diff options
Diffstat (limited to 'kernel')
37 files changed, 531 insertions, 304 deletions
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 8974b3755670..3c18260403dd 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -162,10 +162,14 @@ static void cpu_map_kthread_stop(struct work_struct *work) static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf) { + unsigned int hard_start_headroom; unsigned int frame_size; void *pkt_data_start; struct sk_buff *skb; + /* Part of headroom was reserved to xdpf */ + hard_start_headroom = sizeof(struct xdp_frame) + xdpf->headroom; + /* build_skb need to place skb_shared_info after SKB end, and * also want to know the memory "truesize". Thus, need to * know the memory frame size backing xdp_buff. @@ -183,15 +187,15 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, * is not at a fixed memory location, with mixed length * packets, which is bad for cache-line hotness. */ - frame_size = SKB_DATA_ALIGN(xdpf->len + xdpf->headroom) + + frame_size = SKB_DATA_ALIGN(xdpf->len + hard_start_headroom) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - pkt_data_start = xdpf->data - xdpf->headroom; + pkt_data_start = xdpf->data - hard_start_headroom; skb = build_skb(pkt_data_start, frame_size); if (!skb) return NULL; - skb_reserve(skb, xdpf->headroom); + skb_reserve(skb, hard_start_headroom); __skb_put(skb, xdpf->len); if (xdpf->metasize) skb_metadata_set(skb, xdpf->metasize); @@ -205,6 +209,9 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, * - RX ring dev queue index (skb_record_rx_queue) */ + /* Allow SKB to reuse area used by xdp_frame */ + xdp_scrub_frame(xdpf); + return skb; } diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 2ada5e21dfa6..4a8f390a2b82 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -554,19 +554,6 @@ struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type typ } EXPORT_SYMBOL(bpf_prog_get_type_path); -static void bpf_evict_inode(struct inode *inode) -{ - enum bpf_type type; - - truncate_inode_pages_final(&inode->i_data); - clear_inode(inode); - - if (S_ISLNK(inode->i_mode)) - kfree(inode->i_link); - if (!bpf_inode_type(inode, &type)) - bpf_any_put(inode->i_private, type); -} - /* * Display the mount options in /proc/mounts. */ @@ -579,11 +566,28 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root) return 0; } +static void bpf_destroy_inode_deferred(struct rcu_head *head) +{ + struct inode *inode = container_of(head, struct inode, i_rcu); + enum bpf_type type; + + if (S_ISLNK(inode->i_mode)) + kfree(inode->i_link); + if (!bpf_inode_type(inode, &type)) + bpf_any_put(inode->i_private, type); + free_inode_nonrcu(inode); +} + +static void bpf_destroy_inode(struct inode *inode) +{ + call_rcu(&inode->i_rcu, bpf_destroy_inode_deferred); +} + static const struct super_operations bpf_super_ops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, .show_options = bpf_show_options, - .evict_inode = bpf_evict_inode, + .destroy_inode = bpf_destroy_inode, }; enum { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 62f6bced3a3c..afca36f53c49 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -136,21 +136,29 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) void *bpf_map_area_alloc(size_t size, int numa_node) { - /* We definitely need __GFP_NORETRY, so OOM killer doesn't - * trigger under memory pressure as we really just want to - * fail instead. + /* We really just want to fail instead of triggering OOM killer + * under memory pressure, therefore we set __GFP_NORETRY to kmalloc, + * which is used for lower order allocation requests. + * + * It has been observed that higher order allocation requests done by + * vmalloc with __GFP_NORETRY being set might fail due to not trying + * to reclaim memory from the page cache, thus we set + * __GFP_RETRY_MAYFAIL to avoid such situations. */ - const gfp_t flags = __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO; + + const gfp_t flags = __GFP_NOWARN | __GFP_ZERO; void *area; if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { - area = kmalloc_node(size, GFP_USER | flags, numa_node); + area = kmalloc_node(size, GFP_USER | __GFP_NORETRY | flags, + numa_node); if (area != NULL) return area; } - return __vmalloc_node_flags_caller(size, numa_node, GFP_KERNEL | flags, - __builtin_return_address(0)); + return __vmalloc_node_flags_caller(size, numa_node, + GFP_KERNEL | __GFP_RETRY_MAYFAIL | + flags, __builtin_return_address(0)); } void bpf_map_area_free(void *area) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index ce166a002d16..09d5d972c9ff 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -212,7 +212,7 @@ struct bpf_call_arg_meta { int access_size; s64 msize_smax_value; u64 msize_umax_value; - int ptr_id; + int ref_obj_id; int func_id; }; @@ -346,35 +346,23 @@ static bool reg_type_may_be_null(enum bpf_reg_type type) type == PTR_TO_TCP_SOCK_OR_NULL; } -static bool type_is_refcounted(enum bpf_reg_type type) -{ - return type == PTR_TO_SOCKET; -} - -static bool type_is_refcounted_or_null(enum bpf_reg_type type) -{ - return type == PTR_TO_SOCKET || type == PTR_TO_SOCKET_OR_NULL; -} - -static bool reg_is_refcounted(const struct bpf_reg_state *reg) -{ - return type_is_refcounted(reg->type); -} - static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg) { return reg->type == PTR_TO_MAP_VALUE && map_value_has_spin_lock(reg->map_ptr); } -static bool reg_is_refcounted_or_null(const struct bpf_reg_state *reg) +static bool reg_type_may_be_refcounted_or_null(enum bpf_reg_type type) { - return type_is_refcounted_or_null(reg->type); + return type == PTR_TO_SOCKET || + type == PTR_TO_SOCKET_OR_NULL || + type == PTR_TO_TCP_SOCK || + type == PTR_TO_TCP_SOCK_OR_NULL; } -static bool arg_type_is_refcounted(enum bpf_arg_type type) +static bool arg_type_may_be_refcounted(enum bpf_arg_type type) { - return type == ARG_PTR_TO_SOCKET; + return type == ARG_PTR_TO_SOCK_COMMON; } /* Determine whether the function releases some resources allocated by another @@ -392,6 +380,12 @@ static bool is_acquire_function(enum bpf_func_id func_id) func_id == BPF_FUNC_sk_lookup_udp; } +static bool is_ptr_cast_function(enum bpf_func_id func_id) +{ + return func_id == BPF_FUNC_tcp_sock || + func_id == BPF_FUNC_sk_fullsock; +} + /* string representation of 'enum bpf_reg_type' */ static const char * const reg_type_str[] = { [NOT_INIT] = "?", @@ -466,6 +460,8 @@ static void print_verifier_state(struct bpf_verifier_env *env, verbose(env, ",call_%d", func(env, reg)->callsite); } else { verbose(env, "(id=%d", reg->id); + if (reg_type_may_be_refcounted_or_null(t)) + verbose(env, ",ref_obj_id=%d", reg->ref_obj_id); if (t != SCALAR_VALUE) verbose(env, ",off=%d", reg->off); if (type_is_pkt_pointer(t)) @@ -1901,8 +1897,9 @@ continue_func: } frame++; if (frame >= MAX_CALL_FRAMES) { - WARN_ONCE(1, "verifier bug. Call stack is too deep\n"); - return -EFAULT; + verbose(env, "the call stack of %d frames is too deep !