diff options
Diffstat (limited to 'kernel')
33 files changed, 1421 insertions, 483 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index 172d151d429c..f85ae5dfa474 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -81,6 +81,7 @@ obj-$(CONFIG_AUDIT_TREE) += audit_tree.o obj-$(CONFIG_GCOV_KERNEL) += gcov/ obj-$(CONFIG_KCOV) += kcov.o obj-$(CONFIG_KPROBES) += kprobes.o +obj-$(CONFIG_FAIL_FUNCTION) += fail_function.o obj-$(CONFIG_KGDB) += debug/ obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o obj-$(CONFIG_LOCKUP_DETECTOR) += watchdog.o diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 7c25426d3cf5..b1f66480135b 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -49,34 +49,64 @@ static int bpf_array_alloc_percpu(struct bpf_array *array) } /* Called from syscall */ -static struct bpf_map *array_map_alloc(union bpf_attr *attr) +static int array_map_alloc_check(union bpf_attr *attr) { bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; int numa_node = bpf_map_attr_numa_node(attr); - struct bpf_array *array; - u64 array_size; - u32 elem_size; /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || attr->value_size == 0 || attr->map_flags & ~ARRAY_CREATE_FLAG_MASK || (percpu && numa_node != NUMA_NO_NODE)) - return ERR_PTR(-EINVAL); + return -EINVAL; if (attr->value_size > KMALLOC_MAX_SIZE) /* if value_size is bigger, the user space won't be able to * access the elements. */ - return ERR_PTR(-E2BIG); + return -E2BIG; + + return 0; +} + +static struct bpf_map *array_map_alloc(union bpf_attr *attr) +{ + bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; + int numa_node = bpf_map_attr_numa_node(attr); + u32 elem_size, index_mask, max_entries; + bool unpriv = !capable(CAP_SYS_ADMIN); + struct bpf_array *array; + u64 array_size, mask64; elem_size = round_up(attr->value_size, 8); + max_entries = attr->max_entries; + + /* On 32 bit archs roundup_pow_of_two() with max_entries that has + * upper most bit set in u32 space is undefined behavior due to + * resulting 1U << 32, so do it manually here in u64 space. + */ + mask64 = fls_long(max_entries - 1); + mask64 = 1ULL << mask64; + mask64 -= 1; + + index_mask = mask64; + if (unpriv) { + /* round up array size to nearest power of 2, + * since cpu will speculate within index_mask limits + */ + max_entries = index_mask + 1; + /* Check for overflows. */ + if (max_entries < attr->max_entries) + return ERR_PTR(-E2BIG); + } + array_size = sizeof(*array); if (percpu) - array_size += (u64) attr->max_entries * sizeof(void *); + array_size += (u64) max_entries * sizeof(void *); else - array_size += (u64) attr->max_entries * elem_size; + array_size += (u64) max_entries * elem_size; /* make sure there is no u32 overflow later in round_up() */ if (array_size >= U32_MAX - PAGE_SIZE) @@ -86,14 +116,11 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) array = bpf_map_area_alloc(array_size, numa_node); if (!array) return ERR_PTR(-ENOMEM); + array->index_mask = index_mask; + array->map.unpriv_array = unpriv; /* copy mandatory map attributes */ - array->map.map_type = attr->map_type; - 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->map.numa_node = numa_node; + bpf_map_init_from_attr(&array->map, attr); array->elem_size = elem_size; if (!percpu) @@ -121,12 +148,13 @@ static void *array_map_lookup_elem(struct bpf_map *map, void *key) if (unlikely(index >= array->map.max_entries)) return NULL; - return array->value + array->elem_size * index; + return array->value + array->elem_size * (index & array->index_mask); } /* emit BPF instructions equivalent to C code of array_map_lookup_elem() */ static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) { + struct bpf_array *array = container_of(map, struct bpf_array, map); struct bpf_insn *insn = insn_buf; u32 elem_size = round_up(map->value_size, 8); const int ret = BPF_REG_0; @@ -135,7 +163,12 @@ static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) *insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value)); *insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0); - *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 3); + if (map->unpriv_array) { + *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 4); + *insn++ = BPF_ALU32_IMM(BPF_AND, ret, array->index_mask); + } else { + *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 3); + } if (is_power_of_2(elem_size)) { *insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size)); @@ -157,7 +190,7 @@ static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key) if (unlikely(index >= array->map.max_entries)) return NULL; - return this_cpu_ptr(array->pptrs[index]); + return this_cpu_ptr(array->pptrs[index & array->index_mask]); } int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value) @@ -177,7 +210,7 @@ int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value) */ size = round_up(map->value_size, 8); rcu_read_lock(); - pptr = array->pptrs[index]; + pptr = array->pptrs[index & array->index_mask]; for_each_possible_cpu(cpu) { bpf_long_memcpy(value + off, per_cpu_ptr(pptr, cpu), size); off += size; @@ -225,10 +258,11 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value, return -EEXIST; if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) - memcpy(this_cpu_ptr(array->pptrs[index]), + memcpy(this_cpu_ptr(array->pptrs[index & array->index_mask]), value, map->value_size); else - memcpy(array->value + array->elem_size * index, + memcpy(array->value + + array->elem_size * (index & array->index_mask), value, map->value_size); return 0; } @@ -262,7 +296,7 @@ int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, */ size = round_up(map->value_size, 8); rcu_read_lock(); - pptr = array->pptrs[index]; + pptr = array->pptrs[index & array->index_mask]; for_each_possible_cpu(cpu) { bpf_long_memcpy(per_cpu_ptr(pptr, cpu), value + off, size); off += size; @@ -296,6 +330,7 @@ static void array_map_free(struct bpf_map *map) } const struct bpf_map_ops array_map_ops = { + .map_alloc_check = array_map_alloc_check, .map_alloc = array_map_alloc, .map_free = array_map_free, .map_get_next_key = array_map_get_next_key, @@ -306,6 +341,7 @@ const struct bpf_map_ops array_map_ops = { }; const struct bpf_map_ops percpu_array_map_ops = { + .map_alloc_check = array_map_alloc_check, .map_alloc = array_map_alloc, .map_free = array_map_free, .map_get_next_key = array_map_get_next_key, @@ -314,12 +350,12 @@ const struct bpf_map_ops percpu_array_map_ops = { .map_delete_elem = array_map_delete_elem, }; -static struct bpf_map *fd_array_map_alloc(union bpf_attr *attr) +static int fd_array_map_alloc_check(union bpf_attr *attr) { /* only file descriptors can be stored in this type of map */ if (attr->value_size != sizeof(u32)) - return ERR_PTR(-EINVAL); - return array_map_alloc(attr); + return -EINVAL; + return array_map_alloc_check(attr); } static void fd_array_map_free(struct bpf_map *map) @@ -443,7 +479,8 @@ void bpf_fd_array_map_clear(struct bpf_map *map) } const struct bpf_map_ops prog_array_map_ops = { - .map_alloc = fd_array_map_alloc, + .map_alloc_check = fd_array_map_alloc_check, + .map_alloc = array_map_alloc, .map_free = fd_array_map_free, .map_get_next_key = array_map_get_next_key, .map_lookup_elem = fd_array_map_lookup_elem, @@ -530,7 +567,8 @@ static void perf_event_fd_array_release(struct bpf_map *map, } const struct bpf_map_ops perf_event_array_map_ops = { - .map_alloc = fd_array_map_alloc, + .map_alloc_check = fd_array_map_alloc_check, + .map_alloc = array_map_alloc, .map_free = fd_array_map_free, .map_get_next_key = array_map_get_next_key, .map_lookup_elem = fd_array_map_lookup_elem, @@ -561,7 +599,8 @@ static void cgroup_fd_array_free(struct bpf_map *map) } const struct bpf_map_ops cgroup_array_map_ops = { - .map_alloc = fd_array_map_alloc, + .map_alloc_check = fd_array_map_alloc_check, + .map_alloc = array_map_alloc, .map_free = cgroup_fd_array_free, .map_get_next_key = array_map_get_next_key, .map_lookup_elem = fd_array_map_lookup_elem, @@ -579,7 +618,7 @@ static struct bpf_map *array_of_map_alloc(union bpf_attr *attr) if (IS_ERR(inner_map_meta)) return inner_map_meta; - map = fd_array_map_alloc(attr); + map = array_map_alloc(attr); if (IS_ERR(map)) { bpf_map_meta_free(inner_map_meta); return map; @@ -613,6 +652,7 @@ static void *array_of_map_lookup_elem(struct bpf_map *map, void *key) static u32 array_of_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) { + struct bpf_array *array = container_of(map, struct bpf_array, map); u32 elem_size = round_up(map->value_size, 8); struct bpf_insn *insn = insn_buf; const int ret = BPF_REG_0; @@ -621,7 +661,12 @@ static u32 array_of_map_gen_lookup(struct bpf_map *map, *insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value)); *insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0); - *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 5); + if (map->unpriv_array) { + *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 6); + *insn++ = BPF_ALU32_IMM(BPF_AND, ret, array->index_mask); + } else { + *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 5); + } if (is_power_of_2(elem_size)) *insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size)); else @@ -636,6 +681,7 @@ static u32 array_of_map_gen_lookup(struct bpf_map *map, } const struct bpf_map_ops array_of_maps_map_ops = { + .map_alloc_check = fd_array_map_alloc_check, .map_alloc = array_of_map_alloc, .map_free = array_of_map_free, .map_get_next_key = array_map_get_next_key, diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 70a534549cd3..3aa0658add76 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -300,6 +300,11 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, } #ifdef CONFIG_BPF_JIT +/* All BPF JIT sysctl knobs here. */ +int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_ALWAYS_ON); +int bpf_jit_harden __read_mostly; +int bpf_jit_kallsyms __read_mostly; + static __always_inline void bpf_get_prog_addr_region(const struct bpf_prog *prog, unsigned long *symbol_start, @@ -381,8 +386,6 @@ static DEFINE_SPINLOCK(bpf_lock); static LIST_HEAD(bpf_kallsyms); static struct latch_tree_root bpf_tree __cacheline_aligned; -int bpf_jit_kallsyms __read_mostly; - static void bpf_prog_ksym_node_add(struct bpf_prog_aux *aux) { WARN_ON_ONCE(!list_empty(&aux->ksym_lnode)); @@ -563,8 +566,6 @@ void __weak bpf_jit_free(struct bpf_prog *fp) bpf_prog_unlock_free(fp); } -int bpf_jit_harden __read_mostly; - static int bpf_jit_blind_insn(const struct bpf_insn *from, const struct bpf_insn *aux, struct bpf_insn *to_buff) @@ -781,6 +782,7 @@ noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) } EXPORT_SYMBOL_GPL(__bpf_call_base); +#ifndef CONFIG_BPF_JIT_ALWAYS_ON /** * __bpf_prog_run - run eBPF program on a given context * @ctx: is the data we are operating on @@ -969,7 +971,7 @@ select_insn: DST = tmp; CONT; ALU_MOD_X: - if (unlikely(SRC == 0)) + if (unlikely((u32)SRC == 0)) return 0; tmp = (u32) DST; DST = do_div(tmp, (u32) SRC); @@ -988,7 +990,7 @@ select_insn: DST = div64_u64(DST, SRC); CONT; ALU_DIV_X: - if (unlikely(SRC == 0)) + if (unlikely((u32)SRC == 0)) return 0; tmp = (u32) DST; do_div(tmp, (u32) SRC); @@ -1377,6 +1379,18 @@ void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth) insn->code = BPF_JMP | BPF_CALL_ARGS; } +#else +static unsigned int __bpf_prog_ret0_warn(const void *ctx, + const struct bpf_insn *insn) +{ + /* If this handler ever gets executed, then BPF_JIT_ALWAYS_ON + * is not working properly, so warn about it! + */ + WARN_ON_ONCE(1); + return 0; +} +#endif + bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp) { @@ -1427,9 +1441,13 @@ static int bpf_check_tail_call(const struct bpf_prog *fp) */ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) { +#ifndef CONFIG_BPF_JIT_ALWAYS_ON u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1); fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1]; +#else + fp->bpf_func = __bpf_prog_ret0_warn; +#endif /* eBPF JITs can rewrite the program in case constant * blinding is active. However, in case of error during @@ -1439,6 +1457,12 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) */ if (!bpf_prog_is_dev_bound(fp->aux)) { fp = bpf_int_jit_compile(fp); +#ifdef CONFIG_BPF_JIT_ALWAYS_ON + if (!fp->jited) { + *err = -ENOTSUPP; + return fp; + } +#endif } else { *err = bpf_prog_offload_compile(fp); if (*err) diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index ce5b669003b2..fbfdada6caee 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -94,13 +94,7 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) if (!cmap) return ERR_PTR(-ENOMEM); - /* mandatory map attributes */ - cmap->map.map_type = attr->map_type; - cmap->map.key_size = attr->key_size; - cmap->map.value_size = attr->value_size; - cmap->map.max_entries = attr->max_entries; - cmap->map.map_flags = attr->map_flags; - cmap->map.numa_node = bpf_map_attr_numa_node(attr); + bpf_map_init_from_attr(&cmap->map, attr); /* Pre-limit array size based on NR_CPUS, not final CPU check */ if (cmap->map.max_entries > NR_CPUS) { @@ -143,7 +137,7 @@ free_cmap: return ERR_PTR(err); } -void __cpu_map_queue_destructor(void *ptr) +static void __cpu_map_queue_destructor(void *ptr) { /* The tear-down procedure should have made sure that queue is * empty. See __cpu_map_entry_replace() and work-queue @@ -222,8 +216,8 @@ static struct xdp_pkt *convert_to_xdp_pkt(struct xdp_buff *xdp) return xdp_pkt; } -struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, - struct xdp_pkt *xdp_pkt) +static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, + struct xdp_pkt *xdp_pkt) { unsigned int frame_size; void *pkt_data_start; @@ -337,7 +331,8 @@ static int cpu_map_kthread_run(void *data) return 0; } -struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu, int map_id) +static struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu, + int map_id) { gfp_t gfp = GFP_ATOMIC|__GFP_NOWARN; struct bpf_cpu_map_entry *rcpu; @@ -395,7 +390,7 @@ free_rcu: return NULL; } -void __cpu_map_entry_free(struct rcu_head *rcu) +static void __cpu_map_entry_free(struct rcu_head *rcu) { struct bpf_cpu_map_entry *rcpu; int cpu; @@ -438,8 +433,8 @@ void __cpu_map_entry_free(struct rcu_head *rcu) * cpu_map_kthread_stop, which waits for an RCU graze period before * stopping kthread, emptying the queue. */ -void __cpu_map_entry_replace(struct bpf_cpu_map *cmap, - u32 key_cpu, struct bpf_cpu_map_entry *rcpu) +static void __cpu_map_entry_replace(struct bpf_cpu_map *cmap, + u32 key_cpu, struct bpf_cpu_map_entry *rcpu) { struct bpf_cpu_map_entry *old_rcpu; @@ -451,7 +446,7 @@ void __cpu_map_entry_replace(struct bpf_cpu_map *cmap, } } -int cpu_map_delete_elem(struct bpf_map *map, void *key) +static int cpu_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); u32 key_cpu = *(u32 *)key; @@ -464,8 +459,8 @@ int cpu_map_delete_elem(struct bpf_map *map, void *key) return 0; } -int cpu_map_update_elem(struct bpf_map *map, void *key, void *value, - u64 map_flags) +static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) { struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); struct bpf_cpu_map_entry *rcpu; @@ -502,7 +497,7 @@ int cpu_map_update_elem(struct bpf_map *map, void *key, void *value, return 0; } -void cpu_map_free(struct bpf_map *map) +static void cpu_map_free(struct bpf_map *map) { struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); int cpu; diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index ebdef54bf7df..565f9ece9115 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -93,13 +93,7 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) if (!dtab) return ERR_PTR(-ENOMEM); - /* mandatory map attributes */ - dtab->map.map_type = attr->map_type; - dtab->map.key_size = attr->key_size; - dtab->map.value_size = attr->value_size; - dtab->map.max_entries = attr->max_entries; - dtab->map.map_flags = attr->map_flags; - dtab->map.numa_node = bpf_map_attr_numa_node(attr); + bpf_map_init_from_attr(&dtab->map, attr); /* make sure page count doesn't overflow */ cost = (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *); diff --git a/kernel/bpf/disasm.h b/kernel/bpf/disasm.h index e0857d016f89..266fe8ee542b 100644 --- a/kernel/bpf/disasm.h +++ b/kernel/bpf/disasm.h @@ -29,8 +29,8 @@ extern const char *const bpf_class_string[8]; const char *func_id_name(int id); -typedef void (*bpf_insn_print_t)(struct bpf_verifier_env *env, - const char *, ...); +typedef __printf(2, 3) void (*bpf_insn_print_t)(struct bpf_verifier_env *env, + const char *, ...); typedef const char *(*bpf_insn_revmap_call_t)(void *private_data, const struct bpf_insn *insn); typedef const char *(*bpf_insn_print_imm_t)(void *private_data, diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 3905d4bc5b80..b76828f23b49 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -227,7 +227,7 @@ static int alloc_extra_elems(struct bpf_htab *htab) } /* Called from syscall */ -static struct bpf_map *htab_map_alloc(union bpf_attr *attr) +static int htab_map_alloc_check(union bpf_attr *attr) { bool percpu = (attr->map_type == BPF_MAP_TYPE_PERCPU_HASH || attr->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH); @@ -241,9 +241,6 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU); bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC); int numa_node = bpf_map_attr_numa_node(attr); - struct bpf_htab *htab; - int err, i; - u64 cost; BUILD_BUG_ON(offsetof(struct htab_elem, htab) != offsetof(struct htab_elem, hash_node.pprev)); @@ -254,40 +251,68 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) /* LRU implementation is much complicated than other * maps. Hence, limit to CAP_SYS_ADMIN for now. */ - return ERR_PTR(-EPERM); + return -EPERM; if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK) /* reserved bits should not be used */ - return ERR_PTR(-EINVAL); + return -EINVAL; if (!lru && percpu_lru) - return ERR_PTR(-EINVAL); + return -EINVAL; if (lru && !prealloc) - return ERR_PTR(-ENOTSUPP); + return -ENOTSUPP; if (numa_node != NUMA_NO_NODE && (percpu || percpu_lru)) - return ERR_PTR(-EINVAL); + return -EINVAL; + + /* check sanity of attributes. + * value_size == 0 may be allowed in the future to use map as a set + */ + if (attr->max_entries == 0 || attr->key_size == 0 || + attr->value_size == 0) + return -EINVAL; + + if (attr->key_size > MAX_BPF_STACK) + /* eBPF programs initialize keys on stack, so they cannot be + * larger than max stack size + */ + return -E2BIG; + + if (attr->value_size >= KMALLOC_MAX_SIZE - + MAX_BPF_STACK - sizeof(struct htab_elem)) + /* if value_size is bigger, the user space won't be able to + * access the elements via bpf syscall. This check also makes + * sure that the elem_size doesn't overflow and it's + * kmalloc-able later in htab_map_update_elem() + */ + return -E2BIG; + + return 0; +} + +static struct bpf_map *htab_map_alloc(union bpf_attr *attr) +{ + bool percpu = (attr->map_type == BPF_MAP_TYPE_PERCPU_HASH || + attr->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH); + bool lru = (attr->map_type == BPF_MAP_TYPE_LRU_HASH || + attr->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH); + /* percpu_lru means each cpu has its own LRU list. + * it is different from BPF_MAP_TYPE_PERCPU_HASH where + * the map's value itself is percpu. percpu_lru has + * nothing to do with the map's value. + */ + bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU); + bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC); + struct bpf_htab *htab; + int err, i; + u64 cost; htab = kzalloc(sizeof(*htab), GFP_USER); if (!htab) return ERR_PTR(-ENOMEM); - /* mandatory map attributes */ - htab->map.map_type = attr->map_type; - htab->map.key_size = attr->key_size; - htab->map.value_size = attr->value_size; - htab->map.max_entries = attr->max_entries; - htab->map.map_flags = attr->map_flags; - htab->map.numa_node = numa_node; - - /* check sanity of attributes. - * value_size == 0 may be allowed in the future to use map as a set - */ - err = -EINVAL; - if (htab->map.max_entries == 0 || htab->map.key_size == 0 || - htab->map.value_size == 0) - goto free_htab; + bpf_map_init_from_attr(&htab->map, attr); if (percpu_lru) { /* ensure each CPU's lru list has >=1 elements. @@ -304,22 +329,6 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) /* hash table size must be power of 2 */ htab->n_buckets = roundup_pow_of_two(htab->map.max_entries); - err = -E2BIG; - if (htab->map.key_size > MAX_BPF_STACK) - /* eBPF programs initialize keys on stack, so they cannot be - * larger than max stack size - */ - goto free_htab; - - if (htab->map.value_size >= KMALLOC_MAX_SIZE - - MAX_BPF_STACK - sizeof(struct htab_elem)) - /* if value_size is bigger, the user space won't be able to - * access the elements via bpf syscall. This check also makes - * sure that the elem_size doesn't overflow and it's - * kmalloc-able later in htab_map_update_elem() - */ - goto free_htab; - htab->elem_size = sizeof(struct htab_elem) + round_up(htab->map.key_size, 8); if (percpu) @@ -327,6 +336,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) else htab->elem_size += round_up(htab->map.value_size, 8); + err = -E2BIG; /* prevent zero size kmalloc and check for u32 overflow */ if (htab->n_buckets == 0 || htab->n_buckets > U32_MAX / sizeof(struct bucket)) @@ -1143,6 +1153,7 @@ static void htab_map_free(struct bpf_map *map) } const struct bpf_map_ops htab_map_ops = { + .map_alloc_check = htab_map_alloc_check, .map_alloc = htab_map_alloc, .map_free = htab_map_free, .map_get_next_key = htab_map_get_next_key, @@ -1153,6 +1164,7 @@ const struct bpf_map_ops htab_map_ops = { }; const struct bpf_map_ops htab_lru_map_ops = { + .map_alloc_check = htab_map_alloc_check, .map_alloc = htab_map_alloc, .map_free = htab_map_free, .map_get_next_key = htab_map_get_next_key, @@ -1236,6 +1248,7 @@ int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value, } const struct bpf_map_ops htab_percpu_map_ops = { + .map_alloc_check = htab_map_alloc_check, .map_alloc = htab_map_alloc, .map_free = htab_map_free, .map_get_next_key = htab_map_get_next_key, @@ -1245,6 +1258,7 @@ const struct bpf_map_ops htab_percpu_map_ops = { }; const struct bpf_map_ops htab_lru_percpu_map_ops = { + .map_alloc_check = htab_map_alloc_check, .map_alloc = htab_map_alloc, .map_free = htab_map_free, .map_get_next_key = htab_map_get_next_key, @@ -1253,11 +1267,11 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = { .map_delete_elem = htab_lru_map_delete_elem, }; -static struct bpf_map *fd_htab_map_alloc(union bpf_attr *attr) +static int fd_htab_map_alloc_check(union bpf_attr *attr) { if (attr->value_size != sizeof(u32)) - return ERR_PTR(-EINVAL); - return htab_map_alloc(attr); + return -EINVAL; + return htab_map_alloc_check(attr); } static void fd_htab_map_free(struct bpf_map *map) @@ -1328,7 +1342,7 @@ static struct bpf_map *htab_of_map_alloc(union bpf_attr *attr) if (IS_ERR(inner_map_meta)) return inner_map_meta; - map = fd_htab_map_alloc(attr); + map = htab_map_alloc(attr); if (IS_ERR(map)) { bpf_map_meta_free(inner_map_meta); return map; @@ -1372,6 +1386,7 @@ static void htab_of_map_free(struct bpf_map *map) } const struct bpf_map_ops htab_of_maps_map_ops = { + .map_alloc_check = fd_htab_map_alloc_check, .map_alloc = htab_of_map_alloc, .map_free = htab_of_map_free, .map_get_next_key = htab_map_get_next_key, diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 