diff options
Diffstat (limited to 'kernel')
45 files changed, 1616 insertions, 750 deletions
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index 1ed19b775912..f2e81be8265e 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -545,22 +545,38 @@ static void kill_rules(struct audit_context *context, struct audit_tree *tree) { struct audit_krule *rule, *next; struct audit_entry *entry; + bool need_sync = false; list_for_each_entry_safe(rule, next, &tree->rules, rlist) { entry = container_of(rule, struct audit_entry, rule); - list_del_init(&rule->rlist); if (rule->tree) { /* not a half-baked one */ audit_tree_log_remove_rule(context, rule); - if (entry->rule.exe) - audit_remove_mark(entry->rule.exe); rule->tree = NULL; list_del_rcu(&entry->list); list_del(&entry->rule.list); - call_rcu(&entry->rcu, audit_free_rule_rcu); + if (entry->rule.exe) + need_sync = true; + } else { + list_del_init(&rule->rlist); } } + + if (list_empty(&tree->rules)) + return; + + if (need_sync) + synchronize_rcu(); + + list_for_each_entry_safe(rule, next, &tree->rules, rlist) { + entry = container_of(rule, struct audit_entry, rule); + + list_del_init(&rule->rlist); + if (entry->rule.exe) + audit_remove_mark(entry->rule.exe); + call_rcu(&entry->rcu, audit_free_rule_rcu); + } } /* diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 9f33e95d5741..d870bc5e50bc 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -4268,13 +4268,10 @@ int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec) { int i; - /* There are three types that signify ownership of some other type: - * kptr_ref, bpf_list_head, bpf_rb_root. - * kptr_ref only supports storing kernel types, which can't store - * references to program allocated local types. - * - * Hence we only need to ensure that bpf_{list_head,rb_root} ownership - * does not form cycles. + /* + * Check fields which require the complete BTF and initialize runtime + * metadata. Ownership relationships are validated after every record has + * been fixed up. */ if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & (BPF_GRAPH_ROOT | BPF_UPTR))) return 0; @@ -4305,51 +4302,88 @@ int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec) if (!meta) return -EFAULT; rec->fields[i].graph_root.value_rec = meta->record; + } + return 0; +} - /* We need to set value_rec for all root types, but no need - * to check ownership cycle for a type unless it's also a - * node type. - */ - if (!(rec->field_mask & BPF_GRAPH_NODE)) +static int btf_owned_type_idx(const struct btf *btf, struct btf_struct_metas *tab, + const struct btf_field *field) +{ + struct btf_struct_meta *meta; + u32 btf_id; + + if (field->type & BPF_GRAPH_ROOT) { + btf_id = field->graph_root.value_btf_id; + } else if (field->type == BPF_KPTR_REF || field->type == BPF_KPTR_PERCPU) { + if (btf_is_kernel(field->kptr.btf)) + return -ENOENT; + btf_id = field->kptr.btf_id; + } else { + return -ENOENT; + } + + meta = btf_find_struct_meta(btf, btf_id); + if (!meta) + return field->type & BPF_GRAPH_ROOT ? -EFAULT : -ENOENT; + return meta - tab->types; +} + +/* + * Each ownership edge adds kernel frames through bpf_obj_free_fields() and + * __bpf_obj_drop_impl(). Keep the bound deliberately small because object + * destruction can itself run below a BPF call chain. A final pointee without + * special fields is not present in the struct metadata table and adds only a + * non-recursing drop. + */ +#define BTF_MAX_OWNERSHIP_DEPTH 8 + +static int btf_ownership_depth(const struct btf *btf, + struct btf_struct_metas *tab, u8 *depth, + int idx, int depth_left) +{ + const struct btf_record *rec = tab->types[idx].record; + int i, ret, max_depth = 0; + + if (!depth_left) + return -ELOOP; + if (depth[idx]) + goto done; + + for (i = 0; i < rec->cnt; i++) { + ret = btf_owned_type_idx(btf, tab, &rec->fields[i]); + if (ret == -ENOENT) continue; + if (ret < 0) + return ret; + ret = btf_ownership_depth(btf, tab, depth, ret, depth_left - 1); + if (ret < 0) + return ret; + max_depth = max(max_depth, ret); + } + depth[idx] = max_depth + 1; +done: + return depth[idx] > depth_left ? -ELOOP : depth[idx]; +} - /* We need to ensure ownership acyclicity among all types. The - * proper way to do it would be to topologically sort all BTF - * IDs based on the ownership edges, since there can be multiple - * bpf_{list_head,rb_node} in a type. Instead, we use the - * following resaoning: - * - * - A type can only be owned by another type in user BTF if it - * has a bpf_{list,rb}_node. Let's call these node types. - * - A type can only _own_ another type in user BTF if it has a - * bpf_{list_head,rb_root}. Let's call these root types. - * - * We ensure that if a type is both a root and node, its - * element types cannot be root types. - * - * To ensure acyclicity: - * - * When A is an root type but not a node, its ownership - * chain can be: - * A -> B -> C - * Where: - * - A is an root, e.g. has bpf_rb_root. - * - B is both a root and node, e.g. has bpf_rb_node and - * bpf_list_head. - * - C is only an root, e.g. has bpf_list_node - * - * When A is both a root and node, some other type already - * owns it in the BTF domain, hence it can not own - * another root type through any of the ownership edges. - * A -> B - * Where: - * - A is both an root and node. - * - B is only an node. - */ - if (meta->record->field_mask & BPF_GRAPH_ROOT) - return -ELOOP; +static int btf_check_ownership_depth(const struct btf *btf, + struct btf_struct_metas *tab) +{ + u8 *depth; + int i, ret = 0; + + depth = kvcalloc(tab->cnt, sizeof(*depth), GFP_KERNEL | __GFP_NOWARN); + if (!depth) + return -ENOMEM; + + for (i = 0; i < tab->cnt; i++) { + ret = btf_ownership_depth(btf, tab, depth, i, + BTF_MAX_OWNERSHIP_DEPTH); + if (ret < 0) + break; + ret = 0; } - return 0; + kvfree(depth); + return ret; } static void __btf_struct_show(const struct btf *btf, const struct btf_type *t, @@ -6044,6 +6078,10 @@ static struct btf *btf_parse(const union bpf_attr *attr, bpfptr_t uattr, if (err < 0) goto errout_meta; } + + err = btf_check_ownership_depth(btf, struct_meta_tab); + if (err < 0) + goto errout_meta; } err = bpf_log_attr_finalize(attr_log, &env->log); @@ -7187,7 +7225,7 @@ again: if (btf_type_is_int(t)) return WALK_SCALAR; - if (!btf_type_is_struct(t)) + if (!btf_type_is_struct(t) || !t->size) goto error; off = (off - moff) % t->size; diff --git a/kernel/bpf/check_btf.c b/kernel/bpf/check_btf.c index 0e8b3ccc7a5b..4c1ed842f661 100644 --- a/kernel/bpf/check_btf.c +++ b/kernel/bpf/check_btf.c @@ -338,9 +338,9 @@ err_free: #define MIN_CORE_RELO_SIZE sizeof(struct bpf_core_relo) #define MAX_CORE_RELO_SIZE MAX_FUNCINFO_REC_SIZE -static int check_core_relo(struct bpf_verifier_env *env, - const union bpf_attr *attr, - bpfptr_t uattr) +int bpf_check_core_relo(struct bpf_verifier_env *env, + const union bpf_attr *attr, + bpfptr_t uattr) { u32 i, nr_core_relo, ncopy, expected_size, rec_size; struct bpf_core_relo core_relo = {}; @@ -414,7 +414,7 @@ int bpf_prepare_btf_info(struct bpf_verifier_env *env, struct btf *btf; int err; - if (!attr->func_info_cnt && !attr->line_info_cnt) { + if (!attr->func_info_cnt && !attr->line_info_cnt && !attr->core_relo_cnt) { if (check_abnormal_return(env)) return -EINVAL; return 0; @@ -455,9 +455,5 @@ int bpf_check_btf_info(struct bpf_verifier_env *env, if (err) return err; - err = check_core_relo(env, attr, uattr); - if (err) - return err; - return 0; } diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 8b294dfc1ad4..7f11555a5070 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -19,6 +19,7 @@ #include <uapi/linux/btf.h> #include <linux/filter.h> +#include <linux/sched/signal.h> #include <linux/skbuff.h> #include <linux/static_call.h> #include <linux/vmalloc.h> @@ -1361,7 +1362,7 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from, { struct bpf_insn *to = to_buff; u32 imm_rnd = get_random_u32(); - s16 off; + int off; BUILD_BUG_ON(BPF_REG_PARAMS + 2 != MAX_BPF_JIT_REG); BUILD_BUG_ON(BPF_REG_AX + 1 != MAX_BPF_JIT_REG); @@ -1437,6 +1438,8 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from, off = from->off; if (off < 0) off -= 2; + if (off < S16_MIN) + return -ERANGE; *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_JMP_REG(from->code, from->dst_reg, BPF_REG_AX, off); @@ -1457,6 +1460,8 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from, off = from->off; if (off < 0) off -= 2; + if (off < S16_MIN) + return -ERANGE; *to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_JMP32_REG(from->code, from->dst_reg, BPF_REG_AX, @@ -1605,7 +1610,9 @@ struct bpf_prog *bpf_jit_blind_constants(struct bpf_verifier_env *env, struct bp if (!rewritten) continue; - if (env) + if (rewritten < 0) + tmp = ERR_PTR(rewritten); + else if (env) tmp = bpf_patch_insn_data(env, i, insn_buff, rewritten); else tmp = bpf_patch_insn_single(clone, i, insn_buff, rewritten); @@ -1619,6 +1626,8 @@ struct bpf_prog *bpf_jit_blind_constants(struct bpf_verifier_env *env, struct bp * fix it up here on error. */ bpf_jit_prog_release_other(prog, clone); + if (env && fatal_signal_pending(current)) + return ERR_PTR(-EINTR); return IS_ERR(tmp) ? tmp : ERR_PTR(-ENOMEM); } @@ -2636,11 +2645,14 @@ static struct bpf_prog *bpf_prog_jit_compile(struct bpf_verifier_env *env, struc orig_prog = prog; prog = bpf_jit_blind_constants(env, prog); /* - * If blinding was requested and we failed during blinding, we must fall - * back to the interpreter. + * Fall back to the interpreter after blinding failures, except when + * the loader was killed. */ - if (IS_ERR(prog)) + if (IS_ERR(prog)) { + if (PTR_ERR(prog) == -EINTR) + return prog; goto out_restore; + } prog = bpf_int_jit_compile(env, prog); if (prog->jited) { @@ -2659,6 +2671,8 @@ out_restore: struct bpf_prog *__bpf_prog_select_runtime(struct bpf_verifier_env *env, struct bpf_prog *fp, int *err) { + struct bpf_prog *jit_prog; + /* In case of BPF to BPF calls, verifier did all the prep * work with regards to JITing, etc. */ @@ -2681,7 +2695,12 @@ struct bpf_prog *__bpf_prog_select_runtime(struct bpf_verifier_env *env, struct if (*err) return fp; - fp = bpf_prog_jit_compile(env, fp); + jit_prog = bpf_prog_jit_compile(env, fp); + if (IS_ERR(jit_prog)) { + *err = PTR_ERR(jit_prog); + return fp; + } + fp = jit_prog; bpf_prog_jit_attempt_done(fp); if (!fp->jited && jit_needed) { *err = -ENOTSUPP; diff --git a/kernel/bpf/crypto.c b/kernel/bpf/crypto.c index 51f89cecefb4..3f3fe2450fc6 100644 --- a/kernel/bpf/crypto.c +++ b/kernel/bpf/crypto.c @@ -149,8 +149,9 @@ bpf_crypto_ctx_create(const struct bpf_crypto_params *params, u32 params__sz, const struct bpf_crypto_type *type; struct bpf_crypto_ctx *ctx; - if (!params || params->reserved[0] || params->reserved[1] || - params__sz != sizeof(struct bpf_crypto_params)) { + if (!params || + params__sz != sizeof(struct bpf_crypto_params) || + params->reserved[0] || params->reserved[1]) { *err = -EINVAL; return NULL; } diff --git a/kernel/bpf/fixups.c b/kernel/bpf/fixups.c index 52d3cec33672..d6f83521fc78 100644 --- a/kernel/bpf/fixups.c +++ b/kernel/bpf/fixups.c @@ -8,6 +8,7 @@ #include <linux/bsearch.h> #include <linux/sort.h> #include <linux/perf_event.h> +#include <linux/sched/signal.h> #include <net/xdp.h> #include "disasm.h" @@ -306,12 +307,28 @@ static void adjust_poke_descs(struct bpf_prog *prog, u32 off, u32 len) } } +/* + * Some post-verification instruction rewriting passes require an + * O(prog->len) operation per instruction. Keep their shared primitives + * killable and preemptible. + */ +static bool bpf_rewrite_must_abort(void) +{ + if (fatal_signal_pending(current)) + return true; + cond_resched(); + return false; +} + struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off, const struct bpf_insn *patch, u32 len) { struct bpf_prog *new_prog; struct bpf_insn_aux_data *new_data = NULL; + if (bpf_rewrite_must_abort()) + return NULL; + if (len > 1) { new_data = vrealloc(env->insn_aux_data, array_size(env->prog->len + len - 1, @@ -523,6 +540,9 @@ static int verifier_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt) unsigned int orig_prog_len = env->prog->len; int err; + if (bpf_rewrite_must_abort()) + return -EINTR; + if (bpf_prog_is_offloaded(env->prog->aux)) bpf_prog_offload_remove_insns(env, off, cnt); @@ -1356,7 +1376,7 @@ int bpf_jit_subprogs(struct bpf_verifier_env *env) } prog = bpf_jit_blind_constants(env, prog); if (IS_ERR(prog)) { - err = -ENOMEM; + err = PTR_ERR(prog); prog = orig_prog; goto out_restore; } @@ -1433,7 +1453,7 @@ int bpf_fixup_call_args(struct bpf_verifier_env *env) err = bpf_jit_subprogs(env); if (err == 0) return 0; - if (err == -EFAULT) + if (err == -EFAULT || err == -EINTR) return err; } #ifndef CONFIG_BPF_JIT_ALWAYS_ON diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 6f331c80130d..13a2356c84cf 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -128,6 +128,7 @@ struct htab_elem { struct htab_btf_record { struct btf_record *record; + struct btf *btf; u32 key_size; }; @@ -497,8 +498,13 @@ static void htab_dtor_ctx_free(void *ctx) { struct htab_btf_record *hrec = ctx; + /* + * The duplicated record still points into the map BTF, so free it + * before dropping the reference that keeps that BTF alive. + */ btf_record_free(hrec->record); - kfree(ctx); + btf_put(hrec->btf); + kfree(hrec); } static int bpf_ma_set_dtor(struct bpf_map *map, struct bpf_mem_alloc *ma, @@ -521,6 +527,15 @@ static int bpf_ma_set_dtor(struct bpf_map *map, struct bpf_mem_alloc *ma, kfree(hrec); return err; } + /* + * btf_record_dup() only acquires kernel and module BTF. Fields whose + * types live in the map BTF keep pointing into it: kptrs to local + * types refer to map->btf, and graph roots carry a value record owned + * by its struct meta table. The context can outlive the map when the + * allocator defers its teardown, so hold a reference of our own. + */ + hrec->btf = map->btf; + btf_get(hrec->btf); bpf_mem_alloc_set_dtor(ma, dtor, htab_dtor_ctx_free, hrec); return 0; } @@ -1054,14 +1069,17 @@ static void pcpu_init_value(struct bpf_htab *htab, void __percpu *pptr, /* When not setting the initial value on all cpus, zero-fill element * values for other cpus. Otherwise, bpf program has no way to ensure * known initial values for cpus other than current one - * (onallcpus=false always when coming from bpf prog). + * (onallcpus=false always when coming from bpf prog, + * map_flags & BPF_F_CPU when coming from syscall but setting + * only one cpu). */ - if (!onallcpus) { - int current_cpu = raw_smp_processor_id(); + if (!onallcpus || (map_flags & BPF_F_CPU)) { + int init_cpu = (map_flags & BPF_F_CPU) ? map_flags >> 32 : + raw_smp_processor_id(); int cpu; for_each_possible_cpu(cpu) { - if (cpu == current_cpu) + if (cpu == init_cpu) copy_map_value(&htab->map, per_cpu_ptr(pptr, cpu), value); else /* Since elem is preallocated, we cannot touch special fields */ zero_map_value(&htab->map, per_cpu_ptr(pptr, cpu)); @@ -1772,6 +1790,12 @@ static int htab_lru_percpu_map_lookup_and_delete_elem(struct bpf_map *map, flags); } +/* + * Max consecutive empty buckets to walk in one RCU + + * instrumentation-disabled section before rescheduling. + */ +#define HTAB_BATCH_EMPTY_RESCHED 64 + static int __htab_map_lookup_and_delete_batch(struct bpf_map *map, const union bpf_attr *attr, @@ -1793,6 +1817,7 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map, unsigned long flags = 0; bool locked = false; struct htab_elem *l; + u32 empty_cnt = 0; struct bucket *b; int ret = 0; @@ -1971,30 +1996,41 @@ again_nocopy: } next_batch: - /* If we are not copying data, we can go to next bucket and avoid - * unlocking the rcu. + /* + * If we are not copying data, we can go to next bucket and avoid + * unlocking the rcu. Bound the walk though: after + * HTAB_BATCH_EMPTY_RESCHED consecutive empty buckets, fully exit + * the critical section (no locks are held here) and reschedule. */ if (!bucket_cnt && (batch + 1 < htab->n_buckets)) { batch++; - goto again_nocopy; + if (++empty_cnt < HTAB_BATCH_EMPTY_RESCHED) + goto again_nocopy; + empty_cnt = 0; + rcu_read_unlock(); + bpf_enable_instrumentation(); + cond_resched_tasks_rcu_qs(); + goto again; } rcu_read_unlock(); bpf_enable_instrumentation(); - if (bucket_cnt && (copy_to_user(ukeys + total * key_size, keys, - key_size * bucket_cnt) || - copy_to_user(uvalues + total * value_size, values, - value_size * bucket_cnt))) { + if (bucket_cnt && (copy_to_user(ukeys + (size_t)total * key_size, keys, + (size_t)key_size * bucket_cnt) || + copy_to_user(uvalues + (size_t)total * value_size, values, + (size_t)value_size * bucket_cnt))) { ret = -EFAULT; goto after_loop; } total += bucket_cnt; + empty_cnt = 0; batch++; if (batch >= htab->n_buckets) { ret = -ENOENT; goto after_loop; } + cond_resched_tasks_rcu_qs(); goto again; after_loop: @@ -3338,8 +3374,10 @@ static int __rhtab_map_lookup_and_delete_batch(struct bpf_map *map, } if (do_delete) { + migrate_disable(); for (i = 0; i < total; i++) rhtab_delete_elem(rhtab, del_elems[i], NULL, 0); + migrate_enable(); } rcu_read_unlock(); diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index b3cc5c8fc875..712dca5a2c5b 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -4883,7 +4883,7 @@ BTF_ID(func, bpf_cgroup_release_dtor) BTF_KFUNCS_START(common_btf_ids) BTF_ID_FLAGS(func, bpf_cast_to_kern_ctx, KF_FASTCALL) -BTF_ID_FLAGS(func, bpf_rdonly_cast, KF_FASTCALL) +BTF_ID_FLAGS(func, bpf_rdonly_cast, KF_FASTCALL | KF_PERFMON) BTF_ID_FLAGS(func, bpf_rcu_read_lock) BTF_ID_FLAGS(func, bpf_rcu_read_unlock) BTF_ID_FLAGS(func, bpf_dynptr_slice, KF_RET_NULL) @@ -4920,26 +4920,26 @@ BTF_ID_FLAGS(func, bpf_wq_set_callback, KF_IMPLICIT_ARGS) BTF_ID_FLAGS(func, bpf_wq_start) BTF_ID_FLAGS(func, bpf_preempt_disable) BTF_ID_FLAGS(func, bpf_preempt_enable) -BTF_ID_FLAGS(func, bpf_iter_bits_new, KF_ITER_NEW) +BTF_ID_FLAGS(func, bpf_iter_bits_new, KF_ITER_NEW | KF_PERFMON) BTF_ID_FLAGS(func, bpf_iter_bits_next, KF_ITER_NEXT | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_iter_bits_destroy, KF_ITER_DESTROY) -BTF_ID_FLAGS(func, bpf_copy_from_user_str, KF_SLEEPABLE) -BTF_ID_FLAGS(func, bpf_copy_from_user_task_str, KF_SLEEPABLE) -BTF_ID_FLAGS(func, bpf_get_kmem_cache) +BTF_ID_FLAGS(func, bpf_copy_from_user_str, KF_SLEEPABLE | KF_PERFMON) +BTF_ID_FLAGS(func, bpf_copy_from_user_task_str, KF_SLEEPABLE | KF_PERFMON) +BTF_ID_FLAGS(func, bpf_get_kmem_cache, KF_PERFMON) BTF_ID_FLAGS(func, bpf_iter_kmem_cache_new, KF_ITER_NEW | KF_SLEEPABLE) BTF_ID_FLAGS(func, bpf_iter_kmem_cache_next, KF_ITER_NEXT | KF_RET_NULL | KF_SLEEPABLE) BTF_ID_FLAGS(func, bpf_iter_kmem_cache_destroy, KF_ITER_DESTROY | KF_SLEEPABLE) BTF_ID_FLAGS(func, bpf_local_irq_save) BTF_ID_FLAGS(func, bpf_local_irq_restore) #ifdef CONFIG_BPF_EVENTS -BTF_ID_FLAGS(func, bpf_probe_read_user_dynptr) -BTF_ID_FLAGS(func, bpf_probe_read_kernel_dynptr) -BTF_ID_FLAGS(func, bpf_probe_read_user_str_dynptr) -BTF_ID_FLAGS(func, bpf_probe_read_kernel_str_dynptr) -BTF_ID_FLAGS(func, bpf_copy_from_user_dynptr, KF_SLEEPABLE) -BTF_ID_FLAGS(func, bpf_copy_from_user_str_dynptr, KF_SLEEPABLE) -BTF_ID_FLAGS(func, bpf_copy_from_user_task_dynptr, KF_SLEEPABLE) -BTF_ID_FLAGS(func, bpf_copy_from_user_task_str_dynptr, KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_probe_read_user_dynptr, KF_PERFMON) +BTF_ID_FLAGS(func, bpf_probe_read_kernel_dynptr, KF_PERFMON) +BTF_ID_FLAGS(func, bpf_probe_read_user_str_dynptr, KF_PERFMON) +BTF_ID_FLAGS(func, bpf_probe_read_kernel_str_dynptr, KF_PERFMON) +BTF_ID_FLAGS(func, bpf_copy_from_user_dynptr, KF_SLEEPABLE | KF_PERFMON) +BTF_ID_FLAGS(func, bpf_copy_from_user_str_dynptr, KF_SLEEPABLE | KF_PERFMON) +BTF_ID_FLAGS(func, bpf_copy_from_user_task_dynptr, KF_SLEEPABLE | KF_PERFMON) +BTF_ID_FLAGS(func, bpf_copy_from_user_task_str_dynptr, KF_SLEEPABLE | KF_PERFMON) #endif #ifdef CONFIG_DMA_SHARED_BUFFER BTF_ID_FLAGS(func, bpf_iter_dmabuf_new, KF_ITER_NEW | KF_SLEEPABLE) @@ -4947,26 +4947,26 @@ BTF_ID_FLAGS(func, bpf_iter_dmabuf_next, KF_ITER_NEXT | KF_RET_NULL | KF_SLEEPAB BTF_ID_FLAGS(func, bpf_iter_dmabuf_destroy, KF_ITER_DESTROY | KF_SLEEPABLE) #endif BTF_ID_FLAGS(func, __bpf_trap) -BTF_ID_FLAGS(func, bpf_strcmp); -BTF_ID_FLAGS(func, bpf_strcasecmp); -BTF_ID_FLAGS(func, bpf_strncasecmp); -BTF_ID_FLAGS(func, bpf_strchr); -BTF_ID_FLAGS(func, bpf_strchrnul); -BTF_ID_FLAGS(func, bpf_strnchr); -BTF_ID_FLAGS(func, bpf_strrchr); -BTF_ID_FLAGS(func, bpf_strlen); -BTF_ID_FLAGS(func, bpf_strnlen); -BTF_ID_FLAGS(func, bpf_strspn); -BTF_ID_FLAGS(func, bpf_strcspn); -BTF_ID_FLAGS(func, bpf_strstr); -BTF_ID_FLAGS(func, bpf_strcasestr); -BTF_ID_FLAGS(func, bpf_strnstr); -BTF_ID_FLAGS(func, bpf_strncasestr); +BTF_ID_FLAGS(func, bpf_strcmp, KF_PERFMON); +BTF_ID_FLAGS(func, bpf_strcasecmp, KF_PERFMON); +BTF_ID_FLAGS(func, bpf_strncasecmp, KF_PERFMON); +BTF_ID_FLAGS(func, bpf_strchr, KF_PERFMON); +BTF_ID_FLAGS(func, bpf_strchrnul, KF_PERFMON); +BTF_ID_FLAGS(func, bpf_strnchr, KF_PERFMON); +BTF_ID_FLAGS(func, bpf_strrchr, KF_PERFMON); +BTF_ID_FLAGS(func, bpf_strlen, KF_PERFMON); +BTF_ID_FLAGS(func, bpf_strnlen, KF_PERFMON); +BTF_ID_FLAGS(func, bpf_strspn, KF_PERFMON); +BTF_ID_FLAGS(func, bpf_strcspn, KF_PERFMON); +BTF_ID_FLAGS(func, bpf_strstr, KF_PERFMON); +BTF_ID_FLAGS(func, bpf_strcasestr, KF_PERFMON); +BTF_ID_FLAGS(func, bpf_strnstr, KF_PERFMON); +BTF_ID_FLAGS(func, bpf_strncasestr, KF_PERFMON); #if