\n", + frame); + return -E2BIG; } goto process_func; } @@ -2414,16 +2411,15 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, /* Any sk pointer can be ARG_PTR_TO_SOCK_COMMON */ if (!type_is_sk_pointer(type)) goto err_type; - } else if (arg_type == ARG_PTR_TO_SOCKET) { - expected_type = PTR_TO_SOCKET; - if (type != expected_type) - goto err_type; - if (meta->ptr_id || !reg->id) { - verbose(env, "verifier internal error: mismatched references meta=%d, reg=%d\n", - meta->ptr_id, reg->id); - return -EFAULT; + if (reg->ref_obj_id) { + if (meta->ref_obj_id) { + verbose(env, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n", + regno, reg->ref_obj_id, + meta->ref_obj_id); + return -EFAULT; + } + meta->ref_obj_id = reg->ref_obj_id; } - meta->ptr_id = reg->id; } else if (arg_type == ARG_PTR_TO_SPIN_LOCK) { if (meta->func_id == BPF_FUNC_spin_lock) { if (process_spin_lock(env, regno, true)) @@ -2740,32 +2736,38 @@ static bool check_arg_pair_ok(const struct bpf_func_proto *fn) return true; } -static bool check_refcount_ok(const struct bpf_func_proto *fn) +static bool check_refcount_ok(const struct bpf_func_proto *fn, int func_id) { int count = 0; - if (arg_type_is_refcounted(fn->arg1_type)) + if (arg_type_may_be_refcounted(fn->arg1_type)) count++; - if (arg_type_is_refcounted(fn->arg2_type)) + if (arg_type_may_be_refcounted(fn->arg2_type)) count++; - if (arg_type_is_refcounted(fn->arg3_type)) + if (arg_type_may_be_refcounted(fn->arg3_type)) count++; - if (arg_type_is_refcounted(fn->arg4_type)) + if (arg_type_may_be_refcounted(fn->arg4_type)) count++; - if (arg_type_is_refcounted(fn->arg5_type)) + if (arg_type_may_be_refcounted(fn->arg5_type)) count++; + /* A reference acquiring function cannot acquire + * another refcounted ptr. + */ + if (is_acquire_function(func_id) && count) + return false; + /* We only support one arg being unreferenced at the moment, * which is sufficient for the helper functions we have right now. */ return count <= 1; } -static int check_func_proto(const struct bpf_func_proto *fn) +static int check_func_proto(const struct bpf_func_proto *fn, int func_id) { return check_raw_mode_ok(fn) && check_arg_pair_ok(fn) && - check_refcount_ok(fn) ? 0 : -EINVAL; + check_refcount_ok(fn, func_id) ? 0 : -EINVAL; } /* Packet data might have moved, any old PTR_TO_PACKET[_META,_END] @@ -2799,19 +2801,20 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) } static void release_reg_references(struct bpf_verifier_env *env, - struct bpf_func_state *state, int id) + struct bpf_func_state *state, + int ref_obj_id) { struct bpf_reg_state *regs = state->regs, *reg; int i; for (i = 0; i < MAX_BPF_REG; i++) - if (regs[i].id == id) + if (regs[i].ref_obj_id == ref_obj_id) mark_reg_unknown(env, regs, i); bpf_for_each_spilled_reg(i, state, reg) { if (!reg) continue; - if (reg_is_refcounted(reg) && reg->id == id) + if (reg->ref_obj_id == ref_obj_id) __mark_reg_unknown(reg); } } @@ -2820,15 +2823,20 @@ static void release_reg_references(struct bpf_verifier_env *env, * resources. Identify all copies of the same pointer and clear the reference. */ static int release_reference(struct bpf_verifier_env *env, - struct bpf_call_arg_meta *meta) + int ref_obj_id) { struct bpf_verifier_state *vstate = env->cur_state; + int err; int i; + err = release_reference_state(cur_func(env), ref_obj_id); + if (err) + return err; + for (i = 0; i <= vstate->curframe; i++) - release_reg_references(env, vstate->frame[i], meta->ptr_id); + release_reg_references(env, vstate->frame[i], ref_obj_id); - return release_reference_state(cur_func(env), meta->ptr_id); + return 0; } static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, @@ -3047,7 +3055,7 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn memset(&meta, 0, sizeof(meta)); meta.pkt_access = fn->pkt_access; - err = check_func_proto(fn); + err = check_func_proto(fn, func_id); if (err) { verbose(env, "kernel subsystem misconfigured func %s#%d\n", func_id_name(func_id), func_id); @@ -3093,7 +3101,7 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn return err; } } else if (is_release_function(func_id)) { - err = release_reference(env, &meta); + err = release_reference(env, meta.ref_obj_id); if (err) { verbose(env, "func %s#%d reference has not been acquired before\n", func_id_name(func_id), func_id); @@ -3154,8 +3162,10 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn if (id < 0) return id; - /* For release_reference() */ + /* For mark_ptr_or_null_reg() */ regs[BPF_REG_0].id = id; + /* For release_reference() */ + regs[BPF_REG_0].ref_obj_id = id; } else { /* For mark_ptr_or_null_reg() */ regs[BPF_REG_0].id = ++env->id_gen; @@ -3170,6 +3180,10 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn return -EINVAL; } + if (is_ptr_cast_function(func_id)) + /* For release_reference() */ + regs[BPF_REG_0].ref_obj_id = meta.ref_obj_id; + do_refine_retval_range(regs, fn->ret_type, func_id, &meta); err = check_map_func_compatibility(env, meta.map_ptr, func_id); @@ -3368,7 +3382,7 @@ do_sim: *dst_reg = *ptr_reg; } ret = push_stack(env, env->insn_idx + 1, env->insn_idx, true); - if (!ptr_is_dst_reg) + if (!ptr_is_dst_reg && ret) *dst_reg = tmp; return !ret ? -EFAULT : 0; } @@ -4124,15 +4138,35 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) return 0; } +static void __find_good_pkt_pointers(struct bpf_func_state *state, + struct bpf_reg_state *dst_reg, + enum bpf_reg_type type, u16 new_range) +{ + struct bpf_reg_state *reg; + int i; + + for (i = 0; i < MAX_BPF_REG; i++) { + reg = &state->regs[i]; + if (reg->type == type && reg->id == dst_reg->id) + /* keep the maximum range already checked */ + reg->range = max(reg->range, new_range); + } + + bpf_for_each_spilled_reg(i, state, reg) { + if (!reg) + continue; + if (reg->type == type && reg->id == dst_reg->id) + reg->range = max(reg->range, new_range); + } +} + static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, struct bpf_reg_state *dst_reg, enum bpf_reg_type type, bool range_right_open) { - struct bpf_func_state *state = vstate->frame[vstate->curframe]; - struct bpf_reg_state *regs = state->regs, *reg; u16 new_range; - int i, j; + int i; if (dst_reg->off < 0 || (dst_reg->off == 0 && range_right_open)) @@ -4197,20 +4231,9 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, * the range won't allow anything. * dst_reg->off is known < MAX_PACKET_OFF, therefore it fits in a u16. */ - for (i = 0; i < MAX_BPF_REG; i++) - if (regs[i].type == type && regs[i].id == dst_reg->id) - /* keep the maximum range already checked */ - regs[i].range = max(regs[i].range, new_range); - - for (j = 0; j <= vstate->curframe; j++) { - state = vstate->frame[j]; - bpf_for_each_spilled_reg(i, state, reg) { - if (!reg) - continue; - if (reg->type == type && reg->id == dst_reg->id) - reg->range = max(reg->range, new_range); - } - } + for (i = 0; i <= vstate->curframe; i++) + __find_good_pkt_pointers(vstate->frame[i], dst_reg, type, + new_range); } /* compute branch direction of the expression "if (reg opcode val) goto target;" @@ -4665,17 +4688,41 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state, } else if (reg->type == PTR_TO_TCP_SOCK_OR_NULL) { reg->type = PTR_TO_TCP_SOCK; } - if (is_null || !