kernel itself + */ + + mm->start_code = prctl_map.start_code; + mm->end_code = prctl_map.end_code; + mm->start_data = prctl_map.start_data; + mm->end_data = prctl_map.end_data; + mm->start_brk = prctl_map.start_brk; + mm->brk = prctl_map.brk; + mm->start_stack = prctl_map.start_stack; + mm->arg_start = prctl_map.arg_start; + mm->arg_end = prctl_map.arg_end; + mm->env_start = prctl_map.env_start; + mm->env_end = prctl_map.env_end; + + /* + * Note this update of @saved_auxv is lockless thus + * if someone reads this member in procfs while we're + * updating -- it may get partly updated results. It's + * known and acceptable trade off: we leave it as is to + * not introduce additional locks here making the kernel + * more complex. + */ + if (prctl_map.auxv_size) + memcpy(mm->saved_auxv, user_auxv, sizeof(user_auxv)); + + error = 0; +out: + up_read(&mm->mmap_sem); + return error; +} +#endif /* CONFIG_CHECKPOINT_RESTORE */ + static int prctl_set_mm(int opt, unsigned long addr, unsigned long arg4, unsigned long arg5) { - unsigned long rlim = rlimit(RLIMIT_DATA); struct mm_struct *mm = current->mm; struct vm_area_struct *vma; int error; - if (arg5 || (arg4 && opt != PR_SET_MM_AUXV)) + if (arg5 || (arg4 && (opt != PR_SET_MM_AUXV && + opt != PR_SET_MM_MAP && + opt != PR_SET_MM_MAP_SIZE))) return -EINVAL; +#ifdef CONFIG_CHECKPOINT_RESTORE + if (opt == PR_SET_MM_MAP || opt == PR_SET_MM_MAP_SIZE) + return prctl_set_mm_map(opt, (const void __user *)addr, arg4); +#endif + if (!capable(CAP_SYS_RESOURCE)) return -EPERM; - if (opt == PR_SET_MM_EXE_FILE) - return prctl_set_mm_exe_file(mm, (unsigned int)addr); + if (opt == PR_SET_MM_EXE_FILE) { + down_write(&mm->mmap_sem); + error = prctl_set_mm_exe_file_locked(mm, (unsigned int)addr); + up_write(&mm->mmap_sem); + return error; + } if (addr >= TASK_SIZE || addr < mmap_min_addr) return -EINVAL; @@ -1733,9 +1927,8 @@ static int prctl_set_mm(int opt, unsigned long addr, if (addr <= mm->end_data) goto out; - if (rlim < RLIM_INFINITY && - (mm->brk - addr) + - (mm->end_data - mm->start_data) > rlim) + if (check_data_rlimit(rlimit(RLIMIT_DATA), mm->brk, addr, + mm->end_data, mm->start_data)) goto out; mm->start_brk = addr; @@ -1745,9 +1938,8 @@ static int prctl_set_mm(int opt, unsigned long addr, if (addr <= mm->end_data) goto out; - if (rlim < RLIM_INFINITY && - (addr - mm->start_brk) + - (mm->end_data - mm->start_data) > rlim) + if (check_data_rlimit(rlimit(RLIMIT_DATA), addr, mm->start_brk, + mm->end_data, mm->start_data)) goto out; mm->brk = addr; @@ -2023,6 +2215,7 @@ SYSCALL_DEFINE3(getcpu, unsigned __user *, cpup, unsigned __user *, nodep, { int err = 0; int cpu = raw_smp_processor_id(); + if (cpup) err |= put_user(cpu, cpup); if (nodep) @@ -2135,7 +2328,7 @@ COMPAT_SYSCALL_DEFINE1(sysinfo, struct compat_sysinfo __user *, info) /* Check to see if any memory value is too large for 32-bit and scale * down if needed */ - if ((s.totalram >> 32) || (s.totalswap >> 32)) { + if (upper_32_bits(s.totalram) || upper_32_bits(s.totalswap)) { int bitcount = 0; while (s.mem_unit < PAGE_SIZE) { diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 391d4ddb6f4b..02aa4185b17e 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -156,6 +156,9 @@ cond_syscall(sys_process_vm_writev); cond_syscall(compat_sys_process_vm_readv); cond_syscall(compat_sys_process_vm_writev); cond_syscall(sys_uselib); +cond_syscall(sys_fadvise64); +cond_syscall(sys_fadvise64_64); +cond_syscall(sys_madvise); /* arch-specific weak syscall entries */ cond_syscall(sys_pciconfig_read); @@ -218,3 +221,6 @@ cond_syscall(sys_kcmp); /* operate on Secure Computing state */ cond_syscall(sys_seccomp); + +/* access BPF programs and maps */ +cond_syscall(sys_bpf); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 75875a741b5e..4aada6d9fe74 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1055,15 +1055,6 @@ static struct ctl_table kern_table[] = { .child = key_sysctls, }, #endif -#ifdef CONFIG_RCU_TORTURE_TEST - { - .procname = "rcutorture_runnable", - .data = &rcutorture_runnable, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif #ifdef CONFIG_PERF_EVENTS /* * User-space scripts rely on the existence of this file @@ -1460,13 +1451,6 @@ static struct ctl_table vm_table[] = { .extra2 = &one, }, #endif - { - .procname = "scan_unevictable_pages", - .data = &scan_unevictable_pages, - .maxlen = sizeof(scan_unevictable_pages), - .mode = 0644, - .proc_handler = scan_unevictable_handler, - }, #ifdef CONFIG_MEMORY_FAILURE { .procname = "memory_failure_early_kill", diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index e4ba9a5a5ccb..9a4f750a2963 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -390,7 +390,6 @@ static const struct bin_table bin_net_ipv4_table[] = { { CTL_INT, NET_TCP_MTU_PROBING, "tcp_mtu_probing" }, { CTL_INT, NET_TCP_BASE_MSS, "tcp_base_mss" }, { CTL_INT, NET_IPV4_TCP_WORKAROUND_SIGNED_WINDOWS, "tcp_workaround_signed_windows" }, - { CTL_INT, NET_TCP_DMA_COPYBREAK, "tcp_dma_copybreak" }, { CTL_INT, NET_TCP_SLOW_START_AFTER_IDLE, "tcp_slow_start_after_idle" }, { CTL_INT, NET_CIPSOV4_CACHE_ENABLE, "cipso_cache_enable" }, { CTL_INT, NET_CIPSOV4_CACHE_BUCKET_SIZE, "cipso_cache_bucket_size" }, diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 4aec4a457431..a7077d3ae52f 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -464,18 +464,26 @@ static enum alarmtimer_type clock2alarm(clockid_t clockid) static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm, ktime_t now) { + unsigned long flags; struct k_itimer *ptr = container_of(alarm, struct k_itimer, it.alarm.alarmtimer); - if (posix_timer_event(ptr, 0) != 0) - ptr->it_overrun++; + enum alarmtimer_restart result = ALARMTIMER_NORESTART; + + spin_lock_irqsave(&ptr->it_lock, flags); + if ((ptr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) { + if (posix_timer_event(ptr, 0) != 0) + ptr->it_overrun++; + } /* Re-add periodic timers */ if (ptr->it.alarm.interval.tv64) { ptr->it_overrun += alarm_forward(alarm, now, ptr->it.alarm.interval); - return ALARMTIMER_RESTART; + result = ALARMTIMER_RESTART; } - return ALARMTIMER_NORESTART; + spin_unlock_irqrestore(&ptr->it_lock, flags); + + return result; } /** @@ -541,18 +549,22 @@ static int alarm_timer_create(struct k_itimer *new_timer) * @new_timer: k_itimer pointer * @cur_setting: itimerspec data to fill * - * Copies the itimerspec data out from the k_itimer + * Copies out the current itimerspec data */ static void alarm_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting) { - memset(cur_setting, 0, sizeof(struct itimerspec)); + ktime_t relative_expiry_time = + alarm_expires_remaining(&(timr->it.alarm.alarmtimer)); + + if (ktime_to_ns(relative_expiry_time) > 0) { + cur_setting->it_value = ktime_to_timespec(relative_expiry_time); + } else { + cur_setting->it_value.tv_sec = 0; + cur_setting->it_value.tv_nsec = 0; + } - cur_setting->it_interval = - ktime_to_timespec(timr->it.alarm.interval); - cur_setting->it_value = - ktime_to_timespec(timr->it.alarm.alarmtimer.node.expires); - return; + cur_setting->it_interval = ktime_to_timespec(timr->it.alarm.interval); } /** diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 1c2fe7de2842..ab370ffffd53 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1776,7 +1776,6 @@ schedule_hrtimeout_range_clock(ktime_t *expires, unsigned long delta, */ if (!expires) { schedule(); - __set_current_state(TASK_RUNNING); return -EINTR; } diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 3b8946416a5f..492b986195d5 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -272,22 +272,8 @@ static int posix_cpu_clock_get_task(struct task_struct *tsk, if (same_thread_group(tsk, current)) err = cpu_clock_sample(which_clock, tsk, &rtn); } else { - unsigned long flags; - struct sighand_struct *sighand; - - /* - * while_each_thread() is not yet entirely RCU safe, - * keep locking the group while sampling process - * clock for now. - */ - sighand = lock_task_sighand(tsk, &flags); - if (!sighand) - return err; - if (tsk == current || thread_group_leader(tsk)) err = cpu_clock_sample_group(which_clock, tsk, &rtn); - - unlock_task_sighand(tsk, &flags); } if (!err) diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 0a0608edeb26..052b4b53c3d6 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -400,4 +400,5 @@ void tick_resume(void) void __init tick_init(void) { tick_broadcast_init(); + tick_nohz_init(); } diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index c19c1d84b6f3..366aeb4f2c66 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -99,6 +99,13 @@ static inline int tick_broadcast_oneshot_active(void) { return 0; } static inline bool tick_broadcast_oneshot_available(void) { return false; } #endif /* !TICK_ONESHOT */ +/* NO_HZ_FULL internal */ +#ifdef CONFIG_NO_HZ_FULL +extern void tick_nohz_init(void); +# else +static inline void tick_nohz_init(void) { } +#endif + /* * Broadcasting support */ diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 01d512fd45f1..a73efdf6f696 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -295,22 +295,12 @@ out: /* Parse the boot-time nohz CPU list from the kernel parameters. */ static int __init tick_nohz_full_setup(char *str) { - int cpu; - alloc_bootmem_cpumask_var(&tick_nohz_full_mask); - alloc_bootmem_cpumask_var(&housekeeping_mask); if (cpulist_parse(str, tick_nohz_full_mask) < 0) { pr_warning("NOHZ: Incorrect nohz_full cpumask\n"); + free_bootmem_cpumask_var(tick_nohz_full_mask); return 1; } - - cpu = smp_processor_id(); - if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) { - pr_warning("NO_HZ: Clearing %d from nohz_full range for timekeeping\n", cpu); - cpumask_clear_cpu(cpu, tick_nohz_full_mask); - } - cpumask_andnot(housekeeping_mask, - cpu_possible_mask, tick_nohz_full_mask); tick_nohz_full_running = true; return 1; @@ -349,18 +339,11 @@ static int tick_nohz_init_all(void) #ifdef CONFIG_NO_HZ_FULL_ALL if (!alloc_cpumask_var(&tick_nohz_full_mask, GFP_KERNEL)) { - pr_err("NO_HZ: Can't allocate full dynticks cpumask\n"); - return err; - } - if (!alloc_cpumask_var(&housekeeping_mask, GFP_KERNEL)) { - pr_err("NO_HZ: Can't allocate not-full dynticks cpumask\n"); + WARN(1, "NO_HZ: Can't allocate full dynticks cpumask\n"); return err; } err = 0; cpumask_setall(tick_nohz_full_mask); - cpumask_clear_cpu(smp_processor_id(), tick_nohz_full_mask); - cpumask_clear(housekeeping_mask); - cpumask_set_cpu(smp_processor_id(), housekeeping_mask); tick_nohz_full_running = true; #endif return err; @@ -375,6 +358,37 @@ void __init tick_nohz_init(void) return; } + if (!alloc_cpumask_var(&housekeeping_mask, GFP_KERNEL)) { + WARN(1, "NO_HZ: Can't allocate not-full dynticks cpumask\n"); + cpumask_clear(tick_nohz_full_mask); + tick_nohz_full_running = false; + return; + } + + /* + * Full dynticks uses irq work to drive the tick rescheduling on safe + * locking contexts. But then we need irq work to raise its own + * interrupts to avoid circular dependency on the tick + */ + if (!arch_irq_work_has_interrupt()) { + pr_warning("NO_HZ: Can't run full dynticks because arch doesn't " + "support irq work self-IPIs\n"); + cpumask_clear(tick_nohz_full_mask); + cpumask_copy(housekeeping_mask, cpu_possible_mask); + tick_nohz_full_running = false; + return; + } + + cpu = smp_processor_id(); + + if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) { + pr_warning("NO_HZ: Clearing %d from nohz_full range for timekeeping\n", cpu); + cpumask_clear_cpu(cpu, tick_nohz_full_mask); + } + + cpumask_andnot(housekeeping_mask, + cpu_possible_mask, tick_nohz_full_mask); + for_each_cpu(cpu, tick_nohz_full_mask) context_tracking_cpu_set(cpu); @@ -982,6 +996,10 @@ static void tick_nohz_handler(struct clock_event_device *dev) tick_sched_do_timer(now); tick_sched_handle(ts, regs); + /* No need to reprogram if we are running tickless */ + if (unlikely(ts->tick_stopped)) + return; + while (tick_nohz_reprogram(ts, now)) { now = ktime_get(); tick_do_update_jiffies64(now); @@ -1109,6 +1127,10 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer) if (regs) tick_sched_handle(ts, regs); + /* No need to reprogram if we are in idle or full dynticks mode */ + if (unlikely(ts->tick_stopped)) + return HRTIMER_NORESTART; + hrtimer_forward(timer, now, tick_period); return HRTIMER_RESTART; diff --git a/kernel/time/time.c b/kernel/time/time.c index f0294ba14634..a9ae20fb0b11 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -559,17 +559,20 @@ EXPORT_SYMBOL(usecs_to_jiffies); * that a remainder subtract here would not do the right thing as the * resolution values don't fall on second boundries. I.e. the line: * nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding. + * Note that due to the small error in the multiplier here, this + * rounding is incorrect for sufficiently large values of tv_nsec, but + * well formed timespecs should have tv_nsec < NSEC_PER_SEC, so we're + * OK. * * Rather, we just shift the bits off the right. * * The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec * value to a scaled second value. */ -unsigned long -timespec_to_jiffies(const struct timespec *value) +static unsigned long +__timespec_to_jiffies(unsigned long sec, long nsec) { - unsigned long sec = value->tv_sec; - long nsec = value->tv_nsec + TICK_NSEC - 1; + nsec = nsec + TICK_NSEC - 1; if (sec >= MAX_SEC_IN_JIFFIES){ sec = MAX_SEC_IN_JIFFIES; @@ -580,6 +583,13 @@ timespec_to_jiffies(const struct timespec *value) (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC; } + +unsigned long +timespec_to_jiffies(const struct timespec *value) +{ + return __timespec_to_jiffies(value->tv_sec, value->tv_nsec); +} + EXPORT_SYMBOL(timespec_to_jiffies); void @@ -596,31 +606,27 @@ jiffies_to_timespec(const unsigned long jiffies, struct timespec *value) } EXPORT_SYMBOL(jiffies_to_timespec); -/* Same for "timeval" - * - * Well, almost. The problem here is that the real system resolution is - * in nanoseconds and the value being converted is in micro seconds. - * Also for some machines (those that use HZ = 1024, in-particular), - * there is a LARGE error in the tick size in microseconds. - - * The solution we use is to do the rounding AFTER we convert the - * microsecond part. Thus the USEC_ROUND, the bits to be shifted off. - * Instruction wise, this should cost only an additional add with carry - * instruction above the way it was done above. +/* + * We could use a similar algorithm to timespec_to_jiffies (with a + * different multiplier for usec instead of nsec). But this has a + * problem with rounding: we can't exactly add TICK_NSEC - 1 to the + * usec value, since it's not necessarily integral. + * + * We could instead round in the intermediate scaled representation + * (i.e. in units of 1/2^(large scale) jiffies) but that's also + * perilous: the scaling introduces a small positive error, which + * combined with a division-rounding-upward (i.e. adding 2^(scale) - 1 + * units to the intermediate before shifting) leads to accidental + * overflow and overestimates. + * + * At the cost of one additional multiplication by a constant, just + * use the timespec implementation. */ unsigned long timeval_to_jiffies(const struct timeval *value) { - unsigned long sec = value->tv_sec; - long usec = value->tv_usec; - - if (sec >= MAX_SEC_IN_JIFFIES){ - sec = MAX_SEC_IN_JIFFIES; - usec = 0; - } - return (((u64)sec * SEC_CONVERSION) + - (((u64)usec * USEC_CONVERSION + USEC_ROUND) >> - (USEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC; + return __timespec_to_jiffies(value->tv_sec, + value->tv_usec * NSEC_PER_USEC); } EXPORT_SYMBOL(timeval_to_jiffies); diff --git a/kernel/time/timer.c b/kernel/time/timer.c index aca5dfe2fa3d..9bbb8344ed3b 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1385,7 +1385,7 @@ void update_process_times(int user_tick) rcu_check_callbacks(cpu, user_tick); #ifdef CONFIG_IRQ_WORK if (in_irq()) - irq_work_run(); + irq_work_tick(); #endif scheduler_tick(); run_posix_cpu_timers(p); diff --git a/kernel/torture.c b/kernel/torture.c index d600af21f022..dd70993c266c 100644 --- a/kernel/torture.c +++ b/kernel/torture.c @@ -211,18 +211,16 @@ EXPORT_SYMBOL_GPL(torture_onoff_cleanup); /* * Print online/offline testing statistics. */ -char *torture_onoff_stats(char *page) +void torture_onoff_stats(void) { #ifdef CONFIG_HOTPLUG_CPU - page += sprintf(page, - "onoff: %ld/%ld:%ld/%ld %d,%d:%d,%d %lu:%lu (HZ=%d) ", - n_online_successes, n_online_attempts, - n_offline_successes, n_offline_attempts, - min_online, max_online, - min_offline, max_offline, - sum_online, sum_offline, HZ); + pr_cont("onoff: %ld/%ld:%ld/%ld %d,%d:%d,%d %lu:%lu (HZ=%d) ", + n_online_successes, n_online_attempts, + n_offline_successes, n_offline_attempts, + min_online, max_online, + min_offline, max_offline, + sum_online, sum_offline, HZ); #endif /* #ifdef CONFIG_HOTPLUG_CPU */ - return page; } EXPORT_SYMBOL_GPL(torture_onoff_stats); @@ -635,8 +633,13 @@ EXPORT_SYMBOL_GPL(torture_init_end); * * This must be called before the caller starts shutting down its own * kthreads. + * + * Both torture_cleanup_begin() and torture_cleanup_end() must be paired, + * in order to correctly perform the cleanup. They are separated because + * threads can still need to reference the torture_type type, thus nullify + * only after completing all other relevant calls. */ -bool torture_cleanup(void) +bool torture_cleanup_begin(void) { mutex_lock(&fullstop_mutex); if (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) { @@ -651,12 +654,17 @@ bool torture_cleanup(void) torture_shuffle_cleanup(); torture_stutter_cleanup(); torture_onoff_cleanup(); + return false; +} +EXPORT_SYMBOL_GPL(torture_cleanup_begin); + +void torture_cleanup_end(void) +{ mutex_lock(&fullstop_mutex); torture_type = NULL; mutex_unlock(&fullstop_mutex); - return false; } -EXPORT_SYMBOL_GPL(torture_cleanup); +EXPORT_SYMBOL_GPL(torture_cleanup_end); /* * Is it time for the current torture test to stop? diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 5916a8e59e87..fb186b9ddf51 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -113,6 +113,9 @@ ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub; static struct ftrace_ops global_ops; static struct ftrace_ops control_ops; +static void ftrace_ops_recurs_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs); + #if ARCH_SUPPORTS_FTRACE_OPS static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct pt_regs *regs); @@ -251,18 +254,24 @@ static void update_ftrace_function(void) ftrace_func_t func; /* + * Prepare the ftrace_ops that the arch callback will use. + * If there's only one ftrace_ops registered, the ftrace_ops_list + * will point to the ops we want. + */ + set_function_trace_op = ftrace_ops_list; + + /* If there's no ftrace_ops registered, just call the stub function */ + if (ftrace_ops_list == &ftrace_list_end) { + func = ftrace_stub; + + /* * If we are at the end of the list and this ops is * recursion safe and not dynamic and the arch supports passing ops, * then have the mcount trampoline call the function directly. */ - if (ftrace_ops_list == &ftrace_list_end || - (ftrace_ops_list->next == &ftrace_list_end && - !(ftrace_ops_list->flags & FTRACE_OPS_FL_DYNAMIC) && - (ftrace_ops_list->flags & FTRACE_OPS_FL_RECURSION_SAFE) && - !FTRACE_FORCE_LIST_FUNC)) { - /* Set the ftrace_ops that the arch callback uses */ - set_function_trace_op = ftrace_ops_list; - func = ftrace_ops_list->func; + } else if (ftrace_ops_list->next == &ftrace_list_end) { + func = ftrace_ops_get_func(ftrace_ops_list); + } else { /* Just use the default ftrace_ops */ set_function_trace_op = &ftrace_list_end; @@ -1048,6 +1057,12 @@ static struct pid * const ftrace_swapper_pid = &init_struct_pid; static struct ftrace_ops *removed_ops; +/* + * Set when doing a global update, like enabling all recs or disabling them. + * It is not set when just updating a single ftrace_ops. + */ +static bool update_all_ops; + #ifndef CONFIG_FTRACE_MCOUNT_RECORD # error Dynamic ftrace depends on MCOUNT_RECORD #endif @@ -1307,7 +1322,6 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable, struct ftrace_func_entry *entry; struct hlist_node *tn; struct hlist_head *hhd; - struct ftrace_hash *old_hash; struct ftrace_hash *new_hash; int size = src->count; int bits = 0; @@ -1352,15 +1366,28 @@ update: */ ftrace_hash_rec_disable_modify(ops, enable); - old_hash = *dst; rcu_assign_pointer(*dst, new_hash); - free_ftrace_hash_rcu(old_hash); ftrace_hash_rec_enable_modify(ops, enable); return 0; } +static bool hash_contains_ip(unsigned long ip, + struct ftrace_ops_hash *hash) +{ + /* + * The function record is a match if it exists in the filter + * hash and not in the notrace hash. Note, an emty hash is + * considered a match for the filter hash, but an empty + * notrace hash is considered not in the notrace hash. + */ + return (ftrace_hash_empty(hash->filter_hash) || + ftrace_lookup_ip(hash->filter_hash, ip)) && + (ftrace_hash_empty(hash->notrace_hash) || + !ftrace_lookup_ip(hash->notrace_hash, ip)); +} + /* * Test the hashes for this ops to see if we want to call * the ops->func or not. @@ -1376,8 +1403,7 @@ update: static int ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs) { - struct ftrace_hash *filter_hash; - struct ftrace_hash *notrace_hash; + struct ftrace_ops_hash hash; int ret; #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS @@ -1390,13 +1416,10 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs) return 0; #endif - filter_hash = rcu_dereference_raw_notrace(ops->func_hash->filter_hash); - notrace_hash = rcu_dereference_raw_notrace(ops->func_hash->notrace_hash); + hash.filter_hash = rcu_dereference_raw_notrace(ops->func_hash->filter_hash); + hash.notrace_hash = rcu_dereference_raw_notrace(ops->func_hash->notrace_hash); - if ((ftrace_hash_empty(filter_hash) || - ftrace_lookup_ip(filter_hash, ip)) && - (ftrace_hash_empty(notrace_hash) || - !ftrace_lookup_ip(notrace_hash, ip))) + if (hash_contains_ip(ip, &hash)) ret = 1; else ret = 0; @@ -1508,46 +1531,6 @@ static bool test_rec_ops_needs_regs(struct dyn_ftrace *rec) return keep_regs; } -static void ftrace_remove_tramp(struct ftrace_ops *ops, - struct dyn_ftrace *rec) -{ - /* If TRAMP is not set, no ops should have a trampoline for this */ - if (!(rec->flags & FTRACE_FL_TRAMP)) - return; - - rec->flags &= ~FTRACE_FL_TRAMP; - - if ((!ftrace_hash_empty(ops->func_hash->filter_hash) && - !ftrace_lookup_ip(ops->func_hash->filter_hash, rec->ip)) || - ftrace_lookup_ip(ops->func_hash->notrace_hash, rec->ip)) - return; - /* - * The tramp_hash entry will be removed at time - * of update. - */ - ops->nr_trampolines--; -} - -static void ftrace_clear_tramps(struct dyn_ftrace *rec, struct ftrace_ops *ops) -{ - struct ftrace_ops *op; - - /* If TRAMP is not set, no ops should have a trampoline for this */ - if (!