defined(CONFIG_BPF_LSM) && defined(CONFIG_CGROUPS) BTF_ID_FLAGS(func, bpf_cgroup_read_xattr, KF_RCU) #endif -BTF_ID_FLAGS(func, bpf_stream_vprintk, KF_IMPLICIT_ARGS | KF_SPINLOCK_SAFE) -BTF_ID_FLAGS(func, bpf_stream_print_stack, KF_IMPLICIT_ARGS | KF_SPINLOCK_SAFE) +BTF_ID_FLAGS(func, bpf_stream_vprintk, KF_IMPLICIT_ARGS | KF_SPINLOCK_SAFE | KF_PERFMON) +BTF_ID_FLAGS(func, bpf_stream_print_stack, KF_IMPLICIT_ARGS | KF_SPINLOCK_SAFE | KF_PERFMON) BTF_ID_FLAGS(func, bpf_task_work_schedule_signal, KF_IMPLICIT_ARGS) BTF_ID_FLAGS(func, bpf_task_work_schedule_resume, KF_IMPLICIT_ARGS) BTF_ID_FLAGS(func, bpf_dynptr_from_file) diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c index e9662db7198f..15684d0fc883 100644 --- a/kernel/bpf/memalloc.c +++ b/kernel/bpf/memalloc.c @@ -118,7 +118,13 @@ struct bpf_mem_cache { struct llist_head free_by_rcu_ttrace; struct llist_head waiting_for_gp_ttrace; struct rcu_head rcu_ttrace; + /* + * 0 - idle + * 1 - __free_rcu() is queued + * 2 - __free_rcu() is queued and free_by_rcu_ttrace got more objects since + */ atomic_t call_rcu_ttrace_in_progress; + raw_spinlock_t lock; }; struct bpf_mem_caches { @@ -214,25 +220,24 @@ static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node, bool atomic) gfp = __GFP_NOWARN | __GFP_ACCOUNT; gfp |= atomic ? GFP_NOWAIT : GFP_KERNEL; - for (i = 0; i < cnt; i++) { - /* - * For every 'c' llist_del_first(&c->free_by_rcu_ttrace); is - * done only by one CPU == current CPU. Other CPUs might - * llist_add() and llist_del_all() in parallel. - */ - obj = llist_del_first(&c->free_by_rcu_ttrace); - if (!obj) - break; - add_obj_to_free_list(c, obj); - } - if (i >= cnt) - return; + /* + * c->lock serializes concurrent llist_del_first() against + * llist_del_all() in __free_rcu() and do_call_rcu_ttrace(). + */ + scoped_guard(raw_spinlock_irqsave, &c->lock) { + for (i = 0; i < cnt; i++) { + obj = llist_del_first(&c->free_by_rcu_ttrace); + if (!obj) + break; + add_obj_to_free_list(c, obj); + } - for (; i < cnt; i++) { - obj = llist_del_first(&c->waiting_for_gp_ttrace); - if (!obj) - break; - add_obj_to_free_list(c, obj); + for (; i < cnt; i++) { + obj = llist_del_first(&c->waiting_for_gp_ttrace); + if (!obj) + break; + add_obj_to_free_list(c, obj); + } } if (i >= cnt) return; @@ -276,12 +281,30 @@ static int free_all(struct bpf_mem_cache *c, struct llist_node *llnode, bool per return cnt; } +static void __do_call_rcu_ttrace(struct bpf_mem_cache *c); + static void __free_rcu(struct rcu_head *head) { struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu_ttrace); + struct llist_node *llnode; + + scoped_guard(raw_spinlock_irqsave, &c->lock) + llnode = llist_del_all(&c->waiting_for_gp_ttrace); + + free_all(c, llnode, !!c->percpu_size); - free_all(c, llist_del_all(&c->waiting_for_gp_ttrace), !!c->percpu_size); - atomic_set(&c->call_rcu_ttrace_in_progress, 0); + /* + * do_call_rcu_ttrace() that ran while GP was in flight left its objects + * in free_by_rcu_ttrace. This cache may never free or alloc in bulk + * again, so start the next GP from here. + * 'c' can be freed as soon as call_rcu_ttrace_in_progress is zero. + */ + if (atomic_cmpxchg(&c->call_rcu_ttrace_in_progress, 1, 0) == 1) + return; + + /* Pairs with synchronize_rcu() in free_mem_alloc() */ + guard(rcu)(); + __do_call_rcu_ttrace(c); } static void enque_to_free(struct bpf_mem_cache *c, void *obj) @@ -294,17 +317,15 @@ static void enque_to_free(struct bpf_mem_cache *c, void *obj) llist_add(llnode, &c->free_by_rcu_ttrace); } -static void do_call_rcu_ttrace(struct bpf_mem_cache *c) +static void __do_call_rcu_ttrace(struct bpf_mem_cache *c) { struct llist_node *llnode, *t; - if (atomic_xchg(&c->call_rcu_ttrace_in_progress, 1)) { - if (unlikely(READ_ONCE(c->draining))) { - llnode = llist_del_all(&c->free_by_rcu_ttrace); - free_all(c, llnode, !!c->percpu_size); - } - return; - } + /* + * Must be done before llist_del_all(). Objects that it misses were + * added by do_call_rcu_ttrace() that will set 2 after this store. + */ + atomic_set(&c->call_rcu_ttrace_in_progress, 1); WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp_ttrace)); llist_for_each_safe(llnode, t, llist_del_all(&c->free_by_rcu_ttrace)) @@ -323,6 +344,22 @@ static void do_call_rcu_ttrace(struct bpf_mem_cache *c) call_rcu_tasks_trace(&c->rcu_ttrace, __free_rcu); } +static void do_call_rcu_ttrace(struct bpf_mem_cache *c) +{ + struct llist_node *llnode; + + if (atomic_xchg(&c->call_rcu_ttrace_in_progress, 2)) { + if (unlikely(READ_ONCE(c->draining))) { + scoped_guard(raw_spinlock_irqsave, &c->lock) + llnode = llist_del_all(&c->free_by_rcu_ttrace); + free_all(c, llnode, !!c->percpu_size); + } + return; + } + + __do_call_rcu_ttrace(c); +} + static void free_bulk(struct bpf_mem_cache *c) { struct bpf_mem_cache *tgt = c->tgt; @@ -535,6 +572,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu) c->objcg = objcg; c->percpu_size = percpu_size; c->tgt = c; + raw_spin_lock_init(&c->lock); init_refill_work(c); prefill_mem_cache(c, cpu); } @@ -557,7 +595,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu) c->objcg = objcg; c->percpu_size = percpu_size; c->tgt = c; - + raw_spin_lock_init(&c->lock); init_refill_work(c); prefill_mem_cache(c, cpu); } @@ -609,7 +647,7 @@ int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size) c->objcg = objcg; c->percpu_size = percpu_size; c->tgt = c; - + raw_spin_lock_init(&c->lock); init_refill_work(c); prefill_mem_cache(c, cpu); } @@ -694,7 +732,12 @@ static void free_mem_alloc(struct bpf_mem_alloc *ma) * to wait for the pending __free_by_rcu(), and __free_rcu(). RCU Tasks * Trace grace period implies RCU grace period, so all __free_rcu don't * need extra call_rcu() (and thus extra rcu_barrier() here). + * + * __free_rcu() queues itself again unless it sees 'draining'. After + * synchronize_rcu() it either did that already or will not do it, so + * rcu_barrier_tasks_trace() cannot miss it. */ + synchronize_rcu(); rcu_barrier(); /* wait for __free_by_rcu */ rcu_barrier_tasks_trace(); /* wait for __free_rcu */ free_mem_alloc_no_barrier(ma); diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index 0d6f5569588c..d855399812ee 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -698,6 +698,8 @@ static bool __bpf_offload_dev_match(struct bpf_prog *prog, return false; if (offload->netdev == netdev) return true; + if (!bpf_prog_is_offloaded(prog->aux)) + return false; ondev1 = bpf_offload_find_netdev(offload->netdev); ondev2 = bpf_offload_find_netdev(netdev); diff --git a/kernel/bpf/states.c b/kernel/bpf/states.c index 66fb11b6c6a7..012b82513a3b 100644 --- a/kernel/bpf/states.c +++ b/kernel/bpf/states.c @@ -491,7 +491,8 @@ static bool regs_exact(const struct bpf_reg_state *rold, { return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 && check_ids(rold->id, rcur->id, idmap) && - check_ids(rold->parent_id, rcur->parent_id, idmap); + check_ids(rold->parent_id, rcur->parent_id, idmap) && + check_ids(rold->map_uid, rcur->map_uid, idmap); } enum exact_level { @@ -616,7 +617,8 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, range_within(rold, rcur) && tnum_in(rold->var_off, rcur->var_off) && check_ids(rold->id, rcur->id, idmap) && - check_ids(rold->parent_id, rcur->parent_id, idmap); + check_ids(rold->parent_id, rcur->parent_id, idmap) && + check_ids(rold->map_uid, rcur->map_uid, idmap); case PTR_TO_PACKET_META: case PTR_TO_PACKET: /* We must have at least as much range as the old ptr @@ -635,14 +637,14 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, /* id relations must be preserved */ if (!check_ids(rold->id, rcur->id, idmap)) return false; + /* Preserve displacements between pointers sharing an ID. */ + if (rold->id && rold->r64.base != rcur->r64.base) + return false; /* new val must satisfy old val knowledge */ return range_within(rold, rcur) && tnum_in(rold->var_off, rcur->var_off); case PTR_TO_STACK: - /* two stack pointers are equal only if they're pointing to - * the same stack frame, since fp-8 in foo != fp-8 in bar - */ - return regs_exact(rold, rcur, idmap) && rold->frameno == rcur->frameno; + return regs_exact(rold, rcur, idmap); case PTR_TO_ARENA: return true; case PTR_TO_INSN: @@ -1121,7 +1123,7 @@ static bool states_maybe_looping(struct bpf_verifier_state *old, fcur = cur->frame[fr]; for (i = 0; i < MAX_BPF_REG; i++) if (memcmp(&fold->regs[i], &fcur->regs[i], - offsetof(struct bpf_reg_state, frameno))) + offsetof(struct bpf_reg_state, precise))) return false; return true; } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index c7bc9ba9b331..96217b99399d 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2036,7 +2036,7 @@ int generic_map_delete_batch(struct bpf_map *map, for (cp = 0; cp < max_count; cp++) { err = -EFAULT; - if (copy_from_user(key, keys + cp * map->key_size, + if (copy_from_user(key, keys + (size_t)cp * map->key_size, map->key_size)) break; @@ -2098,9 +2098,9 @@ int generic_map_update_batch(struct bpf_map *map, struct file *map_file, for (cp = 0; cp < max_count; cp++) { err = -EFAULT; - if (copy_from_user(key, keys + cp * map->key_size, + if (copy_from_user(key, keys + (size_t)cp * map->key_size, map->key_size) || - copy_from_user(value, values + cp * value_size, value_size)) + copy_from_user(value, values + (size_t)cp * value_size, value_size)) break; err = bpf_map_update_value(map, map_file, key, value, @@ -2179,12 +2179,12 @@ int generic_map_lookup_batch(struct bpf_map *map, if (err) goto free_buf; - if (copy_to_user(keys + cp * map->key_size, key, + if (copy_to_user(keys + (size_t)cp * map->key_size, key, map->key_size)) { err = -EFAULT; goto free_buf; } - if (copy_to_user(values + cp * value_size, value, value_size)) { + if (copy_to_user(values + (size_t)cp * value_size, value, value_size)) { err = -EFAULT; goto free_buf; } @@ -2448,6 +2448,21 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu) bpf_prog_free(aux->prog); } +/* + * Progs called from a trampoline can also be reached by a task that was + * preempted in the trampoline before the prog's enter helper took its RCU + * read lock, wait for those first. + */ +static void __bpf_prog_put_rcu_tasks(struct rcu_head *rcu) +{ + struct bpf_prog *prog = container_of(rcu, struct bpf_prog_aux, rcu)->prog; + + if (prog->sleepable) + call_rcu_tasks_trace(rcu, __bpf_prog_put_rcu); + else + call_rcu(rcu, __bpf_prog_put_rcu); +} + static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred) { bpf_prog_kallsyms_del_all(prog); @@ -2461,7 +2476,9 @@ static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred) btf_put(prog->aux->attach_btf); if (deferred) { - if (prog->sleepable) + if (IS_ENABLED(CONFIG_TASKS_RCU) && prog->aux->tramp_linked) + call_rcu_tasks(&prog->aux->rcu, __bpf_prog_put_rcu_tasks); + else if (prog->sleepable) call_rcu_tasks_trace(&prog->aux->rcu, __bpf_prog_put_rcu); else call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); @@ -6042,7 +6059,10 @@ struct bpf_link *bpf_link_get_curr_or_next(u32 *id) again: link = idr_get_next(&link_idr, id); if (link) { - link = bpf_link_inc_not_zero(link); + if (link->id) + link = bpf_link_inc_not_zero(link); + else + link = ERR_PTR(-EAGAIN); if (IS_ERR(link)) { (*id)++; goto again; diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 90b70ea0d370..bf4cb3dd444d 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -401,6 +401,7 @@ static struct bpf_trampoline *bpf_trampoline_lookup(u64 key, unsigned long ip) head = &trampoline_ip_table[hash_64(tr->ip, TRAMPOLINE_HASH_BITS)]; hlist_add_head(&tr->hlist_ip, head); refcount_set(&tr->refcnt, 1); + INIT_LIST_HEAD(&tr->images); for (i = 0; i < BPF_TRAMP_MAX; i++) INIT_HLIST_HEAD(&tr->progs_hlist[i]); out: @@ -565,15 +566,22 @@ static void bpf_tramp_image_free(struct bpf_tramp_image *im) arch_free_bpf_trampoline(im->image, im->size); bpf_jit_uncharge_modmem(im->size); percpu_ref_exit(&im->pcref); + kfree(im->skips); kfree_rcu(im, rcu); } static void __bpf_tramp_image_put_deferred(struct work_struct *work) { struct bpf_tramp_image *im; + struct bpf_trampoline *tr; im = container_of(work, struct bpf_tramp_image, work); + tr = im->tr; + trampoline_lock(tr); + list_del(&im->list); + trampoline_unlock(tr); bpf_tramp_image_free(im); + bpf_trampoline_put(tr); } /* callback, fexit step 3 or fentry step 2 */ @@ -601,7 +609,7 @@ static void __bpf_tramp_image_put_rcu_tasks(struct rcu_head *rcu) struct bpf_tramp_image *im; im = container_of(rcu, struct bpf_tramp_image, rcu); - if (im->ip_after_call) + if (im->call_orig) /* the case of fmod_ret/fexit trampoline and CONFIG_PREEMPTION=y */ percpu_ref_kill(&im->pcref); else @@ -621,9 +629,9 @@ static void bpf_tramp_image_put(struct bpf_tramp_image *im) * * The trampoline is unreachable before bpf_tramp_image_put(). * - * First, patch the trampoline to avoid calling into fexit progs. - * The progs will be freed even if the original function is still - * executing or sleeping. + * Progs are patched out of the image when they are detached, see + * bpf_trampoline_skip_prog(), so they can be freed even if a task is + * still in the image. * In case of CONFIG_PREEMPT=y use call_rcu_tasks() to wait on * first few asm instructions to execute and call into * __bpf_tramp_enter->percpu_ref_get. @@ -637,11 +645,7 @@ static void bpf_tramp_image_put(struct bpf_tramp_image *im) * percpu_ref_kill will be waiting for. Hence the first * call_rcu_tasks() is not necessary. */ - if (im->ip_after_call) { - int err = bpf_arch_text_poke(im->ip_after_call, BPF_MOD_NOP, - BPF_MOD_JUMP, NULL, - im->ip_epilogue); - WARN_ON(err); + if (im->call_orig) { if (IS_ENABLED(CONFIG_TASKS_RCU)) call_rcu_tasks(&im->rcu, __bpf_tramp_image_put_rcu_tasks); else @@ -658,7 +662,7 @@ static void bpf_tramp_image_put(struct bpf_tramp_image *im) call_rcu_tasks_trace(&im->rcu, __bpf_tramp_image_put_rcu_tasks); } -static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key, int size) +static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key, int size, int nr_progs) { struct bpf_tramp_image *im; struct bpf_ksym *ksym; @@ -669,6 +673,10 @@ static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key, int size) if (!im) goto out; + im->skips = kzalloc_objs(*im->skips, nr_progs); + if (!im->skips) + goto out_free_im; + err = bpf_jit_charge_modmem(size); if (err) goto out_free_im; @@ -695,6 +703,7 @@ out_free_image: out_uncharge: bpf_jit_uncharge_modmem(size); out_free_im: + kfree(im->skips); kfree(im); out: return ERR_PTR(err); @@ -771,11 +780,12 @@ again: goto out; } - im = bpf_tramp_image_alloc(tr->key, size); + im = bpf_tramp_image_alloc(tr->key, size, total); if (IS_ERR(im)) { err = PTR_ERR(im); goto out; } + im->call_orig = tr->flags & BPF_TRAMP_F_CALL_ORIG; err = arch_prepare_bpf_trampoline(im, im->image, im->image + size, &tr->func.model, tr->flags, tnodes, @@ -806,8 +816,14 @@ again: #endif out_free: - if (err) + if (err) { bpf_tramp_image_free(im); + } else { + /* track the image until it is freed, for bpf_trampoline_skip_prog() */ + refcount_inc(&tr->refcnt); + im->tr = tr; + list_add(&im->list, &tr->images); + } out: /* If any error happens, restore previous flags */ if (err) @@ -907,6 +923,7 @@ static int bpf_trampoline_add_prog(struct bpf_trampoline *tr, } hlist_add_head(&node->tramp_hlist, prog_list); + node->link->prog->aux->tramp_linked = true; if (kind == BPF_TRAMP_FSESSION) { tr->progs_cnt[BPF_TRAMP_FENTRY]++; fexit = fsession_exit(node); @@ -920,6 +937,41 @@ static int bpf_trampoline_add_prog(struct bpf_trampoline *tr, return 0; } +/* + * Patch the nop in front of a prog call to a jump over it. A task can be + * preempted anywhere in the image, so archs that need several instructions for + * a jump of any range patch a single near branch here instead. + */ +int __weak arch_bpf_trampoline_skip(void *nop, void *target) +{ + return bpf_arch_text_poke(nop, BPF_MOD_NOP, BPF_MOD_JUMP, NULL, target); +} + +/* + * prog was detached and can be freed, but tasks may still be running in images + * that call it, sleeping in an earlier prog for example. They can be in any + * image that is not freed yet, not only in cur_image, so patch all of them to + * jump over prog. + */ +static void bpf_trampoline_skip_prog(struct bpf_trampoline *tr, struct bpf_prog *prog) +{ + struct bpf_tramp_image *im; + int i, err; + + list_for_each_entry(im, &tr->images, list) { + for (i = 0; i < im->nr_skips; i++) { + struct bpf_tramp_skip *skip = &im->skips[i]; + + if (skip->prog != prog) + continue; + err = arch_bpf_trampoline_skip(skip->nop, skip->target); + WARN_ON_ONCE(err); + /* not a nop anymore, and prog's address can be reused */ + skip->prog = NULL; + } + } +} + static void bpf_trampoline_remove_prog(struct bpf_trampoline *tr, struct bpf_tramp_node *node) { @@ -937,6 +989,7 @@ static void bpf_trampoline_remove_prog(struct bpf_trampoline *tr, } hlist_del_init(&node->tramp_hlist); tr->progs_cnt[kind]--; + bpf_trampoline_skip_prog(tr, node->link->prog); } static int __bpf_trampoline_link_prog(struct bpf_tramp_node *node, @@ -1245,11 +1298,9 @@ void bpf_trampoline_put(struct bpf_trampoline *tr) if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[i]))) goto out; - /* This code will be executed even when the last bpf_tramp_image - * is alive. All progs are detached from the trampoline and the - * trampoline image is patched with jmp into epilogue to skip - * fexit progs. The fentry-only trampoline will be freed via - * multiple rcu callbacks. + /* + * All progs are detached and the last image has been freed, images + * hold a reference on the trampoline until then. */ hlist_del(&tr->hlist_key); hlist_del(&tr->hlist_ip); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 72a3f5998dd2..5f874979b8d7 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -567,7 +567,7 @@ static int stack_slot_obj_get_spi(struct bpf_verifier_env *env, struct bpf_reg_s } off = reg->var_off.value; - if (off % BPF_REG_SIZE) { + if (off >= 0 || off % BPF_REG_SIZE) { verbose(env, "cannot pass in %s at an offset=%d\n", obj_kind, off); return -EINVAL; } @@ -1864,6 +1864,7 @@ static void __mark_reg_known(struct bpf_reg_state *reg, u64 imm) offsetof(struct bpf_reg_state, var_off) - sizeof(reg->type)); reg->id = 0; reg->parent_id = 0; + reg->map_uid = 0; ___mark_reg_known(reg, imm); } @@ -1925,17 +1926,18 @@ static void refine_map_lookup_value(struct bpf_reg_state *reg) if (map->inner_map_meta) { reg->type = CONST_PTR_TO_MAP | maybe_null; reg->map_ptr = map->inner_map_meta; - /* transfer reg's id which is unique for every map_lookup_elem + /* + * transfer reg's id which is unique for every map_lookup_elem * as UID of the inner map. */ - if (btf_record_has_field(map->inner_map_meta->record, - BPF_TIMER | BPF_WORKQUEUE | BPF_TASK_WORK)) - reg->map_uid = reg->id; + reg->map_uid = reg->id; } else if (map->map_type == BPF_MAP_TYPE_XSKMAP) { reg->type = PTR_TO_XDP_SOCK | maybe_null; + reg->map_uid = 0; } else if (map->map_type == BPF_MAP_TYPE_SOCKMAP || map->map_type == BPF_MAP_TYPE_SOCKHASH) { reg->type = PTR_TO_SOCKET | maybe_null; + reg->map_uid = 0; } } @@ -3042,6 +3044,8 @@ static int check_subprogs(struct bpf_verifier_env *env) subprog[cur_subprog].exit_idx = i; goto next; } + if (insn_is_gotox(&insn[i])) + goto next; off = i + bpf_jmp_offset(&insn[i]) + 1; if (off < subprog_start || off >= subprog_end) { verbose(env, "jump out of range from insn %d to %d\n", i, off); @@ -3061,7 +3065,8 @@ next: */ if (code != (BPF_JMP | BPF_EXIT) && code != (BPF_JMP32 | BPF_JA) && - code != (BPF_JMP | BPF_JA)) { + code != (BPF_JMP | BPF_JA) && + !insn_is_gotox(&insn[i])) { verbose(env, "last insn is not an exit or jmp\n"); bpf_diag_program_structure( env, i, "subprogram can fall through", @@ -3582,7 +3587,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, save_register_state(env, state, spi, reg, size); /* Break the relation on a narrowing spill. */ if (!reg_value_fits) - state->stack[spi].spilled_ptr.id = 0; + clear_scalar_id(&state->stack[spi].spilled_ptr); } else if (!reg && !(off % BPF_REG_SIZE) && is_bpf_st_mem(insn) && env->bpf_capable) { struct bpf_reg_state *tmp_reg = &env->fake_reg[0]; @@ -6453,6 +6458,15 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, struct b return -EACCES; } + if (rdonly_untrusted && !env->allow_ptr_leaks) { + verbose(env, "%s access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN\n", + reg_type_str(env, reg->type)); + bpf_diag_policy(env, insn_idx, "read from untrusted read-only memory", + "the access requires CAP_PERFMON", + "Load the program with CAP_PERFMON, or avoid dereferencing untrusted pointers."); + return -EPERM; + } + /* * Accesses to untrusted PTR_TO_MEM are done through probe * instructions, hence no need to check bounds in that case. @@ -9736,6 +9750,16 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog, if (check_mem_reg(env, reg, argno, arg->mem_size, BPF_READ | BPF_WRITE, NULL, NULL)) return -EINVAL; + /* + * PTR_TO_PACKET get passed as PTR_TO_MEM, preventing + * us from adjusting bounds tracking info. + */ + if ((reg_is_pkt_pointer_any(reg) || reg_is_dynptr_slice_pkt(reg)) && + sub->changes_pkt_data) { + bpf_log(log, "%s is a packet pointer, but func#%d may change packet data\n", + reg_arg_name(env, argno), subprog); + return -EINVAL; + } if (!