diff options
Diffstat (limited to 'kernel')
47 files changed, 695 insertions, 468 deletions
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 0d302a8..690e1e3 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -457,13 +457,15 @@ void audit_remove_watch_rule(struct audit_krule *krule) list_del(&krule->rlist); if (list_empty(&watch->rules)) { + /* + * audit_remove_watch() drops our reference to 'parent' which + * can get freed. Grab our own reference to be safe. + */ + audit_get_parent(parent); audit_remove_watch(watch); - - if (list_empty(&parent->watches)) { - audit_get_parent(parent); + if (list_empty(&parent->watches)) fsnotify_destroy_mark(&parent->mark, audit_watch_group); - audit_put_parent(parent); - } + audit_put_parent(parent); } } diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index a2ac051..f3721e1 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -11,7 +11,6 @@ */ #include <linux/bpf.h> #include <linux/err.h> -#include <linux/vmalloc.h> #include <linux/slab.h> #include <linux/mm.h> #include <linux/filter.h> @@ -74,14 +73,10 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) if (array_size >= U32_MAX - PAGE_SIZE) return ERR_PTR(-ENOMEM); - /* allocate all map elements and zero-initialize them */ - array = kzalloc(array_size, GFP_USER | __GFP_NOWARN); - if (!array) { - array = vzalloc(array_size); - if (!array) - return ERR_PTR(-ENOMEM); - } + array = bpf_map_area_alloc(array_size); + if (!array) + return ERR_PTR(-ENOMEM); /* copy mandatory map attributes */ array->map.map_type = attr->map_type; @@ -97,7 +92,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) if (array_size >= U32_MAX - PAGE_SIZE || elem_size > PCPU_MIN_UNIT_SIZE || bpf_array_alloc_percpu(array)) { - kvfree(array); + bpf_map_area_free(array); return ERR_PTR(-ENOMEM); } out: @@ -262,7 +257,7 @@ static void array_map_free(struct bpf_map *map) if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) bpf_array_free_percpu(array); - kvfree(array); + bpf_map_area_free(array); } static const struct bpf_map_ops array_ops = { @@ -319,7 +314,8 @@ static void fd_array_map_free(struct bpf_map *map) /* make sure it's empty */ for (i = 0; i < array->map.max_entries; i++) BUG_ON(array->ptrs[i] != NULL); - kvfree(array); + + bpf_map_area_free(array); } static void *fd_array_map_lookup_elem(struct bpf_map *map, void *key) diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index ad1bc67..ad2f0ed 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -13,7 +13,6 @@ #include <linux/bpf.h> #include <linux/jhash.h> #include <linux/filter.h> -#include <linux/vmalloc.h> #include "percpu_freelist.h" struct bucket { @@ -84,14 +83,15 @@ static void htab_free_elems(struct bpf_htab *htab) free_percpu(pptr); } free_elems: - vfree(htab->elems); + bpf_map_area_free(htab->elems); } static int prealloc_elems_and_freelist(struct bpf_htab *htab) { int err = -ENOMEM, i; - htab->elems = vzalloc(htab->elem_size * htab->map.max_entries); + htab->elems = bpf_map_area_alloc(htab->elem_size * + htab->map.max_entries); if (!htab->elems) return -ENOMEM; @@ -227,14 +227,10 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) goto free_htab; err = -ENOMEM; - htab->buckets = kmalloc_array(htab->n_buckets, sizeof(struct bucket), - GFP_USER | __GFP_NOWARN); - - if (!htab->buckets) { - htab->buckets = vmalloc(htab->n_buckets * sizeof(struct bucket)); - if (!htab->buckets) - goto free_htab; - } + htab->buckets = bpf_map_area_alloc(htab->n_buckets * + sizeof(struct bucket)); + if (!htab->buckets) + goto free_htab; for (i = 0; i < htab->n_buckets; i++) { INIT_HLIST_HEAD(&htab->buckets[i].head); @@ -258,7 +254,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) free_extra_elems: free_percpu(htab->extra_elems); free_buckets: - kvfree(htab->buckets); + bpf_map_area_free(htab->buckets); free_htab: kfree(htab); return ERR_PTR(err); @@ -715,7 +711,7 @@ static void htab_map_free(struct bpf_map *map) pcpu_freelist_destroy(&htab->freelist); } free_percpu(htab->extra_elems); - kvfree(htab->buckets); + bpf_map_area_free(htab->buckets); kfree(htab); } diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 732ae16..be85191 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -7,7 +7,6 @@ #include <linux/bpf.h> #include <linux/jhash.h> #include <linux/filter.h> -#include <linux/vmalloc.h> #include <linux/stacktrace.h> #include <linux/perf_event.h> #include "percpu_freelist.h" @@ -32,7 +31,7 @@ static int prealloc_elems_and_freelist(struct bpf_stack_map *smap) u32 elem_size = sizeof(struct stack_map_bucket) + smap->map.value_size; int err; - smap->elems = vzalloc(elem_size * smap->map.max_entries); + smap->elems = bpf_map_area_alloc(elem_size * smap->map.max_entries); if (!smap->elems) return -ENOMEM; @@ -45,7 +44,7 @@ static int prealloc_elems_and_freelist(struct bpf_stack_map *smap) return 0; free_elems: - vfree(smap->elems); + bpf_map_area_free(smap->elems); return err; } @@ -76,12 +75,9 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) if (cost >= U32_MAX - PAGE_SIZE) return ERR_PTR(-E2BIG); - smap = kzalloc(cost, GFP_USER | __GFP_NOWARN); - if (!smap) { - smap = vzalloc(cost); - if (!smap) - return ERR_PTR(-ENOMEM); - } + smap = bpf_map_area_alloc(cost); + if (!smap) + return ERR_PTR(-ENOMEM); err = -E2BIG; cost += n_buckets * (value_size + sizeof(struct stack_map_bucket)); @@ -112,7 +108,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) put_buffers: put_callchain_buffers(); free_smap: - kvfree(smap); + bpf_map_area_free(smap); return ERR_PTR(err); } @@ -262,9 +258,9 @@ static void stack_map_free(struct bpf_map *map) /* wait for bpf programs to complete before freeing stack map */ synchronize_rcu(); - vfree(smap->elems); + bpf_map_area_free(smap->elems); pcpu_freelist_destroy(&smap->freelist); - kvfree(smap); + bpf_map_area_free(smap); put_callchain_buffers(); } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 237f3d6..72ea91d 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -12,6 +12,8 @@ #include <linux/bpf.h> #include <linux/syscalls.h> #include <linux/slab.h> +#include <linux/vmalloc.h> +#include <linux/mmzone.h> #include <linux/anon_inodes.h> #include <linux/file.h> #include <linux/license.h> @@ -48,6 +50,30 @@ void bpf_register_map_type(struct bpf_map_type_list *tl) list_add(&tl->list_node, &bpf_map_types); } +void *bpf_map_area_alloc(size_t size) +{ + /* We definitely need __GFP_NORETRY, so OOM killer doesn't + * trigger under memory pressure as we really just want to + * fail instead. + */ + const gfp_t flags = __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO; + void *area; + + if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { + area = kmalloc(size, GFP_USER | flags); + if (area != NULL) + return area; + } + + return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | flags, + PAGE_KERNEL); +} + +void bpf_map_area_free(void *area) +{ + kvfree(area); +} + int bpf_map_precharge_memlock(u32 pages) { struct user_struct *user = get_current_user(); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 44c17f4..372454a 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -139,7 +139,7 @@ struct bpf_verifier_stack_elem { struct bpf_verifier_stack_elem *next; }; -#define BPF_COMPLEXITY_LIMIT_INSNS 65536 +#define BPF_COMPLEXITY_LIMIT_INSNS 98304 #define BPF_COMPLEXITY_LIMIT_STACK 1024 struct bpf_call_arg_meta { @@ -682,12 +682,13 @@ static int check_ctx_access(struct bpf_verifier_env *env, int off, int size, return -EACCES; } -static bool is_pointer_value(struct bpf_verifier_env *env, int regno) +static bool __is_pointer_value(bool allow_ptr_leaks, + const struct bpf_reg_state *reg) { - if (env->allow_ptr_leaks) + if (allow_ptr_leaks) return false; - switch (env->cur_state.regs[regno].type) { + switch (reg->type) { case UNKNOWN_VALUE: case CONST_IMM: return false; @@ -696,6 +697,11 @@ static bool is_pointer_value(struct bpf_verifier_env *env, int regno) } } +static bool is_pointer_value(struct bpf_verifier_env *env, int regno) +{ + return __is_pointer_value(env->allow_ptr_leaks, &env->cur_state.regs[regno]); +} + static int check_ptr_alignment(struct bpf_verifier_env *env, struct bpf_reg_state *reg, int off, int size) { @@ -885,6 +891,11 @@ static int check_xadd(struct bpf_verifier_env *env, struct bpf_insn *insn) if (err) return err; + if (is_pointer_value(env, insn->src_reg)) { + verbose("R%d leaks addr into mem\n", insn->src_reg); + return -EACCES; + } + /* check whether atomic_add can read the memory */ err = check_mem_access(env, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_READ, -1); @@ -1462,6 +1473,65 @@ static int evaluate_reg_alu(struct bpf_verifier_env *env, struct bpf_insn *insn) return 0; } +static int evaluate_reg_imm_alu_unknown(struct bpf_verifier_env *env, + struct bpf_insn *insn) +{ + struct bpf_reg_state *regs = env->cur_state.regs; + struct bpf_reg_state *dst_reg = ®s[insn->dst_reg]; + struct bpf_reg_state *src_reg = ®s[insn->src_reg]; + u8 opcode = BPF_OP(insn->code); + s64 imm_log2 = __ilog2_u64((long long)dst_reg->imm); + + /* BPF_X code with src_reg->type UNKNOWN_VALUE here. */ + if (src_reg->imm > 0 && dst_reg->imm) { + switch (opcode) { + case BPF_ADD: + /* dreg += sreg + * where both have zero upper bits. Adding them + * can only result making one more bit non-zero + * in the larger value. + * Ex. 0xffff (imm=48) + 1 (imm=63) = 0x10000 (imm=47) + * 0xffff (imm=48) + 0xffff = 0x1fffe (imm=47) + */ + dst_reg->imm = min(src_reg->imm, 63 - imm_log2); + dst_reg->imm--; + break; + case BPF_AND: + /* dreg &= sreg + * AND can not extend zero bits only shrink + * Ex. 0x00..00ffffff + * & 0x0f..ffffffff + * ---------------- + * 0x00..00ffffff + */ + dst_reg->imm = max(src_reg->imm, 63 - imm_log2); + break; + case BPF_OR: + /* dreg |= sreg + * OR can only extend zero bits + * Ex. 0x00..00ffffff + * | 0x0f..ffffffff + * ---------------- + * 0x0f..00ffffff + */ + dst_reg->imm = min(src_reg->imm, 63 - imm_log2); + break; + case BPF_SUB: + case BPF_MUL: + case BPF_RSH: + case BPF_LSH: + /* These may be flushed out later */ + default: + mark_reg_unknown_value(regs, insn->dst_reg); + } + } else { + mark_reg_unknown_value(regs, insn->dst_reg); + } + + dst_reg->type = UNKNOWN_VALUE; + return 0; +} + static int evaluate_reg_imm_alu(struct bpf_verifier_env *env, struct bpf_insn *insn) { @@ -1470,6 +1540,9 @@ static int evaluate_reg_imm_alu(struct bpf_verifier_env *env, struct bpf_reg_state *src_reg = ®s[insn->src_reg]; u8 opcode = BPF_OP(insn->code); + if (BPF_SRC(insn->code) == BPF_X && src_reg->type == UNKNOWN_VALUE) + return evaluate_reg_imm_alu_unknown(env, insn); + /* dst_reg->type == CONST_IMM here, simulate execution of 'add' insn. * Don't care about overflow or negative values, just add them */ @@ -1525,10 +1598,24 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env, } /* We don't know anything about what was done to this register, mark it - * as unknown. + * as unknown. Also, if both derived bounds came from signed/unsigned + * mixed compares and one side is unbounded, we cannot really do anything + * with them as boundaries cannot be trusted. Thus, arithmetic of two + * regs of such kind will get invalidated bounds on the dst side. */ - if (min_val == BPF_REGISTER_MIN_RANGE && - max_val == BPF_REGISTER_MAX_RANGE) { + if ((min_val == BPF_REGISTER_MIN_RANGE && + max_val == BPF_REGISTER_MAX_RANGE) || + (BPF_SRC(insn->code) == BPF_X && + ((min_val != BPF_REGISTER_MIN_RANGE && + max_val == BPF_REGISTER_MAX_RANGE) || + (min_val == BPF_REGISTER_MIN_RANGE && + max_val != BPF_REGISTER_MAX_RANGE) || + (dst_reg->min_value != BPF_REGISTER_MIN_RANGE && + dst_reg->max_value == BPF_REGISTER_MAX_RANGE) || + (dst_reg->min_value == BPF_REGISTER_MIN_RANGE && + dst_reg->max_value != BPF_REGISTER_MAX_RANGE)) && + regs[insn->dst_reg].value_from_signed != + regs[insn->src_reg].value_from_signed)) { reset_reg_range_values(regs, insn->dst_reg); return; } @@ -1537,10 +1624,12 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env, * do our normal operations to the register, we need to set the values * to the min/max since they are undefined. */ - if (min_val == BPF_REGISTER_MIN_RANGE) - dst_reg->min_value = BPF_REGISTER_MIN_RANGE; - if (max_val == BPF_REGISTER_MAX_RANGE) - dst_reg->max_value = BPF_REGISTER_MAX_RANGE; + if (opcode != BPF_SUB) { + if (min_val == BPF_REGISTER_MIN_RANGE) + dst_reg->min_value = BPF_REGISTER_MIN_RANGE; + if (max_val == BPF_REGISTER_MAX_RANGE) + dst_reg->max_value = BPF_REGISTER_MAX_RANGE; + } switch (opcode) { case BPF_ADD: @@ -1550,10 +1639,17 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env, dst_reg->max_value += max_val; break; case BPF_SUB: + /* If one of our values was at the end of our ranges, then the + * _opposite_ value in the dst_reg goes to the end of our range. + */ + if (min_val == BPF_REGISTER_MIN_RANGE) + dst_reg->max_value = BPF_REGISTER_MAX_RANGE; + if (max_val == BPF_REGISTER_MAX_RANGE) + dst_reg->min_value = BPF_REGISTER_MIN_RANGE; if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE) - dst_reg->min_value -= min_val; + dst_reg->min_value -= max_val; if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) - dst_reg->max_value -= max_val; + dst_reg->max_value -= min_val; break; case BPF_MUL: if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE) @@ -1624,7 +1720,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) } } else { if (insn->src_reg != BPF_REG_0 || insn->off != 0 || - (insn->imm != 16 && insn->imm != 32 && insn->imm != 64)) { + (insn->imm != 16 && insn->imm != 32 && insn->imm != 64) || + BPF_CLASS(insn->code) == BPF_ALU64) { verbose("BPF_END uses reserved fields\n"); return -EINVAL; } @@ -1803,6 +1900,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) * register as unknown. */ if (env->allow_ptr_leaks && + BPF_CLASS(insn->code) == BPF_ALU64 && opcode == BPF_ADD && (dst_reg->type == PTR_TO_MAP_VALUE || dst_reg->type == PTR_TO_MAP_VALUE_ADJ)) dst_reg->type = PTR_TO_MAP_VALUE_ADJ; @@ -1871,38 +1969,63 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg, struct bpf_reg_state *false_reg, u64 val, u8 opcode) { + bool value_from_signed = true; + bool is_range = true; + switch (opcode) { case BPF_JEQ: /* If this is false then we know nothing Jon Snow, but if it is * true then we know for sure. */ true_reg->max_value = true_reg->min_value = val; + is_range = false; break; case BPF_JNE: /* If this is true we know nothing Jon Snow, but if it is false * we know the value for sure; */ false_reg->max_value = false_reg->min_value = val; + is_range = false; break; case BPF_JGT: - /* Unsigned comparison, the minimum value is 0. */ - false_reg->min_value = 0; + value_from_signed = false; + /* fallthrough */ case BPF_JSGT: + if (true_reg->value_from_signed != value_from_signed) + reset_reg_range_values(true_reg, 0); + if (false_reg->value_from_signed != value_from_signed) + reset_reg_range_values(false_reg, 0); + if (opcode == BPF_JGT) { + /* Unsigned comparison, the minimum value is 0. */ + false_reg->min_value = 0; + } /* If this is false then we know the maximum val is val, * otherwise we know the min val is val+1. */ false_reg->max_value = val; + false_reg->value_from_signed = value_from_signed; true_reg->min_value = val + 1; + true_reg->value_from_signed = value_from_signed; break; case BPF_JGE: - /* Unsigned comparison, the minimum value is 0. */ - false_reg->min_value = 0; + value_from_signed = false; + /* fallthrough */ case BPF_JSGE: + if (true_reg->value_from_signed != value_from_signed) + reset_reg_range_values(true_reg, 0); + if (false_reg->value_from_signed != value_from_signed) + reset_reg_range_values(false_reg, 0); + if (opcode == BPF_JGE) { + /* Unsigned comparison, the minimum value is 0. */ + false_reg->min_value = 0; + } /* If this is false then we know the maximum value is val - 1, * otherwise we know the mimimum value is val. */ false_reg->max_value = val - 1; + false_reg->value_from_signed = value_from_signed; true_reg->min_value = val; + true_reg->value_from_signed = value_from_signed; break; default: break; @@ -1910,6 +2033,12 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg, check_reg_overflow(false_reg); check_reg_overflow(true_reg); + if (is_range) { + if (__is_pointer_value(false, false_reg)) + reset_reg_range_values(false_reg, 0); + if (__is_pointer_value(false, true_reg)) + reset_reg_range_values(true_reg, 0); + } } /* Same as above, but for the case that dst_reg is a CONST_IMM reg and src_reg @@ -1919,39 +2048,64 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg, struct bpf_reg_state *false_reg, u64 val, u8 opcode) { + bool value_from_signed = true; + bool is_range = true; + switch (opcode) { case BPF_JEQ: /* If this is false then we know nothing Jon Snow, but if it is * true then we know for sure. */ true_reg->max_value = true_reg->min_value = val; + is_range = false; break; case BPF_JNE: /* If this is true we know nothing Jon Snow, but if it is false * we know the value for sure; */ false_reg->max_value = false_reg->min_value = val; + is_range = false; break; case BPF_JGT: - /* Unsigned comparison, the minimum value is 0. */ - true_reg->min_value = 0; + value_from_signed = false; + /* fallthrough */ case BPF_JSGT: + if (true_reg->value_from_signed != value_from_signed) + reset_reg_range_values(true_reg, 0); + if (false_reg->value_from_signed != value_from_signed) + reset_reg_range_values(false_reg, 0); + if (opcode == BPF_JGT) { + /* Unsigned comparison, the minimum value is 0. */ + true_reg->min_value = 0; + } /* * If this is false, then the val is <= the register, if it is * true the register <= to the val. */ false_reg->min_value = val; + false_reg->value_from_signed = value_from_signed; true_reg->max_value = val - 1; + true_reg->value_from_signed = value_from_signed; break; case BPF_JGE: - /* Unsigned comparison, the minimum value is 0. */ - true_reg->min_value = 0; + value_from_signed = false; + /* fallthrough */ case BPF_JSGE: + if (true_reg->value_from_signed != value_from_signed) + reset_reg_range_values(true_reg, 0); + if (false_reg->value_from_signed != value_from_signed) + reset_reg_range_values(false_reg, 0); + if (opcode == BPF_JGE) { + /* Unsigned comparison, the minimum value is 0. */ + true_reg->min_value = 0; + } /* If this is false then constant < register, if it is true then * the register < constant. */ false_reg->min_value = val + 1; + false_reg->value_from_signed = value_from_signed; true_reg->max_value = val; + true_reg->value_from_signed = value_from_signed; break; default: break; @@ -1959,6 +2113,12 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg, check_reg_overflow(false_reg); check_reg_overflow(true_reg); + if (is_range) { + if (__is_pointer_value(false, false_reg)) + reset_reg_range_values(false_reg, 0); + if (__is_pointer_value(false, true_reg)) + reset_reg_range_values(true_reg, 0); + } } static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id, @@ -2385,6 +2545,7 @@ peek_stack: env->explored_states[t + 1] = STATE_LIST_MARK; } else { /* conditional jump with two edges */ + env->explored_states[t] = STATE_LIST_MARK; ret = push_insn(t, t + 1, FALLTHROUGH, env); if (ret == 1) goto peek_stack; @@ -2543,6 +2704,12 @@ static bool states_equal(struct bpf_verifier_env *env, rcur->type != NOT_INIT)) continue; + /* Don't care about the reg->id in this case. */ + if (rold->type == PTR_TO_MAP_VALUE_OR_NULL && + rcur->type == PTR_TO_MAP_VALUE_OR_NULL && + rold->map_ptr == rcur->map_ptr) + continue; + if (rold->type == PTR_TO_PACKET && rcur->type == PTR_TO_PACKET && compare_ptrs_to_packet(rold, rcur)) continue; @@ -2677,6 +2844,9 @@ static int do_check(struct bpf_verifier_env *env) goto process_bpf_exit; } + if (need_resched()) + cond_resched(); + if (log_level && do_print_state) { verbose("\nfrom %d to %d:", prev_insn_idx, insn_idx); print_verifier_state(&env->cur_state); diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 1fde8ee..4c23343 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -3487,11 +3487,11 