diff options
Diffstat (limited to 'kernel')
72 files changed, 1051 insertions, 672 deletions
diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt index 60f1bfc3c7b2..ce77f0265660 100644 --- a/kernel/Kconfig.preempt +++ b/kernel/Kconfig.preempt @@ -1,12 +1,23 @@ # SPDX-License-Identifier: GPL-2.0-only +config PREEMPT_NONE_BUILD + bool + +config PREEMPT_VOLUNTARY_BUILD + bool + +config PREEMPT_BUILD + bool + select PREEMPTION + select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK + choice prompt "Preemption Model" - default PREEMPT_NONE_BEHAVIOUR + default PREEMPT_NONE -config PREEMPT_NONE_BEHAVIOUR +config PREEMPT_NONE bool "No Forced Preemption (Server)" - select PREEMPT_NONE if !PREEMPT_DYNAMIC + select PREEMPT_NONE_BUILD if !PREEMPT_DYNAMIC help This is the traditional Linux preemption model, geared towards throughput. It will still provide good latencies most of the @@ -18,10 +29,10 @@ config PREEMPT_NONE_BEHAVIOUR raw processing power of the kernel, irrespective of scheduling latencies. -config PREEMPT_VOLUNTARY_BEHAVIOUR +config PREEMPT_VOLUNTARY bool "Voluntary Kernel Preemption (Desktop)" depends on !ARCH_NO_PREEMPT - select PREEMPT_VOLUNTARY if !PREEMPT_DYNAMIC + select PREEMPT_VOLUNTARY_BUILD if !PREEMPT_DYNAMIC help This option reduces the latency of the kernel by adding more "explicit preemption points" to the kernel code. These new @@ -37,10 +48,10 @@ config PREEMPT_VOLUNTARY_BEHAVIOUR Select this if you are building a kernel for a desktop system. -config PREEMPT_BEHAVIOUR +config PREEMPT bool "Preemptible Kernel (Low-Latency Desktop)" depends on !ARCH_NO_PREEMPT - select PREEMPT + select PREEMPT_BUILD help This option reduces the latency of the kernel by making all kernel code (that is not executing in a critical section) @@ -58,7 +69,7 @@ config PREEMPT_BEHAVIOUR config PREEMPT_RT bool "Fully Preemptible Kernel (Real-Time)" - depends on EXPERT && ARCH_SUPPORTS_RT && !PREEMPT_DYNAMIC + depends on EXPERT && ARCH_SUPPORTS_RT select PREEMPTION help This option turns the kernel into a real-time kernel by replacing @@ -75,17 +86,6 @@ config PREEMPT_RT endchoice -config PREEMPT_NONE - bool - -config PREEMPT_VOLUNTARY - bool - -config PREEMPT - bool - select PREEMPTION - select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK - config PREEMPT_COUNT bool @@ -95,8 +95,8 @@ config PREEMPTION config PREEMPT_DYNAMIC bool "Preemption behaviour defined on boot" - depends on HAVE_PREEMPT_DYNAMIC - select PREEMPT + depends on HAVE_PREEMPT_DYNAMIC && !PREEMPT_RT + select PREEMPT_BUILD default y help This option allows to define the preemption model on the kernel diff --git a/kernel/audit.c b/kernel/audit.c index 121d37e700a6..4cebadb5f30d 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -718,7 +718,7 @@ static int kauditd_send_queue(struct sock *sk, u32 portid, { int rc = 0; struct sk_buff *skb; - static unsigned int failed = 0; + unsigned int failed = 0; /* NOTE: kauditd_thread takes care of all our locking, we just use * the netlink info passed to us (e.g. sk and portid) */ @@ -735,32 +735,30 @@ static int kauditd_send_queue(struct sock *sk, u32 portid, continue; } +retry: /* grab an extra skb reference in case of error */ skb_get(skb); rc = netlink_unicast(sk, skb, portid, 0); if (rc < 0) { - /* fatal failure for our queue flush attempt? */ + /* send failed - try a few times unless fatal error */ if (++failed >= retry_limit || rc == -ECONNREFUSED || rc == -EPERM) { - /* yes - error processing for the queue */ sk = NULL; if (err_hook) (*err_hook)(skb); - if (!skb_hook) - goto out; - /* keep processing with the skb_hook */ + if (rc == -EAGAIN) + rc = 0; + /* continue to drain the queue */ continue; } else - /* no - requeue to preserve ordering */ - skb_queue_head(queue, skb); + goto retry; } else { - /* it worked - drop the extra reference and continue */ + /* skb sent - drop the extra reference and continue */ consume_skb(skb); failed = 0; } } -out: return (rc >= 0 ? 0 : rc); } @@ -1609,7 +1607,8 @@ static int __net_init audit_net_init(struct net *net) audit_panic("cannot initialize netlink socket in namespace"); return -ENOMEM; } - aunet->sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; + /* limit the timeout in case auditd is blocked/stopped */ + aunet->sk->sk_sndtimeo = HZ / 10; return 0; } diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c index 60739d5e3373..02348b48447c 100644 --- a/kernel/audit_fsnotify.c +++ b/kernel/audit_fsnotify.c @@ -160,8 +160,7 @@ static int audit_mark_handle_event(struct fsnotify_mark *inode_mark, u32 mask, audit_mark = container_of(inode_mark, struct audit_fsnotify_mark, mark); - if (WARN_ON_ONCE(inode_mark->group != audit_fsnotify_group) || - WARN_ON_ONCE(!inode)) + if (WARN_ON_ONCE(inode_mark->group != audit_fsnotify_group)) return 0; if (mask & (FS_CREATE|FS_MOVED_TO|FS_DELETE|FS_MOVED_FROM)) { diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 698b62b4a2ec..713b256be944 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -473,8 +473,7 @@ static int audit_watch_handle_event(struct fsnotify_mark *inode_mark, u32 mask, parent = container_of(inode_mark, struct audit_parent, mark); - if (WARN_ON_ONCE(inode_mark->group != audit_watch_group) || - WARN_ON_ONCE(!inode)) + if (WARN_ON_ONCE(inode_mark->group != audit_watch_group)) return 0; if (mask & (FS_CREATE|FS_MOVED_TO) && inode) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index dbc3ad07e21b..9bdb03767db5 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6346,11 +6346,6 @@ BTF_ID_LIST_GLOBAL_SINGLE(btf_task_struct_ids, struct, task_struct) /* BTF ID set registration API for modules */ -struct kfunc_btf_id_list { - struct list_head list; - struct mutex mutex; -}; - #ifdef CONFIG_DEBUG_INFO_BTF_MODULES void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, @@ -6376,8 +6371,6 @@ bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, { struct kfunc_btf_id_set *s; - if (!owner) - return false; mutex_lock(&klist->mutex); list_for_each_entry(s, &klist->list, list) { if (s->owner == owner && btf_id_set_contains(s->set, kfunc_id)) { @@ -6389,8 +6382,6 @@ bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, return false; } -#endif - #define DEFINE_KFUNC_BTF_ID_LIST(name) \ struct kfunc_btf_id_list name = { LIST_HEAD_INIT(name.list), \ __MUTEX_INITIALIZER(name.mutex) }; \ @@ -6398,3 +6389,5 @@ bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, DEFINE_KFUNC_BTF_ID_LIST(bpf_tcp_ca_kfunc_list); DEFINE_KFUNC_BTF_ID_LIST(prog_test_kfunc_list); + +#endif diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 2ca643af9a54..43eb3501721b 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1809,6 +1809,8 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sysctl_get_new_value_proto; case BPF_FUNC_sysctl_set_new_value: return &bpf_sysctl_set_new_value_proto; + case BPF_FUNC_ktime_get_coarse_ns: + return &bpf_ktime_get_coarse_ns_proto; default: return cgroup_base_func_proto(func_id, prog); } diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 327e3996eadb..2405e39d800f 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -390,6 +390,13 @@ static int bpf_adj_branches(struct bpf_prog *prog, u32 pos, s32 end_old, i = end_new; insn = prog->insnsi + end_old; } + if (bpf_pseudo_func(insn)) { + ret = bpf_adj_delta_to_imm(insn, pos, end_old, + end_new, i, probe_pass); + if (ret) + return ret; + continue; + } code = insn->code; if ((BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32) || diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 1ffd469c217f..649f07623df6 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1364,8 +1364,6 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_ktime_get_ns_proto; case BPF_FUNC_ktime_get_boot_ns: return &bpf_ktime_get_boot_ns_proto; - case BPF_FUNC_ktime_get_coarse_ns: - return &bpf_ktime_get_coarse_ns_proto; case BPF_FUNC_ringbuf_output: return &bpf_ringbuf_output_proto; case BPF_FUNC_ringbuf_reserve: diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 50f96ea4452a..1033ee8c0caf 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -132,6 +132,21 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) return map; } +static void bpf_map_write_active_inc(struct bpf_map *map) +{ + atomic64_inc(&map->writecnt); +} + +static void bpf_map_write_active_dec(struct bpf_map *map) +{ + atomic64_dec(&map->writecnt); +} + +bool bpf_map_write_active(const struct bpf_map *map) +{ + return atomic64_read(&map->writecnt) != 0; +} + static u32 bpf_map_value_size(const struct bpf_map *map) { if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || @@ -601,11 +616,8 @@ static void bpf_map_mmap_open(struct vm_area_struct *vma) { struct bpf_map *map = vma->vm_file->private_data; - if (vma->vm_flags & VM_MAYWRITE) { - mutex_lock(&map->freeze_mutex); - map->writecnt++; - mutex_unlock(&map->freeze_mutex); - } + if (vma->vm_flags & VM_MAYWRITE) + bpf_map_write_active_inc(map); } /* called for all unmapped memory region (including initial) */ @@ -613,11 +625,8 @@ static void bpf_map_mmap_close(struct vm_area_struct *vma) { struct bpf_map *map = vma->vm_file->private_data; - if (vma->vm_flags & VM_MAYWRITE) { - mutex_lock(&map->freeze_mutex); - map->writecnt--; - mutex_unlock(&map->freeze_mutex); - } + if (vma->vm_flags & VM_MAYWRITE) + bpf_map_write_active_dec(map); } static const struct vm_operations_struct bpf_map_default_vmops = { @@ -668,7 +677,7 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) goto out; if (vma->vm_flags & VM_MAYWRITE) - map->writecnt++; + bpf_map_write_active_inc(map); out: mutex_unlock(&map->freeze_mutex); return err; @@ -1139,6 +1148,7 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); + bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; @@ -1174,6 +1184,7 @@ free_value: free_key: kvfree(key); err_put: + bpf_map_write_active_dec(map); fdput(f); return err; } @@ -1196,6 +1207,7 @@ static int map_delete_elem(union bpf_attr *attr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); + bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; @@ -1226,6 +1238,7 @@ static int map_delete_elem(union bpf_attr *attr) out: kvfree(key); err_put: + bpf_map_write_active_dec(map); fdput(f); return err; } @@ -1533,6 +1546,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); + bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ) || !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; @@ -1597,6 +1611,7 @@ free_value: free_key: kvfree(key); err_put: + bpf_map_write_active_dec(map); fdput(f); return err; } @@ -1624,8 +1639,7 @@ static int map_freeze(const union bpf_attr *attr) } mutex_lock(&map->freeze_mutex); - - if (map->writecnt) { + if (bpf_map_write_active(map)) { err = -EBUSY; goto err_put; } @@ -4171,6 +4185,9 @@ static int bpf_map_do_batch(const union bpf_attr *attr, union bpf_attr __user *uattr, int cmd) { + bool has_read = cmd == BPF_MAP_LOOKUP_BATCH || + cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH; + bool has_write = cmd != BPF_MAP_LOOKUP_BATCH; struct bpf_map *map; int err, ufd; struct fd f; @@ -4183,16 +4200,13 @@ static int bpf_map_do_batch(const union bpf_attr *attr, map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - - if ((cmd == BPF_MAP_LOOKUP_BATCH || - cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) && - !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { + if (has_write) + bpf_map_write_active_inc(map); + if (has_read && !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { err = -EPERM; goto err_put; } - - if (cmd != BPF_MAP_LOOKUP_BATCH && - !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { + if (has_write && !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } @@ -4205,8 +4219,9 @@ static int bpf_map_do_batch(const union bpf_attr *attr, BPF_DO_BATCH(map->ops->map_update_batch); else BPF_DO_BATCH(map->ops->map_delete_batch); - err_put: + if (has_write) + bpf_map_write_active_dec(map); fdput(f); return err; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f0dca726ebfd..b532f1058d35 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -240,12 +240,6 @@ static bool bpf_pseudo_kfunc_call(const struct bpf_insn *insn) insn->src_reg == BPF_PSEUDO_KFUNC_CALL; } -static bool bpf_pseudo_func(const struct bpf_insn *insn) -{ - return insn->code == (BPF_LD | BPF_IMM | BPF_DW) && - insn->src_reg == BPF_PSEUDO_FUNC; -} - struct bpf_call_arg_meta { struct bpf_map *map_ptr; bool raw_mode; @@ -1157,7 +1151,8 @@ static void mark_ptr_not_null_reg(struct bpf_reg_state *reg) /* transfer reg's id which is unique for every map_lookup_elem * as UID of the inner map. */ - reg->map_uid = reg->id; + if (map_value_has_timer(map->inner_map_meta)) + reg->map_uid = reg->id; } else if (map->map_type == BPF_MAP_TYPE_XSKMAP) { reg->type = PTR_TO_XDP_SOCK; } else if (map->map_type == BPF_MAP_TYPE_SOCKMAP || @@ -1371,22 +1366,28 @@ static void __reg_bound_offset(struct bpf_reg_state *reg) reg->var_off = tnum_or(tnum_clear_subreg(var64_off), var32_off); } +static bool __reg32_bound_s64(s32 a) +{ + return a >= 0 && a <= S32_MAX; +} + static void __reg_assign_32_into_64(struct bpf_reg_state *reg) { reg->umin_value = reg->u32_min_value; reg->umax_value = reg->u32_max_value; - /* Attempt to pull 32-bit signed bounds into 64-bit bounds - * but must be positive otherwise set to worse case bounds - * and refine later from tnum. + + /* Attempt to pull 32-bit signed bounds into 64-bit bounds but must + * be positive otherwise set to worse case bounds and refine later + * from tnum. */ - if (reg->s32_min_value >= 0 && reg->s32_max_value >= 0) - reg->smax_value = reg->s32_max_value; - else - reg->smax_value = U32_MAX; - if (reg->s32_min_value >= 0) + if (__reg32_bound_s64(reg->s32_min_value) && + __reg32_bound_s64(reg->s32_max_value)) { reg->smin_value = reg->s32_min_value; - else + reg->smax_value = reg->s32_max_value; + } else { reg->smin_value = 0; + reg->smax_value = U32_MAX; + } } static void __reg_combine_32_into_64(struct bpf_reg_state *reg) @@ -1960,16 +1961,10 @@ static int add_subprog_and_kfunc(struct bpf_verifier_env *env) return -EPERM; } - if (bpf_pseudo_func(insn)) { - ret = add_subprog(env, i + insn->imm + 1); - if (ret >= 0) - /* remember subprog */ - insn[1].imm = ret; - } else if (bpf_pseudo_call(insn)) { + if (bpf_pseudo_func(insn) || bpf_pseudo_call(insn)) ret = add_subprog(env, i + insn->imm + 1); - } else { + else ret = add_kfunc_call(env, insn->imm, insn->off); - } if (ret < 0) return ret; @@ -2390,8 +2385,6 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, */ if (insn->src_reg != BPF_REG_FP) return 0; - if (BPF_SIZE(insn->code) != BPF_DW) - return 0; /* dreg = *(u64 *)[fp - off] was a fill from the stack. * that [fp - off] slot contains scalar that needs to be @@ -2414,8 +2407,6 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, /* scalars can only be spilled into stack */ if (insn->dst_reg != BPF_REG_FP) return 0; - if (BPF_SIZE(insn->code) != BPF_DW) - return 0; spi = (-insn->off - 1) / BPF_REG_SIZE; if (spi >= 64) { verbose(env, "BUG spi %d\n", spi); @@ -3088,9 +3079,12 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, reg = ®_state->stack[spi].spilled_ptr; if (is_spilled_reg(®_state->stack[spi])) { - if (size != BPF_REG_SIZE) { - u8 scalar_size = 0; + u8 spill_size = 1; + + for (i = BPF_REG_SIZE - 1; i > 0 && stype[i - 1] == STACK_SPILL; i--) + spill_size++; + if (size != BPF_REG_SIZE || spill_size != BPF_REG_SIZE) { if (reg->type != SCALAR_VALUE) { verbose_linfo(env, env->insn_idx, "; "); verbose(env, "invalid size of register fill\n"); @@ -3101,10 +3095,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, if (dst_regno < 0) return 0; - for (i = BPF_REG_SIZE; i > 0 && stype[i - 1] == STACK_SPILL; i--) - scalar_size++; - - if (!(off % BPF_REG_SIZE) && size == scalar_size) { + if (!