(arg->arg_type & PTR_MAYBE_NULL) && (type_may_be_null(reg->type) || bpf_register_is_null(reg))) { bpf_log(log, "%s is expected to be non-NULL\n", @@ -9919,6 +9943,7 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, if (err == -EFAULT) return err; if (bpf_subprog_is_global(env, subprog)) { + struct bpf_func_info_aux *sub_aux = subprog_aux(env, subprog); const char *sub_name = bpf_subprog_name(env, subprog); const char *operation; bool returns_void; @@ -9950,11 +9975,10 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, if (env->log.level & BPF_LOG_LEVEL) verbose(env, "Func#%d ('%s') is global and assumed valid.\n", subprog, sub_name); + sub_aux->called[in_sleepable_context(env)] = true; returns_void = subprog_returns_void(env, subprog); if (env->subprog_info[subprog].changes_pkt_data) clear_all_pkt_pointers(env); - /* mark global subprog for verifying after main prog */ - subprog_aux(env, subprog)->called = true; if (returns_void) bpf_diag_record_scrub(env, &caller->regs[BPF_REG_0], BPF_DIAG_MOD_CALLER_SAVED); else @@ -10036,6 +10060,7 @@ int map_set_for_each_callback_args(struct bpf_verifier_env *env, __mark_reg_known_zero(&callee->regs[BPF_REG_3]); callee->regs[BPF_REG_3].map_ptr = caller->regs[BPF_REG_1].map_ptr; callee->regs[BPF_REG_3].map_uid = caller->regs[BPF_REG_1].map_uid; + callee->regs[BPF_REG_3].id = ++env->id_gen; /* pointer to stack or null */ callee->regs[BPF_REG_4] = caller->regs[BPF_REG_3]; @@ -10132,6 +10157,7 @@ static int set_timer_callback_state(struct bpf_verifier_env *env, __mark_reg_known_zero(&callee->regs[BPF_REG_3]); callee->regs[BPF_REG_3].map_ptr = map_ptr; callee->regs[BPF_REG_3].map_uid = map_uid; + callee->regs[BPF_REG_3].id = ++env->id_gen; /* unused */ bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_4]); @@ -10250,6 +10276,7 @@ static int set_task_work_schedule_callback_state(struct bpf_verifier_env *env, __mark_reg_known_zero(&callee->regs[BPF_REG_3]); callee->regs[BPF_REG_3].map_ptr = map_ptr; callee->regs[BPF_REG_3].map_uid = map_uid; + callee->regs[BPF_REG_3].id = ++env->id_gen; /* unused */ bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_4]); @@ -10772,11 +10799,7 @@ int bpf_get_helper_proto(struct bpf_verifier_env *env, int func_id, /* Check if we're in a sleepable context. */ static inline bool in_sleepable_context(struct bpf_verifier_env *env) { - return !env->cur_state->active_rcu_locks && - !env->cur_state->active_preempt_locks && - !env->cur_state->active_locks && - !env->cur_state->active_irq_id && - in_sleepable(env); + return !in_rcu_cs(env); } static const char *non_sleepable_context_description(struct bpf_verifier_env *env) @@ -11356,6 +11379,11 @@ static bool is_kfunc_destructive(struct bpf_call_arg_meta *meta) return meta->kfunc_flags & KF_DESTRUCTIVE; } +static bool is_kfunc_perfmon(struct bpf_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_PERFMON; +} + static bool is_kfunc_rcu(struct bpf_call_arg_meta *meta) { return meta->kfunc_flags & KF_RCU; @@ -13834,6 +13862,15 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, return -EACCES; } + if (is_kfunc_perfmon(&meta) && !env->allow_ptr_leaks) { + verbose(env, "%s is allowed only to CAP_PERFMON and CAP_SYS_ADMIN\n", + func_name); + operation = bpf_diag_fmt(env, "kfunc %s", func_name); + bpf_diag_policy(env, insn_idx, operation, "the kfunc requires CAP_PERFMON", + "Load the program with CAP_PERFMON, or avoid the kfunc."); + return -EPERM; + } + sleepable = bpf_is_kfunc_sleepable(&meta); if (sleepable && !in_sleepable(env)) { verbose(env, "program must be sleepable to call sleepable kfunc %s\n", func_name); @@ -14789,7 +14826,15 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, struct bpf_insn "Tighten the scalar bounds before the arithmetic so the resulting pointer remains within the allowed range."); return -EINVAL; } - reg_bounds_sync(dst_reg); + /* + * A packet pointer that keeps its id or range is checked against a + * range set from the checked pointer's umax, so var_off must not tighten + * its umax. r32 must still match var_off for reg_bounds_sanity_check(). + */ + if (reg_is_pkt_pointer(dst_reg) && (known || dst_reg->range > 0)) + __update_reg32_bounds(dst_reg); + else + reg_bounds_sync(dst_reg); bounds_ret = sanitize_check_bounds(env, insn, dst_reg); if (bounds_ret == -EACCES) return bounds_ret; @@ -15704,6 +15749,7 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, struct bpf_reg_state *regs = state->regs, *dst_reg, *src_reg; struct bpf_reg_state *ptr_reg = NULL, off_reg = {0}; bool alu32 = (BPF_CLASS(insn->code) != BPF_ALU64); + struct bpf_insn_aux_data *aux = cur_aux(env); u8 opcode = BPF_OP(insn->code); int err; @@ -15715,13 +15761,24 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, /* Case where at least one operand is an arena. */ if (dst_reg->type == PTR_TO_ARENA || (src_reg && src_reg->type == PTR_TO_ARENA)) { - struct bpf_insn_aux_data *aux = cur_aux(env); if (dst_reg->type != PTR_TO_ARENA) *dst_reg = *src_reg; if (BPF_CLASS(insn->code) == BPF_ALU64) { /* + * Only arena pointers set needs_zext, but doing so + * modifies the instruction at fixup time to an ALU32 + * and makes it unsuitable for 64-bit scalar args. We + * prevent zext from being set if the instruction has + * been previously called with non-arena registers. + */ + if (aux->prevent_zext) { + verbose(env, "same insn cannot be used with and without arena pointer\n"); + return -EINVAL; + } + + /* * 32-bit operations zero upper bits automatically. * 64-bit operations need to be converted to 32. */ @@ -15733,6 +15790,16 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, return 0; } + /* Prevent the instruction from being used with arena pointers (see above). */ + if (env->prog->aux->arena && BPF_CLASS(insn->code) == BPF_ALU64) { + if (aux->needs_zext) { + verbose(env, "same insn cannot be used with and without arena pointer\n"); + return -EINVAL; + } + + aux->prevent_zext = true; + } + if (dst_reg->type != SCALAR_VALUE) ptr_reg = dst_reg; @@ -19421,13 +19488,14 @@ static void free_states(struct bpf_verifier_env *env) } } -static int do_check_common(struct bpf_verifier_env *env, int subprog) +static int do_check_common(struct bpf_verifier_env *env, int subprog, bool is_sleepable) { bool pop_log = !(env->log.level & BPF_LOG_LEVEL2); struct bpf_subprog_info *sub = subprog_info(env, subprog); struct bpf_prog_aux *aux = env->prog->aux; struct bpf_verifier_state *state; struct bpf_reg_state *regs; + u32 old_insns_total = sub->insns_total; u32 insn_processed = env->insn_processed; int ret, i; @@ -19440,7 +19508,7 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog) state->curframe = 0; state->speculative = false; state->branches = 1; - state->in_sleepable = env->prog->sleepable; + state->in_sleepable = is_sleepable; state->frame[0] = kzalloc_obj(struct bpf_func_state, GFP_KERNEL_ACCOUNT); if (!state->frame[0]) { kfree(state); @@ -19581,8 +19649,10 @@ out: * not accounted as callees by account_current_path(). * Accumulate their total counts as total counts of the main or * global subprog hosting the async call. + * Start from the saved total of earlier contexts: adding to the current + * total would count this pass's synchronous paths twice. */ - env->subprog_info[subprog].insns_total = env->insn_processed - insn_processed; + sub->insns_total = old_insns_total + (env->insn_processed - insn_processed); return ret; } @@ -19610,14 +19680,19 @@ static int do_check_subprogs(struct bpf_verifier_env *env) { struct bpf_prog_aux *aux = env->prog->aux; struct bpf_func_info_aux *sub_aux; - int i, ret, new_cnt; + int context, i, ret, new_cnt; if (!aux->func_info) return 0; - /* exception callback is presumed to be always called */ - if (env->exception_callback_subprog) - subprog_aux(env, env->exception_callback_subprog)->called = true; + /* + * Callbacks cannot throw, so the exception callback always runs in the + * main program's context. It is presumed to be always called. + */ + if (env->exception_callback_subprog) { + sub_aux = subprog_aux(env, env->exception_callback_subprog); + sub_aux->called[env->prog->sleepable] = true; + } again: new_cnt = 0; @@ -19626,29 +19701,28 @@ again: continue; sub_aux = subprog_aux(env, i); - if (!sub_aux->called || sub_aux->verified) - continue; + for (context = 0; context < ARRAY_SIZE(sub_aux->called); context++) { + if (!sub_aux->called[context] || sub_aux->verified[context]) + continue; - env->insn_idx = env->subprog_info[i].start; - WARN_ON_ONCE(env->insn_idx == 0); - ret = do_check_common(env, i); - if (ret) { - return ret; - } else if (env->log.level & BPF_LOG_LEVEL) { - verbose(env, "Func#%d ('%s') is safe for any args that match its prototype\n", - i, bpf_subprog_name(env, i)); - } + env->insn_idx = env->subprog_info[i].start; + WARN_ON_ONCE(env->insn_idx == 0); + ret = do_check_common(env, i, context); + if (ret) + return ret; + if (env->log.level & BPF_LOG_LEVEL) + verbose(env, "Func#%d ('%s') is safe for any args " + "that match its prototype\n", + i, bpf_subprog_name(env, i)); - /* We verified new global subprog, it might have called some - * more global subprogs that we haven't verified yet, so we - * need to do another pass over subprogs to verify those. - */ - sub_aux->verified = true; - new_cnt++; + sub_aux->verified[context] = true; + new_cnt++; + } } - /* We can't loop forever as we verify at least one global subprog on - * each pass. + /* + * We can't loop forever as each pass verifies at least one new context, + * and there are only two contexts per global subprog. */ if (new_cnt) goto again; @@ -19661,7 +19735,7 @@ static int do_check_main(struct bpf_verifier_env *env) int ret; env->insn_idx = 0; - ret = do_check_common(env, 0); + ret = do_check_common(env, 0, env->prog->sleepable); if (!ret) env->prog->aux->stack_depth = env->subprog_info[0].stack_depth; return ret; @@ -21170,6 +21244,11 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, ret = bpf_diag_init(env); if (ret) goto err_prep; + if (env->prog->insnsi[env->prog->len - 1].code == (BPF_LD | BPF_IMM | BPF_DW)) { + verbose(env, "invalid bpf_ld_imm64 insn\n"); + ret = -EINVAL; + goto err_prep; + } if (env->signature) { ret = bpf_prog_calc_tag(env->prog); if (ret < 0) @@ -21245,6 +21324,11 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, if (ret < 0) goto skip_full_check; + /* Apply CO-RE before validating the program's instruction layout. */ + ret = bpf_check_core_relo(env, attr, uattr); + if (ret < 0) + goto skip_full_check; + /* Discover all subprograms before validating their layout and BTF. */ ret = add_subprogs(env); if (ret < 0) @@ -21254,7 +21338,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, if (ret < 0) goto skip_full_check; - /* Validate BTF against the complete subprogram layout and apply CO-RE. */ + /* Validate BTF against the complete subprogram layout. */ ret = bpf_check_btf_info(env, attr, uattr); if (ret < 0) goto skip_full_check; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 2d532bf2c0c7..227d09704ca5 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5303,10 +5303,13 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it) if (it->flags & CSS_TASK_ITER_SKIPPED) css_task_iter_advance(it); - if (it->task_pos) { + while (it->task_pos && !it->cur_task) { it->cur_task = list_entry(it->task_pos, struct task_struct, cg_list); - get_task_struct(it->cur_task); + /* a task on dying_tasks with zero refcount is only valid for + * RCU readers, not even interesting for + * CSS_TASK_ITER_WITH_DEAD, find another one */ + it->cur_task = tryget_task_struct(it->cur_task); css_task_iter_advance(it); } diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 2538faac9aba..3f52717c1965 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1591,10 +1591,11 @@ static int remote_partition_enable(struct cpuset *cs, int new_prs, * above it or remote partition root underneath it is not allowed. */ compute_excpus(cs, tmp->new_cpus); - WARN_ON_ONCE(cpumask_intersects(tmp->new_cpus, subpartitions_cpus)); if (!cpumask_intersects(tmp->new_cpus, cpu_active_mask) || cpumask_subset(top_cpuset.effective_cpus, tmp->new_cpus)) return PERR_INVCPUS; + if (cpumask_intersects(tmp->new_cpus, subpartitions_cpus)) + return PERR_NOCPUS; if (((new_prs == PRS_ISOLATED) && !isolated_cpus_can_update(tmp->new_cpus, NULL)) || prstate_housekeeping_conflict(new_prs, tmp->new_cpus)) diff --git a/kernel/cgroup/pids.c b/kernel/cgroup/pids.c index ecbb839d2acb..78cdc0558d0c 100644 --- a/kernel/cgroup/pids.c +++ b/kernel/cgroup/pids.c @@ -253,6 +253,11 @@ static void pids_event(struct pids_cgroup *pids_forking, } if (!cgroup_subsys_on_dfl(pids_cgrp_subsys) || cgrp_dfl_root.flags & CGRP_ROOT_PIDS_LOCAL_EVENTS) { + /* + * pids.events reports the local counter on legacy hierarchies + * and when pids_localevents is enabled. + */ + cgroup_file_notify(&p->events_file); cgroup_file_notify(&p->events_local_file); return; } diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c index 45bbae947f4b..4d0266893bcc 100644 --- a/kernel/dma/coherent.c +++ b/kernel/dma/coherent.c @@ -352,8 +352,7 @@ static int rmem_dma_device_init(struct reserved_mem *rmem, struct device *dev) min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit)) dev_warn(dev, "reserved memory is beyond device's set DMA address range\n"); - dma_assign_coherent_memory(dev, mem); - return 0; + return dma_assign_coherent_memory(dev, mem); } static void rmem_dma_device_release(struct reserved_mem *rmem, diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index ded7016a46a7..aa2f1c4588b9 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -1019,7 +1019,6 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size int index = (tlb_addr - mem->start) >> IO_TLB_SHIFT; phys_addr_t orig_addr = mem->slots[index].orig_addr; size_t alloc_size = mem->slots[index].alloc_size; - unsigned long pfn = PFN_DOWN(orig_addr); unsigned char *vaddr = mem->vaddr + tlb_addr - mem->start; int tlb_offset; @@ -1052,7 +1051,8 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size size = alloc_size; } - if (PageHighMem(pfn_to_page(pfn))) { + if (PhysHighMem(orig_addr)) { + unsigned long pfn = PFN_DOWN(orig_addr); unsigned int offset = orig_addr & ~PAGE_MASK; struct page *page; unsigned int sz = 0; diff --git a/kernel/events/core.c b/kernel/events/core.c index fe33fe15689d..7846d70be57f 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3764,6 +3764,9 @@ static void perf_ctx_sched_task_cb(struct perf_event_context *ctx, list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) { cpc = this_cpc(pmu_ctx->pmu); + if (cpc->task_epc != pmu_ctx) + continue; + if (cpc->sched_cb_usage && pmu_ctx->pmu->sched_task) pmu_ctx->pmu->sched_task(pmu_ctx, task, sched_in); } @@ -3914,7 +3917,7 @@ static void __perf_pmu_sched_task(struct perf_cpu_pmu_context *cpc, perf_ctx_lock(cpuctx, cpuctx->task_ctx); perf_pmu_disable(pmu); - pmu->sched_task(cpc->task_epc, task, sched_in); + pmu->sched_task(&cpc->epc, task, sched_in); perf_pmu_enable(pmu); perf_ctx_unlock(cpuctx, cpuctx->task_ctx); @@ -3924,15 +3927,17 @@ static void perf_pmu_sched_task(struct task_struct *prev, struct task_struct *next, bool sched_in) { - struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context); struct perf_cpu_pmu_context *cpc, *cpc2; - /* cpuctx->task_ctx will be handled in perf_event_context_sched_in/out */ - if (prev == next || cpuctx->task_ctx) + if (prev == next) return; - list_for_each_entry_safe(cpc, cpc2, this_cpu_ptr(&sched_cb_list), sched_cb_entry) + list_for_each_entry_safe(cpc, cpc2, this_cpu_ptr(&sched_cb_list), sched_cb_entry) { + if (cpc->task_epc) + continue; + __perf_pmu_sched_task(cpc, sched_in ? next : prev, sched_in); + } } static void perf_event_switch(struct task_struct *task, @@ -5454,6 +5459,8 @@ attach_task_ctx_data(struct task_struct *task, struct kmem_cache *ctx_cache, } if (refcount_inc_not_zero(&old->refcount)) { + if (global) + old->global = true; free_perf_ctx_data(cd); /* unused */ return 0; } @@ -6350,6 +6357,9 @@ static DEFINE_MUTEX(perf_mediated_pmu_mutex); /* !exclude_guest event of PMU with PERF_PMU_CAP_MEDIATED_VPMU */ static inline bool is_include_guest_event(struct perf_event *event) { + if (!event->pmu) + return false; + if ((event->pmu->capabilities & PERF_PMU_CAP_MEDIATED_VPMU) && !event->attr.exclude_guest) return true; @@ -7616,9 +7626,11 @@ static void perf_sigtrap(struct perf_event *event) { /* * Both perf_pending_task() and perf_pending_irq() can race with the - * task exiting. + * task exiting or exec-ing. We can determine if such a race has + * occurred by checking if perf_event_exit_task(), which will set + * ctx->task to TASK_TOMBSTONE, has already been called. */ - if (current->flags & PF_EXITING) + if (event->ctx->task == TASK_TOMBSTONE) return; /* @@ -8119,10 +8131,15 @@ static void __perf_event_header__init_id(struct perf_sample_data *data, } } -void perf_event_header__init_id(struct perf_event_header *header, - struct perf_sample_data *data, - struct perf_event *event) +void perf_event_header__init(struct perf_event_header *header, + struct perf_sample_data *data, + u32 type, u16 misc, u16 size, + struct perf_event *event) { + header->type = type; + header->misc = misc; + header->size = size; + if (event->attr.sample_id_all) { header->size += event->id_header_size; __perf_event_header__init_id(data, event, event->attr.sample_type); @@ -8959,17 +8976,16 @@ perf_event_read_event(struct perf_event *event, struct perf_output_handle handle; struct perf_sample_data sample; struct perf_read_event read_event = { - .header = { - .type = PERF_RECORD_READ, - .misc = 0, - .size = sizeof(read_event) + event->read_size, - }, .pid = perf_event_pid(event, task), .tid = perf_event_tid(event, task), }; int ret; - perf_event_header__init_id(&read_event.header, &sample, event); + perf_event_header__init(&read_event.header, &sample, + PERF_RECORD_READ, + /* misc= */ 0, + sizeof(read_event) + event->read_size, + event); ret = perf_output_begin(&handle, &sample, event, read_event.header.size); if (ret) return; @@ -9210,6 +9226,7 @@ struct perf_task_event { u32 ptid; u64 time; } event_id; + int new; }; static int perf_event_task_match(struct perf_event *event) @@ -9226,17 +9243,21 @@ static void perf_event_task_output(struct perf_event *event, struct perf_output_handle handle; struct perf_sample_data sample; struct task_struct *task = task_event->task; - int ret, size = task_event->event_id.header.size; + int ret; if (!perf_event_task_match(event)) return; - perf_event_header__init_id(&task_event->event_id.header, &sample, event); + perf_event_header__init(&task_event->event_id.header, &sample, + task_event->new ? PERF_RECORD_FORK : PERF_RECORD_EXIT, + /* misc= */ 0, + sizeof(task_event->event_id), + event); ret = perf_output_begin(&handle, &sample, event, task_event->event_id.header.size); if (ret) - goto out; + return; task_event->event_id.pid = perf_event_pid(event, task); task_event->event_id.tid = perf_event_tid(event, task); @@ -9258,8 +9279,6 @@ static void perf_event_task_output(struct perf_event *event, perf_event__output_id_sample(event, &handle, &sample); perf_output_end(&handle); -out: - task_event->event_id.header.size = size; } static void perf_event_task(struct task_struct *task, @@ -9276,18 +9295,7 @@ static void perf_event_task(struct task_struct *task, task_event = (struct perf_task_event){ .task = task, .task_ctx = task_ctx, - .event_id = { - .header = { - .type = new ? PERF_RECORD_FORK : PERF_RECORD_EXIT, - .misc = 0, - .size = sizeof(task_event.event_id), - }, - /* .pid */ - /* .ppid */ - /* .tid */ - /* .ptid */ - /* .time */ - }, + .new = new, }; perf_iterate_sb(perf_event_task_output, @@ -9364,6 +9372,7 @@ struct perf_comm_event { u32 pid; u32 tid; } event_id; + bool exec; }; static int perf_event_comm_match(struct perf_event *event) @@ -9377,18 +9386,21 @@ static void perf_event_comm_output(struct perf_event *event, struct perf_comm_event *comm_event = data; struct perf_output_handle handle; struct perf_sample_data sample; - int size = comm_event->event_id.header.size; int ret; if (!perf_event_comm_match(event)) return; - perf_event_header__init_id(&comm_event->event_id.header, &sample, event); + perf_event_header__init(&comm_event->event_id.header, &sample, + PERF_RECORD_COMM, + comm_event->exec ? PERF_RECORD_MISC_COMM_EXEC : 0, + sizeof(comm_event->event_id) + comm_event->comm_size, + event); ret = perf_output_begin(&handle, &sample, event, comm_event->event_id.header.size); if (ret) - goto out; + return; comm_event->event_id.pid = perf_event_pid(event, comm_event->task); comm_event->event_id.tid = perf_event_tid(event, comm_event->task); @@ -9400,8 +9412,6 @@ static void perf_event_comm_output(struct perf_event *event, perf_event__output_id_sample(event, &handle, &sample); perf_output_end(&handle); -out: - comm_event->event_id.header.size = size; } static void