diff options
Diffstat (limited to 'kernel')
40 files changed, 426 insertions, 283 deletions
diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c index 6edff97ad594..6639640523c0 100644 --- a/kernel/bpf/bpf_inode_storage.c +++ b/kernel/bpf/bpf_inode_storage.c @@ -125,8 +125,12 @@ static int bpf_fd_inode_storage_update_elem(struct bpf_map *map, void *key, fd = *(int *)key; f = fget_raw(fd); - if (!f || !inode_storage_ptr(f->f_inode)) + if (!f) + return -EBADF; + if (!inode_storage_ptr(f->f_inode)) { + fput(f); return -EBADF; + } sdata = bpf_local_storage_update(f->f_inode, (struct bpf_local_storage_map *)map, @@ -176,14 +180,14 @@ BPF_CALL_4(bpf_inode_storage_get, struct bpf_map *, map, struct inode *, inode, * bpf_local_storage_update expects the owner to have a * valid storage pointer. */ - if (!inode_storage_ptr(inode)) + if (!inode || !inode_storage_ptr(inode)) return (unsigned long)NULL; sdata = inode_storage_lookup(inode, map, true); if (sdata) return (unsigned long)sdata->data; - /* This helper must only called from where the inode is gurranteed + /* This helper must only called from where the inode is guaranteed * to have a refcount and cannot be freed. */ if (flags & BPF_LOCAL_STORAGE_GET_F_CREATE) { @@ -200,7 +204,10 @@ BPF_CALL_4(bpf_inode_storage_get, struct bpf_map *, map, struct inode *, inode, BPF_CALL_2(bpf_inode_storage_delete, struct bpf_map *, map, struct inode *, inode) { - /* This helper must only called from where the inode is gurranteed + if (!inode) + return -EINVAL; + + /* This helper must only called from where the inode is guaranteed * to have a refcount and cannot be freed. */ return inode_storage_delete(inode, map); diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 70e5e0b6d69d..1622a44d1617 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -149,7 +149,11 @@ BTF_ID(func, bpf_lsm_file_ioctl) BTF_ID(func, bpf_lsm_file_lock) BTF_ID(func, bpf_lsm_file_open) BTF_ID(func, bpf_lsm_file_receive) + +#ifdef CONFIG_SECURITY_NETWORK BTF_ID(func, bpf_lsm_inet_conn_established) +#endif /* CONFIG_SECURITY_NETWORK */ + BTF_ID(func, bpf_lsm_inode_create) BTF_ID(func, bpf_lsm_inode_free_security) BTF_ID(func, bpf_lsm_inode_getattr) @@ -166,7 +170,11 @@ BTF_ID(func, bpf_lsm_inode_symlink) BTF_ID(func, bpf_lsm_inode_unlink) BTF_ID(func, bpf_lsm_kernel_module_request) BTF_ID(func, bpf_lsm_kernfs_init_security) + +#ifdef CONFIG_KEYS BTF_ID(func, bpf_lsm_key_free) +#endif /* CONFIG_KEYS */ + BTF_ID(func, bpf_lsm_mmap_file) BTF_ID(func, bpf_lsm_netlink_send) BTF_ID(func, bpf_lsm_path_notify) @@ -181,6 +189,8 @@ BTF_ID(func, bpf_lsm_sb_show_options) BTF_ID(func, bpf_lsm_sb_statfs) BTF_ID(func, bpf_lsm_sb_umount) BTF_ID(func, bpf_lsm_settime) + +#ifdef CONFIG_SECURITY_NETWORK BTF_ID(func, bpf_lsm_socket_accept) BTF_ID(func, bpf_lsm_socket_bind) BTF_ID(func, bpf_lsm_socket_connect) @@ -195,6 +205,8 @@ BTF_ID(func, bpf_lsm_socket_recvmsg) BTF_ID(func, bpf_lsm_socket_sendmsg) BTF_ID(func, bpf_lsm_socket_shutdown) BTF_ID(func, bpf_lsm_socket_socketpair) +#endif /* CONFIG_SECURITY_NETWORK */ + BTF_ID(func, bpf_lsm_syslog) BTF_ID(func, bpf_lsm_task_alloc) BTF_ID(func, bpf_lsm_task_getsecid) diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c index 4ef1959a78f2..e0da0258b732 100644 --- a/kernel/bpf/bpf_task_storage.c +++ b/kernel/bpf/bpf_task_storage.c @@ -218,7 +218,7 @@ BPF_CALL_4(bpf_task_storage_get, struct bpf_map *, map, struct task_struct *, * bpf_local_storage_update expects the owner to have a * valid storage pointer. */ - if (!task_storage_ptr(task)) + if (!task || !task_storage_ptr(task)) return (unsigned long)NULL; sdata = task_storage_lookup(task, map, true); @@ -243,6 +243,9 @@ BPF_CALL_4(bpf_task_storage_get, struct bpf_map *, map, struct task_struct *, BPF_CALL_2(bpf_task_storage_delete, struct bpf_map *, map, struct task_struct *, task) { + if (!task) + return -EINVAL; + /* This helper must only be called from places where the lifetime of the task * is guaranteed. Either by being refcounted or by being protected * by an RCU read-side critical section. diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 8d6bdb4f4d61..84a36ee4a4c2 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -4172,7 +4172,7 @@ static int btf_parse_hdr(struct btf_verifier_env *env) return -ENOTSUPP; } - if (btf_data_size == hdr->hdr_len) { + if (!btf->base_btf && btf_data_size == hdr->hdr_len) { btf_verifier_log(env, "No data"); return -EINVAL; } diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 6ec088a96302..6aa9e10c6335 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1391,12 +1391,13 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, if (ctx.optlen != 0) { *optlen = ctx.optlen; *kernel_optval = ctx.optval; + /* export and don't free sockopt buf */ + return 0; } } out: - if (ret) - sockopt_free_buf(&ctx); + sockopt_free_buf(&ctx); return ret; } @@ -1441,6 +1442,11 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, goto out; } + if (ctx.optlen < 0) { + ret = -EFAULT; + goto out; + } + if (copy_from_user(ctx.optval, optval, min(ctx.optlen, max_optlen)) != 0) { ret = -EFAULT; @@ -1458,7 +1464,7 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, goto out; } - if (ctx.optlen > max_optlen) { + if (ctx.optlen > max_optlen || ctx.optlen < 0) { ret = -EFAULT; goto out; } diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index bd8a3183d030..41ca280b1dc1 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -108,7 +108,7 @@ BPF_CALL_2(bpf_map_peek_elem, struct bpf_map *, map, void *, value) } const struct bpf_func_proto bpf_map_peek_elem_proto = { - .func = bpf_map_pop_elem, + .func = bpf_map_peek_elem, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, diff --git a/kernel/bpf/preload/Makefile b/kernel/bpf/preload/Makefile index 23ee310b6eb4..1951332dd15f 100644 --- a/kernel/bpf/preload/Makefile +++ b/kernel/bpf/preload/Makefile @@ -4,8 +4,11 @@ LIBBPF_SRCS = $(srctree)/tools/lib/bpf/ LIBBPF_A = $(obj)/libbpf.a LIBBPF_OUT = $(abspath $(obj)) +# Although not in use by libbpf's Makefile, set $(O) so that the "dummy" test +# in tools/scripts/Makefile.include always succeeds when building the kernel +# with $(O) pointing to a relative path, as in "make O=build bindeb-pkg". $(LIBBPF_A): - $(Q)$(MAKE) -C $(LIBBPF_SRCS) OUTPUT=$(LIBBPF_OUT)/ $(LIBBPF_OUT)/libbpf.a + $(Q)$(MAKE) -C $(LIBBPF_SRCS) O=$(LIBBPF_OUT)/ OUTPUT=$(LIBBPF_OUT)/ $(LIBBPF_OUT)/libbpf.a userccflags += -I $(srctree)/tools/include/ -I $(srctree)/tools/include/uapi \ -I $(srctree)/tools/lib/ -Wno-unused-result diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index aea96b638473..bfafbf115bf3 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -115,6 +115,8 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) /* hash table size must be power of 