(off % BPF_REG_SIZE) && size == spill_size) { /* The earlier check_reg_arg() has decided the * subreg_def for this insn. Save it first. */ @@ -3128,12 +3119,6 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, state->regs[dst_regno].live |= REG_LIVE_WRITTEN; return 0; } - for (i = 1; i < BPF_REG_SIZE; i++) { - if (stype[(slot - i) % BPF_REG_SIZE] != STACK_SPILL) { - verbose(env, "corrupted spill memory\n"); - return -EACCES; - } - } if (dst_regno >= 0) { /* restore register state from stack */ @@ -4073,7 +4058,22 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size) static bool bpf_map_is_rdonly(const struct bpf_map *map) { - return (map->map_flags & BPF_F_RDONLY_PROG) && map->frozen; + /* A map is considered read-only if the following condition are true: + * + * 1) BPF program side cannot change any of the map content. The + * BPF_F_RDONLY_PROG flag is throughout the lifetime of a map + * and was set at map creation time. + * 2) The map value(s) have been initialized from user space by a + * loader and then "frozen", such that no new map update/delete + * operations from syscall side are possible for the rest of + * the map's lifetime from that point onwards. + * 3) Any parallel/pending map update/delete operations from syscall + * side have been completed. Only after that point, it's safe to + * assume that map value(s) are immutable. + */ + return (map->map_flags & BPF_F_RDONLY_PROG) && + READ_ONCE(map->frozen) && + !bpf_map_write_active(map); } static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val) @@ -4553,9 +4553,16 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i if (insn->imm == BPF_CMPXCHG) { /* Check comparison of R0 with memory location */ - err = check_reg_arg(env, BPF_REG_0, SRC_OP); + const u32 aux_reg = BPF_REG_0; + + err = check_reg_arg(env, aux_reg, SRC_OP); if (err) return err; + + if (is_pointer_value(env, aux_reg)) { + verbose(env, "R%d leaks addr into mem\n", aux_reg); + return -EACCES; + } } if (is_pointer_value(env, insn->src_reg)) { @@ -4590,13 +4597,19 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i load_reg = -1; } - /* check whether we can read the memory */ + /* Check whether we can read the memory, with second call for fetch + * case to simulate the register fill. + */ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, - BPF_SIZE(insn->code), BPF_READ, load_reg, true); + BPF_SIZE(insn->code), BPF_READ, -1, true); + if (!err && load_reg >= 0) + err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, + BPF_SIZE(insn->code), BPF_READ, load_reg, + true); if (err) return err; - /* check whether we can write into the same memory */ + /* Check whether we can write into the same memory. */ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, -1, true); if (err) @@ -8310,6 +8323,10 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) insn->dst_reg); } zext_32_to_64(dst_reg); + + __update_reg_bounds(dst_reg); + __reg_deduce_bounds(dst_reg); + __reg_bound_offset(dst_reg); } } else { /* case: R = imm @@ -8424,7 +8441,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, new_range = dst_reg->off; if (range_right_open) - new_range--; + new_range++; /* Examples for register markings: * @@ -9393,7 +9410,8 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) if (insn->src_reg == BPF_PSEUDO_FUNC) { struct bpf_prog_aux *aux = env->prog->aux; - u32 subprogno = insn[1].imm; + u32 subprogno = find_subprog(env, + env->insn_idx + insn->imm + 1); if (!aux->func_info) { verbose(env, "missing btf func_info\n"); @@ -11648,6 +11666,13 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, } } + if (map_value_has_timer(map)) { + if (is_tracing_prog_type(prog_type)) { + verbose(env, "tracing progs cannot use bpf_timer yet\n"); + return -EINVAL; + } + } + if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) && !bpf_offload_prog_map_match(prog, map)) { verbose(env, "offload device mismatch between prog and map\n"); @@ -12563,14 +12588,9 @@ static int jit_subprogs(struct bpf_verifier_env *env) return 0; for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { - if (bpf_pseudo_func(insn)) { - env->insn_aux_data[i].call_imm = insn->imm; - /* subprog is encoded in insn[1].imm */ + if (!bpf_pseudo_func(insn) && !bpf_pseudo_call(insn)) continue; - } - if (!bpf_pseudo_call(insn)) - continue; /* Upon error here we cannot fall back to interpreter but * need a hard reject of the program. Thus -EFAULT is * propagated in any case. @@ -12591,6 +12611,12 @@ static int jit_subprogs(struct bpf_verifier_env *env) env->insn_aux_data[i].call_imm = insn->imm; /* point imm to __bpf_call_base+1 from JITs point of view */ insn->imm = 1; + if (bpf_pseudo_func(insn)) + /* jit (e.g. x86_64) may emit fewer instructions + * if it learns a u32 imm is the same as a u64 imm. + * Force a non zero here. + */ + insn[1].imm = 1; } err = bpf_prog_alloc_jited_linfo(prog); @@ -12675,7 +12701,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) insn = func[i]->insnsi; for (j = 0; j < func[i]->len; j++, insn++) { if (bpf_pseudo_func(insn)) { - subprog = insn[1].imm; + subprog = insn->off; insn[0].imm = (u32)(long)func[subprog]->bpf_func; insn[1].imm = ((u64)(long)func[subprog]->bpf_func) >> 32; continue; @@ -12726,7 +12752,8 @@ static int jit_subprogs(struct bpf_verifier_env *env) for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { if (bpf_pseudo_func(insn)) { insn[0].imm = env->insn_aux_data[i].call_imm; - insn[1].imm = find_subprog(env, i + insn[0].imm + 1); + insn[1].imm = insn->off; + insn->off = 0; continue; } if (!bpf_pseudo_call(insn)) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 2a9695ccb65f..d0e163a02099 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -69,6 +69,13 @@ DEFINE_STATIC_KEY_FALSE(cpusets_pre_enable_key); DEFINE_STATIC_KEY_FALSE(cpusets_enabled_key); +/* + * There could be abnormal cpuset configurations for cpu or memory + * node binding, add this key to provide a quick low-cost judgement + * of the situation. + */ +DEFINE_STATIC_KEY_FALSE(cpusets_insane_config_key); + /* See "Frequency meter" comments, below. */ struct fmeter { @@ -372,6 +379,17 @@ static DECLARE_WORK(cpuset_hotplug_work, cpuset_hotplug_workfn); static DECLARE_WAIT_QUEUE_HEAD(cpuset_attach_wq); +static inline void check_insane_mems_config(nodemask_t *nodes) +{ + if (!cpusets_insane_config() && + movable_only_nodes(nodes)) { + static_branch_enable(&cpusets_insane_config_key); + pr_info("Unsupported (movable nodes only) cpuset configuration detected (nmask=%*pbl)!\n" + "Cpuset allocations might fail even with a lot of memory available.\n", + nodemask_pr_args(nodes)); + } +} + /* * Cgroup v2 behavior is used on the "cpus" and "mems" control files when * on default hierarchy or when the cpuset_v2_mode flag is set by mounting @@ -1870,6 +1888,8 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs, if (retval < 0) goto done; + check_insane_mems_config(&trialcs->mems_allowed); + spin_lock_irq(&callback_lock); cs->mems_allowed = trialcs->mems_allowed; spin_unlock_irq(&callback_lock); @@ -3173,6 +3193,9 @@ update_tasks: cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus); mems_updated = !nodes_equal(new_mems, cs->effective_mems); + if (mems_updated) + check_insane_mems_config(&new_mems); + if (is_in_v2_mode()) hotplug_update_tasks(cs, &new_cpus, &new_mems, cpus_updated, mems_updated); diff --git a/kernel/cpu.c b/kernel/cpu.c index 192e43a87407..407a2568f35e 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -31,6 +31,7 @@ #include <linux/smpboot.h> #include <linux/relay.h> #include <linux/slab.h> +#include <linux/scs.h> #include <linux/percpu-rwsem.h> #include <linux/cpuset.h> @@ -588,6 +589,12 @@ static int bringup_cpu(unsigned int cpu) int ret; /* + * Reset stale stack state from the last time this CPU was online. + */ + scs_task_reset(idle); + kasan_unpoison_task_stack(idle); + + /* * Some architectures have to walk the irq descriptors to * setup the vector space for the cpu which comes online. * Prevent irq alloc/free across the bringup. diff --git a/kernel/debug/kdb/kdb_bt.c b/kernel/debug/kdb/kdb_bt.c index 1f9f0e47aeda..10b454554ab0 100644 --- a/kernel/debug/kdb/kdb_bt.c +++ b/kernel/debug/kdb/kdb_bt.c @@ -46,7 +46,7 @@ static void kdb_show_stack(struct task_struct *p, void *addr) * btp <pid> Kernel stack for <pid> * btt <address-expression> Kernel stack for task structure at * <address-expression> - * bta [DRSTCZEUIMA] All useful processes, optionally + * bta [state_chars>|A] All useful processes, optionally * filtered by state * btc [<cpu>] The current process on one cpu, * default is all cpus @@ -74,7 +74,7 @@ static void kdb_show_stack(struct task_struct *p, void *addr) */ static int -kdb_bt1(struct task_struct *p, unsigned long mask, bool btaprompt) +kdb_bt1(struct task_struct *p, const char *mask, bool btaprompt) { char ch; @@ -120,7 +120,7 @@ kdb_bt_cpu(unsigned long cpu) return; } - kdb_bt1(kdb_tsk, ~0UL, false); + kdb_bt1(kdb_tsk, "A", false); } int @@ -138,8 +138,8 @@ kdb_bt(int argc, const char **argv) if (strcmp(argv[0], "bta") == 0) { struct task_struct *g, *p; unsigned long cpu; - unsigned long mask = kdb_task_state_string(argc ? argv[1] : - NULL); + const char *mask = argc ? argv[1] : kdbgetenv("PS"); + if (argc == 0) kdb_ps_suppressed(); /* Run the active tasks first */ @@ -167,7 +167,7 @@ kdb_bt(int argc, const char **argv) return diag; p = find_task_by_pid_ns(pid, &init_pid_ns); if (p) - return kdb_bt1(p, ~0UL, false); + return kdb_bt1(p, "A", false); kdb_printf("No process with pid == %ld found\n", pid); return 0; } else if (strcmp(argv[0], "btt") == 0) { @@ -176,7 +176,7 @@ kdb_bt(int argc, const char **argv) diag = kdbgetularg((char *)argv[1], &addr); if (diag) return diag; - return kdb_bt1((struct task_struct *)addr, ~0UL, false); + return kdb_bt1((struct task_struct *)addr, "A", false); } else if (strcmp(argv[0], "btc") == 0) { unsigned long cpu = ~0; if (argc > 1) @@ -212,7 +212,7 @@ kdb_bt(int argc, const char **argv) kdb_show_stack(kdb_current_task, (void *)addr); return 0; } else { - return kdb_bt1(kdb_current_task, ~0UL, false); + return kdb_bt1(kdb_current_task, "A", false); } } diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index fa6deda894a1..0852a537dad4 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -2203,8 +2203,8 @@ static void kdb_cpu_status(void) state = 'D'; /* cpu is online but unresponsive */ } else { state = ' '; /* cpu is responding to kdb */ - if (kdb_task_state_char(KDB_TSK(i)) == 'I') - state = 'I'; /* idle task */ + if (kdb_task_state_char(KDB_TSK(i)) == '-') + state = '-'; /* idle task */ } if (state != prev_state) { if (prev_state != '?') { @@ -2271,37 +2271,30 @@ static int kdb_cpu(int argc, const char **argv) void kdb_ps_suppressed(void) { int idle = 0, daemon = 0; - unsigned long mask_I = kdb_task_state_string("I"), - mask_M = kdb_task_state_string("M"); unsigned long cpu; const struct task_struct *p, *g; for_each_online_cpu(cpu) { p = kdb_curr_task(cpu); - if (kdb_task_state(p, mask_I)) + if (kdb_task_state(p, "-")) ++idle; } for_each_process_thread(g, p) { - if (kdb_task_state(p, mask_M)) + if (kdb_task_state(p, "ims")) ++daemon; } if (idle || daemon) { if (idle) - kdb_printf("%d idle process%s (state I)%s\n", + kdb_printf("%d idle process%s (state -)%s\n", idle, idle == 1 ? "" : "es", daemon ? " and " : ""); if (daemon) - kdb_printf("%d sleeping system daemon (state M) " + kdb_printf("%d sleeping system daemon (state [ims]) " "process%s", daemon, daemon == 1 ? "" : "es"); kdb_printf(" suppressed,\nuse 'ps A' to see all.\n"); } } -/* - * kdb_ps - This function implements the 'ps' command which shows a - * list of the active processes. - * ps [DRSTCZEUIMA] All processes, optionally filtered by state - */ void kdb_ps1(const struct task_struct *p) { int cpu; @@ -2330,17 +2323,25 @@ void kdb_ps1(const struct task_struct *p) } } +/* + * kdb_ps - This function implements the 'ps' command which shows a + * list of the active processes. + * + * ps [<state_chars>] Show processes, optionally selecting only those whose + * state character is found in <state_chars>. + */ static int kdb_ps(int argc, const char **argv) { struct task_struct *g, *p; - unsigned long mask, cpu; + const char *mask; + unsigned long cpu; if (argc == 0) kdb_ps_suppressed(); kdb_printf("%-*s Pid Parent [*] cpu State %-*s Command\n", (int)(2*sizeof(void *))+2, "Task Addr", (int)(2*sizeof(void *))+2, "Thread"); - mask = kdb_task_state_string(argc ? argv[1] : NULL); + mask = argc ? argv[1] : kdbgetenv("PS"); /* Run the active tasks first */ for_each_online_cpu(cpu) { if (KDB_FLAG(CMD_INTERRUPT)) @@ -2742,8 +2743,8 @@ static kdbtab_t maintab[] = { }, { .name = "bta", .func = kdb_bt, - .usage = "[D|R|S|T|C|Z|E|U|I|M|A]", - .help = "Backtrace all processes matching state flag", + .usage = "[<state_chars>|A]", + .help = "Backtrace all processes whose state matches", .flags = KDB_ENABLE_INSPECT, }, { .name = "btc", @@ -2797,7 +2798,7 @@ static kdbtab_t maintab[] = { }, { .name = "ps", .func = kdb_ps, - .usage = "[<flags>|A]", + .usage = "[<state_chars>|A]", .help = "Display active task list", .flags = KDB_ENABLE_INSPECT, }, diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h index 629590084a0d..0d2f9feea0a4 100644 --- a/kernel/debug/kdb/kdb_private.h +++ b/kernel/debug/kdb/kdb_private.h @@ -190,10 +190,8 @@ extern char kdb_grep_string[]; extern int kdb_grep_leading; extern int kdb_grep_trailing; extern char *kdb_cmds[]; -extern unsigned long kdb_task_state_string(const char *); extern char kdb_task_state_char (const struct task_struct *); -extern unsigned long kdb_task_state(const struct task_struct *p, - unsigned long mask); +extern bool kdb_task_state(const struct task_struct *p, const char *mask); extern void kdb_ps_suppressed(void); extern void kdb_ps1(const struct task_struct *p); extern void kdb_send_sig(struct task_struct *p, int sig); diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c index 7507d9a8dc6a..df2bface866e 100644 --- a/kernel/debug/kdb/kdb_support.c +++ b/kernel/debug/kdb/kdb_support.c @@ -24,6 +24,7 @@ #include <linux/uaccess.h> #include <linux/kdb.h> #include <linux/slab.h> +#include <linux/ctype.h> #include "kdb_private.h" /* @@ -473,82 +474,7 @@ int kdb_putword(unsigned long addr, unsigned long word, size_t size) return diag; } -/* - * kdb_task_state_string - Convert a string containing any of the - * letters DRSTCZEUIMA to a mask for the process state field and - * return the value. If no argument is supplied, return the mask - * that corresponds to environment variable PS, DRSTCZEU by - * default. - * Inputs: - * s String to convert - * Returns: - * Mask for process state. - * Notes: - * The mask folds data from several sources into a single long value, so - * be careful not to overlap the bits. TASK_* bits are in the LSB, - * special cases like UNRUNNABLE are in the MSB. As of 2.6.10-rc1 there - * is no overlap between TASK_* and EXIT_* but that may not always be - * true, so EXIT_* bits are shifted left 16 bits before being stored in - * the mask. - */ - -/* unrunnable is < 0 */ -#define UNRUNNABLE (1UL << (8*sizeof(unsigned long) - 1)) -#define RUNNING (1UL << (8*sizeof(unsigned long) - 2)) -#define IDLE (1UL << (8*sizeof(unsigned long) - 3)) -#define DAEMON (1UL << (8*sizeof(unsigned long) - 4)) -unsigned long kdb_task_state_string(const char *s) -{ - long res = 0; - if (!s) { - s = kdbgetenv("PS"); - if (!s) - s = "DRSTCZEU"; /* default value for ps */ - } - while (*s) { - switch (*s) { - case 'D': - res |= TASK_UNINTERRUPTIBLE; - break; - case 'R': - res |= RUNNING; - break; - case 'S': - res |= TASK_INTERRUPTIBLE; - break; - case 'T': - res |= TASK_STOPPED; - break; - case 'C': - res |= TASK_TRACED; - break; - case 'Z': - res |= EXIT_ZOMBIE << 16; - break; - case 'E': - res |= EXIT_DEAD << 16; - break; - case 'U': - res |= UNRUNNABLE; - break; - case 'I': - res |= IDLE; - break; - case 'M': - res |= DAEMON; - break; - case 'A': - res = ~0UL; - break; - default: - kdb_func_printf("unknown flag '%c' ignored\n", *s); - break; - } - ++s; - } - return res; -} /* * kdb_task_state_char - Return the character that represents the task state. @@ -559,7 +485,6 @@ unsigned long kdb_task_state_string(const char *s) */ char kdb_task_state_char (const struct task_struct *p) { - unsigned int p_state; unsigned long tmp; char state; int cpu; @@ -568,25 +493,18 @@ char kdb_task_state_char (const struct task_struct *p) copy_from_kernel_nofault(&tmp, (char *)p, sizeof(unsigned long))) return 'E'; - cpu = kdb_process_cpu(p); - p_state = READ_ONCE(p->__state); - state = (p_state == 0) ? 'R' : - (p_state < 0) ? 'U' : - (p_state & TASK_UNINTERRUPTIBLE) ? 'D' : - (p_state & TASK_STOPPED) ? 