diff options
Diffstat (limited to 'kernel')
52 files changed, 732 insertions, 899 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index 318789c728d3..a7e1f49ab2b3 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -7,7 +7,7 @@ obj-y = fork.o exec_domain.o panic.o \ cpu.o exit.o softirq.o resource.o \ sysctl.o capability.o ptrace.o user.o \ signal.o sys.o umh.o workqueue.o pid.o task_work.o \ - extable.o params.o \ + extable.o params.o platform-feature.o \ kthread.o sys_ni.o nsproxy.o \ notifier.o ksysfs.o cred.o reboot.o \ async.o range.o smpboot.o ucount.o regset.o diff --git a/kernel/auditsc.c b/kernel/auditsc.c index f3a2abd6d1a1..3a8c9d744800 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1014,10 +1014,10 @@ static void audit_reset_context(struct audit_context *ctx) ctx->target_comm[0] = '\0'; unroll_tree_refs(ctx, NULL, 0); WARN_ON(!list_empty(&ctx->killed_trees)); - ctx->type = 0; audit_free_module(ctx); ctx->fds[0] = -1; audit_proctitle_free(ctx); + ctx->type = 0; /* reset last for audit_free_*() */ } static inline struct audit_context *audit_alloc_context(enum audit_state state) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 7bccaa4646e5..eb12d4f705cc 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -4815,6 +4815,7 @@ static int btf_check_type_tags(struct btf_verifier_env *env, n = btf_nr_types(btf); for (i = start_id; i < n; i++) { const struct btf_type *t; + int chain_limit = 32; u32 cur_id = i; t = btf_type_by_id(btf, i); @@ -4827,6 +4828,10 @@ static int btf_check_type_tags(struct btf_verifier_env *env, in_tags = btf_type_is_type_tag(t); while (btf_type_is_modifier(t)) { + if (!chain_limit--) { + btf_verifier_log(env, "Max chain length or cycle detected"); + return -ELOOP; + } if (btf_type_is_type_tag(t)) { if (!in_tags) { btf_verifier_log(env, "Type tags don't precede modifiers"); @@ -6054,6 +6059,7 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, struct bpf_reg_state *regs, bool ptr_to_mem_ok) { + enum bpf_prog_type prog_type = resolve_prog_type(env->prog); struct bpf_verifier_log *log = &env->log; u32 i, nargs, ref_id, ref_obj_id = 0; bool is_kfunc = btf_is_kernel(btf); @@ -6171,7 +6177,7 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, return -EINVAL; } /* rest of the arguments can be anything, like normal kfunc */ - } else if (btf_get_prog_ctx_type(log, btf, t, env->prog->type, i)) { + } else if (btf_get_prog_ctx_type(log, btf, t, prog_type, i)) { /* If function expects ctx type in BTF check that caller * is passing PTR_TO_CTX. */ diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 5f6f3f829b36..e7961508a47d 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -68,11 +68,13 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns { u8 *ptr = NULL; - if (k >= SKF_NET_OFF) + if (k >= SKF_NET_OFF) { ptr = skb_network_header(skb) + k - SKF_NET_OFF; - else if (k >= SKF_LL_OFF) + } else if (k >= SKF_LL_OFF) { + if (unlikely(!skb_mac_header_was_set(skb))) + return NULL; ptr = skb_mac_header(skb) + k - SKF_LL_OFF; - + } if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb)) return ptr; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 225806a02efb..bb1254f07667 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1497,11 +1497,12 @@ const struct bpf_func_proto bpf_dynptr_from_mem_proto = { .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL | MEM_UNINIT, }; -BPF_CALL_4(bpf_dynptr_read, void *, dst, u32, len, struct bpf_dynptr_kern *, src, u32, offset) +BPF_CALL_5(bpf_dynptr_read, void *, dst, u32, len, struct bpf_dynptr_kern *, src, + u32, offset, u64, flags) { int err; - if (!src->data) + if (!src->data || flags) return -EINVAL; err = bpf_dynptr_check_off_len(src, offset, len); @@ -1521,13 +1522,15 @@ const struct bpf_func_proto bpf_dynptr_read_proto = { .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_PTR_TO_DYNPTR, .arg4_type = ARG_ANYTHING, + .arg5_type = ARG_ANYTHING, }; -BPF_CALL_4(bpf_dynptr_write, struct bpf_dynptr_kern *, dst, u32, offset, void *, src, u32, len) +BPF_CALL_5(bpf_dynptr_write, struct bpf_dynptr_kern *, dst, u32, offset, void *, src, + u32, len, u64, flags) { int err; - if (!dst->data || bpf_dynptr_is_rdonly(dst)) + if (!dst->data || flags || bpf_dynptr_is_rdonly(dst)) return -EINVAL; err = bpf_dynptr_check_off_len(dst, offset, len); @@ -1547,6 +1550,7 @@ const struct bpf_func_proto bpf_dynptr_write_proto = { .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE_OR_ZERO, + .arg5_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_dynptr_data, struct bpf_dynptr_kern *, ptr, u32, offset, u32, len) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index aedac2ac02b9..0efbac0fd126 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1562,6 +1562,21 @@ static void __reg_bound_offset(struct bpf_reg_state *reg) reg->var_off = tnum_or(tnum_clear_subreg(var64_off), var32_off); } +static void reg_bounds_sync(struct bpf_reg_state *reg) +{ + /* We might have learned new bounds from the var_off. */ + __update_reg_bounds(reg); + /* We might have learned something about the sign bit. */ + __reg_deduce_bounds(reg); + /* We might have learned some bits from the bounds. */ + __reg_bound_offset(reg); + /* Intersecting with the old var_off might have improved our bounds + * slightly, e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc), + * then new var_off is (0; 0x7f...fc) which improves our umax. + */ + __update_reg_bounds(reg); +} + static bool __reg32_bound_s64(s32 a) { return a >= 0 && a <= S32_MAX; @@ -1603,16 +1618,8 @@ static void __reg_combine_32_into_64(struct bpf_reg_state *reg) * so they do not impact tnum bounds calculation. */ __mark_reg64_unbounded(reg); - __update_reg_bounds(reg); } - - /* Intersecting with the old var_off might have improved our bounds - * slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc), - * then new var_off is (0; 0x7f...fc) which improves our umax. - */ - __reg_deduce_bounds(reg); - __reg_bound_offset(reg); - __update_reg_bounds(reg); + reg_bounds_sync(reg); } static bool __reg64_bound_s32(s64 a) @@ -1628,7 +1635,6 @@ static bool __reg64_bound_u32(u64 a) static void __reg_combine_64_into_32(struct bpf_reg_state *reg) { __mark_reg32_unbounded(reg); - if (__reg64_bound_s32(reg->smin_value) && __reg64_bound_s32(reg->smax_value)) { reg->s32_min_value = (s32)reg->smin_value; reg->s32_max_value = (s32)reg->smax_value; @@ -1637,14 +1643,7 @@ static void __reg_combine_64_into_32(struct bpf_reg_state *reg) reg->u32_min_value = (u32)reg->umin_value; reg->u32_max_value = (u32)reg->umax_value; } - - /* Intersecting with the old var_off might have improved our bounds - * slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc), - * then new var_off is (0; 0x7f...fc) which improves our umax. - */ - __reg_deduce_bounds(reg); - __reg_bound_offset(reg); - __update_reg_bounds(reg); + reg_bounds_sync(reg); } /* Mark a register as having a completely unknown (scalar) value. */ @@ -6943,9 +6942,7 @@ static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type, ret_reg->s32_max_value = meta->msize_max_value; ret_reg->smin_value = -MAX_ERRNO; ret_reg->s32_min_value = -MAX_ERRNO; - __reg_deduce_bounds(ret_reg); - __reg_bound_offset(ret_reg); - __update_reg_bounds(ret_reg); + reg_bounds_sync(ret_reg); } static int @@ -8202,11 +8199,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, if (!check_reg_sane_offset(env, dst_reg, ptr_reg->type)) return -EINVAL; - - __update_reg_bounds(dst_reg); - __reg_deduce_bounds(dst_reg); - __reg_bound_offset(dst_reg); - + reg_bounds_sync(dst_reg); if (sanitize_check_bounds(env, insn, dst_reg) < 0) return -EACCES; if (sanitize_needed(opcode)) { @@ -8944,10 +8937,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, /* ALU32 ops are zero extended into 64bit register */ if (alu32) zext_32_to_64(dst_reg); - - __update_reg_bounds(dst_reg); - __reg_deduce_bounds(dst_reg); - __reg_bound_offset(dst_reg); + reg_bounds_sync(dst_reg); return 0; } @@ -9136,10 +9126,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) insn->dst_reg); } zext_32_to_64(dst_reg); - - __update_reg_bounds(dst_reg); - __reg_deduce_bounds(dst_reg); - __reg_bound_offset(dst_reg); + reg_bounds_sync(dst_reg); } } else { /* case: R = imm @@ -9577,26 +9564,33 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg, return; switch (opcode) { + /* JEQ/JNE comparison doesn't change the register equivalence. + * + * r1 = r2; + * if (r1 == 42) goto label; + * ... + * label: // here both r1 and r2 are known to be 42. + * + * Hence when marking register as known preserve it's ID. + */ case BPF_JEQ: + if (is_jmp32) { + __mark_reg32_known(true_reg, val32); + true_32off = tnum_subreg(true_reg->var_off); + } else { + ___mark_reg_known(true_reg, val); + true_64off = true_reg->var_off; + } + break; case BPF_JNE: - { - struct bpf_reg_state *reg = - opcode == BPF_JEQ ? true_reg : false_reg; - - /* JEQ/JNE comparison doesn't change the register equivalence. - * r1 = r2; - * if (r1 == 42) goto label; - * ... - * label: // here both r1 and r2 are known to be 42. - * - * Hence when marking register as known preserve it's ID. - */ - if (is_jmp32) - __mark_reg32_known(reg, val32); - else - ___mark_reg_known(reg, val); + if (is_jmp32) { + __mark_reg32_known(false_reg, val32); + false_32off = tnum_subreg(false_reg->var_off); + } else { + ___mark_reg_known(false_reg, val); + false_64off = false_reg->var_off; + } break; - } case BPF_JSET: if (is_jmp32) { false_32off = tnum_and(false_32off, tnum_const(~val32)); @@ -9735,21 +9729,8 @@ static void __reg_combine_min_max(struct bpf_reg_state *src_reg, dst_reg->smax_value); src_reg->var_off = dst_reg->var_off = tnum_intersect(src_reg->var_off, dst_reg->var_off); - /* We might have learned new bounds from the var_off. */ - __update_reg_bounds(src_reg); - __update_reg_bounds(dst_reg); - /* We might have learned something about the sign bit. */ - __reg_deduce_bounds(src_reg); - __reg_deduce_bounds(dst_reg); - /* We might have learned some bits from the bounds. */ - __reg_bound_offset(src_reg); - __reg_bound_offset(dst_reg); - /* Intersecting with the old var_off might have improved our bounds - * slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc), - * then new var_off is (0; 0x7f...fc) which improves our umax. - */ - __update_reg_bounds(src_reg); - __update_reg_bounds(dst_reg); + reg_bounds_sync(src_reg); + reg_bounds_sync(dst_reg); } static void reg_combine_min_max(struct bpf_reg_state *true_src, diff --git a/kernel/cfi.c b/kernel/cfi.c index 9594cfd1cf2c..08102d19ec15 100644 --- a/kernel/cfi.c +++ b/kernel/cfi.c @@ -281,6 +281,8 @@ static inline cfi_check_fn find_module_check_fn(unsigned long ptr) static inline cfi_check_fn find_check_fn(unsigned long ptr) { cfi_check_fn fn = NULL; + unsigned long flags; + bool rcu_idle; if (is_kernel_text(ptr)) return __cfi_check; @@ -290,13 +292,21 @@ static inline cfi_check_fn find_check_fn(unsigned long ptr) * the shadow and __module_address use RCU, so we need to wake it * up if necessary. */ - RCU_NONIDLE({ - if (IS_ENABLED(CONFIG_CFI_CLANG_SHADOW)) - fn = find_shadow_check_fn(ptr); + rcu_idle = !rcu_is_watching(); + if (rcu_idle) { + local_irq_save(flags); + rcu_irq_enter(); + } + + if (IS_ENABLED(CONFIG_CFI_CLANG_SHADOW)) + fn = find_shadow_check_fn(ptr); + if (!fn) + fn = find_module_check_fn(ptr); - if (!fn) - fn = find_module_check_fn(ptr); - }); + if (rcu_idle) { + rcu_irq_exit(); + local_irq_restore(flags); + } return fn; } diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 1779ccddb734..13c8e91d7862 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -765,7 +765,8 @@ struct css_set init_css_set = { .task_iters = LIST_HEAD_INIT(init_css_set.task_iters), .threaded_csets = LIST_HEAD_INIT(init_css_set.threaded_csets), .cgrp_links = LIST_HEAD_INIT(init_css_set.cgrp_links), - .mg_preload_node = LIST_HEAD_INIT(init_css_set.mg_preload_node), + .mg_src_preload_node = LIST_HEAD_INIT(init_css_set.mg_src_preload_node), + .mg_dst_preload_node = LIST_HEAD_INIT(init_css_set.mg_dst_preload_node), .mg_node = LIST_HEAD_INIT(init_css_set.mg_node), /* @@ -1240,7 +1241,8 @@ static struct css_set *find_css_set(struct css_set *old_cset, INIT_LIST_HEAD(&cset->threaded_csets); INIT_HLIST_NODE(&cset->hlist); INIT_LIST_HEAD(&cset->cgrp_links); - INIT_LIST_HEAD(&cset->mg_preload_node); + INIT_LIST_HEAD(&cset->mg_src_preload_node); + INIT_LIST_HEAD(&cset->mg_dst_preload_node); INIT_LIST_HEAD(&cset->mg_node); /* Copy the set of subsystem state objects generated in @@ -2597,21 +2599,27 @@ int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp) */ void cgroup_migrate_finish(struct cgroup_mgctx *mgctx) { - LIST_HEAD(preloaded); struct css_set *cset, *tmp_cset; lockdep_assert_held(&cgroup_mutex); spin_lock_irq(&css_set_lock); - list_splice_tail_init(&mgctx->preloaded_src_csets, &preloaded); - list_splice_tail_init(&mgctx->preloaded_dst_csets, &preloaded); + list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_src_csets, + mg_src_preload_node) { + cset->mg_src_cgrp = NULL; + cset->mg_dst_cgrp = NULL; + cset->mg_dst_cset = NULL; + list_del_init(&cset->mg_src_preload_node); + put_css_set_locked(cset); + } - list_for_each_entry_safe(cset, tmp_cset, &preloaded, mg_preload_node) { + list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_dst_csets, + mg_dst_preload_node) { cset->mg_src_cgrp = NULL; cset->mg_dst_cgrp = NULL; cset->mg_dst_cset = NULL; - list_del_init(&cset->mg_preload_node); + list_del_init(&cset->mg_dst_preload_node); put_css_set_locked(cset); } @@ -2651,7 +2659,7 @@ void cgroup_migrate_add_src(struct css_set *src_cset, if (src_cset->dead) return; - if (!list_empty(&src_cset->mg_preload_node)) + if (!list_empty(&src_cset->mg_src_preload_node)) return; src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root); @@ -2664,7 +2672,7 @@ void cgroup_migrate_add_src(struct css_set *src_cset, src_cset->mg_src_cgrp = src_cgrp; src_cset->mg_dst_cgrp = dst_cgrp; get_css_set(src_cset); - list_add_tail(&src_cset->mg_preload_node, &mgctx->preloaded_src_csets); + list_add_tail(&src_cset->mg_src_preload_node, &mgctx->preloaded_src_csets); } /** @@ -2689,7 +2697,7 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx) /* look up the dst cset for each src cset and link it to src */ list_for_each_entry_safe(src_cset, tmp_cset, &mgctx->preloaded_src_csets, - mg_preload_node) { + mg_src_preload_node) { struct css_set *dst_cset; struct cgroup_subsys *ss; int ssid; @@ -2708,7 +2716,7 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx) if (src_cset == dst_cset) { src_cset->mg_src_cgrp = NULL; src_cset->mg_dst_cgrp = NULL; - list_del_init(&src_cset->mg_preload_node); + list_del_init(&src_cset->mg_src_preload_node); put_css_set(src_cset); put_css_set(dst_cset); continue; @@ -2716,8 +2724,8 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx) src_cset->mg_dst_cset = dst_cset; - if (list_empty(&dst_cset->mg_preload_node)) - list_add_tail(&dst_cset->mg_preload_node, + if (list_empty(&dst_cset->mg_dst_preload_node)) + list_add_tail(&dst_cset->mg_dst_preload_node, &mgctx->preloaded_dst_csets); else put_css_set(dst_cset); @@ -2963,7 +2971,8 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) goto out_finish; spin_lock_irq(&css_set_lock); - list_for_each_entry(src_cset, &mgctx.preloaded_src_csets, mg_preload_node) { + list_for_each_entry(src_cset, &mgctx.preloaded_src_csets, + mg_src_preload_node) { struct task_struct *task, *ntask; /* all tasks in src_csets need to be migrated */ diff --git a/kernel/configs/x86_debug.config b/kernel/configs/x86_debug.config index dcd86f32f4ed..6fac5b405334 100644 --- a/kernel/configs/x86_debug.config +++ b/kernel/configs/x86_debug.config @@ -7,12 +7,11 @@ CONFIG_DEBUG_SLAB=y CONFIG_DEBUG_KMEMLEAK=y CONFIG_DEBUG_PAGEALLOC=y CONFIG_SLUB_DEBUG_ON=y -CONFIG_KMEMCHECK=y CONFIG_DEBUG_OBJECTS=y CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT=1 CONFIG_GCOV_KERNEL=y CONFIG_LOCKDEP=y CONFIG_PROVE_LOCKING=y CONFIG_SCHEDSTATS=y -CONFIG_VMLINUX_VALIDATION=y +CONFIG_NOINSTR_VALIDATION=y CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index ac740630c79c..2caafd13f8aa 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -564,7 +564,7 @@ static void add_dma_entry(struct dma_debug_entry *entry, unsigned long attrs) rc = active_cacheline_insert(entry); if (rc == -ENOMEM) { - pr_err("cacheline tracking ENOMEM, dma-debug disabled\n"); + pr_err_once("cacheline tracking ENOMEM, dma-debug disabled\n"); global_disable = true; } else if (rc == -EEXIST && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) { err_printk(entry->dev, entry, diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index e978f36e6be8..8d0b68a17042 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -357,7 +357,7 @@ void dma_direct_free(struct device *dev, size_t size, } else { if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_CLEAR_UNCACHED)) arch_dma_clear_uncached(cpu_addr, size); - if (dma_set_encrypted(dev, cpu_addr, 1 << page_order)) + if (dma_set_encrypted(dev, cpu_addr, size)) return; } @@ -392,7 +392,6 @@ void dma_direct_free_pages(struct device *dev, size_t size, struct page *page, dma_addr_t dma_addr, enum dma_data_direction dir) { - unsigned int page_order = get_order(size); void *vaddr = page_address(page); /* If cpu_addr is not from an atomic pool, dma_free_from_pool() fails */ @@ -400,7 +399,7 @@ void dma_direct_free_pages(struct device *dev, size_t size, dma_free_from_pool(dev, vaddr, size)) return; - if (dma_set_encrypted(dev, vaddr, 1 << page_order)) + if (dma_set_encrypted(dev, vaddr, size)) return; __dma_direct_free_pages(dev, page, size); } diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index dfa1de89dc94..cb50f8d38360 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -192,7 +192,7 @@ void __init swiotlb_update_mem_attributes(void) } static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start, - unsigned long nslabs, bool late_alloc) + unsigned long nslabs, unsigned int flags, bool late_alloc) { void *vaddr = phys_to_virt(start); unsigned long bytes = nslabs << IO_TLB_SHIFT, i; @@ -203,8 +203,7 @@ static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start, mem->index = 0; mem->late_alloc = late_alloc; - if (swiotlb_force_bounce) - mem->force_bounce = true; + mem->force_bounce = swiotlb_force_bounce || (flags & SWIOTLB_FORCE); spin_lock_init(&mem->lock); for (i = 0; i < mem->nslabs; i++) { @@ -275,8 +274,7 @@ retry: panic("%s: Failed to allocate %zu bytes align=0x%lx\n", __func__, alloc_size, PAGE_SIZE); - swiotlb_init_io_tlb_mem(mem, __pa(tlb), nslabs, false); - mem->force_bounce = flags & SWIOTLB_FORCE; + swiotlb_init_io_tlb_mem(mem, __pa(tlb), nslabs, flags, false); if (flags & SWIOTLB_VERBOSE) swiotlb_print_info(); @@ -348,7 +346,7 @@ retry: set_memory_decrypted((unsigned long)vstart, (nslabs << IO_TLB_SHIFT) >> PAGE_SHIFT); - swiotlb_init_io_tlb_mem(mem, virt_to_phys(vstart), nslabs, true); + swiotlb_init_io_tlb_mem(mem, virt_to_phys(vstart), nslabs, 0, true); swiotlb_print_info(); return 0; @@ -835,8 +833,8 @@ static int rmem_swiotlb_device_init(struct reserved_mem *rmem, set_memory_decrypted((unsigned long)phys_to_virt(rmem->base), rmem->size >> PAGE_SHIFT); - swiotlb_init_io_tlb_mem(mem, rmem->base, nslabs, false); - mem->force_bounce = true; + swiotlb_init_io_tlb_mem(mem, rmem->base, nslabs, SWIOTLB_FORCE, + false); mem->for_alloc = true; rmem->priv = mem; diff --git a/kernel/entry/kvm.c b/kernel/entry/kvm.c index 9d09f489b60e..2e0f75bcb7fd 100644 --- a/kernel/entry/kvm.c +++ b/kernel/entry/kvm.c @@ -9,12 +9,6 @@ static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work) int ret; if (ti_work & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) { - clear_notify_signal(); - if (task_work_pending(current)) - task_work_run(); - } - - if (ti_work & _TIF_SIGPENDING) { kvm_handle_signal_exit(vcpu); return -EINTR; } diff --git a/kernel/events/core.c b/kernel/events/core.c index 80782cddb1da..d2b354991bf5 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6253,10 +6253,10 @@ again: if (!atomic_inc_not_zero(&event->rb->mmap_count)) { /* - * Raced against perf_mmap_close() through - * perf_event_set_output(). Try again, hope for better - * luck. + * Raced against perf_mmap_close(); remove the + * event and try again. */ + ring_buffer_attach(event, NULL); mutex_unlock(&event->mmap_mutex); goto again; } @@ -11825,14 +11825,25 @@ err_size: goto out; } +static void mutex_lock_double(struct mutex *a, struct mutex *b) +{ + if (b < a) + swap(a, b); + + mutex_lock(a); + mutex_lock_nested(b, SINGLE_DEPTH_NESTING); +} + static int perf_event_set_output(struct perf_event *event, struct perf_event *output_event) { struct perf_buffer *rb = NULL; int ret = -EINVAL; - if (!output_event) + if (!output_event) { + mutex_lock(&event->mmap_mutex); goto set; + } /* don't allow circular references */ if (event == output_event) @@ -11870,8 +11881,15 @@ perf_event_set_output(struct perf_event *event, struct perf_event *output_event) event->pmu != output_event->pmu) goto out; + /* + * Hold both mmap_mutex to serialize against perf_mmap_close(). Since + * output_event is already on rb->event_list, and the list iteration + * restarts after every removal, it is guaranteed this new event is + * observed *OR* if output_event is already removed, it's guaranteed we + * observe !rb->mmap_count. + */ + mutex_lock_double(&event->mmap_mutex, &output_event->mmap_mutex); set: - mutex_lock(&event->mmap_mutex); /* Can't redirect output if we've got an active mmap() */ if (atomic_read(&event->mmap_count)) goto unlock; @@ -11881,6 +11899,12 @@ set: rb = ring_buffer_get(output_event); if (!rb) goto unlock; + + /* did we race against perf_mmap_close() */ + if (!atomic_read(&rb->mmap_count)) { + ring_buffer_put(rb); + goto unlock; + } } ring_buffer_attach(event, rb); @@ -11888,20 +11912,13 @@ set: ret = 0; unlock: mutex_unlock(&event->mmap_mutex); + if (output_event) + mutex_unlock(&output_event->mmap_mutex); out: return ret; } -static void mutex_lock_double(struct mutex *a, struct mutex *b) -{ - if (b < a) - swap(a, b); - - mutex_lock(a); - mutex_lock_nested(b, SINGLE_DEPTH_NESTING); -} - static int perf_event_set_clock(struct perf_event *event, clockid_t clk_id) { bool nmi_safe = false; diff --git a/kernel/exit.c b/kernel/exit.c index f072959fcab7..64c938ce36fe 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -766,7 +766,7 @@ void __noreturn do_exit(long code) #ifdef CONFIG_POSIX_TIMERS hrtimer_cancel(&tsk->signal->real_timer); - exit_itimers(tsk->signal); + exit_itimers(tsk); #endif if (tsk->mm) setmax_mm_hiwater_rss(&tsk->signal->maxrss, tsk->mm); diff --git a/kernel/hung_task.c b/kernel/hung_task.c index 80bfea5dd5c4..cff3ae8c818f 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -127,8 +127,6 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) * complain: */ if (sysctl_hung_task_warnings) { - printk_prefer_direct_enter(); - if (sysctl_hung_task_warnings > 0) sysctl_hung_task_warnings--; pr_err("INFO: task %s:%d blocked for more than %ld seconds.\n", @@ -144,8 +142,6 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) if (sysctl_hung_task_all_cpu_backtrace) hung_task_show_all_bt = true; - - printk_prefer_direct_exit(); } touch_nmi_watchdog(); @@ -208,17 +204,12 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout) } unlock: rcu_read_unlock(); - if (hung_task_show_lock) { - printk_prefer_direct_enter(); + if (hung_task_show_lock) debug_show_all_locks(); - printk_prefer_direct_exit(); - } if (hung_task_show_all_bt) { hung_task_show_all_bt = false; - printk_prefer_direct_enter(); trigger_all_cpu_backtrace(); - printk_prefer_direct_exit(); } if (hung_task_call_panic) diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index e6b8e564b37f..886789dcee43 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -1006,8 +1006,10 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle, if (desc->irq_data.chip != &no_irq_chip) mask_ack_irq(desc); irq_state_set_disabled(desc); - if (is_chained) + if (is_chained) { desc->action = NULL; + WARN_ON(irq_chip_pm_put(irq_desc_get_irq_data(desc))); + } desc->depth = 1; } desc->handle_irq = handle; @@ -1033,6 +1035,7 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle, irq_settings_set_norequest(desc); irq_settings_set_nothread(desc); desc->action = &chained_action; + WARN_ON(irq_chip_pm_get(irq_desc_get_irq_data(desc))); irq_activate_and_startup(desc, IRQ_RESEND); } } diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 145321a5e798..f9261c07b048 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -29,6 +29,15 @@ #include <linux/vmalloc.h> #include "kexec_internal.h" +#ifdef CONFIG_KEXEC_SIG +static bool sig_enforce = IS_ENABLED(CONFIG_KEXEC_SIG_FORCE); + +void set_kexec_sig_enforced(void) +{ + sig_enforce = true; +} +#endif + static int kexec_calculate_store_digests(struct kimage *image); /* @@ -159,7 +168,7 @@ kimage_validate_signature(struct kimage *image) image->kernel_buf_len); if (ret) { - if (IS_ENABLED(CONFIG_KEXEC_SIG_FORCE)) { + if (sig_enforce) { pr_notice("Enforced kernel signature verification failed (%d).