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, cgrp->subtree_control &= ~disable; ret = cgroup_apply_control(cgrp); - cgroup_finalize_control(cgrp, ret); + if (ret) + goto out_unlock; kernfs_activate(cgrp->kn); - ret = 0; out_unlock: cgroup_kn_unlock(of->kn); return ret ?: nbytes; @@ -5718,6 +5718,10 @@ int __init cgroup_init(void) if (ss->bind) ss->bind(init_css_set.subsys[ssid]); + + mutex_lock(&cgroup_mutex); + css_populate_dir(init_css_set.subsys[ssid]); + mutex_unlock(&cgroup_mutex); } /* init_css_set.subsys[] has been updated, re-hash */ diff --git a/kernel/cpu.c b/kernel/cpu.c index 8f52977..26a4f74 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -410,11 +410,26 @@ static int notify_online(unsigned int cpu) return 0; } +static void __cpuhp_kick_ap_work(struct cpuhp_cpu_state *st); + static int bringup_wait_for_ap(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + /* Wait for the CPU to reach CPUHP_AP_ONLINE_IDLE */ wait_for_completion(&st->done); + if (WARN_ON_ONCE((!cpu_online(cpu)))) + return -ECANCELED; + + /* Unpark the stopper thread and the hotplug thread of the target cpu */ + stop_machine_unpark(cpu); + kthread_unpark(st->thread); + + /* Should we go further up ? */ + if (st->target > CPUHP_AP_ONLINE_IDLE) { + __cpuhp_kick_ap_work(st); + wait_for_completion(&st->done); + } return st->result; } @@ -437,9 +452,7 @@ static int bringup_cpu(unsigned int cpu) cpu_notify(CPU_UP_CANCELED, cpu); return ret; } - ret = bringup_wait_for_ap(cpu); - BUG_ON(!cpu_online(cpu)); - return ret; + return bringup_wait_for_ap(cpu); } /* @@ -974,31 +987,20 @@ void notify_cpu_starting(unsigned int cpu) } /* - * Called from the idle task. We need to set active here, so we can kick off - * the stopper thread and unpark the smpboot threads. If the target state is - * beyond CPUHP_AP_ONLINE_IDLE we kick cpuhp thread and let it bring up the - * cpu further. + * Called from the idle task. Wake up the controlling task which brings the + * stopper and the hotplug thread of the upcoming CPU up and then delegates + * the rest of the online bringup to the hotplug thread. */ void cpuhp_online_idle(enum cpuhp_state state) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); - unsigned int cpu = smp_processor_id(); /* Happens for the boot cpu */ if (state != CPUHP_AP_ONLINE_IDLE) return; st->state = CPUHP_AP_ONLINE_IDLE; - - /* Unpark the stopper thread and the hotplug thread of this cpu */ - stop_machine_unpark(cpu); - kthread_unpark(st->thread); - - /* Should we go further up ? */ - if (st->target > CPUHP_AP_ONLINE_IDLE) - __cpuhp_kick_ap_work(st); - else - complete(&st->done); + complete(&st->done); } /* Requires cpu_add_remove_lock to be held */ diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 24d175d..511b1dd 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -61,6 +61,7 @@ #include <linux/cgroup.h> #include <linux/wait.h> +DEFINE_STATIC_KEY_FALSE(cpusets_pre_enable_key); DEFINE_STATIC_KEY_FALSE(cpusets_enabled_key); /* See "Frequency meter" comments, below. */ @@ -1904,6 +1905,7 @@ static struct cftype files[] = { { .name = "memory_pressure", .read_u64 = cpuset_read_u64, + .private = FILE_MEMORY_PRESSURE, }, { @@ -2274,6 +2276,13 @@ retry: mutex_unlock(&cpuset_mutex); } +static bool force_rebuild; + +void cpuset_force_rebuild(void) +{ + force_rebuild = true; +} + /** * cpuset_hotplug_workfn - handle CPU/memory hotunplug for a cpuset * @@ -2348,8 +2357,10 @@ static void cpuset_hotplug_workfn(struct work_struct *work) } /* rebuild sched domains if cpus_allowed has changed */ - if (cpus_updated) + if (cpus_updated || force_rebuild) { + force_rebuild = false; rebuild_sched_domains(); + } } void cpuset_update_active_cpus(bool cpu_online) @@ -2368,6 +2379,11 @@ void cpuset_update_active_cpus(bool cpu_online) schedule_work(&cpuset_hotplug_work); } +void cpuset_wait_for_hotplug(void) +{ + flush_work(&cpuset_hotplug_work); +} + /* * Keep top_cpuset.mems_allowed tracking node_states[N_MEMORY]. * Call this routine anytime after node_states[N_MEMORY] changes. diff --git a/kernel/events/core.c b/kernel/events/core.c index 11cc1d8..36ff2d9 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2272,7 +2272,7 @@ static int __perf_install_in_context(void *info) struct perf_event_context *ctx = event->ctx; struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); struct perf_event_context *task_ctx = cpuctx->task_ctx; - bool activate = true; + bool reprogram = true; int ret = 0; raw_spin_lock(&cpuctx->ctx.lock); @@ -2280,27 +2280,26 @@ static int __perf_install_in_context(void *info) raw_spin_lock(&ctx->lock); task_ctx = ctx; - /* If we're on the wrong CPU, try again */ - if (task_cpu(ctx->task) != smp_processor_id()) { - ret = -ESRCH; - goto unlock; - } + reprogram = (ctx->task == current); /* - * If we're on the right CPU, see if the task we target is - * current, if not we don't have to activate the ctx, a future - * context switch will do that for us. + * If the task is running, it must be running on this CPU, + * otherwise we cannot reprogram things. + * + * If its not running, we don't care, ctx->lock will + * serialize against it becoming runnable. */ - if (ctx->task != current) - activate = false; - else - WARN_ON_ONCE(cpuctx->task_ctx && cpuctx->task_ctx != ctx); + if (task_curr(ctx->task) && !reprogram) { + ret = -ESRCH; + goto unlock; + } + WARN_ON_ONCE(reprogram && cpuctx->task_ctx && cpuctx->task_ctx != ctx); } else if (task_ctx) { raw_spin_lock(&task_ctx->lock); } - if (activate) { + if (reprogram) { ctx_sched_out(ctx, cpuctx, EVENT_TIME); add_event_to_ctx(event, ctx); ctx_resched(cpuctx, task_ctx); @@ -2351,13 +2350,36 @@ perf_install_in_context(struct perf_event_context *ctx, /* * Installing events is tricky because we cannot rely on ctx->is_active * to be set in case this is the nr_events 0 -> 1 transition. + * + * Instead we use task_curr(), which tells us if the task is running. + * However, since we use task_curr() outside of rq::lock, we can race + * against the actual state. This means the result can be wrong. + * + * If we get a false positive, we retry, this is harmless. + * + * If we get a false negative, things are complicated. If we are after + * perf_event_context_sched_in() ctx::lock will serialize us, and the + * value must be correct. If we're before, it doesn't matter since + * perf_event_context_sched_in() will program the counter. + * + * However, this hinges on the remote context switch having observed + * our task->perf_event_ctxp[] store, such that it will in fact take + * ctx::lock in perf_event_context_sched_in(). + * + * We do this by task_function_call(), if the IPI fails to hit the task + * we know any future context switch of task must see the + * perf_event_ctpx[] store. */ -again: + /* - * Cannot use task_function_call() because we need to run on the task's - * CPU regardless of whether its current or not. + * This smp_mb() orders the task->perf_event_ctxp[] store with the + * task_cpu() load, such that if the IPI then does not find the task + * running, a future context switch of that task must observe the + * store. */ - if (!cpu_function_call(task_cpu(task), __perf_install_in_context, event)) + smp_mb(); +again: + if (!task_function_call(task, __perf_install_in_context, event)) return; raw_spin_lock_irq(&ctx->lock); @@ -2371,12 +2393,16 @@ again: raw_spin_unlock_irq(&ctx->lock); return; } - raw_spin_unlock_irq(&ctx->lock); /* - * Since !ctx->is_active doesn't mean anything, we must IPI - * unconditionally. + * If the task is not running, ctx->lock will avoid it becoming so, + * thus we can safely install the event. */ - goto again; + if (task_curr(task)) { + raw_spin_unlock_irq(&ctx->lock); + goto again; + } + add_event_to_ctx(event, ctx); + raw_spin_unlock_irq(&ctx->lock); } /* @@ -7062,21 +7088,6 @@ static void perf_log_itrace_start(struct perf_event *event) perf_output_end(&handle); } -static bool sample_is_allowed(struct perf_event *event, struct pt_regs *regs) -{ - /* - * Due to interrupt latency (AKA "skid"), we may enter the - * kernel before taking an overflow, even if the PMU is only - * counting user events. - * To avoid leaking information to userspace, we must always - * reject kernel samples when exclude_kernel is set. - */ - if (event->attr.exclude_kernel && !user_mode(regs)) - return false; - - return true; -} - /* * Generic event overflow handling, sampling. */ @@ -7124,12 +7135,6 @@ static int __perf_event_overflow(struct perf_event *event, } /* - * For security, drop the skid kernel samples if necessary. - */ - if (!sample_is_allowed(event, regs)) - return ret; - - /* * XXX event_limit might not quite work as expected on inherited * events */ @@ -7866,6 +7871,7 @@ static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd) } } event->tp_event->prog = prog; + event->tp_event->bpf_prog_owner = event; return 0; } @@ -7880,7 +7886,7 @@ static void perf_event_free_bpf_prog(struct perf_event *event) return; prog = event->tp_event->prog; - if (prog) { + if (prog && event->tp_event->bpf_prog_owner == event) { event->tp_event->prog = NULL; bpf_prog_put(prog); } @@ -9781,28 +9787,27 @@ SYSCALL_DEFINE5(perf_event_open, goto err_context; /* - * Do not allow to attach to a group in a different - * task or CPU context: + * Make sure we're both events for the same CPU; + * grouping events for different CPUs is broken; since + * you can never concurrently schedule them anyhow. */ - if (move_group) { - /* - * Make sure we're both on the same task, or both - * per-cpu events. - */ - if (group_leader->ctx->task != ctx->task) - goto err_context; + if (group_leader->cpu != event->cpu) + goto err_context; - /* - * Make sure we're both events for the same CPU; - * grouping events for different CPUs is broken; since - * you can never concurrently schedule them anyhow. - */ - if (group_leader->cpu != event->cpu) - goto err_context; - } else { - if (group_leader->ctx != ctx) - goto err_context; - } + /* + * Make sure we're both on