'T' : - (p_state & TASK_TRACED) ? 'C' : - (p->exit_state & EXIT_ZOMBIE) ? 'Z' : - (p->exit_state & EXIT_DEAD) ? 'E' : - (p_state & TASK_INTERRUPTIBLE) ? 'S' : '?'; + state = task_state_to_char((struct task_struct *) p); + if (is_idle_task(p)) { /* Idle task. Is it really idle, apart from the kdb * interrupt? */ + cpu = kdb_process_cpu(p); if (!kdb_task_has_cpu(p) || kgdb_info[cpu].irq_depth == 1) { if (cpu != kdb_initial_cpu) - state = 'I'; /* idle task */ + state = '-'; /* idle task */ } - } else if (!p->mm && state == 'S') { - state = 'M'; /* sleeping system daemon */ + } else if (!p->mm && strchr("IMS", state)) { + state = tolower(state); /* sleeping system daemon */ } return state; } @@ -596,14 +514,28 @@ char kdb_task_state_char (const struct task_struct *p) * given by the mask. * Inputs: * p struct task for the process - * mask mask from kdb_task_state_string to select processes + * mask set of characters used to select processes; both NULL + * and the empty string mean adopt a default filter, which + * is to suppress sleeping system daemons and the idle tasks * Returns: * True if the process matches at least one criteria defined by the mask. */ -unsigned long kdb_task_state(const struct task_struct *p, unsigned long mask) +bool kdb_task_state(const struct task_struct *p, const char *mask) { - char state[] = { kdb_task_state_char(p), '\0' }; - return (mask & kdb_task_state_string(state)) != 0; + char state = kdb_task_state_char(p); + + /* If there is no mask, then we will filter code that runs when the + * scheduler is idling and any system daemons that are currently + * sleeping. + */ + if (!mask || mask[0] == '\0') + return !strchr("-ims", state); + + /* A is a special case that matches all states */ + if (strchr(mask, 'A')) + return true; + + return strchr(mask, state); } /* Maintain a small stack of kdb_flags to allow recursion without disturbing diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c index 25fc85a7aebe..375fb3c9538d 100644 --- a/kernel/dma/coherent.c +++ b/kernel/dma/coherent.c @@ -40,7 +40,6 @@ static struct dma_coherent_mem *dma_init_coherent_memory(phys_addr_t phys_addr, { struct dma_coherent_mem *dma_mem; int pages = size >> PAGE_SHIFT; - int bitmap_size = BITS_TO_LONGS(pages) * sizeof(long); void *mem_base; if (!size) @@ -53,7 +52,7 @@ static struct dma_coherent_mem *dma_init_coherent_memory(phys_addr_t phys_addr, dma_mem = kzalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL); if (!dma_mem) goto out_unmap_membase; - dma_mem->bitmap = kzalloc(bitmap_size, GFP_KERNEL); + dma_mem->bitmap = bitmap_zalloc(pages, GFP_KERNEL); if (!dma_mem->bitmap) goto out_free_dma_mem; @@ -81,7 +80,7 @@ static void dma_release_coherent_memory(struct dma_coherent_mem *mem) return; memunmap(mem->virt_base); - kfree(mem->bitmap); + bitmap_free(mem->bitmap); kfree(mem); } diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 6fab31ea47d6..8e840fbbed7c 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -247,7 +247,7 @@ swiotlb_init(int verbose) return; fail_free_mem: - memblock_free_early(__pa(tlb), bytes); + memblock_free(tlb, bytes); fail: pr_warn("Cannot allocate buffer"); } diff --git a/kernel/entry/syscall_user_dispatch.c b/kernel/entry/syscall_user_dispatch.c index c240302f56e2..0b6379adff6b 100644 --- a/kernel/entry/syscall_user_dispatch.c +++ b/kernel/entry/syscall_user_dispatch.c @@ -47,14 +47,18 @@ bool syscall_user_dispatch(struct pt_regs *regs) * access_ok() is performed once, at prctl time, when * the selector is loaded by userspace. */ - if (unlikely(__get_user(state, sd->selector))) - do_exit(SIGSEGV); + if (unlikely(__get_user(state, sd->selector))) { + force_exit_sig(SIGSEGV); + return true; + } if (likely(state == SYSCALL_DISPATCH_FILTER_ALLOW)) return false; - if (state != SYSCALL_DISPATCH_FILTER_BLOCK) - do_exit(SIGSYS); + if (state != SYSCALL_DISPATCH_FILTER_BLOCK) { + force_exit_sig(SIGSYS); + return true; + } } sd->on_dispatch = true; diff --git a/kernel/events/core.c b/kernel/events/core.c index f2253ea729a2..30d94f68c5bd 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -7154,7 +7154,6 @@ void perf_output_sample(struct perf_output_handle *handle, static u64 perf_virt_to_phys(u64 virt) { u64 phys_addr = 0; - struct page *p = NULL; if (!virt) return 0; @@ -7173,14 +7172,15 @@ static u64 perf_virt_to_phys(u64 virt) * If failed, leave phys_addr as 0. */ if (current->mm != NULL) { + struct page *p; + pagefault_disable(); - if (get_user_page_fast_only(virt, 0, &p)) + if (get_user_page_fast_only(virt, 0, &p)) { phys_addr = page_to_phys(p) + virt % PAGE_SIZE; + put_page(p); + } pagefault_enable(); } - - if (p) - put_page(p); } return phys_addr; @@ -9759,6 +9759,9 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, continue; if (event->attr.config != entry->type) continue; + /* Cannot deliver synchronous signal to other task. */ + if (event->attr.sigtrap) + continue; if (perf_tp_event_match(event, &data, regs)) perf_swevent_event(event, count, &data, regs); } diff --git a/kernel/extable.c b/kernel/extable.c index b0ea5eb0c3b4..b6f330f0fe74 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -62,40 +62,13 @@ const struct exception_table_entry *search_exception_tables(unsigned long addr) return e; } -int init_kernel_text(unsigned long addr) -{ - if (addr >= (unsigned long)_sinittext && - addr < (unsigned long)_einittext) - return 1; - return 0; -} - int notrace core_kernel_text(unsigned long addr) { - if (addr >= (unsigned long)_stext && - addr < (unsigned long)_etext) + if (is_kernel_text(addr)) return 1; - if (system_state < SYSTEM_RUNNING && - init_kernel_text(addr)) - return 1; - return 0; -} - -/** - * core_kernel_data - tell if addr points to kernel data - * @addr: address to test - * - * Returns true if @addr passed in is from the core kernel data - * section. - * - * Note: On some archs it may return true for core RODATA, and false - * for others. But will always be true for core RW data. - */ -int core_kernel_data(unsigned long addr) -{ - if (addr >= (unsigned long)_sdata && - addr < (unsigned long)_edata) + if (system_state < SYSTEM_FREEING_INITMEM && + is_kernel_inittext(addr)) return 1; return 0; } @@ -112,7 +85,7 @@ int __kernel_text_address(unsigned long addr) * Since we are after the module-symbols check, there's * no danger of address overlap: */ - if (init_kernel_text(addr)) + if (is_kernel_inittext(addr)) return 1; return 0; } diff --git a/kernel/fork.c b/kernel/fork.c index 3f112b11a9ad..3244cc56b697 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2277,6 +2277,7 @@ static __latent_entropy struct task_struct *copy_process( p->pdeath_signal = 0; INIT_LIST_HEAD(&p->thread_group); p->task_works = NULL; + clear_posix_cputimers_work(p); #ifdef CONFIG_KRETPROBES p->kretprobe_instances.first = NULL; @@ -3024,7 +3025,7 @@ int unshare_fd(unsigned long unshare_flags, unsigned int max_fds, int ksys_unshare(unsigned long unshare_flags) { struct fs_struct *fs, *new_fs = NULL; - struct files_struct *fd, *new_fd = NULL; + struct files_struct *new_fd = NULL; struct cred *new_cred = NULL; struct nsproxy *new_nsproxy = NULL; int do_sysvsem = 0; @@ -3111,11 +3112,8 @@ int ksys_unshare(unsigned long unshare_flags) spin_unlock(&fs->lock); } - if (new_fd) { - fd = current->files; - current->files = new_fd; - new_fd = fd; - } + if (new_fd) + swap(current->files, new_fd); task_unlock(current); diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 4d8fc65cf38f..bf38c546aa25 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -744,9 +744,8 @@ static int irq_domain_translate(struct irq_domain *d, return 0; } -static void of_phandle_args_to_fwspec(struct device_node *np, const u32 *args, - unsigned int count, - struct irq_fwspec *fwspec) +void of_phandle_args_to_fwspec(struct device_node *np, const u32 *args, + unsigned int count, struct irq_fwspec *fwspec) { int i; @@ -756,6 +755,7 @@ static void of_phandle_args_to_fwspec(struct device_node *np, const u32 *args, for (i = 0; i < count; i++) fwspec->param[i] = args[i]; } +EXPORT_SYMBOL_GPL(of_phandle_args_to_fwspec); unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec) { @@ -1502,6 +1502,7 @@ out_free_desc: irq_free_descs(virq, nr_irqs); return ret; } +EXPORT_SYMBOL_GPL(__irq_domain_alloc_irqs); /* The irq_data was moved, fix the revmap to refer to the new location */ static void irq_domain_fix_revmap(struct irq_data *d) diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 6a5ecee6e567..7f350ae59c5f 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -529,10 +529,10 @@ static bool msi_check_reservation_mode(struct irq_domain *domain, /* * Checking the first MSI descriptor is sufficient. MSIX supports - * masking and MSI does so when the maskbit is set. + * masking and MSI does so when the can_mask attribute is set. */ desc = first_msi_entry(dev); - return desc->msi_attrib.is_msix || desc->msi_attrib.maskbit; + return desc->msi_attrib.is_msix || desc->msi_attrib.can_mask; } int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, diff --git a/kernel/kcov.c b/kernel/kcov.c index 80bfe71bbe13..36ca640c4f8e 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -88,6 +88,7 @@ static struct list_head kcov_remote_areas = LIST_HEAD_INIT(kcov_remote_areas); struct kcov_percpu_data { void *irq_area; + local_lock_t lock; unsigned int saved_mode; unsigned int saved_size; @@ -96,7 +97,9 @@ struct kcov_percpu_data { int saved_sequence; }; -static DEFINE_PER_CPU(struct kcov_percpu_data, kcov_percpu_data); +static DEFINE_PER_CPU(struct kcov_percpu_data, kcov_percpu_data) = { + .lock = INIT_LOCAL_LOCK(lock), +}; /* Must be called with kcov_remote_lock locked. */ static struct kcov_remote *kcov_remote_find(u64 handle) @@ -824,7 +827,7 @@ void kcov_remote_start(u64 handle) if (!in_task() && !in_serving_softirq()) return; - local_irq_save(flags); + local_lock_irqsave(&kcov_percpu_data.lock, flags); /* * Check that kcov_remote_start() is not called twice in background @@ -832,7 +835,7 @@ void kcov_remote_start(u64 handle) */ mode = READ_ONCE(t->kcov_mode); if (WARN_ON(in_task() && kcov_mode_enabled(mode))) { - local_irq_restore(flags); + local_unlock_irqrestore(&kcov_percpu_data.lock, flags); return; } /* @@ -841,14 +844,15 @@ void kcov_remote_start(u64 handle) * happened while collecting coverage from a background thread. */ if (WARN_ON(in_serving_softirq() && t->kcov_softirq)) { - local_irq_restore(flags); + local_unlock_irqrestore(&kcov_percpu_data.lock, flags); return; } spin_lock(&kcov_remote_lock); remote = kcov_remote_find(handle); if (!remote) { - spin_unlock_irqrestore(&kcov_remote_lock, flags); + spin_unlock(&kcov_remote_lock); + local_unlock_irqrestore(&kcov_percpu_data.lock, flags); return; } kcov_debug("handle = %llx, context: %s\n", handle, @@ -869,19 +873,19 @@ void kcov_remote_start(u64 handle) size = CONFIG_KCOV_IRQ_AREA_SIZE; area = this_cpu_ptr(&kcov_percpu_data)->irq_area; } - spin_unlock_irqrestore(&kcov_remote_lock, flags); + spin_unlock(&kcov_remote_lock); /* Can only happen when in_task(). */ if (!area) { + local_unlock_irqrestore(&kcov_percpu_data.lock, flags); area = vmalloc(size * sizeof(unsigned long)); if (!area) { kcov_put(kcov); return; } + local_lock_irqsave(&kcov_percpu_data.lock, flags); } - local_irq_save(flags); - /* Reset coverage size. */ *(u64 *)area = 0; @@ -891,7 +895,7 @@ void kcov_remote_start(u64 handle) } kcov_start(t, kcov, size, area, mode, sequence); - local_irq_restore(flags); + local_unlock_irqrestore(&kcov_percpu_data.lock, flags); } EXPORT_SYMBOL(kcov_remote_start); @@ -965,12 +969,12 @@ void kcov_remote_stop(void) if (!in_task() && !in_serving_softirq()) return; - local_irq_save(flags); + local_lock_irqsave(&kcov_percpu_data.lock, flags); mode = READ_ONCE(t->kcov_mode); barrier(); if (!kcov_mode_enabled(mode)) { - local_irq_restore(flags); + local_unlock_irqrestore(&kcov_percpu_data.lock, flags); return; } /* @@ -978,12 +982,12 @@ void kcov_remote_stop(void) * actually found the remote handle and started collecting coverage. */ if (in_serving_softirq() && !t->kcov_softirq) { - local_irq_restore(flags); + local_unlock_irqrestore(&kcov_percpu_data.lock, flags); return; } /* Make sure that kcov_softirq is only set when in softirq. */ if (WARN_ON(!in_serving_softirq() && t->kcov_softirq)) { - local_irq_restore(flags); + local_unlock_irqrestore(&kcov_percpu_data.lock, flags); return; } @@ -1013,7 +1017,7 @@ void kcov_remote_stop(void) spin_unlock(&kcov_remote_lock); } - local_irq_restore(flags); + local_unlock_irqrestore(&kcov_percpu_data.lock, flags); /* Get in kcov_remote_start(). */ kcov_put(kcov); @@ -1034,8 +1038,8 @@ static int __init kcov_init(void) int cpu; for_each_possible_cpu(cpu) { - void *area = vmalloc(CONFIG_KCOV_IRQ_AREA_SIZE * - sizeof(unsigned long)); + void *area = vmalloc_node(CONFIG_KCOV_IRQ_AREA_SIZE * + sizeof(unsigned long), cpu_to_node(cpu)); if (!area) return -ENOMEM; per_cpu_ptr(&kcov_percpu_data, cpu)->irq_area = area; diff --git a/kernel/kcsan/core.c b/kernel/kcsan/core.c index 76e67d1e02d4..4b84c8e7884b 100644 --- a/kernel/kcsan/core.c +++ b/kernel/kcsan/core.c @@ -202,6 +202,9 @@ static __always_inline struct kcsan_ctx *get_ctx(void) return in_task() ? ¤t->kcsan_ctx : raw_cpu_ptr(&kcsan_cpu_ctx); } +static __always_inline void +check_access(const volatile void *ptr, size_t size, int type, unsigned long ip); + /* Check scoped accesses; never inline because this is a slow-path! */ static noinline void kcsan_check_scoped_accesses(void) { @@ -210,14 +213,16 @@ static noinline void kcsan_check_scoped_accesses(void) struct kcsan_scoped_access *scoped_access; ctx->scoped_accesses.prev = NULL; /* Avoid recursion. */ - list_for_each_entry(scoped_access, &ctx->scoped_accesses, list) - __kcsan_check_access(scoped_access->ptr, scoped_access->size, scoped_access->type); + list_for_each_entry(scoped_access, &ctx->scoped_accesses, list) { + check_access(scoped_access->ptr, scoped_access->size, + scoped_access->type, scoped_access->ip); + } ctx->scoped_accesses.prev = prev_save; } /* Rules for generic atomic accesses. Called from fast-path. */ static __always_inline bool -is_atomic(const volatile void *ptr, size_t size, int type, struct kcsan_ctx *ctx) +is_atomic(struct kcsan_ctx *ctx, const volatile void *ptr, size_t size, int type) { if (type & KCSAN_ACCESS_ATOMIC) return true; @@ -254,7 +259,7 @@ is_atomic(const volatile void *ptr, size_t size, int type, struct kcsan_ctx *ctx } static __always_inline bool -should_watch(const volatile void *ptr, size_t size, int type, struct kcsan_ctx *ctx) +should_watch(struct kcsan_ctx *ctx, const volatile void *ptr, size_t size, int type) { /* * Never set up watchpoints when memory operations are atomic. @@ -263,7 +268,7 @@ should_watch(const volatile void *ptr, size_t size, int type, struct kcsan_ctx * * should not count towards skipped instructions, and (2) to actually * decrement kcsan_atomic_next for consecutive instruction stream. */ - if (is_atomic(ptr, size, type, ctx)) + if (is_atomic(ctx, ptr, size, type)) return false; if (this_cpu_dec_return(kcsan_skip) >= 0) @@ -350,6 +355,7 @@ void kcsan_restore_irqtrace(struct task_struct *task) static noinline void kcsan_found_watchpoint(const volatile void *ptr, size_t size, int type, + unsigned long ip, atomic_long_t *watchpoint, long encoded_watchpoint) { @@ -396,7 +402,7 @@ static noinline void kcsan_found_watchpoint(const volatile void *ptr, if (consumed) { kcsan_save_irqtrace(current); - kcsan_report_set_info(ptr, size, type, watchpoint - watchpoints); + kcsan_report_set_info(ptr, size, type, ip, watchpoint - watchpoints); kcsan_restore_irqtrace(current); } else { /* @@ -416,7 +422,7 @@ static noinline void kcsan_found_watchpoint(const volatile void *ptr, } static noinline void -kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type) +kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type, unsigned long ip) { const bool is_write = (type & KCSAN_ACCESS_WRITE) != 0; const bool is_assert = (type & KCSAN_ACCESS_ASSERT) != 0; @@ -568,8 +574,8 @@ kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type) if (is_assert && value_change == KCSAN_VALUE_CHANGE_TRUE) atomic_long_inc(&kcsan_counters[KCSAN_COUNTER_ASSERT_FAILURES]); - kcsan_report_known_origin(ptr, size, type, value_change, - watchpoint - watchpoints, + kcsan_report_known_origin(ptr, size, type, ip, + value_change, watchpoint - watchpoints, old, new, access_mask); } else if (value_change == KCSAN_VALUE_CHANGE_TRUE) { /* Inferring a race, since the value should not have changed. */ @@ -578,8 +584,10 @@ kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type) if (is_assert) atomic_long_inc(&kcsan_counters[KCSAN_COUNTER_ASSERT_FAILURES]); - if (IS_ENABLED(CONFIG_KCSAN_REPORT_RACE_UNKNOWN_ORIGIN) || is_assert) - kcsan_report_unknown_origin(ptr, size, type, old, new, access_mask); + if (IS_ENABLED(CONFIG_KCSAN_REPORT_RACE_UNKNOWN_ORIGIN) || is_assert) { + kcsan_report_unknown_origin(ptr, size, type, ip, + old, new, access_mask); + } } /* @@ -596,8 +604,8 @@ out: user_access_restore(ua_flags); } -static __always_inline void check_access(const volatile void *ptr, size_t size, - int type) +static __always_inline void +check_access(const volatile void *ptr, size_t size, int type, unsigned long ip) { const bool is_write = (type & KCSAN_ACCESS_WRITE) != 0; atomic_long_t *watchpoint; @@ -625,13 +633,12 @@ static __always_inline void check_access(const volatile void *ptr, size_t size, */ if (unlikely(watchpoint != NULL)) - kcsan_found_watchpoint(ptr, size, type, watchpoint, - encoded_watchpoint); + kcsan_found_watchpoint(ptr, size, type, ip, watchpoint, encoded_watchpoint); else { struct kcsan_ctx *ctx = get_ctx(); /* Call only once in fast-path. */ - if (unlikely(should_watch(ptr, size, type, ctx))) - kcsan_setup_watchpoint(ptr, size, type); + if (unlikely(should_watch(ctx, ptr, size, type))) + kcsan_setup_watchpoint(ptr, size, type, ip); else if (unlikely(ctx->scoped_accesses.prev)) kcsan_check_scoped_accesses(); } @@ -757,7 +764,7 @@ kcsan_begin_scoped_access(const volatile void *ptr, size_t size, int type, { struct kcsan_ctx *ctx = get_ctx(); - __kcsan_check_access(ptr, size, type); + check_access(ptr, size, type, _RET_IP_); ctx->disable_count++; /* Disable KCSAN, in case list debugging is on. */ @@ -765,6 +772,7 @@ kcsan_begin_scoped_access(const volatile void *ptr, size_t size, int type, sa->ptr = ptr; sa->size = size; sa->type = type; + sa->ip = _RET_IP_; if (!ctx->scoped_accesses.prev) /* Lazy initialize list head. */ INIT_LIST_HEAD(&ctx->scoped_accesses); @@ -796,13 +804,13 @@ void kcsan_end_scoped_access(struct kcsan_scoped_access *sa) ctx->disable_count--; - __kcsan_check_access(sa->ptr, sa->size, sa->type); + check_access(sa->ptr, sa->size, sa->type, sa->ip); } EXPORT_SYMBOL(kcsan_end_scoped_access); void __kcsan_check_access(const volatile void *ptr, size_t size, int type) { - check_access(ptr, size, type); + check_access(ptr, size, type, _RET_IP_); } EXPORT_SYMBOL(__kcsan_check_access); @@ -823,7 +831,7 @@ EXPORT_SYMBOL(__kcsan_check_access); void __tsan_read##size(void *ptr); \ void __tsan_read##size(void *ptr) \ { \ - check_access(ptr, size, 0); \ + check_access(ptr, size, 0, _RET_IP_); \ } \ EXPORT_SYMBOL(__tsan_read##size); \ void __tsan_unaligned_read##size(void *ptr) \ @@ -832,7 +840,7 @@ EXPORT_SYMBOL(__kcsan_check_access); void __tsan_write##size(void *ptr); \ void __tsan_write##size(void *ptr) \ { \ - check_access(ptr, size, KCSAN_ACCESS_WRITE); \ + check_access(ptr, size, KCSAN_ACCESS_WRITE, _RET_IP_); \ } \ EXPORT_SYMBOL(__tsan_write##size); \ void __tsan_unaligned_write##size(void *ptr) \ @@ -842,7 +850,8 @@ EXPORT_SYMBOL(__kcsan_check_access); void __tsan_read_write##size(void *ptr) \ { \ check_access(ptr, size, \ - KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE); \ + KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE, \ + _RET_IP_); \ } \ EXPORT_SYMBOL(__tsan_read_write##size); \ void __tsan_unaligned_read_write##size(void *ptr) \ @@ -858,14 +867,14 @@ DEFINE_TSAN_READ_WRITE(16); void __tsan_read_range(void *ptr, size_t size); void __tsan_read_range(void *ptr, size_t size) { - check_access(ptr, size, 0); + check_access(ptr, size, 0, _RET_IP_); } EXPORT_SYMBOL(__tsan_read_range); void __tsan_write_range(void *ptr, size_t size); void __tsan_write_range(void *ptr, size_t size) { - check_access(ptr, size, KCSAN_ACCESS_WRITE); + check_access(ptr, size, KCSAN_ACCESS_WRITE, _RET_IP_); } EXPORT_SYMBOL(__tsan_write_range); @@ -886,7 +895,8 @@ EXPORT_SYMBOL(__tsan_write_range); IS_ALIGNED((unsigned long)ptr, size); \ if (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS) && is_atomic) \ return; \ - check_access(ptr, size, is_atomic ? KCSAN_ACCESS_ATOMIC : 0); \ + check_access(ptr, size, is_atomic ? KCSAN_ACCESS_ATOMIC : 0, \ + _RET_IP_); \ } \ EXPORT_SYMBOL(__tsan_volatile_read##size); \ void __tsan_unaligned_volatile_read##size(void *ptr) \ @@ -901,7 +911,8 @@ EXPORT_SYMBOL(__tsan_write_range); return; \ check_access(ptr, size, \ KCSAN_ACCESS_WRITE | \ - (is_atomic ? KCSAN_ACCESS_ATOMIC : 0)); \ + (is_atomic ? KCSAN_ACCESS_ATOMIC : 0), \ + _RET_IP_); \ } \ EXPORT_SYMBOL(__tsan_volatile_write##size); \ void __tsan_unaligned_volatile_write##size(void *ptr) \ @@ -955,7 +966,7 @@ EXPORT_SYMBOL(__tsan_init); u##bits __tsan_atomic##bits##_load(const u##bits *ptr, int memorder) \ { \ if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { \ - check_access(ptr, bits / BITS_PER_BYTE, KCSAN_ACCESS_ATOMIC); \ + check_access(ptr, bits / BITS_PER_BYTE, KCSAN_ACCESS_ATOMIC, _RET_IP_); \ } \ return __atomic_load_n(ptr, memorder); \ } \ @@ -965,7 +976,7 @@ EXPORT_SYMBOL(__tsan_init); { \ if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { \ check_access(ptr, bits / BITS_PER_BYTE, \ - KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC); \ + KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC, _RET_IP_); \ } \ __atomic_store_n(ptr, v, memorder); \ } \ @@ -978,7 +989,7 @@ EXPORT_SYMBOL(__tsan_init); if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { \ check_access(ptr, bits / BITS_PER_BYTE, \ KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | \ - KCSAN_ACCESS_ATOMIC); \ + KCSAN_ACCESS_ATOMIC, _RET_IP_); \ } \ return __atomic_##op##suffix(ptr, v, memorder); \ } \ @@ -1010,7 +1021,7 @@ EXPORT_SYMBOL(__tsan_init); if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { \ check_access(ptr, bits / BITS_PER_BYTE, \ KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | \ - KCSAN_ACCESS_ATOMIC); \ + KCSAN_ACCESS_ATOMIC, _RET_IP_); \ } \ return __atomic_compare_exchange_n(ptr, exp, val, weak, mo, fail_mo); \ } \ @@ -1025,7 +1036,7 @@ EXPORT_SYMBOL(__tsan_init); if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { \ check_access(ptr, bits / BITS_PER_BYTE, \ KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | \ - KCSAN_ACCESS_ATOMIC); \ + KCSAN_ACCESS_ATOMIC, _RET_IP_); \ } \ __atomic_compare_exchange_n(ptr, &exp, val, 0, mo, fail_mo); \ return exp; \ diff --git a/kernel/kcsan/kcsan.h b/kernel/kcsan/kcsan.h index f36e25c497ed..ae33c2a7f07e 100644 --- a/kernel/kcsan/kcsan.h +++ b/kernel/kcsan/kcsan.h @@ -121,7 +121,7 @@ enum kcsan_value_change { * to be consumed by the reporting thread. No report is printed yet. */ void kcsan_report_set_info(const volatile void *ptr, size_t size, int access_type, - int watchpoint_idx); + unsigned long ip, int watchpoint_idx); /* * The calling thread observed that the watchpoint it set up was hit and @@ -129,14 +129,14 @@ void kcsan_report_set_info(const volatile void *ptr, size_t size, int access_typ * thread. */ void kcsan_report_known_origin(const volatile void *ptr, size_t size, int access_type, - enum kcsan_value_change value_change, int watchpoint_idx, - u64 old, u64 new, u64 mask); + unsigned long ip, enum kcsan_value_change value_change, + int watchpoint_idx, u64 old, u64 new, u64 mask); /* * No other thread was observed to race with the access, but the data value * before and after the stall differs. Reports a race of "unknown origin". */ void kcsan_report_unknown_origin(const volatile void *ptr, size_t size, int access_type, - u64 old, u64 new, u64 mask); + unsigned long ip, u64 old, u64 new, u64 mask); #endif /* _KERNEL_KCSAN_KCSAN_H */ diff --git a/kernel/kcsan/kcsan_test.c b/kernel/kcsan/kcsan_test.c index dc55fd5a36fc..660729238588 100644 --- a/kernel/kcsan/kcsan_test.c +++ b/kernel/kcsan/kcsan_test.c @@ -29,6 +29,11 @@ #include <linux/types.h> #include <trace/events/printk.h> +#define KCSAN_TEST_REQUIRES(test, cond) do { \ + if (!(cond)) \ + kunit_skip((test), "Test requires: " #cond); \ +} while (0) + #ifdef CONFIG_CC_HAS_TSAN_COMPOUND_READ_BEFORE_WRITE #define __KCSAN_ACCESS_RW(alt) (KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE) #else @@ -205,10 +210,12 @@ static bool report_matches(const struct expect_report *r) "read-write" : "write") : "read"); + const bool is_atomic = (ty & KCSAN_ACCESS_ATOMIC); + const bool is_scoped = (ty & KCSAN_ACCESS_SCOPED); const char *const access_type_aux = - (ty & KCSAN_ACCESS_ATOMIC) ? - " (marked)" : - ((ty & KCSAN_ACCESS_SCOPED) ? " (scoped)" : ""); + (is_atomic && is_scoped) ? " (marked, scoped)" + : (is_atomic ? " (marked)" + : (is_scoped ? " (scoped)" : "")); if (i == 1) { /* Access 2 */ @@ -333,7 +340,10 @@ static noinline void test_kernel_assert_bits_nochange(void) ASSERT_EXCLUSIVE_BITS(test_var, ~TEST_CHANGE_BITS); } -/* To check that scoped assertions do trigger anywhere in scope. */ +/* + * Scoped assertions do trigger anywhere in scope. However, the report should + * still only point at the start of the scope. + */ static noinline void test_enter_scope(void) { int x = 0; @@ -488,17 +498,24 @@ static void test_concurrent_races(struct kunit *test) __no_kcsan static void test_novalue_change(struct kunit *test) { - const struct expect_report expect = { + const struct expect_report expect_rw = { .access = { { test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, { test_kernel_read, &test_var, sizeof(test_var), 0 }, }, }; + const struct expect_report expect_ww = { + .access = { + { test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + { test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + }, + }; bool match_expect = false; + test_kernel_write_nochange(); /* Reset value. */ begin_test_checks(test_kernel_write_nochange, test_kernel_read); do { - match_expect = report_matches(&expect); + match_expect = report_matches(&expect_rw) || report_matches(&expect_ww); } while (!end_test_checks(match_expect)); if (IS_ENABLED(CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY)) KUNIT_EXPECT_FALSE(test, match_expect); @@ -513,17 +530,24 @@ static void test_novalue_change(struct kunit *test) __no_kcsan static void test_novalue_change_exception(struct kunit *test) { - const struct expect_report expect = { + const struct expect_report expect_rw = { .access = { { test_kernel_write_nochange_rcu, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, { test_kernel_read, &test_var, sizeof(test_var), 0 }, }, }; + const struct expect_report expect_ww = { + .access = { + { test_kernel_write_nochange_rcu, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + { test_kernel_write_nochange_rcu, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + }, + }; bool match_expect = false; + test_kernel_write_nochange_rcu(); /* Reset value. */ begin_test_checks(test_kernel_write_nochange_rcu, test_kernel_read); do { - match_expect = report_matches(&expect); + match_expect = report_matches(&expect_rw) || report_matches(&expect_ww); } while (!end_test_checks(match_expect)); KUNIT_EXPECT_TRUE(test, match_expect); } @@ -642,8 +666,7 @@ static void test_read_plain_atomic_write(struct kunit *test) }; bool match_expect = false; - if (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) - return; + KCSAN_TEST_REQUIRES(test, !IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)); begin_test_checks(test_kernel_read, test_kernel_write_atomic); do { @@ -665,8 +688,7 @@ static void test_read_plain_atomic_rmw(struct kunit *test) }; bool match_expect = false; - if (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) - return; + KCSAN_TEST_REQUIRES(test, !IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)); begin_test_checks(test_kernel_read, test_kernel_atomic_rmw); do { @@ -828,22 +850,22 @@ static void test_assert_exclusive_writer_scoped(struct kunit *test) { test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, }, }; - const struct expect_report expect_anywhere = { + const struct expect_report expect_inscope = { .access = { { test_enter_scope, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_SCOPED }, { test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, }, }; bool match_expect_start = false; - bool match_expect_anywhere = false; + bool match_expect_inscope = false; begin_test_checks(test_kernel_assert_writer_scoped, test_kernel_write_nochange); do { match_expect_start |= report_matches(&expect_start); - match_expect_anywhere |= report_matches(&expect_anywhere); - } while (!end_test_checks(match_expect_start && match_expect_anywhere)); + match_expect_inscope |= report_matches(&expect_inscope); + } while (!end_test_checks(match_expect_inscope)); KUNIT_EXPECT_TRUE(test, match_expect_start); - KUNIT_EXPECT_TRUE(test, match_expect_anywhere); + KUNIT_EXPECT_FALSE(test, match_expect_inscope); } __no_kcsan @@ -872,9 +894,9 @@ static void test_assert_exclusive_access_scoped(struct kunit *test) do { match_expect_start |= report_matches(&expect_start1) || report_matches(&expect_start2); match_expect_inscope |= report_matches(&expect_inscope); - } while (!end_test_checks(match_expect_start && match_expect_inscope)); + } while (!end_test_checks(match_expect_inscope)); KUNIT_EXPECT_TRUE(test, match_expect_start); - KUNIT_EXPECT_TRUE(test, match_expect_inscope); + KUNIT_EXPECT_FALSE(test, match_expect_inscope); } /* @@ -1224,7 +1246,7 @@ static void kcsan_test_exit(void) tracepoint_synchronize_unregister(); } -late_initcall(kcsan_test_init); +late_initcall_sync(kcsan_test_init); module_exit(kcsan_test_exit); MODULE_LICENSE("GPL v2"); diff --git a/kernel/kcsan/report.c b/kernel/kcsan/report.c index 21137929d428..fc15077991c4 100644 --- a/kernel/kcsan/report.c +++ b/kernel/kcsan/report.c @@ -8,6 +8,7 @@ #include <linux/debug_locks.h> #include <linux/delay.h> #include <linux/jiffies.h> +#include <linux/kallsyms.h> #include <linux/kernel.h> #include <linux/lockdep.h> #include <linux/preempt.h> @@ -31,6 +32,7 @@ struct access_info { int access_type; int task_pid; int cpu_id; + unsigned long ip; }; /* @@ -245,6 +247,10 @@ static const char *get_access_type(int type) return "write (scoped)"; case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC: return "write (marked, scoped)"; + case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE: + return "read-write (scoped)"; + case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC: + return "read-write (marked, scoped)"; default: BUG(); } @@ -300,6 +306,48 @@ static int get_stack_skipnr(const unsigned long stack_entries[], int num_entries return skip; } +/* + * Skips to the first entry that matches the function of @ip, and then replaces + * that entry with @ip, returning the entries to skip. + */ +static int +replace_stack_entry(unsigned long stack_entries[], int num_entries, unsigned long ip) +{ + unsigned long symbolsize, offset; + unsigned long target_func; + int skip; + + if (kallsyms_lookup_size_offset(ip, &symbolsize, &offset)) + target_func = ip - offset; + else + goto fallback; + + for (skip = 0; skip < num_entries; ++skip) { + unsigned long func = stack_entries[skip]; + + if (!kallsyms_lookup_size_offset(func, &symbolsize, &offset)) + goto fallback; + func -= offset; + + if (func == target_func) { + stack_entries[skip] = ip; + return skip; + } + } + +fallback: + /* Should not happen; the resulting stack trace is likely misleading. */ + WARN_ONCE(1, "Cannot find frame for %pS in stack trace", (void *)ip); + return get_stack_skipnr(stack_entries, num_entries); +} + +static int +sanitize_stack_entries(unsigned long stack_entries[], int num_entries, unsigned long ip) +{ + return ip ? replace_stack_entry(stack_entries, num_entries, ip) : + get_stack_skipnr(stack_entries, num_entries); +} + /* Compares symbolized strings of addr1 and addr2. */ static int sym_strcmp(void *addr1, void *addr2) { @@ -327,12 +375,12 @@ static void print_verbose_info(struct task_struct *task) static