diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/bpf/arraymap.c | 29 | ||||
-rw-r--r-- | kernel/bpf/core.c | 47 | ||||
-rw-r--r-- | kernel/bpf/lpm_trie.c | 1 | ||||
-rw-r--r-- | kernel/bpf/stackmap.c | 1 | ||||
-rw-r--r-- | kernel/bpf/syscall.c | 437 | ||||
-rw-r--r-- | kernel/bpf/verifier.c | 93 | ||||
-rw-r--r-- | kernel/cgroup/cgroup.c | 5 | ||||
-rw-r--r-- | kernel/cgroup/cpuset.c | 4 | ||||
-rw-r--r-- | kernel/events/core.c | 47 | ||||
-rw-r--r-- | kernel/fork.c | 25 | ||||
-rw-r--r-- | kernel/irq/chip.c | 2 | ||||
-rw-r--r-- | kernel/kprobes.c | 10 | ||||
-rw-r--r-- | kernel/livepatch/Kconfig | 1 | ||||
-rw-r--r-- | kernel/locking/rtmutex.c | 24 | ||||
-rw-r--r-- | kernel/pid_namespace.c | 2 | ||||
-rw-r--r-- | kernel/power/snapshot.c | 2 | ||||
-rw-r--r-- | kernel/ptrace.c | 20 | ||||
-rw-r--r-- | kernel/sched/core.c | 25 | ||||
-rw-r--r-- | kernel/sched/cpufreq_schedutil.c | 7 | ||||
-rw-r--r-- | kernel/sched/idle.c | 2 | ||||
-rw-r--r-- | kernel/sched/sched.h | 2 | ||||
-rw-r--r-- | kernel/time/posix-cpu-timers.c | 24 | ||||
-rw-r--r-- | kernel/trace/blktrace.c | 4 | ||||
-rw-r--r-- | kernel/trace/bpf_trace.c | 22 | ||||
-rw-r--r-- | kernel/trace/ftrace.c | 14 | ||||
-rw-r--r-- | kernel/trace/trace.c | 34 | ||||
-rw-r--r-- | kernel/trace/trace.h | 5 | ||||
-rw-r--r-- | kernel/trace/trace_kprobe.c | 5 |
28 files changed, 721 insertions, 173 deletions
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 5e00b2333c26..ecb43542246e 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -86,6 +86,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) array->map.key_size = attr->key_size; array->map.value_size = attr->value_size; array->map.max_entries = attr->max_entries; + array->map.map_flags = attr->map_flags; array->elem_size = elem_size; if (!percpu) @@ -451,38 +452,24 @@ static void bpf_event_entry_free_rcu(struct bpf_event_entry *ee) static void *perf_event_fd_array_get_ptr(struct bpf_map *map, struct file *map_file, int fd) { - const struct perf_event_attr *attr; struct bpf_event_entry *ee; struct perf_event *event; struct file *perf_file; + u64 value; perf_file = perf_event_get(fd); if (IS_ERR(perf_file)) return perf_file; + ee = ERR_PTR(-EOPNOTSUPP); event = perf_file->private_data; - ee = ERR_PTR(-EINVAL); - - attr = perf_event_attrs(event); - if (IS_ERR(attr) || attr->inherit) + if (perf_event_read_local(event, &value) == -EOPNOTSUPP) goto err_out; - switch (attr->type) { - case PERF_TYPE_SOFTWARE: - if (attr->config != PERF_COUNT_SW_BPF_OUTPUT) - goto err_out; - /* fall-through */ - case PERF_TYPE_RAW: - case PERF_TYPE_HARDWARE: - ee = bpf_event_entry_gen(perf_file, map_file); - if (ee) - return ee; - ee = ERR_PTR(-ENOMEM); - /* fall-through */ - default: - break; - } - + ee = bpf_event_entry_gen(perf_file, map_file); + if (ee) + return ee; + ee = ERR_PTR(-ENOMEM); err_out: fput(perf_file); return ee; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index dedf367f59bb..774069ca18a7 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -763,10 +763,10 @@ EXPORT_SYMBOL_GPL(__bpf_call_base); * * Decode and execute eBPF instructions. */ -static unsigned int __bpf_prog_run(void *ctx, const struct bpf_insn *insn) +static unsigned int ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, + u64 *stack) { - u64 stack[MAX_BPF_STACK / sizeof(u64)]; - u64 regs[MAX_BPF_REG], tmp; + u64 tmp; static const void *jumptable[256] = { [0 ... 255] = &&default_label, /* Now overwrite non-defaults ... */ @@ -824,7 +824,7 @@ static unsigned int __bpf_prog_run(void *ctx, const struct bpf_insn *insn) [BPF_ALU64 | BPF_NEG] = &&ALU64_NEG, /* Call instruction */ [BPF_JMP | BPF_CALL] = &&JMP_CALL, - [BPF_JMP | BPF_CALL | BPF_X] = &&JMP_TAIL_CALL, + [BPF_JMP | BPF_TAIL_CALL] = &&JMP_TAIL_CALL, /* Jumps */ [BPF_JMP | BPF_JA] = &&JMP_JA, [BPF_JMP | BPF_JEQ | BPF_X] = &&JMP_JEQ_X, @@ -874,9 +874,6 @@ static unsigned int __bpf_prog_run(void *ctx, const struct bpf_insn *insn) #define CONT ({ insn++; goto select_insn; }) #define CONT_JMP ({ insn++; goto select_insn; }) - FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; - ARG1 = (u64) (unsigned long) ctx; - select_insn: goto *jumptable[insn->code]; @@ -1219,7 +1216,39 @@ load_byte: WARN_RATELIMIT(1, "unknown opcode %02x\n", insn->code); return 0; } -STACK_FRAME_NON_STANDARD(__bpf_prog_run); /* jump table */ +STACK_FRAME_NON_STANDARD(___bpf_prog_run); /* jump table */ + +#define PROG_NAME(stack_size) __bpf_prog_run##stack_size +#define DEFINE_BPF_PROG_RUN(stack_size) \ +static unsigned int PROG_NAME(stack_size)(const void *ctx, const struct bpf_insn *insn) \ +{ \ + u64 stack[stack_size / sizeof(u64)]; \ + u64 regs[MAX_BPF_REG]; \ +\ + FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \ + ARG1 = (u64) (unsigned long) ctx; \ + return ___bpf_prog_run(regs, insn, stack); \ +} + +#define EVAL1(FN, X) FN(X) +#define EVAL2(FN, X, Y...) FN(X) EVAL1(FN, Y) +#define EVAL3(FN, X, Y...) FN(X) EVAL2(FN, Y) +#define EVAL4(FN, X, Y...) FN(X) EVAL3(FN, Y) +#define EVAL5(FN, X, Y...) FN(X) EVAL4(FN, Y) +#define EVAL6(FN, X, Y...) FN(X) EVAL5(FN, Y) + +EVAL6(DEFINE_BPF_PROG_RUN, 32, 64, 96, 128, 160, 192); +EVAL6(DEFINE_BPF_PROG_RUN, 224, 256, 288, 320, 352, 384); +EVAL4(DEFINE_BPF_PROG_RUN, 416, 448, 480, 512); + +#define PROG_NAME_LIST(stack_size) PROG_NAME(stack_size), + +static unsigned int (*interpreters[])(const void *ctx, + const struct bpf_insn *insn) = { +EVAL6(PROG_NAME_LIST, 32, 64, 96, 128, 160, 192) +EVAL6(PROG_NAME_LIST, 224, 256, 288, 320, 352, 384) +EVAL4(PROG_NAME_LIST, 416, 448, 480, 512) +}; bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp) @@ -1268,7 +1297,7 @@ static int bpf_check_tail_call(const struct bpf_prog *fp) */ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) { - fp->bpf_func = (void *) __bpf_prog_run; + fp->bpf_func = interpreters[round_down(fp->aux->stack_depth, 32) / 32]; /* eBPF JITs can rewrite the program in case constant * blinding is active. However, in case of error during diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 39cfafd895b8..b09185f0f17d 