(reg_is_refcounted(reg) || - reg_may_point_to_spin_lock(reg))) { - /* We don't need id from this point onwards anymore, - * thus we should better reset it, so that state - * pruning has chances to take effect. + if (is_null) { + /* We don't need id and ref_obj_id from this point + * onwards anymore, thus we should better reset it, + * so that state pruning has chances to take effect. + */ + reg->id = 0; + reg->ref_obj_id = 0; + } else if (!reg_may_point_to_spin_lock(reg)) { + /* For not-NULL ptr, reg->ref_obj_id will be reset + * in release_reg_references(). + * + * reg->id is still used by spin_lock ptr. Other + * than spin_lock ptr type, reg->id can be reset. */ reg->id = 0; } } } +static void __mark_ptr_or_null_regs(struct bpf_func_state *state, u32 id, + bool is_null) +{ + struct bpf_reg_state *reg; + int i; + + for (i = 0; i < MAX_BPF_REG; i++) + mark_ptr_or_null_reg(state, &state->regs[i], id, is_null); + + bpf_for_each_spilled_reg(i, state, reg) { + if (!reg) + continue; + mark_ptr_or_null_reg(state, reg, id, is_null); + } +} + /* The logic is similar to find_good_pkt_pointers(), both could eventually * be folded together at some point. */ @@ -4683,24 +4730,20 @@ static void mark_ptr_or_null_regs(struct bpf_verifier_state *vstate, u32 regno, bool is_null) { struct bpf_func_state *state = vstate->frame[vstate->curframe]; - struct bpf_reg_state *reg, *regs = state->regs; + struct bpf_reg_state *regs = state->regs; + u32 ref_obj_id = regs[regno].ref_obj_id; u32 id = regs[regno].id; - int i, j; - - if (reg_is_refcounted_or_null(®s[regno]) && is_null) - release_reference_state(state, id); + int i; - for (i = 0; i < MAX_BPF_REG; i++) - mark_ptr_or_null_reg(state, ®s[i], id, is_null); + if (ref_obj_id && ref_obj_id == id && is_null) + /* regs[regno] is in the " == NULL" branch. + * No one could have freed the reference state before + * doing the NULL check. + */ + WARN_ON_ONCE(release_reference_state(state, id)); - for (j = 0; j <= vstate->curframe; j++) { - state = vstate->frame[j]; - bpf_for_each_spilled_reg(i, state, reg) { - if (!reg) - continue; - mark_ptr_or_null_reg(state, reg, id, is_null); - } - } + for (i = 0; i <= vstate->curframe; i++) + __mark_ptr_or_null_regs(vstate->frame[i], id, is_null); } static bool try_match_pkt_pointers(const struct bpf_insn *insn, @@ -6052,15 +6095,17 @@ static int propagate_liveness(struct bpf_verifier_env *env, } /* Propagate read liveness of registers... */ BUILD_BUG_ON(BPF_REG_FP + 1 != MAX_BPF_REG); - /* We don't need to worry about FP liveness because it's read-only */ - for (i = 0; i < BPF_REG_FP; i++) { - if (vparent->frame[vparent->curframe]->regs[i].live & REG_LIVE_READ) - continue; - if (vstate->frame[vstate->curframe]->regs[i].live & REG_LIVE_READ) { - err = mark_reg_read(env, &vstate->frame[vstate->curframe]->regs[i], - &vparent->frame[vstate->curframe]->regs[i]); - if (err) - return err; + for (frame = 0; frame <= vstate->curframe; frame++) { + /* We don't need to worry about FP liveness, it's read-only */ + for (i = frame < vstate->curframe ? BPF_REG_6 : 0; i < BPF_REG_FP; i++) { + if (vparent->frame[frame]->regs[i].live & REG_LIVE_READ) + continue; + if (vstate->frame[frame]->regs[i].live & REG_LIVE_READ) { + err = mark_reg_read(env, &vstate->frame[frame]->regs[i], + &vparent->frame[frame]->regs[i]); + if (err) + return err; + } } } diff --git a/kernel/cpu.c b/kernel/cpu.c index 025f419d16f6..6754f3ecfd94 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -564,6 +564,20 @@ static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st) cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); } +static inline bool can_rollback_cpu(struct cpuhp_cpu_state *st) +{ + if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) + return true; + /* + * When CPU hotplug is disabled, then taking the CPU down is not + * possible because takedown_cpu() and the architecture and + * subsystem specific mechanisms are not available. So the CPU + * which would be completely unplugged again needs to stay around + * in the current state. + */ + return st->state <= CPUHP_BRINGUP_CPU; +} + static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { @@ -574,8 +588,10 @@ static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, st->state++; ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); if (ret) { - st->target = prev_state; - undo_cpu_up(cpu, st); + if (can_rollback_cpu(st)) { + st->target = prev_state; + undo_cpu_up(cpu, st); + } break; } } diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index 45d51e8e26f6..a218e43cc382 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -706,7 +706,7 @@ static struct dma_debug_entry *dma_entry_alloc(void) #ifdef CONFIG_STACKTRACE entry->stacktrace.max_entries = DMA_DEBUG_STACKTRACE_ENTRIES; entry->stacktrace.entries = entry->st_entries; - entry->stacktrace.skip = 2; + entry->stacktrace.skip = 1; save_stack_trace(&entry->stacktrace); #endif diff --git a/kernel/events/core.c b/kernel/events/core.c index 1032a16bd186..dc7dead2d2cc 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2009,8 +2009,8 @@ event_sched_out(struct perf_event *event, event->pmu->del(event, 0); event->oncpu = -1; - if (event->pending_disable) { - event->pending_disable = 0; + if (READ_ONCE(event->pending_disable) >= 0) { + WRITE_ONCE(event->pending_disable, -1); state = PERF_EVENT_STATE_OFF; } perf_event_set_state(event, state); @@ -2198,7 +2198,8 @@ EXPORT_SYMBOL_GPL(perf_event_disable); void perf_event_disable_inatomic(struct perf_event *event) { - event->pending_disable = 1; + WRITE_ONCE(event->pending_disable, smp_processor_id()); + /* can fail, see perf_pending_event_disable() */ irq_work_queue(&event->pending); } @@ -5810,10 +5811,45 @@ void perf_event_wakeup(struct perf_event *event) } } +static void perf_pending_event_disable(struct perf_event *event) +{ + int cpu = READ_ONCE(event->pending_disable); + + if (cpu < 0) + return; + + if (cpu == smp_processor_id()) { + WRITE_ONCE(event->pending_disable, -1); + perf_event_disable_local(event); + return; + } + + /* + * CPU-A CPU-B + * + * perf_event_disable_inatomic() + * @pending_disable = CPU-A; + * irq_work_queue(); + * + * sched-out + * @pending_disable = -1; + * + * sched-in + * perf_event_disable_inatomic() + * @pending_disable = CPU-B; + * irq_work_queue(); // FAILS + * + * irq_work_run() + * perf_pending_event() + * + * But the event runs on CPU-B and wants disabling there. + */ + irq_work_queue_on(&event->pending, cpu); +} + static void perf_pending_event(struct irq_work *entry) { - struct perf_event *event = container_of(entry, - struct perf_event, pending); + struct perf_event *event = container_of(entry, struct perf_event, pending); int rctx; rctx = perf_swevent_get_recursion_context(); @@ -5822,10 +5858,7 @@ static void perf_pending_event(struct irq_work *entry) * and we won't recurse 'further'. */ - if (event->pending_disable) { - event->pending_disable = 0; - perf_event_disable_local(event); - } + perf_pending_event_disable(event); if (event->pending_wakeup) { event->pending_wakeup = 0; @@ -7189,6 +7222,7 @@ static void perf_event_mmap_output(struct perf_event *event, struct perf_output_handle handle; struct perf_sample_data sample; int size = mmap_event->event_id.header.size; + u32 type = mmap_event->event_id.header.type; int ret; if (!perf_event_mmap_match(event, data)) @@ -7232,6 +7266,7 @@ static void perf_event_mmap_output(struct perf_event *event, perf_output_end(&handle); out: mmap_event->event_id.header.size = size; + mmap_event->event_id.header.type = type; } static void perf_event_mmap_event(struct perf_mmap_event *mmap_event) @@ -9042,26 +9077,29 @@ static void perf_event_addr_filters_apply(struct perf_event *event) if (task == TASK_TOMBSTONE) return; - if (!ifh->nr_file_filters) - return; - - mm = get_task_mm(event->ctx->task); - if (!mm) - goto restart; + if (ifh->nr_file_filters) { + mm = get_task_mm(event->ctx->task); + if (!mm) + goto