885e45479680..d7ea96218516 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -522,12 +522,7 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr) return ERR_PTR(-ENOMEM); /* copy mandatory map attributes */ - trie->map.map_type = attr->map_type; - 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->map.numa_node = bpf_map_attr_numa_node(attr); + bpf_map_init_from_attr(&trie->map, attr); trie->data_size = attr->key_size - offsetof(struct bpf_lpm_trie_key, data); trie->max_prefixlen = trie->data_size * 8; @@ -596,9 +591,100 @@ unlock: raw_spin_unlock(&trie->lock); } -static int trie_get_next_key(struct bpf_map *map, void *key, void *next_key) +static int trie_get_next_key(struct bpf_map *map, void *_key, void *_next_key) { - return -ENOTSUPP; + struct lpm_trie *trie = container_of(map, struct lpm_trie, map); + struct bpf_lpm_trie_key *key = _key, *next_key = _next_key; + struct lpm_trie_node *node, *next_node = NULL, *parent; + struct lpm_trie_node **node_stack = NULL; + struct lpm_trie_node __rcu **root; + int err = 0, stack_ptr = -1; + unsigned int next_bit; + size_t matchlen; + + /* The get_next_key follows postorder. For the 4 node example in + * the top of this file, the trie_get_next_key() returns the following + * one after another: + * 192.168.0.0/24 + * 192.168.1.0/24 + * 192.168.128.0/24 + * 192.168.0.0/16 + * + * The idea is to return more specific keys before less specific ones. + */ + + /* Empty trie */ + if (!rcu_dereference(trie->root)) + return -ENOENT; + + /* For invalid key, find the leftmost node in the trie */ + if (!key || key->prefixlen > trie->max_prefixlen) { + root = &trie->root; + goto find_leftmost; + } + + node_stack = kmalloc(trie->max_prefixlen * sizeof(struct lpm_trie_node *), + GFP_USER | __GFP_NOWARN); + if (!node_stack) + return -ENOMEM; + + /* Try to find the exact node for the given key */ + for (node = rcu_dereference(trie->root); node;) { + node_stack[++stack_ptr] = node; + matchlen = longest_prefix_match(trie, node, key); + if (node->prefixlen != matchlen || + node->prefixlen == key->prefixlen) + break; + + next_bit = extract_bit(key->data, node->prefixlen); + node = rcu_dereference(node->child[next_bit]); + } + if (!node || node->prefixlen != key->prefixlen || + (node->flags & LPM_TREE_NODE_FLAG_IM)) { + root = &trie->root; + goto find_leftmost; + } + + /* The node with the exactly-matching key has been found, + * find the first node in postorder after the matched node. + */ + node = node_stack[stack_ptr]; + while (stack_ptr > 0) { + parent = node_stack[stack_ptr - 1]; + if (rcu_dereference(parent->child[0]) == node && + rcu_dereference(parent->child[1])) { + root = &parent->child[1]; + goto find_leftmost; + } + if (!(parent->flags & LPM_TREE_NODE_FLAG_IM)) { + next_node = parent; + goto do_copy; + } + + node = parent; + stack_ptr--; + } + + /* did not find anything */ + err = -ENOENT; + goto free_stack; + +find_leftmost: + /* Find the leftmost non-intermediate node, all intermediate nodes + * have exact two children, so this function will never return NULL. + */ + for (node = rcu_dereference(*root); node;) { + if (!(node->flags & LPM_TREE_NODE_FLAG_IM)) + next_node = node; + node = rcu_dereference(node->child[0]); + } +do_copy: + next_key->prefixlen = next_node->prefixlen; + memcpy((void *)next_key + offsetof(struct bpf_lpm_trie_key, data), + next_node->data, trie->data_size); +free_stack: + kfree(node_stack); + return err; } const struct bpf_map_ops trie_map_ops = { diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index 040d4e0edf3f..c9401075b58c 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -24,15 +24,27 @@ #include <linux/rtnetlink.h> #include <linux/rwsem.h> -/* Protects bpf_prog_offload_devs and offload members of all progs. +/* Protects bpf_prog_offload_devs, bpf_map_offload_devs and offload members + * of all progs. * RTNL lock cannot be taken when holding this lock. */ static DECLARE_RWSEM(bpf_devs_lock); static LIST_HEAD(bpf_prog_offload_devs); +static LIST_HEAD(bpf_map_offload_devs); + +static int bpf_dev_offload_check(struct net_device *netdev) +{ + if (!netdev) + return -EINVAL; + if (!netdev->netdev_ops->ndo_bpf) + return -EOPNOTSUPP; + return 0; +} int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) { - struct bpf_dev_offload *offload; + struct bpf_prog_offload *offload; + int err; if (attr->prog_type != BPF_PROG_TYPE_SCHED_CLS && attr->prog_type != BPF_PROG_TYPE_XDP) @@ -49,12 +61,15 @@ int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) offload->netdev = dev_get_by_index(current->nsproxy->net_ns, attr->prog_ifindex); - if (!offload->netdev) - goto err_free; + err = bpf_dev_offload_check(offload->netdev); + if (err) + goto err_maybe_put; down_write(&bpf_devs_lock); - if (offload->netdev->reg_state != NETREG_REGISTERED) + if (offload->netdev->reg_state != NETREG_REGISTERED) { + err = -EINVAL; goto err_unlock; + } prog->aux->offload = offload; list_add_tail(&offload->offloads, &bpf_prog_offload_devs); dev_put(offload->netdev); @@ -63,16 +78,17 @@ int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) return 0; err_unlock: up_write(&bpf_devs_lock); - dev_put(offload->netdev); -err_free: +err_maybe_put: + if (offload->netdev) + dev_put(offload->netdev); kfree(offload); - return -EINVAL; + return err; } static int __bpf_offload_ndo(struct bpf_prog *prog, enum bpf_netdev_command cmd, struct netdev_bpf *data) { - struct bpf_dev_offload *offload = prog->aux->offload; + struct bpf_prog_offload *offload = prog->aux->offload; struct net_device *netdev; ASSERT_RTNL(); @@ -80,8 +96,6 @@ static int __bpf_offload_ndo(struct bpf_prog *prog, enum bpf_netdev_command cmd, if (!offload) return -ENODEV; netdev = offload->netdev; - if (!netdev->netdev_ops->ndo_bpf) - return -EOPNOTSUPP; data->command = cmd; @@ -110,7 +124,7 @@ exit_unlock: int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx) { - struct bpf_dev_offload *offload; + struct bpf_prog_offload *offload; int ret = -ENODEV; down_read(&bpf_devs_lock); @@ -124,7 +138,7 @@ int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env, static void __bpf_prog_offload_destroy(struct bpf_prog *prog) { - struct bpf_dev_offload *offload = prog->aux->offload; + struct bpf_prog_offload *offload = prog->aux->offload; struct netdev_bpf data = {}; data.offload.prog = prog; @@ -216,9 +230,12 @@ int bpf_prog_offload_info_fill(struct bpf_prog_info *info, .prog = prog, .info = info, }; + struct bpf_prog_aux *aux = prog->aux; struct inode *ns_inode; struct path ns_path; + char __user *uinsns; void *res; + u32 ulen; res = ns_get_path_cb(&ns_path, bpf_prog_offload_info_fill_ns, &args); if (IS_ERR(res)) { @@ -227,6 +244,26 @@ int bpf_prog_offload_info_fill(struct bpf_prog_info *info, return PTR_ERR(res); } + down_read(&bpf_devs_lock); + + if (!aux->offload) { + up_read(&bpf_devs_lock); + return -ENODEV; + } + + ulen = info->jited_prog_len; + info->jited_prog_len = aux->offload->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, aux->offload->jited_image, ulen)) { + up_read(&bpf_devs_lock); + return -EFAULT; + } + } + + up_read(&bpf_devs_lock); + ns_inode = ns_path.dentry->d_inode; info->netns_dev = new_encode_dev(ns_inode->i_sb->s_dev); info->netns_ino = ns_inode->i_ino; @@ -238,11 +275,240 @@ int bpf_prog_offload_info_fill(struct bpf_prog_info *info, const struct bpf_prog_ops bpf_offload_prog_ops = { }; +static int bpf_map_offload_ndo(struct bpf_offloaded_map *offmap, + enum bpf_netdev_command cmd) +{ + struct netdev_bpf data = {}; + struct net_device *netdev; + + ASSERT_RTNL(); + + data.command = cmd; + data.offmap = offmap; + /* Caller must make sure netdev is valid */ + netdev = offmap->netdev; + + return netdev->netdev_ops->ndo_bpf(netdev, &data); +} + +struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr) +{ + struct net *net = current->nsproxy->net_ns; + struct bpf_offloaded_map *offmap; + int err; + + if (!capable(CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); + if (attr->map_type != BPF_MAP_TYPE_ARRAY && + attr->map_type != BPF_MAP_TYPE_HASH) + return ERR_PTR(-EINVAL); + + offmap = kzalloc(sizeof(*offmap), GFP_USER); + if (!offmap) + return ERR_PTR(-ENOMEM); + + bpf_map_init_from_attr(&offmap->map, attr); + + rtnl_lock(); + down_write(&bpf_devs_lock); + offmap->netdev = __dev_get_by_index(net, attr->map_ifindex); + err = bpf_dev_offload_check(offmap->netdev); + if (err) + goto err_unlock; + + err = bpf_map_offload_ndo(offmap, BPF_OFFLOAD_MAP_ALLOC); + if (err) + goto err_unlock; + + list_add_tail(&offmap->offloads, &bpf_map_offload_devs); + up_write(&bpf_devs_lock); + rtnl_unlock(); + + return &offmap->map; + +err_unlock: + up_write(&bpf_devs_lock); + rtnl_unlock(); + kfree(offmap); + return ERR_PTR(err); +} + +static void __bpf_map_offload_destroy(struct bpf_offloaded_map *offmap) +{ + WARN_ON(bpf_map_offload_ndo(offmap, BPF_OFFLOAD_MAP_FREE)); + /* Make sure BPF_MAP_GET_NEXT_ID can't find this dead map */ + bpf_map_free_id(&offmap->map, true); + list_del_init(&offmap->offloads); + offmap->netdev = NULL; +} + +void bpf_map_offload_map_free(struct bpf_map *map) +{ + struct bpf_offloaded_map *offmap = map_to_offmap(map); + + rtnl_lock(); + down_write(&bpf_devs_lock); + if (offmap->netdev) + __bpf_map_offload_destroy(offmap); + up_write(&bpf_devs_lock); + rtnl_unlock(); + + kfree(offmap); +} + +int bpf_map_offload_lookup_elem(struct bpf_map *map, void *key, void *value) +{ + struct bpf_offloaded_map *offmap = map_to_offmap(map); + int ret = -ENODEV; + + down_read(&bpf_devs_lock); + if (offmap->netdev) + ret = offmap->dev_ops->map_lookup_elem(offmap, key, value); + up_read(&bpf_devs_lock); + + return ret; +} + +int bpf_map_offload_update_elem(struct bpf_map *map, + void *key, void *value, u64 flags) +{ + struct bpf_offloaded_map *offmap = map_to_offmap(map); + int ret = -ENODEV; + + if (unlikely(flags > BPF_EXIST)) + return -EINVAL; + + down_read(&bpf_devs_lock); + if (offmap->netdev) + ret = offmap->dev_ops->map_update_elem(offmap, key, value, + flags); + up_read(&bpf_devs_lock); + + return ret; +} + +int bpf_map_offload_delete_elem(struct bpf_map *map, void *key) +{ + struct bpf_offloaded_map *offmap = map_to_offmap(map); + int ret = -ENODEV; + + down_read(&bpf_devs_lock); + if (offmap->netdev) + ret = offmap->dev_ops->map_delete_elem(offmap, key); + up_read(&bpf_devs_lock); + + return ret; +} + +int bpf_map_offload_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + struct bpf_offloaded_map *offmap = map_to_offmap(map); + int ret = -ENODEV; + + down_read(&bpf_devs_lock); + if (offmap->netdev) + ret = offmap->dev_ops->map_get_next_key(offmap, key, next_key); + up_read(&bpf_devs_lock); + + return ret; +} + +struct ns_get_path_bpf_map_args { + struct bpf_offloaded_map *offmap; + struct bpf_map_info *info; +}; + +static struct ns_common *bpf_map_offload_info_fill_ns(void *private_data) +{ + struct ns_get_path_bpf_map_args *args = private_data; + struct ns_common *ns; + struct net *net; + + rtnl_lock(); + down_read(&bpf_devs_lock); + + if (args->offmap->netdev) { + args->info->ifindex = args->offmap->netdev->ifindex; + net = dev_net(args->offmap->netdev); + get_net(net); + ns = &net->ns; + } else { + args->info->ifindex = 0; + ns = NULL; + } + + up_read(&bpf_devs_lock); + rtnl_unlock(); + + return ns; +} + +int bpf_map_offload_info_fill(struct bpf_map_info *info, struct bpf_map *map) +{ + struct ns_get_path_bpf_map_args args = { + .offmap = map_to_offmap(map), + .info = info, + }; + struct inode *ns_inode; + struct path ns_path; + void *res; + + res = ns_get_path_cb(&ns_path, bpf_map_offload_info_fill_ns, &args); + if (IS_ERR(res)) { + if (!info->ifindex) + return -ENODEV; + return PTR_ERR(res); + } + + ns_inode = ns_path.dentry->d_inode; + info->netns_dev = new_encode_dev(ns_inode->i_sb->s_dev); + info->netns_ino = ns_inode->i_ino; + path_put(&ns_path); + + return 0; +} + +bool bpf_offload_dev_match(struct bpf_prog *prog, struct bpf_map *map) +{ + struct bpf_offloaded_map *offmap; + struct bpf_prog_offload *offload; + bool ret; + + if (!bpf_prog_is_dev_bound(prog->aux) || !bpf_map_is_dev_bound(map)) + return false; + + down_read(&bpf_devs_lock); + offload = prog->aux->offload; + offmap = map_to_offmap(map); + + ret = offload && offload->netdev == offmap->netdev; + up_read(&bpf_devs_lock); + + return ret; +} + +static void bpf_offload_orphan_all_progs(struct net_device *netdev) +{ + struct bpf_prog_offload *offload, *tmp; + + list_for_each_entry_safe(offload, tmp, &bpf_prog_offload_devs, offloads) + if (offload->netdev == netdev) + __bpf_prog_offload_destroy(offload->prog); +} + +static void bpf_offload_orphan_all_maps(struct net_device *netdev) +{ + struct bpf_offloaded_map *offmap, *tmp; + + list_for_each_entry_safe(offmap, tmp, &bpf_map_offload_devs, offloads) + if (offmap->netdev == netdev) + __bpf_map_offload_destroy(offmap); +} + static int bpf_offload_notification(struct notifier_block *notifier, ulong event, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); - struct bpf_dev_offload *offload, *tmp; ASSERT_RTNL(); @@ -253,11 +519,8 @@ static int bpf_offload_notification(struct notifier_block *notifier, break; down_write(&bpf_devs_lock); - list_for_each_entry_safe(offload, tmp, &bpf_prog_offload_devs, - offloads) { - if (offload->netdev == netdev) - __bpf_prog_offload_destroy(offload->prog); - } + bpf_offload_orphan_all_progs(netdev); + bpf_offload_orphan_all_maps(netdev); up_write(&bpf_devs_lock); break; default: diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 3f662ee23a34..0314d1783d77 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -513,13 +513,7 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr) if (!stab) return ERR_PTR(-ENOMEM); - /* mandatory map attributes */ - stab->map.map_type = attr->map_type; - stab->map.key_size = attr->key_size; - stab->map.value_size = attr->value_size; - stab->map.max_entries = attr->max_entries; - stab->map.map_flags = attr->map_flags; - stab->map.numa_node = bpf_map_attr_numa_node(attr); + bpf_map_init_from_attr(&stab->map, attr); /* make sure page count doesn't overflow */ cost = (u64) stab->map.max_entries * sizeof(struct sock *); @@ -583,8 +577,15 @@ static void sock_map_free(struct bpf_map *map) write_lock_bh(&sock->sk_callback_lock); psock = smap_psock_sk(sock); - smap_list_remove(psock, &stab->sock_map[i]); - smap_release_sock(psock, sock); + /* This check handles a racing sock event that can get the + * sk_callback_lock before this case but after xchg happens + * causing the refcnt to hit zero and sock user data (psock) + * to be null and queued for garbage collection. + */ + if (likely(psock)) { + smap_list_remove(psock, &stab->sock_map[i]); + smap_release_sock(psock, sock); + } write_unlock_bh(&sock->sk_callback_lock); } rcu_read_unlock(); diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 6c63c2222ea8..b0ecf43f5894 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -88,14 +88,10 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) if (cost >= U32_MAX - PAGE_SIZE) goto free_smap; - smap->map.map_type = attr->map_type; - smap->map.key_size = attr->key_size; + bpf_map_init_from_attr(&smap->map, attr); 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; - smap->map.numa_node = bpf_map_attr_numa_node(attr); err = bpf_map_precharge_memlock(smap->map.pages); if (err) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 2bac0dc8baba..5bdb0cc84ad2 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -94,18 +94,34 @@ static int check_uarg_tail_zero(void __user *uaddr, return 0; } +const struct bpf_map_ops bpf_map_offload_ops = { + .map_alloc = bpf_map_offload_map_alloc, + .map_free = bpf_map_offload_map_free, +}; + static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) { + const struct bpf_map_ops *ops; struct bpf_map *map; + int err; - if (attr->map_type >= ARRAY_SIZE(bpf_map_types) || - !bpf_map_types[attr->map_type]) + if (attr->map_type >= ARRAY_SIZE(bpf_map_types)) + return ERR_PTR(-EINVAL); + ops = bpf_map_types[attr->map_type]; + if (!ops) return ERR_PTR(-EINVAL); - map = bpf_map_types[attr->map_type]->map_alloc(attr); + if (ops->map_alloc_check) { + err = ops->map_alloc_check(attr); + if (err) + return ERR_PTR(err); + } + if (attr->map_ifindex) + ops = &bpf_map_offload_ops; + map = ops->map_alloc(attr); if (IS_ERR(map)) return map; - map->ops = bpf_map_types[attr->map_type]; + map->ops = ops; map->map_type = attr->map_type; return map; } @@ -134,6 +150,16 @@ void bpf_map_area_free(void *area) kvfree(area); } +void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr) +{ + map->map_type = attr->map_type; + map->key_size = attr->key_size; + map->value_size = attr->value_size; + map->max_entries = attr->max_entries; + map->map_flags = attr->map_flags; + map->numa_node = bpf_map_attr_numa_node(attr); +} + int bpf_map_precharge_memlock(u32 pages) { struct user_struct *user = get_current_user(); @@ -189,16 +215,25 @@ static int bpf_map_alloc_id(struct bpf_map *map) return id > 0 ? 0 : id; } -static void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock) +void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock) { unsigned long flags; + /* Offloaded maps are removed from the IDR store when their device + * disappears - even if someone holds an fd to them they are unusable, + * the memory is gone, all ops will fail; they are simply waiting for + * refcnt to drop to be freed. + */ + if (!map->id) + return; + if (do_idr_lock) spin_lock_irqsave(&map_idr_lock, flags); else __acquire(&map_idr_lock); idr_remove(&map_idr, map->id); + map->id = 0; if (do_idr_lock) spin_unlock_irqrestore(&map_idr_lock, flags); @@ -378,7 +413,7 @@ static int bpf_obj_name_cpy(char *dst, const char *src) return 0; } -#define BPF_MAP_CREATE_LAST_FIELD map_name +#define BPF_MAP_CREATE_LAST_FIELD map_ifindex /* called via syscall */ static int map_create(union bpf_attr *attr) { @@ -566,8 +601,10 @@ static int map_lookup_elem(union bpf_attr *attr) if (!value) goto free_key; - if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || - map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { + if (bpf_map_is_dev_bound(map)) { + err = bpf_map_offload_lookup_elem(map, key, value); + } else if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { err = bpf_percpu_hash_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_copy(map, key, value); @@ -654,7 +691,10 @@ static int map_update_elem(union bpf_attr *attr) goto free_value; /* Need to create a kthread, thus must support schedule */ - if (map->map_type == BPF_MAP_TYPE_CPUMAP) { + if (bpf_map_is_dev_bound(map)) { + err = bpf_map_offload_update_elem(map, key, value, attr->flags); + goto out; + } else if (map->map_type == BPF_MAP_TYPE_CPUMAP) { err = map->ops->map_update_elem(map, key, value, attr->flags); goto out; } @@ -731,6 +771,11 @@ static int map_delete_elem(union bpf_attr *attr) goto err_put; } + if (bpf_map_is_dev_bound(map)) { + err = bpf_map_offload_delete_elem(map, key); + goto out; + } + preempt_disable(); __this_cpu_inc(bpf_prog_active); rcu_read_lock(); @@ -738,7 +783,7 @@ static int map_delete_elem(union bpf_attr *attr) rcu_read_unlock(); __this_cpu_dec(bpf_prog_active); preempt_enable(); - +out: if (!err) trace_bpf_map_delete_elem(map, ufd, key); kfree(key); @@ -788,9 +833,15 @@ static int map_get_next_key(union bpf_attr *attr) if (!next_key) goto free_key; + if (bpf_map_is_dev_bound(map)) { + err = bpf_map_offload_get_next_key(map, key, next_key); + goto out; + } + rcu_read_lock(); err = map->ops->map_get_next_key(map, key, next_key); rcu_read_unlock(); +out: if (err) goto free_next_key; @@ -1453,6 +1504,8 @@ static int bpf_prog_test_run(const union bpf_attr *attr, struct bpf_prog *prog; int ret = -ENOTSUPP; + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; if (CHECK_ATTR(BPF_PROG_TEST_RUN)) return -EINVAL; @@ -1673,19 +1726,6 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, goto done; } - ulen = info.jited_prog_len; - info.jited_prog_len = prog->jited_len; - if (info.jited_prog_len && ulen) { - if (bpf_dump_raw_ok()) { - 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; - } else { - info.jited_prog_insns = 0; - } - } - ulen = info.xlated_prog_len; info.xlated_prog_len = bpf_prog_insn_size(prog); if (info.xlated_prog_len && ulen) { @@ -1711,6 +1751,24 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, err = bpf_prog_offload_info_fill(&info, prog); if (err) return err; + goto done; + } + + /* NOTE: the following code is supposed to be skipped for offload. + * bpf_prog_offload_info_fill() is the place to fill similar fields + * for offload. + */ + ulen = info.jited_prog_len; + info.jited_prog_len = prog->jited_len; + if (info.jited_prog_len && ulen) { + if (bpf_dump_raw_ok()) { + 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; + } else { + info.jited_prog_insns = 0; + } } done: @@ -1743,6 +1801,12 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map, info.map_flags = map->map_flags; memcpy(info.name, map->name, sizeof(map->name)); + if (bpf_map_is_dev_bound(map)) { + err = bpf_map_offload_info_fill(&info, map); + if (err) + return err; + } + if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) return -EFAULT; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index a2b211262c25..dfb138b46488 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -169,11 +169,11 @@ struct bpf_call_arg_meta { 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 + * bpf_verifier_log_write() is used to dump the verification trace to the log, + * so the user can figure out what's wrong with the program */ -static __printf(2, 3) void verbose(struct bpf_verifier_env *env, - const char *fmt, ...) +__printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env, + const char *fmt, ...) { struct bpf_verifer_log *log = &env->log; unsigned int n; @@ -197,6 +197,14 @@ static __printf(2, 3) void verbose(struct bpf_verifier_env *env, else log->ubuf = NULL; } +EXPORT_SYMBOL_GPL(bpf_verifier_log_write); +/* Historically bpf_verifier_log_write was called verbose, but the name was too + * generic for symbol export. The function was renamed, but not the calls in + * the verifier to avoid complicating backports. Hence the alias below. + */ +static __printf(2, 3) void verbose(struct bpf_verifier_env *env, + const char *fmt, ...) + __attribute__((alias("bpf_verifier_log_write"))); static bool type_is_pkt_pointer(enum bpf_reg_type type) { @@ -375,6 +383,8 @@ static int realloc_func_state(struct bpf_func_state *state, int size, static void free_func_state(struct bpf_func_state *state) { + if (!state) + return; kfree(state->stack); kfree(state); } @@ -487,6 +497,8 @@ static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env, } return &elem->st; err: + free_verifier_state(env->cur_state, true); + env->cur_state = NULL; /* pop all elements and return */ while (!pop_stack(env, NULL, NULL)); return NULL; @@ -1337,6 +1349,13 @@ static bool is_pointer_value(struct bpf_verifier_env *env, int regno) return __is_pointer_value(env->allow_ptr_leaks, cur_regs(env) + regno); } +static bool is_ctx_reg(struct bpf_verifier_env *env, int regno) +{ + const struct bpf_reg_state *reg = cur_regs(env) + regno; + + return reg->type == PTR_TO_CTX; +} + static int check_pkt_ptr_alignment(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int off, int size, bool strict) @@ -1511,6 +1530,7 @@ continue_func: goto continue_func; } +#ifndef