void print_report(enum kcsan_value_change value_change, const struct access_info *ai, - const struct other_info *other_info, + struct other_info *other_info, u64 old, u64 new, u64 mask) { unsigned long stack_entries[NUM_STACK_ENTRIES] = { 0 }; int num_stack_entries = stack_trace_save(stack_entries, NUM_STACK_ENTRIES, 1); - int skipnr = get_stack_skipnr(stack_entries, num_stack_entries); + int skipnr = sanitize_stack_entries(stack_entries, num_stack_entries, ai->ip); unsigned long this_frame = stack_entries[skipnr]; unsigned long other_frame = 0; int other_skipnr = 0; /* silence uninit warnings */ @@ -344,8 +392,9 @@ static void print_report(enum kcsan_value_change value_change, return; if (other_info) { - other_skipnr = get_stack_skipnr(other_info->stack_entries, - other_info->num_stack_entries); + other_skipnr = sanitize_stack_entries(other_info->stack_entries, + other_info->num_stack_entries, + other_info->ai.ip); other_frame = other_info->stack_entries[other_skipnr]; /* @value_change is only known for the other thread */ @@ -576,21 +625,23 @@ discard: } static struct access_info prepare_access_info(const volatile void *ptr, size_t size, - int access_type) + int access_type, unsigned long ip) { return (struct access_info) { .ptr = ptr, .size = size, .access_type = access_type, .task_pid = in_task() ? task_pid_nr(current) : -1, - .cpu_id = raw_smp_processor_id() + .cpu_id = raw_smp_processor_id(), + /* Only replace stack entry with @ip if scoped access. */ + .ip = (access_type & KCSAN_ACCESS_SCOPED) ? ip : 0, }; } void kcsan_report_set_info(const volatile void *ptr, size_t size, int access_type, - int watchpoint_idx) + unsigned long ip, int watchpoint_idx) { - const struct access_info ai = prepare_access_info(ptr, size, access_type); + const struct access_info ai = prepare_access_info(ptr, size, access_type, ip); unsigned long flags; kcsan_disable_current(); @@ -603,10 +654,10 @@ void kcsan_report_set_info(const volatile void *ptr, size_t size, int access_typ } void kcsan_report_known_origin(const volatile void *ptr, size_t size, int access_type, - enum kcsan_value_change value_change, int watchpoint_idx, - u64 old, u64 new, u64 mask) + unsigned long ip, enum kcsan_value_change value_change, + int watchpoint_idx, u64 old, u64 new, u64 mask) { - const struct access_info ai = prepare_access_info(ptr, size, access_type); + const struct access_info ai = prepare_access_info(ptr, size, access_type, ip); struct other_info *other_info = &other_infos[watchpoint_idx]; unsigned long flags = 0; @@ -637,9 +688,9 @@ out: } void kcsan_report_unknown_origin(const volatile void *ptr, size_t size, int access_type, - u64 old, u64 new, u64 mask) + unsigned long ip, u64 old, u64 new, u64 mask) { - const struct access_info ai = prepare_access_info(ptr, size, access_type); + const struct access_info ai = prepare_access_info(ptr, size, access_type, ip); unsigned long flags; kcsan_disable_current(); diff --git a/kernel/kcsan/selftest.c b/kernel/kcsan/selftest.c index 7f29cb0f5e63..b4295a3892b7 100644 --- a/kernel/kcsan/selftest.c +++ b/kernel/kcsan/selftest.c @@ -18,7 +18,7 @@ #define ITERS_PER_TEST 2000 /* Test requirements. */ -static bool test_requires(void) +static bool __init test_requires(void) { /* random should be initialized for the below tests */ return prandom_u32() + prandom_u32() != 0; @@ -28,14 +28,18 @@ static bool test_requires(void) * Test watchpoint encode and decode: check that encoding some access's info, * and then subsequent decode preserves the access's info. */ -static bool test_encode_decode(void) +static bool __init test_encode_decode(void) { int i; for (i = 0; i < ITERS_PER_TEST; ++i) { size_t size = prandom_u32_max(MAX_ENCODABLE_SIZE) + 1; bool is_write = !!prandom_u32_max(2); + unsigned long verif_masked_addr; + long encoded_watchpoint; + bool verif_is_write; unsigned long addr; + size_t verif_size; prandom_bytes(&addr, sizeof(addr)); if (addr < PAGE_SIZE) @@ -44,53 +48,37 @@ static bool test_encode_decode(void) if (WARN_ON(!check_encodable(addr, size))) return false; - /* Encode and decode */ - { - const long encoded_watchpoint = - encode_watchpoint(addr, size, is_write); - unsigned long verif_masked_addr; - size_t verif_size; - bool verif_is_write; - - /* Check special watchpoints */ - if (WARN_ON(decode_watchpoint( - INVALID_WATCHPOINT, &verif_masked_addr, - &verif_size, &verif_is_write))) - return false; - if (WARN_ON(decode_watchpoint( - CONSUMED_WATCHPOINT, &verif_masked_addr, - &verif_size, &verif_is_write))) - return false; - - /* Check decoding watchpoint returns same data */ - if (WARN_ON(!decode_watchpoint( - encoded_watchpoint, &verif_masked_addr, - &verif_size, &verif_is_write))) - return false; - if (WARN_ON(verif_masked_addr != - (addr & WATCHPOINT_ADDR_MASK))) - goto fail; - if (WARN_ON(verif_size != size)) - goto fail; - if (WARN_ON(is_write != verif_is_write)) - goto fail; - - continue; -fail: - pr_err("%s fail: %s %zu bytes @ %lx -> encoded: %lx -> %s %zu bytes @ %lx\n", - __func__, is_write ? "write" : "read", size, - addr, encoded_watchpoint, - verif_is_write ? "write" : "read", verif_size, - verif_masked_addr); + encoded_watchpoint = encode_watchpoint(addr, size, is_write); + + /* Check special watchpoints */ + if (WARN_ON(decode_watchpoint(INVALID_WATCHPOINT, &verif_masked_addr, &verif_size, &verif_is_write))) return false; - } + if (WARN_ON(decode_watchpoint(CONSUMED_WATCHPOINT, &verif_masked_addr, &verif_size, &verif_is_write))) + return false; + + /* Check decoding watchpoint returns same data */ + if (WARN_ON(!decode_watchpoint(encoded_watchpoint, &verif_masked_addr, &verif_size, &verif_is_write))) + return false; + if (WARN_ON(verif_masked_addr != (addr & WATCHPOINT_ADDR_MASK))) + goto fail; + if (WARN_ON(verif_size != size)) + goto fail; + if (WARN_ON(is_write != verif_is_write)) + goto fail; + + continue; +fail: + pr_err("%s fail: %s %zu bytes @ %lx -> encoded: %lx -> %s %zu bytes @ %lx\n", + __func__, is_write ? "write" : "read", size, addr, encoded_watchpoint, + verif_is_write ? "write" : "read", verif_size, verif_masked_addr); + return false; } return true; } /* Test access matching function. */ -static bool test_matching_access(void) +static bool __init test_matching_access(void) { if (WARN_ON(!matching_access(10, 1, 10, 1))) return false; diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 33400ff051a8..8347fc158d2b 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -556,6 +556,11 @@ static int kexec_walk_memblock(struct kexec_buf *kbuf, if (kbuf->image->type == KEXEC_TYPE_CRASH) return func(&crashk_res, kbuf); + /* + * Using MEMBLOCK_NONE will properly skip MEMBLOCK_DRIVER_MANAGED. See + * IORESOURCE_SYSRAM_DRIVER_MANAGED handling in + * locate_mem_hole_callback(). + */ if (kbuf->top_down) { for_each_free_mem_range_reverse(i, NUMA_NO_NODE, MEMBLOCK_NONE, &mstart, &mend, NULL) { diff --git a/kernel/kprobes.c b/kernel/kprobes.c index e9db0c810554..21eccc961bba 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -2086,6 +2086,9 @@ int register_kretprobe(struct kretprobe *rp) } } + if (rp->data_size > KRETPROBE_MAX_DATA_SIZE) + return -E2BIG; + rp->kp.pre_handler = pre_handler_kretprobe; rp->kp.post_handler = NULL; diff --git a/kernel/kthread.c b/kernel/kthread.c index 4a4d7092a2d8..7113003fab63 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -433,7 +433,7 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data), * If thread is going to be bound on a particular cpu, give its node * in @node, to get NUMA affinity for kthread stack, or else give NUMA_NO_NODE. * When woken, the thread will run @threadfn() with @data as its - * argument. @threadfn() can either call do_exit() directly if it is a + * argument. @threadfn() can either return directly if it is a * standalone thread for which no one will call kthread_stop(), or * return when 'kthread_should_stop()' is true (which means * kthread_stop() has been called). The return value should be zero diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 7096384dc60f..2270ec68f10a 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -788,6 +788,21 @@ static int very_verbose(struct lock_class *class) * Is this the address of a static object: */ #ifdef __KERNEL__ +/* + * Check if an address is part of freed initmem. After initmem is freed, + * memory can be allocated from it, and such allocations would then have + * addresses within the range [_stext, _end]. + */ +#ifndef arch_is_kernel_initmem_freed +static int arch_is_kernel_initmem_freed(unsigned long addr) +{ + if (system_state < SYSTEM_FREEING_INITMEM) + return 0; + + return init_section_contains((void *)addr, 1); +} +#endif + static int static_obj(const void *obj) { unsigned long start = (unsigned long) &_stext, @@ -803,9 +818,6 @@ static int static_obj(const void *obj) if ((addr >= start) && (addr < end)) return 1; - if (arch_is_kernel_data(addr)) - return 1; - /* * in-kernel percpu var? */ diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 0c6a48dfcecb..1f25a4d7de27 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1380,7 +1380,7 @@ static bool rtmutex_spin_on_owner(struct rt_mutex_base *lock, * - the VCPU on which owner runs is preempted */ if (!owner->on_cpu || need_resched() || - rt_mutex_waiter_is_top_waiter(lock, waiter) || + !rt_mutex_waiter_is_top_waiter(lock, waiter) || vcpu_is_preempted(task_cpu(owner))) { res = false; break; diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index c51387a43265..04a74d040a6d 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -105,9 +105,9 @@ * atomic_long_cmpxchg() will be used to obtain writer lock. * * There are three places where the lock handoff bit may be set or cleared. - * 1) rwsem_mark_wake() for readers. - * 2) rwsem_try_write_lock() for writers. - * 3) Error path of rwsem_down_write_slowpath(). + * 1) rwsem_mark_wake() for readers -- set, clear + * 2) rwsem_try_write_lock() for writers -- set, clear + * 3) rwsem_del_waiter() -- clear * * For all the above cases, wait_lock will be held. A writer must also * be the first one in the wait_list to be eligible for setting the handoff @@ -334,6 +334,9 @@ struct rwsem_waiter { struct task_struct *task; enum rwsem_waiter_type type; unsigned long timeout; + + /* Writer only, not initialized in reader */ + bool handoff_set; }; #define rwsem_first_waiter(sem) \ list_first_entry(&sem->wait_list, struct rwsem_waiter, list) @@ -344,12 +347,6 @@ enum rwsem_wake_type { RWSEM_WAKE_READ_OWNED /* Waker thread holds the read lock */ }; -enum writer_wait_state { - WRITER_NOT_FIRST, /* Writer is not first in wait list */ - WRITER_FIRST, /* Writer is first in wait list */ - WRITER_HANDOFF /* Writer is first & handoff needed */ -}; - /* * The typical HZ value is either 250 or 1000. So set the minimum waiting * time to at least 4ms or 1 jiffy (if it is higher than 4ms) in the wait @@ -365,6 +362,31 @@ enum writer_wait_state { */ #define MAX_READERS_WAKEUP 0x100 +static inline void +rwsem_add_waiter(struct rw_semaphore *sem, struct rwsem_waiter *waiter) +{ + lockdep_assert_held(&sem->wait_lock); + list_add_tail(&waiter->list, &sem->wait_list); + /* caller will set RWSEM_FLAG_WAITERS */ +} + +/* + * Remove a waiter from the wait_list and clear flags. + * + * Both rwsem_mark_wake() and rwsem_try_write_lock() contain a full 'copy' of + * this function. Modify with care. + */ +static inline void +rwsem_del_waiter(struct rw_semaphore *sem, struct rwsem_waiter *waiter) +{ + lockdep_assert_held(&sem->wait_lock); + list_del(&waiter->list); + if (likely(!list_empty(&sem->wait_list))) + return; + + atomic_long_andnot(RWSEM_FLAG_HANDOFF | RWSEM_FLAG_WAITERS, &sem->count); +} + /* * handle the lock release when processes blocked on it that can now run * - if we come here from up_xxxx(), then the RWSEM_FLAG_WAITERS bit must @@ -376,6 +398,8 @@ enum writer_wait_state { * preferably when the wait_lock is released * - woken process blocks are discarded from the list after having task zeroed * - writers are only marked woken if downgrading is false + * + * Implies rwsem_del_waiter() for all woken readers. */ static void rwsem_mark_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type, @@ -490,18 +514,25 @@ static void rwsem_mark_wake(struct rw_semaphore *sem, adjustment = woken * RWSEM_READER_BIAS - adjustment; lockevent_cond_inc(rwsem_wake_reader, woken); + + oldcount = atomic_long_read(&sem->count); if (list_empty(&sem->wait_list)) { - /* hit end of list above */ + /* + * Combined with list_move_tail() above, this implies + * rwsem_del_waiter(). + */ adjustment -= RWSEM_FLAG_WAITERS; + if (oldcount & RWSEM_FLAG_HANDOFF) + adjustment -= RWSEM_FLAG_HANDOFF; + } else if (woken) { + /* + * When we've woken a reader, we no longer need to force + * writers to give up the lock and we can clear HANDOFF. + */ + if (oldcount & RWSEM_FLAG_HANDOFF) + adjustment -= RWSEM_FLAG_HANDOFF; } - /* - * When we've woken a reader, we no longer need to force writers - * to give up the lock and we can clear HANDOFF. - */ - if (woken && (atomic_long_read(&sem->count) & RWSEM_FLAG_HANDOFF)) - adjustment -= RWSEM_FLAG_HANDOFF; - if (adjustment) atomic_long_add(adjustment, &sem->count); @@ -532,12 +563,12 @@ static void rwsem_mark_wake(struct rw_semaphore *sem, * race conditions between checking the rwsem wait list and setting the * sem->count accordingly. * - * If wstate is WRITER_HANDOFF, it will make sure that either the handoff - * bit is set or the lock is acquired with handoff bit cleared. + * Implies rwsem_del_waiter() on success. */ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem, - enum writer_wait_state wstate) + struct rwsem_waiter *waiter) { + bool first = rwsem_first_waiter(sem) == waiter; long count, new; lockdep_assert_held(&sem->wait_lock); @@ -546,13 +577,19 @@ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem, do { bool has_handoff = !!(count & RWSEM_FLAG_HANDOFF); - if (has_handoff && wstate == WRITER_NOT_FIRST) - return false; + if (has_handoff) { + if (!first) + return false; + + /* First waiter inherits a previously set handoff bit */ + waiter->handoff_set = true; + } new = count; if (count & RWSEM_LOCK_MASK) { - if (has_handoff || (wstate != WRITER_HANDOFF)) + if (has_handoff || (!rt_task(waiter->task) && + !time_after(jiffies, waiter->timeout))) return false; new |= RWSEM_FLAG_HANDOFF; @@ -569,9 +606,17 @@ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem, * We have either acquired the lock with handoff bit cleared or * set the handoff bit. */ - if (new & RWSEM_FLAG_HANDOFF) + if (new & RWSEM_FLAG_HANDOFF) { + waiter->handoff_set = true; + lockevent_inc(rwsem_wlock_handoff); return false; + } + /* + * Have rwsem_try_write_lock() fully imply rwsem_del_waiter() on + * success. + */ + list_del(&waiter->list); rwsem_set_owner(sem); return true; } @@ -956,7 +1001,7 @@ queue: } adjustment += RWSEM_FLAG_WAITERS; } - list_add_tail(&waiter.list, &sem->wait_list); + rwsem_add_waiter(sem, &waiter); /* we're now waiting on the lock, but no longer actively locking */ count = atomic_long_add_return(adjustment, &sem->count); @@ -1002,11 +1047,7 @@ queue: return sem; out_nolock: - list_del(&waiter.list); - if (list_empty(&sem->wait_list)) { - atomic_long_andnot(RWSEM_FLAG_WAITERS|RWSEM_FLAG_HANDOFF, - &sem->count); - } + rwsem_del_waiter(sem, &waiter); raw_spin_unlock_irq(&sem->wait_lock); __set_current_state(TASK_RUNNING); lockevent_inc(rwsem_rlock_fail); @@ -1020,9 +1061,7 @@ static struct rw_semaphore * rwsem_down_write_slowpath(struct rw_semaphore *sem, int state) { long count; - enum writer_wait_state wstate; struct rwsem_waiter waiter; - struct rw_semaphore *ret = sem; DEFINE_WAKE_Q(wake_q); /* do optimistic spinning and steal lock if possible */ @@ -1038,16 +1077,13 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state) waiter.task = current; waiter.type = RWSEM_WAITING_FOR_WRITE; waiter.timeout = jiffies + RWSEM_WAIT_TIMEOUT; + waiter.handoff_set = false; raw_spin_lock_irq(&sem->wait_lock); - - /* account for this before adding a new element to the list */ - wstate = list_empty(&sem->wait_list) ? WRITER_FIRST : WRITER_NOT_FIRST; - - list_add_tail(&waiter.list, &sem->wait_list); + rwsem_add_waiter(sem, &waiter); /* we're now waiting on the lock */ - if (wstate == WRITER_NOT_FIRST) { + if (rwsem_first_waiter(sem) != &waiter) { count = atomic_long_read(&sem->count); /* @@ -1083,13 +1119,16 @@ wait: /* wait until we successfully acquire the lock */ set_current_state(state); for (;;) { - if (rwsem_try_write_lock(sem, wstate)) { + if (rwsem_try_write_lock(sem, &waiter)) { /* rwsem_try_write_lock() implies ACQUIRE on success */ break; } raw_spin_unlock_irq(&sem->wait_lock); + if (signal_pending_state(state, current)) + goto out_nolock; + /* * After setting the handoff bit and failing to acquire * the lock, attempt to spin on owner to accelerate lock @@ -1098,7 +1137,7 @@ wait: * In this case, we attempt to acquire the lock again * without sleeping. */ - if (wstate == WRITER_HANDOFF) { + if (waiter.handoff_set) { enum owner_state owner_state; preempt_disable(); @@ -1109,66 +1148,26 @@ wait: goto trylock_again; } - /* Block until there are no active lockers. */ - for (;;) { - if (signal_pending_state(state, current)) - goto out_nolock; - - schedule(); - lockevent_inc(rwsem_sleep_writer); - set_current_state(state); - /* - * If HANDOFF bit is set, unconditionally do - * a trylock. - */ - if (wstate == WRITER_HANDOFF) - break; - - if ((wstate == WRITER_NOT_FIRST) && - (rwsem_first_waiter(sem) == &waiter)) - wstate = WRITER_FIRST; - - count = atomic_long_read(&sem->count); - if (!