(rec->flags & FTRACE_FL_TRAMP)) - return; - - do_for_each_ftrace_op(op, ftrace_ops_list) { - /* - * This function is called to clear other tramps - * not the one that is being updated. - */ - if (op == ops) - continue; - if (op->nr_trampolines) - ftrace_remove_tramp(op, rec); - } while_for_each_ftrace_op(op); -} - static void __ftrace_hash_rec_update(struct ftrace_ops *ops, int filter_hash, bool inc) @@ -1636,18 +1619,16 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, * function, and the ops has a trampoline registered * for it, then we can call it directly. */ - if (ftrace_rec_count(rec) == 1 && ops->trampoline) { + if (ftrace_rec_count(rec) == 1 && ops->trampoline) rec->flags |= FTRACE_FL_TRAMP; - ops->nr_trampolines++; - } else { + else /* * If we are adding another function callback * to this function, and the previous had a * custom trampoline in use, then we need to go * back to the default trampoline. */ - ftrace_clear_tramps(rec, ops); - } + rec->flags &= ~FTRACE_FL_TRAMP; /* * If any ops wants regs saved for this function @@ -1660,9 +1641,6 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, return; rec->flags--; - if (ops->trampoline && !ftrace_rec_count(rec)) - ftrace_remove_tramp(ops, rec); - /* * If the rec had REGS enabled and the ops that is * being removed had REGS set, then see if there is @@ -1677,6 +1655,17 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, } /* + * If the rec had TRAMP enabled, then it needs to + * be cleared. As TRAMP can only be enabled iff + * there is only a single ops attached to it. + * In otherwords, always disable it on decrementing. + * In the future, we may set it if rec count is + * decremented to one, and the ops that is left + * has a trampoline. + */ + rec->flags &= ~FTRACE_FL_TRAMP; + + /* * flags will be cleared in ftrace_check_record() * if rec count is zero. */ @@ -1895,21 +1884,72 @@ int ftrace_test_record(struct dyn_ftrace *rec, int enable) } static struct ftrace_ops * +ftrace_find_tramp_ops_any(struct dyn_ftrace *rec) +{ + struct ftrace_ops *op; + unsigned long ip = rec->ip; + + do_for_each_ftrace_op(op, ftrace_ops_list) { + + if (!op->trampoline) + continue; + + if (hash_contains_ip(ip, op->func_hash)) + return op; + } while_for_each_ftrace_op(op); + + return NULL; +} + +static struct ftrace_ops * ftrace_find_tramp_ops_curr(struct dyn_ftrace *rec) { struct ftrace_ops *op; + unsigned long ip = rec->ip; - /* Removed ops need to be tested first */ - if (removed_ops && removed_ops->tramp_hash) { - if (ftrace_lookup_ip(removed_ops->tramp_hash, rec->ip)) + /* + * Need to check removed ops first. + * If they are being removed, and this rec has a tramp, + * and this rec is in the ops list, then it would be the + * one with the tramp. + */ + if (removed_ops) { + if (hash_contains_ip(ip, &removed_ops->old_hash)) return removed_ops; } + /* + * Need to find the current trampoline for a rec. + * Now, a trampoline is only attached to a rec if there + * was a single 'ops' attached to it. But this can be called + * when we are adding another op to the rec or removing the + * current one. Thus, if the op is being added, we can + * ignore it because it hasn't attached itself to the rec + * yet. That means we just need to find the op that has a + * trampoline and is not beeing added. + */ do_for_each_ftrace_op(op, ftrace_ops_list) { - if (!op->tramp_hash) + + if (!op->trampoline) continue; - if (ftrace_lookup_ip(op->tramp_hash, rec->ip)) + /* + * If the ops is being added, it hasn't gotten to + * the point to be removed from this tree yet. + */ + if (op->flags & FTRACE_OPS_FL_ADDING) + continue; + + /* + * If the ops is not being added and has a trampoline, + * then it must be the one that we want! + */ + if (hash_contains_ip(ip, op->func_hash)) + return op; + + /* If the ops is being modified, it may be in the old hash. */ + if ((op->flags & FTRACE_OPS_FL_MODIFYING) && + hash_contains_ip(ip, &op->old_hash)) return op; } while_for_each_ftrace_op(op); @@ -1921,10 +1961,11 @@ static struct ftrace_ops * ftrace_find_tramp_ops_new(struct dyn_ftrace *rec) { struct ftrace_ops *op; + unsigned long ip = rec->ip; do_for_each_ftrace_op(op, ftrace_ops_list) { /* pass rec in as regs to have non-NULL val */ - if (ftrace_ops_test(op, rec->ip, rec)) + if (hash_contains_ip(ip, op->func_hash)) return op; } while_for_each_ftrace_op(op); @@ -2231,92 +2272,6 @@ void __weak arch_ftrace_update_code(int command) ftrace_run_stop_machine(command); } -static int ftrace_save_ops_tramp_hash(struct ftrace_ops *ops) -{ - struct ftrace_page *pg; - struct dyn_ftrace *rec; - int size, bits; - int ret; - - size = ops->nr_trampolines; - bits = 0; - /* - * Make the hash size about 1/2 the # found - */ - for (size /= 2; size; size >>= 1) - bits++; - - ops->tramp_hash = alloc_ftrace_hash(bits); - /* - * TODO: a failed allocation is going to screw up - * the accounting of what needs to be modified - * and not. For now, we kill ftrace if we fail - * to allocate here. But there are ways around this, - * but that will take a little more work. - */ - if (!ops->tramp_hash) - return -ENOMEM; - - do_for_each_ftrace_rec(pg, rec) { - if (ftrace_rec_count(rec) == 1 && - ftrace_ops_test(ops, rec->ip, rec)) { - - /* - * If another ops adds to a rec, the rec will - * lose its trampoline and never get it back - * until all ops are off of it. - */ - if (!(rec->flags & FTRACE_FL_TRAMP)) - continue; - - /* This record had better have a trampoline */ - if (FTRACE_WARN_ON(!(rec->flags & FTRACE_FL_TRAMP_EN))) - return -1; - - ret = add_hash_entry(ops->tramp_hash, rec->ip); - if (ret < 0) - return ret; - } - } while_for_each_ftrace_rec(); - - /* The number of recs in the hash must match nr_trampolines */ - if (FTRACE_WARN_ON(ops->tramp_hash->count != ops->nr_trampolines)) - pr_warn("count=%ld trampolines=%d\n", - ops->tramp_hash->count, - ops->nr_trampolines); - - return 0; -} - -static int ftrace_save_tramp_hashes(void) -{ - struct ftrace_ops *op; - int ret; - - /* - * Now that any trampoline is being used, we need to save the - * hashes for the ops that have them. This allows the mapping - * back from the record to the ops that has the trampoline to - * know what code is being replaced. Modifying code must always - * verify what it is changing. - */ - do_for_each_ftrace_op(op, ftrace_ops_list) { - - /* The tramp_hash is recreated each time. */ - free_ftrace_hash(op->tramp_hash); - op->tramp_hash = NULL; - - if (op->nr_trampolines) { - ret = ftrace_save_ops_tramp_hash(op); - if (ret) - return ret; - } - - } while_for_each_ftrace_op(op); - - return 0; -} - static void ftrace_run_update_code(int command) { int ret; @@ -2336,9 +2291,13 @@ static void ftrace_run_update_code(int command) ret = ftrace_arch_code_modify_post_process(); FTRACE_WARN_ON(ret); +} - ret = ftrace_save_tramp_hashes(); - FTRACE_WARN_ON(ret); +static void ftrace_run_modify_code(struct ftrace_ops *ops, int command) +{ + ops->flags |= FTRACE_OPS_FL_MODIFYING; + ftrace_run_update_code(command); + ops->flags &= ~FTRACE_OPS_FL_MODIFYING; } static ftrace_func_t saved_ftrace_func; @@ -2362,6 +2321,13 @@ static void ftrace_startup_enable(int command) ftrace_run_update_code(command); } +static void ftrace_startup_all(int command) +{ + update_all_ops = true; + ftrace_startup_enable(command); + update_all_ops = false; +} + static int ftrace_startup(struct ftrace_ops *ops, int command) { int ret; @@ -2376,12 +2342,22 @@ static int ftrace_startup(struct ftrace_ops *ops, int command) ftrace_start_up++; command |= FTRACE_UPDATE_CALLS; - ops->flags |= FTRACE_OPS_FL_ENABLED; + /* + * Note that ftrace probes uses this to start up + * and modify functions it will probe. But we still + * set the ADDING flag for modification, as probes + * do not have trampolines. If they add them in the + * future, then the probes will need to distinguish + * between adding and updating probes. + */ + ops->flags |= FTRACE_OPS_FL_ENABLED | FTRACE_OPS_FL_ADDING; ftrace_hash_rec_enable(ops, 1); ftrace_startup_enable(command); + ops->flags &= ~FTRACE_OPS_FL_ADDING; + return 0; } @@ -2431,11 +2407,35 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command) * If the ops uses a trampoline, then it needs to be * tested first on update. */ + ops->flags |= FTRACE_OPS_FL_REMOVING; removed_ops = ops; + /* The trampoline logic checks the old hashes */ + ops->old_hash.filter_hash = ops->func_hash->filter_hash; + ops->old_hash.notrace_hash = ops->func_hash->notrace_hash; + ftrace_run_update_code(command); + /* + * If there's no more ops registered with ftrace, run a + * sanity check to make sure all rec flags are cleared. + */ + if (ftrace_ops_list == &ftrace_list_end) { + struct ftrace_page *pg; + struct dyn_ftrace *rec; + + do_for_each_ftrace_rec(pg, rec) { + if (FTRACE_WARN_ON_ONCE(rec->flags)) + pr_warn(" %pS flags:%lx\n", + (void *)rec->ip, rec->flags); + } while_for_each_ftrace_rec(); + } + + ops->old_hash.filter_hash = NULL; + ops->old_hash.notrace_hash = NULL; + removed_ops = NULL; + ops->flags &= ~FTRACE_OPS_FL_REMOVING; /* * Dynamic ops may be freed, we must make sure that all @@ -2960,8 +2960,8 @@ static int t_show(struct seq_file *m, void *v) if (rec->flags & FTRACE_FL_TRAMP_EN) { struct ftrace_ops *ops; - ops = ftrace_find_tramp_ops_curr(rec); - if (ops && ops->trampoline) + ops = ftrace_find_tramp_ops_any(rec); + if (ops) seq_printf(m, "\ttramp: %pS", (void *)ops->trampoline); else @@ -3348,7 +3348,7 @@ static void __enable_ftrace_function_probe(void) if (ftrace_probe_registered) { /* still need to update the function call sites */ if (ftrace_enabled) - ftrace_run_update_code(FTRACE_UPDATE_CALLS); + ftrace_run_modify_code(&trace_probe_ops, FTRACE_UPDATE_CALLS); return; } @@ -3399,6 +3399,7 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, { struct ftrace_func_probe *entry; struct ftrace_hash **orig_hash = &trace_probe_ops.func_hash->filter_hash; + struct ftrace_hash *old_hash = *orig_hash; struct ftrace_hash *hash; struct ftrace_page *pg; struct dyn_ftrace *rec; @@ -3417,7 +3418,7 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, mutex_lock(&trace_probe_ops.func_hash->regex_lock); - hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash); + hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, old_hash); if (!hash) { count = -ENOMEM; goto out; @@ -3476,7 +3477,9 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, } while_for_each_ftrace_rec(); ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash); - if (ret < 0) + if (!ret) + free_ftrace_hash_rcu(old_hash); + else count = ret; __enable_ftrace_function_probe(); @@ -3503,6 +3506,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, struct ftrace_func_probe *entry; struct ftrace_func_probe *p; struct ftrace_hash **orig_hash = &trace_probe_ops.func_hash->filter_hash; + struct ftrace_hash *old_hash = *orig_hash; struct list_head free_list; struct ftrace_hash *hash; struct hlist_node *tmp; @@ -3510,6 +3514,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, int type = MATCH_FULL; int i, len = 0; char *search; + int ret; if (glob && (strcmp(glob, "*") == 0 || !strlen(glob))) glob = NULL; @@ -3568,8 +3573,11 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, * Remove after the disable is called. Otherwise, if the last * probe is removed, a null hash means *all enabled*. */ - ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash); + ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash); synchronize_sched(); + if (!ret) + free_ftrace_hash_rcu(old_hash); + list_for_each_entry_safe(entry, p, &free_list, free_list) { list_del(&entry->free_list); ftrace_free_entry(entry); @@ -3759,7 +3767,7 @@ ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove) static void ftrace_ops_update_code(struct ftrace_ops *ops) { if (ops->flags & FTRACE_OPS_FL_ENABLED && ftrace_enabled) - ftrace_run_update_code(FTRACE_UPDATE_CALLS); + ftrace_run_modify_code(ops, FTRACE_UPDATE_CALLS); } static int @@ -3767,6 +3775,7 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len, unsigned long ip, int remove, int reset, int enable) { struct ftrace_hash **orig_hash; + struct ftrace_hash *old_hash; struct ftrace_hash *hash; int ret; @@ -3801,10 +3810,12 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len, } mutex_lock(&ftrace_lock); + old_hash = *orig_hash; ret = ftrace_hash_move(ops, enable, orig_hash, hash); - if (!ret) + if (!ret) { ftrace_ops_update_code(ops); - + free_ftrace_hash_rcu(old_hash); + } mutex_unlock(&ftrace_lock); out_regex_unlock: @@ -4013,6 +4024,7 @@ int ftrace_regex_release(struct inode *inode, struct file *file) struct seq_file *m = (struct seq_file *)file->private_data; struct ftrace_iterator *iter; struct ftrace_hash **orig_hash; + struct ftrace_hash *old_hash; struct trace_parser *parser; int filter_hash; int ret; @@ -4042,11 +4054,13 @@ int ftrace_regex_release(struct inode *inode, struct file *file) orig_hash = &iter->ops->func_hash->notrace_hash; mutex_lock(&ftrace_lock); + old_hash = *orig_hash; ret = ftrace_hash_move(iter->ops, filter_hash, orig_hash, iter->hash); - if (!ret) + if (!ret) { ftrace_ops_update_code(iter->ops); - + free_ftrace_hash_rcu(old_hash); + } mutex_unlock(&ftrace_lock); } @@ -4678,6 +4692,7 @@ core_initcall(ftrace_nodyn_init); static inline int ftrace_init_dyn_debugfs(struct dentry *d_tracer) { return 0; } static inline void ftrace_startup_enable(int command) { } +static inline void ftrace_startup_all(int command) { } /* Keep as macros so we do not need to define the commands */ # define ftrace_startup(ops, command) \ ({ \ @@ -4827,6 +4842,56 @@ static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip) } #endif +/* + * If there's only one function registered but it does not support + * recursion, this function will be called by the mcount trampoline. + * This function will handle recursion protection. + */ +static void ftrace_ops_recurs_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs) +{ + int bit; + + bit = trace_test_and_set_recursion(TRACE_LIST_START, TRACE_LIST_MAX); + if (bit < 0) + return; + + op->func(ip, parent_ip, op, regs); + + trace_clear_recursion(bit); +} + +/** + * ftrace_ops_get_func - get the function a trampoline should call + * @ops: the ops to get the function for + * + * Normally the mcount trampoline will call the ops->func, but there + * are times that it should not. For example, if the ops does not + * have its own recursion protection, then it should call the + * ftrace_ops_recurs_func() instead. + * + * Returns the function that the trampoline should call for @ops. + */ +ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops) +{ + /* + * If this is a dynamic ops or we force list func, + * then it needs to call the list anyway. + */ + if (ops->flags & FTRACE_OPS_FL_DYNAMIC || FTRACE_FORCE_LIST_FUNC) + return ftrace_ops_list_func; + + /* + * If the func handles its own recursion, call it directly. + * Otherwise call the recursion protected function that + * will call the ftrace ops function. + */ + if (!(ops->flags & FTRACE_OPS_FL_RECURSION_SAFE)) + return ftrace_ops_recurs_func; + + return ops->func; +} + static void clear_ftrace_swapper(void) { struct task_struct *p; @@ -4927,7 +4992,8 @@ static int ftrace_pid_add(int p) set_ftrace_pid_task(pid); ftrace_update_pid_func(); - ftrace_startup_enable(0); + + ftrace_startup_all(0); mutex_unlock(&ftrace_lock); return 0; @@ -4956,7 +5022,7 @@ static void ftrace_pid_reset(void) } ftrace_update_pid_func(); - ftrace_startup_enable(0); + ftrace_startup_all(0); mutex_unlock(&ftrace_lock); } diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index b38fb2b9e237..2d75c94ae87d 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3359,7 +3359,7 @@ static void rb_iter_reset(struct ring_buffer_iter *iter) iter->head = cpu_buffer->reader_page->read; iter->cache_reader_page = iter->head_page; - iter->cache_read = iter->head; + iter->cache_read = cpu_buffer->read; if (iter->head) iter->read_stamp = cpu_buffer->read_stamp; diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c index 0434ff1b808e..3f9e328c30b5 100644 --- a/kernel/trace/ring_buffer_benchmark.c +++ b/kernel/trace/ring_buffer_benchmark.c @@ -205,7 +205,6 @@ static void ring_buffer_consumer(void) break; schedule(); - __set_current_state(TASK_RUNNING); } reader_finish = 0; complete(&read_done); @@ -379,7 +378,6 @@ static int ring_buffer_consumer_thread(void *arg) break; schedule(); - __set_current_state(TASK_RUNNING); } __set_current_state(TASK_RUNNING); @@ -407,7 +405,6 @@ static int ring_buffer_producer_thread(void *arg) trace_printk("Sleeping for 10 secs\n"); set_current_state(TASK_INTERRUPTIBLE); schedule_timeout(HZ * SLEEP_TIME); - __set_current_state(TASK_RUNNING); } if (kill_test) diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index ef06ce7e9cf8..0cc51edde3a8 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2513,8 +2513,11 @@ static __init int event_test_thread(void *unused) kfree(test_malloc); set_current_state(TASK_INTERRUPTIBLE); - while (!kthread_should_stop()) + while (!kthread_should_stop()) { schedule(); + set_current_state(TASK_INTERRUPTIBLE); + } + __set_current_state(TASK_RUNNING); return 0; } diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 5ef60499dc8e..b0f86ea77881 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -382,6 +382,8 @@ static int trace_selftest_startup_dynamic_tracing(struct tracer *trace, /* check the trace buffer */ ret = trace_test_buffer(&tr->trace_buffer, &count); + + ftrace_enabled = 1; tracing_start(); /* we should only have one item */ @@ -679,6 +681,8 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr) /* check the trace buffer */ ret = trace_test_buffer(&tr->trace_buffer, &count); + + ftrace_enabled = 1; trace->reset(tr); tracing_start(); @@ -1025,6 +1029,12 @@ trace_selftest_startup_nop(struct tracer *trace, struct trace_array *tr) #endif #ifdef CONFIG_SCHED_TRACER + +struct wakeup_test_data { + struct completion is_ready; + int go; +}; + static int trace_wakeup_test_thread(void *data) { /* Make this a -deadline thread */ @@ -1034,51 +1044,56 @@ static int trace_wakeup_test_thread(void *data) .sched_deadline = 10000000ULL, .sched_period = 10000000ULL }; - struct completion *x = data; + struct wakeup_test_data *x = data; sched_setattr(current, &attr); /* Make it know we have a new prio */ - complete(x); + complete(&x->is_ready); /* now go to sleep and let the test wake us up */ set_current_state(TASK_INTERRUPTIBLE); - schedule(); + while (!x->go) { + schedule(); + set_current_state(TASK_INTERRUPTIBLE); + } - complete(x); + complete(&x->is_ready); + + set_current_state(TASK_INTERRUPTIBLE); /* we