CONFIG_BPF_JIT_ALWAYS_ON static int get_callee_stack_depth(struct bpf_verifier_env *env, const struct bpf_insn *insn, int idx) { @@ -1525,6 +1545,7 @@ static int get_callee_stack_depth(struct bpf_verifier_env *env, subprog++; return env->subprog_stack_depth[subprog]; } +#endif /* truncate register to smaller size (in bytes) * must be called with size < BPF_REG_SIZE @@ -1714,6 +1735,12 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins return -EACCES; } + if (is_ctx_reg(env, insn->dst_reg)) { + verbose(env, "BPF_XADD stores into R%d context is not allowed\n", + insn->dst_reg); + return -EACCES; + } + /* check whether atomic_add can read the memory */ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_READ, -1); @@ -1823,6 +1850,19 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, } } +static bool arg_type_is_mem_ptr(enum bpf_arg_type type) +{ + return type == ARG_PTR_TO_MEM || + type == ARG_PTR_TO_MEM_OR_NULL || + type == ARG_PTR_TO_UNINIT_MEM; +} + +static bool arg_type_is_mem_size(enum bpf_arg_type type) +{ + return type == ARG_CONST_SIZE || + type == ARG_CONST_SIZE_OR_ZERO; +} + static int check_func_arg(struct bpf_verifier_env *env, u32 regno, enum bpf_arg_type arg_type, struct bpf_call_arg_meta *meta) @@ -1872,9 +1912,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, expected_type = PTR_TO_CTX; if (type != expected_type) goto err_type; - } else if (arg_type == ARG_PTR_TO_MEM || - arg_type == ARG_PTR_TO_MEM_OR_NULL || - arg_type == ARG_PTR_TO_UNINIT_MEM) { + } else if (arg_type_is_mem_ptr(arg_type)) { expected_type = PTR_TO_STACK; /* One exception here. In case function allows for NULL to be * passed in as argument, it's a SCALAR_VALUE type. Final test @@ -1935,25 +1973,12 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, err = check_stack_boundary(env, regno, meta->map_ptr->value_size, false, NULL); - } else if (arg_type == ARG_CONST_SIZE || - arg_type == ARG_CONST_SIZE_OR_ZERO) { + } else if (arg_type_is_mem_size(arg_type)) { bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO); - /* 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(env, - "ARG_CONST_SIZE cannot be first argument\n"); - return -EACCES; - } - /* The register is SCALAR_VALUE; the access check * happens using its boundaries. */ - if (!tnum_is_const(reg->var_off)) /* For unprivileged variable accesses, disable raw * mode so that the program is required to @@ -2097,7 +2122,7 @@ error: return -EINVAL; } -static int check_raw_mode(const struct bpf_func_proto *fn) +static bool check_raw_mode_ok(const struct bpf_func_proto *fn) { int count = 0; @@ -2112,7 +2137,44 @@ static int check_raw_mode(const struct bpf_func_proto *fn) if (fn->arg5_type == ARG_PTR_TO_UNINIT_MEM) count++; - return count > 1 ? -EINVAL : 0; + /* We only support one arg being in raw mode at the moment, + * which is sufficient for the helper functions we have + * right now. + */ + return count <= 1; +} + +static bool check_args_pair_invalid(enum bpf_arg_type arg_curr, + enum bpf_arg_type arg_next) +{ + return (arg_type_is_mem_ptr(arg_curr) && + !arg_type_is_mem_size(arg_next)) || + (!arg_type_is_mem_ptr(arg_curr) && + arg_type_is_mem_size(arg_next)); +} + +static bool check_arg_pair_ok(const struct bpf_func_proto *fn) +{ + /* bpf_xxx(..., buf, len) call will access 'len' + * bytes from memory 'buf'. Both arg types need + * to be paired, so make sure there's no buggy + * helper function specification. + */ + if (arg_type_is_mem_size(fn->arg1_type) || + arg_type_is_mem_ptr(fn->arg5_type) || + check_args_pair_invalid(fn->arg1_type, fn->arg2_type) || + check_args_pair_invalid(fn->arg2_type, fn->arg3_type) || + check_args_pair_invalid(fn->arg3_type, fn->arg4_type) || + check_args_pair_invalid(fn->arg4_type, fn->arg5_type)) + return false; + + return true; +} + +static int check_func_proto(const struct bpf_func_proto *fn) +{ + return check_raw_mode_ok(fn) && + check_arg_pair_ok(fn) ? 0 : -EINVAL; } /* Packet data might have moved, any old PTR_TO_PACKET[_META,_END] @@ -2268,7 +2330,6 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn if (env->ops->get_func_proto) fn = env->ops->get_func_proto(func_id); - if (!fn) { verbose(env, "unknown func %s#%d\n", func_id_name(func_id), func_id); @@ -2292,10 +2353,7 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn memset(&meta, 0, sizeof(meta)); meta.pkt_access = fn->pkt_access; - /* We only support one arg being in raw mode at the moment, which - * is sufficient for the helper functions we have right now. - */ - err = check_raw_mode(fn); + err = check_func_proto(fn); if (err) { verbose(env, "kernel subsystem misconfigured func %s#%d\n", func_id_name(func_id), func_id); @@ -2309,6 +2367,13 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn err = check_func_arg(env, BPF_REG_2, fn->arg2_type, &meta); if (err) return err; + if (func_id == BPF_FUNC_tail_call) { + if (meta.map_ptr == NULL) { + verbose(env, "verifier bug\n"); + return -EINVAL; + } + env->insn_aux_data[insn_idx].map_ptr = meta.map_ptr; + } err = check_func_arg(env, BPF_REG_3, fn->arg3_type, &meta); if (err) return err; @@ -2457,17 +2522,13 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, dst_reg = ®s[dst]; - if (WARN_ON_ONCE(known && (smin_val != smax_val))) { - print_verifier_state(env, state); - verbose(env, - "verifier internal error: known but bad sbounds\n"); - return -EINVAL; - } - if (WARN_ON_ONCE(known && (umin_val != umax_val))) { - print_verifier_state(env, state); - verbose(env, - "verifier internal error: known but bad ubounds\n"); - return -EINVAL; + if ((known && (smin_val != smax_val || umin_val != umax_val)) || + smin_val > smax_val || umin_val > umax_val) { + /* Taint dst register if offset had invalid bounds derived from + * e.g. dead branches. + */ + __mark_reg_unknown(dst_reg); + return 0; } if (BPF_CLASS(insn->code) != BPF_ALU64) { @@ -2659,6 +2720,15 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, src_known = tnum_is_const(src_reg.var_off); dst_known = tnum_is_const(dst_reg->var_off); + if ((src_known && (smin_val != smax_val || umin_val != umax_val)) || + smin_val > smax_val || umin_val > umax_val) { + /* Taint dst register if offset had invalid bounds derived from + * e.g. dead branches. + */ + __mark_reg_unknown(dst_reg); + return 0; + } + if (!src_known && opcode != BPF_ADD && opcode != BPF_SUB && opcode != BPF_AND) { __mark_reg_unknown(dst_reg); @@ -3070,6 +3140,11 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) return -EINVAL; } + if (opcode == BPF_ARSH && BPF_CLASS(insn->code) != BPF_ALU64) { + verbose(env, "BPF_ARSH not supported for 32 bit ALU\n"); + return -EINVAL; + } + if ((opcode == BPF_LSH || opcode == BPF_RSH || opcode == BPF_ARSH) && BPF_SRC(insn->code) == BPF_K) { int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32; @@ -4635,6 +4710,12 @@ static int do_check(struct bpf_verifier_env *env) if (err) return err; + if (is_ctx_reg(env, insn->dst_reg)) { + verbose(env, "BPF_ST stores into R%d context is not allowed\n", + insn->dst_reg); + return -EACCES; + } + /* check that memory (dst_reg + off) is writeable */ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, @@ -4753,7 +4834,8 @@ process_bpf_exit: insn_idx++; } - verbose(env, "processed %d insns, stack depth ", insn_processed); + verbose(env, "processed %d insns (limit %d), stack depth ", + insn_processed, BPF_COMPLEXITY_LIMIT_INSNS); for (i = 0; i < env->subprog_cnt + 1; i++) { u32 depth = env->subprog_stack_depth[i]; @@ -4795,6 +4877,13 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, return -EINVAL; } } + + if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) && + !bpf_offload_dev_match(prog, map)) { + verbose(env, "offload device mismatch between prog and map\n"); + return -EINVAL; + } + return 0; } @@ -5252,14 +5341,20 @@ out_free: static int fixup_call_args(struct bpf_verifier_env *env) { +#ifndef CONFIG_BPF_JIT_ALWAYS_ON struct bpf_prog *prog = env->prog; struct bpf_insn *insn = prog->insnsi; int i, depth; +#endif + int err; - if (env->prog->jit_requested) - if (jit_subprogs(env) == 0) + err = 0; + if (env->prog->jit_requested) { + err = jit_subprogs(env); + if (err == 0) return 0; - + } +#ifndef CONFIG_BPF_JIT_ALWAYS_ON for (i = 0; i < prog->len; i++, insn++) { if (insn->code != (BPF_JMP | BPF_CALL) || insn->src_reg != BPF_PSEUDO_CALL) @@ -5269,7 +5364,9 @@ static int fixup_call_args(struct bpf_verifier_env *env) return depth; bpf_patch_call_args(insn, depth); } - return 0; + err = 0; +#endif + return err; } /* fixup insn->imm field of bpf_call instructions @@ -5289,6 +5386,24 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) int i, cnt, delta = 0; for (i = 0; i < insn_cnt; i++, insn++) { + if (insn->code == (BPF_ALU | BPF_MOD | BPF_X) || + insn->code == (BPF_ALU | BPF_DIV | BPF_X)) { + /* due to JIT bugs clear upper 32-bits of src register + * before div/mod operation + */ + insn_buf[0] = BPF_MOV32_REG(insn->src_reg, insn->src_reg); + insn_buf[1] = *insn; + cnt = 2; + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } + if (insn->code != (BPF_JMP | BPF_CALL)) continue; if (insn->src_reg == BPF_PSEUDO_CALL) @@ -5316,6 +5431,35 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) */ insn->imm = 0; insn->code = BPF_JMP | BPF_TAIL_CALL; + + /* instead of changing every JIT dealing with tail_call + * emit two extra insns: + * if (index >= max_entries) goto out; + * index &= array->index_mask; + * to avoid out-of-bounds cpu speculation + */ + map_ptr = env->insn_aux_data[i + delta].map_ptr; + if (map_ptr == BPF_MAP_PTR_POISON) { + verbose(env, "tail_call abusing map_ptr\n"); + return -EINVAL; + } + if (!map_ptr->unpriv_array) + continue; + insn_buf[0] = BPF_JMP_IMM(BPF_JGE, BPF_REG_3, + map_ptr->max_entries, 2); + insn_buf[1] = BPF_ALU32_IMM(BPF_AND, BPF_REG_3, + container_of(map_ptr, + struct bpf_array, + map)->index_mask); + insn_buf[2] = *insn; + cnt = 3; + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; continue; } diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 2cf06c274e4c..7e4c44538119 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -4447,6 +4447,7 @@ static struct cftype cgroup_base_files[] = { }, { .name = "cgroup.threads", + .flags = CFTYPE_NS_DELEGATABLE, .release = cgroup_procs_release, .seq_start = cgroup_threads_start, .seq_next = cgroup_procs_next, diff --git a/kernel/crash_core.c b/kernel/crash_core.c index b3663896278e..4f63597c824d 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -410,7 +410,7 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_SYMBOL(contig_page_data); #endif #ifdef CONFIG_SPARSEMEM - VMCOREINFO_SYMBOL(mem_section); + VMCOREINFO_SYMBOL_ARRAY(mem_section); VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS); VMCOREINFO_STRUCT_SIZE(mem_section); VMCOREINFO_OFFSET(mem_section, section_mem_map); diff --git a/kernel/delayacct.c b/kernel/delayacct.c index 4a1c33416b6a..e2764d767f18 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -51,16 +51,16 @@ void __delayacct_tsk_init(struct task_struct *tsk) * Finish delay accounting for a statistic using its timestamps (@start), * accumalator (@total) and @count */ -static void delayacct_end(u64 *start, u64 *total, u32 *count) +static void delayacct_end(spinlock_t *lock, u64 *start, u64 *total, u32 *count) { s64 ns = ktime_get_ns() - *start; unsigned long flags; if (ns > 0) { - spin_lock_irqsave(¤t->delays->lock, flags); + spin_lock_irqsave(lock, flags); *total += ns; (*count)++; - spin_unlock_irqrestore(¤t->delays->lock, flags); + spin_unlock_irqrestore(lock, flags); } } @@ -69,17 +69,25 @@ void __delayacct_blkio_start(void) current->delays->blkio_start = ktime_get_ns(); } -void __delayacct_blkio_end(void) +/* + * We cannot rely on the `current` macro, as we haven't yet switched back to + * the process being woken. + */ +void __delayacct_blkio_end(struct task_struct *p) { - if (current->delays->flags & DELAYACCT_PF_SWAPIN) - /* Swapin block I/O */ - delayacct_end(¤t->delays->blkio_start, - ¤t->delays->swapin_delay, - ¤t->delays->swapin_count); - else /* Other block I/O */ - delayacct_end(¤t->delays->blkio_start, - ¤t->delays->blkio_delay, - ¤t->delays->blkio_count); + struct task_delay_info *delays = p->delays; + u64 *total; + u32 *count; + + if (p->delays->flags & DELAYACCT_PF_SWAPIN) { + total = &delays->swapin_delay; + count = &delays->swapin_count; + } else { + total = &delays->blkio_delay; + count = &delays->blkio_count; + } + + delayacct_end(&delays->lock, &delays->blkio_start, total, count); } int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) @@ -153,8 +161,10 @@ void __delayacct_freepages_start(void) void __delayacct_freepages_end(void) { - delayacct_end(¤t->delays->freepages_start, - ¤t->delays->freepages_delay, - ¤t->delays->freepages_count); + delayacct_end( + ¤t->delays->lock, + ¤t->delays->freepages_start, + ¤t->delays->freepages_delay, + ¤t->delays->freepages_count); } diff --git a/kernel/fail_function.c b/kernel/fail_function.c new file mode 100644 index 000000000000..21b0122cb39c --- /dev/null +++ b/kernel/fail_function.c @@ -0,0 +1,349 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * fail_function.c: Function-based error injection + */ +#include <linux/error-injection.h> +#include <linux/debugfs.h> +#include <linux/fault-inject.h> +#include <linux/kallsyms.h> +#include <linux/kprobes.