the same task, or both + * per-CPU events. + */ + if (group_leader->ctx->task != ctx->task) + goto err_context; + + /* + * Do not allow to attach to a group in a different task + * or CPU context. If we're moving SW events, we'll fix + * this up later, so allow that. + */ + if (!move_group && group_leader->ctx != ctx) + goto err_context; /* * Only a group leader can be exclusive or pinned diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index f9ec9ad..a1de021 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1254,8 +1254,6 @@ void uprobe_end_dup_mmap(void) void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm) { - newmm->uprobes_state.xol_area = NULL; - if (test_bit(MMF_HAS_UPROBES, &oldmm->flags)) { set_bit(MMF_HAS_UPROBES, &newmm->flags); /* unconditionally, dup_mmap() skips VM_DONTCOPY vmas */ diff --git a/kernel/extable.c b/kernel/extable.c index e820cce..4f06fc3 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -66,7 +66,7 @@ static inline int init_kernel_text(unsigned long addr) return 0; } -int core_kernel_text(unsigned long addr) +int notrace core_kernel_text(unsigned long addr) { if (addr >= (unsigned long)_stext && addr < (unsigned long)_etext) diff --git a/kernel/fork.c b/kernel/fork.c index 59faac4..9321b1a 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -745,6 +745,13 @@ static void mm_init_owner(struct mm_struct *mm, struct task_struct *p) #endif } +static void mm_init_uprobes_state(struct mm_struct *mm) +{ +#ifdef CONFIG_UPROBES + mm->uprobes_state.xol_area = NULL; +#endif +} + static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, struct user_namespace *user_ns) { @@ -766,11 +773,13 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, mm_init_cpumask(mm); mm_init_aio(mm); mm_init_owner(mm, p); + RCU_INIT_POINTER(mm->exe_file, NULL); mmu_notifier_mm_init(mm); clear_tlb_flush_pending(mm); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS mm->pmd_huge_pte = NULL; #endif + mm_init_uprobes_state(mm); if (current->mm) { mm->flags = current->mm->flags & MMF_INIT_MASK; diff --git a/kernel/futex.c b/kernel/futex.c index 4c6b6e6..88bad86 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -668,13 +668,14 @@ again: * this reference was taken by ihold under the page lock * pinning the inode in place so i_lock was unnecessary. The * only way for this check to fail is if the inode was - * truncated in parallel so warn for now if this happens. + * truncated in parallel which is almost certainly an + * application bug. In such a case, just retry. * * We are not calling into get_futex_key_refs() in file-backed * cases, therefore a successful atomic_inc return below will * guarantee that get_futex_key() will still imply smp_mb(); (B). */ - if (WARN_ON_ONCE(!atomic_inc_not_zero(&inode->i_count))) { + if (!atomic_inc_not_zero(&inode->i_count)) { rcu_read_unlock(); put_page(page); diff --git a/kernel/gcov/base.c b/kernel/gcov/base.c index 2f9df37..c51a49c 100644 --- a/kernel/gcov/base.c +++ b/kernel/gcov/base.c @@ -98,6 +98,12 @@ void __gcov_merge_icall_topn(gcov_type *counters, unsigned int n_counters) } EXPORT_SYMBOL(__gcov_merge_icall_topn); +void __gcov_exit(void) +{ + /* Unused. */ +} +EXPORT_SYMBOL(__gcov_exit); + /** * gcov_enable_events - enable event reporting through gcov_event() * diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c index 6a5c239..46a18e7 100644 --- a/kernel/gcov/gcc_4_7.c +++ b/kernel/gcov/gcc_4_7.c @@ -18,7 +18,9 @@ #include <linux/vmalloc.h> #include "gcov.h" -#if (__GNUC__ > 5) || (__GNUC__ == 5 && __GNUC_MINOR__ >= 1) +#if (__GNUC__ >= 7) +#define GCOV_COUNTERS 9 +#elif (__GNUC__ > 5) || (__GNUC__ == 5 && __GNUC_MINOR__ >= 1) #define GCOV_COUNTERS 10 #elif __GNUC__ == 4 && __GNUC_MINOR__ >= 9 #define GCOV_COUNTERS 9 diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 077c87f..f30110e 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -895,13 +895,15 @@ EXPORT_SYMBOL_GPL(irq_set_chip_and_handler_name); void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set) { - unsigned long flags; + unsigned long flags, trigger, tmp; struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0); if (!desc) return; irq_settings_clr_and_set(desc, clr, set); + trigger = irqd_get_trigger_type(&desc->irq_data); + irqd_clear(&desc->irq_data, IRQD_NO_BALANCING | IRQD_PER_CPU | IRQD_TRIGGER_MASK | IRQD_LEVEL | IRQD_MOVE_PCNTXT); if (irq_settings_has_no_balance_set(desc)) @@ -913,7 +915,11 @@ void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set) if (irq_settings_is_level(desc)) irqd_set(&desc->irq_data, IRQD_LEVEL); - irqd_set(&desc->irq_data, irq_settings_get_trigger_mask(desc)); + tmp = irq_settings_get_trigger_mask(desc); + if (tmp != IRQ_TYPE_NONE) + trigger = tmp; + + irqd_set(&desc->irq_data, trigger); irq_put_desc_unlock(desc, flags); } diff --git a/kernel/irq/ipi.c b/kernel/irq/ipi.c index 1a9abc1..259a22a 100644 --- a/kernel/irq/ipi.c +++ b/kernel/irq/ipi.c @@ -165,7 +165,7 @@ irq_hw_number_t ipi_get_hwirq(unsigned int irq, unsigned int cpu) struct irq_data *data = irq_get_irq_data(irq); struct cpumask *ipimask = data ? irq_data_get_affinity_mask(data) : NULL; - if (!data || !ipimask || cpu > nr_cpu_ids) + if (!data || !ipimask || cpu >= nr_cpu_ids) return INVALID_HWIRQ; if (!cpumask_test_cpu(cpu, ipimask)) @@ -195,7 +195,7 @@ static int ipi_send_verify(struct irq_chip *chip, struct irq_data *data, if (!chip->ipi_send_single && !chip->ipi_send_mask) return -EINVAL; - if (cpu > nr_cpu_ids) + if (cpu >= nr_cpu_ids) return -EINVAL; if (dest) { diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 00bb0ae..77977f55df 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -405,10 +405,8 @@ static void free_desc(unsigned int irq) * The sysfs entry must be serialized against a concurrent * irq_sysfs_init() as well. */ - mutex_lock(&sparse_irq_lock); kobject_del(&desc->kobj); delete_irq_desc(irq); - mutex_unlock(&sparse_irq_lock); /* * We free the descriptor, masks and stat fields via RCU. That @@ -446,20 +444,15 @@ static int alloc_descs(unsigned int start, unsigned int cnt, int node, desc = alloc_desc(start + i, node, flags, mask, owner); if (!desc) goto err; - mutex_lock(&sparse_irq_lock); irq_insert_desc(start + i, desc); irq_sysfs_add(start + i, desc); - mutex_unlock(&sparse_irq_lock); } + bitmap_set(allocated_irqs, start, cnt); return start; err: for (i--; i >= 0; i--) free_desc(start + i); - - mutex_lock(&sparse_irq_lock); - bitmap_clear(allocated_irqs, start, cnt); - mutex_unlock(&sparse_irq_lock); return -ENOMEM; } @@ -558,6 +551,7 @@ static inline int alloc_descs(unsigned int start, unsigned int cnt, int node, desc->owner = owner; } + bitmap_set(allocated_irqs, start, cnt); return start; } @@ -653,10 +647,10 @@ void irq_free_descs(unsigned int from, unsigned int cnt) if (from >= nr_irqs || (from + cnt) > nr_irqs) return; + mutex_lock(&sparse_irq_lock); for (i = 0; i < cnt; i++) free_desc(from + i); - mutex_lock(&sparse_irq_lock); bitmap_clear(allocated_irqs, from, cnt); mutex_unlock(&sparse_irq_lock); } @@ -703,19 +697,15 @@ __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node, from, cnt, 0); ret = -EEXIST; if (irq >=0 && start != irq) - goto err; + goto unlock; if (start + cnt > nr_irqs) { ret = irq_expand_nr_irqs(start + cnt); if (ret) - goto err; + goto unlock; } - - bitmap_set(allocated_irqs, start, cnt); - mutex_unlock(&sparse_irq_lock); - return alloc_descs(start, cnt, node, affinity, owner); - -err: + ret = alloc_descs(start, cnt, node, affinity, owner); +unlock: mutex_unlock(&sparse_irq_lock); return ret; } diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 4d7ffc0..6599c7f 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -3260,10 +3260,17 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, if (depth) { hlock = curr->held_locks + depth - 1; if (hlock->class_idx == class_idx && nest_lock) { - if (hlock->references) + if (hlock->references) { + /* + * Check: unsigned int references:12, overflow. + */ + if (DEBUG_LOCKS_WARN_ON(hlock->references == (1 << 12)-1)) + return 0; + hlock->references++; - else + } else { hlock->references = 2; + } return 1; } diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index f8c5af5..d3de04b 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -780,6 +780,10 @@ static void lock_torture_cleanup(void) else lock_torture_print_module_parms(cxt.cur_ops, "End of test: SUCCESS"); + + kfree(cxt.lwsa); + kfree(cxt.lrsa); + end: torture_cleanup_end(); } @@ -924,6 +928,8 @@ static int __init lock_torture_init(void) GFP_KERNEL); if (reader_tasks == NULL) { VERBOSE_TOROUT_ERRSTRING("reader_tasks: Out of memory"); + kfree(writer_tasks); + writer_tasks = NULL; firsterr = -ENOMEM; goto unwind; } diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c index 2bef4ab..a608f7a 100644 --- a/kernel/locking/rwsem-spinlock.c +++ b/kernel/locking/rwsem-spinlock.c @@ -233,8 +233,8 @@ int __sched __down_write_common(struct rw_semaphore *sem, int state) out_nolock: list_del(&waiter.list); - if (!list_empty(&sem->wait_list)) - __rwsem_do_wake(sem, 1); + if (!list_empty(&sem->wait_list) && sem->count >= 0) + __rwsem_do_wake(sem, 0); raw_spin_unlock_irqrestore(&sem->wait_lock, flags); return -EINTR; diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c index 0374a59..9aa0fcc 100644 --- a/kernel/locking/spinlock_debug.c +++ b/kernel/locking/spinlock_debug.c @@ -103,38 +103,14 @@ static inline void debug_spin_unlock(raw_spinlock_t *lock) lock->owner_cpu = -1; } -static void __spin_lock_debug(raw_spinlock_t *lock) -{ - u64 i; - u64 loops = loops_per_jiffy * HZ; - - for (i = 0; i < loops; i++) { - if (arch_spin_trylock(&lock->raw_lock)) - return; - __delay(1); - } - /* lockup suspected: */ - spin_dump(lock, "lockup suspected"); -#ifdef CONFIG_SMP - trigger_all_cpu_backtrace(); -#endif - - /* - * The trylock above was causing a livelock. Give the lower level arch - * specific lock code a chance to acquire the lock. We have already - * printed a warning/backtrace at this