2 */ n_buckets = roundup_pow_of_two(attr->max_entries); + if (!n_buckets) + return ERR_PTR(-E2BIG); cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap); cost += n_buckets * (value_size + sizeof(struct stack_map_bucket)); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index c3bb03c8371f..e5999d86c76e 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2712,7 +2712,6 @@ out_unlock: out_put_prog: if (tgt_prog_fd && tgt_prog) bpf_prog_put(tgt_prog); - bpf_prog_put(prog); return err; } @@ -2825,7 +2824,10 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) tp_name = prog->aux->attach_func_name; break; } - return bpf_tracing_prog_attach(prog, 0, 0); + err = bpf_tracing_prog_attach(prog, 0, 0); + if (err >= 0) + return err; + goto out_put_prog; case BPF_PROG_TYPE_RAW_TRACEPOINT: case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: if (strncpy_from_user(buf, diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 17270b8404f1..37581919e050 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2217,6 +2217,8 @@ static bool is_spillable_regtype(enum bpf_reg_type type) case PTR_TO_RDWR_BUF: case PTR_TO_RDWR_BUF_OR_NULL: case PTR_TO_PERCPU_BTF_ID: + case PTR_TO_MEM: + case PTR_TO_MEM_OR_NULL: return true; default: return false; @@ -5311,7 +5313,7 @@ static bool signed_add_overflows(s64 a, s64 b) return res < a; } -static bool signed_add32_overflows(s64 a, s64 b) +static bool signed_add32_overflows(s32 a, s32 b) { /* Do the add in u32, where overflow is well-defined */ s32 res = (s32)((u32)a + (u32)b); @@ -5321,7 +5323,7 @@ static bool signed_add32_overflows(s64 a, s64 b) return res < a; } -static bool signed_sub_overflows(s32 a, s32 b) +static bool signed_sub_overflows(s64 a, s64 b) { /* Do the sub in u64, where overflow is well-defined */ s64 res = (s64)((u64)a - (u64)b); @@ -5333,7 +5335,7 @@ static bool signed_sub_overflows(s32 a, s32 b) static bool signed_sub32_overflows(s32 a, s32 b) { - /* Do the sub in u64, where overflow is well-defined */ + /* Do the sub in u32, where overflow is well-defined */ s32 res = (s32)((u32)a - (u32)b); if (b < 0) @@ -6875,7 +6877,7 @@ static int is_branch32_taken(struct bpf_reg_state *reg, u32 val, u8 opcode) case BPF_JSGT: if (reg->s32_min_value > sval) return 1; - else if (reg->s32_max_value < sval) + else if (reg->s32_max_value <= sval) return 0; break; case BPF_JLT: @@ -6948,7 +6950,7 @@ static int is_branch64_taken(struct bpf_reg_state *reg, u64 val, u8 opcode) case BPF_JSGT: if (reg->smin_value > sval) return 1; - else if (reg->smax_value < sval) + else if (reg->smax_value <= sval) return 0; break; case BPF_JLT: @@ -8588,7 +8590,11 @@ static bool range_within(struct bpf_reg_state *old, return old->umin_value <= cur->umin_value && old->umax_value >= cur->umax_value && old->smin_value <= cur->smin_value && - old->smax_value >= cur->smax_value; + old->smax_value >= cur->smax_value && + old->u32_min_value <= cur->u32_min_value && + old->u32_max_value >= cur->u32_max_value && + old->s32_min_value <= cur->s32_min_value && + old->s32_max_value >= cur->s32_max_value; } /* Maximum number of register states that can exist at once */ @@ -10997,30 +11003,28 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) insn->code == (BPF_ALU | BPF_MOD | BPF_X) || insn->code == (BPF_ALU | BPF_DIV | BPF_X)) { bool is64 = BPF_CLASS(insn->code) == BPF_ALU64; - struct bpf_insn mask_and_div[] = { - BPF_MOV32_REG(insn->src_reg, insn->src_reg), + bool isdiv = BPF_OP(insn->code) == BPF_DIV; + struct bpf_insn *patchlet; + struct bpf_insn chk_and_div[] = { /* Rx div 0 -> 0 */ - BPF_JMP_IMM(BPF_JNE, insn->src_reg, 0, 2), + BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) | + BPF_JNE | BPF_K, insn->src_reg, + 0, 2, 0), BPF_ALU32_REG(BPF_XOR, insn->dst_reg, insn->dst_reg), BPF_JMP_IMM(BPF_JA, 0, 0, 1), *insn, }; - struct bpf_insn mask_and_mod[] = { - BPF_MOV32_REG(insn->src_reg, insn->src_reg), + struct bpf_insn chk_and_mod[] = { /* Rx mod 0 -> Rx */ - BPF_JMP_IMM(BPF_JEQ, insn->src_reg, 0, 1), + BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) | + BPF_JEQ | BPF_K, insn->src_reg, + 0, 1, 0), *insn, }; - struct bpf_insn *patchlet; - if (insn->code == (BPF_ALU64 | BPF_DIV | BPF_X) || - insn->code == (BPF_ALU | BPF_DIV | BPF_X)) { - patchlet = mask_and_div + (is64 ? 1 : 0); - cnt = ARRAY_SIZE(mask_and_div) - (is64 ? 1 : 0); - } else { - patchlet = mask_and_mod + (is64 ? 1 : 0); - cnt = ARRAY_SIZE(mask_and_mod) - (is64 ? 1 : 0); - } + patchlet = isdiv ? chk_and_div : chk_and_mod; + cnt = isdiv ? ARRAY_SIZE(chk_and_div) : + ARRAY_SIZE(chk_and_mod); new_prog = bpf_patch_insn_data(env, i + delta, patchlet, cnt); if (!new_prog) diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c index b1496e744c68..da95df381483 100644 --- a/kernel/dma/map_benchmark.c +++ b/kernel/dma/map_benchmark.c @@ -36,7 +36,7 @@ struct map_benchmark { __s32 node; /* which numa node this benchmark will run on */ __u32 dma_bits; /* DMA addressing capability */ __u32 dma_dir; /* DMA data direction */ - __u64 expansion[10]; /* For future use */ + __u8 expansion[84]; /* For future use */ }; struct map_benchmark_data { @@ -147,8 +147,10 @@ static int do_map_benchmark(struct map_benchmark_data *map) atomic64_set(&map->sum_sq_unmap, 0); atomic64_set(&map->loops, 0); - for (i = 0; i < threads; i++) + for (i = 0; i < threads; i++) { + get_task_struct(tsk[i]); wake_up_process(tsk[i]); + } msleep_interruptible(map->bparam.seconds * 1000); @@ -183,6 +185,8 @@ static int do_map_benchmark(struct map_benchmark_data *map) } out: + for (i = 0; i < threads; i++) + put_task_struct(tsk[i]); put_device(map->dev); kfree(tsk); return ret; diff --git a/kernel/entry/common.c b/kernel/entry/common.c index 378341642f94..f9d491b17b78 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -209,26 +209,18 @@ static void exit_to_user_mode_prepare(struct pt_regs *regs) lockdep_sys_exit(); } -#ifndef _TIF_SINGLESTEP -static inline bool report_single_step(unsigned long work) -{ - return false; -} -#else /* * If SYSCALL_EMU is set, then the only reason to report is when - * TIF_SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP). This syscall + * SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP). This syscall * instruction has been already reported in syscall_enter_from_user_mode(). */ static inline bool report_single_step(unsigned long work) { - if (!(work & SYSCALL_WORK_SYSCALL_EMU)) + if (work & SYSCALL_WORK_SYSCALL_EMU) return false; - return !!