\n", ret); return ret; } diff --git a/kernel/kthread.c b/kernel/kthread.c index 544fd4097406..3c677918d8f2 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -340,7 +340,7 @@ static int kthread(void *_create) self = to_kthread(current); - /* If user was SIGKILLed, I release the structure. */ + /* Release the structure when caller killed by a fatal signal. */ done = xchg(&create->done, NULL); if (!done) { kfree(create); @@ -398,7 +398,7 @@ static void create_kthread(struct kthread_create_info *create) /* We want our own signal handler (we take no signals by default). */ pid = kernel_thread(kthread, create, CLONE_FS | CLONE_FILES | SIGCHLD); if (pid < 0) { - /* If user was SIGKILLed, I release the structure. */ + /* Release the structure when caller killed by a fatal signal. */ struct completion *done = xchg(&create->done, NULL); if (!done) { @@ -440,9 +440,9 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data), */ if (unlikely(wait_for_completion_killable(&done))) { /* - * If I was SIGKILLed before kthreadd (or new kernel thread) - * calls complete(), leave the cleanup of this structure to - * that thread. + * If I was killed by a fatal signal before kthreadd (or new + * kernel thread) calls complete(), leave the cleanup of this + * structure to that thread. */ if (xchg(&create->done, NULL)) return ERR_PTR(-EINTR); @@ -876,7 +876,7 @@ fail_task: * * Returns a pointer to the allocated worker on success, ERR_PTR(-ENOMEM) * when the needed structures could not get allocated, and ERR_PTR(-EINTR) - * when the worker was SIGKILLed. + * when the caller was killed by a fatal signal. */ struct kthread_worker * kthread_create_worker(unsigned int flags, const char namefmt[], ...) @@ -925,7 +925,7 @@ EXPORT_SYMBOL(kthread_create_worker); * Return: * The pointer to the allocated worker on success, ERR_PTR(-ENOMEM) * when the needed structures could not get allocated, and ERR_PTR(-EINTR) - * when the worker was SIGKILLed. + * when the caller was killed by a fatal signal. */ struct kthread_worker * kthread_create_worker_on_cpu(int cpu, unsigned int flags, diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 81e87280513e..f06b91ca6482 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -5432,7 +5432,7 @@ static struct pin_cookie __lock_pin_lock(struct lockdep_map *lock) * be guessable and still allows some pin nesting in * our u32 pin_count. */ - cookie.val = 1 + (prandom_u32() >> 16); + cookie.val = 1 + (sched_clock() & 0xffff); hlock->pin_count += cookie.val; return cookie; } diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index 9d1db4a54d34..65f0262f635e 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -335,8 +335,6 @@ struct rwsem_waiter { struct task_struct *task; enum rwsem_waiter_type type; unsigned long timeout; - - /* Writer only, not initialized in reader */ bool handoff_set; }; #define rwsem_first_waiter(sem) \ @@ -459,10 +457,12 @@ static void rwsem_mark_wake(struct rw_semaphore *sem, * to give up the lock), request a HANDOFF to * force the issue. */ - if (!(oldcount & RWSEM_FLAG_HANDOFF) && - time_after(jiffies, waiter->timeout)) { - adjustment -= RWSEM_FLAG_HANDOFF; - lockevent_inc(rwsem_rlock_handoff); + if (time_after(jiffies, waiter->timeout)) { + if (!(oldcount & RWSEM_FLAG_HANDOFF)) { + adjustment -= RWSEM_FLAG_HANDOFF; + lockevent_inc(rwsem_rlock_handoff); + } + waiter->handoff_set = true; } atomic_long_add(-adjustment, &sem->count); @@ -599,7 +599,7 @@ rwsem_del_wake_waiter(struct rw_semaphore *sem, struct rwsem_waiter *waiter, static inline bool rwsem_try_write_lock(struct rw_semaphore *sem, struct rwsem_waiter *waiter) { - bool first = rwsem_first_waiter(sem) == waiter; + struct rwsem_waiter *first = rwsem_first_waiter(sem); long count, new; lockdep_assert_held(&sem->wait_lock); @@ -609,11 +609,20 @@ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem, bool has_handoff = !!(count & RWSEM_FLAG_HANDOFF); if (has_handoff) { - if (!first) + /* + * Honor handoff bit and yield only when the first + * waiter is the one that set it. Otherwisee, we + * still try to acquire the rwsem. + */ + if (first->handoff_set && (waiter != first)) return false; - /* First waiter inherits a previously set handoff bit */ - waiter->handoff_set = true; + /* + * First waiter can inherit a previously set handoff + * bit and spin on rwsem if lock acquisition fails. + */ + if (waiter == first) + waiter->handoff_set = true; } new = count; @@ -1027,6 +1036,7 @@ queue: waiter.task = current; waiter.type = RWSEM_WAITING_FOR_READ; waiter.timeout = jiffies + RWSEM_WAIT_TIMEOUT; + waiter.handoff_set = false; raw_spin_lock_irq(&sem->wait_lock); if (list_empty(&sem->wait_list)) { diff --git a/kernel/module/internal.h b/kernel/module/internal.h index bc5507ab8450..ec104c2950c3 100644 --- a/kernel/module/internal.h +++ b/kernel/module/internal.h @@ -11,6 +11,7 @@ #include <linux/mutex.h> #include <linux/rculist.h> #include <linux/rcupdate.h> +#include <linux/mm.h> #ifndef ARCH_SHF_SMALL #define ARCH_SHF_SMALL 0 @@ -30,11 +31,13 @@ * to ensure complete separation of code and data, but * only when CONFIG_STRICT_MODULE_RWX=y */ -#ifdef CONFIG_STRICT_MODULE_RWX -# define strict_align(X) PAGE_ALIGN(X) -#else -# define strict_align(X) (X) -#endif +static inline unsigned int strict_align(unsigned int size) +{ + if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) + return PAGE_ALIGN(size); + else + return size; +} extern struct mutex module_mutex; extern struct list_head modules; diff --git a/kernel/module/kallsyms.c b/kernel/module/kallsyms.c index 3e11523bc6f6..77e75bead569 100644 --- a/kernel/module/kallsyms.c +++ b/kernel/module/kallsyms.c @@ -137,6 +137,7 @@ void layout_symtab(struct module *mod, struct load_info *info) info->symoffs = ALIGN(mod->data_layout.size, symsect->sh_addralign ?: 1); info->stroffs = mod->data_layout.size = info->symoffs + ndst * sizeof(Elf_Sym); mod->data_layout.size += strtab_size; + /* Note add_kallsyms() computes strtab_size as core_typeoffs - stroffs */ info->core_typeoffs = mod->data_layout.size; mod->data_layout.size += ndst * sizeof(char); mod->data_layout.size = strict_align(mod->data_layout.size); @@ -169,19 +170,20 @@ void add_kallsyms(struct module *mod, const struct load_info *info) Elf_Sym *dst; char *s; Elf_Shdr *symsec = &info->sechdrs[info->index.sym]; + unsigned long strtab_size; /* Set up to point into init section. */ mod->kallsyms = (void __rcu *)mod->init_layout.base + info->mod_kallsyms_init_off; - preempt_disable(); + rcu_read_lock(); /* The following is safe since this pointer cannot change */ - rcu_dereference_sched(mod->kallsyms)->symtab = (void *)symsec->sh_addr; - rcu_dereference_sched(mod->kallsyms)->num_symtab = symsec->sh_size / sizeof(Elf_Sym); + rcu_dereference(mod->kallsyms)->symtab = (void *)symsec->sh_addr; + rcu_dereference(mod->kallsyms)->num_symtab = symsec->sh_size / sizeof(Elf_Sym); /* Make sure we get permanent strtab: don't use info->strtab. */ - rcu_dereference_sched(mod->kallsyms)->strtab = + rcu_dereference(mod->kallsyms)->strtab = (void *)info->sechdrs[info->index.str].sh_addr; - rcu_dereference_sched(mod->kallsyms)->typetab = mod->init_layout.base + info->init_typeoffs; + rcu_dereference(mod->kallsyms)->typetab = mod->init_layout.base + info->init_typeoffs; /* * Now populate the cut down core kallsyms for after init @@ -190,22 +192,29 @@ void add_kallsyms(struct module *mod, const struct load_info *info) mod->core_kallsyms.symtab = dst = mod->data_layout.base + info->symoffs; mod->core_kallsyms.strtab = s = mod->data_layout.base + info->stroffs; mod->core_kallsyms.typetab = mod->data_layout.base + info->core_typeoffs; - src = rcu_dereference_sched(mod->kallsyms)->symtab; - for (ndst = i = 0; i < rcu_dereference_sched(mod->kallsyms)->num_symtab; i++) { - rcu_dereference_sched(mod->kallsyms)->typetab[i] = elf_type(src + i, info); + strtab_size = info->core_typeoffs - info->stroffs; + src = rcu_dereference(mod->kallsyms)->symtab; + for (ndst = i = 0; i < rcu_dereference(mod->kallsyms)->num_symtab; i++) { + rcu_dereference(mod->kallsyms)->typetab[i] = elf_type(src + i, info); if (i == 0 || is_livepatch_module(mod) || is_core_symbol(src + i, info->sechdrs, info->hdr->e_shnum, info->index.pcpu)) { + ssize_t ret; + mod->core_kallsyms.typetab[ndst] = - rcu_dereference_sched(mod->kallsyms)->typetab[i]; + rcu_dereference(mod->kallsyms)->typetab[i]; dst[ndst] = src[i]; dst[ndst++].st_name = s - mod->core_kallsyms.strtab; - s += strscpy(s, - &rcu_dereference_sched(mod->kallsyms)->strtab[src[i].st_name], - KSYM_NAME_LEN) + 1; + ret = strscpy(s, + &rcu_dereference(mod->kallsyms)->strtab[src[i].st_name], + strtab_size); + if (ret < 0) + break; + s += ret + 1; + strtab_size -= ret + 1; } } - preempt_enable(); + rcu_read_unlock(); mod->core_kallsyms.num_symtab = ndst; } diff --git a/kernel/module/main.c b/kernel/module/main.c index fed58d30725d..0548151dd933 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -2939,24 +2939,25 @@ static void cfi_init(struct module *mod) { #ifdef CONFIG_CFI_CLANG initcall_t *init; +#ifdef CONFIG_MODULE_UNLOAD exitcall_t *exit; +#endif rcu_read_lock_sched(); mod->cfi_check = (cfi_check_fn) find_kallsyms_symbol_value(mod, "__cfi_check"); init = (initcall_t *) find_kallsyms_symbol_value(mod, "__cfi_jt_init_module"); - exit = (exitcall_t *) - find_kallsyms_symbol_value(mod, "__cfi_jt_cleanup_module"); - rcu_read_unlock_sched(); - /* Fix init/exit functions to point to the CFI jump table */ if (init) mod->init = *init; #ifdef CONFIG_MODULE_UNLOAD + exit = (exitcall_t *) + find_kallsyms_symbol_value(mod, "__cfi_jt_cleanup_module"); if (exit) mod->exit = *exit; #endif + rcu_read_unlock_sched(); cfi_module_add(mod, mod_tree.addr_min); #endif diff --git a/kernel/panic.c b/kernel/panic.c index a3c758dba15a..a3308af28a21 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -603,8 +603,6 @@ void __warn(const char *file, int line, void *caller, unsigned taint, { disable_trace_on_warning(); - printk_prefer_direct_enter(); - if (file) pr_warn("WARNING: CPU: %d PID: %d at %s:%d %pS\n", raw_smp_processor_id(), current->pid, file, line, @@ -634,8 +632,6 @@ void __warn(const char *file, int line, void *caller, unsigned taint, /* Just a warning, don't kill lockdep. */ add_taint(taint, LOCKDEP_STILL_OK); - - printk_prefer_direct_exit(); } #ifndef __WARN_FLAGS diff --git a/kernel/platform-feature.c b/kernel/platform-feature.c new file mode 100644 index 000000000000..cb6a6c3e4fed --- /dev/null +++ b/kernel/platform-feature.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bitops.h> +#include <linux/cache.h> +#include <linux/export.h> +#include <linux/platform-feature.h> + +#define PLATFORM_FEAT_ARRAY_SZ BITS_TO_LONGS(PLATFORM_FEAT_N) +static unsigned long __read_mostly platform_features[PLATFORM_FEAT_ARRAY_SZ]; + +void platform_set(unsigned int feature) +{ + set_bit(feature, platform_features); +} +EXPORT_SYMBOL_GPL(platform_set); + +void platform_clear(unsigned int feature) +{ + clear_bit(feature, platform_features); +} +EXPORT_SYMBOL_GPL(platform_clear); + +bool platform_has(unsigned int feature) +{ + return test_bit(feature, platform_features); +} +EXPORT_SYMBOL_GPL(platform_has); diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 20a66bf9f465..89c71fce225d 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -665,7 +665,7 @@ static void power_down(void) hibernation_platform_enter(); fallthrough; case HIBERNATION_SHUTDOWN: - if (pm_power_off) + if (kernel_can_power_off()) kernel_power_off(); break; } diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index ea3dd55709e7..a1a81fd9889b 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -224,33 +224,6 @@ int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, static int nr_ext_console_drivers; /* - * Used to synchronize printing kthreads against direct printing via - * console_trylock/console_unlock. - * - * Values: - * -1 = console kthreads atomically blocked (via global trylock) - * 0 = no kthread printing, console not locked (via trylock) - * >0 = kthread(s) actively printing - * - * Note: For synchronizing against direct printing via - * console_lock/console_unlock, see the @lock variable in - * struct console. - */ -static atomic_t console_kthreads_active = ATOMIC_INIT(0); - -#define console_kthreads_atomic_tryblock() \ - (atomic_cmpxchg(&console_kthreads_active, 0, -1) == 0) -#define console_kthreads_atomic_unblock() \ - atomic_cmpxchg(&console_kthreads_active, -1, 0) -#define console_kthreads_atomically_blocked() \ - (atomic_read(&console_kthreads_active) == -1) - -#define console_kthread_printing_tryenter() \ - atomic_inc_unless_negative(&console_kthreads_active) -#define console_kthread_printing_exit() \ - atomic_dec(&console_kthreads_active) - -/* * Helper macros to handle lockdep when locking/unlocking console_sem. We use * macros instead of functions so that _RET_IP_ contains useful information. */ @@ -298,49 +271,14 @@ static bool panic_in_progress(void) } /* - * Tracks whether kthread printers are all blocked. A value of true implies - * that the console is locked via console_lock() or the console is suspended. - * Writing to this variable requires holding @console_sem. - */ -static bool console_kthreads_blocked; - -/* - * Block all kthread printers from a schedulable context. - * - * Requires holding @console_sem. - */ -static void console_kthreads_block(void) -{ - struct console *con; - - for_each_console(con) { - mutex_lock(&con->lock); - con->blocked = true; - mutex_unlock(&con->lock); - } - - console_kthreads_blocked = true; -} - -/* - * Unblock all kthread printers from a schedulable context. - * - * Requires holding @console_sem. + * This is used for debugging the mess that is the VT code by + * keeping track if we have the console semaphore held. It's + * definitely not the perfect debug tool (we don't know if _WE_ + * hold it and are racing, but it helps tracking those weird code + * paths in the console code where we end up in places I want + * locked without the console semaphore held). */ -static void console_kthreads_unblock(void) -{ - struct console *con; - - for_each_console(con) { - mutex_lock(&con->lock); - con->blocked = false; - mutex_unlock(&con->lock); - } - - console_kthreads_blocked = false; -} - -static int console_suspended; +static int console_locked, console_suspended; /* * Array of consoles built from command line options (console=) @@ -423,75 +361,7 @@ static int console_msg_format = MSG_FORMAT_DEFAULT; /* syslog_lock protects syslog_* variables and write access to clear_seq. */ static DEFINE_MUTEX(syslog_lock); -/* - * A flag to signify if printk_activate_kthreads() has already started the - * kthread printers. If true, any later registered consoles must start their - * own kthread directly. The flag is write protected by the console_lock. - */ -static bool printk_kthreads_available; - #ifdef CONFIG_PRINTK -static atomic_t printk_prefer_direct = ATOMIC_INIT(0); - -/** - * printk_prefer_direct_enter - cause printk() calls to attempt direct - * printing to all enabled consoles - * - * Since it is not possible to call into the console printing code from any - * context, there is no guarantee that direct printing will occur. - * - * This globally effects all printk() callers. - * - * Context: Any context. - */ -void printk_prefer_direct_enter(void) -{ - atomic_inc(&printk_prefer_direct); -} - -/** - * printk_prefer_direct_exit - restore printk() behavior - * - * Context: Any context. - */ -void printk_prefer_direct_exit(void) -{ - WARN_ON(atomic_dec_if_positive(&printk_prefer_direct) < 0); -} - -/* - * Calling printk() always wakes kthread printers so that they can - * flush the new message to their respective consoles. Also, if direct - * printing is allowed, printk() tries to flush the messages directly. - * - * Direct printing is allowed in situations when the kthreads - * are not available or the system is in a problematic state. - * - * See the implementation about possible races. - */ -static inline bool allow_direct_printing(void) -{ - /* - * Checking kthread availability is a possible race because the - * kthread printers can become permanently disabled during runtime. - * However, doing that requires holding the console_lock, so any - * pending messages will be direct printed by console_unlock(). - */ - if (!printk_kthreads_available) - return true; - - /* - * Prefer direct printing when the system is in a problematic state. - * The context that sets this state will always see the updated value. - * The other contexts do not care. Anyway, direct printing is just a - * best effort. The direct output is only possible when console_lock - * is not already taken and no kthread printers are actively printing. - */ - return (system_state > SYSTEM_RUNNING || - oops_in_progress || - atomic_read(&printk_prefer_direct)); -} - DECLARE_WAIT_QUEUE_HEAD(log_wait); /* All 3 protected by @syslog_lock. */ /* the next printk record to read by syslog(READ) or /proc/kmsg */ @@ -2382,10 +2252,10 @@ asmlinkage int vprintk_emit(int facility, int level, printed_len = vprintk_store(facility, level, dev_info, fmt, args); /* If called from the scheduler, we can not call up(). */ - if (!in_sched && allow_direct_printing()) { + if (!in_sched) { /* * The caller may be holding system-critical or - * timing-sensitive locks. Disable preemption during direct + * timing-sensitive locks. Disable preemption during * printing of all remaining records to all consoles so that * this context can return as soon as possible. Hopefully * another printk() caller will take over the printing. @@ -2428,8 +2298,6 @@ EXPORT_SYMBOL(_printk); static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress); -static void printk_start_kthread(struct console *con); - #else /* CONFIG_PRINTK */ #define CONSOLE_LOG_MAX 0 @@ -2463,8 +2331,6 @@ static void call_console_driver(struct console *con, const char *text, size_t le } static bool suppress_message_printing(int level) { return false; } static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress) { return true; } -static void printk_start_kthread(struct console *con) { } -static bool allow_direct_printing(void) { return true; } #endif /* CONFIG_PRINTK */ @@ -2683,14 +2549,6 @@ static int console_cpu_notify(unsigned int cpu) /* If trylock fails, someone else is doing the printing */ if (console_trylock()) console_unlock(); - else { - /* - * If a new CPU comes online, the conditions for - * printer_should_wake() may have changed for some - * kthread printer with !CON_ANYTIME. - */ - wake_up_klogd(); - } } return 0; } @@ -2710,7 +2568,7 @@ void console_lock(void) down_console_sem(); if (console_suspended) return; - console_kthreads_block(); + console_locked = 1; console_may_schedule = 1; } EXPORT_SYMBOL(console_lock); @@ -2731,30 +2589,15 @@ int console_trylock(void) up_console_sem(); return 0; } - if (!console_kthreads_atomic_tryblock()) { - up_console_sem(); - return 0; - } + console_locked = 1; console_may_schedule = 0; return 1; } EXPORT_SYMBOL(console_trylock); -/* - * This is used to help to make sure that certain paths within the VT code are - * running with the console lock held. It is definitely not the perfect debug - * tool (it is not known if the VT code is the task holding the console lock), - * but it helps tracking those weird code paths in the console code such as - * when the console is suspended: where the console is not locked but no - * console printing may occur. - * - * Note: This returns true when the console is suspended but is not locked. - * This is intentional because the VT code must consider that situation - * the same as if the console was locked. - */ int is_console_locked(void) { - return (console_kthreads_blocked || atomic_read(&console_kthreads_active)); + return console_locked; } EXPORT_SYMBOL(is_console_locked); @@ -2777,9 +2620,18 @@ static bool abandon_console_lock_in_panic(void) return atomic_read(&panic_cpu) != raw_smp_processor_id(); } -static inline bool __console_is_usable(short flags) +/* + * Check if the given console is currently capable and allowed to print + * records. + * + * Requires the console_lock. + */ +static inline bool console_is_usable(struct console *con) { - if (!(flags & CON_ENABLED)) + if (!(con->flags & CON_ENABLED)) + return false; + + if (!con->write) return false; /* @@ -2788,43 +2640,15 @@ static inline bool __console_is_usable(short flags) * cope (CON_ANYTIME) don't call them until this CPU is officially up. */ if (!cpu_online(raw_smp_processor_id()) && - !(flags & CON_ANYTIME)) + !(con->flags & CON_ANYTIME)) return false; return true; } -/* - * Check if the given console is currently capable and allowed to print - * records. - * - * Requires holding the console_lock. - */ -static inline bool console_is_usable(struct console *con) -{ - if (!con->write) - return false; - - return __console_is_usable(con->flags); -} - static void __console_unlock(void) { - /* - * Depending on whether console_lock() or console_trylock() was used, - * appropriately allow the kthread printers to continue. - */ - if (console_kthreads_blocked) - console_kthreads_unblock(); - else - console_kthreads_atomic_unblock(); - - /* - * New records may have arrived while the console was locked. - * Wake the kthread printers to print them. - */ - wake_up_klogd(); - + console_locked = 0; up_console_sem(); } @@ -2842,19 +2666,17 @@ static void __console_unlock(void) * * @handover will be set to true if a printk waiter has taken over the * console_lock, in which case the caller is no longer holding the - * console_lock. Otherwise it is set to false. A NULL pointer may be provided - * to disable allowing the console_lock to be taken over by a printk waiter. + * console_lock. Otherwise it is set to false. * * Returns false if the given console has no next record to print, otherwise * true. * - * Requires the console_lock if @handover is non-NULL. - * Requires con->lock otherwise. + * Requires the console_lock. */ -static bool __console_emit_next_record(struct console *con, char *text, char *ext_text, - char *dropped_text, bool *handover) +static bool console_emit_next_record(struct console *con, char *text, char *ext_text, + char *dropped_text, bool *handover) { - static atomic_t panic_console_dropped = ATOMIC_INIT(0); + static int panic_console_dropped; struct printk_info info; struct printk_record r; unsigned long flags; @@ -2863,8 +2685,7 @@ static bool __console_emit_next_record(struct console *con, char *text, char *ex prb_rec_init_rd(&r, &info, text, CONSOLE_LOG_MAX); - if (handover) - *handover = false; + *handover = false; if (!prb_read_valid(prb, con->seq, &r)) return false; @@ -2872,8 +2693,7 @@ static bool __console_emit_next_record(struct console *con, char *text, char *ex if (con->seq != r.info->seq) { con->dropped += r.info->seq - con->seq; con->seq = r.info->seq; - if (panic_in_progress() && - atomic_fetch_inc_relaxed(&panic_console_dropped) > 10) { + if (panic_in_progress() && panic_console_dropped++ > 10) { suppress_panic_printk = 1; pr_warn_once("Too many dropped messages. Suppress messages on non-panic CPUs to prevent livelock.\n"); } @@ -2895,62 +2715,32 @@ static bool __console_emit_next_record(struct console *con, char *text, char *ex len = record_print_text(&r, console_msg_format & MSG_FORMAT_SYSLOG, printk_time); } - if (handover) { - /* - * While actively printing out messages, if another printk() - * were to occur on another CPU, it may wait for this one to - * finish. This task can not be preempted if there is a - * waiter waiting to take over. - * - * Interrupts are disabled because the hand over to a waiter - * must not be interrupted until the hand over is completed - * (@console_waiter is cleared). - */ - printk_safe_enter_irqsave(flags); - console_lock_spinning_enable(); - - /* don't trace irqsoff print latency */ - stop_critical_timings(); - } + /* + * While actively printing out messages, if another printk() + * were to occur on another CPU, it may wait for this one to + * finish. This task can not be preempted if there is a + * waiter waiting to take over. + * + * Interrupts are disabled because the hand over to a waiter + * must not be interrupted until the hand over is completed + * (@console_waiter is cleared). + */ + printk_safe_enter_irqsave(flags); + console_lock_spinning_enable(); + stop_critical_timings(); /* don't trace print latency */ call_console_driver(con, write_text, len, dropped_text); + start_critical_timings(); con->seq++; - if (handover) { - start_critical_timings(); - *handover = console_lock_spinning_disable_and_check(); - printk_safe_exit_irqrestore(flags); - } + *handover = console_lock_spinning_disable_and_check(); + printk_safe_exit_irqrestore(flags); skip: return true; } /* - * Print a record for a given console, but allow another printk() caller to - * take over the console_lock and continue printing. - * - * Requires the console_lock, but depending on @handover after the call, the - * caller may no longer have the console_lock. - * - * See __console_emit_next_record() for argument and return details. - */ -static bool console_emit_next_record_transferable(struct console *con, char *text, char *ext_text, - char *dropped_text, bool *handover) -{ - /* - * Handovers are only supported if threaded printers are atomically - * blocked. The context taking over the console_lock may be atomic. - */ - if (!console_kthreads_atomically_blocked()) { - *handover = false; - handover = NULL; - } - - return __console_emit_next_record(con, text, ext_text, dropped_text, handover); -} - -/* * Print out all remaining records to all consoles. * * @do_cond_resched is set by the caller. It can be true only in schedulable @@ -2968,8 +2758,8 @@ static bool