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -432,6 +432,7 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr) trie->map.key_size = attr->key_size; trie->map.value_size = attr->value_size; trie->map.max_entries = attr->max_entries; + trie->map.map_flags = attr->map_flags; trie->data_size = attr->key_size - offsetof(struct bpf_lpm_trie_key, data); trie->max_prefixlen = trie->data_size * 8; diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 4dfd6f2ec2f9..31147d730abf 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -88,6 +88,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) smap->map.key_size = attr->key_size; smap->map.value_size = value_size; smap->map.max_entries = attr->max_entries; + smap->map.map_flags = attr->map_flags; smap->n_buckets = n_buckets; smap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 265a0d854e33..8942c820d620 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -22,8 +22,13 @@ #include <linux/filter.h> #include <linux/version.h> #include <linux/kernel.h> +#include <linux/idr.h> DEFINE_PER_CPU(int, bpf_prog_active); +static DEFINE_IDR(prog_idr); +static DEFINE_SPINLOCK(prog_idr_lock); +static DEFINE_IDR(map_idr); +static DEFINE_SPINLOCK(map_idr_lock); int sysctl_unprivileged_bpf_disabled __read_mostly; @@ -114,6 +119,37 @@ static void bpf_map_uncharge_memlock(struct bpf_map *map) free_uid(user); } +static int bpf_map_alloc_id(struct bpf_map *map) +{ + int id; + + spin_lock_bh(&map_idr_lock); + id = idr_alloc_cyclic(&map_idr, map, 1, INT_MAX, GFP_ATOMIC); + if (id > 0) + map->id = id; + spin_unlock_bh(&map_idr_lock); + + if (WARN_ON_ONCE(!id)) + return -ENOSPC; + + return id > 0 ? 0 : id; +} + +static void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock) +{ + if (do_idr_lock) + spin_lock_bh(&map_idr_lock); + else + __acquire(&map_idr_lock); + + idr_remove(&map_idr, map->id); + + if (do_idr_lock) + spin_unlock_bh(&map_idr_lock); + else + __release(&map_idr_lock); +} + /* called from workqueue */ static void bpf_map_free_deferred(struct work_struct *work) { @@ -135,14 +171,21 @@ static void bpf_map_put_uref(struct bpf_map *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) +static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock) { if (atomic_dec_and_test(&map->refcnt)) { + /* bpf_map_free_id() must be called first */ + bpf_map_free_id(map, do_idr_lock); INIT_WORK(&map->work, bpf_map_free_deferred); schedule_work(&map->work); } } +void bpf_map_put(struct bpf_map *map) +{ + __bpf_map_put(map, true); +} + void bpf_map_put_with_uref(struct bpf_map *map) { bpf_map_put_uref(map); @@ -236,11 +279,22 @@ static int map_create(union bpf_attr *attr) if (err) goto free_map_nouncharge; - err = bpf_map_new_fd(map); - if (err < 0) - /* failed to allocate fd */ + err = bpf_map_alloc_id(map); + if (err) goto free_map; + err = bpf_map_new_fd(map); + if (err < 0) { + /* failed to allocate fd. + * bpf_map_put() is needed because the above + * bpf_map_alloc_id() has published the map + * to the userspace and the userspace may + * have refcnt-ed it through BPF_MAP_GET_FD_BY_ID. + */ + bpf_map_put(map); + return err; + } + trace_bpf_map_create(map, err); return err; @@ -295,6 +349,28 @@ struct bpf_map *bpf_map_get_with_uref(u32 ufd) return map; } +/* map_idr_lock should have been held */ +static struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map, + bool uref) +{ + int refold; + + refold = __atomic_add_unless(&map->refcnt, 1, 0); + + if (refold >= BPF_MAX_REFCNT) { + __bpf_map_put(map, false); + return ERR_PTR(-EBUSY); + } + + if (!refold) + return ERR_PTR(-ENOENT); + + if (uref) + atomic_inc(&map->usercnt); + + return map; +} + int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value) { return -ENOTSUPP; @@ -650,6 +726,42 @@ static void bpf_prog_uncharge_memlock(struct bpf_prog *prog) free_uid(user); } +static int bpf_prog_alloc_id(struct bpf_prog *prog) +{ + int id; + + spin_lock_bh(&prog_idr_lock); + id = idr_alloc_cyclic(&prog_idr, prog, 1, INT_MAX, GFP_ATOMIC); + if (id > 0) + prog->aux->id = id; + spin_unlock_bh(&prog_idr_lock); + + /* id is in [1, INT_MAX) */ + if (WARN_ON_ONCE(!id)) + return -ENOSPC; + + return id > 0 ? 0 : id; +} + +static void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock) +{ + /* cBPF to eBPF migrations are currently not in the idr store. */ + if (!prog->aux->id) + return; + + if (do_idr_lock) + spin_lock_bh(&prog_idr_lock); + else + __acquire(&prog_idr_lock); + + idr_remove(&prog_idr, prog->aux->id); + + if (do_idr_lock) + spin_unlock_bh(&prog_idr_lock); + else + __release(&prog_idr_lock); +} + static void __bpf_prog_put_rcu(struct rcu_head *rcu) { struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu); @@ -659,14 +771,21 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu) bpf_prog_free(aux->prog); } -void bpf_prog_put(struct bpf_prog *prog) +static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock) { if (atomic_dec_and_test(&prog->aux->refcnt)) { trace_bpf_prog_put_rcu(prog); + /* bpf_prog_free_id() must be called first */ + bpf_prog_free_id(prog, do_idr_lock); bpf_prog_kallsyms_del(prog); call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); } } + +void bpf_prog_put(struct bpf_prog *prog) +{ + __bpf_prog_put(prog, true); +} EXPORT_SYMBOL_GPL(bpf_prog_put); static int bpf_prog_release(struct inode *inode, struct file *filp) @@ -748,6 +867,24 @@ struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog) } EXPORT_SYMBOL_GPL(bpf_prog_inc); +/* prog_idr_lock should have been held */ +static struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog) +{ + int refold; + + refold = __atomic_add_unless(&prog->aux->refcnt, 1, 0); + + if (refold >= BPF_MAX_REFCNT) { + __bpf_prog_put(prog, false); + return ERR_PTR(-EBUSY); + } + + if (!refold) + return ERR_PTR(-ENOENT); + + return prog; +} + static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *type) { struct fd f = fdget(ufd); @@ -815,7 +952,9 @@ static int bpf_prog_load(union bpf_attr *attr) attr->kern_version != LINUX_VERSION_CODE) return -EINVAL; - if (type != BPF_PROG_TYPE_SOCKET_FILTER && !capable(CAP_SYS_ADMIN)) + if (type != BPF_PROG_TYPE_SOCKET_FILTER && + type != BPF_PROG_TYPE_CGROUP_SKB && + !capable(CAP_SYS_ADMIN)) return -EPERM; /* plain bpf_prog allocation */ @@ -855,11 +994,22 @@ static int bpf_prog_load(union bpf_attr *attr) if (err < 0) goto free_used_maps; - err = bpf_prog_new_fd(prog); - if (err < 0) - /* failed to allocate fd */ + err = bpf_prog_alloc_id(prog); + if (err) goto free_used_maps; + err = bpf_prog_new_fd(prog); + if (err < 0) { + /* failed to allocate fd. + * bpf_prog_put() is needed because the above + * bpf_prog_alloc_id() has published the prog + * to the userspace and the userspace may + * have refcnt-ed it through BPF_PROG_GET_FD_BY_ID. + */ + bpf_prog_put(prog); + return err; + } + bpf_prog_kallsyms_add(prog); trace_bpf_prog_load(prog, err); return err; @@ -997,6 +1147,237 @@ static int bpf_prog_test_run(const union bpf_attr *attr, return ret; } +#define BPF_OBJ_GET_NEXT_ID_LAST_FIELD next_id + +static int bpf_obj_get_next_id(const union bpf_attr *attr, + union bpf_attr __user *uattr, + struct idr *idr, + spinlock_t *lock) +{ + u32 next_id = attr->start_id; + int err = 0; + + if (CHECK_ATTR(BPF_OBJ_GET_NEXT_ID) || next_id >= INT_MAX) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + next_id++; + spin_lock_bh(lock); + if (!idr_get_next(idr, &next_id)) + err = -ENOENT; + spin_unlock_bh(lock); + + if (!err) + err = put_user(next_id, &uattr->next_id); + + return err; +} + +#define BPF_PROG_GET_FD_BY_ID_LAST_FIELD prog_id + +static int bpf_prog_get_fd_by_id(const union bpf_attr *attr) +{ + struct bpf_prog *prog; + u32 id = attr->prog_id; + int fd; + + if (CHECK_ATTR(BPF_PROG_GET_FD_BY_ID)) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + spin_lock_bh(&prog_idr_lock); + prog = idr_find(&prog_idr, id); + if (prog) + prog = bpf_prog_inc_not_zero(prog); + else + prog = ERR_PTR(-ENOENT); + spin_unlock_bh(&prog_idr_lock); + + if (IS_ERR(prog)) + return PTR_ERR(prog); + + fd = bpf_prog_new_fd(prog); + if (fd < 0) + bpf_prog_put(prog); + + return fd; +} + +#define BPF_MAP_GET_FD_BY_ID_LAST_FIELD map_id + +static int bpf_map_get_fd_by_id(const union bpf_attr *attr) +{ + struct bpf_map *map; + u32 id = attr->map_id; + int fd; + + if (CHECK_ATTR(BPF_MAP_GET_FD_BY_ID)) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + spin_lock_bh(&map_idr_lock); + map = idr_find(&map_idr, id); + if (map) + map = bpf_map_inc_not_zero(map, true); + else + map = ERR_PTR(-ENOENT); + spin_unlock_bh(&map_idr_lock); + + if (IS_ERR(map)) + return PTR_ERR(map); + + fd = bpf_map_new_fd(map); + if (fd < 0) + bpf_map_put(map); + + return fd; +} + +static int check_uarg_tail_zero(void __user *uaddr, + size_t expected_size, + size_t actual_size) +{ + unsigned char __user *addr; + unsigned char __user *end; + unsigned char val; + int err; + + if (actual_size <= expected_size) + return 0; + + addr = uaddr + expected_size; + end = uaddr + actual_size; + + for (; addr < end; addr++) { + err = get_user(val, addr); + if (err) + return err; + if (val) + return -E2BIG; + } + + return 0; +} + +static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + struct bpf_prog_info __user *uinfo = u64_to_user_ptr(attr->info.info); + struct bpf_prog_info info = {}; + u32 info_len = attr->info.info_len; + char __user *uinsns; + u32 ulen; + int err; + + err = check_uarg_tail_zero(uinfo, sizeof(info), info_len); + if (err) + return err; + info_len = min_t(u32, sizeof(info), info_len); + + if (copy_from_user(&info, uinfo, info_len)) + return err; + + info.type = prog->type; + info.id = prog->aux->id; + + memcpy(info.tag, prog->tag, sizeof(prog->tag)); + + if (!capable(CAP_SYS_ADMIN)) { + info.jited_prog_len = 0; + info.xlated_prog_len = 0; + goto done; + } + + ulen = info.jited_prog_len; + info.jited_prog_len = prog->jited_len; + if (info.jited_prog_len && ulen) { + uinsns = u64_to_user_ptr(info.jited_prog_insns); + ulen = min_t(u32, info.jited_prog_len, ulen); + if (copy_to_user(uinsns, prog->bpf_func, ulen)) + return -EFAULT; + } + + ulen = info.xlated_prog_len; + info.xlated_prog_len = bpf_prog_size(prog->len); + if (info.xlated_prog_len && ulen) { + uinsns = u64_to_user_ptr(info.xlated_prog_insns); + ulen = min_t(u32, info.xlated_prog_len, ulen); + if (copy_to_user(uinsns, prog->insnsi, ulen)) + return -EFAULT; + } + +done: + if (copy_to_user(uinfo, &info, info_len) || + put_user(info_len, &uattr->info.info_len)) + return -EFAULT; + + return 0; +} + +static int bpf_map_get_info_by_fd(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + struct bpf_map_info __user *uinfo = u64_to_user_ptr(attr->info.info); + struct bpf_map_info info = {}; + u32 info_len = attr->info.info_len; + int err; + + err = check_uarg_tail_zero(uinfo, sizeof(info), info_len); + if (err) + return err; + info_len = min_t(u32, sizeof(info), info_len); + + info.type = map->map_type; + info.id = map->id; + info.key_size = map->key_size; + info.value_size = map->value_size; + info.max_entries = map->max_entries; + info.map_flags = map->map_flags; + + if (copy_to_user(uinfo, &info, info_len) || + put_user(info_len, &uattr->info.info_len)) + return -EFAULT; + + return 0; +} + +#define BPF_OBJ_GET_INFO_BY_FD_LAST_FIELD info.info + +static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + int ufd = attr->info.bpf_fd; + struct fd f; + int err; + + if (CHECK_ATTR(BPF_OBJ_GET_INFO_BY_FD)) + return -EINVAL; + + f = fdget(ufd); + if (!f.file) + return -EBADFD; + + if (f.file->f_op == &bpf_prog_fops) + err = bpf_prog_get_info_by_fd(f.file->private_data, attr, + uattr); + else if (f.file->f_op == &bpf_map_fops) + err = bpf_map_get_info_by_fd(f.file->private_data, attr, + uattr); + else + err = -EINVAL; + + fdput(f); + return err; +} + SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) { union bpf_attr attr = {}; @@ -1016,23 +1397,10 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz * 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); - } + err = check_uarg_tail_zero(uattr, sizeof(attr), size); + if (err) + return err; + size = min_t(u32, size, sizeof(attr)); /* copy attributes from user