(current_thread_info()->flags & _TIF_SINGLESTEP); + return work & SYSCALL_WORK_SYSCALL_EXIT_TRAP; } -#endif - static void syscall_exit_work(struct pt_regs *regs, unsigned long work) { diff --git a/kernel/entry/syscall_user_dispatch.c b/kernel/entry/syscall_user_dispatch.c index b0338a5625d9..c240302f56e2 100644 --- a/kernel/entry/syscall_user_dispatch.c +++ b/kernel/entry/syscall_user_dispatch.c @@ -50,10 +50,10 @@ bool syscall_user_dispatch(struct pt_regs *regs) if (unlikely(__get_user(state, sd->selector))) do_exit(SIGSEGV); - if (likely(state == PR_SYS_DISPATCH_OFF)) + if (likely(state == SYSCALL_DISPATCH_FILTER_ALLOW)) return false; - if (state != PR_SYS_DISPATCH_ON) + if (state != SYSCALL_DISPATCH_FILTER_BLOCK) do_exit(SIGSYS); } diff --git a/kernel/fork.c b/kernel/fork.c index 37720a6d04ea..d66cd1014211 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -819,9 +819,8 @@ void __init fork_init(void) init_task.signal->rlim[RLIMIT_SIGPENDING] = init_task.signal->rlim[RLIMIT_NPROC]; - for (i = 0; i < UCOUNT_COUNTS; i++) { + for (i = 0; i < UCOUNT_COUNTS; i++) init_user_ns.ucount_max[i] = max_threads/2; - } #ifdef CONFIG_VMAP_STACK cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache", @@ -1654,9 +1653,8 @@ static inline void init_task_pid_links(struct task_struct *task) { enum pid_type type; - for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) { + for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) INIT_HLIST_NODE(&task->pid_links[type]); - } } static inline void diff --git a/kernel/futex.c b/kernel/futex.c index c47d1015d759..45a13eb8894e 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -763,6 +763,29 @@ static struct futex_pi_state *alloc_pi_state(void) return pi_state; } +static void pi_state_update_owner(struct futex_pi_state *pi_state, + struct task_struct *new_owner) +{ + struct task_struct *old_owner = pi_state->owner; + + lockdep_assert_held(&pi_state->pi_mutex.wait_lock); + + if (old_owner) { + raw_spin_lock(&old_owner->pi_lock); + WARN_ON(list_empty(&pi_state->list)); + list_del_init(&pi_state->list); + raw_spin_unlock(&old_owner->pi_lock); + } + + if (new_owner) { + raw_spin_lock(&new_owner->pi_lock); + WARN_ON(!list_empty(&pi_state->list)); + list_add(&pi_state->list, &new_owner->pi_state_list); + pi_state->owner = new_owner; + raw_spin_unlock(&new_owner->pi_lock); + } +} + static void get_pi_state(struct futex_pi_state *pi_state) { WARN_ON_ONCE(!refcount_inc_not_zero(&pi_state->refcount)); @@ -785,17 +808,11 @@ static void put_pi_state(struct futex_pi_state *pi_state) * and has cleaned up the pi_state already */ if (pi_state->owner) { - struct task_struct *owner; unsigned long flags; raw_spin_lock_irqsave(&pi_state->pi_mutex.wait_lock, flags); - owner = pi_state->owner; - if (owner) { - raw_spin_lock(&owner->pi_lock); - list_del_init(&pi_state->list); - raw_spin_unlock(&owner->pi_lock); - } - rt_mutex_proxy_unlock(&pi_state->pi_mutex, owner); + pi_state_update_owner(pi_state, NULL); + rt_mutex_proxy_unlock(&pi_state->pi_mutex); raw_spin_unlock_irqrestore(&pi_state->pi_mutex.wait_lock, flags); } @@ -941,7 +958,8 @@ static inline void exit_pi_state_list(struct task_struct *curr) { } * FUTEX_OWNER_DIED bit. See [4] * * [10] There is no transient state which leaves owner and user space - * TID out of sync. + * TID out of sync. Except one error case where the kernel is denied + * write access to the user address, see fixup_pi_state_owner(). * * * Serialization and lifetime rules: @@ -1521,26 +1539,15 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_ ret = -EINVAL; } - if (ret) - goto out_unlock; - - /* - * This is a point of no return; once we modify the uval there is no - * going back and subsequent operations must not fail. - */ - - raw_spin_lock(&pi_state->owner->pi_lock); - WARN_ON(list_empty(&pi_state->list)); - list_del_init(&pi_state->list); - raw_spin_unlock(&pi_state->owner->pi_lock); - - raw_spin_lock(&new_owner->pi_lock); - WARN_ON(!list_empty(&pi_state->list)); - list_add(&pi_state->list, &new_owner->pi_state_list); - pi_state->owner = new_owner; - raw_spin_unlock(&new_owner->pi_lock); - - postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q); + if (!ret) { + /* + * This is a point of no return; once we modified the uval + * there is no going back and subsequent operations must + * not fail. + */ + pi_state_update_owner(pi_state, new_owner); + postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q); + } out_unlock: raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); @@ -2323,18 +2330,13 @@ static void unqueue_me_pi(struct futex_q *q) spin_unlock(q->lock_ptr); } -static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, - struct task_struct *argowner) +static int __fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, + struct task_struct *argowner) { struct futex_pi_state *pi_state = q->pi_state; - u32 uval, curval, newval; struct task_struct *oldowner, *newowner; - u32 newtid; - int ret, err = 0; - - lockdep_assert_held(q->lock_ptr); - - raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + u32 uval, curval, newval, newtid; + int err = 0; oldowner = pi_state->owner; @@ -2368,14 +2370,12 @@ retry: * We raced against a concurrent self; things are * already fixed up. Nothing to do. */ - ret = 0; - goto out_unlock; + return 0; } if (__rt_mutex_futex_trylock(&pi_state->pi_mutex)) { - /* We got the lock after all, nothing to fix. */ - ret = 0; - goto out_unlock; + /* We got the lock. pi_state is correct. Tell caller. */ + return 1; } /* @@ -2402,8 +2402,7 @@ retry: * We raced against a concurrent self; things are * already fixed up. Nothing to do. */ - ret = 0; - goto out_unlock; + return 1; } newowner = argowner; } @@ -2433,22 +2432,9 @@ retry: * We fixed up user space. Now we need to fix the pi_state * itself. */ - if (pi_state->owner != NULL) { - raw_spin_lock(&pi_state->owner->pi_lock); - WARN_ON(list_empty(&pi_state->list)); - list_del_init(&pi_state->list); - raw_spin_unlock(&pi_state->owner->pi_lock); - } + pi_state_update_owner(pi_state, newowner); - pi_state->owner = newowner; - - raw_spin_lock(&newowner->pi_lock); - WARN_ON(!list_empty(&pi_state->list)); - list_add(&pi_state->list, &newowner->pi_state_list); - raw_spin_unlock(&newowner->pi_lock); - raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); - - return 0; + return argowner == current; /* * In order to reschedule or handle a page fault, we need to drop the @@ -2469,17 +2455,16 @@ handle_err: switch (err) { case -EFAULT: - ret = fault_in_user_writeable(uaddr); + err = fault_in_user_writeable(uaddr); break; case -EAGAIN: cond_resched(); - ret = 0; + err = 0; break; default: WARN_ON_ONCE(1); - ret = err; break; } @@ -2489,17 +2474,44 @@ handle_err: /* * Check if someone else fixed it for us: */ - if (pi_state->owner != oldowner) { - ret = 0; - goto out_unlock; - } + if (pi_state->owner != oldowner) + return argowner == current; - if (ret) - goto out_unlock; + /* Retry if err was -EAGAIN or the fault in succeeded */ + if (!err) + goto retry; - goto retry; + /* + * fault_in_user_writeable() failed so user state