console_emit_next_record_transferable(struct console *con, char *tex * were flushed to all usable consoles. A returned false informs the caller * that everything was not flushed (either there were no usable consoles or * another context has taken over printing or it is a panic situation and this - * is not the panic CPU or direct printing is not preferred). Regardless the - * reason, the caller should assume it is not useful to immediately try again. + * is not the panic CPU). Regardless the reason, the caller should assume it + * is not useful to immediately try again. * * Requires the console_lock. */ @@ -2986,10 +2776,6 @@ static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handove *handover = false; do { - /* Let the kthread printers do the work if they can. */ - if (!allow_direct_printing()) - return false; - any_progress = false; for_each_console(con) { @@ -3001,11 +2787,13 @@ static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handove if (con->flags & CON_EXTENDED) { /* Extended consoles do not print "dropped messages". */ - progress = console_emit_next_record_transferable(con, &text[0], - &ext_text[0], NULL, handover); + progress = console_emit_next_record(con, &text[0], + &ext_text[0], NULL, + handover); } else { - progress = console_emit_next_record_transferable(con, &text[0], - NULL, &dropped_text[0], handover); + progress = console_emit_next_record(con, &text[0], + NULL, &dropped_text[0], + handover); } if (*handover) return false; @@ -3120,13 +2908,10 @@ void console_unblank(void) if (oops_in_progress) { if (down_trylock_console_sem() != 0) return; - if (!console_kthreads_atomic_tryblock()) { - up_console_sem(); - return; - } } else console_lock(); + console_locked = 1; console_may_schedule = 0; for_each_console(c) if ((c->flags & CON_ENABLED) && c->unblank) @@ -3405,10 +3190,6 @@ void register_console(struct console *newcon) nr_ext_console_drivers++; newcon->dropped = 0; - newcon->thread = NULL; - newcon->blocked = true; - mutex_init(&newcon->lock); - if (newcon->flags & CON_PRINTBUFFER) { /* Get a consistent copy of @syslog_seq. */ mutex_lock(&syslog_lock); @@ -3418,10 +3199,6 @@ void register_console(struct console *newcon) /* Begin with next message. */ newcon->seq = prb_next_seq(prb); } - - if (printk_kthreads_available) - printk_start_kthread(newcon); - console_unlock(); console_sysfs_notify(); @@ -3448,7 +3225,6 @@ EXPORT_SYMBOL(register_console); int unregister_console(struct console *console) { - struct task_struct *thd; struct console *con; int res; @@ -3489,20 +3265,7 @@ int unregister_console(struct console *console) console_drivers->flags |= CON_CONSDEV; console->flags &= ~CON_ENABLED; - - /* - * console->thread can only be cleared under the console lock. But - * stopping the thread must be done without the console lock. The - * task that clears @thread is the task that stops the kthread. - */ - thd = console->thread; - console->thread = NULL; - console_unlock(); - - if (thd) - kthread_stop(thd); - console_sysfs_notify(); if (console->exit) @@ -3598,20 +3361,6 @@ static int __init printk_late_init(void) } late_initcall(printk_late_init); -static int __init printk_activate_kthreads(void) -{ - struct console *con; - - console_lock(); - printk_kthreads_available = true; - for_each_console(con) - printk_start_kthread(con); - console_unlock(); - - return 0; -} -early_initcall(printk_activate_kthreads); - #if defined CONFIG_PRINTK /* If @con is specified, only wait for that console. Otherwise wait for all. */ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress) @@ -3631,6 +3380,7 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre diff = 0; console_lock(); + for_each_console(c) { if (con && con != c) continue; @@ -3640,11 +3390,19 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre if (printk_seq < seq) diff += seq - printk_seq; } - console_unlock(); - if (diff != last_diff && reset_on_progress) + /* + * If consoles are suspended, it cannot be expected that they + * make forward progress, so timeout immediately. @diff is + * still used to return a valid flush status. + */ + if (console_suspended) + remaining = 0; + else if (diff != last_diff && reset_on_progress) remaining = timeout_ms; + console_unlock(); + if (diff == 0 || remaining == 0) break; @@ -3686,206 +3444,11 @@ bool pr_flush(int timeout_ms, bool reset_on_progress) } EXPORT_SYMBOL(pr_flush); -static void __printk_fallback_preferred_direct(void) -{ - printk_prefer_direct_enter(); - pr_err("falling back to preferred direct printing\n"); - printk_kthreads_available = false; -} - -/* - * Enter preferred direct printing, but never exit. Mark console threads as - * unavailable. The system is then forever in preferred direct printing and - * any printing threads will exit. - * - * Must *not* be called under console_lock. Use - * __printk_fallback_preferred_direct() if already holding console_lock. - */ -static void printk_fallback_preferred_direct(void) -{ - console_lock(); - __printk_fallback_preferred_direct(); - console_unlock(); -} - -/* - * Print a record for a given console, not allowing another printk() caller - * to take over. This is appropriate for contexts that do not have the - * console_lock. - * - * See __console_emit_next_record() for argument and return details. - */ -static bool console_emit_next_record(struct console *con, char *text, char *ext_text, - char *dropped_text) -{ - return __console_emit_next_record(con, text, ext_text, dropped_text, NULL); -} - -static bool printer_should_wake(struct console *con, u64 seq) -{ - short flags; - - if (kthread_should_stop() || !printk_kthreads_available) - return true; - - if (con->blocked || - console_kthreads_atomically_blocked()) { - return false; - } - - /* - * This is an unsafe read from con->flags, but a false positive is - * not a problem. Worst case it would allow the printer to wake up - * although it is disabled. But the printer will notice that when - * attempting to print and instead go back to sleep. - */ - flags = data_race(READ_ONCE(con->flags)); - - if (!__console_is_usable(flags)) - return false; - - return prb_read_valid(prb, seq, NULL); -} - -static int printk_kthread_func(void *data) -{ - struct console *con = data; - char *dropped_text = NULL; - char *ext_text = NULL; - u64 seq = 0; - char *text; - int error; - - text = kmalloc(CONSOLE_LOG_MAX, GFP_KERNEL); - if (!text) { - con_printk(KERN_ERR, con, "failed to allocate text buffer\n"); - printk_fallback_preferred_direct(); - goto out; - } - - if (con->flags & CON_EXTENDED) { - ext_text = kmalloc(CONSOLE_EXT_LOG_MAX, GFP_KERNEL); - if (!ext_text) { - con_printk(KERN_ERR, con, "failed to allocate ext_text buffer\n"); - printk_fallback_preferred_direct(); - goto out; - } - } else { - dropped_text = kmalloc(DROPPED_TEXT_MAX, GFP_KERNEL); - if (!dropped_text) { - con_printk(KERN_ERR, con, "failed to allocate dropped_text buffer\n"); - printk_fallback_preferred_direct(); - goto out; - } - } - - con_printk(KERN_INFO, con, "printing thread started\n"); - - for (;;) { - /* - * Guarantee this task is visible on the waitqueue before - * checking the wake condition. - * - * The full memory barrier within set_current_state() of - * prepare_to_wait_event() pairs with the full memory barrier - * within wq_has_sleeper(). - * - * This pairs with __wake_up_klogd:A. - */ - error = wait_event_interruptible(log_wait, - printer_should_wake(con, seq)); /* LMM(printk_kthread_func:A) */ - - if (kthread_should_stop() || !printk_kthreads_available) - break; - - if (error) - continue; - - error = mutex_lock_interruptible(&con->lock); - if (error) - continue; - - if (con->blocked || - !console_kthread_printing_tryenter()) { - /* Another context has locked the console_lock. */ - mutex_unlock(&con->lock); - continue; - } - - /* - * Although this context has not locked the console_lock, it - * is known that the console_lock is not locked and it is not - * possible for any other context to lock the console_lock. - * Therefore it is safe to read con->flags. - */ - - if (!__console_is_usable(con->flags)) { - console_kthread_printing_exit(); - mutex_unlock(&con->lock); - continue; - } - - /* - * Even though the printk kthread is always preemptible, it is - * still not allowed to call cond_resched() from within - * console drivers. The task may become non-preemptible in the - * console driver call chain. For example, vt_console_print() - * takes a spinlock and then can call into fbcon_redraw(), - * which can conditionally invoke cond_resched(). - */ - console_may_schedule = 0; - console_emit_next_record(con, text, ext_text, dropped_text); - - seq = con->seq; - - console_kthread_printing_exit(); - - mutex_unlock(&con->lock); - } - - con_printk(KERN_INFO, con, "printing thread stopped\n"); -out: - kfree(dropped_text); - kfree(ext_text); - kfree(text); - - console_lock(); - /* - * If this kthread is being stopped by another task, con->thread will - * already be NULL. That is fine. The important thing is that it is - * NULL after the kthread exits. - */ - con->thread = NULL; - console_unlock(); - - return 0; -} - -/* Must be called under console_lock. */ -static void printk_start_kthread(struct console *con) -{ - /* - * Do not start a kthread if there is no write() callback. The - * kthreads assume the write() callback exists. - */ - if (!con->write) - return; - - con->thread = kthread_run(printk_kthread_func, con, - "pr/%s%d", con->name, con->index); - if (IS_ERR(con->thread)) { - con->thread = NULL; - con_printk(KERN_ERR, con, "unable to start printing thread\n"); - __printk_fallback_preferred_direct(); - return; - } -} - /* * Delayed printk version, for scheduler-internal messages: */ -#define PRINTK_PENDING_WAKEUP 0x01 -#define PRINTK_PENDING_DIRECT_OUTPUT 0x02 +#define PRINTK_PENDING_WAKEUP 0x01 +#define PRINTK_PENDING_OUTPUT 0x02 static DEFINE_PER_CPU(int, printk_pending); @@ -3893,14 +3456,10 @@ static void wake_up_klogd_work_func(struct irq_work *irq_work) { int pending = this_cpu_xchg(printk_pending, 0); - if (pending & PRINTK_PENDING_DIRECT_OUTPUT) { - printk_prefer_direct_enter(); - + if (pending & PRINTK_PENDING_OUTPUT) { /* If trylock fails, someone else is doing the printing */ if (console_trylock()) console_unlock(); - - printk_prefer_direct_exit(); } if (pending & PRINTK_PENDING_WAKEUP) @@ -3925,11 +3484,10 @@ static void __wake_up_klogd(int val) * prepare_to_wait_event(), which is called after ___wait_event() adds * the waiter but before it has checked the wait condition. * - * This pairs with devkmsg_read:A, syslog_print:A, and - * printk_kthread_func:A. + * This pairs with devkmsg_read:A and syslog_print:A. */ if (wq_has_sleeper(&log_wait) || /* LMM(__wake_up_klogd:A) */ - (val & PRINTK_PENDING_DIRECT_OUTPUT)) { + (val & PRINTK_PENDING_OUTPUT)) { this_cpu_or(printk_pending, val); irq_work_queue(this_cpu_ptr(&wake_up_klogd_work)); } @@ -3947,17 +3505,7 @@ void defer_console_output(void) * New messages may have been added directly to the ringbuffer * using vprintk_store(), so wake any waiters as well. */ - int val = PRINTK_PENDING_WAKEUP; - - /* - * Make sure that some context will print the messages when direct - * printing is allowed. This happens in situations when the kthreads - * may not be as reliable or perhaps unusable. - */ - if (allow_direct_printing()) - val |= PRINTK_PENDING_DIRECT_OUTPUT; - - __wake_up_klogd(val); + __wake_up_klogd(PRINTK_PENDING_WAKEUP | PRINTK_PENDING_OUTPUT); } void printk_trigger_flush(void) diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 156a99283b11..1893d909e45c 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -222,7 +222,7 @@ static void ptrace_unfreeze_traced(struct task_struct *task) if (lock_task_sighand(task, &flags)) { task->jobctl &= ~JOBCTL_PTRACE_FROZEN; if (__fatal_signal_pending(task)) { - task->jobctl &= ~TASK_TRACED; + task->jobctl &= ~JOBCTL_TRACED; wake_up_state(task, __TASK_TRACED); } unlock_task_sighand(task, &flags); diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index 50ba70f019de..1c304fec89c0 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -511,10 +511,52 @@ static bool srcu_readers_active(struct srcu_struct *ssp) return sum; } -#define SRCU_INTERVAL 1 // Base delay if no expedited GPs pending. -#define SRCU_MAX_INTERVAL 10 // Maximum incremental delay from slow readers. -#define SRCU_MAX_NODELAY_PHASE 1 // Maximum per-GP-phase consecutive no-delay instances. -#define SRCU_MAX_NODELAY 100 // Maximum consecutive no-delay instances. +/* + * We use an adaptive strategy for synchronize_srcu() and especially for + * synchronize_srcu_expedited(). We spin for a fixed time period + * (defined below, boot time configurable) to allow SRCU readers to exit + * their