space, may be less than sizeof(bpf_attr) */ if (copy_from_user(&attr, uattr, size) != 0) @@ -1074,6 +1442,23 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_PROG_TEST_RUN: err = bpf_prog_test_run(&attr, uattr); break; + case BPF_PROG_GET_NEXT_ID: + err = bpf_obj_get_next_id(&attr, uattr, + &prog_idr, &prog_idr_lock); + break; + case BPF_MAP_GET_NEXT_ID: + err = bpf_obj_get_next_id(&attr, uattr, + &map_idr, &map_idr_lock); + break; + case BPF_PROG_GET_FD_BY_ID: + err = bpf_prog_get_fd_by_id(&attr); + break; + case BPF_MAP_GET_FD_BY_ID: + err = bpf_map_get_fd_by_id(&attr); + break; + case BPF_OBJ_GET_INFO_BY_FD: + err = bpf_obj_get_info_by_fd(&attr, uattr); + break; default: err = -EINVAL; break; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 39f2dcbc4cbc..14ccb0759fa4 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -140,7 +140,7 @@ struct bpf_verifier_stack_elem { struct bpf_verifier_stack_elem *next; }; -#define BPF_COMPLEXITY_LIMIT_INSNS 65536 +#define BPF_COMPLEXITY_LIMIT_INSNS 98304 #define BPF_COMPLEXITY_LIMIT_STACK 1024 #define BPF_MAP_PTR_POISON ((void *)0xeB9F + POISON_POINTER_DELTA) @@ -463,19 +463,22 @@ 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 mark_reg_not_init(struct bpf_reg_state *regs, u32 regno) +{ + BUG_ON(regno >= MAX_BPF_REG); + + memset(®s[regno], 0, sizeof(regs[regno])); + regs[regno].type = NOT_INIT; + regs[regno].min_value = BPF_REGISTER_MIN_RANGE; + regs[regno].max_value = BPF_REGISTER_MAX_RANGE; +} + static void init_reg_state(struct bpf_reg_state *regs) { int i; - for (i = 0; i < MAX_BPF_REG; i++) { - regs[i].type = NOT_INIT; - regs[i].imm = 0; - regs[i].min_value = BPF_REGISTER_MIN_RANGE; - regs[i].max_value = BPF_REGISTER_MAX_RANGE; - regs[i].min_align = 0; - regs[i].aux_off = 0; - regs[i].aux_off_align = 0; - } + for (i = 0; i < MAX_BPF_REG; i++) + mark_reg_not_init(regs, i); /* frame pointer */ regs[BPF_REG_FP].type = FRAME_PTR; @@ -808,11 +811,15 @@ static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg, reg_off += reg->aux_off; } - /* skb->data is NET_IP_ALIGN-ed, but for strict alignment checking - * we force this to 2 which is universally what architectures use - * when they don't set CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS. + /* For platforms that do not have a Kconfig enabling + * CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS the value of + * NET_IP_ALIGN is universally set to '2'. And on platforms + * that do set CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS, we get + * to this code only in strict mode where we want to emulate + * the NET_IP_ALIGN==2 checking. Therefore use an + * unconditional IP align value of '2'. */ - ip_align = strict ? 2 : NET_IP_ALIGN; + ip_align = 2; if ((ip_align + reg_off + off) % size != 0) { verbose("misaligned packet access off %d+%d+%d size %d\n", ip_align, reg_off, off, size); @@ -839,9 +846,6 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, { bool strict = env->strict_alignment; - if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) - strict = true; - switch (reg->type) { case PTR_TO_PACKET: return check_pkt_ptr_alignment(reg, off, size, strict); @@ -922,6 +926,10 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off, verbose("invalid stack off=%d size=%d\n", off, size); return -EACCES; } + + if (env->prog->aux->stack_depth < -off) + env->prog->aux->stack_depth = -off; + if (t == BPF_WRITE) { if (!env->allow_ptr_leaks && state->stack_slot_type[MAX_BPF_STACK + off] == STACK_SPILL && @@ -1028,6 +1036,9 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, return -EACCES; } + if (env->prog->aux->stack_depth < -off) + env->prog->aux->stack_depth = -off; + if (meta && meta->raw_mode) { meta->access_size = access_size; meta->regno = regno; @@ -1345,7 +1356,6 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) struct bpf_verifier_state *state = &env->cur_state; const struct bpf_func_proto *fn = NULL; struct bpf_reg_state *regs = state->regs; - struct bpf_reg_state *reg; struct bpf_call_arg_meta meta; bool changes_data; int i, err; @@ -1412,11 +1422,8 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) } /* reset caller saved regs */ - for (i = 0; i < CALLER_SAVED_REGS; i++) { - reg = regs + caller_saved[i]; - reg->type = NOT_INIT; - reg->imm = 0; - } + for (i = 0; i < CALLER_SAVED_REGS; i++) + mark_reg_not_init(regs, caller_saved[i]); /* update return register */ if (fn->ret_type == RET_INTEGER) { @@ -2444,7 +2451,6 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_reg_state *regs = env->cur_state.regs; u8 mode = BPF_MODE(insn->code); - struct bpf_reg_state *reg; int i, err; if (!may_access_skb(env->prog->type)) { @@ -2477,11 +2483,8 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) } /* reset caller saved regs to unreadable */ - for (i = 0; i < CALLER_SAVED_REGS; i++) { - reg = regs + caller_saved[i]; - reg->type = NOT_INIT; - reg->imm = 0; - } + for (i = 0; i < CALLER_SAVED_REGS; i++) + mark_reg_not_init(regs, caller_saved[i]); /* mark destination R0 register as readable, since it contains * the value fetched from the packet @@ -2640,6 +2643,7 @@ peek_stack: env->explored_states[t + 1] = STATE_LIST_MARK; } else { /* conditional jump with two edges */ + env->explored_states[t] = STATE_LIST_MARK; ret = push_insn(t, t + 1, FALLTHROUGH, env); if (ret == 1) goto peek_stack; @@ -2691,7 +2695,8 @@ err_free: /* the following conditions reduce the number of explored insns * from ~140k to ~80k for ultra large programs that use a lot of ptr_to_packet */ -static bool compare_ptrs_to_packet(struct bpf_reg_state *old, +static bool compare_ptrs_to_packet(struct bpf_verifier_env *env, + struct bpf_reg_state *old, struct bpf_reg_state *cur) { if (old->id != cur->id) @@ -2734,7 +2739,7 @@ static bool compare_ptrs_to_packet(struct bpf_reg_state *old, * 'if (R4 > data_end)' and all further insn were already good with r=20, * so they will be good with r=30 and we can prune the search. */ - if (old->off <= cur->off && + if (!env->strict_alignment && old->off <= cur->off && old->off >= old->range && cur->off >= cur->range) return true; @@ -2798,8 +2803,14 @@ static bool states_equal(struct bpf_verifier_env *env, rcur->type != NOT_INIT)) continue; + /* Don't care about the reg->id in this case. */ + if (rold->type == PTR_TO_MAP_VALUE_OR_NULL && + rcur->type == PTR_TO_MAP_VALUE_OR_NULL && + rold->map_ptr == rcur->map_ptr) + continue; + if (rold->type == PTR_TO_PACKET && rcur->type == PTR_TO_PACKET && - compare_ptrs_to_packet(rold, rcur)) + compare_ptrs_to_packet(env, rold, rcur)) continue; return false; @@ -2932,6 +2943,9 @@ static int do_check(struct bpf_verifier_env *env) goto process_bpf_exit; } + if (need_resched()) + cond_resched(); + if (log_level > 1 || (log_level && do_print_state)) { if (log_level > 1) verbose("%d:", insn_idx); @@ -3160,7 +3174,8 @@ process_bpf_exit: insn_idx++; } - verbose("processed %d insns\n", insn_processed); + verbose("processed %d insns, stack depth %d\n", + insn_processed, env->prog->aux->stack_depth); return 0; } @@ -3455,6 +3470,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) * the program array. */ prog->cb_access = 1; + env->prog->aux->stack_depth = MAX_BPF_STACK; /* mark bpf_tail_call as different opcode to avoid * conditional branch in the interpeter for every normal @@ -3462,7 +3478,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) * that doesn't support bpf_tail_call yet */ insn->imm = 0; - insn->code |= BPF_X; + insn->code = BPF_JMP | BPF_TAIL_CALL; continue; } @@ -3574,10 +3590,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) } else { log_level = 0; } - if (attr->prog_flags & BPF_F_STRICT_ALIGNMENT) + + env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT); + if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) env->strict_alignment = true; - else - env->strict_alignment = false; ret = replace_map_fd_with_map_ptr(env); if (ret < 0) @@ -3683,7 +3699,10 @@ int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops, mutex_lock(&bpf_verifier_lock); log_level = 0; + env->strict_alignment = false; + if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) + env->strict_alignment = true; env->explored_states = kcalloc(env->prog->len, sizeof(struct bpf_verifier_state_list *), diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index c3c9a0e1b3c9..8d4e85eae42c 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -4265,6 +4265,11 @@ static void kill_css(struct cgroup_subsys_state *css) { lockdep_assert_held(&cgroup_mutex); + if (css->flags & CSS_DYING) + return; + + css->flags |= CSS_DYING; + /* * This must happen before css is disassociated with its cgroup. * See seq_css() for details. diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index f6501f4f6040..ae643412948a 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -176,9 +176,9 @@ typedef enum { } cpuset_flagbits_t; /* convenient tests for these bits */ -static inline bool is_cpuset_online(const struct cpuset *cs) +static inline bool is_cpuset_online(struct cpuset *cs) { - return test_bit(CS_ONLINE, &cs->flags); + return test_bit(CS_ONLINE, &cs->flags) && !css_is_dying(&cs->css); } static inline int is_cpu_exclusive(const struct cpuset *cs) diff --git a/kernel/events/core.c b/kernel/events/core.c index 6e75a5c9412d..51e40e4876c0 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3636,10 +3636,10 @@ static inline u64 perf_event_count(struct perf_event *event) * will not be local and we cannot read them atomically * - must not have a pmu::count method */ -u64 perf_event_read_local(struct perf_event *event) +int perf_event_read_local(struct perf_event *event, u64 *value) { unsigned long flags; - u64 val; + int ret = 0; /* * Disabling interrupts avoids all counter scheduling (context @@ -3647,25 +3647,37 @@ u64 perf_event_read_local(struct perf_event *event) */ local_irq_save(flags); - /* If this is a per-task event, it must be for current */ - WARN_ON_ONCE((event->attach_state & PERF_ATTACH_TASK) && - event->hw.target != current); - - /* If this is a per-CPU event, it must be for this CPU */ - WARN_ON_ONCE(!(event->attach_state & PERF_ATTACH_TASK) && - event->cpu != smp_processor_id()); - /* * It must not be an event with inherit set, we cannot read * all child counters from atomic context. */ - WARN_ON_ONCE(event->attr.inherit); + if (event->attr.inherit) { + ret = -EOPNOTSUPP; + goto out; + } /* * It must not have a pmu::count method, those are not * NMI safe. */ - WARN_ON_ONCE(event->pmu->count); + if (event->pmu->count) { + ret = -EOPNOTSUPP; + goto out; + } + + /* If this is a per-task event, it must be for current */ + if ((event->attach_state & PERF_ATTACH_TASK) && + event->hw.target != current) { + ret = -EINVAL; + goto out; + } + + /* If this is a per-CPU event, it must be for this CPU */ + if (!(event->attach_state & PERF_ATTACH_TASK) && + event->cpu != smp_processor_id()) { + ret = -EINVAL; + goto out; + } /* * If the event is currently on this CPU, its either a per-task event, @@ -3675,10 +3687,11 @@ u64 perf_event_read_local(struct perf_event *event) if (event->oncpu == smp_processor_id()) event->pmu->read(event); - val = local64_read(&event->count); + *value = local64_read(&event->count); +out: local_irq_restore(flags); - return val; + return ret; } static int perf_event_read(struct perf_event *event, bool group) @@ -8037,12 +8050,8 @@ static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd) bool is_kprobe, is_tracepoint; struct bpf_prog *prog; - if (event->attr.type == PERF_TYPE_HARDWARE || - event->attr.type == PERF_TYPE_SOFTWARE) - return perf_event_set_bpf_handler(event, prog_fd); - if (event->attr.type != PERF_TYPE_TRACEPOINT) - return -EINVAL; + return perf_event_set_bpf_handler(event, prog_fd); if (event->tp_event->prog) return -EEXIST; diff --git a/kernel/fork.c b/kernel/fork.c index 06d759ab4c62..e53770d2bf95 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1577,6 +1577,18 @@ static __latent_entropy struct task_struct *copy_process( if (!p) goto fork_out; + /* + * This _must_ happen before we call free_task(), i.e. before we jump + * to any of the bad_fork_* labels. This is to avoid freeing + * p->set_child_tid which is (ab)used as a kthread's data pointer for + * kernel threads (PF_KTHREAD). + */ + p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL; + /* + * Clear TID on mm_release()? + */ + p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr : NULL; + ftrace_graph_init_task(p); rt_mutex_init_task(p); @@ -1743,11 +1755,6 @@ static __latent_entropy struct task_struct *copy_process( } } - p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL; - /* - * Clear TID on mm_release()? - */ - p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr : NULL; #ifdef CONFIG_BLOCK p->plug = NULL; #endif @@ -1845,11 +1852,13 @@ static __latent_entropy struct task_struct *copy_process( */ recalc_sigpending(); if (signal_pending(current)) { - spin_unlock(¤t->sighand->siglock); - write_unlock_irq(&tasklist_lock); retval = -ERESTARTNOINTR; goto bad_fork_cancel_cgroup; } + if (unlikely(!