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/slab.h> +#include <linux/uaccess.h> + +static int fei_kprobe_handler(struct kprobe *kp, struct pt_regs *regs); + +struct fei_attr { + struct list_head list; + struct kprobe kp; + unsigned long retval; +}; +static DEFINE_MUTEX(fei_lock); +static LIST_HEAD(fei_attr_list); +static DECLARE_FAULT_ATTR(fei_fault_attr); +static struct dentry *fei_debugfs_dir; + +static unsigned long adjust_error_retval(unsigned long addr, unsigned long retv) +{ + switch (get_injectable_error_type(addr)) { + case EI_ETYPE_NULL: + if (retv != 0) + return 0; + break; + case EI_ETYPE_ERRNO: + if (retv < (unsigned long)-MAX_ERRNO) + return (unsigned long)-EINVAL; + break; + case EI_ETYPE_ERRNO_NULL: + if (retv != 0 && retv < (unsigned long)-MAX_ERRNO) + return (unsigned long)-EINVAL; + break; + } + + return retv; +} + +static struct fei_attr *fei_attr_new(const char *sym, unsigned long addr) +{ + struct fei_attr *attr; + + attr = kzalloc(sizeof(*attr), GFP_KERNEL); + if (attr) { + attr->kp.symbol_name = kstrdup(sym, GFP_KERNEL); + if (!attr->kp.symbol_name) { + kfree(attr); + return NULL; + } + attr->kp.pre_handler = fei_kprobe_handler; + attr->retval = adjust_error_retval(addr, 0); + INIT_LIST_HEAD(&attr->list); + } + return attr; +} + +static void fei_attr_free(struct fei_attr *attr) +{ + if (attr) { + kfree(attr->kp.symbol_name); + kfree(attr); + } +} + +static struct fei_attr *fei_attr_lookup(const char *sym) +{ + struct fei_attr *attr; + + list_for_each_entry(attr, &fei_attr_list, list) { + if (!strcmp(attr->kp.symbol_name, sym)) + return attr; + } + + return NULL; +} + +static bool fei_attr_is_valid(struct fei_attr *_attr) +{ + struct fei_attr *attr; + + list_for_each_entry(attr, &fei_attr_list, list) { + if (attr == _attr) + return true; + } + + return false; +} + +static int fei_retval_set(void *data, u64 val) +{ + struct fei_attr *attr = data; + unsigned long retv = (unsigned long)val; + int err = 0; + + mutex_lock(&fei_lock); + /* + * Since this operation can be done after retval file is removed, + * It is safer to check the attr is still valid before accessing + * its member. + */ + if (!fei_attr_is_valid(attr)) { + err = -ENOENT; + goto out; + } + + if (attr->kp.addr) { + if (adjust_error_retval((unsigned long)attr->kp.addr, + val) != retv) + err = -EINVAL; + } + if (!err) + attr->retval = val; +out: + mutex_unlock(&fei_lock); + + return err; +} + +static int fei_retval_get(void *data, u64 *val) +{ + struct fei_attr *attr = data; + int err = 0; + + mutex_lock(&fei_lock); + /* Here we also validate @attr to ensure it still exists. */ + if (!fei_attr_is_valid(attr)) + err = -ENOENT; + else + *val = attr->retval; + mutex_unlock(&fei_lock); + + return err; +} +DEFINE_DEBUGFS_ATTRIBUTE(fei_retval_ops, fei_retval_get, fei_retval_set, + "%llx\n"); + +static int fei_debugfs_add_attr(struct fei_attr *attr) +{ + struct dentry *dir; + + dir = debugfs_create_dir(attr->kp.symbol_name, fei_debugfs_dir); + if (!dir) + return -ENOMEM; + + if (!debugfs_create_file("retval", 0600, dir, attr, &fei_retval_ops)) { + debugfs_remove_recursive(dir); + return -ENOMEM; + } + + return 0; +} + +static void fei_debugfs_remove_attr(struct fei_attr *attr) +{ + struct dentry *dir; + + dir = debugfs_lookup(attr->kp.symbol_name, fei_debugfs_dir); + if (dir) + debugfs_remove_recursive(dir); +} + +static int fei_kprobe_handler(struct kprobe *kp, struct pt_regs *regs) +{ + struct fei_attr *attr = container_of(kp, struct fei_attr, kp); + + if (should_fail(&fei_fault_attr, 1)) { + regs_set_return_value(regs, attr->retval); + override_function_with_return(regs); + /* Kprobe specific fixup */ + reset_current_kprobe(); + preempt_enable_no_resched(); + return 1; + } + + return 0; +} +NOKPROBE_SYMBOL(fei_kprobe_handler) + +static void *fei_seq_start(struct seq_file *m, loff_t *pos) +{ + mutex_lock(&fei_lock); + return seq_list_start(&fei_attr_list, *pos); +} + +static void fei_seq_stop(struct seq_file *m, void *v) +{ + mutex_unlock(&fei_lock); +} + +static void *fei_seq_next(struct seq_file *m, void *v, loff_t *pos) +{ + return seq_list_next(v, &fei_attr_list, pos); +} + +static int fei_seq_show(struct seq_file *m, void *v) +{ + struct fei_attr *attr = list_entry(v, struct fei_attr, list); + + seq_printf(m, "%pf\n", attr->kp.addr); + return 0; +} + +static const struct seq_operations fei_seq_ops = { + .start = fei_seq_start, + .next = fei_seq_next, + .stop = fei_seq_stop, + .show = fei_seq_show, +}; + +static int fei_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &fei_seq_ops); +} + +static void fei_attr_remove(struct fei_attr *attr) +{ + fei_debugfs_remove_attr(attr); + unregister_kprobe(&attr->kp); + list_del(&attr->list); + fei_attr_free(attr); +} + +static void fei_attr_remove_all(void) +{ + struct fei_attr *attr, *n; + + list_for_each_entry_safe(attr, n, &fei_attr_list, list) { + fei_attr_remove(attr); + } +} + +static ssize_t fei_write(struct file *file, const char __user *buffer, + size_t count, loff_t *ppos) +{ + struct fei_attr *attr; + unsigned long addr; + char *buf, *sym; + int ret; + + /* cut off if it is too long */ + if (count > KSYM_NAME_LEN) + count = KSYM_NAME_LEN; + buf = kmalloc(sizeof(char) * (count + 1), GFP_KERNEL); + if (!buf) + return -ENOMEM; + + if (copy_from_user(buf, buffer, count)) { + ret = -EFAULT; + goto out; + } + buf[count] = '\0'; + sym = strstrip(buf); + + mutex_lock(&fei_lock); + + /* Writing just spaces will remove all injection points */ + if (sym[0] == '\0') { + fei_attr_remove_all(); + ret = count; + goto out; + } + /* Writing !function will remove one injection point */ + if (sym[0] == '!') { + attr = fei_attr_lookup(sym + 1); + if (!attr) { + ret = -ENOENT; + goto out; + } + fei_attr_remove(attr); + ret = count; + goto out; + } + + addr = kallsyms_lookup_name(sym); + if (!addr) { + ret = -EINVAL; + goto out; + } + if (!within_error_injection_list(addr)) { + ret = -ERANGE; + goto out; + } + if (fei_attr_lookup(sym)) { + ret = -EBUSY; + goto out; + } + attr = fei_attr_new(sym, addr); + if (!attr) { + ret = -ENOMEM; + goto out; + } + + ret = register_kprobe(&attr->kp); + if (!ret) + ret = fei_debugfs_add_attr(attr); + if (ret < 0) + fei_attr_remove(attr); + else { + list_add_tail(&attr->list, &fei_attr_list); + ret = count; + } +out: + kfree(buf); + mutex_unlock(&fei_lock); + return ret; +} + +static const struct file_operations fei_ops = { + .open = fei_open, + .read = seq_read, + .write = fei_write, + .llseek = seq_lseek, + .release = seq_release, +}; + +static int __init fei_debugfs_init(void) +{ + struct dentry *dir; + + dir = fault_create_debugfs_attr("fail_function", NULL, + &fei_fault_attr); + if (IS_ERR(dir)) + return PTR_ERR(dir); + + /* injectable attribute is just a symlink of error_inject/list */ + if (!debugfs_create_symlink("injectable", dir, + "../error_injection/list")) + goto error; + + if (!debugfs_create_file("inject", 0600, dir, NULL, &fei_ops)) + goto error; + + fei_debugfs_dir = dir; + + return 0; +error: + debugfs_remove_recursive(dir); + return -ENOMEM; +} + +late_initcall(fei_debugfs_init); diff --git a/kernel/futex.c b/kernel/futex.c index 57d0b3657e16..8c5424dd5924 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1878,6 +1878,9 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags, struct futex_q *this, *next; DEFINE_WAKE_Q(wake_q); + if (nr_wake < 0 || nr_requeue < 0) + return -EINVAL; + /* * When PI not supported: return -ENOSYS if requeue_pi is true, * consequently the compiler knows requeue_pi is always false past @@ -2294,21 +2297,17 @@ static void unqueue_me_pi(struct futex_q *q) spin_unlock(q->lock_ptr); } -/* - * Fixup the pi_state owner with the new owner. - * - * Must be called with hash bucket lock held and mm->sem held for non - * private futexes. - */ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, - struct task_struct *newowner) + struct task_struct *argowner) { - u32 newtid = task_pid_vnr(newowner) | FUTEX_WAITERS; struct futex_pi_state *pi_state = q->pi_state; u32 uval, uninitialized_var(curval), newval; - struct task_struct *oldowner; + struct task_struct *oldowner, *newowner; + u32 newtid; int ret; + lockdep_assert_held(q->lock_ptr); + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); oldowner = pi_state->owner; @@ -2317,11 +2316,17 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, newtid |= FUTEX_OWNER_DIED; /* - * We are here either because we stole the rtmutex from the - * previous highest priority waiter or we are the highest priority - * waiter but have failed to get the rtmutex the first time. + * We are here because either: + * + * - we stole the lock and pi_state->owner needs updating to reflect + * that (@argowner == current), + * + * or: + * + * - someone stole our lock and we need to fix things to point to the + * new owner (@argowner == NULL). * - * We have to replace the newowner TID in the user space variable. + * Either way, we have to replace the TID in the user space variable. * This must be atomic as we have to preserve the owner died bit here. * * Note: We write the user space value _before_ changing the pi_state @@ -2334,6 +2339,42 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, * in the PID check in lookup_pi_state. */ retry: + if (!argowner) { + if (oldowner != current) { + /* + * We raced against a concurrent self; things are + * already fixed up. Nothing to do. + */ + ret = 0; + goto out_unlock; + } + + if (__rt_mutex_futex_trylock(&pi_state->pi_mutex)) { + /* We got the lock after all, nothing to fix. */ + ret = 0; + goto out_unlock; + } + + /* + * Since we just failed the trylock; there must be an owner. + */ + newowner = rt_mutex_owner(&pi_state->pi_mutex); + BUG_ON(!newowner); + } else { + WARN_ON_ONCE(argowner != current); + if (oldowner == current) { + /* + * We raced against a concurrent self; things are + * already fixed up. Nothing to do. + */ + ret = 0; + goto out_unlock; + } + newowner = argowner; + } + + newtid = task_pid_vnr(newowner) | FUTEX_WAITERS; + if (get_futex_value_locked(&uval, uaddr)) goto