point. The non-debug arch - * specific code might actually succeed in acquiring the lock. If it is - * not successful, the end-result is the same - there is no forward - * progress. - */ - arch_spin_lock(&lock->raw_lock); -} - +/* + * We are now relying on the NMI watchdog to detect lockup instead of doing + * the detection here with an unfair lock which can cause problem of its own. + */ void do_raw_spin_lock(raw_spinlock_t *lock) { debug_spin_lock_before(lock); - if (unlikely(!arch_spin_trylock(&lock->raw_lock))) - __spin_lock_debug(lock); + arch_spin_lock(&lock->raw_lock); debug_spin_lock_after(lock); } @@ -172,32 +148,6 @@ static void rwlock_bug(rwlock_t *lock, const char *msg) #define RWLOCK_BUG_ON(cond, lock, msg) if (unlikely(cond)) rwlock_bug(lock, msg) -#if 0 /* __write_lock_debug() can lock up - maybe this can too? */ -static void __read_lock_debug(rwlock_t *lock) -{ - u64 i; - u64 loops = loops_per_jiffy * HZ; - int print_once = 1; - - for (;;) { - for (i = 0; i < loops; i++) { - if (arch_read_trylock(&lock->raw_lock)) - return; - __delay(1); - } - /* lockup suspected: */ - if (print_once) { - print_once = 0; - printk(KERN_EMERG "BUG: read-lock lockup on CPU#%d, " - "%s/%d, %p\n", - raw_smp_processor_id(), current->comm, - current->pid, lock); - dump_stack(); - } - } -} -#endif - void do_raw_read_lock(rwlock_t *lock) { RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic"); @@ -247,32 +197,6 @@ static inline void debug_write_unlock(rwlock_t *lock) lock->owner_cpu = -1; } -#if 0 /* This can cause lockups */ -static void __write_lock_debug(rwlock_t *lock) -{ - u64 i; - u64 loops = loops_per_jiffy * HZ; - int print_once = 1; - - for (;;) { - for (i = 0; i < loops; i++) { - if (arch_write_trylock(&lock->raw_lock)) - return; - __delay(1); - } - /* lockup suspected: */ - if (print_once) { - print_once = 0; - printk(KERN_EMERG "BUG: write-lock lockup on CPU#%d, " - "%s/%d, %p\n", - raw_smp_processor_id(), current->comm, - current->pid, lock); - dump_stack(); - } - } -} -#endif - void do_raw_write_lock(rwlock_t *lock) { debug_write_lock_before(lock); diff --git a/kernel/panic.c b/kernel/panic.c index e6480e2..dbec387 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -249,7 +249,7 @@ void panic(const char *fmt, ...) * Delay timeout seconds before rebooting the machine. * We can't use the "normal" timers since we just panicked. */ - pr_emerg("Rebooting in %d seconds..", panic_timeout); + pr_emerg("Rebooting in %d seconds..\n", panic_timeout); for (i = 0; i < panic_timeout * 1000; i += PANIC_TIMER_STEP) { touch_nmi_watchdog(); diff --git a/kernel/pid.c b/kernel/pid.c index f66162f..693a643 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -526,8 +526,11 @@ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, if (!ns) ns = task_active_pid_ns(current); if (likely(pid_alive(task))) { - if (type != PIDTYPE_PID) + if (type != PIDTYPE_PID) { + if (type == __PIDTYPE_TGID) + type = PIDTYPE_PID; task = task->group_leader; + } nr = pid_nr_ns(rcu_dereference(task->pids[type].pid), ns); } rcu_read_unlock(); @@ -536,12 +539,6 @@ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, } EXPORT_SYMBOL(__task_pid_nr_ns); -pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) -{ - return pid_nr_ns(task_tgid(tsk), ns); -} -EXPORT_SYMBOL(task_tgid_nr_ns); - struct pid_namespace *task_active_pid_ns(struct task_struct *tsk) { return ns_of_pid(task_pid(tsk)); diff --git a/kernel/power/process.c b/kernel/power/process.c index 2fba066..8ea24de 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -18,8 +18,9 @@ #include <linux/workqueue.h> #include <linux/kmod.h> #include <trace/events/power.h> +#include <linux/cpuset.h> -/* +/* * Timeout for stopping processes */ unsigned int __read_mostly freeze_timeout_msecs = 20 * MSEC_PER_SEC; @@ -200,6 +201,8 @@ void thaw_processes(void) __usermodehelper_set_disable_depth(UMH_FREEZING); thaw_workqueues(); + cpuset_wait_for_hotplug(); + read_lock(&tasklist_lock); for_each_process_thread(g, p) { /* No other threads should have PF_SUSPEND_TASK set */ diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 10f62c6..d1a0287 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -792,8 +792,13 @@ void rcu_irq_exit(void) long long oldval; struct rcu_dynticks *rdtp; - RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_exit() invoked with irqs enabled!!!"); rdtp = this_cpu_ptr(&rcu_dynticks); + + /* Page faults can happen in NMI handlers, so check... */ + if (READ_ONCE(rdtp->dynticks_nmi_nesting)) + return; + + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_exit() invoked with irqs enabled!!!"); oldval = rdtp->dynticks_nesting; rdtp->dynticks_nesting--; WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && @@ -930,8 +935,13 @@ void rcu_irq_enter(void) struct rcu_dynticks *rdtp; long long oldval; - RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_enter() invoked with irqs enabled!!!"); rdtp = this_cpu_ptr(&rcu_dynticks); + + /* Page faults can happen in NMI handlers, so check... */ + if (READ_ONCE(rdtp->dynticks_nmi_nesting)) + return; + + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_enter() invoked with irqs enabled!!!"); oldval = rdtp->dynticks_nesting; rdtp->dynticks_nesting++; WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 56583e7..e3944c4 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -1767,6 +1767,7 @@ static void wake_nocb_leader(struct rcu_data *rdp, bool force) if (READ_ONCE(rdp_leader->nocb_leader_sleep) || force) { /* Prior smp_mb__after_atomic() orders against prior enqueue. */ WRITE_ONCE(rdp_leader->nocb_leader_sleep, false); + smp_mb(); /* ->nocb_leader_sleep before swake_up(). */ swake_up(&rdp_leader->nocb_wq); } } @@ -2021,6 +2022,7 @@ wait_again: * nocb_gp_head, where they await a grace period. */ gotcbs = false; + smp_mb(); /* wakeup before ->nocb_head reads. */ for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) { rdp->nocb_gp_head = READ_ONCE(rdp->nocb_head); if (!rdp->nocb_gp_head) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 692c948..78181c0 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1141,6 +1141,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, int ret = 0; rq = task_rq_lock(p, &rf); + update_rq_clock(rq); if (p->flags & PF_KTHREAD) { /* @@ -6102,6 +6103,9 @@ enum s_alloc { * Build an iteration mask that can exclude certain CPUs from the upwards * domain traversal. * + * Only CPUs that can arrive at this group should be considered to continue + * balancing. + * * Asymmetric node setups can result in situations where the domain tree is of * unequal depth, make sure to skip domains that already cover the entire * range. @@ -6113,18 +6117,31 @@ enum s_alloc { */ static void build_group_mask(struct sched_domain *sd, struct sched_group *sg) { - const struct cpumask *span = sched_domain_span(sd); + const struct cpumask *sg_span = sched_group_cpus(sg); struct sd_data *sdd = sd->private; struct sched_domain *sibling; int i; - for_each_cpu(i, span) { + for_each_cpu(i, sg_span) { sibling = *per_cpu_ptr(sdd->sd, i); - if (!cpumask_test_cpu(i, sched_domain_span(sibling))) + + /* + * Can happen in the asymmetric case, where these siblings are + * unused. The mask will not be empty because those CPUs that + * do have the top domain _should_ span the domain. + */ + if (!sibling->child) + continue; + + /* If we would not end up here, we can't continue from here */ + if (!cpumask_equal(sg_span, sched_domain_span(sibling->child))) continue; cpumask_set_cpu(i, sched_group_mask(sg)); } + + /* We must not have empty masks here */ + WARN_ON_ONCE(cpumask_empty(sched_group_mask(sg))); } /* @@ -6148,7 +6165,7 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu) cpumask_clear(covered); - for_each_cpu(i, span) { + for_each_cpu_wrap(i, span, cpu) { struct cpumask *sg_span; if (cpumask_test_cpu(i, covered)) @@ -7276,16 +7293,15 @@ static void cpuset_cpu_active(void) * operation in the resume sequence, just build a single sched * domain, ignoring cpusets. */ - num_cpus_frozen--; - if (likely(num_cpus_frozen)) { - partition_sched_domains(1, NULL, NULL); + partition_sched_domains(1, NULL, NULL); + if (--num_cpus_frozen) return; - } /* * This is the last CPU online operation. So fall through and * restore the original sched domains by considering the * cpuset configurations. */ + cpuset_force_rebuild(); } cpuset_update_active_cpus(true); } @@ -7422,22 +7438,6 @@ int sched_cpu_dying(unsigned int cpu) } #endif -#ifdef CONFIG_SCHED_SMT -DEFINE_STATIC_KEY_FALSE(sched_smt_present); - -static void sched_init_smt(void) -{ - /* - * We've enumerated all CPUs and will assume that if any CPU - * has SMT siblings, CPU0 will too. - */ - if (cpumask_weight(cpu_smt_mask(0)) > 1) - static_branch_enable(&sched_smt_present); -} -#else -static inline void sched_init_smt(void) { } -#endif - void __init sched_init_smp(void) { cpumask_var_t non_isolated_cpus; @@ -7467,9 +7467,6 @@ void __init sched_init_smp(void) init_sched_rt_class(); init_sched_dl_class(); - - sched_init_smt(); - sched_smp_initialized = true; } @@ -7964,6 +7961,7 @@ void sched_move_task(struct task_struct *tsk) struct rq *rq; rq = task_rq_lock(tsk, &rf); + update_rq_clock(rq); running = task_current(rq, tsk); queued = task_on_rq_queued(tsk); @@ -8379,11 +8377,20 @@ cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) if (IS_ERR(tg)) return ERR_PTR(-ENOMEM); - sched_online_group(tg, parent); - return &tg->css; } +/* Expose task group only after completing cgroup initialization */ +static int cpu_cgroup_css_online(struct cgroup_subsys_state *css) +{ + struct task_group *tg = css_tg(css); + struct task_group *parent = css_tg(css->parent); + + if (parent) + sched_online_group(tg, parent); + return 0; +} + static void cpu_cgroup_css_released(struct cgroup_subsys_state *css) { struct task_group *tg = css_tg(css); @@ -8786,6 +8793,7 @@ static struct cftype cpu_files[] = { struct cgroup_subsys cpu_cgrp_subsys = { .css_alloc = cpu_cgroup_css_alloc, + .css_online = cpu_cgroup_css_online, .css_released = cpu_cgroup_css_released, .css_free = cpu_cgroup_css_free, .fork = cpu_cgroup_fork, diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index c242944..7a68c63 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5310,43 +5310,6 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu) return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu; } -/* - * Implement a for_each_cpu() variant that starts the scan at a given cpu - * (@start), and wraps around. - * - * This is used to scan for idle CPUs; such that not all CPUs looking for an - * idle CPU find the same CPU. The down-side is that tasks tend to cycle - * through the LLC domain. - * - * Especially tbench is found sensitive to this. - */ - -static int cpumask_next_wrap(int n, const struct cpumask *mask, int start, int *wrapped) -{ - int next; - -again: - next = find_next_bit(cpumask_bits(mask), nr_cpumask_bits, n+1); - - if (*wrapped) { - if (next >= start) - return nr_cpumask_bits; - } else { - if (next >= nr_cpumask_bits) { - *wrapped = 1; - n = -1; - goto again; - } - } - - return next; -} - -#define for_each_cpu_wrap(cpu, mask, start, wrap) \ - for ((wrap) = 0, (cpu) = (start)-1; \ - (cpu) = cpumask_next_wrap((cpu), (mask), (start), &(wrap)), \ - (cpu) < nr_cpumask_bits; ) - #ifdef CONFIG_SCHED_SMT static inline void set_idle_cores(int cpu, int val) @@ -5376,7 +5339,7 @@ static inline bool test_idle_cores(int cpu, bool def) * Since SMT siblings share all cache levels, inspecting this limited remote * state should be fairly cheap. */ -void __update_idle_core(struct rq *rq) +void update_idle_core(struct rq *rq) { int core = cpu_of(rq); int cpu; @@ -5406,17 +5369,14 @@ unlock: static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int target) { struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask); - int core, cpu, wrap; - - if (!static_branch_likely(&sched_smt_present)) - return -1; + int core, cpu; if (!test_idle_cores(target, false)) return -1; cpumask_and(cpus, sched_domain_span(sd), tsk_cpus_allowed(p)); - for_each_cpu_wrap(core, cpus, target, wrap) { + for_each_cpu_wrap(core, cpus, target) { bool idle = true; for_each_cpu(cpu, cpu_smt_mask(core)) { @@ -5444,9 +5404,6 @@ static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int t { int cpu; - if (!static_branch_likely(&sched_smt_present)) - return -1; - for_each_cpu(cpu, cpu_smt_mask(target)) { if (!cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) continue; @@ -5482,7 +5439,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t u64 avg_cost, avg_idle = this_rq()->avg_idle; u64 time, cost; s64 delta; - int cpu, wrap; + int cpu; this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc)); if (!this_sd) @@ -5499,7 +5456,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t time = local_clock(); - for_each_cpu_wrap(cpu, sched_domain_span(sd), target, wrap) { + for_each_cpu_wrap(cpu, sched_domain_span(sd), target) { if (!cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) continue; if (idle_cpu(cpu)) diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index a2d6eb7..ec91fcc 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -201,8 +201,9 @@ void calc_load_exit_idle(void) struct rq *this_rq = this_rq(); /* - * If we're still before the sample window, we're done. + * If we're still before the pending sample window, we're done. */ + this_rq->calc_load_update = calc_load_update; if (time_before(jiffies, this_rq->calc_load_update)) return; @@ -211,7 +212,6 @@ void calc_load_exit_idle(void) * accounted through the nohz accounting, so skip the entire deal and * sync up for the next window. */ - this_rq->calc_load_update = calc_load_update; if (time_before(jiffies, this_rq->calc_load_update + 10)) this_rq->calc_load_update += LOAD_FREQ; } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 055f935..ad77d66 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -43,6 +43,12 @@ extern void cpu_load_update_active(struct rq *this_rq); static inline void cpu_load_update_active(struct rq *this_rq) { } #endif +#ifdef CONFIG_SCHED_SMT +extern void update_idle_core(struct rq *rq); +#else +static inline void update_idle_core(struct rq *rq) { } +#endif + /* * Helpers for converting nanosecond timing to jiffy resolution */ @@ -731,23 +737,6 @@ static inline int cpu_of(struct rq *rq) #endif } - -#ifdef CONFIG_SCHED_SMT - -extern struct static_key_false sched_smt_present; - -extern void __update_idle_core(struct rq *rq); - -static inline void update_idle_core(struct rq *rq) -{ - if (static_branch_unlikely(&sched_smt_present)) - __update_idle_core(rq); -} - -#else -static inline void update_idle_core(struct rq *rq) { } -#endif - DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); #define cpu_rq(cpu) (&per_cpu(runqueues, (cpu))) diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 0db7c8a..af182a6 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -457,14 +457,19 @@ static long seccomp_attach_filter(unsigned int flags, return 0; } +void __get_seccomp_filter(struct seccomp_filter *filter) +{ + /* Reference count is bounded by the number of total processes. */ + atomic_inc(&filter->usage); +} + /* get_seccomp_filter - increments the reference count of the filter on @tsk */ void get_seccomp_filter(struct task_struct *tsk) { struct seccomp_filter *orig = tsk->seccomp.filter; if (!orig) return; - /* Reference count is bounded by the number of total processes. */ - atomic_inc(&orig->usage); + __get_seccomp_filter(orig); } static inline void seccomp_filter_free(struct seccomp_filter *filter) @@ -475,10 +480,8 @@ static inline void seccomp_filter_free(struct seccomp_filter *filter) } } -/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */ -void put_seccomp_filter(struct task_struct *tsk) +static void __put_seccomp_filter(struct seccomp_filter *orig) { - struct seccomp_filter *orig = tsk->seccomp.filter; /* Clean up single-reference branches iteratively. */ while (orig && atomic_dec_and_test(&orig->usage)) { struct seccomp_filter *freeme = orig; @@ -487,6 +490,12 @@ void put_seccomp_filter(struct task_struct *tsk) } } +/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */ +void put_seccomp_filter(struct task_struct *tsk) +{ + __put_seccomp_filter(tsk->seccomp.filter); +} + /** * seccomp_send_sigsys - signals the task to allow in-process syscall emulation * @syscall: syscall number to send to userland @@ -892,13 +901,13 @@ long seccomp_get_filter(struct task_struct *task, unsigned long filter_off, if (!data) goto out; - get_seccomp_filter(task); + __get_seccomp_filter(filter); spin_unlock_irq(&task->sighand->siglock); if (copy_to_user(data, fprog->filter, bpf_classic_proglen(fprog))) ret = -EFAULT; - put_seccomp_filter(task); + __put_seccomp_filter(filter); return ret; out: diff --git a/kernel/signal.c b/kernel/signal.c index deb04d5..e48668c 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -346,7 +346,7 @@ static bool task_participate_group_stop(struct task_struct *task) * fresh group stop. Read comment in do_signal_stop() for details. */ if (!sig->group_stop_count && !(sig->flags & SIGNAL_STOP_STOPPED)) { - sig->flags = SIGNAL_STOP_STOPPED; + signal_set_stop_flags(sig, SIGNAL_STOP_STOPPED); return true; } return false; @@ -845,7 +845,7 @@ static bool prepare_signal(int sig, struct task_struct *p, bool force) * will take ->siglock, notice SIGNAL_CLD_MASK, and * notify its parent. See get_signal_to_deliver(). */ - signal->flags = why | SIGNAL_STOP_CONTINUED; + signal_set_stop_flags(signal, why | SIGNAL_STOP_CONTINUED); signal->group_stop_count = 0; signal->group_exit_code = 0; } diff --git a/kernel/sysctl.c b/kernel/sysctl.c index c1095cd..24d603d 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1189,6 +1189,8 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = timer_migration_handler, + .extra1 = &zero, + .extra2 = &one, }, #endif #ifdef CONFIG_BPF_SYSCALL @@ -2146,9 +2148,12 @@ static int do_proc_douintvec_conv(bool *negp, unsigned long *lvalp, if (write) { if (*negp) return -EINVAL; + if (*lvalp > UINT_MAX) + return -EINVAL; *valp = *lvalp; } else { unsigned int val = *valp; + *negp = false; *lvalp = (unsigned long)val; } return 0; diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 9ba04aa..d67ef56 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -629,7 +629,8 @@ static int alarm_timer_set(struct k_itimer *timr, int flags, * Rate limit to the tick as a hot fix to prevent DOS. Will be * mopped up later. */ - if (ktime_to_ns(timr->it.alarm.interval) < TICK_NSEC) + if (timr->it.alarm.interval.tv64 && + ktime_to_ns(timr->it.alarm.interval) < TICK_NSEC) timr->it.alarm.interval = ktime_set(0, TICK_NSEC); exp = timespec_to_ktime(new_setting->it_value); diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index bb5ec42..eeb7f2f 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -94,17 +94,15 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) = }; static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = { + /* Make sure we catch unsupported clockids */ + [0 ... MAX_CLOCKS - 1] = HRTIMER_MAX_CLOCK_BASES, + [CLOCK_REALTIME] = HRTIMER_BASE_REALTIME, [CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC, [CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME, [CLOCK_TAI] = HRTIMER_BASE_TAI, }; -static inline int hrtimer_clockid_to_base(clockid_t clock_id) -{ - return hrtimer_clock_to_base_table[clock_id]; -} - /* * Functions and macros which are different for UP/SMP systems are kept in a * single place @@ -1112,6 +1110,18 @@ u64 hrtimer_get_next_event(void) } #endif +static inline int hrtimer_clockid_to_base(clockid_t clock_id) +{ + if (likely(clock_id < MAX_CLOCKS)) { + int base = hrtimer_clock_to_base_table[clock_id]; + + if (likely(base != HRTIMER_MAX_CLOCK_BASES)) + return base; + } + WARN(1, "Invalid clockid %d. Using MONOTONIC\n", clock_id); + return HRTIMER_BASE_MONOTONIC; +} + static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, enum hrtimer_mode