(count & RWSEM_LOCK_MASK)) - break; - - /* - * The setting of the handoff bit is deferred - * until rwsem_try_write_lock() is called. - */ - if ((wstate == WRITER_FIRST) && (rt_task(current) || - time_after(jiffies, waiter.timeout))) { - wstate = WRITER_HANDOFF; - lockevent_inc(rwsem_wlock_handoff); - break; - } - } + schedule(); + lockevent_inc(rwsem_sleep_writer); + set_current_state(state); trylock_again: raw_spin_lock_irq(&sem->wait_lock); } __set_current_state(TASK_RUNNING); - list_del(&waiter.list); raw_spin_unlock_irq(&sem->wait_lock); lockevent_inc(rwsem_wlock); - - return ret; + return sem; out_nolock: __set_current_state(TASK_RUNNING); raw_spin_lock_irq(&sem->wait_lock); - list_del(&waiter.list); - - if (unlikely(wstate == WRITER_HANDOFF)) - atomic_long_add(-RWSEM_FLAG_HANDOFF, &sem->count); - - if (list_empty(&sem->wait_list)) - atomic_long_andnot(RWSEM_FLAG_WAITERS, &sem->count); - else + rwsem_del_waiter(sem, &waiter); + if (!list_empty(&sem->wait_list)) rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q); raw_spin_unlock_irq(&sem->wait_lock); wake_up_q(&wake_q); lockevent_inc(rwsem_wlock_fail); - return ERR_PTR(-EINTR); } @@ -1249,17 +1248,14 @@ static inline int __down_read_trylock(struct rw_semaphore *sem) DEBUG_RWSEMS_WARN_ON(sem->magic != sem, sem); - /* - * Optimize for the case when the rwsem is not locked at all. - */ - tmp = RWSEM_UNLOCKED_VALUE; - do { + tmp = atomic_long_read(&sem->count); + while (!(tmp & RWSEM_READ_FAILED_MASK)) { if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp, - tmp + RWSEM_READER_BIAS)) { + tmp + RWSEM_READER_BIAS)) { rwsem_set_reader_owned(sem); return 1; } - } while (!(tmp & RWSEM_READ_FAILED_MASK)); + } return 0; } diff --git a/kernel/module.c b/kernel/module.c index 5c26a76e800b..84a9141a5e15 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2942,7 +2942,11 @@ static int module_sig_check(struct load_info *info, int flags) static int validate_section_offset(struct load_info *info, Elf_Shdr *shdr) { +#if defined(CONFIG_64BIT) + unsigned long long secend; +#else unsigned long secend; +#endif /* * Check for both overflow and offset/size being @@ -2967,14 +2971,29 @@ static int elf_validity_check(struct load_info *info) Elf_Shdr *shdr, *strhdr; int err; - if (info->len < sizeof(*(info->hdr))) - return -ENOEXEC; + if (info->len < sizeof(*(info->hdr))) { + pr_err("Invalid ELF header len %lu\n", info->len); + goto no_exec; + } - if (memcmp(info->hdr->e_ident, ELFMAG, SELFMAG) != 0 - || info->hdr->e_type != ET_REL - || !elf_check_arch(info->hdr) - || info->hdr->e_shentsize != sizeof(Elf_Shdr)) - return -ENOEXEC; + if (memcmp(info->hdr->e_ident, ELFMAG, SELFMAG) != 0) { + pr_err("Invalid ELF header magic: != %s\n", ELFMAG); + goto no_exec; + } + if (info->hdr->e_type != ET_REL) { + pr_err("Invalid ELF header type: %u != %u\n", + info->hdr->e_type, ET_REL); + goto no_exec; + } + if (!elf_check_arch(info->hdr)) { + pr_err("Invalid architecture in ELF header: %u\n", + info->hdr->e_machine); + goto no_exec; + } + if (info->hdr->e_shentsize != sizeof(Elf_Shdr)) { + pr_err("Invalid ELF section header size\n"); + goto no_exec; + } /* * e_shnum is 16 bits, and sizeof(Elf_Shdr) is @@ -2983,8 +3002,10 @@ static int elf_validity_check(struct load_info *info) */ if (info->hdr->e_shoff >= info->len || (info->hdr->e_shnum * sizeof(Elf_Shdr) > - info->len - info->hdr->e_shoff)) - return -ENOEXEC; + info->len - info->hdr->e_shoff)) { + pr_err("Invalid ELF section header overflow\n"); + goto no_exec; + } info->sechdrs = (void *)info->hdr + info->hdr->e_shoff; @@ -2992,13 +3013,19 @@ static int elf_validity_check(struct load_info *info) * Verify if the section name table index is valid. */ if (info->hdr->e_shstrndx == SHN_UNDEF - || info->hdr->e_shstrndx >= info->hdr->e_shnum) - return -ENOEXEC; + || info->hdr->e_shstrndx >= info->hdr->e_shnum) { + pr_err("Invalid ELF section name index: %d || e_shstrndx (%d) >= e_shnum (%d)\n", + info->hdr->e_shstrndx, info->hdr->e_shstrndx, + info->hdr->e_shnum); + goto no_exec; + } strhdr = &info->sechdrs[info->hdr->e_shstrndx]; err = validate_section_offset(info, strhdr); - if (err < 0) + if (err < 0) { + pr_err("Invalid ELF section hdr(type %u)\n", strhdr->sh_type); return err; + } /* * The section name table must be NUL-terminated, as required @@ -3006,8 +3033,10 @@ static int elf_validity_check(struct load_info *info) * strings in the section safe. */ info->secstrings = (void *)info->hdr + strhdr->sh_offset; - if (info->secstrings[strhdr->sh_size - 1] != '\0') - return -ENOEXEC; + if (info->secstrings[strhdr->sh_size - 1] != '\0') { + pr_err("ELF Spec violation: section name table isn't null terminated\n"); + goto no_exec; + } /* * The code assumes that section 0 has a length of zero and @@ -3015,8 +3044,11 @@ static int elf_validity_check(struct load_info *info) */ if (info->sechdrs[0].sh_type != SHT_NULL || info->sechdrs[0].sh_size != 0 - || info->sechdrs[0].sh_addr != 0) - return -ENOEXEC; + || info->sechdrs[0].sh_addr != 0) { + pr_err("ELF Spec violation: section 0 type(%d)!=SH_NULL or non-zero len or addr\n", + info->sechdrs[0].sh_type); + goto no_exec; + } for (i = 1; i < info->hdr->e_shnum; i++) { shdr = &info->sechdrs[i]; @@ -3026,8 +3058,12 @@ static int elf_validity_check(struct load_info *info) continue; case SHT_SYMTAB: if (shdr->sh_link == SHN_UNDEF - || shdr->sh_link >= info->hdr->e_shnum) - return -ENOEXEC; + || shdr->sh_link >= info->hdr->e_shnum) { + pr_err("Invalid ELF sh_link!=SHN_UNDEF(%d) or (sh_link(%d) >= hdr->e_shnum(%d)\n", + shdr->sh_link, shdr->sh_link, + info->hdr->e_shnum); + goto no_exec; + } fallthrough; default: err = validate_section_offset(info, shdr); @@ -3049,6 +3085,9 @@ static int elf_validity_check(struct load_info *info) } return 0; + +no_exec: + return -ENOEXEC; } #define COPY_CHUNK_SIZE (16*PAGE_SIZE) @@ -3940,10 +3979,8 @@ static int load_module(struct load_info *info, const char __user *uargs, * sections. */ err = elf_validity_check(info); - if (err) { - pr_err("Module has invalid ELF structures\n"); + if (err) goto free_copy; - } /* * Everything checks out, so set up the section info diff --git a/kernel/pid.c b/kernel/pid.c index efe87db44683..2fc0a16ec77b 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -540,6 +540,42 @@ struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags) } /** + * pidfd_get_task() - Get the task associated with a pidfd + * + * @pidfd: pidfd for which to get the task + * @flags: flags associated with this pidfd + * + * Return the task associated with @pidfd. The function takes a reference on + * the returned task. The caller is responsible for releasing that reference. + * + * Currently, the process identified by @pidfd is always a thread-group leader. + * This restriction currently exists for all aspects of pidfds including pidfd + * creation (CLONE_PIDFD cannot be used with CLONE_THREAD) and pidfd polling + * (only supports thread group leaders). + * + * Return: On success, the task_struct associated with the pidfd. + * On error, a negative errno number will be returned. + */ +struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags) +{ + unsigned int f_flags; + struct pid *pid; + struct task_struct *task; + + pid = pidfd_get_pid(pidfd, &f_flags); + if (IS_ERR(pid)) + return ERR_CAST(pid); + + task = get_pid_task(pid, PIDTYPE_TGID); + put_pid(pid); + if (!task) + return ERR_PTR(-ESRCH); + + *flags = f_flags; + return task; +} + +/** * pidfd_create() - Create a new pid file descriptor. * * @pid: struct pid that the pidfd will reference diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 9ed9b744876c..e6af502c2fd7 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -693,7 +693,7 @@ static int load_image_and_restore(void) goto Unlock; error = swsusp_read(&flags); - swsusp_close(FMODE_READ); + swsusp_close(FMODE_READ | FMODE_EXCL); if (!error) error = hibernation_restore(flags & SF_PLATFORM_MODE); @@ -983,7 +983,7 @@ static int software_resume(void) /* The snapshot device should not be opened while we're running */ if (!hibernate_acquire()) { error = -EBUSY; - swsusp_close(FMODE_READ); + swsusp_close(FMODE_READ | FMODE_EXCL); goto Unlock; } @@ -1018,7 +1018,7 @@ static int software_resume(void) pm_pr_dbg("Hibernation image not present or could not be loaded.\n"); return error; Close_Finish: - swsusp_close(FMODE_READ); + swsusp_close(FMODE_READ | FMODE_EXCL); goto Finish; } diff --git a/kernel/power/user.c b/kernel/power/user.c index 740723bb3885..ad241b4ff64c 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -177,7 +177,7 @@ static ssize_t snapshot_write(struct file *filp, const char __user *buf, if (res <= 0) goto unlock; } else { - res = PAGE_SIZE - pg_offp; + res = PAGE_SIZE; } if (!data_of(data->handle)) { diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 9e5dfb1896a9..57b132b658e1 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1166,9 +1166,9 @@ void __init setup_log_buf(int early) return; err_free_descs: - memblock_free_ptr(new_descs, new_descs_size); + memblock_free(new_descs, new_descs_size); err_free_log_buf: - memblock_free_ptr(new_log_buf, new_log_buf_len); + memblock_free(new_log_buf, new_log_buf_len); } static bool __read_mostly ignore_loglevel; @@ -3253,6 +3253,11 @@ void defer_console_output(void) preempt_enable(); } +void printk_trigger_flush(void) +{ + defer_console_output(); +} + int vprintk_deferred(const char *fmt, va_list args) { int r; diff --git a/kernel/reboot.c b/kernel/reboot.c index f7440c0c7e43..6bcc5d6a6572 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -33,6 +33,7 @@ EXPORT_SYMBOL(cad_pid); #define DEFAULT_REBOOT_MODE #endif enum reboot_mode reboot_mode DEFAULT_REBOOT_MODE; +EXPORT_SYMBOL_GPL(reboot_mode); enum reboot_mode panic_reboot_mode = REBOOT_UNDEFINED; /* @@ -359,7 +360,6 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd, case LINUX_REBOOT_CMD_HALT: kernel_halt(); do_exit(0); - panic("cannot halt"); case LINUX_REBOOT_CMD_POWER_OFF: kernel_power_off(); diff --git a/kernel/resource.c b/kernel/resource.c index ca9f5198a01f..5ad3eba619ba 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -73,6 +73,18 @@ static struct resource *next_resource(struct resource *p) return p->sibling; } +static struct resource *next_resource_skip_children(struct resource *p) +{ + while (!p->sibling && p->parent) + p = p->parent; + return p->sibling; +} + +#define for_each_resource(_root, _p, _skip_children) \ + for ((_p) = (_root)->child; (_p); \ + (_p) = (_skip_children) ? next_resource_skip_children(_p) : \ + next_resource(_p)) + static void *r_next(struct seq_file *m, void *v, loff_t *pos) { struct resource *p = v; @@ -1707,37 +1719,49 @@ static int strict_iomem_checks; #endif /* - * check if an address is reserved in the iomem resource tree - * returns true if reserved, false if not reserved. + * Check if an address is exclusive to the kernel and must not be mapped to + * user space, for example, via /dev/mem. + * + * Returns true if exclusive to the kernel, otherwise returns false. */ bool iomem_is_exclusive(u64 addr) { - struct resource *p = &iomem_resource; - bool err = false; - loff_t l; + const unsigned int exclusive_system_ram = IORESOURCE_SYSTEM_RAM | + IORESOURCE_EXCLUSIVE; + bool skip_children = false, err = false; int size = PAGE_SIZE; - - if (!strict_iomem_checks) - return false; + struct resource *p; addr = addr & PAGE_MASK; read_lock(&resource_lock); - for (p = p->child; p ; p = r_next(NULL, p, &l)) { - /* - * We can probably skip the resources without - * IORESOURCE_IO attribute? - */ + for_each_resource(&iomem_resource, p, skip_children) { if (p->start >= addr + size) break; - if (p->end < addr) + if (p->end < addr) { + skip_children = true; continue; + } + skip_children = false; + + /* + * IORESOURCE_SYSTEM_RAM resources are exclusive if + * IORESOURCE_EXCLUSIVE is set, even if they + * are not busy and even if "iomem=relaxed" is set. The + * responsible driver dynamically adds/removes system RAM within + * such an area and uncontrolled access is dangerous. + */ + if ((p->flags & exclusive_system_ram) == exclusive_system_ram) { + err = true; + break; + } + /* * A resource is exclusive if IORESOURCE_EXCLUSIVE is set * or CONFIG_IO_STRICT_DEVMEM is enabled and the * resource is busy. */ - if ((p->flags & IORESOURCE_BUSY) == 0) + if (!strict_iomem_checks || !(p->flags & IORESOURCE_BUSY)) continue; if (IS_ENABLED(CONFIG_IO_STRICT_DEVMEM) || p->flags & IORESOURCE_EXCLUSIVE) { diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c index 2067080bb235..8629b37d118e 100644 --- a/kernel/sched/autogroup.c +++ b/kernel/sched/autogroup.c @@ -31,7 +31,7 @@ static inline void autogroup_destroy(struct kref *kref) ag->tg->rt_se = NULL; ag->tg->rt_rq = NULL; #endif - sched_offline_group(ag->tg); + sched_release_group(ag->tg); sched_destroy_group(ag->tg); } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 523fd602ea90..77563109c0ea 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1918,7 +1918,7 @@ static void __init init_uclamp_rq(struct rq *rq) }; } - rq->uclamp_flags = 0; + rq->uclamp_flags = UCLAMP_FLAG_IDLE; } static void __init init_uclamp(void) @@ -3726,6 +3726,9 @@ out: bool cpus_share_cache(int this_cpu, int that_cpu) { + if (this_cpu == that_cpu) + return true; + return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu); } @@ -6614,24 +6617,24 @@ static int __init setup_preempt_mode(char *str) int mode = sched_dynamic_mode(str); if (mode < 0) { pr_warn("Dynamic Preempt: unsupported mode: %s\n", str); - return 1; + return 0; } sched_dynamic_update(mode); - return 0; + return 1; } __setup("preempt=", setup_preempt_mode); static void __init preempt_dynamic_init(void) { if (preempt_dynamic_mode == preempt_dynamic_undefined) { - if (IS_ENABLED(CONFIG_PREEMPT_NONE_BEHAVIOUR)) { + if (IS_ENABLED(CONFIG_PREEMPT_NONE)) { sched_dynamic_update(preempt_dynamic_none); - } else if (IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY_BEHAVIOUR)) { + } else if (IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY)) { sched_dynamic_update(preempt_dynamic_voluntary); } else { /* Default static call setting, nothing to do */ - WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT_BEHAVIOUR)); + WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT)); preempt_dynamic_mode = preempt_dynamic_full; pr_info("Dynamic Preempt: full\n"); } @@ -8616,9 +8619,6 @@ void __init init_idle(struct task_struct *idle, int cpu) idle->flags |= PF_IDLE | PF_KTHREAD | PF_NO_SETAFFINITY; kthread_set_per_cpu(idle, cpu); - scs_task_reset(idle); - kasan_unpoison_task_stack(idle); - #ifdef CONFIG_SMP /* * It's possible that init_idle() gets called multiple times on a task, @@ -8774,7 +8774,6 @@ void idle_task_exit(void) finish_arch_post_lock_switch(); } - scs_task_reset(current); /* finish_cpu(), as ran on the BP, will clean up the active_mm state */ } @@ -9716,6 +9715,22 @@ static void sched_free_group(struct task_group *tg) kmem_cache_free(task_group_cache, tg); } +static void sched_free_group_rcu(struct rcu_head *rcu) +{ + sched_free_group(container_of(rcu, struct task_group, rcu)); +} + +static void sched_unregister_group(struct task_group *tg) +{ + unregister_fair_sched_group(tg); + unregister_rt_sched_group(tg); + /* + * We have to wait for yet another RCU grace period to expire, as + * print_cfs_stats() might run concurrently. + */ + call_rcu(&tg->rcu, sched_free_group_rcu); +} + /* allocate runqueue etc for a new task group */ struct task_group *sched_create_group(struct task_group *parent) { @@ -9759,25 +9774,35 @@ void sched_online_group(struct task_group *tg, struct task_group *parent) } /* rcu callback to free various structures associated with a task group */ -static void sched_free_group_rcu(struct rcu_head *rhp) +static void sched_unregister_group_rcu(struct rcu_head *rhp) { /* Now it should be safe to free those cfs_rqs: */ - sched_free_group(container_of(rhp, struct task_group, rcu)); + sched_unregister_group(container_of(rhp, struct task_group, rcu)); } void sched_destroy_group(struct task_group *tg) { /* Wait for possible concurrent references to cfs_rqs complete: */ - call_rcu(&tg->rcu, sched_free_group_rcu); + call_rcu(&tg->rcu, sched_unregister_group_rcu); } -void sched_offline_group(struct task_group *tg) +void sched_release_group(struct task_group *tg) { unsigned long flags; - /* End participation in shares distribution: */ - unregister_fair_sched_group(tg); - + /* + * Unlink first, to avoid walk_tg_tree_from() from finding us (via + * sched_cfs_period_timer()). + * + * For this to be effective, we have to wait for all pending users of + * this task group to leave their RCU critical section to ensure no new + * user will see our dying task group any more. Specifically ensure + * that tg_unthrottle_up() won't add decayed cfs_rq's to it. + * + * We therefore defer calling unregister_fair_sched_group() to + * sched_unregister_group() which is guarantied to get called only after the + * current RCU grace period has expired. + */ spin_lock_irqsave(&task_group_lock, flags); list_del_rcu(&tg->list); list_del_rcu(&tg->siblings); @@ -9896,7 +9921,7 @@ static void cpu_cgroup_css_released(struct cgroup_subsys_state *css) { struct task_group *tg = css_tg(css); - sched_offline_group(tg); + sched_release_group(tg); } static void cpu_cgroup_css_free(struct cgroup_subsys_state *css) @@ -9906,7 +9931,7 @@ static void cpu_cgroup_css_free(struct cgroup_subsys_state *css) /* * Relies on the RCU grace period between css_released() and this. */ - sched_free_group(tg); + sched_unregister_group(tg); } /* diff --git a/kernel/sched/core_sched.c b/kernel/sched/core_sched.c index 48ac72696012..517f72b008f5 100644 --- a/kernel/sched/core_sched.c +++ b/kernel/sched/core_sched.c @@ -135,6 +135,10 @@ int sched_core_share_pid(unsigned int cmd, pid_t pid, enum pid_type type, if (!static_branch_likely(&sched_smt_present)) return -ENODEV; + BUILD_BUG_ON(PR_SCHED_CORE_SCOPE_THREAD != PIDTYPE_PID); + BUILD_BUG_ON(PR_SCHED_CORE_SCOPE_THREAD_GROUP != PIDTYPE_TGID); + BUILD_BUG_ON(PR_SCHED_CORE_SCOPE_PROCESS_GROUP != PIDTYPE_PGID); + if (type > PIDTYPE_PGID || cmd >= PR_SCHED_CORE_MAX || pid < 0 || (cmd != PR_SCHED_CORE_GET && uaddr)) return -EINVAL; diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 872e481d5098..9392aea1804e 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -615,7 +615,8 @@ void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st) .sum_exec_runtime = p->se.sum_exec_runtime, }; - task_cputime(p, &cputime.utime, &cputime.stime); + if (task_cputime(p, &cputime.utime, &cputime.stime)) + cputime.sum_exec_runtime = task_sched_runtime(p); cputime_adjust(&cputime, &p->prev_cputime, ut, st); } EXPORT_SYMBOL_GPL(task_cputime_adjusted); @@ -828,19 +829,21 @@ u64 task_gtime(struct task_struct *t) * add up the pending nohz execution time since the last * cputime snapshot. */ -void task_cputime(struct task_struct *t, u64 *utime, u64 *stime) +bool task_cputime(struct task_struct *t, u64 *utime, u64 *stime) { struct vtime *vtime = &t->vtime; unsigned int seq; u64 delta; + int ret; if (!vtime_accounting_enabled()) { *utime = t->utime; *stime = t->stime; - return; + return false; } do { + ret = false; seq = read_seqcount_begin(&vtime->seqcount); *utime = t->utime; @@ -850,6 +853,7 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime) if (vtime->state < VTIME_SYS) continue; + ret = true; delta = vtime_delta(vtime); /* @@ -861,6 +865,8 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime) else *utime += vtime->utime + delta; } while (read_seqcount_retry(&vtime->seqcount, seq)); + + return ret; } static int vtime_state_fetch(struct vtime *vtime, int cpu) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 13950beb01a2..6e476f6d9435 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -11456,8 +11456,6 @@ void free_fair_sched_group(struct task_group *tg) { int i; - destroy_cfs_bandwidth(tg_cfs_bandwidth(tg)); - for_each_possible_cpu(i) { if (tg->cfs_rq) kfree(tg->cfs_rq[i]); @@ -11534,6 +11532,8 @@ void unregister_fair_sched_group(struct task_group *tg) struct rq *rq; int cpu; + destroy_cfs_bandwidth(tg_cfs_bandwidth(tg)); + for_each_possible_cpu(cpu) { if (tg->se[cpu]) remove_entity_load_avg(tg->se[cpu]); diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index bb945f8faeca..b48baaba2fc2 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -137,13 +137,17 @@ static inline struct rq *rq_of_rt_se(struct sched_rt_entity *rt_se) return rt_rq->rq; } -void free_rt_sched_group(struct task_group *tg) +void unregister_rt_sched_group(struct task_group *tg) { - int i; - if (tg->rt_se) destroy_rt_bandwidth(&tg->rt_bandwidth); +} + +void free_rt_sched_group(struct task_group *tg) +{ + int i; + for_each_possible_cpu(i) { if (tg->rt_rq) kfree(tg->rt_rq[i]); @@ -250,6 +254,8 @@ static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se) return &rq->rt; } +void unregister_rt_sched_group(struct task_group *tg) { } + void free_rt_sched_group(struct task_group *tg) { } int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 7f1612d26c18..0e66749486e7 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -488,6 +488,7 @@ extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b); extern void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b); extern void unthrottle_cfs_rq(struct cfs_rq *cfs_rq); +extern void unregister_rt_sched_group(struct task_group *tg); extern void free_rt_sched_group(struct task_group *tg); extern int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent); extern void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq, @@ -503,7 +504,7 @@ extern struct task_group *sched_create_group(struct task_group *parent); extern void sched_online_group(struct task_group *tg, struct task_group *parent); extern void sched_destroy_group(struct task_group *tg); -extern void sched_offline_group(struct task_group *tg); +extern void sched_release_group(struct task_group *tg); extern void sched_move_task(struct task_struct *tsk); diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 30169c7685b6..d201a7052a29 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1492,7 +1492,6 @@ static int sched_domains_curr_level; int sched_max_numa_distance; static int *sched_domains_numa_distance; static struct cpumask ***sched_domains_numa_masks; -int __read_mostly node_reclaim_distance = RECLAIM_DISTANCE; static unsigned long __read_mostly *sched_numa_onlined_nodes; #endif diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 76577d1642a5..eca38107b32f 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -238,6 +238,13 @@ void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode) } EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */ +void __wake_up_pollfree(struct wait_queue_head *wq_head) +{ + __wake_up(wq_head, TASK_NORMAL, 0, poll_to_key(EPOLLHUP | POLLFREE)); + /* POLLFREE must have cleared the queue. */ + WARN_ON_ONCE(waitqueue_active(wq_head)); +} + /* * Note: we use "set_current_state()" _after_ the wait-queue add, * because we need a memory barrier there on SMP, so that any diff --git a/kernel/signal.c b/kernel/signal.c index 6f3476dc7873..dfcee3888b00 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1298,6 +1298,12 @@ int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p return ret; } +enum sig_handler { + HANDLER_CURRENT, /* If reachable use the current handler */ + HANDLER_SIG_DFL, /* Always use SIG_DFL handler semantics */ + HANDLER_EXIT, /* Only visible as the process exit code */ +}; + /* * Force a signal that the process can't ignore: if necessary * we unblock the signal and change any SIG_IGN to SIG_DFL. @@ -1310,7 +1316,8 @@ int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p * that is why we also clear SIGNAL_UNKILLABLE. */ static int -force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t, bool sigdfl) +force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t, + enum sig_handler handler) { unsigned long int flags; int ret, blocked, ignored; @@ -1321,8 +1328,10 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t, bool action = &t->sighand->action[sig-1]; ignored = action->sa.sa_handler == SIG_IGN; blocked = sigismember(&t->blocked, sig); - if (blocked || ignored || sigdfl) { + if (blocked || ignored || (handler != HANDLER_CURRENT)) { action->sa.sa_handler = SIG_DFL; + if (handler == HANDLER_EXIT) + action->sa.sa_flags |= SA_IMMUTABLE; if (blocked) { sigdelset(&t->blocked, sig); recalc_sigpending_and_wake(t); @@ -1342,7 +1351,7 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t, bool int force_sig_info(struct kernel_siginfo *info) { - return force_sig_info_to_task(info, current, false); + return force_sig_info_to_task(info, current, HANDLER_CURRENT); } /* @@ -1649,6 +1658,32 @@ void force_sig(int sig) } EXPORT_SYMBOL(force_sig); +void force_fatal_sig(int sig) +{ + struct kernel_siginfo info; + + clear_siginfo(&info); + info.si_signo = sig; + info.si_errno = 0; + info.si_code = SI_KERNEL; + info.si_pid = 0; + info.si_uid = 0; + force_sig_info_to_task(&info, current, HANDLER_SIG_DFL); +} + +void force_exit_sig(int sig) +{ + struct kernel_siginfo info; + + clear_siginfo(&info); + info.si_signo = sig; + info.si_errno = 0; + info.si_code = SI_KERNEL; + info.si_pid = 0; + info.si_uid = 0; + force_sig_info_to_task(&info, current, HANDLER_EXIT); +} + /* * When things go south during signal handling, we * will force a SIGSEGV. And if the signal that caused @@ -1657,15 +1692,10 @@ EXPORT_SYMBOL(force_sig); */ void force_sigsegv(int sig) { - struct task_struct *p = current; - - if (sig == SIGSEGV) { - unsigned long flags; - spin_lock_irqsave(&p->sighand->siglock, flags); - p->sighand->action[sig - 1].sa.sa_handler = SIG_DFL; - spin_unlock_irqrestore(&p->sighand->siglock, flags); - } - force_sig(SIGSEGV); + if (sig == SIGSEGV) + force_fatal_sig(SIGSEGV); + else + force_sig(SIGSEGV); } int force_sig_fault_to_task(int sig, int code, void __user *addr @@ -1684,7 +1714,7 @@ int force_sig_fault_to_task(int sig, int code, void __user *addr info.si_flags = flags; info.si_isr = isr; #endif - return force_sig_info_to_task(&info, t, false); + return force_sig_info_to_task(&info, t, HANDLER_CURRENT); } int force_sig_fault(int sig, int code, void __user *addr @@ -1804,7 +1834,8 @@ int force_sig_seccomp(int syscall, int reason, bool force_coredump) info.si_errno = reason; info.si_arch = syscall_get_arch(current); info.si_syscall = syscall; - return force_sig_info_to_task(&info, current, force_coredump); + return force_sig_info_to_task(&info, current, + force_coredump ? HANDLER_EXIT : HANDLER_CURRENT); } /* For the crazy architectures that include trap information in @@ -2704,7 +2735,8 @@ relock: if (!signr) break; /* will return 0 */ - if (unlikely(current->ptrace) && signr != SIGKILL) { + if (unlikely(current->ptrace) && (signr != SIGKILL) && + !(sighand->action[signr -1].sa.sa_flags & SA_IMMUTABLE)) { signr = ptrace_signal(signr, &ksig->info); if (!signr) continue; @@ -4054,6 +4086,10 @@ int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact) k = &p->sighand->action[sig-1]; spin_lock_irq(&p->sighand->siglock); + if (k->sa.sa_flags & SA_IMMUTABLE) { + spin_unlock_irq(&p->sighand->siglock); + return -EINVAL; + } if (oact) *oact = *k; @@ -4149,6 +4185,15 @@ do_sigaltstack (const stack_t *ss, stack_t *oss, unsigned long sp, ss_mode != 0)) return -EINVAL; + /* + * Return before taking any locks if no actual + * sigaltstack changes were requested. + */ + if (t->sas_ss_sp == (unsigned long)ss_sp && + t->sas_ss_size == ss_size && + t->sas_ss_flags == ss_flags) + return 0; + sigaltstack_lock(); if (ss_mode == SS_DISABLE) { ss_size = 0; diff --git a/kernel/softirq.c b/kernel/softirq.c index 322b65d45676..41f470929e99 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -595,7 +595,8 @@ void irq_enter_rcu(void) { __irq_enter_raw(); - if (is_idle_task(current) && (irq_count() == HARDIRQ_OFFSET)) + if (tick_nohz_full_cpu(smp_processor_id()) || + (is_idle_task(current) && (irq_count() == HARDIRQ_OFFSET))) tick_irq_enter(); account_hardirq_enter(current); diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c index 9f8117c7cfdd..9c625257023d 100644 --- a/kernel/stacktrace.c +++ b/kernel/stacktrace.c @@ -13,6 +13,7 @@ #include <linux/export.h> #include <linux/kallsyms.h> #include <linux/stacktrace.h> +#include <linux/interrupt.h> /** * stack_trace_print - Print the entries in the stack trace @@ -373,3 +374,32 @@ unsigned int stack_trace_save_user(unsigned long *store, unsigned int size) #endif /* CONFIG_USER_STACKTRACE_SUPPORT */ #endif /* !CONFIG_ARCH_STACKWALK */ + +static inline bool in_irqentry_text(unsigned long ptr) +{ + return (ptr >= (unsigned long)&__irqentry_text_start && + ptr < (unsigned long)&__irqentry_text_end) || + (ptr >= (unsigned long)&__softirqentry_text_start && + ptr < (unsigned long)&__softirqentry_text_end); +} + +/** + * filter_irq_stacks - Find first IRQ stack entry in trace + * @entries: Pointer to stack trace array + * @nr_entries: Number of entries in the storage array + * + * Return: Number of trace entries until IRQ stack starts. + */ +unsigned int filter_irq_stacks(unsigned long *entries, unsigned int nr_entries) +{ + unsigned int i; + + for (i = 0; i < nr_entries; i++) { + if (in_irqentry_text(entries[i])) { + /* Include the irqentry function into the stack. */ + return i + 1; + } + } + return nr_entries; +} +EXPORT_SYMBOL_GPL(filter_irq_stacks); diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 643d412ac623..96b4e7810426 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -1159,13 +1159,28 @@ static void posix_cpu_timers_work(struct callback_head *work) } /* + * Clear existing posix CPU timers task work. + */ +void clear_posix_cputimers_work(struct task_struct *p) +{ + /* + * A copied work entry from the old task is not meaningful, clear it. + * N.B. init_task_work will not do this. + */ + memset(&p->posix_cputimers_work.work, 0, + sizeof(p->posix_cputimers_work.work)); + init_task_work(&p->posix_cputimers_work.work, + posix_cpu_timers_work); + p->posix_cputimers_work.scheduled = false; +} + +/* * Initialize posix CPU timers task work in init task. Out of line to * keep the callback static and to avoid header recursion hell. */ void __init posix_cputimers_init_work(void) { - init_task_work(¤t->posix_cputimers_work.work, - posix_cpu_timers_work); + clear_posix_cputimers_work(current); } /* diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 6bffe5af8cb1..17a283ce2b20 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -1375,6 +1375,13 @@ static inline void tick_nohz_irq_enter(void) now = ktime_get(); if (ts->idle_active) tick_nohz_stop_idle(ts, now); + /* + * If all CPUs are idle. We may need to update a stale jiffies value. + * Note nohz_full is a special case: a timekeeper is guaranteed to stay + * alive but it might be busy looping with interrupts disabled in some + * rare case (typically stop machine). So we must make sure we have a + * last resort. + */ if (ts->tick_stopped) tick_nohz_update_jiffies(now); } diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index