(ns_of_pid(pid)->nr_hashed & PIDNS_HASH_ADDING))) { + retval = -ENOMEM; + goto bad_fork_cancel_cgroup; + } if (likely(p->pid)) { ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace); @@ -1907,6 +1916,8 @@ static __latent_entropy struct task_struct *copy_process( return p; bad_fork_cancel_cgroup: + spin_unlock(¤t->sighand->siglock); + write_unlock_irq(&tasklist_lock); cgroup_cancel_fork(p); bad_fork_free_pid: cgroup_threadgroup_change_end(current); diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 686be4b73018..c94da688ee9b 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -880,8 +880,8 @@ irq_set_chained_handler_and_data(unsigned int irq, irq_flow_handler_t handle, if (!desc) return; - __irq_do_set_handler(desc, handle, 1, NULL); desc->irq_common_data.handler_data = data; + __irq_do_set_handler(desc, handle, 1, NULL); irq_put_desc_busunlock(desc, flags); } diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 7367e0ec6f81..adfe3b4cfe05 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -122,7 +122,7 @@ static void *alloc_insn_page(void) return module_alloc(PAGE_SIZE); } -static void free_insn_page(void *page) +void __weak free_insn_page(void *page) { module_memfree(page); } @@ -595,7 +595,7 @@ static void kprobe_optimizer(struct work_struct *work) } /* Wait for completing optimization and unoptimization */ -static void wait_for_kprobe_optimizer(void) +void wait_for_kprobe_optimizer(void) { mutex_lock(&kprobe_mutex); @@ -2183,6 +2183,12 @@ static int kprobes_module_callback(struct notifier_block *nb, * The vaddr this probe is installed will soon * be vfreed buy not synced to disk. Hence, * disarming the breakpoint isn't needed. + * + * Note, this will also move any optimized probes + * that are pending to be removed from their + * corresponding lists to the freeing_list and + * will not be touched by the delayed + * kprobe_optimizer work handler. */ kill_kprobe(p); } diff --git a/kernel/livepatch/Kconfig b/kernel/livepatch/Kconfig index 045022557936..ec4565122e65 100644 --- a/kernel/livepatch/Kconfig +++ b/kernel/livepatch/Kconfig @@ -10,6 +10,7 @@ config LIVEPATCH depends on SYSFS depends on KALLSYMS_ALL depends on HAVE_LIVEPATCH + depends on !TRIM_UNUSED_KSYMS help Say Y here if you want to support kernel live patching. This option has no runtime impact until a kernel "patch" diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index b95509416909..28cd09e635ed 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1785,12 +1785,14 @@ int rt_mutex_wait_proxy_lock(struct rt_mutex *lock, int ret; raw_spin_lock_irq(&lock->wait_lock); - - set_current_state(TASK_INTERRUPTIBLE); - /* sleep on the mutex */ + set_current_state(TASK_INTERRUPTIBLE); ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter); - + /* + * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might + * have to fix that up. + */ + fixup_rt_mutex_waiters(lock); raw_spin_unlock_irq(&lock->wait_lock); return ret; @@ -1822,15 +1824,25 @@ bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock, raw_spin_lock_irq(&lock->wait_lock); /* + * Do an unconditional try-lock, this deals with the lock stealing + * state where __rt_mutex_futex_unlock() -> mark_wakeup_next_waiter() + * sets a NULL owner. + * + * We're not interested in the return value, because the subsequent + * test on rt_mutex_owner() will infer that. If the trylock succeeded, + * we will own the lock and it will have removed the waiter. If we + * failed the trylock, we're still not owner and we need to remove + * ourselves. + */ + try_to_take_rt_mutex(lock, current, waiter); + /* * Unless we're the owner; we're still enqueued on the wait_list. * So check if we became owner, if not, take us off the wait_list. */ if (rt_mutex_owner(lock) != current) { remove_waiter(lock, waiter); - fixup_rt_mutex_waiters(lock); cleanup = true; } - /* * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might * have to fix that up. diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index d1f3e9f558b8..74a5a7255b4d 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -277,7 +277,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns) * if reparented. */ for (;;) { - set_current_state(TASK_UNINTERRUPTIBLE); + set_current_state(TASK_INTERRUPTIBLE); if (pid_ns->nr_hashed == init_pids) break; schedule(); diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 3b1e0f3ad07f..fa46606f3356 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1425,7 +1425,7 @@ static unsigned int nr_meta_pages; * Numbers of normal and highmem page frames allocated for hibernation image * before suspending devices. */ -unsigned int alloc_normal, alloc_highmem; +static unsigned int alloc_normal, alloc_highmem; /* * Memory bitmap used for marking saveable pages (during hibernation) or * hibernation image pages (during restore) diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 266ddcc1d8bb..60f356d91060 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -60,19 +60,25 @@ int ptrace_access_vm(struct task_struct *tsk, unsigned long addr, } +void __ptrace_link(struct task_struct *child, struct task_struct *new_parent, + const struct cred *ptracer_cred) +{ + BUG_ON(!list_empty(&child->ptrace_entry)); + list_add(&child->ptrace_entry, &new_parent->ptraced); + child->parent = new_parent; + child->ptracer_cred = get_cred(ptracer_cred); +} + /* * ptrace a task: make the debugger its new parent and * move it to the ptrace list. * * Must be called with the tasklist lock write-held. */ -void __ptrace_link(struct task_struct *child, struct task_struct *new_parent) +static void ptrace_link(struct task_struct *child, struct task_struct *new_parent) { - BUG_ON(!list_empty(&child->ptrace_entry)); - list_add(&child->ptrace_entry, &new_parent->ptraced); - child->parent = new_parent; rcu_read_lock(); - child->ptracer_cred = get_cred(__task_cred(new_parent)); + __ptrace_link(child, new_parent, __task_cred(new_parent)); rcu_read_unlock(); } @@ -386,7 +392,7 @@ static int ptrace_attach(struct task_struct *task, long request, flags |= PT_SEIZED; task->ptrace = flags; - __ptrace_link(task, current); + ptrace_link(task, current); /* SEIZE doesn't trap tracee on attach */ if (!seize) @@ -459,7 +465,7 @@ static int ptrace_traceme(void) */ if (!ret && !(current->real_parent->flags & PF_EXITING)) { current->ptrace = PT_PTRACED; - __ptrace_link(current, current->real_parent); + ptrace_link(current, current->real_parent); } } write_unlock_irq(&tasklist_lock); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 759f4bd52cd6..803c3bc274c4 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3502,6 +3502,31 @@ asmlinkage __visible void __sched schedule(void) } EXPORT_SYMBOL(schedule); +/* + * synchronize_rcu_tasks() makes sure that no task is stuck in preempted + * state (have scheduled out non-voluntarily) by making sure that all + * tasks have either left the run queue or have gone into user space. + * As idle tasks do not do either, they must not ever be preempted + * (schedule out non-voluntarily). + * + * schedule_idle() is similar to schedule_preempt_disable() except that it + * never enables preemption because it does not call sched_submit_work(). + */ +void __sched schedule_idle(void) +{ + /* + * As this skips calling sched_submit_work(), which the idle task does + * regardless because that function is a nop when the task is in a + * TASK_RUNNING state, make sure this isn't used someplace that the + * current task can be in any other state. Note, idle is always in the + * TASK_RUNNING state. + */ + WARN_ON_ONCE(current->state); + do { + __schedule(false); + } while (need_resched()); +} + #ifdef CONFIG_CONTEXT_TRACKING asmlinkage __visible void __sched schedule_user(void) { diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 76877a62b5fa..622eed1b7658 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -245,11 +245,10 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, sugov_update_commit(sg_policy, time, next_f); } -static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu) +static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time) { struct sugov_policy *sg_policy = sg_cpu->sg_policy; struct cpufreq_policy *policy = sg_policy->policy; - u64 last_freq_update_time = sg_policy->last_freq_update_time; unsigned long util = 0, max = 1; unsigned int j; @@ -265,7 +264,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu) * enough, don't take the CPU into account as it probably is * idle now (and clear iowait_boost for it). */ - delta_ns = last_freq_update_time - j_sg_cpu->last_update; + delta_ns = time - j_sg_cpu->last_update; if (delta_ns > TICK_NSEC) { j_sg_cpu->iowait_boost = 0; continue; @@ -309,7 +308,7 @@ static void sugov_update_shared(struct update_util_data *hook, u64 time, if (flags & SCHED_CPUFREQ_RT_DL) next_f = sg_policy->policy->cpuinfo.max_freq; else - next_f = sugov_next_freq_shared(sg_cpu); + next_f = sugov_next_freq_shared(sg_cpu, time); sugov_update_commit(sg_policy, time, next_f); } diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 2a25a9ec2c6e..ef63adce0c9c 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -265,7 +265,7 @@ static void do_idle(void) smp_mb__after_atomic(); sched_ttwu_pending(); - schedule_preempt_disabled(); + schedule_idle(); if (unlikely(klp_patch_pending(current))) klp_update_patch_state(current); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 7808ab050599..6dda2aab731e 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1467,6 +1467,8 @@ static inline struct cpuidle_state *idle_get_state(struct rq *rq) } #endif +extern void schedule_idle(void); + extern void sysrq_sched_debug_show(void); extern void sched_init_granularity(void); extern void update_max_interval(void); diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 1370f067fb51..d2a1e6dd0291 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -825,8 +825,10 @@ static void check_thread_timers(struct task_struct *tsk, * At the hard limit, we just die. * No need to calculate anything else now. */ - pr_info("CPU Watchdog Timeout (hard): %s[%d]\n", - tsk->comm, task_pid_nr(tsk)); + if (print_fatal_signals) { + pr_info("CPU Watchdog Timeout (hard): %s[%d]\n", + tsk->comm, task_pid_nr(tsk)); + } __group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk); return; } @@ -838,8 +840,10 @@ static void check_thread_timers(struct task_struct *tsk, soft += USEC_PER_SEC; sig->rlim[RLIMIT_RTTIME].rlim_cur = soft; } - pr_info("RT Watchdog Timeout (soft): %s[%d]\n", - tsk->comm, task_pid_nr(tsk)); + if (print_fatal_signals) { + pr_info("RT Watchdog Timeout (soft): %s[%d]\n", + tsk->comm, task_pid_nr(tsk)); + } __group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk); } } @@ -936,8 +940,10 @@ static void check_process_timers(struct task_struct *tsk, * At the hard limit, we just die. * No need to calculate anything else now. */ - pr_info("RT Watchdog Timeout (hard): %s[%d]\n", - tsk->comm, task_pid_nr(tsk)); + if (print_fatal_signals) { + pr_info("RT Watchdog Timeout (hard): %s[%d]\n", + tsk->comm, task_pid_nr(tsk)); + } __group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk); return; } @@ -945,8 +951,10 @@ static void check_process_timers(struct task_struct *tsk, /* * At the soft limit, send a SIGXCPU every second. */ - pr_info("CPU