perf_event_comm_event(struct perf_comm_event *comm_event) @@ -9416,8 +9426,6 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event) comm_event->comm = comm; comm_event->comm_size = size; - comm_event->event_id.header.size = sizeof(comm_event->event_id) + size; - perf_iterate_sb(perf_event_comm_output, comm_event, NULL); @@ -9434,15 +9442,8 @@ void perf_event_comm(struct task_struct *task, bool exec) .task = task, /* .comm */ /* .comm_size */ - .event_id = { - .header = { - .type = PERF_RECORD_COMM, - .misc = exec ? PERF_RECORD_MISC_COMM_EXEC : 0, - /* .size */ - }, - /* .pid */ - /* .tid */ - }, + /* .event_id */ + .exec = exec, }; perf_event_comm_event(&comm_event); @@ -9476,18 +9477,20 @@ static void perf_event_namespaces_output(struct perf_event *event, struct perf_namespaces_event *namespaces_event = data; struct perf_output_handle handle; struct perf_sample_data sample; - u16 header_size = namespaces_event->event_id.header.size; int ret; if (!perf_event_namespaces_match(event)) return; - perf_event_header__init_id(&namespaces_event->event_id.header, - &sample, event); + perf_event_header__init(&namespaces_event->event_id.header, &sample, + PERF_RECORD_NAMESPACES, + /* misc= */ 0, + sizeof(namespaces_event->event_id), + event); ret = perf_output_begin(&handle, &sample, event, namespaces_event->event_id.header.size); if (ret) - goto out; + return; namespaces_event->event_id.pid = perf_event_pid(event, namespaces_event->task); @@ -9499,8 +9502,6 @@ static void perf_event_namespaces_output(struct perf_event *event, perf_event__output_id_sample(event, &handle, &sample); perf_output_end(&handle); -out: - namespaces_event->event_id.header.size = header_size; } static void perf_fill_ns_link_info(struct perf_ns_link_info *ns_link_info, @@ -9531,11 +9532,7 @@ void perf_event_namespaces(struct task_struct *task) namespaces_event = (struct perf_namespaces_event){ .task = task, .event_id = { - .header = { - .type = PERF_RECORD_NAMESPACES, - .misc = 0, - .size = sizeof(namespaces_event.event_id), - }, + /* .header */ /* .pid */ /* .tid */ .nr_namespaces = NR_NAMESPACES, @@ -9603,18 +9600,19 @@ static void perf_event_cgroup_output(struct perf_event *event, void *data) struct perf_cgroup_event *cgroup_event = data; struct perf_output_handle handle; struct perf_sample_data sample; - u16 header_size = cgroup_event->event_id.header.size; int ret; + u16 size = sizeof(cgroup_event->event_id) + cgroup_event->path_size; if (!perf_event_cgroup_match(event)) return; - perf_event_header__init_id(&cgroup_event->event_id.header, - &sample, event); + perf_event_header__init(&cgroup_event->event_id.header, &sample, + PERF_RECORD_CGROUP, /* misc= */ 0, size, + event); ret = perf_output_begin(&handle, &sample, event, cgroup_event->event_id.header.size); if (ret) - goto out; + return; perf_output_put(&handle, cgroup_event->event_id); __output_copy(&handle, cgroup_event->path, cgroup_event->path_size); @@ -9622,8 +9620,6 @@ static void perf_event_cgroup_output(struct perf_event *event, void *data) perf_event__output_id_sample(event, &handle, &sample); perf_output_end(&handle); -out: - cgroup_event->event_id.header.size = header_size; } static void perf_event_cgroup(struct cgroup *cgrp) @@ -9638,11 +9634,6 @@ static void perf_event_cgroup(struct cgroup *cgrp) cgroup_event = (struct perf_cgroup_event){ .event_id = { - .header = { - .type = PERF_RECORD_CGROUP, - .misc = 0, - .size = sizeof(cgroup_event.event_id), - }, .id = cgroup_id(cgrp), }, }; @@ -9665,7 +9656,6 @@ static void perf_event_cgroup(struct cgroup *cgrp) while (!IS_ALIGNED(size, sizeof(u64))) cgroup_event.path[size++] = '\0'; - cgroup_event.event_id.header.size += size; cgroup_event.path_size = size; perf_iterate_sb(perf_event_cgroup_output, @@ -9721,38 +9711,40 @@ static void perf_event_mmap_output(struct perf_event *event, struct perf_mmap_event *mmap_event = data; struct perf_output_handle handle; struct perf_sample_data sample; - int size = mmap_event->event_id.header.size; - u32 type = mmap_event->event_id.header.type; - bool use_build_id; + int size = sizeof(mmap_event->event_id) + mmap_event->file_size; + u32 type = PERF_RECORD_MMAP; + u16 misc = PERF_RECORD_MISC_USER; + bool use_build_id = false; int ret; if (!perf_event_mmap_match(event, data)) return; if (event->attr.mmap2) { - mmap_event->event_id.header.type = PERF_RECORD_MMAP2; - mmap_event->event_id.header.size += sizeof(mmap_event->maj); - mmap_event->event_id.header.size += sizeof(mmap_event->min); - mmap_event->event_id.header.size += sizeof(mmap_event->ino); - mmap_event->event_id.header.size += sizeof(mmap_event->ino_generation); - mmap_event->event_id.header.size += sizeof(mmap_event->prot); - mmap_event->event_id.header.size += sizeof(mmap_event->flags); - } - - perf_event_header__init_id(&mmap_event->event_id.header, &sample, event); + type = PERF_RECORD_MMAP2; + size += sizeof(mmap_event->maj); + size += sizeof(mmap_event->min); + size += sizeof(mmap_event->ino); + size += sizeof(mmap_event->ino_generation); + size += sizeof(mmap_event->prot); + size += sizeof(mmap_event->flags); + use_build_id = event->attr.build_id && mmap_event->build_id_size; + if (use_build_id) + misc |= PERF_RECORD_MISC_MMAP_BUILD_ID; + } + if (!(mmap_event->vma->vm_flags & VM_EXEC)) + misc |= PERF_RECORD_MISC_MMAP_DATA; + + perf_event_header__init(&mmap_event->event_id.header, &sample, + type, misc, size, event); ret = perf_output_begin(&handle, &sample, event, mmap_event->event_id.header.size); if (ret) - goto out; + return; mmap_event->event_id.pid = perf_event_pid(event, current); mmap_event->event_id.tid = perf_event_tid(event, current); - use_build_id = event->attr.build_id && mmap_event->build_id_size; - - if (event->attr.mmap2 && use_build_id) - mmap_event->event_id.header.misc |= PERF_RECORD_MISC_MMAP_BUILD_ID; - perf_output_put(&handle, mmap_event->event_id); if (event->attr.mmap2) { @@ -9777,9 +9769,6 @@ static void perf_event_mmap_output(struct perf_event *event, perf_event__output_id_sample(event, &handle, &sample); perf_output_end(&handle); -out: - mmap_event->event_id.header.size = size; - mmap_event->event_id.header.type = type; } static void perf_event_mmap_event(struct perf_mmap_event *mmap_event) @@ -9875,11 +9864,6 @@ got_name: mmap_event->prot = prot; mmap_event->flags = flags; - if (!(vma->vm_flags & VM_EXEC)) - mmap_event->event_id.header.misc |= PERF_RECORD_MISC_MMAP_DATA; - - mmap_event->event_id.header.size = sizeof(mmap_event->event_id) + size; - if (atomic_read(&nr_build_id_events)) build_id_parse_nofault(vma, mmap_event->build_id, &mmap_event->build_id_size); @@ -9999,11 +9983,7 @@ void perf_event_mmap(struct vm_area_struct *vma) /* .file_name */ /* .file_size */ .event_id = { - .header = { - .type = PERF_RECORD_MMAP, - .misc = PERF_RECORD_MISC_USER, - /* .size */ - }, + /* .header */ /* .pid */ /* .tid */ .start = vma->vm_start, @@ -10033,18 +10013,15 @@ void perf_event_aux_event(struct perf_event *event, unsigned long head, u64 size; u64 flags; } rec = { - .header = { - .type = PERF_RECORD_AUX, - .misc = 0, - .size = sizeof(rec), - }, .offset = head, .size = size, .flags = flags, }; int ret; - perf_event_header__init_id(&rec.header, &sample, event); + perf_event_header__init(&rec.header, &sample, + PERF_RECORD_AUX, /* misc= */ 0, sizeof(rec), + event); ret = perf_output_begin(&handle, &sample, event, rec.header.size); if (ret) @@ -10069,15 +10046,14 @@ void perf_log_lost_samples(struct perf_event *event, u64 lost) struct perf_event_header header; u64 lost; } lost_samples_event = { - .header = { - .type = PERF_RECORD_LOST_SAMPLES, - .misc = 0, - .size = sizeof(lost_samples_event), - }, .lost = lost, }; - perf_event_header__init_id(&lost_samples_event.header, &sample, event); + perf_event_header__init(&lost_samples_event.header, &sample, + PERF_RECORD_LOST_SAMPLES, + /* misc= */ 0, + sizeof(lost_samples_event), + event); ret = perf_output_begin(&handle, &sample, event, lost_samples_event.header.size); @@ -10102,6 +10078,8 @@ struct perf_switch_event { u32 next_prev_pid; u32 next_prev_tid; } event_id; + bool sched_in; + bool preempt; }; static int perf_event_switch_match(struct perf_event *event) @@ -10114,6 +10092,9 @@ static void perf_event_switch_output(struct perf_event *event, void *data) struct perf_switch_event *se = data; struct perf_output_handle handle; struct perf_sample_data sample; + u32 type; + u16 misc; + u16 size; int ret; if (!perf_event_switch_match(event)) @@ -10121,18 +10102,22 @@ static void perf_event_switch_output(struct perf_event *event, void *data) /* Only CPU-wide events are allowed to see next/prev pid/tid */ if (event->ctx->task) { - se->event_id.header.type = PERF_RECORD_SWITCH; - se->event_id.header.size = sizeof(se->event_id.header); + type = PERF_RECORD_SWITCH; + size = sizeof(se->event_id.header); } else { - se->event_id.header.type = PERF_RECORD_SWITCH_CPU_WIDE; - se->event_id.header.size = sizeof(se->event_id); + type = PERF_RECORD_SWITCH_CPU_WIDE; + size = sizeof(se->event_id); se->event_id.next_prev_pid = perf_event_pid(event, se->next_prev); se->event_id.next_prev_tid = perf_event_tid(event, se->next_prev); } + misc = se->sched_in ? 0 : PERF_RECORD_MISC_SWITCH_OUT; + if (se->preempt) + misc |= PERF_RECORD_MISC_SWITCH_OUT_PREEMPT; - perf_event_header__init_id(&se->event_id.header, &sample, event); + perf_event_header__init(&se->event_id.header, &sample, + type, misc, size, event); ret = perf_output_begin(&handle, &sample, event, se->event_id.header.size); if (ret) @@ -10158,22 +10143,11 @@ static void perf_event_switch(struct task_struct *task, switch_event = (struct perf_switch_event){ .task = task, .next_prev = next_prev, - .event_id = { - .header = { - /* .type */ - .misc = sched_in ? 0 : PERF_RECORD_MISC_SWITCH_OUT, - /* .size */ - }, - /* .next_prev_pid */ - /* .next_prev_tid */ - }, + /* .event_id */ + .sched_in = sched_in, + .preempt = !sched_in && task_is_runnable(task), }; - if (!sched_in && task_is_runnable(task)) { - switch_event.event_id.header.misc |= - PERF_RECORD_MISC_SWITCH_OUT_PREEMPT; - } - perf_iterate_sb(perf_event_switch_output, &switch_event, NULL); } @@ -10193,20 +10167,17 @@ static void perf_log_throttle(struct perf_event *event, int enable) u64 id; u64 stream_id; } throttle_event = { - .header = { - .type = PERF_RECORD_THROTTLE, - .misc = 0, - .size = sizeof(throttle_event), - }, .time = perf_event_clock(event), .id = primary_event_id(event), .stream_id = event->id, }; - if (enable) - throttle_event.header.type = PERF_RECORD_UNTHROTTLE; - - perf_event_header__init_id(&throttle_event.header, &sample, event); + perf_event_header__init(&throttle_event.header, &sample, + enable ? PERF_RECORD_UNTHROTTLE + : PERF_RECORD_THROTTLE, + /* misc= */ 0, + sizeof(throttle_event), + event); ret = perf_output_begin(&handle, &sample, event, throttle_event.header.size); @@ -10245,12 +10216,14 @@ static void perf_event_ksymbol_output(struct perf_event *event, void *data) struct perf_output_handle handle; struct perf_sample_data sample; int ret; + u16 size = sizeof(ksymbol_event->event_id) + ksymbol_event->name_len; if (!perf_event_ksymbol_match(event)) return; - perf_event_header__init_id(&ksymbol_event->event_id.header, - &sample, event); + perf_event_header__init(&ksymbol_event->event_id.header, &sample, + PERF_RECORD_KSYMBOL, /* misc= */ 0, size, + event); ret = perf_output_begin(&handle, &sample, event, ksymbol_event->event_id.header.size); if (ret) @@ -10291,11 +10264,6 @@ void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister, .name = name, .name_len = name_len, .event_id = { - .header = { - .type = PERF_RECORD_KSYMBOL, - .size = sizeof(ksymbol_event.event_id) + - name_len, - }, .addr = addr, .len = len, .ksym_type = ksym_type, @@ -10339,8 +10307,11 @@ static void perf_event_bpf_output(struct perf_event *event, void *data) if (!perf_event_bpf_match(event)) return; - perf_event_header__init_id(&bpf_event->event_id.header, - &sample, event); + perf_event_header__init(&bpf_event->event_id.header, &sample, + PERF_RECORD_BPF_EVENT, + /* misc= */ 0, + sizeof(bpf_event->event_id), + event); ret = perf_output_begin(&handle, &sample, event, bpf_event->event_id.header.size); if (ret) @@ -10396,10 +10367,6 @@ void perf_event_bpf_event(struct bpf_prog *prog, bpf_event = (struct perf_bpf_event){ .prog = prog, .event_id = { - .header = { - .type = PERF_RECORD_BPF_EVENT, - .size = sizeof(bpf_event.event_id), - }, .type = type, .flags = flags, .id = prog->aux->id, @@ -10427,18 +10394,23 @@ static void perf_callchain_deferred_output(struct perf_event *event, void *data) struct perf_callchain_deferred_event *deferred_event = data; struct perf_output_handle handle; struct perf_sample_data sample; - int ret, size = deferred_event->event.header.size; + int ret; + u16 size = sizeof(deferred_event->event) + (deferred_event->trace->nr * sizeof(u64)); if (!event->attr.defer_output) return; /* XXX do we really need sample_id_all for this ??? */ - perf_event_header__init_id(&deferred_event->event.header, &sample, event); + perf_event_header__init(&deferred_event->event.header, &sample, + PERF_RECORD_CALLCHAIN_DEFERRED, + PERF_RECORD_MISC_USER, + size, + event); ret = perf_output_begin(&handle, &sample, event, deferred_event->event.header.size); if (ret) - goto out; + return; perf_output_put(&handle, deferred_event->event); for (int i = 0; i < deferred_event->trace->nr; i++) { @@ -10448,8 +10420,6 @@ static void perf_callchain_deferred_output(struct perf_event *event, void *data) perf_event__output_id_sample(event, &handle, &sample); perf_output_end(&handle); -out: - deferred_event->event.header.size = size; } static void perf_unwind_deferred_callback(struct unwind_work *work, @@ -10458,12 +10428,6 @@ static void perf_unwind_deferred_callback(struct unwind_work *work, struct perf_callchain_deferred_event deferred_event = { .trace = trace, .event = { - .header = { - .type = PERF_RECORD_CALLCHAIN_DEFERRED, - .misc = PERF_RECORD_MISC_USER, - .size = sizeof(deferred_event.event) + - (trace->nr * sizeof(u64)), - }, .cookie = cookie, .nr = trace->nr, }, @@ -10475,7 +10439,8 @@ static void perf_unwind_deferred_callback(struct unwind_work *work, struct perf_text_poke_event { const void *old_bytes; const void *new_bytes; - size_t pad; + u16 tot; + u16 pad; u16 old_len; u16 new_len; @@ -10496,13 +10461,18 @@ static void perf_event_text_poke_output(struct perf_event *event, void *data) struct perf_text_poke_event *text_poke_event = data; struct perf_output_handle handle; struct perf_sample_data sample; + u16 size = sizeof(text_poke_event->event_id) + text_poke_event->tot + text_poke_event->pad; u64 padding = 0; int ret; if (!perf_event_text_poke_match(event)) return; - perf_event_header__init_id(&text_poke_event->event_id.header, &sample, event); + perf_event_header__init(&text_poke_event->event_id.header, &sample, + PERF_RECORD_TEXT_POKE, + PERF_RECORD_MISC_KERNEL, + size, + event); ret = perf_output_begin(&handle, &sample, event, text_poke_event->event_id.header.size); @@ -10540,15 +10510,11 @@ void perf_event_text_poke(const void *addr, const void *old_bytes, text_poke_event = (struct perf_text_poke_event){ .old_bytes = old_bytes, .new_bytes = new_bytes, + .tot = tot, .pad = pad, .old_len = old_len, .new_len = new_len, .event_id = { - .header = { - .type = PERF_RECORD_TEXT_POKE, - .misc = PERF_RECORD_MISC_KERNEL, - .size = sizeof(text_poke_event.event_id) + tot + pad, - }, .addr = (unsigned long)addr, }, }; @@ -10579,13 +10545,12 @@ static void perf_log_itrace_start(struct perf_event *event) event->attach_state & PERF_ATTACH_ITRACE) return; - rec.header.type = PERF_RECORD_ITRACE_START; - rec.header.misc = 0; - rec.header.size = sizeof(rec); rec.pid = perf_event_pid(event, current); rec.tid = perf_event_tid(event, current); - perf_event_header__init_id(&rec.header, &sample, event); + perf_event_header__init(&rec.header, &sample, + PERF_RECORD_ITRACE_START, /* misc= */ 0, sizeof(rec), + event); ret = perf_output_begin(&handle, &sample, event, rec.header.size); if (ret) @@ -10610,12 +10575,10 @@ void perf_report_aux_output_id(struct perf_event *event, u64 hw_id) if (event->parent) event = event->parent; - rec.header.type = PERF_RECORD_AUX_OUTPUT_HW_ID; - rec.header.misc = 0; - rec.header.size = sizeof(rec); - rec.hw_id = hw_id; - - perf_event_header__init_id(&rec.header, &sample, event); + rec.hw_id = hw_id; + perf_event_header__init(&rec.header, &sample, + PERF_RECORD_AUX_OUTPUT_HW_ID, /* misc= */ 0, + sizeof(rec), event); ret = perf_output_begin(&handle, &sample, event, rec.header.size); if (ret) @@ -13002,6 +12965,7 @@ static void __pmu_detach_event(struct pmu *pmu, struct perf_event *event, exclusive_event_destroy(event); module_put(pmu->module); + mediated_pmu_unaccount_event(event); event->pmu = NULL; /* force fault instead of UAF */ } @@ -13942,7 +13906,7 @@ SYSCALL_DEFINE5(perf_event_open, if (err) return err; - if (!attr.exclude_kernel || + if (!attr.exclude_kernel || attr.text_poke || ((attr.sample_type & PERF_SAMPLE_CALLCHAIN) && !attr.exclude_callchain_kernel)) { err = perf_allow_kernel(); diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 1b1ffe0533e5..13bd42e5493d 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -246,14 +246,13 @@ __perf_output_begin(struct perf_output_handle *handle, handle->size = (1UL << page_shift) - offset; if (unlikely(have_lost)) { - lost_event.header.size = sizeof(lost_event); - lost_event.header.type = PERF_RECORD_LOST; - lost_event.header.misc = 0; lost_event.id = event->id; lost_event.lost = local_xchg(&rb->lost, 0); /* XXX mostly redundant; @data is already fully initializes */ - perf_event_header__init_id(&lost_event.header, data, event); + perf_event_header__init(&lost_event.header, data, + PERF_RECORD_LOST, /* misc= */ 0, + sizeof(lost_event), event); perf_output_put(handle, lost_event); perf_event__output_id_sample(event, handle, data); } diff --git a/kernel/exit.c b/kernel/exit.c index 4e028f157597..282328d2b4cf 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -302,12 +302,13 @@ repeat: free_pids(post.pids); release_thread(p); /* - * This task was already removed from the process/thread/pid lists - * and lock_task_sighand(p) can't succeed. Nobody else can touch - * ->pending or, if group dead, signal->shared_pending. We can call - * flush_sigqueue() lockless. + * This task was already removed from the process/thread/pid lists and + * lock_task_sighand(p) can't succeed. If it's the group leader then + * flush tsk->signal->shared_pending. tsk->pending has been flushed + * already in exit_signals(). Nothing else can touch + * signal->shared_pending anymore, so flush_sigqueue() can be invoked + * lockless. */ - flush_sigqueue(&p->pending); if (thread_group_leader(p)) flush_sigqueue(&p->signal->shared_pending); @@ -550,32 +551,6 @@ void mm_update_next_owner(struct mm_struct *mm) } #endif /* CONFIG_MEMCG */ -#if defined(CONFIG_SCHED_CACHE) && defined(CONFIG_NUMA_BALANCING) -/* - * Subtract the memory footprint of the current task from - * mm. - */ -static void exit_mm_sched_cache(struct mm_struct *mm) -{ - unsigned long fp, sub; - - if (!current->total_numa_faults) - return; - /* - * No lock protection due to performance considerations. - * Make sure mm->sc_stat.footprint does not become - * negative. - */ - fp = READ_ONCE(mm->sc_stat.footprint); - sub = min(fp, current->total_numa_faults); - WRITE_ONCE(mm->sc_stat.footprint, fp - sub); -} -#else -static inline void exit_mm_sched_cache(struct mm_struct *mm) -{ -} -#endif /* CONFIG_SCHED_CACHE CONFIG_NUMA_BALANCING */ - /* * Turn us into a lazy TLB process if we * aren't already.. @@ -588,7 +563,7 @@ static void exit_mm(void) if (!mm) return; - exit_mm_sched_cache(mm); + sched_cache_exit_mm(current); mmap_read_lock(mm); mmgrab_lazy_tlb(mm); diff --git a/kernel/fork.c b/kernel/fork.c index a5934a317634..10f2d05d816a 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1599,6 +1599,7 @@ static int copy_mm(u64 clone_flags, struct task_struct *tsk) tsk->mm = mm; tsk->active_mm = mm; + sched_cache_fork(tsk); return 0; } @@ -1996,9 +1997,9 @@ static bool need_futex_hash_allocate_default(u64 clone_flags) { /* * Allocate a default futex hash for any sibling that will - * share the parent's mm, except vfork. + * share the parent's mm. */ - return (clone_flags & (CLONE_VM | CLONE_VFORK)) == CLONE_VM; + return clone_flags & CLONE_VM; } /* @@ -2602,6 +2603,7 @@ bad_fork_cleanup_io: bad_fork_cleanup_namespaces: exit_nsproxy_namespaces(p); bad_fork_cleanup_mm: + sched_cache_fork_cleanup(p); if (p->mm) { mm_clear_owner(p->mm, p); mmput(p->mm); diff --git a/kernel/futex/core.c b/kernel/futex/core.c index a061f54b606d..095f9fe440e3 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -213,10 +213,12 @@ static bool __futex_pivot_hash(struct mm_struct *mm, struct futex_private_hash * futex_rehash_private(fph, new); } new->state = FR_PERCPU; - scoped_guard(rcu) { - mmph->batches = get_state_synchronize_rcu(); - rcu_assign_pointer(mmph->hash, new); - } + rcu_assign_pointer(mmph->hash, new); + /* + * mmph->batches must reference a grace period which started after + * mmph->hash was assigned. See