mode) { diff --git a/kernel/time/timer.c b/kernel/time/timer.c index c611c47..7d67036 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -201,6 +201,7 @@ struct timer_base { bool migration_enabled; bool nohz_active; bool is_idle; + bool must_forward_clk; DECLARE_BITMAP(pending_map, WHEEL_SIZE); struct hlist_head vectors[WHEEL_SIZE]; } ____cacheline_aligned; @@ -239,7 +240,7 @@ int timer_migration_handler(struct ctl_table *table, int write, int ret; mutex_lock(&mutex); - ret = proc_dointvec(table, write, buffer, lenp, ppos); + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (!ret && write) timers_update_migration(false); mutex_unlock(&mutex); @@ -891,13 +892,19 @@ get_target_base(struct timer_base *base, unsigned tflags) static inline void forward_timer_base(struct timer_base *base) { - unsigned long jnow = READ_ONCE(jiffies); + unsigned long jnow; /* - * We only forward the base when it's idle and we have a delta between - * base clock and jiffies. + * We only forward the base when we are idle or have just come out of + * idle (must_forward_clk logic), and have a delta between base clock + * and jiffies. In the common case, run_timers will take care of it. */ - if (!base->is_idle || (long) (jnow - base->clk) < 2) + if (likely(!base->must_forward_clk)) + return; + + jnow = READ_ONCE(jiffies); + base->must_forward_clk = base->is_idle; + if ((long)(jnow - base->clk) < 2) return; /* @@ -973,6 +980,11 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only) * same array bucket then just return: */ if (timer_pending(timer)) { + /* + * The downside of this optimization is that it can result in + * larger granularity than you would get from adding a new + * timer with this expiry. + */ if (timer->expires == expires) return 1; @@ -983,6 +995,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only) * dequeue/enqueue dance. */ base = lock_timer_base(timer, &flags); + forward_timer_base(base); clk = base->clk; idx = calc_wheel_index(expires, clk); @@ -999,6 +1012,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only) } } else { base = lock_timer_base(timer, &flags); + forward_timer_base(base); } timer_stats_timer_set_start_info(timer); @@ -1028,12 +1042,10 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only) spin_lock(&base->lock); WRITE_ONCE(timer->flags, (timer->flags & ~TIMER_BASEMASK) | base->cpu); + forward_timer_base(base); } } - /* Try to forward a stale timer base clock */ - forward_timer_base(base); - timer->expires = expires; /* * If 'idx' was calculated above and the base time did not advance @@ -1150,6 +1162,7 @@ void add_timer_on(struct timer_list *timer, int cpu) WRITE_ONCE(timer->flags, (timer->flags & ~TIMER_BASEMASK) | cpu); } + forward_timer_base(base); debug_activate(timer, timer->expires); internal_add_timer(base, timer); @@ -1536,12 +1549,18 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) base->is_idle = false; } else { if (!is_max_delta) - expires = basem + (nextevt - basej) * TICK_NSEC; + expires = basem + (u64)(nextevt - basej) * TICK_NSEC; /* - * If we expect to sleep more than a tick, mark the base idle: + * If we expect to sleep more than a tick, mark the base idle. + * Also the tick is stopped so any added timer must forward + * the base clk itself to keep granularity small. This idle + * logic is only maintained for the BASE_STD base, deferrable + * timers may still see large granularity skew (by design). */ - if ((expires - basem) > TICK_NSEC) + if ((expires - basem) > TICK_NSEC) { + base->must_forward_clk = true; base->is_idle = true; + } } spin_unlock(&base->lock); @@ -1651,6 +1670,19 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h) { struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); + /* + * must_forward_clk must be cleared before running timers so that any + * timer functions that call mod_timer will not try to forward the + * base. idle trcking / clock forwarding logic is only used with + * BASE_STD timers. + * + * The deferrable base does not do idle tracking at all, so we do + * not forward it. This can result in very large variations in + * granularity for deferrable timers, but they can be deferred for + * long periods due to idle. + */ + base->must_forward_clk = false; + __run_timers(base); if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active) __run_timers(this_cpu_ptr(&timer_bases[BASE_DEF])); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 5dcb992..41805fb 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -203,10 +203,36 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, fmt_cnt++; } - return __trace_printk(1/* fake ip will not be printed */, fmt, - mod[0] == 2 ? arg1 : mod[0] == 1 ? (long) arg1 : (u32) arg1, - mod[1] == 2 ? arg2 : mod[1] == 1 ? (long) arg2 : (u32) arg2, - mod[2] == 2 ? arg3 : mod[2] == 1 ? (long) arg3 : (u32) arg3); +/* Horrid workaround for getting va_list handling working with different + * argument type combinations generically for 32 and 64 bit archs. + */ +#define __BPF_TP_EMIT() __BPF_ARG3_TP() +#define __BPF_TP(...) \ + __trace_printk(1 /* Fake ip will not be printed. */, \ + fmt, ##__VA_ARGS__) + +#define __BPF_ARG1_TP(...) \ + ((mod[0] == 2 || (mod[0] == 1 && __BITS_PER_LONG == 64)) \ + ? __BPF_TP(arg1, ##__VA_ARGS__) \ + : ((mod[0] == 1 || (mod[0] == 0 && __BITS_PER_LONG == 32)) \ + ? __BPF_TP((long)arg1, ##__VA_ARGS__) \ + : __BPF_TP((u32)arg1, ##__VA_ARGS__))) + +#define __BPF_ARG2_TP(...) \ + ((mod[1] == 2 || (mod[1] == 1 && __BITS_PER_LONG == 64)) \ + ? __BPF_ARG1_TP(arg2, ##__VA_ARGS__) \ + : ((mod[1] == 1 || (mod[1] == 0 && __BITS_PER_LONG == 32)) \ + ? __BPF_ARG1_TP((long)arg2, ##__VA_ARGS__) \ + : __BPF_ARG1_TP((u32)arg2, ##__VA_ARGS__))) + +#define __BPF_ARG3_TP(...) \ + ((mod[2] == 2 || (mod[2] == 1 && __BITS_PER_LONG == 64)) \ + ? __BPF_ARG2_TP(arg3, ##__VA_ARGS__) \ + : ((mod[2] == 1 || (mod[2] == 0 && __BITS_PER_LONG == 32)) \ + ? __BPF_ARG2_TP((long)arg3, ##__VA_ARGS__) \ + : __BPF_ARG2_TP((u32)arg3, ##__VA_ARGS__))) + + return __BPF_TP_EMIT(); } static const struct bpf_func_proto bpf_trace_printk_proto = { diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 221eb59..5b8d718 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -876,6 +876,10 @@ static int profile_graph_entry(struct ftrace_graph_ent *trace) function_profile_call(trace->func, 0, NULL, NULL); + /* If function graph is shutting down, ret_stack can be NULL */ + if (!current->ret_stack) + return 0; + if (index >= 0 && index < FTRACE_RETFUNC_DEPTH) current->ret_stack[index].subtime = 0; @@ -2743,13 +2747,14 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command) if (!command || !ftrace_enabled) { /* - * If these are per_cpu ops, they still need their - * per_cpu field freed. Since, function tracing is + * If these are dynamic or per_cpu ops, they still + * need their data freed. Since, function tracing is * not currently active, we can just free them * without synchronizing all CPUs. */ - if (ops->flags & FTRACE_OPS_FL_PER_CPU) - per_cpu_ops_free(ops); + if (ops->flags & (FTRACE_OPS_FL_DYNAMIC | FTRACE_OPS_FL_PER_CPU)) + goto free_ops; + return 0; } @@ -2804,6 +2809,7 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command) if (ops->flags & (FTRACE_OPS_FL_DYNAMIC | FTRACE_OPS_FL_PER_CPU)) { schedule_on_each_cpu(ftrace_sync); + free_ops: arch_ftrace_trampoline_free(ops); if (ops->flags & FTRACE_OPS_FL_PER_CPU) @@ -3590,7 +3596,7 @@ match_records(struct ftrace_hash *hash, char *func, int len, char *mod) int exclude_mod = 0; int found = 0; int ret; - int clear_filter; + int clear_filter = 0; if (func) { func_g.type = filter_parse_regex(func, len, &func_g.search, @@ -4375,9 +4381,6 @@ static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata; static char ftrace_graph_notrace_buf[FTRACE_FILTER_SIZE] __initdata; static int ftrace_set_func(unsigned long *array, int *idx, int size, char *buffer); -static unsigned long save_global_trampoline; -static unsigned long save_global_flags; - static int __init set_graph_function(char *str) { strlcpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE); @@ -5975,17 +5978,6 @@ void unregister_ftrace_graph(void) unregister_pm_notifier(&ftrace_suspend_notifier); unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL); -#ifdef CONFIG_DYNAMIC_FTRACE - /* - * Function graph does not allocate the trampoline, but - * other global_ops do. We need to reset the ALLOC_TRAMP flag - * if one was used. - */ - global_ops.trampoline = save_global_trampoline; - if (save_global_flags & FTRACE_OPS_FL_ALLOC_TRAMP) - global_ops.flags |= FTRACE_OPS_FL_ALLOC_TRAMP; -#endif - out: mutex_unlock(&ftrace_lock); } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 83c60f9..c1e50cc 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1906,7 +1906,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, #endif ((pc & NMI_MASK ) ? TRACE_FLAG_NMI : 0) | ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) | - ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) | + ((pc & SOFTIRQ_OFFSET) ? TRACE_FLAG_SOFTIRQ : 0) | (tif_need_resched() ? TRACE_FLAG_NEED_RESCHED : 0) | (test_preempt_need_resched() ? TRACE_FLAG_PREEMPT_RESCHED : 0); } @@ -2369,11 +2369,17 @@ static char *get_trace_buf(void) if (!buffer || buffer->nesting >= 4) return NULL; - return &buffer->buffer[buffer->nesting++][0]; + buffer->nesting++; + + /* Interrupts must see nesting incremented before we use the buffer */ + barrier(); + return &buffer->buffer[buffer->nesting][0]; } static void put_trace_buf(void) { + /* Don't let the decrement of nesting leak before this */ + barrier(); this_cpu_dec(trace_percpu_buffer->nesting); } @@ -3563,11 +3569,17 @@ static int tracing_open(struct inode *inode, struct file *file) /* If this file was open for write, then erase contents */ if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { int cpu = tracing_get_cpu(inode); + struct trace_buffer *trace_buf = &tr->trace_buffer; + +#ifdef CONFIG_TRACER_MAX_TRACE + if (tr->current_trace->print_max) + trace_buf = &tr->max_buffer; +#endif if (cpu == RING_BUFFER_ALL_CPUS) - tracing_reset_online_cpus(&tr->trace_buffer); + tracing_reset_online_cpus(trace_buf); else - tracing_reset(&tr->trace_buffer, cpu); + tracing_reset(trace_buf, cpu); } if (file->f_mode & FMODE_READ) { @@ -5122,7 +5134,7 @@ static int tracing_wait_pipe(struct file *filp) * * iter->pos will be 0 if we haven't read anything. */ - if (!tracing_is_on() && iter->pos) + if (!tracer_tracing_is_on(iter->tr) && iter->pos) break; mutex_unlock(&iter->mutex); @@ -5658,7 +5670,7 @@ static int tracing_set_clock(struct trace_array *tr, const char *clockstr) tracing_reset_online_cpus(&tr->trace_buffer); #ifdef CONFIG_TRACER_MAX_TRACE - if (tr->flags & TRACE_ARRAY_FL_GLOBAL && tr->max_buffer.buffer) + if (tr->max_buffer.buffer) ring_buffer_set_clock(tr->max_buffer.buffer, trace_clocks[i].func); tracing_reset_online_cpus(&tr->max_buffer); #endif @@ -7162,6 +7174,7 @@ static int instance_rmdir(const char *name) } kfree(tr->topts); + free_cpumask_var(tr->tracing_cpumask); kfree(tr->name); kfree(tr); @@ -7766,4 +7779,4 @@ __init static int clear_boot_tracer(void) } fs_initcall(tracer_init_tracefs); -late_initcall(clear_boot_tracer); +late_initcall_sync(clear_boot_tracer); diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 9daa9b3..0193f58 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1926,6 +1926,10 @@ static int create_filter(struct trace_event_call *call, if (err && set_str) append_filter_err(ps, filter); } + if (err && !set_str) { + free_event_filter(filter); + filter = NULL; + } create_filter_finish(ps); *filterp = filter; diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 8d2b4d8..5ff45ca 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -667,30 +667,25 @@ static int create_trace_kprobe(int argc, char **argv) pr_info("Probe point is not specified.\n"); return -EINVAL; } - if (isdigit(argv[1][0])) { - if (is_return) { - pr_info("Return probe point must be a symbol.\n"); - return -EINVAL; - } - /* an address specified */ - ret = kstrtoul(&argv[1][0], 0, (unsigned long *)&addr); - if (ret) { - pr_info("Failed to parse address.\n"); - return ret; - } - } else { + + /* try to parse an address. if that fails, try to read the + * input as a symbol. */ + if (kstrtoul(argv[1], 0, (unsigned long *)&addr)) { /* a symbol specified */ symbol = argv[1]; /* TODO: support .init module functions */ ret = traceprobe_split_symbol_offset(symbol, &offset); if (ret) { - pr_info("Failed to parse symbol.\n"); + pr_info("Failed to parse either an address or a symbol.\n"); return ret; } if (offset && is_return) { pr_info("Return probe must be used without offset.\n"); return -EINVAL; } + } else if (is_return) { + pr_info("Return probe point must be a symbol.\n"); + return -EINVAL; } argc -= 2; argv += 2; diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index b0f86ea..ca70d11 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -272,7 +272,7 @@ static int trace_selftest_ops(struct trace_array *tr, int cnt) goto out_free; if (cnt > 1) { if (trace_selftest_test_global_cnt == 0) - goto out; + goto out_free; } if (trace_selftest_test_dyn_cnt == 0) goto out_free; diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c index 0a689bb..305039b 100644 --- a/kernel/trace/tracing_map.c +++ b/kernel/trace/tracing_map.c @@ -221,16 +221,19 @@ void tracing_map_array_free(struct tracing_map_array *a) if (!a) return; - if (!a->pages) { - kfree(a); - return; - } + if (!a->pages) + goto free; for (i = 0; i < a->n_pages; i++) { if (!a->pages[i]) break; free_page((unsigned long)a->pages[i]); } + + kfree(a->pages); + + free: + kfree(a); } struct tracing_map_array *tracing_map_array_alloc(unsigned int n_elts, diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 479d840..296dcca 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -68,6 +68,7 @@ enum { * attach_mutex to avoid changing binding state while * worker_attach_to_pool() is in progress. */ + POOL_MANAGER_ACTIVE = 1 << 0, /* being managed */ POOL_DISASSOCIATED = 1 << 2, /* cpu can't serve workers */ /* worker flags */ @@ -165,7 +166,6 @@ struct worker_pool { /* L: hash of busy workers */ /* see manage_workers() for details on the two manager mutexes */ - struct mutex manager_arb; /* manager arbitration */ struct worker *manager; /* L: purely informational */ struct mutex attach_mutex; /* attach/detach exclusion */ struct list_head workers; /* A: attached workers */ @@ -297,6 +297,7 @@ static struct workqueue_attrs *wq_update_unbound_numa_attrs_buf; static DEFINE_MUTEX(wq_pool_mutex); /* protects pools and workqueues list */ static DEFINE_SPINLOCK(wq_mayday_lock); /* protects wq->maydays list */ +static DECLARE_WAIT_QUEUE_HEAD(wq_manager_wait); /* wait for manager to go away */ static LIST_HEAD(workqueues); /* PR: list of all workqueues */ static bool workqueue_freezing; /* PL: have wqs started freezing? */ @@ -799,7 +800,7 @@ static bool need_to_create_worker(struct worker_pool *pool) /* Do we have too many workers and should some go away? */ static bool too_many_workers(struct worker_pool *pool) { - bool managing = mutex_is_locked(&pool->manager_arb); + bool managing = pool->flags & POOL_MANAGER_ACTIVE; int nr_idle = pool->nr_idle + managing; /* manager is considered idle */ int nr_busy = pool->nr_workers - nr_idle; @@ -1979,24 +1980,17 @@ static bool manage_workers(struct worker *worker) { struct worker_pool *pool = worker->pool; - /* - * Anyone who successfully grabs manager_arb wins the arbitration - * and becomes the manager. mutex_trylock() on pool->manager_arb - * failure while holding pool->lock reliably indicates that someone - * else is managing the pool and the worker which failed trylock - * can proceed to executing work items. This means that anyone - * grabbing manager_arb is responsible for actually performing - * manager duties. If manager_arb is grabbed and released without - * actual management, the pool may stall indefinitely. - */ - if (!mutex_trylock(&pool->manager_arb)) + if (pool->flags & POOL_MANAGER_ACTIVE) return false; + + pool->flags |= POOL_MANAGER_ACTIVE; pool->manager = worker; maybe_create_worker(pool); pool->manager = NULL; - mutex_unlock(&pool->manager_arb); + pool->flags &= ~POOL_MANAGER_ACTIVE; + wake_up(&wq_manager_wait); return true; } @@ -3203,7 +3197,6 @@ static int init_worker_pool(struct worker_pool *pool) setup_timer(&pool->mayday_timer, pool_mayday_timeout, (unsigned long)pool); - mutex_init(&pool->manager_arb); mutex_init(&pool->attach_mutex); INIT_LIST_HEAD(&pool->workers); @@ -3273,13 +3266,15 @@ static void put_unbound_pool(struct worker_pool *pool) hash_del(&pool->hash_node); /* - * Become the manager and destroy all workers. Grabbing - * manager_arb prevents @pool's workers from blocking on - * attach_mutex. + * Become the manager and destroy all workers. This prevents + * @pool's workers from blocking on attach_mutex. We're the last + * manager and @pool gets freed with the flag set. */ - mutex_lock(&pool->manager_arb); - spin_lock_irq(&pool->lock); + wait_event_lock_irq(wq_manager_wait, + !(pool->flags & POOL_MANAGER_ACTIVE), pool->lock); + pool->flags |= POOL_MANAGER_ACTIVE; + while ((worker = first_idle_worker(pool))) destroy_worker(worker); WARN_ON(pool->nr_workers || pool->nr_idle); @@ -3293,8 +3288,6 @@ static void put_unbound_pool(struct worker_pool *pool) if (pool->detach_completion) wait_for_completion(pool->detach_completion); - mutex_unlock(&pool->manager_arb); - /* shut down the timers */ del_timer_sync(&pool->idle_timer); del_timer_sync(&pool->mayday_timer); @@ -3730,8 +3723,12 @@ static int apply_workqueue_attrs_locked(struct workqueue_struct *wq, return -EINVAL; /* creating multiple pwqs breaks ordering guarantee */ - if (WARN_ON((wq->flags & __WQ_ORDERED) && !list_empty(&wq->pwqs))) - return -EINVAL; + if (!list_empty(&wq->pwqs)) { + if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT)) + return -EINVAL; + + wq->flags &= ~__WQ_ORDERED; + } ctx = apply_wqattrs_prepare(wq, attrs); if (!ctx) @@ -3915,6 +3912,16 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt, struct workqueue_struct *wq; struct pool_workqueue *pwq; + /* + * Unbound && max_active == 1 used to imply ordered, which is no + * longer the case on NUMA machines due to per-node pools. While + * alloc_ordered_workqueue() is the right way to create an ordered + * workqueue, keep the previous behavior to avoid subtle breakages + * on NUMA. + */ + if ((flags & WQ_UNBOUND) && max_active == 1) + flags |= __WQ_ORDERED; + /* see the comment above the definition of WQ_POWER_EFFICIENT */ if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient) flags |= WQ_UNBOUND; @@ -4103,13 +4110,14 @@ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active) struct pool_workqueue *pwq; /* disallow meddling with max_active for ordered workqueues */ - if (WARN_ON(wq->flags & __WQ_ORDERED)) + if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT)) return; max_active = wq_clamp_max_active(max_active, wq->flags, wq->name); mutex_lock(&wq->mutex); + wq->flags &= ~__WQ_ORDERED; wq->saved_max_active = max_active; for_each_pwq(pwq, wq) @@ -5214,7 +5222,7 @@ int workqueue_sysfs_register(struct workqueue_struct *wq) * attributes breaks ordering guarantee. Disallow exposing ordered * workqueues. */ - if (WARN_ON(wq->flags & __WQ_ORDERED)) + if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT)) return -EINVAL; wq->wq_dev = wq_dev = kzalloc(sizeof(*wq_dev), GFP_KERNEL); diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h index 8635417..29fa81f 100644 --- a/kernel/workqueue_internal.h +++ b/kernel/workqueue_internal.h @@ -9,6 +9,7 @@ #include <linux/workqueue.h> #include <linux/kthread.h> +#include <linux/preempt.h> struct worker_pool; @@ -59,7 +60,7 @@ struct worker { */ static inline struct worker *current_wq_worker(void) { - if (current->flags & PF_WQ_WORKER) + if (in_task() && (current->flags & PF_WQ_WORKER)) return kthread_data(current); return NULL; } |