is immutable. At + * best we can make the kernel state consistent but user state will + * be most likely hosed and any subsequent unlock operation will be + * rejected due to PI futex rule [10]. + * + * Ensure that the rtmutex owner is also the pi_state owner despite + * the user space value claiming something different. There is no + * point in unlocking the rtmutex if current is the owner as it + * would need to wait until the next waiter has taken the rtmutex + * to guarantee consistent state. Keep it simple. Userspace asked + * for this wreckaged state. + * + * The rtmutex has an owner - either current or some other + * task. See the EAGAIN loop above. + */ + pi_state_update_owner(pi_state, rt_mutex_owner(&pi_state->pi_mutex)); -out_unlock: + return err; +} + +static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, + struct task_struct *argowner) +{ + struct futex_pi_state *pi_state = q->pi_state; + int ret; + + lockdep_assert_held(q->lock_ptr); + + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + ret = __fixup_pi_state_owner(uaddr, q, argowner); raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); return ret; } @@ -2523,8 +2535,6 @@ static long futex_wait_restart(struct restart_block *restart); */ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked) { - int ret = 0; - if (locked) { /* * Got the lock. We might not be the anticipated owner if we @@ -2535,8 +2545,8 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked) * stable state, anything else needs more attention. */ if (q->pi_state->owner != current) - ret = fixup_pi_state_owner(uaddr, q, current); - return ret ? ret : locked; + return fixup_pi_state_owner(uaddr, q, current); + return 1; } /* @@ -2547,23 +2557,17 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked) * Another speculative read; pi_state->owner == current is unstable * but needs our attention. */ - if (q->pi_state->owner == current) { - ret = fixup_pi_state_owner(uaddr, q, NULL); - return ret; - } + if (q->pi_state->owner == current) + return fixup_pi_state_owner(uaddr, q, NULL); /* * Paranoia check. If we did not take the lock, then we should not be - * the owner of the rt_mutex. + * the owner of the rt_mutex. Warn and establish consistent state. */ - if (rt_mutex_owner(&q->pi_state->pi_mutex) == current) { - printk(KERN_ERR "fixup_owner: ret = %d pi-mutex: %p " - "pi-state %p\n", ret, - q->pi_state->pi_mutex.owner, - q->pi_state->owner); - } + if (WARN_ON_ONCE(rt_mutex_owner(&q->pi_state->pi_mutex) == current)) + return fixup_pi_state_owner(uaddr, q, current); - return ret; + return 0; } /** @@ -2771,7 +2775,6 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int trylock) { struct hrtimer_sleeper timeout, *to; - struct futex_pi_state *pi_state = NULL; struct task_struct *exiting = NULL; struct rt_mutex_waiter rt_waiter; struct futex_hash_bucket *hb; @@ -2907,23 +2910,8 @@ no_block: if (res) ret = (res < 0) ? res : 0; - /* - * If fixup_owner() faulted and was unable to handle the fault, unlock - * it and return the fault to userspace. - */ - if (ret && (rt_mutex_owner(&q.pi_state->pi_mutex) == current)) { - pi_state = q.pi_state; - get_pi_state(pi_state); - } - /* Unqueue and drop the lock */ unqueue_me_pi(&q); - - if (pi_state) { - rt_mutex_futex_unlock(&pi_state->pi_mutex); - put_pi_state(pi_state); - } - goto out; out_unlock_put_key: @@ -3183,7 +3171,6 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, u32 __user *uaddr2) { struct hrtimer_sleeper timeout, *to; - struct futex_pi_state *pi_state = NULL; struct rt_mutex_waiter rt_waiter; struct futex_hash_bucket *hb; union futex_key key2 = FUTEX_KEY_INIT; @@ -3261,16 +3248,17 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, if (q.pi_state && (q.pi_state->owner != current)) { spin_lock(q.lock_ptr); ret = fixup_pi_state_owner(uaddr2, &q, current); - if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) { - pi_state = q.pi_state; - get_pi_state(pi_state); - } /* * Drop the reference to the pi state which * the requeue_pi() code acquired for us. */ put_pi_state(q.pi_state); spin_unlock(q.lock_ptr); + /* + * Adjust the return value. It's either -EFAULT or + * success (1) but the caller expects 0 for success. + */ + ret = ret < 0 ? ret : 0; } } else { struct rt_mutex *pi_mutex; @@ -3301,25 +3289,10 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, if (res) ret = (res < 0) ? res : 0; - /* - * If fixup_pi_state_owner() faulted and was unable to handle - * the fault, unlock the rt_mutex and return the fault to - * userspace. - */ - if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) { - pi_state = q.pi_state; - get_pi_state(pi_state); - } - /* Unqueue and drop the lock. */ unqueue_me_pi(&q); } - if (pi_state) { - rt_mutex_futex_unlock(&pi_state->pi_mutex); - put_pi_state(pi_state); - } - if (ret == -EINTR) { /* * We've already been requeued, but cannot restart by calling diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig index 3110c77230c7..f62de2dea8a3 100644 --- a/kernel/gcov/Kconfig +++ b/kernel/gcov/Kconfig @@ -4,7 +4,7 @@ menu "GCOV-based kernel profiling" config GCOV_KERNEL bool "Enable gcov-based kernel profiling" depends on DEBUG_FS - select CONSTRUCTORS if !UML + select CONSTRUCTORS default n help This option enables gcov-based code profiling (e.g. for code coverage diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index ab8567f32501..dec3f73e8db9 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -2859,3 +2859,4 @@ bool irq_check_status_bit(unsigned int irq, unsigned int bitmask) rcu_read_unlock(); return res; } +EXPORT_SYMBOL_GPL(irq_check_status_bit); diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 2c0c4d6d0f83..b338d622f26e 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -402,7 +402,7 @@ int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, struct msi_domain_ops *ops = info->ops; struct irq_data *irq_data; struct msi_desc *desc; - msi_alloc_info_t arg; + msi_alloc_info_t arg = { }; int i, ret, virq; bool can_reserve; @@ -436,22 +436,22 @@ int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, can_reserve = msi_check_reservation_mode(domain, info, dev); - for_each_msi_entry(desc, dev) { - virq = desc->irq; - if (desc->nvec_used == 1) - dev_dbg(dev, "irq %d for MSI\n", virq); - else + /* + * This flag is set by the PCI layer as we need to activate + * the MSI entries before the PCI layer enables MSI in the + * card. Otherwise the card latches a random msi message. + */ + if (!(info->flags & MSI_FLAG_ACTIVATE_EARLY)) + goto skip_activate; + + for_each_msi_vector(desc, i, dev) { + if (desc->irq == i) { + virq = desc->irq; dev_dbg(dev, "irq [%d-%d] for MSI\n", virq, virq + desc->nvec_used - 1); - /* - * This flag is set by the PCI layer as we need to activate - * the MSI entries before the PCI layer enables MSI in the - * card. Otherwise the card latches a random msi message. - */ - if (!