restart; - down_read(&mm->mmap_sem); + down_read(&mm->mmap_sem); + } raw_spin_lock_irqsave(&ifh->lock, flags); list_for_each_entry(filter, &ifh->list, entry) { - event->addr_filter_ranges[count].start = 0; - event->addr_filter_ranges[count].size = 0; + if (filter->path.dentry) { + /* + * Adjust base offset if the filter is associated to a + * binary that needs to be mapped: + */ + event->addr_filter_ranges[count].start = 0; + event->addr_filter_ranges[count].size = 0; - /* - * Adjust base offset if the filter is associated to a binary - * that needs to be mapped: - */ - if (filter->path.dentry) perf_addr_filter_apply(filter, mm, &event->addr_filter_ranges[count]); + } else { + event->addr_filter_ranges[count].start = filter->offset; + event->addr_filter_ranges[count].size = filter->size; + } count++; } @@ -9069,9 +9107,11 @@ static void perf_event_addr_filters_apply(struct perf_event *event) event->addr_filters_gen++; raw_spin_unlock_irqrestore(&ifh->lock, flags); - up_read(&mm->mmap_sem); + if (ifh->nr_file_filters) { + up_read(&mm->mmap_sem); - mmput(mm); + mmput(mm); + } restart: perf_event_stop(event, 1); @@ -10234,6 +10274,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, init_waitqueue_head(&event->waitq); + event->pending_disable = -1; init_irq_work(&event->pending, perf_pending_event); mutex_init(&event->mmap_mutex); diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index a4047321d7d8..674b35383491 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -392,7 +392,7 @@ void *perf_aux_output_begin(struct perf_output_handle *handle, * store that will be enabled on successful return */ if (!handle->size) { /* A, matches D */ - event->pending_disable = 1; + event->pending_disable = smp_processor_id(); perf_output_wakeup(handle); local_set(&rb->aux_nest, 0); goto err_put; @@ -455,24 +455,21 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) rb->aux_head += size; } - if (size || handle->aux_flags) { - /* - * Only send RECORD_AUX if we have something useful to communicate - * - * Note: the OVERWRITE records by themselves are not considered - * useful, as they don't communicate any *new* information, - * aside from the short-lived offset, that becomes history at - * the next event sched-in and therefore isn't useful. - * The userspace that needs to copy out AUX data in overwrite - * mode should know to use user_page::aux_head for the actual - * offset. So, from now on we don't output AUX records that - * have *only* OVERWRITE flag set. - */ - - if (handle->aux_flags & ~(u64)PERF_AUX_FLAG_OVERWRITE) - perf_event_aux_event(handle->event, aux_head, size, - handle->aux_flags); - } + /* + * Only send RECORD_AUX if we have something useful to communicate + * + * Note: the OVERWRITE records by themselves are not considered + * useful, as they don't communicate any *new* information, + * aside from the short-lived offset, that becomes history at + * the next event sched-in and therefore isn't useful. + * The userspace that needs to copy out AUX data in overwrite + * mode should know to use user_page::aux_head for the actual + * offset. So, from now on we don't output AUX records that + * have *only* OVERWRITE flag set. + */ + if (size || (handle->aux_flags & ~(u64)PERF_AUX_FLAG_OVERWRITE)) + perf_event_aux_event(handle->event, aux_head, size, + handle->aux_flags); rb->user_page->aux_head = rb->aux_head; if (rb_need_aux_wakeup(rb)) @@ -480,7 +477,7 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) if (wakeup) { if (handle->aux_flags & PERF_AUX_FLAG_TRUNCATED) - handle->event->pending_disable = 1; + handle->event->pending_disable = smp_processor_id(); perf_output_wakeup(handle); } @@ -613,8 +610,7 @@ int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event, * PMU requests more than one contiguous chunks of memory * for SW double buffering */ - if ((event->pmu->capabilities & PERF_PMU_CAP_AUX_SW_DOUBLEBUF) && - !overwrite) { + if (!overwrite) { if (!max_order) return -EINVAL; diff --git a/kernel/futex.c b/kernel/futex.c index c3b73b0311bc..9e40cf7be606 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -3436,6 +3436,10 @@ static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int p { u32 uval, uninitialized_var(nval), mval; + /* Futex address must be 32bit aligned */ + if ((((unsigned long)uaddr) % sizeof(*uaddr)) != 0) + return -1; + retry: if (get_user(uval, uaddr)) return -1; diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 3faef4a77f71..51128bea3846 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -1449,6 +1449,10 @@ int irq_chip_set_vcpu_affinity_parent(struct irq_data *data, void *vcpu_info) int irq_chip_set_wake_parent(struct irq_data *data, unsigned int on) { data = data->parent_data; + + if (data->chip->flags & IRQCHIP_SKIP_SET_WAKE) + return 0; + if (data->chip->irq_set_wake) return data->chip->irq_set_wake(data, on); diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c index 5d5378ea0afe..f808c6a97dcc 100644 --- a/kernel/irq/devres.c +++ b/kernel/irq/devres.c @@ -84,8 +84,6 @@ EXPORT_SYMBOL(devm_request_threaded_irq); * @dev: device to request interrupt for * @irq: Interrupt line to allocate * @handler: Function to be called when the IRQ occurs - * @thread_fn: function to be called in a threaded interrupt context. NULL - * for devices which handle everything in @handler * @irqflags: Interrupt type flags * @devname: An ascii name for the claiming device, dev_name(dev) if NULL * @dev_id: A cookie passed back to the handler function diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 13539e12cd80..9f8a709337cf 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -558,6 +558,7 @@ int __init early_irq_init(void) alloc_masks(&desc[i], node); raw_spin_lock_init(&desc[i].lock); lockdep_set_class(&desc[i].lock, &irq_desc_lock_class); + mutex_init(&desc[i].request_mutex); desc_set_defaults(i, &desc[i], node, NULL, NULL); } return arch_early_irq_init(); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 9ec34a2a6638..1401afa0d58a 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -196,6 +196,7 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, case IRQ_SET_MASK_OK: case IRQ_SET_MASK_OK_DONE: cpumask_copy(desc->irq_common_data.affinity, mask); + /* fall through */ case IRQ_SET_MASK_OK_NOCOPY: irq_validate_effective_affinity(data); irq_set_thread_affinity(desc); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index c83e54727131..b1ea30a5540e 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -709,7 +709,6 @@ static void unoptimize_kprobe(struct kprobe *p, bool force) static int reuse_unused_kprobe(struct kprobe *ap) { struct optimized_kprobe *op; - int ret; /* * Unused kprobe MUST be on the way of delayed unoptimizing (means @@ -720,9 +719,8 @@ static int reuse_unused_kprobe(struct kprobe *ap) /* Enable the probe again */ ap->flags &= ~KPROBE_FLAG_DISABLED; /* Optimize it again (remove from op->list) */ - ret = kprobe_optready(ap); - if (ret) - return ret; + if (!kprobe_optready(ap)) + return -EINVAL; optimize_kprobe(ap); return 0; diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 34cdcbedda49..e221be724fe8 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -4689,8 +4689,8 @@ static void free_zapped_rcu(struct rcu_head *ch) return; raw_local_irq_save(flags); - if (!graph_lock()) - goto out_irq; + arch_spin_lock(&lockdep_lock); + current->lockdep_recursion = 1; /* closed head */ pf = delayed_free.pf + (delayed_free.index ^ 1); @@ -4702,8 +4702,8 @@ static void free_zapped_rcu(struct rcu_head *ch) */ call_rcu_zapped(delayed_free.pf + delayed_free.index); - graph_unlock(); -out_irq: + current->lockdep_recursion = 0; + arch_spin_unlock(&lockdep_lock); raw_local_irq_restore(flags); } @@ -4744,21 +4744,17 @@ static void lockdep_free_key_range_reg(void *start, unsigned long size) { struct pending_free *pf; unsigned long flags; - int locked; init_data_structures_once(); raw_local_irq_save(flags); - locked = graph_lock(); - if (!locked) - goto out_irq; - + arch_spin_lock(&lockdep_lock); + current->lockdep_recursion = 1; pf = get_pending_free(); __lockdep_free_key_range(pf, start, size); call_rcu_zapped(pf); - - graph_unlock(); -out_irq: + current->lockdep_recursion = 0; + arch_spin_unlock(&lockdep_lock); raw_local_irq_restore(flags); /* diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 771e93f9c43f..6f357f4fc859 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -29,6 +29,7 @@ #include <linux/hw_breakpoint.h> #include <linux/cn_proc.h> #include <linux/compat.h> +#include <linux/sched/signal.h> /* * Access another process' address space via ptrace. @@ -924,18 +925,26 @@ int ptrace_request(struct task_struct *child, long request, ret = ptrace_setsiginfo(child, &siginfo); break; - case PTRACE_GETSIGMASK: + case PTRACE_GETSIGMASK: { + sigset_t *mask; + if (addr != sizeof(sigset_t)) { ret = -EINVAL; break; } - if (copy_to_user(datavp, &child->blocked, sizeof(sigset_t))) + if (test_tsk_restore_sigmask(child)) + mask = &child->saved_sigmask; + else + mask = &child->blocked; + + if (copy_to_user(datavp, mask, sizeof(sigset_t))) ret = -EFAULT; else ret = 0; break; + } case PTRACE_SETSIGMASK: { sigset_t new_set; @@ -961,6 +970,8 @@ int ptrace_request(struct task_struct *child, long request, child->blocked = new_set; spin_unlock_irq(&child->sighand->siglock); + clear_tsk_restore_sigmask(child); + ret = 0; break; } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index ead464a0f2e5..4778c48a7fda 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6998,7 +6998,7 @@ static int __maybe_unused cpu_period_quota_parse(char *buf, { char tok[21]; /* U64_MAX */ - if (!sscanf(buf, "%s %llu", tok, periodp)) + if (sscanf(buf, "%20s %llu", tok, periodp) < 1) return -EINVAL; *periodp *= NSEC_PER_USEC; diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 2efe629425be..3638d2377e3c 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -48,10 +48,10 @@ struct sugov_cpu { bool iowait_boost_pending; unsigned int iowait_boost; - unsigned int iowait_boost_max; u64 last_update; unsigned long bw_dl; + unsigned long min; unsigned long max; /* The field below is for single-CPU policies only: */ @@ -303,8 +303,7 @@ static bool sugov_iowait_reset(struct sugov_cpu *sg_cpu, u64 time, if (delta_ns <= TICK_NSEC) return false; - sg_cpu->iowait_boost = set_iowait_boost - ? sg_cpu->sg_policy->policy->min : 0; + sg_cpu->iowait_boost = set_iowait_boost ? sg_cpu->min : 0; sg_cpu->iowait_boost_pending = set_iowait_boost; return true; @@ -344,14 +343,13 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time, /* Double the boost at each request */ if (sg_cpu->iowait_boost) { - sg_cpu->iowait_boost <<= 1; - if (sg_cpu->iowait_boost > sg_cpu->iowait_boost_max) - sg_cpu->iowait_boost = sg_cpu->iowait_boost_max; + sg_cpu->iowait_boost = + min_t(unsigned int, sg_cpu->iowait_boost << 1, SCHED_CAPACITY_SCALE); return; } /* First wakeup after IO: start with minimum boost */ - sg_cpu->iowait_boost = sg_cpu->sg_policy->policy->min; + sg_cpu->iowait_boost = sg_cpu->min; } /** @@ -373,47 +371,38 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time, * This mechanism is designed to boost high frequently IO waiting tasks, while * being more conservative on tasks which does sporadic IO operations. */ -static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time, - unsigned long *util, unsigned long *max) +static unsigned long sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time, + unsigned long util, unsigned long max) { - unsigned int boost_util, boost_max; + unsigned long boost; /* No boost currently required */ if (!sg_cpu->iowait_boost) - return; + return util; /* Reset boost if the CPU appears to have been idle enough */ if (sugov_iowait_reset(sg_cpu, time, false)) - return; + return util; - /* - * An IO waiting task has just woken up: - * allow to further double the boost value - */ - if (sg_cpu->iowait_boost_pending) { - sg_cpu->iowait_boost_pending = false; - } else { + if (!sg_cpu->iowait_boost_pending) { /* - * Otherwise: reduce the boost value and disable it when we - * reach the minimum. + * No boost pending; reduce the boost value. */ sg_cpu->iowait_boost >>= 1; - if (sg_cpu->iowait_boost < sg_cpu->sg_policy->policy->min) { + if (sg_cpu->iowait_boost < sg_cpu->min) { sg_cpu->iowait_boost = 0; - return; + return util; } } + sg_cpu->iowait_boost_pending = false; + /* - * Apply the current boost value: a CPU is boosted only if its current - * utilization is smaller then the current IO boost level. + * @util is already in capacity scale; convert iowait_boost + * into the same scale so we can compare. */ - boost_util = sg_cpu->iowait_boost; - boost_max = sg_cpu->iowait_boost_max; - if (*util * boost_max < *max * boost_util) { - *util = boost_util; - *max = boost_max; - } + boost = (sg_cpu->iowait_boost * max) >> SCHED_CAPACITY_SHIFT; + return max(boost, util); } #ifdef CONFIG_NO_HZ_COMMON @@ -460,7 +449,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, util = sugov_get_util(sg_cpu); max = sg_cpu->max; - sugov_iowait_apply(sg_cpu, time, &util, &max); + util = sugov_iowait_apply(sg_cpu, time, util, max); next_f = get_next_freq(sg_policy, util, max); /* * Do not reduce the frequency if the CPU has not been idle @@ -500,7 +489,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time) j_util = sugov_get_util(j_sg_cpu); j_max = j_sg_cpu->max; - sugov_iowait_apply(j_sg_cpu, time, &j_util, &j_max); + j_util = sugov_iowait_apply(j_sg_cpu, time, j_util, j_max); if (j_util * max > j_max * util) { util = j_util; @@ -782,6 +771,7 @@ out: return 0; fail: + kobject_put(&tunables->attr_set.kobj); policy->governor_data = NULL; sugov_tunables_free(tunables); @@ -837,7 +827,9 @@ static int sugov_start(struct cpufreq_policy *policy) memset(sg_cpu, 0, sizeof(*sg_cpu)); sg_cpu->cpu = cpu; sg_cpu->sg_policy = sg_policy; - sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq; + sg_cpu->min = + (SCHED_CAPACITY_SCALE * policy->cpuinfo.min_freq) / + policy->cpuinfo.max_freq; } for_each_cpu(cpu, policy->cpus) { diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 6a73e41a2016..43901fa3f269 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -252,7 +252,6 @@ static void task_non_contending(struct task_struct *p) if (dl_entity_is_special(dl_se)) return; - WARN_ON(hrtimer_active(&dl_se->inactive_timer)); WARN_ON(dl_se->dl_non_contending); zerolag_time = dl_se->deadline - @@ -269,7 +268,7 @@ static void task_non_contending(struct task_struct *p) * If the "0-lag time" already passed, decrease the active * utilization now, instead of starting a timer */ - if (zerolag_time < 0) { + if ((zerolag_time < 0) || hrtimer_active(&dl_se->inactive_timer)) { if (dl_task(p)) sub_running_bw(dl_se, dl_rq); if (!dl_task(p) || p->state == TASK_DEAD) { diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index ea74d43924b2..35f3ea375084 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2007,6 +2007,10 @@ static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period) if (p->last_task_numa_placement) { delta = runtime - p->last_sum_exec_runtime; *period = now - p->last_task_numa_placement; + + /* Avoid time going backwards, prevent potential divide error: */ + if (unlikely((s64)*period < 0)) + *period = 0; } else { delta = p->se.avg.load_sum; *period = LOAD_AVG_MAX; @@ -4885,6 +4889,8 @@ static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer) return HRTIMER_NORESTART; } +extern const u64 max_cfs_quota_period; + static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) { struct cfs_bandwidth *cfs_b = @@ -4892,6 +4898,7 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) unsigned long flags; int overrun; int idle = 0; + int count = 0; raw_spin_lock_irqsave(&cfs_b->lock, flags); for (;;) { @@ -4899,6 +4906,28 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) if (!overrun) break; + if (++count > 3) { + u64 new, old = ktime_to_ns(cfs_b->period); + + new = (old * 147) / 128; /* ~115% */ + new = min(new, max_cfs_quota_period); + + cfs_b->period = ns_to_ktime(new); + + /* since max is 1s, this is limited to 1e9^2, which fits in u64 */ + cfs_b->quota *= new; + cfs_b->quota = div64_u64(cfs_b->quota, old); + + pr_warn_ratelimited( + "cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us %lld, cfs_quota_us = %lld)\n", + smp_processor_id(), + div_u64(new, NSEC_PER_USEC), + div_u64(cfs_b->quota, NSEC_PER_USEC)); + + /* reset count so we don't come right back in here */ + count = 0; + } + idle = do_sched_cfs_period_timer(cfs_b, overrun, flags); } if (idle) @@ -7784,10 +7813,10 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq) if (cfs_rq->last_h_load_update == now) return; - cfs_rq->h_load_next = NULL; + WRITE_ONCE(cfs_rq->h_load_next, NULL); for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); - cfs_rq->h_load_next = se; + WRITE_ONCE(cfs_rq->h_load_next, se); if (cfs_rq->last_h_load_update == now) break; } @@ -7797,7 +7826,7 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq) cfs_rq->last_h_load_update = now; } - while ((se = cfs_rq->h_load_next) != NULL) { + while ((se = READ_ONCE(cfs_rq->h_load_next)) != NULL) { load = cfs_rq->h_load; load = div64_ul(load * se->avg.load_avg, cfs_rq_load_avg(cfs_rq) + 1); @@ -8060,6 +8089,18 @@ check_cpu_capacity(struct rq *rq, struct sched_domain *sd) } /* + * Check whether a rq has a misfit task and if it looks like we can actually + * help that task: we can migrate the task to a CPU of higher capacity, or + * the task's current CPU is heavily pressured. + */ +static inline int check_misfit_status(struct rq *rq, struct sched_domain *sd) +{ + return rq->misfit_task_load && + (rq->cpu_capacity_orig < rq->rd->max_cpu_capacity || + check_cpu_capacity(rq, sd)); +} + +/* * Group imbalance indicates (and tries to solve) the problem where balancing * groups is inadequate due to ->cpus_allowed constraints. * @@ -9586,35 +9627,21 @@ static void nohz_balancer_kick(struct rq *rq) if (time_before(now, nohz.next_balance)) goto out; - if (rq->nr_running >= 2 || rq->misfit_task_load) { + if (rq->nr_running >= 2) { flags = NOHZ_KICK_MASK; goto out; } rcu_read_lock(); - sds = rcu_dereference(per_cpu(sd_llc_shared, cpu)); - if (sds) { - /* - * If there is an imbalance between LLC domains (IOW we could - * increase the overall cache use), we need some less-loaded LLC - * domain to pull some load. Likewise, we may need to spread - * load within the current LLC domain (e.g. packed SMT cores but - * other CPUs are idle). We can't really know from here how busy - * the others are - so just get a nohz balance going if it looks - * like this LLC domain has tasks we could move. - */ - nr_busy = atomic_read(&sds->nr_busy_cpus); - if (nr_busy > 1) { - flags = NOHZ_KICK_MASK; - goto unlock; - } - - } sd = rcu_dereference(rq->sd); if (sd) { - if ((rq->cfs.h_nr_running >= 1) && - check_cpu_capacity(rq, sd)) { + /* + * If there's a CFS task and the current CPU has reduced + * capacity; kick the ILB to see if there's a better CPU to run + * on. + */ + if (rq->cfs.h_nr_running >= 1 && check_cpu_capacity(rq, sd)) { flags = NOHZ_KICK_MASK; goto unlock; } @@ -9622,6 +9649,11 @@ static void nohz_balancer_kick(struct rq *rq) sd = rcu_dereference(per_cpu(sd_asym_packing, cpu)); if (sd) { + /* + * When ASYM_PACKING; see if there's a more preferred CPU + * currently idle; in which case, kick the ILB to move tasks + * around. + */ for_each_cpu_and(i, sched_domain_span(sd), nohz.idle_cpus_mask) { if (sched_asym_prefer(i, cpu)) { flags = NOHZ_KICK_MASK; @@ -9629,6 +9661,45 @@ static void nohz_balancer_kick(struct rq *rq) } } } + + sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, cpu)); + if (sd) { + /* + * When ASYM_CPUCAPACITY; see if there's a higher capacity CPU + * to run the misfit task on. + */ + if (check_misfit_status(rq, sd)) { + flags = NOHZ_KICK_MASK; + goto unlock; + } + + /* + * For asymmetric systems, we do not want to nicely balance + * cache use, instead we want to embrace asymmetry and only + * ensure tasks have enough CPU capacity. + * + * Skip the LLC logic because it's not relevant in that case. + */ + goto unlock; + } + + sds = rcu_dereference(per_cpu(sd_llc_shared, cpu)); + if (sds) { + /* + * If there is an imbalance between LLC domains (IOW we could + * increase the overall cache use), we need some less-loaded LLC + * domain to pull some load. Likewise, we may need to spread + * load within the current LLC domain (e.g. packed SMT cores but + * other CPUs are idle). We can't really know from here how busy + * the others are - so just get a nohz balance going if it looks + * like this LLC domain has tasks we could move. + */ + nr_busy = atomic_read(&sds->nr_busy_cpus); + if (nr_busy > 1) { + flags = NOHZ_KICK_MASK; + goto unlock; + } + } unlock: rcu_read_unlock(); out: diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 54a0347ca812..3582eeb59893 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -149,7 +149,7 @@ static void populate_seccomp_data(struct seccomp_data *sd) sd->nr = syscall_get_nr(task, regs); sd->arch = syscall_get_arch(); - syscall_get_arguments(task, regs, 0, 6, args); + syscall_get_arguments(task, regs, args); sd->args[0] = args[0]; sd->args[1] = args[1]; sd->args[2] = args[2]; @@ -502,7 +502,10 @@ out: * * Caller must be holding current->sighand->siglock lock. * - * Returns 0 on success, -ve on error. + * Returns 0 on success, -ve on error, or + * - in TSYNC mode: the pid of a thread which was either not in the correct + * seccomp mode or did not have an ancestral seccomp filter + * - in NEW_LISTENER mode: the fd of the new listener */ static long seccomp_attach_filter(unsigned int flags, struct seccomp_filter *filter) @@ -1258,6 +1261,16 @@ static long seccomp_set_mode_filter(unsigned int flags, if (flags & ~SECCOMP_FILTER_FLAG_MASK) return -EINVAL; + /* + * In the successful case, NEW_LISTENER returns the new listener fd. + * But in the failure case, TSYNC returns the thread that died. If you + * combine these two flags, there's no way to tell whether something + * succeeded or failed. So, let's disallow this combination. + */ + if ((flags & SECCOMP_FILTER_FLAG_TSYNC) && + (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER)) + return -EINVAL; + /* Prepare the new filter before holding any locks. */ prepared = seccomp_prepare_user_filter(filter); if (IS_ERR(prepared)) @@ -1304,7 +1317,7 @@ out: mutex_unlock(¤t->signal->cred_guard_mutex); out_put_fd: if (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER) { - if (ret < 0) { + if (ret) { listener_f->private_data = NULL; fput(listener_f); put_unused_fd(listener); diff --git a/kernel/signal.c b/kernel/signal.c index b7953934aa99..227ba170298e 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -3581,7 +3581,7 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, if (flags) return -EINVAL; - f = fdget_raw(pidfd); + f = fdget(pidfd); if (!f.file) return -EBADF; @@ -3605,16 +3605,11 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, if (unlikely(sig != kinfo.si_signo)) goto err; + /* Only allow sending arbitrary signals to yourself. */ + ret = -EPERM; if ((task_pid(current) != pid) && - (kinfo.si_code >= 0 || kinfo.si_code == SI_TKILL)) { - /* Only allow sending arbitrary signals to yourself. */ - ret = -EPERM; - if (kinfo.si_code != SI_USER) - goto err; - - /* Turn this into a regular kill signal. */ - prepare_kill_siginfo(sig, &kinfo); - } + (kinfo.si_code >= 0 || kinfo.si_code == SI_TKILL)) + goto err; } else { prepare_kill_siginfo(sig, &kinfo); } diff --git a/kernel/sysctl.c b/kernel/sysctl.c index e5da394d1ca3..c9ec050bcf46 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -128,6 +128,7 @@ static int zero; static int __maybe_unused one = 1; static int __maybe_unused two = 2; static int __maybe_unused four = 4; +static unsigned long zero_ul; static unsigned long one_ul = 1; static unsigned long long_max = LONG_MAX; static int one_hundred = 100; @@ -1750,7 +1751,7 @@ static struct ctl_table fs_table[] = { .maxlen = sizeof(files_stat.max_files), .mode = 0644, .proc_handler = proc_doulongvec_minmax, - .extra1 = &zero, + .extra1 = &zero_ul, .extra2 = &long_max, }, { diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 2c97e8c2d29f..0519a8805aab 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -594,7 +594,7 @@ static ktime_t alarm_timer_remaining(struct k_itimer *timr, ktime_t now) { struct alarm *alarm = &timr->it.alarm.alarmtimer; - return ktime_sub(now, alarm->node.expires); + return ktime_sub(alarm->node.expires, now); } /** diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index dc1b6f1929f9..ac9c03dd6c7d 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -89,7 +89,7 @@ struct clocksource * __init __weak clocksource_default_clock(void) return &clocksource_jiffies; } -struct clocksource refined_jiffies; +static struct clocksource refined_jiffies; int register_refined_jiffies(long cycles_per_second) { diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c index 094b82ca95e5..930113b9799a 100644 --- a/kernel/time/sched_clock.c +++ b/kernel/time/sched_clock.c @@ -272,7 +272,7 @@ static u64 notrace suspended_sched_clock_read(void) return cd.read_data[seq & 1].epoch_cyc; } -static int sched_clock_suspend(void) +int sched_clock_suspend(void) { struct clock_read_data *rd = &cd.read_data[0]; @@ -283,7 +283,7 @@ static int sched_clock_suspend(void) return 0; } -static void sched_clock_resume(void) +void sched_clock_resume(void) { struct clock_read_data *rd = &cd.read_data[0]; diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 529143b4c8d2..df401463a191 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -487,6 +487,7 @@ void tick_freeze(void) trace_suspend_resume(TPS("timekeeping_freeze"), smp_processor_id(), true); system_state = SYSTEM_SUSPEND; + sched_clock_suspend(); timekeeping_suspend(); } else { tick_suspend_local(); @@ -510,6 +511,7 @@ void tick_unfreeze(void) if (tick_freeze_depth == num_online_cpus()) { timekeeping_resume(); + sched_clock_resume(); system_state = SYSTEM_RUNNING; trace_suspend_resume(TPS("timekeeping_freeze"), smp_processor_id(), false); diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h index 7a9b4eb7a1d5..141ab3ab0354 100644 --- a/kernel/time/timekeeping.h +++ b/kernel/time/timekeeping.h @@ -14,6 +14,13 @@ extern u64 timekeeping_max_deferment(void); extern void timekeeping_warp_clock(void); extern int timekeeping_suspend(void); extern void timekeeping_resume(void); +#ifdef CONFIG_GENERIC_SCHED_CLOCK +extern int sched_clock_suspend(void); +extern void sched_clock_resume(void); +#else +static inline int sched_clock_suspend(void) { return 0; } +static inline void sched_clock_resume(void) { } +#endif extern void do_timer(unsigned long ticks); extern void update_wall_time(void); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index fa79323331b2..b920358dd8f7 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -33,6 +33,7 @@ #include <linux/list.h> #include <linux/hash.h> #include <linux/rcupdate.h> +#include <linux/kprobes.h> #include <trace/events/sched.h> @@ -1992,7 +1993,7 @@ static void print_bug_type(void) * modifying the code. @failed should be one of either: * EFAULT - if the problem happens on reading the @ip address * EINVAL - if what is read at @ip is not what was expected - * EPERM - if the problem happens on writting to the @ip address + * EPERM - if the problem happens on writing to the @ip address */ void ftrace_bug(int failed, struct dyn_ftrace *rec) { @@ -2391,7 +2392,7 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable) return ftrace_modify_call(rec, ftrace_old_addr, ftrace_addr); } - return -1; /* unknow ftrace bug */ + return -1; /* unknown ftrace bug */ } void __weak ftrace_replace_code(int mod_flags) @@ -3004,7 +3005,7 @@ ftrace_allocate_pages(unsigned long num_to_init) int cnt; if (!num_to_init) - return 0; + return NULL; start_pg = pg = kzalloc(sizeof(*pg), GFP_KERNEL); if (!pg) @@ -4755,7 +4756,7 @@ static int ftrace_set_addr(struct ftrace_ops *ops, unsigned long ip, int remove, int reset, int enable) { - return ftrace_set_hash(ops, 0, 0, ip, remove, reset, enable); + return ftrace_set_hash(ops, NULL, 0, ip, remove, reset, enable); } /** @@ -5463,7 +5464,7 @@ void ftrace_create_filter_files(struct ftrace_ops *ops, /* * The name "destroy_filter_files" is really a misnomer. Although - * in the future, it may actualy delete the files, but this is + * in the future, it may actually delete the files, but this is * really intended to make sure the ops passed in are disabled * and that when this function returns, the caller is free to * free the ops. @@ -5786,7 +5787,7 @@ void ftrace_module_enable(struct module *mod) /* * If the tracing is enabled, go ahead and enable the record. * - * The reason not to enable the record immediatelly is the + * The reason not to enable the record immediately is the * inherent check of ftrace_make_nop/ftrace_make_call for * correct previous instructions. Making first the NOP * conversion puts the module to the correct state, thus @@ -6246,7 +6247,7 @@ void ftrace_reset_array_ops(struct trace_array *tr) tr->ops->func = ftrace_stub; } -static inline void +static nokprobe_inline void __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ignored, struct pt_regs *regs) { @@ -6306,11 +6307,13 @@ static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, { __ftrace_ops_list_func(ip, parent_ip, NULL, regs); } +NOKPROBE_SYMBOL(ftrace_ops_list_func); #else static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip) { __ftrace_ops_list_func(ip, parent_ip, NULL, NULL); } +NOKPROBE_SYMBOL(ftrace_ops_no_ops); #endif /* @@ -6337,6 +6340,7 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip, preempt_enable_notrace(); trace_clear_recursion(bit); } +NOKPROBE_SYMBOL(ftrace_ops_assist_func); /** * ftrace_ops_get_func - get the function a trampoline should call diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 41b6f96e5366..4ee8d8aa3d0f 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -762,7 +762,7 @@ u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu) preempt_disable_notrace(); time = rb_time_stamp(buffer); - preempt_enable_no_resched_notrace(); + preempt_enable_notrace(); return time; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 21153e64bf1c..ca1ee656d6d8 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -496,8 +496,10 @@ int trace_pid_write(struct trace_pid_list *filtered_pids, * not modified. */ pid_list = kmalloc(sizeof(*pid_list), GFP_KERNEL); - if (!pid_list) + if (!pid_list) { + trace_parser_put(&parser); return -ENOMEM; + } pid_list->pid_max = READ_ONCE(pid_max); @@ -507,6 +509,7 @@ int trace_pid_write(struct trace_pid_list *filtered_pids, pid_list->pids = vzalloc((pid_list->pid_max + 7) >> 3); if (!pid_list->pids) { + trace_parser_put(&parser); kfree(pid_list); return -ENOMEM; } @@ -7025,35 +7028,43 @@ struct buffer_ref { struct ring_buffer *buffer; void *page; int cpu; - int ref; + refcount_t refcount; }; +static void buffer_ref_release(struct buffer_ref *ref) +{ + if (!refcount_dec_and_test(&ref->refcount)) + return; + ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page); + kfree(ref); +} + static void buffer_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct buffer_ref *ref = (struct buffer_ref *)buf->private; - if (--ref->ref) - return; - - ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page); - kfree(ref); + buffer_ref_release(ref); buf->private = 0; } -static void buffer_pipe_buf_get(struct pipe_inode_info *pipe, +static bool buffer_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct buffer_ref *ref = (struct buffer_ref *)buf->private; - ref->ref++; + if (refcount_read(&ref->refcount) > INT_MAX/2) + return false; + + refcount_inc(&ref->refcount); + return true; } /* Pipe buffer operations for a buffer. */ static const struct pipe_buf_operations buffer_pipe_buf_ops = { .confirm = generic_pipe_buf_confirm, .release = buffer_pipe_buf_release, - .steal = generic_pipe_buf_steal, + .steal = generic_pipe_buf_nosteal, .get = buffer_pipe_buf_get, }; @@ -7066,11 +7077,7 @@ static void buffer_spd_release(struct splice_pipe_desc *spd, unsigned int i) struct buffer_ref *ref = (struct buffer_ref *)spd->partial[i].private; - if (--ref->ref) - return; - - ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page); - kfree(ref); + buffer_ref_release(ref); spd->partial[i].private = 0; } @@ -7125,7 +7132,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, break; } - ref->ref = 1; + refcount_set(&ref->refcount, 1); ref->buffer = iter->trace_buffer->buffer; ref->page = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file); if (IS_ERR(ref->page)) { diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c index dd1f43588d70..fa100ed3b4de 100644 --- a/kernel/trace/trace_dynevent.c +++ b/kernel/trace/trace_dynevent.c @@ -74,7 +74,7 @@ int dyn_event_release(int argc, char **argv, struct dyn_event_operations *type) static int create_dyn_event(int argc, char **argv) { struct dyn_event_operations *ops; - int ret; + int ret = -ENODEV; if (argv[0][0] == '-' || argv[0][0] == '!') return dyn_event_release(argc, argv, NULL); diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index ca46339f3009..795aa2038377 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -3713,7 +3713,6 @@ static void track_data_destroy(struct hist_trigger_data *hist_data, struct trace_event_file *file = hist_data->event_file; destroy_hist_field(data->track_data.track_var, 0); - destroy_hist_field(data->track_data.var_ref, 0); if (data->action == ACTION_SNAPSHOT) { struct track_data *track_data; diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index f93a56d2db27..fa8fbff736d6 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -314,6 +314,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) struct ring_buffer_event *event; struct ring_buffer *buffer; unsigned long irq_flags; + unsigned long args[6]; int pc; int syscall_nr; int size; @@ -347,7 +348,8 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) entry = ring_buffer_event_data(event); entry->nr = syscall_nr; - syscall_get_arguments(current, regs, 0, sys_data->nb_args, entry->args); + syscall_get_arguments(current, regs, args); + memcpy(entry->args, args, sizeof(unsigned long) * sys_data->nb_args); event_trigger_unlock_commit(trace_file, buffer, event, entry, irq_flags, pc); @@ -583,6 +585,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) struct syscall_metadata *sys_data; struct syscall_trace_enter *rec; struct hlist_head *head; + unsigned long args[6]; bool valid_prog_array; int syscall_nr; int rctx; @@ -613,8 +616,8 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) return; rec->nr = syscall_nr; - syscall_get_arguments(current, regs, 0, sys_data->nb_args, - (unsigned long *)&rec->args); + syscall_get_arguments(current, regs, args); + memcpy(&rec->args, args, sizeof(unsigned long) * sys_data->nb_args); if ((valid_prog_array && !perf_call_bpf_enter(sys_data->enter_event, regs, sys_data, rec)) || diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 8fbfda94a67b..6a5787233113 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -42,9 +42,9 @@ int __read_mostly watchdog_user_enabled = 1; int __read_mostly nmi_watchdog_user_enabled = NMI_WATCHDOG_DEFAULT; int __read_mostly soft_watchdog_user_enabled = 1; int __read_mostly watchdog_thresh = 10; -int __read_mostly nmi_watchdog_available; +static int __read_mostly nmi_watchdog_available; -struct cpumask watchdog_allowed_mask __read_mostly; +static struct cpumask watchdog_allowed_mask __read_mostly; struct cpumask watchdog_cpumask __read_mostly; unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); @@ -554,13 +554,15 @@ static void softlockup_start_all(void) int lockup_detector_online_cpu(unsigned int cpu) { - watchdog_enable(cpu); + if (cpumask_test_cpu(cpu, &watchdog_allowed_mask)) + watchdog_enable(cpu); return 0; } int lockup_detector_offline_cpu(unsigned int cpu) { - watchdog_disable(cpu); + if (cpumask_test_cpu(cpu, &watchdog_allowed_mask)) + watchdog_disable(cpu); return 0; } diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 71381168dede..247bf0b1582c 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -135,7 +135,8 @@ static void watchdog_overflow_callback(struct perf_event *event, if (__this_cpu_read(hard_watchdog_warn) == true) return; - pr_emerg("Watchdog detected hard LOCKUP on cpu %d", this_cpu); + pr_emerg("Watchdog detected hard LOCKUP on cpu %d\n", + this_cpu); print_modules(); print_irqtrace_events(current); if (regs) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 4026d1871407..ddee541ea97a 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -4266,7 +4266,7 @@ struct workqueue_struct *alloc_workqueue(const char *fmt, INIT_LIST_HEAD(&wq->list); if (alloc_and_link_pwqs(wq) < 0) - goto err_free_wq; + goto err_unreg_lockdep; if (wq_online && init_rescuer(wq) < 0) goto err_destroy; @@ -4292,9 +4292,10 @@ struct workqueue_struct *alloc_workqueue(const char *fmt, return wq; -err_free_wq: +err_unreg_lockdep: wq_unregister_lockdep(wq); wq_free_lockdep(wq); +err_free_wq: free_workqueue_attrs(wq->unbound_attrs); kfree(wq); return NULL; |