b348749a9fc6..dcdcb85121e4 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1306,8 +1306,7 @@ int do_settimeofday64(const struct timespec64 *ts) timekeeping_forward_now(tk); xt = tk_xtime(tk); - ts_delta.tv_sec = ts->tv_sec - xt.tv_sec; - ts_delta.tv_nsec = ts->tv_nsec - xt.tv_nsec; + ts_delta = timespec64_sub(*ts, xt); if (timespec64_compare(&tk->wall_to_monotonic, &ts_delta) > 0) { ret = -EINVAL; diff --git a/kernel/time/timer.c b/kernel/time/timer.c index e3d2c23c413d..85f1021ad459 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -2054,26 +2054,28 @@ unsigned long msleep_interruptible(unsigned int msecs) EXPORT_SYMBOL(msleep_interruptible); /** - * usleep_range - Sleep for an approximate time - * @min: Minimum time in usecs to sleep - * @max: Maximum time in usecs to sleep + * usleep_range_state - Sleep for an approximate time in a given state + * @min: Minimum time in usecs to sleep + * @max: Maximum time in usecs to sleep + * @state: State of the current task that will be while sleeping * * In non-atomic context where the exact wakeup time is flexible, use - * usleep_range() instead of udelay(). The sleep improves responsiveness + * usleep_range_state() instead of udelay(). The sleep improves responsiveness * by avoiding the CPU-hogging busy-wait of udelay(), and the range reduces * power usage by allowing hrtimers to take advantage of an already- * scheduled interrupt instead of scheduling a new one just for this sleep. */ -void __sched usleep_range(unsigned long min, unsigned long max) +void __sched usleep_range_state(unsigned long min, unsigned long max, + unsigned int state) { ktime_t exp = ktime_add_us(ktime_get(), min); u64 delta = (u64)(max - min) * NSEC_PER_USEC; for (;;) { - __set_current_state(TASK_UNINTERRUPTIBLE); + __set_current_state(state); /* Do not return before the requested sleep time has elapsed */ if (!schedule_hrtimeout_range(&exp, delta, HRTIMER_MODE_ABS)) break; } } -EXPORT_SYMBOL(usleep_range); +EXPORT_SYMBOL(usleep_range_state); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 7396488793ff..ae9755037b7e 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1111,8 +1111,6 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_ktime_get_ns_proto; case BPF_FUNC_ktime_get_boot_ns: return &bpf_ktime_get_boot_ns_proto; - case BPF_FUNC_ktime_get_coarse_ns: - return &bpf_ktime_get_coarse_ns_proto; case BPF_FUNC_tail_call: return &bpf_tail_call_proto; case BPF_FUNC_get_current_pid_tgid: diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index f3ea4e20072f..be5f6b32a012 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -318,7 +318,7 @@ int __register_ftrace_function(struct ftrace_ops *ops) if (!ftrace_enabled && (ops->flags & FTRACE_OPS_FL_PERMANENT)) return -EBUSY; - if (!core_kernel_data((unsigned long)ops)) + if (!is_kernel_core_data((unsigned long)ops)) ops->flags |= FTRACE_OPS_FL_DYNAMIC; add_ftrace_ops(&ftrace_ops_list, ops); @@ -5217,6 +5217,7 @@ int unregister_ftrace_direct(unsigned long ip, unsigned long addr) { struct ftrace_direct_func *direct; struct ftrace_func_entry *entry; + struct ftrace_hash *hash; int ret = -ENODEV; mutex_lock(&direct_mutex); @@ -5225,7 +5226,8 @@ int unregister_ftrace_direct(unsigned long ip, unsigned long addr) if (!entry) goto out_unlock; - if (direct_functions->count == 1) + hash = direct_ops.func_hash->filter_hash; + if (hash->count == 1) unregister_ftrace_function(&direct_ops); ret = ftrace_set_filter_ip(&direct_ops, ip, 1, 0); @@ -5540,6 +5542,10 @@ int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr) err = unregister_ftrace_function(ops); remove_direct_functions_hash(hash, addr); mutex_unlock(&direct_mutex); + + /* cleanup for possible another register call */ + ops->func = NULL; + ops->trampoline = 0; return err; } EXPORT_SYMBOL_GPL(unregister_ftrace_direct_multi); @@ -5602,10 +5608,11 @@ int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr) } } + mutex_unlock(&ftrace_lock); + /* Removing the tmp_ops will add the updated direct callers to the functions */ unregister_ftrace_function(&tmp_ops); - mutex_unlock(&ftrace_lock); out_direct: mutex_unlock(&direct_mutex); return err; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index f6520d0a4c8c..2699e9e562b1 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -5228,6 +5228,9 @@ void ring_buffer_reset(struct trace_buffer *buffer) struct ring_buffer_per_cpu *cpu_buffer; int cpu; + /* prevent another thread from changing buffer sizes */ + mutex_lock(&buffer->mutex); + for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; @@ -5246,6 +5249,8 @@ void ring_buffer_reset(struct trace_buffer *buffer) atomic_dec(&cpu_buffer->record_disabled); atomic_dec(&cpu_buffer->resize_disabled); } + + mutex_unlock(&buffer->mutex); } EXPORT_SYMBOL_GPL(ring_buffer_reset); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index f9139dc1262c..88de94da596b 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3812,6 +3812,18 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, iter->fmt[i] = '\0'; trace_seq_vprintf(&iter->seq, iter->fmt, ap); + /* + * If iter->seq is full, the above call no longer guarantees + * that ap is in sync with fmt processing, and further calls + * to va_arg() can return wrong positional arguments. + * + * Ensure that ap is no longer used in this case. + */ + if (iter->seq.full) { + p = ""; + break; + } + if (star) len = va_arg(ap, int); @@ -6706,9 +6718,7 @@ waitagain: cnt = PAGE_SIZE - 1; /* reset all but tr, trace, and overruns */ - memset(&iter->seq, 0, - sizeof(struct trace_iterator) - - offsetof(struct trace_iterator, seq)); + memset_startat(iter, 0, seq); cpumask_clear(iter->started); trace_seq_init(&iter->seq); iter->pos = -1; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 6b60ab9475ed..38715aa6cfdf 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1366,14 +1366,26 @@ __event_trigger_test_discard(struct trace_event_file *file, if (eflags & EVENT_FILE_FL_TRIGGER_COND) *tt = event_triggers_call(file, buffer, entry, event); - if (test_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags) || - (unlikely(file->flags & EVENT_FILE_FL_FILTERED) && - !filter_match_preds(file->filter, entry))) { - __trace_event_discard_commit(buffer, event); - return true; - } + if (likely(!(file->flags & (EVENT_FILE_FL_SOFT_DISABLED | + EVENT_FILE_FL_FILTERED | + EVENT_FILE_FL_PID_FILTER)))) + return false; + + if (file->flags & EVENT_FILE_FL_SOFT_DISABLED) + goto discard; + + if (file->flags & EVENT_FILE_FL_FILTERED && + !filter_match_preds(file->filter, entry)) + goto discard; + + if ((file->flags & EVENT_FILE_FL_PID_FILTER) && + trace_event_ignore_this_pid(file)) + goto discard; return false; + discard: + __trace_event_discard_commit(buffer, event); + return true; } /** diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 4021b9a79f93..92be9cb1d7d4 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2678,12 +2678,24 @@ static struct trace_event_file * trace_create_new_event(struct trace_event_call *call, struct trace_array *tr) { + struct trace_pid_list *no_pid_list; + struct trace_pid_list *pid_list; struct trace_event_file *file; + unsigned int first; file = kmem_cache_alloc(file_cachep, GFP_TRACE); if (!file) return NULL; + pid_list = rcu_dereference_protected(tr->filtered_pids, + lockdep_is_held(&event_mutex)); + no_pid_list = rcu_dereference_protected(tr->filtered_no_pids, + lockdep_is_held(&event_mutex)); + + if (!trace_pid_list_first(pid_list, &first) || + !trace_pid_list_first(no_pid_list, &first)) + file->flags |= EVENT_FILE_FL_PID_FILTER; + file->event_call = call; file->tr = tr; atomic_set(&file->sm_ref, 0); diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 0abc9a413b4d..319f9c8ca7e7 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -1953,9 +1953,10 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data, if (!hist_field->type) goto free; - if (field->filter_type == FILTER_STATIC_STRING) + if (field->filter_type == FILTER_STATIC_STRING) { hist_field->fn = hist_field_string; - else if (field->filter_type == FILTER_DYN_STRING) + hist_field->size = field->size; + } else if (field->filter_type == FILTER_DYN_STRING) hist_field->fn = hist_field_dynstring; else hist_field->fn = hist_field_pstring; @@ -2575,27 +2576,27 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data, /* Split the expression string at the root operator */ if (!sep) - goto free; + return ERR_PTR(-EINVAL); + *sep = '\0'; operand1_str = str; str = sep+1; - if (!operand1_str || !str) - goto free; + /* Binary operator requires both operands */ + if (*operand1_str == '\0' || *str == '\0') + return ERR_PTR(-EINVAL); operand_flags = 0; /* LHS of string is an expression e.g. a+b in a+b+c */ operand1 = parse_expr(hist_data, file, operand1_str, operand_flags, NULL, n_subexprs); - if (IS_ERR(operand1)) { - ret = PTR_ERR(operand1); - operand1 = NULL; - goto free; - } + if (IS_ERR(operand1)) + return ERR_CAST(operand1); + if (operand1->flags & HIST_FIELD_FL_STRING) { hist_err(file->tr, HIST_ERR_INVALID_STR_OPERAND, errpos(operand1_str)); ret = -EINVAL; - goto free; + goto free_op1; } /* RHS of string is another expression e.g. c in a+b+c */ @@ -2603,13 +2604,12 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data, operand2 = parse_expr(hist_data, file, str, operand_flags, NULL, n_subexprs); if (IS_ERR(operand2)) { ret = PTR_ERR(operand2); - operand2 = NULL; - goto free; + goto free_op1; } if (operand2->flags & HIST_FIELD_FL_STRING) { hist_err(file->tr, HIST_ERR_INVALID_STR_OPERAND, errpos(str)); ret = -EINVAL; - goto free; + goto free_operands; } switch (field_op) { @@ -2627,12 +2627,12 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data, break; default: ret = -EINVAL; - goto free; + goto free_operands; } ret = check_expr_operands(file->tr, operand1, operand2, &var1, &var2); if (ret) - goto free; + goto free_operands; operand_flags = var1 ? var1->flags : operand1->flags; operand2_flags = var2 ? var2->flags : operand2->flags; @@ -2651,12 +2651,13 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data, expr = create_hist_field(hist_data, NULL, flags, var_name); if (!expr) { ret = -ENOMEM; - goto free; + goto free_operands; } operand1->read_once = true; operand2->read_once = true; + /* The operands are now owned and free'd by 'expr' */ expr->operands[0] = operand1; expr->operands[1] = operand2; @@ -2667,7 +2668,7 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data, if (!divisor) { hist_err(file->tr, HIST_ERR_DIVISION_BY_ZERO, errpos(str)); ret = -EDOM; - goto free; + goto free_expr; } /* @@ -2707,18 +2708,22 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data, expr->type = kstrdup_const(operand1->type, GFP_KERNEL); if (!expr->type) { ret = -ENOMEM; - goto free; + goto free_expr; } expr->name = expr_str(expr, 0); } return expr; -free: - destroy_hist_field(operand1, 0); + +free_operands: destroy_hist_field(operand2, 0); - destroy_hist_field(expr, 0); +free_op1: + destroy_hist_field(operand1, 0); + return ERR_PTR(ret); +free_expr: + destroy_hist_field(expr, 0); return ERR_PTR(ret); } @@ -3024,8 +3029,10 @@ static inline void __update_field_vars(struct tracing_map_elt *elt, if (val->flags & HIST_FIELD_FL_STRING) { char *str = elt_data->field_var_str[j++]; char *val_str = (char *)(uintptr_t)var_val; + unsigned int size; - strscpy(str, val_str, STR_VAR_LEN_MAX); + size = min(val->size, STR_VAR_LEN_MAX); + strscpy(str, val_str, size); var_val = (u64)(uintptr_t)str; } tracing_map_set_var(elt, var_idx, var_val); @@ -3750,7 +3757,7 @@ static int check_synth_field(struct synth_event *event, if (strcmp(field->type, hist_field->type) != 0) { if (field->size != hist_field->size || - field->is_signed != hist_field->is_signed) + (!field->is_string && field->is_signed != hist_field->is_signed)) return -EINVAL; } @@ -4912,6 +4919,7 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data, if (hist_field->flags & HIST_FIELD_FL_STRING) { unsigned int str_start, var_str_idx, idx; char *str, *val_str; + unsigned int size; str_start = hist_data->n_field_var_str + hist_data->n_save_var_str; @@ -4920,7 +4928,9 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data, str = elt_data->field_var_str[idx]; val_str = (char *)(uintptr_t)hist_val; - strscpy(str, val_str, STR_VAR_LEN_MAX); + + size = min(hist_field->size, STR_VAR_LEN_MAX); + strscpy(str, val_str, size); hist_val = (u64)(uintptr_t)str; } diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index 22db3ce95e74..ca9c13b2ecf4 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -1237,9 +1237,8 @@ static int __create_synth_event(const char *name, const char *raw_fields) argv + consumed, &consumed, &field_version); if (IS_ERR(field)) { - argv_free(argv); ret = PTR_ERR(field); - goto err; + goto err_free_arg; } /* @@ -1262,18 +1261,19 @@ static int __create_synth_event(const char *name, const char *raw_fields) if (cmd_version > 1 && n_fields_this_loop >= 1) { synth_err(SYNTH_ERR_INVALID_CMD, errpos(field_str)); ret = -EINVAL; - goto err; + goto err_free_arg; } fields[n_fields++] = field; if (n_fields == SYNTH_FIELDS_MAX) { synth_err(SYNTH_ERR_TOO_MANY_FIELDS, 0); ret = -EINVAL; - goto err; + goto err_free_arg; } n_fields_this_loop++; } + argv_free(argv); if (consumed < argc) { synth_err(SYNTH_ERR_INVALID_CMD, 0); @@ -1281,7 +1281,6 @@ static int __create_synth_event(const char *name, const char *raw_fields) goto err; } - argv_free(argv); } if (n_fields == 0) { @@ -1307,6 +1306,8 @@ static int __create_synth_event(const char *name, const char *raw_fields) kfree(saved_fields); return ret; + err_free_arg: + argv_free(argv); err: for (i = 0; i < n_fields; i++) free_synth_field(fields[i]); diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index 3e4a1651e329..7520d43aed55 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -55,7 +55,8 @@ struct osnoise_instance { struct list_head list; struct trace_array *tr; }; -struct list_head osnoise_instances; + +static struct list_head osnoise_instances; static bool osnoise_has_registered_instances(void) { diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 0a5c0db3137e..f5f0039d31e5 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1313,6 +1313,7 @@ static int uprobe_perf_open(struct trace_event_call *call, return 0; list_for_each_entry(pos, trace_probe_probe_list(tp), list) { + tu = container_of(pos, struct trace_uprobe, tp); err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true); if (err) { uprobe_perf_close(call, event); diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c index 39bb56d2dcbe..9628b5571846 100644 --- a/kernel/trace/tracing_map.c +++ b/kernel/trace/tracing_map.c @@ -15,6 +15,7 @@ #include <linux/jhash.h> #include <linux/slab.h> #include <linux/sort.h> +#include <linux/kmemleak.h> #include "tracing_map.h" #include "trace.h" @@ -307,6 +308,7 @@ static void tracing_map_array_free(struct tracing_map_array *a) for (i = 0; i < a->n_pages; i++) { if (!a->pages[i]) break; + kmemleak_free(a->pages[i]); free_page((unsigned long)a->pages[i]); } @@ -342,6 +344,7 @@ static struct tracing_map_array *tracing_map_array_alloc(unsigned int n_elts, a->pages[i] = (void *)get_zeroed_page(GFP_KERNEL); if (!a->pages[i]) goto free; + kmemleak_alloc(a->pages[i], PAGE_SIZE, 1, GFP_KERNEL); } out: return a; diff --git a/kernel/tsacct.c b/kernel/tsacct.c index 257ffb993ea2..f00de83d0246 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -137,7 +137,7 @@ static void __acct_update_integrals(struct task_struct *tsk, * the rest of the math is done in xacct_add_tsk. */ tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm) >> 10; - tsk->acct_vm_mem1 += delta * tsk->mm->total_vm >> 10; + tsk->acct_vm_mem1 += delta * READ_ONCE(tsk->mm->total_vm) >> 10; } /** diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 1a7df882f55e..613917bbc4e7 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1351,7 +1351,7 @@ static void insert_work(struct pool_workqueue *pwq, struct work_struct *work, struct worker_pool *pool = pwq->pool; /* record the work call stack in order to print it in KASAN reports */ - kasan_record_aux_stack(work); + kasan_record_aux_stack_noalloc(work); /* we own @work, set data and link */ set_work_pwq(work, pwq, extra_flags); |