are awake, now wait to disappear */ while (!kthread_should_stop()) { - /* - * This will likely be the system top priority - * task, do short sleeps to let others run. - */ - msleep(100); + schedule(); + set_current_state(TASK_INTERRUPTIBLE); } + __set_current_state(TASK_RUNNING); + return 0; } - int trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr) { unsigned long save_max = tr->max_latency; struct task_struct *p; - struct completion is_ready; + struct wakeup_test_data data; unsigned long count; int ret; - init_completion(&is_ready); + memset(&data, 0, sizeof(data)); + + init_completion(&data.is_ready); /* create a -deadline thread */ - p = kthread_run(trace_wakeup_test_thread, &is_ready, "ftrace-test"); + p = kthread_run(trace_wakeup_test_thread, &data, "ftrace-test"); if (IS_ERR(p)) { printk(KERN_CONT "Failed to create ftrace wakeup test thread "); return -1; } /* make sure the thread is running at -deadline policy */ - wait_for_completion(&is_ready); + wait_for_completion(&data.is_ready); /* start the tracing */ ret = tracer_init(trace, tr); @@ -1099,18 +1114,20 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr) msleep(100); } - init_completion(&is_ready); + init_completion(&data.is_ready); + + data.go = 1; + /* memory barrier is in the wake_up_process() */ wake_up_process(p); /* Wait for the task to wake up */ - wait_for_completion(&is_ready); + wait_for_completion(&data.is_ready); /* stop the tracing. */ tracing_stop(); /* check both trace buffers */ ret = trace_test_buffer(&tr->trace_buffer, NULL); - printk("ret = %d\n", ret); if (!ret) ret = trace_test_buffer(&tr->max_buffer, &count); diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 8a4e5cb66a4c..16eddb308c33 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -13,7 +13,6 @@ #include <linux/sysctl.h> #include <linux/init.h> #include <linux/fs.h> -#include <linux/magic.h> #include <asm/setup.h> @@ -171,8 +170,7 @@ check_stack(unsigned long ip, unsigned long *stack) i++; } - if ((current != &init_task && - *(end_of_stack(current)) != STACK_END_MAGIC)) { + if (task_stack_end_corrupted(current)) { print_max_stack(); BUG(); } diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 759d5e004517..4dc8b79c5f75 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -425,7 +425,7 @@ static void unreg_event_syscall_enter(struct ftrace_event_file *file, return; mutex_lock(&syscall_trace_lock); tr->sys_refcount_enter--; - rcu_assign_pointer(tr->enter_syscall_files[num], NULL); + RCU_INIT_POINTER(tr->enter_syscall_files[num], NULL); if (!tr->sys_refcount_enter) unregister_trace_sys_enter(ftrace_syscall_enter, tr); mutex_unlock(&syscall_trace_lock); @@ -463,7 +463,7 @@ static void unreg_event_syscall_exit(struct ftrace_event_file *file, return; mutex_lock(&syscall_trace_lock); tr->sys_refcount_exit--; - rcu_assign_pointer(tr->exit_syscall_files[num], NULL); + RCU_INIT_POINTER(tr->exit_syscall_files[num], NULL); if (!tr->sys_refcount_exit) unregister_trace_sys_exit(ftrace_syscall_exit, tr); mutex_unlock(&syscall_trace_lock); diff --git a/kernel/watchdog.c b/kernel/watchdog.c index a8d6914030fe..ff7fd80bef99 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -15,11 +15,6 @@ #include <linux/cpu.h> #include <linux/nmi.h> #include <linux/init.h> -#include <linux/delay.h> -#include <linux/freezer.h> -#include <linux/kthread.h> -#include <linux/lockdep.h> -#include <linux/notifier.h> #include <linux/module.h> #include <linux/sysctl.h> #include <linux/smpboot.h> @@ -47,6 +42,7 @@ static DEFINE_PER_CPU(bool, softlockup_touch_sync); static DEFINE_PER_CPU(bool, soft_watchdog_warn); static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts); static DEFINE_PER_CPU(unsigned long, soft_lockup_hrtimer_cnt); +static DEFINE_PER_CPU(struct task_struct *, softlockup_task_ptr_saved); #ifdef CONFIG_HARDLOCKUP_DETECTOR static DEFINE_PER_CPU(bool, hard_watchdog_warn); static DEFINE_PER_CPU(bool, watchdog_nmi_touch); @@ -333,8 +329,22 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) return HRTIMER_RESTART; /* only warn once */ - if (__this_cpu_read(soft_watchdog_warn) == true) + if (__this_cpu_read(soft_watchdog_warn) == true) { + /* + * When multiple processes are causing softlockups the + * softlockup detector only warns on the first one + * because the code relies on a full quiet cycle to + * re-arm. The second process prevents the quiet cycle + * and never gets reported. Use task pointers to detect + * this. + */ + if (__this_cpu_read(softlockup_task_ptr_saved) != + current) { + __this_cpu_write(soft_watchdog_warn, false); + __touch_watchdog(); + } return HRTIMER_RESTART; + } if (softlockup_all_cpu_backtrace) { /* Prevent multiple soft-lockup reports if one cpu is already @@ -350,6 +360,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n", smp_processor_id(), duration, current->comm, task_pid_nr(current)); + __this_cpu_write(softlockup_task_ptr_saved, current); print_modules(); print_irqtrace_events(current); if (regs) @@ -514,7 +525,10 @@ static void watchdog_nmi_disable(unsigned int cpu) /* should be in cleanup, but blocks oprofile */ perf_event_release_kernel(event); } - return; + if (cpu == 0) { + /* watchdog_nmi_enable() expects this to be zero initially. */ + cpu0_err = 0; + } } #else static int watchdog_nmi_enable(unsigned int cpu) { return 0; } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 5dbe22aa3efd..09b685daee3d 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2043,9 +2043,10 @@ __acquires(&pool->lock) * kernels, where a requeueing work item waiting for something to * happen could deadlock with stop_machine as such work item could * indefinitely requeue itself while all other CPUs are trapped in - * stop_machine. + * stop_machine. At the same time, report a quiescent RCU state so + * the same condition doesn't freeze RCU. */ - cond_resched(); + cond_resched_rcu_qs(); spin_lock_irq(&pool->lock); |