(info->flags & MSI_FLAG_ACTIVATE_EARLY)) - continue; + } - irq_data = irq_domain_get_irq_data(domain, desc->irq); + irq_data = irq_domain_get_irq_data(domain, i); if (!can_reserve) { irqd_clr_can_reserve(irq_data); if (domain->flags & IRQ_DOMAIN_MSI_NOMASK_QUIRK) @@ -462,28 +462,24 @@ int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, goto cleanup; } +skip_activate: /* * If these interrupts use reservation mode, clear the activated bit * so request_irq() will assign the final vector. */ if (can_reserve) { - for_each_msi_entry(desc, dev) { - irq_data = irq_domain_get_irq_data(domain, desc->irq); + for_each_msi_vector(desc, i, dev) { + irq_data = irq_domain_get_irq_data(domain, i); irqd_clr_activated(irq_data); } } return 0; cleanup: - for_each_msi_entry(desc, dev) { - struct irq_data *irqd; - - if (desc->irq == virq) - break; - - irqd = irq_domain_get_irq_data(domain, desc->irq); - if (irqd_is_activated(irqd)) - irq_domain_deactivate_irq(irqd); + for_each_msi_vector(desc, i, dev) { + irq_data = irq_domain_get_irq_data(domain, i); + if (irqd_is_activated(irq_data)) + irq_domain_deactivate_irq(irq_data); } msi_domain_free_irqs(domain, dev); return ret; diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 4f8efc278aa7..aa919585c24b 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -1134,7 +1134,6 @@ int kernel_kexec(void) #ifdef CONFIG_KEXEC_JUMP if (kexec_image->preserve_context) { - lock_system_sleep(); pm_prepare_console(); error = freeze_processes(); if (error) { @@ -1197,7 +1196,6 @@ int kernel_kexec(void) thaw_processes(); Restore_console: pm_restore_console(); - unlock_system_sleep(); } #endif diff --git a/kernel/kprobes.c b/kernel/kprobes.c index f7fb5d135930..d5a3eb74a657 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1954,28 +1954,48 @@ bool __weak arch_kprobe_on_func_entry(unsigned long offset) return !offset; } -bool kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset) +/** + * kprobe_on_func_entry() -- check whether given address is function entry + * @addr: Target address + * @sym: Target symbol name + * @offset: The offset from the symbol or the address + * + * This checks whether the given @addr+@offset or @sym+@offset is on the + * function entry address or not. + * This returns 0 if it is the function entry, or -EINVAL if it is not. + * And also it returns -ENOENT if it fails the symbol or address lookup. + * Caller must pass @addr or @sym (either one must be NULL), or this + * returns -EINVAL. + */ +int kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset) { kprobe_opcode_t *kp_addr = _kprobe_addr(addr, sym, offset); if (IS_ERR(kp_addr)) - return false; + return PTR_ERR(kp_addr); - if (!kallsyms_lookup_size_offset((unsigned long)kp_addr, NULL, &offset) || - !arch_kprobe_on_func_entry(offset)) - return false; + if (!kallsyms_lookup_size_offset((unsigned long)kp_addr, NULL, &offset)) + return -ENOENT; - return true; + if (!arch_kprobe_on_func_entry(offset)) + return -EINVAL; + + return 0; } int register_kretprobe(struct kretprobe *rp) { - int ret = 0; + int ret; struct kretprobe_instance *inst; int i; void *addr; - if (!kprobe_on_func_entry(rp->kp.addr, rp->kp.symbol_name, rp->kp.offset)) + ret = kprobe_on_func_entry(rp->kp.addr, rp->kp.symbol_name, rp->kp.offset); + if (ret) + return ret; + + /* If only rp->kp.addr is specified, check reregistering kprobes */ + if (rp->kp.addr && check_kprobe_rereg(&rp->kp)) return -EINVAL; if (kretprobe_blacklist_size) { diff --git a/kernel/kthread.c b/kernel/kthread.c index a5eceecd4513..1578973c5740 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -294,7 +294,7 @@ static int kthread(void *_create) do_exit(ret); } -/* called from do_fork() to get node information for about to be created task */ +/* called from kernel_clone() to get node information for about to be created task */ int tsk_fork_get_node(struct task_struct *tsk) { #ifdef CONFIG_NUMA @@ -493,11 +493,36 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), return p; kthread_bind(p, cpu); /* CPU hotplug need to bind once again when unparking the thread. */ - set_bit(KTHREAD_IS_PER_CPU, &to_kthread(p)->flags); to_kthread(p)->cpu = cpu; return p; } +void kthread_set_per_cpu(struct task_struct *k, int cpu) +{ + struct kthread *kthread = to_kthread(k); + if (!kthread) + return; + + WARN_ON_ONCE(!(k->flags & PF_NO_SETAFFINITY)); + + if (cpu < 0) { + clear_bit(KTHREAD_IS_PER_CPU, &kthread->flags); + return; + } + + kthread->cpu = cpu; + set_bit(KTHREAD_IS_PER_CPU, &kthread->flags); +} + +bool kthread_is_per_cpu(struct task_struct *k) +{ + struct kthread *kthread = to_kthread(k); + if (!kthread) + return false; + + return test_bit(KTHREAD_IS_PER_CPU, &kthread->flags); +} + /** * kthread_unpark - unpark a thread created by kthread_create(). * @k: thread created by kthread_create(). diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index c1418b47f625..bdaf4829098c 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -79,7 +79,7 @@ module_param(lock_stat, int, 0644); DEFINE_PER_CPU(unsigned int, lockdep_recursion); EXPORT_PER_CPU_SYMBOL_GPL(lockdep_recursion); -static inline bool lockdep_enabled(void) +static __always_inline bool lockdep_enabled(void) { if (!debug_locks) return false; @@ -5271,12 +5271,15 @@ static void __lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie cookie /* * Check whether we follow the irq-flags state precisely: */ -static void check_flags(unsigned long flags) +static noinstr void check_flags(unsigned long flags) { #if defined(CONFIG_PROVE_LOCKING) && defined(CONFIG_DEBUG_LOCKDEP) if (!debug_locks) return; + /* Get the warning out.. */ + instrumentation_begin(); + if (irqs_disabled_flags(flags)) { if (DEBUG_LOCKS_WARN_ON(lockdep_hardirqs_enabled())) { printk("possible reason: unannotated irqs-off.