Watchdog Timeout (soft): %s[%d]\n", - tsk->comm, task_pid_nr(tsk)); + if (print_fatal_signals) { + pr_info("CPU Watchdog Timeout (soft): %s[%d]\n", + tsk->comm, task_pid_nr(tsk)); + } __group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk); if (soft < hard) { soft++; diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index bd8ae8d5ae9c..193c5f5e3f79 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -1662,14 +1662,14 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, goto out; if (attr == &dev_attr_act_mask) { - if (sscanf(buf, "%llx", &value) != 1) { + if (kstrtoull(buf, 0, &value)) { /* Assume it is a list of trace category names */ ret = blk_trace_str2mask(buf); if (ret < 0) goto out; value = ret; } - } else if (sscanf(buf, "%llu", &value) != 1) + } else if (kstrtoull(buf, 0, &value)) goto out; ret = -ENXIO; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 460a031c77e5..08eb072430b9 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -234,7 +234,8 @@ BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags) unsigned int cpu = smp_processor_id(); u64 index = flags & BPF_F_INDEX_MASK; struct bpf_event_entry *ee; - struct perf_event *event; + u64 value = 0; + int err; if (unlikely(flags & ~(BPF_F_INDEX_MASK))) return -EINVAL; @@ -247,21 +248,14 @@ BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags) if (!ee) return -ENOENT; - event = ee->event; - if (unlikely(event->attr.type != PERF_TYPE_HARDWARE && - event->attr.type != PERF_TYPE_RAW)) - return -EINVAL; - - /* make sure event is local and doesn't have pmu::count */ - if (unlikely(event->oncpu != cpu || event->pmu->count)) - return -EINVAL; - + err = perf_event_read_local(ee->event, &value); /* - * we don't know if the function is run successfully by the - * return value. It can be judged in other places, such as - * eBPF programs. + * this api is ugly since we miss [-22..-2] range of valid + * counter values, but that's uapi */ - return perf_event_read_local(event); + if (err) + return err; + return value; } static const struct bpf_func_proto bpf_perf_event_read_proto = { diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 39dca4e86a94..9e5841dc14b5 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4144,9 +4144,9 @@ unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr, int i, ret = -ENODEV; int size; - if (glob && (strcmp(glob, "*") == 0 || !strlen(glob))) + if (!glob || !strlen(glob) || !strcmp(glob, "*")) func_g.search = NULL; - else if (glob) { + else { int not; func_g.type = filter_parse_regex(glob, strlen(glob), @@ -4256,6 +4256,14 @@ unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr, return ret; } +void clear_ftrace_function_probes(struct trace_array *tr) +{ + struct ftrace_func_probe *probe, *n; + + list_for_each_entry_safe(probe, n, &tr->func_probes, list) + unregister_ftrace_function_probe_func(NULL, tr, probe->probe_ops); +} + static LIST_HEAD(ftrace_commands); static DEFINE_MUTEX(ftrace_cmd_mutex); @@ -5055,7 +5063,7 @@ ftrace_graph_release(struct inode *inode, struct file *file) } out: - kfree(fgd->new_hash); + free_ftrace_hash(fgd->new_hash); kfree(fgd); return ret; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c4536c449021..1122f151466f 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1558,7 +1558,7 @@ static __init int init_trace_selftests(void) return 0; } -early_initcall(init_trace_selftests); +core_initcall(init_trace_selftests); #else static inline int run_tracer_selftest(struct tracer *type) { @@ -2568,7 +2568,36 @@ static inline void ftrace_trace_stack(struct trace_array *tr, void __trace_stack(struct trace_array *tr, unsigned long flags, int skip, int pc) { - __ftrace_trace_stack(tr->trace_buffer.buffer, flags, skip, pc, NULL); + struct ring_buffer *buffer = tr->trace_buffer.buffer; + + if (rcu_is_watching()) { + __ftrace_trace_stack(buffer, flags, skip, pc, NULL); + return; + } + + /* + * When an NMI triggers, RCU is enabled via rcu_nmi_enter(), + * but if the above rcu_is_watching() failed, then the NMI + * triggered someplace critical, and rcu_irq_enter() should + * not be called from NMI. + */ + if (unlikely(in_nmi())) + return; + + /* + * It is possible that a function is being traced in a + * location that RCU is not watching. A call to + * rcu_irq_enter() will make sure that it is, but there's + * a few internal rcu functions that could be traced + * where that wont work either. In those cases, we just + * do nothing. + */ + if (unlikely(rcu_irq_enter_disabled())) + return; + + rcu_irq_enter_irqson(); + __ftrace_trace_stack(buffer, flags, skip, pc, NULL); + rcu_irq_exit_irqson(); } /** @@ -7550,6 +7579,7 @@ static int instance_rmdir(const char *name) } tracing_set_nop(tr); + clear_ftrace_function_probes(tr); event_trace_del_tracer(tr); ftrace_clear_pids(tr); ftrace_destroy_function_files(tr); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 291a1bca5748..39fd77330aab 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -980,6 +980,7 @@ register_ftrace_function_probe(char *glob, struct trace_array *tr, extern int unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr, struct ftrace_probe_ops *ops); +extern void clear_ftrace_function_probes(struct trace_array *tr); int register_ftrace_command(struct ftrace_func_command *cmd); int unregister_ftrace_command(struct ftrace_func_command *cmd); @@ -998,6 +999,10 @@ static inline __init int unregister_ftrace_command(char *cmd_name) { return -EINVAL; } +static inline void clear_ftrace_function_probes(struct trace_array *tr) +{ +} + /* * The ops parameter passed in is usually undefined. * This must be a macro. diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 8485f6738a87..c129fca6ec99 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1535,6 +1535,11 @@ static __init int kprobe_trace_self_tests_init(void) end: release_all_trace_kprobes(); + /* + * Wait for the optimizer work to finish. Otherwise it might fiddle + * with probes in already freed __init text. + */ + wait_for_kprobe_optimizer(); if (warn) pr_cont("NG: Some tests are failed. Please check them.\n"); else |