read-side critical sections. If there are still some readers + * after one jiffy, we repeatedly block for one jiffy time periods. + * The blocking time is increased as the grace-period age increases, + * with max blocking time capped at 10 jiffies. + */ +#define SRCU_DEFAULT_RETRY_CHECK_DELAY 5 + +static ulong srcu_retry_check_delay = SRCU_DEFAULT_RETRY_CHECK_DELAY; +module_param(srcu_retry_check_delay, ulong, 0444); + +#define SRCU_INTERVAL 1 // Base delay if no expedited GPs pending. +#define SRCU_MAX_INTERVAL 10 // Maximum incremental delay from slow readers. + +#define SRCU_DEFAULT_MAX_NODELAY_PHASE_LO 3UL // Lowmark on default per-GP-phase + // no-delay instances. +#define SRCU_DEFAULT_MAX_NODELAY_PHASE_HI 1000UL // Highmark on default per-GP-phase + // no-delay instances. + +#define SRCU_UL_CLAMP_LO(val, low) ((val) > (low) ? (val) : (low)) +#define SRCU_UL_CLAMP_HI(val, high) ((val) < (high) ? (val) : (high)) +#define SRCU_UL_CLAMP(val, low, high) SRCU_UL_CLAMP_HI(SRCU_UL_CLAMP_LO((val), (low)), (high)) +// per-GP-phase no-delay instances adjusted to allow non-sleeping poll upto +// one jiffies time duration. Mult by 2 is done to factor in the srcu_get_delay() +// called from process_srcu(). +#define SRCU_DEFAULT_MAX_NODELAY_PHASE_ADJUSTED \ + (2UL * USEC_PER_SEC / HZ / SRCU_DEFAULT_RETRY_CHECK_DELAY) + +// Maximum per-GP-phase consecutive no-delay instances. +#define SRCU_DEFAULT_MAX_NODELAY_PHASE \ + SRCU_UL_CLAMP(SRCU_DEFAULT_MAX_NODELAY_PHASE_ADJUSTED, \ + SRCU_DEFAULT_MAX_NODELAY_PHASE_LO, \ + SRCU_DEFAULT_MAX_NODELAY_PHASE_HI) + +static ulong srcu_max_nodelay_phase = SRCU_DEFAULT_MAX_NODELAY_PHASE; +module_param(srcu_max_nodelay_phase, ulong, 0444); + +// Maximum consecutive no-delay instances. +#define SRCU_DEFAULT_MAX_NODELAY (SRCU_DEFAULT_MAX_NODELAY_PHASE > 100 ? \ + SRCU_DEFAULT_MAX_NODELAY_PHASE : 100) + +static ulong srcu_max_nodelay = SRCU_DEFAULT_MAX_NODELAY; +module_param(srcu_max_nodelay, ulong, 0444); /* * Return grace-period delay, zero if there are expedited grace @@ -522,16 +564,22 @@ static bool srcu_readers_active(struct srcu_struct *ssp) */ static unsigned long srcu_get_delay(struct srcu_struct *ssp) { + unsigned long gpstart; + unsigned long j; unsigned long jbase = SRCU_INTERVAL; if (ULONG_CMP_LT(READ_ONCE(ssp->srcu_gp_seq), READ_ONCE(ssp->srcu_gp_seq_needed_exp))) jbase = 0; - if (rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq))) - jbase += jiffies - READ_ONCE(ssp->srcu_gp_start); - if (!jbase) { - WRITE_ONCE(ssp->srcu_n_exp_nodelay, READ_ONCE(ssp->srcu_n_exp_nodelay) + 1); - if (READ_ONCE(ssp->srcu_n_exp_nodelay) > SRCU_MAX_NODELAY_PHASE) - jbase = 1; + if (rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq))) { + j = jiffies - 1; + gpstart = READ_ONCE(ssp->srcu_gp_start); + if (time_after(j, gpstart)) + jbase += j - gpstart; + if (!jbase) { + WRITE_ONCE(ssp->srcu_n_exp_nodelay, READ_ONCE(ssp->srcu_n_exp_nodelay) + 1); + if (READ_ONCE(ssp->srcu_n_exp_nodelay) > srcu_max_nodelay_phase) + jbase = 1; + } } return jbase > SRCU_MAX_INTERVAL ? SRCU_MAX_INTERVAL : jbase; } @@ -607,15 +655,6 @@ void __srcu_read_unlock(struct srcu_struct *ssp, int idx) EXPORT_SYMBOL_GPL(__srcu_read_unlock); /* - * We use an adaptive strategy for synchronize_srcu() and especially for - * synchronize_srcu_expedited(). We spin for a fixed time period - * (defined below) to allow SRCU readers to exit their read-side critical - * sections. If there are still some readers after a few microseconds, - * we repeatedly block for 1-millisecond time periods. - */ -#define SRCU_RETRY_CHECK_DELAY 5 - -/* * Start an SRCU grace period. */ static void srcu_gp_start(struct srcu_struct *ssp) @@ -700,7 +739,7 @@ static void srcu_schedule_cbs_snp(struct srcu_struct *ssp, struct srcu_node *snp */ static void srcu_gp_end(struct srcu_struct *ssp) { - unsigned long cbdelay; + unsigned long cbdelay = 1; bool cbs; bool last_lvl; int cpu; @@ -720,7 +759,9 @@ static void srcu_gp_end(struct srcu_struct *ssp) spin_lock_irq_rcu_node(ssp); idx = rcu_seq_state(ssp->srcu_gp_seq); WARN_ON_ONCE(idx != SRCU_STATE_SCAN2); - cbdelay = !!srcu_get_delay(ssp); + if (ULONG_CMP_LT(READ_ONCE(ssp->srcu_gp_seq), READ_ONCE(ssp->srcu_gp_seq_needed_exp))) + cbdelay = 0; + WRITE_ONCE(ssp->srcu_last_gp_end, ktime_get_mono_fast_ns()); rcu_seq_end(&ssp->srcu_gp_seq); gpseq = rcu_seq_current(&ssp->srcu_gp_seq); @@ -921,12 +962,16 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp, */ static bool try_check_zero(struct srcu_struct *ssp, int idx, int trycount) { + unsigned long curdelay; + + curdelay = !srcu_get_delay(ssp); + for (;;) { if (srcu_readers_active_idx_check(ssp, idx)) return true; - if (--trycount + !srcu_get_delay(ssp) <= 0) + if ((--trycount + curdelay) <= 0) return false; - udelay(SRCU_RETRY_CHECK_DELAY); + udelay(srcu_retry_check_delay); } } @@ -1582,7 +1627,7 @@ static void process_srcu(struct work_struct *work) j = jiffies; if (READ_ONCE(ssp->reschedule_jiffies) == j) { WRITE_ONCE(ssp->reschedule_count, READ_ONCE(ssp->reschedule_count) + 1); - if (READ_ONCE(ssp->reschedule_count) > SRCU_MAX_NODELAY) + if (READ_ONCE(ssp->reschedule_count) > srcu_max_nodelay) curdelay = 1; } else { WRITE_ONCE(ssp->reschedule_count, 1); @@ -1674,6 +1719,11 @@ static int __init srcu_bootup_announce(void) pr_info("Hierarchical SRCU implementation.\n"); if (exp_holdoff != DEFAULT_SRCU_EXP_HOLDOFF) pr_info("\tNon-default auto-expedite holdoff of %lu ns.\n", exp_holdoff); + if (srcu_retry_check_delay != SRCU_DEFAULT_RETRY_CHECK_DELAY) + pr_info("\tNon-default retry check delay of %lu us.\n", srcu_retry_check_delay); + if (srcu_max_nodelay != SRCU_DEFAULT_MAX_NODELAY) + pr_info("\tNon-default max no-delay of %lu.\n", srcu_max_nodelay); + pr_info("\tMax phase no-delay instances is %lu.\n", srcu_max_nodelay_phase); return 0; } early_initcall(srcu_bootup_announce); diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index 4995c078cff9..a001e1e7a992 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -647,7 +647,6 @@ static void print_cpu_stall(unsigned long gps) * See Documentation/RCU/stallwarn.rst for info on how to debug * RCU CPU stall warnings. */ - printk_prefer_direct_enter(); trace_rcu_stall_warning(rcu_state.name, TPS("SelfDetected")); pr_err("INFO: %s self-detected stall on CPU\n", rcu_state.name); raw_spin_lock_irqsave_rcu_node(rdp->mynode, flags); @@ -685,7 +684,6 @@ static void print_cpu_stall(unsigned long gps) */ set_tsk_need_resched(current); set_preempt_need_resched(); - printk_prefer_direct_exit(); } static void check_cpu_stall(struct rcu_data *rdp) diff --git a/kernel/reboot.c b/kernel/reboot.c index a091145ee710..3c35445bf5ad 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -315,6 +315,43 @@ static int sys_off_notify(struct notifier_block *nb, return handler->sys_off_cb(&data); } +static struct sys_off_handler platform_sys_off_handler; + +static struct sys_off_handler *alloc_sys_off_handler(int priority) +{ + struct sys_off_handler *handler; + gfp_t flags; + + /* + * Platforms like m68k can't allocate sys_off handler dynamically + * at the early boot time because memory allocator isn't available yet. + */ + if (priority == SYS_OFF_PRIO_PLATFORM) { + handler = &platform_sys_off_handler; + if (handler->cb_data) + return ERR_PTR(-EBUSY); + } else { + if (system_state > SYSTEM_RUNNING) + flags = GFP_ATOMIC; + else + flags = GFP_KERNEL; + + handler = kzalloc(sizeof(*handler), flags); + if (!handler) + return ERR_PTR(-ENOMEM); + } + + return handler; +} + +static void free_sys_off_handler(struct sys_off_handler *handler) +{ + if (handler == &platform_sys_off_handler) + memset(handler, 0, sizeof(*handler)); + else + kfree(handler); +} + /** * register_sys_off_handler - Register sys-off handler * @mode: Sys-off mode @@ -345,9 +382,9 @@ register_sys_off_handler(enum sys_off_mode mode, struct sys_off_handler *handler; int err; - handler = kzalloc(sizeof(*handler), GFP_KERNEL); - if (!handler) - return ERR_PTR(-ENOMEM); + handler = alloc_sys_off_handler(priority); + if (IS_ERR(handler)) + return handler; switch (mode) { case SYS_OFF_MODE_POWER_OFF_PREPARE: @@ -364,7 +401,7 @@ register_sys_off_handler(enum sys_off_mode mode, break; default: - kfree(handler); + free_sys_off_handler(handler); return ERR_PTR(-EINVAL); } @@ -391,7 +428,7 @@ register_sys_off_handler(enum sys_off_mode mode, } if (err) { - kfree(handler); + free_sys_off_handler(handler); return ERR_PTR(err); } @@ -409,7 +446,7 @@ void unregister_sys_off_handler(struct sys_off_handler *handler) { int err; - if (!handler) + if (IS_ERR_OR_NULL(handler)) return; if (handler->blocking) @@ -422,7 +459,7 @@ void unregister_sys_off_handler(struct sys_off_handler *handler) /* sanity check, shall never happen */ WARN_ON(err); - kfree(handler); + free_sys_off_handler(handler); } EXPORT_SYMBOL_GPL(unregister_sys_off_handler); @@ -584,7 +621,23 @@ static void do_kernel_power_off_prepare(void) */ void do_kernel_power_off(void) { + struct sys_off_handler *sys_off = NULL; + + /* + * Register sys-off handlers for legacy PM callback. This allows + * legacy PM callbacks temporary co-exist with the new sys-off API. + * + * TODO: Remove legacy handlers once all legacy PM users will be + * switched to the sys-off based APIs. + */ + if (pm_power_off) + sys_off = register_sys_off_handler(SYS_OFF_MODE_POWER_OFF, + SYS_OFF_PRIO_DEFAULT, + legacy_pm_power_off, NULL); + atomic_notifier_call_chain(&power_off_handler_list, 0, NULL); + + unregister_sys_off_handler(sys_off); } /** @@ -595,7 +648,8 @@ void do_kernel_power_off(void) */ bool kernel_can_power_off(void) { - return !atomic_notifier_call_chain_is_empty(&power_off_handler_list); + return !atomic_notifier_call_chain_is_empty(&power_off_handler_list) || + pm_power_off; } EXPORT_SYMBOL_GPL(kernel_can_power_off); @@ -630,7 +684,6 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd, void __user *, arg) { struct pid_namespace *pid_ns = task_active_pid_ns(current); - struct sys_off_handler *sys_off = NULL; char buffer[256]; int ret = 0; @@ -655,21 +708,6 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd, if (ret) return ret; - /* - * Register sys-off handlers for legacy PM callback. This allows - * legacy PM callbacks temporary co-exist with the new sys-off API. - * - * TODO: Remove legacy handlers once all legacy PM users will be - * switched to the sys-off based APIs. - */ - if (pm_power_off) { - sys_off = register_sys_off_handler(SYS_OFF_MODE_POWER_OFF, - SYS_OFF_PRIO_DEFAULT, - legacy_pm_power_off, NULL); - if (IS_ERR(sys_off)) - return PTR_ERR(sys_off); - } - /* Instead of trying to make the power_off code look like * halt when pm_power_off is not set do it the easy way. */ @@ -727,7 +765,6 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd, break; } mutex_unlock(&system_transition_mutex); - unregister_sys_off_handler(sys_off); return ret; } @@ -782,11 +819,9 @@ static int __orderly_reboot(void) ret = run_cmd(reboot_cmd); if (ret) { - printk_prefer_direct_enter(); pr_warn("Failed to start orderly reboot: forcing the issue\n"); emergency_sync(); kernel_restart(NULL); - printk_prefer_direct_exit(); } return ret; @@ -799,7 +834,6 @@ static int __orderly_poweroff(bool force) ret = run_cmd(poweroff_cmd); if (ret && force) { - printk_prefer_direct_enter(); pr_warn("Failed to start orderly shutdown: forcing the issue\n"); /* @@ -809,7 +843,6 @@ static int __orderly_poweroff(bool force) */ emergency_sync(); kernel_power_off(); - printk_prefer_direct_exit(); } return ret; @@ -867,8 +900,6 @@ EXPORT_SYMBOL_GPL(orderly_reboot); */ static void hw_failure_emergency_poweroff_func(struct work_struct *work) { - printk_prefer_direct_enter(); - /* * We have reached here after the emergency shutdown waiting period has * expired. This means orderly_poweroff has not been able to shut off @@ -885,8 +916,6 @@ static void hw_failure_emergency_poweroff_func(struct work_struct *work) */ pr_emerg("Hardware protection shutdown failed. Trying emergency restart\n"); emergency_restart(); - - printk_prefer_direct_exit(); } static DECLARE_DELAYED_WORK(hw_failure_emergency_poweroff_work, @@ -925,13 +954,11 @@ void hw_protection_shutdown(const char *reason, int ms_until_forced) { static atomic_t allow_proceed = ATOMIC_INIT(1); - printk_prefer_direct_enter(); - pr_emerg("HARDWARE PROTECTION shutdown (%s)\n", reason); /* Shutdown should be initiated only once. */ if (!atomic_dec_and_test(&allow_proceed)) - goto out; + return; /* * Queue a backup emergency shutdown in the event of @@ -939,8 +966,6 @@ void hw_protection_shutdown(const char *reason, int ms_until_forced) */ hw_failure_emergency_poweroff(ms_until_forced); orderly_poweroff(true); -out: - printk_prefer_direct_exit(); } EXPORT_SYMBOL_GPL(hw_protection_shutdown); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index bfa7452ca92e..da0bf6fe9ecd 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4798,25 +4798,55 @@ static void do_balance_callbacks(struct rq *rq, struct callback_head *head) static void balance_push(struct rq *rq); +/* + * balance_push_callback is a right abuse of the callback interface and plays + * by significantly different rules. + * + * Where the normal balance_callback's purpose is to be ran in the same context + * that queued it (only later, when it's safe to drop rq->lock again), + * balance_push_callback is specifically targeted at __schedule(). + * + * This abuse is tolerated because it places all the unlikely/odd cases behind + * a single test, namely: rq->balance_callback == NULL. + */ struct callback_head balance_push_callback = { .next = NULL, .func = (void (*)(struct callback_head *))balance_push, }; -static inline struct callback_head *splice_balance_callbacks(struct rq *rq) +static inline struct callback_head * +__splice_balance_callbacks(struct rq *rq, bool split) { struct callback_head *head = rq->balance_callback; + if (likely(!head)) + return NULL; + lockdep_assert_rq_held(rq); - if (head) + /* + * Must not take balance_push_callback off the list when + * splice_balance_callbacks() and balance_callbacks() are not + * in the same rq->lock section. + * + * In that case it would be possible for __schedule() to interleave + * and observe the list empty. + */ + if (split && head == &balance_push_callback) + head = NULL; + else rq->balance_callback = NULL; return head; } +static inline struct callback_head *splice_balance_callbacks(struct rq *rq) +{ + return __splice_balance_callbacks(rq, true); +} + static void __balance_callbacks(struct rq *rq) { - do_balance_callbacks(rq, splice_balance_callbacks(rq)); + do_balance_callbacks(rq, __splice_balance_callbacks(rq, false)); } static inline void balance_callbacks(struct rq *rq, struct callback_head *head) diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index b5152961b743..7bf561262cb8 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1701,7 +1701,10 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) * the throttle. */ p->dl.dl_throttled = 0; - BUG_ON(!is_dl_boosted(&p->dl) || flags != ENQUEUE_REPLENISH); + if (!(flags & ENQUEUE_REPLENISH)) + printk_deferred_once("sched: DL de-boosted task PID %d: REPLENISH flag missing\n", + task_pid_nr(p)); + return; } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 01259611beb9..47b89a0fc6e5 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1693,6 +1693,11 @@ queue_balance_callback(struct rq *rq, { lockdep_assert_rq_held(rq); + /* + * Don't (re)queue an already queued item; nor queue anything when + * balance_push() is active, see the comment with + * balance_push_callback. + */ if (unlikely(head->next || rq->balance_callback == &balance_push_callback)) return; diff --git a/kernel/signal.c b/kernel/signal.c index edb1dc9b00dc..6f86fda5e432 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2029,12 +2029,12 @@ bool do_notify_parent(struct task_struct *tsk, int sig) bool autoreap = false; u64 utime, stime; - BUG_ON(sig == -1); + WARN_ON_ONCE(sig == -1); - /* do_notify_parent_cldstop should have been called instead. */ - BUG_ON(task_is_stopped_or_traced(tsk)); + /* do_notify_parent_cldstop should have been called instead. */ + WARN_ON_ONCE(task_is_stopped_or_traced(tsk)); - BUG_ON(!tsk->ptrace && + WARN_ON_ONCE(!tsk->ptrace && (tsk->group_leader != tsk || !thread_group_empty(tsk))); /* Wake up all pidfd waiters */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index e52b6e372c60..35d034219513 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -446,14 +446,14 @@ static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp, if (*negp) { if (*lvalp > (unsigned long) INT_MAX + 1) return -EINVAL; - *valp = -*lvalp; + WRITE_ONCE(*valp, -*lvalp); } else { if (*lvalp > (unsigned long) INT_MAX) return -EINVAL; - *valp = *lvalp; + WRITE_ONCE(*valp, *lvalp); } } else { - int val = *valp; + int val = READ_ONCE(*valp); if (val < 0) { *negp = true; *lvalp = -(unsigned long)val; @@ -472,9 +472,9 @@ static int do_proc_douintvec_conv(unsigned long *lvalp, if (write) { if (*lvalp > UINT_MAX) return -EINVAL; - *valp = *lvalp; + WRITE_ONCE(*valp, *lvalp); } else { - unsigned int val = *valp; + unsigned int val = READ_ONCE(*valp); *lvalp = (unsigned long)val; } return 0; @@ -857,7 +857,7 @@ static int do_proc_dointvec_minmax_conv(bool *negp, unsigned long *lvalp, if ((param->min && *param->min > tmp) || (param->max && *param->max < tmp)) return -EINVAL; - *valp = tmp; + WRITE_ONCE(*valp, tmp); } return 0; @@ -923,7 +923,7 @@ static int do_proc_douintvec_minmax_conv(unsigned long *lvalp, (param->max && *param->max < tmp)) return -ERANGE; - *valp = tmp; + WRITE_ONCE(*valp, tmp); } return 0; @@ -1007,13 +1007,13 @@ int proc_dou8vec_minmax(struct ctl_table *table, int write, tmp.maxlen = sizeof(val); tmp.data = &val; - val = *data; + val = READ_ONCE(*data); res = do_proc_douintvec(&tmp, write, buffer, lenp, ppos, do_proc_douintvec_minmax_conv, ¶m); if (res) return res; if (write) - *data = val; + WRITE_ONCE(*data, val); return 0; } EXPORT_SYMBOL_GPL(proc_dou8vec_minmax); @@ -1090,9 +1090,9 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, err = -EINVAL; break; } - *i = val; + WRITE_ONCE(*i, val); } else { - val = convdiv * (*i) / convmul; + val = convdiv * READ_ONCE(*i) / convmul; if (!first) proc_put_char(&buffer, &left, '\t'); proc_put_long(&buffer, &left, val, false); @@ -1173,9 +1173,12 @@ static int do_proc_dointvec_jiffies_conv(bool *negp, unsigned long *lvalp, if (write) { if (*lvalp > INT_MAX / HZ) return 1; - *valp = *negp ? -(*lvalp*HZ) : (*lvalp*HZ); + if (*negp) + WRITE_ONCE(*valp, -*lvalp * HZ); + else + WRITE_ONCE(*valp, *lvalp * HZ); } else { - int val = *valp; + int val = READ_ONCE(*valp); unsigned long lval; if (val < 0) { *negp = true; @@ -1221,9 +1224,9 @@ static int do_proc_dointvec_ms_jiffies_conv(bool *negp, unsigned long *lvalp, if (jif > INT_MAX) return 1; - *valp = (int)jif; + WRITE_ONCE(*valp, (int)jif); } else { - int val = *valp; + int val = READ_ONCE(*valp); unsigned long lval; if (val < 0) { *negp = true; @@ -1291,8 +1294,8 @@ int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, * @ppos: the current position in the file * * Reads/writes up to table->maxlen/sizeof(unsigned int) integer - * values from/to the user buffer, treated as an ASCII string. - * The values read are assumed to be in 1/1000 seconds, and + * values from/to the user buffer, treated as an ASCII string. + * The values read are assumed to be in 1/1000 seconds, and * are converted into jiffies. * * Returns 0 on success. @@ -2091,6 +2094,17 @@ static struct ctl_table vm_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO_HUNDRED, }, +#ifdef CONFIG_NUMA + { + .procname = "numa_stat", + .data = &sysctl_vm_numa_stat, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = sysctl_vm_numa_stat_handler, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, +#endif #ifdef CONFIG_HUGETLB_PAGE { .procname = "nr_hugepages", @@ -2107,15 +2121,6 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = &hugetlb_mempolicy_sysctl_handler, }, - { - .procname = "numa_stat", - .data = &sysctl_vm_numa_stat, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = sysctl_vm_numa_stat_handler, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, #endif { .procname = "hugetlb_shm_group", diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 1cd10b102c51..5dead89308b7 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -1051,15 +1051,24 @@ retry_delete: } /* - * This is called by do_exit or de_thread, only when there are no more - * references to the shared signal_struct. + * This is called by do_exit or de_thread, only when nobody else can + * modify the signal->posix_timers list. Yet we need sighand->siglock + * to prevent the race with /proc/pid/timers. */ -void exit_itimers(struct signal_struct *sig) +void exit_itimers(struct task_struct *tsk) { + struct list_head timers; struct k_itimer *tmr; - while (!list_empty(&sig->posix_timers)) { - tmr = list_entry(sig->posix_timers.next, struct k_itimer, list); + if (list_empty(&tsk->signal->posix_timers)) + return; + + spin_lock_irq(&tsk->sighand->siglock); + list_replace_init(&tsk->signal->posix_timers, &timers); + spin_unlock_irq(&tsk->sighand->siglock); + + while (!list_empty(&timers)) { + tmr = list_first_entry(&timers, struct k_itimer, list); itimer_delete(tmr); } } diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 58a11f859ac7..30049580cd62 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -526,7 +526,6 @@ void __init tick_nohz_full_setup(cpumask_var_t cpumask) cpumask_copy(tick_nohz_full_mask, cpumask); tick_nohz_full_running = true; } -EXPORT_SYMBOL_GPL(tick_nohz_full_setup); static int tick_nohz_cpu_down(unsigned int cpu) { diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index debbbb083286..ccd6a5ade3e9 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -194,7 +194,8 @@ config FUNCTION_TRACER sequence is then dynamically patched into a tracer call when tracing is enabled by the administrator. If it's runtime disabled (the bootup default), then the overhead of the instructions is very - small and not measurable even in micro-benchmarks. + small and not measurable even in micro-benchmarks (at least on + x86, but may have impact on other architectures). config FUNCTION_GRAPH_TRACER bool "Kernel Function Graph Tracer" diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 10a32b0f2deb..fe04c6f96ca5 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -770,14 +770,11 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) **/ void blk_trace_shutdown(struct request_queue *q) { - mutex_lock(&q->debugfs_mutex); if (rcu_dereference_protected(q->blk_trace, lockdep_is_held(&q->debugfs_mutex))) { __blk_trace_startstop(q, 0); __blk_trace_remove(q); } - - mutex_unlock(&q->debugfs_mutex); } #ifdef CONFIG_BLK_CGROUP diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 10b157a6d73e..88589d74a892 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2263,11 +2263,11 @@ static int copy_user_syms(struct user_syms *us, unsigned long __user *usyms, u32 int err = -ENOMEM; unsigned int i; - syms = kvmalloc(cnt * sizeof(*syms), GFP_KERNEL); + syms = kvmalloc_array(cnt, sizeof(*syms), GFP_KERNEL); if (!syms) goto error; - buf = kvmalloc(cnt * KSYM_NAME_LEN, GFP_KERNEL); + buf = kvmalloc_array(cnt, KSYM_NAME_LEN, GFP_KERNEL); if (!buf) goto error; @@ -2423,7 +2423,7 @@ kprobe_multi_link_handler(struct fprobe *fp, unsigned long entry_ip, kprobe_multi_link_prog_run(link, entry_ip, regs); } -static int symbols_cmp(const void *a, const void *b) +static int symbols_cmp_r(const void *a, const void *b, const void *priv) { const char **str_a = (const char **) a; const char **str_b = (const char **) b; @@ -2431,6 +2431,28 @@ static int symbols_cmp(const void *a, const void *b) return strcmp(*str_a, *str_b); } +struct multi_symbols_sort { + const char **funcs; + u64 *cookies; +}; + +static void symbols_swap_r(void *a, void *b, int size, const void *priv) +{ + const struct multi_symbols_sort *data = priv; + const char **name_a = a, **name_b = b; + + swap(*name_a, *name_b); + + /* If defined, swap also related cookies. */ + if (data->cookies) { + u64 *cookie_a, *cookie_b; + + cookie_a = data->cookies + (name_a - data->funcs); + cookie_b = data->cookies + (name_b - data->funcs); + swap(*cookie_a, *cookie_b); + } +} + int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { struct bpf_kprobe_multi_link *link = NULL; @@ -2464,42 +2486,50 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr return -EINVAL; size = cnt * sizeof(*addrs); - addrs = kvmalloc(size, GFP_KERNEL); + addrs = kvmalloc_array(cnt, sizeof(*addrs), GFP_KERNEL); if (!addrs) return -ENOMEM; + ucookies = u64_to_user_ptr(attr->link_create.kprobe_multi.cookies); + if (ucookies) { + cookies = kvmalloc_array(cnt, sizeof(*addrs), GFP_KERNEL); + if (!cookies) { + err = -ENOMEM; + goto error; + } + if (copy_from_user(cookies, ucookies, size)) { + err = -EFAULT; + goto error; + } + } + if (uaddrs) { if (copy_from_user(addrs, uaddrs, size)) { err = -EFAULT; goto error; } } else { + struct multi_symbols_sort data = { + .cookies = cookies, + }; struct user_syms us; err = copy_user_syms(&us, usyms, cnt); if (err) goto error; - sort(us.syms, cnt, sizeof(*us.syms), symbols_cmp, NULL); + if (cookies) + data.funcs = us.syms; + + sort_r(us.syms, cnt, sizeof(*us.syms), symbols_cmp_r, + symbols_swap_r, &data); + err = ftrace_lookup_symbols(us.syms, cnt, addrs); free_user_syms(&us); if (err) goto error; } - ucookies = u64_to_user_ptr(attr->link_create.kprobe_multi.cookies); - if (ucookies) { - cookies = kvmalloc(size, GFP_KERNEL); - if (!cookies) { - err = -ENOMEM; - goto error; - } - if (copy_from_user(cookies, ucookies, size)) { - err = -EFAULT; - goto error; - } - } - link = kzalloc(sizeof(*link), GFP_KERNEL); if (!link) { err = -ENOMEM; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index e750fe141a60..601ccf1b2f09 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -8029,15 +8029,23 @@ static int kallsyms_callback(void *data, const char *name, struct module *mod, unsigned long addr) { struct kallsyms_data *args = data; + const char **sym; + int idx; - if (!bsearch(&name, args->syms, args->cnt, sizeof(*args->syms), symbols_cmp)) + sym = bsearch(&name, args->syms, args->cnt, sizeof(*args->syms), symbols_cmp); + if (!sym) + return 0; + + idx = sym - args->syms; + if (args->addrs[idx]) return 0; addr = ftrace_location(addr); if (!addr) return 0; - args->addrs[args->found++] = addr; + args->addrs[idx] = addr; + args->found++; return args->found == args->cnt ? 