\n"); @@ -5304,6 +5307,8 @@ static void check_flags(unsigned long flags) if (!debug_locks) print_irqtrace_events(current); + + instrumentation_end(); #endif } diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index cfdd5b93264d..2f8cd616d3b2 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1716,8 +1716,7 @@ void rt_mutex_init_proxy_locked(struct rt_mutex *lock, * possible because it belongs to the pi_state which is about to be freed * and it is not longer visible to other tasks. */ -void rt_mutex_proxy_unlock(struct rt_mutex *lock, - struct task_struct *proxy_owner) +void rt_mutex_proxy_unlock(struct rt_mutex *lock) { debug_rt_mutex_proxy_unlock(lock); rt_mutex_set_owner(lock, NULL); diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h index d1d62f942be2..ca6fb489007b 100644 --- a/kernel/locking/rtmutex_common.h +++ b/kernel/locking/rtmutex_common.h @@ -133,8 +133,7 @@ enum rtmutex_chainwalk { extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock); extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock, struct task_struct *proxy_owner); -extern void rt_mutex_proxy_unlock(struct rt_mutex *lock, - struct task_struct *proxy_owner); +extern void rt_mutex_proxy_unlock(struct rt_mutex *lock); extern void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter); extern int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, diff --git a/kernel/power/swap.c b/kernel/power/swap.c index c73f2e295167..72e33054a2e1 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -497,10 +497,10 @@ static int swap_writer_finish(struct swap_map_handle *handle, unsigned int flags, int error) { if (!error) { - flush_swap_writer(handle); pr_info("S"); error = mark_swapfiles(handle, flags); pr_cont("|\n"); + flush_swap_writer(handle); } if (error) diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index ffdd0dc7ec6d..5a95c688621f 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1291,11 +1291,16 @@ static size_t info_print_prefix(const struct printk_info *info, bool syslog, * done: * * - Add prefix for each line. + * - Drop truncated lines that no longer fit into the buffer. * - Add the trailing newline that has been removed in vprintk_store(). - * - Drop truncated lines that do not longer fit into the buffer. + * - Add a string terminator. + * + * Since the produced string is always terminated, the maximum possible + * return value is @r->text_buf_size - 1; * * Return: The length of the updated/prepared text, including the added - * prefixes and the newline. The dropped line(s) are not counted. + * prefixes and the newline. The terminator is not counted. The dropped + * line(s) are not counted. */ static size_t record_print_text(struct printk_record *r, bool syslog, bool time) @@ -1338,26 +1343,31 @@ static size_t record_print_text(struct printk_record *r, bool syslog, /* * Truncate the text if there is not enough space to add the - * prefix and a trailing newline. + * prefix and a trailing newline and a terminator. */ - if (len + prefix_len + text_len + 1 > buf_size) { + if (len + prefix_len + text_len + 1 + 1 > buf_size) { /* Drop even the current line if no space. */ - if (len + prefix_len + line_len + 1 > buf_size) + if (len + prefix_len + line_len + 1 + 1 > buf_size) break; - text_len = buf_size - len - prefix_len - 1; + text_len = buf_size - len - prefix_len - 1 - 1; truncated = true; } memmove(text + prefix_len, text, text_len); memcpy(text, prefix, prefix_len); + /* + * Increment the prepared length to include the text and + * prefix that were just moved+copied. Also increment for the + * newline at the end of this line. If this is the last line, + * there is no newline, but it will be added immediately below. + */ len += prefix_len + line_len + 1; - if (text_len == line_len) { /* - * Add the trailing newline removed in - * vprintk_store(). + * This is the last line. Add the trailing newline + * removed in vprintk_store(). */ text[prefix_len + line_len] = '\n'; break; @@ -1382,6 +1392,14 @@ static size_t record_print_text(struct printk_record *r, bool syslog, text_len -= line_len + 1; } + /* + * If a buffer was provided, it will be terminated. Space for the + * string terminator is guaranteed to be available. The terminator is + * not counted in the return value. + */ + if (buf_size > 0) + r->text_buf[len] = 0; + return len; } @@ -3427,7 +3445,7 @@ bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, while (prb_read_valid_info(prb, seq, &info, &line_count)) { if (r.info->seq >= dumper->next_seq) break; - l += get_record_print_text_size(&info, line_count, true, time); + l += get_record_print_text_size(&info, line_count, syslog, time); seq = r.info->seq + 1; } @@ -3437,7 +3455,7 @@ bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, &info, &line_count)) { if (r.info->seq >= dumper->next_seq) break; - l -= get_record_print_text_size(&info, line_count, true, time); + l -= get_record_print_text_size(&info, line_count, syslog, time); seq = r.info->seq + 1; } diff --git a/kernel/printk/printk_ringbuffer.c b/kernel/printk/printk_ringbuffer.c index 6704f06e0417..8a7b7362c0dd 100644 --- a/kernel/printk/printk_ringbuffer.c +++ b/kernel/printk/printk_ringbuffer.c @@ -1718,7 +1718,7 @@ static bool copy_data(struct prb_data_ring *data_ring, /* Caller interested in the line count? */ if (line_count) - *line_count = count_lines(data, data_size); + *line_count = count_lines(data, len); /* Caller interested in the data content? */ if (!buf || !buf_size) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 15d2562118d1..ff74fca39ed2 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1796,13 +1796,28 @@ static inline bool rq_has_pinned_tasks(struct rq *rq) */ static inline bool is_cpu_allowed(struct task_struct *p, int cpu) { + /* When not in the task's cpumask, no point in looking further. */ if (!cpumask_test_cpu(cpu, p->cpus_ptr)) return false; - if (is_per_cpu_kthread(p) || is_migration_disabled(p)) + /* migrate_disabled() must be allowed to finish. */ + if (is_migration_disabled(p)) return cpu_online(cpu); - return cpu_active(cpu); + /* Non kernel threads are not allowed during either online or offline. */ + if (!(p->flags & PF_KTHREAD)) + return cpu_active(cpu); + + /* KTHREAD_IS_PER_CPU is always allowed. */ + if (kthread_is_per_cpu(p)) + return cpu_online(cpu); + + /* Regular kernel threads don't get to stay during offline. */ + if (cpu_rq(cpu)->balance_push) + return false; + + /* But are allowed during online. */ + return cpu_online(cpu); } /* @@ -2327,7 +2342,9 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, if (p->flags & PF_KTHREAD || is_migration_disabled(p)) { /* - * Kernel threads are allowed on online && !active CPUs. + * Kernel threads are allowed on online && !active CPUs, + * however, during cpu-hot-unplug, even these might get pushed + * away if not KTHREAD_IS_PER_CPU. * * Specifically, migration_disabled() tasks must not fail the * cpumask_any_and_distribute() pick below, esp. so on @@ -2371,16 +2388,6 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, __do_set_cpus_allowed(p, new_mask, flags); - if (p->flags & PF_KTHREAD) { - /* - * For kernel threads that do indeed end up on online && - * !active we want to ensure they are strict per-CPU threads. - */ - WARN_ON(cpumask_intersects(new_mask, cpu_online_mask) && - !cpumask_intersects(new_mask, cpu_active_mask) && - p->nr_cpus_allowed != 1); - } - return affine_move_task(rq, p, &rf, dest_cpu, flags); out: @@ -3122,6 +3129,13 @@ bool cpus_share_cache(int this_cpu, int that_cpu) static inline bool ttwu_queue_cond(int cpu, int wake_flags) { /* + * Do not complicate things with the async wake_list while the CPU