futex_ref_drop(). + */ + mmph->batches = get_state_synchronize_rcu(); kvfree_rcu(fph, rcu); return true; } diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index 05cba4e16dad..6923f37eaab4 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -150,6 +150,18 @@ config IRQ_KUNIT_TEST If unsure, say N. +config REFCOUNT_INTERRUPT_KUNIT_TEST + tristate "Test refcounted interrupt enable/disable" if !KUNIT_ALL_TESTS + depends on KUNIT + default KUNIT_ALL_TESTS + help + This builds the kunit tests for the refcounted interrupt + infrastructure. It verifies the correctness of single, nested, + and multiple interrupt enable/disable state changes and ensures + that the underlying reference counting mechanisms work as expected. + + If unsure, say N. + endmenu config GENERIC_IRQ_MULTI_HANDLER diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile index 44c4d6fc502a..0e5df962a149 100644 --- a/kernel/irq/Makefile +++ b/kernel/irq/Makefile @@ -16,4 +16,4 @@ obj-$(CONFIG_SMP) += affinity.o obj-$(CONFIG_GENERIC_IRQ_DEBUGFS) += debugfs.o obj-$(CONFIG_GENERIC_IRQ_MATRIX_ALLOCATOR) += matrix.o obj-$(CONFIG_IRQ_KUNIT_TEST) += irq_test.o -obj-$(CONFIG_KUNIT) += refcount_interrupt_test.o +obj-$(CONFIG_REFCOUNT_INTERRUPT_KUNIT_TEST) += refcount_interrupt_test.o diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 6337da5cab9e..e787e4948c8b 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -42,6 +42,7 @@ #include <linux/execmem.h> #include <linux/cleanup.h> #include <linux/wait.h> +#include <linux/wait_bit.h> #include <asm/sections.h> #include <asm/cacheflush.h> @@ -495,14 +496,16 @@ static bool kprobe_queued(struct kprobe *p) static struct kprobe *get_optimized_kprobe(kprobe_opcode_t *addr) { int i; - struct kprobe *p = NULL; + struct kprobe *p; struct optimized_kprobe *op; /* Don't check i == 0, since that is a breakpoint case. */ - for (i = 1; !p && i < MAX_OPTIMIZED_LENGTH / sizeof(kprobe_opcode_t); i++) + for (i = 1; i < MAX_OPTIMIZED_LENGTH / sizeof(kprobe_opcode_t); i++) { p = get_kprobe(addr - i); + /* A disabled probe can have prepared, but inactive, optinsns. */ + if (!p || !kprobe_optready(p) || kprobe_disarmed(p)) + continue; - if (p && kprobe_optready(p)) { op = container_of(p, struct optimized_kprobe, kp); if (arch_within_optimized_kprobe(op, addr)) return p; @@ -526,7 +529,8 @@ enum { OPTIMIZER_ST_FLUSHING = 2, }; -static DECLARE_COMPLETION(optimizer_completion); +/* Bumped at the end of each kprobe_optimizer() pass, under 'kprobe_mutex' */ +static unsigned long optimizer_passes; #define OPTIMIZE_DELAY 5 @@ -654,9 +658,9 @@ static void kprobe_optimizer(void) do_free_cleaned_kprobes(); } - /* Step 5: Kick optimizer again if needed. But if there is a flush requested, */ - if (completion_done(&optimizer_completion)) - complete(&optimizer_completion); + /* Step 5: Wake up flushers, and kick optimizer again if needed. */ + optimizer_passes++; + wake_up_var_locked(&optimizer_passes, &kprobe_mutex); if (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list)) kick_kprobe_optimizer(); /*normal kick*/ @@ -708,7 +712,8 @@ static void wait_for_kprobe_optimizer_locked(void) lockdep_assert_held(&kprobe_mutex); while (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list)) { - init_completion(&optimizer_completion); + unsigned long passes = optimizer_passes; + /* * Set state to OPTIMIZER_ST_FLUSHING and wake up the thread if it's * idle. If it's already kicked, it will see the state change. @@ -717,9 +722,12 @@ static void wait_for_kprobe_optimizer_locked(void) OPTIMIZER_ST_FLUSHING) != OPTIMIZER_ST_FLUSHING) wake_up(&kprobe_optimizer_wait); - mutex_unlock(&kprobe_mutex); - wait_for_completion(&optimizer_completion); - mutex_lock(&kprobe_mutex); + /* + * kprobe_optimizer() holds 'kprobe_mutex' for a whole pass, which + * this drops while sleeping, so a new count means a full pass ran. + */ + wait_var_event_mutex(&optimizer_passes, + optimizer_passes != passes, &kprobe_mutex); } } diff --git a/kernel/module/main.c b/kernel/module/main.c index d0e1e0bd2ad0..c1b34dc1e89a 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -3581,8 +3581,9 @@ static int load_module(struct load_info *info, const char __user *uargs, goto sysfs_cleanup; } - if (codetag_load_module(mod)) - goto sysfs_cleanup; + err = codetag_load_module(mod); + if (err) + goto livepatch_cleanup; /* Get rid of temporary copy. */ free_copy(info, flags); @@ -3592,6 +3593,9 @@ static int load_module(struct load_info *info, const char __user *uargs, return do_init_module(mod); + livepatch_cleanup: + if (is_livepatch_module(mod)) + free_module_elf(mod); sysfs_cleanup: mod_sysfs_teardown(mod); coming_cleanup: diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index d2479c69d71a..c13f68ab7f6e 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -408,9 +408,18 @@ int hibernation_snapshot(int platform_mode) if (error) goto Close; + error = dpm_prepare(PMSG_FREEZE); + if (error) + goto Complete; + + /* Preallocate image memory before freezing kernel threads and shutting down devices. */ + error = hibernate_preallocate_memory(); + if (error) + goto Complete; + error = freeze_kernel_threads(); if (error) - goto Close; + goto Cleanup; if (hibernation_test(TEST_FREEZER)) { @@ -422,15 +431,6 @@ int hibernation_snapshot(int platform_mode) goto Thaw; } - error = dpm_prepare(PMSG_FREEZE); - if (error) - goto Complete; - - /* Preallocate image memory before shutting down devices. */ - error = hibernate_preallocate_memory(); - if (error) - goto Complete; - console_suspend_all(); pm_restrict_gfp_mask(); @@ -464,10 +464,12 @@ int hibernation_snapshot(int platform_mode) platform_end(platform_mode); return error; - Complete: - dpm_complete(PMSG_RECOVER); Thaw: thaw_kernel_threads(); + Cleanup: + swsusp_free(); + Complete: + dpm_complete(PMSG_RECOVER); goto Close; } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 7885ff76e69f..1fe40de6ebe3 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3351,6 +3351,8 @@ void relax_compatible_cpus_allowed_ptr(struct task_struct *p) void set_task_cpu(struct task_struct *p, unsigned int new_cpu) { unsigned int state = READ_ONCE(p->__state); + bool proxy_migrated = sched_proxy_exec() && p->is_blocked && + task_cpu(p) != p->wake_cpu; /* * We should never call set_task_cpu() on a blocked task, @@ -3386,7 +3388,12 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) */ WARN_ON_ONCE(!cpu_online(new_cpu)); - WARN_ON_ONCE(is_migration_disabled(p)); + /* + * Proxy execution can move a blocked task's scheduling context to any + * CPU without moving its migration-disabled execution context. The + * wakeup path will return the task to a CPU where it can execute. + */ + WARN_ON_ONCE(is_migration_disabled(p) && !proxy_migrated); trace_sched_migrate_task(p, new_cpu); @@ -5791,7 +5798,7 @@ void sched_tick(void) curr = rq->curr; donor = rq->donor; - psi_account_irqtime(rq, donor, NULL); + psi_account_irqtime(rq, curr, NULL); update_rq_clock(rq); hw_pressure = arch_scale_hw_pressure(cpu_of(rq)); diff --git a/kernel/sched/ext/cid.c b/kernel/sched/ext/cid.c index bc4eee5bb4cb..4b08866d75f6 100644 --- a/kernel/sched/ext/cid.c +++ b/kernel/sched/ext/cid.c @@ -912,30 +912,36 @@ bool scx_cmask_empty(const struct scx_cmask *m) /** * scx_bpf_cid_topo - Copy out per-cid topology info * @cid: cid to look up - * @out__uninit: where to copy the topology info; fully written by this call + * @out: where to copy the topology info + * @out__sz: size of @out, the program's sizeof(struct scx_cid_topo) * @aux: implicit BPF argument to access bpf_prog_aux hidden from BPF progs * - * Fill @out__uninit with the topology info for @cid. Trigger scx_error() if - * @cid is out of range. If @cid is valid but in the no-topo section, all fields - * are set to -1. All fields are also set to -1 when no cid tables have been - * published yet, which a program may observe while racing the root enable. + * Fill @out with the topology info for @cid. Trigger scx_error() if @cid is out + * of range. If @cid is valid but in the no-topo section, all fields are set to + * -1. All fields are also set to -1 when no cid tables have been published yet, + * which a program may observe while racing the root enable. + * + * The program's struct may be older or newer than the kernel's. The smaller of + * @out__sz and the kernel's size is copied and the rest of @out is set to -1. */ -__bpf_kfunc void scx_bpf_cid_topo(s32 cid, struct scx_cid_topo *out__uninit, +__bpf_kfunc void scx_bpf_cid_topo(s32 cid, struct scx_cid_topo *out, size_t out__sz, const struct bpf_prog_aux *aux) { + size_t len = min(out__sz, sizeof(*out)); struct scx_cid_topo *topo; struct scx_sched *sch; + /* the error cases and fields the kernel lacks read as -1 */ + memset(out, 0xff, out__sz); + guard(rcu)(); sch = scx_prog_sched(aux); topo = rcu_dereference(scx_cid_topo); - if (unlikely(!sch) || !cid_valid(sch, cid) || unlikely(!topo)) { - *out__uninit = SCX_CID_TOPO_NEG; + if (unlikely(!sch) || !cid_valid(sch, cid) || unlikely(!topo)) return; - } - *out__uninit = topo[cid]; + memcpy(out, &topo[cid], len); } __bpf_kfunc_end_defs(); diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c index 51de1d8b72a1..e56c3c95018f 100644 --- a/kernel/sched/ext/ext.c +++ b/kernel/sched/ext/ext.c @@ -447,37 +447,45 @@ static void switch_rq_lock(struct rq *from, struct rq *to) DEFINE_STATIC_KEY_FALSE(__scx_is_cid_type); /** - * scx_call_op_set_cpumask - invoke ops.set_cpumask / ops_cid.set_cmask for @task + * scx_fill_cmask_scratch - Build this cpu's arena cmask from @cpumask + * @sch: scx_sched whose scratch to fill + * @cpumask: cpus to translate into cids + * + * The scratch lives in BPF-writable arena memory and its header can't be + * trusted, so it is rewritten from kernel geometry rather than read. Caller + * must hold an rq lock so this cpu is the sole kernel writer for as long as the + * returned address is in use. + */ +static struct scx_cmask *scx_fill_cmask_scratch(struct scx_sched *sch, + const struct cpumask *cpumask) +{ + struct scx_cmask *kern_va = *this_cpu_ptr(sch->set_cmask_scratch); + struct scx_cmask_ref ref; + + scx_cmask_ref_init_kern(sch, kern_va, 0, num_possible_cpus(), &ref); + scx_cmask_ref_from_cpumask(&ref, cpumask); + return kern_va; +} + +/** + * scx_call_op_set_cpumask - Invoke the set_cpumask or set_cmask op for @task * @sch: scx_sched being invoked * @rq: rq to update as the currently-locked rq, or NULL * @task: task whose affinity is changing * @cpumask: new cpumask * - * For cid-form schedulers, translate @cpumask to a cmask via the per-cpu - * scratch in cid.c and dispatch through the ops_cid union view. Caller - * must hold @rq's rq lock so this_cpu_ptr is stable across the call. + * For cid-form schedulers, translate @cpumask to a cmask in the per-cpu scratch + * and dispatch through the ops_cid union view. Caller must hold @rq's rq lock. */ static inline void scx_call_op_set_cpumask(struct scx_sched *sch, struct rq *rq, struct task_struct *task, const struct cpumask *cpumask) { - if (scx_is_cid_type()) { - struct scx_cmask *kern_va = *this_cpu_ptr(sch->set_cmask_scratch); - struct scx_cmask_ref ref; - - /* - * Build the per-cpu arena cmask from kernel geometry via @ref, - * never reading its BPF-writable header. set_cmask()'s __arena - * argument takes the kernel address and the struct_ops - * trampoline rebases it into BPF's arena pointer form. The rq - * lock makes this cpu the sole kernel writer. - */ - scx_cmask_ref_init_kern(sch, kern_va, 0, num_possible_cpus(), &ref); - scx_cmask_ref_from_cpumask(&ref, cpumask); - SCX_CALL_CID_OP_TASK(sch, set_cmask, rq, task, kern_va); - } else { + if (scx_is_cid_type()) + SCX_CALL_CID_OP_TASK(sch, set_cmask, rq, task, + scx_fill_cmask_scratch(sch, cpumask)); + else SCX_CALL_OP_TASK(sch, set_cpumask, rq, task, cpumask); - } } enum scx_dsq_iter_flags { @@ -1499,27 +1507,22 @@ static inline bool task_scx_migrating(struct task_struct *p) return p->scx.sticky_cpu >= 0; } -/* - * Call ops.dequeue() if the task is in BPF custody and not migrating. - * Clears %SCX_TASK_IN_CUSTODY when the callback is invoked. - */ -static void call_task_dequeue(struct scx_sched *sch, struct rq *rq, - struct task_struct *p, u64 deq_flags) +/* Must be called under the lock serializing @p's custody transfers. */ +static bool task_leave_custody(struct task_struct *p) { if (!(p->scx.flags & SCX_TASK_IN_CUSTODY) || task_scx_migrating(p)) - return; - - if (SCX_HAS_OP(sch, dequeue)) - SCX_CALL_OP_TASK(sch, dequeue, rq, p, deq_flags); + return false; p->scx.flags &= ~SCX_TASK_IN_CUSTODY; + return true; } static void rq_owned_post_enq(struct scx_sched *sch, struct rq *rq, struct scx_dispatch_q *dsq, struct task_struct *p, u64 enq_flags) { - call_task_dequeue(sch, rq, p, 0); + if (task_leave_custody(p) && SCX_HAS_OP(sch, dequeue)) + SCX_CALL_OP_TASK(sch, dequeue, rq, p, 0); /* * Only local inserts get the wakeup treatment below. Rejects kick the @@ -1705,20 +1708,28 @@ static void scx_dispatch_enqueue(struct scx_sched *sch, struct rq *rq, if (is_rq_owned) { rq_owned_post_enq(sch, rq, dsq, p, enq_flags); } else { + bool call_dequeue = false; + /* * Global and bypass DSQs are terminal - the task leaves the - * scheduler's custody, so ops.dequeue() fires here. It can run + * scheduler's custody, so ops.dequeue() fires. It can run * without @p's rq lock (finish_dispatch() passes the dispatch * rq); that's safe because dequeue_task_scx() waits on * SCX_OPSS_DISPATCHING (see the ops_state note above) and so * can't race it. A non-terminal DSQ keeps the task in custody. + * The custody transfer happens under @dsq->lock so that later + * consumers see the flag clear; the callback runs after + * @dsq->lock is dropped because it may lock a DSQ itself. */ if (dsq->id == SCX_DSQ_GLOBAL || dsq->id == SCX_DSQ_BYPASS) - call_task_dequeue(sch, rq, p, 0); + call_dequeue = task_leave_custody(p); else p->scx.flags |= SCX_TASK_IN_CUSTODY; raw_spin_unlock(&dsq->lock); + + if (call_dequeue && SCX_HAS_OP(sch, dequeue)) + SCX_CALL_OP_TASK(sch, dequeue, rq, p, 0); } /* @@ -2141,7 +2152,12 @@ static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int core_enq_ int sticky_cpu = p->scx.sticky_cpu; u64 enq_flags = core_enq_flags | rq->scx.remote_activate_enq_flags; - if (enq_flags & ENQUEUE_WAKEUP) + /* + * SCX_RQ_IN_WAKEUP promises a task_woken_scx() call once this enqueue + * returns. Only the core's wakeup path delivers one. The flags stashed + * for a remote activation may carry the wakeup bit without it. + */ + if (core_enq_flags & ENQUEUE_WAKEUP) rq->scx.flags |= SCX_RQ_IN_WAKEUP; /* @@ -2210,7 +2226,7 @@ retry: /* * A queued task must always be in BPF scheduler's custody. If * SCX_TASK_IN_CUSTODY is clear, finish_dispatch() on another - * CPU has already passed call_task_dequeue() (which clears the + * CPU has already passed task_leave_custody() (which clears the * flag), but has not yet written SCX_OPSS_NONE. That final * store does not require this rq's lock, so retrying with * cpu_relax() is bounded: we will observe NONE (or DISPATCHING, @@ -2258,7 +2274,8 @@ retry: * NONE but the task may still have %SCX_TASK_IN_CUSTODY set until * it is enqueued on the destination. */ - call_task_dequeue(sch, rq, p, deq_flags); + if (task_leave_custody(p) && SCX_HAS_OP(sch, dequeue)) + SCX_CALL_OP_TASK(sch, dequeue, rq, p, deq_flags); } static bool dequeue_task_scx(struct rq *rq, struct task_struct *p, int core_deq_flags) @@ -2374,14 +2391,10 @@ static void wakeup_preempt_scx(struct rq *rq, struct task_struct *p, int wake_fl } void scx_move_local_task_to_local_dsq(struct scx_sched *sch, struct task_struct *p, - u64 enq_flags, struct scx_dispatch_q *src_dsq, - struct rq *dst_rq) + u64 enq_flags, struct rq *dst_rq) { struct scx_dispatch_q *dst_dsq = scx_resolve_local_dsq(sch, dst_rq, p, &enq_flags); - /* @p is on @dst_rq, an rq-owned @src_dsq is covered by the rq lock */ - if (!dsq_is_rq_owned(src_dsq)) - lockdep_assert_held(&src_dsq->lock); lockdep_assert_rq_held(dst_rq); WARN_ON_ONCE(p->scx.holding_cpu >= 0); @@ -2629,8 +2642,8 @@ static struct rq *move_task_between_dsqs(struct scx_sched *sch, /* @p is going from a non-local DSQ to a local DSQ */ if (src_rq == dst_rq) { scx_task_unlink_from_dsq(p, src_dsq); - scx_move_local_task_to_local_dsq(sch, p, enq_flags, src_dsq, dst_rq); raw_spin_unlock(&src_dsq->lock); + scx_move_local_task_to_local_dsq(sch, p, enq_flags, dst_rq); } else { raw_spin_unlock(&src_dsq->lock); move_remote_task_to_local_dsq(sch, p, enq_flags, src_rq, dst_rq); @@ -2680,8 +2693,8 @@ retry: if (rq == task_rq) { scx_task_unlink_from_dsq(p, dsq); - scx_move_local_task_to_local_dsq(sch, p, enq_flags, dsq, rq); raw_spin_unlock(&dsq->lock); + scx_move_local_task_to_local_dsq(sch, p, enq_flags, rq); return true; } @@ -2919,7 +2932,7 @@ static inline void maybe_queue_balance_callback(struct rq *rq) static enum scx_dsp_verdict dispatch_one(struct rq *rq, struct task_struct *prev) { - struct scx_sched *sch = scx_root_protected_live(); + struct scx_sched *root_sch = scx_root_protected_live(); enum scx_dsp_verdict verdict; s32 cpu = cpu_of(rq); @@ -2928,7 +2941,7 @@ static enum scx_dsp_verdict dispatch_one(struct rq *rq, struct task_struct *prev scx_process_sync_ecaps(rq, prev); - if ((sch->ops.flags & SCX_OPS_HAS_CPU_PREEMPT) && + if ((root_sch->ops.flags & SCX_OPS_HAS_CPU_PREEMPT) && unlikely(rq->scx.cpu_released)) { /* * If the previous sched_class for the current CPU was not SCX, @@ -2936,8 +2949,8 @@ static enum scx_dsp_verdict dispatch_one(struct rq *rq, struct task_struct *prev * core. This callback complements ->cpu_release(), which is * emitted in switch_class(). */ - if (sch->ops.cpu_acquire) - SCX_CALL_OP(sch, cpu_acquire, rq, cpu, NULL); + if (root_sch->ops.cpu_acquire) + SCX_CALL_OP(root_sch, cpu_acquire, rq, cpu, NULL); rq->scx.cpu_released = false; } @@ -2955,7 +2968,7 @@ static enum scx_dsp_verdict dispatch_one(struct rq *rq, struct task_struct *prev * test. */ if ((prev->scx.flags & SCX_TASK_QUEUED) && prev->scx.slice && - !scx_bypassing(sch, cpu)) { + !scx_bypassing(scx_task_sched(prev), cpu)) { verdict = SCX_DSP_PREV; goto has_tasks; } @@ -2967,20 +2980,25 @@ static enum scx_dsp_verdict dispatch_one(struct rq *rq, struct task_struct *prev goto has_tasks; } - verdict = scx_dispatch_sched(sch, rq, prev, false); + verdict = scx_dispatch_sched(root_sch, rq, prev, false); if (verdict != SCX_DSP_NONE) goto has_tasks; /* - * Didn't find another task to run. Keep running @prev unless - * %SCX_OPS_ENQ_LAST is in effect. + * Didn't find another task to run. Keep running @prev unless its own + * scheduler set %SCX_OPS_ENQ_LAST and takes the enqueue instead, see + * put_prev_task_scx(). Read the scheduler here as the dispatch above + * may have dropped the rq lock while @prev changed class or scheduler. */ - if ((prev->scx.flags & SCX_TASK_QUEUED) && - (!(sch->ops.flags & SCX_OPS_ENQ_LAST) || scx_bypassing(sch, cpu)) && - scx_task_can_stay_on_cpu(rq, prev)) { - __scx_add_event(sch, SCX_EV_DISPATCH_KEEP_LAST, 1); - verdict = SCX_DSP_PREV; - goto has_tasks; + if (prev->scx.flags & SCX_TASK_QUEUED) { + struct scx_sched *prev_sch = scx_task_sched(prev); + + if ((!