handle_fault; @@ -2434,9 +2475,9 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked) * Got the lock. We might not be the anticipated owner if we * did a lock-steal - fix up the PI-state in that case: * - * We can safely read pi_state->owner without holding wait_lock - * because we now own the rt_mutex, only the owner will attempt - * to change it. + * Speculative pi_state->owner read (we don't hold wait_lock); + * since we own the lock pi_state->owner == current is the + * stable state, anything else needs more attention. */ if (q->pi_state->owner != current) ret = fixup_pi_state_owner(uaddr, q, current); @@ -2444,6 +2485,19 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked) } /* + * If we didn't get the lock; check if anybody stole it from us. In + * that case, we need to fix up the uval to point to them instead of + * us, otherwise bad things happen. [10] + * + * Another speculative read; pi_state->owner == current is unstable + * but needs our attention. + */ + if (q->pi_state->owner == current) { + ret = fixup_pi_state_owner(uaddr, q, NULL); + goto out; + } + + /* * Paranoia check. If we did not take the lock, then we should not be * the owner of the rt_mutex. */ diff --git a/kernel/kprobes.c b/kernel/kprobes.c index b4aab48ad258..da2ccf142358 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -83,16 +83,6 @@ static raw_spinlock_t *kretprobe_table_lock_ptr(unsigned long hash) return &(kretprobe_table_locks[hash].lock); } -/* List of symbols that can be overriden for error injection. */ -static LIST_HEAD(kprobe_error_injection_list); -static DEFINE_MUTEX(kprobe_ei_mutex); -struct kprobe_ei_entry { - struct list_head list; - unsigned long start_addr; - unsigned long end_addr; - void *priv; -}; - /* Blacklist -- list of struct kprobe_blacklist_entry */ static LIST_HEAD(kprobe_blacklist); @@ -1404,17 +1394,6 @@ bool within_kprobe_blacklist(unsigned long addr) return false; } -bool within_kprobe_error_injection_list(unsigned long addr) -{ - struct kprobe_ei_entry *ent; - - list_for_each_entry(ent, &kprobe_error_injection_list, list) { - if (addr >= ent->start_addr && addr < ent->end_addr) - return true; - } - return false; -} - /* * If we have a symbol_name argument, look it up and add the offset field * to it. This way, we can specify a relative address to a symbol. @@ -2189,86 +2168,6 @@ static int __init populate_kprobe_blacklist(unsigned long *start, return 0; } -#ifdef CONFIG_BPF_KPROBE_OVERRIDE -/* Markers of the _kprobe_error_inject_list section */ -extern unsigned long __start_kprobe_error_inject_list[]; -extern unsigned long __stop_kprobe_error_inject_list[]; - -/* - * Lookup and populate the kprobe_error_injection_list. - * - * For safety reasons we only allow certain functions to be overriden with - * bpf_error_injection, so we need to populate the list of the symbols that have - * been marked as safe for overriding. - */ -static void populate_kprobe_error_injection_list(unsigned long *start, - unsigned long *end, - void *priv) -{ - unsigned long *iter; - struct kprobe_ei_entry *ent; - unsigned long entry, offset = 0, size = 0; - - mutex_lock(&kprobe_ei_mutex); - for (iter = start; iter < end; iter++) { - entry = arch_deref_entry_point((void *)*iter); - - if (!kernel_text_address(entry) || - !kallsyms_lookup_size_offset(entry, &size, &offset)) { - pr_err("Failed to find error inject entry at %p\n", - (void *)entry); - continue; - } - - ent = kmalloc(sizeof(*ent), GFP_KERNEL); - if (!ent) - break; - ent->start_addr = entry; - ent->end_addr = entry + size; - ent->priv = priv; - INIT_LIST_HEAD(&ent->list); - list_add_tail(&ent->list, &kprobe_error_injection_list); - } - mutex_unlock(&kprobe_ei_mutex); -} - -static void __init populate_kernel_kprobe_ei_list(void) -{ - populate_kprobe_error_injection_list(__start_kprobe_error_inject_list, - __stop_kprobe_error_inject_list, - NULL); -} - -static void module_load_kprobe_ei_list(struct module *mod) -{ - if (!mod->num_kprobe_ei_funcs) - return; - populate_kprobe_error_injection_list(mod->kprobe_ei_funcs, - mod->kprobe_ei_funcs + - mod->num_kprobe_ei_funcs, mod); -} - -static void module_unload_kprobe_ei_list(struct module *mod) -{ - struct kprobe_ei_entry *ent, *n; - if (!mod->num_kprobe_ei_funcs) - return; - - mutex_lock(&kprobe_ei_mutex); - list_for_each_entry_safe(ent, n, &kprobe_error_injection_list, list) { - if (ent->priv == mod) { - list_del_init(&ent->list); - kfree(ent); - } - } - mutex_unlock(&kprobe_ei_mutex); -} -#else -static inline void __init populate_kernel_kprobe_ei_list(void) {} -static inline void module_load_kprobe_ei_list(struct module *m) {} -static inline void module_unload_kprobe_ei_list(struct module *m) {} -#endif - /* Module notifier call back, checking kprobes on the module */ static int kprobes_module_callback(struct notifier_block *nb, unsigned long val, void *data) @@ -2279,11 +2178,6 @@ static int kprobes_module_callback(struct notifier_block *nb, unsigned int i; int checkcore = (val == MODULE_STATE_GOING); - if (val == MODULE_STATE_COMING) - module_load_kprobe_ei_list(mod); - else if (val == MODULE_STATE_GOING) - module_unload_kprobe_ei_list(mod); - if (val != MODULE_STATE_GOING && val != MODULE_STATE_LIVE) return NOTIFY_DONE; @@ -2346,8 +2240,6 @@ static int __init init_kprobes(void) pr_err("Please take care of using kprobes.\n"); } - populate_kernel_kprobe_ei_list(); - if (kretprobe_blacklist_size) { /* lookup the function address from its name */ for (i = 0; kretprobe_blacklist[i].name != NULL; i++) { @@ -2515,56 +2407,6 @@ static const struct file_operations debugfs_kprobe_blacklist_ops = { .release = seq_release, }; -/* - * kprobes/error_injection_list -- shows which functions can be overriden for - * error injection. - * */ -static void *kprobe_ei_seq_start(struct seq_file *m, loff_t *pos) -{ - mutex_lock(&kprobe_ei_mutex); - return seq_list_start(&kprobe_error_injection_list, *pos); -} - -static void kprobe_ei_seq_stop(struct seq_file *m, void *v) -{ - mutex_unlock(&kprobe_ei_mutex); -} - -static void *kprobe_ei_seq_next(struct seq_file *m, void *v, loff_t *pos) -{ - return seq_list_next(v, &kprobe_error_injection_list, pos); -} - -static int kprobe_ei_seq_show(struct seq_file *m, void *v) -{ - char buffer[KSYM_SYMBOL_LEN]; - struct kprobe_ei_entry *ent = - list_entry(v, struct kprobe_ei_entry, list); - - sprint_symbol(buffer, ent->start_addr); - seq_printf(m, "%s\n", buffer); - return 0; -} - -static const struct seq_operations kprobe_ei_seq_ops = { - .start = kprobe_ei_seq_start, - .next = kprobe_ei_seq_next, - .stop = kprobe_ei_seq_stop, - .show = kprobe_ei_seq_show, -}; - -static int kprobe_ei_open(struct inode *inode, struct file *filp) -{ - return seq_open(filp, &kprobe_ei_seq_ops); -} - -static const struct file_operations debugfs_kprobe_ei_ops = { - .open = kprobe_ei_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - static void arm_all_kprobes(void) { struct hlist_head *head; @@ -2706,11 +2548,6 @@ static int __init debugfs_kprobe_init(void) if (!file) goto error; - file = debugfs_create_file("error_injection_list", 0444, dir, NULL, - &debugfs_kprobe_ei_ops); - if (!file) - goto error; - return 0; error: diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 6f3dba6e4e9e..65cc0cb984e6 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1290,6 +1290,19 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, return ret; } +static inline int __rt_mutex_slowtrylock(struct rt_mutex *lock) +{ + int ret = try_to_take_rt_mutex(lock, current, NULL); + + /* + * try_to_take_rt_mutex() sets the lock waiters bit + * unconditionally. Clean this up. + */ + fixup_rt_mutex_waiters(lock); + + return ret; +} + /* * Slow path try-lock function: */ @@ -1312,13 +1325,7 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock) */ raw_spin_lock_irqsave(&lock->wait_lock, flags); - ret = try_to_take_rt_mutex(lock, current, NULL); - - /* - * try_to_take_rt_mutex() sets the lock waiters bit - * unconditionally. Clean this up. - */ - fixup_rt_mutex_waiters(lock); + ret = __rt_mutex_slowtrylock(lock); raw_spin_unlock_irqrestore(&lock->wait_lock, flags); @@ -1505,6 +1512,11 @@ int __sched rt_mutex_futex_trylock(struct rt_mutex *lock) return rt_mutex_slowtrylock(lock); } +int __sched __rt_mutex_futex_trylock(struct rt_mutex *lock) +{ + return __rt_mutex_slowtrylock(lock); +} + /** * rt_mutex_timed_lock - lock a rt_mutex interruptible * the timeout structure is provided diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h index 124e98ca0b17..68686b3ec3c1 100644 --- a/kernel/locking/rtmutex_common.h +++ b/kernel/locking/rtmutex_common.h @@ -148,6 +148,7 @@ extern bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock, struct rt_mutex_waiter *waiter); extern int rt_mutex_futex_trylock(struct rt_mutex *l); +extern int __rt_mutex_futex_trylock(struct rt_mutex *l); extern void rt_mutex_futex_unlock(struct rt_mutex *lock); extern bool __rt_mutex_futex_unlock(struct rt_mutex *lock, diff --git a/kernel/module.c b/kernel/module.c index bd695bfdc5c4..601494d4b7ea 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3118,10 +3118,10 @@ static int find_module_sections(struct module *mod, struct load_info *info) sizeof(*mod->ftrace_callsites), &mod->num_ftrace_callsites); #endif -#ifdef CONFIG_BPF_KPROBE_OVERRIDE - mod->kprobe_ei_funcs = section_objs(info, "_kprobe_error_inject_list", - sizeof(*mod->kprobe_ei_funcs), - &mod->num_kprobe_ei_funcs); +#ifdef CONFIG_FUNCTION_ERROR_INJECTION + mod->ei_funcs = section_objs(info, "_error_injection_whitelist", + sizeof(*mod->ei_funcs), + &mod->num_ei_funcs); #endif mod->extable = section_objs(info, "__ex_table", sizeof(*mod->extable), &mod->num_exentries); diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c index 2ddaec40956f..0926aef10dad 100644 --- a/kernel/sched/completion.c +++ b/kernel/sched/completion.c @@ -34,11 +34,6 @@ void complete(struct completion *x) spin_lock_irqsave(&x->wait.lock, flags); - /* - * Perform commit of crossrelease here. - */ - complete_release_commit(x); - if (x->done != UINT_MAX) x->done++; __wake_up_locked(&x->wait, TASK_NORMAL, 1); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 644fa2e3d993..a7bf32aabfda 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2056,7 +2056,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) p->state = TASK_WAKING; if (p->in_iowait) { - delayacct_blkio_end(); + delayacct_blkio_end(p); atomic_dec(&task_rq(p)->nr_iowait); } @@ -2069,7 +2069,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) #else /* CONFIG_SMP */ if (p->in_iowait) { - delayacct_blkio_end(); + delayacct_blkio_end(p); atomic_dec(&task_rq(p)->nr_iowait); } @@ -2122,7 +2122,7 @@ static void try_to_wake_up_local(struct task_struct *p, struct rq_flags *rf) if (!task_on_rq_queued(p)) { if (p->in_iowait) { - delayacct_blkio_end(); + delayacct_blkio_end(p); atomic_dec(&rq->nr_iowait); } ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK); diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index dd7908743dab..9bcbacba82a8 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -89,7 +89,9 @@ static int membarrier_private_expedited(void) rcu_read_unlock(); } if (!fallback) { + preempt_disable(); smp_call_function_many(tmpmask, ipi_mb, NULL, 1); + preempt_enable(); free_cpumask_var(tmpmask); } cpus_read_unlock(); diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 89a9e1b4264a..0bcf00e3ce48 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1696,7 +1696,7 @@ void run_local_timers(void) hrtimer_run_queues(); /* Raise the softirq only if required. */ if (time_before(jiffies, base->clk)) { - if (!IS_ENABLED(CONFIG_NO_HZ_COMMON) || !base->nohz_active) + if (!IS_ENABLED(CONFIG_NO_HZ_COMMON)) return; /* CPU is awake, so check the deferrable base. */ base++; diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index ae3a2d519e50..0b249e2f0c3c 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -355,7 +355,7 @@ config PROFILE_ANNOTATED_BRANCHES on if you need to profile the system's use of these macros. config PROFILE_ALL_BRANCHES - bool "Profile all if conditionals" + bool "Profile all if conditionals" if !FORTIFY_SOURCE select TRACE_BRANCH_PROFILING help This tracer profiles all branch conditions. Every if () @@ -533,9 +533,7 @@ config FUNCTION_PROFILER config BPF_KPROBE_OVERRIDE bool "Enable BPF programs to override a kprobed function" depends on BPF_EVENTS - depends on KPROBES_ON_FTRACE - depends on HAVE_KPROBE_OVERRIDE - depends on DYNAMIC_FTRACE_WITH_REGS + depends on FUNCTION_ERROR_INJECTION default n help Allows BPF to override the execution of a probed function and diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index f6d2327ecb59..fc2838ac8b78 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -14,7 +14,7 @@ #include <linux/uaccess.h> #include <linux/ctype.h> #include <linux/kprobes.h> -#include <asm/kprobes.h> +#include <linux/error-injection.h> #include "trace_probe.h" #include "trace.h" @@ -83,9 +83,8 @@ EXPORT_SYMBOL_GPL(trace_call_bpf); #ifdef CONFIG_BPF_KPROBE_OVERRIDE BPF_CALL_2(bpf_override_return, struct pt_regs *, regs, unsigned long, rc) { - __this_cpu_write(bpf_kprobe_override, 1); regs_set_return_value(regs, rc); - arch_ftrace_kprobe_override_function(regs); + override_function_with_return(regs); return 0; } @@ -246,7 +245,7 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, */ #define __BPF_TP_EMIT() __BPF_ARG3_TP() #define __BPF_TP(...) \ - __trace_printk(1 /* Fake ip will not be printed. */, \ + __trace_printk(0 /* Fake ip */, \ fmt, ##__VA_ARGS__) #define __BPF_ARG1_TP(...) \ @@ -800,11 +799,11 @@ int perf_event_attach_bpf_prog(struct perf_event *event, int ret = -EEXIST; /* - * Kprobe override only works for ftrace based kprobes, and only if they - * are on the opt-in list. + * Kprobe override only works if they are on the function entry, + * and only if they are on the opt-in list. */ if (prog->kprobe_override && - (!trace_kprobe_ftrace(event->tp_event) || + (!trace_kprobe_on_func_entry(event->tp_event) || !trace_kprobe_error_injectable(event->tp_event))) return -EINVAL; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 9ab18995ff1e..5af2842dea96 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2534,29 +2534,58 @@ rb_wakeups(struct ring_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer) * The lock and unlock are done within a preempt disable section. * The current_context per_cpu variable can only be modified * by the current task between lock and unlock. But it can - * be modified more than once via an interrupt. There are four - * different contexts that we need to consider. + * be modified more than once via an interrupt. To pass this + * information from the lock to the unlock without having to + * access the 'in_interrupt()' functions again (which do show + * a bit of overhead in something as critical as function tracing, + * we use a bitmask trick. * - * Normal context. - * SoftIRQ context - * IRQ context - * NMI context + * bit 0 = NMI context + * bit 1 = IRQ context + * bit 2 = SoftIRQ context + * bit 3 = normal context. * - * If for some reason the ring buffer starts to recurse, we - * only allow that to happen at most 4 times (one for each - * context). If it happens 5 times, then we consider this a - * recusive loop and do not let it go further. + * This works because this is the order of contexts that can + * preempt other contexts. A SoftIRQ never preempts an IRQ + * context. + * + * When the context is determined, the corresponding bit is + * checked and set (if it was set, then a recursion of that context + * happened). + * + * On unlock, we need to clear this bit. To do so, just subtract + * 1 from the current_context and AND it to itself. + * + * (binary) + * 101 - 1 = 100 + * 101 & 100 = 100 (clearing bit zero) + * + * 1010 - 1 = 1001 + * 1010 & 1001 = 1000 (clearing bit 1) + * + * The least significant bit can be cleared this way, and it + * just so happens that it is the same bit corresponding to + * the current context. */ static __always_inline int trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer) { - if (cpu_buffer->current_context >= 4) + unsigned int val = cpu_buffer->current_context; + unsigned long pc = preempt_count(); + int bit; + + if (!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET))) + bit = RB_CTX_NORMAL; + else + bit = pc & NMI_MASK ? RB_CTX_NMI : + pc & HARDIRQ_MASK ? RB_CTX_IRQ : RB_CTX_SOFTIRQ; + + if (unlikely(val & (1 << bit))) return 1; - cpu_buffer->current_context++; - /* Interrupts must see this update */ - barrier(); + val |= (1 << bit); + cpu_buffer->current_context = val; return 0; } @@ -2564,9 +2593,7 @@ trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer) static __always_inline void trace_recursive_unlock(struct ring_buffer_per_cpu *cpu_buffer) { - /* Don't let the dec leak out */ - barrier(); - cpu_buffer->current_context--; + cpu_buffer->current_context &= cpu_buffer->current_context - 1; } /** diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index ec0f9aa4e151..1b87157edbff 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2213,6 +2213,7 @@ void trace_event_eval_update(struct trace_eval_map **map, int len) { struct trace_event_call *call, *p; const char *last_system = NULL; + bool first = false; int last_i; int i; @@ -2220,15 +2221,28 @@ void trace_event_eval_update(struct trace_eval_map **map, int len) list_for_each_entry_safe(call, p, &ftrace_events, list) { /* events are usually grouped together with systems */ if (!last_system || call->class->system != last_system) { + first = true; last_i = 0; last_system = call->class->system; } + /* + * Since calls are grouped by systems, the likelyhood that the + * next call in the iteration belongs to the same system as the + * previous call is high. As an optimization, we skip seaching + * for a map[] that matches the call's system if the last call + * was from the same system. That's what last_i is for. If the + * call has the same system as the previous call, then last_i + * will be the index of the first map[] that has a matching + * system. + */ for (i = last_i; i < len; i++) { if (call->class->system == map[i]->system) { /* Save the first system if need be */ - if (!last_i) + if (first) { last_i = i; + first = false; + } update_event_printk(call, map[i]); } } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 91f4b57dab82..1fad24acd444 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -21,6 +21,7 @@ #include <linux/module.h> #include <linux/uaccess.h> #include <linux/rculist.h> +#include <linux/error-injection.h> #include "trace_probe.h" @@ -42,8 +43,6 @@ struct trace_kprobe { (offsetof(struct trace_kprobe, tp.args) + \ (sizeof(struct probe_arg) * (n))) -DEFINE_PER_CPU(int, bpf_kprobe_override); - static nokprobe_inline bool trace_kprobe_is_return(struct trace_kprobe *tk) { return tk->rp.handler != NULL; @@ -88,13 +87,16 @@ static nokprobe_inline unsigned long trace_kprobe_nhit(struct trace_kprobe *tk) return nhit; } -int trace_kprobe_ftrace(struct trace_event_call *call) +bool trace_kprobe_on_func_entry(struct trace_event_call *call) { struct trace_kprobe *tk = (struct trace_kprobe *)call->data; - return kprobe_ftrace(&tk->rp.kp); + + return kprobe_on_func_entry(tk->rp.kp.addr, + tk->rp.kp.addr ? NULL : tk->rp.kp.symbol_name, + tk->rp.kp.addr ? 0 : tk->rp.kp.offset); } -int trace_kprobe_error_injectable(struct trace_event_call *call) +bool trace_kprobe_error_injectable(struct trace_event_call *call) { struct trace_kprobe *tk = (struct trace_kprobe *)call->data; unsigned long addr; @@ -106,7 +108,7 @@ int trace_kprobe_error_injectable(struct trace_event_call *call) } else { addr = (unsigned long)tk->rp.kp.addr; } - return within_kprobe_error_injection_list(addr); + return within_error_injection_list(addr); } static int register_kprobe_event(struct trace_kprobe *tk); @@ -1202,6 +1204,7 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) int rctx; if (bpf_prog_array_valid(call)) { + unsigned long orig_ip = instruction_pointer(regs); int ret; ret = trace_call_bpf(call, regs); @@ -1209,12 +1212,13 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) /* * We need to check and see if we modified the pc of the * pt_regs, and if so clear the kprobe and return 1 so that we - * don't do the instruction skipping. Also reset our state so - * we are clean the next pass through. + * don't do the single stepping. + * The ftrace kprobe handler leaves it up to us to re-enable + * preemption here before returning if we've modified the ip. */ - if (__this_cpu_read(bpf_kprobe_override)) { - __this_cpu_write(bpf_kprobe_override, 0); + if (orig_ip != instruction_pointer(regs)) { reset_current_kprobe(); + preempt_enable_no_resched(); return 1; } if (!ret) @@ -1322,15 +1326,8 @@ static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs) if (tk->tp.flags & TP_FLAG_TRACE) kprobe_trace_func(tk, regs); #ifdef CONFIG_PERF_EVENTS - if (tk->tp.flags & TP_FLAG_PROFILE) { + if (tk->tp.flags & TP_FLAG_PROFILE) ret = kprobe_perf_func(tk, regs); - /* - * The ftrace kprobe handler leaves it up to us to re-enable - * preemption here before returning if we've modified the ip. - */ - if (ret) - preempt_enable_no_resched(); - } #endif return ret; } diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 5e54d748c84c..e101c5bb9eda 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -252,8 +252,8 @@ struct symbol_cache; unsigned long update_symbol_cache(struct symbol_cache *sc); void free_symbol_cache(struct symbol_cache *sc); struct symbol_cache *alloc_symbol_cache(const char *sym, long offset); -int trace_kprobe_ftrace(struct trace_event_call *call); -int trace_kprobe_error_injectable(struct trace_event_call *call); +bool trace_kprobe_on_func_entry(struct trace_event_call *call); +bool trace_kprobe_error_injectable(struct trace_event_call *call); #else /* uprobes do not support symbol fetch methods */ #define fetch_symbol_u8 NULL @@ -280,14 +280,14 @@ alloc_symbol_cache(const char *sym, long offset) return NULL; } -static inline int trace_kprobe_ftrace(struct trace_event_call *call) +static inline bool trace_kprobe_on_func_entry(struct trace_event_call *call) { - return 0; + return false; } -static inline int trace_kprobe_error_injectable(struct trace_event_call *call) +static inline bool trace_kprobe_error_injectable(struct trace_event_call *call) { - return 0; + return false; } #endif /* CONFIG_KPROBE_EVENTS */ diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 43d18cb46308..f699122dab32 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -48,6 +48,7 @@ #include <linux/moduleparam.h> #include <linux/uaccess.h> #include <linux/sched/isolation.h> +#include <linux/nmi.h> #include "workqueue_internal.h" @@ -4463,6 +4464,12 @@ void show_workqueue_state(void) if (pwq->nr_active || !list_empty(&pwq->delayed_works)) show_pwq(pwq); spin_unlock_irqrestore(&pwq->pool->lock, flags); + /* + * We could be printing a lot from atomic context, e.g. + * sysrq-t -> show_workqueue_state(). Avoid triggering + * hard lockup. + */ + touch_nmi_watchdog(); } } @@ -4490,6 +4497,12 @@ void show_workqueue_state(void) pr_cont("\n"); next_pool: spin_unlock_irqrestore(&pool->lock, flags); + /* + * We could be printing a lot from atomic context, e.g. + * sysrq-t -> show_workqueue_state(). Avoid triggering + * hard lockup. + */ + touch_nmi_watchdog(); } rcu_read_unlock_sched(); |