is + * in hotplug state. + */ + if (!cpu_active(cpu)) + return false; + + /* * If the CPU does not share cache, then queue the task on the * remote rqs wakelist to avoid accessing remote data. */ @@ -7276,8 +7290,14 @@ static void balance_push(struct rq *rq) /* * Both the cpu-hotplug and stop task are in this case and are * required to complete the hotplug process. + * + * XXX: the idle task does not match kthread_is_per_cpu() due to + * histerical raisins. */ - if (is_per_cpu_kthread(push_task) || is_migration_disabled(push_task)) { + if (rq->idle == push_task || + ((push_task->flags & PF_KTHREAD) && kthread_is_per_cpu(push_task)) || + is_migration_disabled(push_task)) { + /* * If this is the idle task on the outgoing CPU try to wake * up the hotplug control thread which might wait for the @@ -7309,7 +7329,7 @@ static void balance_push(struct rq *rq) /* * At this point need_resched() is true and we'll take the loop in * schedule(). The next pick is obviously going to be the stop task - * which is_per_cpu_kthread() and will push this task away. + * which kthread_is_per_cpu() and will push this task away. */ raw_spin_lock(&rq->lock); } @@ -7320,10 +7340,13 @@ static void balance_push_set(int cpu, bool on) struct rq_flags rf; rq_lock_irqsave(rq, &rf); - if (on) + rq->balance_push = on; + if (on) { + WARN_ON_ONCE(rq->balance_callback); rq->balance_callback = &balance_push_callback; - else + } else if (rq->balance_callback == &balance_push_callback) { rq->balance_callback = NULL; + } rq_unlock_irqrestore(rq, &rf); } @@ -7441,6 +7464,10 @@ int sched_cpu_activate(unsigned int cpu) struct rq *rq = cpu_rq(cpu); struct rq_flags rf; + /* + * Make sure that when the hotplug state machine does a roll-back + * we clear balance_push. Ideally that would happen earlier... + */ balance_push_set(cpu, false); #ifdef CONFIG_SCHED_SMT @@ -7483,17 +7510,27 @@ int sched_cpu_deactivate(unsigned int cpu) int ret; set_cpu_active(cpu, false); + + /* + * From this point forward, this CPU will refuse to run any task that + * is not: migrate_disable() or KTHREAD_IS_PER_CPU, and will actively + * push those tasks away until this gets cleared, see + * sched_cpu_dying(). + */ + balance_push_set(cpu, true); + /* - * We've cleared cpu_active_mask, wait for all preempt-disabled and RCU - * users of this state to go away such that all new such users will - * observe it. + * We've cleared cpu_active_mask / set balance_push, wait for all + * preempt-disabled and RCU users of this state to go away such that + * all new such users will observe it. + * + * Specifically, we rely on ttwu to no longer target this CPU, see + * ttwu_queue_cond() and is_cpu_allowed(). * * Do sync before park smpboot threads to take care the rcu boost case. */ synchronize_rcu(); - balance_push_set(cpu, true); - rq_lock_irqsave(rq, &rf); if (rq->rd) { update_rq_clock(rq); @@ -7574,6 +7611,25 @@ static void calc_load_migrate(struct rq *rq) atomic_long_add(delta, &calc_load_tasks); } +static void dump_rq_tasks(struct rq *rq, const char *loglvl) +{ + struct task_struct *g, *p; + int cpu = cpu_of(rq); + + lockdep_assert_held(&rq->lock); + + printk("%sCPU%d enqueued tasks (%u total):\n", loglvl, cpu, rq->nr_running); + for_each_process_thread(g, p) { + if (task_cpu(p) != cpu) + continue; + + if (!task_on_rq_queued(p)) + continue; + + printk("%s\tpid: %d, name: %s\n", loglvl, p->pid, p->comm); + } +} + int sched_cpu_dying(unsigned int cpu) { struct rq *rq = cpu_rq(cpu); @@ -7583,9 +7639,18 @@ int sched_cpu_dying(unsigned int cpu) sched_tick_stop(cpu); rq_lock_irqsave(rq, &rf); - BUG_ON(rq->nr_running != 1 || rq_has_pinned_tasks(rq)); + if (rq->nr_running != 1 || rq_has_pinned_tasks(rq)) { + WARN(true, "Dying CPU not properly vacated!"); + dump_rq_tasks(rq, KERN_WARNING); + } rq_unlock_irqrestore(rq, &rf); + /* + * Now that the CPU is offline, make sure we're welcome + * to new tasks once we come back up. + */ + balance_push_set(cpu, false); + calc_load_migrate(rq); update_max_interval(); nohz_balance_exit_idle(rq); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 12ada79d40f3..bb09988451a0 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -975,6 +975,7 @@ struct rq { unsigned long cpu_capacity_orig; struct callback_head *balance_callback; + unsigned char balance_push; unsigned char nohz_idle_balance; unsigned char idle_balance; diff --git a/kernel/signal.c b/kernel/signal.c index 5736c55aaa1a..5ad8566534e7 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2550,6 +2550,9 @@ bool get_signal(struct ksignal *ksig) struct signal_struct *signal = current->signal; int signr; + if (unlikely(current->task_works)) + task_work_run(); + /* * For non-generic architectures, check for TIF_NOTIFY_SIGNAL so * that the arch handlers don't all have to do it. If we get here @@ -3701,7 +3704,8 @@ static bool access_pidfd_pidns(struct pid *pid) return true; } -static int copy_siginfo_from_user_any(kernel_siginfo_t *kinfo, siginfo_t *info) +static int copy_siginfo_from_user_any(kernel_siginfo_t *kinfo, + siginfo_t __user *info) { #ifdef CONFIG_COMPAT /* diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 2efe1e206167..f25208e8df83 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -188,6 +188,7 @@ __smpboot_create_thread(struct smp_hotplug_thread *ht, unsigned int cpu) kfree(td); return PTR_ERR(tsk); } + kthread_set_per_cpu(tsk, cpu); /* * Park the thread so that it could start right on the CPU * when it is available. diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 7404d3831527..5247afd7f345 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -498,11 +498,11 @@ out: static void sync_hw_clock(struct work_struct *work); static DECLARE_WORK(sync_work, sync_hw_clock); static struct hrtimer sync_hrtimer; -#define SYNC_PERIOD_NS (11UL * 60 * NSEC_PER_SEC) +#define SYNC_PERIOD_NS (11ULL * 60 * NSEC_PER_SEC) static enum hrtimer_restart sync_timer_callback(struct hrtimer *timer) { - queue_work(system_power_efficient_wq, &sync_work); + queue_work(system_freezable_power_efficient_wq, &sync_work); return HRTIMER_NORESTART; } @@ -512,7 +512,7 @@ static void sched_sync_hw_clock(unsigned long offset_nsec, bool retry) ktime_t exp = ktime_set(ktime_get_real_seconds(), 0); if (retry) - exp = ktime_add_ns(exp, 2 * NSEC_PER_SEC - offset_nsec); + exp = ktime_add_ns(exp, 2ULL * NSEC_PER_SEC - offset_nsec); else exp = ktime_add_ns(exp, SYNC_PERIOD_NS - offset_nsec); @@ -668,7 +668,7 @@ void ntp_notify_cmos_timer(void) * just a pointless work scheduled. */ if (ntp_synced() && !hrtimer_is_queued(&sync_hrtimer)) - queue_work(system_power_efficient_wq, &sync_work); + queue_work(system_freezable_power_efficient_wq, &sync_work); } static void __init ntp_init_cmos_sync(void) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index