(prev_sch->ops.flags & SCX_OPS_ENQ_LAST) || + scx_bypassing(prev_sch, cpu)) && scx_task_can_stay_on_cpu(rq, prev)) { + __scx_add_event(prev_sch, SCX_EV_DISPATCH_KEEP_LAST, 1); + verdict = SCX_DSP_PREV; + goto has_tasks; + } } rq->scx.flags &= ~SCX_RQ_IN_DISPATCH; return SCX_DSP_NONE; @@ -3624,8 +3642,12 @@ static void set_cpus_allowed_scx(struct task_struct *p, * * Fine-grained memory write control is enforced by BPF making the const * designation pointless. Cast it away when calling the operation. + * + * The cid form receives the initial mask when the task is enabled and + * hears about changes only afterwards, see struct scx_enable_args. */ - if (SCX_HAS_OP(sch, set_cpumask)) + if (SCX_HAS_OP(sch, set_cpumask) && + (!scx_is_cid_type() || scx_get_task_state(p) == SCX_TASK_ENABLED)) scx_call_op_set_cpumask(sch, task_rq(p), p, (struct cpumask *)p->cpus_ptr); } @@ -3665,8 +3687,20 @@ static void handle_hotplug(struct rq *rq, bool online) s16 *tbl = rcu_dereference_check(scx_cpu_to_cid_tbl, lockdep_is_cpus_held()); - if (tbl) + if (tbl) { + struct scx_sched *pos; + cpu_or_cid = tbl[cpu]; + + guard(raw_spinlock_irqsave)(&scx_sched_lock); + list_for_each_entry(pos, &scx_sched_all, all) { + struct scx_cmask *mask = pos->online_cmask; + + if (mask) + __assign_bit(cpu_or_cid, (unsigned long *)mask->bits, + online); + } + } } if (online && SCX_HAS_OP(sch, cpu_online)) @@ -3922,8 +3956,27 @@ static void __scx_enable_task(struct scx_sched *sch, struct task_struct *p) p->scx.weight = sched_weight_to_cgroup(weight); - if (SCX_HAS_OP(sch, enable)) - SCX_CALL_OP_TASK(sch, enable, rq, p); + if (SCX_HAS_OP(sch, enable)) { + if (scx_is_cid_type()) { + struct scx_cmask *cmask = scx_fill_cmask_scratch(sch, p->cpus_ptr); + struct scx_enable_args args = { + .cmask_arena_addr = scx_kaddr_to_arena(sch, cmask), + }; + + SCX_CALL_CID_OP_TASK(sch, enable, rq, p, &args); + } else { + SCX_CALL_OP_TASK(sch, enable, rq, p); + } + } + + /* + * The initial mask also goes out through set_cmask() so a scheduler can + * track affinity there alone, and before set_weight() so that the mask + * is in place when weight-dependent state is derived, see struct + * scx_enable_args. + */ + if (scx_is_cid_type() && SCX_HAS_OP(sch, set_cpumask)) + scx_call_op_set_cpumask(sch, rq, p, p->cpus_ptr); if (SCX_HAS_OP(sch, set_weight)) SCX_CALL_OP_TASK(sch, set_weight, rq, p, p->scx.weight); @@ -4266,9 +4319,10 @@ static void switching_to_scx(struct rq *rq, struct task_struct *p) /* * set_cpus_allowed_scx() is not called while @p is associated with a - * different scheduler class. Keep the BPF scheduler up-to-date. + * different scheduler class. Keep the BPF scheduler up-to-date. The cid + * form gets its mask from scx_enable_task(). */ - if (SCX_HAS_OP(sch, set_cpumask)) + if (!scx_is_cid_type() && SCX_HAS_OP(sch, set_cpumask)) scx_call_op_set_cpumask(sch, rq, p, (struct cpumask *)p->cpus_ptr); } @@ -4387,6 +4441,17 @@ static bool local_task_should_reenq(struct rq *rq, struct task_struct *p, return *reenq_flags & SCX_REENQ_ANY; } +/* + * The dispatcher stores the final ops_state after dropping the DSQ lock, so @p + * can be found on a DSQ while still %SCX_OPSS_DISPATCHING. Reenqueueing @p + * before that store lands would have it clobber the new %SCX_OPSS_QUEUED. + */ +void scx_reenq_wait_dispatching(struct task_struct *p) +{ + if (unlikely(atomic_long_read_acquire(&p->scx.ops_state) == SCX_OPSS_DISPATCHING)) + wait_ops_state(p, SCX_OPSS_DISPATCHING); +} + static u32 reenq_local(struct scx_sched *sch, struct rq *rq, u64 reenq_flags) { LIST_HEAD(tasks); @@ -4430,6 +4495,7 @@ static u32 reenq_local(struct scx_sched *sch, struct rq *rq, u64 reenq_flags) if (!local_task_should_reenq(rq, p, &reenq_flags, &reason)) continue; + scx_reenq_wait_dispatching(p); scx_dispatch_dequeue(rq, p); if (WARN_ON_ONCE(p->scx.flags & SCX_TASK_REENQ_REASON_MASK)) @@ -4553,6 +4619,7 @@ static void reenq_user(struct rq *rq, struct scx_dispatch_q *dsq, u64 reenq_flag } /* @p is on @dsq, its rq and @dsq are locked */ + scx_reenq_wait_dispatching(p); dispatch_dequeue_locked(p, dsq); raw_spin_unlock(&dsq->lock); @@ -4766,7 +4833,8 @@ int scx_tg_online(struct task_group *tg) { .weight = tg->scx.weight, .bw_period_us = tg->scx.bw_period_us, .bw_quota_us = tg->scx.bw_quota_us, - .bw_burst_us = tg->scx.bw_burst_us }; + .bw_burst_us = tg->scx.bw_burst_us, + .sched_idle = tg->scx.idle }; ret = SCX_CALL_OP_RET(sch, cgroup_init, NULL, tg->css.cgroup, &args); @@ -4932,7 +5000,8 @@ void scx_group_set_idle(struct task_group *tg, bool idle) percpu_down_read(&scx_cgroup_ops_rwsem); sch = scx_tg_knob_sched(tg); - if (scx_cgroup_enabled && sch && SCX_HAS_OP(sch, cgroup_set_idle)) + if (scx_cgroup_enabled && sch && SCX_HAS_OP(sch, cgroup_set_idle) && + tg->scx.idle != idle) SCX_CALL_OP(sch, cgroup_set_idle, NULL, tg_cgrp(tg), idle); /* Update the task group's idle state */ @@ -5187,6 +5256,7 @@ static int scx_cgroup_init(struct scx_sched *sch) .bw_period_us = tg->scx.bw_period_us, .bw_quota_us = tg->scx.bw_quota_us, .bw_burst_us = tg->scx.bw_burst_us, + .sched_idle = tg->scx.idle, }; ret = SCX_CALL_OP_RET(sch, cgroup_init, NULL, css->cgroup, &args); @@ -5272,12 +5342,17 @@ static void free_exit_info(struct scx_exit_info *ei); static const char *scx_exit_reason(enum scx_exit_kind kind); static bool scx_claim_exit(struct scx_sched *sch, enum scx_exit_kind kind); -s32 scx_set_cmask_scratch_alloc(struct scx_sched *sch) +s32 scx_alloc_kern_arena_objs(struct scx_sched *sch) { size_t size = struct_size_t(struct scx_cmask, bits, SCX_CMASK_NR_WORDS(num_possible_cpus())); + struct scx_cmask *online; + struct scx_cmask_ref ref; int cpu; + /* hotplug stays excluded until the online mask is published */ + lockdep_assert_cpus_held(); + if (!sch->is_cid_type || !sch->arena_pool) return 0; @@ -5293,15 +5368,28 @@ s32 scx_set_cmask_scratch_alloc(struct scx_sched *sch) return -ENOMEM; scx_cmask_init(*slot, 0, num_possible_cpus()); } + + /* pack the online mask alongside the scratch masks */ + online = scx_arena_alloc(sch, size); + if (!online) + return -ENOMEM; + + scoped_guard(rcu) { + scx_cmask_ref_init_kern(sch, online, 0, num_possible_cpus(), &ref); + scx_cmask_ref_from_cpumask(&ref, cpu_active_mask); + } + sch->online_cmask = online; + return 0; } -static void scx_set_cmask_scratch_free(struct scx_sched *sch) +static void scx_free_kern_arena_objs(struct scx_sched *sch) { size_t size = struct_size_t(struct scx_cmask, bits, SCX_CMASK_NR_WORDS(num_possible_cpus())); int cpu; + scx_arena_free(sch, sch->online_cmask, size); if (!sch->set_cmask_scratch) return; @@ -5388,7 +5476,7 @@ static void scx_sched_free_rcu_work(struct work_struct *work) rhashtable_free_and_destroy(&sch->dsq_hash, NULL, NULL); free_exit_info(sch->exit_info); - scx_set_cmask_scratch_free(sch); + scx_free_kern_arena_objs(sch); scx_arena_pool_destroy(sch); if (sch->arena_map) bpf_map_put(sch->arena_map); @@ -7508,22 +7596,24 @@ static void scx_root_enable_workfn(struct kthread_work *work) #ifdef CONFIG_EXT_SUB_SCHED cgroup_get(cgrp); #endif + /* + * Transition to ENABLING to arm the disable path. Allocation failure + * still unwinds locally. Full disabling on failure applies only after + * scx_alloc_and_add_sched() succeeds. + */ + WARN_ON_ONCE(scx_set_enable_state(SCX_ENABLING) != SCX_DISABLED); + WARN_ON_ONCE(scx_root); + sch = scx_alloc_and_add_sched(cmd, cgrp, NULL); if (IS_ERR(sch)) { ret = PTR_ERR(sch); + WARN_ON_ONCE(scx_set_enable_state(SCX_DISABLED) != SCX_ENABLING); goto err_free_tid_hash; } if (sch->is_cid_type) static_branch_enable(&__scx_is_cid_type); - /* - * Transition to ENABLING and clear exit info to arm the disable path. - * Failure triggers full disabling from here on. - */ - WARN_ON_ONCE(scx_set_enable_state(SCX_ENABLING) != SCX_DISABLED); - WARN_ON_ONCE(scx_root); - atomic_long_set(&scx_nr_rejected, 0); for_each_possible_cpu(cpu) { @@ -7591,7 +7681,7 @@ static void scx_root_enable_workfn(struct kthread_work *work) goto err_disable; } - ret = scx_set_cmask_scratch_alloc(sch); + ret = scx_alloc_kern_arena_objs(sch); if (ret) { cpus_read_unlock(); goto err_disable; @@ -8316,10 +8406,11 @@ static struct bpf_struct_ops bpf_sched_ext_ops = { /* * cid-form cfi stubs. Stubs whose signatures match the cpu-form (param types * identical, only param names differ across structs) are reused. Some need - * fresh stubs, set_cmask due to an argument type difference and the sub-sched - * notifiers because no cpu-form stub exists to reuse. + * fresh stubs, set_cmask and enable due to argument differences and the + * sub-sched notifiers because no cpu-form stub exists to reuse. */ static void sched_ext_ops_cid__set_cmask(struct task_struct *p, const struct scx_cmask *cmask__arena) {} +static void sched_ext_ops_cid__enable(struct task_struct *p, struct scx_enable_args *args) {} static void sched_ext_ops__sub_caps_updated(const struct scx_cmask *cmask__arena, u64 caps) {} static void sched_ext_ops__sub_ecaps_updated(s32 cid, u64 before, u64 after) {} @@ -8340,7 +8431,7 @@ static struct sched_ext_ops_cid __bpf_ops_sched_ext_ops_cid = { .update_idle = sched_ext_ops__update_idle, .init_task = sched_ext_ops__init_task, .exit_task = sched_ext_ops__exit_task, - .enable = sched_ext_ops__enable, + .enable = sched_ext_ops_cid__enable, .disable = sched_ext_ops__disable, #ifdef CONFIG_EXT_GROUP_SCHED .cpuctl_init = sched_ext_ops__cgroup_init, @@ -8946,10 +9037,17 @@ __bpf_kfunc void scx_bpf_dsq_insert_vtime(struct task_struct *p, u64 dsq_id, #ifdef CONFIG_EXT_SUB_SCHED /* * Disallow if any sub-scheds are attached. There is no way to tell - * which scheduler called us, just error out @p's scheduler. + * which scheduler called us, so error out @p's scheduler -- read it + * under RCU as @p's locks aren't necessarily held here. @p may be a + * task past sched_ext_dead() or an idle task, in which case its + * scheduler can't be determined and there is nothing obviously wrong + * to report; just refuse the call. */ if (unlikely(!list_empty(&sch->children))) { - scx_error(scx_task_sched(p), "__scx_bpf_dsq_insert_vtime() must be used"); + struct scx_sched *tsch = scx_task_sched_rcu(p); + + if (tsch) + scx_error(tsch, "__scx_bpf_dsq_insert_vtime() must be used"); return; } #endif @@ -10321,7 +10419,8 @@ __bpf_kfunc u32 scx_bpf_nr_cids(void) * hotplug, which lets schedulers treat [0, nr_online_cids) as the online * range. Schedulers that prefer to handle hotplug without a restart should * install a custom mapping via scx_bpf_cid_override() and track onlining - * through the ops.cid_online / ops.cid_offline callbacks. + * through the ops.cid_online / ops.cid_offline callbacks, starting from the + * mask scx_bpf_online_cmask() returns. */ __bpf_kfunc u32 scx_bpf_nr_online_cids(void) { @@ -10329,6 +10428,36 @@ __bpf_kfunc u32 scx_bpf_nr_online_cids(void) } /** + * scx_bpf_online_cmask - Return the online cid mask in the scheduler arena + * @aux: implicit BPF argument to access bpf_prog_aux hidden from BPF progs + * + * Return a kernel-maintained cmask covering [0, scx_bpf_nr_cids()), or NULL if + * the calling program is not associated with a live cid-form scheduler or the + * mask is not allocated yet, as in ops.init_cids(). Treat the mask as read-only + * even though arena memory stays writable by the BPF scheduler. The mask + * follows the SCX hotplug notifications: a cid's bit is updated before + * ops.cid_online/offline() runs for it. The pointer is valid from ops.init() + * through ops.exit(). Root ops.init() runs with hotplug excluded. Other + * contexts can observe concurrent updates. + */ +__bpf_kfunc const void *scx_bpf_online_cmask(const struct bpf_prog_aux *aux) +{ + struct scx_sched *sch; + struct scx_cmask *online; + + guard(rcu)(); + + sch = scx_prog_sched(aux); + if (unlikely(!sch)) + return NULL; + online = sch->online_cmask; + if (unlikely(!online)) + return NULL; + + return (void *)scx_kaddr_to_arena(sch, online); +} + +/** * scx_bpf_this_cid - Return the cid of the CPU this program is running on * * cid-addressed equivalent of bpf_get_smp_processor_id() for scx programs. @@ -10691,6 +10820,7 @@ BTF_ID_FLAGS(func, scx_bpf_nr_node_ids) BTF_ID_FLAGS(func, scx_bpf_nr_cpu_ids) BTF_ID_FLAGS(func, scx_bpf_nr_cids) BTF_ID_FLAGS(func, scx_bpf_nr_online_cids) +BTF_ID_FLAGS(func, scx_bpf_online_cmask, KF_IMPLICIT_ARGS | KF_ARENA_RET) BTF_ID_FLAGS(func, scx_bpf_this_cid) BTF_ID_FLAGS(func, scx_bpf_get_possible_cpumask, KF_ACQUIRE) BTF_ID_FLAGS(func, scx_bpf_get_online_cpumask, KF_ACQUIRE) diff --git a/kernel/sched/ext/idle.c b/kernel/sched/ext/idle.c index d2973fb3af6d..aa9fb6de0ad6 100644 --- a/kernel/sched/ext/idle.c +++ b/kernel/sched/ext/idle.c @@ -1142,10 +1142,17 @@ __bpf_kfunc s32 scx_bpf_select_cpu_and(struct task_struct *p, s32 prev_cpu, u64 #ifdef CONFIG_EXT_SUB_SCHED /* * Disallow if any sub-scheds are attached. There is no way to tell - * which scheduler called us, just error out @p's scheduler. + * which scheduler called us, so error out @p's scheduler -- read it + * under RCU as @p's locks aren't necessarily held here. @p may be a + * task past sched_ext_dead() or an idle task, in which case its + * scheduler can't be determined and there is nothing obviously wrong + * to report; just refuse the call. */ if (unlikely(!list_empty(&sch->children))) { - scx_error(scx_task_sched(p), "__scx_bpf_select_cpu_and() must be used"); + struct scx_sched *tsch = scx_task_sched_rcu(p); + + if (tsch) + scx_error(tsch, "__scx_bpf_select_cpu_and() must be used"); return -EINVAL; } #endif diff --git a/kernel/sched/ext/inlines.h b/kernel/sched/ext/inlines.h index ed423bcc26b8..2ff5479334cb 100644 --- a/kernel/sched/ext/inlines.h +++ b/kernel/sched/ext/inlines.h @@ -129,8 +129,10 @@ scx_dispatch_sched(struct scx_sched *sch, struct rq *rq, * scheduler's ops.dispatch() doesn't yield any tasks. */ if (scx_bypass_dsp_enabled(sch) && - scx_consume_dispatch_q(sch, rq, scx_bypass_dsq(sch, cpu), 0)) + scx_consume_dispatch_q(sch, rq, scx_bypass_dsq(sch, cpu), 0)) { + __scx_add_event(sch, SCX_EV_SUB_BYPASS_DISPATCH, 1); return SCX_DSP_LOCAL; + } return SCX_DSP_NONE; } diff --git a/kernel/sched/ext/internal.h b/kernel/sched/ext/internal.h index 0967b99a4948..1df8f583b0ec 100644 --- a/kernel/sched/ext/internal.h +++ b/kernel/sched/ext/internal.h @@ -250,6 +250,31 @@ struct scx_exit_task_args { bool cancelled; }; +/** + * struct scx_enable_args - Argument container for cid-form ops.enable() + * @cmask_arena_addr: BPF arena address of the cmask of cids the task may run on + * + * @cmask_arena_addr is the task's affinity as it enters the scheduler. + * set_cmask() delivers the same mask right after enable(), before set_weight() + * and the first enqueue, then every affinity change afterwards, and is never + * called before enable(). A scheduler may therefore track affinity in + * set_cmask() alone. + * + * The kernel builds the mask in the scheduler arena from its own geometry, so + * the header is valid regardless of what the scheduler last wrote there. The + * memory is per-cpu scratch reused once the callback returns: copy the bits + * out, don't keep the address. The set_cmask() argument follows the same rules. + * + * The address is a plain value rather than a typed pointer because BTF can't + * mark a struct member as an arena pointer yet and a pointer member would reach + * the program typed as a kernel pointer. Cast it to struct scx_cmask __arena * + * before use. Once arena members can be typed, a typed alias will join this + * field in an anonymous union at the same offset. + */ +struct scx_enable_args { + u64 cmask_arena_addr; +}; + /* argument container for ops.cgroup_init() */ struct scx_cgroup_init_args { /* the weight of the cgroup [1..10000] */ @@ -259,6 +284,9 @@ struct scx_cgroup_init_args { u64 bw_period_us; u64 bw_quota_us; u64 bw_burst_us; + + /* whether the cgroup is configured SCHED_IDLE via cpu.idle */ + bool sched_idle; }; enum scx_cpu_preempt_reason { @@ -569,6 +597,12 @@ struct sched_ext_ops { * * Specify the %SCX_OPS_KEEP_BUILTIN_IDLE flag to keep the built-in idle * tracking. + * + * Only actual transitions are reported. A CPU that is claimed with an + * idle pick and kicked but dispatches no task returns to idle without a + * transition. A scheduler tracking idle CPUs itself must restore the + * idle state from ops.dispatch() when it returns without the next task + * to run. */ void (*update_idle)(s32 cpu, bool idle); @@ -1028,6 +1062,7 @@ struct sched_ext_ops { * - dispatch -> dispatch (cpu arg is now cid) * - update_idle -> update_idle (cpu arg is now cid) * - set_cpumask -> set_cmask (cmask instead of cpumask) + * - enable -> enable (takes struct scx_enable_args) * - cpu_online -> cid_online * - cpu_offline -> cid_offline * - dump_cpu -> dump_cid @@ -1061,7 +1096,7 @@ struct sched_ext_ops_cid { struct scx_init_task_args *args); void (*exit_task)(struct task_struct *p, struct scx_exit_task_args *args); - void (*enable)(struct task_struct *p); + void (*enable)(struct task_struct *p, struct scx_enable_args *args); void (*disable)(struct task_struct *p); void (*dump)(struct scx_dump_ctx *ctx); void (*dump_cid)(struct scx_dump_ctx *ctx, s32 cid, bool idle); @@ -1524,7 +1559,8 @@ struct scx_sched { * by BUILD_BUG_ON in scx_init()). The anonymous union lets the kernel * access either view of the same storage without function-pointer * casts: use .ops for cpu-form and shared fields, .ops_cid for the - * cid-renamed callbacks (set_cmask, select_cid, cid_online, ...). + * callbacks whose cid-form signature differs (set_cmask, enable, + * select_cid, cid_online, ...). */ union { struct sched_ext_ops ops; @@ -1547,11 +1583,12 @@ struct scx_sched { uintptr_t arena_kern_base; /* - * Per-CPU arena cmask used by scx_call_op_set_cpumask() to hand a cmask - * to ops_cid.set_cmask(). The kernel writes through the stored kern_va - * and passes it to the callback's __arena argument. + * Per-CPU arena cmask the kernel fills from a task's cpumask and hands + * to ops_cid.enable() and ops_cid.set_cmask(). The stored pointers are + * the kernel addresses. */ struct scx_cmask * __percpu *set_cmask_scratch; + struct scx_cmask *online_cmask; DECLARE_BITMAP(has_op, SCX_OPI_END); @@ -1659,6 +1696,19 @@ static inline void *scx_arena_to_kaddr(struct scx_sched *sch, const void *bpf_pt return (void *)(sch->arena_kern_base + (u32)(uintptr_t)bpf_ptr); } +/** + * scx_kaddr_to_arena - Translate a kernel arena address to the BPF form + * @sch: scheduler whose arena hosts @kaddr + * @kaddr: kernel address inside @sch's arena + * + * __arena callback arguments need no translation. Addresses handed to BPF any + * other way, such as struct fields and kfunc return values, go through this. + */ +static inline uintptr_t scx_kaddr_to_arena(struct scx_sched *sch, const void *kaddr) +{ + return (uintptr_t)kaddr - sch->arena_kern_base; +} + enum scx_wake_flags { /* expose select WF_* flags as enums */ SCX_WAKE_FORK = WF_FORK, @@ -2055,8 +2105,7 @@ void scx_dispatch_dequeue(struct rq *rq, struct task_struct *p); void scx_do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags, int sticky_cpu); void scx_move_local_task_to_local_dsq(struct scx_sched *sch, struct task_struct *p, - u64 enq_flags, struct scx_dispatch_q *src_dsq, - struct rq *dst_rq); + u64 enq_flags, struct rq *dst_rq); bool scx_consume_dispatch_q(struct scx_sched *sch, struct rq *rq, struct scx_dispatch_q *dsq, u64 enq_flags); bool scx_consume_global_dsq(struct scx_sched *sch, struct rq *rq); @@ -2068,6 +2117,7 @@ void scx_kick_cpu(struct scx_sched *sch, s32 cpu, u64 flags); u64 __scx_bpf_now(struct rq *rq); void schedule_dsq_reenq(struct scx_sched *sch, struct scx_dispatch_q *dsq, u64 reenq_flags, struct rq *locked_rq); +void scx_reenq_wait_dispatching(struct task_struct *p); int __scx_init_task(struct scx_sched *sch, struct task_struct *p, struct cgroup *cgrp, bool fork); void scx_enable_task(struct scx_sched *sch, struct task_struct *p); @@ -2078,7 +2128,7 @@ void scx_disable_and_exit_task(struct scx_sched *sch, struct task_struct *p); void scx_cgroup_lock(void); void scx_cgroup_unlock(void); #endif -s32 scx_set_cmask_scratch_alloc(struct scx_sched *sch); +s32 scx_alloc_kern_arena_objs(struct scx_sched *sch); void scx_disable_bypass_dsp(struct scx_sched *sch); void scx_bypass(struct scx_sched *sch, bool bypass); s32 scx_link_sched(struct scx_sched *sch); @@ -2292,9 +2342,9 @@ do { \ } while (0) /* - * Dispatch a task op through the cid-form ops_cid table. Only set_cmask() needs - * this: it takes an arena cmask address instead of a cpumask, so it cannot be - * invoked via its cpu-form set_cpumask() slot. + * Dispatch a task op through the cid-form ops_cid table, for the ops whose + * cid-form signature differs from the cpu-form slot: set_cmask() takes an arena + * cmask instead of a cpumask and enable() takes scx_enable_args. */ #define SCX_CALL_CID_OP_TASK(sch, op, locked_rq, task, args...) \ __SCX_CALL_OP_TASK(sch, ops_cid, op, locked_rq, task, ##args) diff --git a/kernel/sched/ext/sub.c b/kernel/sched/ext/sub.c index 9e7040482bde..0472eaf41c7c 100644 --- a/kernel/sched/ext/sub.c +++ b/kernel/sched/ext/sub.c @@ -555,8 +555,8 @@ static void scx_rescue_timerfn(struct timer_list *timer) scx.dsq_list.node); scx_task_unlink_from_dsq(p, &rq->scx.rescue.dsq); scx_rescue_admit(rq, p, slice); - scx_move_local_task_to_local_dsq(scx_task_sched(p), p, SCX_ENQ_IGNORE_CAPS, - &rq->scx.rescue.dsq, rq); + scx_move_local_task_to_local_dsq(scx_task_sched(p), p, + SCX_ENQ_IGNORE_CAPS, rq); if (sched_class_above(&ext_sched_class, rq->curr->sched_class)) resched_curr(rq); } else if (p->scx.dsq && rq->scx.rescue.budget > 2 * scx_rescue_quantum_ns) { @@ -572,7 +572,7 @@ static void scx_rescue_timerfn(struct timer_list *timer) scx_task_unlink_from_dsq(p, &rq->scx.local_dsq); scx_move_local_task_to_local_dsq(scx_task_sched(p), p, SCX_ENQ_HEAD | SCX_ENQ_PREEMPT | SCX_ENQ_IGNORE_CAPS, - &rq->scx.local_dsq, rq); + rq); } out_arm: scx_rescue_timer_arm(rq); @@ -596,8 +596,8 @@ void scx_rescue_flush(struct rq *rq) /* and flush out all pending ones */ list_for_each_entry_safe(p, n, &rq->scx.rescue.dsq.list, scx.dsq_list.node) { scx_task_unlink_from_dsq(p, &rq->scx.rescue.dsq); - scx_move_local_task_to_local_dsq(scx_task_sched(p), p, SCX_ENQ_IGNORE_CAPS, - &rq->scx.rescue.dsq, rq); + scx_move_local_task_to_local_dsq(scx_task_sched(p), p, + SCX_ENQ_IGNORE_CAPS, rq); } timer_delete(&rq->scx.rescue.timer); @@ -801,6 +801,7 @@ void scx_reenq_reject(struct rq *rq) if (WARN_ON_ONCE(p->migration_pending)) continue; + scx_reenq_wait_dispatching(p); scx_dispatch_dequeue(rq, p); if (WARN_ON_ONCE(p->scx.flags & SCX_TASK_REENQ_REASON_MASK)) @@ -1361,6 +1362,7 @@ static s32 scx_cgroup_claim_subtree(struct scx_sched *sch) .bw_period_us = tg->scx.bw_period_us, .bw_quota_us = tg->scx.bw_quota_us, .bw_burst_us = tg->scx.bw_burst_us, + .sched_idle = tg->scx.idle, }; if (tg->scx.sched != parent || @@ -1464,6 +1466,7 @@ static void scx_cgroup_return_subtree(struct scx_sched *sch) .bw_period_us = tg->scx.bw_period_us, .bw_quota_us = tg->scx.bw_quota_us, .bw_burst_us = tg->scx.bw_burst_us, + .sched_idle = tg->scx.idle, }; /* the first pass must have transferred everything */ @@ -1803,6 +1806,12 @@ void scx_sub_enable_workfn(struct kthread_work *work) goto err_disable; } + scoped_guard(cpus_read_lock) { + ret = scx_alloc_kern_arena_objs(sch); + if (ret) + goto err_disable; + } + if (sch->ops.init) { ret = SCX_CALL_OP_RET(sch, init, NULL); if (ret) { @@ -1813,10 +1822,6 @@ void scx_sub_enable_workfn(struct kthread_work *work) sch->exit_info->flags |= SCX_EFLAG_INITIALIZED; } - ret = scx_set_cmask_scratch_alloc(sch); - if (ret) - goto err_disable; - struct scx_sub_attach_args sub_attach_args = { .ops = &sch->ops, .cgroup_path = sch->cgrp_path, diff --git a/kernel/sched/ext/types.h b/kernel/sched/ext/types.h index 943d8d429a2c..139176cf9fc6 100644 --- a/kernel/sched/ext/types.h +++ b/kernel/sched/ext/types.h @@ -70,6 +70,10 @@ enum scx_consts { * smaller shards if the LLC exceeds the target size. No-topo cids are packed * into their own max-sized shards. * + * New fields are appended, never inserted: scx_bpf_cid_topo() copies this + * struct out sized by the program's own layout, and an older program's copy + * must stay a prefix of the kernel's. + * * @core_cid: first cid of this cid's core (smt-sibling group) * @core_idx: global index of that core, in [0, nr_cores_at_init) * @llc_cid: first cid of this cid's LLC diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 7455a83a6a99..57360f5cdde4 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1478,7 +1478,7 @@ static inline int get_sched_cache_scale(int mul) return (1 + (tol - 1) * mul); } -static bool exceed_llc_capacity(struct mm_struct *mm, int cpu) +static bool exceed_llc_capacity(struct sched_cache_group *grp, int cpu) { #ifdef CONFIG_NUMA_BALANCING unsigned long llc, footprint; @@ -1497,7 +1497,7 @@ static bool exceed_llc_capacity(struct mm_struct *mm, int cpu) * excluded. */ llc = sd->llc_bytes; - footprint = READ_ONCE(mm->sc_stat.footprint); + footprint = READ_ONCE(grp->footprint); /* * Scale the LLC size by 256*llc_aggr_tolerance @@ -1526,7 +1526,7 @@ static bool exceed_llc_capacity(struct mm_struct *mm, int cpu) return false; } -static bool invalid_llc_nr(struct mm_struct *mm, struct task_struct *p, +static bool invalid_llc_nr(struct sched_cache_group *grp, struct task_struct *p, int cpu) { int scale; @@ -1542,10 +1542,32 @@ static bool invalid_llc_nr(struct mm_struct *mm, struct task_struct *p, if (scale == INT_MAX) return false; - return !fits_capacity((mm->sc_stat.nr_running_avg * cpu_smt_num_threads), + return !fits_capacity((READ_ONCE(grp->nr_running_avg) * cpu_smt_num_threads), (scale * per_cpu(sd_llc_size, cpu))); } +/* + * A task counts in nr_pref_llc_running while it is queued on its preferred + * LLC (pref_llc_queued) and runnable (!sched_delayed), keeping the counter in + * the runnable domain so alb_break_llc() can compare it with h_nr_runnable. + */ +static bool task_pref_llc_runnable(struct task_struct *p) +{ + return p->pref_llc_queued && !p->se.sched_delayed; +} + +static void pref_llc_running_inc(struct rq *rq, struct task_struct *p) +{ + if (task_pref_llc_runnable(p)) + rq->nr_pref_llc_running++; +} + +static void pref_llc_running_dec(struct rq *rq, struct task_struct *p) +{ + if (task_pref_llc_runnable(p)) + rq->nr_pref_llc_running--; +} + static void account_llc_enqueue(struct rq *rq, struct task_struct *p) { int pref_llc, pref_llc_queued; @@ -1557,7 +1579,6 @@ static void account_llc_enqueue(struct rq *rq, struct task_struct *p) pref_llc_queued = (pref_llc == task_llc(p)); rq->nr_llc_running++; - rq->nr_pref_llc_running += pref_llc_queued; /* * Record whether p is enqueued on its preferred @@ -1575,6 +1596,9 @@ static void account_llc_enqueue(struct rq *rq, struct task_struct *p) */ p->pref_llc_queued = pref_llc_queued; + /* Skipped while delayed; clear_delayed() adds it back on wake. */ + pref_llc_running_inc(rq, p); + sd = rcu_dereference_all(rq->sd); if (sd && (unsigned int)pref_llc < sd->llc_max) sd->llc_counts[pref_llc]++; @@ -1591,7 +1615,12 @@ static void account_llc_dequeue(struct rq *rq, struct task_struct *p) rq->nr_llc_running--; if (p->pref_llc_queued) { - rq->nr_pref_llc_running--; + /* + * Skipped if still delayed (set_delayed() already removed it); + * clearing pref_llc_queued below also stops clear_delayed() + * from re-adding it. + */ + pref_llc_running_dec(rq, p); /* * Update the status in case * other logic might query @@ -1619,12 +1648,20 @@ static void account_llc_dequeue(struct rq *rq, struct task_struct *p) } } -void mm_init_sched(struct mm_struct *mm, - struct sched_cache_time __percpu *_pcpu_sched) +int mm_init_sched(struct mm_struct *mm, + struct sched_cache_time __percpu *_pcpu_sched) { + struct sched_cache_group *grp; unsigned long epoch = 0; int i; + grp = kzalloc_obj(*grp); + if (!grp) { + free_percpu(_pcpu_sched); + mm->sched_cache_grp = NULL; + return -ENOMEM; + } + for_each_possible_cpu(i) { struct sched_cache_time *pcpu_sched = per_cpu_ptr(_pcpu_sched, i); struct rq *rq = cpu_rq(i); @@ -1635,18 +1672,141 @@ void mm_init_sched(struct mm_struct *mm, epoch = rq->cpu_epoch; } - raw_spin_lock_init(&mm->sc_stat.lock); - mm->sc_stat.epoch = epoch; - mm->sc_stat.cpu = -1; - mm->sc_stat.next_scan = jiffies; - mm->sc_stat.nr_running_avg = 0; - mm->sc_stat.footprint = 0; + raw_spin_lock_init(&grp->lock); + grp->epoch = epoch; + grp->cpu = -1; + grp->next_scan = jiffies; + grp->nr_running_avg = 0; + grp->footprint = 0; + refcount_set(&grp->refcnt, 1); /* - * The update to mm->sc_stat should not be reordered - * before initialization to mm's other fields, in case + * The update to grp->pcpu_sched should not be reordered + * before initialization to grp's other fields, in case * the readers may get invalid mm_sched_epoch, etc. */ - smp_store_release(&mm->sc_stat.pcpu_sched, _pcpu_sched); + smp_store_release(&grp->pcpu_sched, _pcpu_sched); + /* + * Publish the group last. Not every reader qualifies it by + * grp->pcpu_sched - can_migrate_llc_task() only checks that the + * pointer is non-NULL before reading grp->footprint and + * grp->nr_running_avg - so a reachable group must already be + * fully initialized. + */ + smp_store_release(&mm->sched_cache_grp, grp); + return 0; +} + +static void sched_cache_group_free_rcu(struct rcu_head *rcu) +{ + struct sched_cache_group *grp = + container_of(rcu, struct sched_cache_group, rcu); + + free_percpu(grp->pcpu_sched); + kfree(grp); +} + +static void sched_cache_group_put(struct sched_cache_group *grp) +{ + if (!grp || !refcount_dec_and_test(&grp->refcnt)) + return; + + call_rcu(&grp->rcu, sched_cache_group_free_rcu); +} + +DEFINE_FREE(sched_cache_group_put, struct sched_cache_group *, + sched_cache_group_put(_T)); + +#define rcu_deref_sched_cache_grp(tsk) \ + rcu_dereference_check((tsk)->sched_cache_grp, (tsk) == current) + +static struct sched_cache_group *sched_cache_replace_grp(struct task_struct *p, + struct sched_cache_group *new) +{ + struct sched_cache_group *old; + + old = rcu_deref_sched_cache_grp(p); + rcu_assign_pointer(p->sched_cache_grp, new); + + return old; +} + +struct sched_cache_group *sched_cache_group_get(struct sched_cache_group *grp) +{ + /* + * refcount_inc_not_zero() is the acquire primitive for lockless + * (RCU) lookups; plain refcount_inc() would scribble the count if + * it already reached zero. Return NULL in that case. + */ + if (grp && !refcount_inc_not_zero(&grp->refcnt)) + grp = NULL; + + return grp; +} + +struct sched_cache_group *task_cache_group_get(struct task_struct *p) +{ + guard(rcu)(); + return sched_cache_group_get(rcu_dereference(p->sched_cache_grp)); +} + +void sched_cache_fork(struct task_struct *p) +{ + /* + * The child takes its own reference on the mm's cache group, separate + * from the reference held by the mm. @p is not yet visible to readers, + * so a plain initializing store is enough. + */ + RCU_INIT_POINTER(p->sched_cache_grp, + sched_cache_group_get(p->mm->sched_cache_grp)); +} + +void sched_cache_fork_cleanup(struct task_struct *p) +{ + /* + * A fork that fails after sched_cache_fork() never reaches exit_mm(), + * so drop the reference here. @p never became visible, so there are no + * concurrent readers and the reference we hold keeps the group alive. + */ + sched_cache_group_put(rcu_access_pointer(p->sched_cache_grp)); + RCU_INIT_POINTER(p->sched_cache_grp, NULL); +} + +void sched_cache_exec_mmap(struct task_struct *p, struct mm_struct *mm) +{ + struct sched_cache_group *old; + + /* + * Acquire the new reference before publishing the pointer, then drop + * the old one. @p is current and the only writer of its own pointer. + */ + old = sched_cache_replace_grp(p, sched_cache_group_get(mm->sched_cache_grp)); + sched_cache_group_put(old); +} + +void sched_cache_exit_mm(struct task_struct *p) +{ + struct sched_cache_group *grp = sched_cache_replace_grp(p, NULL); + +#ifdef CONFIG_NUMA_BALANCING + /* + * Subtract this task's footprint from the group before dropping the + * reference, so the group footprint converges as its threads exit. + * Unlocked for performance; clamp to avoid underflow. + */ + if (grp && p->total_numa_faults) { + unsigned long fp = READ_ONCE(grp->footprint); + unsigned long sub = min(fp, p->total_numa_faults); + + WRITE_ONCE(grp->footprint, fp - sub); + } +#endif + sched_cache_group_put(grp); +} + +void mm_destroy_sched(struct mm_struct *mm) +{ + sched_cache_group_put(mm->sched_cache_grp); + mm->sched_cache_grp = NULL; } /* because why would C be fully specified */ @@ -1697,14 +1857,14 @@ static unsigned long fraction_mm_sched(struct rq *rq, return div64_u64(NICE_0_LOAD * pcpu_sched->runtime, rq->cpu_runtime + 1); } -static int get_pref_llc(struct task_struct *p, struct mm_struct *mm) +static int get_pref_llc(struct task_struct *p, struct sched_cache_group *grp) { int mm_sched_llc = -1, mm_sched_cpu; - if (!mm) + if (!grp) return -1; - mm_sched_cpu = READ_ONCE(mm->sc_stat.cpu); + mm_sched_cpu = READ_ONCE(grp->cpu); if (mm_sched_cpu != -1) { mm_sched_llc = llc_id(mm_sched_cpu); @@ -1734,8 +1894,8 @@ static unsigned int task_running_on_cpu(int cpu, struct task_struct *p); static inline void account_mm_sched(struct rq *rq, struct task_struct *p, s64 delta_exec) { + struct sched_cache_group *grp = rcu_dereference_all(p->sched_cache_grp); struct sched_cache_time *pcpu_sched; - struct mm_struct *mm = p->mm; int mm_sched_llc = -1; unsigned long epoch; @@ -1746,12 +1906,18 @@ void account_mm_sched(struct rq *rq, struct task_struct *p, s64 delta_exec) return; /* * init_task, kthreads and user thread created - * by user_mode_thread() don't have mm. + * by user_mode_thread() don't have a cache group. + * In theory a kernel thread does not have any valid + * cache group, because sched_cache_fork() is not + * invoked for a kernel thread - !grp should gate the + * kernel thread. Use the PF_KTHREAD check explicitly + * here for safety reasons, to guard against future + * modifications and to pair with task_tick_cache(). */ - if (!mm || !mm->sc_stat.pcpu_sched) + if (p->flags & PF_KTHREAD || !grp || !grp->pcpu_sched) return; - pcpu_sched = per_cpu_ptr(mm->sc_stat.pcpu_sched, cpu_of(rq)); + pcpu_sched = per_cpu_ptr(grp->pcpu_sched, cpu_of(rq)); scoped_guard (raw_spinlock, &rq->cpu_epoch_lock) { __update_mm_sched(rq, pcpu_sched); @@ -1764,14 +1930,14 @@ void account_mm_sched(struct rq *rq, struct task_struct *p, s64 delta_exec) * If this process hasn't hit task_cache_work() for a while invalidate * its preferred state. */ - if ((long)(epoch - READ_ONCE(mm->sc_stat.epoch)) > llc_epoch_affinity_timeout || - invalid_llc_nr(mm, p, cpu_of(rq)) || - exceed_llc_capacity(mm, cpu_of(rq))) { - if (READ_ONCE(mm->sc_stat.cpu) != -1) - WRITE_ONCE(mm->sc_stat.cpu, -1); + if ((long)(epoch - READ_ONCE(grp->epoch)) > llc_epoch_affinity_timeout || + invalid_llc_nr(grp, p, cpu_of(rq)) || + exceed_llc_capacity(grp, cpu_of(rq))) { + if (READ_ONCE(grp->cpu) != -1) + WRITE_ONCE(grp->cpu, -1); } - mm_sched_llc = get_pref_llc(p, mm); + mm_sched_llc = get_pref_llc(p, grp); /* task not on rq accounted later in account_entity_enqueue() */ if (task_running_on_cpu(rq->cpu, p) && @@ -1784,31 +1950,32 @@ void account_mm_sched(struct rq *rq, struct task_struct *p, s64 delta_exec) static void task_tick_cache(struct rq *rq, struct task_struct *p) { + struct sched_cache_group *grp = rcu_dereference_all(p->sched_cache_grp); struct callback_head *work = &p->cache_work; - struct mm_struct *mm = p->mm; unsigned long epoch; if (!sched_cache_enabled()) return; - if (!mm || p->flags & PF_KTHREAD || - !mm->sc_stat.pcpu_sched) + if (!grp || p->flags & PF_KTHREAD || + !grp->pcpu_sched) return; epoch = rq->cpu_epoch; /* avoid moving backwards */ - if (time_after_eq(mm->sc_stat.epoch, epoch)) + if (time_after_eq(grp->epoch, epoch)) return; - guard(raw_spinlock)(&mm->sc_stat.lock); + guard(raw_spinlock)(&grp->lock); if (work->next == work) { task_work_add(p, work, TWA_RESUME); - WRITE_ONCE(mm->sc_stat.epoch, epoch); + WRITE_ONCE(grp->epoch, epoch); } } -static void get_scan_cpumasks(cpumask_var_t cpus, struct task_struct *p) +static void get_scan_cpumasks(cpumask_var_t cpus, struct task_struct *p, + struct sched_cache_group *grp) { #ifdef CONFIG_NUMA_BALANCING int cpu, curr_cpu, nid, pref_nid; @@ -1816,7 +1983,7 @@ static void get_scan_cpumasks(cpumask_var_t cpus, struct task_struct *p) if (!static_branch_likely(&sched_numa_balancing)) goto out; - cpu = READ_ONCE(p->mm->sc_stat.cpu); + cpu = READ_ONCE(grp->cpu); if (cpu != -1) nid = cpu_to_node(cpu); curr_cpu = task_cpu(p); @@ -1873,13 +2040,13 @@ static inline void update_avg_scale(u64 *avg, u64 sample) static void task_cache_work(struct callback_head *work) { + struct sched_cache_group *grp __free(sched_cache_group_put) = NULL; + cpumask_var_t cpus __free(free_cpumask_var) = CPUMASK_VAR_NULL; int cpu, m_a_cpu = -1, nr_running = 0, curr_cpu; unsigned long next_scan, now = jiffies; struct task_struct *p = current, *cur; unsigned long curr_m_a_occ = 0; - struct mm_struct *mm = p->mm; unsigned long m_a_occ = 0; - cpumask_var_t cpus; WARN_ON_ONCE(work != &p->cache_work); @@ -1888,21 +2055,30 @@ static void task_cache_work(struct callback_head *work) if (p->flags & PF_EXITING) return; - next_scan = READ_ONCE(mm->sc_stat.next_scan); + /* + * A reference makes sure grp is not released by others. The rcu + * lock can not be held till after zalloc_cpumask_var() below, + * because the latter might sleep. + */ + grp = task_cache_group_get(p); + if (!grp) + return; + + next_scan = READ_ONCE(grp->next_scan); if (time_before(now, next_scan)) return; /* only 1 thread is allowed to scan */ - if (!try_cmpxchg(&mm->sc_stat.next_scan, &next_scan, + if (!try_cmpxchg(&grp->next_scan, &next_scan, now + max_t(unsigned long, READ_ONCE(llc_epoch_period), 1))) return; curr_cpu = task_cpu(p); - if (invalid_llc_nr(mm, p, curr_cpu) || - exceed_llc_capacity(mm, curr_cpu)) { - if (READ_ONCE(mm->sc_stat.cpu) != -1) - WRITE_ONCE(mm->sc_stat.cpu, -1); + if (invalid_llc_nr(grp, p, curr_cpu) || + exceed_llc_capacity(grp, curr_cpu)) { + if (READ_ONCE(grp->cpu) != -1) + WRITE_ONCE(grp->cpu, -1); return; } @@ -1913,7 +2089,7 @@ static void task_cache_work(struct callback_head *work) scoped_guard (cpus_read_lock) { guard(rcu)(); - get_scan_cpumasks(cpus, p); + get_scan_cpumasks(cpus, p, grp); for_each_cpu(cpu, cpus) { /* XXX sched_cluster_active */ @@ -1926,16 +2102,20 @@ static void task_cache_work(struct callback_head *work) for_each_cpu(i, sched_domain_span(sd)) { occ = fraction_mm_sched(cpu_rq(i), - per_cpu_ptr(mm->sc_stat.pcpu_sched, i)); + per_cpu_ptr(grp->pcpu_sched, i)); a_occ += occ; if (occ > m_occ) { m_occ = occ; m_cpu = i; } + /* + * rcu_access_pointer() is used because the + * pointer is only compared, never dereferenced. + */ cur = rcu_dereference_all(cpu_rq(i)->curr); if (cur && !(cur->flags & (PF_EXITING | PF_KTHREAD)) && - cur->mm == mm) + rcu_access_pointer(cur->sched_cache_grp) == grp) nr_running++; } @@ -1959,7 +2139,7 @@ static void task_cache_work(struct callback_head *work) m_a_cpu = m_cpu; } - if (llc_id(cpu) == llc_id(READ_ONCE(mm->sc_stat.cpu))) + if (llc_id(cpu) == llc_id(READ_ONCE(grp->cpu))) curr_m_a_occ = a_occ; cpumask_andnot(cpus, cpus, sched_domain_span(sd)); @@ -1968,7 +2148,7 @@ static void task_cache_work(struct callback_head *work) if (m_a_occ > (2 * curr_m_a_occ)) { /* - * Avoid switching sc_stat.cpu too fast. + * Avoid switching sched_cache_grp->cpu too fast. * The reason to choose 2X is because: * 1. It is better to keep the preferred LLC stable, * rather than changing it frequently and cause migrations @@ -1977,11 +2157,10 @@ static void task_cache_work(struct callback_head *work) * 3. 2X is chosen based on test results, as it delivers * the optimal performance gain so far. */ - WRITE_ONCE(mm->sc_stat.cpu, m_a_cpu); + WRITE_ONCE(grp->cpu, m_a_cpu); } - update_avg_scale(&mm->sc_stat.nr_running_avg, nr_running); - free_cpumask_var(cpus); + update_avg_scale(&grp->nr_running_avg, nr_running); } void init_sched_mm(struct task_struct *p) @@ -1991,10 +2170,18 @@ void init_sched_mm(struct task_struct *p) init_task_work(work, task_cache_work); work->next = work; /* + * dup_task_struct() copies the parent's task_struct, including its + * sched_cache_grp, for which the child holds no reference. Clear it + * here - before copy_mm() runs - so the child never carries a + * borrowed pointer that the fork error path would put. + */ + RCU_INIT_POINTER(p->sched_cache_grp, NULL); + /* * Reset new task's preference to avoid * polluting account_llc_enqueue(). */ p->preferred_llc = -1; + p->pref_llc_queued = 0; } #else /* CONFIG_SCHED_CACHE */ @@ -2016,6 +2203,10 @@ static void account_llc_enqueue(struct rq *rq, struct task_struct *p) {} static void account_llc_dequeue(struct rq *rq, struct task_struct *p) {} +static void pref_llc_running_inc(struct rq *rq, struct task_struct *p) {} + +static void pref_llc_running_dec(struct rq *rq, struct task_struct *p) {} + #endif /* CONFIG_SCHED_CACHE */ /* @@ -3692,6 +3883,7 @@ static int preferred_group_nid(struct task_struct *p, int nid) static void task_numa_placement(struct task_struct *p) __context_unsafe(/* conditional locking */) { + struct sched_cache_group __maybe_unused *grp; int seq, nid, max_nid = NUMA_NO_NODE; unsigned long max_faults = 0; unsigned long fault_types[2] = { 0, 0 }; @@ -3784,19 +3976,24 @@ static void task_numa_placement(struct task_struct *p) * heuristic and occasional lost updates are tolerable. * * If a task exits, its corresponding footprint must - * be subtracted from the mm->sc_stat.footprint, otherwise - * the mm->sc_stat.footprint will not converge: - * the exiting thread's footprint remains unchanged/undecayed - * in mm->sc_stat.footprint. See exit_mm(). + * be subtracted from p->sched_cache_grp->footprint, + * otherwise the footprint will not converge: the + * exiting thread's footprint remains unchanged/undecayed. + * See exit_mm(). * * Lost updates and unsynchronized subtraction * in exit_mm() can cause footprint + diff to * go negative. Clamp to zero to prevent the * unsigned footprint from wrapping. */ - new_fp = (long)READ_ONCE(p->mm->sc_stat.footprint) + diff; - WRITE_ONCE(p->mm->sc_stat.footprint, - max(new_fp, 0L)); + scoped_guard(rcu) { + grp = rcu_dereference(p->sched_cache_grp); + + if (grp) { + new_fp = (long)READ_ONCE(grp->footprint) + diff; + WRITE_ONCE(grp->footprint, max(new_fp, 0L)); + } + } #endif } @@ -6390,15 +6587,27 @@ static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq); static void set_delayed(struct sched_entity *se) { - se->sched_delayed = 1; - /* * Delayed se of cfs_rq have no tasks queued on them. * Do not adjust h_nr_runnable since __dequeue_task() * will account it for blocked tasks. + * + * This check can be removed because when flat pick + * patches get merged as only task can get delayed, + * same for clear_delayed(). */ - if (!entity_is_task(se)) + if (!entity_is_task(se)) { + se->sched_delayed = 1; return; + } + + /* + * Drop a task leaving the runnable set. + * Needs to be called before sched_delayed is set. + * clear_delayed() mirrors this after clearing the flag. + */ + pref_llc_running_dec(rq_of(cfs_rq_of(se)), task_of(se)); + se->sched_delayed = 1; for_each_sched_entity(se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); @@ -6420,6 +6629,13 @@ static void clear_delayed(struct sched_entity *se) if (!entity_is_task(se)) return; + /* + * Re-add on wake, after sched_delayed is cleared. On a final delayed + * dequeue account_llc_dequeue() already cleared pref_llc_queued, so + * this does nothing. + */ + pref_llc_running_inc(rq_of(cfs_rq_of(se)), task_of(se)); + for_each_sched_entity(se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); @@ -10395,6 +10611,7 @@ enum migration_type { #define LBF_SOME_PINNED 0x08 #define LBF_ACTIVE_LB 0x10 #define LBF_LLC_PINNED 0x20 +#define LBF_ACTIVE_LB_LLC 0x40 struct lb_env { struct sched_domain *sd; @@ -10724,7 +10941,7 @@ static inline bool task_misfits_asym_cpu(struct lb_env *env, struct task_struct static enum llc_mig can_migrate_llc_task(struct lb_env *env, struct task_struct *p) { - struct mm_struct *mm; + struct sched_cache_group *grp; bool