1 : 0; } @@ -8062,6 +8070,7 @@ int ftrace_lookup_symbols(const char **sorted_syms, size_t cnt, unsigned long *a struct kallsyms_data args; int err; + memset(addrs, 0, sizeof(*addrs) * cnt); args.addrs = addrs; args.syms = sorted_syms; args.cnt = cnt; diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c index b56833700d23..c69d82273ce7 100644 --- a/kernel/trace/rethook.c +++ b/kernel/trace/rethook.c @@ -154,6 +154,15 @@ struct rethook_node *rethook_try_get(struct rethook *rh) if (unlikely(!handler)) return NULL; + /* + * This expects the caller will set up a rethook on a function entry. + * When the function returns, the rethook will eventually be reclaimed + * or released in the rethook_recycle() with call_rcu(). + * This means the caller must be run in the RCU-availabe context. + */ + if (unlikely(!rcu_is_watching())) + return NULL; + fn = freelist_try_get(&rh->pool); if (!fn) return NULL; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 2c95992e2c71..b8dd54627075 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6424,9 +6424,7 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) synchronize_rcu(); free_snapshot(tr); } -#endif -#ifdef CONFIG_TRACER_MAX_TRACE if (t->use_max_tr && !had_max_tr) { ret = tracing_alloc_snapshot_instance(tr); if (ret < 0) @@ -9866,6 +9864,12 @@ void trace_init_global_iter(struct trace_iterator *iter) /* Output in nanoseconds only if we are using a clock in nanoseconds. */ if (trace_clocks[iter->tr->clock_id].in_ns) iter->iter_flags |= TRACE_FILE_TIME_IN_NS; + + /* Can not use kmalloc for iter.temp and iter.fmt */ + iter->temp = static_temp_buf; + iter->temp_size = STATIC_TEMP_BUF_SIZE; + iter->fmt = static_fmt_buf; + iter->fmt_size = STATIC_FMT_BUF_SIZE; } void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) @@ -9898,11 +9902,6 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) /* Simulate the iterator */ trace_init_global_iter(&iter); - /* Can not use kmalloc for iter.temp and iter.fmt */ - iter.temp = static_temp_buf; - iter.temp_size = STATIC_TEMP_BUF_SIZE; - iter.fmt = static_fmt_buf; - iter.fmt_size = STATIC_FMT_BUF_SIZE; for_each_tracing_cpu(cpu) { atomic_inc(&per_cpu_ptr(iter.array_buffer->data, cpu)->disabled); diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 48e82e141d54..e87a46794079 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -4430,6 +4430,8 @@ static int parse_var_defs(struct hist_trigger_data *hist_data) s = kstrdup(field_str, GFP_KERNEL); if (!s) { + kfree(hist_data->attrs->var_defs.name[n_vars]); + hist_data->attrs->var_defs.name[n_vars] = NULL; ret = -ENOMEM; goto free; } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 93507330462c..a245ea673715 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1718,8 +1718,17 @@ static int kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs) { struct kretprobe *rp = get_kretprobe(ri); - struct trace_kprobe *tk = container_of(rp, struct trace_kprobe, rp); + struct trace_kprobe *tk; + + /* + * There is a small chance that get_kretprobe(ri) returns NULL when + * the kretprobe is unregister on another CPU between kretprobe's + * trampoline_handler and this function. + */ + if (unlikely(!rp)) + return 0; + tk = container_of(rp, struct trace_kprobe, rp); raw_cpu_inc(*tk->nhit); if (trace_probe_test_flag(&tk->tp, TP_FLAG_TRACE)) diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 9711589273cd..c3dc4f859a6b 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -546,7 +546,6 @@ static int __trace_uprobe_create(int argc, const char **argv) bool is_return = false; int i, ret; - ret = 0; ref_ctr_offset = 0; switch (argv[0][0]) { diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c index 230038d4f908..59ddb00d6944 100644 --- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -34,6 +34,27 @@ MODULE_LICENSE("GPL"); #define WATCH_QUEUE_NOTE_SIZE 128 #define WATCH_QUEUE_NOTES_PER_PAGE (PAGE_SIZE / WATCH_QUEUE_NOTE_SIZE) +/* + * This must be called under the RCU read-lock, which makes + * sure that the wqueue still exists. It can then take the lock, + * and check that the wqueue hasn't been destroyed, which in + * turn makes sure that the notification pipe still exists. + */ +static inline bool lock_wqueue(struct watch_queue *wqueue) +{ + spin_lock_bh(&wqueue->lock); + if (unlikely(wqueue->defunct)) { + spin_unlock_bh(&wqueue->lock); + return false; + } + return true; +} + +static inline void unlock_wqueue(struct watch_queue *wqueue) +{ + spin_unlock_bh(&wqueue->lock); +} + static void watch_queue_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { @@ -69,6 +90,10 @@ static const struct pipe_buf_operations watch_queue_pipe_buf_ops = { /* * Post a notification to a watch queue. + * + * Must be called with the RCU lock for reading, and the + * watch_queue lock held, which guarantees that the pipe + * hasn't been released. */ static bool post_one_notification(struct watch_queue *wqueue, struct watch_notification *n) @@ -85,9 +110,6 @@ static bool post_one_notification(struct watch_queue *wqueue, spin_lock_irq(&pipe->rd_wait.lock); - if (wqueue->defunct) - goto out; - mask = pipe->ring_size - 1; head = pipe->head; tail = pipe->tail; @@ -203,7 +225,10 @@ void __post_watch_notification(struct watch_list *wlist, if (security_post_notification(watch->cred, cred, n) < 0) continue; - post_one_notification(wqueue, n); + if (lock_wqueue(wqueue)) { + post_one_notification(wqueue, n); + unlock_wqueue(wqueue); + } } rcu_read_unlock(); @@ -429,6 +454,33 @@ void init_watch(struct watch *watch, struct watch_queue *wqueue) rcu_assign_pointer(watch->queue, wqueue); } +static int add_one_watch(struct watch *watch, struct watch_list *wlist, struct watch_queue *wqueue) +{ + const struct cred *cred; + struct watch *w; + + hlist_for_each_entry(w, &wlist->watchers, list_node) { + struct watch_queue *wq = rcu_access_pointer(w->queue); + if (wqueue == wq && watch->id == w->id) + return -EBUSY; + } + + cred = current_cred(); + if (atomic_inc_return(&cred->user->nr_watches) > task_rlimit(current, RLIMIT_NOFILE)) { + atomic_dec(&cred->user->nr_watches); + return -EAGAIN; + } + + watch->cred = get_cred(cred); + rcu_assign_pointer(watch->watch_list, wlist); + + kref_get(&wqueue->usage); + kref_get(&watch->usage); + hlist_add_head(&watch->queue_node, &wqueue->watches); + hlist_add_head_rcu(&watch->list_node, &wlist->watchers); + return 0; +} + /** * add_watch_to_object - Add a watch on an object to a watch list * @watch: The watch to add @@ -443,33 +495,21 @@ void init_watch(struct watch *watch, struct watch_queue *wqueue) */ int add_watch_to_object(struct watch *watch, struct watch_list *wlist) { - struct watch_queue *wqueue = rcu_access_pointer(watch->queue); - struct watch *w; - - hlist_for_each_entry(w, &wlist->watchers, list_node) { - struct watch_queue *wq = rcu_access_pointer(w->queue); - if (wqueue == wq && watch->id == w->id) - return -EBUSY; - } + struct watch_queue *wqueue; + int ret = -ENOENT; - watch->cred = get_current_cred(); - rcu_assign_pointer(watch->watch_list, wlist); + rcu_read_lock(); - if (atomic_inc_return(&watch->cred->user->nr_watches) > - task_rlimit(current, RLIMIT_NOFILE)) { - atomic_dec(&watch->cred->user->nr_watches); - put_cred(watch->cred); - return -EAGAIN; + wqueue = rcu_access_pointer(watch->queue); + if (lock_wqueue(wqueue)) { + spin_lock(&wlist->lock); + ret = add_one_watch(watch, wlist, wqueue); + spin_unlock(&wlist->lock); + unlock_wqueue(wqueue); } - spin_lock_bh(&wqueue->lock); - kref_get(&wqueue->usage); - kref_get(&watch->usage); - hlist_add_head(&watch->queue_node, &wqueue->watches); - spin_unlock_bh(&wqueue->lock); - - hlist_add_head(&watch->list_node, &wlist->watchers); - return 0; + rcu_read_unlock(); + return ret; } EXPORT_SYMBOL(add_watch_to_object); @@ -520,20 +560,15 @@ found: wqueue = rcu_dereference(watch->queue); - /* We don't need the watch list lock for the next bit as RCU is - * protecting *wqueue from deallocation. - */ - if (wqueue) { + if (lock_wqueue(wqueue)) { post_one_notification(wqueue, &n.watch); - spin_lock_bh(&wqueue->lock); - if (!hlist_unhashed(&watch->queue_node)) { hlist_del_init_rcu(&watch->queue_node); put_watch(watch); } - spin_unlock_bh(&wqueue->lock); + unlock_wqueue(wqueue); } if (wlist->release_watch) { diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 20a7a55e62b6..ecb0e8346e65 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -424,8 +424,6 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) /* Start period for the next softlockup warning. */ update_report_ts(); - printk_prefer_direct_enter(); - pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n", smp_processor_id(), duration, current->comm, task_pid_nr(current)); @@ -444,8 +442,6 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) add_taint(TAINT_SOFTLOCKUP, LOCKDEP_STILL_OK); if (softlockup_panic) panic("softlockup: hung tasks"); - - printk_prefer_direct_exit(); } return HRTIMER_RESTART; diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 701f35f0e2d4..247bf0b1582c 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -135,8 +135,6 @@ static void watchdog_overflow_callback(struct perf_event *event, if (__this_cpu_read(hard_watchdog_warn) == true) return; - printk_prefer_direct_enter(); - pr_emerg("Watchdog detected hard LOCKUP on cpu %d\n", this_cpu); print_modules(); @@ -157,8 +155,6 @@ static void watchdog_overflow_callback(struct perf_event *event, if (hardlockup_panic) nmi_panic(regs, "Hard LOCKUP"); - printk_prefer_direct_exit(); - __this_cpu_write(hard_watchdog_warn, true); return; } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 4056f2a3f9d5..aa8a82bc6738 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2788,13 +2788,13 @@ static bool flush_workqueue_prep_pwqs(struct workqueue_struct *wq, } /** - * flush_workqueue - ensure that any scheduled work has run to completion. + * __flush_workqueue - ensure that any scheduled work has run to completion. * @wq: workqueue to flush * * This function sleeps until all work items which were queued on entry * have finished execution, but it is not livelocked by new incoming ones. */ -void flush_workqueue(struct workqueue_struct *wq) +void __flush_workqueue(struct workqueue_struct *wq) { struct wq_flusher this_flusher = { .list = LIST_HEAD_INIT(this_flusher.list), @@ -2943,7 +2943,7 @@ void flush_workqueue(struct workqueue_struct *wq) out_unlock: mutex_unlock(&wq->mutex); } -EXPORT_SYMBOL(flush_workqueue); +EXPORT_SYMBOL(__flush_workqueue); /** * drain_workqueue - drain a workqueue @@ -2971,7 +2971,7 @@ void drain_workqueue(struct workqueue_struct *wq) wq->flags |= __WQ_DRAINING; mutex_unlock(&wq->mutex); reflush: - flush_workqueue(wq); + __flush_workqueue(wq); mutex_lock(&wq->mutex); @@ -5001,7 +5001,10 @@ static void unbind_workers(int cpu) for_each_pool_worker(worker, pool) { kthread_set_per_cpu(worker->task, -1); - WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, wq_unbound_cpumask) < 0); + if (cpumask_intersects(wq_unbound_cpumask, cpu_active_mask)) + WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, wq_unbound_cpumask) < 0); + else + WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, cpu_possible_mask) < 0); } mutex_unlock(&wq_pool_attach_mutex); @@ -6111,3 +6114,11 @@ void __init workqueue_init(void) wq_online = true; wq_watchdog_init(); } + +/* + * Despite the naming, this is a no-op function which is here only for avoiding + * link error. Since compile-time warning may fail to catch, we will need to + * emit run-time warning from __flush_workqueue(). + */ +void __warn_flushing_systemwide_wq(void) { } +EXPORT_SYMBOL(__warn_flushing_systemwide_wq); |