a45cedda93a7..6aee5768c86f 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -991,8 +991,7 @@ EXPORT_SYMBOL_GPL(ktime_get_seconds); /** * ktime_get_real_seconds - Get the seconds portion of CLOCK_REALTIME * - * Returns the wall clock seconds since 1970. This replaces the - * get_seconds() interface which is not y2038 safe on 32bit systems. + * Returns the wall clock seconds since 1970. * * For 64bit systems the fast access to tk->xtime_sec is preserved. On * 32bit systems the access must be protected with the sequence diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 6c0018abe68a..764400260eb6 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -96,9 +96,6 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) { unsigned int ret; - if (in_nmi()) /* not supported yet */ - return 1; - cant_sleep(); if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) { diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 73edb9e4f354..29a6ebeebc9e 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -394,7 +394,6 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list) } if (t->ret_stack == NULL) { - atomic_set(&t->tracing_graph_pause, 0); atomic_set(&t->trace_overrun, 0); t->curr_ret_stack = -1; t->curr_ret_depth = -1; @@ -489,7 +488,6 @@ static DEFINE_PER_CPU(struct ftrace_ret_stack *, idle_ret_stack); static void graph_init_task(struct task_struct *t, struct ftrace_ret_stack *ret_stack) { - atomic_set(&t->tracing_graph_pause, 0); atomic_set(&t->trace_overrun, 0); t->ftrace_timestamp = 0; /* make curr_ret_stack visible before we add the ret_stack */ diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index b8a2d786b503..b5815a022ecc 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2745,7 +2745,7 @@ trace_event_buffer_lock_reserve(struct trace_buffer **current_rb, (entry = this_cpu_read(trace_buffered_event))) { /* Try to use the per cpu buffer first */ val = this_cpu_inc_return(trace_buffered_event_cnt); - if (val == 1) { + if ((len < (PAGE_SIZE - sizeof(*entry))) && val == 1) { trace_event_setup(entry, type, flags, pc); entry->array[0] = len; return entry; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index e9d28eeccb7e..d387b774ceeb 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1212,7 +1212,8 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt, mutex_lock(&event_mutex); list_for_each_entry(file, &tr->events, list) { call = file->event_call; - if (!trace_event_name(call) || !call->class || !call->class->reg) + if ((call->flags & TRACE_EVENT_FL_IGNORE_ENABLE) || + !trace_event_name(call) || !call->class || !call->class->reg) continue; if (system && strcmp(call->class->system, system->name) != 0) diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index d06aab4dcbb8..6756379b661f 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -562,6 +562,8 @@ static int __irqsoff_tracer_init(struct trace_array *tr) /* non overwrite screws up the latency tracers */ set_tracer_flag(tr, TRACE_ITER_OVERWRITE, 1); set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, 1); + /* without pause, we will produce garbage if another latency occurs */ + set_tracer_flag(tr, TRACE_ITER_PAUSE_ON_TRACE, 1); tr->max_latency = 0; irqsoff_trace = tr; @@ -583,11 +585,13 @@ static void __irqsoff_tracer_reset(struct trace_array *tr) { int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT; int overwrite_flag = save_flags & TRACE_ITER_OVERWRITE; + int pause_flag = save_flags & TRACE_ITER_PAUSE_ON_TRACE; stop_irqsoff_tracer(tr, is_graph(tr)); set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, lat_flag); set_tracer_flag(tr, TRACE_ITER_OVERWRITE, overwrite_flag); + set_tracer_flag(tr, TRACE_ITER_PAUSE_ON_TRACE, pause_flag); ftrace_reset_array_ops(tr); irqsoff_busy = false; diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index e6fba1798771..56c7fbff7bd7 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -221,9 +221,9 @@ bool trace_kprobe_on_func_entry(struct trace_event_call *call) { struct trace_kprobe *tk = trace_kprobe_primary_from_call(call); - return tk ? kprobe_on_func_entry(tk->rp.kp.addr, + return tk ? (kprobe_on_func_entry(tk->rp.kp.addr, tk->rp.kp.addr ? NULL : tk->rp.kp.symbol_name, - tk->rp.kp.addr ? 0 : tk->rp.kp.offset) : false; + tk->rp.kp.addr ? 0 : tk->rp.kp.offset) == 0) : false; } bool trace_kprobe_error_injectable(struct trace_event_call *call) @@ -828,9 +828,11 @@ static int trace_kprobe_create(int argc, const char *argv[]) } if (is_return) flags |= TPARG_FL_RETURN; - if (kprobe_on_func_entry(NULL, symbol, offset)) + ret = kprobe_on_func_entry(NULL, symbol, offset); + if (ret == 0) flags |= TPARG_FL_FENTRY; - if (offset && is_return && !(flags & TPARG_FL_FENTRY)) { + /* Defer the ENOENT case until register kprobe */ + if (ret == -EINVAL && is_return) { trace_probe_log_err(0, BAD_RETPROBE); goto parse_error; } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 9880b6c0e272..894bb885b40b 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1849,18 +1849,17 @@ static void worker_attach_to_pool(struct worker *worker, mutex_lock(&wq_pool_attach_mutex); /* - * set_cpus_allowed_ptr() will fail if the cpumask doesn't have any - * online CPUs. It'll be re-applied when any of the CPUs come up. - */ - set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask); - - /* * The wq_pool_attach_mutex ensures %POOL_DISASSOCIATED remains * stable across this function. See the comments above the flag * definition for details. */ if (pool->flags & POOL_DISASSOCIATED) worker->flags |= WORKER_UNBOUND; + else + kthread_set_per_cpu(worker->task, pool->cpu); + + if (worker->rescue_wq) + set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask); list_add_tail(&worker->node, &pool->workers); worker->pool = pool; @@ -1883,6 +1882,7 @@ static void worker_detach_from_pool(struct worker *worker) mutex_lock(&wq_pool_attach_mutex); + kthread_set_per_cpu(worker->task, -1); list_del(&worker->node); worker->pool = NULL; @@ -4919,8 +4919,10 @@ static void unbind_workers(int cpu) raw_spin_unlock_irq(&pool->lock); - for_each_pool_worker(worker, pool) - WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, cpu_active_mask) < 0); + for_each_pool_worker(worker, pool) { + kthread_set_per_cpu(worker->task, -1); + WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, cpu_possible_mask) < 0); + } mutex_unlock(&wq_pool_attach_mutex); @@ -4972,9 +4974,11 @@ static void rebind_workers(struct worker_pool *pool) * of all workers first and then clear UNBOUND. As we're called * from CPU_ONLINE, the following shouldn't fail. */ - for_each_pool_worker(worker, pool) + for_each_pool_worker(worker, pool) { + kthread_set_per_cpu(worker->task, pool->cpu); WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask) < 0); + } raw_spin_lock_irq(&pool->lock); |