to_pref; int cpu, src_cpu, dst_cpu; @@ -10733,19 +10950,19 @@ static enum llc_mig can_migrate_llc_task(struct lb_env *env, src_cpu = env->src_cpu; dst_cpu = env->dst_cpu; - mm = p->mm; - if (!mm) + grp = rcu_dereference_all(p->sched_cache_grp); + if (!grp) return mig_unrestricted; - cpu = READ_ONCE(mm->sc_stat.cpu); + cpu = READ_ONCE(grp->cpu); if (cpu < 0 || cpus_share_cache(src_cpu, dst_cpu)) return mig_unrestricted; /* skip cache aware load balance for too many threads */ - if (invalid_llc_nr(mm, p, dst_cpu) || - exceed_llc_capacity(mm, dst_cpu)) { - if (READ_ONCE(mm->sc_stat.cpu) != -1) - WRITE_ONCE(mm->sc_stat.cpu, -1); + if (invalid_llc_nr(grp, p, dst_cpu) || + exceed_llc_capacity(grp, dst_cpu)) { + if (READ_ONCE(grp->cpu) != -1) + WRITE_ONCE(grp->cpu, -1); return mig_unrestricted; } @@ -10814,6 +11031,21 @@ alb_break_llc(struct lb_env *env) } /* + * Returns true if p's preferred LLC does not match the destination CPU + * under migrate_llc_task semantics. Passive LB passes migrate_llc_task + * in env->migration_type, while active LB carries LBF_ACTIVE_LB_LLC in + * env->flags to avoid overwriting env->migration_type. + */ +static inline bool +migrate_llc_task_wrong_dst(struct task_struct *p, struct lb_env *env) +{ + return sched_cache_enabled() && + (env->migration_type == migrate_llc_task || + env->flags & LBF_ACTIVE_LB_LLC) && + READ_ONCE(p->preferred_llc) != llc_id(env->dst_cpu); +} + +/* * Check if migrating task p from env->src_cpu to * env->dst_cpu breaks LLC localiy. */ @@ -10841,8 +11073,7 @@ static bool migrate_degrades_llc(struct task_struct *p, struct lb_env *env) * run on env->dst_cpu, skip the tasks do not prefer * env->dst_cpu, and find the one that prefers. */ - if (env->migration_type == migrate_llc_task && - READ_ONCE(p->preferred_llc) != llc_id(env->dst_cpu)) + if (migrate_llc_task_wrong_dst(p, env)) return true; if (can_migrate_llc_task(env, p) != mig_forbid) @@ -10865,6 +11096,12 @@ alb_break_llc(struct lb_env *env) } static inline bool +migrate_llc_task_wrong_dst(struct task_struct *p, struct lb_env *env) +{ + return false; +} + +static inline bool migrate_degrades_llc(struct task_struct *p, struct lb_env *env) { return false; @@ -10963,7 +11200,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) * 4) too many balance attempts have failed. */ if (env->flags & LBF_ACTIVE_LB) - return 1; + return !migrate_llc_task_wrong_dst(p, env); degrades = migrate_degrades_locality(p, env); if (!degrades) { @@ -13362,6 +13599,20 @@ static int need_active_balance(struct lb_env *env) } static int active_load_balance_cpu_stop(void *data); +static int active_load_balance_llc_cpu_stop(void *data); + +/* + * migration_type is checked elsewhere to decide migration policy, so + * it shouldn't be repurposed just to flag an LLC-directed active + * balance across the stopper. Pick the callback here instead. + */ +static inline cpu_stop_fn_t alb_stop_fn(struct lb_env *env) +{ + if (env->migration_type == migrate_llc_task) + return active_load_balance_llc_cpu_stop; + + return active_load_balance_cpu_stop; +} static int should_we_balance(struct lb_env *env) { @@ -13707,7 +13958,7 @@ more_balance: } if (active_balance) { stop_one_cpu_nowait(cpu_of(busiest), - active_load_balance_cpu_stop, busiest, + alb_stop_fn(&env), busiest, &busiest->active_balance_work); } preempt_enable(); @@ -13812,7 +14063,7 @@ update_next_balance(struct sched_domain *sd, unsigned long *next_balance) * least 1 task to be running on each physical CPU where possible, and * avoids physical / logical imbalances. */ -static int active_load_balance_cpu_stop(void *data) +static int __active_load_balance_cpu_stop(void *data, unsigned int lb_flags) { struct rq *busiest_rq = data; int busiest_cpu = cpu_of(busiest_rq); @@ -13862,7 +14113,7 @@ static int active_load_balance_cpu_stop(void *data) .src_cpu = busiest_rq->cpu, .src_rq = busiest_rq, .idle = CPU_IDLE, - .flags = LBF_ACTIVE_LB, + .flags = LBF_ACTIVE_LB | lb_flags, }; schedstat_inc(sd->alb_count); @@ -13890,6 +14141,16 @@ out_unlock: return 0; } +static int active_load_balance_cpu_stop(void *data) +{ + return __active_load_balance_cpu_stop(data, 0); +} + +static int active_load_balance_llc_cpu_stop(void *data) +{ + return __active_load_balance_cpu_stop(data, LBF_ACTIVE_LB_LLC); +} + /* * Scale the max sched_balance_rq interval with the number of CPUs in the system. * This trades load-balance latency on larger machines for less cross talk. diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 0248227d983a..3dab0253976f 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -985,8 +985,8 @@ void sched_cache_active_set(void) } /* - * Update the bottom sched_domain's llc_bytes for @cpu and all its - * LLC siblings. Called from cacheinfo_cpu_online() or + * Update the bottom sched_domain's llc_bytes for @cpus sharing a physical + * LLC. Called from cacheinfo_cpu_online() or * cacheinfo_cpu_pre_down() with cpu hotplug lock held. * * Note: get_effective_llc_bytes() returns 0 on PowerPC. @@ -996,17 +996,13 @@ void sched_cache_active_set(void) * and does not populates the per-CPU struct cpu_cacheinfo array * that get_cpu_cacheinfo_llc() reads. */ -void sched_update_llc_bytes(unsigned int cpu) +void sched_update_llc_bytes(const struct cpumask *cpus) { struct sched_domain *sd, *sdp; unsigned int i; sched_domains_mutex_lock(); - sdp = rcu_dereference_sched_domain(per_cpu(sd_llc, cpu)); - if (!sdp) - goto unlock; - /* * ci->shared_cpu_map is built incrementally as CPUs come * online, so the first CPU in an LLC initially sees @@ -1014,14 +1010,22 @@ void sched_update_llc_bytes(unsigned int cpu) * get_effective_llc_bytes(). Re-evaluating every LLC * sibling on each online event corrects this once the full * shared_cpu_map is known. + * + * The departing CPU's domains have already been detached when + * cacheinfo removes it. Use the surviving cache siblings instead. + * They may belong to different cpuset partitions, so use each CPU's + * own LLC domain to scale its share of the physical cache. */ - for_each_cpu(i, sched_domain_span(sdp)) { + for_each_cpu(i, cpus) { + sdp = rcu_dereference_sched_domain(per_cpu(sd_llc, i)); + if (!sdp) + continue; + sd = rcu_dereference_sched_domain(cpu_rq(i)->sd); if (sd) sd->llc_bytes = get_effective_llc_bytes(i, sdp); } -unlock: sched_domains_mutex_unlock(); } diff --git a/kernel/signal.c b/kernel/signal.c index ec30550951ec..d31ebcb6ed4d 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -457,18 +457,42 @@ static void __sigqueue_free(struct sigqueue *q) kmem_cache_free(sigqueue_cachep, q); } -void flush_sigqueue(struct sigpending *queue) +/* + * flush_sigqueue_list() can only be invoked without holding sighand::siglock in + * the following cases: + * + * 1) When flushing task::pending _after_ setting task::flags PF_EXITING + * + * All functions which try to send a signal to @task will observe PF_EXITING + * and drop the signal. + * + * 2) When flushing task::signal::shared_pending _after_ the last task in a + * thread group was unhashed and task::sighand is NULL. + * + * Nothing can queue a signal anymore because sighand is NULL. + */ +static void flush_sigqueue_list(struct list_head *head) { - struct sigqueue *q; + struct sigqueue *q, *tmp; - sigemptyset(&queue->signal); - while (!list_empty(&queue->list)) { - q = list_entry(queue->list.next, struct sigqueue , list); + list_for_each_entry_safe(q, tmp, head, list) { list_del_init(&q->list); __sigqueue_free(q); } } +void flush_sigqueue(struct sigpending *queue) +{ + sigemptyset(&queue->signal); + flush_sigqueue_list(&queue->list); +} + +static void sigqueue_dequeue_pending(struct sigpending *queue, struct list_head *head) +{ + sigemptyset(&queue->signal); + list_splice_init(&queue->list, head); +} + /* * Flush all pending signals for this kthread. */ @@ -1019,6 +1043,21 @@ static inline bool legacy_queue(struct sigpending *signals, int sig) return (sig < SIGRTMIN) && sigismember(&signals->signal, sig); } +/* + * When PF_EXITING is set the task is on the way out and has t::pending + * flushed already. Prevent queueing of PIDTYPE_PID signals as they would + * be leaked. + */ +static inline bool task_can_queue_signal(struct task_struct *t, enum pid_type type) +{ + lockdep_assert_held(&t->sighand->siglock); + + if (!(t->flags & PF_EXITING)) + return true; + + return type != PIDTYPE_PID; +} + static int __send_signal_locked(int sig, struct kernel_siginfo *info, struct task_struct *t, enum pid_type type, bool force) { @@ -1030,6 +1069,10 @@ static int __send_signal_locked(int sig, struct kernel_siginfo *info, lockdep_assert_held(&t->sighand->siglock); result = TRACE_SIGNAL_IGNORED; + + if (!task_can_queue_signal(t, type)) + goto ret; + if (!prepare_signal(sig, t, force)) goto ret; @@ -1980,11 +2023,25 @@ static inline struct task_struct *posixtimer_get_target(struct k_itimer *tmr) struct task_struct *t = pid_task(tmr->it_pid, tmr->it_pid_type); if (t && tmr->it_pid_type != PIDTYPE_PID && - same_thread_group(t, current) && !current->exit_state) + same_thread_group(t, current) && !(current->flags & PF_EXITING)) t = current; return t; } +/* + * Find the target task for the POSIX timer signal and prevent that a + * PIDTYPE_PID signal is queued on a task which has PF_EXITING set. + */ +static inline struct task_struct *posixtimer_get_unignore_target(struct k_itimer *tmr) +{ + struct task_struct *t = posixtimer_get_target(tmr); + + if (t && task_can_queue_signal(t, tmr->it_pid_type)) + return t; + + return NULL; +} + void posixtimer_send_sigqueue(struct k_itimer *tmr) { struct sigqueue *q = &tmr->sigq; @@ -2002,6 +2059,9 @@ void posixtimer_send_sigqueue(struct k_itimer *tmr) if (!likely(lock_task_sighand(t, &flags))) return; + if (!task_can_queue_signal(t, tmr->it_pid_type)) + goto unlock; + /* * Update @tmr::sigqueue_seq for posix timer signals with sighand * locked to prevent a race against dequeue_signal(). @@ -2093,6 +2153,7 @@ void posixtimer_send_sigqueue(struct k_itimer *tmr) result = TRACE_SIGNAL_DELIVERED; out: trace_signal_generate(sig, &q->info, t, tmr->it_pid_type != PIDTYPE_PID, result); +unlock: unlock_task_sighand(t, &flags); } @@ -2148,7 +2209,7 @@ static void posixtimer_sig_unignore(struct task_struct *tsk, int sig) * has exited by now, drop the reference count. */ guard(rcu)(); - target = posixtimer_get_target(tmr); + target = posixtimer_get_unignore_target(tmr); if (target) posixtimer_queue_sigqueue(&tmr->sigq, target, tmr->it_pid_type); else @@ -3132,42 +3193,36 @@ static void retarget_shared_pending(struct task_struct *tsk, sigset_t *which) void exit_signals(struct task_struct *tsk) { + LIST_HEAD(sigq_list); int group_stop = 0; - sigset_t unblocked; /* * @tsk is about to have PF_EXITING set - lock out users which - * expect stable threadgroup. + * expect a stable threadgroup. */ cgroup_threadgroup_change_begin(tsk); - if (thread_group_empty(tsk) || (tsk->signal->flags & SIGNAL_GROUP_EXIT)) { + scoped_guard(spinlock_irq, &tsk->sighand->siglock) { tsk->flags |= PF_EXITING; - cgroup_threadgroup_change_end(tsk); - return; - } - spin_lock_irq(&tsk->sighand->siglock); - /* - * From now this task is not visible for group-wide signals, - * see wants_signal(), do_signal_stop(). - */ - tsk->flags |= PF_EXITING; + sigqueue_dequeue_pending(&tsk->pending, &sigq_list); - cgroup_threadgroup_change_end(tsk); + if (task_sigpending(tsk) && !thread_group_empty(tsk) && + !(tsk->signal->flags & SIGNAL_GROUP_EXIT)) { + sigset_t unblocked = tsk->blocked; - if (!task_sigpending(tsk)) - goto out; + signotset(&unblocked); + retarget_shared_pending(tsk, &unblocked); - unblocked = tsk->blocked; - signotset(&unblocked); - retarget_shared_pending(tsk, &unblocked); + if (unlikely(tsk->jobctl & JOBCTL_STOP_PENDING) && + task_participate_group_stop(tsk)) + group_stop = CLD_STOPPED; + } + } - if (unlikely(tsk->jobctl & JOBCTL_STOP_PENDING) && - task_participate_group_stop(tsk)) - group_stop = CLD_STOPPED; -out: - spin_unlock_irq(&tsk->sighand->siglock); + cgroup_threadgroup_change_end(tsk); + + flush_sigqueue_list(&sigq_list); /* * If group stop has completed, deliver the notification. This diff --git a/kernel/sysctl.c b/kernel/sysctl.c index f7b75985d542..38597f26b34c 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -483,7 +483,7 @@ int proc_int_k2u_conv_kop(ulong *u_ptr, const int *k_ptr, bool *negp, if (val < 0) { *negp = true; - *u_ptr = k_ptr_op ? -k_ptr_op((ulong)val) : -(ulong)val; + *u_ptr = k_ptr_op ? k_ptr_op(-(ulong)val) : -(ulong)val; } else { *negp = false; *u_ptr = k_ptr_op ? k_ptr_op((ulong)val) : (ulong) val; diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index 213ae1d6a014..9b3487d40cd6 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -101,6 +101,8 @@ void __init register_refined_jiffies(long cycles_per_second) #ifdef CONFIG_SYSCTL static ulong mult_hz(const ulong val) { + if (val >= ULONG_MAX / HZ) + return ULONG_MAX; return val * HZ; } @@ -136,6 +138,8 @@ static int sysctl_k2u_int_conv_userhz(bool *negp, ulong *u_ptr, const int *k_ptr static ulong sysctl_msecs_to_jiffies(const ulong val) { + if (val > jiffies_to_msecs(MAX_JIFFY_OFFSET)) + return MAX_JIFFY_OFFSET; return msecs_to_jiffies(val); } @@ -181,7 +185,7 @@ static int do_proc_int_conv_ms_jiffies_minmax(bool *negp, ulong *u_ptr, int *k_ptr, int dir, const struct ctl_table *tbl) { - return proc_int_conv(negp, u_ptr, k_ptr, dir, tbl, false, + return proc_int_conv(negp, u_ptr, k_ptr, dir, tbl, true, sysctl_u2k_int_conv_ms, sysctl_k2u_int_conv_ms); } @@ -195,10 +199,10 @@ static int sysctl_k2u_ulong_conv_ms(ulong *u_ptr, const ulong *k_ptr) return proc_ulong_k2u_conv_kop(u_ptr, k_ptr, sysctl_jiffies_to_msecs); } -static int do_proc_ulong_conv_ms_jiffies(bool *negp, ulong *u_ptr, ulong *k_ptr, - int dir, const struct ctl_table *tbl) +static int do_proc_ulong_conv_ms_jiffies_minmax(bool *negp, ulong *u_ptr, ulong *k_ptr, + int dir, const struct ctl_table *tbl) { - return proc_ulong_conv(u_ptr, k_ptr, dir, tbl, false, + return proc_ulong_conv(u_ptr, k_ptr, dir, tbl, true, sysctl_u2k_ulong_conv_ms, sysctl_k2u_ulong_conv_ms); } @@ -229,8 +233,8 @@ static int do_proc_int_conv_ms_jiffies_minmax(bool *negp, ulong *u_ptr, return -ENOSYS; } -static int do_proc_ulong_conv_ms_jiffies(bool *negp, ulong *u_ptr, ulong *k_ptr, - int dir, const struct ctl_table *tbl) +static int do_proc_ulong_conv_ms_jiffies_minmax(bool *negp, ulong *u_ptr, ulong *k_ptr, + int dir, const struct ctl_table *tbl) { return -ENOSYS; } @@ -333,7 +337,7 @@ int proc_doulongvec_ms_jiffies_minmax(const struct ctl_table *table, int dir, void *buffer, size_t *lenp, loff_t *ppos) { return proc_doulongvec_conv(table, dir, buffer, lenp, ppos, - do_proc_ulong_conv_ms_jiffies); + do_proc_ulong_conv_ms_jiffies_minmax); } EXPORT_SYMBOL(proc_doulongvec_ms_jiffies_minmax); diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index d73d31c7994f..0bf4fcd969c8 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -408,6 +408,7 @@ static int posix_cpu_timer_create(struct k_itimer *new_timer) new_timer->kclock = &clock_posix_cpu; timerqueue_init(&new_timer->it.cpu.node); + INIT_LIST_HEAD(&new_timer->it.cpu.elist); new_timer->it.cpu.pid = get_pid(pid); rcu_read_unlock(); return 0; @@ -566,6 +567,24 @@ static struct task_struct *timer_lock_sighand(struct k_itimer *timer, unsigned l } /* + * If the timer is queued on the expiry list, then it cannot be dequeued because + * the firing list is not protected by sighand->lock. The delivery path is + * waiting for the timer lock. So go back, unlock and retry. + */ +static bool posix_cpu_timer_on_expiry_list(struct k_itimer *timer) +{ + if (list_empty(&timer->it.cpu.elist)) + return false; + + /* + * Prevent signal delivery as there is no point in delivering a signal + * which is made obsolete right away. + */ + timer->it.cpu.firing = false; + return true; +} + +/* * Clean up a CPU-clock timer that is about to be destroyed. * This is called from timer deletion with the timer already locked. * If we return TIMER_RETRY, it's necessary to release the timer's lock @@ -580,18 +599,10 @@ static int posix_cpu_timer_del(struct k_itimer *timer) p = timer_lock_sighand(timer, &flags); if (likely(p)) { - if (timer->it.cpu.firing) { - /* - * Prevent signal delivery. The timer cannot be dequeued - * because it is on the firing list which is not protected - * by sighand->lock. The delivery path is waiting for - * the timer lock. So go back, unlock and retry. - */ - timer->it.cpu.firing = false; + if (posix_cpu_timer_on_expiry_list(timer)) ret = TIMER_RETRY; - } else { + else disarm_timer(timer, p); - } unlock_task_sighand(p, &flags); } @@ -731,14 +742,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, /* Retrieve the current expiry time before disarming the timer */ old_expires = cpu_timer_getexpires(ctmr); - if (unlikely(timer->it.cpu.firing)) { - /* - * Prevent signal delivery. The timer cannot be dequeued - * because it is on the firing list which is not protected - * by sighand->lock. The delivery path is waiting for - * the timer lock. So go back, unlock and retry. - */ - timer->it.cpu.firing = false; + if (posix_cpu_timer_on_expiry_list(timer)) { ret = TIMER_RETRY; } else { cpu_timer_dequeue(ctmr); diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 1e9b00997ff2..da286619c5d8 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -47,6 +47,10 @@ static struct rhltable fprobe_ip_table; static DEFINE_MUTEX(fprobe_mutex); static struct fgraph_ops fprobe_graph_ops; +DEFINE_LOCK_GUARD_0(rcu_sched_notrace, + rcu_read_lock_sched_notrace(), + rcu_read_unlock_sched_notrace()) + static u32 fprobe_node_hashfn(const void *data, u32 len, u32 seed) { return hash_ptr(*(unsigned long **)data, 32); @@ -171,6 +175,11 @@ static inline bool write_fprobe_header(unsigned long *stack, static inline void read_fprobe_header(unsigned long *stack, struct fprobe **fp, unsigned int *size_words) { + if (!*stack) { + *fp = NULL; + *size_words = 0; + return; + } *fp = arch_decode_fprobe_header_fp(*stack); *size_words = arch_decode_fprobe_header_size(*stack); } @@ -203,6 +212,12 @@ static inline void read_fprobe_header(unsigned long *stack, { struct __fprobe_header *fph = (struct __fprobe_header *)stack; + if (!*stack) { + *fp = NULL; + *size_words = 0; + return; + } + *fp = fph->fp; *size_words = fph->size_words; } @@ -318,16 +333,14 @@ static void fprobe_ftrace_entry(unsigned long ip, unsigned long parent_ip, struct fprobe *fp; int bit; + if (!rcu_is_watching()) + return; + bit = ftrace_test_recursion_trylock(ip, parent_ip); if (bit < 0) return; - /* - * ftrace_test_recursion_trylock() disables preemption, but - * rhltable_lookup() checks whether rcu_read_lcok is held. - * So we take rcu_read_lock() here. - */ - rcu_read_lock(); + guard(rcu_sched_notrace)(); head = rhltable_lookup(&fprobe_ip_table, &ip, fprobe_rht_params); rhl_for_each_entry_rcu(node, pos, head, hlist) { @@ -342,7 +355,6 @@ static void fprobe_ftrace_entry(unsigned long ip, unsigned long parent_ip, else __fprobe_handler(ip, parent_ip, fp, fregs, NULL); } - rcu_read_unlock(); ftrace_test_recursion_unlock(bit); } NOKPROBE_SYMBOL(fprobe_ftrace_entry); @@ -556,10 +568,13 @@ static int fprobe_fgraph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops struct fprobe *fp; int used, ret; + if (!rcu_is_watching()) + return 0; + if (WARN_ON_ONCE(!fregs)) return 0; - guard(rcu)(); + guard(rcu_sched_notrace)(); head = rhltable_lookup(&fprobe_ip_table, &func, fprobe_rht_params); reserved_words = 0; rhl_for_each_entry_rcu(node, pos, head, hlist) { @@ -635,6 +650,10 @@ static int fprobe_fgraph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops } } + /* Terminate the list, fgraph_reserve_data() does not clear it. */ + if (used && used < reserved_words) + fgraph_data[used] = 0; + /* If any exit_handler is set, data must be used. */ return used != 0; } @@ -650,13 +669,16 @@ static void fprobe_return(struct ftrace_graph_ret *trace, int size, curr; int size_words; + if (!rcu_is_watching()) + return; + fgraph_data = (unsigned long *)fgraph_retrieve_data(gops->idx, &size); if (WARN_ON_ONCE(!fgraph_data)) return; size_words = SIZE_IN_LONG(size); ret_ip = ftrace_regs_get_instruction_pointer(fregs); - preempt_disable_notrace(); + guard(rcu_sched_notrace)(); curr = 0; while (size_words > curr) { @@ -672,7 +694,6 @@ static void fprobe_return(struct ftrace_graph_ret *trace, } curr += size; } - preempt_enable_notrace(); } NOKPROBE_SYMBOL(fprobe_return); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 1ae3732a2c51..959525393739 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3918,7 +3918,7 @@ static void check_flush_dependency(struct workqueue_struct *target_wq, WARN_ONCE(current->flags & PF_MEMALLOC, "workqueue: PF_MEMALLOC task %d(%s) is flushing !WQ_MEM_RECLAIM %s:%ps", current->pid, current->comm, target_wq->name, target_func); - WARN_ONCE(worker && ((worker->current_pwq->wq->flags & + WARN_ONCE(worker && worker->current_pwq && ((worker->current_pwq->wq->flags & (WQ_MEM_RECLAIM | __WQ_LEGACY)) == WQ_MEM_RECLAIM), "workqueue: WQ_MEM_RECLAIM %s:%ps is flushing !WQ_MEM_RECLAIM %s:%ps", worker->current_pwq->wq->name, worker->current_func, |